Convert cpu_sibling_map to be a per cpu variable

Convert cpu_sibling_map from a static array sized by NR_CPUS to a per_cpu
variable.  This saves sizeof(cpumask_t) * NR unused cpus.  Access is mostly
from startup and CPU HOTPLUG functions.

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>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 38 insertions, 38 deletions

diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 8eb414b..793eae8 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -200,7 +200,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	policy->cpus = cpu_sibling_map[policy->cpu];
+	policy->cpus = per_cpu(cpu_sibling_map, policy->cpu);
 #endif
 
 	/* Errata workaround */
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 36685e8..14d68aa 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/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
-	policy->cpus = cpu_sibling_map[policy->cpu];
+	policy->cpus = per_cpu(cpu_sibling_map, policy->cpu);
 #endif
 
 	cpus_allowed = current->cpus_allowed;
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index e2f4a1c..4ee1e5e 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -378,7 +378,7 @@ static struct irq_cpu_info {
 
 #define IRQ_ALLOWED(cpu, allowed_mask)	cpu_isset(cpu, allowed_mask)
 
-#define CPU_TO_PACKAGEINDEX(i) (first_cpu(cpu_sibling_map[i]))
+#define CPU_TO_PACKAGEINDEX(i) (first_cpu(per_cpu(cpu_sibling_map, i)))
 
 static cpumask_t balance_irq_affinity[NR_IRQS] = {
 	[0 ... NR_IRQS-1] = CPU_MASK_ALL
@@ -598,7 +598,7 @@ tryanotherirq:
 	 * (A+B)/2 vs B
 	 */
 	load = CPU_IRQ(min_loaded) >> 1;
-	for_each_cpu_mask(j, cpu_sibling_map[min_loaded]) {
+	for_each_cpu_mask(j, per_cpu(cpu_sibling_map, min_loaded)) {
 		if (load > CPU_IRQ(j)) {
 			/* This won't change cpu_sibling_map[min_loaded] */
 			load = CPU_IRQ(j);
diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c
index 4cbab48..31fc08b 100644
--- a/arch/x86/kernel/smpboot_32.c
+++ b/arch/x86/kernel/smpboot_32.c
@@ -70,8 +70,8 @@ EXPORT_SYMBOL(smp_num_siblings);
 int cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID};
 
 /* representing HT siblings of each logical CPU */
-cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_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);
@@ -319,8 +319,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		for_each_cpu_mask(i, cpu_sibling_setup_map) {
 			if (c[cpu].phys_proc_id == c[i].phys_proc_id &&
 			    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, per_cpu(cpu_sibling_map, cpu));
+				cpu_set(cpu, per_cpu(cpu_sibling_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);
@@ -328,13 +328,13 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 			}
 		}
 	} else {
-		cpu_set(cpu, cpu_sibling_map[cpu]);
+		cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
 	}
 
 	cpu_set(cpu, c[cpu].llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
-		per_cpu(cpu_core_map, cpu) = cpu_sibling_map[cpu];
+		per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
 		c[cpu].booted_cores = 1;
 		return;
 	}
@@ -351,12 +351,12 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+			if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
 				 */
-				if (first_cpu(cpu_sibling_map[i]) == i)
+				if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
 					c[cpu].booted_cores++;
 				/*
 				 * increment the core count for all
@@ -983,7 +983,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 			printk(KERN_NOTICE "Local APIC not detected."
 					   " Using dummy APIC emulation.\n");
 		map_cpu_to_logical_apicid();
-		cpu_set(0, cpu_sibling_map[0]);
+		cpu_set(0, per_cpu(cpu_sibling_map, 0));
 		cpu_set(0, per_cpu(cpu_core_map, 0));
 		return;
 	}
@@ -1008,7 +1008,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 		printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n");
 		smpboot_clear_io_apic_irqs();
 		phys_cpu_present_map = physid_mask_of_physid(0);
-		cpu_set(0, cpu_sibling_map[0]);
+		cpu_set(0, per_cpu(cpu_sibling_map, 0));
 		cpu_set(0, per_cpu(cpu_core_map, 0));
 		return;
 	}
@@ -1023,7 +1023,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 		printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n");
 		smpboot_clear_io_apic_irqs();
 		phys_cpu_present_map = physid_mask_of_physid(0);
-		cpu_set(0, cpu_sibling_map[0]);
+		cpu_set(0, per_cpu(cpu_sibling_map, 0));
 		cpu_set(0, per_cpu(cpu_core_map, 0));
 		return;
 	}
@@ -1102,15 +1102,15 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 	Dprintk("Boot done.\n");
 
 	/*
-	 * construct cpu_sibling_map[], so that we can tell sibling CPUs
+	 * construct cpu_sibling_map, so that we can tell sibling CPUs
 	 * efficiently.
 	 */
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
-		cpus_clear(cpu_sibling_map[cpu]);
+		cpus_clear(per_cpu(cpu_sibling_map, cpu));
 		cpus_clear(per_cpu(cpu_core_map, cpu));
 	}
 
-	cpu_set(0, cpu_sibling_map[0]);
+	cpu_set(0, per_cpu(cpu_sibling_map, 0));
 	cpu_set(0, per_cpu(cpu_core_map, 0));
 
 	smpboot_setup_io_apic();
@@ -1153,13 +1153,13 @@ void remove_siblinginfo(int cpu)
 		/*/
 		 * last thread sibling in this cpu core going down
 		 */
-		if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+		if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
 			c[sibling].booted_cores--;
 	}
 			
-	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
-		cpu_clear(cpu, cpu_sibling_map[sibling]);
-	cpus_clear(cpu_sibling_map[cpu]);
+	for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
+		cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
+	cpus_clear(per_cpu(cpu_sibling_map, cpu));
 	cpus_clear(per_cpu(cpu_core_map, cpu));
 	c[cpu].phys_proc_id = 0;
 	c[cpu].cpu_core_id = 0;
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index 6723c86..0faa0a0 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -91,8 +91,8 @@ EXPORT_SYMBOL(cpu_data);
 int smp_threads_ready;
 
 /* representing HT siblings of each logical CPU */
-cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_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);
@@ -262,8 +262,8 @@ static inline void set_cpu_sibling_map(int cpu)
 		for_each_cpu_mask(i, cpu_sibling_setup_map) {
 			if (c[cpu].phys_proc_id == c[i].phys_proc_id &&
 			    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, per_cpu(cpu_sibling_map, cpu));
+				cpu_set(cpu, per_cpu(cpu_sibling_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);
@@ -271,13 +271,13 @@ static inline void set_cpu_sibling_map(int cpu)
 			}
 		}
 	} else {
-		cpu_set(cpu, cpu_sibling_map[cpu]);
+		cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
 	}
 
 	cpu_set(cpu, c[cpu].llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
-		per_cpu(cpu_core_map, cpu) = cpu_sibling_map[cpu];
+		per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
 		c[cpu].booted_cores = 1;
 		return;
 	}
@@ -294,12 +294,12 @@ static inline void set_cpu_sibling_map(int cpu)
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+			if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
 				 */
-				if (first_cpu(cpu_sibling_map[i]) == i)
+				if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
 					c[cpu].booted_cores++;
 				/*
 				 * increment the core count for all
@@ -735,7 +735,7 @@ static __init void disable_smp(void)
 		phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
 	else
 		phys_cpu_present_map = physid_mask_of_physid(0);
-	cpu_set(0, cpu_sibling_map[0]);
+	cpu_set(0, per_cpu(cpu_sibling_map, 0));
 	cpu_set(0, per_cpu(cpu_core_map, 0));
 }
 
@@ -976,13 +976,13 @@ static void remove_siblinginfo(int cpu)
 		/*
 		 * last thread sibling in this cpu core going down
 		 */
-		if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+		if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
 			c[sibling].booted_cores--;
 	}
 			
-	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
-		cpu_clear(cpu, cpu_sibling_map[sibling]);
-	cpus_clear(cpu_sibling_map[cpu]);
+	for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
+		cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
+	cpus_clear(per_cpu(cpu_sibling_map, cpu));
 	cpus_clear(per_cpu(cpu_core_map, cpu));
 	c[cpu].phys_proc_id = 0;
 	c[cpu].cpu_core_id = 0;
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 4792592..56b4757 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -379,7 +379,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return (cpu != first_cpu(cpu_sibling_map[cpu]));
+	return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
 #endif	
 	return 0;
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 539d425..4fa33c2 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -147,7 +147,7 @@ void __init xen_smp_prepare_boot_cpu(void)
 	make_lowmem_page_readwrite(&per_cpu__gdt_page);
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
-		cpus_clear(cpu_sibling_map[cpu]);
+		cpus_clear(per_cpu(cpu_sibling_map, cpu));
 		/*
 		 * cpu_core_map lives in a per cpu area that is cleared
 		 * when the per cpu array is allocated.
@@ -164,7 +164,7 @@ void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	unsigned cpu;
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
-		cpus_clear(cpu_sibling_map[cpu]);
+		cpus_clear(per_cpu(cpu_sibling_map, cpu));
 		/*
 		 * cpu_core_ map will be zeroed when the per
 		 * cpu area is allocated.