1 files changed, 71 insertions, 9 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 362dd8953f48..fdbd47ceb84d 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;
@@ -210,17 +215,11 @@ static void notrace start_secondary(void *unused)
 	 * before cpu_init(), SMP booting is too fragile that we want to
 	 * limit the things done here to the most necessary things.
 	 */
-	if (boot_cpu_has(X86_FEATURE_PCID))
-		__write_cr4(__read_cr4() | X86_CR4_PCIDE);
+	cr4_init();
 
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
 	load_cr3(swapper_pg_dir);
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
 	__flush_tlb_all();
 #endif
 	load_current_idt();
@@ -300,6 +299,26 @@ 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
@@ -324,6 +343,29 @@ 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)
 {
@@ -333,6 +375,7 @@ 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;
 }
 
@@ -387,6 +430,7 @@ 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");
@@ -398,6 +442,7 @@ 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");
 	}
@@ -460,6 +505,15 @@ 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)
 {
@@ -522,6 +576,7 @@ 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;
 	}
@@ -570,6 +625,9 @@ 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));
@@ -1174,6 +1232,7 @@ 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));
 }
 
 /*
@@ -1269,6 +1328,7 @@ 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);
 	}
 
@@ -1308,8 +1368,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
-	native_pv_lock_init();
-
 	uv_system_init();
 
 	set_mtrr_aps_delayed_init();
@@ -1339,6 +1397,7 @@ void __init native_smp_prepare_boot_cpu(void)
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
 	cpu_set_state_online(me);
+	native_pv_lock_init();
 }
 
 void __init calculate_max_logical_packages(void)
@@ -1489,6 +1548,8 @@ 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))
@@ -1496,6 +1557,7 @@ 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);