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

3 files changed, 139 insertions, 19 deletions

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);