[PATCH 3/3] x86/smpboot: Fix __max_logical_packages estimate

[Prarit Bhargava]

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.

ie) 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.

Here's an example of the panic:

     smpboot: Booting Node   1, Processors  #1 OK
     smpboot: Package 1 of CPU 1 exceeds BIOS package data 1.
     ------------[ cut here ]------------
     kernel BUG at arch/x86/kernel/cpu/common.c:1087!
     invalid opcode: 0000 [#1] SMP
     Modules linked in:
     CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.14.0-rc2+ #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@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Piotr Luc <piotr.luc@xxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Arvind Yadav <arvind.yadav.cs@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: Mathias Krause <minipli@xxxxxxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 arch/x86/kernel/smpboot.c | 57 +++++++++--------------------------------------
 1 file changed, 10 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ca615bc94e82..6307e92f54ae 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -307,12 +307,6 @@ 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++;
 
 	/* Allocate and copy a new array */
@@ -335,46 +329,6 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 	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);
-
-	logical_packages = 0;
-
-	topology_update_package_map(c->phys_proc_id, cpu);
-}
-
 void __init smp_store_boot_cpu_info(void)
 {
 	int id = 0; /* CPU 0 */
@@ -382,7 +336,7 @@ 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);
 }
 
 /*
@@ -1382,7 +1336,16 @@ 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);
-- 
2.15.0.rc0.39.g2f0e14e64