bootmem.c

最新最稳定的Linux内存管理模块源代码

/*
 *  bootmem - A boot-time physical memory allocator and configurator
 *
 *  Copyright (C) 1999 Ingo Molnar
 *                1999 Kanoj Sarcar, SGI
 *                2008 Johannes Weiner
 *
 * Access to this subsystem has to be serialized externally (which is true
 * for the boot process anyway).
 */
#include <linux/init.h>
#include <linux/pfn.h>
#include <linux/bootmem.h>
#include <linux/module.h>

#include <asm/bug.h>
#include <asm/io.h>
#include <asm/processor.h>

#include "internal.h"

unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;

#ifdef CONFIG_CRASH_DUMP
/*
 * If we have booted due to a crash, max_pfn will be a very low value. We need
 * to know the amount of memory that the previous kernel used.
 */
unsigned long saved_max_pfn;
#endif

bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;

static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);

static int bootmem_debug;

static int __init bootmem_debug_setup(char *buf)
{
	bootmem_debug = 1;
	return 0;
}
early_param("bootmem_debug", bootmem_debug_setup);

#define bdebug(fmt, args...) ({				\
	if (unlikely(bootmem_debug))			\
		printk(KERN_INFO			\
			"bootmem::%s " fmt,		\
			__func__, ## args);		\
})

static unsigned long __init bootmap_bytes(unsigned long pages)
{
	unsigned long bytes = (pages + 7) / 8;

	return ALIGN(bytes, sizeof(long));
}

/**
 * bootmem_bootmap_pages - calculate bitmap size in pages
 * @pages: number of pages the bitmap has to represent
 */
unsigned long __init bootmem_bootmap_pages(unsigned long pages)
{
	unsigned long bytes = bootmap_bytes(pages);

	return PAGE_ALIGN(bytes) >> PAGE_SHIFT;
}

/*
 * link bdata in order
 */
static void __init link_bootmem(bootmem_data_t *bdata)
{
	struct list_head *iter;

	list_for_each(iter, &bdata_list) {
		bootmem_data_t *ent;

		ent = list_entry(iter, bootmem_data_t, list);
		if (bdata->node_min_pfn < ent->node_min_pfn)
			break;
	}
	list_add_tail(&bdata->list, iter);
}

/*
 * Called once to set up the allocator itself.
 */
static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
	unsigned long mapstart, unsigned long start, unsigned long end)
{
	unsigned long mapsize;

	mminit_validate_memmodel_limits(&start, &end);
	bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
	bdata->node_min_pfn = start;
	bdata->node_low_pfn = end;
	link_bootmem(bdata);

	/*
	 * Initially all pages are reserved - setup_arch() has to
	 * register free RAM areas explicitly.
	 */
	mapsize = bootmap_bytes(end - start);
	memset(bdata->node_bootmem_map, 0xff, mapsize);

	bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n",
		bdata - bootmem_node_data, start, mapstart, end, mapsize);

	return mapsize;
}

/**
 * init_bootmem_node - register a node as boot memory
 * @pgdat: node to register
 * @freepfn: pfn where the bitmap for this node is to be placed
 * @startpfn: first pfn on the node
 * @endpfn: first pfn after the node
 *
 * Returns the number of bytes needed to hold the bitmap for this node.
 */
unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
				unsigned long startpfn, unsigned long endpfn)
{
	return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
}

/**
 * init_bootmem - register boot memory
 * @start: pfn where the bitmap is to be placed
 * @pages: number of available physical pages
 *
 * Returns the number of bytes needed to hold the bitmap.
 */
unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
{
	max_low_pfn = pages;
	min_low_pfn = start;
	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
}

static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
{
	int aligned;
	struct page *page;
	unsigned long start, end, pages, count = 0;

	if (!bdata->node_bootmem_map)
		return 0;

	start = bdata->node_min_pfn;
	end = bdata->node_low_pfn;

	/*
	 * If the start is aligned to the machines wordsize, we might
	 * be able to free pages in bulks of that order.
	 */
	aligned = !(start & (BITS_PER_LONG - 1));

	bdebug("nid=%td start=%lx end=%lx aligned=%d\n",
		bdata - bootmem_node_data, start, end, aligned);

	while (start < end) {
		unsigned long *map, idx, vec;

		map = bdata->node_bootmem_map;
		idx = start - bdata->node_min_pfn;
		vec = ~map[idx / BITS_PER_LONG];

		if (aligned && vec == ~0UL && start + BITS_PER_LONG < end) {
			int order = ilog2(BITS_PER_LONG);

			__free_pages_bootmem(pfn_to_page(start), order);
			count += BITS_PER_LONG;
		} else {
			unsigned long off = 0;

			while (vec && off < BITS_PER_LONG) {
				if (vec & 1) {
					page = pfn_to_page(start + off);
					__free_pages_bootmem(page, 0);
					count++;
				}
				vec >>= 1;
				off++;
			}
		}
		start += BITS_PER_LONG;
	}

	page = virt_to_page(bdata->node_bootmem_map);
	pages = bdata->node_low_pfn - bdata->node_min_pfn;
	pages = bootmem_bootmap_pages(pages);
	count += pages;
	while (pages--)
		__free_pages_bootmem(page++, 0);

	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);

	return count;
}

/**
 * free_all_bootmem_node - release a node's free pages to the buddy allocator
 * @pgdat: node to be released
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
{
	register_page_bootmem_info_node(pgdat);
	return free_all_bootmem_core(pgdat->bdata);
}

/**
 * free_all_bootmem - release free pages to the buddy allocator
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem(void)
{
	return free_all_bootmem_core(NODE_DATA(0)->bdata);
}

static void __init __free(bootmem_data_t *bdata,
			unsigned long sidx, unsigned long eidx)
{
	unsigned long idx;

	bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data,
		sidx + bdata->node_min_pfn,
		eidx + bdata->node_min_pfn);

	if (bdata->hint_idx > sidx)
		bdata->hint_idx = sidx;

	for (idx = sidx; idx < eidx; idx++)
		if (!test_and_clear_bit(idx, bdata->node_bootmem_map))
			BUG();
}

static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
			unsigned long eidx, int flags)
{
	unsigned long idx;
	int exclusive = flags & BOOTMEM_EXCLUSIVE;

	bdebug("nid=%td start=%lx end=%lx flags=%x\n",
		bdata - bootmem_node_data,
		sidx + bdata->node_min_pfn,
		eidx + bdata->node_min_pfn,
		flags);

	for (idx = sidx; idx < eidx; idx++)
		if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
			if (exclusive) {
				__free(bdata, sidx, idx);
				return -EBUSY;
			}
			bdebug("silent double reserve of PFN %lx\n",
				idx + bdata->node_min_pfn);
		}
	return 0;
}

static int __init mark_bootmem_node(bootmem_data_t *bdata,
				unsigned long start, unsigned long end,
				int reserve, int flags)
{
	unsigned long sidx, eidx;

	bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n",
		bdata - bootmem_node_data, start, end, reserve, flags);

	BUG_ON(start < bdata->node_min_pfn);
	BUG_ON(end > bdata->node_low_pfn);

	sidx = start - bdata->node_min_pfn;
	eidx = end - bdata->node_min_pfn;

	if (reserve)
		return __reserve(bdata, sidx, eidx, flags);
	else
		__free(bdata, sidx, eidx);
	return 0;
}

static int __init mark_bootmem(unsigned long start, unsigned long end,
				int reserve, int flags)
{
	unsigned long pos;
	bootmem_data_t *bdata;

	pos = start;
	list_for_each_entry(bdata, &bdata_list, list) {
		int err;
		unsigned long max;

		if (pos < bdata->node_min_pfn ||
		    pos >= bdata->node_low_pfn) {
			BUG_ON(pos != start);
			continue;
		}

		max = min(bdata->node_low_pfn, end);

		err = mark_bootmem_node(bdata, pos, max, reserve, flags);
		if (reserve && err) {
			mark_bootmem(start, pos, 0, 0);
			return err;
		}

		if (max == end)
			return 0;
		pos = bdata->node_low_pfn;
	}
	BUG();
}

/**
 * free_bootmem_node - mark a page range as usable
 * @pgdat: node the range resides on
 * @physaddr: starting address of the range
 * @size: size of the range in bytes
 *
 * Partial pages will be considered reserved and left as they are.
 *
 * The range must reside completely on the specified node.
 */
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
			      unsigned long size)
{
	unsigned long start, end;

	start = PFN_UP(physaddr);
	end = PFN_DOWN(physaddr + size);

	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
}

/**
 * free_bootmem - mark a page range as usable
 * @addr: starting address of the range
 * @size: size of the range in bytes
 *
 * Partial pages will be considered reserved and left as they are.
 *
 * The range must be contiguous but may span node boundaries.
 */
void __init free_bootmem(unsigned long addr, unsigned long size)
{
	unsigned long start, end;

	start = PFN_UP(addr);
	end = PFN_DOWN(addr + size);

	mark_bootmem(start, end, 0, 0);
}

/**
 * reserve_bootmem_node - mark a page range as reserved