x86/smpboot: Fix __max_logical_packages estimate

A system booted with a small number of cores enabled per package
panics because the estimate of __max_logical_packages is too low.

This occurs when the total number of active cores across all packages is
less than the maximum core count for a single package. e.g.:

  On a 4 package system with 20 cores/package where only 4 cores are
  enabled on each package, the value of __max_logical_packages is
  calculated as DIV_ROUND_UP(16 / 20) = 1 and not 4.

Calculate __max_logical_packages after the cpu enumeration has completed.
Use the boot cpu's data to extrapolate the number of packages.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: He Chen <he.chen@linux.intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Piotr Luc <piotr.luc@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arvind Yadav <arvind.yadav.cs@gmail.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mathias Krause <minipli@googlemail.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: https://lkml.kernel.org/r/20171114124257.22013-4-prarit@redhat.com

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index da5e162636fd636226f854e628e49bbf5d403dde..3d01df7d7cf60cdbe1342fe84006405712394663 100644 (file)
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -310,12 +310,6 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
        if (new >= 0)
                goto found;
 
-       if (logical_packages >= __max_logical_packages) {
-               pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n",
-                       logical_packages, cpu, __max_logical_packages);
-               return -ENOSPC;
-       }
-
        new = logical_packages++;
        if (new != pkg) {
                pr_info("CPU %u Converting physical %u to logical package %u\n",
@@ -326,44 +320,6 @@ found:
        return 0;
 }
 
-static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
-{
-       unsigned int ncpus;
-
-       /*
-        * Today neither Intel nor AMD support heterogenous systems. That
-        * might change in the future....
-        *
-        * While ideally we'd want '* smp_num_siblings' in the below @ncpus
-        * computation, this won't actually work since some Intel BIOSes
-        * report inconsistent HT data when they disable HT.
-        *
-        * In particular, they reduce the APIC-IDs to only include the cores,
-        * but leave the CPUID topology to say there are (2) siblings.
-        * This means we don't know how many threads there will be until
-        * after the APIC enumeration.
-        *
-        * By not including this we'll sometimes over-estimate the number of
-        * logical packages by the amount of !present siblings, but this is
-        * still better than MAX_LOCAL_APIC.
-        *
-        * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited
-        * on the command line leading to a similar issue as the HT disable
-        * problem because the hyperthreads are usually enumerated after the
-        * primary cores.
-        */
-       ncpus = boot_cpu_data.x86_max_cores;
-       if (!ncpus) {
-               pr_warn("x86_max_cores == zero !?!?");
-               ncpus = 1;
-       }
-
-       __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
-       pr_info("Max logical packages: %u\n", __max_logical_packages);
-
-       topology_update_package_map(c->phys_proc_id, cpu);
-}
-
 void __init smp_store_boot_cpu_info(void)
 {
        int id = 0; /* CPU 0 */
@@ -371,7 +327,7 @@ void __init smp_store_boot_cpu_info(void)
 
        *c = boot_cpu_data;
        c->cpu_index = id;
-       smp_init_package_map(c, id);
+       topology_update_package_map(c->phys_proc_id, id);
        c->initialized = true;
 }
 
@@ -1341,7 +1297,16 @@ void __init native_smp_prepare_boot_cpu(void)
 
 void __init native_smp_cpus_done(unsigned int max_cpus)
 {
+       int ncpus;
+
        pr_debug("Boot done\n");
+       /*
+        * Today neither Intel nor AMD support heterogenous systems so
+        * extrapolate the boot cpu's data to all packages.
+        */
+       ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+       __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+       pr_info("Max logical packages: %u\n", __max_logical_packages);
 
        if (x86_has_numa_in_package)
                set_sched_topology(x86_numa_in_package_topology);