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>

4 files changed, 131 insertions, 35 deletions

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index e25c57b8aa84..0ab59edd7067 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -25,6 +25,24 @@
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
 
+/* boot cpu pda */
+static struct x8664_pda _boot_cpu_pda __read_mostly;
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * We install an empty cpu_pda pointer table to trap references before
+ * the actual cpu_pda pointer table is created in setup_cpu_pda_map().
+ */
+static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata;
+#else
+static struct x8664_pda *__cpu_pda[1] __read_mostly;
+#endif
+
+#else /* !CONFIG_SMP (NR_CPUS will be 1) */
+static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly;
+#endif
+
 static void __init zap_identity_mappings(void)
 {
         pgd_t *pgd = pgd_offset_k(0UL);
@@ -156,10 +174,12 @@ void __init x86_64_start_kernel(char * real_mode_data)
 
         early_printk("Kernel alive\n");
 
-        for (i = 0; i < NR_CPUS; i++)
-                cpu_pda(i) = &boot_cpu_pda[i];
-
+        _cpu_pda = __cpu_pda;
+        cpu_pda(0) = &_boot_cpu_pda;
         pda_init(0);
+
+        early_printk("Kernel really alive\n");
+
         copy_bootdata(__va(real_mode_data));
 
         reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 913af838c3c5..dd12c1c84a8f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -101,6 +101,50 @@ static inline void setup_cpumask_of_cpu(void) { }
  */
 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 @@ EXPORT_SYMBOL(__per_cpu_offset);
  */
 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 @@ void __cpuinit numa_set_node(int cpu, int node)
 {
         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)
diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c
index aee0e8200777..631ea6cc01d8 100644
--- a/arch/x86/kernel/setup64.c
+++ b/arch/x86/kernel/setup64.c
@@ -12,6 +12,7 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/kgdb.h>
+#include <linux/topology.h>
 #include <asm/pda.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -34,9 +35,8 @@ struct boot_params boot_params;
 
 cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
 
-struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
+struct x8664_pda **_cpu_pda __read_mostly;
 EXPORT_SYMBOL(_cpu_pda);
-struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
 
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 
@@ -114,8 +114,10 @@ void pda_init(int cpu)
                         __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
                 if (!pda->irqstackptr)
                         panic("cannot allocate irqstack for cpu %d", cpu); 
-        }
 
+                if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
+                        pda->nodenumber = cpu_to_node(cpu);
+        }
 
         pda->irqstackptr += IRQSTACKSIZE-64;
 } 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 036604d3daed..bf0833487455 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -816,6 +816,43 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
         complete(&c_idle->done);
 }
 
+/*
+ * Allocate node local memory for the AP pda.
+ *
+ * Must be called after the _cpu_pda pointer table is initialized.
+ */
+static int __cpuinit get_local_pda(int cpu)
+{
+        struct x8664_pda *oldpda, *newpda;
+        unsigned long size = sizeof(struct x8664_pda);
+        int node = cpu_to_node(cpu);
+
+        if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
+                return 0;
+
+        oldpda = cpu_pda(cpu);
+        newpda = kmalloc_node(size, GFP_ATOMIC, node);
+        if (!newpda) {
+                printk(KERN_ERR "Could not allocate node local PDA "
+                        "for CPU %d on node %d\n", cpu, node);
+
+                if (oldpda)
+                        return 0;       /* have a usable pda */
+                else
+                        return -1;
+        }
+
+        if (oldpda) {
+                memcpy(newpda, oldpda, size);
+                if (!after_bootmem)
+                        free_bootmem((unsigned long)oldpda, size);
+        }
+
+        newpda->in_bootmem = 0;
+        cpu_pda(cpu) = newpda;
+        return 0;
+}
+
 static int __cpuinit do_boot_cpu(int apicid, int cpu)
 /*
  * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
@@ -841,19 +878,11 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
         }
 
         /* Allocate node local memory for AP pdas */
-        if (cpu_pda(cpu) == &boot_cpu_pda[cpu]) {
-                struct x8664_pda *newpda, *pda;
-                int node = cpu_to_node(cpu);
-                pda = cpu_pda(cpu);
-                newpda = kmalloc_node(sizeof(struct x8664_pda), GFP_ATOMIC,
-                                      node);
-                if (newpda) {
-                        memcpy(newpda, pda, sizeof(struct x8664_pda));
-                        cpu_pda(cpu) = newpda;
-                } else
-                        printk(KERN_ERR
-                "Could not allocate node local PDA for CPU %d on node %d\n",
-                                cpu, node);
+        if (cpu > 0) {
+                boot_error = get_local_pda(cpu);
+                if (boot_error)
+                        goto restore_state;
+                        /* if can't get pda memory, can't start cpu */
         }
 #endif
 
@@ -972,6 +1001,8 @@ do_rest:
                 }
         }
 
+restore_state:
+
         if (boot_error) {
                 /* Try to put things back the way they were before ... */
                 unmap_cpu_to_logical_apicid(cpu);
@@ -1347,6 +1378,8 @@ __init void prefill_possible_map(void)
 
         for (i = 0; i < possible; i++)
                 cpu_set(i, cpu_possible_map);
+
+        nr_cpu_ids = possible;
 }
 
 static void __ref remove_cpu_from_maps(int cpu)