From: Juri Lelli <juri.lelli@arm.com>
To: linux-kernel@vger.kernel.org
Cc: mark.rutland@arm.com, devicetree@vger.kernel.org,
lorenzo.pieralisi@arm.com, vincent.guittot@linaro.org,
juri.lelli@arm.com, linux-pm@vger.kernel.org,
peterz@infradead.org, catalin.marinas@arm.com,
broonie@kernel.org, will.deacon@arm.com,
gregkh@linuxfoundation.org, dietmar.eggemann@arm.com,
Russell King <linux@armlinux.org.uk>,
robh+dt@kernel.org, sudeep.holla@arm.com, linux@arm.linux.org.uk,
morten.rasmussen@arm.com, linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 5/9] arm, arm64: factorize common cpu capacity default code
Date: Mon, 27 Mar 2017 14:18:21 +0100 [thread overview]
Message-ID: <20170327131825.32134-6-juri.lelli@arm.com> (raw)
In-Reply-To: <20170327131825.32134-1-juri.lelli@arm.com>
arm and arm64 share lot of code relative to parsing CPU capacity
information from DT, using that information for appropriate scaling and
exposing a sysfs interface for chaging such values at runtime.
Factorize such code in a common place (driver/base/arch_topology.c) in
preparation for further additions.
Suggested-by: Will Deacon <will.deacon@arm.com>
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
---
Changes from v2:
- make capacity_scale and raw_capacity static
- added SPDX header
- improved indent
- misc. whitespaces/newlines fixes
Changes from v1:
- keep the original GPLv2 header
---
arch/arm/Kconfig | 1 +
arch/arm/kernel/topology.c | 213 ++-----------------------------------
arch/arm64/Kconfig | 1 +
arch/arm64/kernel/topology.c | 219 +--------------------------------------
drivers/base/Kconfig | 8 ++
drivers/base/Makefile | 1 +
drivers/base/arch_topology.c | 242 +++++++++++++++++++++++++++++++++++++++++++
7 files changed, 262 insertions(+), 423 deletions(-)
create mode 100644 drivers/base/arch_topology.c
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0d4e71b42c77..cd61154bb6d0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -25,6 +25,7 @@ config ARM
select EDAC_SUPPORT
select EDAC_ATOMIC_SCRUB
select GENERIC_ALLOCATOR
+ select GENERIC_ARCH_TOPOLOGY if ARM_CPU_TOPOLOGY
select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_EARLY_IOREMAP
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 162c82aeed96..49ef025ffaa0 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -44,75 +44,10 @@
* to run the rebalance_domains for all idle cores and the cpu_capacity can be
* updated during this sequence.
*/
-static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-static DEFINE_MUTEX(cpu_scale_mutex);
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return per_cpu(cpu_scale, cpu);
-}
-
-static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
-{
- per_cpu(cpu_scale, cpu) = capacity;
-}
-
-static ssize_t cpu_capacity_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
-
- return sprintf(buf, "%lu\n",
- arch_scale_cpu_capacity(NULL, cpu->dev.id));
-}
-
-static ssize_t cpu_capacity_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
- int this_cpu = cpu->dev.id, i;
- unsigned long new_capacity;
- ssize_t ret;
-
- if (count) {
- ret = kstrtoul(buf, 0, &new_capacity);
- if (ret)
- return ret;
- if (new_capacity > SCHED_CAPACITY_SCALE)
- return -EINVAL;
-
- mutex_lock(&cpu_scale_mutex);
- for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
- set_capacity_scale(i, new_capacity);
- mutex_unlock(&cpu_scale_mutex);
- }
-
- return count;
-}
-
-static DEVICE_ATTR_RW(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
- int i;
- struct device *cpu;
-
- for_each_possible_cpu(i) {
- cpu = get_cpu_device(i);
- if (!cpu) {
- pr_err("%s: too early to get CPU%d device!\n",
- __func__, i);
- continue;
- }
- device_create_file(cpu, &dev_attr_cpu_capacity);
- }
-
- return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
+extern unsigned long
+arch_scale_cpu_capacity(struct sched_domain *sd, int cpu);
+extern void set_capacity_scale(unsigned int cpu, unsigned long capacity);
#ifdef CONFIG_OF
struct cpu_efficiency {
@@ -141,145 +76,9 @@ static unsigned long *__cpu_capacity;
static unsigned long middle_capacity = 1;
static bool cap_from_dt = true;
-static u32 *raw_capacity;
-static bool cap_parsing_failed;
-static u32 capacity_scale;
-
-static int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
-{
- int ret = 1;
- u32 cpu_capacity;
-
- if (cap_parsing_failed)
- return !ret;
-
- ret = of_property_read_u32(cpu_node,
- "capacity-dmips-mhz",
- &cpu_capacity);
- if (!ret) {
- if (!raw_capacity) {
- raw_capacity = kcalloc(num_possible_cpus(),
- sizeof(*raw_capacity),
- GFP_KERNEL);
- if (!raw_capacity) {
- pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
- cap_parsing_failed = true;
- return ret;
- }
- }
- capacity_scale = max(cpu_capacity, capacity_scale);
- raw_capacity[cpu] = cpu_capacity;
- pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
- cpu_node->full_name, raw_capacity[cpu]);
- } else {
- if (raw_capacity) {
- pr_err("cpu_capacity: missing %s raw capacity\n",
- cpu_node->full_name);
- pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
- }
- cap_parsing_failed = true;
- kfree(raw_capacity);
- }
-
- return !ret;
-}
-
-static void normalize_cpu_capacity(void)
-{
- u64 capacity;
- int cpu;
-
- if (!raw_capacity || cap_parsing_failed)
- return;
-
- pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
- mutex_lock(&cpu_scale_mutex);
- for_each_possible_cpu(cpu) {
- capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
- / capacity_scale;
- set_capacity_scale(cpu, capacity);
- pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
- cpu, arch_scale_cpu_capacity(NULL, cpu));
- }
- mutex_unlock(&cpu_scale_mutex);
-}
-
-#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static bool cap_parsing_done;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-
-static int
-init_cpu_capacity_callback(struct notifier_block *nb,
- unsigned long val,
- void *data)
-{
- struct cpufreq_policy *policy = data;
- int cpu;
-
- if (cap_parsing_failed || cap_parsing_done)
- return 0;
-
- switch (val) {
- case CPUFREQ_NOTIFY:
- pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
- cpumask_pr_args(policy->related_cpus),
- cpumask_pr_args(cpus_to_visit));
- cpumask_andnot(cpus_to_visit,
- cpus_to_visit,
- policy->related_cpus);
- for_each_cpu(cpu, policy->related_cpus) {
- raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
- policy->cpuinfo.max_freq / 1000UL;
- capacity_scale = max(raw_capacity[cpu], capacity_scale);
- }
- if (cpumask_empty(cpus_to_visit)) {
- normalize_cpu_capacity();
- kfree(raw_capacity);
- pr_debug("cpu_capacity: parsing done\n");
- cap_parsing_done = true;
- schedule_work(&parsing_done_work);
- }
- }
- return 0;
-}
-
-static struct notifier_block init_cpu_capacity_notifier = {
- .notifier_call = init_cpu_capacity_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
- if (cap_parsing_failed)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
- pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
- return -ENOMEM;
- }
- cpumask_copy(cpus_to_visit, cpu_possible_mask);
-
- return cpufreq_register_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-static void parsing_done_workfn(struct work_struct *work)
-{
- cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-
-#else
-static int __init free_raw_capacity(void)
-{
- kfree(raw_capacity);
-
- return 0;
-}
-core_initcall(free_raw_capacity);
-#endif
+extern bool cap_parsing_failed;
+extern void normalize_cpu_capacity(void);
+extern int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu);
/*
* Iterate all CPUs' descriptor in DT and compute the efficiency
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3741859765cf..e36fb12afad6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -40,6 +40,7 @@ config ARM64
select EDAC_SUPPORT
select FRAME_POINTER
select GENERIC_ALLOCATOR
+ select GENERIC_ARCH_TOPOLOGY
select GENERIC_CLOCKEVENTS
select GENERIC_CLOCKEVENTS_BROADCAST
select GENERIC_CPU_AUTOPROBE
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 08243533e5ee..c5bc31eb97e8 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,7 +11,6 @@
* for more details.
*/
-#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
@@ -23,226 +22,14 @@
#include <linux/sched/topology.h>
#include <linux/slab.h>
#include <linux/string.h>
-#include <linux/cpufreq.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>
-static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-static DEFINE_MUTEX(cpu_scale_mutex);
-
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return per_cpu(cpu_scale, cpu);
-}
-
-static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
-{
- per_cpu(cpu_scale, cpu) = capacity;
-}
-
-static ssize_t cpu_capacity_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
-
- return sprintf(buf, "%lu\n",
- arch_scale_cpu_capacity(NULL, cpu->dev.id));
-}
-
-static ssize_t cpu_capacity_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
- int this_cpu = cpu->dev.id, i;
- unsigned long new_capacity;
- ssize_t ret;
-
- if (count) {
- ret = kstrtoul(buf, 0, &new_capacity);
- if (ret)
- return ret;
- if (new_capacity > SCHED_CAPACITY_SCALE)
- return -EINVAL;
-
- mutex_lock(&cpu_scale_mutex);
- for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
- set_capacity_scale(i, new_capacity);
- mutex_unlock(&cpu_scale_mutex);
- }
-
- return count;
-}
-
-static DEVICE_ATTR_RW(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
- int i;
- struct device *cpu;
-
- for_each_possible_cpu(i) {
- cpu = get_cpu_device(i);
- if (!cpu) {
- pr_err("%s: too early to get CPU%d device!\n",
- __func__, i);
- continue;
- }
- device_create_file(cpu, &dev_attr_cpu_capacity);
- }
-
- return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
-
-static u32 capacity_scale;
-static u32 *raw_capacity;
-static bool cap_parsing_failed;
-
-static void __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
-{
- int ret;
- u32 cpu_capacity;
-
- if (cap_parsing_failed)
- return;
-
- ret = of_property_read_u32(cpu_node,
- "capacity-dmips-mhz",
- &cpu_capacity);
- if (!ret) {
- if (!raw_capacity) {
- raw_capacity = kcalloc(num_possible_cpus(),
- sizeof(*raw_capacity),
- GFP_KERNEL);
- if (!raw_capacity) {
- pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
- cap_parsing_failed = true;
- return;
- }
- }
- capacity_scale = max(cpu_capacity, capacity_scale);
- raw_capacity[cpu] = cpu_capacity;
- pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
- cpu_node->full_name, raw_capacity[cpu]);
- } else {
- if (raw_capacity) {
- pr_err("cpu_capacity: missing %s raw capacity\n",
- cpu_node->full_name);
- pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
- }
- cap_parsing_failed = true;
- kfree(raw_capacity);
- }
-}
-
-static void normalize_cpu_capacity(void)
-{
- u64 capacity;
- int cpu;
-
- if (!raw_capacity || cap_parsing_failed)
- return;
-
- pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
- mutex_lock(&cpu_scale_mutex);
- for_each_possible_cpu(cpu) {
- pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
- cpu, raw_capacity[cpu]);
- capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
- / capacity_scale;
- set_capacity_scale(cpu, capacity);
- pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
- cpu, arch_scale_cpu_capacity(NULL, cpu));
- }
- mutex_unlock(&cpu_scale_mutex);
-}
-
-#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static bool cap_parsing_done;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-
-static int
-init_cpu_capacity_callback(struct notifier_block *nb,
- unsigned long val,
- void *data)
-{
- struct cpufreq_policy *policy = data;
- int cpu;
-
- if (cap_parsing_failed || cap_parsing_done)
- return 0;
-
- switch (val) {
- case CPUFREQ_NOTIFY:
- pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
- cpumask_pr_args(policy->related_cpus),
- cpumask_pr_args(cpus_to_visit));
- cpumask_andnot(cpus_to_visit,
- cpus_to_visit,
- policy->related_cpus);
- for_each_cpu(cpu, policy->related_cpus) {
- raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
- policy->cpuinfo.max_freq / 1000UL;
- capacity_scale = max(raw_capacity[cpu], capacity_scale);
- }
- if (cpumask_empty(cpus_to_visit)) {
- normalize_cpu_capacity();
- kfree(raw_capacity);
- pr_debug("cpu_capacity: parsing done\n");
- cap_parsing_done = true;
- schedule_work(&parsing_done_work);
- }
- }
- return 0;
-}
-
-static struct notifier_block init_cpu_capacity_notifier = {
- .notifier_call = init_cpu_capacity_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
- /*
- * on ACPI-based systems we need to use the default cpu capacity
- * until we have the necessary code to parse the cpu capacity, so
- * skip registering cpufreq notifier.
- */
- if (!acpi_disabled || cap_parsing_failed)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
- pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
- return -ENOMEM;
- }
- cpumask_copy(cpus_to_visit, cpu_possible_mask);
-
- return cpufreq_register_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-static void parsing_done_workfn(struct work_struct *work)
-{
- cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-
-#else
-static int __init free_raw_capacity(void)
-{
- kfree(raw_capacity);
-
- return 0;
-}
-core_initcall(free_raw_capacity);
-#endif
+extern bool cap_parsing_failed;
+extern void normalize_cpu_capacity(void);
+extern int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu);
static int __init get_cpu_for_node(struct device_node *node)
{
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index d718ae4b907a..f046d21de57d 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -339,4 +339,12 @@ config CMA_ALIGNMENT
endif
+config GENERIC_ARCH_TOPOLOGY
+ bool
+ help
+ Enable support for architectures common topology code: e.g., parsing
+ CPU capacity information from DT, usage of such information for
+ appropriate scaling, sysfs interface for changing capacity values at
+ runtime.
+
endmenu
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index f2816f6ff76a..397e5c344e6a 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_SOC_BUS) += soc.o
obj-$(CONFIG_PINCTRL) += pinctrl.o
obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o
+obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o
obj-y += test/
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
new file mode 100644
index 000000000000..c33482121b7d
--- /dev/null
+++ b/drivers/base/arch_topology.c
@@ -0,0 +1,242 @@
+/*
+ * Arch specific cpu topology information
+ *
+ * Copyright (C) 2016, ARM Ltd.
+ * Written by: Juri Lelli, ARM Ltd.
+ *
+ * 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.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#include <linux/acpi.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/sched/topology.h>
+
+static DEFINE_MUTEX(cpu_scale_mutex);
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(cpu_scale, cpu);
+}
+
+void set_capacity_scale(unsigned int cpu, unsigned long capacity)
+{
+ per_cpu(cpu_scale, cpu) = capacity;
+}
+
+static ssize_t cpu_capacity_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+ return sprintf(buf, "%lu\n",
+ arch_scale_cpu_capacity(NULL, cpu->dev.id));
+}
+
+static ssize_t cpu_capacity_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ int this_cpu = cpu->dev.id;
+ int i;
+ unsigned long new_capacity;
+ ssize_t ret;
+
+ if (!count)
+ return 0;
+
+ ret = kstrtoul(buf, 0, &new_capacity);
+ if (ret)
+ return ret;
+ if (new_capacity > SCHED_CAPACITY_SCALE)
+ return -EINVAL;
+
+ mutex_lock(&cpu_scale_mutex);
+ for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
+ set_capacity_scale(i, new_capacity);
+ mutex_unlock(&cpu_scale_mutex);
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(cpu_capacity);
+
+static int register_cpu_capacity_sysctl(void)
+{
+ int i;
+ struct device *cpu;
+
+ for_each_possible_cpu(i) {
+ cpu = get_cpu_device(i);
+ if (!cpu) {
+ pr_err("%s: too early to get CPU%d device!\n",
+ __func__, i);
+ continue;
+ }
+ device_create_file(cpu, &dev_attr_cpu_capacity);
+ }
+
+ return 0;
+}
+subsys_initcall(register_cpu_capacity_sysctl);
+
+static u32 capacity_scale;
+static u32 *raw_capacity;
+bool cap_parsing_failed;
+
+void normalize_cpu_capacity(void)
+{
+ u64 capacity;
+ int cpu;
+
+ if (!raw_capacity || cap_parsing_failed)
+ return;
+
+ pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
+ mutex_lock(&cpu_scale_mutex);
+ for_each_possible_cpu(cpu) {
+ pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
+ cpu, raw_capacity[cpu]);
+ capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
+ / capacity_scale;
+ set_capacity_scale(cpu, capacity);
+ pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
+ cpu, arch_scale_cpu_capacity(NULL, cpu));
+ }
+ mutex_unlock(&cpu_scale_mutex);
+}
+
+int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
+{
+ int ret = 1;
+ u32 cpu_capacity;
+
+ if (cap_parsing_failed)
+ return !ret;
+
+ ret = of_property_read_u32(cpu_node,
+ "capacity-dmips-mhz",
+ &cpu_capacity);
+ if (!ret) {
+ if (!raw_capacity) {
+ raw_capacity = kcalloc(num_possible_cpus(),
+ sizeof(*raw_capacity),
+ GFP_KERNEL);
+ if (!raw_capacity) {
+ pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
+ cap_parsing_failed = true;
+ return ret;
+ }
+ }
+ capacity_scale = max(cpu_capacity, capacity_scale);
+ raw_capacity[cpu] = cpu_capacity;
+ pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
+ cpu_node->full_name, raw_capacity[cpu]);
+ } else {
+ if (raw_capacity) {
+ pr_err("cpu_capacity: missing %s raw capacity\n",
+ cpu_node->full_name);
+ pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+ }
+ cap_parsing_failed = true;
+ kfree(raw_capacity);
+ }
+
+ return !ret;
+}
+
+#ifdef CONFIG_CPU_FREQ
+static cpumask_var_t cpus_to_visit;
+static bool cap_parsing_done;
+static void parsing_done_workfn(struct work_struct *work);
+static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+
+static int
+init_cpu_capacity_callback(struct notifier_block *nb,
+ unsigned long val,
+ void *data)
+{
+ struct cpufreq_policy *policy = data;
+ int cpu;
+
+ if (cap_parsing_failed || cap_parsing_done)
+ return 0;
+
+ switch (val) {
+ case CPUFREQ_NOTIFY:
+ pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
+ cpumask_pr_args(policy->related_cpus),
+ cpumask_pr_args(cpus_to_visit));
+ cpumask_andnot(cpus_to_visit,
+ cpus_to_visit,
+ policy->related_cpus);
+ for_each_cpu(cpu, policy->related_cpus) {
+ raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
+ policy->cpuinfo.max_freq / 1000UL;
+ capacity_scale = max(raw_capacity[cpu], capacity_scale);
+ }
+ if (cpumask_empty(cpus_to_visit)) {
+ normalize_cpu_capacity();
+ kfree(raw_capacity);
+ pr_debug("cpu_capacity: parsing done\n");
+ cap_parsing_done = true;
+ schedule_work(&parsing_done_work);
+ }
+ }
+ return 0;
+}
+
+static struct notifier_block init_cpu_capacity_notifier = {
+ .notifier_call = init_cpu_capacity_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+ /*
+ * on ACPI-based systems we need to use the default cpu capacity
+ * until we have the necessary code to parse the cpu capacity, so
+ * skip registering cpufreq notifier.
+ */
+ if (!acpi_disabled || cap_parsing_failed)
+ return -EINVAL;
+
+ if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
+ pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
+ return -ENOMEM;
+ }
+
+ cpumask_copy(cpus_to_visit, cpu_possible_mask);
+
+ return cpufreq_register_notifier(&init_cpu_capacity_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+static void parsing_done_workfn(struct work_struct *work)
+{
+ cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+
+#else
+static int __init free_raw_capacity(void)
+{
+ kfree(raw_capacity);
+
+ return 0;
+}
+core_initcall(free_raw_capacity);
+#endif
--
2.10.0
WARNING: multiple messages have this Message-ID (diff)
From: juri.lelli@arm.com (Juri Lelli)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 5/9] arm, arm64: factorize common cpu capacity default code
Date: Mon, 27 Mar 2017 14:18:21 +0100 [thread overview]
Message-ID: <20170327131825.32134-6-juri.lelli@arm.com> (raw)
In-Reply-To: <20170327131825.32134-1-juri.lelli@arm.com>
arm and arm64 share lot of code relative to parsing CPU capacity
information from DT, using that information for appropriate scaling and
exposing a sysfs interface for chaging such values at runtime.
Factorize such code in a common place (driver/base/arch_topology.c) in
preparation for further additions.
Suggested-by: Will Deacon <will.deacon@arm.com>
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
---
Changes from v2:
- make capacity_scale and raw_capacity static
- added SPDX header
- improved indent
- misc. whitespaces/newlines fixes
Changes from v1:
- keep the original GPLv2 header
---
arch/arm/Kconfig | 1 +
arch/arm/kernel/topology.c | 213 ++-----------------------------------
arch/arm64/Kconfig | 1 +
arch/arm64/kernel/topology.c | 219 +--------------------------------------
drivers/base/Kconfig | 8 ++
drivers/base/Makefile | 1 +
drivers/base/arch_topology.c | 242 +++++++++++++++++++++++++++++++++++++++++++
7 files changed, 262 insertions(+), 423 deletions(-)
create mode 100644 drivers/base/arch_topology.c
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0d4e71b42c77..cd61154bb6d0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -25,6 +25,7 @@ config ARM
select EDAC_SUPPORT
select EDAC_ATOMIC_SCRUB
select GENERIC_ALLOCATOR
+ select GENERIC_ARCH_TOPOLOGY if ARM_CPU_TOPOLOGY
select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_EARLY_IOREMAP
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 162c82aeed96..49ef025ffaa0 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -44,75 +44,10 @@
* to run the rebalance_domains for all idle cores and the cpu_capacity can be
* updated during this sequence.
*/
-static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-static DEFINE_MUTEX(cpu_scale_mutex);
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return per_cpu(cpu_scale, cpu);
-}
-
-static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
-{
- per_cpu(cpu_scale, cpu) = capacity;
-}
-
-static ssize_t cpu_capacity_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
-
- return sprintf(buf, "%lu\n",
- arch_scale_cpu_capacity(NULL, cpu->dev.id));
-}
-
-static ssize_t cpu_capacity_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
- int this_cpu = cpu->dev.id, i;
- unsigned long new_capacity;
- ssize_t ret;
-
- if (count) {
- ret = kstrtoul(buf, 0, &new_capacity);
- if (ret)
- return ret;
- if (new_capacity > SCHED_CAPACITY_SCALE)
- return -EINVAL;
-
- mutex_lock(&cpu_scale_mutex);
- for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
- set_capacity_scale(i, new_capacity);
- mutex_unlock(&cpu_scale_mutex);
- }
-
- return count;
-}
-
-static DEVICE_ATTR_RW(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
- int i;
- struct device *cpu;
-
- for_each_possible_cpu(i) {
- cpu = get_cpu_device(i);
- if (!cpu) {
- pr_err("%s: too early to get CPU%d device!\n",
- __func__, i);
- continue;
- }
- device_create_file(cpu, &dev_attr_cpu_capacity);
- }
-
- return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
+extern unsigned long
+arch_scale_cpu_capacity(struct sched_domain *sd, int cpu);
+extern void set_capacity_scale(unsigned int cpu, unsigned long capacity);
#ifdef CONFIG_OF
struct cpu_efficiency {
@@ -141,145 +76,9 @@ static unsigned long *__cpu_capacity;
static unsigned long middle_capacity = 1;
static bool cap_from_dt = true;
-static u32 *raw_capacity;
-static bool cap_parsing_failed;
-static u32 capacity_scale;
-
-static int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
-{
- int ret = 1;
- u32 cpu_capacity;
-
- if (cap_parsing_failed)
- return !ret;
-
- ret = of_property_read_u32(cpu_node,
- "capacity-dmips-mhz",
- &cpu_capacity);
- if (!ret) {
- if (!raw_capacity) {
- raw_capacity = kcalloc(num_possible_cpus(),
- sizeof(*raw_capacity),
- GFP_KERNEL);
- if (!raw_capacity) {
- pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
- cap_parsing_failed = true;
- return ret;
- }
- }
- capacity_scale = max(cpu_capacity, capacity_scale);
- raw_capacity[cpu] = cpu_capacity;
- pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
- cpu_node->full_name, raw_capacity[cpu]);
- } else {
- if (raw_capacity) {
- pr_err("cpu_capacity: missing %s raw capacity\n",
- cpu_node->full_name);
- pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
- }
- cap_parsing_failed = true;
- kfree(raw_capacity);
- }
-
- return !ret;
-}
-
-static void normalize_cpu_capacity(void)
-{
- u64 capacity;
- int cpu;
-
- if (!raw_capacity || cap_parsing_failed)
- return;
-
- pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
- mutex_lock(&cpu_scale_mutex);
- for_each_possible_cpu(cpu) {
- capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
- / capacity_scale;
- set_capacity_scale(cpu, capacity);
- pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
- cpu, arch_scale_cpu_capacity(NULL, cpu));
- }
- mutex_unlock(&cpu_scale_mutex);
-}
-
-#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static bool cap_parsing_done;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-
-static int
-init_cpu_capacity_callback(struct notifier_block *nb,
- unsigned long val,
- void *data)
-{
- struct cpufreq_policy *policy = data;
- int cpu;
-
- if (cap_parsing_failed || cap_parsing_done)
- return 0;
-
- switch (val) {
- case CPUFREQ_NOTIFY:
- pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
- cpumask_pr_args(policy->related_cpus),
- cpumask_pr_args(cpus_to_visit));
- cpumask_andnot(cpus_to_visit,
- cpus_to_visit,
- policy->related_cpus);
- for_each_cpu(cpu, policy->related_cpus) {
- raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
- policy->cpuinfo.max_freq / 1000UL;
- capacity_scale = max(raw_capacity[cpu], capacity_scale);
- }
- if (cpumask_empty(cpus_to_visit)) {
- normalize_cpu_capacity();
- kfree(raw_capacity);
- pr_debug("cpu_capacity: parsing done\n");
- cap_parsing_done = true;
- schedule_work(&parsing_done_work);
- }
- }
- return 0;
-}
-
-static struct notifier_block init_cpu_capacity_notifier = {
- .notifier_call = init_cpu_capacity_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
- if (cap_parsing_failed)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
- pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
- return -ENOMEM;
- }
- cpumask_copy(cpus_to_visit, cpu_possible_mask);
-
- return cpufreq_register_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-static void parsing_done_workfn(struct work_struct *work)
-{
- cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-
-#else
-static int __init free_raw_capacity(void)
-{
- kfree(raw_capacity);
-
- return 0;
-}
-core_initcall(free_raw_capacity);
-#endif
+extern bool cap_parsing_failed;
+extern void normalize_cpu_capacity(void);
+extern int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu);
/*
* Iterate all CPUs' descriptor in DT and compute the efficiency
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3741859765cf..e36fb12afad6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -40,6 +40,7 @@ config ARM64
select EDAC_SUPPORT
select FRAME_POINTER
select GENERIC_ALLOCATOR
+ select GENERIC_ARCH_TOPOLOGY
select GENERIC_CLOCKEVENTS
select GENERIC_CLOCKEVENTS_BROADCAST
select GENERIC_CPU_AUTOPROBE
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 08243533e5ee..c5bc31eb97e8 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,7 +11,6 @@
* for more details.
*/
-#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
@@ -23,226 +22,14 @@
#include <linux/sched/topology.h>
#include <linux/slab.h>
#include <linux/string.h>
-#include <linux/cpufreq.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>
-static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-static DEFINE_MUTEX(cpu_scale_mutex);
-
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return per_cpu(cpu_scale, cpu);
-}
-
-static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
-{
- per_cpu(cpu_scale, cpu) = capacity;
-}
-
-static ssize_t cpu_capacity_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
-
- return sprintf(buf, "%lu\n",
- arch_scale_cpu_capacity(NULL, cpu->dev.id));
-}
-
-static ssize_t cpu_capacity_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
- int this_cpu = cpu->dev.id, i;
- unsigned long new_capacity;
- ssize_t ret;
-
- if (count) {
- ret = kstrtoul(buf, 0, &new_capacity);
- if (ret)
- return ret;
- if (new_capacity > SCHED_CAPACITY_SCALE)
- return -EINVAL;
-
- mutex_lock(&cpu_scale_mutex);
- for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
- set_capacity_scale(i, new_capacity);
- mutex_unlock(&cpu_scale_mutex);
- }
-
- return count;
-}
-
-static DEVICE_ATTR_RW(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
- int i;
- struct device *cpu;
-
- for_each_possible_cpu(i) {
- cpu = get_cpu_device(i);
- if (!cpu) {
- pr_err("%s: too early to get CPU%d device!\n",
- __func__, i);
- continue;
- }
- device_create_file(cpu, &dev_attr_cpu_capacity);
- }
-
- return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
-
-static u32 capacity_scale;
-static u32 *raw_capacity;
-static bool cap_parsing_failed;
-
-static void __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
-{
- int ret;
- u32 cpu_capacity;
-
- if (cap_parsing_failed)
- return;
-
- ret = of_property_read_u32(cpu_node,
- "capacity-dmips-mhz",
- &cpu_capacity);
- if (!ret) {
- if (!raw_capacity) {
- raw_capacity = kcalloc(num_possible_cpus(),
- sizeof(*raw_capacity),
- GFP_KERNEL);
- if (!raw_capacity) {
- pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
- cap_parsing_failed = true;
- return;
- }
- }
- capacity_scale = max(cpu_capacity, capacity_scale);
- raw_capacity[cpu] = cpu_capacity;
- pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
- cpu_node->full_name, raw_capacity[cpu]);
- } else {
- if (raw_capacity) {
- pr_err("cpu_capacity: missing %s raw capacity\n",
- cpu_node->full_name);
- pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
- }
- cap_parsing_failed = true;
- kfree(raw_capacity);
- }
-}
-
-static void normalize_cpu_capacity(void)
-{
- u64 capacity;
- int cpu;
-
- if (!raw_capacity || cap_parsing_failed)
- return;
-
- pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
- mutex_lock(&cpu_scale_mutex);
- for_each_possible_cpu(cpu) {
- pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
- cpu, raw_capacity[cpu]);
- capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
- / capacity_scale;
- set_capacity_scale(cpu, capacity);
- pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
- cpu, arch_scale_cpu_capacity(NULL, cpu));
- }
- mutex_unlock(&cpu_scale_mutex);
-}
-
-#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static bool cap_parsing_done;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-
-static int
-init_cpu_capacity_callback(struct notifier_block *nb,
- unsigned long val,
- void *data)
-{
- struct cpufreq_policy *policy = data;
- int cpu;
-
- if (cap_parsing_failed || cap_parsing_done)
- return 0;
-
- switch (val) {
- case CPUFREQ_NOTIFY:
- pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
- cpumask_pr_args(policy->related_cpus),
- cpumask_pr_args(cpus_to_visit));
- cpumask_andnot(cpus_to_visit,
- cpus_to_visit,
- policy->related_cpus);
- for_each_cpu(cpu, policy->related_cpus) {
- raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
- policy->cpuinfo.max_freq / 1000UL;
- capacity_scale = max(raw_capacity[cpu], capacity_scale);
- }
- if (cpumask_empty(cpus_to_visit)) {
- normalize_cpu_capacity();
- kfree(raw_capacity);
- pr_debug("cpu_capacity: parsing done\n");
- cap_parsing_done = true;
- schedule_work(&parsing_done_work);
- }
- }
- return 0;
-}
-
-static struct notifier_block init_cpu_capacity_notifier = {
- .notifier_call = init_cpu_capacity_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
- /*
- * on ACPI-based systems we need to use the default cpu capacity
- * until we have the necessary code to parse the cpu capacity, so
- * skip registering cpufreq notifier.
- */
- if (!acpi_disabled || cap_parsing_failed)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
- pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
- return -ENOMEM;
- }
- cpumask_copy(cpus_to_visit, cpu_possible_mask);
-
- return cpufreq_register_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-static void parsing_done_workfn(struct work_struct *work)
-{
- cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-
-#else
-static int __init free_raw_capacity(void)
-{
- kfree(raw_capacity);
-
- return 0;
-}
-core_initcall(free_raw_capacity);
-#endif
+extern bool cap_parsing_failed;
+extern void normalize_cpu_capacity(void);
+extern int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu);
static int __init get_cpu_for_node(struct device_node *node)
{
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index d718ae4b907a..f046d21de57d 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -339,4 +339,12 @@ config CMA_ALIGNMENT
endif
+config GENERIC_ARCH_TOPOLOGY
+ bool
+ help
+ Enable support for architectures common topology code: e.g., parsing
+ CPU capacity information from DT, usage of such information for
+ appropriate scaling, sysfs interface for changing capacity values at
+ runtime.
+
endmenu
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index f2816f6ff76a..397e5c344e6a 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_SOC_BUS) += soc.o
obj-$(CONFIG_PINCTRL) += pinctrl.o
obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o
+obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o
obj-y += test/
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
new file mode 100644
index 000000000000..c33482121b7d
--- /dev/null
+++ b/drivers/base/arch_topology.c
@@ -0,0 +1,242 @@
+/*
+ * Arch specific cpu topology information
+ *
+ * Copyright (C) 2016, ARM Ltd.
+ * Written by: Juri Lelli, ARM Ltd.
+ *
+ * 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.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#include <linux/acpi.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/sched/topology.h>
+
+static DEFINE_MUTEX(cpu_scale_mutex);
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(cpu_scale, cpu);
+}
+
+void set_capacity_scale(unsigned int cpu, unsigned long capacity)
+{
+ per_cpu(cpu_scale, cpu) = capacity;
+}
+
+static ssize_t cpu_capacity_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+ return sprintf(buf, "%lu\n",
+ arch_scale_cpu_capacity(NULL, cpu->dev.id));
+}
+
+static ssize_t cpu_capacity_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ int this_cpu = cpu->dev.id;
+ int i;
+ unsigned long new_capacity;
+ ssize_t ret;
+
+ if (!count)
+ return 0;
+
+ ret = kstrtoul(buf, 0, &new_capacity);
+ if (ret)
+ return ret;
+ if (new_capacity > SCHED_CAPACITY_SCALE)
+ return -EINVAL;
+
+ mutex_lock(&cpu_scale_mutex);
+ for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
+ set_capacity_scale(i, new_capacity);
+ mutex_unlock(&cpu_scale_mutex);
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(cpu_capacity);
+
+static int register_cpu_capacity_sysctl(void)
+{
+ int i;
+ struct device *cpu;
+
+ for_each_possible_cpu(i) {
+ cpu = get_cpu_device(i);
+ if (!cpu) {
+ pr_err("%s: too early to get CPU%d device!\n",
+ __func__, i);
+ continue;
+ }
+ device_create_file(cpu, &dev_attr_cpu_capacity);
+ }
+
+ return 0;
+}
+subsys_initcall(register_cpu_capacity_sysctl);
+
+static u32 capacity_scale;
+static u32 *raw_capacity;
+bool cap_parsing_failed;
+
+void normalize_cpu_capacity(void)
+{
+ u64 capacity;
+ int cpu;
+
+ if (!raw_capacity || cap_parsing_failed)
+ return;
+
+ pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
+ mutex_lock(&cpu_scale_mutex);
+ for_each_possible_cpu(cpu) {
+ pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
+ cpu, raw_capacity[cpu]);
+ capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
+ / capacity_scale;
+ set_capacity_scale(cpu, capacity);
+ pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
+ cpu, arch_scale_cpu_capacity(NULL, cpu));
+ }
+ mutex_unlock(&cpu_scale_mutex);
+}
+
+int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
+{
+ int ret = 1;
+ u32 cpu_capacity;
+
+ if (cap_parsing_failed)
+ return !ret;
+
+ ret = of_property_read_u32(cpu_node,
+ "capacity-dmips-mhz",
+ &cpu_capacity);
+ if (!ret) {
+ if (!raw_capacity) {
+ raw_capacity = kcalloc(num_possible_cpus(),
+ sizeof(*raw_capacity),
+ GFP_KERNEL);
+ if (!raw_capacity) {
+ pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
+ cap_parsing_failed = true;
+ return ret;
+ }
+ }
+ capacity_scale = max(cpu_capacity, capacity_scale);
+ raw_capacity[cpu] = cpu_capacity;
+ pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
+ cpu_node->full_name, raw_capacity[cpu]);
+ } else {
+ if (raw_capacity) {
+ pr_err("cpu_capacity: missing %s raw capacity\n",
+ cpu_node->full_name);
+ pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+ }
+ cap_parsing_failed = true;
+ kfree(raw_capacity);
+ }
+
+ return !ret;
+}
+
+#ifdef CONFIG_CPU_FREQ
+static cpumask_var_t cpus_to_visit;
+static bool cap_parsing_done;
+static void parsing_done_workfn(struct work_struct *work);
+static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+
+static int
+init_cpu_capacity_callback(struct notifier_block *nb,
+ unsigned long val,
+ void *data)
+{
+ struct cpufreq_policy *policy = data;
+ int cpu;
+
+ if (cap_parsing_failed || cap_parsing_done)
+ return 0;
+
+ switch (val) {
+ case CPUFREQ_NOTIFY:
+ pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
+ cpumask_pr_args(policy->related_cpus),
+ cpumask_pr_args(cpus_to_visit));
+ cpumask_andnot(cpus_to_visit,
+ cpus_to_visit,
+ policy->related_cpus);
+ for_each_cpu(cpu, policy->related_cpus) {
+ raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
+ policy->cpuinfo.max_freq / 1000UL;
+ capacity_scale = max(raw_capacity[cpu], capacity_scale);
+ }
+ if (cpumask_empty(cpus_to_visit)) {
+ normalize_cpu_capacity();
+ kfree(raw_capacity);
+ pr_debug("cpu_capacity: parsing done\n");
+ cap_parsing_done = true;
+ schedule_work(&parsing_done_work);
+ }
+ }
+ return 0;
+}
+
+static struct notifier_block init_cpu_capacity_notifier = {
+ .notifier_call = init_cpu_capacity_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+ /*
+ * on ACPI-based systems we need to use the default cpu capacity
+ * until we have the necessary code to parse the cpu capacity, so
+ * skip registering cpufreq notifier.
+ */
+ if (!acpi_disabled || cap_parsing_failed)
+ return -EINVAL;
+
+ if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
+ pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
+ return -ENOMEM;
+ }
+
+ cpumask_copy(cpus_to_visit, cpu_possible_mask);
+
+ return cpufreq_register_notifier(&init_cpu_capacity_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+static void parsing_done_workfn(struct work_struct *work)
+{
+ cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+
+#else
+static int __init free_raw_capacity(void)
+{
+ kfree(raw_capacity);
+
+ return 0;
+}
+core_initcall(free_raw_capacity);
+#endif
--
2.10.0
WARNING: multiple messages have this Message-ID (diff)
From: Juri Lelli <juri.lelli@arm.com>
To: linux-kernel@vger.kernel.org
Cc: linux-pm@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
devicetree@vger.kernel.org, peterz@infradead.org,
vincent.guittot@linaro.org, robh+dt@kernel.org,
mark.rutland@arm.com, linux@arm.linux.org.uk,
sudeep.holla@arm.com, lorenzo.pieralisi@arm.com,
catalin.marinas@arm.com, will.deacon@arm.com,
morten.rasmussen@arm.com, dietmar.eggemann@arm.com,
juri.lelli@arm.com, broonie@kernel.org,
gregkh@linuxfoundation.org, Russell King <linux@armlinux.org.uk>
Subject: [PATCH v3 5/9] arm, arm64: factorize common cpu capacity default code
Date: Mon, 27 Mar 2017 14:18:21 +0100 [thread overview]
Message-ID: <20170327131825.32134-6-juri.lelli@arm.com> (raw)
In-Reply-To: <20170327131825.32134-1-juri.lelli@arm.com>
arm and arm64 share lot of code relative to parsing CPU capacity
information from DT, using that information for appropriate scaling and
exposing a sysfs interface for chaging such values at runtime.
Factorize such code in a common place (driver/base/arch_topology.c) in
preparation for further additions.
Suggested-by: Will Deacon <will.deacon@arm.com>
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
---
Changes from v2:
- make capacity_scale and raw_capacity static
- added SPDX header
- improved indent
- misc. whitespaces/newlines fixes
Changes from v1:
- keep the original GPLv2 header
---
arch/arm/Kconfig | 1 +
arch/arm/kernel/topology.c | 213 ++-----------------------------------
arch/arm64/Kconfig | 1 +
arch/arm64/kernel/topology.c | 219 +--------------------------------------
drivers/base/Kconfig | 8 ++
drivers/base/Makefile | 1 +
drivers/base/arch_topology.c | 242 +++++++++++++++++++++++++++++++++++++++++++
7 files changed, 262 insertions(+), 423 deletions(-)
create mode 100644 drivers/base/arch_topology.c
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0d4e71b42c77..cd61154bb6d0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -25,6 +25,7 @@ config ARM
select EDAC_SUPPORT
select EDAC_ATOMIC_SCRUB
select GENERIC_ALLOCATOR
+ select GENERIC_ARCH_TOPOLOGY if ARM_CPU_TOPOLOGY
select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select GENERIC_EARLY_IOREMAP
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 162c82aeed96..49ef025ffaa0 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -44,75 +44,10 @@
* to run the rebalance_domains for all idle cores and the cpu_capacity can be
* updated during this sequence.
*/
-static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-static DEFINE_MUTEX(cpu_scale_mutex);
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return per_cpu(cpu_scale, cpu);
-}
-
-static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
-{
- per_cpu(cpu_scale, cpu) = capacity;
-}
-
-static ssize_t cpu_capacity_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
-
- return sprintf(buf, "%lu\n",
- arch_scale_cpu_capacity(NULL, cpu->dev.id));
-}
-
-static ssize_t cpu_capacity_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
- int this_cpu = cpu->dev.id, i;
- unsigned long new_capacity;
- ssize_t ret;
-
- if (count) {
- ret = kstrtoul(buf, 0, &new_capacity);
- if (ret)
- return ret;
- if (new_capacity > SCHED_CAPACITY_SCALE)
- return -EINVAL;
-
- mutex_lock(&cpu_scale_mutex);
- for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
- set_capacity_scale(i, new_capacity);
- mutex_unlock(&cpu_scale_mutex);
- }
-
- return count;
-}
-
-static DEVICE_ATTR_RW(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
- int i;
- struct device *cpu;
-
- for_each_possible_cpu(i) {
- cpu = get_cpu_device(i);
- if (!cpu) {
- pr_err("%s: too early to get CPU%d device!\n",
- __func__, i);
- continue;
- }
- device_create_file(cpu, &dev_attr_cpu_capacity);
- }
-
- return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
+extern unsigned long
+arch_scale_cpu_capacity(struct sched_domain *sd, int cpu);
+extern void set_capacity_scale(unsigned int cpu, unsigned long capacity);
#ifdef CONFIG_OF
struct cpu_efficiency {
@@ -141,145 +76,9 @@ static unsigned long *__cpu_capacity;
static unsigned long middle_capacity = 1;
static bool cap_from_dt = true;
-static u32 *raw_capacity;
-static bool cap_parsing_failed;
-static u32 capacity_scale;
-
-static int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
-{
- int ret = 1;
- u32 cpu_capacity;
-
- if (cap_parsing_failed)
- return !ret;
-
- ret = of_property_read_u32(cpu_node,
- "capacity-dmips-mhz",
- &cpu_capacity);
- if (!ret) {
- if (!raw_capacity) {
- raw_capacity = kcalloc(num_possible_cpus(),
- sizeof(*raw_capacity),
- GFP_KERNEL);
- if (!raw_capacity) {
- pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
- cap_parsing_failed = true;
- return ret;
- }
- }
- capacity_scale = max(cpu_capacity, capacity_scale);
- raw_capacity[cpu] = cpu_capacity;
- pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
- cpu_node->full_name, raw_capacity[cpu]);
- } else {
- if (raw_capacity) {
- pr_err("cpu_capacity: missing %s raw capacity\n",
- cpu_node->full_name);
- pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
- }
- cap_parsing_failed = true;
- kfree(raw_capacity);
- }
-
- return !ret;
-}
-
-static void normalize_cpu_capacity(void)
-{
- u64 capacity;
- int cpu;
-
- if (!raw_capacity || cap_parsing_failed)
- return;
-
- pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
- mutex_lock(&cpu_scale_mutex);
- for_each_possible_cpu(cpu) {
- capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
- / capacity_scale;
- set_capacity_scale(cpu, capacity);
- pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
- cpu, arch_scale_cpu_capacity(NULL, cpu));
- }
- mutex_unlock(&cpu_scale_mutex);
-}
-
-#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static bool cap_parsing_done;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-
-static int
-init_cpu_capacity_callback(struct notifier_block *nb,
- unsigned long val,
- void *data)
-{
- struct cpufreq_policy *policy = data;
- int cpu;
-
- if (cap_parsing_failed || cap_parsing_done)
- return 0;
-
- switch (val) {
- case CPUFREQ_NOTIFY:
- pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
- cpumask_pr_args(policy->related_cpus),
- cpumask_pr_args(cpus_to_visit));
- cpumask_andnot(cpus_to_visit,
- cpus_to_visit,
- policy->related_cpus);
- for_each_cpu(cpu, policy->related_cpus) {
- raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
- policy->cpuinfo.max_freq / 1000UL;
- capacity_scale = max(raw_capacity[cpu], capacity_scale);
- }
- if (cpumask_empty(cpus_to_visit)) {
- normalize_cpu_capacity();
- kfree(raw_capacity);
- pr_debug("cpu_capacity: parsing done\n");
- cap_parsing_done = true;
- schedule_work(&parsing_done_work);
- }
- }
- return 0;
-}
-
-static struct notifier_block init_cpu_capacity_notifier = {
- .notifier_call = init_cpu_capacity_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
- if (cap_parsing_failed)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
- pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
- return -ENOMEM;
- }
- cpumask_copy(cpus_to_visit, cpu_possible_mask);
-
- return cpufreq_register_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-static void parsing_done_workfn(struct work_struct *work)
-{
- cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-
-#else
-static int __init free_raw_capacity(void)
-{
- kfree(raw_capacity);
-
- return 0;
-}
-core_initcall(free_raw_capacity);
-#endif
+extern bool cap_parsing_failed;
+extern void normalize_cpu_capacity(void);
+extern int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu);
/*
* Iterate all CPUs' descriptor in DT and compute the efficiency
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3741859765cf..e36fb12afad6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -40,6 +40,7 @@ config ARM64
select EDAC_SUPPORT
select FRAME_POINTER
select GENERIC_ALLOCATOR
+ select GENERIC_ARCH_TOPOLOGY
select GENERIC_CLOCKEVENTS
select GENERIC_CLOCKEVENTS_BROADCAST
select GENERIC_CPU_AUTOPROBE
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 08243533e5ee..c5bc31eb97e8 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,7 +11,6 @@
* for more details.
*/
-#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
@@ -23,226 +22,14 @@
#include <linux/sched/topology.h>
#include <linux/slab.h>
#include <linux/string.h>
-#include <linux/cpufreq.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>
-static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
-static DEFINE_MUTEX(cpu_scale_mutex);
-
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
- return per_cpu(cpu_scale, cpu);
-}
-
-static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
-{
- per_cpu(cpu_scale, cpu) = capacity;
-}
-
-static ssize_t cpu_capacity_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
-
- return sprintf(buf, "%lu\n",
- arch_scale_cpu_capacity(NULL, cpu->dev.id));
-}
-
-static ssize_t cpu_capacity_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct cpu *cpu = container_of(dev, struct cpu, dev);
- int this_cpu = cpu->dev.id, i;
- unsigned long new_capacity;
- ssize_t ret;
-
- if (count) {
- ret = kstrtoul(buf, 0, &new_capacity);
- if (ret)
- return ret;
- if (new_capacity > SCHED_CAPACITY_SCALE)
- return -EINVAL;
-
- mutex_lock(&cpu_scale_mutex);
- for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
- set_capacity_scale(i, new_capacity);
- mutex_unlock(&cpu_scale_mutex);
- }
-
- return count;
-}
-
-static DEVICE_ATTR_RW(cpu_capacity);
-
-static int register_cpu_capacity_sysctl(void)
-{
- int i;
- struct device *cpu;
-
- for_each_possible_cpu(i) {
- cpu = get_cpu_device(i);
- if (!cpu) {
- pr_err("%s: too early to get CPU%d device!\n",
- __func__, i);
- continue;
- }
- device_create_file(cpu, &dev_attr_cpu_capacity);
- }
-
- return 0;
-}
-subsys_initcall(register_cpu_capacity_sysctl);
-
-static u32 capacity_scale;
-static u32 *raw_capacity;
-static bool cap_parsing_failed;
-
-static void __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
-{
- int ret;
- u32 cpu_capacity;
-
- if (cap_parsing_failed)
- return;
-
- ret = of_property_read_u32(cpu_node,
- "capacity-dmips-mhz",
- &cpu_capacity);
- if (!ret) {
- if (!raw_capacity) {
- raw_capacity = kcalloc(num_possible_cpus(),
- sizeof(*raw_capacity),
- GFP_KERNEL);
- if (!raw_capacity) {
- pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
- cap_parsing_failed = true;
- return;
- }
- }
- capacity_scale = max(cpu_capacity, capacity_scale);
- raw_capacity[cpu] = cpu_capacity;
- pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
- cpu_node->full_name, raw_capacity[cpu]);
- } else {
- if (raw_capacity) {
- pr_err("cpu_capacity: missing %s raw capacity\n",
- cpu_node->full_name);
- pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
- }
- cap_parsing_failed = true;
- kfree(raw_capacity);
- }
-}
-
-static void normalize_cpu_capacity(void)
-{
- u64 capacity;
- int cpu;
-
- if (!raw_capacity || cap_parsing_failed)
- return;
-
- pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
- mutex_lock(&cpu_scale_mutex);
- for_each_possible_cpu(cpu) {
- pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
- cpu, raw_capacity[cpu]);
- capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
- / capacity_scale;
- set_capacity_scale(cpu, capacity);
- pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
- cpu, arch_scale_cpu_capacity(NULL, cpu));
- }
- mutex_unlock(&cpu_scale_mutex);
-}
-
-#ifdef CONFIG_CPU_FREQ
-static cpumask_var_t cpus_to_visit;
-static bool cap_parsing_done;
-static void parsing_done_workfn(struct work_struct *work);
-static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
-
-static int
-init_cpu_capacity_callback(struct notifier_block *nb,
- unsigned long val,
- void *data)
-{
- struct cpufreq_policy *policy = data;
- int cpu;
-
- if (cap_parsing_failed || cap_parsing_done)
- return 0;
-
- switch (val) {
- case CPUFREQ_NOTIFY:
- pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
- cpumask_pr_args(policy->related_cpus),
- cpumask_pr_args(cpus_to_visit));
- cpumask_andnot(cpus_to_visit,
- cpus_to_visit,
- policy->related_cpus);
- for_each_cpu(cpu, policy->related_cpus) {
- raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
- policy->cpuinfo.max_freq / 1000UL;
- capacity_scale = max(raw_capacity[cpu], capacity_scale);
- }
- if (cpumask_empty(cpus_to_visit)) {
- normalize_cpu_capacity();
- kfree(raw_capacity);
- pr_debug("cpu_capacity: parsing done\n");
- cap_parsing_done = true;
- schedule_work(&parsing_done_work);
- }
- }
- return 0;
-}
-
-static struct notifier_block init_cpu_capacity_notifier = {
- .notifier_call = init_cpu_capacity_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
- /*
- * on ACPI-based systems we need to use the default cpu capacity
- * until we have the necessary code to parse the cpu capacity, so
- * skip registering cpufreq notifier.
- */
- if (!acpi_disabled || cap_parsing_failed)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
- pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
- return -ENOMEM;
- }
- cpumask_copy(cpus_to_visit, cpu_possible_mask);
-
- return cpufreq_register_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-static void parsing_done_workfn(struct work_struct *work)
-{
- cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
- CPUFREQ_POLICY_NOTIFIER);
-}
-
-#else
-static int __init free_raw_capacity(void)
-{
- kfree(raw_capacity);
-
- return 0;
-}
-core_initcall(free_raw_capacity);
-#endif
+extern bool cap_parsing_failed;
+extern void normalize_cpu_capacity(void);
+extern int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu);
static int __init get_cpu_for_node(struct device_node *node)
{
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index d718ae4b907a..f046d21de57d 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -339,4 +339,12 @@ config CMA_ALIGNMENT
endif
+config GENERIC_ARCH_TOPOLOGY
+ bool
+ help
+ Enable support for architectures common topology code: e.g., parsing
+ CPU capacity information from DT, usage of such information for
+ appropriate scaling, sysfs interface for changing capacity values at
+ runtime.
+
endmenu
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index f2816f6ff76a..397e5c344e6a 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_SOC_BUS) += soc.o
obj-$(CONFIG_PINCTRL) += pinctrl.o
obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o
+obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o
obj-y += test/
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
new file mode 100644
index 000000000000..c33482121b7d
--- /dev/null
+++ b/drivers/base/arch_topology.c
@@ -0,0 +1,242 @@
+/*
+ * Arch specific cpu topology information
+ *
+ * Copyright (C) 2016, ARM Ltd.
+ * Written by: Juri Lelli, ARM Ltd.
+ *
+ * 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.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#include <linux/acpi.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/sched/topology.h>
+
+static DEFINE_MUTEX(cpu_scale_mutex);
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(cpu_scale, cpu);
+}
+
+void set_capacity_scale(unsigned int cpu, unsigned long capacity)
+{
+ per_cpu(cpu_scale, cpu) = capacity;
+}
+
+static ssize_t cpu_capacity_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+ return sprintf(buf, "%lu\n",
+ arch_scale_cpu_capacity(NULL, cpu->dev.id));
+}
+
+static ssize_t cpu_capacity_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ int this_cpu = cpu->dev.id;
+ int i;
+ unsigned long new_capacity;
+ ssize_t ret;
+
+ if (!count)
+ return 0;
+
+ ret = kstrtoul(buf, 0, &new_capacity);
+ if (ret)
+ return ret;
+ if (new_capacity > SCHED_CAPACITY_SCALE)
+ return -EINVAL;
+
+ mutex_lock(&cpu_scale_mutex);
+ for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
+ set_capacity_scale(i, new_capacity);
+ mutex_unlock(&cpu_scale_mutex);
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(cpu_capacity);
+
+static int register_cpu_capacity_sysctl(void)
+{
+ int i;
+ struct device *cpu;
+
+ for_each_possible_cpu(i) {
+ cpu = get_cpu_device(i);
+ if (!cpu) {
+ pr_err("%s: too early to get CPU%d device!\n",
+ __func__, i);
+ continue;
+ }
+ device_create_file(cpu, &dev_attr_cpu_capacity);
+ }
+
+ return 0;
+}
+subsys_initcall(register_cpu_capacity_sysctl);
+
+static u32 capacity_scale;
+static u32 *raw_capacity;
+bool cap_parsing_failed;
+
+void normalize_cpu_capacity(void)
+{
+ u64 capacity;
+ int cpu;
+
+ if (!raw_capacity || cap_parsing_failed)
+ return;
+
+ pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
+ mutex_lock(&cpu_scale_mutex);
+ for_each_possible_cpu(cpu) {
+ pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
+ cpu, raw_capacity[cpu]);
+ capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
+ / capacity_scale;
+ set_capacity_scale(cpu, capacity);
+ pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
+ cpu, arch_scale_cpu_capacity(NULL, cpu));
+ }
+ mutex_unlock(&cpu_scale_mutex);
+}
+
+int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
+{
+ int ret = 1;
+ u32 cpu_capacity;
+
+ if (cap_parsing_failed)
+ return !ret;
+
+ ret = of_property_read_u32(cpu_node,
+ "capacity-dmips-mhz",
+ &cpu_capacity);
+ if (!ret) {
+ if (!raw_capacity) {
+ raw_capacity = kcalloc(num_possible_cpus(),
+ sizeof(*raw_capacity),
+ GFP_KERNEL);
+ if (!raw_capacity) {
+ pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
+ cap_parsing_failed = true;
+ return ret;
+ }
+ }
+ capacity_scale = max(cpu_capacity, capacity_scale);
+ raw_capacity[cpu] = cpu_capacity;
+ pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
+ cpu_node->full_name, raw_capacity[cpu]);
+ } else {
+ if (raw_capacity) {
+ pr_err("cpu_capacity: missing %s raw capacity\n",
+ cpu_node->full_name);
+ pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+ }
+ cap_parsing_failed = true;
+ kfree(raw_capacity);
+ }
+
+ return !ret;
+}
+
+#ifdef CONFIG_CPU_FREQ
+static cpumask_var_t cpus_to_visit;
+static bool cap_parsing_done;
+static void parsing_done_workfn(struct work_struct *work);
+static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+
+static int
+init_cpu_capacity_callback(struct notifier_block *nb,
+ unsigned long val,
+ void *data)
+{
+ struct cpufreq_policy *policy = data;
+ int cpu;
+
+ if (cap_parsing_failed || cap_parsing_done)
+ return 0;
+
+ switch (val) {
+ case CPUFREQ_NOTIFY:
+ pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
+ cpumask_pr_args(policy->related_cpus),
+ cpumask_pr_args(cpus_to_visit));
+ cpumask_andnot(cpus_to_visit,
+ cpus_to_visit,
+ policy->related_cpus);
+ for_each_cpu(cpu, policy->related_cpus) {
+ raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
+ policy->cpuinfo.max_freq / 1000UL;
+ capacity_scale = max(raw_capacity[cpu], capacity_scale);
+ }
+ if (cpumask_empty(cpus_to_visit)) {
+ normalize_cpu_capacity();
+ kfree(raw_capacity);
+ pr_debug("cpu_capacity: parsing done\n");
+ cap_parsing_done = true;
+ schedule_work(&parsing_done_work);
+ }
+ }
+ return 0;
+}
+
+static struct notifier_block init_cpu_capacity_notifier = {
+ .notifier_call = init_cpu_capacity_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+ /*
+ * on ACPI-based systems we need to use the default cpu capacity
+ * until we have the necessary code to parse the cpu capacity, so
+ * skip registering cpufreq notifier.
+ */
+ if (!acpi_disabled || cap_parsing_failed)
+ return -EINVAL;
+
+ if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
+ pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
+ return -ENOMEM;
+ }
+
+ cpumask_copy(cpus_to_visit, cpu_possible_mask);
+
+ return cpufreq_register_notifier(&init_cpu_capacity_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+static void parsing_done_workfn(struct work_struct *work)
+{
+ cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+}
+
+#else
+static int __init free_raw_capacity(void)
+{
+ kfree(raw_capacity);
+
+ return 0;
+}
+core_initcall(free_raw_capacity);
+#endif
--
2.10.0
next prev parent reply other threads:[~2017-03-27 13:18 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-27 13:18 [PATCH v3 0/9] Fix issues and factorize arm/arm64 capacity information code Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` [PATCH v3 1/9] Documentation: arm: fix wrong reference number in DT definition Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` [PATCH v3 2/9] Documentation/ABI: add information about cpu_capacity Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli [this message]
2017-03-27 13:18 ` [PATCH v3 5/9] arm, arm64: factorize common cpu capacity default code Juri Lelli
2017-03-27 13:18 ` Juri Lelli
[not found] ` <20170327131825.32134-6-juri.lelli-5wv7dgnIgG8@public.gmane.org>
2017-04-08 16:25 ` Greg KH
2017-04-08 16:25 ` Greg KH
2017-04-08 16:25 ` Greg KH
2017-04-10 8:18 ` Catalin Marinas
2017-04-10 8:18 ` Catalin Marinas
[not found] ` <20170410081806.GB27538-M2fw3Uu6cmfZROr8t4l/smS4ubULX0JqMm0uRHvK7Nw@public.gmane.org>
2017-04-10 16:23 ` Juri Lelli
2017-04-10 16:23 ` Juri Lelli
2017-04-10 16:23 ` Juri Lelli
2017-03-27 13:18 ` [PATCH v3 8/9] arm,arm64,drivers: move externs in a new header file Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
[not found] ` <20170327131825.32134-9-juri.lelli-5wv7dgnIgG8@public.gmane.org>
2017-04-10 8:31 ` Catalin Marinas
2017-04-10 8:31 ` Catalin Marinas
2017-04-10 8:31 ` Catalin Marinas
2017-03-27 13:18 ` [PATCH v3 9/9] arm,arm64,drivers: add a prefix to drivers arch_topology interfaces Juri Lelli
2017-03-27 13:18 ` [PATCH v3 9/9] arm, arm64, drivers: " Juri Lelli
[not found] ` <20170327131825.32134-10-juri.lelli-5wv7dgnIgG8@public.gmane.org>
2017-04-10 8:32 ` Catalin Marinas
2017-04-10 8:32 ` Catalin Marinas
2017-04-10 8:32 ` Catalin Marinas
[not found] ` <20170327131825.32134-1-juri.lelli-5wv7dgnIgG8@public.gmane.org>
2017-03-27 13:18 ` [PATCH v3 3/9] arm: fix return value of parse_cpu_capacity Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-29 7:37 ` Vincent Guittot
2017-03-29 7:37 ` Vincent Guittot
[not found] ` <CAKfTPtCswVBMCaEUzBF4w_GZf-2iLORsS5S0HhGD94ps4+J1Xg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-03-29 8:06 ` Juri Lelli
2017-03-29 8:06 ` Juri Lelli
2017-03-29 8:06 ` Juri Lelli
2017-03-27 13:18 ` [PATCH v3 4/9] arm: remove wrong CONFIG_PROC_SYSCTL ifdef Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
[not found] ` <20170327131825.32134-5-juri.lelli-5wv7dgnIgG8@public.gmane.org>
2017-03-29 7:39 ` Vincent Guittot
2017-03-29 7:39 ` Vincent Guittot
2017-03-29 7:39 ` Vincent Guittot
2017-03-27 13:18 ` [PATCH v3 6/9] drivers: remove useless comment from base/arch_topology.c Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-04-10 13:51 ` Russell King - ARM Linux
2017-04-10 13:51 ` Russell King - ARM Linux
2017-04-10 14:02 ` Juri Lelli
2017-04-10 14:02 ` Juri Lelli
2017-04-10 16:33 ` Russell King - ARM Linux
2017-04-10 16:33 ` Russell King - ARM Linux
2017-04-11 10:43 ` Juri Lelli
2017-04-11 10:43 ` Juri Lelli
2017-04-11 10:43 ` Juri Lelli
2017-03-27 13:18 ` [PATCH v3 7/9] arm,arm64,drivers: reduce scope of cap_parsing_failed Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-03-27 13:18 ` Juri Lelli
2017-04-10 8:31 ` Catalin Marinas
2017-04-10 8:31 ` Catalin Marinas
2017-04-06 14:14 ` [PATCH v3 0/9] Fix issues and factorize arm/arm64 capacity information code Juri Lelli
2017-04-06 14:14 ` Juri Lelli
2017-04-06 14:14 ` Juri Lelli
2017-04-10 15:05 ` Russell King - ARM Linux
2017-04-10 15:05 ` Russell King - ARM Linux
2017-04-10 15:05 ` Russell King - ARM Linux
2017-04-10 16:21 ` Juri Lelli
2017-04-10 16:21 ` Juri Lelli
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170327131825.32134-6-juri.lelli@arm.com \
--to=juri.lelli@arm.com \
--cc=broonie@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=devicetree@vger.kernel.org \
--cc=dietmar.eggemann@arm.com \
--cc=gregkh@linuxfoundation.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=linux@armlinux.org.uk \
--cc=lorenzo.pieralisi@arm.com \
--cc=mark.rutland@arm.com \
--cc=morten.rasmussen@arm.com \
--cc=peterz@infradead.org \
--cc=robh+dt@kernel.org \
--cc=sudeep.holla@arm.com \
--cc=vincent.guittot@linaro.org \
--cc=will.deacon@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.