path: root/arch/x86/mm/numa_32.c

/*
 * Written by: Patricia Gaughen <gone@us.ibm.com>, IBM Corporation
 * August 2002: added remote node KVA remap - Martin J. Bligh 
 *
 * Copyright (C) 2002, IBM Corp.
 *
 * All rights reserved.          
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
 * NON INFRINGEMENT.  See the GNU General Public License for more
 * details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/mmzone.h>
#include <linux/highmem.h>
#include <linux/initrd.h>
#include <linux/nodemask.h>
#include <linux/module.h>
#include <linux/kexec.h>
#include <linux/pfn.h>
#include <linux/swap.h>
#include <linux/acpi.h>

#include <asm/e820.h>
#include <asm/setup.h>
#include <asm/mmzone.h>
#include <asm/bios_ebda.h>
#include <asm/proto.h>

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

/*
 * numa interface - we expect the numa architecture specific code to have
 *                  populated the following initialisation.
 *
 * 1) node_online_map  - the map of all nodes configured (online) in the system
 * 2) node_start_pfn   - the starting page frame number for a node
 * 3) node_end_pfn     - the ending page fram number for a node
 */
unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly;
unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly;


#ifdef CONFIG_DISCONTIGMEM
/*
 * 4) physnode_map     - the mapping between a pfn and owning node
 * physnode_map keeps track of the physical memory layout of a generic
 * numa node on a 64Mb break (each element of the array will
 * represent 64Mb of memory and will be marked by the node id.  so,
 * if the first gig is on node 0, and the second gig is on node 1
 * physnode_map will contain:
 *
 *     physnode_map[0-15] = 0;
 *     physnode_map[16-31] = 1;
 *     physnode_map[32- ] = -1;
 */
s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1};
EXPORT_SYMBOL(physnode_map);

void memory_present(int nid, unsigned long start, unsigned long end)
{
	unsigned long pfn;

	printk(KERN_INFO "Node: %d, start_pfn: %lx, end_pfn: %lx\n",
			nid, start, end);
	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
	printk(KERN_DEBUG "  ");
	for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) {
		physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
		printk(KERN_CONT "%lx ", pfn);
	}
	printk(KERN_CONT "\n");
}

unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
					      unsigned long end_pfn)
{
	unsigned long nr_pages = end_pfn - start_pfn;

	if (!nr_pages)
		return 0;

	return (nr_pages + 1) * sizeof(struct page);
}
#endif

extern unsigned long find_max_low_pfn(void);
extern unsigned long highend_pfn, highstart_pfn;

#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)

unsigned long node_remap_size[MAX_NUMNODES];
static void *node_remap_start_vaddr[MAX_NUMNODES];
void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);

static unsigned long kva_start_pfn;
static unsigned long kva_pages;
/*
 * FLAT - support for basic PC memory model with discontig enabled, essentially
 *        a single node with all available processors in it with a flat
 *        memory map.
 */
int __init get_memcfg_numa_flat(void)
{
	printk(KERN_DEBUG "NUMA - single node, flat memory mode\n");

	node_start_pfn[0] = 0;
	node_end_pfn[0] = max_pfn;
	e820_register_active_regions(0, 0, max_pfn);
	memory_present(0, 0, max_pfn);
	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);

        /* Indicate there is one node available. */
	nodes_clear(node_online_map);
	node_set_online(0);
	return 1;
}

/*
 * Find the highest page frame number we have available for the node
 */
static void __init propagate_e820_map_node(int nid)
{
	if (node_end_pfn[nid] > max_pfn)
		node_end_pfn[nid] = max_pfn;
	/*
	 * if a user has given mem=XXXX, then we need to make sure 
	 * that the node _starts_ before that, too, not just ends
	 */
	if (node_start_pfn[nid] > max_pfn)
		node_start_pfn[nid] = max_pfn;
	BUG_ON(node_start_pfn[nid] > node_end_pfn[nid]);
}

/* 
 * Allocate memory for the pg_data_t for this node via a crude pre-bootmem
 * method.  For node zero take this from the bottom of memory, for
 * subsequent nodes place them at node_remap_start_vaddr which contains
 * node local data in physically node local memory.  See setup_memory()
 * for details.
 */
static void __init allocate_pgdat(int nid)
{
	char buf[16];

	if (node_has_online_mem(nid) && node_remap_start_vaddr[nid])
		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
	else {
		unsigned long pgdat_phys;
		pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT,
				 max_pfn_mapped<<PAGE_SHIFT,
				 sizeof(pg_data_t),
				 PAGE_SIZE);
		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
		memset(buf, 0, sizeof(buf));
		sprintf(buf, "NODE_DATA %d",  nid);
		reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
	}
	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
		nid, (unsigned long)NODE_DATA(nid));
}

/*
 * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel
 * virtual address space (KVA) is reserved and portions of nodes are mapped
 * using it. This is to allow node-local memory to be allocated for
 * structures that would normally require ZONE_NORMAL. The memory is
 * allocated with alloc_remap() and callers should be prepared to allocate
 * from the bootmem allocator instead.
 */
static unsigned long node_remap_start_pfn[MAX_NUMNODES];
static void *node_remap_end_vaddr[MAX_NUMNODES];
static void *node_remap_alloc_vaddr[MAX_NUMNODES];
static unsigned long node_remap_offset[MAX_NUMNODES];

void *alloc_remap(int nid, unsigned long size)
{
	void *allocation = node_remap_alloc_vaddr[nid];

	size = ALIGN(size, L1_CACHE_BYTES);

	if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
		return 0;

	node_remap_alloc_vaddr[nid] += size;
	memset(allocation, 0, size);

	return allocation;
}

static void __init remap_numa_kva(void)
{
	void *vaddr;
	unsigned long pfn;
	int node;

	for_each_online_node(node) {
		printk(KERN_DEBUG "remap_numa_kva: node %d\n", node);
		for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
			vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
			printk(KERN_DEBUG "remap_numa_kva: %08lx to pfn %08lx\n",
				(unsigned long)vaddr,
				node_remap_start_pfn[node] + pfn);
			set_pmd_pfn((ulong) vaddr, 
				node_remap_start_pfn[node] + pfn, 
				PAGE_KERNEL_LARGE);
		}
	}
}

#ifdef CONFIG_HIBERNATION
/**
 * resume_map_numa_kva - add KVA mapping to the temporary page tables created
 *                       during resume from hibernation
 * @pgd_base - temporary resume page directory
 */
void resume_map_numa_kva(pgd_t *pgd_base)
{
	int node;

	for_each_online_node(node) {
		unsigned long start_va, start_pfn, size, pfn;

		start_va = (unsigned long)node_remap_start_vaddr[node];
		start_pfn = node_remap_start_pfn[node];
		size = node_remap_size[node];

		printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);

		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
			pgd_t *pgd = pgd_base + pgd_index(vaddr);
			pud_t *pud = pud_offset(pgd, vaddr);
			pmd_t *pmd = pmd_offset(pud, vaddr);

			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
						PAGE_KERNEL_LARGE_EXEC));

			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
				__FUNCTION__, vaddr, start_pfn + pfn);
		}
	}
}
#endif

static unsigned long calculate_numa_remap_pages(void)
{
	int nid;
	unsigned long size, reserve_pages = 0;

	for_each_online_node(nid) {
		u64 node_kva_target;
		u64 node_kva_final;

		/*
		 * The acpi/srat node info can show hot-add memroy zones
		 * where memory could be added but not currently present.
		 */
		printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
			nid<