aboutsummaryrefslogtreecommitdiff
path: root/arch/sparc64/mm/hugetlbpage.c
blob: eaba9b70b184ef67d47fbf76bdc9d92ea4314754 (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
/*
 * SPARC64 Huge TLB page support.
 *
 * Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net)
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.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>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>

/* Slightly simplified from the non-hugepage variant because by
 * definition we don't have to worry about any page coloring stuff
 */
#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL))
#define VA_EXCLUDE_END   (0xfffff80000000000UL + (1UL << 32UL))

static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
							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 task_size = TASK_SIZE;
	unsigned long start_addr;

	if (test_thread_flag(TIF_32BIT))
		task_size = STACK_TOP32;
	if (unlikely(len >= VA_EXCLUDE_START))
		return -ENOMEM;

	if (len > mm->cached_hole_size) {
	        start_addr = addr = mm->free_area_cache;
	} else {
	        start_addr = addr = TASK_UNMAPPED_BASE;
	        mm->cached_hole_size = 0;
	}

	task_size -= len;

full_search:
	addr = ALIGN(addr, HPAGE_SIZE);

	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (addr < VA_EXCLUDE_START &&
		    (addr + len) >= VA_EXCLUDE_START) {
			addr = VA_EXCLUDE_END;
			vma = find_vma(mm, VA_EXCLUDE_END);
		}
		if (unlikely(task_size < addr)) {
			if (start_addr != TASK_UNMAPPED_BASE) {
				start_addr = addr = TASK_UNMAPPED_BASE;
				mm->cached_hole_size = 0;
				goto full_search;
			}
			return -ENOMEM;
		}
		if (likely(!vma || addr + len <= vma->vm_start)) {
			/*
			 * Remember the place where we stopped the search:
			 */
			mm->free_area_cache = addr + len;
			return addr;
		}
		if (addr + mm->cached_hole_size < vma->vm_start)
		        mm->cached_hole_size = vma->vm_start - addr;

		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
	}
}

static unsigned long
hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
				  const unsigned long len,
				  const unsigned long pgoff,
				  const unsigned long flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	unsigned long addr = addr0;

	/* This should only ever run for 32-bit processes.  */
	BUG_ON(!test_thread_flag(TIF_32BIT));

	/* check if free_area_cache is useful for us */
	if (len <= mm->cached_hole_size) {
 	        mm->cached_hole_size = 0;
 		mm->free_area_cache = mm->mmap_base;
 	}

	/* either no address requested or can't fit in requested address hole */
	addr = mm->free_area_cache & HPAGE_MASK;

	/* make sure it can fit in the remaining address space */
	if (likely(addr > len)) {
		vma = find_vma(mm, addr-len);
		if (!vma || addr <= vma->vm_start) {
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr-len);
		}
	}

	if (unlikely(mm->mmap_base < len))
		goto bottomup;

	addr = (mm->mmap_base-len) & HPAGE_MASK;

	do {
		/*
		 * Lookup failure means no vma is above this address,
		 * else if new region fits below vma->vm_start,
		 * return with success:
		 */
		vma = find_vma(mm, addr);
		if (likely(!vma || addr+len <= vma->vm_start)) {
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr);
		}

 		/* remember the largest hole we saw so far */
 		if (addr + mm->cached_hole_size < vma->vm_start)
 		        mm->cached_hole_size = vma->vm_start - addr;

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

bottomup:
	/*
	 * 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->cached_hole_size = ~0UL;
  	mm->free_area_cache = TASK_UNMAPPED_BASE;
	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
	/*
	 * Restore the topdown base:
	 */
	mm->free_area_cache = mm->mmap_base;
	mm->cached_hole_size = ~0UL;

	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;
	unsigned long task_size = TASK_SIZE;

	if (test_thread_flag(TIF_32BIT))
		task_size = STACK_TOP32;

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

	if (flags & MAP_FIXED) {
		if (prepare_hugepage_range(addr, len, pgoff))
			return -EINVAL;
		return addr;
	}

	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);
}

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

	/* We must align the address, because our caller will run
	 * set_huge_pte_at() on whatever we return, which writes out
	 * all of the sub-ptes for the hugepage range.  So we have
	 * to give it the first such sub-pte.
	 */
	addr &= HPAGE_MASK;

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

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

	addr &= HPAGE_MASK;

	pgd = pgd_offset(mm, addr);
	if (!pgd_none(*pgd)) {
		pud = pud_offset(pgd, addr);
		if (!pud_none(*pud)) {
			pmd = pmd_offset(pud, addr);
			if (!pmd_none(*pmd))
				pte = pte_offset_map(pmd, addr);
		}
	}
	return pte;
}

int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
{
	return 0;
}

void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
		     pte_t *ptep, pte_t entry)
{
	int i;

	if (!pte_present(*ptep) && pte_present(entry))
		mm->context.huge_pte_count++;

	addr &= HPAGE_MASK;
	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
		set_pte_at(mm, addr, ptep, entry);
		ptep++;
		addr += PAGE_SIZE;
		pte_val(entry) += PAGE_SIZE;
	}
}

pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
			      pte_t *ptep)
{
	pte_t entry;
	int i;

	entry = *ptep;
	if (pte_present(entry))
		mm->context.huge_pte_count--;

	addr &= HPAGE_MASK;

	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
		pte_clear(mm, addr, ptep);
		addr += PAGE_SIZE;
		ptep++;
	}

	return entry;
}

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 0;
}

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

static void context_reload(void *__data)
{
	struct mm_struct *mm = __data;

	if (mm == current->mm)
		load_secondary_context(mm);
}

void hugetlb_prefault_arch_hook(struct mm_struct *mm)
{
	struct tsb_config *tp = &mm->context.tsb_block[MM_TSB_HUGE];

	if (likely(tp->tsb != NULL))
		return;

	tsb_grow(mm, MM_TSB_HUGE, 0);
	tsb_context_switch(mm);
	smp_tsb_sync(mm);

	/* On UltraSPARC-III+ and later, configure the second half of
	 * the Data-TLB for huge pages.
	 */
	if (tlb_type == cheetah_plus) {
		unsigned long ctx;

		spin_lock(&ctx_alloc_lock);
		ctx = mm->context.sparc64_ctx_val;
		ctx &= ~CTX_PGSZ_MASK;
		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
		ctx |= CTX_PGSZ_HUGE << CTX_PGSZ1_SHIFT;

		if (ctx != mm->context.sparc64_ctx_val) {
			/* When changing the page size fields, we
			 * must perform a context flush so that no
			 * stale entries match.  This flush must
			 * occur with the original context register
			 * settings.
			 */
			do_flush_tlb_mm(mm);

			/* Reload the context register of all processors
			 * also executing in this address space.
			 */
			mm->context.sparc64_ctx_val = ctx;
			on_each_cpu(context_reload, mm, 0, 0);
		}
		spin_unlock(&ctx_alloc_lock);
	}
}