@@ -316,6 +316,10 @@ static void __init reset_cpu_topology(void)
}
#ifdef CONFIG_ACPI
+
+#define acpi_topology_mktag(x) (-((x) + 1))
+#define acpi_topology_istag(x) ((x) < 0)
+
/*
* Propagate the topology information of the processor_topology_node tree to the
* cpu_topology array.
@@ -323,27 +327,31 @@ static void __init reset_cpu_topology(void)
static int __init parse_acpi_topology(void)
{
bool is_threaded;
- int cpu, topology_id;
+ int package_id = 0;
+ int cpu, ret;
is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
+ /*
+ * Loop through all PEs twice. In the first loop store parent
+ * tags into the IDs. In the second loop we reset the IDs as
+ * 0..N-1 per parent tag.
+ */
+
for_each_possible_cpu(cpu) {
int i, cache_id;
- topology_id = find_acpi_cpu_topology(cpu, 0);
- if (topology_id < 0)
- return topology_id;
-
- if (is_threaded) {
- cpu_topology[cpu].thread_id = topology_id;
- topology_id = find_acpi_cpu_topology(cpu, 1);
- cpu_topology[cpu].core_id = topology_id;
- } else {
- cpu_topology[cpu].thread_id = -1;
- cpu_topology[cpu].core_id = topology_id;
- }
- topology_id = find_acpi_cpu_topology_package(cpu);
- cpu_topology[cpu].package_id = topology_id;
+ ret = find_acpi_cpu_topology(cpu, 0);
+ if (ret < 0)
+ return ret;
+
+ if (is_threaded)
+ ret = find_acpi_cpu_topology(cpu, 1);
+ else
+ cpu_topology[cpu].thread_id = -1;
+ cpu_topology[cpu].core_id = acpi_topology_mktag(ret);
+ ret = find_acpi_cpu_topology_package(cpu);
+ cpu_topology[cpu].package_id = acpi_topology_mktag(ret);
i = acpi_find_last_cache_level(cpu);
@@ -358,6 +366,38 @@ static int __init parse_acpi_topology(void)
}
}
+ for_each_possible_cpu(cpu) {
+ int package_tag = cpu_topology[cpu].package_id;
+ int core_id = 0, cpu2;
+
+ if (!acpi_topology_istag(package_tag))
+ continue;
+
+ for_each_possible_cpu(cpu2) {
+ if (cpu_topology[cpu2].package_id != package_tag)
+ continue;
+
+ if (is_threaded) {
+ int core_tag = cpu_topology[cpu2].core_id;
+ int thread_id = 0, cpu3;
+
+ for_each_possible_cpu(cpu3) {
+ if (cpu_topology[cpu3].core_id != core_tag)
+ continue;
+
+ cpu_topology[cpu3].thread_id = thread_id++;
+ cpu_topology[cpu3].core_id = core_id;
+ cpu_topology[cpu3].package_id = package_id;
+ }
+ ++core_id;
+ } else {
+ cpu_topology[cpu2].core_id = core_id++;
+ cpu_topology[cpu2].package_id = package_id;
+ }
+ }
+ ++package_id;
+ }
+
return 0;
}
When booting with devicetree, and the devicetree has the cpu-map node, the topology IDs that are visible from sysfs are generated with counters. ACPI, on the other hand, uses ACPI table pointer offsets, which, while guaranteed to be unique, look a bit weird. Instead, we can generate DT identical topology IDs for ACPI by just using counters for the leaf nodes and by remapping the non-leaf table pointer offsets to counters. Cc: Jeremy Linton <jeremy.linton@arm.com> Cc: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by: Andrew Jones <drjones@redhat.com> --- v1: Reworked this since the RFC in order to make the algorithm more obvious. It wasn't clear in the RFC that the ACPI nodes could be in any order, although they could have been. I've tested that this works with nodes in arbitrary order by hacking the QEMU PPTT table generator[*]. Note, while this produces equivalent topology IDs to what the DT cpu-map node produces for all sane configs, if PEs are threads (have MPIDR.MT set), but the cpu-map does not specify threads, then, while the DT parsing code will happily call the threads "cores", ACPI will see that the PPTT leaf nodes are for threads and produce different topology IDs. I see this difference as a bug with the DT parsing which can be addressed separately. [*] https://github.com/rhdrjones/qemu/commits/virt-cpu-topology arch/arm64/kernel/topology.c | 70 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 55 insertions(+), 15 deletions(-)