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
|
// TODO VM_EXEC flag work-around, cache aliasing
/*
* arch/xtensa/mm/fault.c
*
* 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.
*
* Copyright (C) 2001 - 2010 Tensilica Inc.
*
* Chris Zankel <chris@zankel.net>
* Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
*/
#include <linux/mm.h>
#include <linux/extable.h>
#include <linux/hardirq.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/hardirq.h>
void bad_page_fault(struct pt_regs*, unsigned long, int);
static void vmalloc_fault(struct pt_regs *regs, unsigned int address)
{
#ifdef CONFIG_MMU
/* Synchronize this task's top level page-table
* with the 'reference' page table.
*/
struct mm_struct *act_mm = current->active_mm;
int index = pgd_index(address);
pgd_t *pgd, *pgd_k;
p4d_t *p4d, *p4d_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
if (act_mm == NULL)
goto bad_page_fault;
pgd = act_mm->pgd + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k))
goto bad_page_fault;
pgd_val(*pgd) = pgd_val(*pgd_k);
p4d = p4d_offset(pgd, address);
p4d_k = p4d_offset(pgd_k, address);
if (!p4d_present(*p4d) || !p4d_present(*p4d_k))
goto bad_page_fault;
pud = pud_offset(p4d, address);
pud_k = pud_offset(p4d_k, address);
if (!pud_present(*pud) || !pud_present(*pud_k))
goto bad_page_fault;
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd) || !pmd_present(*pmd_k))
goto bad_page_fault;
pmd_val(*pmd) = pmd_val(*pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto bad_page_fault;
return;
bad_page_fault:
bad_page_fault(regs, address, SIGKILL);
#else
WARN_ONCE(1, "%s in noMMU configuration\n", __func__);
#endif
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*
* Note: does not handle Miss and MultiHit.
*/
void do_page_fault(struct pt_regs *regs)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int exccause = regs->exccause;
unsigned int address = regs->excvaddr;
int code;
int is_write, is_exec;
vm_fault_t fault;
unsigned int flags = FAULT_FLAG_DEFAULT;
code = SEGV_MAPERR;
/* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*/
if (address >= TASK_SIZE && !user_mode(regs)) {
vmalloc_fault(regs, address);
return;
}
/* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm) {
bad_page_fault(regs, address, SIGSEGV);
return;
}
is_write = (exccause == EXCCAUSE_STORE_CACHE_ATTRIBUTE) ? 1 : 0;
is_exec = (exccause == EXCCAUSE_ITLB_PRIVILEGE ||
exccause == EXCCAUSE_ITLB_MISS ||
exccause == EXCCAUSE_FETCH_CACHE_ATTRIBUTE) ? 1 : 0;
pr_debug("[%s:%d:%08x:%d:%08lx:%s%s]\n",
current->comm, current->pid,
address, exccause, regs->pc,
is_write ? "w" : "", is_exec ? "x" : "");
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
retry:
mmap_read_lock(mm);
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:
code = SEGV_ACCERR;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
flags |= FAULT_FLAG_WRITE;
} else if (is_exec) {
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
} else /* Allow read even from write-only pages. */
if (!(vma->vm_flags & (VM_READ | 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.
*/
fault = handle_mm_fault(vma, address, flags, regs);
if (fault_signal_pending(fault, regs)) {
if (!user_mode(regs))
bad_page_fault(regs, address, SIGKILL);
return;
}
/* The fault is fully completed (including releasing mmap lock) */
if (fault & VM_FAULT_COMPLETED)
return;
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
/* No need to mmap_read_unlock(mm) as we would
* have already released it in __lock_page_or_retry
* in mm/filemap.c.
*/
goto retry;
}
mmap_read_unlock(mm);
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:
mmap_read_unlock(mm);
if (user_mode(regs)) {
current->thread.bad_vaddr = address;
current->thread.error_code = is_write;
force_sig_fault(SIGSEGV, code, (void *) address);
return;
}
bad_page_fault(regs, address, SIGSEGV);
return;
/* 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:
mmap_read_unlock(mm);
if (!user_mode(regs))
bad_page_fault(regs, address, SIGKILL);
else
pagefault_out_of_memory();
return;
do_sigbus:
mmap_read_unlock(mm);
/* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
current->thread.bad_vaddr = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
bad_page_fault(regs, address, SIGBUS);
return;
}
void
bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
{
extern void __noreturn die(const char*, struct pt_regs*, long);
const struct exception_table_entry *entry;
/* Are we prepared to handle this kernel fault? */
if ((entry = search_exception_tables(regs->pc)) != NULL) {
pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
current->comm, regs->pc, entry->fixup);
current->thread.bad_uaddr = address;
regs->pc = entry->fixup;
return;
}
/* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
pr_alert("Unable to handle kernel paging request at virtual "
"address %08lx\n pc = %08lx, ra = %08lx\n",
address, regs->pc, regs->areg[0]);
die("Oops", regs, sig);
}
|