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
|
/*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
*
* Derived from "arch/i386/mm/fault.c"
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* Modified by Cort Dougan and Paul Mackerras.
*
* Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#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/interrupt.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
#include <linux/ratelimit.h>
#include <linux/context_tracking.h>
#include <linux/hugetlb.h>
#include <asm/firmware.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/siginfo.h>
#include <asm/debug.h>
#include "icswx.h"
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs)
{
int ret = 0;
/* kprobe_running() needs smp_processor_id() */
if (!user_mode(regs)) {
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, 11))
ret = 1;
preempt_enable();
}
return ret;
}
#else
static inline int notify_page_fault(struct pt_regs *regs)
{
return 0;
}
#endif
/*
* Check whether the instruction at regs->nip is a store using
* an update addressing form which will update r1.
*/
static int store_updates_sp(struct pt_regs *regs)
{
unsigned int inst;
if (get_user(inst, (unsigned int __user *)regs->nip))
return 0;
/* check for 1 in the rA field */
if (((inst >> 16) & 0x1f) != 1)
return 0;
/* check major opcode */
switch (inst >> 26) {
case 37: /* stwu */
case 39: /* stbu */
case 45: /* sthu */
case 53: /* stfsu */
case 55: /* stfdu */
return 1;
case 62: /* std or stdu */
return (inst & 3) == 1;
case 31:
/* check minor opcode */
switch ((inst >> 1) & 0x3ff) {
case 181: /* stdux */
case 183: /* stwux */
case 247: /* stbux */
case 439: /* sthux */
case 695: /* stfsux */
case 759: /* stfdux */
return 1;
}
}
return 0;
}
/*
* do_page_fault error handling helpers
*/
#define MM_FAULT_RETURN 0
#define MM_FAULT_CONTINUE -1
#define MM_FAULT_ERR(sig) (sig)
static int do_sigbus(struct pt_regs *regs, unsigned long address,
unsigned int fault)
{
siginfo_t info;
unsigned int lsb = 0;
up_read(¤t->mm->mmap_sem);
if (!user_mode(regs))
return MM_FAULT_ERR(SIGBUS);
current->thread.trap_nr = BUS_ADRERR;
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void __user *)address;
#ifdef CONFIG_MEMORY_FAILURE
if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
current->comm, current->pid, address);
info.si_code = BUS_MCEERR_AR;
}
if (fault & VM_FAULT_HWPOISON_LARGE)
lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
if (fault & VM_FAULT_HWPOISON)
lsb = PAGE_SHIFT;
#endif
info.si_addr_lsb = lsb;
force_sig_info(SIGBUS, &info, current);
return MM_FAULT_RETURN;
}
static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
{
/*
* Pagefault was interrupted by SIGKILL. We have no reason to
* continue the pagefault.
*/
if (fatal_signal_pending(current)) {
/*
* If we have retry set, the mmap semaphore will have
* alrady been released in __lock_page_or_retry(). Else
* we release it now.
*/
if (!(fault & VM_FAULT_RETRY))
up_read(¤t->mm->mmap_sem);
/* Coming from kernel, we need to deal with uaccess fixups */
if (user_mode(regs))
return MM_FAULT_RETURN;
return MM_FAULT_ERR(SIGKILL);
}
/* No fault: be happy */
if (!(fault & VM_FAULT_ERROR))
return MM_FAULT_CONTINUE;
/* Out of memory */
if (fault & VM_FAULT_OOM) {
up_read(¤t->mm->mmap_sem);
/*
* We ran out of memory, or some other thing happened to us that
* made us unable to handle the page fault gracefully.
*/
if (!user_mode(regs))
return MM_FAULT_ERR(SIGKILL);
pagefault_out_of_memory();
return MM_FAULT_RETURN;
}
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE))
return do_sigbus(regs, addr, fault);
/* We don't understand the fault code, this is fatal */
BUG();
return MM_FAULT_CONTINUE;
}
/*
* For 600- and 800-family processors, the error_code parameter is DSISR
* for a data fault, SRR1 for an instruction fault. For 400-family processors
* the error_code parameter is ESR for a data fault, 0 for an instruction
* fault.
* For 64-bit processors, the error_code parameter is
* - DSISR for a non-SLB data access fault,
* - SRR1 & 0x08000000 for a non-SLB instruction access fault
* - 0 any SLB fault.
*
* The return value is 0 if the fault was handled, or the signal
* number if this is a kernel fault that can't be handled here.
*/
int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
enum ctx_state prev_state = exception_enter();
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
int code = SEGV_MAPERR;
int is_write = 0;
int trap = TRAP(regs);
int is_exec = trap == 0x400;
int fault;
int rc = 0, store_update_sp = 0;
#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
/*
* Fortunately the bit assignments in SRR1 for an instruction
* fault and DSISR for a data fault are mostly the same for the
* bits we are interested in. But there are some bits which
* indicate errors in DSISR but can validly be set in SRR1.
*/
if (trap == 0x400)
error_code &= 0x48200000;
else
is_write = error_code & DSISR_ISSTORE;
#else
is_write = error_code & ESR_DST;
#endif /* CONFIG_4xx || CONFIG_BOOKE */
#ifdef CONFIG_PPC_ICSWX
/*
* we need to do this early because this "data storage
* interrupt" does not update the DAR/DEAR so we don't want to
* look at it
*/
if (error_code & ICSWX_DSI_UCT) {
rc = acop_handle_fault(regs, address, error_code);
if (rc)
goto bail;
}
#endif /* CONFIG_PPC_ICSWX */
if (notify_page_fault(regs))
goto bail;
if (unlikely(debugger_fault_handler(regs)))
goto bail;
/* On a kernel SLB miss we can only check for a valid exception entry */
if (!user_mode(regs) && (address >= TASK_SIZE)) {
rc = SIGSEGV;
goto bail;
}
#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \
defined(CONFIG_PPC_BOOK3S_64))
if (error_code & DSISR_DABRMATCH) {
/* breakpoint match */
do_break(regs, address, error_code);
goto bail;
}
#endif
/* We restore the interrupt state now */
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
if (in_atomic() || mm == NULL) {
if (!user_mode(regs)) {
rc = SIGSEGV;
goto bail;
}
/* in_atomic() in user mode is really bad,
as is current->mm == NULL. */
printk(KERN_EMERG "Page fault in user mode with "
"in_atomic() = %d mm = %p\n", in_atomic(), mm);
printk
|