1
0
Fork 0
alistair23-linux/arch/arm64/kernel/topology.c

310 lines
6.7 KiB
C
Raw Normal View History

/*
* 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/arch_topology.h>
#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/of.h>
#include <linux/sched.h>
#include <linux/sched/topology.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>
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[10];
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[10];
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;
}
/*
* 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;
/* update core and thread sibling masks */
for_each_possible_cpu(cpu) {
cpu_topo = &cpu_topology[cpu];
if (cpuid_topo->package_id != cpu_topo->package_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)
{
struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
u64 mpidr;
if (cpuid_topo->package_id != -1)
goto topology_populated;
mpidr = read_cpuid_mpidr();
/* Uniprocessor systems can rely on default topology values */
if (mpidr & MPIDR_UP_BITMASK)
return;
/* Create cpu topology mapping based on MPIDR. */
if (mpidr & MPIDR_MT_BITMASK) {
/* Multiprocessor system : Multi-threads per core */
cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
arm64: topology: Fix handling of multi-level cluster MPIDR-based detection The only requirement the scheduler has on cluster IDs is that they must be unique. When enumerating the topology based on MPIDR information the kernel currently generates cluster IDs by using the first level of affinity above the core ID (either level one or two depending on if the core has multiple threads) however the ARMv8 architecture allows for up to three levels of affinity. This means that an ARMv8 system may contain cores which have MPIDRs identical other than affinity level three which with current code will cause us to report multiple cores with the same identification to the scheduler in violation of its uniqueness requirement. Ensure that we do not violate the scheduler requirements on systems that uses all the affinity levels by incorporating both affinity levels two and three into the cluser ID when the cores are not threaded. While no currently known hardware uses multi-level clusters it is better to program defensively, this will help ease bringup of systems that have them and will ensure that things like distribution install media do not need to be respun to replace kernels in order to deploy such systems. In the worst case the system will work but perform suboptimally until a kernel modified to handle the new topology better is installed, in the best case this will be an adequate description of such topologies for the scheduler to perform well. Signed-off-by: Mark Brown <broonie@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-11-20 17:36:49 -07:00
MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8;
} else {
/* Multiprocessor system : Single-thread per core */
cpuid_topo->thread_id = -1;
cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
arm64: topology: Fix handling of multi-level cluster MPIDR-based detection The only requirement the scheduler has on cluster IDs is that they must be unique. When enumerating the topology based on MPIDR information the kernel currently generates cluster IDs by using the first level of affinity above the core ID (either level one or two depending on if the core has multiple threads) however the ARMv8 architecture allows for up to three levels of affinity. This means that an ARMv8 system may contain cores which have MPIDRs identical other than affinity level three which with current code will cause us to report multiple cores with the same identification to the scheduler in violation of its uniqueness requirement. Ensure that we do not violate the scheduler requirements on systems that uses all the affinity levels by incorporating both affinity levels two and three into the cluser ID when the cores are not threaded. While no currently known hardware uses multi-level clusters it is better to program defensively, this will help ease bringup of systems that have them and will ensure that things like distribution install media do not need to be respun to replace kernels in order to deploy such systems. In the worst case the system will work but perform suboptimally until a kernel modified to handle the new topology better is installed, in the best case this will be an adequate description of such topologies for the scheduler to perform well. Signed-off-by: Mark Brown <broonie@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-11-20 17:36:49 -07:00
MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 |
MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16;
}
pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
cpuid_topo->thread_id, mpidr);
topology_populated:
update_siblings_masks(cpuid);
}
static 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 = 0;
cpu_topo->package_id = -1;
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 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 (of_have_populated_dt() && parse_dt_topology())
reset_cpu_topology();
}