-
Notifications
You must be signed in to change notification settings - Fork 3
/
mmu.c
1509 lines (1276 loc) · 39 KB
/
mmu.c
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
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* 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/cache.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/kexec.h>
#include <linux/libfdt.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#ifdef CONFIG_HKIP_PRMEM
#include <linux/hisi/prmem.h>
#endif
#include <linux/hisi/hkip.h>
#include <asm/barrier.h>
#include <asm/cputype.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/kernel-pgtable.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 <asm/ptdump.h>
#define NO_BLOCK_MAPPINGS BIT(0)
#define NO_CONT_MAPPINGS BIT(1)
u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
/*
* Empty_zero_page is a special page that is used for zero-initialized data
* and COW.
*/
unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);
static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
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 phys_addr_t __init early_pgtable_alloc(void)
{
phys_addr_t phys;
void *ptr;
phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
/*
* The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
* slot will be free, so we can (ab)use the FIX_PTE slot to initialise
* any level of table.
*/
ptr = pte_set_fixmap(phys);
memset(ptr, 0, PAGE_SIZE);
/*
* Implicit barriers also ensure the zeroed page is visible to the page
* table walker
*/
pte_clear_fixmap();
return phys;
}
static bool pgattr_change_is_safe(u64 old, u64 new)
{
/*
* The following mapping attributes may be updated in live
* kernel mappings without the need for break-before-make.
*/
static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
/* creating or taking down mappings is always safe */
if (old == 0 || new == 0)
return true;
/* live contiguous mappings may not be manipulated at all */
if ((old | new) & PTE_CONT)
return false;
/* Transitioning from Non-Global to Global is unsafe */
if (old & ~new & PTE_NG)
return false;
return ((old ^ new) & ~mask) == 0;
}
static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot)
{
pte_t *pte;
pte = pte_set_fixmap_offset(pmd, addr);
do {
pte_t old_pte = *pte;
set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot));
/*
* After the PTE entry has been populated once, we
* only allow updates to the permission attributes.
*/
BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte)));
phys += PAGE_SIZE;
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_clear_fixmap();
}
static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void),
int flags)
{
unsigned long next;
BUG_ON(pmd_sect(*pmd));
if (pmd_none(*pmd)) {
phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
pte_phys = pgtable_alloc();
__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
}
BUG_ON(pmd_bad(*pmd));
do {
pgprot_t __prot = prot;
next = pte_cont_addr_end(addr, end);
/* use a contiguous mapping if the range is suitably aligned */
if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
(flags & NO_CONT_MAPPINGS) == 0)
__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
init_pte(pmd, addr, next, phys, __prot);
phys += next - addr;
} while (addr = next, addr != end);
}
static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void), int flags)
{
unsigned long next;
pmd_t *pmd;
pmd = pmd_set_fixmap_offset(pud, addr);
do {
pmd_t old_pmd = *pmd;
next = pmd_addr_end(addr, end);
/* try section mapping first */
if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
(flags & NO_BLOCK_MAPPINGS) == 0) {
pmd_set_huge(pmd, phys, prot);
/*
* After the PMD entry has been populated once, we
* only allow updates to the permission attributes.
*/
BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
pmd_val(*pmd)));
} else {
alloc_init_cont_pte(pmd, addr, next, phys, prot,
pgtable_alloc, flags);
BUG_ON(pmd_val(old_pmd) != 0 &&
pmd_val(old_pmd) != pmd_val(*pmd));
}
phys += next - addr;
} while (pmd++, addr = next, addr != end);
pmd_clear_fixmap();
}
static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void), int flags)
{
unsigned long next;
/*
* Check for initial section mappings in the pgd/pud.
*/
BUG_ON(pud_sect(*pud));
if (pud_none(*pud)) {
phys_addr_t pmd_phys;
BUG_ON(!pgtable_alloc);
pmd_phys = pgtable_alloc();
__pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
}
BUG_ON(pud_bad(*pud));
do {
pgprot_t __prot = prot;
next = pmd_cont_addr_end(addr, end);
/* use a contiguous mapping if the range is suitably aligned */
if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
(flags & NO_CONT_MAPPINGS) == 0)
__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags);
phys += next - addr;
} while (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(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void),
int flags)
{
pud_t *pud;
unsigned long next;
if (pgd_none(*pgd)) {
phys_addr_t pud_phys;
BUG_ON(!pgtable_alloc);
pud_phys = pgtable_alloc();
__pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE);
}
BUG_ON(pgd_bad(*pgd));
pud = pud_set_fixmap_offset(pgd, addr);
do {
pud_t old_pud = *pud;
next = pud_addr_end(addr, end);
/*
* For 4K granule only, attempt to put down a 1GB block
*/
if (use_1G_block(addr, next, phys) &&
(flags & NO_BLOCK_MAPPINGS) == 0) {
pud_set_huge(pud, phys, prot);
/*
* After the PUD entry has been populated once, we
* only allow updates to the permission attributes.
*/
BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
pud_val(*pud)));
} else {
alloc_init_cont_pmd(pud, addr, next, phys, prot,
pgtable_alloc, flags);
BUG_ON(pud_val(old_pud) != 0 &&
pud_val(old_pud) != pud_val(*pud));
}
phys += next - addr;
} while (pud++, addr = next, addr != end);
pud_clear_fixmap();
}
static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void),
int flags)
{
unsigned long addr, length, end, next;
pgd_t *pgd = pgd_offset_raw(pgdir, virt);
/*
* If the virtual and physical address don't have the same offset
* within a page, we cannot map the region as the caller expects.
*/
if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
return;
phys &= PAGE_MASK;
addr = virt & PAGE_MASK;
length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
end = addr + length;
do {
next = pgd_addr_end(addr, end);
alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
flags);
phys += next - addr;
} while (pgd++, addr = next, addr != end);
}
static phys_addr_t pgd_pgtable_alloc(void)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
BUG();
/* Ensure the zeroed page is visible to the page table walker */
dsb(ishst);
return __pa(ptr);
}
/*
* This function can only be used to modify existing table entries,
* without allocating new levels of table. Note that this permits the
* creation of new section or page entries.
*/
static void __init create_mapping_noalloc(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_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
NO_CONT_MAPPINGS);
}
void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot, bool page_mappings_only)
{
int flags = 0;
BUG_ON(mm == &init_mm);
if (page_mappings_only)
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
pgd_pgtable_alloc, flags);
}
static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot)
{
if (virt < VMALLOC_START) {
pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
&phys, virt);
return;
}
__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
NO_CONT_MAPPINGS);
/* flush the TLBs after updating live kernel mappings */
flush_tlb_kernel_range(virt, virt + size);
}
static void __init __map_memblock(pgd_t *pgd, phys_addr_t start,
phys_addr_t end, pgprot_t prot, int flags)
{
__create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start,
prot, early_pgtable_alloc, flags);
}
void __init mark_linear_text_alias_ro(void)
{
/*
* Remove the write permissions from the linear alias of .text/.rodata
*/
update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text),
(unsigned long)__init_begin - (unsigned long)_text,
PAGE_KERNEL_RO);
}
#ifdef CONFIG_HISI_LB_L3_EXTENSION
static void lb_memblk_map_clear(pgd_t *pgd, int flags)
{
int i;
for (i = 0; i < MAX_LB_MEMBLK_SP; i++) {
struct lb_memory_block *lbmem = &lb_memblk_sp[i];
if (lbmem->size) {
/*
* Use section-level mappings here
* so that we can mark the region
* in section granularity and
* up the mem perfermance for cam_mem.
*/
__map_memblock(pgd, lbmem->base,
lbmem->base + lbmem->size,
PAGE_KERNEL, flags);/*lint !e446*/
memblock_clear_nomap(lbmem->base,
lbmem->size);
}
}
}
static void lb_memblk_mark_nomap(void)
{
int i;
for (i = 0; i < MAX_LB_MEMBLK_SP; i++) {
struct lb_memory_block *lbmem = &lb_memblk_sp[i];;
if (lbmem->size)
memblock_mark_nomap(lbmem->base,
lbmem->size);
}
}
#endif
static void __init map_mem(pgd_t *pgd)
{
phys_addr_t kernel_start = __pa_symbol(_text);
phys_addr_t kernel_end = __pa_symbol(__init_begin);
struct memblock_region *reg;
int flags = 0;
if (debug_pagealloc_enabled())
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
* Take care not to create a writable alias for the
* read-only text and rodata sections of the kernel image.
* So temporarily mark them as NOMAP to skip mappings in
* the following for-loop
*/
memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
#ifdef CONFIG_KEXEC_CORE
if (crashk_res.end)
memblock_mark_nomap(crashk_res.start,
resource_size(&crashk_res));
#endif
#ifdef CONFIG_HISI_LB_L3_EXTENSION
lb_memblk_mark_nomap();
#endif
/* 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;
if (memblock_is_nomap(reg))
continue;
#ifdef CONFIG_HISI_LB_L3_EXTENSION
__map_memblock(pgd, start, end, PAGE_KERNEL,
NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
#else
__map_memblock(pgd, start, end, PAGE_KERNEL, flags);
#endif
}
/*
* Map the linear alias of the [_text, __init_begin) interval
* as non-executable now, and remove the write permission in
* mark_linear_text_alias_ro() below (which will be called after
* alternative patching has completed). This makes the contents
* of the region accessible to subsystems such as hibernate,
* but protects it from inadvertent modification or execution.
* Note that contiguous mappings cannot be remapped in this way,
* so we should avoid them here.
*/
__map_memblock(pgd, kernel_start, kernel_end,
PAGE_KERNEL, NO_CONT_MAPPINGS);
memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
#ifdef CONFIG_KEXEC_CORE
/*
* Use page-level mappings here so that we can shrink the region
* in page granularity and put back unused memory to buddy system
* through /sys/kernel/kexec_crash_size interface.
*/
if (crashk_res.end) {
__map_memblock(pgd, crashk_res.start, crashk_res.end + 1,
PAGE_KERNEL,
NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
memblock_clear_nomap(crashk_res.start,
resource_size(&crashk_res));
}
#endif
#ifdef CONFIG_HISI_LB_L3_EXTENSION
lb_memblk_map_clear(pgd, flags);
#endif
}
#ifdef CONFIG_HKIP_PRMEM
void mark_wr_data_wr(void)
{
unsigned long section_size;
if (!prmem_active())
return;
section_size = (unsigned long)(uintptr_t)__end_data_wr -
(unsigned long)(uintptr_t)__start_data_wr;
update_mapping_prot(__pa_symbol(__start_data_wr),
(unsigned long)(uintptr_t)__start_data_wr,
section_size, PAGE_KERNEL_RO);
hkip_register_rowm((void *)__start_data_wr,
ALIGN(section_size, PAGE_SIZE));
}
void mark_wr_after_init_data_wr(void)
{
unsigned long section_size;
if (!prmem_active())
return;
section_size = (unsigned long)(uintptr_t)__end_data_wr_after_init-
(unsigned long)(uintptr_t)__start_data_wr_after_init;
if (unlikely(!section_size)) /* Skip empty segment */
return;
update_mapping_prot(__pa_symbol(__start_data_wr_after_init),
(unsigned long)(uintptr_t)__start_data_wr_after_init,
section_size, PAGE_KERNEL_RO);
hkip_register_rowm((void *)__start_data_wr_after_init,
ALIGN(section_size, PAGE_SIZE));
}
#else /* CONFIG_HKIP_PRMEM */
void mark_wr_data_wr(void)
{
}
void mark_wr_after_init_data_wr(void)
{
}
#endif /* CONFIG_HKIP_PRMEM */
void mark_rodata_ro(void)
{
unsigned long section_size;
unsigned long text_size;
section_size = (unsigned long)__end_data_ro_after_init -
(unsigned long)__start_data_ro_after_init;
update_mapping_prot(__pa_symbol(__start_data_ro_after_init), (unsigned long)__start_data_ro_after_init,
section_size, PAGE_KERNEL_RO);
hkip_register_ro((void *)__start_data_ro_after_init,
ALIGN(section_size, PAGE_SIZE));
text_size = (unsigned long)_etext - (unsigned long)_text;
hkip_register_rox_text((void *)_text, ALIGN(text_size, PAGE_SIZE));
mark_wr_after_init_data_wr();
}
#ifdef CONFIG_DEBUG_HKIP_EARLY_RODATA_PROTECTION
void test_early_rodata_protection(void);
#endif
void mark_constdata_ro(void)
{
#ifdef CONFIG_DEBUG_HKIP_EARLY_RODATA_PROTECTION
test_early_rodata_protection();
#else
unsigned long start = (unsigned long)__start_rodata;
unsigned long end = (unsigned long)__init_begin;
unsigned long section_size = (unsigned long)end - (unsigned long)start;
/*
* mark .rodata as read only. Use __init_begin rather than __end_rodata
* to cover NOTES and EXCEPTION_TABLE.
*/
update_mapping_prot(__pa_symbol(__start_rodata), start,
section_size, PAGE_KERNEL_RO);
hkip_register_ro((void *)start, ALIGN(section_size, PAGE_SIZE));
#endif
debug_checkwx();
}
static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
pgprot_t prot, struct vm_struct *vma,
int flags, unsigned long vm_flags)
{
phys_addr_t pa_start = __pa_symbol(va_start);
unsigned long size = va_end - va_start;
#ifdef CONFIG_HKIP_PRMEM
if (unlikely(!size)) /* Mapping an empty segment will BUG() */
return;
#endif
BUG_ON(!PAGE_ALIGNED(pa_start));
BUG_ON(!PAGE_ALIGNED(size));
__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
early_pgtable_alloc, flags);
if (!(vm_flags & VM_NO_GUARD))
size += PAGE_SIZE;
vma->addr = va_start;
vma->phys_addr = pa_start;
vma->size = size;
vma->flags = VM_MAP | vm_flags;
vma->caller = __builtin_return_address(0);
vm_area_add_early(vma);
}
static int __init parse_rodata(char *arg)
{
return strtobool(arg, &rodata_enabled);
}
early_param("rodata", parse_rodata);
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
static int __init map_entry_trampoline(void)
{
extern char __entry_tramp_text_start[];
/* change to the code which exist in kernel/git/arm64/linux.git */
pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
/* The trampoline is always mapped and can therefore be global */
pgprot_val(prot) &= ~PTE_NG;
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
prot, pgd_pgtable_alloc, 0);
/* Map both the text and data into the kernel page table */
__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
extern char __entry_tramp_data_start[];
__set_fixmap(FIX_ENTRY_TRAMP_DATA,
__pa_symbol(__entry_tramp_data_start),
PAGE_KERNEL_RO);
}
return 0;
}
core_initcall(map_entry_trampoline);
#endif
/*
* Create fine-grained mappings for the kernel.
*/
static void __init map_kernel(pgd_t *pgd)
{
static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext,
vmlinux_initdata, vmlinux_data, vmlinux_ro_after_init_data;
#ifdef CONFIG_HKIP_PRMEM
static struct vm_struct vmlinux_wr_data, vmlinux_wr_after_init_data,
vmlinux_rw;
#endif
/*
* External debuggers may need to write directly to the text
* mapping to install SW breakpoints. Allow this (only) when
* explicitly requested with rodata=off.
*/
pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
/*
* Only rodata will be remapped with different permissions later on,
* all other segments are allowed to use contiguous mappings.
*/
map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0,
VM_NO_GUARD);
map_kernel_segment(pgd, __start_data_ro_after_init, __end_data_ro_after_init, PAGE_KERNEL,
&vmlinux_ro_after_init_data, NO_CONT_MAPPINGS, VM_NO_GUARD);
map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
&vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
&vmlinux_inittext, 0, VM_NO_GUARD);
map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
&vmlinux_initdata, 0, VM_NO_GUARD);
#ifdef CONFIG_HKIP_PRMEM
map_kernel_segment(pgd, __start_data_wr, __end_data_wr, PAGE_KERNEL,
&vmlinux_wr_data, NO_CONT_MAPPINGS, VM_NO_GUARD);
map_kernel_segment(pgd, __start_data_wr_after_init, __end_data_wr_after_init, PAGE_KERNEL,
&vmlinux_wr_after_init_data, NO_CONT_MAPPINGS, VM_NO_GUARD);
map_kernel_segment(pgd, __start_data_rw, __end_data_rw, PAGE_KERNEL,
&vmlinux_rw, NO_CONT_MAPPINGS, VM_NO_GUARD);
#endif /* CONFIG_HKIP_PRMEM */
map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
/*
* The fixmap falls in a separate pgd to the kernel, and doesn't
* live in the carveout for the swapper_pg_dir. We can simply
* re-use the existing dir for the fixmap.
*/
set_pgd(pgd_offset_raw(pgd, FIXADDR_START),
*pgd_offset_k(FIXADDR_START));
} else if (CONFIG_PGTABLE_LEVELS > 3) {
/*
* The fixmap shares its top level pgd entry with the kernel
* mapping. This can really only occur when we are running
* with 16k/4 levels, so we can simply reuse the pud level
* entry instead.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START),
lm_alias(bm_pmd));
pud_clear_fixmap();
} else {
BUG();
}
kasan_copy_shadow(pgd);
}
/*
* paging_init() sets up the page tables, initialises the zone memory
* maps and sets up the zero page.
*/
void __init paging_init(void)
{
phys_addr_t pgd_phys = early_pgtable_alloc();
pgd_t *pgd = pgd_set_fixmap(pgd_phys);
map_kernel(pgd);
map_mem(pgd);
/*
* We want to reuse the original swapper_pg_dir so we don't have to
* communicate the new address to non-coherent secondaries in
* secondary_entry, and so cpu_switch_mm can generate the address with
* adrp+add rather than a load from some global variable.
*
* To do this we need to go via a temporary pgd.
*/
cpu_replace_ttbr1(__va(pgd_phys));
memcpy(swapper_pg_dir, pgd, PGD_SIZE);
cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
pgd_clear_fixmap();
memblock_free(pgd_phys, PAGE_SIZE);
/* Ensure the zero page is visible to the page table walker */
dsb(ishst);
/*
* We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
* allocated with it.
*/
#ifndef CONFIG_HISI_LB_L3_EXTENSION
memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
SWAPPER_DIR_SIZE - PAGE_SIZE);
#endif
}
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* hotplug_paging() is used by memory hotplug to build new page tables
* for hot added memory.
*/
void hotplug_paging(phys_addr_t start, phys_addr_t size)
{
int flags;
flags = debug_pagealloc_enabled() ? NO_BLOCK_MAPPINGS : 0;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), size,
PAGE_KERNEL, pgd_pgtable_alloc, flags);
}
#ifdef CONFIG_MEMORY_HOTREMOVE
#define PAGE_INUSE 0xFD
static void free_pagetable(struct page *page, int order, bool direct)
{
unsigned long magic;
unsigned int nr_pages = 1 << order;
/* bootmem page has reserved flag */
if (PageReserved(page)) {
__ClearPageReserved(page);
magic = (unsigned long)page->lru.next;
if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
while (nr_pages--)
put_page_bootmem(page++);
} else {
while (nr_pages--)
free_reserved_page(page++);
}
} else {
/*
* Only direct pagetable allocation (those allocated via
* hotplug) call the pgtable_page_ctor; vmemmap pgtable
* allocations don't.
*/
if (direct)
pgtable_page_dtor(page);
free_pages((unsigned long)page_address(page), order);
}
}
static void free_pte_table(pmd_t *pmd, bool direct)
{
pte_t *pte_start = NULL;
pte_t *pte = NULL;
struct page *page = NULL;
int i;
pte_start = (pte_t *) pmd_page_vaddr(*pmd);
/* Check if there is no valid entry in the PMD */
for (i = 0; i < PTRS_PER_PTE; i++) {
pte = pte_start + i;
if (!pte_none(*pte))
return;
}
page = pmd_page(*pmd);
free_pagetable(page, 0, direct);
/*
* This spin lock could be only taken in _pte_aloc_kernel
* in mm/memory.c and nowhere else (for arm64). Not sure if
* the function above can be called concurrently. In doubt,
* I am living it here for now, but it probably can be removed
*/
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
}
static void free_pmd_table(pud_t *pud, bool direct)
{
pmd_t *pmd_start = NULL;
pmd_t *pmd = NULL;
struct page *page = NULL;
int i;
pmd_start = (pmd_t *) pud_page_vaddr(*pud);
/* Check if there is no valid entry in the PMD */
for (i = 0; i < PTRS_PER_PMD; i++) {
pmd = pmd_start + i;
if (!pmd_none(*pmd))
return;
}
page = pud_page(*pud);
free_pagetable(page, 0, direct);
/*
* This spin lock could be only taken in _pte_aloc_kernel
* in mm/memory.c and nowhere else (for arm64). Not sure if
* the function above can be called concurrently. In doubt,
* I am living it here for now, but it probably can be removed
*/
spin_lock(&init_mm.page_table_lock);
pud_clear(pud);
spin_unlock(&init_mm.page_table_lock);
}
/*
* When the PUD is folded on the PGD (three levels of paging),
* there's no need to free PUDs
*/
#if CONFIG_PGTABLE_LEVELS > 3
static void free_pud_table(pgd_t *pgd, bool direct)
{
pud_t *pud_start = NULL;
pud_t *pud = NULL;
struct page *page = NULL;
int i;
pud_start = (pud_t *) pgd_page_vaddr(*pgd);
/* Check if there is no valid entry in the PUD */
for (i = 0; i < PTRS_PER_PUD; i++) {
pud = pud_start + i;
if (!pud_none(*pud))
return;
}
page = pgd_page(*pgd);
free_pagetable(page, 0, direct);
/*
* This spin lock could be only
* taken in _pte_aloc_kernel in
* mm/memory.c and nowhere else
* (for arm64). Not sure if the
* function above can be called
* concurrently. In doubt,
* I am living it here for now,
* but it probably can be removed.
*/
spin_lock(&init_mm.page_table_lock);
pgd_clear(pgd);
spin_unlock(&init_mm.page_table_lock);
}
#endif
static void remove_pte_table(pte_t *pte, unsigned long addr,
unsigned long end, bool direct)
{
unsigned long next;
void *page_addr = NULL;
for (; addr < end; addr = next, pte++) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
if (next > end)
next = end;
if (!pte_present(*pte))
continue;
if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) {
/*
* Do not free direct mapping pages since they were
* freed when offlining, or simplely not in use.
*/
if (!direct)
free_pagetable(pte_page(*pte), 0, direct);
/*
* This spin lock could be only
* taken in _pte_aloc_kernel in
* mm/memory.c and nowhere else
* (for arm64). Not sure if the
* function above can be called
* concurrently. In doubt,
* I am living it here for now,
* but it probably can be removed.
*/
spin_lock(&init_mm.page_table_lock);
pte_clear(&init_mm, addr, pte);
spin_unlock(&init_mm.page_table_lock);
} else {
/*
* If we are here, we are freeing vmemmap pages since
* direct mapped memory ranges to be freed are aligned.
*
* If we are not removing the whole page, it means
* other page structs in this page are being used and
* we canot remove them. So fill the unused page_structs
* with 0xFD, and remove the page when it is wholly
* filled with 0xFD.
*/
memset((void *)addr, PAGE_INUSE, next - addr);
page_addr = page_address(pte_page(*pte));
if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
free_pagetable(pte_page(*pte), 0, direct);
/*
* This spin lock could be only