forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
zone.c
1468 lines (1267 loc) · 35.4 KB
/
zone.c
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
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0
/*
* Provide a pstore intermediate backend, organized into kernel memory
* allocated zones that are then mapped and flushed into a single
* contiguous region on a storage backend of some kind (block, mtd, etc).
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/printk.h>
#include <linux/fs.h>
#include <linux/pstore_zone.h>
#include <linux/kdev_t.h>
#include <linux/device.h>
#include <linux/namei.h>
#include <linux/fcntl.h>
#include <linux/uio.h>
#include <linux/writeback.h>
#include "internal.h"
/**
* struct psz_buffer - header of zone to flush to storage
*
* @sig: signature to indicate header (PSZ_SIG xor PSZONE-type value)
* @datalen: length of data in @data
* @start: offset into @data where the beginning of the stored bytes begin
* @data: zone data.
*/
struct psz_buffer {
#define PSZ_SIG (0x43474244) /* DBGC */
uint32_t sig;
atomic_t datalen;
atomic_t start;
uint8_t data[];
};
/**
* struct psz_kmsg_header - kmsg dump-specific header to flush to storage
*
* @magic: magic num for kmsg dump header
* @time: kmsg dump trigger time
* @compressed: whether conpressed
* @counter: kmsg dump counter
* @reason: the kmsg dump reason (e.g. oops, panic, etc)
* @data: pointer to log data
*
* This is a sub-header for a kmsg dump, trailing after &psz_buffer.
*/
struct psz_kmsg_header {
#define PSTORE_KMSG_HEADER_MAGIC 0x4dfc3ae5 /* Just a random number */
uint32_t magic;
struct timespec64 time;
bool compressed;
uint32_t counter;
enum kmsg_dump_reason reason;
uint8_t data[];
};
/**
* struct pstore_zone - single stored buffer
*
* @off: zone offset of storage
* @type: front-end type for this zone
* @name: front-end name for this zone
* @buffer: pointer to data buffer managed by this zone
* @oldbuf: pointer to old data buffer
* @buffer_size: bytes in @buffer->data
* @should_recover: whether this zone should recover from storage
* @dirty: whether the data in @buffer dirty
*
* zone structure in memory.
*/
struct pstore_zone {
loff_t off;
const char *name;
enum pstore_type_id type;
struct psz_buffer *buffer;
struct psz_buffer *oldbuf;
size_t buffer_size;
bool should_recover;
atomic_t dirty;
};
/**
* struct psz_context - all about running state of pstore/zone
*
* @kpszs: kmsg dump storage zones
* @ppsz: pmsg storage zone
* @cpsz: console storage zone
* @fpszs: ftrace storage zones
* @kmsg_max_cnt: max count of @kpszs
* @kmsg_read_cnt: counter of total read kmsg dumps
* @kmsg_write_cnt: counter of total kmsg dump writes
* @pmsg_read_cnt: counter of total read pmsg zone
* @console_read_cnt: counter of total read console zone
* @ftrace_max_cnt: max count of @fpszs
* @ftrace_read_cnt: counter of max read ftrace zone
* @oops_counter: counter of oops dumps
* @panic_counter: counter of panic dumps
* @recovered: whether finished recovering data from storage
* @on_panic: whether panic is happening
* @pstore_zone_info_lock: lock to @pstore_zone_info
* @pstore_zone_info: information from backend
* @pstore: structure for pstore
*/
struct psz_context {
struct pstore_zone **kpszs;
struct pstore_zone *ppsz;
struct pstore_zone *cpsz;
struct pstore_zone **fpszs;
unsigned int kmsg_max_cnt;
unsigned int kmsg_read_cnt;
unsigned int kmsg_write_cnt;
unsigned int pmsg_read_cnt;
unsigned int console_read_cnt;
unsigned int ftrace_max_cnt;
unsigned int ftrace_read_cnt;
/*
* These counters should be calculated during recovery.
* It records the oops/panic times after crashes rather than boots.
*/
unsigned int oops_counter;
unsigned int panic_counter;
atomic_t recovered;
atomic_t on_panic;
/*
* pstore_zone_info_lock protects this entire structure during calls
* to register_pstore_zone()/unregister_pstore_zone().
*/
struct mutex pstore_zone_info_lock;
struct pstore_zone_info *pstore_zone_info;
struct pstore_info pstore;
};
static struct psz_context pstore_zone_cxt;
static void psz_flush_all_dirty_zones(struct work_struct *);
static DECLARE_DELAYED_WORK(psz_cleaner, psz_flush_all_dirty_zones);
/**
* enum psz_flush_mode - flush mode for psz_zone_write()
*
* @FLUSH_NONE: do not flush to storage but update data on memory
* @FLUSH_PART: just flush part of data including meta data to storage
* @FLUSH_META: just flush meta data of zone to storage
* @FLUSH_ALL: flush all of zone
*/
enum psz_flush_mode {
FLUSH_NONE = 0,
FLUSH_PART,
FLUSH_META,
FLUSH_ALL,
};
static inline int buffer_datalen(struct pstore_zone *zone)
{
return atomic_read(&zone->buffer->datalen);
}
static inline int buffer_start(struct pstore_zone *zone)
{
return atomic_read(&zone->buffer->start);
}
static inline bool is_on_panic(void)
{
return atomic_read(&pstore_zone_cxt.on_panic);
}
static ssize_t psz_zone_read_buffer(struct pstore_zone *zone, char *buf,
size_t len, unsigned long off)
{
if (!buf || !zone || !zone->buffer)
return -EINVAL;
if (off > zone->buffer_size)
return -EINVAL;
len = min_t(size_t, len, zone->buffer_size - off);
memcpy(buf, zone->buffer->data + off, len);
return len;
}
static int psz_zone_read_oldbuf(struct pstore_zone *zone, char *buf,
size_t len, unsigned long off)
{
if (!buf || !zone || !zone->oldbuf)
return -EINVAL;
if (off > zone->buffer_size)
return -EINVAL;
len = min_t(size_t, len, zone->buffer_size - off);
memcpy(buf, zone->oldbuf->data + off, len);
return 0;
}
static int psz_zone_write(struct pstore_zone *zone,
enum psz_flush_mode flush_mode, const char *buf,
size_t len, unsigned long off)
{
struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info;
ssize_t wcnt = 0;
ssize_t (*writeop)(const char *buf, size_t bytes, loff_t pos);
size_t wlen;
if (off > zone->buffer_size)
return -EINVAL;
wlen = min_t(size_t, len, zone->buffer_size - off);
if (buf && wlen) {
memcpy(zone->buffer->data + off, buf, wlen);
atomic_set(&zone->buffer->datalen, wlen + off);
}
/* avoid to damage old records */
if (!is_on_panic() && !atomic_read(&pstore_zone_cxt.recovered))
goto dirty;
writeop = is_on_panic() ? info->panic_write : info->write;
if (!writeop)
goto dirty;
switch (flush_mode) {
case FLUSH_NONE:
if (unlikely(buf && wlen))
goto dirty;
return 0;
case FLUSH_PART:
wcnt = writeop((const char *)zone->buffer->data + off, wlen,
zone->off + sizeof(*zone->buffer) + off);
if (wcnt != wlen)
goto dirty;
fallthrough;
case FLUSH_META:
wlen = sizeof(struct psz_buffer);
wcnt = writeop((const char *)zone->buffer, wlen, zone->off);
if (wcnt != wlen)
goto dirty;
break;
case FLUSH_ALL:
wlen = zone->buffer_size + sizeof(*zone->buffer);
wcnt = writeop((const char *)zone->buffer, wlen, zone->off);
if (wcnt != wlen)
goto dirty;
break;
}
return 0;
dirty:
/* no need to mark dirty if going to try next zone */
if (wcnt == -ENOMSG)
return -ENOMSG;
atomic_set(&zone->dirty, true);
/* flush dirty zones nicely */
if (wcnt == -EBUSY && !is_on_panic())
schedule_delayed_work(&psz_cleaner, msecs_to_jiffies(500));
return -EBUSY;
}
static int psz_flush_dirty_zone(struct pstore_zone *zone)
{
int ret;
if (unlikely(!zone))
return -EINVAL;
if (unlikely(!atomic_read(&pstore_zone_cxt.recovered)))
return -EBUSY;
if (!atomic_xchg(&zone->dirty, false))
return 0;
ret = psz_zone_write(zone, FLUSH_ALL, NULL, 0, 0);
if (ret)
atomic_set(&zone->dirty, true);
return ret;
}
static int psz_flush_dirty_zones(struct pstore_zone **zones, unsigned int cnt)
{
int i, ret;
struct pstore_zone *zone;
if (!zones)
return -EINVAL;
for (i = 0; i < cnt; i++) {
zone = zones[i];
if (!zone)
return -EINVAL;
ret = psz_flush_dirty_zone(zone);
if (ret)
return ret;
}
return 0;
}
static int psz_move_zone(struct pstore_zone *old, struct pstore_zone *new)
{
const char *data = (const char *)old->buffer->data;
int ret;
ret = psz_zone_write(new, FLUSH_ALL, data, buffer_datalen(old), 0);
if (ret) {
atomic_set(&new->buffer->datalen, 0);
atomic_set(&new->dirty, false);
return ret;
}
atomic_set(&old->buffer->datalen, 0);
return 0;
}
static void psz_flush_all_dirty_zones(struct work_struct *work)
{
struct psz_context *cxt = &pstore_zone_cxt;
int ret = 0;
if (cxt->ppsz)
ret |= psz_flush_dirty_zone(cxt->ppsz);
if (cxt->cpsz)
ret |= psz_flush_dirty_zone(cxt->cpsz);
if (cxt->kpszs)
ret |= psz_flush_dirty_zones(cxt->kpszs, cxt->kmsg_max_cnt);
if (cxt->fpszs)
ret |= psz_flush_dirty_zones(cxt->fpszs, cxt->ftrace_max_cnt);
if (ret && cxt->pstore_zone_info)
schedule_delayed_work(&psz_cleaner, msecs_to_jiffies(1000));
}
static int psz_kmsg_recover_data(struct psz_context *cxt)
{
struct pstore_zone_info *info = cxt->pstore_zone_info;
struct pstore_zone *zone = NULL;
struct psz_buffer *buf;
unsigned long i;
ssize_t rcnt;
if (!info->read)
return -EINVAL;
for (i = 0; i < cxt->kmsg_max_cnt; i++) {
zone = cxt->kpszs[i];
if (unlikely(!zone))
return -EINVAL;
if (atomic_read(&zone->dirty)) {
unsigned int wcnt = cxt->kmsg_write_cnt;
struct pstore_zone *new = cxt->kpszs[wcnt];
int ret;
ret = psz_move_zone(zone, new);
if (ret) {
pr_err("move zone from %lu to %d failed\n",
i, wcnt);
return ret;
}
cxt->kmsg_write_cnt = (wcnt + 1) % cxt->kmsg_max_cnt;
}
if (!zone->should_recover)
continue;
buf = zone->buffer;
rcnt = info->read((char *)buf, zone->buffer_size + sizeof(*buf),
zone->off);
if (rcnt != zone->buffer_size + sizeof(*buf))
return (int)rcnt < 0 ? (int)rcnt : -EIO;
}
return 0;
}
static int psz_kmsg_recover_meta(struct psz_context *cxt)
{
struct pstore_zone_info *info = cxt->pstore_zone_info;
struct pstore_zone *zone;
size_t rcnt, len;
struct psz_buffer *buf;
struct psz_kmsg_header *hdr;
struct timespec64 time = { };
unsigned long i;
/*
* Recover may on panic, we can't allocate any memory by kmalloc.
* So, we use local array instead.
*/
char buffer_header[sizeof(*buf) + sizeof(*hdr)] = {0};
if (!info->read)
return -EINVAL;
len = sizeof(*buf) + sizeof(*hdr);
buf = (struct psz_buffer *)buffer_header;
for (i = 0; i < cxt->kmsg_max_cnt; i++) {
zone = cxt->kpszs[i];
if (unlikely(!zone))
return -EINVAL;
rcnt = info->read((char *)buf, len, zone->off);
if (rcnt == -ENOMSG) {
pr_debug("%s with id %lu may be broken, skip\n",
zone->name, i);
continue;
} else if (rcnt != len) {
pr_err("read %s with id %lu failed\n", zone->name, i);
return (int)rcnt < 0 ? (int)rcnt : -EIO;
}
if (buf->sig != zone->buffer->sig) {
pr_debug("no valid data in kmsg dump zone %lu\n", i);
continue;
}
if (zone->buffer_size < atomic_read(&buf->datalen)) {
pr_info("found overtop zone: %s: id %lu, off %lld, size %zu\n",
zone->name, i, zone->off,
zone->buffer_size);
continue;
}
hdr = (struct psz_kmsg_header *)buf->data;
if (hdr->magic != PSTORE_KMSG_HEADER_MAGIC) {
pr_info("found invalid zone: %s: id %lu, off %lld, size %zu\n",
zone->name, i, zone->off,
zone->buffer_size);
continue;
}
/*
* we get the newest zone, and the next one must be the oldest
* or unused zone, because we do write one by one like a circle.
*/
if (hdr->time.tv_sec >= time.tv_sec) {
time.tv_sec = hdr->time.tv_sec;
cxt->kmsg_write_cnt = (i + 1) % cxt->kmsg_max_cnt;
}
if (hdr->reason == KMSG_DUMP_OOPS)
cxt->oops_counter =
max(cxt->oops_counter, hdr->counter);
else if (hdr->reason == KMSG_DUMP_PANIC)
cxt->panic_counter =
max(cxt->panic_counter, hdr->counter);
if (!atomic_read(&buf->datalen)) {
pr_debug("found erased zone: %s: id %lu, off %lld, size %zu, datalen %d\n",
zone->name, i, zone->off,
zone->buffer_size,
atomic_read(&buf->datalen));
continue;
}
if (!is_on_panic())
zone->should_recover = true;
pr_debug("found nice zone: %s: id %lu, off %lld, size %zu, datalen %d\n",
zone->name, i, zone->off,
zone->buffer_size, atomic_read(&buf->datalen));
}
return 0;
}
static int psz_kmsg_recover(struct psz_context *cxt)
{
int ret;
if (!cxt->kpszs)
return 0;
ret = psz_kmsg_recover_meta(cxt);
if (ret)
goto recover_fail;
ret = psz_kmsg_recover_data(cxt);
if (ret)
goto recover_fail;
return 0;
recover_fail:
pr_debug("psz_recover_kmsg failed\n");
return ret;
}
static int psz_recover_zone(struct psz_context *cxt, struct pstore_zone *zone)
{
struct pstore_zone_info *info = cxt->pstore_zone_info;
struct psz_buffer *oldbuf, tmpbuf;
int ret = 0;
char *buf;
ssize_t rcnt, len, start, off;
if (!zone || zone->oldbuf)
return 0;
if (is_on_panic()) {
/* save data as much as possible */
psz_flush_dirty_zone(zone);
return 0;
}
if (unlikely(!info->read))
return -EINVAL;
len = sizeof(struct psz_buffer);
rcnt = info->read((char *)&tmpbuf, len, zone->off);
if (rcnt != len) {
pr_debug("read zone %s failed\n", zone->name);
return (int)rcnt < 0 ? (int)rcnt : -EIO;
}
if (tmpbuf.sig != zone->buffer->sig) {
pr_debug("no valid data in zone %s\n", zone->name);
return 0;
}
if (zone->buffer_size < atomic_read(&tmpbuf.datalen) ||
zone->buffer_size < atomic_read(&tmpbuf.start)) {
pr_info("found overtop zone: %s: off %lld, size %zu\n",
zone->name, zone->off, zone->buffer_size);
/* just keep going */
return 0;
}
if (!atomic_read(&tmpbuf.datalen)) {
pr_debug("found erased zone: %s: off %lld, size %zu, datalen %d\n",
zone->name, zone->off, zone->buffer_size,
atomic_read(&tmpbuf.datalen));
return 0;
}
pr_debug("found nice zone: %s: off %lld, size %zu, datalen %d\n",
zone->name, zone->off, zone->buffer_size,
atomic_read(&tmpbuf.datalen));
len = atomic_read(&tmpbuf.datalen) + sizeof(*oldbuf);
oldbuf = kzalloc(len, GFP_KERNEL);
if (!oldbuf)
return -ENOMEM;
memcpy(oldbuf, &tmpbuf, sizeof(*oldbuf));
buf = (char *)oldbuf + sizeof(*oldbuf);
len = atomic_read(&oldbuf->datalen);
start = atomic_read(&oldbuf->start);
off = zone->off + sizeof(*oldbuf);
/* get part of data */
rcnt = info->read(buf, len - start, off + start);
if (rcnt != len - start) {
pr_err("read zone %s failed\n", zone->name);
ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
goto free_oldbuf;
}
/* get the rest of data */
rcnt = info->read(buf + len - start, start, off);
if (rcnt != start) {
pr_err("read zone %s failed\n", zone->name);
ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
goto free_oldbuf;
}
zone->oldbuf = oldbuf;
psz_flush_dirty_zone(zone);
return 0;
free_oldbuf:
kfree(oldbuf);
return ret;
}
static int psz_recover_zones(struct psz_context *cxt,
struct pstore_zone **zones, unsigned int cnt)
{
int ret;
unsigned int i;
struct pstore_zone *zone;
if (!zones)
return 0;
for (i = 0; i < cnt; i++) {
zone = zones[i];
if (unlikely(!zone))
continue;
ret = psz_recover_zone(cxt, zone);
if (ret)
goto recover_fail;
}
return 0;
recover_fail:
pr_debug("recover %s[%u] failed\n", zone->name, i);
return ret;
}
/**
* psz_recovery() - recover data from storage
* @cxt: the context of pstore/zone
*
* recovery means reading data back from storage after rebooting
*
* Return: 0 on success, others on failure.
*/
static inline int psz_recovery(struct psz_context *cxt)
{
int ret;
if (atomic_read(&cxt->recovered))
return 0;
ret = psz_kmsg_recover(cxt);
if (ret)
goto out;
ret = psz_recover_zone(cxt, cxt->ppsz);
if (ret)
goto out;
ret = psz_recover_zone(cxt, cxt->cpsz);
if (ret)
goto out;
ret = psz_recover_zones(cxt, cxt->fpszs, cxt->ftrace_max_cnt);
out:
if (unlikely(ret))
pr_err("recover failed\n");
else {
pr_debug("recover end!\n");
atomic_set(&cxt->recovered, 1);
}
return ret;
}
static int psz_pstore_open(struct pstore_info *psi)
{
struct psz_context *cxt = psi->data;
cxt->kmsg_read_cnt = 0;
cxt->pmsg_read_cnt = 0;
cxt->console_read_cnt = 0;
cxt->ftrace_read_cnt = 0;
return 0;
}
static inline bool psz_old_ok(struct pstore_zone *zone)
{
if (zone && zone->oldbuf && atomic_read(&zone->oldbuf->datalen))
return true;
return false;
}
static inline bool psz_ok(struct pstore_zone *zone)
{
if (zone && zone->buffer && buffer_datalen(zone))
return true;
return false;
}
static inline int psz_kmsg_erase(struct psz_context *cxt,
struct pstore_zone *zone, struct pstore_record *record)
{
struct psz_buffer *buffer = zone->buffer;
struct psz_kmsg_header *hdr =
(struct psz_kmsg_header *)buffer->data;
size_t size;
if (unlikely(!psz_ok(zone)))
return 0;
/* this zone is already updated, no need to erase */
if (record->count != hdr->counter)
return 0;
size = buffer_datalen(zone) + sizeof(*zone->buffer);
atomic_set(&zone->buffer->datalen, 0);
if (cxt->pstore_zone_info->erase)
return cxt->pstore_zone_info->erase(size, zone->off);
else
return psz_zone_write(zone, FLUSH_META, NULL, 0, 0);
}
static inline int psz_record_erase(struct psz_context *cxt,
struct pstore_zone *zone)
{
if (unlikely(!psz_old_ok(zone)))
return 0;
kfree(zone->oldbuf);
zone->oldbuf = NULL;
/*
* if there are new data in zone buffer, that means the old data
* are already invalid. It is no need to flush 0 (erase) to
* block device.
*/
if (!buffer_datalen(zone))
return psz_zone_write(zone, FLUSH_META, NULL, 0, 0);
psz_flush_dirty_zone(zone);
return 0;
}
static int psz_pstore_erase(struct pstore_record *record)
{
struct psz_context *cxt = record->psi->data;
switch (record->type) {
case PSTORE_TYPE_DMESG:
if (record->id >= cxt->kmsg_max_cnt)
return -EINVAL;
return psz_kmsg_erase(cxt, cxt->kpszs[record->id], record);
case PSTORE_TYPE_PMSG:
return psz_record_erase(cxt, cxt->ppsz);
case PSTORE_TYPE_CONSOLE:
return psz_record_erase(cxt, cxt->cpsz);
case PSTORE_TYPE_FTRACE:
if (record->id >= cxt->ftrace_max_cnt)
return -EINVAL;
return psz_record_erase(cxt, cxt->fpszs[record->id]);
default: return -EINVAL;
}
}
static void psz_write_kmsg_hdr(struct pstore_zone *zone,
struct pstore_record *record)
{
struct psz_context *cxt = record->psi->data;
struct psz_buffer *buffer = zone->buffer;
struct psz_kmsg_header *hdr =
(struct psz_kmsg_header *)buffer->data;
hdr->magic = PSTORE_KMSG_HEADER_MAGIC;
hdr->compressed = record->compressed;
hdr->time.tv_sec = record->time.tv_sec;
hdr->time.tv_nsec = record->time.tv_nsec;
hdr->reason = record->reason;
if (hdr->reason == KMSG_DUMP_OOPS)
hdr->counter = ++cxt->oops_counter;
else if (hdr->reason == KMSG_DUMP_PANIC)
hdr->counter = ++cxt->panic_counter;
else
hdr->counter = 0;
}
/*
* In case zone is broken, which may occur to MTD device, we try each zones,
* start at cxt->kmsg_write_cnt.
*/
static inline int notrace psz_kmsg_write_record(struct psz_context *cxt,
struct pstore_record *record)
{
size_t size, hlen;
struct pstore_zone *zone;
unsigned int i;
for (i = 0; i < cxt->kmsg_max_cnt; i++) {
unsigned int zonenum, len;
int ret;
zonenum = (cxt->kmsg_write_cnt + i) % cxt->kmsg_max_cnt;
zone = cxt->kpszs[zonenum];
if (unlikely(!zone))
return -ENOSPC;
/* avoid destroying old data, allocate a new one */
len = zone->buffer_size + sizeof(*zone->buffer);
zone->oldbuf = zone->buffer;
zone->buffer = kzalloc(len, GFP_KERNEL);
if (!zone->buffer) {
zone->buffer = zone->oldbuf;
return -ENOMEM;
}
zone->buffer->sig = zone->oldbuf->sig;
pr_debug("write %s to zone id %d\n", zone->name, zonenum);
psz_write_kmsg_hdr(zone, record);
hlen = sizeof(struct psz_kmsg_header);
size = min_t(size_t, record->size, zone->buffer_size - hlen);
ret = psz_zone_write(zone, FLUSH_ALL, record->buf, size, hlen);
if (likely(!ret || ret != -ENOMSG)) {
cxt->kmsg_write_cnt = zonenum + 1;
cxt->kmsg_write_cnt %= cxt->kmsg_max_cnt;
/* no need to try next zone, free last zone buffer */
kfree(zone->oldbuf);
zone->oldbuf = NULL;
return ret;
}
pr_debug("zone %u may be broken, try next dmesg zone\n",
zonenum);
kfree(zone->buffer);
zone->buffer = zone->oldbuf;
zone->oldbuf = NULL;
}
return -EBUSY;
}
static int notrace psz_kmsg_write(struct psz_context *cxt,
struct pstore_record *record)
{
int ret;
/*
* Explicitly only take the first part of any new crash.
* If our buffer is larger than kmsg_bytes, this can never happen,
* and if our buffer is smaller than kmsg_bytes, we don't want the
* report split across multiple records.
*/
if (record->part != 1)
return -ENOSPC;
if (!cxt->kpszs)
return -ENOSPC;
ret = psz_kmsg_write_record(cxt, record);
if (!ret && is_on_panic()) {
/* ensure all data are flushed to storage when panic */
pr_debug("try to flush other dirty zones\n");
psz_flush_all_dirty_zones(NULL);
}
/* always return 0 as we had handled it on buffer */
return 0;
}
static int notrace psz_record_write(struct pstore_zone *zone,
struct pstore_record *record)
{
size_t start, rem;
bool is_full_data = false;
char *buf;
int cnt;
if (!zone || !record)
return -ENOSPC;
if (atomic_read(&zone->buffer->datalen) >= zone->buffer_size)
is_full_data = true;
cnt = record->size;
buf = record->buf;
if (unlikely(cnt > zone->buffer_size)) {
buf += cnt - zone->buffer_size;
cnt = zone->buffer_size;
}
start = buffer_start(zone);
rem = zone->buffer_size - start;
if (unlikely(rem < cnt)) {
psz_zone_write(zone, FLUSH_PART, buf, rem, start);
buf += rem;
cnt -= rem;
start = 0;
is_full_data = true;
}
atomic_set(&zone->buffer->start, cnt + start);
psz_zone_write(zone, FLUSH_PART, buf, cnt, start);
/**
* psz_zone_write will set datalen as start + cnt.
* It work if actual data length lesser than buffer size.
* If data length greater than buffer size, pmsg will rewrite to
* beginning of zone, which make buffer->datalen wrongly.
* So we should reset datalen as buffer size once actual data length
* greater than buffer size.
*/
if (is_full_data) {
atomic_set(&zone->buffer->datalen, zone->buffer_size);
psz_zone_write(zone, FLUSH_META, NULL, 0, 0);
}
return 0;
}
static int notrace psz_pstore_write(struct pstore_record *record)
{
struct psz_context *cxt = record->psi->data;
if (record->type == PSTORE_TYPE_DMESG &&
record->reason == KMSG_DUMP_PANIC)
atomic_set(&cxt->on_panic, 1);
/*
* if on panic, do not write except panic records
* Fix case that panic_write prints log which wakes up console backend.
*/
if (is_on_panic() && record->type != PSTORE_TYPE_DMESG)
return -EBUSY;
switch (record->type) {
case PSTORE_TYPE_DMESG:
return psz_kmsg_write(cxt, record);
case PSTORE_TYPE_CONSOLE:
return psz_record_write(cxt->cpsz, record);
case PSTORE_TYPE_PMSG:
return psz_record_write(cxt->ppsz, record);
case PSTORE_TYPE_FTRACE: {
int zonenum = smp_processor_id();
if (!cxt->fpszs)
return -ENOSPC;
return psz_record_write(cxt->fpszs[zonenum], record);
}
default:
return -EINVAL;
}
}
static struct pstore_zone *psz_read_next_zone(struct psz_context *cxt)
{
struct pstore_zone *zone = NULL;
while (cxt->kmsg_read_cnt < cxt->kmsg_max_cnt) {
zone = cxt->kpszs[cxt->kmsg_read_cnt++];
if (psz_ok(zone))
return zone;
}
if (cxt->ftrace_read_cnt < cxt->ftrace_max_cnt)
/*
* No need psz_old_ok(). Let psz_ftrace_read() do so for
* combination. psz_ftrace_read() should traverse over
* all zones in case of some zone without data.
*/
return cxt->fpszs[cxt->ftrace_read_cnt++];
if (cxt->pmsg_read_cnt == 0) {
cxt->pmsg_read_cnt++;
zone = cxt->ppsz;
if (psz_old_ok(zone))
return zone;
}
if (cxt->console_read_cnt == 0) {
cxt->console_read_cnt++;
zone = cxt->cpsz;
if (psz_old_ok(zone))
return zone;
}
return NULL;
}
static int psz_kmsg_read_hdr(struct pstore_zone *zone,
struct pstore_record *record)
{
struct psz_buffer *buffer = zone->buffer;
struct psz_kmsg_header *hdr =
(struct psz_kmsg_header *)buffer->data;
if (hdr->magic != PSTORE_KMSG_HEADER_MAGIC)
return -EINVAL;
record->compressed = hdr->compressed;
record->time.tv_sec = hdr->time.tv_sec;
record->time.tv_nsec = hdr->time.tv_nsec;
record->reason = hdr->reason;
record->count = hdr->counter;
return 0;
}
static ssize_t psz_kmsg_read(struct pstore_zone *zone,
struct pstore_record *record)
{
ssize_t size, hlen = 0;
size = buffer_datalen(zone);
/* Clear and skip this kmsg dump record if it has no valid header */
if (psz_kmsg_read_hdr(zone, record)) {
atomic_set(&zone->buffer->datalen, 0);
atomic_set(&zone->dirty, 0);
return -ENOMSG;
}
size -= sizeof(struct psz_kmsg_header);
if (!record->compressed) {
char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n",
kmsg_dump_reason_str(record->reason),
record->count);
hlen = strlen(buf);
record->buf = krealloc(buf, hlen + size, GFP_KERNEL);
if (!record->buf) {
kfree(buf);
return -ENOMEM;
}
} else {
record->buf = kmalloc(size, GFP_KERNEL);
if (!record->buf)
return -ENOMEM;
}
size = psz_zone_read_buffer(zone, record->buf + hlen, size,
sizeof(struct psz_kmsg_header));
if (unlikely(size < 0)) {
kfree(record->buf);
return -ENOMSG;
}
return size + hlen;
}
/* try to combine all ftrace zones */
static ssize_t psz_ftrace_read(struct pstore_zone *zone,
struct pstore_record *record)