summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/book3s32/mmu.c
blob: c0162911f6cbdce7b3677795dd8176932669855f (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * This file contains the routines for handling the MMU on those
 * PowerPC implementations where the MMU substantially follows the
 * architecture specification.  This includes the 6xx, 7xx, 7xxx,
 * and 8260 implementations but excludes the 8xx and 4xx.
 *  -- paulus
 *
 *  Derived from arch/ppc/mm/init.c:
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
 *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
 *    Copyright (C) 1996 Paul Mackerras
 *
 *  Derived from "arch/i386/mm/init.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/memblock.h>

#include <asm/prom.h>
#include <asm/mmu.h>
#include <asm/machdep.h>
#include <asm/code-patching.h>
#include <asm/sections.h>

#include <mm/mmu_decl.h>

struct hash_pte *Hash;
static unsigned long Hash_size, Hash_mask;
unsigned long _SDR1;
static unsigned int hash_mb, hash_mb2;

struct ppc_bat BATS[8][2];	/* 8 pairs of IBAT, DBAT */

struct batrange {		/* stores address ranges mapped by BATs */
	unsigned long start;
	unsigned long limit;
	phys_addr_t phys;
} bat_addrs[8];

/*
 * Return PA for this VA if it is mapped by a BAT, or 0
 */
phys_addr_t v_block_mapped(unsigned long va)
{
	int b;
	for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b)
		if (va >= bat_addrs[b].start && va < bat_addrs[b].limit)
			return bat_addrs[b].phys + (va - bat_addrs[b].start);
	return 0;
}

/*
 * Return VA for a given PA or 0 if not mapped
 */
unsigned long p_block_mapped(phys_addr_t pa)
{
	int b;
	for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b)
		if (pa >= bat_addrs[b].phys
	    	    && pa < (bat_addrs[b].limit-bat_addrs[b].start)
		              +bat_addrs[b].phys)
			return bat_addrs[b].start+(pa-bat_addrs[b].phys);
	return 0;
}

static int find_free_bat(void)
{
	int b;

	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) {
		for (b = 0; b < 4; b++) {
			struct ppc_bat *bat = BATS[b];

			if (!(bat[0].batl & 0x40))
				return b;
		}
	} else {
		int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;

		for (b = 0; b < n; b++) {
			struct ppc_bat *bat = BATS[b];

			if (!(bat[1].batu & 3))
				return b;
		}
	}
	return -1;
}

/*
 * This function calculates the size of the larger block usable to map the
 * beginning of an area based on the start address and size of that area:
 * - max block size is 8M on 601 and 256 on other 6xx.
 * - base address must be aligned to the block size. So the maximum block size
 *   is identified by the lowest bit set to 1 in the base address (for instance
 *   if base is 0x16000000, max size is 0x02000000).
 * - block size has to be a power of two. This is calculated by finding the
 *   highest bit set to 1.
 */
static unsigned int block_size(unsigned long base, unsigned long top)
{
	unsigned int max_size = IS_ENABLED(CONFIG_PPC_BOOK3S_601) ? SZ_8M : SZ_256M;
	unsigned int base_shift = (ffs(base) - 1) & 31;
	unsigned int block_shift = (fls(top - base) - 1) & 31;

	return min3(max_size, 1U << base_shift, 1U << block_shift);
}

/*
 * Set up one of the IBAT (block address translation) register pairs.
 * The parameters are not checked; in particular size must be a power
 * of 2 between 128k and 256M.
 * Only for 603+ ...
 */
static void setibat(int index, unsigned long virt, phys_addr_t phys,
		    unsigned int size, pgprot_t prot)
{
	unsigned int bl = (size >> 17) - 1;
	int wimgxpp;
	struct ppc_bat *bat = BATS[index];
	unsigned long flags = pgprot_val(prot);

	if (!cpu_has_feature(CPU_FTR_NEED_COHERENT))
		flags &= ~_PAGE_COHERENT;

	wimgxpp = (flags & _PAGE_COHERENT) | (_PAGE_EXEC ? BPP_RX : BPP_XX);
	bat[0].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
	bat[0].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
	if (flags & _PAGE_USER)
		bat[0].batu |= 1;	/* Vp = 1 */
}

static void clearibat(int index)
{
	struct ppc_bat *bat = BATS[index];

	bat[0].batu = 0;
	bat[0].batl = 0;
}

static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long top)
{
	int idx;

	while ((idx = find_free_bat()) != -1 && base != top) {
		unsigned int size = block_size(base, top);

		if (size < 128 << 10)
			break;
		setbat(idx, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
		base += size;
	}

	return base;
}

unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
	unsigned long done;
	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;

	if (__map_without_bats) {
		pr_debug("RAM mapped without BATs\n");
		return base;
	}
	if (debug_pagealloc_enabled()) {
		if (base >= border)
			return base;
		if (top >= border)
			top = border;
	}

	if (!strict_kernel_rwx_enabled() || base >= border || top <= border)
		return __mmu_mapin_ram(base, top);

	done = __mmu_mapin_ram(base, border);
	if (done != border)
		return done;

	return __mmu_mapin_ram(border, top);
}

static bool is_module_segment(unsigned long addr)
{
	if (!IS_ENABLED(CONFIG_MODULES))
		return false;
	if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M))
		return false;
	if (addr >= ALIGN(VMALLOC_END, SZ_256M))
		return false;
	return true;
}

void mmu_mark_initmem_nx(void)
{
	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
	int i;
	unsigned long base = (unsigned long)_stext - PAGE_OFFSET;
	unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
	unsigned long size;

	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
		return;

	for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) {
		size = block_size(base, top);
		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
		base += size;
	}
	if (base < top) {
		size = block_size(base, top);
		size = max(size, 128UL << 10);
		if ((top - base) > size) {
			size <<= 1;
			if (strict_kernel_rwx_enabled() && base + size > border)
				pr_warn("Some RW data is getting mapped X. "
					"Adjust CONFIG_DATA_SHIFT to avoid that.\n");
		}
		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
		base += size;
	}
	for (; i < nb; i++)
		clearibat(i);

	update_bats();

	for (i = TASK_SIZE >> 28; i < 16; i++) {
		/* Do not set NX on VM space for modules */
		if (is_module_segment(i << 28))
			continue;

		mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
	}
}

void mmu_mark_rodata_ro(void)
{
	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
	int i;

	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
		return;

	for (i = 0; i < nb; i++) {
		struct ppc_bat *bat = BATS[i];

		if (bat_addrs[i].start < (unsigned long)__init_begin)
			bat[1].batl = (bat[1].batl & ~BPP_RW) | BPP_RX;
	}

	update_bats();
}

/*
 * Set up one of the I/D BAT (block address translation) register pairs.
 * The parameters are not checked; in particular size must be a power
 * of 2 between 128k and 256M.
 * On 603+, only set IBAT when _PAGE_EXEC is set
 */
void __init setbat(int index, unsigned long virt, phys_addr_t phys,
		   unsigned int size, pgprot_t prot)
{
	unsigned int bl;
	int wimgxpp;
	struct ppc_bat *bat;
	unsigned long flags = pgprot_val(prot);

	if (index == -1)
		index = find_free_bat();
	if (index == -1) {
		pr_err("%s: no BAT available for mapping 0x%llx\n", __func__,
		       (unsigned long long)phys);
		return;
	}
	bat = BATS[index];

	if ((flags & _PAGE_NO_CACHE) ||
	    (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0))
		flags &= ~_PAGE_COHERENT;

	bl = (size >> 17) - 1;
	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_601)) {
		/* 603, 604, etc. */
		/* Do DBAT first */
		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
				   | _PAGE_COHERENT | _PAGE_GUARDED);
		wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX;
		bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
		bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
		if (flags & _PAGE_USER)
			bat[1].batu |= 1; 	/* Vp = 1 */
		if (flags & _PAGE_GUARDED) {
			/* G bit must be zero in IBATs */
			flags &= ~_PAGE_EXEC;
		}
		if (flags & _PAGE_EXEC)
			bat[0] = bat[1];
		else
			bat[0].batu = bat[0].batl = 0;
	} else {
		/* 601 cpu */
		if (bl > BL_8M)
			bl = BL_8M;
		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
				   | _PAGE_COHERENT);
		wimgxpp |= (flags & _PAGE_RW)?
			((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX;
		bat->batu = virt | wimgxpp | 4;	/* Ks=0, Ku=1 */
		bat->batl = phys | bl | 0x40;	/* V=1 */
	}

	bat_addrs[index].start = virt;
	bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
	bat_addrs[index].phys = phys;
}

/*
 * Preload a translation in the hash table
 */
void hash_preload(struct mm_struct *mm, unsigned long ea)
{
	pmd_t *pmd;

	if (!Hash)
		return;
	pmd = pmd_off(mm, ea);
	if (!pmd_none(*pmd))
		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
}

/*
 * This is called at the end of handling a user page fault, when the
 * fault has been handled by updating a PTE in the linux page tables.
 * We use it to preload an HPTE into the hash table corresponding to
 * the updated linux PTE.
 *
 * This must always be called with the pte lock held.
 */
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
		      pte_t *ptep)
{
	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
		return;
	/*
	 * We don't need to worry about _PAGE_PRESENT here because we are
	 * called with either mm->page_table_lock held or ptl lock held
	 */

	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
	if (!pte_young(*ptep) || address >= TASK_SIZE)
		return;

	/* We have to test for regs NULL since init will get here first thing at boot */
	if (!current->thread.regs)
		return;

	/* We also avoid filling the hash if not coming from a fault */
	if (TRAP(current->thread.regs) != 0x300 && TRAP(current->thread.regs) != 0x400)
		return;

	hash_preload(vma->vm_mm, address);
}

/*
 * Initialize the hash table and patch the instructions in hashtable.S.
 */
void __init MMU_init_hw(void)
{
	unsigned int n_hpteg, lg_n_hpteg;

	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
		return;

	if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105);

#define LG_HPTEG_SIZE	6		/* 64 bytes per HPTEG */
#define SDR1_LOW_BITS	((n_hpteg - 1) >> 10)
#define MIN_N_HPTEG	1024		/* min 64kB hash table */

	/*
	 * Allow 1 HPTE (1/8 HPTEG) for each page of memory.
	 * This is less than the recommended amount, but then
	 * Linux ain't AIX.
	 */
	n_hpteg = total_memory / (PAGE_SIZE * 8);
	if (n_hpteg < MIN_N_HPTEG)
		n_hpteg = MIN_N_HPTEG;
	lg_n_hpteg = __ilog2(n_hpteg);
	if (n_hpteg & (n_hpteg - 1)) {
		++lg_n_hpteg;		/* round up if not power of 2 */
		n_hpteg = 1 << lg_n_hpteg;
	}
	Hash_size = n_hpteg << LG_HPTEG_SIZE;

	/*
	 * Find some memory for the hash table.
	 */
	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
	Hash = memblock_alloc(Hash_size, Hash_size);
	if (!Hash)
		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
		      __func__, Hash_size, Hash_size);
	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;

	pr_info("Total memory = %lldMB; using %ldkB for hash table\n",
		(unsigned long long)(total_memory >> 20), Hash_size >> 10);


	Hash_mask = n_hpteg - 1;
	hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg;
	if (lg_n_hpteg > 16)
		hash_mb2 = 16 - LG_HPTEG_SIZE;

	/*
	 * When KASAN is selected, there is already an early temporary hash
	 * table and the switch to the final hash table is done later.
	 */
	if (IS_ENABLED(CONFIG_KASAN))
		return;

	MMU_init_hw_patch();
}

void __init MMU_init_hw_patch(void)
{
	unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
	unsigned int hash = (unsigned int)Hash - PAGE_OFFSET;

	if (ppc_md.progress)
		ppc_md.progress("hash:patch", 0x345);
	if (ppc_md.progress)
		ppc_md.progress("hash:done", 0x205);

	/* WARNING: Make sure nothing can trigger a KASAN check past this point */

	/*
	 * Patch up the instructions in hashtable.S:create_hpte
	 */
	modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16);
	modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6);
	modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6);
	modify_instruction_site(&patch__hash_page_B, 0xffff, hmask);
	modify_instruction_site(&patch__hash_page_C, 0xffff, hmask);

	/*
	 * Patch up the instructions in hashtable.S:flush_hash_page
	 */
	modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16);
	modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6);
	modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6);
	modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask);
}

void setup_initial_memory_limit(phys_addr_t first_memblock_base,
				phys_addr_t first_memblock_size)
{
	/* We don't currently support the first MEMBLOCK not mapping 0
	 * physical on those processors
	 */
	BUG_ON(first_memblock_base != 0);

	/* 601 can only access 16MB at the moment */
	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
	else /* Anything else has 256M mapped */
		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
}

void __init print_system_hash_info(void)
{
	pr_info("Hash_size         = 0x%lx\n", Hash_size);
	if (Hash_mask)
		pr_info("Hash_mask         = 0x%lx\n", Hash_mask);
}

#ifdef CONFIG_PPC_KUEP
void __init setup_kuep(bool disabled)
{
	pr_info("Activating Kernel Userspace Execution Prevention\n");

	if (disabled)
		pr_warn("KUEP cannot be disabled yet on 6xx when compiled in\n");
}
#endif

#ifdef CONFIG_PPC_KUAP
void __init setup_kuap(bool disabled)
{
	pr_info("Activating Kernel Userspace Access Protection\n");

	if (disabled)
		pr_warn("KUAP cannot be disabled yet on 6xx when compiled in\n");
}
#endif