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 --- arch/arm64/kernel/topology.c | 130 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 130 insertions(+)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index c88970b1b863..83d6919d4e0a 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -79,6 +79,121 @@ static unsigned long *__cpu_capacity; #define cpu_capacity(cpu) __cpu_capacity[cpu]
static unsigned long middle_capacity = 1; +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) { + 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) +{ + 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); + 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 (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++; +}
/* * Iterate all CPUs' descriptor in DT and compute the efficiency @@ -100,6 +215,21 @@ static void __init parse_dt_topology(void) alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity); __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+ 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); + for_each_possible_cpu(cpu) { const u32 *rate; int len;