From 090610ba704a66d7a58919be3bad195f24499ecb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Feb 2024 22:06:03 +0100 Subject: x86/cpu/topology: Use topology bitmaps for sizing Now that all possible APIC IDs are tracked in the topology bitmaps, its trivial to retrieve the real information from there. This gets rid of the guesstimates for the maximal packages and dies per package as the actual numbers can be determined before a single AP has been brought up. The number of SMT threads can now be determined correctly from the bitmaps in all situations. Up to now a system which has SMT disabled in the BIOS will still claim that it is SMT capable, because the lowest APIC ID bit is reserved for that and CPUID leaf 0xb/0x1f still enumerates the SMT domain accordingly. By calculating the bitmap weights of the SMT and the CORE domain and setting them into relation the SMT disabled in BIOS situation reports correctly that the system is not SMT capable. It also handles the situation correctly when a hybrid systems boot CPU does not have SMT as it takes the SMT capability of the APs fully into account. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Sohil Mehta Link: https://lore.kernel.org/r/20240213210252.681709880@linutronix.de --- arch/x86/kernel/cpu/common.c | 9 ++++++--- arch/x86/kernel/cpu/debugfs.c | 2 +- arch/x86/kernel/cpu/topology.c | 20 +++++++++++++++++++- arch/x86/kernel/cpu/topology_common.c | 24 ------------------------ 4 files changed, 26 insertions(+), 29 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b221e144c9fc..4babe3ca4f67 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -73,11 +73,14 @@ u32 elf_hwcap2 __read_mostly; /* Number of siblings per CPU package */ -int smp_num_siblings = 1; +unsigned int smp_num_siblings __ro_after_init = 1; EXPORT_SYMBOL(smp_num_siblings); -unsigned int __max_die_per_package __read_mostly = 1; -EXPORT_SYMBOL(__max_die_per_package); +unsigned int __max_dies_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__max_dies_per_package); + +unsigned int __max_logical_packages __ro_after_init = 1; +EXPORT_SYMBOL(__max_logical_packages); static struct ppin_info { int feature; diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c index 86de544cdb14..543efc487206 100644 --- a/arch/x86/kernel/cpu/debugfs.c +++ b/arch/x86/kernel/cpu/debugfs.c @@ -29,7 +29,7 @@ static int cpu_debug_show(struct seq_file *m, void *p) seq_printf(m, "amd_node_id: %u\n", c->topo.amd_node_id); seq_printf(m, "amd_nodes_per_pkg: %u\n", topology_amd_nodes_per_pkg()); seq_printf(m, "max_cores: %u\n", c->x86_max_cores); - seq_printf(m, "max_die_per_pkg: %u\n", __max_die_per_package); + seq_printf(m, "max_dies_per_pkg: %u\n", __max_dies_per_package); seq_printf(m, "smp_num_siblings: %u\n", smp_num_siblings); return 0; } diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 07124da9df71..630ebe503ae3 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -348,8 +348,8 @@ void __init topology_init_possible_cpus(void) { unsigned int assigned = topo_info.nr_assigned_cpus; unsigned int disabled = topo_info.nr_disabled_cpus; + unsigned int cnta, cntb, cpu, allowed = 1; unsigned int total = assigned + disabled; - unsigned int cpu, allowed = 1; u32 apicid; if (!restrict_to_up()) { @@ -372,6 +372,24 @@ void __init topology_init_possible_cpus(void) total_cpus = allowed; set_nr_cpu_ids(allowed); + cnta = domain_weight(TOPO_PKG_DOMAIN); + cntb = domain_weight(TOPO_DIE_DOMAIN); + __max_logical_packages = cnta; + __max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta)); + + pr_info("Max. logical packages: %3u\n", cnta); + pr_info("Max. logical dies: %3u\n", cntb); + pr_info("Max. dies per package: %3u\n", __max_dies_per_package); + + cnta = domain_weight(TOPO_CORE_DOMAIN); + cntb = domain_weight(TOPO_SMT_DOMAIN); + /* + * Can't use order delta here as order(cnta) can be equal + * order(cntb) even if cnta != cntb. + */ + smp_num_siblings = DIV_ROUND_UP(cntb, cnta); + pr_info("Max. threads per core: %3u\n", smp_num_siblings); + pr_info("Allowing %u present CPUs plus %u hotplug CPUs\n", assigned, disabled); if (topo_info.nr_rejected_cpus) pr_info("Rejected CPUs %u\n", topo_info.nr_rejected_cpus); diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c index b0b68c867aaf..0276978bc272 100644 --- a/arch/x86/kernel/cpu/topology_common.c +++ b/arch/x86/kernel/cpu/topology_common.c @@ -196,16 +196,6 @@ void cpu_parse_topology(struct cpuinfo_x86 *c) tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]); } - /* Bug compatible with the existing parsers */ - if (tscan.dom_ncpus[TOPO_SMT_DOMAIN] > smp_num_siblings) { - if (system_state == SYSTEM_BOOTING) { - pr_warn_once("CPU%d: SMT detected and enabled late\n", cpu); - smp_num_siblings = tscan.dom_ncpus[TOPO_SMT_DOMAIN]; - } else { - pr_warn_once("CPU%d: SMT detected after init. Too late!\n", cpu); - } - } - topo_set_ids(&tscan); topo_set_max_cores(&tscan); } @@ -231,20 +221,6 @@ void __init cpu_init_topology(struct cpuinfo_x86 *c) topo_set_ids(&tscan); topo_set_max_cores(&tscan); - /* - * Bug compatible with the existing code. If the boot CPU does not - * have SMT this ends up with one sibling. This needs way deeper - * changes further down the road to get it right during early boot. - */ - smp_num_siblings = tscan.dom_ncpus[TOPO_SMT_DOMAIN]; - - /* - * Neither it's clear whether there are as many dies as the APIC - * space indicating die level is. But assume that the actual number - * of CPUs gives a proper indication for now to stay bug compatible. - */ - __max_die_per_package = tscan.dom_ncpus[TOPO_DIE_DOMAIN] / - tscan.dom_ncpus[TOPO_DIE_DOMAIN - 1]; /* * AMD systems have Nodes per package which cannot be mapped to * APIC ID. -- cgit v1.2.3