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.
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 something simple and basic.
A following patch will implement support for parsing the DT topology bindings for ARM, similar patches will be needed for ACPI.
Signed-off-by: Mark Brown broonie@linaro.org --- arch/arm64/Kconfig | 24 ++++++++++ arch/arm64/include/asm/topology.h | 39 +++++++++++++++++ arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/smp.c | 12 +++++ arch/arm64/kernel/topology.c | 92 +++++++++++++++++++++++++++++++++++++++ 5 files changed, 168 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 249acb9da4e3..a53514cdf39c 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -162,6 +162,30 @@ config SMP
If you don't know what to do here, say N.
+config ARM_CPU_TOPOLOGY + bool "Support CPU topology definition" + depends on SMP + default y + help + Support CPU topology definition, based on configuration + provided by the firmware. + +config 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 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 000000000000..58b8b84adcd2 --- /dev/null +++ b/arch/arm64/include/asm/topology.h @@ -0,0 +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(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 1cd339d5037b..b2fe6ba97080 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -19,6 +19,7 @@ arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o +arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o
obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 1b7617ab499b..40e20efc13e6 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 __cpuinit smp_store_cpu_info(unsigned int cpuid) +{ + store_cpu_topology(cpuid); +} + /* * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. @@ -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 +398,11 @@ 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 000000000000..853544f30a8b --- /dev/null +++ b/arch/arm64/kernel/topology.c @@ -0,0 +1,92 @@ +/* + * arch/arm64/kernel/topology.c + * + * Copyright (C) 2011,2013 Linaro Limited. + * + * Based on the arm32 version written by Vincent Guittot in turn based on + * arch/sh/kernel/topology.c + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/topology.h> + +/* + * cpu topology table + */ +struct cputopo_arm cpu_topology[NR_CPUS]; +EXPORT_SYMBOL_GPL(cpu_topology); + +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_sibling; +} + +static void update_siblings_masks(unsigned int cpuid) +{ + struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int cpu; + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id != cpu_topo->socket_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id != cpu_topo->core_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); + } + smp_wmb(); +} + +void store_cpu_topology(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + + /* DT should have been parsed by the time we get here */ + if (cpuid_topo->core_id == -1) + pr_info("CPU%u: No topology information configured\n", cpuid); + else + update_siblings_masks(cpuid); +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void __init init_cpu_topology(void) +{ + unsigned int cpu; + + /* init core mask and power*/ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); + + cpu_topo->thread_id = -1; + cpu_topo->core_id = -1; + cpu_topo->socket_id = -1; + cpumask_clear(&cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + } + smp_wmb(); +}
From: Mark Brown broonie@linaro.org
Add support for parsing the explicit topology bindings to discover the topology of the system.
Since it is not currently clear how to map multi-level clusters for the scheduler all leaf clusters are presented to the scheduler at the same level. This should be enough to provide good support for current systems.
Signed-off-by: Mark Brown broonie@linaro.org ---
This doesn't actually ignore CPUs in the root cpu-map, merely warns about them. After looking at ignoring them it seemed like a more sensible thing to just shove them in a separate cluster for now - giving the scheduler information about only some of the cores seemed like it was asking for trouble and trying to do anything more active seems like a lot of work to unsupport broken systems (if you see what I mean). I would expect that the end result of putting them in a cluster is going to be about the same as not providing information anyway.
It seems like if this isn't enough then either disabling the affected CPUs entirely or making the warnings louder is the way forwards.
arch/arm64/kernel/topology.c | 149 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 149 insertions(+)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 853544f30a8b..e77c6b0844be 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -17,11 +17,157 @@ #include <linux/percpu.h> #include <linux/node.h> #include <linux/nodemask.h> +#include <linux/of.h> #include <linux/sched.h> #include <linux/slab.h>
#include <asm/topology.h>
+#ifdef CONFIG_OF +static int cluster_id; + +static int __init get_cpu_for_node(struct device_node *node) +{ + struct device_node *cpu_node; + int cpu; + + cpu_node = of_parse_phandle(node, "cpu", 0); + if (!cpu_node) { + pr_crit("%s: Unable to parse CPU phandle\n", node->full_name); + return -1; + } + + for_each_possible_cpu(cpu) { + if (of_get_cpu_node(cpu, NULL) == cpu_node) + return cpu; + } + + pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name); + return -1; +} + +static void __init parse_core(struct device_node *core, int core_id) +{ + char name[10]; + bool leaf = true; + int i, cpu; + struct device_node *t; + + i = 0; + do { + snprintf(name, sizeof(name), "thread%d", i); + t = of_get_child_by_name(core, name); + if (t) { + leaf = false; + cpu = get_cpu_for_node(t); + if (cpu >= 0) { + pr_info("CPU%d: socket %d core %d thread %d\n", + cpu, cluster_id, core_id, i); + cpu_topology[cpu].socket_id = cluster_id; + cpu_topology[cpu].core_id = core_id; + cpu_topology[cpu].thread_id = i; + } else { + pr_err("%s: Can't get CPU for thread\n", + t->full_name); + } + } + i++; + } while (t); + + cpu = get_cpu_for_node(core); + if (cpu >= 0) { + if (!leaf) { + pr_err("%s: Core has both threads and CPU\n", + core->full_name); + return; + } + + pr_info("CPU%d: socket %d core %d\n", + cpu, cluster_id, core_id); + cpu_topology[cpu].socket_id = cluster_id; + cpu_topology[cpu].core_id = core_id; + } else if (leaf) { + pr_err("%s: Can't get CPU for leaf core\n", core->full_name); + } +} + +static void __init parse_cluster(struct device_node *cluster, int depth) +{ + char name[10]; + bool leaf = true; + bool has_cores = false; + struct device_node *c; + int core_id = 0; + int i; + + /* + * First check for child clusters; we currently ignore any + * information about the nesting of clusters and present the + * scheduler with a flat list of them. + */ + i = 0; + do { + snprintf(name, sizeof(name), "cluster%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + parse_cluster(c, depth + 1); + leaf = false; + } + i++; + } while (c); + + /* Now check for cores */ + i = 0; + do { + snprintf(name, sizeof(name), "core%d", i); + c = of_get_child_by_name(cluster, name); + if (c) { + has_cores = true; + + if (depth == 0) + pr_err("%s: cpu-map children should be clusters\n", + c->full_name); + + if (leaf) + parse_core(c, core_id++); + else + pr_err("%s: Non-leaf cluster with core %s\n", + cluster->full_name, name); + } + i++; + } while (c); + + if (leaf && !has_cores) + pr_warn("%s: empty cluster\n", cluster->full_name); + + if (leaf) + cluster_id++; +} + +static void __init parse_dt_topology(void) +{ + struct device_node *cn; + + cn = of_find_node_by_path("/cpus"); + if (!cn) { + pr_err("No CPU information found in DT\n"); + return; + } + + /* + * If topology is provided as a cpu-map it is essentially a + * root cluster. + */ + cn = of_find_node_by_name(cn, "cpu-map"); + if (!cn) + return; + parse_cluster(cn, 0); +} + +#else +static inline void parse_dt_topology(void) {} +#endif + /* * cpu topology table */ @@ -88,5 +234,8 @@ void __init init_cpu_topology(void) cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); } + + parse_dt_topology(); + smp_wmb(); }
On Wed, Jan 08, 2014 at 05:10:11PM +0000, Mark Brown wrote:
From: Mark Brown broonie@linaro.org
Add support for parsing the explicit topology bindings to discover the topology of the system.
Since it is not currently clear how to map multi-level clusters for the scheduler all leaf clusters are presented to the scheduler at the same level. This should be enough to provide good support for current systems.
Signed-off-by: Mark Brown broonie@linaro.org
This doesn't actually ignore CPUs in the root cpu-map, merely warns about them. After looking at ignoring them it seemed like a more sensible thing to just shove them in a separate cluster for now - giving the scheduler information about only some of the cores seemed like it was asking for trouble and trying to do anything more active seems like a lot of work to unsupport broken systems (if you see what I mean). I would expect that the end result of putting them in a cluster is going to be about the same as not providing information anyway.
It seems like if this isn't enough then either disabling the affected CPUs entirely or making the warnings louder is the way forwards.
Well, there are so many corner cases (eg duplicated CPUs might be another one - should we track that ? It is probably something worth warning on, you check before initializing a cpu struct if it has already been initialized) that they are hard to track. What you did makes sense to me at first glance.
arch/arm64/kernel/topology.c | 149 +++++++++++++++++++++++++++++++++++++++++++ +static void __init parse_cluster(struct device_node *cluster, int depth)
Is it really worth adding a depth parameter just for cpu-map ? Can't we check the node name ? Either way is fine by me, just flagging this up.
+{
- char name[10];
- bool leaf = true;
- bool has_cores = false;
- struct device_node *c;
- int core_id = 0;
- int i;
- /*
* First check for child clusters; we currently ignore any* information about the nesting of clusters and present the* scheduler with a flat list of them.*/- i = 0;
- do {
snprintf(name, sizeof(name), "cluster%d", i);c = of_get_child_by_name(cluster, name);if (c) {parse_cluster(c, depth + 1);leaf = false;}i++;- } while (c);
- /* Now check for cores */
- i = 0;
- do {
snprintf(name, sizeof(name), "core%d", i);c = of_get_child_by_name(cluster, name);if (c) {has_cores = true;if (depth == 0)pr_err("%s: cpu-map children should be clusters\n",c->full_name);if (leaf)parse_core(c, core_id++);elsepr_err("%s: Non-leaf cluster with core %s\n",cluster->full_name, name);}i++;- } while (c);
- if (leaf && !has_cores)
pr_warn("%s: empty cluster\n", cluster->full_name);- if (leaf)
cluster_id++;
We increment cluster_id even for leaf clusters with no cores, it is probably safe to do it given that cluster id are completely arbitrary numbers, just wanted to mention that.
+}
+static void __init parse_dt_topology(void) +{
- struct device_node *cn;
- cn = of_find_node_by_path("/cpus");
- if (!cn) {
pr_err("No CPU information found in DT\n");return;- }
- /*
* If topology is provided as a cpu-map it is essentially a* root cluster.*/- cn = of_find_node_by_name(cn, "cpu-map");
- if (!cn)
return;- parse_cluster(cn, 0);
You could loop through cluster children here, but I understand you want to avoid copying the sprintf variables and code here too just to check for cluster children, so it is fine to leave code as it is (probably we can remove the depth parameter too).
Lorenzo
On Wed, Jan 08, 2014 at 06:23:31PM +0000, Lorenzo Pieralisi wrote:
This doesn't actually ignore CPUs in the root cpu-map, merely warns about them. After looking at ignoring them it seemed like a more sensible thing to just shove them in a separate cluster for now - giving the scheduler information about only some of the cores seemed like it was asking for trouble and trying to do anything more active seems like a lot of work to unsupport broken systems (if you see what I mean). I would expect that the end result of putting them in a cluster is going to be about the same as not providing information anyway.
It seems like if this isn't enough then either disabling the affected CPUs entirely or making the warnings louder is the way forwards.
Well, there are so many corner cases (eg duplicated CPUs might be another one - should we track that ? It is probably something worth warning on, you check before initializing a cpu struct if it has already been initialized) that they are hard to track. What you did makes sense to me at first glance.
Yes, there's definitely scope for improving the robustness. On the other hand I'm sure all device tree authors are dilligent and careful so there's no need for us to worry! :P
arch/arm64/kernel/topology.c | 149 +++++++++++++++++++++++++++++++++++++++++++ +static void __init parse_cluster(struct device_node *cluster, int depth)
Is it really worth adding a depth parameter just for cpu-map ? Can't we check the node name ? Either way is fine by me, just flagging this up.
It seemed more idiomatic and I suspect we may want the depth in future if we try to tell the scheduler about clusters of clusters. It's certainly easier to leave the code as is now I've written it this way if nothing else.
- if (leaf)
cluster_id++;
We increment cluster_id even for leaf clusters with no cores, it is probably safe to do it given that cluster id are completely arbitrary numbers, just wanted to mention that.
Right, my thoughts exactly - this is the simplest thing I thought of.
From: Mark Brown broonie@linaro.org
In non-heterogeneous systems like big.LITTLE systems the scheduler will be able to make better use of the available cores if we provide power numbers to it indicating their relative performance. Do this by parsing the CPU nodes in the DT.
This code currently has no effect as no information on the relative performance of the cores is provided.
Signed-off-by: Mark Brown broonie@linaro.org --- arch/arm64/kernel/topology.c | 145 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 145 insertions(+)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index e77c6b0844be..e5140b03b342 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -23,6 +23,29 @@
#include <asm/topology.h>
+/* + * cpu power table + * This per cpu data structure describes the relative capacity of each core. + * On a heteregenous system, cores don't have the same computation capacity + * and we reflect that difference in the cpu_power field so the scheduler can + * take this difference into account during load balance. A per cpu structure + * is preferred because each CPU updates its own cpu_power field during the + * load balance except for idle cores. One idle core is selected to run the + * rebalance_domains for all idle cores and the cpu_power can be updated + * during this sequence. + */ +static DEFINE_PER_CPU(unsigned long, cpu_scale); + +unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} + +static void set_power_scale(unsigned int cpu, unsigned long power) +{ + per_cpu(cpu_scale, cpu) = power; +} + #ifdef CONFIG_OF static int cluster_id;
@@ -144,9 +167,49 @@ static void __init parse_cluster(struct device_node *cluster, int depth) cluster_id++; }
+struct cpu_efficiency { + const char *compatible; + unsigned long efficiency; +}; + +/* + * Table of relative efficiency of each processors + * The efficiency value must fit in 20bit and the final + * cpu_scale value must be in the range + * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2 + * in order to return at most 1 when DIV_ROUND_CLOSEST + * is used to compute the capacity of a CPU. + * Processors that are not defined in the table, + * use the default SCHED_POWER_SCALE value for cpu_scale. + */ +static const struct cpu_efficiency table_efficiency[] = { + { NULL, }, +}; + +static unsigned long *__cpu_capacity; +#define cpu_capacity(cpu) __cpu_capacity[cpu] + +static unsigned long middle_capacity = 1; + +/* + * Iterate all CPUs' descriptor in DT and compute the efficiency + * (as per table_efficiency). Also calculate a middle efficiency + * as close as possible to (max{eff_i} - min{eff_i}) / 2 + * This is later used to scale the cpu_power field such that an + * 'average' CPU is of middle power. Also see the comments near + * table_efficiency[] and update_cpu_power(). + */ static void __init parse_dt_topology(void) { + const struct cpu_efficiency *cpu_eff; struct device_node *cn; + unsigned long min_capacity = ULONG_MAX; + unsigned long max_capacity = 0; + unsigned long capacity = 0; + int cpu; + + __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity), + GFP_NOWAIT);
cn = of_find_node_by_path("/cpus"); if (!cn) { @@ -162,10 +225,88 @@ static void __init parse_dt_topology(void) if (!cn) return; parse_cluster(cn, 0); + + for_each_possible_cpu(cpu) { + const u32 *rate; + int len; + + /* Too early to use cpu->of_node */ + cn = of_get_cpu_node(cpu, NULL); + if (!cn) { + pr_err("Missing device node for CPU %d\n", cpu); + continue; + } + + /* check if the cpu is marked as "disabled", if so ignore */ + if (!of_device_is_available(cn)) + continue; + + for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) + if (of_device_is_compatible(cn, cpu_eff->compatible)) + break; + + if (cpu_eff->compatible == NULL) { + pr_warn("%s: Unknown CPU type\n", cn->full_name); + continue; + } + + rate = of_get_property(cn, "clock-frequency", &len); + if (!rate || len != 4) { + pr_err("%s: Missing clock-frequency property\n", + cn->full_name); + continue; + } + + capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency; + + /* Save min capacity of the system */ + if (capacity < min_capacity) + min_capacity = capacity; + + /* Save max capacity of the system */ + if (capacity > max_capacity) + max_capacity = capacity; + + cpu_capacity(cpu) = capacity; + } + + /* If min and max capacities are equal we bypass the update of the + * cpu_scale because all CPUs have the same capacity. Otherwise, we + * compute a middle_capacity factor that will ensure that the capacity + * of an 'average' CPU of the system will be as close as possible to + * SCHED_POWER_SCALE, which is the default value, but with the + * constraint explained near table_efficiency[]. + */ + if (min_capacity == max_capacity) + return; + else if (4 * max_capacity < (3 * (max_capacity + min_capacity))) + middle_capacity = (min_capacity + max_capacity) + >> (SCHED_POWER_SHIFT+1); + else + middle_capacity = ((max_capacity / 3) + >> (SCHED_POWER_SHIFT-1)) + 1; + +} + +/* + * Look for a customed capacity of a CPU in the cpu_topo_data table during the + * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the + * function returns directly for SMP system. + */ +static void update_cpu_power(unsigned int cpu) +{ + if (!cpu_capacity(cpu)) + return; + + set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); + + pr_info("CPU%u: update cpu_power %lu\n", + cpu, arch_scale_freq_power(NULL, cpu)); }
#else static inline void parse_dt_topology(void) {} +static inline void update_cpu_power(unsigned int cpuid) {} #endif
/* @@ -214,6 +355,8 @@ void store_cpu_topology(unsigned int cpuid) pr_info("CPU%u: No topology information configured\n", cpuid); else update_siblings_masks(cpuid); + + update_cpu_power(cpuid); }
/* @@ -233,6 +376,8 @@ void __init init_cpu_topology(void) cpu_topo->socket_id = -1; cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); + + set_power_scale(cpu, SCHED_POWER_SCALE); }
parse_dt_topology();
On Wed, Jan 08, 2014 at 05:10:12PM +0000, Mark Brown wrote:
From: Mark Brown broonie@linaro.org
[...]
/* check if the cpu is marked as "disabled", if so ignore */if (!of_device_is_available(cn))continue;
This check must go. As I mentioned, either we define what this means properly or to me the status property of cpu nodes must not be relied upon on ARM.
I can add a patch on top of your series that defines the behaviour for both arm32 and arm64 when we reach agreement and code initializing cpu_logical_map should be patched as well, accordingly.
Lorenzo
On Wed, Jan 08, 2014 at 06:39:39PM +0000, Lorenzo Pieralisi wrote:
On Wed, Jan 08, 2014 at 05:10:12PM +0000, Mark Brown wrote:
From: Mark Brown broonie@linaro.org
/* check if the cpu is marked as "disabled", if so ignore */if (!of_device_is_available(cn))continue;
This check must go. As I mentioned, either we define what this means properly or to me the status property of cpu nodes must not be relied upon on ARM.
Meh, sorry - forgot to squash in that patch.
From: Mark Brown broonie@linaro.org
Provide performance numbers to the scheduler to help it fill the cores in the system on big.LITTLE systems. With the current scheduler this may perform poorly for applications that try to do OpenMP style work over all cores but should help for more common workloads.
The power numbers are the same as for ARMv7 since it seems that the expected differential between the big and little cores is very similar on both ARMv7 and ARMv8. These numbers are just an initial and basic approximation for use with the current scheduler, it is likely that both experience with silicon and ongoing work on improving the scheduler will lead to further tuning. In both ARMv7 and ARMv8 cases the numbers were based on the published DMIPS numbers.
Signed-off-by: Mark Brown broonie@linaro.org --- arch/arm64/kernel/topology.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index e5140b03b342..869aeaff02dc 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -183,6 +183,8 @@ struct cpu_efficiency { * use the default SCHED_POWER_SCALE value for cpu_scale. */ static const struct cpu_efficiency table_efficiency[] = { + { "arm,cortex-a57", 3891 }, + { "arm,cortex-a53", 2048 }, { NULL, }, };
On Wed, Jan 08, 2014 at 05:10:10PM +0000, Mark Brown wrote:
[...]
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c new file mode 100644 index 000000000000..853544f30a8b --- /dev/null +++ b/arch/arm64/kernel/topology.c @@ -0,0 +1,92 @@ +/*
- arch/arm64/kernel/topology.c
- Copyright (C) 2011,2013 Linaro Limited.
- Based on the arm32 version written by Vincent Guittot in turn based on
- arch/sh/kernel/topology.c
- This file is subject to the terms and conditions of the GNU General Public
- License. See the file "COPYING" in the main directory of this archive
- for more details.
- */
+#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/sched.h> +#include <linux/slab.h>
Nitpick, <linux/slab.h> does not belong in this patch. There are other includes that should be moved to the respective patch (percpu.h ?) where they are actually used.
Lorenzo
On Wed, Jan 08, 2014 at 06:30:06PM +0000, Lorenzo Pieralisi wrote:
On Wed, Jan 08, 2014 at 05:10:10PM +0000, Mark Brown wrote:
+#include <linux/slab.h>
Nitpick, <linux/slab.h> does not belong in this patch. There are other includes that should be moved to the respective patch (percpu.h ?) where they are actually used.
I can move this one but honestly I'm having an extremely difficult time summoning up the enthusiasm for looking for others and moving them - the practical impact will not be substantial.
On Wed, Jan 08, 2014 at 06:40:21PM +0000, Mark Brown wrote:
On Wed, Jan 08, 2014 at 06:30:06PM +0000, Lorenzo Pieralisi wrote:
On Wed, Jan 08, 2014 at 05:10:10PM +0000, Mark Brown wrote:
+#include <linux/slab.h>
Nitpick, <linux/slab.h> does not belong in this patch. There are other includes that should be moved to the respective patch (percpu.h ?) where they are actually used.
I can move this one but honestly I'm having an extremely difficult time summoning up the enthusiasm for looking for others and moving them - the practical impact will not be substantial.
Ok, it is your call and I understand I am being pedantic but from a logical patch split perspective that's not correct and honestly it should take no more than few minutes to move the includes where they actually belong.
Lorenzo
linaro-kernel@lists.linaro.org
-
Lorenzo Pieralisi -
Mark Brown