x86: convert cpuinfo_x86 array to a per_cpu array
cpu_data is currently an array defined using NR_CPUS. This means that
we overallocate since we will rarely really use maximum configured cpus.
When NR_CPU count is raised to 4096 the size of cpu_data becomes
3,145,728 bytes.
These changes were adopted from the sparc64 (and ia64) code. An
additional field was added to cpuinfo_x86 to be a non-ambiguous cpu
index. This corresponds to the index into a cpumask_t as well as the
per_cpu index. It's used in various places like show_cpuinfo().
cpu_data is defined to be the boot_cpu_data structure for the NON-SMP
case.
Signed-off-by: Mike Travis <travis@sgi.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@suse.de>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: Dmitry Torokhov <dtor@mail.ru>
Cc: "Antonino A. Daplas" <adaplas@pol.net>
Cc: Mark M. Hoffman <mhoffman@lightlink.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c
index 7c8f586..fd1fff6 100644
--- a/arch/x86/kernel/smpboot_64.c
+++ b/arch/x86/kernel/smpboot_64.c
@@ -84,8 +84,8 @@
EXPORT_SYMBOL(cpu_possible_map);
/* Per CPU bogomips and other parameters */
-struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
-EXPORT_SYMBOL(cpu_data);
+DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
+EXPORT_PER_CPU_SYMBOL(cpu_info);
/* Set when the idlers are all forked */
int smp_threads_ready;
@@ -138,9 +138,10 @@
static void __cpuinit smp_store_cpu_info(int id)
{
- struct cpuinfo_x86 *c = cpu_data + id;
+ struct cpuinfo_x86 *c = &cpu_data(id);
*c = boot_cpu_data;
+ c->cpu_index = id;
identify_cpu(c);
print_cpu_info(c);
}
@@ -237,7 +238,7 @@
/* maps the cpu to the sched domain representing multi-core */
cpumask_t cpu_coregroup_map(int cpu)
{
- struct cpuinfo_x86 *c = cpu_data + cpu;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
/*
* For perf, we return last level cache shared map.
* And for power savings, we return cpu_core_map
@@ -254,41 +255,41 @@
static inline void set_cpu_sibling_map(int cpu)
{
int i;
- struct cpuinfo_x86 *c = cpu_data;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
cpu_set(cpu, cpu_sibling_setup_map);
if (smp_num_siblings > 1) {
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) {
+ if (c->phys_proc_id == cpu_data(i).phys_proc_id &&
+ c->cpu_core_id == cpu_data(i).cpu_core_id) {
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);
- cpu_set(cpu, c[i].llc_shared_map);
+ cpu_set(i, c->llc_shared_map);
+ cpu_set(cpu, cpu_data(i).llc_shared_map);
}
}
} else {
cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
}
- cpu_set(cpu, c[cpu].llc_shared_map);
+ cpu_set(cpu, c->llc_shared_map);
if (current_cpu_data.x86_max_cores == 1) {
per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
- c[cpu].booted_cores = 1;
+ c->booted_cores = 1;
return;
}
for_each_cpu_mask(i, cpu_sibling_setup_map) {
if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
- cpu_set(i, c[cpu].llc_shared_map);
- cpu_set(cpu, c[i].llc_shared_map);
+ cpu_set(i, c->llc_shared_map);
+ cpu_set(cpu, cpu_data(i).llc_shared_map);
}
- if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
+ if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
cpu_set(i, per_cpu(cpu_core_map, cpu));
cpu_set(cpu, per_cpu(cpu_core_map, i));
/*
@@ -300,15 +301,15 @@
* the booted_cores for this new cpu
*/
if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
- c[cpu].booted_cores++;
+ c->booted_cores++;
/*
* increment the core count for all
* the other cpus in this package
*/
if (i != cpu)
- c[i].booted_cores++;
- } else if (i != cpu && !c[cpu].booted_cores)
- c[cpu].booted_cores = c[i].booted_cores;
+ cpu_data(i).booted_cores++;
+ } else if (i != cpu && !c->booted_cores)
+ c->booted_cores = cpu_data(i).booted_cores;
}
}
}
@@ -989,7 +990,7 @@
static void remove_siblinginfo(int cpu)
{
int sibling;
- struct cpuinfo_x86 *c = cpu_data;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
@@ -997,15 +998,15 @@
* last thread sibling in this cpu core going down
*/
if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
- c[sibling].booted_cores--;
+ cpu_data(sibling).booted_cores--;
}
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;
+ c->phys_proc_id = 0;
+ c->cpu_core_id = 0;
cpu_clear(cpu, cpu_sibling_setup_map);
}