sparse.c 4.7 KB
Newer Older
A
Andy Whitcroft 已提交
1 2 3 4 5 6 7 8
/*
 * sparse memory mappings.
 */
#include <linux/config.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/bootmem.h>
#include <linux/module.h>
9
#include <linux/spinlock.h>
A
Andy Whitcroft 已提交
10 11 12 13 14 15 16
#include <asm/dma.h>

/*
 * Permanent SPARSEMEM data:
 *
 * 1) mem_section	- memory sections, mem_map's for valid memory
 */
17
#ifdef CONFIG_SPARSEMEM_EXTREME
B
Bob Picco 已提交
18 19
struct mem_section *mem_section[NR_SECTION_ROOTS]
	____cacheline_maxaligned_in_smp;
20 21 22 23 24 25 26
#else
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
	____cacheline_maxaligned_in_smp;
#endif
EXPORT_SYMBOL(mem_section);

#ifdef CONFIG_SPARSEMEM_EXTREME
27 28 29 30 31 32 33 34 35 36 37 38
static struct mem_section *sparse_index_alloc(int nid)
{
	struct mem_section *section = NULL;
	unsigned long array_size = SECTIONS_PER_ROOT *
				   sizeof(struct mem_section);

	section = alloc_bootmem_node(NODE_DATA(nid), array_size);

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

	return section;
39
}
B
Bob Picco 已提交
40

41
static int sparse_index_init(unsigned long section_nr, int nid)
B
Bob Picco 已提交
42
{
43 44 45 46
	static spinlock_t index_init_lock = SPIN_LOCK_UNLOCKED;
	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
	struct mem_section *section;
	int ret = 0;
B
Bob Picco 已提交
47 48

	if (mem_section[root])
49
		return -EEXIST;
50

51 52 53 54 55 56
	section = sparse_index_alloc(nid);
	/*
	 * This lock keeps two different sections from
	 * reallocating for the same index
	 */
	spin_lock(&index_init_lock);
57

58 59 60 61 62 63 64 65 66 67 68 69 70 71
	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;
B
Bob Picco 已提交
72
}
73 74
#endif

A
Andy Whitcroft 已提交
75 76 77 78 79 80 81 82
/* Record a memory area against a node. */
void memory_present(int nid, unsigned long start, unsigned long end)
{
	unsigned long pfn;

	start &= PAGE_SECTION_MASK;
	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
		unsigned long section = pfn_to_section_nr(pfn);
B
Bob Picco 已提交
83 84 85 86 87 88 89
		struct mem_section *ms;

		sparse_index_init(section, nid);

		ms = __nr_to_section(section);
		if (!ms->section_mem_map)
			ms->section_mem_map = SECTION_MARKED_PRESENT;
A
Andy Whitcroft 已提交
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113
	}
}

/*
 * 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;

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

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

	return nr_pages * sizeof(struct page);
}

A
Andy Whitcroft 已提交
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
/*
 * 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)));
}

/*
 * We need this if we ever free the mem_maps.  While not implemented yet,
 * this function is included for parity with its sibling.
 */
static __attribute((unused))
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
{
	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}

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

	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum);

	return 1;
}

static struct page *sparse_early_mem_map_alloc(unsigned long pnum)
{
	struct page *map;
	int nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
B
Bob Picco 已提交
149
	struct mem_section *ms = __nr_to_section(pnum);
A
Andy Whitcroft 已提交
150 151 152 153 154 155 156 157 158 159 160

	map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
	if (map)
		return map;

	map = alloc_bootmem_node(NODE_DATA(nid),
			sizeof(struct page) * PAGES_PER_SECTION);
	if (map)
		return map;

	printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
B
Bob Picco 已提交
161
	ms->section_mem_map = 0;
A
Andy Whitcroft 已提交
162 163 164
	return NULL;
}

A
Andy Whitcroft 已提交
165 166 167 168 169 170 171 172 173 174
/*
 * Allocate the accumulated non-linear sections, allocate a mem_map
 * for each and record the physical to section mapping.
 */
void sparse_init(void)
{
	unsigned long pnum;
	struct page *map;

	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
A
Andy Whitcroft 已提交
175
		if (!valid_section_nr(pnum))
A
Andy Whitcroft 已提交
176 177
			continue;

A
Andy Whitcroft 已提交
178
		map = sparse_early_mem_map_alloc(pnum);
B
Bob Picco 已提交
179 180 181
		if (!map)
			continue;
		sparse_init_one_section(__nr_to_section(pnum), pnum, map);
A
Andy Whitcroft 已提交
182 183
	}
}
A
Andy Whitcroft 已提交
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200

/*
 * returns the number of sections whose mem_maps were properly
 * set.  If this is <=0, then that means that the passed-in
 * map was not consumed and must be freed.
 */
int sparse_add_one_section(unsigned long start_pfn, int nr_pages, struct page *map)
{
	struct mem_section *ms = __pfn_to_section(start_pfn);

	if (ms->section_mem_map & SECTION_MARKED_PRESENT)
		return -EEXIST;

	ms->section_mem_map |= SECTION_MARKED_PRESENT;

	return sparse_init_one_section(ms, pfn_to_section_nr(start_pfn), map);
}