aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/pageattr_64.c
blob: cbded8300e362ca23719f9cd0f53f173895ad2cc (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
/*
 * Copyright 2002 Andi Kleen, SuSE Labs.
 * Thanks to Ben LaHaise for precious feedback.
 */

#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>

void clflush_cache_range(void *addr, int size)
{
	int i;

	for (i = 0; i < size; i += boot_cpu_data.x86_clflush_size)
		clflush(addr+i);
}

#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>

pte_t *lookup_address(unsigned long address, int *level)
{
	pgd_t *pgd = pgd_offset_k(address);
	pud_t *pud;
	pmd_t *pmd;

	if (pgd_none(*pgd))
		return NULL;
	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return NULL;
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return NULL;
	*level = 3;
	if (pmd_large(*pmd))
		return (pte_t *)pmd;
	*level = 4;

	return pte_offset_kernel(pmd, address);
}

static struct page *
split_large_page(unsigned long address, pgprot_t ref_prot)
{
	unsigned long addr;
	struct page *base;
	pte_t *pbase;
	int i;

	base = alloc_pages(GFP_KERNEL, 0);
	if (!base)
		return NULL;

	address = __pa(address);
	addr = address & LARGE_PAGE_MASK;
	pbase = (pte_t *)page_address(base);
	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE)
		pbase[i] = pfn_pte(addr >> PAGE_SHIFT, ref_prot);

	return base;
}

static int
__change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
		   pgprot_t ref_prot)
{
	struct page *kpte_page;
	pte_t *kpte;
	pgprot_t ref_prot2, oldprot;
	int level;

repeat:
	kpte = lookup_address(address, &level);
	if (!kpte)
		return 0;

	kpte_page = virt_to_page(kpte);
	oldprot = pte_pgprot(*kpte);
	BUG_ON(PageLRU(kpte_page));
	BUG_ON(PageCompound(kpte_page));
	ref_prot = canon_pgprot(ref_prot);
	prot = canon_pgprot(prot);

	if (pgprot_val(prot) != pgprot_val(ref_prot)) {
		if (level == 4) {
			set_pte(kpte, pfn_pte(pfn, prot));
		} else {
			/*
			 * split_large_page will take the reference for this
			 * change_page_attr on the split page.
			 */
			struct page *split;

			ref_prot2 = pte_pgprot(pte_clrhuge(*kpte));
			split = split_large_page(address, ref_prot2);
			if (!split)
				return -ENOMEM;
			pgprot_val(ref_prot2) &= ~_PAGE_NX;
			set_pte(kpte, mk_pte(split, ref_prot2));
			goto repeat;
		}
	} else {
		if (level == 4) {
			set_pte(kpte, pfn_pte(pfn, ref_prot));
		} else
			BUG();
	}

	return 0;
}

/**
 * change_page_attr_addr - Change page table attributes in linear mapping
 * @address: Virtual address in linear mapping.
 * @numpages: Number of pages to change
 * @prot:    New page table attribute (PAGE_*)
 *
 * Change page attributes of a page in the direct mapping. This is a variant
 * of change_page_attr() that also works on memory holes that do not have
 * mem_map entry (pfn_valid() is false).
 *
 * See change_page_attr() documentation for more details.
 */

int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
{
	int err = 0, kernel_map = 0, i;

	if (address >= __START_KERNEL_map &&
			address < __START_KERNEL_map + KERNEL_TEXT_SIZE) {

		address = (unsigned long)__va(__pa(address));
		kernel_map = 1;
	}

	down_write(&init_mm.mmap_sem);
	for (i = 0; i < numpages; i++, address += PAGE_SIZE) {
		unsigned long pfn = __pa(address) >> PAGE_SHIFT;

		if (!kernel_map || pte_present(pfn_pte(0, prot))) {
			err = __change_page_attr(address, pfn, prot,
						PAGE_KERNEL);
			if (err)
				break;
		}
		/* Handle kernel mapping too which aliases part of the
		 * lowmem */
		if (__pa(address) < KERNEL_TEXT_SIZE) {
			unsigned long addr2;
			pgprot_t prot2;

			addr2 = __START_KERNEL_map + __pa(address);
			/* Make sure the kernel mappings stay executable */
			prot2 = pte_pgprot(pte_mkexec(pfn_pte(0, prot)));
			err = __change_page_attr(addr2, pfn, prot2,
						 PAGE_KERNEL_EXEC);
		}
	}
	up_write(&init_mm.mmap_sem);

	return err;
}

/**
 * change_page_attr - Change page table attributes in the linear mapping.
 * @page: First page to change
 * @numpages: Number of pages to change
 * @prot: New protection/caching type (PAGE_*)
 *
 * Returns 0 on success, otherwise a negated errno.
 *
 * This should be used when a page is mapped with a different caching policy
 * than write-back somewhere - some CPUs do not like it when mappings with
 * different caching policies exist. This changes the page attributes of the
 * in kernel linear mapping too.
 *
 * Caller must call global_flush_tlb() later to make the changes active.
 *
 * The caller needs to ensure that there are no conflicting mappings elsewhere
 * (e.g. in user space) * This function only deals with the kernel linear map.
 *
 * For MMIO areas without mem_map use change_page_attr_addr() instead.
 */
int change_page_attr(struct page *page, int numpages, pgprot_t prot)
{
	unsigned long addr = (unsigned long)page_address(page);

	return change_page_attr_addr(addr, numpages, prot);
}
EXPORT_SYMBOL(change_page_attr);

static void flush_kernel_map(void *arg)
{
	/*
	 * Flush all to work around Errata in early athlons regarding
	 * large page flushing.
	 */
	__flush_tlb_all();

	if (boot_cpu_data.x86_model >= 4)
		wbinvd();
}

void global_flush_tlb(void)
{
	BUG_ON(irqs_disabled());

	on_each_cpu(flush_kernel_map, NULL, 1, 1);
}
EXPORT_SYMBOL(global_flush_tlb);