Merge branch 'x86-topology-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 topology updates from Ingo Molnar:
 "Implement multi-die topology support on Intel CPUs and expose the die
  topology to user-space tooling, by Len Brown, Kan Liang and Zhang Rui.

  These changes should have no effect on the kernel's existing
  understanding of topologies, i.e. there should be no behavioral impact
  on cache, NUMA, scheduler, perf and other topologies and overall
  system performance"

* 'x86-topology-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/rapl: Cosmetic rename internal variables in response to multi-die/pkg support
  perf/x86/intel/uncore: Cosmetic renames in response to multi-die/pkg support
  hwmon/coretemp: Cosmetic: Rename internal variables to zones from packages
  thermal/x86_pkg_temp_thermal: Cosmetic: Rename internal variables to zones from packages
  perf/x86/intel/cstate: Support multi-die/package
  perf/x86/intel/rapl: Support multi-die/package
  perf/x86/intel/uncore: Support multi-die/package
  topology: Create core_cpus and die_cpus sysfs attributes
  topology: Create package_cpus sysfs attribute
  hwmon/coretemp: Support multi-die/package
  powercap/intel_rapl: Update RAPL domain name and debug messages
  thermal/x86_pkg_temp_thermal: Support multi-die/package
  powercap/intel_rapl: Support multi-die/package
  powercap/intel_rapl: Simplify rapl_find_package()
  x86/topology: Define topology_logical_die_id()
  x86/topology: Define topology_die_id()
  cpu/topology: Export die_id
  x86/topology: Create topology_max_die_per_package()
  x86/topology: Add CPUID.1F multi-die/package support

12 files changed, 226 insertions, 77 deletions

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 6072f92cb8ea..267d7f8e12ab 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -302,7 +302,7 @@ static int cstate_pmu_event_init(struct perf_event *event)
 			return -EINVAL;
 		event->hw.event_base = pkg_msr[cfg].msr;
 		cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
-				      topology_core_cpumask(event->cpu));
+				      topology_die_cpumask(event->cpu));
 	} else {
 		return -ENOENT;
 	}
@@ -385,7 +385,7 @@ static int cstate_cpu_exit(unsigned int cpu)
 	if (has_cstate_pkg &&
 	    cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
 
-		target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+		target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
 		/* Migrate events if there is a valid target */
 		if (target < nr_cpu_ids) {
 			cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
@@ -414,7 +414,7 @@ static int cstate_cpu_init(unsigned int cpu)
 	 * in the package cpu mask as the designated reader.
 	 */
 	target = cpumask_any_and(&cstate_pkg_cpu_mask,
-				 topology_core_cpumask(cpu));
+				 topology_die_cpumask(cpu));
 	if (has_cstate_pkg && target >= nr_cpu_ids)
 		cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
 
@@ -663,7 +663,13 @@ static int __init cstate_init(void)
 	}
 
 	if (has_cstate_pkg) {
-		err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
+		if (topology_max_die_per_package() > 1) {
+			err = perf_pmu_register(&cstate_pkg_pmu,
+						"cstate_die", -1);
+		} else {
+			err = perf_pmu_register(&cstate_pkg_pmu,
+						cstate_pkg_pmu.name, -1);
+		}
 		if (err) {
 			has_cstate_pkg = false;
 			pr_info("Failed to register cstate pkg pmu\n");
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 26c03f5adfb9..8c7ecde3ba70 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -149,7 +149,7 @@ struct rapl_pmu {
 
 struct rapl_pmus {
 	struct pmu		pmu;
-	unsigned int		maxpkg;
+	unsigned int		maxdie;
 	struct rapl_pmu		*pmus[];
 };
 
@@ -162,13 +162,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	unsigned int pkgid = topology_logical_package_id(cpu);
+	unsigned int dieid = topology_logical_die_id(cpu);
 
 	/*
 	 * The unsigned check also catches the '-1' return value for non
 	 * existent mappings in the topology map.
 	 */
-	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
+	return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -572,7 +572,7 @@ static int rapl_cpu_offline(unsigned int cpu)
 
 	pmu->cpu = -1;
 	/* Find a new cpu to collect rapl events */
-	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+	target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
 
 	/* Migrate rapl events to the new target */
 	if (target < nr_cpu_ids) {
@@ -599,14 +599,14 @@ static int rapl_cpu_online(unsigned int cpu)
 		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
 		rapl_hrtimer_init(pmu);
 
-		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+		rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
 	}
 
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.
 	 */
-	target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
+	target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
 	if (target < nr_cpu_ids)
 		return 0;
 
@@ -669,22 +669,22 @@ static void cleanup_rapl_pmus(void)
 {
 	int i;
 
-	for (i = 0; i < rapl_pmus->maxpkg; i++)
+	for (i = 0; i < rapl_pmus->maxdie; i++)
 		kfree(rapl_pmus->pmus[i]);
 	kfree(rapl_pmus);
 }
 
 static int __init init_rapl_pmus(void)
 {
-	int maxpkg = topology_max_packages();
+	int maxdie = topology_max_packages() * topology_max_die_per_package();
 	size_t size;
 
-	size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *);
+	size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
 	rapl_pmus = kzalloc(size, GFP_KERNEL);
 	if (!rapl_pmus)
 		return -ENOMEM;
 
-	rapl_pmus->maxpkg		= maxpkg;
+	rapl_pmus->maxdie		= maxdie;
 	rapl_pmus->pmu.attr_groups	= rapl_attr_groups;
 	rapl_pmus->pmu.task_ctx_nr	= perf_invalid_context;
 	rapl_pmus->pmu.event_init	= rapl_pmu_event_init;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 089bfcdf2f7f..6094c8db949d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -15,7 +15,7 @@ struct pci_driver *uncore_pci_driver;
 DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
 struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
 struct pci_extra_dev *uncore_extra_pci_dev;
-static int max_packages;
+static int max_dies;
 
 /* mask of cpus that collect uncore events */
 static cpumask_t uncore_cpu_mask;
@@ -101,13 +101,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
 
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
-	unsigned int pkgid = topology_logical_package_id(cpu);
+	unsigned int dieid = topology_logical_die_id(cpu);
 
 	/*
 	 * The unsigned check also catches the '-1' return value for non
 	 * existent mappings in the topology map.
 	 */
-	return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
+	return dieid < max_dies ? pmu->boxes[dieid] : NULL;
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -312,7 +312,7 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
 	uncore_pmu_init_hrtimer(box);
 	box->cpu = -1;
 	box->pci_phys_id = -1;
-	box->pkgid = -1;
+	box->dieid = -1;
 
 	/* set default hrtimer timeout */
 	box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
@@ -827,10 +827,10 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
 
 static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 {
-	int pkg;
+	int die;
 
-	for (pkg = 0; pkg < max_packages; pkg++)
-		kfree(pmu->boxes[pkg]);
+	for (die = 0; die < max_dies; die++)
+		kfree(pmu->boxes[die]);
 	kfree(pmu->boxes);
 }
 
@@ -867,7 +867,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	if (!pmus)
 		return -ENOMEM;
 
-	size = max_packages * sizeof(struct intel_uncore_box *);
+	size = max_dies * sizeof(struct intel_uncore_box *);
 
 	for (i = 0; i < type->num_boxes; i++) {
 		pmus[i].func_id	= setid ? i : -1;
@@ -937,20 +937,21 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	struct intel_uncore_type *type;
 	struct intel_uncore_pmu *pmu = NULL;
 	struct intel_uncore_box *box;
-	int phys_id, pkg, ret;
+	int phys_id, die, ret;
 
 	phys_id = uncore_pcibus_to_physid(pdev->bus);
 	if (phys_id < 0)
 		return -ENODEV;
 
-	pkg = topology_phys_to_logical_pkg(phys_id);
-	if (pkg < 0)
+	die = (topology_max_die_per_package() > 1) ? phys_id :
+					topology_phys_to_logical_pkg(phys_id);
+	if (die < 0)
 		return -EINVAL;
 
 	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
 		int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
 
-		uncore_extra_pci_dev[pkg].dev[idx] = pdev;
+		uncore_extra_pci_dev[die].dev[idx] = pdev;
 		pci_set_drvdata(pdev, NULL);
 		return 0;
 	}
@@ -989,7 +990,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
 	}
 
-	if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
+	if (WARN_ON_ONCE(pmu->boxes[die] != NULL))
 		return -EINVAL;
 
 	box = uncore_alloc_box(type, NUMA_NO_NODE);
@@ -1003,13 +1004,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 	atomic_inc(&box->refcnt);
 	box->pci_phys_id = phys_id;
-	box->pkgid = pkg;
+	box->dieid = die;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
 	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
-	pmu->boxes[pkg] = box;
+	pmu->boxes[die] = box;
 	if (atomic_inc_return(&pmu->activeboxes) > 1)
 		return 0;
 
@@ -1017,7 +1018,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	ret = uncore_pmu_register(pmu);
 	if (ret) {
 		pci_set_drvdata(pdev, NULL);
-		pmu->boxes[pkg] = NULL;
+		pmu->boxes[die] = NULL;
 		uncore_box_exit(box);
 		kfree(box);
 	}
@@ -1028,16 +1029,17 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 {
 	struct intel_uncore_box *box;
 	struct intel_uncore_pmu *pmu;
-	int i, phys_id, pkg;
+	int i, phys_id, die;
 
 	phys_id = uncore_pcibus_to_physid(pdev->bus);
 
 	box = pci_get_drvdata(pdev);
 	if (!box) {
-		pkg = topology_phys_to_logical_pkg(phys_id);
+		die = (topology_max_die_per_package() > 1) ? phys_id :
+					topology_phys_to_logical_pkg(phys_id);
 		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
-			if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
-				uncore_extra_pci_dev[pkg].dev[i] = NULL;
+			if (uncore_extra_pci_dev[die].dev[i] == pdev) {
+				uncore_extra_pci_dev[die].dev[i] = NULL;
 				break;
 			}
 		}
@@ -1050,7 +1052,7 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 		return;
 
 	pci_set_drvdata(pdev, NULL);
-	pmu->boxes[box->pkgid] = NULL;
+	pmu->boxes[box->dieid] = NULL;
 	if (atomic_dec_return(&pmu->activeboxes) == 0)
 		uncore_pmu_unregister(pmu);
 	uncore_box_exit(box);
@@ -1062,7 +1064,7 @@ static int __init uncore_pci_init(void)
 	size_t size;
 	int ret;
 
-	size = max_packages * sizeof(struct pci_extra_dev);
+	size = max_dies * sizeof(struct pci_extra_dev);
 	uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
 	if (!uncore_extra_pci_dev) {
 		ret = -ENOMEM;
@@ -1109,11 +1111,11 @@ static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 {
 	struct intel_uncore_pmu *pmu = type->pmus;
 	struct intel_uncore_box *box;
-	int i, pkg;
+	int i, die;
 
-	pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu);
+	die = topology_logical_die_id(old_cpu < 0 ? new_cpu : old_cpu);
 	for (i = 0; i < type->num_boxes; i++, pmu++) {
-		box = pmu->boxes[pkg];
+		box = pmu->boxes[die];
 		if (!box)
 			continue;
 
@@ -1146,13 +1148,13 @@ static int uncore_event_cpu_offline(unsigned int cpu)
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
-	int i, pkg, target;
+	int i, die, target;
 
 	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
 		goto unref;
 	/* Find a new cpu to collect uncore events */
-	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+	target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
 
 	/* Migrate uncore events to the new target */
 	if (target < nr_cpu_ids)
@@ -1165,12 +1167,12 @@ static int uncore_event_cpu_offline(unsigned int cpu)
 
 unref:
 	/* Clear the references */
-	pkg = topology_logical_package_id(cpu);
+	die = topology_logical_die_id(cpu);
 	for (; *types; types++) {
 		type = *types;
 		pmu = type->pmus;
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
+			box = pmu->boxes[die];
 			if (box && atomic_dec_return(&box->refcnt) == 0)
 				uncore_box_exit(box);
 		}
@@ -1179,7 +1181,7 @@ unref:
 }
 
 static int allocate_boxes(struct intel_uncore_type **types,
-			 unsigned int pkg, unsigned int cpu)
+			 unsigned int die, unsigned int cpu)
 {
 	struct intel_uncore_box *box, *tmp;
 	struct intel_uncore_type *type;
@@ -1192,20 +1194,20 @@ static int allocate_boxes(struct intel_uncore_type **types,
 		type = *types;
 		pmu = type->pmus;
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			if (pmu->boxes[pkg])
+			if (pmu->boxes[die])
 				continue;
 			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				goto cleanup;
 			box->pmu = pmu;
-			box->pkgid = pkg;
+			box->dieid = die;
 			list_add(&box->active_list, &allocated);
 		}
 	}
 	/* Install them in the pmus */
 	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
 		list_del_init(&box->active_list);
-		box->pmu->boxes[pkg] = box;
+		box->pmu->boxes[die] = box;
 	}
 	return 0;
 
@@ -1222,10 +1224,10 @@ static int uncore_event_cpu_online(unsigned int cpu)
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
-	int i, ret, pkg, target;
+	int i, ret, die, target;
 
-	pkg = topology_logical_package_id(cpu);
-	ret = allocate_boxes(types, pkg, cpu);
+	die = topology_logical_die_id(cpu);
+	ret = allocate_boxes(types, die, cpu);
 	if (ret)
 		return ret;
 
@@ -1233,7 +1235,7 @@ static int uncore_event_cpu_online(unsigned int cpu)
 		type = *types;
 		pmu = type->pmus;
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
+			box = pmu->boxes[die];
 			if (box && atomic_inc_return(&box->refcnt) == 1)
 				uncore_box_init(box);
 		}
@@ -1243,7 +1245,7 @@ static int uncore_event_cpu_online(unsigned int cpu)
 	 * Check if there is an online cpu in the package
 	 * which collects uncore events already.
 	 */
-	target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
+	target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
 	if (target < nr_cpu_ids)
 		return 0;
 
@@ -1419,7 +1421,7 @@ static int __init intel_uncore_init(void)
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return -ENODEV;
 
-	max_packages = topology_max_packages();
+	max_dies = topology_max_packages() * topology_max_die_per_package();
 
 	uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
 	if (uncore_init->pci_init) {
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 79eb2e21e4f0..33aba2504cb1 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -108,7 +108,7 @@ struct intel_uncore_extra_reg {
 
 struct intel_uncore_box {
 	int pci_phys_id;
-	int pkgid;	/* Logical package ID */
+	int dieid;	/* Logical die ID */
 	int n_active;	/* number of active events */
 	int n_events;
 	int cpu;	/* cpu to collect events */
@@ -467,7 +467,7 @@ static inline void uncore_box_exit(struct intel_uncore_box *box)
 
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
-	return (box->pkgid < 0);
+	return (box->dieid < 0);
 }
 
 static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b10e04387f38..bbe89bc589f9 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1058,8 +1058,8 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve
 
 	if (reg1->idx != EXTRA_REG_NONE) {
 		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
-		int pkg = box->pkgid;
-		struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
+		int die = box->dieid;
+		struct pci_dev *filter_pdev = uncore_extra_pci_dev[die].dev[idx];
 
 		if (filter_pdev) {
 			pci_write_config_dword(filter_pdev, reg1->reg,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index e57d2ca2ed87..3eab6ece52b4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -105,7 +105,7 @@ struct cpuinfo_x86 {
 	int			x86_power;
 	unsigned long		loops_per_jiffy;
 	/* cpuid returned max cores value: */
-	u16			 x86_max_cores;
+	u16			x86_max_cores;
 	u16			apicid;
 	u16			initial_apicid;
 	u16			x86_clflush_size;
@@ -117,6 +117,8 @@ struct cpuinfo_x86 {
 	u16			logical_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
+	u16			cpu_die_id;
+	u16			logical_die_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0d3fe060a44f..e1356a3b8223 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -23,6 +23,7 @@ extern unsigned int num_processors;
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
 /* cpus sharing the last level cache: */
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 453cf38a1c33..4b14d2318251 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -106,15 +106,25 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #define topology_logical_package_id(cpu)	(cpu_data(cpu).logical_proc_id)
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
+#define topology_logical_die_id(cpu)		(cpu_data(cpu).logical_die_id)
+#define topology_die_id(cpu)			(cpu_data(cpu).cpu_die_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
 
 #ifdef CONFIG_SMP
+#define topology_die_cpumask(cpu)		(per_cpu(cpu_die_map, cpu))
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
 
+extern unsigned int __max_die_per_package;
+
+static inline int topology_max_die_per_package(void)
+{
+	return __max_die_per_package;
+}
+
 extern int __max_smt_threads;
 
 static inline int topology_max_smt_threads(void)
@@ -123,14 +133,21 @@ static inline int topology_max_smt_threads(void)
 }
 
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
+int topology_update_die_map(unsigned int dieid, unsigned int cpu);
 int topology_phys_to_logical_pkg(unsigned int pkg);
+int topology_phys_to_logical_die(unsigned int die, unsigned int cpu);
 bool topology_is_primary_thread(unsigned int cpu);
 bool topology_smt_supported(void);
 #else
 #define topology_max_packages()			(1)
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
+static inline int
+topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
+static inline int topology_phys_to_logical_die(unsigned int die,
+		unsigned int cpu) { return 0; }
+static inline int topology_max_die_per_package(void) { return 1; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
 static inline bool topology_smt_supported(void) { return false; }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8febe90470f4..309b6b9b49d4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1322,6 +1322,7 @@ static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
 		       cpu, apicid, c->initial_apicid);
 	}
 	BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
+	BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
 #else
 	c->logical_proc_id = 0;
 #endif
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 8f6c784141d1..ee48c3fc8a65 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -15,33 +15,66 @@
 /* leaf 0xb SMT level */
 #define SMT_LEVEL	0
 
-/* leaf 0xb sub-leaf types */
+/* extended topology sub-leaf types */
 #define INVALID_TYPE	0
 #define SMT_TYPE	1
 #define CORE_TYPE	2
+#define DIE_TYPE	5
 
 #define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-int detect_extended_topology_early(struct cpuinfo_x86 *c)
-{
 #ifdef CONFIG_SMP
+unsigned int __max_die_per_package __read_mostly = 1;
+EXPORT_SYMBOL(__max_die_per_package);
+
+/*
+ * Check if given CPUID extended toplogy "leaf" is implemented
+ */
+static int check_extended_topology_leaf(int leaf)
+{
 	unsigned int eax, ebx, ecx, edx;
 
-	if (c->cpuid_level < 0xb)
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
 		return -1;
 
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	return 0;
+}
+/*
+ * Return best CPUID Extended Toplogy Leaf supported
+ */
+static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
+{
+	if (c->cpuid_level >= 0x1f) {
+		if (check_extended_topology_leaf(0x1f) == 0)
+			return 0x1f;
+	}
 
-	/*
-	 * check if the cpuid leaf 0xb is actually implemented.
-	 */
-	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+	if (c->cpuid_level >= 0xb) {
+		if (check_extended_topology_leaf(0xb) == 0)
+			return 0xb;
+	}
+
+	return -1;
+}
+#endif
+
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx;
+	int leaf;
+
+	leaf = detect_extended_topology_leaf(c);
+	if (leaf < 0)
 		return -1;
 
 	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
 
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	/*
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
@@ -52,7 +85,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * Check for extended topology enumeration cpuid leaf, and if it
  * exists, use it for populating initial_apicid and cpu topology
  * detection.
  */
@@ -60,22 +93,28 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
+	unsigned int die_select_mask, die_level_siblings;
+	int leaf;
 
-	if (detect_extended_topology_early(c) < 0)
+	leaf = detect_extended_topology_leaf(c);
+	if (leaf < 0)
 		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	c->initial_apicid = edx;
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
 	do {
-		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
 		 * Check for the Core type in the implemented sub leaves.
@@ -83,23 +122,34 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
 			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
 			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-			break;
+			die_level_siblings = core_level_siblings;
+			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+		}
+		if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
+			die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 
 		sub_index++;
 	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
 
 	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
-
-	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width)
-						 & core_select_mask;
-	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+	die_select_mask = (~(-1 << die_plus_mask_width)) >>
+				core_plus_mask_width;
+
+	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
+				ht_mask_width) & core_select_mask;
+	c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
+				core_plus_mask_width) & die_select_mask;
+	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
+				die_plus_mask_width);
 	/*
 	 * Reinit the apicid, now that we have extended initial_apicid.
 	 */
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+	__max_die_per_package = (die_level_siblings / core_level_siblings);
 #endif
 	return 0;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1af7a2d89419..f78801114ee1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -89,6 +89,10 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
+/* representing HT, core, and die siblings of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
+EXPORT_PER_CPU_SYMBOL(cpu_die_map);
+
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
 /* Per CPU bogomips and other parameters */
@@ -99,6 +103,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
+static unsigned int logical_die __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
 int __read_mostly __max_smt_threads = 1;
@@ -306,6 +311,26 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg)
 	return -1;
 }
 EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+/**
+ * topology_phys_to_logical_die - Map a physical die id to logical
+ *
+ * Returns logical die id or -1 if not found
+ */
+int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
+{
+	int cpu;
+	int proc_id = cpu_data(cur_cpu).phys_proc_id;
+
+	for_each_possible_cpu(cpu) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->initialized && c->cpu_die_id == die_id &&
+		    c->phys_proc_id == proc_id)
+			return c->logical_die_id;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_die);
 
 /**
  * topology_update_package_map - Update the physical to logical package map
@@ -330,6 +355,29 @@ found:
 	cpu_data(cpu).logical_proc_id = new;
 	return 0;
 }
+/**
+ * topology_update_die_map - Update the physical to logical die map
+ * @die:	The die id as retrieved via CPUID
+ * @cpu:	The cpu for which this is updated
+ */
+int topology_update_die_map(unsigned int die, unsigned int cpu)
+{
+	int new;
+
+	/* Already available somewhere? */
+	new = topology_phys_to_logical_die(die, cpu);
+	if (new >= 0)
+		goto found;
+
+	new = logical_die++;
+	if (new != die) {
+		pr_info("CPU %u Converting physical %u to logical die %u\n",
+			cpu, die, new);
+	}
+found:
+	cpu_data(cpu).logical_die_id = new;
+	return 0;
+}
 
 void __init smp_store_boot_cpu_info(void)
 {
@@ -339,6 +387,7 @@ void __init smp_store_boot_cpu_info(void)
 	*c = boot_cpu_data;
 	c->cpu_index = id;
 	topology_update_package_map(c->phys_proc_id, id);
+	topology_update_die_map(c->cpu_die_id, id);
 	c->initialized = true;
 }
 
@@ -393,6 +442,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
+		    c->cpu_die_id == o->cpu_die_id &&
 		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
 			if (c->cpu_core_id == o->cpu_core_id)
 				return topology_sane(c, o, "smt");
@@ -404,6 +454,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
+		   c->cpu_die_id == o->cpu_die_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
 		return topology_sane(c, o, "smt");
 	}
@@ -466,6 +517,15 @@ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if ((c->phys_proc_id == o->phys_proc_id) &&
+		(c->cpu_die_id == o->cpu_die_id))
+		return true;
+	return false;
+}
+
+
 #if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
@@ -528,6 +588,7 @@ void set_cpu_sibling_map(int cpu)
 		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
+		cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
 		c->booted_cores = 1;
 		return;
 	}
@@ -576,6 +637,9 @@ void set_cpu_sibling_map(int cpu)
 		}
 		if (match_pkg(c, o) && !topology_same_node(c, o))
 			x86_has_numa_in_package = true;
+
+		if ((i == cpu) || (has_mp && match_die(c, o)))
+			link_mask(topology_die_cpumask, cpu, i);
 	}
 
 	threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -1180,6 +1244,7 @@ static __init void disable_smp(void)
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	cpumask_set_cpu(0, topology_sibling_cpumask(0));
 	cpumask_set_cpu(0, topology_core_cpumask(0));
+	cpumask_set_cpu(0, topology_die_cpumask(0));
 }
 
 /*
@@ -1275,6 +1340,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
 
@@ -1495,6 +1561,8 @@ static void remove_siblinginfo(int cpu)
 			cpu_data(sibling).booted_cores--;
 	}
 
+	for_each_cpu(sibling, topology_die_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
 	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
 		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
 	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
@@ -1502,6 +1570,7 @@ static void remove_siblinginfo(int cpu)
 	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
 	cpumask_clear(topology_core_cpumask(cpu));
+	cpumask_clear(topology_die_cpumask(cpu));
 	c->cpu_core_id = 0;
 	c->booted_cores = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 590fcf863006..77d81c1a63e9 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -251,6 +251,7 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
 	set_cpu_sibling_map(0);