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>

2 files changed, 18 insertions, 12 deletions

diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 9e392a30d197..777c8d8bd5e7 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -528,10 +528,6 @@ setup_arch (char **cmdline_p)
 
 #ifdef CONFIG_SMP
 	cpu_physical_id(0) = hard_smp_processor_id();
-
-	cpu_set(0, cpu_sibling_map[0]);
-	cpu_set(0, cpu_core_map[0]);
-
 	check_for_logical_procs();
 	if (smp_num_cpucores > 1)
 		printk(KERN_INFO
@@ -873,6 +869,14 @@ cpu_init (void)
 	void *cpu_data;
 
 	cpu_data = per_cpu_init();
+	/*
+	 * insert boot cpu into sibling and core mapes
+	 * (must be done after per_cpu area is setup)
+	 */
+	if (smp_processor_id() == 0) {
+		cpu_set(0, per_cpu(cpu_sibling_map, 0));
+		cpu_set(0, cpu_core_map[0]);
+	}
 
 	/*
 	 * We set ar.k3 so that assembly code in MCA handler can compute
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 308772f7cddc..c57dbce25c12 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -138,7 +138,9 @@ cpumask_t cpu_possible_map = CPU_MASK_NONE;
 EXPORT_SYMBOL(cpu_possible_map);
 
 cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned;
-cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned;
+DEFINE_PER_CPU_SHARED_ALIGNED(cpumask_t, cpu_sibling_map);
+EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
+
 int smp_num_siblings = 1;
 int smp_num_cpucores = 1;
 
@@ -650,12 +652,12 @@ clear_cpu_sibling_map(int cpu)
 {
 	int i;
 
-	for_each_cpu_mask(i, cpu_sibling_map[cpu])
-		cpu_clear(cpu, cpu_sibling_map[i]);
+	for_each_cpu_mask(i, per_cpu(cpu_sibling_map, cpu))
+		cpu_clear(cpu, per_cpu(cpu_sibling_map, i));
 	for_each_cpu_mask(i, cpu_core_map[cpu])
 		cpu_clear(cpu, cpu_core_map[i]);
 
-	cpu_sibling_map[cpu] = cpu_core_map[cpu] = CPU_MASK_NONE;
+	per_cpu(cpu_sibling_map, cpu) = cpu_core_map[cpu] = CPU_MASK_NONE;
 }
 
 static void
@@ -666,7 +668,7 @@ remove_siblinginfo(int cpu)
 	if (cpu_data(cpu)->threads_per_core == 1 &&
 	    cpu_data(cpu)->cores_per_socket == 1) {
 		cpu_clear(cpu, cpu_core_map[cpu]);
-		cpu_clear(cpu, cpu_sibling_map[cpu]);
+		cpu_clear(cpu, per_cpu(cpu_sibling_map, cpu));
 		return;
 	}
 
@@ -807,8 +809,8 @@ set_cpu_sibling_map(int cpu)
 			cpu_set(i, cpu_core_map[cpu]);
 			cpu_set(cpu, cpu_core_map[i]);
 			if (cpu_data(cpu)->core_id == cpu_data(i)->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));
 			}
 		}
 	}
@@ -839,7 +841,7 @@ __cpu_up (unsigned int cpu)
 
 	if (cpu_data(cpu)->threads_per_core == 1 &&
 	    cpu_data(cpu)->cores_per_socket == 1) {
-		cpu_set(cpu, cpu_sibling_map[cpu]);
+		cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
 		cpu_set(cpu, cpu_core_map[cpu]);
 		return 0;
 	}