aboutsummaryrefslogtreecommitdiff
path: root/arch/ia64/mm/hugetlbpage.c
blob: df08ae7634b61d2efadf065e246c4bfb7f342b2c (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
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
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
/*
 * IA-64 Huge TLB Page Support for Kernel.
 *
 * Copyright (C) 2002-2004 Rohit Seth <rohit.seth@intel.com>
 * Copyright (C) 2003-2004 Ken Chen <kenneth.w.chen@intel.com>
 *
 * Sep, 2003: add numa support
 * Feb, 2004: dynamic hugetlb page size via boot parameter
 */

#include <linux/config.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>

unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT;

static pte_t *
huge_pte_alloc (struct mm_struct *mm, unsigned long addr)
{
	unsigned long taddr = htlbpage_to_page(addr);
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte = NULL;

	pgd = pgd_offset(mm, taddr);
	pud = pud_alloc(mm, pgd, taddr);
	if (pud) {
		pmd = pmd_alloc(mm, pud, taddr);
		if (pmd)
			pte = pte_alloc_map(mm, pmd, taddr);
	}
	return pte;
}

static pte_t *
huge_pte_offset (struct mm_struct *mm, unsigned long addr)
{
	unsigned long taddr = htlbpage_to_page(addr);
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte = NULL;

	pgd = pgd_offset(mm, taddr);
	if (pgd_present(*pgd)) {
		pud = pud_offset(pgd, taddr);
		if (pud_present(*pud)) {
			pmd = pmd_offset(pud, taddr);
			if (pmd_present(*pmd))
				pte = pte_offset_map(pmd, taddr);
		}
	}

	return pte;
}

#define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }

static void
set_huge_pte (struct mm_struct *mm, struct vm_area_struct *vma,
	      struct page *page, pte_t * page_table, int write_access)
{
	pte_t entry;

	add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
	if (write_access) {
		entry =
		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
	} else
		entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
	entry = pte_mkyoung(entry);
	mk_pte_huge(entry);
	set_pte(page_table, entry);
	return;
}
/*
 * This function checks for proper alignment of input addr and len parameters.
 */
int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
{
	if (len & ~HPAGE_MASK)
		return -EINVAL;
	if (addr & ~HPAGE_MASK)
		return -EINVAL;
	if (REGION_NUMBER(addr) != REGION_HPAGE)
		return -EINVAL;

	return 0;
}

int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			struct vm_area_struct *vma)
{
	pte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr = vma->vm_start;
	unsigned long end = vma->vm_end;

	while (addr < end) {
		dst_pte = huge_pte_alloc(dst, addr);
		if (!dst_pte)
			goto nomem;
		src_pte = huge_pte_offset(src, addr);
		entry = *src_pte;
		ptepage = pte_page(entry);
		get_page(ptepage);
		set_pte(dst_pte, entry);
		add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
		addr += HPAGE_SIZE;
	}
	return 0;
nomem:
	return -ENOMEM;
}

int
follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
		    struct page **pages, struct vm_area_struct **vmas,
		    unsigned long *st, int *length, int i)
{
	pte_t *ptep, pte;
	unsigned long start = *st;
	unsigned long pstart;
	int len = *length;
	struct page *page;

	do {
		pstart = start & HPAGE_MASK;
		ptep = huge_pte_offset(mm, start);
		pte = *ptep;

back1:
		page = pte_page(pte);
		if (pages) {
			page += ((start & ~HPAGE_MASK) >> PAGE_SHIFT);
			get_page(page);
			pages[i] = page;
		}
		if (vmas)
			vmas[i] = vma;
		i++;
		len--;
		start += PAGE_SIZE;
		if (((start & HPAGE_MASK) == pstart) && len &&
				(start < vma->vm_end))
			goto back1;
	} while (len && start < vma->vm_end);
	*length = len;
	*st = start;
	return i;
}

struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int write)
{
	struct page *page;
	pte_t *ptep;

	if (REGION_NUMBER(addr) != REGION_HPAGE)
		return ERR_PTR(-EINVAL);

	ptep = huge_pte_offset(mm, addr);
	if (!ptep || pte_none(*ptep))
		return NULL;
	page = pte_page(*ptep);
	page += ((addr & ~HPAGE_MASK) >> PAGE_SHIFT);
	return page;
}
int pmd_huge(pmd_t pmd)
{
	return 0;
}
struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
{
	return NULL;
}

void hugetlb_free_pgd_range(struct mmu_gather **tlb,
			unsigned long addr, unsigned long end,
			unsigned long floor, unsigned long ceiling)
{
	/*
	 * This is called only when is_hugepage_only_range(addr,),
	 * and it follows that is_hugepage_only_range(end,) also.
	 *
	 * The offset of these addresses from the base of the hugetlb
	 * region must be scaled down by HPAGE_SIZE/PAGE_SIZE so that
	 * the standard free_pgd_range will free the right page tables.
	 *
	 * If floor and ceiling are also in the hugetlb region, they
	 * must likewise be scaled down; but if outside, left unchanged.
	 */

	addr = htlbpage_to_page(addr);
	end  = htlbpage_to_page(end);
	if (is_hugepage_only_range(tlb->mm, floor, HPAGE_SIZE))
		floor = htlbpage_to_page(floor);
	if (is_hugepage_only_range(tlb->mm, ceiling, HPAGE_SIZE))
		ceiling = htlbpage_to_page(ceiling);

	free_pgd_range(tlb, addr, end, floor, ceiling);
}

void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address;
	pte_t *pte;
	struct page *page;

	BUG_ON(start & (HPAGE_SIZE - 1));
	BUG_ON(end & (HPAGE_SIZE - 1));

	for (address = start; address < end; address += HPAGE_SIZE) {
		pte = huge_pte_offset(mm, address);
		if (pte_none(*pte))
			continue;
		page = pte_page(*pte);
		put_page(page);
		pte_clear(mm, address, pte);
	}
	add_mm_counter(mm, rss, - ((end - start) >> PAGE_SHIFT));
	flush_tlb_range(vma, start, end);
}

int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
{
	struct mm_struct *mm = current->mm;
	unsigned long addr;
	int ret = 0;

	BUG_ON(vma->vm_start & ~HPAGE_MASK);
	BUG_ON(vma->vm_end & ~HPAGE_MASK);

	spin_lock(&mm->page_table_lock);
	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
		unsigned long idx;
		pte_t *pte = huge_pte_alloc(mm, addr);
		struct page *page;

		if (!pte) {
			ret = -ENOMEM;
			goto out;
		}
		if (!pte_none(*pte))
			continue;

		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
		page = find_get_page(mapping, idx);
		if (!page) {
			/* charge the fs quota first */
			if (hugetlb_get_quota(mapping)) {
				ret = -ENOMEM;
				goto out;
			}
			page = alloc_huge_page();
			if (!page) {
				hugetlb_put_quota(mapping);
				ret = -ENOMEM;
				goto out;
			}
			ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
			if (! ret) {
				unlock_page(page);
			} else {
				hugetlb_put_quota(mapping);
				page_cache_release(page);
				goto out;
			}
		}
		set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
	}
out:
	spin_unlock(&mm->page_table_lock);
	return ret;
}

unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
		unsigned long pgoff, unsigned long flags)
{
	struct vm_area_struct *vmm;

	if (len > RGN_MAP_LIMIT)
		return -ENOMEM;
	if (len & ~HPAGE_MASK)
		return -EINVAL;
	/* This code assumes that REGION_HPAGE != 0. */
	if ((REGION_NUMBER(addr) != REGION_HPAGE) || (addr & (HPAGE_SIZE - 1)))
		addr = HPAGE_REGION_BASE;
	else
		addr = ALIGN(addr, HPAGE_SIZE);
	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
		/* At this point:  (!vmm || addr < vmm->vm_end). */
		if (REGION_OFFSET(addr) + len > RGN_MAP_LIMIT)
			return -ENOMEM;
		if (!vmm || (addr + len) <= vmm->vm_start)
			return addr;
		addr = ALIGN(vmm->vm_end, HPAGE_SIZE);
	}
}

static int __init hugetlb_setup_sz(char *str)
{
	u64 tr_pages;
	unsigned long long size;

	if (ia64_pal_vm_page_size(&tr_pages, NULL) != 0)
		/*
		 * shouldn't happen, but just in case.
		 */
		tr_pages = 0x15557000UL;

	size = memparse(str, &str);
	if (*str || (size & (size-1)) || !(tr_pages & size) ||
		size <= PAGE_SIZE ||
		size >= (1UL << PAGE_SHIFT << MAX_ORDER)) {
		printk(KERN_WARNING "Invalid huge page size specified\n");
		return 1;
	}

	hpage_shift = __ffs(size);
	/*
	 * boot cpu already executed ia64_mmu_init, and has HPAGE_SHIFT_DEFAULT
	 * override here with new page shift.
	 */
	ia64_set_rr(HPAGE_REGION_BASE, hpage_shift << 2);
	return 1;
}
__setup("hugepagesz=", hugetlb_setup_sz);