memory_hotplug.c

最新最稳定的Linux内存管理模块源代码

/*
 *  linux/mm/memory_hotplug.c
 *
 *  Copyright (C)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>

#include <asm/tlbflush.h>

#include "internal.h"

/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
	struct resource *res;
	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
	BUG_ON(!res);

	res->name = "System RAM";
	res->start = start;
	res->end = start + size - 1;
	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
	if (request_resource(&iomem_resource, res) < 0) {
		printk("System RAM resource %llx - %llx cannot be added\n",
		(unsigned long long)res->start, (unsigned long long)res->end);
		kfree(res);
		res = NULL;
	}
	return res;
}

static void release_memory_resource(struct resource *res)
{
	if (!res)
		return;
	release_resource(res);
	kfree(res);
	return;
}

#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
static void get_page_bootmem(unsigned long info,  struct page *page, int type)
{
	atomic_set(&page->_mapcount, type);
	SetPagePrivate(page);
	set_page_private(page, info);
	atomic_inc(&page->_count);
}

void put_page_bootmem(struct page *page)
{
	int type;

	type = atomic_read(&page->_mapcount);
	BUG_ON(type >= -1);

	if (atomic_dec_return(&page->_count) == 1) {
		ClearPagePrivate(page);
		set_page_private(page, 0);
		reset_page_mapcount(page);
		__free_pages_bootmem(page, 0);
	}

}

static void register_page_bootmem_info_section(unsigned long start_pfn)
{
	unsigned long *usemap, mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;

	if (!pfn_valid(start_pfn))
		return;

	section_nr = pfn_to_section_nr(start_pfn);
	ms = __nr_to_section(section_nr);

	/* Get section's memmap address */
	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);

	/*
	 * Get page for the memmap's phys address
	 * XXX: need more consideration for sparse_vmemmap...
	 */
	page = virt_to_page(memmap);
	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;

	/* remember memmap's page */
	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, SECTION_INFO);

	usemap = __nr_to_section(section_nr)->pageblock_flags;
	page = virt_to_page(usemap);

	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;

	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);

}

void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
	unsigned long i, pfn, end_pfn, nr_pages;
	int node = pgdat->node_id;
	struct page *page;
	struct zone *zone;

	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
	page = virt_to_page(pgdat);

	for (i = 0; i < nr_pages; i++, page++)
		get_page_bootmem(node, page, NODE_INFO);

	zone = &pgdat->node_zones[0];
	for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
		if (zone->wait_table) {
			nr_pages = zone->wait_table_hash_nr_entries
				* sizeof(wait_queue_head_t);
			nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
			page = virt_to_page(zone->wait_table);

			for (i = 0; i < nr_pages; i++, page++)
				get_page_bootmem(node, page, NODE_INFO);
		}
	}

	pfn = pgdat->node_start_pfn;
	end_pfn = pfn + pgdat->node_spanned_pages;

	/* register_section info */
	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
		register_page_bootmem_info_section(pfn);

}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */

static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
			   unsigned long end_pfn)
{
	unsigned long old_zone_end_pfn;

	zone_span_writelock(zone);

	old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
	if (start_pfn < zone->zone_start_pfn)
		zone->zone_start_pfn = start_pfn;

	zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
				zone->zone_start_pfn;

	zone_span_writeunlock(zone);
}

static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
			    unsigned long end_pfn)
{
	unsigned long old_pgdat_end_pfn =
		pgdat->node_start_pfn + pgdat->node_spanned_pages;

	if (start_pfn < pgdat->node_start_pfn)
		pgdat->node_start_pfn = start_pfn;

	pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
					pgdat->node_start_pfn;
}

static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	int nid = pgdat->node_id;
	int zone_type;
	unsigned long flags;

	zone_type = zone - pgdat->node_zones;
	if (!zone->wait_table) {
		int ret;

		ret = init_currently_empty_zone(zone, phys_start_pfn,
						nr_pages, MEMMAP_HOTPLUG);
		if (ret)
			return ret;
	}
	pgdat_resize_lock(zone->zone_pgdat, &flags);
	grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
	grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
			phys_start_pfn + nr_pages);
	pgdat_resize_unlock(zone->zone_pgdat, &flags);
	memmap_init_zone(nr_pages, nid, zone_type,
			 phys_start_pfn, MEMMAP_HOTPLUG);
	return 0;
}

static int __meminit __add_section(int nid, struct zone *zone,
					unsigned long phys_start_pfn)
{
	int nr_pages = PAGES_PER_SECTION;
	int ret;

	if (pfn_valid(phys_start_pfn))
		return -EEXIST;

	ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);

	if (ret < 0)
		return ret;

	ret = __add_zone(zone, phys_start_pfn);

	if (ret < 0)
		return ret;

	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
}

#ifdef CONFIG_SPARSEMEM_VMEMMAP
static int __remove_section(struct zone *zone, struct mem_section *ms)
{
	/*
	 * XXX: Freeing memmap with vmemmap is not implement yet.
	 *      This should be removed later.
	 */
	return -EBUSY;
}
#else
static int __remove_section(struct zone *zone, struct mem_section *ms)
{
	unsigned long flags;
	struct pglist_data *pgdat = zone->zone_pgdat;
	int ret = -EINVAL;

	if (!valid_section(ms))
		return ret;

	ret = unregister_memory_section(ms);
	if (ret)
		return ret;

	pgdat_resize_lock(pgdat, &flags);
	sparse_remove_one_section(zone, ms);
	pgdat_resize_unlock(pgdat, &flags);
	return 0;
}
#endif

/*
 * Reasonably generic function for adding memory.  It is
 * expected that archs that support memory hotplug will
 * call this function after deciding the zone to which to
 * add the new pages.
 */
int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
			unsigned long nr_pages)
{
	unsigned long i;
	int err = 0;
	int start_sec, end_sec;
	/* during initialize mem_map, align hot-added range to section */
	start_sec = pfn_to_section_nr(phys_start_pfn);
	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);

	for (i = start_sec; i <= end_sec; i++) {
		err = __add_section(nid, zone, i << PFN_SECTION_SHIFT);

		/*
		 * EEXIST is finally dealt with by ioresource collision
		 * check. see add_memory() => register_memory_resource()
		 * Warning will be printed if there is collision.
		 */
		if (err && (err != -EEXIST))
			break;
		err = 0;
	}

	return err;
}
EXPORT_SYMBOL_GPL(__add_pages);

/**
 * __remove_pages() - remove sections of pages from a zone
 * @zone: zone from which pages need to be removed
 * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
 * @nr_pages: number of pages to remove (must be multiple of section size)
 *
 * Generic helper function to remove section mappings and sysfs entries
 * for the section of the memory we are removing. Caller needs to make
 * sure that pages are marked reserved and zones are adjust properly by
 * calling offline_pages().
 */
int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
		 unsigned long nr_pages)
{
	unsigned long i, ret = 0;
	int sections_to_remove;

	/*
	 * We can only remove entire sections
	 */
	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
	BUG_ON(nr_pages % PAGES_PER_SECTION);

	sections_to_remove = nr_pages / PAGES_PER_SECTION;
	for (i = 0; i < sections_to_remove; i++) {
		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
		release_mem_region(pfn << PAGE_SHIFT,
				   PAGES_PER_SECTION << PAGE_SHIFT);
		ret = __remove_section(zone, __pfn_to_section(pfn));
		if (ret)
			break;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(__remove_pages);

void online_page(struct page *page)
{
	totalram_pages++;
	num_physpages++;

#ifdef CONFIG_HIGHMEM
	if (PageHighMem(page))
		totalhigh_pages++;
#endif

#ifdef CONFIG_FLATMEM
	max_mapnr = max(page_to_pfn(page), max_mapnr);
#endif

	ClearPageReserved(page);
	init_page_count(page);
	__free_page(page);
}

static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
			void *arg)
{
	unsigned long i;
	unsigned long onlined_pages = *(unsigned long *)arg;
	struct page *page;
	if (PageReserved(pfn_to_page(start_pfn)))
		for (i = 0; i < nr_pages; i++) {
			page = pfn_to_page(start_pfn + i);
			online_page(page);
			onlined_pages++;
		}
	*(unsigned long *)arg = onlined_pages;
	return 0;
}


int online_pages(unsigned long pfn, unsigned long nr_pages)
{
	unsigned long onlined_pages = 0;
	struct zone *zone;
	int need_zonelists_rebuild = 0;
	int nid;
	int ret;
	struct memory_notify arg;

	arg.start_pfn = pfn;
	arg.nr_pages = nr_pages;
	arg.status_change_nid = -1;

	nid = page_to_nid(pfn_to_page(pfn));
	if (node_present_pages(nid) == 0)
		arg.status_change_nid = nid;

	ret = memory_notify(MEM_GOING_ONLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret) {
		memory_notify(MEM_CANCEL_ONLINE, &arg);
		return ret;
	}
	/*
	 * This doesn't need a lock to do pfn_to_page().
	 * The section can't be removed here because of the
	 * memory_block->state_mutex.
	 */
	zone = page_zone(pfn_to_page(pfn));
	/*
	 * If this zone is not populated, then it is not in zonelist.
	 * This means the page allocator ignores this zone.
	 * So, zonelist must be updated after online.
	 */
	if (!populated_zone(zone))
		need_zonelists_rebuild = 1;

	ret = walk_memory_resource(pfn, nr_pages, &onlined_pages,
		online_pages_range);
	if (ret) {
		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
			nr_pages, pfn);
		memory_notify(MEM_CANCEL_ONLINE, &arg);
		return ret;
	}

	zone->present_pages += onlined_pages;
	zone->zone_pgdat->node_present_pages += onlined_pages;

	setup_per_zone_pages_min();
	if (onlined_pages) {
		kswapd_run(zone_to_nid(zone));
		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
	}

	if (need_zonelists_rebuild)
		build_all_zonelists();
	else