pgtable.c 6.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32
/*
 *  linux/arch/i386/mm/pgtable.c
 */

#include <linux/config.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/spinlock.h>

#include <asm/system.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>

void show_mem(void)
{
	int total = 0, reserved = 0;
	int shared = 0, cached = 0;
	int highmem = 0;
	struct page *page;
	pg_data_t *pgdat;
	unsigned long i;
33
	struct page_state ps;
L
Linus Torvalds 已提交
34

35
	printk(KERN_INFO "Mem-info:\n");
L
Linus Torvalds 已提交
36
	show_free_areas();
37
	printk(KERN_INFO "Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
L
Linus Torvalds 已提交
38 39
	for_each_pgdat(pgdat) {
		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
40
			page = pgdat_page_nr(pgdat, i);
L
Linus Torvalds 已提交
41 42 43 44 45 46 47 48 49 50 51
			total++;
			if (PageHighMem(page))
				highmem++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (page_count(page))
				shared += page_count(page) - 1;
		}
	}
52 53 54 55 56
	printk(KERN_INFO "%d pages of RAM\n", total);
	printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
	printk(KERN_INFO "%d reserved pages\n", reserved);
	printk(KERN_INFO "%d pages shared\n", shared);
	printk(KERN_INFO "%d pages swap cached\n", cached);
57 58

	get_page_state(&ps);
59 60 61 62 63
	printk(KERN_INFO "%lu pages dirty\n", ps.nr_dirty);
	printk(KERN_INFO "%lu pages writeback\n", ps.nr_writeback);
	printk(KERN_INFO "%lu pages mapped\n", ps.nr_mapped);
	printk(KERN_INFO "%lu pages slab\n", ps.nr_slab);
	printk(KERN_INFO "%lu pages pagetables\n", ps.nr_page_table_pages);
L
Linus Torvalds 已提交
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
}

/*
 * Associate a virtual page frame with a given physical page frame 
 * and protection flags for that frame.
 */ 
static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	pgd = swapper_pg_dir + pgd_index(vaddr);
	if (pgd_none(*pgd)) {
		BUG();
		return;
	}
	pud = pud_offset(pgd, vaddr);
	if (pud_none(*pud)) {
		BUG();
		return;
	}
	pmd = pmd_offset(pud, vaddr);
	if (pmd_none(*pmd)) {
		BUG();
		return;
	}
	pte = pte_offset_kernel(pmd, vaddr);
	/* <pfn,flags> stored as-is, to permit clearing entries */
	set_pte(pte, pfn_pte(pfn, flags));

	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	__flush_tlb_one(vaddr);
}

/*
 * Associate a large virtual page frame with a given physical page frame 
 * and protection flags for that frame. pfn is for the base of the page,
 * vaddr is what the page gets mapped to - both must be properly aligned. 
 * The pmd must already be instantiated. Assumes PAE mode.
 */ 
void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	if (vaddr & (PMD_SIZE-1)) {		/* vaddr is misaligned */
116
		printk(KERN_WARNING "set_pmd_pfn: vaddr misaligned\n");
L
Linus Torvalds 已提交
117 118 119
		return; /* BUG(); */
	}
	if (pfn & (PTRS_PER_PTE-1)) {		/* pfn is misaligned */
120
		printk(KERN_WARNING "set_pmd_pfn: pfn misaligned\n");
L
Linus Torvalds 已提交
121 122 123 124
		return; /* BUG(); */
	}
	pgd = swapper_pg_dir + pgd_index(vaddr);
	if (pgd_none(*pgd)) {
125
		printk(KERN_WARNING "set_pmd_pfn: pgd_none\n");
L
Linus Torvalds 已提交
126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
		return; /* BUG(); */
	}
	pud = pud_offset(pgd, vaddr);
	pmd = pmd_offset(pud, vaddr);
	set_pmd(pmd, pfn_pmd(pfn, flags));
	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	__flush_tlb_one(vaddr);
}

void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
{
	unsigned long address = __fix_to_virt(idx);

	if (idx >= __end_of_fixed_addresses) {
		BUG();
		return;
	}
	set_pte_pfn(address, phys >> PAGE_SHIFT, flags);
}

pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
	return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
}

struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
	struct page *pte;

#ifdef CONFIG_HIGHPTE
	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
#else
	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
#endif
	return pte;
}

void pmd_ctor(void *pmd, kmem_cache_t *cache, unsigned long flags)
{
	memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t));
}

/*
 * List of all pgd's needed for non-PAE so it can invalidate entries
 * in both cached and uncached pgd's; not needed for PAE since the
 * kernel pmd is shared. If PAE were not to share the pmd a similar
 * tactic would be needed. This is essentially codepath-based locking
 * against pageattr.c; it is the unique case in which a valid change
 * of kernel pagetables can't be lazily synchronized by vmalloc faults.
 * vmalloc faults work because attached pagetables are never freed.
 * The locking scheme was chosen on the basis of manfred's
 * recommendations and having no core impact whatsoever.
 * -- wli
 */
DEFINE_SPINLOCK(pgd_lock);
struct page *pgd_list;

static inline void pgd_list_add(pgd_t *pgd)
{
	struct page *page = virt_to_page(pgd);
	page->index = (unsigned long)pgd_list;
	if (pgd_list)
H
Hugh Dickins 已提交
191
		set_page_private(pgd_list, (unsigned long)&page->index);
L
Linus Torvalds 已提交
192
	pgd_list = page;
H
Hugh Dickins 已提交
193
	set_page_private(page, (unsigned long)&pgd_list);
L
Linus Torvalds 已提交
194 195 196 197 198 199
}

static inline void pgd_list_del(pgd_t *pgd)
{
	struct page *next, **pprev, *page = virt_to_page(pgd);
	next = (struct page *)page->index;
H
Hugh Dickins 已提交
200
	pprev = (struct page **)page_private(page);
L
Linus Torvalds 已提交
201 202
	*pprev = next;
	if (next)
H
Hugh Dickins 已提交
203
		set_page_private(next, (unsigned long)pprev);
L
Linus Torvalds 已提交
204 205 206 207 208 209
}

void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
{
	unsigned long flags;

210 211
	if (PTRS_PER_PMD == 1) {
		memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
L
Linus Torvalds 已提交
212
		spin_lock_irqsave(&pgd_lock, flags);
213
	}
L
Linus Torvalds 已提交
214

215
	clone_pgd_range((pgd_t *)pgd + USER_PTRS_PER_PGD,
L
Linus Torvalds 已提交
216
			swapper_pg_dir + USER_PTRS_PER_PGD,
217
			KERNEL_PGD_PTRS);
L
Linus Torvalds 已提交
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265
	if (PTRS_PER_PMD > 1)
		return;

	pgd_list_add(pgd);
	spin_unlock_irqrestore(&pgd_lock, flags);
}

/* never called when PTRS_PER_PMD > 1 */
void pgd_dtor(void *pgd, kmem_cache_t *cache, unsigned long unused)
{
	unsigned long flags; /* can be called from interrupt context */

	spin_lock_irqsave(&pgd_lock, flags);
	pgd_list_del(pgd);
	spin_unlock_irqrestore(&pgd_lock, flags);
}

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	int i;
	pgd_t *pgd = kmem_cache_alloc(pgd_cache, GFP_KERNEL);

	if (PTRS_PER_PMD == 1 || !pgd)
		return pgd;

	for (i = 0; i < USER_PTRS_PER_PGD; ++i) {
		pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL);
		if (!pmd)
			goto out_oom;
		set_pgd(&pgd[i], __pgd(1 + __pa(pmd)));
	}
	return pgd;

out_oom:
	for (i--; i >= 0; i--)
		kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1));
	kmem_cache_free(pgd_cache, pgd);
	return NULL;
}

void pgd_free(pgd_t *pgd)
{
	int i;

	/* in the PAE case user pgd entries are overwritten before usage */
	if (PTRS_PER_PMD > 1)
		for (i = 0; i < USER_PTRS_PER_PGD; ++i)
			kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1));
266
	/* in the non-PAE case, free_pgtables() clears user pgd entries */
L
Linus Torvalds 已提交
267 268
	kmem_cache_free(pgd_cache, pgd);
}