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
|
/*
* linux/arch/i386/mm/fault.c
*
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/head.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 <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
extern void die_if_kernel(const char *,struct pt_regs *,long);
/*
* Ugly, ugly, but the goto's result in better assembly..
*/
int __verify_write(const void * addr, unsigned long size)
{
struct vm_area_struct * vma;
unsigned long start = (unsigned long) addr;
if (!size)
return 1;
vma = find_vma(current->mm, start);
if (!vma)
goto bad_area;
if (vma->vm_start > start)
goto check_stack;
good_area:
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
size--;
size += start & ~PAGE_MASK;
size >>= PAGE_SHIFT;
start &= PAGE_MASK;
for (;;) {
handle_mm_fault(current,vma, start, 1);
if (!size)
break;
size--;
start += PAGE_SIZE;
if (start < vma->vm_end)
continue;
vma = vma->vm_next;
if (!vma || vma->vm_start != start)
goto bad_area;
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;;
}
return 1;
check_stack:
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, start) == 0)
goto good_area;
bad_area:
return 0;
}
/*
* 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
*/
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
struct vm_area_struct * vma;
unsigned long address;
unsigned long page;
unsigned long fixup;
int write;
lock_kernel();
/* get the address */
__asm__("movl %%cr2,%0":"=r" (address));
down(&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 pre-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:
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;
}
handle_mm_fault(tsk, vma, address, write);
up(&mm->mmap_sem);
/*
* 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->tss.screen_bitmap |= 1 << bit;
}
goto out;
/*
* 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(&mm->mmap_sem);
/* User mode accesses just cause a SIGSEGV */
if (error_code & 4) {
tsk->tss.cr2 = address;
tsk->tss.error_code = error_code;
tsk->tss.trap_no = 14;
force_sig(SIGSEGV, tsk);
goto out;
}
/* Are we prepared to handle this kernel fault? */
if ((fixup = search_exception_table(regs->eip)) != 0) {
printk(KERN_DEBUG "%s: Exception at [<%lx>] (%lx)\n",
tsk->comm,
regs->eip,
fixup);
regs->eip = fixup;
goto out;
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*
* First we check if it was the bootup rw-test, though..
*/
if (wp_works_ok < 0 && address == 0xc0000000 && (error_code & 1)) {
wp_works_ok = 1;
pg0[0] = pte_val(mk_pte(0, PAGE_SHARED));
flush_tlb();
goto out;
}
if (address < PAGE_SIZE) {
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
pg0[0] = pte_val(mk_pte(0, PAGE_SHARED));
} else
printk(KERN_ALERT "Unable to handle kernel paging request");
printk(" at virtual address %08lx\n",address);
__asm__("movl %%cr3,%0" : "=r" (page));
printk(KERN_ALERT "current->tss.cr3 = %08lx, %%cr3 = %08lx\n",
tsk->tss.cr3, page);
page = ((unsigned long *) __va(page))[address >> 22];
printk(KERN_ALERT "*pde = %08lx\n", page);
if (page & 1) {
page &= PAGE_MASK;
address &= 0x003ff000;
page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
printk(KERN_ALERT "*pte = %08lx\n", page);
}
die_if_kernel("Oops", regs, error_code);
do_exit(SIGKILL);
out:
unlock_kernel();
}
|
