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
|
/*
* Page fault handler for SH with an MMU.
*
* Copyright (C) 1999 Niibe Yutaka
* Copyright (C) 2003 Paul Mundt
*
* Based on linux/arch/i386/mm/fault.c:
* Copyright (C) 1995 Linus Torvalds
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*/
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/kprobes.h>
#include <asm/system.h>
#include <asm/mmu_context.h>
#include <asm/kgdb.h>
extern void die(const char *,struct pt_regs *,long);
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
unsigned long writeaccess,
unsigned long address)
{
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct * vma;
unsigned long page;
int si_code;
siginfo_t info;
trace_hardirqs_on();
local_irq_enable();
#ifdef CONFIG_SH_KGDB
if (kgdb_nofault && kgdb_bus_err_hook)
kgdb_bus_err_hook();
#endif
tsk = current;
mm = tsk->mm;
si_code = SEGV_MAPERR;
if (unlikely(address >= TASK_SIZE)) {
/*
* 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 offset = pgd_index(address);
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pgd = get_TTB() + offset;
pgd_k = swapper_pg_dir + offset;
/* This will never happen with the folded page table. */
if (!pgd_present(*pgd)) {
if (!pgd_present(*pgd_k))
goto bad_area_nosemaphore;
set_pgd(pgd, *pgd_k);
return;
}
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (pud_present(*pud) || !pud_present(*pud_k))
goto bad_area_nosemaphore;
set_pud(pud, *pud_k);
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (pmd_present(*pmd) || !pmd_present(*pmd_k))
goto bad_area_nosemaphore;
set_pmd(pmd, *pmd_k);
return;
}
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto no_context;
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 (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;
if (writeaccess) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto bad_area;
}
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
survive:
switch (handle_mm_fault(mm, vma, address, writeaccess)) {
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();
}
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:
if (user_mode(regs)) {
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = si_code;
info.si_addr = (void *) address;
force_sig_info(SIGSEGV, &info, tsk);
return;
}
no_context:
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
return;
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*
*/
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 "pc = %08lx\n", regs->pc);
page = (unsigned long)get_TTB();
if (page) {
page = ((unsigned long *) page)[address >> PGDIR_SHIFT];
printk(KERN_ALERT "*pde = %08lx\n", page);
if (page & _PAGE_PRESENT) {
page &= PAGE_MASK;
address &= 0x003ff000;
page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
printk(KERN_ALERT "*pte = %08lx\n", page);
}
}
die("Oops", regs, writeaccess);
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 (is_init(current)) {
yield();
down_read(&mm->mmap_sem);
goto survive;
}
printk("VM: killing process %s\n", tsk->comm);
if (user_mode(regs))
do_exit(SIGKILL);
goto no_context;
do_sigbus:
up_read(&mm->mmap_sem);
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void *)address;
force_sig_info(SIGBUS, &info, tsk);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
goto no_context;
}
|
