fremap.c 6.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7
/*
 *   linux/mm/fremap.c
 * 
 * Explicit pagetable population and nonlinear (random) mappings support.
 *
 * started by Ingo Molnar, Copyright (C) 2002, 2003
 */
A
Alexey Dobriyan 已提交
8
#include <linux/backing-dev.h>
L
Linus Torvalds 已提交
9 10 11 12 13 14 15 16 17 18 19 20 21 22
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/syscalls.h>

#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

N
Nick Piggin 已提交
23
static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
L
Linus Torvalds 已提交
24 25 26 27 28
			unsigned long addr, pte_t *ptep)
{
	pte_t pte = *ptep;

	if (pte_present(pte)) {
N
Nick Piggin 已提交
29 30
		struct page *page;

31
		flush_cache_page(vma, addr, pte_pfn(pte));
L
Linus Torvalds 已提交
32
		pte = ptep_clear_flush(vma, addr, ptep);
33 34 35 36
		page = vm_normal_page(vma, addr, pte);
		if (page) {
			if (pte_dirty(pte))
				set_page_dirty(page);
N
Nick Piggin 已提交
37
			page_remove_rmap(page, vma);
38
			page_cache_release(page);
N
Nick Piggin 已提交
39 40
			update_hiwater_rss(mm);
			dec_mm_counter(mm, file_rss);
L
Linus Torvalds 已提交
41 42 43 44
		}
	} else {
		if (!pte_file(pte))
			free_swap_and_cache(pte_to_swp_entry(pte));
45
		pte_clear_not_present_full(mm, addr, ptep, 0);
L
Linus Torvalds 已提交
46 47 48 49 50 51 52
	}
}

/*
 * Install a file pte to a given virtual memory address, release any
 * previously existing mapping.
 */
N
Nick Piggin 已提交
53
static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
L
Linus Torvalds 已提交
54 55 56 57
		unsigned long addr, unsigned long pgoff, pgprot_t prot)
{
	int err = -ENOMEM;
	pte_t *pte;
H
Hugh Dickins 已提交
58
	spinlock_t *ptl;
L
Linus Torvalds 已提交
59

60
	pte = get_locked_pte(mm, addr, &ptl);
L
Linus Torvalds 已提交
61
	if (!pte)
H
Hugh Dickins 已提交
62
		goto out;
L
Linus Torvalds 已提交
63

N
Nick Piggin 已提交
64 65
	if (!pte_none(*pte))
		zap_pte(mm, vma, addr, pte);
L
Linus Torvalds 已提交
66 67

	set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
68 69 70 71 72 73 74
	/*
	 * We don't need to run update_mmu_cache() here because the "file pte"
	 * being installed by install_file_pte() is not a real pte - it's a
	 * non-present entry (like a swap entry), noting what file offset should
	 * be mapped there when there's a fault (in a non-linear vma where
	 * that's not obvious).
	 */
H
Hugh Dickins 已提交
75 76 77
	pte_unmap_unlock(pte, ptl);
	err = 0;
out:
L
Linus Torvalds 已提交
78 79 80
	return err;
}

81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99
static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long addr, unsigned long size, pgoff_t pgoff)
{
	int err;

	do {
		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
		if (err)
			return err;

		size -= PAGE_SIZE;
		addr += PAGE_SIZE;
		pgoff++;
	} while (size);

        return 0;

}

L
Linus Torvalds 已提交
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
/***
 * sys_remap_file_pages - remap arbitrary pages of a shared backing store
 *                        file within an existing vma.
 * @start: start of the remapped virtual memory range
 * @size: size of the remapped virtual memory range
 * @prot: new protection bits of the range
 * @pgoff: to be mapped page of the backing store file
 * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
 *
 * this syscall works purely via pagetables, so it's the most efficient
 * way to map the same (large) file into a given virtual window. Unlike
 * mmap()/mremap() it does not create any new vmas. The new mappings are
 * also safe across swapout.
 *
 * NOTE: the 'prot' parameter right now is ignored, and the vma's default
 * protection is used. Arbitrary protections might be implemented in the
 * future.
 */
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
	unsigned long __prot, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct address_space *mapping;
	unsigned long end = start + size;
	struct vm_area_struct *vma;
	int err = -EINVAL;
	int has_write_lock = 0;

	if (__prot)
		return err;
	/*
	 * Sanitize the syscall parameters:
	 */
	start = start & PAGE_MASK;
	size = size & PAGE_MASK;

	/* Does the address range wrap, or is the span zero-sized? */
	if (start + size <= start)
		return err;

	/* Can we represent this offset inside this architecture's pte's? */
#if PTE_FILE_MAX_BITS < BITS_PER_LONG
	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
		return err;
#endif

	/* We need down_write() to change vma->vm_flags. */
	down_read(&mm->mmap_sem);
 retry:
	vma = find_vma(mm, start);

	/*
	 * Make sure the vma is shared, that it supports prefaulting,
	 * and that the remapped range is valid and fully within
	 * the single existing vma.  vm_private_data is used as a
155
	 * swapout cursor in a VM_NONLINEAR vma.
L
Linus Torvalds 已提交
156
	 */
157 158 159 160 161 162
	if (!vma || !(vma->vm_flags & VM_SHARED))
		goto out;

	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
		goto out;

163
	if (!(vma->vm_flags & VM_CAN_NONLINEAR))
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183
		goto out;

	if (end <= start || start < vma->vm_start || end > vma->vm_end)
		goto out;

	/* Must set VM_NONLINEAR before any pages are populated. */
	if (!(vma->vm_flags & VM_NONLINEAR)) {
		/* Don't need a nonlinear mapping, exit success */
		if (pgoff == linear_page_index(vma, start)) {
			err = 0;
			goto out;
		}

		if (!has_write_lock) {
			up_read(&mm->mmap_sem);
			down_write(&mm->mmap_sem);
			has_write_lock = 1;
			goto retry;
		}
		mapping = vma->vm_file->f_mapping;
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
		/*
		 * page_mkclean doesn't work on nonlinear vmas, so if
		 * dirty pages need to be accounted, emulate with linear
		 * vmas.
		 */
		if (mapping_cap_account_dirty(mapping)) {
			unsigned long addr;

			flags &= MAP_NONBLOCK;
			addr = mmap_region(vma->vm_file, start, size,
					flags, vma->vm_flags, pgoff, 1);
			if (IS_ERR_VALUE(addr)) {
				err = addr;
			} else {
				BUG_ON(addr != start);
				err = 0;
			}
			goto out;
		}
203 204 205 206 207 208 209 210 211
		spin_lock(&mapping->i_mmap_lock);
		flush_dcache_mmap_lock(mapping);
		vma->vm_flags |= VM_NONLINEAR;
		vma_prio_tree_remove(vma, &mapping->i_mmap);
		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
		flush_dcache_mmap_unlock(mapping);
		spin_unlock(&mapping->i_mmap_lock);
	}

N
Nick Piggin 已提交
212 213 214 215 216
	err = populate_range(mm, vma, start, size, pgoff);
	if (!err && !(flags & MAP_NONBLOCK)) {
		if (unlikely(has_write_lock)) {
			downgrade_write(&mm->mmap_sem);
			has_write_lock = 0;
L
Linus Torvalds 已提交
217
		}
N
Nick Piggin 已提交
218 219
		make_pages_present(start, start+size);
	}
L
Linus Torvalds 已提交
220

221 222 223 224 225
	/*
	 * We can't clear VM_NONLINEAR because we'd have to do
	 * it after ->populate completes, and that would prevent
	 * downgrading the lock.  (Locks can't be upgraded).
	 */
L
Linus Torvalds 已提交
226

227
out:
L
Linus Torvalds 已提交
228 229 230 231 232 233 234 235
	if (likely(!has_write_lock))
		up_read(&mm->mmap_sem);
	else
		up_write(&mm->mmap_sem);

	return err;
}