x86: Convert cpu_core_map to be a per cpu variable

This is from an earlier message from 'Christoph Lameter':

    cpu_core_map is currently an array defined using NR_CPUS. This means that
    we overallocate since we will rarely really use maximum configured cpu.

    If we put the cpu_core_map into the per cpu area then it will be allocated
    for each processor as it comes online.

    This means that the core map cannot be accessed until the per cpu area
    has been allocated. Xen does a weird thing here looping over all processors
    and zeroing the masks that are not yet allocated and that will be zeroed
    when they are allocated. I commented the code out.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 54 insertions, 42 deletions

diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index ffd01e5dcb5..2ca43ba32bc 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -595,7 +595,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	dmi_check_system(sw_any_bug_dmi_table);
 	if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) {
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-		policy->cpus = cpu_core_map[cpu];
+		policy->cpus = per_cpu(cpu_core_map, cpu);
 	}
 #endif
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index b273b69cfdd..c06ac680c9c 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -57,7 +57,7 @@ static struct powernow_k8_data *powernow_data[NR_CPUS];
 static int cpu_family = CPU_OPTERON;
 
 #ifndef CONFIG_SMP
-static cpumask_t cpu_core_map[1];
+DEFINE_PER_CPU(cpumask_t, cpu_core_map);
 #endif
 
 /* Return a frequency in MHz, given an input fid */
@@ -667,7 +667,7 @@ 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(cpu_core_map[data->cpu]) == data->cpu)
+	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -821,7 +821,7 @@ 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(cpu_core_map[data->cpu]) == data->cpu)
+	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
 		print_basics(data);
 	powernow_k8_acpi_pst_values(data, 0);
 
@@ -1214,7 +1214,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cpus = cpumask_of_cpu(pol->cpu);
 	else
-		pol->cpus = cpu_core_map[pol->cpu];
+		pol->cpus = per_cpu(cpu_core_map, pol->cpu);
 	data->available_cores = &(pol->cpus);
 
 	/* Take a crude guess here.
@@ -1281,7 +1281,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	cpumask_t oldmask = current->cpus_allowed;
 	unsigned int khz = 0;
 
-	data = powernow_data[first_cpu(cpu_core_map[cpu])];
+	data = powernow_data[first_cpu(per_cpu(cpu_core_map, cpu))];
 
 	if (!data)
 		return -EINVAL;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 1e31b6caffb..879a0f789b1 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -122,7 +122,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #ifdef CONFIG_X86_HT
 	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(cpu_core_map[n]));
+		seq_printf(m, "siblings\t: %d\n",
+				cpus_weight(per_cpu(cpu_core_map, n)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 	}
diff --git a/arch/x86/kernel/mce_amd_64.c b/arch/x86/kernel/mce_amd_64.c
index 2f8a7f18b0f..805b62b1e0d 100644
--- a/arch/x86/kernel/mce_amd_64.c
+++ b/arch/x86/kernel/mce_amd_64.c
@@ -472,7 +472,7 @@ 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 = first_cpu(cpu_core_map[cpu]);
+		i = first_cpu(per_cpu(cpu_core_map, cpu));
 
 		/* first core not up yet */
 		if (cpu_data[i].cpu_core_id)
@@ -492,7 +492,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		b->cpus = cpu_core_map[cpu];
+		b->cpus = per_cpu(cpu_core_map, cpu);
 		per_cpu(threshold_banks, cpu)[bank] = b;
 		goto out;
 	}
@@ -509,7 +509,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	b->cpus = CPU_MASK_ALL;
 #else
-	b->cpus = cpu_core_map[cpu];
+	b->cpus = per_cpu(cpu_core_map, cpu);
 #endif
 	err = kobject_register(&b->kobj);
 	if (err)
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index b7da90e79c7..85b5b6310ac 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -1070,7 +1070,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (smp_num_siblings * c->x86_max_cores > 1) {
 		int cpu = c - cpu_data;
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
-		seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[cpu]));
+		seq_printf(m, "siblings\t: %d\n",
+			       cpus_weight(per_cpu(cpu_core_map, 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);
 	}
diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c
index e4f61d1c624..4cbab48ba86 100644
--- a/arch/x86/kernel/smpboot_32.c
+++ b/arch/x86/kernel/smpboot_32.c
@@ -74,8 +74,8 @@ cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* bitmap of online cpus */
 cpumask_t cpu_online_map __read_mostly;
@@ -300,7 +300,7 @@ cpumask_t cpu_coregroup_map(int cpu)
 	 * And for power savings, we return cpu_core_map
 	 */
 	if (sched_mc_power_savings || sched_smt_power_savings)
-		return cpu_core_map[cpu];
+		return per_cpu(cpu_core_map, cpu);
 	else
 		return c->llc_shared_map;
 }
@@ -321,8 +321,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 			    c[cpu].cpu_core_id == c[i].cpu_core_id) {
 				cpu_set(i, cpu_sibling_map[cpu]);
 				cpu_set(cpu, cpu_sibling_map[i]);
-				cpu_set(i, cpu_core_map[cpu]);
-				cpu_set(cpu, cpu_core_map[i]);
+				cpu_set(i, per_cpu(cpu_core_map, cpu));
+				cpu_set(cpu, per_cpu(cpu_core_map, i));
 				cpu_set(i, c[cpu].llc_shared_map);
 				cpu_set(cpu, c[i].llc_shared_map);
 			}
@@ -334,7 +334,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	cpu_set(cpu, c[cpu].llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
-		cpu_core_map[cpu] = cpu_sibling_map[cpu];
+		per_cpu(cpu_core_map, cpu) = cpu_sibling_map[cpu];
 		c[cpu].booted_cores = 1;
 		return;
 	}
@@ -346,8 +346,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 			cpu_set(cpu, c[i].llc_shared_map);
 		}
 		if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
-			cpu_set(i, cpu_core_map[cpu]);
-			cpu_set(cpu, cpu_core_map[i]);
+			cpu_set(i, per_cpu(cpu_core_map, cpu));
+			cpu_set(cpu, per_cpu(cpu_core_map, i));
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
@@ -984,7 +984,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 					   " Using dummy APIC emulation.\n");
 		map_cpu_to_logical_apicid();
 		cpu_set(0, cpu_sibling_map[0]);
-		cpu_set(0, cpu_core_map[0]);
+		cpu_set(0, per_cpu(cpu_core_map, 0));
 		return;
 	}
 
@@ -1009,7 +1009,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 		smpboot_clear_io_apic_irqs();
 		phys_cpu_present_map = physid_mask_of_physid(0);
 		cpu_set(0, cpu_sibling_map[0]);
-		cpu_set(0, cpu_core_map[0]);
+		cpu_set(0, per_cpu(cpu_core_map, 0));
 		return;
 	}
 
@@ -1024,7 +1024,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 		smpboot_clear_io_apic_irqs();
 		phys_cpu_present_map = physid_mask_of_physid(0);
 		cpu_set(0, cpu_sibling_map[0]);
-		cpu_set(0, cpu_core_map[0]);
+		cpu_set(0, per_cpu(cpu_core_map, 0));
 		return;
 	}
 
@@ -1107,11 +1107,11 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 	 */
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
 		cpus_clear(cpu_sibling_map[cpu]);
-		cpus_clear(cpu_core_map[cpu]);
+		cpus_clear(per_cpu(cpu_core_map, cpu));
 	}
 
 	cpu_set(0, cpu_sibling_map[0]);
-	cpu_set(0, cpu_core_map[0]);
+	cpu_set(0, per_cpu(cpu_core_map, 0));
 
 	smpboot_setup_io_apic();
 
@@ -1148,9 +1148,9 @@ void remove_siblinginfo(int cpu)
 	int sibling;
 	struct cpuinfo_x86 *c = cpu_data;
 
-	for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
-		cpu_clear(cpu, cpu_core_map[sibling]);
-		/*
+	for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
+		cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
+		/*/
 		 * last thread sibling in this cpu core going down
 		 */
 		if (cpus_weight(cpu_sibling_map[cpu]) == 1)
@@ -1160,7 +1160,7 @@ void remove_siblinginfo(int cpu)
 	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
 		cpu_clear(cpu, cpu_sibling_map[sibling]);
 	cpus_clear(cpu_sibling_map[cpu]);
-	cpus_clear(cpu_core_map[cpu]);
+	cpus_clear(per_cpu(cpu_core_map, cpu));
 	c[cpu].phys_proc_id = 0;
 	c[cpu].cpu_core_id = 0;
 	cpu_clear(cpu, cpu_sibling_setup_map);
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index 720a7d1f886..6723c862282 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -95,8 +95,8 @@ cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /*
  * Trampoline 80x86 program as an array.
@@ -243,7 +243,7 @@ cpumask_t cpu_coregroup_map(int cpu)
 	 * And for power savings, we return cpu_core_map
 	 */
 	if (sched_mc_power_savings || sched_smt_power_savings)
-		return cpu_core_map[cpu];
+		return per_cpu(cpu_core_map, cpu);
 	else
 		return c->llc_shared_map;
 }
@@ -264,8 +264,8 @@ static inline void set_cpu_sibling_map(int cpu)
 			    c[cpu].cpu_core_id == c[i].cpu_core_id) {
 				cpu_set(i, cpu_sibling_map[cpu]);
 				cpu_set(cpu, cpu_sibling_map[i]);
-				cpu_set(i, cpu_core_map[cpu]);
-				cpu_set(cpu, cpu_core_map[i]);
+				cpu_set(i, per_cpu(cpu_core_map, cpu));
+				cpu_set(cpu, per_cpu(cpu_core_map, i));
 				cpu_set(i, c[cpu].llc_shared_map);
 				cpu_set(cpu, c[i].llc_shared_map);
 			}
@@ -277,7 +277,7 @@ static inline void set_cpu_sibling_map(int cpu)
 	cpu_set(cpu, c[cpu].llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
-		cpu_core_map[cpu] = cpu_sibling_map[cpu];
+		per_cpu(cpu_core_map, cpu) = cpu_sibling_map[cpu];
 		c[cpu].booted_cores = 1;
 		return;
 	}
@@ -289,8 +289,8 @@ static inline void set_cpu_sibling_map(int cpu)
 			cpu_set(cpu, c[i].llc_shared_map);
 		}
 		if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
-			cpu_set(i, cpu_core_map[cpu]);
-			cpu_set(cpu, cpu_core_map[i]);
+			cpu_set(i, per_cpu(cpu_core_map, cpu));
+			cpu_set(cpu, per_cpu(cpu_core_map, i));
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
@@ -736,7 +736,7 @@ static __init void disable_smp(void)
 	else
 		phys_cpu_present_map = physid_mask_of_physid(0);
 	cpu_set(0, cpu_sibling_map[0]);
-	cpu_set(0, cpu_core_map[0]);
+	cpu_set(0, per_cpu(cpu_core_map, 0));
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -971,8 +971,8 @@ static void remove_siblinginfo(int cpu)
 	int sibling;
 	struct cpuinfo_x86 *c = cpu_data;
 
-	for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
-		cpu_clear(cpu, cpu_core_map[sibling]);
+	for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
+		cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
 		/*
 		 * last thread sibling in this cpu core going down
 		 */
@@ -983,7 +983,7 @@ static void remove_siblinginfo(int cpu)
 	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
 		cpu_clear(cpu, cpu_sibling_map[sibling]);
 	cpus_clear(cpu_sibling_map[cpu]);
-	cpus_clear(cpu_core_map[cpu]);
+	cpus_clear(per_cpu(cpu_core_map, cpu));
 	c[cpu].phys_proc_id = 0;
 	c[cpu].cpu_core_id = 0;
 	cpu_clear(cpu, cpu_sibling_setup_map);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 557b8e24706..539d42530fc 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -148,7 +148,12 @@ void __init xen_smp_prepare_boot_cpu(void)
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
 		cpus_clear(cpu_sibling_map[cpu]);
-		cpus_clear(cpu_core_map[cpu]);
+		/*
+		 * cpu_core_map lives in a per cpu area that is cleared
+		 * when the per cpu array is allocated.
+		 *
+		 * cpus_clear(per_cpu(cpu_core_map, cpu));
+		 */
 	}
 
 	xen_setup_vcpu_info_placement();
@@ -160,7 +165,12 @@ void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
 		cpus_clear(cpu_sibling_map[cpu]);
-		cpus_clear(cpu_core_map[cpu]);
+		/*
+		 * cpu_core_ map will be zeroed when the per
+		 * cpu area is allocated.
+		 *
+		 * cpus_clear(per_cpu(cpu_core_map, cpu));
+		 */
 	}
 
 	smp_store_cpu_info(0);