summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/mmu.c
blob: eb293febfb5603147f433e3a60b156fdba850eb1 (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
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
/*
 * Based on arch/arm/mm/mmu.c
 *
 * Copyright (C) 1995-2005 Russell King
 * Copyright (C) 2012 ARM Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/stop_machine.h>

#include <asm/cputype.h>
#include <asm/fixmap.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/sizes.h>
#include <asm/tlb.h>
#include <asm/memblock.h>
#include <asm/mmu_context.h>

#include "mm.h"

/*
 * Empty_zero_page is a special page that is used for zero-initialized data
 * and COW.
 */
struct page *empty_zero_page;
EXPORT_SYMBOL(empty_zero_page);

pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
			      unsigned long size, pgprot_t vma_prot)
{
	if (!pfn_valid(pfn))
		return pgprot_noncached(vma_prot);
	else if (file->f_flags & O_SYNC)
		return pgprot_writecombine(vma_prot);
	return vma_prot;
}
EXPORT_SYMBOL(phys_mem_access_prot);

static void __init *early_alloc(unsigned long sz)
{
	void *ptr = __va(memblock_alloc(sz, sz));
	BUG_ON(!ptr);
	memset(ptr, 0, sz);
	return ptr;
}

/*
 * remap a PMD into pages
 */
static void split_pmd(pmd_t *pmd, pte_t *pte)
{
	unsigned long pfn = pmd_pfn(*pmd);
	int i = 0;

	do {
		/*
		 * Need to have the least restrictive permissions available
		 * permissions will be fixed up later
		 */
		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
		pfn++;
	} while (pte++, i++, i < PTRS_PER_PTE);
}

static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
				  unsigned long end, unsigned long pfn,
				  pgprot_t prot,
				  void *(*alloc)(unsigned long size))
{
	pte_t *pte;

	if (pmd_none(*pmd) || pmd_bad(*pmd)) {
		pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
		if (pmd_sect(*pmd))
			split_pmd(pmd, pte);
		__pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE);
		flush_tlb_all();
	}

	pte = pte_offset_kernel(pmd, addr);
	do {
		set_pte(pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
}

void split_pud(pud_t *old_pud, pmd_t *pmd)
{
	unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT;
	pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr);
	int i = 0;

	do {
		set_pmd(pmd, __pmd(addr | prot));
		addr += PMD_SIZE;
	} while (pmd++, i++, i < PTRS_PER_PMD);
}

static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud,
				  unsigned long addr, unsigned long end,
				  phys_addr_t phys, pgprot_t prot,
				  void *(*alloc)(unsigned long size))
{
	pmd_t *pmd;
	unsigned long next;

	/*
	 * Check for initial section mappings in the pgd/pud and remove them.
	 */
	if (pud_none(*pud) || pud_bad(*pud)) {
		pmd = alloc(PTRS_PER_PMD * sizeof(pmd_t));
		if (pud_sect(*pud)) {
			/*
			 * need to have the 1G of mappings continue to be
			 * present
			 */
			split_pud(pud, pmd);
		}
		pud_populate(mm, pud, pmd);
		flush_tlb_all();
	}

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		/* try section mapping first */
		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
			pmd_t old_pmd =*pmd;
			set_pmd(pmd, __pmd(phys |
					   pgprot_val(mk_sect_prot(prot))));
			/*
			 * Check for previous table entries created during
			 * boot (__create_page_tables) and flush them.
			 */
			if (!pmd_none(old_pmd)) {
				flush_tlb_all();
				if (pmd_table(old_pmd)) {
					phys_addr_t table = __pa(pte_offset_map(&old_pmd, 0));
					BUG_ON(alloc != early_alloc);
					memblock_free(table, PAGE_SIZE);
				}
			}
		} else {
			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
				       prot, alloc);
		}
		phys += next - addr;
	} while (pmd++, addr = next, addr != end);
}

static inline bool use_1G_block(unsigned long addr, unsigned long next,
			unsigned long phys)
{
	if (PAGE_SHIFT != 12)
		return false;

	if (((addr | next | phys) & ~PUD_MASK) != 0)
		return false;

	return true;
}

static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd,
				  unsigned long addr, unsigned long end,
				  phys_addr_t phys, pgprot_t prot,
				  void *(*alloc)(unsigned long size))
{
	pud_t *pud;
	unsigned long next;

	if (pgd_none(*pgd)) {
		pud = alloc(PTRS_PER_PUD * sizeof(pud_t));
		pgd_populate(mm, pgd, pud);
	}
	BUG_ON(pgd_bad(*pgd));

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);

		/*
		 * For 4K granule only, attempt to put down a 1GB block
		 */
		if (use_1G_block(addr, next, phys)) {
			pud_t old_pud = *pud;
			set_pud(pud, __pud(phys |
					   pgprot_val(mk_sect_prot(prot))));

			/*
			 * If we have an old value for a pud, it will
			 * be pointing to a pmd table that we no longer
			 * need (from swapper_pg_dir).
			 *
			 * Look up the old pmd table and free it.
			 */
			if (!pud_none(old_pud)) {
				flush_tlb_all();
				if (pud_table(old_pud)) {
					phys_addr_t table = __pa(pmd_offset(&old_pud, 0));
					BUG_ON(alloc != early_alloc);
					memblock_free(table, PAGE_SIZE);
				}
			}
		} else {
			alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc);
		}
		phys += next - addr;
	} while (pud++, addr = next, addr != end);
}

/*
 * Create the page directory entries and any necessary page tables for the
 * mapping specified by 'md'.
 */
static void  __create_mapping(struct mm_struct *mm, pgd_t *pgd,
				    phys_addr_t phys, unsigned long virt,
				    phys_addr_t size, pgprot_t prot,
				    void *(*alloc)(unsigned long size))
{
	unsigned long addr, length, end, next;

	addr = virt & PAGE_MASK;
	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));

	end = addr + length;
	do {
		next = pgd_addr_end(addr, end);
		alloc_init_pud(mm, pgd, addr, next, phys, prot, alloc);
		phys += next - addr;
	} while (pgd++, addr = next, addr != end);
}

static void *late_alloc(unsigned long size)
{
	void *ptr;

	BUG_ON(size > PAGE_SIZE);
	ptr = (void *)__get_free_page(PGALLOC_GFP);
	BUG_ON(!ptr);
	return ptr;
}

static void __ref create_mapping(phys_addr_t phys, unsigned long virt,
				  phys_addr_t size, pgprot_t prot)
{
	if (virt < VMALLOC_START) {
		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
			&phys, virt);
		return;
	}
	__create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt,
			 size, prot, early_alloc);
}

void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
			       unsigned long virt, phys_addr_t size,
			       pgprot_t prot)
{
	__create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot,
				late_alloc);
}

static void create_mapping_late(phys_addr_t phys, unsigned long virt,
				  phys_addr_t size, pgprot_t prot)
{
	if (virt < VMALLOC_START) {
		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
			&phys, virt);
		return;
	}

	return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK),
				phys, virt, size, prot, late_alloc);
}

#ifdef CONFIG_DEBUG_RODATA
static void __init __map_memblock(phys_addr_t start, phys_addr_t end)
{
	/*
	 * Set up the executable regions using the existing section mappings
	 * for now. This will get more fine grained later once all memory
	 * is mapped
	 */
	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);

	if (end < kernel_x_start) {
		create_mapping(start, __phys_to_virt(start),
			end - start, PAGE_KERNEL);
	} else if (start >= kernel_x_end) {
		create_mapping(start, __phys_to_virt(start),
			end - start, PAGE_KERNEL);
	} else {
		if (start < kernel_x_start)
			create_mapping(start, __phys_to_virt(start),
				kernel_x_start - start,
				PAGE_KERNEL);
		create_mapping(kernel_x_start,
				__phys_to_virt(kernel_x_start),
				kernel_x_end - kernel_x_start,
				PAGE_KERNEL_EXEC);
		if (kernel_x_end < end)
			create_mapping(kernel_x_end,
				__phys_to_virt(kernel_x_end),
				end - kernel_x_end,
				PAGE_KERNEL);
	}

}
#else
static void __init __map_memblock(phys_addr_t start, phys_addr_t end)
{
	create_mapping(start, __phys_to_virt(start), end - start,
			PAGE_KERNEL_EXEC);
}
#endif

static void __init map_mem(void)
{
	struct memblock_region *reg;
	phys_addr_t limit;

	/*
	 * Temporarily limit the memblock range. We need to do this as
	 * create_mapping requires puds, pmds and ptes to be allocated from
	 * memory addressable from the initial direct kernel mapping.
	 *
	 * The initial direct kernel mapping, located at swapper_pg_dir, gives
	 * us PUD_SIZE (4K pages) or PMD_SIZE (64K pages) memory starting from
	 * PHYS_OFFSET (which must be aligned to 2MB as per
	 * Documentation/arm64/booting.txt).
	 */
	if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
		limit = PHYS_OFFSET + PMD_SIZE;
	else
		limit = PHYS_OFFSET + PUD_SIZE;
	memblock_set_current_limit(limit);

	/* map all the memory banks */
	for_each_memblock(memory, reg) {
		phys_addr_t start = reg->base;
		phys_addr_t end = start + reg->size;

		if (start >= end)
			break;

#ifndef CONFIG_ARM64_64K_PAGES
		/*
		 * For the first memory bank align the start address and
		 * current memblock limit to prevent create_mapping() from
		 * allocating pte page tables from unmapped memory.
		 * When 64K pages are enabled, the pte page table for the
		 * first PGDIR_SIZE is already present in swapper_pg_dir.
		 */
		if (start < limit)
			start = ALIGN(start, PMD_SIZE);
		if (end < limit) {
			limit = end & PMD_MASK;
			memblock_set_current_limit(limit);
		}
#endif
		__map_memblock(start, end);
	}

	/* Limit no longer required. */
	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
}

void __init fixup_executable(void)
{
#ifdef CONFIG_DEBUG_RODATA
	/* now that we are actually fully mapped, make the start/end more fine grained */
	if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) {
		unsigned long aligned_start = round_down(__pa(_stext),
							SECTION_SIZE);

		create_mapping(aligned_start, __phys_to_virt(aligned_start),
				__pa(_stext) - aligned_start,
				PAGE_KERNEL);
	}

	if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) {
		unsigned long aligned_end = round_up(__pa(__init_end),
							SECTION_SIZE);
		create_mapping(__pa(__init_end), (unsigned long)__init_end,
				aligned_end - __pa(__init_end),
				PAGE_KERNEL);
	}
#endif
}

#ifdef CONFIG_DEBUG_RODATA
void mark_rodata_ro(void)
{
	create_mapping_late(__pa(_stext), (unsigned long)_stext,
				(unsigned long)_etext - (unsigned long)_stext,
				PAGE_KERNEL_EXEC | PTE_RDONLY);

}
#endif

void fixup_init(void)
{
	create_mapping_late(__pa(__init_begin), (unsigned long)__init_begin,
			(unsigned long)__init_end - (unsigned long)__init_begin,
			PAGE_KERNEL);
}

/*
 * paging_init() sets up the page tables, initialises the zone memory
 * maps and sets up the zero page.
 */
void __init paging_init(void)
{
	void *zero_page;

	map_mem();
	fixup_executable();

	/*
	 * Finally flush the caches and tlb to ensure that we're in a
	 * consistent state.
	 */
	flush_cache_all();
	flush_tlb_all();

	/* allocate the zero page. */
	zero_page = early_alloc(PAGE_SIZE);

	bootmem_init();

	empty_zero_page = virt_to_page(zero_page);

	/*
	 * TTBR0 is only used for the identity mapping at this stage. Make it
	 * point to zero page to avoid speculatively fetching new entries.
	 */
	cpu_set_reserved_ttbr0();
	flush_tlb_all();
}

/*
 * Enable the identity mapping to allow the MMU disabling.
 */
void setup_mm_for_reboot(void)
{
	cpu_switch_mm(idmap_pg_dir, &init_mm);
	flush_tlb_all();
}

/*
 * Check whether a kernel address is valid (derived from arch/x86/).
 */
int kern_addr_valid(unsigned long addr)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if ((((long)addr) >> VA_BITS) != -1UL)
		return 0;

	pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd))
		return 0;

	pud = pud_offset(pgd, addr);
	if (pud_none(*pud))
		return 0;

	if (pud_sect(*pud))
		return pfn_valid(pud_pfn(*pud));

	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return 0;

	if (pmd_sect(*pmd))
		return pfn_valid(pmd_pfn(*pmd));

	pte = pte_offset_kernel(pmd, addr);
	if (pte_none(*pte))
		return 0;

	return pfn_valid(pte_pfn(*pte));
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#ifdef CONFIG_ARM64_64K_PAGES
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
	return vmemmap_populate_basepages(start, end, node);
}
#else	/* !CONFIG_ARM64_64K_PAGES */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
	unsigned long addr = start;
	unsigned long next;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	do {
		next = pmd_addr_end(addr, end);

		pgd = vmemmap_pgd_populate(addr, node);
		if (!pgd)
			return -ENOMEM;

		pud = vmemmap_pud_populate(pgd, addr, node);
		if (!pud)
			return -ENOMEM;

		pmd = pmd_offset(pud, addr);
		if (pmd_none(*pmd)) {
			void *p = NULL;

			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
			if (!p)
				return -ENOMEM;

			set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
		} else
			vmemmap_verify((pte_t *)pmd, node, addr, next);
	} while (addr = next, addr != end);

	return 0;
}
#endif	/* CONFIG_ARM64_64K_PAGES */
void vmemmap_free(unsigned long start, unsigned long end)
{
}
#endif	/* CONFIG_SPARSEMEM_VMEMMAP */

static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
#if CONFIG_ARM64_PGTABLE_LEVELS > 2
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss;
#endif
#if CONFIG_ARM64_PGTABLE_LEVELS > 3
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss;
#endif

static inline pud_t * fixmap_pud(unsigned long addr)
{
	pgd_t *pgd = pgd_offset_k(addr);

	BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));

	return pud_offset(pgd, addr);
}

static inline pmd_t * fixmap_pmd(unsigned long addr)
{
	pud_t *pud = fixmap_pud(addr);

	BUG_ON(pud_none(*pud) || pud_bad(*pud));

	return pmd_offset(pud, addr);
}

static inline pte_t * fixmap_pte(unsigned long addr)
{
	pmd_t *pmd = fixmap_pmd(addr);

	BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd));

	return pte_offset_kernel(pmd, addr);
}

void __init early_fixmap_init(void)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	unsigned long addr = FIXADDR_START;

	pgd = pgd_offset_k(addr);
	pgd_populate(&init_mm, pgd, bm_pud);
	pud = pud_offset(pgd, addr);
	pud_populate(&init_mm, pud, bm_pmd);
	pmd = pmd_offset(pud, addr);
	pmd_populate_kernel(&init_mm, pmd, bm_pte);

	/*
	 * The boot-ioremap range spans multiple pmds, for which
	 * we are not preparted:
	 */
	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));

	if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
	     || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
		WARN_ON(1);
		pr_warn("pmd %p != %p, %p\n",
			pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
			fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
			fix_to_virt(FIX_BTMAP_BEGIN));
		pr_warn("fix_to_virt(FIX_BTMAP_END):   %08lx\n",
			fix_to_virt(FIX_BTMAP_END));

		pr_warn("FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
		pr_warn("FIX_BTMAP_BEGIN:     %d\n", FIX_BTMAP_BEGIN);
	}
}

void __set_fixmap(enum fixed_addresses idx,
			       phys_addr_t phys, pgprot_t flags)
{
	unsigned long addr = __fix_to_virt(idx);
	pte_t *pte;

	if (idx >= __end_of_fixed_addresses) {
		BUG();
		return;
	}

	pte = fixmap_pte(addr);

	if (pgprot_val(flags)) {
		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
	} else {
		pte_clear(&init_mm, addr, pte);
		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
	}
}