static int __init parse_dt_topology(void)
{
struct device_node *cn, *map;
int ret = 0;
int cpu;
/* (1) 找到dts中cpu topology的根节点"/cpus"" */
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.
*/
/* (2) 找到"cpu-map"节点 */
map = of_get_child_by_name(cn, "cpu-map");
if (!map)
goto out;
/* (3) 解析"cpu-map"中的cluster */
ret = parse_cluster(map, 0);
if (ret != 0)
goto out_map;
/*
* 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].cluster_id == -1)
ret = -EINVAL;
out_map:
of_node_put(map);
out:
of_node_put(cn);
return ret;
}
对应于dts中的文件如下:
cpus {
#address-cells = <2>;
#size-cells = <0>;
cpu-map {
cluster0 {
core0 {
cpu = <&CPU0>;
};
core1 {
cpu = <&CPU1>;
};
core2 {
cpu = <&CPU2>;
};
core3 {
cpu = <&CPU3>;
};
};
cluster1 {
core0 {
cpu = <&CPU4>;
};
core1 {
cpu = <&CPU5>;
};
core2 {
cpu = <&CPU6>;
};
core3 {
cpu = <&CPU7>;
};
};
};
.....}
搜索上面这个dts文件,先解析cluster--->core
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 cluster_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;
/* (3.1) 如果有多级cluster,继续递归搜索 */
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 {
/* (3.2) 或者core层次的节点 */
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);
of_node_put(c);
return -EINVAL;
}
if (leaf) {
/* (3.3) 如果是叶子cluster节点,继续遍历core中的cpu节点 */
ret = parse_core(c, cluster_id, core_id++);
} else {
pr_err("%s: Non-leaf cluster with core %s\n",
cluster->full_name, name);
ret = -EINVAL;
}
of_node_put(c);
if (ret != 0)
return ret;
}
i++;
} while (c);
if (leaf && !has_cores)
pr_warn("%s: empty cluster\n", cluster->full_name);
if (leaf)
cluster_id++;
return 0;
}
再从core解析到cpu
CPU1: cpu@100 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x100>;
enable-method = "psci";
cpu-supply = <&fan53555_dcdc>;
cpufreq-data-v1 = <&cpufreq_clus0>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_0 &CLUSTER_COST_0>;
};
CPU2: cpu@200 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x200>;
enable-method = "psci";
cpu-supply = <&fan53555_dcdc>;
cpufreq-data-v1 = <&cpufreq_clus0>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_0 &CLUSTER_COST_0>;
};
CPU3: cpu@300 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x300>;
enable-method = "psci";
cpu-supply = <&fan53555_dcdc>;
cpufreq-data-v1 = <&cpufreq_clus0>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_0 &CLUSTER_COST_0>;
};
CPU4: cpu@400 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x400>;
enable-method = "psci";
cpu-supply = <&vddcpu>;
cpufreq-data-v1 = <&cpufreq_clus1>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>;
};
CPU5: cpu@500 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x500>;
enable-method = "psci";
cpu-supply = <&vddcpu>;
cpufreq-data-v1 = <&cpufreq_clus1>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>;
};
CPU6: cpu@600 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x600>;
enable-method = "psci";
cpu-supply = <&vddcpu>;
cpufreq-data-v1 = <&cpufreq_clus1>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>;
};
CPU7: cpu@700 {
device_type = "cpu";
compatible = "arm,cortex-a55","arm,armv8";
reg = <0x0 0x700>;
enable-method = "psci";
cpu-supply = <&vddcpu>;
cpufreq-data-v1 = <&cpufreq_clus1>;
cpu-idle-states = <&CORE_PD>;
sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>;
};
};
继续解析cpu层级
static int __init parse_core(struct device_node *core, int cluster_id,
int core_id)
{
char name[10];
bool leaf = true;
int i = 0;
int cpu;
struct device_node *t;
do {
/* (3.3.1) 如果存在thread层级,解析thread和cpu层级 */
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].cluster_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);
of_node_put(t);
return -EINVAL;
}
of_node_put(t);
}
i++;
} while (t);
/* (3.3.2) 否则直接解析cpu层级 */
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 -EINVAL;
}
/* (3.3.3) 得到了cpu的cluster_id/core_id */
cpu_topology[cpu].cluster_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);
return -EINVAL;
}
return 0;
}
这里没有thread层级,所以直接解析cpu层级
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;
for_each_possible_cpu(cpu) {
if (of_get_cpu_node(cpu, NULL) == cpu_node) {
of_node_put(cpu_node);
return cpu;
}
}
pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
of_node_put(cpu_node);
return -1;
}
生成的外部节点信息
1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
physical package id of cpuX. Typically corresponds to a physical
socket number, but the actual value is architecture and platform
dependent.
2) /sys/devices/system/cpu/cpuX/topology/core_id:
the CPU core ID of cpuX. Typically it is the hardware platform's
identifier (rather than the kernel's). The actual value is
architecture and platform dependent.
3) /sys/devices/system/cpu/cpuX/topology/book_id:
the book ID of cpuX. Typically it is the hardware platform's
identifier (rather than the kernel's). The actual value is
architecture and platform dependent.
4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
internal kernel map of cpuX's hardware threads within the same
core as cpuX.
5) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
human-readable list of cpuX's hardware threads within the same
core as cpuX.
6) /sys/devices/system/cpu/cpuX/topology/core_siblings:
internal kernel map of cpuX's hardware threads within the same
physical_package_id.
7) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
human-readable list of cpuX's hardware threads within the same
physical_package_id.
8) /sys/devices/system/cpu/cpuX/topology/book_siblings:
internal kernel map of cpuX's hardware threads within the same
book_id.
9) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
human-readable list of cpuX's hardware threads within the same
book_id.
当前手机扫描出来的数据如下:
core_id 0
core_siblings 0f
core_siblings_list 0-3
physical_package_id 0
thread_siblings 01
thread_siblings_list 0
core_id 1
core_siblings 0f
core_siblings_list 0-3
physical_package_id 0
thread_siblings 02
thread_siblings_list 1
core_id 2
core_siblings 0f
core_siblings_list 0-3
physical_package_id 0
thread_siblings 04
thread_siblings_list 2
core_id 3
core_siblings 0f
core_siblings_list 0-3
physical_package_id 0
thread_siblings 08
thread_siblings_list 3
core_id 0
core_siblings f0
core_siblings_list 4-7
physical_package_id 1
thread_siblings 10
thread_siblings_list 4
core_id 1
core_siblings f0
core_siblings_list 4-7
physical_package_id 1
thread_siblings 20
thread_siblings_list 5
core_id 2
core_siblings f0
core_siblings_list 4-7
physical_package_id 1
thread_siblings 40
thread_siblings_list 6
core_id 3
core_siblings f0
core_siblings_list 4-7
physical_package_id 1
thread_siblings 80
thread_siblings_list 7
关于core_id\thread_sibling\core_sibling的解析如下:
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->cluster_id != cpu_topo->cluster_id)
continue;
// 关联的兄弟cpu
cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
if (cpu != cpuid)
cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
// 硬件plat的值
if (cpuid_topo->core_id != cpu_topo->core_id)
continue;
// 关联硬件thread
cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
if (cpu != cpuid)
cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
}
}
一切感觉都是在填充topology这个结构体。
arm64架构的cpu拓扑结构存储在cpu_topology[]变量当中:
/*
* cpu topology table
*/
struct cpu_topology cpu_topology[NR_CPUS];
struct cpu_topology {
int thread_id;
int core_id;
int cluster_id; // 本cpu所在的cluster
unsigned int partno;
cpumask_t thread_sibling;
cpumask_t core_sibling; // 在MutiCore层次(即同一个cluster中),有哪些兄弟cpu
};