1 files changed, 36 insertions, 23 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7e52f83d3a4b..7249dcf2cbcb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -471,7 +471,7 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
         return false;
 }
 
-static struct sched_domain_topology_level numa_inside_package_topology[] = {
+static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 #ifdef CONFIG_SCHED_SMT
         { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 #endif
@@ -480,22 +480,23 @@ static struct sched_domain_topology_level numa_inside_package_topology[] = {
 #endif
         { NULL, },
 };
+
+static struct sched_domain_topology_level x86_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+        { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+        { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+        { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+        { NULL, },
+};
+
 /*
- * set_sched_topology() sets the topology internal to a CPU.  The
- * NUMA topologies are layered on top of it to build the full
- * system topology.
- *
- * If NUMA nodes are observed to occur within a CPU package, this
- * function should be called.  It forces the sched domain code to
- * only use the SMT level for the CPU portion of the topology.
- * This essentially falls back to relying on NUMA information
- * from the SRAT table to describe the entire system topology
- * (except for hyperthreads).
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours and Intel Cluster-on-Die have this.
  */
-static void primarily_use_numa_for_topology(void)
-{
-        set_sched_topology(numa_inside_package_topology);
-}
+static bool x86_has_numa_in_package;
 
 void set_cpu_sibling_map(int cpu)
 {
@@ -558,7 +559,7 @@ void set_cpu_sibling_map(int cpu)
                                 c->booted_cores = cpu_data(i).booted_cores;
                 }
                 if (match_die(c, o) && !topology_same_node(c, o))
-                        primarily_use_numa_for_topology();
+                        x86_has_numa_in_package = true;
         }
 
         threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -690,7 +691,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
          * Give the other CPU some time to accept the IPI.
          */
         udelay(200);
-        if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+        if (APIC_INTEGRATED(boot_cpu_apic_version)) {
                 maxlvt = lapic_get_maxlvt();
                 if (maxlvt > 3)                 /* Due to the Pentium erratum 3AP.  */
                         apic_write(APIC_ESR, 0);
@@ -717,7 +718,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
         /*
          * Be paranoid about clearing APIC errors.
          */
-        if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+        if (APIC_INTEGRATED(boot_cpu_apic_version)) {
                 if (maxlvt > 3)         /* Due to the Pentium erratum 3AP.  */
                         apic_write(APIC_ESR, 0);
                 apic_read(APIC_ESR);
@@ -756,7 +757,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
          * Determine this based on the APIC version.
          * If we don't have an integrated APIC, don't send the STARTUP IPIs.
          */
-        if (APIC_INTEGRATED(apic_version[phys_apicid]))
+        if (APIC_INTEGRATED(boot_cpu_apic_version))
                 num_starts = 2;
         else
                 num_starts = 0;
@@ -993,7 +994,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
                 /*
                  * Be paranoid about clearing APIC errors.
                 */
-                if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+                if (APIC_INTEGRATED(boot_cpu_apic_version)) {
                         apic_write(APIC_ESR, 0);
                         apic_read(APIC_ESR);
                 }
@@ -1248,7 +1249,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
         /*
          * If we couldn't find a local APIC, then get out of here now!
          */
-        if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
+        if (APIC_INTEGRATED(boot_cpu_apic_version) &&
             !boot_cpu_has(X86_FEATURE_APIC)) {
                 if (!disable_apic) {
                         pr_err("BIOS bug, local APIC #%d not detected!...\n",
@@ -1303,6 +1304,16 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
                 zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
                 zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
         }
+
+        /*
+         * Set 'default' x86 topology, this matches default_topology() in that
+         * it has NUMA nodes as a topology level. See also
+         * native_smp_cpus_done().
+         *
+         * Must be done before set_cpus_sibling_map() is ran.
+         */
+        set_sched_topology(x86_topology);
+
         set_cpu_sibling_map(0);
 
         switch (smp_sanity_check(max_cpus)) {
@@ -1322,14 +1333,13 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
                 break;
         }
 
-        default_setup_apic_routing();
-
         if (read_apic_id() != boot_cpu_physical_apicid) {
                 panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
                      read_apic_id(), boot_cpu_physical_apicid);
                 /* Or can we switch back to PIC here? */
         }
 
+        default_setup_apic_routing();
         cpu0_logical_apicid = apic_bsp_setup(false);
 
         pr_info("CPU%d: ", 0);
@@ -1369,6 +1379,9 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 {
         pr_debug("Boot done\n");
 
+        if (x86_has_numa_in_package)
+                set_sched_topology(x86_numa_in_package_topology);
+
         nmi_selftest();
         impress_friends();
         setup_ioapic_dest();