| Message ID | 1393919477-27814-1-git-send-email-broonie@kernel.org |
|---|---|
| State | New |
| Headers | show |
On Tue, Mar 04, 2014 at 07:51:17AM +0000, Mark Brown wrote: > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig > index 764d682..80e0eb1 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -165,6 +165,30 @@ config SMP > > If you don't know what to do here, say N. > > +config CPU_TOPOLOGY > + bool "Support CPU topology definition" Thanks for the patch. I applied it but not pushed to -next yet. I wonder whether it makes sense to drop the description of the CPU_TOPOLOGY entry here so that it is no longer selectable. It will be enabled by default when SMP (I can do the change myself, no need to repost).
On Tue, Mar 04, 2014 at 09:55:36AM +0000, Catalin Marinas wrote: > On Tue, Mar 04, 2014 at 07:51:17AM +0000, Mark Brown wrote: > > +config CPU_TOPOLOGY > > + bool "Support CPU topology definition" > Thanks for the patch. I applied it but not pushed to -next yet. I wonder > whether it makes sense to drop the description of the CPU_TOPOLOGY entry > here so that it is no longer selectable. It will be enabled by default > when SMP (I can do the change myself, no need to repost). I'm totally fine with that, I only made it selectable due to the 32 bit code doing that - I'm not sure we even need the separate symbol. Whatever you prefer.
On Tue, Mar 04, 2014 at 07:51:17AM +0000, Mark Brown wrote: > 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. > > Following patches will implement support for interpreting topology > information from MPIDR and for parsing the DT topology bindings for ARM, > similar patches will be needed for ACPI. > > Signed-off-by: Mark Brown <broonie@linaro.org> > Acked-by: Mark RUtland <mark.rutland@arm.com> > --- > 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 764d682..80e0eb1 100644 > --- a/arch/arm64/Kconfig > +++ b/arch/arm64/Kconfig > @@ -165,6 +165,30 @@ 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 e52bcdc..da1dafb 100644 > --- a/arch/arm64/kernel/Makefile > +++ b/arch/arm64/kernel/Makefile > @@ -21,6 +21,7 @@ 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_KGDB) += kgdb.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 5070dc3..f0a141d 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 > @@ -391,6 +398,10 @@ 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..3e06b0b > --- /dev/null > +++ b/arch/arm64/kernel/topology.c > @@ -0,0 +1,95 @@ > +/* > + * arch/arm64/kernel/topology.c > + * > + * Copyright (C) 2011,2013,2014 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 above can go > +#include <linux/cpumask.h> > +#include <linux/init.h> > +#include <linux/percpu.h> > +#include <linux/node.h> > +#include <linux/nodemask.h> > +#include <linux/sched.h> Ditto for the four includes above, I know you will have to add them later, but removing them is not that complex, up to you guys. Having said that: Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> > + > +#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_debug("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 > >
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 764d682..80e0eb1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -165,6 +165,30 @@ 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 e52bcdc..da1dafb 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -21,6 +21,7 @@ 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-$(CONFIG_KGDB) += kgdb.o +arm64-obj-$(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 5070dc3..f0a141d 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 @@ -391,6 +398,10 @@ 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..3e06b0b --- /dev/null +++ b/arch/arm64/kernel/topology.c @@ -0,0 +1,95 @@ +/* + * arch/arm64/kernel/topology.c + * + * Copyright (C) 2011,2013,2014 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_debug("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); + } +}