Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 2aaad0418e629c66a304ae731f3480b52db9bee1 (plain)
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
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
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
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
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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
/*
 *	linux/mm/msync.c
 *
 * Copyright (C) 1994-1999  Linus Torvalds
 */

/*
 * The msync() system call.
 */
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/hugetlb.h>

#include <asm/pgtable.h>
#include <asm/tlbflush.h>

/*
 * Called with mm->page_table_lock held to protect against other
 * threads/the swapper from ripping pte's out from under us.
 */
static int filemap_sync_pte(pte_t *ptep, struct vm_area_struct *vma,
	unsigned long address, unsigned int flags)
{
	pte_t pte = *ptep;
	unsigned long pfn = pte_pfn(pte);
	struct page *page;

	if (pte_present(pte) && pfn_valid(pfn)) {
		page = pfn_to_page(pfn);
		if (!PageReserved(page) &&
		    (ptep_clear_flush_dirty(vma, address, ptep) ||
		     page_test_and_clear_dirty(page)))
			set_page_dirty(page);
	}
	return 0;
}

static int filemap_sync_pte_range(pmd_t * pmd,
	unsigned long address, unsigned long end, 
	struct vm_area_struct *vma, unsigned int flags)
{
	pte_t *pte;
	int error;

	if (pmd_none(*pmd))
		return 0;
	if (pmd_bad(*pmd)) {
		pmd_ERROR(*pmd);
		pmd_clear(pmd);
		return 0;
	}
	pte = pte_offset_map(pmd, address);
	if ((address & PMD_MASK) != (end & PMD_MASK))
		end = (address & PMD_MASK) + PMD_SIZE;
	error = 0;
	do {
		error |= filemap_sync_pte(pte, vma, address, flags);
		address += PAGE_SIZE;
		pte++;
	} while (address && (address < end));

	pte_unmap(pte - 1);

	return error;
}

static inline int filemap_sync_pmd_range(pgd_t * pgd,
	unsigned long address, unsigned long end, 
	struct vm_area_struct *vma, unsigned int flags)
{
	pmd_t * pmd;
	int error;

	if (pgd_none(*pgd))
		return 0;
	if (pgd_bad(*pgd)) {
		pgd_ERROR(*pgd);
		pgd_clear(pgd);
		return 0;
	}
	pmd = pmd_offset(pgd, address);
	if ((address & PGDIR_MASK) != (end & PGDIR_MASK))
		end = (address & PGDIR_MASK) + PGDIR_SIZE;
	error = 0;
	do {
		error |= filemap_sync_pte_range(pmd, address, end, vma, flags);
		address = (address + PMD_SIZE) & PMD_MASK;
		pmd++;
	} while (address && (address < end));
	return error;
}

static int filemap_sync(struct vm_area_struct * vma, unsigned long address,
	size_t size, unsigned int flags)
{
	pgd_t * dir;
	unsigned long end = address + size;
	int error = 0;

	/* Aquire the lock early; it may be possible to avoid dropping
	 * and reaquiring it repeatedly.
	 */
	spin_lock(&vma->vm_mm->page_table_lock);

	dir = pgd_offset(vma->vm_mm, address);
	flush_cache_range(vma, address, end);

	/* For hugepages we can't go walking the page table normally,
	 * but that's ok, hugetlbfs is memory based, so we don't need
	 * to do anything more on an msync() */
	if (is_vm_hugetlb_page(vma))
		goto out;

	if (address >= end)
		BUG();
	do {
		error |= filemap_sync_pmd_range(dir, address, end, vma, flags);
		address = (address + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (address && (address < end));
	/*
	 * Why flush ? filemap_sync_pte already flushed the tlbs with the
	 * dirty bits.
	 */
	flush_tlb_range(vma, end - size, end);
 out:
	spin_unlock(&vma->vm_mm->page_table_lock);

	return error;
}

/*
 * MS_SYNC syncs the entire file - including mappings.
 *
 * MS_ASYNC does not start I/O (it used to, up to 2.5.67).  Instead, it just
 * marks the relevant pages dirty.  The application may now run fsync() to
 * write out the dirty pages and wait on the writeout and check the result.
 * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
 * async writeout immediately.
 * So my _not_ starting I/O in MS_ASYNC we provide complete flexibility to
 * applications.
 */
static int msync_interval(struct vm_area_struct * vma,
	unsigned long start, unsigned long end, int flags)
{
	int ret = 0;
	struct file * file = vma->vm_file;

	if ((flags & MS_INVALIDATE) && (vma->vm_flags & VM_LOCKED))
		return -EBUSY;

	if (file && (vma->vm_flags & VM_SHARED)) {
		ret = filemap_sync(vma, start, end-start, flags);

		if (!ret && (flags & MS_SYNC)) {
			struct address_space *mapping = file->f_mapping;
			int err;

			down(&mapping->host->i_sem);
			ret = filemap_fdatawrite(mapping);
			if (file->f_op && file->f_op->fsync) {
				err = file->f_op->fsync(file,file->f_dentry,1);
				if (err && !ret)
					ret = err;
			}
			err = filemap_fdatawait(mapping);
			if (!ret)
				ret = err;
			up(&mapping->host->i_sem);
		}
	}
	return ret;
}

asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
{
	unsigned long end;
	struct vm_area_struct * vma;
	int unmapped_error, error = -EINVAL;

	down_read(&current->mm->mmap_sem);
	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
		goto out;
	if (start & ~PAGE_MASK)
		goto out;
	if ((flags & MS_ASYNC) && (flags & MS_SYNC))
		goto out;
	error = -ENOMEM;
	len = (len + ~PAGE_MASK) & PAGE_MASK;
	end = start + len;
	if (end < start)
		goto out;
	error = 0;
	if (end == start)
		goto out;
	/*
	 * If the interval [start,end) covers some unmapped address ranges,
	 * just ignore them, but return -ENOMEM at the end.
	 */
	vma = find_vma(current->mm, start);
	unmapped_error = 0;
	for (;;) {
		/* Still start < end. */
		error = -ENOMEM;
		if (!vma)
			goto out;
		/* Here start < vma->vm_end. */
		if (start < vma->vm_start) {
			unmapped_error = -ENOMEM;
			start = vma->vm_start;
		}
		/* Here vma->vm_start <= start < vma->vm_end. */
		if (end <= vma->vm_end) {
			if (start < end) {
				error = msync_interval(vma, start, end, flags);
				if (error)
					goto out;
			}
			error = unmapped_error;
			goto out;
		}
		/* Here vma->vm_start <= start < vma->vm_end < end. */
		error = msync_interval(vma, start, vma->vm_end, flags);
		if (error)
			goto out;
		start = vma->vm_end;
		vma = vma->vm_next;
	}
out:
	up_read(&current->mm->mmap_sem);
	return error;
}