[PATCH] x86_64: Allocate PDAs in the local node

Patch uses a static PDA array early at boot and reallocates processor PDA
with node local memory when kmalloc is ready, just before pda_init.
The boot_cpu_pda is needed since the cpu_pda is used even before pda_init for
that cpu is called (to set the static per-cpu areas offset table etc)
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/x86_64/kernel/head64.c

@@ -92,6 +92,9 @@ void __init x86_64_start_kernel(char * real_mode_data)
 	memcpy(init_level4_pgt, boot_level4_pgt, PTRS_PER_PGD*sizeof(pgd_t));
 	asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
 
+ 	for (i = 0; i < NR_CPUS; i++)
+ 		cpu_pda(i) = &boot_cpu_pda[i];
+
 	pda_init(0);
 	copy_bootdata(real_mode_data);
 #ifdef CONFIG_SMP

arch/x86_64/kernel/setup64.c

@@ -30,7 +30,8 @@ char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,};
 
 cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
 
-struct x8664_pda _cpu_pda[NR_CPUS] __cacheline_aligned;
+struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
+struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
 
 struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table }; 
 

arch/x86_64/kernel/smpboot.c

@@ -757,6 +757,23 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 		return -1;
 	}
 
+	/* 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);
+	}
+
+
 	c_idle.idle = get_idle_for_cpu(cpu);
 
 	if (c_idle.idle) {

include/asm-x86_64/pda.h

@@ -27,9 +27,10 @@ struct x8664_pda {
 	unsigned apic_timer_irqs;
 } ____cacheline_aligned_in_smp;
 
-extern struct x8664_pda _cpu_pda[];
+extern struct x8664_pda *_cpu_pda[];
+extern struct x8664_pda boot_cpu_pda[];
 
-#define cpu_pda(i) (&_cpu_pda[i])
+#define cpu_pda(i) (_cpu_pda[i])
 
 /* 
  * There is no fast way to get the base address of the PDA, all the accesses