The affinity between ARM processors is defined in the MPIDR register.
We can identify which processors are in the same cluster,
and which ones have performance interdependency. We can define the
cpu topology of ARM platform, that is then used by sched_mc and sched_smt.
The default state of sched_mc and sched_smt config is disable.
When enabled, the behavior of the scheduler can be modified with
sched_mc_power_savings and sched_smt_power_savings sysfs interfaces.
Changes since v2 :
* Update the commit message and some comments
Changes since v1 :
* Update the commit message
* Add read_cpuid_mpidr in arch/arm/include/asm/cputype.h
* Modify header of arch/arm/kernel/topology.c
* Modify tests and manipulation of MPIDR's bitfields
* Modify the place and dependancy of the config
* Modify Noop functions
Signed-off-by: Vincent Guittot <vincent.guittot(a)linaro.org>
Reviewed-by: Amit Kucheria <amit.kucheria(a)linaro.org>
---
arch/arm/Kconfig | 25 +++++++
arch/arm/include/asm/cputype.h | 6 ++
arch/arm/include/asm/topology.h | 33 +++++++++
arch/arm/kernel/Makefile | 1 +
arch/arm/kernel/smp.c | 6 ++
arch/arm/kernel/topology.c | 150 +++++++++++++++++++++++++++++++++++++++
6 files changed, 221 insertions(+), 0 deletions(-)
create mode 100644 arch/arm/kernel/topology.c
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9adc278..f327e55 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1344,6 +1344,31 @@ config SMP_ON_UP
If you don't know what to do here, say Y.
+config ARM_CPU_TOPOLOGY
+ bool "Support cpu topology definition"
+ depends on SMP && CPU_V7
+ default y
+ help
+ Support ARM cpu topology definition. The MPIDR register defines
+ affinity between processors which is then used to describe the cpu
+ topology of an ARM System.
+
+config SCHED_MC
+ bool "Multi-core scheduler support"
+ depends on ARM_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 ARM_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 HAVE_ARM_SCU
bool
depends on SMP
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cd4458f..cb47d28 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -8,6 +8,7 @@
#define CPUID_CACHETYPE 1
#define CPUID_TCM 2
#define CPUID_TLBTYPE 3
+#define CPUID_MPIDR 5
#define CPUID_EXT_PFR0 "c1, 0"
#define CPUID_EXT_PFR1 "c1, 1"
@@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
return read_cpuid(CPUID_TCM);
}
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+ return read_cpuid(CPUID_MPIDR);
+}
+
/*
* Intel's XScale3 core supports some v6 features (supersections, L2)
* but advertises itself as v5 as it does not support the v6 ISA. For
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index accbd7c..63a7454 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -1,6 +1,39 @@
#ifndef _ASM_ARM_TOPOLOGY_H
#define _ASM_ARM_TOPOLOGY_H
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+ int thread_id;
+ int core_id;
+ int socket_id;
+ cpumask_t thread_sibling;
+ cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu) (cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu) (&(cpu_topology[cpu].core_sibling))
+#define topology_thread_cpumask(cpu) (&(cpu_topology[cpu].thread_sibling))
+
+#define mc_capable() (cpu_topology[0].socket_id != -1)
+#define smt_capable() (cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(unsigned 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/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index a5b31af..816a481 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_IWMMXT) += iwmmxt.o
obj-$(CONFIG_CPU_HAS_PMU) += pmu.o
obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o
AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt
+obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o
ifneq ($(CONFIG_ARCH_EBSA110),y)
obj-y += io.o
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 344e52b..3e8dc3b 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -31,6 +31,7 @@
#include <asm/cacheflush.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
+#include <asm/topology.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -268,6 +269,9 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
cpu_info->loops_per_jiffy = loops_per_jiffy;
+
+ store_cpu_topology(cpuid);
+
}
/*
@@ -354,6 +358,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int ncores = num_possible_cpus();
+ init_cpu_topology();
+
smp_store_cpu_info(smp_processor_id());
/*
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
new file mode 100644
index 0000000..52f5265
--- /dev/null
+++ b/arch/arm/kernel/topology.c
@@ -0,0 +1,150 @@
+/*
+ * arch/arm/kernel/topology.c
+ *
+ * Copyright (C) 2011 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+/*
+ * These masks reflect the current use of the affinity levels.
+ * The affinity level can be up to 16 bits according to ARM ARM
+ */
+
+#define MPIDR_LEVEL0_MASK 0x3
+#define MPIDR_LEVEL0_SHIFT 0
+
+#define MPIDR_LEVEL1_MASK 0xF
+#define MPIDR_LEVEL1_SHIFT 8
+
+#define MPIDR_LEVEL2_MASK 0xFF
+#define MPIDR_LEVEL2_SHIFT 16
+
+struct cputopo_arm cpu_topology[NR_CPUS];
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+ return &(cpu_topology[cpu].core_sibling);
+}
+
+/*
+ * store_cpu_topology is called at boot when only one cpu is running
+ * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
+ * which prevents simultaneous write access to cpu_topology array
+ */
+void store_cpu_topology(unsigned int cpuid)
+{
+ struct cputopo_arm *cpuid_topo = &(cpu_topology[cpuid]);
+ unsigned int mpidr;
+ unsigned int cpu;
+
+ /* If the cpu topology has been already set, just return */
+ if (cpuid_topo->core_id != -1)
+ return;
+
+ mpidr = read_cpuid_mpidr();
+
+ /* create cpu topology mapping */
+ if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
+ /*
+ * This is a multiprocessor system
+ * multiprocessor format & multiprocessor mode field are set
+ */
+
+ if (mpidr & MPIDR_MT_BITMASK) {
+ /* core performance interdependency */
+ cpuid_topo->thread_id = ((mpidr >> MPIDR_LEVEL0_SHIFT)
+ & MPIDR_LEVEL0_MASK);
+ cpuid_topo->core_id = ((mpidr >> MPIDR_LEVEL1_SHIFT)
+ & MPIDR_LEVEL1_MASK);
+ cpuid_topo->socket_id = ((mpidr >> MPIDR_LEVEL2_SHIFT)
+ & MPIDR_LEVEL2_MASK);
+ } else {
+ /* largely independent cores */
+ cpuid_topo->thread_id = -1;
+ cpuid_topo->core_id = ((mpidr >> MPIDR_LEVEL0_SHIFT)
+ & MPIDR_LEVEL0_MASK);
+ cpuid_topo->socket_id = ((mpidr >> MPIDR_LEVEL1_SHIFT)
+ & MPIDR_LEVEL1_MASK);
+ }
+ } else {
+ /*
+ * This is an uniprocessor system
+ * we are in multiprocessor format but uniprocessor system
+ * or in the old uniprocessor format
+ */
+
+ cpuid_topo->thread_id = -1;
+ cpuid_topo->core_id = 0;
+ cpuid_topo->socket_id = -1;
+ }
+
+ /* update core and thread sibling masks */
+ for_each_possible_cpu(cpu) {
+ struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+ if (cpuid_topo->socket_id == cpu_topo->socket_id) {
+ 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) {
+ cpumask_set_cpu(cpuid,
+ &cpu_topo->thread_sibling);
+ if (cpu != cpuid)
+ cpumask_set_cpu(cpu,
+ &cpuid_topo->thread_sibling);
+ }
+ }
+ }
+ smp_wmb();
+
+ printk(KERN_INFO "cpu %u : thread %d cpu %d, socket %d, mpidr %x\n",
+ cpuid, cpu_topology[cpuid].thread_id,
+ cpu_topology[cpuid].core_id,
+ cpu_topology[cpuid].socket_id, mpidr);
+
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void init_cpu_topology(void)
+{
+ unsigned int cpu;
+
+ /* init core mask */
+ for_each_possible_cpu(cpu) {
+ struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+ cpu_topo->thread_id = -1;
+ cpu_topo->core_id = -1;
+ cpu_topo->socket_id = -1;
+ cpumask_clear(&cpu_topo->core_sibling);
+ cpumask_clear(&cpu_topo->thread_sibling);
+ }
+ smp_wmb();
+}
--
1.7.4.1
Hi there,
I took a look at the AOSP libjpeg code which is included in
git://android.git.kernel.org/platform/external/jpeg
during my flight back home (which incidentally had been diverted and
landed me in Rio de Janeiro; not sure if I celebrate or cry) and noted
the following things:
- There is a v6 implementation of the fast IDCT algorithm which
lives in armv6_idct.S.
- The commit which adds this implementation was added October 2010,
and there haven't been any changes since.
- The code that selects the decoder IDCT implementation in
jddctmgr.c always uses that implementation if ANDROID_ARMV6_IDCT
is defined.
- Google have an "ashmem" backing store implementation, and have
code to enable tile-based mode. It's a fairly non-intrusive change
to use ashmem since it just replaces jpeg_open_backing_store.
- The code is pretty much standard libjpeg without any structural
changes to it.
- There isn't any NEON code in this branch.
- Mans has an optimized version here:
http://git.mansr.com/?p=libjpeg;a=summary
I don't know if he's submitted this to AOSP or not.
This suggests to me that a simple drop-in of libjpeg-turbo might be
actually easy to do, and that there is probably a significant
performance benefit to be achieved. One thing to keep in mind is that
this code still supports armv6, so we'd probably want to preserve that.
Thanks!
--
Christian Robottom Reis, Engineering VP
Brazil (GMT-3) | [+55] 16 9112 6430 | [+1] 612 216 4935
Linaro.org: Open Source Software for ARM SoCs
I've started on some basic documentation for LAVA at
https://wiki.linaro.org/Platform/Validation/LAVA/Documentation
This is mostly aimed at those who are trying to set it up for themselves, or
get started on development for it. However I'm also starting to cover
example jobs, and will expand that section further to list the available
actions and the parameters they can take. It's a wiki, so feel free to add
to it, or let me know if there's a particular section you have questions
about and want to see expanded sooner.
Thanks,
Paul Larson
Dear ARM fans,
Linaro Developer Platform team organises every week (Wednesday 14:00 -
18:00 UTC) an ARM porting Jam. The idea is to gather all developers together to
fix userspace portability issues across the board. The list of bugs
being worked on
is at launchpad:
https://bugs.launchpad.net/ubuntu/+bugs?field.tag=arm-porting-queue&orderby…
Interested in making the software in Ubuntu run better on ARM? Join us on
the #linaro channel on irc.linaro.org right now!
Cheers,
Riku
Enclosed you'll find a link to the agenda, notes and actions from the
Linaro Developer Platforms Weekly Status meeting held on June 23rd
in #linaro-meeting on irc.freenode.net at 14:00 UTC.
https://wiki.linaro.org/Platform/DevPlatform/Meetings/2011-06-23
New Actions:
* everybody to go over joey's monthly milestones presentation
* rsalveti to move the stand-up meeting discussion to email, trying
to get more input from others and see if we could try a different
process than email
* start the linaro evaluation for the linaro dev platform team
--
Regards,
Tom
"We want great men who, when fortune frowns will not be discouraged."
- Colonel Henry Knox
Linaro.org │ Open source software for ARM SoCs
w) tom.gall att linaro.org
w) tom_gall att vnet.ibm.com
h) tom_gall att mac.com
== Key Points for wider discussion ==
* Android LEB is almost done
* Pushing to AOSP
== Team Highlights ==
* Started weekly WG and LT integration meetings
* Helped debug SGX issue
* Continued SPDX work
* Almost finished with Pandroid build
* LAVA Gtk+ published
* AOSP contribution: https://review.source.android.com//#change,23997
* AOSP contribution: https://review.source.android.com//#change,23998
* Tried snowball community distro: Unable to boot
* Frans and Bernhard coming onboard
== Risks / Issues ==
* Staff
* Licensing
== Miscellaneous ==
* New starters: Frans Gifford, Bernhard Rosenkränzer