summaryrefslogtreecommitdiff
path: root/arch/i386/mm/hugetlbpage.c
blob: 171fc925e1e4e7c699c6222b229914b320c987c3 (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
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
/*
 * IA-32 Huge TLB Page Support for Kernel.
 *
 * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
 */

#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/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>

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

	pgd = pgd_offset(mm, addr);
	pud = pud_alloc(mm, pgd, addr);
	pmd = pmd_alloc(mm, pud, addr);
	return (pte_t *) pmd;
}

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

	pgd = pgd_offset(mm, addr);
	pud = pud_offset(pgd, addr);
	pmd = pmd_offset(pud, addr);
	return (pte_t *) pmd;
}

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);
}

/*
 * 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;
	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 *position, int *length, int i)
{
	unsigned long vpfn, vaddr = *position;
	int remainder = *length;

	WARN_ON(!is_vm_hugetlb_page(vma));

	vpfn = vaddr/PAGE_SIZE;
	while (vaddr < vma->vm_end && remainder) {

		if (pages) {
			pte_t *pte;
			struct page *page;

			pte = huge_pte_offset(mm, vaddr);

			/* hugetlb should be locked, and hence, prefaulted */
			WARN_ON(!pte || pte_none(*pte));

			page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];

			WARN_ON(!PageCompound(page));

			get_page(page);
			pages[i] = page;
		}

		if (vmas)
			vmas[i] = vma;

		vaddr += PAGE_SIZE;
		++vpfn;
		--remainder;
		++i;
	}

	*length = remainder;
	*position = vaddr;

	return i;
}

#if 0	/* This is just for testing */
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
	unsigned long start = address;
	int length = 1;
	int nr;
	struct page *page;
	struct vm_area_struct *vma;

	vma = find_vma(mm, addr);
	if (!vma || !is_vm_hugetlb_page(vma))
		return ERR_PTR(-EINVAL);

	pte = huge_pte_offset(mm, address);

	/* hugetlb should be locked, and hence, prefaulted */
	WARN_ON(!pte || pte_none(*pte));

	page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];

	WARN_ON(!PageCompound(page));

	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;
}

#else

struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
	return ERR_PTR(-EINVAL);
}

int pmd_huge(pmd_t pmd)
{
	return !!(pmd_val(pmd) & _PAGE_PSE);
}

struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
		pmd_t *pmd, int write)
{
	struct page *page;

	page = pte_page(*(pte_t *)pmd);
	if (page)
		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
	return page;
}
#endif

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, *ptep;
	struct page *page;

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

	for (address = start; address < end; address += HPAGE_SIZE) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;
		pte = ptep_get_and_clear(mm, address, ptep);
		if (pte_none(pte))
			continue;
		page = pte_page(pte);
		put_page(page);
	}
	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);
				free_huge_page(page);
				goto out;
			}
		}
		set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
	}
out:
	spin_unlock(&mm->page_table_lock);
	return ret;
}

/* x86_64 also uses this file */

#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
		unsigned long addr, unsigned long len,
		unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long start_addr;

	start_addr = mm->free_area_cache;

full_search:
	addr = ALIGN(start_addr, HPAGE_SIZE);

	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (TASK_SIZE - len < addr) {
			/*
			 * Start a new search - just in case we missed
			 * some holes.
			 */
			if (start_addr != TASK_UNMAPPED_BASE) {
				start_addr = TASK_UNMAPPED_BASE;
				goto full_search;
			}
			return -ENOMEM;
		}
		if (!vma || addr + len <= vma->vm_start) {
			mm->free_area_cache = addr + len;
			return addr;
		}
		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
	}
}

static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
		unsigned long addr0, unsigned long len,
		unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma, *prev_vma;
	unsigned long base = mm->mmap_base, addr = addr0;
	int first_time = 1;

	/* don't allow allocations above current base */
	if (mm->free_area_cache > base)
		mm->free_area_cache = base;

try_again:
	/* make sure it can fit in the remaining address space */
	if (mm->free_area_cache < len)
		goto fail;

	/* either no address requested or cant fit in requested address hole */
	addr = (mm->free_area_cache - len) & HPAGE_MASK;
	do {
		/*
		 * Lookup failure means no vma is above this address,
		 * i.e. return with success:
		 */
		if (!(vma = find_vma_prev(mm, addr, &prev_vma)))
			return addr;

		/*
		 * new region fits between prev_vma->vm_end and
		 * vma->vm_start, use it:
		 */
		if (addr + len <= vma->vm_start &&
				(!prev_vma || (addr >= prev_vma->vm_end)))
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr);
		else
			/* pull free_area_cache down to the first hole */
			if (mm->free_area_cache == vma->vm_end)
				mm->free_area_cache = vma->vm_start;

		/* try just below the current vma->vm_start */
		addr = (vma->vm_start - len) & HPAGE_MASK;
	} while (len <= vma->vm_start);

fail:
	/*
	 * if hint left us with no space for the requested
	 * mapping then try again:
	 */
	if (first_time) {
		mm->free_area_cache = base;
		first_time = 0;
		goto try_again;
	}
	/*
	 * A failed mmap() very likely causes application failure,
	 * so fall back to the bottom-up function here. This scenario
	 * can happen with large stack limits and large mmap()
	 * allocations.
	 */
	mm->free_area_cache = TASK_UNMAPPED_BASE;
	addr = hugetlb_get_unmapped_area_bottomup(file, addr0,
			len, pgoff, flags);

	/*
	 * Restore the topdown base:
	 */
	mm->free_area_cache = base;

	return addr;
}

unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	if (len & ~HPAGE_MASK)
		return -EINVAL;
	if (len > TASK_SIZE)
		return -ENOMEM;

	if (addr) {
		addr = ALIGN(addr, HPAGE_SIZE);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}
	if (mm->get_unmapped_area == arch_get_unmapped_area)
		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
				pgoff, flags);
	else
		return hugetlb_get_unmapped_area_topdown(file, addr, len,
				pgoff, flags);
}

#endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/