x86: remove static boot_cpu_pda array v2
* Remove the boot_cpu_pda array and pointer table from the data section.
Allocate the pointer table and array during init. do_boot_cpu()
will reallocate the pda in node local memory and if the cpu is being
brought up before the bootmem array is released (after_bootmem = 0),
then it will free the initial pda. This will happen for all cpus
present at system startup.
This removes 512k + 32k bytes from the data section.
For inclusion into sched-devel/latest tree.
Based on:
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
+ sched-devel/latest .../mingo/linux-2.6-sched-devel.git
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 913af83..dd12c1c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -101,6 +101,50 @@
*/
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
+static inline void setup_cpu_pda_map(void) { }
+
+#elif !defined(CONFIG_SMP)
+static inline void setup_cpu_pda_map(void) { }
+
+#else /* CONFIG_SMP && CONFIG_X86_64 */
+
+/*
+ * Allocate cpu_pda pointer table and array via alloc_bootmem.
+ */
+static void __init setup_cpu_pda_map(void)
+{
+ char *pda;
+ struct x8664_pda **new_cpu_pda;
+ unsigned long size;
+ int cpu;
+
+ size = roundup(sizeof(struct x8664_pda), cache_line_size());
+
+ /* allocate cpu_pda array and pointer table */
+ {
+ unsigned long tsize = nr_cpu_ids * sizeof(void *);
+ unsigned long asize = size * (nr_cpu_ids - 1);
+
+ tsize = roundup(tsize, cache_line_size());
+ new_cpu_pda = alloc_bootmem(tsize + asize);
+ pda = (char *)new_cpu_pda + tsize;
+ }
+
+ /* initialize pointer table to static pda's */
+ for_each_possible_cpu(cpu) {
+ if (cpu == 0) {
+ /* leave boot cpu pda in place */
+ new_cpu_pda[0] = cpu_pda(0);
+ continue;
+ }
+ new_cpu_pda[cpu] = (struct x8664_pda *)pda;
+ new_cpu_pda[cpu]->in_bootmem = 1;
+ pda += size;
+ }
+
+ /* point to new pointer table */
+ _cpu_pda = new_cpu_pda;
+}
#endif
/*
@@ -110,46 +154,43 @@
*/
void __init setup_per_cpu_areas(void)
{
- int i, highest_cpu = 0;
- unsigned long size;
+ ssize_t size = PERCPU_ENOUGH_ROOM;
+ char *ptr;
+ int cpu;
#ifdef CONFIG_HOTPLUG_CPU
prefill_possible_map();
+#else
+ nr_cpu_ids = num_processors;
#endif
+ /* Setup cpu_pda map */
+ setup_cpu_pda_map();
+
/* Copy section for each CPU (we discard the original) */
size = PERCPU_ENOUGH_ROOM;
printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n",
size);
- for_each_possible_cpu(i) {
- char *ptr;
+ for_each_possible_cpu(cpu) {
#ifndef CONFIG_NEED_MULTIPLE_NODES
ptr = alloc_bootmem_pages(size);
#else
- int node = early_cpu_to_node(i);
+ int node = early_cpu_to_node(cpu);
if (!node_online(node) || !NODE_DATA(node)) {
ptr = alloc_bootmem_pages(size);
printk(KERN_INFO
"cpu %d has no node %d or node-local memory\n",
- i, node);
+ cpu, node);
}
else
ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
#endif
- if (!ptr)
- panic("Cannot allocate cpu data for CPU %d\n", i);
-#ifdef CONFIG_X86_64
- cpu_pda(i)->data_offset = ptr - __per_cpu_start;
-#else
- __per_cpu_offset[i] = ptr - __per_cpu_start;
-#endif
+ per_cpu_offset(cpu) = ptr - __per_cpu_start;
memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
- highest_cpu = i;
}
- nr_cpu_ids = highest_cpu + 1;
printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
NR_CPUS, nr_cpu_ids, nr_node_ids);
@@ -199,7 +240,7 @@
{
int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
- if (node != NUMA_NO_NODE)
+ if (cpu_pda(cpu) && node != NUMA_NO_NODE)
cpu_pda(cpu)->nodenumber = node;
if (cpu_to_node_map)