init.c

linux-2.6.15.6

/*
 *  linux/arch/arm/mm/init.c
 *
 *  Copyright (C) 1995-2005 Russell King
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>

#include <asm/mach-types.h>
#include <asm/hardware.h>
#include <asm/setup.h>
#include <asm/tlb.h>

#include <asm/mach/arch.h>
#include <asm/mach/map.h>

#define TABLE_SIZE	(2 * PTRS_PER_PTE * sizeof(pte_t))

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);

extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern void _stext, _text, _etext, __data_start, _end, __init_begin, __init_end;
extern unsigned long phys_initrd_start;
extern unsigned long phys_initrd_size;

/*
 * The sole use of this is to pass memory configuration
 * data from paging_init to mem_init.
 */
static struct meminfo meminfo __initdata = { 0, };

/*
 * empty_zero_page is a special page that is used for
 * zero-initialized data and COW.
 */
struct page *empty_zero_page;

void show_mem(void)
{
	int free = 0, total = 0, reserved = 0;
	int shared = 0, cached = 0, slab = 0, node;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));

	for_each_online_node(node) {
		struct page *page, *end;

		page = NODE_MEM_MAP(node);
		end  = page + NODE_DATA(node)->node_spanned_pages;

		do {
			total++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (PageSlab(page))
				slab++;
			else if (!page_count(page))
				free++;
			else
				shared += page_count(page) - 1;
			page++;
		} while (page < end);
	}

	printk("%d pages of RAM\n", total);
	printk("%d free pages\n", free);
	printk("%d reserved pages\n", reserved);
	printk("%d slab pages\n", slab);
	printk("%d pages shared\n", shared);
	printk("%d pages swap cached\n", cached);
}

static inline pmd_t *pmd_off(pgd_t *pgd, unsigned long virt)
{
	return pmd_offset(pgd, virt);
}

static inline pmd_t *pmd_off_k(unsigned long virt)
{
	return pmd_off(pgd_offset_k(virt), virt);
}

#define for_each_nodebank(iter,mi,no)			\
	for (iter = 0; iter < mi->nr_banks; iter++)	\
		if (mi->bank[iter].node == no)

/*
 * FIXME: We really want to avoid allocating the bootmap bitmap
 * over the top of the initrd.  Hopefully, this is located towards
 * the start of a bank, so if we allocate the bootmap bitmap at
 * the end, we won't clash.
 */
static unsigned int __init
find_bootmap_pfn(int node, struct meminfo *mi, unsigned int bootmap_pages)
{
	unsigned int start_pfn, bank, bootmap_pfn;

	start_pfn   = PAGE_ALIGN(__pa(&_end)) >> PAGE_SHIFT;
	bootmap_pfn = 0;

	for_each_nodebank(bank, mi, node) {
		unsigned int start, end;

		start = mi->bank[bank].start >> PAGE_SHIFT;
		end   = (mi->bank[bank].size +
			 mi->bank[bank].start) >> PAGE_SHIFT;

		if (end < start_pfn)
			continue;

		if (start < start_pfn)
			start = start_pfn;

		if (end <= start)
			continue;

		if (end - start >= bootmap_pages) {
			bootmap_pfn = start;
			break;
		}
	}

	if (bootmap_pfn == 0)
		BUG();

	return bootmap_pfn;
}

static int __init check_initrd(struct meminfo *mi)
{
	int initrd_node = -2;
#ifdef CONFIG_BLK_DEV_INITRD
	unsigned long end = phys_initrd_start + phys_initrd_size;

	/*
	 * Make sure that the initrd is within a valid area of
	 * memory.
	 */
	if (phys_initrd_size) {
		unsigned int i;

		initrd_node = -1;

		for (i = 0; i < mi->nr_banks; i++) {
			unsigned long bank_end;

			bank_end = mi->bank[i].start + mi->bank[i].size;

			if (mi->bank[i].start <= phys_initrd_start &&
			    end <= bank_end)
				initrd_node = mi->bank[i].node;
		}
	}

	if (initrd_node == -1) {
		printk(KERN_ERR "initrd (0x%08lx - 0x%08lx) extends beyond "
		       "physical memory - disabling initrd\n",
		       phys_initrd_start, end);
		phys_initrd_start = phys_initrd_size = 0;
	}
#endif

	return initrd_node;
}

/*
 * Reserve the various regions of node 0
 */
static __init void reserve_node_zero(pg_data_t *pgdat)
{
	unsigned long res_size = 0;

	/*
	 * Register the kernel text and data with bootmem.
	 * Note that this can only be in node 0.
	 */
#ifdef CONFIG_XIP_KERNEL
	reserve_bootmem_node(pgdat, __pa(&__data_start), &_end - &__data_start);
#else
	reserve_bootmem_node(pgdat, __pa(&_stext), &_end - &_stext);
#endif

	/*
	 * Reserve the page tables.  These are already in use,
	 * and can only be in node 0.
	 */
	reserve_bootmem_node(pgdat, __pa(swapper_pg_dir),
			     PTRS_PER_PGD * sizeof(pgd_t));

	/*
	 * Hmm... This should go elsewhere, but we really really need to
	 * stop things allocating the low memory; ideally we need a better
	 * implementation of GFP_DMA which does not assume that DMA-able
	 * memory starts at zero.
	 */
	if (machine_is_integrator() || machine_is_cintegrator())
		res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;

	/*
	 * These should likewise go elsewhere.  They pre-reserve the
	 * screen memory region at the start of main system memory.
	 */
	if (machine_is_edb7211())
		res_size = 0x00020000;
	if (machine_is_p720t())
		res_size = 0x00014000;

#ifdef CONFIG_SA1111
	/*
	 * Because of the SA1111 DMA bug, we want to preserve our
	 * precious DMA-able memory...
	 */
	res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;
#endif
	if (res_size)
		reserve_bootmem_node(pgdat, PHYS_OFFSET, res_size);
}

void __init build_mem_type_table(void);
void __init create_mapping(struct map_desc *md);

static unsigned long __init
bootmem_init_node(int node, int initrd_node, struct meminfo *mi)
{
	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
	unsigned long start_pfn, end_pfn, boot_pfn;
	unsigned int boot_pages;
	pg_data_t *pgdat;
	int i;

	start_pfn = -1UL;
	end_pfn = 0;

	/*
	 * Calculate the pfn range, and map the memory banks for this node.
	 */
	for_each_nodebank(i, mi, node) {
		unsigned long start, end;
		struct map_desc map;

		start = mi->bank[i].start >> PAGE_SHIFT;
		end = (mi->bank[i].start + mi->bank[i].size) >> PAGE_SHIFT;

		if (start_pfn > start)
			start_pfn = start;
		if (end_pfn < end)
			end_pfn = end;

		map.pfn = __phys_to_pfn(mi->bank[i].start);
		map.virtual = __phys_to_virt(mi->bank[i].start);
		map.length = mi->bank[i].size;
		map.type = MT_MEMORY;

		create_mapping(&map);
	}

	/*
	 * If there is no memory in this node, ignore it.
	 */
	if (end_pfn == 0)
		return end_pfn;

	/*
	 * Allocate the bootmem bitmap page.
	 */
	boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
	boot_pfn = find_bootmap_pfn(node, mi, boot_pages);

	/*
	 * Initialise the bootmem allocator for this node, handing the
	 * memory banks over to bootmem.
	 */
	node_set_online(node);
	pgdat = NODE_DATA(node);
	init_bootmem_node(pgdat, boot_pfn, start_pfn, end_pfn);

	for_each_nodebank(i, mi, node)
		free_bootmem_node(pgdat, mi->bank[i].start, mi->bank[i].size);

	/*
	 * Reserve the bootmem bitmap for this node.
	 */
	reserve_bootmem_node(pgdat, boot_pfn << PAGE_SHIFT,
			     boot_pages << PAGE_SHIFT);

#ifdef CONFIG_BLK_DEV_INITRD
	/*
	 * If the initrd is in this node, reserve its memory.
	 */
	if (node == initrd_node) {
		reserve_bootmem_node(pgdat, phys_initrd_start,
				     phys_initrd_size);
		initrd_start = __phys_to_virt(phys_initrd_start);
		initrd_end = initrd_start + phys_initrd_size;
	}
#endif

	/*
	 * Finally, reserve any node zero regions.
	 */
	if (node == 0)
		reserve_node_zero(pgdat);

	/*
	 * initialise the zones within this node.
	 */
	memset(zone_size, 0, sizeof(zone_size));
	memset(zhole_size, 0, sizeof(zhole_size));

	/*
	 * The size of this node has already been determined.  If we need
	 * to do anything fancy with the allocation of this memory to the
	 * zones, now is the time to do it.
	 */
	zone_size[0] = end_pfn - start_pfn;

	/*
	 * For each bank in this node, calculate the size of the holes.
	 *  holes = node_size - sum(bank_sizes_in_node)
	 */
	zhole_size[0] = zone_size[0];
	for_each_nodebank(i, mi, node)
		zhole_size[0] -= mi->bank[i].size >> PAGE_SHIFT;

	/*
	 * Adjust the sizes according to any special requirements for
	 * this machine type.
	 */
	arch_adjust_zones(node, zone_size, zhole_size);