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/module.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 <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/system.h>
#include <asm/smp.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;

/*
 * 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_active_region_work_fn - A helper function for get_node_active_region
 *	Returns datax set to the start_pfn and end_pfn if they contain
 *	the initial value of datax->start_pfn between them
 * @start_pfn: start page(inclusive) of region to check
 * @end_pfn: end page(exclusive) of region to check
 * @datax: comes in with ->start_pfn set to value to search for and
 *	goes out with active range if it contains it
 * Returns 1 if search value is in range else 0
 */
static int __init get_active_region_work_fn(unsigned long start_pfn,
					unsigned long end_pfn, void *datax)
{
	struct node_active_region *data;
	data = (struct node_active_region *)datax;

	if (start_pfn <= data->start_pfn && end_pfn > data->start_pfn) {
		data->start_pfn = start_pfn;
		data->end_pfn = end_pfn;
		return 1;
	}
	return 0;

}

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

	node_ar->nid = nid;
	node_ar->start_pfn = start_pfn;
	node_ar->end_pfn = start_pfn;
	work_with_active_regions(nid, get_active_region_work_fn, node_ar);
}

static void __cpuinit 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]);
}

#ifdef CONFIG_HOTPLUG_CPU
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_set_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 */

/* 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;