[PATCH] x86_64: Speed up numa_node_id by putting it directly into the PDA

Not go from the CPU number to an mapping array.
Mode number is often used now in fast paths.

This also adds a generic numa_node_id to all the topology includes

Suggested by Eric Dumazet

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/asm-x86_64/numa.h

@@ -17,6 +17,8 @@ extern void numa_add_cpu(int cpu);
 extern void numa_init_array(void);
 extern int numa_off;
 
+extern void numa_set_node(int cpu, int node);
+
 extern unsigned char apicid_to_node[256];
 
 #define NUMA_NO_NODE 0xff

include/asm-x86_64/pda.h

@@ -15,6 +15,7 @@ struct x8664_pda {
         int irqcount;		    /* Irq nesting counter. Starts with -1 */  	
 	int cpunumber;		    /* Logical CPU number */
 	char *irqstackptr;	/* top of irqstack */
+	int nodenumber;		    /* number of current node */
 	unsigned int __softirq_pending;
 	unsigned int __nmi_count;	/* number of NMI on this CPUs */
 	struct mm_struct *active_mm;

include/asm-x86_64/topology.h

@@ -28,6 +28,8 @@ extern int __node_distance(int, int);
 #define pcibus_to_node(bus)		((long)(bus->sysdata))	
 #define pcibus_to_cpumask(bus)		node_to_cpumask(pcibus_to_node(bus));
 
+#define numa_node_id()			read_pda(nodenumber)
+
 /* sched_domains SD_NODE_INIT for x86_64 machines */
 #define SD_NODE_INIT (struct sched_domain) {		\
 	.span			= CPU_MASK_NONE,	\

include/linux/mmzone.h

@@ -435,7 +435,9 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
 
 #include <linux/topology.h>
 /* Returns the number of the current Node. */
+#ifndef numa_node_id
 #define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
+#endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES