sparse.c

最新最稳定的Linux内存管理模块源代码

/*
 * sparse memory mappings.
 */
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include "internal.h"
#include <asm/dma.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>

/*
 * Permanent SPARSEMEM data:
 *
 * 1) mem_section	- memory sections, mem_map's for valid memory
 */
#ifdef CONFIG_SPARSEMEM_EXTREME
struct mem_section *mem_section[NR_SECTION_ROOTS]
	____cacheline_internodealigned_in_smp;
#else
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
	____cacheline_internodealigned_in_smp;
#endif
EXPORT_SYMBOL(mem_section);

#ifdef NODE_NOT_IN_PAGE_FLAGS
/*
 * If we did not store the node number in the page then we have to
 * do a lookup in the section_to_node_table in order to find which
 * node the page belongs to.
 */
#if MAX_NUMNODES <= 256
static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
#else
static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
#endif

int page_to_nid(struct page *page)
{
	return section_to_node_table[page_to_section(page)];
}
EXPORT_SYMBOL(page_to_nid);

static void set_section_nid(unsigned long section_nr, int nid)
{
	section_to_node_table[section_nr] = nid;
}
#else /* !NODE_NOT_IN_PAGE_FLAGS */
static inline void set_section_nid(unsigned long section_nr, int nid)
{
}
#endif

#ifdef CONFIG_SPARSEMEM_EXTREME
static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
{
	struct mem_section *section = NULL;
	unsigned long array_size = SECTIONS_PER_ROOT *
				   sizeof(struct mem_section);

	if (slab_is_available())
		section = kmalloc_node(array_size, GFP_KERNEL, nid);
	else
		section = alloc_bootmem_node(NODE_DATA(nid), array_size);

	if (section)
		memset(section, 0, array_size);

	return section;
}

static int __meminit sparse_index_init(unsigned long section_nr, int nid)
{
	static DEFINE_SPINLOCK(index_init_lock);
	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
	struct mem_section *section;
	int ret = 0;

	if (mem_section[root])
		return -EEXIST;

	section = sparse_index_alloc(nid);
	if (!section)
		return -ENOMEM;
	/*
	 * This lock keeps two different sections from
	 * reallocating for the same index
	 */
	spin_lock(&index_init_lock);

	if (mem_section[root]) {
		ret = -EEXIST;
		goto out;
	}

	mem_section[root] = section;
out:
	spin_unlock(&index_init_lock);
	return ret;
}
#else /* !SPARSEMEM_EXTREME */
static inline int sparse_index_init(unsigned long section_nr, int nid)
{
	return 0;
}
#endif

/*
 * Although written for the SPARSEMEM_EXTREME case, this happens
 * to also work for the flat array case because
 * NR_SECTION_ROOTS==NR_MEM_SECTIONS.
 */
int __section_nr(struct mem_section* ms)
{
	unsigned long root_nr;
	struct mem_section* root;

	for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
		root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
		if (!root)
			continue;

		if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
		     break;
	}

	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}

/*
 * During early boot, before section_mem_map is used for an actual
 * mem_map, we use section_mem_map to store the section's NUMA
 * node.  This keeps us from having to use another data structure.  The
 * node information is cleared just before we store the real mem_map.
 */
static inline unsigned long sparse_encode_early_nid(int nid)
{
	return (nid << SECTION_NID_SHIFT);
}

static inline int sparse_early_nid(struct mem_section *section)
{
	return (section->section_mem_map >> SECTION_NID_SHIFT);
}

/* Validate the physical addressing limitations of the model */
void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
						unsigned long *end_pfn)
{
	unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);

	/*
	 * Sanity checks - do not allow an architecture to pass
	 * in larger pfns than the maximum scope of sparsemem:
	 */
	if (*start_pfn > max_sparsemem_pfn) {
		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
			"Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
			*start_pfn, *end_pfn, max_sparsemem_pfn);
		WARN_ON_ONCE(1);
		*start_pfn = max_sparsemem_pfn;
		*end_pfn = max_sparsemem_pfn;
	}

	if (*end_pfn > max_sparsemem_pfn) {
		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
			"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
			*start_pfn, *end_pfn, max_sparsemem_pfn);
		WARN_ON_ONCE(1);
		*end_pfn = max_sparsemem_pfn;
	}
}

/* Record a memory area against a node. */
void __init memory_present(int nid, unsigned long start, unsigned long end)
{
	unsigned long pfn;

	start &= PAGE_SECTION_MASK;
	mminit_validate_memmodel_limits(&start, &end);
	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
		unsigned long section = pfn_to_section_nr(pfn);
		struct mem_section *ms;

		sparse_index_init(section, nid);
		set_section_nid(section, nid);

		ms = __nr_to_section(section);
		if (!ms->section_mem_map)
			ms->section_mem_map = sparse_encode_early_nid(nid) |
							SECTION_MARKED_PRESENT;
	}
}

/*
 * Only used by the i386 NUMA architecures, but relatively
 * generic code.
 */
unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
						     unsigned long end_pfn)
{
	unsigned long pfn;
	unsigned long nr_pages = 0;

	mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		if (nid != early_pfn_to_nid(pfn))
			continue;

		if (pfn_present(pfn))
			nr_pages += PAGES_PER_SECTION;
	}

	return nr_pages * sizeof(struct page);
}

/*
 * Subtle, we encode the real pfn into the mem_map such that
 * the identity pfn - section_mem_map will return the actual
 * physical page frame number.
 */
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
{
	return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
}

/*
 * Decode mem_map from the coded memmap
 */
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
{
	/* mask off the extra low bits of information */
	coded_mem_map &= SECTION_MAP_MASK;
	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}

static int __meminit sparse_init_one_section(struct mem_section *ms,
		unsigned long pnum, struct page *mem_map,
		unsigned long *pageblock_bitmap)
{
	if (!present_section(ms))
		return -EINVAL;

	ms->section_mem_map &= ~SECTION_MAP_MASK;
	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
							SECTION_HAS_MEM_MAP;
 	ms->pageblock_flags = pageblock_bitmap;

	return 1;
}

unsigned long usemap_size(void)
{
	unsigned long size_bytes;
	size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;
	size_bytes = roundup(size_bytes, sizeof(unsigned long));
	return size_bytes;
}

#ifdef CONFIG_MEMORY_HOTPLUG
static unsigned long *__kmalloc_section_usemap(void)
{
	return kmalloc(usemap_size(), GFP_KERNEL);
}
#endif /* CONFIG_MEMORY_HOTPLUG */

#ifdef CONFIG_MEMORY_HOTREMOVE
static unsigned long * __init
sparse_early_usemap_alloc_pgdat_section(struct pglist_data *pgdat)
{
	unsigned long section_nr;

	/*
	 * A page may contain usemaps for other sections preventing the
	 * page being freed and making a section unremovable while
	 * other sections referencing the usemap retmain active. Similarly,
	 * a pgdat can prevent a section being removed. If section A
	 * contains a pgdat and section B contains the usemap, both
	 * sections become inter-dependent. This allocates usemaps
	 * from the same section as the pgdat where possible to avoid
	 * this problem.
	 */
	section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
	return alloc_bootmem_section(usemap_size(), section_nr);
}

static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
{
	unsigned long usemap_snr, pgdat_snr;
	static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
	static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
	struct pglist_data *pgdat = NODE_DATA(nid);
	int usemap_nid;

	usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
	pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
	if (usemap_snr == pgdat_snr)
		return;

	if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
		/* skip redundant message */
		return;

	old_usemap_snr = usemap_snr;
	old_pgdat_snr = pgdat_snr;

	usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
	if (usemap_nid != nid) {
		printk(KERN_INFO
		       "node %d must be removed before remove section %ld\n",
		       nid, usemap_snr);
		return;
	}
	/*
	 * There is a circular dependency.