Many modern machines have cluster on die (COD) non-uniformity as well as the traditional multi-socket architectures. Reusing the multi-socket or NUMA on die concepts for these (as arm64 does) breaks down when presented with actual multi-socket/COD machines. Similar, problems are also visible on some x86 machines so it seems appropriate to start abstracting and making these topologies visible.
To start, a topology_cod_id() macro is added which defaults to returning the same information as topology_physical_package_id(). Moving forward we can start to spit out the differences. For arm64, an additional package_id is added to the cpu_topology array. Initially this will be equal to the cluster_id as well. Signed-off-by: Jeremy Linton <[email protected]> --- arch/arm64/include/asm/topology.h | 4 +++- arch/arm64/kernel/topology.c | 8 ++++++-- include/linux/topology.h | 3 +++ 3 files changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 8b57339823e9..bd7517960d39 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -7,13 +7,15 @@ struct cpu_topology { int thread_id; int core_id; int cluster_id; + int package_id; cpumask_t thread_sibling; cpumask_t core_sibling; }; extern struct cpu_topology cpu_topology[NR_CPUS]; -#define topology_physical_package_id(cpu) (cpu_topology[cpu].cluster_id) +#define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) +#define topology_cod_id(cpu) (cpu_topology[cpu].cluster_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 8d48b233e6ce..9147e5b6326d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -67,6 +67,8 @@ static int __init parse_core(struct device_node *core, int cluster_id, leaf = false; cpu = get_cpu_for_node(t); if (cpu >= 0) { + /* maintain DT cluster == package behavior */ + cpu_topology[cpu].package_id = cluster_id; cpu_topology[cpu].cluster_id = cluster_id; cpu_topology[cpu].core_id = core_id; cpu_topology[cpu].thread_id = i; @@ -88,7 +90,7 @@ static int __init parse_core(struct device_node *core, int cluster_id, core); return -EINVAL; } - + cpu_topology[cpu].package_id = cluster_id; cpu_topology[cpu].cluster_id = cluster_id; cpu_topology[cpu].core_id = core_id; } else if (leaf) { @@ -228,7 +230,7 @@ static void update_siblings_masks(unsigned int cpuid) for_each_possible_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; - if (cpuid_topo->cluster_id != cpu_topo->cluster_id) + if (cpuid_topo->package_id != cpu_topo->package_id) continue; cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); @@ -273,6 +275,7 @@ void store_cpu_topology(unsigned int cpuid) MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16; } + cpuid_topo->package_id = cpuid_topo->cluster_id; pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", cpuid, cpuid_topo->cluster_id, cpuid_topo->core_id, @@ -292,6 +295,7 @@ static void __init reset_cpu_topology(void) cpu_topo->thread_id = -1; cpu_topo->core_id = 0; cpu_topo->cluster_id = -1; + cpu_topo->package_id = -1; cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); diff --git a/include/linux/topology.h b/include/linux/topology.h index cb0775e1ee4b..4660749a7303 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -184,6 +184,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif +#ifndef topology_cod_id /* cluster on die */ +#define topology_cod_id(cpu) topology_physical_package_id(cpu) +#endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif -- 2.13.5
