aboutsummaryrefslogtreecommitdiff
path: root/arch/i386/mm/pageattr.c
blob: f600fc244f0284e67261e394de644705a67eb744 (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
/* 
 * Copyright 2002 Andi Kleen, SuSE Labs. 
 * Thanks to Ben LaHaise for precious feedback.
 */ 

#include <linux/config.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>

static DEFINE_SPINLOCK(cpa_lock);
static struct list_head df_list = LIST_HEAD_INIT(df_list);


pte_t *lookup_address(unsigned long address) 
{ 
	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;
	if (pmd_large(*pmd))
		return (pte_t *)pmd;
        return pte_offset_kernel(pmd, address);
} 

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

	spin_unlock_irq(&cpa_lock);
	base = alloc_pages(GFP_KERNEL, 0);
	spin_lock_irq(&cpa_lock);
	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) {
               set_pte(&pbase[i], pfn_pte(addr >> PAGE_SHIFT,
                                          addr == address ? prot : PAGE_KERNEL));
	}
	return base;
} 

static void flush_kernel_map(void *dummy) 
{ 
	/* Could use CLFLUSH here if the CPU supports it (Hammer,P4) */
	if (boot_cpu_data.x86_model >= 4) 
		wbinvd();
	/* Flush all to work around Errata in early athlons regarding 
	 * large page flushing. 
	 */
	__flush_tlb_all(); 	
}

static void set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) 
{ 
	struct page *page;
	unsigned long flags;

	set_pte_atomic(kpte, pte); 	/* change init_mm */
	if (PTRS_PER_PMD > 1)
		return;

	spin_lock_irqsave(&pgd_lock, flags);
	for (page = pgd_list; page; page = (struct page *)page->index) {
		pgd_t *pgd;
		pud_t *pud;
		pmd_t *pmd;
		pgd = (pgd_t *)page_address(page) + pgd_index(address);
		pud = pud_offset(pgd, address);
		pmd = pmd_offset(pud, address);
		set_pte_atomic((pte_t *)pmd, pte);
	}
	spin_unlock_irqrestore(&pgd_lock, flags);
}

/* 
 * No more special protections in this 2/4MB area - revert to a
 * large page again. 
 */
static inline void revert_page(struct page *kpte_page, unsigned long address)
{
	pte_t *linear = (pte_t *) 
		pmd_offset(pud_offset(pgd_offset_k(address), address), address);
	set_pmd_pte(linear,  address,
		    pfn_pte((__pa(address) & LARGE_PAGE_MASK) >> PAGE_SHIFT,
			    PAGE_KERNEL_LARGE));
}

static int
__change_page_attr(struct page *page, pgprot_t prot)
{ 
	pte_t *kpte; 
	unsigned long address;
	struct page *kpte_page;

	BUG_ON(PageHighMem(page));
	address = (unsigned long)page_address(page);

	kpte = lookup_address(address);
	if (!kpte)
		return -EINVAL;
	kpte_page = virt_to_page(kpte);
	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) { 
		if ((pte_val(*kpte) & _PAGE_PSE) == 0) { 
			set_pte_atomic(kpte, mk_pte(page, prot)); 
		} else {
			struct page *split = split_large_page(address, prot); 
			if (!split)
				return -ENOMEM;
			set_pmd_pte(kpte,address,mk_pte(split, PAGE_KERNEL));
			kpte_page = split;
		}	
		get_page(kpte_page);
	} else if ((pte_val(*kpte) & _PAGE_PSE) == 0) { 
		set_pte_atomic(kpte, mk_pte(page, PAGE_KERNEL));
		__put_page(kpte_page);
	} else
		BUG();

	/*
	 * If the pte was reserved, it means it was created at boot
	 * time (not via split_large_page) and in turn we must not
	 * replace it with a largepage.
	 */
	if (!PageReserved(kpte_page)) {
		/* memleak and potential failed 2M page regeneration */
		BUG_ON(!page_count(kpte_page));

		if (cpu_has_pse && (page_count(kpte_page) == 1)) {
			list_add(&kpte_page->lru, &df_list);
			revert_page(kpte_page, address);
		}
	}
	return 0;
} 

static inline void flush_map(void)
{
	on_each_cpu(flush_kernel_map, NULL, 1, 1);
}

/*
 * Change the page attributes of an page in the linear mapping.
 *
 * 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.
 * 
 * The caller needs to ensure that there are no conflicting mappings elsewhere.
 * This function only deals with the kernel linear map.
 * 
 * Caller must call global_flush_tlb() after this.
 */
int change_page_attr(struct page *page, int numpages, pgprot_t prot)
{
	int err = 0; 
	int i; 
	unsigned long flags;

	spin_lock_irqsave(&cpa_lock, flags);
	for (i = 0; i < numpages; i++, page++) { 
		err = __change_page_attr(page, prot);
		if (err) 
			break; 
	} 	
	spin_unlock_irqrestore(&cpa_lock, flags);
	return err;
}

void global_flush_tlb(void)
{ 
	LIST_HEAD(l);
	struct page *pg, *next;

	BUG_ON(irqs_disabled());

	spin_lock_irq(&cpa_lock);
	list_splice_init(&df_list, &l);
	spin_unlock_irq(&cpa_lock);
	flush_map();
	list_for_each_entry_safe(pg, next, &l, lru)
		__free_page(pg);
} 

#ifdef CONFIG_DEBUG_PAGEALLOC
void kernel_map_pages(struct page *page, int numpages, int enable)
{
	if (PageHighMem(page))
		return;
	/* the return value is ignored - the calls cannot fail,
	 * large pages are disabled at boot time.
	 */
	change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0));
	/* we should perform an IPI and flush all tlbs,
	 * but that can deadlock->flush only current cpu.
	 */
	__flush_tlb_all();
}
#endif

EXPORT_SYMBOL(change_page_attr);
EXPORT_SYMBOL(global_flush_tlb);