path: root/arch/powerpc/mm/numa.c

/*
 * pSeries NUMA support
 *
 * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */
#include <linux/threads.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/export.h>
#include <linux/nodemask.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/memblock.h>
#include <linux/of.h>
#include <linux/pfn.h>
#include <linux/cpuset.h>
#include <linux/node.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/system.h>
#include <asm/smp.h>
#include <asm/firmware.h>
#include <asm/paca.h>
#include <asm/hvcall.h>

static int numa_enabled = 1;

static char *cmdline __initdata;

static int numa_debug;
#define dbg(args...) if (numa_debug) { printk(KERN_INFO args); }

int numa_cpu_lookup_table[NR_CPUS];
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
struct pglist_data *node_data[MAX_NUMNODES];

EXPORT_SYMBOL(numa_cpu_lookup_table);
EXPORT_SYMBOL(node_to_cpumask_map);
EXPORT_SYMBOL(node_data);

static int min_common_depth;
static int n_mem_addr_cells, n_mem_size_cells;
static int form1_affinity;

#define MAX_DISTANCE_REF_POINTS 4
static int distance_ref_points_depth;
static const unsigned int *distance_ref_points;
static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];

/*
 * Allocate node_to_cpumask_map based on number of available nodes
 * Requires node_possible_map to be valid.
 *
 * Note: node_to_cpumask() is not valid until after this is done.
 */
static void __init setup_node_to_cpumask_map(void)
{
	unsigned int node, num = 0;

	/* setup nr_node_ids if not done yet */
	if (nr_node_ids == MAX_NUMNODES) {
		for_each_node_mask(node, node_possible_map)
			num = node;
		nr_node_ids = num + 1;
	}

	/* allocate the map */
	for (node = 0; node < nr_node_ids; node++)
		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);

	/* cpumask_of_node() will now work */
	dbg("Node to cpumask map for %d nodes\n", nr_node_ids);
}

static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
						unsigned int *nid)
{
	unsigned long long mem;
	char *p = cmdline;
	static unsigned int fake_nid;
	static unsigned long long curr_boundary;

	/*
	 * Modify node id, iff we started creating NUMA nodes
	 * We want to continue from where we left of the last time
	 */
	if (fake_nid)
		*nid = fake_nid;
	/*
	 * In case there are no more arguments to parse, the
	 * node_id should be the same as the last fake node id
	 * (we've handled this above).
	 */
	if (!p)
		return 0;

	mem = memparse(p, &p);
	if (!mem)
		return 0;

	if (mem < curr_boundary)
		return 0;

	curr_boundary = mem;

	if ((end_pfn << PAGE_SHIFT) > mem) {
		/*
		 * Skip commas and spaces
		 */
		while (*p == ',' || *p == ' ' || *p == '\t')
			p++;

		cmdline = p;
		fake_nid++;
		*nid = fake_nid;
		dbg("created new fake_node with id %d\n", fake_nid);
		return 1;
	}
	return 0;
}

/*
 * get_node_active_region - Return active region containing pfn
 * Active range returned is empty if none found.
 * @pfn: The page to return the region for
 * @node_ar: Returned set to the active region containing @pfn
 */
static void __init get_node_active_region(unsigned long pfn,
					  struct node_active_region *node_ar)
{
	unsigned long start_pfn, end_pfn;
	int i, nid;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
		if (pfn >= start_pfn && pfn < end_pfn) {
			node_ar->nid = nid;
			node_ar->start_pfn = start_pfn;
			node_ar->end_pfn = end_pfn;
			break;
		}
	}
}

static void map_cpu_to_node(int cpu, int node)
{
	numa_cpu_lookup_table[cpu] = node;

	dbg("adding cpu %d to node %d\n", cpu, node);

	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node])))
		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
}

#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
static void unmap_cpu_from_node(unsigned long cpu)
{
	int node = numa_cpu_lookup_table[cpu];

	dbg("removing cpu %lu from node %d\n", cpu, node);

	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
	} else {
		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
		       cpu, node);
	}
}
#endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */

/* must hold reference to node during call */
static const int *of_get_associativity(struct device_node *dev)
{
	return of_get_property(dev, "ibm,associativity", NULL);
}

/*
 * Returns the property linux,drconf-usable-memory if
 * it exists (the property exists only in kexec/kdump kernels,
 * added by kexec-tools)
 */
static const u32 *of_get_usable_memory(struct device_node *memory)
{
	const u32 *prop;
	u32 len;
	prop = of_get_property(memory, "linux,drconf-usable-memory", &len);
	if (!prop || len < sizeof(unsigned int))
		return 0;
	return prop;
}

int __node_distance(int a, int b)
{
	int i;
	int distance = LOCAL_DISTANCE;

	if (!form1_affinity)
		return distance;

	for (i = 0; i < distance_ref_points_depth; i++) {
		if (distance_lookup_table[a][i] == distance_lookup_table[b][i])
			break;

		/* Double the distance for each NUMA level */
		distance *= 2;
	}

	return distance;
}

static void initialize_distance_lookup_table(int nid,
		const unsigned int *associativity)
{
	int i;

	if (!form1_affinity)
		return;

	for (i = 0; i < distance_ref_points_depth; i++) {
		distance_lookup_table[nid][i] =
			associativity[distance_ref_points[i]];
	}
}

/* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
 * info is found.
 */
static int associativity_to_nid(const unsigned int *associativity)
{
	int nid = -1;

	if (min_common_depth == -1)
		goto out;

	if (associativity[0] >= min_common_depth)
		nid = associativity[min_common_depth];

	/* POWER4 LPAR uses 0xffff as invalid node */
	if (nid == 0xffff || nid >= MAX_NUMNODES)
		nid = -1;

	if (nid > 0 && associativity[0] >= distance_ref_points_depth)
		initialize_distance_lookup_table(nid, associativity);

out:
	return nid;
}

/* Returns the nid associated with the given device tree node,
 * or -1 if not found.
 */
static int of_node_to_nid_single(struct device_node *device)
{
	int nid = -1;
	const unsigned int *tmp;

	tmp = of_get_associativity(device);
	if (tmp)
		nid = associativity_to_nid(tmp);
	return nid;
}

/* Walk the device tree upwards, looking for an associativity id */
int of_node_to_nid(struct device_node *device)
{
	struct device_node *tmp;
	int nid = -1;

	of_node_get(device);
	while (device) {
		nid = of_node_to_nid_single(device);
		if (nid != -1)
			break;

	        tmp = device;
		device = of_get_parent(tmp);
		of_node_put(tmp);
	}
	of_node_put(device);

	return nid;
}
EXPORT_SYMBOL_GPL(of_node_to_nid);

static int __init find_min_common_depth(void)
{
	int depth;
	struct device_node *chosen;
	struct device_node *root;
	const char *vec5;

	if (firmware_has_feature(FW_FEATURE_OPAL))
		root = of_find_node_by_path("/ibm,opal");
	else
		root = of_find_node_by_path("/rtas");
	if (!root)
		root = of_find_node_by_path("/");

	/*
	 * This property is a set of 32-bit integers, each representing
	 * an index into the ibm,associativity nodes.
	 *
	 *