litmus-rt.git - The LITMUS^RT kernel.

index : litmus-rt.git

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

path: root/include/linux/elfnote.h

diff options

Diffstat (limited to 'include/linux/elfnote.h')

0 files changed, 0 insertions, 0 deletions

t;kmannth@us.ibm.com> 2006-10-01 02:27:09 -0400 committer Linus Torvalds <torvalds@g5.osdl.org> 2006-10-01 03:39:18 -0400 [PATCH] hot-add-mem x86_64: use CONFIG_MEMORY_HOTPLUG_RESERVE' href='/cgit/cgit.cgi/litmus-rt-imx6.git/commit/mm/memory_hotplug.c?id=45e0b78b0532f92c01e363dd4287617c5be4574f'>45e0b78b0532

25
26
27

33
34
35

36
37

95
96

104
105
106

111
112
113

132
133

165
166

222
223

297
298

301
302

303
304
305

339
340

343
344

345
346
347

356
357

359
360

361
362

364
365
366

401
402

403
404
405

412
413

415
416

417
418

421
422

423
424
425

437
438

674
675

676
677

692
693
694

711
712

775
776

777
778

790
791

793
794

808
809

810
811

849
850
851

853
854
855

893
894

896
897

913
914

918
919

955
956

958
959

966
967

976
977

982
983

991
992
993

1001
1002
1003

1006
1007
1008

1015
1016
1017

1020
1021

1024
1025

1038
1039

1085
1086
1087

1088
1089

1092
1093

1095
1096

1114
1115

1116
1117
1118

1119
1120
1121

1123
1124

1135
1136
1137

1138
1139

1148
1149
1150

1151
1152
1153

1168
1169
1170

1270
1271
1272

1275
1276
1277

1281
1282
1283

1285
1286

1287
1288

1399
1400
1401

1403
1404
1405

1472
1473

1479
1480

1512
1513

1516
1517
1518

1573
1574

1579
1580
1581

1583
1584

1593
1594

1597
1598

1599
1600

1602
1603
1604

1605
1606
1607

1614
1615

1622
1623
1624

1637
1638

1639
1640

1660
1661

1699
1700
1701

1754
1755
1756

1758
1759

1813
1814

1840
1841
1842

1862
1863

1864
1865
1866

1867
1868

1869
1870

1871
1872

1881
1882
1883

/*
 *  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/export.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 <linux/suspend.h>
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>

#include <asm/tlbflush.h>

#include "internal.h"

/*
 * online_page_callback contains pointer to current page onlining function.
 * Initially it is generic_online_page(). If it is required it could be
 * changed by calling set_online_page_callback() for callback registration
 * and restore_online_page_callback() for generic callback restore.
 */

static void generic_online_page(struct page *page);

static online_page_callback_t online_page_callback = generic_online_page;

DEFINE_MUTEX(mem_hotplug_mutex);

void lock_memory_hotplug(void)
{
	mutex_lock(&mem_hotplug_mutex);

	/* for exclusive hibernation if CONFIG_HIBERNATION=y */
	lock_system_sleep();
}

void unlock_memory_hotplug(void)
{
	unlock_system_sleep();
	mutex_unlock(&mem_hotplug_mutex);
}


/* 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 %pR cannot be added\n", res);
		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
void get_page_bootmem(unsigned long info,  struct page *page,
		      unsigned long type)
{
	page->lru.next = (struct list_head *) type;
	SetPagePrivate(page);
	set_page_private(page, info);
	atomic_inc(&page->_count);
}

/* reference to __meminit __free_pages_bootmem is valid
 * so use __ref to tell modpost not to generate a warning */
void __ref put_page_bootmem(struct page *page)
{
	unsigned long type;
	static DEFINE_MUTEX(ppb_lock);

	type = (unsigned long) page->lru.next;
	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);

	if (atomic_dec_return(&page->_count) == 1) {
		ClearPagePrivate(page);
		set_page_private(page, 0);
		INIT_LIST_HEAD(&page->lru);

		/*
		 * Please refer to comment for __free_pages_bootmem()
		 * for why we serialize here.
		 */
		mutex_lock(&ppb_lock);
		__free_pages_bootmem(page, 0);
		mutex_unlock(&ppb_lock);
		totalram_pages++;
	}

}

#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
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;

	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);

}
#else /* CONFIG_SPARSEMEM_VMEMMAP */
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);

	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);

	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);

	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);
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */

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 = pgdat_end_pfn(pgdat);

	/* register_section info */
	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		/*
		 * Some platforms can assign the same pfn to multiple nodes - on
		 * node0 as well as nodeN.  To avoid registering a pfn against
		 * multiple nodes we check that this pfn does not already
		 * reside in some other node.
		 */
		if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
			register_page_bootmem_info_section(pfn);
	}
}
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */

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 (!zone->spanned_pages || 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 resize_zone(struct zone *zone, unsigned long start_pfn,
		unsigned long end_pfn)
{
	zone_span_writelock(zone);

	if (end_pfn - start_pfn) {
		zone->zone_start_pfn = start_pfn;
		zone->spanned_pages = end_pfn - start_pfn;
	} else {
		/*
		 * make it consist as free_area_init_core(),
		 * if spanned_pages = 0, then keep start_pfn = 0
		 */
		zone->zone_start_pfn = 0;
		zone->spanned_pages = 0;
	}

	zone_span_writeunlock(zone);
}

static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
		unsigned long end_pfn)
{
	enum zone_type zid = zone_idx(zone);
	int nid = zone->zone_pgdat->node_id;
	unsigned long pfn;

	for (pfn = start_pfn; pfn < end_pfn; pfn++)
		set_page_links(pfn_to_page(pfn), zid, nid, pfn);
}

/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
 * alloc_bootmem_node_nopanic() */
static int __ref ensure_zone_is_initialized(struct zone *zone,
			unsigned long start_pfn, unsigned long num_pages)
{
	if (!zone_is_initialized(zone))
		return init_currently_empty_zone(zone, start_pfn, num_pages,
						 MEMMAP_HOTPLUG);
	return 0;
}

static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
		unsigned long start_pfn, unsigned long end_pfn)
{
	int ret;
	unsigned long flags;
	unsigned long z1_start_pfn;

	ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
	if (ret)
		return ret;

	pgdat_resize_lock(z1->zone_pgdat, &flags);

	/* can't move pfns which are higher than @z2 */
	if (end_pfn > zone_end_pfn(z2))
		goto out_fail;
	/* the move out part mast at the left most of @z2 */
	if (start_pfn > z2->zone_start_pfn)
		goto out_fail;
	/* must included/overlap */
	if (end_pfn <= z2->zone_start_pfn)
		goto out_fail;

	/* use start_pfn for z1's start_pfn if z1 is empty */
	if (z1->spanned_pages)
		z1_start_pfn = z1->zone_start_pfn;
	else
		z1_start_pfn = start_pfn;

	resize_zone(z1, z1_start_pfn, end_pfn);
	resize_zone(z2, end_pfn, zone_end_pfn(z2));

	pgdat_resize_unlock(z1->zone_pgdat, &flags);

	fix_zone_id(z1, start_pfn, end_pfn);

	return 0;
out_fail:
	pgdat_resize_unlock(z1->zone_pgdat, &flags);
	return -1;
}

static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
		unsigned long start_pfn, unsigned long end_pfn)
{
	int ret;
	unsigned long flags;
	unsigned long z2_end_pfn;

	ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
	if (ret)
		return ret;

	pgdat_resize_lock(z1->zone_pgdat, &flags);

	/* can't move pfns which are lower than @z1 */
	if (z1->zone_start_pfn > start_pfn)
		goto out_fail;
	/* the move out part mast at the right most of @z1 */
	if (zone_end_pfn(z1) >  end_pfn)
		goto out_fail;
	/* must included/overlap */
	if (start_pfn >= zone_end_pfn(z1))
		goto out_fail;

	/* use end_pfn for z2's end_pfn if z2 is empty */
	if (z2->spanned_pages)
		z2_end_pfn = zone_end_pfn(z2);
	else
		z2_end_pfn = end_pfn;

	resize_zone(z1, z1->zone_start_pfn, start_pfn);
	resize_zone(z2, start_pfn, z2_end_pfn);

	pgdat_resize_unlock(z1->zone_pgdat, &flags);

	fix_zone_id(z2, start_pfn, end_pfn);

	return 0;
out_fail:
	pgdat_resize_unlock(z1->zone_pgdat, &flags);
	return -1;
}

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 (!pgdat->node_spanned_pages || 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;
	int ret;

	zone_type = zone - pgdat->node_zones;
	ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
	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));
}

/*
 * 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);

#ifdef CONFIG_MEMORY_HOTREMOVE
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static int find_smallest_section_pfn(int nid, struct zone *zone,
				     unsigned long start_pfn,
				     unsigned long end_pfn)
{
	struct mem_section *ms;

	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(start_pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (unlikely(pfn_to_nid(start_pfn) != nid))
			continue;

		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
			continue;

		return start_pfn;
	}

	return 0;
}

/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
static int find_biggest_section_pfn(int nid, struct zone *zone,
				    unsigned long start_pfn,
				    unsigned long end_pfn)
{
	struct mem_section *ms;
	unsigned long pfn;

	/* pfn is the end pfn of a memory section. */
	pfn = end_pfn - 1;
	for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (unlikely(pfn_to_nid(pfn) != nid))
			continue;

		if (zone && zone != page_zone(pfn_to_page(pfn)))
			continue;

		return pfn;
	}

	return 0;
}

static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
			     unsigned long end_pfn)
{
	unsigned long zone_start_pfn =  zone->zone_start_pfn;
	unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
	unsigned long pfn;
	struct mem_section *ms;
	int nid = zone_to_nid(zone);

	zone_span_writelock(zone);
	if (zone_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the zone, it need
		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
		 * In this case, we find second smallest valid mem_section
		 * for shrinking zone.
		 */
		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
						zone_end_pfn);
		if (pfn) {
			zone->zone_start_pfn = pfn;
			zone->spanned_pages = zone_end_pfn - pfn;
		}
	} else if (zone_end_pfn == end_pfn) {
		/*
		 * If the section is biggest section in the zone, it need
		 * shrink zone->spanned_pages.
		 * In this case, we find second biggest valid mem_section for
		 * shrinking zone.
		 */
		pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
					       start_pfn);
		if (pfn)
			zone->spanned_pages = pfn - zone_start_pfn + 1;
	}

	/*
	 * The section is not biggest or smallest mem_section in the zone, it
	 * only creates a hole in the zone. So in this case, we need not
	 * change the zone. But perhaps, the zone has only hole data. Thus
	 * it check the zone has only hole or not.
	 */
	pfn = zone_start_pfn;
	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (page_zone(pfn_to_page(pfn)) != zone)
			continue;

		 /* If the section is current section, it continues the loop */
		if (start_pfn == pfn)
			continue;

		/* If we find valid section, we have nothing to do */
		zone_span_writeunlock(zone);
		return;
	}

	/* The zone has no valid section */
	zone->zone_start_pfn = 0;
	zone->spanned_pages = 0;
	zone_span_writeunlock(zone);
}

static void shrink_pgdat_span(struct pglist_data *pgdat,
			      unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pgdat_start_pfn =  pgdat->node_start_pfn;
	unsigned long pgdat_end_pfn =
		pgdat->node_start_pfn + pgdat->node_spanned_pages;
	unsigned long pfn;
	struct mem_section *ms;
	int nid = pgdat->node_id;

	if (pgdat_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the pgdat, it need
		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.


context:
space:
mode: