x86/topology: Create logical package id

For per package oriented services we must be able to rely on the number of CPU
packages to be within bounds. Create a tracking facility, which

- calculates the number of possible packages depending on nr_cpu_ids after boot

- makes sure that the package id is within the number of possible packages. If
  the apic id is outside we map it to a logical package id if there is enough
  space available.

Provide interfaces for drivers to query the mapping and do translations from
physcial to logical ids.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Harish Chegondi <harish.chegondi@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/20160222221011.541071755@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 129 insertions, 0 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8a5cddac7d44..531b9611c51d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2078,6 +2078,20 @@ int generic_processor_info(int apicid, int version)
 		cpu = cpumask_next_zero(-1, cpu_present_mask);
 
 	/*
+	 * This can happen on physical hotplug. The sanity check at boot time
+	 * is done from native_smp_prepare_cpus() after num_possible_cpus() is
+	 * established.
+	 */
+	if (topology_update_package_map(apicid, cpu) < 0) {
+		int thiscpu = max + disabled_cpus;
+
+		pr_warning("ACPI: Package limit reached. Processor %d/0x%x ignored.\n",
+			   thiscpu, apicid);
+		disabled_cpus++;
+		return -ENOSPC;
+	}
+
+	/*
 	 * Validate version
 	 */
 	if (version == 0x0) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 68a80e9b67fc..81cf716f6f97 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -975,6 +975,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
+	/* The boot/hotplug time assigment got cleared, restore it */
+	c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 05b9211ea0f7..38766c2b5b00 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -160,6 +160,19 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		pr_info("Disabling PGE capability bit\n");
 		setup_clear_cpu_cap(X86_FEATURE_PGE);
 	}
+
+	if (c->cpuid_level >= 0x00000001) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
+		/*
+		 * If HTT (EDX[28]) is set EBX[16:23] contain the number of
+		 * apicids which are reserved per package. Store the resulting
+		 * shift value for the package management code.
+		 */
+		if (edx & (1U << 28))
+			c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
+	}
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 24d57f77b3c1..3bf1e0b5f827 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -97,6 +97,14 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
+/* Logical package management. We might want to allocate that dynamically */
+static int *physical_to_logical_pkg __read_mostly;
+static unsigned long *physical_package_map __read_mostly;;
+static unsigned long *logical_package_map  __read_mostly;
+static unsigned int max_physical_pkg_id __read_mostly;
+unsigned int __max_logical_packages __read_mostly;
+EXPORT_SYMBOL(__max_logical_packages);
+
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
@@ -251,6 +259,97 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
+int topology_update_package_map(unsigned int apicid, unsigned int cpu)
+{
+	unsigned int new, pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+
+	/* Called from early boot ? */
+	if (!physical_package_map)
+		return 0;
+
+	if (pkg >= max_physical_pkg_id)
+		return -EINVAL;
+
+	/* Set the logical package id */
+	if (test_and_set_bit(pkg, physical_package_map))
+		goto found;
+
+	if (pkg < __max_logical_packages) {
+		set_bit(pkg, logical_package_map);
+		physical_to_logical_pkg[pkg] = pkg;
+		goto found;
+	}
+	new = find_first_zero_bit(logical_package_map, __max_logical_packages);
+	if (new >= __max_logical_packages) {
+		physical_to_logical_pkg[pkg] = -1;
+		pr_warn("APIC(%x) Package %u exceeds logical package map\n",
+			apicid, pkg);
+		return -ENOSPC;
+	}
+	set_bit(new, logical_package_map);
+	pr_info("APIC(%x) Converting physical %u to logical package %u\n",
+		apicid, pkg, new);
+	physical_to_logical_pkg[pkg] = new;
+
+found:
+	cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+	return 0;
+}
+
+/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+	if (phys_pkg >= max_physical_pkg_id)
+		return -1;
+	return physical_to_logical_pkg[phys_pkg];
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
+static void __init smp_init_package_map(void)
+{
+	unsigned int ncpus, cpu;
+	size_t size;
+
+	/*
+	 * Today neither Intel nor AMD support heterogenous systems. That
+	 * might change in the future....
+	 */
+	ncpus = boot_cpu_data.x86_max_cores * smp_num_siblings;
+	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+
+	/*
+	 * Possibly larger than what we need as the number of apic ids per
+	 * package can be smaller than the actual used apic ids.
+	 */
+	max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
+	size = max_physical_pkg_id * sizeof(unsigned int);
+	physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
+	memset(physical_to_logical_pkg, 0xff, size);
+	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
+	physical_package_map = kzalloc(size, GFP_KERNEL);
+	size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long);
+	logical_package_map = kzalloc(size, GFP_KERNEL);
+
+	pr_info("Max logical packages: %u\n", __max_logical_packages);
+
+	for_each_present_cpu(cpu) {
+		unsigned int apicid = apic->cpu_present_to_apicid(cpu);
+
+		if (apicid == BAD_APICID || !apic->apic_id_valid(apicid))
+			continue;
+		if (!topology_update_package_map(apicid, cpu))
+			continue;
+		pr_warn("CPU %u APICId %x disabled\n", cpu, apicid);
+		per_cpu(x86_bios_cpu_apicid, cpu) = BAD_APICID;
+		set_cpu_possible(cpu, false);
+		set_cpu_present(cpu, false);
+	}
+}
+
 void __init smp_store_boot_cpu_info(void)
 {
 	int id = 0; /* CPU 0 */
@@ -258,6 +357,7 @@ void __init smp_store_boot_cpu_info(void)
 
 	*c = boot_cpu_data;
 	c->cpu_index = id;
+	smp_init_package_map();
 }
 
 /*