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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/mm/init.c
*
* Copyright (C) 1995-2005 Russell King
*/
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/mman.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/export.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
#include <linux/of_fdt.h>
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/dma-map-ops.h>
#include <linux/sizes.h>
#include <linux/stop_machine.h>
#include <linux/swiotlb.h>
#include <asm/cp15.h>
#include <asm/mach-types.h>
#include <asm/memblock.h>
#include <asm/memory.h>
#include <asm/prom.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/set_memory.h>
#include <asm/system_info.h>
#include <asm/tlb.h>
#include <asm/fixmap.h>
#include <asm/ptdump.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
#include "mm.h"
#ifdef CONFIG_CPU_CP15_MMU
unsigned long __init __clear_cr(unsigned long mask)
{
cr_alignment = cr_alignment & ~mask;
return cr_alignment;
}
#endif
#ifdef CONFIG_BLK_DEV_INITRD
static int __init parse_tag_initrd(const struct tag *tag)
{
pr_warn("ATAG_INITRD is deprecated; "
"please update your bootloader.\n");
phys_initrd_start = __virt_to_phys(tag->u.initrd.start);
phys_initrd_size = tag->u.initrd.size;
return 0;
}
__tagtable(ATAG_INITRD, parse_tag_initrd);
static int __init parse_tag_initrd2(const struct tag *tag)
{
phys_initrd_start = tag->u.initrd.start;
phys_initrd_size = tag->u.initrd.size;
return 0;
}
__tagtable(ATAG_INITRD2, parse_tag_initrd2);
#endif
static void __init find_limits(unsigned long *min, unsigned long *max_low,
unsigned long *max_high)
{
*max_low = PFN_DOWN(memblock_get_current_limit());
*min = PFN_UP(memblock_start_of_DRAM());
*max_high = PFN_DOWN(memblock_end_of_DRAM());
}
#ifdef CONFIG_ZONE_DMA
phys_addr_t arm_dma_zone_size __read_mostly;
EXPORT_SYMBOL(arm_dma_zone_size);
/*
* The DMA mask corresponding to the maximum bus address allocatable
* using GFP_DMA. The default here places no restriction on DMA
* allocations. This must be the smallest DMA mask in the system,
* so a successful GFP_DMA allocation will always satisfy this.
*/
phys_addr_t arm_dma_limit;
unsigned long arm_dma_pfn_limit;
#endif
void __init setup_dma_zone(const struct machine_desc *mdesc)
{
#ifdef CONFIG_ZONE_DMA
if (mdesc->dma_zone_size) {
arm_dma_zone_size = mdesc->dma_zone_size;
arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
} else
arm_dma_limit = 0xffffffff;
arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;
#endif
}
static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
unsigned long max_high)
{
unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
#ifdef CONFIG_ZONE_DMA
max_zone_pfn[ZONE_DMA] = min(arm_dma_pfn_limit, max_low);
#endif
max_zone_pfn[ZONE_NORMAL] = max_low;
#ifdef CONFIG_HIGHMEM
max_zone_pfn[ZONE_HIGHMEM] = max_high;
#endif
free_area_init(max_zone_pfn);
}
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
phys_addr_t addr = __pfn_to_phys(pfn);
if (__phys_to_pfn(addr) != pfn)
return 0;
return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_valid);
#endif
static bool arm_memblock_steal_permitted = true;
phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
{
phys_addr_t phys;
BUG_ON(!arm_memblock_steal_permitted);
phys = memblock_phys_alloc(size, align);
if (!phys)
panic("Failed to steal %pa bytes at %pS\n",
&size, (void *)_RET_IP_);
memblock_free(phys, size);
memblock_remove(phys, size);
return phys;
}
static void __init arm_initrd_init(void)
{
#ifdef CONFIG_BLK_DEV_INITRD
phys_addr_t start;
unsigned long size;
initrd_start = initrd_end = 0;
if (!phys_initrd_size)
return;
/*
* Round the memory region to page boundaries as per free_initrd_mem()
* This allows us to detect whether the pages overlapping the initrd
* are in use, but more importantly, reserves the entire set of pages
* as we don't want these pages allocated for other purposes.
*/
start = round_down(phys_initrd_start, PAGE_SIZE);
size = phys_initrd_size + (phys_initrd_start - start);
size = round_up(size, PAGE_SIZE);
if (!memblock_is_region_memory(start, size)) {
pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
(u64)start, size);
return;
}
if (memblock_is_region_reserved(start, size)) {
pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n",
(u64)start, size);
return;
}
memblock_reserve(start, size);
/* Now convert initrd to virtual addresses */
initrd_start = __phys_to_virt(phys_initrd_start);
initrd_end = initrd_start + phys_initrd_size;
#endif
}
#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
void check_cpu_icache_size(int cpuid)
{
u32 size, ctr;
asm("mrc p15, 0, %0, c0, c0, 1" : "=r" (ctr));
size = 1 << ((ctr & 0xf) + 2);
if (cpuid != 0 && icache_size != size)
pr_info("CPU%u: detected I-Cache line size mismatch, workaround enabled\n",
cpuid);
if (icache_size > size)
icache_size = size;
}
#endif
void __init arm_memblock_init(const struct machine_desc *mdesc)
{
/* Register the kernel text, kernel data and initrd with memblock. */
memblock_reserve(__pa(KERNEL_START), KERNEL_END - KERNEL_START);
arm_initrd_init();
arm_mm_memblock_reserve();
/* reserve any platform specific memblock areas */
if (mdesc->reserve)
mdesc->reserve();
early_init_fdt_scan_reserved_mem();
/* reserve memory for DMA contiguous allocations */
dma_contiguous_reserve(arm_dma_limit);
arm_memblock_steal_permitted = false;
memblock_dump_all();
}
void __init bootmem_init(void)
{
memblock_allow_resize();
find_limits(&min_low_pfn, &max_low_pfn, &max_pfn);
early_memtest((phys_addr_t)min_low_pfn << PAGE_SHIFT,
(phys_addr_t)max_low_pfn << PAGE_SHIFT);
/*
* sparse_init() tries to allocate memory from memblock, so must be
* done after the fixed reservations
*/
sparse_init();
/*
* Now free the memory - free_area_init needs
* the sparse mem_map arrays initialized by sparse_init()
* for memmap_init_zone(), otherwise all PFNs are invalid.
*/
zone_sizes_init(min_low_pfn, max_low_pfn, max_pfn);
}
/*
* Poison init memory with an undefined instruction (ARM) or a branch to an
* undefined instruction (Thumb).
*/
static inline void poison_init_mem(void *s, size_t count)
{
u32 *p = (u32 *)s;
for (; count != 0; count -= 4)
*p++ = 0xe7fddef0;
}
static void __init free_highpages(void)
{
#ifdef CONFIG_HIGHMEM
unsigned long max_low = max_low_pfn;
phys_addr_t range_start, range_end;
u64 i;
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
unsigned long start = PFN_UP(range_start);
unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
continue;
/* Truncate partial highmem entries */
if (start < max_low)
start = max_low;
for (; start < end; start++)
free_highmem_page(pfn_to_page(start));
}
#endif
}
/*
* mem_init() marks the free areas in the mem_map and tells us how much
* memory is free. This is done after various parts of the system have
* claimed their memory after the kernel image.
*/
void __init mem_init(void)
{
#ifdef CONFIG_ARM_LPAE
if (swiotlb_force == SWIOTLB_FORCE ||
max_pfn > arm_dma_pfn_limit)
swiotlb_init(1);
else
swiotlb_force = SWIOTLB_NO_FORCE;
#endif
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
/* this will put all unused low memory onto the freelists */
memblock_free_all();
#ifdef CONFIG_SA1111
/* now that our DMA memory is actually so designated, we can free it */
free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, -1, NULL);
#endif
free_highpages();
/*
* Check boundaries twice: Some fundamental inconsistencies can
* be detected at build time already.
*/
#ifdef CONFIG_MMU
BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
BUG_ON(TASK_SIZE > MODULES_VADDR);
#endif
#ifdef CONFIG_HIGHMEM
BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE > PAGE_OFFSET);
BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE > PAGE_OFFSET);
#endif
}
#ifdef CONFIG_STRICT_KERNEL_RWX
struct section_perm {
const char *name;
unsigned long start;
unsigned long end;
pmdval_t mask;
pmdval_t prot;
pmdval_t clear;
};
/* First section-aligned location at or after __start_rodata. */
extern char __start_rodata_section_aligned[];
static struct section_perm nx_perms[] = {
/* Make pages tables, etc before _stext RW (set NX). */
{
.name = "pre-text NX",
.start = PAGE_OFFSET,
.end = (unsigned long)_stext,
.mask = ~PMD_SECT_XN,
.prot = PMD_SECT_XN,
},
/* Make init RW (set NX). */
{
.name = "init NX",
.start = (unsigned long)__init_begin,
.end = (unsigned long)_sdata,
.mask = ~PMD_SECT_XN,
.prot = PMD_SECT_XN,
},
/* Make rodata NX (set RO in ro_perms below). */
{
.name = "rodata NX",
.start = (unsigned long)__start_rodata_section_aligned,
.end = (unsigned long)__init_begin,
.mask = ~PMD_SECT_XN,
.prot = PMD_SECT_XN,
},
};
static struct section_perm ro_perms[] = {
/* Make kernel code and rodata RX (set RO). */
{
.name = "text/rodata RO",
.start = (unsigned long)_stext,
.end = (unsigned long)__init_begin,
#ifdef CONFIG_ARM_LPAE
.mask = ~(L_PMD_SECT_RDONLY | PMD_SECT_AP2),
.prot = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
#else
.mask = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
.prot = PMD_SECT_APX | PMD_SECT_AP_WRITE,
.clear = PMD_SECT_AP_WRITE,
#endif
},
};
/*
* Updates section permissions only for the current mm (sections are
* copied into each mm). During startup, this is the init_mm. Is only
* safe to be called with preemption disabled, as under stop_machine().
*/
static inline void section_update(unsigned long addr, pmdval_t mask,
pmdval_t prot, struct mm_struct *mm)
{
pmd_t *pmd;
pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr);
#ifdef CONFIG_ARM_LPAE
pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
#else
if (addr & SECTION_SIZE)
pmd[1] = __pmd((pmd_val(pmd[1]) & mask) | prot);
else
pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
#endif
flush_pmd_entry(pmd);
local_flush_tlb_kernel_range(addr, addr + SECTION_SIZE);
}
/* Make sure extended page tables are in use. */
static inline bool arch_has_strict_perms(void)
{
if (cpu_architecture() < CPU_ARCH_ARMv6)
return false;
return !!(get_cr() & CR_XP);
}
static void set_section_perms(struct section_perm *perms, int n, bool set,
struct mm_struct *mm)
{
size_t i;
unsigned long addr;
if (!arch_has_strict_perms())
return;
for (i = 0; i < n; i++) {
if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||
!IS_ALIGNED(perms[i].end, SECTION_SIZE)) {
pr_err("BUG: %s section %lx-%lx not aligned to %lx\n",
perms[i].name, perms[i].start, perms[i].end,
SECTION_SIZE);
continue;
}
for (addr = perms[i].start;
addr < perms[i].end;
addr += SECTION_SIZE)
section_update(addr, perms[i].mask,
set ? perms[i].prot : perms[i].clear, mm);
}
}
/**
* update_sections_early intended to be called only through stop_machine
* framework and executed by only one CPU while all other CPUs will spin and
* wait, so no locking is required in this function.
*/
static void update_sections_early(struct section_perm perms[], int n)
{
struct task_struct *t, *s;
for_each_process(t) {
if (t->flags & PF_KTHREAD)
continue;
for_each_thread(t, s)
if (s->mm)
set_section_perms(perms, n, true, s->mm);
}
set_section_perms(perms, n, true, current->active_mm);
set_section_perms(perms, n, true, &init_mm);
}
static int __fix_kernmem_perms(void *unused)
{
update_sections_early(nx_perms, ARRAY_SIZE(nx_perms));
return 0;
}
static void fix_kernmem_perms(void)
{
stop_machine(__fix_kernmem_perms, NULL, NULL);
}
static int __mark_rodata_ro(void *unused)
{
update_sections_early(ro_perms, ARRAY_SIZE(ro_perms));
return 0;
}
void mark_rodata_ro(void)
{
stop_machine(__mark_rodata_ro, NULL, NULL);
debug_checkwx();
}
#else
static inline void fix_kernmem_perms(void) { }
#endif /* CONFIG_STRICT_KERNEL_RWX */
void free_initmem(void)
{
fix_kernmem_perms();
poison_init_mem(__init_begin, __init_end - __init_begin);
if (!machine_is_integrator() && !machine_is_cintegrator())
free_initmem_default(-1);
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
if (start == initrd_start)
start = round_down(start, PAGE_SIZE);
if (end == initrd_end)
end = round_up(end, PAGE_SIZE);
poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
free_reserved_area((void *)start, (void *)end, -1, "initrd");
}
#endif
|