linux/drivers/base/arch_topology.c

542 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Arch specific cpu topology information
*
* Copyright (C) 2016, ARM Ltd.
* Written by: Juri Lelli, ARM Ltd.
*/
#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>
#include <linux/cpuset.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/smp.h>
DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
unsigned long max_freq)
{
unsigned long scale;
int i;
scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq;
for_each_cpu(i, cpus)
per_cpu(freq_scale, i) = scale;
}
DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
void topology_set_cpu_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", topology_get_cpu_scale(cpu->dev.id));
}
static void update_topology_flags_workfn(struct work_struct *work);
static DECLARE_WORK(update_topology_flags_work, update_topology_flags_workfn);
arch_topology: Make cpu_capacity sysfs node as read-only If user updates any cpu's cpu_capacity, then the new value is going to be applied to all its online sibling cpus. But this need not to be correct always, as sibling cpus (in ARM, same micro architecture cpus) would have different cpu_capacity with different performance characteristics. So, updating the user supplied cpu_capacity to all cpu siblings is not correct. And another problem is, current code assumes that 'all cpus in a cluster or with same package_id (core_siblings), would have same cpu_capacity'. But with commit '5bdd2b3f0f8 ("arm64: topology: add support to remove cpu topology sibling masks")', when a cpu hotplugged out, the cpu information gets cleared in its sibling cpus. So, user supplied cpu_capacity would be applied to only online sibling cpus at the time. After that, if any cpu hotplugged in, it would have different cpu_capacity than its siblings, which breaks the above assumption. So, instead of mucking around the core sibling mask for user supplied value, use device-tree to set cpu capacity. And make the cpu_capacity node as read-only to know the asymmetry between cpus in the system. While at it, remove cpu_scale_mutex usage, which used for sysfs write protection. Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Quentin Perret <quentin.perret@arm.com> Reviewed-by: Quentin Perret <quentin.perret@arm.com> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Lingutla Chandrasekhar <clingutla@codeaurora.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-04-01 06:24:41 +02:00
static DEVICE_ATTR_RO(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 int update_topology;
int topology_update_cpu_topology(void)
{
return update_topology;
}
/*
* Updating the sched_domains can't be done directly from cpufreq callbacks
* due to locking, so queue the work for later.
*/
static void update_topology_flags_workfn(struct work_struct *work)
{
update_topology = 1;
rebuild_sched_domains();
pr_debug("sched_domain hierarchy rebuilt, flags updated\n");
update_topology = 0;
}
static u32 capacity_scale;
static u32 *raw_capacity;
static int free_raw_capacity(void)
{
kfree(raw_capacity);
raw_capacity = NULL;
return 0;
}
void topology_normalize_cpu_scale(void)
{
u64 capacity;
int cpu;
if (!raw_capacity)
return;
pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
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;
topology_set_cpu_scale(cpu, capacity);
pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
cpu, topology_get_cpu_scale(cpu));
}
}
bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
{
static bool cap_parsing_failed;
int ret;
u32 cpu_capacity;
if (cap_parsing_failed)
return false;
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) {
cap_parsing_failed = true;
return false;
}
}
capacity_scale = max(cpu_capacity, capacity_scale);
raw_capacity[cpu] = cpu_capacity;
pr_debug("cpu_capacity: %pOF cpu_capacity=%u (raw)\n",
cpu_node, raw_capacity[cpu]);
} else {
if (raw_capacity) {
pr_err("cpu_capacity: missing %pOF raw capacity\n",
cpu_node);
pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
}
cap_parsing_failed = true;
free_raw_capacity();
}
return !ret;
}
#ifdef CONFIG_CPU_FREQ
Revert "base: arch_topology: fix section mismatch build warnings" This reverts commit 452562abb5b7 ("base: arch_topology: fix section mismatch build warnings"). It causes the notifier call hangs in some use-cases. In some cases with using maxcpus, some of cpus are booted first and then the remaining cpus are booted. As an example, some users who want to realize fast boot up often use the following procedure. 1) Define all CPUs on device tree (CA57x4 + CA53x4) 2) Add "maxcpus=4" in bootargs 3) Kernel boot up with CA57x4 4) After kernel boot up, CA53x4 is booted from user When kernel init was finished, CPUFREQ_POLICY_NOTIFIER was not still unregisterd. This means that "__init init_cpu_capacity_callback()" will be called after kernel init sequence. To avoid this problem, it needs to remove __init{,data} annotations by reverting this commit. Also, this commit was needed to fix kernel compile issue below. However, this issue was also fixed by another patch: commit 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") in v4.15 as well. Whereas commit 452562abb5b7 added all the missing __init annotations, commit 82d8ba717ccb removed it from free_raw_capacity(). WARNING: vmlinux.o(.text+0x548f24): Section mismatch in reference from the function init_cpu_capacity_callback() to the variable .init.text:$x The function init_cpu_capacity_callback() references the variable __init $x. This is often because init_cpu_capacity_callback lacks a __init annotation or the annotation of $x is wrong. Fixes: 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") Cc: stable <stable@vger.kernel.org> Signed-off-by: Gaku Inami <gaku.inami.xh@renesas.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-13 03:06:40 +01:00
static cpumask_var_t cpus_to_visit;
static void parsing_done_workfn(struct work_struct *work);
static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
Revert "base: arch_topology: fix section mismatch build warnings" This reverts commit 452562abb5b7 ("base: arch_topology: fix section mismatch build warnings"). It causes the notifier call hangs in some use-cases. In some cases with using maxcpus, some of cpus are booted first and then the remaining cpus are booted. As an example, some users who want to realize fast boot up often use the following procedure. 1) Define all CPUs on device tree (CA57x4 + CA53x4) 2) Add "maxcpus=4" in bootargs 3) Kernel boot up with CA57x4 4) After kernel boot up, CA53x4 is booted from user When kernel init was finished, CPUFREQ_POLICY_NOTIFIER was not still unregisterd. This means that "__init init_cpu_capacity_callback()" will be called after kernel init sequence. To avoid this problem, it needs to remove __init{,data} annotations by reverting this commit. Also, this commit was needed to fix kernel compile issue below. However, this issue was also fixed by another patch: commit 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") in v4.15 as well. Whereas commit 452562abb5b7 added all the missing __init annotations, commit 82d8ba717ccb removed it from free_raw_capacity(). WARNING: vmlinux.o(.text+0x548f24): Section mismatch in reference from the function init_cpu_capacity_callback() to the variable .init.text:$x The function init_cpu_capacity_callback() references the variable __init $x. This is often because init_cpu_capacity_callback lacks a __init annotation or the annotation of $x is wrong. Fixes: 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") Cc: stable <stable@vger.kernel.org> Signed-off-by: Gaku Inami <gaku.inami.xh@renesas.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-13 03:06:40 +01:00
static int
init_cpu_capacity_callback(struct notifier_block *nb,
unsigned long val,
void *data)
{
struct cpufreq_policy *policy = data;
int cpu;
if (!raw_capacity)
return 0;
if (val != CPUFREQ_CREATE_POLICY)
return 0;
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] = topology_get_cpu_scale(cpu) *
policy->cpuinfo.max_freq / 1000UL;
capacity_scale = max(raw_capacity[cpu], capacity_scale);
}
if (cpumask_empty(cpus_to_visit)) {
topology_normalize_cpu_scale();
schedule_work(&update_topology_flags_work);
free_raw_capacity();
pr_debug("cpu_capacity: parsing done\n");
schedule_work(&parsing_done_work);
}
return 0;
}
Revert "base: arch_topology: fix section mismatch build warnings" This reverts commit 452562abb5b7 ("base: arch_topology: fix section mismatch build warnings"). It causes the notifier call hangs in some use-cases. In some cases with using maxcpus, some of cpus are booted first and then the remaining cpus are booted. As an example, some users who want to realize fast boot up often use the following procedure. 1) Define all CPUs on device tree (CA57x4 + CA53x4) 2) Add "maxcpus=4" in bootargs 3) Kernel boot up with CA57x4 4) After kernel boot up, CA53x4 is booted from user When kernel init was finished, CPUFREQ_POLICY_NOTIFIER was not still unregisterd. This means that "__init init_cpu_capacity_callback()" will be called after kernel init sequence. To avoid this problem, it needs to remove __init{,data} annotations by reverting this commit. Also, this commit was needed to fix kernel compile issue below. However, this issue was also fixed by another patch: commit 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") in v4.15 as well. Whereas commit 452562abb5b7 added all the missing __init annotations, commit 82d8ba717ccb removed it from free_raw_capacity(). WARNING: vmlinux.o(.text+0x548f24): Section mismatch in reference from the function init_cpu_capacity_callback() to the variable .init.text:$x The function init_cpu_capacity_callback() references the variable __init $x. This is often because init_cpu_capacity_callback lacks a __init annotation or the annotation of $x is wrong. Fixes: 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") Cc: stable <stable@vger.kernel.org> Signed-off-by: Gaku Inami <gaku.inami.xh@renesas.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-13 03:06:40 +01:00
static struct notifier_block init_cpu_capacity_notifier = {
.notifier_call = init_cpu_capacity_callback,
};
static int __init register_cpufreq_notifier(void)
{
int ret;
/*
* 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 || !raw_capacity)
return -EINVAL;
if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL))
return -ENOMEM;
cpumask_copy(cpus_to_visit, cpu_possible_mask);
ret = cpufreq_register_notifier(&init_cpu_capacity_notifier,
CPUFREQ_POLICY_NOTIFIER);
if (ret)
free_cpumask_var(cpus_to_visit);
return ret;
}
core_initcall(register_cpufreq_notifier);
Revert "base: arch_topology: fix section mismatch build warnings" This reverts commit 452562abb5b7 ("base: arch_topology: fix section mismatch build warnings"). It causes the notifier call hangs in some use-cases. In some cases with using maxcpus, some of cpus are booted first and then the remaining cpus are booted. As an example, some users who want to realize fast boot up often use the following procedure. 1) Define all CPUs on device tree (CA57x4 + CA53x4) 2) Add "maxcpus=4" in bootargs 3) Kernel boot up with CA57x4 4) After kernel boot up, CA53x4 is booted from user When kernel init was finished, CPUFREQ_POLICY_NOTIFIER was not still unregisterd. This means that "__init init_cpu_capacity_callback()" will be called after kernel init sequence. To avoid this problem, it needs to remove __init{,data} annotations by reverting this commit. Also, this commit was needed to fix kernel compile issue below. However, this issue was also fixed by another patch: commit 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") in v4.15 as well. Whereas commit 452562abb5b7 added all the missing __init annotations, commit 82d8ba717ccb removed it from free_raw_capacity(). WARNING: vmlinux.o(.text+0x548f24): Section mismatch in reference from the function init_cpu_capacity_callback() to the variable .init.text:$x The function init_cpu_capacity_callback() references the variable __init $x. This is often because init_cpu_capacity_callback lacks a __init annotation or the annotation of $x is wrong. Fixes: 82d8ba717ccb ("arch_topology: Fix section miss match warning due to free_raw_capacity()") Cc: stable <stable@vger.kernel.org> Signed-off-by: Gaku Inami <gaku.inami.xh@renesas.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Acked-by: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-02-13 03:06:40 +01:00
static void parsing_done_workfn(struct work_struct *work)
{
cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
CPUFREQ_POLICY_NOTIFIER);
free_cpumask_var(cpus_to_visit);
}
#else
core_initcall(free_raw_capacity);
#endif
#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
static int __init get_cpu_for_node(struct device_node *node)
{
struct device_node *cpu_node;
int cpu;
cpu_node = of_parse_phandle(node, "cpu", 0);
if (!cpu_node)
return -1;
cpu = of_cpu_node_to_id(cpu_node);
if (cpu >= 0)
topology_parse_cpu_capacity(cpu_node, cpu);
else
pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
of_node_put(cpu_node);
return cpu;
}
static int __init parse_core(struct device_node *core, int package_id,
int core_id)
{
char name[20];
bool leaf = true;
int i = 0;
int cpu;
struct device_node *t;
do {
snprintf(name, sizeof(name), "thread%d", i);
t = of_get_child_by_name(core, name);
if (t) {
leaf = false;
cpu = get_cpu_for_node(t);
if (cpu >= 0) {
cpu_topology[cpu].package_id = package_id;
cpu_topology[cpu].core_id = core_id;
cpu_topology[cpu].thread_id = i;
} else {
pr_err("%pOF: Can't get CPU for thread\n",
t);
of_node_put(t);
return -EINVAL;
}
of_node_put(t);
}
i++;
} while (t);
cpu = get_cpu_for_node(core);
if (cpu >= 0) {
if (!leaf) {
pr_err("%pOF: Core has both threads and CPU\n",
core);
return -EINVAL;
}
cpu_topology[cpu].package_id = package_id;
cpu_topology[cpu].core_id = core_id;
} else if (leaf) {
pr_err("%pOF: Can't get CPU for leaf core\n", core);
return -EINVAL;
}
return 0;
}
static int __init parse_cluster(struct device_node *cluster, int depth)
{
char name[20];
bool leaf = true;
bool has_cores = false;
struct device_node *c;
static int package_id __initdata;
int core_id = 0;
int i, ret;
/*
* 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) {
leaf = false;
ret = parse_cluster(c, depth + 1);
of_node_put(c);
if (ret != 0)
return ret;
}
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("%pOF: cpu-map children should be clusters\n",
c);
of_node_put(c);
return -EINVAL;
}
if (leaf) {
ret = parse_core(c, package_id, core_id++);
} else {
pr_err("%pOF: Non-leaf cluster with core %s\n",
cluster, name);
ret = -EINVAL;
}
of_node_put(c);
if (ret != 0)
return ret;
}
i++;
} while (c);
if (leaf && !has_cores)
pr_warn("%pOF: empty cluster\n", cluster);
if (leaf)
package_id++;
return 0;
}
static int __init parse_dt_topology(void)
{
struct device_node *cn, *map;
int ret = 0;
int cpu;
cn = of_find_node_by_path("/cpus");
if (!cn) {
pr_err("No CPU information found in DT\n");
return 0;
}
/*
* When topology is provided cpu-map is essentially a root
* cluster with restricted subnodes.
*/
map = of_get_child_by_name(cn, "cpu-map");
if (!map)
goto out;
ret = parse_cluster(map, 0);
if (ret != 0)
goto out_map;
topology_normalize_cpu_scale();
/*
* Check that all cores are in the topology; the SMP code will
* only mark cores described in the DT as possible.
*/
for_each_possible_cpu(cpu)
if (cpu_topology[cpu].package_id == -1)
ret = -EINVAL;
out_map:
of_node_put(map);
out:
of_node_put(cn);
return ret;
}
#endif
/*
* cpu topology table
*/
struct cpu_topology cpu_topology[NR_CPUS];
EXPORT_SYMBOL_GPL(cpu_topology);
const struct cpumask *cpu_coregroup_mask(int cpu)
{
const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
/* Find the smaller of NUMA, core or LLC siblings */
if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
/* not numa in package, lets use the package siblings */
core_mask = &cpu_topology[cpu].core_sibling;
}
if (cpu_topology[cpu].llc_id != -1) {
if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
core_mask = &cpu_topology[cpu].llc_sibling;
}
return core_mask;
}
void update_siblings_masks(unsigned int cpuid)
{
struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
int cpu;
/* update core and thread sibling masks */
for_each_online_cpu(cpu) {
cpu_topo = &cpu_topology[cpu];
if (cpuid_topo->llc_id == cpu_topo->llc_id) {
cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
}
if (cpuid_topo->package_id != cpu_topo->package_id)
continue;
cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
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);
cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
}
}
static void clear_cpu_topology(int cpu)
{
struct cpu_topology *cpu_topo = &cpu_topology[cpu];
cpumask_clear(&cpu_topo->llc_sibling);
cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
cpumask_clear(&cpu_topo->core_sibling);
cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
cpumask_clear(&cpu_topo->thread_sibling);
cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
}
void __init reset_cpu_topology(void)
{
unsigned int cpu;
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->package_id = -1;
cpu_topo->llc_id = -1;
clear_cpu_topology(cpu);
}
}
void remove_cpu_topology(unsigned int cpu)
{
int sibling;
for_each_cpu(sibling, topology_core_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
for_each_cpu(sibling, topology_sibling_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
for_each_cpu(sibling, topology_llc_cpumask(cpu))
cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
clear_cpu_topology(cpu);
}
__weak int __init parse_acpi_topology(void)
{
return 0;
}
#if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
void __init init_cpu_topology(void)
{
reset_cpu_topology();
/*
* Discard anything that was parsed if we hit an error so we
* don't use partial information.
*/
if (parse_acpi_topology())
reset_cpu_topology();
else if (of_have_populated_dt() && parse_dt_topology())
reset_cpu_topology();
}
#endif