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
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Persistent Storage - platform driver interface parts.
*
* Copyright (C) 2007-2008 Google, Inc.
* Copyright (C) 2010 Intel Corporation <tony.luck@intel.com>
*/
#define pr_fmt(fmt) "pstore: " fmt
#include <linux/atomic.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/kmsg_dump.h>
#include <linux/console.h>
#include <linux/module.h>
#include <linux/pstore.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/jiffies.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <linux/zlib.h>
#include "internal.h"
/*
* We defer making "oops" entries appear in pstore - see
* whether the system is actually still running well enough
* to let someone see the entry
*/
static int pstore_update_ms = -1;
module_param_named(update_ms, pstore_update_ms, int, 0600);
MODULE_PARM_DESC(update_ms, "milliseconds before pstore updates its content "
"(default is -1, which means runtime updates are disabled; "
"enabling this option may not be safe; it may lead to further "
"corruption on Oopses)");
/* Names should be in the same order as the enum pstore_type_id */
static const char * const pstore_type_names[] = {
"dmesg",
"mce",
"console",
"ftrace",
"rtas",
"powerpc-ofw",
"powerpc-common",
"pmsg",
"powerpc-opal",
};
static int pstore_new_entry;
static void pstore_timefunc(struct timer_list *);
static DEFINE_TIMER(pstore_timer, pstore_timefunc);
static void pstore_dowork(struct work_struct *);
static DECLARE_WORK(pstore_work, pstore_dowork);
/*
* psinfo_lock protects "psinfo" during calls to
* pstore_register(), pstore_unregister(), and
* the filesystem mount/unmount routines.
*/
static DEFINE_MUTEX(psinfo_lock);
struct pstore_info *psinfo;
static char *backend;
module_param(backend, charp, 0444);
MODULE_PARM_DESC(backend, "specific backend to use");
/*
* pstore no longer implements compression via the crypto API, and only
* supports zlib deflate compression implemented using the zlib library
* interface. This removes additional complexity which is hard to justify for a
* diagnostic facility that has to operate in conditions where the system may
* have become unstable. Zlib deflate is comparatively small in terms of code
* size, and compresses ASCII text comparatively well. In terms of compression
* speed, deflate is not the best performer but for recording the log output on
* a kernel panic, this is not considered critical.
*
* The only remaining arguments supported by the compress= module parameter are
* 'deflate' and 'none'. To retain compatibility with existing installations,
* all other values are logged and replaced with 'deflate'.
*/
static char *compress = "deflate";
module_param(compress, charp, 0444);
MODULE_PARM_DESC(compress, "compression to use");
/* How much of the kernel log to snapshot */
unsigned long kmsg_bytes = CONFIG_PSTORE_DEFAULT_KMSG_BYTES;
module_param(kmsg_bytes, ulong, 0444);
MODULE_PARM_DESC(kmsg_bytes, "amount of kernel log to snapshot (in bytes)");
static void *compress_workspace;
static char *big_oops_buf;
void pstore_set_kmsg_bytes(int bytes)
{
kmsg_bytes = bytes;
}
/* Tag each group of saved records with a sequence number */
static int oopscount;
const char *pstore_type_to_name(enum pstore_type_id type)
{
BUILD_BUG_ON(ARRAY_SIZE(pstore_type_names) != PSTORE_TYPE_MAX);
if (WARN_ON_ONCE(type >= PSTORE_TYPE_MAX))
return "unknown";
return pstore_type_names[type];
}
EXPORT_SYMBOL_GPL(pstore_type_to_name);
enum pstore_type_id pstore_name_to_type(const char *name)
{
int i;
for (i = 0; i < PSTORE_TYPE_MAX; i++) {
if (!strcmp(pstore_type_names[i], name))
return i;
}
return PSTORE_TYPE_MAX;
}
EXPORT_SYMBOL_GPL(pstore_name_to_type);
static void pstore_timer_kick(void)
{
if (pstore_update_ms < 0)
return;
mod_timer(&pstore_timer, jiffies + msecs_to_jiffies(pstore_update_ms));
}
static bool pstore_cannot_block_path(enum kmsg_dump_reason reason)
{
/*
* In case of NMI path, pstore shouldn't be blocked
* regardless of reason.
*/
if (in_nmi())
return true;
switch (reason) {
/* In panic case, other cpus are stopped by smp_send_stop(). */
case KMSG_DUMP_PANIC:
/*
* Emergency restart shouldn't be blocked by spinning on
* pstore_info::buf_lock.
*/
case KMSG_DUMP_EMERG:
return true;
default:
return false;
}
}
static int pstore_compress(const void *in, void *out,
unsigned int inlen, unsigned int outlen)
{
struct z_stream_s zstream = {
.next_in = in,
.avail_in = inlen,
.next_out = out,
.avail_out = outlen,
.workspace = compress_workspace,
};
int ret;
if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS))
return -EINVAL;
ret = zlib_deflateInit2(&zstream, Z_DEFAULT_COMPRESSION, Z_DEFLATED,
-MAX_WBITS, DEF_MEM_LEVEL, Z_DEFAULT_STRATEGY);
if (ret != Z_OK)
return -EINVAL;
ret = zlib_deflate(&zstream, Z_FINISH);
if (ret != Z_STREAM_END)
return -EINVAL;
ret = zlib_deflateEnd(&zstream);
if (ret != Z_OK)
pr_warn_once("zlib_deflateEnd() failed: %d\n", ret);
return zstream.total_out;
}
static void allocate_buf_for_compression(void)
{
char *buf;
/* Skip if not built-in or compression disabled. */
if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !compress ||
!strcmp(compress, "none")) {
compress = NULL;
return;
}
if (strcmp(compress, "deflate")) {
pr_err("Unsupported compression '%s', falling back to deflate\n",
compress);
compress = "deflate";
}
/*
* The compression buffer only needs to be as large as the maximum
* uncompressed record size, since any record that would be expanded by
* compression is just stored uncompressed.
*/
buf = kmalloc(psinfo->bufsize, GFP_KERNEL);
if (!buf) {
pr_err("Failed %zu byte compression buffer allocation for: %s\n",
psinfo->bufsize, compress);
return;
}
compress_workspace =
vmalloc(zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL));
if (!compress_workspace) {
pr_err("Failed to allocate zlib deflate workspace\n");
kfree(buf);
return;
}
/* A non-NULL big_oops_buf indicates compression is available. */
big_oops_buf = buf;
pr_info("Using crash dump compression: %s\n", compress);
}
static void free_buf_for_compression(void)
{
if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && compress_workspace) {
vfree(compress_workspace);
compress_workspace = NULL;
}
kfree(big_oops_buf);
big_oops_buf = NULL;
}
void pstore_record_init(struct pstore_record *record,
struct pstore_info *psinfo)
{
memset(record, 0, sizeof(*record));
record->psi = psinfo;
/* Report zeroed timestamp if called before timekeeping has resumed. */
record->time = ns_to_timespec64(ktime_get_real_fast_ns());
}
/*
* callback from kmsg_dump. Save as much as we can (up to kmsg_bytes) from the
* end of the buffer.
*/
static void pstore_dump(struct kmsg_dumper *dumper,
enum kmsg_dump_reason reason)
{
struct kmsg_dump_iter iter;
unsigned long total = 0;
const char *why;
unsigned int part = 1;
unsigned long flags = 0;
int saved_ret = 0;
int ret;
why = kmsg_dump_reason_str(reason);
if (pstore_cannot_block_path(reason)) {
if (!spin_trylock_irqsave(&psinfo->buf_lock, flags)) {
pr_err("dump skipped in %s path because of concurrent dump\n",
in_nmi() ? "NMI" : why);
return;
}
} else {
spin_lock_irqsave(&psinfo->buf_lock, flags);
}
kmsg_dump_rewind(&iter);
oopscount++;
while (total < kmsg_bytes) {
char *dst;
size_t dst_size;
int header_size;
int zipped_len = -1;
size_t dump_size;
struct pstore_record record;
pstore_record_init(&record, psinfo);
record.type = PSTORE_TYPE_DMESG;
record.count = oopscount;
record.reason = reason;
record.part = part;
record.buf = psinfo->buf;
dst = big_oops_buf ?: psinfo->buf;
dst_size = psinfo->bufsize;
/* Write dump header. */
header_size = snprintf(dst, dst_size, "%s#%d Part%u\n", why,
oopscount, part);
dst_size -= header_size;
/* Write dump contents. */
if (!kmsg_dump_get_buffer(&iter, true, dst + header_size,
dst_size, &dump_size))
break;
if (big_oops_buf) {
zipped_len = pstore_compress(dst, psinfo->buf,
header_size + dump_size,
psinfo->bufsize);
if (zipped_len > 0) {
record.compressed = true;
record.size = zipped_len;
} else {
record.size = header_size + dump_size;
memcpy(psinfo->buf, dst, record.size);
}
} else {
record.size = header_size + dump_size;
}
ret = psinfo->write(&record);
if (ret == 0 && reason == KMSG_DUMP_OOPS) {
pstore_new_entry = 1;
pstore_timer_kick();
} else {
/* Preserve only the first non-zero returned value. */
if (!saved_ret)
saved_ret = ret;
}
total += record.size;
part++;
}
spin_unlock_irqrestore(&psinfo->buf_lock, flags);
if (saved_ret) {
pr_err_once("backend (%s) writing error (%d)\n", psinfo->name,
saved_ret);
}
}
static struct kmsg_dumper pstore_dumper = {
.dump = pstore_dump,
};
/*
* Register with kmsg_dump to save last part of console log on panic.
*/
static void pstore_register_kmsg(void)
{
kmsg_dump_register(&pstore_dumper);
}
static void pstore_unregister_kmsg(void)
{
kmsg_dump_unregister(&pstore_dumper);
}
#ifdef CONFIG_PSTORE_CONSOLE
static void pstore_console_write(struct console *con, const char *s, unsigned c)
{
struct pstore_record record;
if (!c)
return;
pstore_record_init(&record, psinfo);
record.type = PSTORE_TYPE_CONSOLE;
record.buf = (char *)s;
record.size = c;
psinfo->write(&record);
}
static struct console pstore_console = {
.write = pstore_console_write,
.index = -1,
};
static void pstore_register_console(void)
{
/* Show which backend is going to get console writes. */
strscpy(pstore_console.name, psinfo->name,
sizeof(pstore_console.name));
/*
* Always initialize flags here since prior unregister_console()
* calls may have changed settings (specifically CON_ENABLED).
*/
pstore_console.flags = CON_PRINTBUFFER | CON_ENABLED | CON_ANYTIME;
register_console(&pstore_console);
}
static void pstore_unregister_console(void)
{
unregister_console(&pstore_console);
}
#else
static void pstore_register_console(void) {}
static void pstore_unregister_console(void) {}
#endif
static int pstore_write_user_compat(struct pstore_record *record,
const char __user *buf)
{
int ret = 0;
if (record->buf)
return -EINVAL;
record->buf = memdup_user(buf, record->size);
if (IS_ERR(record->buf)) {
ret = PTR_ERR(record->buf);
goto out;
}
ret = record->psi->write(record);
kfree(record->buf);
out:
record->buf = NULL;
return unlikely(ret < 0) ? ret : record->size;
}
/*
* platform specific persistent storage driver registers with
* us here. If pstore is already mounted, call the platform
* read function right away to populate the file system. If not
* then the pstore mount code will call us later to fill out
* the file system.
*/
int pstore_register(struct pstore_info *psi)
{
if (backend && strcmp(backend, psi->name)) {
pr_warn("backend '%s' already in use: ignoring '%s'\n",
backend, psi->name);
return -EBUSY;
}
/* Sanity check flags. */
if (!psi->flags) {
pr_warn("backend '%s' must support at least one frontend\n",
psi->name);
return -EINVAL;
}
/* Check for required functions. */
if (!psi->read || !psi->write) {
pr_warn("backend '%s' must implement read() and write()\n",
psi->name);
return -EINVAL;
}
mutex_lock(&psinfo_lock);
if (psinfo) {
pr_warn("backend '%s' already loaded: ignoring '%s'\n",
psinfo->name, psi->name);
mutex_unlock(&psinfo_lock);
return -EBUSY;
}
if (!psi->write_user)
psi->write_user = pstore_write_user_compat;
psinfo = psi;
mutex_init(&psinfo->read_mutex);
spin_lock_init(&psinfo->buf_lock);
if (psi->flags & PSTORE_FLAGS_DMESG)
allocate_buf_for_compression();
pstore_get_records(0);
if (psi->flags & PSTORE_FLAGS_DMESG) {
pstore_dumper.max_reason = psinfo->max_reason;
pstore_register_kmsg();
}
if (psi->flags & PSTORE_FLAGS_CONSOLE)
pstore_register_console();
if (psi->flags & PSTORE_FLAGS_FTRACE)
pstore_register_ftrace();
if (psi->flags & PSTORE_FLAGS_PMSG)
pstore_register_pmsg();
/* Start watching for new records, if desired. */
pstore_timer_kick();
/*
* Update the module parameter backend, so it is visible
* through /sys/module/pstore/parameters/backend
*/
backend = kstrdup(psi->name, GFP_KERNEL);
pr_info("Registered %s as persistent store backend\n", psi->name);
mutex_unlock(&psinfo_lock);
return 0;
}
EXPORT_SYMBOL_GPL(pstore_register);
void pstore_unregister(struct pstore_info *psi)
{
/* It's okay to unregister nothing. */
if (!psi)
return;
mutex_lock(&psinfo_lock);
/* Only one backend can be registered at a time. */
if (WARN_ON(psi != psinfo)) {
mutex_unlock(&psinfo_lock);
return;
}
/* Unregister all callbacks. */
if (psi->flags & PSTORE_FLAGS_PMSG)
pstore_unregister_pmsg();
if (psi->flags & PSTORE_FLAGS_FTRACE)
pstore_unregister_ftrace();
if (psi->flags & PSTORE_FLAGS_CONSOLE)
pstore_unregister_console();
if (psi->flags & PSTORE_FLAGS_DMESG)
pstore_unregister_kmsg();
/* Stop timer and make sure all work has finished. */
del_timer_sync(&pstore_timer);
flush_work(&pstore_work);
/* Remove all backend records from filesystem tree. */
pstore_put_backend_records(psi);
free_buf_for_compression();
psinfo = NULL;
kfree(backend);
backend = NULL;
pr_info("Unregistered %s as persistent store backend\n", psi->name);
mutex_unlock(&psinfo_lock);
}
EXPORT_SYMBOL_GPL(pstore_unregister);
static void decompress_record(struct pstore_record *record,
struct z_stream_s *zstream)
{
int ret;
int unzipped_len;
char *unzipped, *workspace;
if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed)
return;
/* Only PSTORE_TYPE_DMESG support compression. */
if (record->type != PSTORE_TYPE_DMESG) {
pr_warn("ignored compressed record type %d\n", record->type);
return;
}
/* Missing compression buffer means compression was not initialized. */
if (!zstream->workspace) {
pr_warn("no decompression method initialized!\n");
return;
}
ret = zlib_inflateReset(zstream);
if (ret != Z_OK) {
pr_err("zlib_inflateReset() failed, ret = %d!\n", ret);
return;
}
/* Allocate enough space to hold max decompression and ECC. */
workspace = kmalloc(psinfo->bufsize + record->ecc_notice_size,
GFP_KERNEL);
if (!workspace)
return;
zstream->next_in = record->buf;
zstream->avail_in = record->size;
zstream->next_out = workspace;
zstream->avail_out = psinfo->bufsize;
ret = zlib_inflate(zstream, Z_FINISH);
if (ret != Z_STREAM_END) {
pr_err("zlib_inflate() failed, ret = %d!\n", ret);
kfree(workspace);
return;
}
unzipped_len = zstream->total_out;
/* Append ECC notice to decompressed buffer. */
memcpy(workspace + unzipped_len, record->buf + record->size,
record->ecc_notice_size);
/* Copy decompressed contents into an minimum-sized allocation. */
unzipped = kmemdup(workspace, unzipped_len + record->ecc_notice_size,
GFP_KERNEL);
kfree(workspace);
if (!unzipped)
return;
/* Swap out compressed contents with decompressed contents. */
kfree(record->buf);
record->buf = unzipped;
record->size = unzipped_len;
record->compressed = false;
}
/*
* Read all the records from one persistent store backend. Create
* files in our filesystem. Don't warn about -EEXIST errors
* when we are re-scanning the backing store looking to add new
* error records.
*/
void pstore_get_backend_records(struct pstore_info *psi,
struct dentry *root, int quiet)
{
int failed = 0;
unsigned int stop_loop = 65536;
struct z_stream_s zstream = {};
if (!psi || !root)
return;
if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && compress) {
zstream.workspace = kvmalloc(zlib_inflate_workspacesize(),
GFP_KERNEL);
zlib_inflateInit2(&zstream, -DEF_WBITS);
}
mutex_lock(&psi->read_mutex);
if (psi->open && psi->open(psi))
goto out;
/*
* Backend callback read() allocates record.buf. decompress_record()
* may reallocate record.buf. On success, pstore_mkfile() will keep
* the record.buf, so free it only on failure.
*/
for (; stop_loop; stop_loop--) {
struct pstore_record *record;
int rc;
record = kzalloc(sizeof(*record), GFP_KERNEL);
if (!record) {
pr_err("out of memory creating record\n");
break;
}
pstore_record_init(record, psi);
record->size = psi->read(record);
/* No more records left in backend? */
if (record->size <= 0) {
kfree(record);
break;
}
decompress_record(record, &zstream);
rc = pstore_mkfile(root, record);
if (rc) {
/* pstore_mkfile() did not take record, so free it. */
kfree(record->buf);
kfree(record->priv);
kfree(record);
if (rc != -EEXIST || !quiet)
failed++;
}
}
if (psi->close)
psi->close(psi);
out:
mutex_unlock(&psi->read_mutex);
if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && compress) {
if (zlib_inflateEnd(&zstream) != Z_OK)
pr_warn("zlib_inflateEnd() failed\n");
kvfree(zstream.workspace);
}
if (failed)
pr_warn("failed to create %d record(s) from '%s'\n",
failed, psi->name);
if (!stop_loop)
pr_err("looping? Too many records seen from '%s'\n",
psi->name);
}
static void pstore_dowork(struct work_struct *work)
{
pstore_get_records(1);
}
static void pstore_timefunc(struct timer_list *unused)
{
if (pstore_new_entry) {
pstore_new_entry = 0;
schedule_work(&pstore_work);
}
pstore_timer_kick();
}
static int __init pstore_init(void)
{
int ret;
ret = pstore_init_fs();
if (ret)
free_buf_for_compression();
return ret;
}
late_initcall(pstore_init);
static void __exit pstore_exit(void)
{
pstore_exit_fs();
}
module_exit(pstore_exit)
MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>");
MODULE_LICENSE("GPL");
|