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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/mm/fault.c
*
* Copyright (C) 1995 Linus Torvalds
* Modifications for ARM processor (c) 1995-2004 Russell King
*/
#include <linux/extable.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/page-flags.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
#include <linux/kfence.h>
#include <asm/system_misc.h>
#include <asm/system_info.h>
#include <asm/tlbflush.h>
#include "fault.h"
#ifdef CONFIG_MMU
/*
* This is useful to dump out the page tables associated with
* 'addr' in mm 'mm'.
*/
void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
if (!mm)
mm = &init_mm;
pgd = pgd_offset(mm, addr);
printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
do {
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d))
break;
if (p4d_bad(*p4d)) {
pr_cont("(bad)");
break;
}
pud = pud_offset(p4d, addr);
if (PTRS_PER_PUD != 1)
pr_cont(", *pud=%08llx", (long long)pud_val(*pud));
if (pud_none(*pud))
break;
if (pud_bad(*pud)) {
pr_cont("(bad)");
break;
}
pmd = pmd_offset(pud, addr);
if (PTRS_PER_PMD != 1)
pr_cont(", *pmd=%08llx", (long long)pmd_val(*pmd));
if (pmd_none(*pmd))
break;
if (pmd_bad(*pmd)) {
pr_cont("(bad)");
break;
}
/* We must not map this if we have highmem enabled */
if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
break;
pte = pte_offset_map(pmd, addr);
pr_cont(", *pte=%08llx", (long long)pte_val(*pte));
#ifndef CONFIG_ARM_LPAE
pr_cont(", *ppte=%08llx",
(long long)pte_val(pte[PTE_HWTABLE_PTRS]));
#endif
pte_unmap(pte);
} while(0);
pr_cont("\n");
}
#else /* CONFIG_MMU */
void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
{ }
#endif /* CONFIG_MMU */
static inline bool is_write_fault(unsigned int fsr)
{
return (fsr & FSR_WRITE) && !(fsr & FSR_CM);
}
static inline bool is_translation_fault(unsigned int fsr)
{
int fs = fsr_fs(fsr);
#ifdef CONFIG_ARM_LPAE
if ((fs & FS_MMU_NOLL_MASK) == FS_TRANS_NOLL)
return true;
#else
if (fs == FS_L1_TRANS || fs == FS_L2_TRANS)
return true;
#endif
return false;
}
static void die_kernel_fault(const char *msg, struct mm_struct *mm,
unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
bust_spinlocks(1);
pr_alert("8<--- cut here ---\n");
pr_alert("Unable to handle kernel %s at virtual address %08lx when %s\n",
msg, addr, fsr & FSR_LNX_PF ? "execute" :
fsr & FSR_WRITE ? "write" : "read");
show_pte(KERN_ALERT, mm, addr);
die("Oops", regs, fsr);
bust_spinlocks(0);
make_task_dead(SIGKILL);
}
/*
* Oops. The kernel tried to access some page that wasn't present.
*/
static void
__do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
const char *msg;
/*
* Are we prepared to handle this kernel fault?
*/
if (fixup_exception(regs))
return;
/*
* No handler, we'll have to terminate things with extreme prejudice.
*/
if (addr < PAGE_SIZE) {
msg = "NULL pointer dereference";
} else {
if (is_translation_fault(fsr) &&
kfence_handle_page_fault(addr, is_write_fault(fsr), regs))
return;
msg = "paging request";
}
die_kernel_fault(msg, mm, addr, fsr, regs);
}
/*
* Something tried to access memory that isn't in our memory map..
* User mode accesses just cause a SIGSEGV
*/
static void
__do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig,
int code, struct pt_regs *regs)
{
struct task_struct *tsk = current;
if (addr > TASK_SIZE)
harden_branch_predictor();
#ifdef CONFIG_DEBUG_USER
if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
((user_debug & UDBG_BUS) && (sig == SIGBUS))) {
pr_err("8<--- cut here ---\n");
pr_err("%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
tsk->comm, sig, addr, fsr);
show_pte(KERN_ERR, tsk->mm, addr);
show_regs(regs);
}
#endif
#ifndef CONFIG_KUSER_HELPERS
if ((sig == SIGSEGV) && ((addr & PAGE_MASK) == 0xffff0000))
printk_ratelimited(KERN_DEBUG
"%s: CONFIG_KUSER_HELPERS disabled at 0x%08lx\n",
tsk->comm, addr);
#endif
tsk->thread.address = addr;
tsk->thread.error_code = fsr;
tsk->thread.trap_no = 14;
force_sig_fault(sig, code, (void __user *)addr);
}
void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
/*
* If we are in kernel mode at this point, we
* have no context to handle this fault with.
*/
if (user_mode(regs))
__do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
else
__do_kernel_fault(mm, addr, fsr, regs);
}
#ifdef CONFIG_MMU
#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000)
#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000)
static inline bool is_permission_fault(unsigned int fsr)
{
int fs = fsr_fs(fsr);
#ifdef CONFIG_ARM_LPAE
if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL)
return true;
#else
if (fs == FS_L1_PERM || fs == FS_L2_PERM)
return true;
#endif
return false;
}
static int __kprobes
do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int sig, code;
vm_fault_t fault;
unsigned int flags = FAULT_FLAG_DEFAULT;
unsigned long vm_flags = VM_ACCESS_FLAGS;
if (kprobe_page_fault(regs, fsr))
return 0;
/* Enable interrupts if they were enabled in the parent context. */
if (interrupts_enabled(regs))
local_irq_enable();
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (is_write_fault(fsr)) {
flags |= FAULT_FLAG_WRITE;
vm_flags = VM_WRITE;
}
if (fsr & FSR_LNX_PF) {
vm_flags = VM_EXEC;
if (is_permission_fault(fsr) && !user_mode(regs))
die_kernel_fault("execution of memory",
mm, addr, fsr, regs);
}
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
retry:
vma = lock_mm_and_find_vma(mm, addr, regs);
if (unlikely(!vma)) {
fault = VM_FAULT_BADMAP;
goto bad_area;
}
/*
* ok, we have a good vm_area for this memory access, check the
* permissions on the VMA allow for the fault which occurred.
*/
if (!(vma->vm_flags & vm_flags))
fault = VM_FAULT_BADACCESS;
else
fault = handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
/* If we need to retry but a fatal signal is pending, handle the
* signal first. We do not need to release the mmap_lock because
* it would already be released in __lock_page_or_retry in
* mm/filemap.c. */
if (fault_signal_pending(fault, regs)) {
if (!user_mode(regs))
goto no_context;
return 0;
}
/* The fault is fully completed (including releasing mmap lock) */
if (fault & VM_FAULT_COMPLETED)
return 0;
if (!(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
goto retry;
}
}
mmap_read_unlock(mm);
/*
* Handle the "normal" case first - VM_FAULT_MAJOR
*/
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
bad_area:
/*
* If we are in kernel mode at this point, we
* have no context to handle this fault with.
*/
if (!user_mode(regs))
goto no_context;
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
* userspace (which will retry the fault, or kill us if we
* got oom-killed)
*/
pagefault_out_of_memory();
return 0;
}
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
* successfully fix up this page fault.
*/
sig = SIGBUS;
code = BUS_ADRERR;
} else {
/*
* Something tried to access memory that
* isn't in our memory map..
*/
sig = SIGSEGV;
code = fault == VM_FAULT_BADACCESS ?
SEGV_ACCERR : SEGV_MAPERR;
}
__do_user_fault(addr, fsr, sig, code, regs);
return 0;
no_context:
__do_kernel_fault(mm, addr, fsr, regs);
return 0;
}
#else /* CONFIG_MMU */
static int
do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
return 0;
}
#endif /* CONFIG_MMU */
/*
* First Level Translation Fault Handler
*
* We enter here because the first level page table doesn't contain
* a valid entry for the address.
*
* If the address is in kernel space (>= TASK_SIZE), then we are
* probably faulting in the vmalloc() area.
*
* If the init_task's first level page tables contains the relevant
* entry, we copy the it to this task. If not, we send the process
* a signal, fixup the exception, or oops the kernel.
*
* NOTE! We MUST NOT take any locks for this case. We may be in an
* interrupt or a critical region, and should only copy the information
* from the master page table, nothing more.
*/
#ifdef CONFIG_MMU
static int __kprobes
do_translation_fault(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
unsigned int index;
pgd_t *pgd, *pgd_k;
p4d_t *p4d, *p4d_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
if (addr < TASK_SIZE)
return do_page_fault(addr, fsr, regs);
if (user_mode(regs))
goto bad_area;
index = pgd_index(addr);
pgd = cpu_get_pgd() + index;
pgd_k = init_mm.pgd + index;
p4d = p4d_offset(pgd, addr);
p4d_k = p4d_offset(pgd_k, addr);
if (p4d_none(*p4d_k))
goto bad_area;
if (!p4d_present(*p4d))
set_p4d(p4d, *p4d_k);
pud = pud_offset(p4d, addr);
pud_k = pud_offset(p4d_k, addr);
if (pud_none(*pud_k))
goto bad_area;
if (!pud_present(*pud))
set_pud(pud, *pud_k);
pmd = pmd_offset(pud, addr);
pmd_k = pmd_offset(pud_k, addr);
#ifdef CONFIG_ARM_LPAE
/*
* Only one hardware entry per PMD with LPAE.
*/
index = 0;
#else
/*
* On ARM one Linux PGD entry contains two hardware entries (see page
* tables layout in pgtable.h). We normally guarantee that we always
* fill both L1 entries. But create_mapping() doesn't follow the rule.
* It can create inidividual L1 entries, so here we have to call
* pmd_none() check for the entry really corresponded to address, not
* for the first of pair.
*/
index = (addr >> SECTION_SHIFT) & 1;
#endif
if (pmd_none(pmd_k[index]))
goto bad_area;
copy_pmd(pmd, pmd_k);
return 0;
bad_area:
do_bad_area(addr, fsr, regs);
return 0;
}
#else /* CONFIG_MMU */
static int
do_translation_fault(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
return 0;
}
#endif /* CONFIG_MMU */
/*
* Some section permission faults need to be handled gracefully.
* They can happen due to a __{get,put}_user during an oops.
*/
#ifndef CONFIG_ARM_LPAE
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
do_bad_area(addr, fsr, regs);
return 0;
}
#endif /* CONFIG_ARM_LPAE */
/*
* This abort handler always returns "fault".
*/
static int
do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
return 1;
}
struct fsr_info {
int (*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
int sig;
int code;
const char *name;
};
/* FSR definition */
#ifdef CONFIG_ARM_LPAE
#include "fsr-3level.c"
#else
#include "fsr-2level.c"
#endif
void __init
hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
{
if (nr < 0 || nr >= ARRAY_SIZE(fsr_info))
BUG();
fsr_info[nr].fn = fn;
fsr_info[nr].sig = sig;
fsr_info[nr].code = code;
fsr_info[nr].name = name;
}
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void
do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
return;
pr_alert("8<--- cut here ---\n");
pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n",
inf->name, fsr, addr);
show_pte(KERN_ALERT, current->mm, addr);
arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
fsr, 0);
}
void __init
hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
{
if (nr < 0 || nr >= ARRAY_SIZE(ifsr_info))
BUG();
ifsr_info[nr].fn = fn;
ifsr_info[nr].sig = sig;
ifsr_info[nr].code = code;
ifsr_info[nr].name = name;
}
asmlinkage void
do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
{
const struct fsr_info *inf = ifsr_info + fsr_fs(ifsr);
if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs))
return;
pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
inf->name, ifsr, addr);
arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
ifsr, 0);
}
/*
* Abort handler to be used only during first unmasking of asynchronous aborts
* on the boot CPU. This makes sure that the machine will not die if the
* firmware/bootloader left an imprecise abort pending for us to trip over.
*/
static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
pr_warn("Hit pending asynchronous external abort (FSR=0x%08x) during "
"first unmask, this is most likely caused by a "
"firmware/bootloader bug.\n", fsr);
return 0;
}
void __init early_abt_enable(void)
{
fsr_info[FSR_FS_AEA].fn = early_abort_handler;
local_abt_enable();
fsr_info[FSR_FS_AEA].fn = do_bad;
}
#ifndef CONFIG_ARM_LPAE
static int __init exceptions_init(void)
{
if (cpu_architecture() >= CPU_ARCH_ARMv6) {
hook_fault_code(4, do_translation_fault, SIGSEGV, SEGV_MAPERR,
"I-cache maintenance fault");
}
if (cpu_architecture() >= CPU_ARCH_ARMv7) {
/*
* TODO: Access flag faults introduced in ARMv6K.
* Runtime check for 'K' extension is needed
*/
hook_fault_code(3, do_bad, SIGSEGV, SEGV_MAPERR,
"section access flag fault");
hook_fault_code(6, do_bad, SIGSEGV, SEGV_MAPERR,
"section access flag fault");
}
return 0;
}
arch_initcall(exceptions_init);
#endif
|