summaryrefslogtreecommitdiffstats
path: root/arch/arm/mm/fault.c
blob: 379f7855605554c9ae955cf7ffe44964374f297e (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
/*
 *  linux/arch/arm/mm/fault.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *  Modifications for ARM processor (c) 1995-2004 Russell King
 *
 * 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.
 */
#include <linux/module.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.h>
#include <linux/highmem.h>

#include <asm/system.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>

#include "fault.h"

/*
 * Fault status register encodings.  We steal bit 31 for our own purposes.
 */
#define FSR_LNX_PF		(1 << 31)
#define FSR_WRITE		(1 << 11)
#define FSR_FS4			(1 << 10)
#define FSR_FS3_0		(15)

static inline int fsr_fs(unsigned int fsr)
{
	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
}

#ifdef CONFIG_MMU

#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
{
	int ret = 0;

	if (!user_mode(regs)) {
		/* kprobe_running() needs smp_processor_id() */
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, fsr))
			ret = 1;
		preempt_enable();
	}

	return ret;
}
#else
static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
{
	return 0;
}
#endif

/*
 * This is useful to dump out the page tables associated with
 * 'addr' in mm 'mm'.
 */
void show_pte(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;

	if (!mm)
		mm = &init_mm;

	printk(KERN_ALERT "pgd = %p\n", mm->pgd);
	pgd = pgd_offset(mm, addr);
	printk(KERN_ALERT "[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));

	do {
		pmd_t *pmd;
		pte_t *pte;

		if (pgd_none(*pgd))
			break;

		if (pgd_bad(*pgd)) {
			printk("(bad)");
			break;
		}

		pmd = pmd_offset(pgd, addr);
		if (PTRS_PER_PMD != 1)
			printk(", *pmd=%08lx", pmd_val(*pmd));

		if (pmd_none(*pmd))
			break;

		if (pmd_bad(*pmd)) {
			printk("(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);
		printk(", *pte=%08lx", pte_val(*pte));
		printk(", *ppte=%08lx", pte_val(pte[-PTRS_PER_PTE]));
		pte_unmap(pte);
	} while(0);

	printk("\n");
}
#else					/* CONFIG_MMU */
void show_pte(struct mm_struct *mm, unsigned long addr)
{ }
#endif					/* CONFIG_MMU */

/*
 * 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)
{
	/*
	 * Are we prepared to handle this kernel fault?
	 */
	if (fixup_exception(regs))
		return;

	/*
	 * No handler, we'll have to terminate things with extreme prejudice.
	 */
	bust_spinlocks(1);
	printk(KERN_ALERT
		"Unable to handle kernel %s at virtual address %08lx\n",
		(addr < PAGE_SIZE) ? "NULL pointer dereference" :
		"paging request", addr);

	show_pte(mm, addr);
	die("Oops", regs, fsr);
	bust_spinlocks(0);
	do_exit(SIGKILL);
}

/*
 * Something tried to access memory that isn't in our memory map..
 * User mode accesses just cause a SIGSEGV
 */
static void
__do_user_fault(struct task_struct *tsk, unsigned long addr,
		unsigned int fsr, unsigned int sig, int code,
		struct pt_regs *regs)
{
	struct siginfo si;

#ifdef CONFIG_DEBUG_USER
	if (user_debug & UDBG_SEGV) {
		printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
		       tsk->comm, sig, addr, fsr);
		show_pte(tsk->mm, addr);
		show_regs(regs);
	}
#endif

	tsk->thread.address = addr;
	tsk->thread.error_code = fsr;
	tsk->thread.trap_no = 14;
	si.si_signo = sig;
	si.si_errno = 0;
	si.si_code = code;
	si.si_addr = (void __user *)addr;
	force_sig_info(sig, &si, tsk);
}

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(tsk, addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
	else
		__do_kernel_fault(mm, addr, fsr, regs);
}

#ifdef CONFIG_MMU
#define VM_FAULT_BADMAP		0x010000
#define VM_FAULT_BADACCESS	0x020000

/*
 * Check that the permissions on the VMA allow for the fault which occurred.
 * If we encountered a write fault, we must have write permission, otherwise
 * we allow any permission.
 */
static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
{
	unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;

	if (fsr & FSR_WRITE)
		mask = VM_WRITE;
	if (fsr & FSR_LNX_PF)
		mask = VM_EXEC;

	return vma->vm_flags & mask ? false : true;
}

static int __kprobes
__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
		struct task_struct *tsk)
{
	struct vm_area_struct *vma;
	int fault;

	vma = find_vma(mm, addr);
	fault = VM_FAULT_BADMAP;
	if (unlikely(!vma))
		goto out;
	if (unlikely(vma->vm_start > addr))
		goto check_stack;

	/*
	 * Ok, we have a good vm_area for this
	 * memory access, so we can handle it.
	 */
good_area:
	if (access_error(fsr, vma)) {
		fault = VM_FAULT_BADACCESS;
		goto out;
	}

	/*
	 * If for any reason at all we couldn't handle the fault, make
	 * sure we exit gracefully rather than endlessly redo the fault.
	 */
	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & FSR_WRITE) ? FAULT_FLAG_WRITE : 0);
	if (unlikely(fault & VM_FAULT_ERROR))
		return fault;
	if (fault & VM_FAULT_MAJOR)
		tsk->maj_flt++;
	else
		tsk->min_flt++;
	return fault;

check_stack:
	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
		goto good_area;
out:
	return fault;
}

static int __kprobes
do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	int fault, sig, code;

	if (notify_page_fault(regs, fsr))
		return 0;

	tsk = current;
	mm  = tsk->mm;

	/*
	 * If we're in an interrupt or have no user
	 * context, we must not take the fault..
	 */
	if (in_atomic() || !mm)
		goto no_context;

	/*
	 * As per x86, we may deadlock here.  However, since the kernel only
	 * validly references user space from well defined areas of the code,
	 * we can bug out early if this is from code which shouldn't.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
			goto no_context;
		down_read(&mm->mmap_sem);
	} else {
		/*
		 * The above down_read_trylock() might have succeeded in
		 * which case, we'll have missed the might_sleep() from
		 * down_read()
		 */
		might_sleep();
	}

	fault = __do_page_fault(mm, addr, fsr, tsk);
	up_read(&mm->mmap_sem);

	/*
	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
	 */
	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
		return 0;

	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 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_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(tsk, 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;
	pmd_t *pmd, *pmd_k;

	if (addr < TASK_SIZE)
		return do_page_fault(addr, fsr, regs);

	index = pgd_index(addr);

	/*
	 * FIXME: CP15 C1 is write only on ARMv3 architectures.
	 */
	pgd = cpu_get_pgd() + index;
	pgd_k = init_mm.pgd + index;

	if (pgd_none(*pgd_k))
		goto bad_area;

	if (!pgd_present(*pgd))
		set_pgd(pgd, *pgd_k);

	pmd_k = pmd_offset(pgd_k, addr);
	pmd   = pmd_offset(pgd, addr);

	if (pmd_none(*pmd_k))
		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.
 */
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
	do_bad_area(addr, fsr, regs);
	return 0;
}

/*
 * This abort handler always returns "fault".
 */
static int
do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
	return 1;
}

static struct fsr_info {
	int	(*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
	int	sig;
	int	code;
	const char *name;
} fsr_info[] = {
	/*
	 * The following are the standard ARMv3 and ARMv4 aborts.  ARMv5
	 * defines these to be "precise" aborts.
	 */
	{ do_bad,		SIGSEGV, 0,		"vector exception"		   },
	{ do_bad,		SIGILL,	 BUS_ADRALN,	"alignment exception"		   },
	{ do_bad,		SIGKILL, 0,		"terminal exception"		   },
	{ do_bad,		SIGILL,	 BUS_ADRALN,	"alignment exception"		   },
	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"section domain fault"		   },
	{ do_bad,		SIGBUS,	 0,		"external abort on non-linefetch"  },
	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"page domain fault"		   },
	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"section permission fault"	   },
	{ do_bad,		SIGBUS,	 0,		"external abort on translation"	   },
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"page permission fault"		   },
	/*
	 * The following are "imprecise" aborts, which are signalled by bit
	 * 10 of the FSR, and may not be recoverable.  These are only
	 * supported if the CPU abort handler supports bit 10.
	 */
	{ do_bad,		SIGBUS,  0,		"unknown 16"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 17"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 18"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 19"			   },
	{ do_bad,		SIGBUS,  0,		"lock abort"			   }, /* xscale */
	{ do_bad,		SIGBUS,  0,		"unknown 21"			   },
	{ do_bad,		SIGBUS,  BUS_OBJERR,	"imprecise external abort"	   }, /* xscale */
	{ do_bad,		SIGBUS,  0,		"unknown 23"			   },
	{ do_bad,		SIGBUS,  0,		"dcache parity error"		   }, /* xscale */
	{ do_bad,		SIGBUS,  0,		"unknown 25"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 26"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 27"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 28"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 29"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 30"			   },
	{ do_bad,		SIGBUS,  0,		"unknown 31"			   }
};

void __init
hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
		int sig, const char *name)
{
	if (nr >= 0 && nr < ARRAY_SIZE(fsr_info)) {
		fsr_info[nr].fn   = fn;
		fsr_info[nr].sig  = sig;
		fsr_info[nr].name = name;
	}
}

/*
 * Dispatch a data abort to the relevant handler.
 */
asmlinkage void __exception
do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
	const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
	struct siginfo info;

	if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
		return;

	printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n",
		inf->name, fsr, addr);

	info.si_signo = inf->sig;
	info.si_errno = 0;
	info.si_code  = inf->code;
	info.si_addr  = (void __user *)addr;
	arm_notify_die("", regs, &info, fsr, 0);
}

asmlinkage void __exception
do_PrefetchAbort(unsigned long addr, struct pt_regs *regs)
{
	do_translation_fault(addr, FSR_LNX_PF, regs);
}