path: root/arch/x86/mm/numa_64.c

/*
 * Generic VM initialization for x86-64 NUMA setups.
 * Copyright 2002,2003 Andi Kleen, SuSE Labs.
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/sched.h>

#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/dma.h>
#include <asm/numa.h>
#include <asm/acpi.h>
#include <asm/amd_nb.h>

struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);

struct memnode memnode;

s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};

static unsigned long __initdata nodemap_addr;
static unsigned long __initdata nodemap_size;

/*
 * Map cpu index to node index
 */
DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);

/*
 * Given a shift value, try to populate memnodemap[]
 * Returns :
 * 1 if OK
 * 0 if memnodmap[] too small (of shift too small)
 * -1 if node overlap or lost ram (shift too big)
 */
static int __init populate_memnodemap(const struct bootnode *nodes,
				      int numnodes, int shift, int *nodeids)
{
	unsigned long addr, end;
	int i, res = -1;

	memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
	for (i = 0; i < numnodes; i++) {
		addr = nodes[i].start;
		end = nodes[i].end;
		if (addr >= end)
			continue;
		if ((end >> shift) >= memnodemapsize)
			return 0;
		do {
			if (memnodemap[addr >> shift] != NUMA_NO_NODE)
				return -1;

			if (!nodeids)
				memnodemap[addr >> shift] = i;
			else
				memnodemap[addr >> shift] = nodeids[i];

			addr += (1UL << shift);
		} while (addr < end);
		res = 1;
	}
	return res;
}

static int __init allocate_cachealigned_memnodemap(void)
{
	unsigned long addr;

	memnodemap = memnode.embedded_map;
	if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map))
		return 0;

	addr = 0x8000;
	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
	nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT,
				      nodemap_size, L1_CACHE_BYTES);
	if (nodemap_addr == MEMBLOCK_ERROR) {
		printk(KERN_ERR
		       "NUMA: Unable to allocate Memory to Node hash map\n");
		nodemap_addr = nodemap_size = 0;
		return -1;
	}
	memnodemap = phys_to_virt(nodemap_addr);
	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");

	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
	       nodemap_addr, nodemap_addr + nodemap_size);
	return 0;
}

/*
 * The LSB of all start and end addresses in the node map is the value of the
 * maximum possible shift.
 */
static int __init extract_lsb_from_nodes(const struct bootnode *nodes,
					 int numnodes)
{
	int i, nodes_used = 0;
	unsigned long start, end;
	unsigned long bitfield = 0, memtop = 0;

	for (i = 0; i < numnodes; i++) {
		start = nodes[i].start;
		end = nodes[i].end;
		if (start >= end)
			continue;
		bitfield |= start;
		nodes_used++;
		if (end > memtop)
			memtop = end;
	}
	if (nodes_used <= 1)
		i = 63;
	else
		i = find_first_bit(&bitfield, sizeof(unsigned long)*8);
	memnodemapsize = (memtop >> i)+1;
	return i;
}

int __init compute_hash_shift(struct bootnode *nodes, int numnodes,
			      int *nodeids)
{
	int shift;

	shift = extract_lsb_from_nodes(nodes, numnodes);
	if (allocate_cachealigned_memnodemap())
		return -1;
	printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
		shift);

	if (populate_memnodemap(nodes, numnodes, shift, nodeids) != 1) {
		printk(KERN_INFO "Your memory is not aligned you need to "
		       "rebuild your kernel with a bigger NODEMAPSIZE "
		       "shift=%d\n", shift);
		return -1;
	}
	return shift;
}

int __meminit  __early_pfn_to_nid(unsigned long pfn)
{