cpumask: x86: convert cpu_sibling_map/cpu_core_map to cpumask_var_t

Impact: reduce per-cpu size for CONFIG_CPUMASK_OFFSTACK=y

In most places it's cleaner to use the accessors cpu_sibling_mask()
and cpu_core_mask() wrappers which already exist.

I couldn't avoid cleaning up the access in oprofile, either.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

arch/x86/include/asm/smp.h

@@ -21,19 +21,19 @@
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
-	return &per_cpu(cpu_sibling_map, cpu);
+	return per_cpu(cpu_sibling_map, cpu);
 }
 
 static inline struct cpumask *cpu_core_mask(int cpu)
 {
-	return &per_cpu(cpu_core_map, cpu);
+	return per_cpu(cpu_core_map, cpu);
 }
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);

arch/x86/include/asm/topology.h

@@ -249,8 +249,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
-#define topology_core_cpumask(cpu)		(&per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
 /* indicates that pointers to the topology cpumask_t maps are valid */
 #define arch_provides_topology_pointers		yes
@@ -264,7 +264,7 @@ struct pci_bus;
 void set_pci_bus_resources_arch_default(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
+#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 

arch/x86/kernel/cpu/cpufreq/p4-clockmod.c

@@ -203,7 +203,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	/* Errata workaround */

arch/x86/kernel/cpu/cpufreq/powernow-k8.c

@@ -56,7 +56,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 static int cpu_family = CPU_OPTERON;
 
 #ifndef CONFIG_SMP
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+static inline const struct cpumask *cpu_core_mask(int cpu)
+{
+	return cpumask_of(0);
+}
 #endif
 
 /* Return a frequency in MHz, given an input fid */
@@ -654,7 +657,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst,
 
 	dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -808,7 +811,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
 	/* fill in data */
 	data->numps = data->acpi_data.state_count;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 	powernow_k8_acpi_pst_values(data, 0);
 
@@ -1224,7 +1227,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (cpu_family == CPU_HW_PSTATE)
 		cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
 	else
-		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
+		cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	if (cpu_family == CPU_HW_PSTATE)
@@ -1286,7 +1289,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	unsigned int khz = 0;
 	unsigned int first;
 
-	first = first_cpu(per_cpu(cpu_core_map, cpu));
+	first = cpumask_first(cpu_core_mask(cpu));
 	data = per_cpu(powernow_data, first);
 
 	if (!data)

arch/x86/kernel/cpu/cpufreq/speedstep-ich.c

@@ -322,7 +322,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	cpus_allowed = current->cpus_allowed;

arch/x86/kernel/cpu/mcheck/mce_amd_64.c

@@ -477,7 +477,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(&per_cpu(cpu_core_map, cpu));
+		i = cpumask_first(cpu_core_mask(cpu));
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -497,7 +497,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+		cpumask_copy(b->cpus, cpu_core_mask(cpu));
 		per_cpu(threshold_banks, cpu)[bank] = b;
 		goto out;
 	}
@@ -521,7 +521,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+	cpumask_copy(b->cpus, cpu_core_mask(cpu));
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;

arch/x86/kernel/cpu/proc.c

@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpus_weight(per_cpu(cpu_core_map, cpu)));
+			   cpumask_weight(cpu_sibling_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);

arch/x86/kernel/smpboot.c

@@ -101,11 +101,11 @@ EXPORT_SYMBOL(smp_num_siblings);
 DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
 
 /* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* Per CPU bogomips and other parameters */
@@ -1026,6 +1026,8 @@ static void __init smp_cpu_index_default(void)
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
+	unsigned int i;
+
 	preempt_disable();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
@@ -1039,6 +1041,12 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	boot_cpu_logical_apicid = logical_smp_processor_id();
 #endif
 	current_thread_info()->cpu = 0;  /* needed? */
+	for_each_possible_cpu(i) {
+		alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		cpumask_clear(per_cpu(cpu_core_map, i));
+		cpumask_clear(per_cpu(cpu_sibling_map, i));
+	}
 	set_cpu_sibling_map(0);
 
 	enable_IR_x2apic();

arch/x86/oprofile/op_model_p4.c

@@ -380,7 +380,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
+	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
 #endif
 	return 0;
 }