summaryrefslogtreecommitdiff
path: root/arch/riscv/include/asm/pgtable.h
blob: 62f3fe7368f39bef7e5d4239b20588e4381cf118 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2012 Regents of the University of California
 */

#ifndef _ASM_RISCV_PGTABLE_H
#define _ASM_RISCV_PGTABLE_H

#include <linux/mmzone.h>
#include <linux/sizes.h>

#include <asm/pgtable-bits.h>

#ifndef CONFIG_MMU
#define KERNEL_LINK_ADDR	PAGE_OFFSET
#else

#define ADDRESS_SPACE_END	(UL(-1))

#ifdef CONFIG_64BIT
/* Leave 2GB for kernel and BPF at the end of the address space */
#define KERNEL_LINK_ADDR	(ADDRESS_SPACE_END - SZ_2G + 1)
#else
#define KERNEL_LINK_ADDR	PAGE_OFFSET
#endif

#define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
#define VMALLOC_END      (PAGE_OFFSET - 1)
#define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

#define BPF_JIT_REGION_SIZE	(SZ_128M)
#ifdef CONFIG_64BIT
#define BPF_JIT_REGION_START	(BPF_JIT_REGION_END - BPF_JIT_REGION_SIZE)
#define BPF_JIT_REGION_END	(MODULES_END)
#else
#define BPF_JIT_REGION_START	(PAGE_OFFSET - BPF_JIT_REGION_SIZE)
#define BPF_JIT_REGION_END	(VMALLOC_END)
#endif

/* Modules always live before the kernel */
#ifdef CONFIG_64BIT
#define MODULES_VADDR	(PFN_ALIGN((unsigned long)&_end) - SZ_2G)
#define MODULES_END	(PFN_ALIGN((unsigned long)&_start))
#endif

/*
 * Roughly size the vmemmap space to be large enough to fit enough
 * struct pages to map half the virtual address space. Then
 * position vmemmap directly below the VMALLOC region.
 */
#define VMEMMAP_SHIFT \
	(CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
#define VMEMMAP_SIZE	BIT(VMEMMAP_SHIFT)
#define VMEMMAP_END	(VMALLOC_START - 1)
#define VMEMMAP_START	(VMALLOC_START - VMEMMAP_SIZE)

/*
 * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
 * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
 */
#define vmemmap		((struct page *)VMEMMAP_START)

#define PCI_IO_SIZE      SZ_16M
#define PCI_IO_END       VMEMMAP_START
#define PCI_IO_START     (PCI_IO_END - PCI_IO_SIZE)

#define FIXADDR_TOP      PCI_IO_START
#ifdef CONFIG_64BIT
#define FIXADDR_SIZE     PMD_SIZE
#else
#define FIXADDR_SIZE     PGDIR_SIZE
#endif
#define FIXADDR_START    (FIXADDR_TOP - FIXADDR_SIZE)

#endif

#ifdef CONFIG_XIP_KERNEL
#define XIP_OFFSET		SZ_8M
#endif

#ifndef __ASSEMBLY__

/* Page Upper Directory not used in RISC-V */
#include <asm-generic/pgtable-nopud.h>
#include <asm/page.h>
#include <asm/tlbflush.h>
#include <linux/mm_types.h>

#ifdef CONFIG_64BIT
#include <asm/pgtable-64.h>
#else
#include <asm/pgtable-32.h>
#endif /* CONFIG_64BIT */

#ifdef CONFIG_XIP_KERNEL
#define XIP_FIXUP(addr) ({							\
	uintptr_t __a = (uintptr_t)(addr);					\
	(__a >= CONFIG_XIP_PHYS_ADDR && __a < CONFIG_XIP_PHYS_ADDR + SZ_16M) ?	\
		__a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\
		__a;								\
	})
#else
#define XIP_FIXUP(addr)		(addr)
#endif /* CONFIG_XIP_KERNEL */

#ifdef CONFIG_MMU
/* Number of entries in the page global directory */
#define PTRS_PER_PGD    (PAGE_SIZE / sizeof(pgd_t))
/* Number of entries in the page table */
#define PTRS_PER_PTE    (PAGE_SIZE / sizeof(pte_t))

/* Number of PGD entries that a user-mode program can use */
#define USER_PTRS_PER_PGD   (TASK_SIZE / PGDIR_SIZE)

/* Page protection bits */
#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER)

#define PAGE_NONE		__pgprot(_PAGE_PROT_NONE)
#define PAGE_READ		__pgprot(_PAGE_BASE | _PAGE_READ)
#define PAGE_WRITE		__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE)
#define PAGE_EXEC		__pgprot(_PAGE_BASE | _PAGE_EXEC)
#define PAGE_READ_EXEC		__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
#define PAGE_WRITE_EXEC		__pgprot(_PAGE_BASE | _PAGE_READ |	\
					 _PAGE_EXEC | _PAGE_WRITE)

#define PAGE_COPY		PAGE_READ
#define PAGE_COPY_EXEC		PAGE_EXEC
#define PAGE_COPY_READ_EXEC	PAGE_READ_EXEC
#define PAGE_SHARED		PAGE_WRITE
#define PAGE_SHARED_EXEC	PAGE_WRITE_EXEC

#define _PAGE_KERNEL		(_PAGE_READ \
				| _PAGE_WRITE \
				| _PAGE_PRESENT \
				| _PAGE_ACCESSED \
				| _PAGE_DIRTY)

#define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
#define PAGE_KERNEL_READ	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL | _PAGE_EXEC)
#define PAGE_KERNEL_READ_EXEC	__pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \
					 | _PAGE_EXEC)

#define PAGE_TABLE		__pgprot(_PAGE_TABLE)

/*
 * The RISC-V ISA doesn't yet specify how to query or modify PMAs, so we can't
 * change the properties of memory regions.
 */
#define _PAGE_IOREMAP _PAGE_KERNEL

extern pgd_t swapper_pg_dir[];

/* MAP_PRIVATE permissions: xwr (copy-on-write) */
#define __P000	PAGE_NONE
#define __P001	PAGE_READ
#define __P010	PAGE_COPY
#define __P011	PAGE_COPY
#define __P100	PAGE_EXEC
#define __P101	PAGE_READ_EXEC
#define __P110	PAGE_COPY_EXEC
#define __P111	PAGE_COPY_READ_EXEC

/* MAP_SHARED permissions: xwr */
#define __S000	PAGE_NONE
#define __S001	PAGE_READ
#define __S010	PAGE_SHARED
#define __S011	PAGE_SHARED
#define __S100	PAGE_EXEC
#define __S101	PAGE_READ_EXEC
#define __S110	PAGE_SHARED_EXEC
#define __S111	PAGE_SHARED_EXEC

static inline int pmd_present(pmd_t pmd)
{
	return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
}

static inline int pmd_none(pmd_t pmd)
{
	return (pmd_val(pmd) == 0);
}

static inline int pmd_bad(pmd_t pmd)
{
	return !pmd_present(pmd);
}

#define pmd_leaf	pmd_leaf
static inline int pmd_leaf(pmd_t pmd)
{
	return pmd_present(pmd) &&
	       (pmd_val(pmd) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
}

static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
	*pmdp = pmd;
}

static inline void pmd_clear(pmd_t *pmdp)
{
	set_pmd(pmdp, __pmd(0));
}

static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot)
{
	return __pgd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
}

static inline unsigned long _pgd_pfn(pgd_t pgd)
{
	return pgd_val(pgd) >> _PAGE_PFN_SHIFT;
}

static inline struct page *pmd_page(pmd_t pmd)
{
	return pfn_to_page(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
}

static inline unsigned long pmd_page_vaddr(pmd_t pmd)
{
	return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
}

static inline pte_t pmd_pte(pmd_t pmd)
{
	return __pte(pmd_val(pmd));
}

/* Yields the page frame number (PFN) of a page table entry */
static inline unsigned long pte_pfn(pte_t pte)
{
	return (pte_val(pte) >> _PAGE_PFN_SHIFT);
}

#define pte_page(x)     pfn_to_page(pte_pfn(x))

/* Constructs a page table entry */
static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
{
	return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
}

#define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)

static inline int pte_present(pte_t pte)
{
	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
}

static inline int pte_none(pte_t pte)
{
	return (pte_val(pte) == 0);
}

static inline int pte_write(pte_t pte)
{
	return pte_val(pte) & _PAGE_WRITE;
}

static inline int pte_exec(pte_t pte)
{
	return pte_val(pte) & _PAGE_EXEC;
}

static inline int pte_huge(pte_t pte)
{
	return pte_present(pte)
		&& (pte_val(pte) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
}

static inline int pte_dirty(pte_t pte)
{
	return pte_val(pte) & _PAGE_DIRTY;
}

static inline int pte_young(pte_t pte)
{
	return pte_val(pte) & _PAGE_ACCESSED;
}

static inline int pte_special(pte_t pte)
{
	return pte_val(pte) & _PAGE_SPECIAL;
}

/* static inline pte_t pte_rdprotect(pte_t pte) */

static inline pte_t pte_wrprotect(pte_t pte)
{
	return __pte(pte_val(pte) & ~(_PAGE_WRITE));
}

/* static inline pte_t pte_mkread(pte_t pte) */

static inline pte_t pte_mkwrite(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_WRITE);
}

/* static inline pte_t pte_mkexec(pte_t pte) */

static inline pte_t pte_mkdirty(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_DIRTY);
}

static inline pte_t pte_mkclean(pte_t pte)
{
	return __pte(pte_val(pte) & ~(_PAGE_DIRTY));
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_ACCESSED);
}

static inline pte_t pte_mkold(pte_t pte)
{
	return __pte(pte_val(pte) & ~(_PAGE_ACCESSED));
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_SPECIAL);
}

static inline pte_t pte_mkhuge(pte_t pte)
{
	return pte;
}

#ifdef CONFIG_NUMA_BALANCING
/*
 * See the comment in include/asm-generic/pgtable.h
 */
static inline int pte_protnone(pte_t pte)
{
	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)) == _PAGE_PROT_NONE;
}

static inline int pmd_protnone(pmd_t pmd)
{
	return pte_protnone(pmd_pte(pmd));
}
#endif

/* Modify page protection bits */
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
}

#define pgd_ERROR(e) \
	pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e))


/* Commit new configuration to MMU hardware */
static inline void update_mmu_cache(struct vm_area_struct *vma,
	unsigned long address, pte_t *ptep)
{
	/*
	 * The kernel assumes that TLBs don't cache invalid entries, but
	 * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
	 * cache flush; it is necessary even after writing invalid entries.
	 * Relying on flush_tlb_fix_spurious_fault would suffice, but
	 * the extra traps reduce performance.  So, eagerly SFENCE.VMA.
	 */
	local_flush_tlb_page(address);
}

#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t pte_a, pte_t pte_b)
{
	return pte_val(pte_a) == pte_val(pte_b);
}

/*
 * Certain architectures need to do special things when PTEs within
 * a page table are directly modified.  Thus, the following hook is
 * made available.
 */
static inline void set_pte(pte_t *ptep, pte_t pteval)
{
	*ptep = pteval;
}

void flush_icache_pte(pte_t pte);

static inline void set_pte_at(struct mm_struct *mm,
	unsigned long addr, pte_t *ptep, pte_t pteval)
{
	if (pte_present(pteval) && pte_exec(pteval))
		flush_icache_pte(pteval);

	set_pte(ptep, pteval);
}

static inline void pte_clear(struct mm_struct *mm,
	unsigned long addr, pte_t *ptep)
{
	set_pte_at(mm, addr, ptep, __pte(0));
}

#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
static inline int ptep_set_access_flags(struct vm_area_struct *vma,
					unsigned long address, pte_t *ptep,
					pte_t entry, int dirty)
{
	if (!pte_same(*ptep, entry))
		set_pte_at(vma->vm_mm, address, ptep, entry);
	/*
	 * update_mmu_cache will unconditionally execute, handling both
	 * the case that the PTE changed and the spurious fault case.
	 */
	return true;
}

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
				       unsigned long address, pte_t *ptep)
{
	return __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
}

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address,
					    pte_t *ptep)
{
	if (!pte_young(*ptep))
		return 0;
	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
}

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pte_t *ptep)
{
	atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep);
}

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
					 unsigned long address, pte_t *ptep)
{
	/*
	 * This comment is borrowed from x86, but applies equally to RISC-V:
	 *
	 * Clearing the accessed bit without a TLB flush
	 * doesn't cause data corruption. [ It could cause incorrect
	 * page aging and the (mistaken) reclaim of hot pages, but the
	 * chance of that should be relatively low. ]
	 *
	 * So as a performance optimization don't flush the TLB when
	 * clearing the accessed bit, it will eventually be flushed by
	 * a context switch or a VM operation anyway. [ In the rare
	 * event of it not getting flushed for a long time the delay
	 * shouldn't really matter because there's no real memory
	 * pressure for swapout to react to. ]
	 */
	return ptep_test_and_clear_young(vma, address, ptep);
}

/*
 * Encode and decode a swap entry
 *
 * Format of swap PTE:
 *	bit            0:	_PAGE_PRESENT (zero)
 *	bit            1:	_PAGE_PROT_NONE (zero)
 *	bits      2 to 6:	swap type
 *	bits 7 to XLEN-1:	swap offset
 */
#define __SWP_TYPE_SHIFT	2
#define __SWP_TYPE_BITS		5
#define __SWP_TYPE_MASK		((1UL << __SWP_TYPE_BITS) - 1)
#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)

#define MAX_SWAPFILES_CHECK()	\
	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)

#define __swp_type(x)	(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
#define __swp_offset(x)	((x).val >> __SWP_OFFSET_SHIFT)
#define __swp_entry(type, offset) ((swp_entry_t) \
	{ ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })

#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x)	((pte_t) { (x).val })

/*
 * In the RV64 Linux scheme, we give the user half of the virtual-address space
 * and give the kernel the other (upper) half.
 */
#ifdef CONFIG_64BIT
#define KERN_VIRT_START	(-(BIT(CONFIG_VA_BITS)) + TASK_SIZE)
#else
#define KERN_VIRT_START	FIXADDR_START
#endif

/*
 * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
 * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
 */
#ifdef CONFIG_64BIT
#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
#else
#define TASK_SIZE FIXADDR_START
#endif

#else /* CONFIG_MMU */

#define PAGE_SHARED		__pgprot(0)
#define PAGE_KERNEL		__pgprot(0)
#define swapper_pg_dir		NULL
#define TASK_SIZE		0xffffffffUL
#define VMALLOC_START		0
#define VMALLOC_END		TASK_SIZE

#endif /* !CONFIG_MMU */

#define kern_addr_valid(addr)   (1) /* FIXME */

extern char _start[];
extern void *_dtb_early_va;
extern uintptr_t _dtb_early_pa;
#if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_MMU)
#define dtb_early_va	(*(void **)XIP_FIXUP(&_dtb_early_va))
#define dtb_early_pa	(*(uintptr_t *)XIP_FIXUP(&_dtb_early_pa))
#else
#define dtb_early_va	_dtb_early_va
#define dtb_early_pa	_dtb_early_pa
#endif /* CONFIG_XIP_KERNEL */

void setup_bootmem(void);
void paging_init(void);
void misc_mem_init(void);

/*
 * ZERO_PAGE is a global shared page that is always zero,
 * used for zero-mapped memory areas, etc.
 */
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))

#endif /* !__ASSEMBLY__ */

#endif /* _ASM_RISCV_PGTABLE_H */