summaryrefslogtreecommitdiffstats
path: root/arch/i386/mm/fault.c
blob: 9edd4485b91eafd6396affe5649c92d00b8666ae (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
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
/*
 *  linux/arch/i386/mm/fault.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 */

#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/tty.h>
#include <linux/vt_kern.h>		/* For unblank_screen() */
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/kprobes.h>

#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/desc.h>
#include <asm/kdebug.h>

extern void die(const char *,struct pt_regs *,long);

/*
 * Unlock any spinlocks which will prevent us from getting the
 * message out 
 */
void bust_spinlocks(int yes)
{
	int loglevel_save = console_loglevel;

	if (yes) {
		oops_in_progress = 1;
		return;
	}
#ifdef CONFIG_VT
	unblank_screen();
#endif
	oops_in_progress = 0;
	/*
	 * OK, the message is on the console.  Now we call printk()
	 * without oops_in_progress set so that printk will give klogd
	 * a poke.  Hold onto your hats...
	 */
	console_loglevel = 15;		/* NMI oopser may have shut the console up */
	printk(" ");
	console_loglevel = loglevel_save;
}

/*
 * Return EIP plus the CS segment base.  The segment limit is also
 * adjusted, clamped to the kernel/user address space (whichever is
 * appropriate), and returned in *eip_limit.
 *
 * The segment is checked, because it might have been changed by another
 * task between the original faulting instruction and here.
 *
 * If CS is no longer a valid code segment, or if EIP is beyond the
 * limit, or if it is a kernel address when CS is not a kernel segment,
 * then the returned value will be greater than *eip_limit.
 * 
 * This is slow, but is very rarely executed.
 */
static inline unsigned long get_segment_eip(struct pt_regs *regs,
					    unsigned long *eip_limit)
{
	unsigned long eip = regs->eip;
	unsigned seg = regs->xcs & 0xffff;
	u32 seg_ar, seg_limit, base, *desc;

	/* The standard kernel/user address space limit. */
	*eip_limit = (seg & 3) ? USER_DS.seg : KERNEL_DS.seg;

	/* Unlikely, but must come before segment checks. */
	if (unlikely((regs->eflags & VM_MASK) != 0))
		return eip + (seg << 4);
	
	/* By far the most common cases. */
	if (likely(seg == __USER_CS || seg == __KERNEL_CS))
		return eip;

	/* Check the segment exists, is within the current LDT/GDT size,
	   that kernel/user (ring 0..3) has the appropriate privilege,
	   that it's a code segment, and get the limit. */
	__asm__ ("larl %3,%0; lsll %3,%1"
		 : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg));
	if ((~seg_ar & 0x9800) || eip > seg_limit) {
		*eip_limit = 0;
		return 1;	 /* So that returned eip > *eip_limit. */
	}

	/* Get the GDT/LDT descriptor base. 
	   When you look for races in this code remember that
	   LDT and other horrors are only used in user space. */
	if (seg & (1<<2)) {
		/* Must lock the LDT while reading it. */
		down(&current->mm->context.sem);
		desc = current->mm->context.ldt;
		desc = (void *)desc + (seg & ~7);
	} else {
		/* Must disable preemption while reading the GDT. */
		desc = (u32 *)&per_cpu(cpu_gdt_table, get_cpu());
		desc = (void *)desc + (seg & ~7);
	}

	/* Decode the code segment base from the descriptor */
	base = get_desc_base((unsigned long *)desc);

	if (seg & (1<<2)) { 
		up(&current->mm->context.sem);
	} else
		put_cpu();

	/* Adjust EIP and segment limit, and clamp at the kernel limit.
	   It's legitimate for segments to wrap at 0xffffffff. */
	seg_limit += base;
	if (seg_limit < *eip_limit && seg_limit >= base)
		*eip_limit = seg_limit;
	return eip + base;
}

/* 
 * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
 * Check that here and ignore it.
 */
static int __is_prefetch(struct pt_regs *regs, unsigned long addr)
{ 
	unsigned long limit;
	unsigned long instr = get_segment_eip (regs, &limit);
	int scan_more = 1;
	int prefetch = 0; 
	int i;

	for (i = 0; scan_more && i < 15; i++) { 
		unsigned char opcode;
		unsigned char instr_hi;
		unsigned char instr_lo;

		if (instr > limit)
			break;
		if (__get_user(opcode, (unsigned char __user *) instr))
			break; 

		instr_hi = opcode & 0xf0; 
		instr_lo = opcode & 0x0f; 
		instr++;

		switch (instr_hi) { 
		case 0x20:
		case 0x30:
			/* Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. */
			scan_more = ((instr_lo & 7) == 0x6);
			break;
			
		case 0x60:
			/* 0x64 thru 0x67 are valid prefixes in all modes. */
			scan_more = (instr_lo & 0xC) == 0x4;
			break;		
		case 0xF0:
			/* 0xF0, 0xF2, and 0xF3 are valid prefixes */
			scan_more = !instr_lo || (instr_lo>>1) == 1;
			break;			
		case 0x00:
			/* Prefetch instruction is 0x0F0D or 0x0F18 */
			scan_more = 0;
			if (instr > limit)
				break;
			if (__get_user(opcode, (unsigned char __user *) instr))
				break;
			prefetch = (instr_lo == 0xF) &&
				(opcode == 0x0D || opcode == 0x18);
			break;			
		default:
			scan_more = 0;
			break;
		} 
	}
	return prefetch;
}

static inline int is_prefetch(struct pt_regs *regs, unsigned long addr,
			      unsigned long error_code)
{
	if (unlikely(boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
		     boot_cpu_data.x86 >= 6)) {
		/* Catch an obscure case of prefetch inside an NX page. */
		if (nx_enabled && (error_code & 16))
			return 0;
		return __is_prefetch(regs, addr);
	}
	return 0;
} 

static noinline void force_sig_info_fault(int si_signo, int si_code,
	unsigned long address, struct task_struct *tsk)
{
	siginfo_t info;

	info.si_signo = si_signo;
	info.si_errno = 0;
	info.si_code = si_code;
	info.si_addr = (void __user *)address;
	force_sig_info(si_signo, &info, tsk);
}

fastcall void do_invalid_op(struct pt_regs *, unsigned long);

/*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 *
 * error_code:
 *	bit 0 == 0 means no page found, 1 means protection fault
 *	bit 1 == 0 means read, 1 means write
 *	bit 2 == 0 means kernel, 1 means user-mode
 */
fastcall void __kprobes do_page_fault(struct pt_regs *regs,
				      unsigned long error_code)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	struct vm_area_struct * vma;
	unsigned long address;
	unsigned long page;
	int write, si_code;

	/* get the address */
        address = read_cr2();

	if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
					SIGSEGV) == NOTIFY_STOP)
		return;
	/* It's safe to allow irq's after cr2 has been saved */
	if (regs->eflags & (X86_EFLAGS_IF|VM_MASK))
		local_irq_enable();

	tsk = current;

	si_code = SEGV_MAPERR;

	/*
	 * We fault-in kernel-space virtual memory on-demand. The
	 * 'reference' page table is init_mm.pgd.
	 *
	 * 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.
	 *
	 * This verifies that the fault happens in kernel space
	 * (error_code & 4) == 0, and that the fault was not a
	 * protection error (error_code & 1) == 0.
	 */
	if (unlikely(address >= TASK_SIZE)) { 
		if (!(error_code & 5))
			goto vmalloc_fault;
		/* 
		 * Don't take the mm semaphore here. If we fixup a prefetch
		 * fault we could otherwise deadlock.
		 */
		goto bad_area_nosemaphore;
	} 

	mm = tsk->mm;

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

	/* When running in the kernel we expect faults to occur only to
	 * addresses in user space.  All other faults represent errors in the
	 * kernel and should generate an OOPS.  Unfortunatly, in the case of an
	 * erroneous fault occuring in a code path which already holds mmap_sem
	 * we will deadlock attempting to validate the fault against the
	 * address space.  Luckily the kernel only validly references user
	 * space from well defined areas of code, which are listed in the
	 * exceptions table.
	 *
	 * As the vast majority of faults will be valid we will only perform
	 * the source reference check when there is a possibilty of a deadlock.
	 * Attempt to lock the address space, if we cannot we then validate the
	 * source.  If this is invalid we can skip the address space check,
	 * thus avoiding the deadlock.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if ((error_code & 4) == 0 &&
		    !search_exception_tables(regs->eip))
			goto bad_area_nosemaphore;
		down_read(&mm->mmap_sem);
	}

	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;
	if (vma->vm_start <= address)
		goto good_area;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;
	if (error_code & 4) {
		/*
		 * accessing the stack below %esp is always a bug.
		 * The "+ 32" is there due to some instructions (like
		 * pusha) doing post-decrement on the stack and that
		 * doesn't show up until later..
		 */
		if (address + 32 < regs->esp)
			goto bad_area;
	}
	if (expand_stack(vma, address))
		goto bad_area;
/*
 * Ok, we have a good vm_area for this memory access, so
 * we can handle it..
 */
good_area:
	si_code = SEGV_ACCERR;
	write = 0;
	switch (error_code & 3) {
		default:	/* 3: write, present */
#ifdef TEST_VERIFY_AREA
			if (regs->cs == KERNEL_CS)
				printk("WP fault at %08lx\n", regs->eip);
#endif
			/* fall through */
		case 2:		/* write, not present */
			if (!(vma->vm_flags & VM_WRITE))
				goto bad_area;
			write++;
			break;
		case 1:		/* read, present */
			goto bad_area;
		case 0:		/* read, not present */
			if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
				goto bad_area;
	}

 survive:
	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	switch (handle_mm_fault(mm, vma, address, write)) {
		case VM_FAULT_MINOR:
			tsk->min_flt++;
			break;
		case VM_FAULT_MAJOR:
			tsk->maj_flt++;
			break;
		case VM_FAULT_SIGBUS:
			goto do_sigbus;
		case VM_FAULT_OOM:
			goto out_of_memory;
		default:
			BUG();
	}

	/*
	 * Did it hit the DOS screen memory VA from vm86 mode?
	 */
	if (regs->eflags & VM_MASK) {
		unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
		if (bit < 32)
			tsk->thread.screen_bitmap |= 1 << bit;
	}
	up_read(&mm->mmap_sem);
	return;

/*
 * Something tried to access memory that isn't in our memory map..
 * Fix it, but check if it's kernel or user first..
 */
bad_area:
	up_read(&mm->mmap_sem);

bad_area_nosemaphore:
	/* User mode accesses just cause a SIGSEGV */
	if (error_code & 4) {
		/* 
		 * Valid to do another page fault here because this one came 
		 * from user space.
		 */
		if (is_prefetch(regs, address, error_code))
			return;

		tsk->thread.cr2 = address;
		/* Kernel addresses are always protection faults */
		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
		tsk->thread.trap_no = 14;
		force_sig_info_fault(SIGSEGV, si_code, address, tsk);
		return;
	}

#ifdef CONFIG_X86_F00F_BUG
	/*
	 * Pentium F0 0F C7 C8 bug workaround.
	 */
	if (boot_cpu_data.f00f_bug) {
		unsigned long nr;
		
		nr = (address - idt_descr.address) >> 3;

		if (nr == 6) {
			do_invalid_op(regs, 0);
			return;
		}
	}
#endif

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

	/* 
	 * Valid to do another page fault here, because if this fault
	 * had been triggered by is_prefetch fixup_exception would have 
	 * handled it.
	 */
 	if (is_prefetch(regs, address, error_code))
 		return;

/*
 * Oops. The kernel tried to access some bad page. We'll have to
 * terminate things with extreme prejudice.
 */

	bust_spinlocks(1);

#ifdef CONFIG_X86_PAE
	if (error_code & 16) {
		pte_t *pte = lookup_address(address);

		if (pte && pte_present(*pte) && !pte_exec_kernel(*pte))
			printk(KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", current->uid);
	}
#endif
	if (address < PAGE_SIZE)
		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
	else
		printk(KERN_ALERT "Unable to handle kernel paging request");
	printk(" at virtual address %08lx\n",address);
	printk(KERN_ALERT " printing eip:\n");
	printk("%08lx\n", regs->eip);
	page = read_cr3();
	page = ((unsigned long *) __va(page))[address >> 22];
	printk(KERN_ALERT "*pde = %08lx\n", page);
	/*
	 * We must not directly access the pte in the highpte
	 * case, the page table might be allocated in highmem.
	 * And lets rather not kmap-atomic the pte, just in case
	 * it's allocated already.
	 */
#ifndef CONFIG_HIGHPTE
	if (page & 1) {
		page &= PAGE_MASK;
		address &= 0x003ff000;
		page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
		printk(KERN_ALERT "*pte = %08lx\n", page);
	}
#endif
	tsk->thread.cr2 = address;
	tsk->thread.trap_no = 14;
	tsk->thread.error_code = error_code;
	die("Oops", regs, error_code);
	bust_spinlocks(0);
	do_exit(SIGKILL);

/*
 * We ran out of memory, or some other thing happened to us that made
 * us unable to handle the page fault gracefully.
 */
out_of_memory:
	up_read(&mm->mmap_sem);
	if (tsk->pid == 1) {
		yield();
		down_read(&mm->mmap_sem);
		goto survive;
	}
	printk("VM: killing process %s\n", tsk->comm);
	if (error_code & 4)
		do_exit(SIGKILL);
	goto no_context;

do_sigbus:
	up_read(&mm->mmap_sem);

	/* Kernel mode? Handle exceptions or die */
	if (!(error_code & 4))
		goto no_context;

	/* User space => ok to do another page fault */
	if (is_prefetch(regs, address, error_code))
		return;

	tsk->thread.cr2 = address;
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = 14;
	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
	return;

vmalloc_fault:
	{
		/*
		 * Synchronize this task's top level page-table
		 * with the 'reference' page table.
		 *
		 * Do _not_ use "tsk" here. We might be inside
		 * an interrupt in the middle of a task switch..
		 */
		int index = pgd_index(address);
		unsigned long pgd_paddr;
		pgd_t *pgd, *pgd_k;
		pud_t *pud, *pud_k;
		pmd_t *pmd, *pmd_k;
		pte_t *pte_k;

		pgd_paddr = read_cr3();
		pgd = index + (pgd_t *)__va(pgd_paddr);
		pgd_k = init_mm.pgd + index;

		if (!pgd_present(*pgd_k))
			goto no_context;

		/*
		 * set_pgd(pgd, *pgd_k); here would be useless on PAE
		 * and redundant with the set_pmd() on non-PAE. As would
		 * set_pud.
		 */

		pud = pud_offset(pgd, address);
		pud_k = pud_offset(pgd_k, address);
		if (!pud_present(*pud_k))
			goto no_context;
		
		pmd = pmd_offset(pud, address);
		pmd_k = pmd_offset(pud_k, address);
		if (!pmd_present(*pmd_k))
			goto no_context;
		set_pmd(pmd, *pmd_k);

		pte_k = pte_offset_kernel(pmd_k, address);
		if (!pte_present(*pte_k))
			goto no_context;
		return;
	}
}