forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
memory-failure.c
1909 lines (1707 loc) · 51.5 KB
/
memory-failure.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-only
/*
* Copyright (C) 2008, 2009 Intel Corporation
* Authors: Andi Kleen, Fengguang Wu
*
* High level machine check handler. Handles pages reported by the
* hardware as being corrupted usually due to a multi-bit ECC memory or cache
* failure.
*
* In addition there is a "soft offline" entry point that allows stop using
* not-yet-corrupted-by-suspicious pages without killing anything.
*
* Handles page cache pages in various states. The tricky part
* here is that we can access any page asynchronously in respect to
* other VM users, because memory failures could happen anytime and
* anywhere. This could violate some of their assumptions. This is why
* this code has to be extremely careful. Generally it tries to use
* normal locking rules, as in get the standard locks, even if that means
* the error handling takes potentially a long time.
*
* It can be very tempting to add handling for obscure cases here.
* In general any code for handling new cases should only be added iff:
* - You know how to test it.
* - You have a test that can be added to mce-test
* https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/
* - The case actually shows up as a frequent (top 10) page state in
* tools/vm/page-types when running a real workload.
*
* There are several operations here with exponential complexity because
* of unsuitable VM data structures. For example the operation to map back
* from RMAP chains to processes has to walk the complete process list and
* has non linear complexity with the number. But since memory corruptions
* are rare we hope to get away with this. This avoids impacting the core
* VM.
*/
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/kernel-page-flags.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/backing-dev.h>
#include <linux/migrate.h>
#include <linux/suspend.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
#include <linux/memremap.h>
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include <linux/page-isolation.h>
#include "internal.h"
#include "ras/ras_event.h"
int sysctl_memory_failure_early_kill __read_mostly = 0;
int sysctl_memory_failure_recovery __read_mostly = 1;
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
u32 hwpoison_filter_enable = 0;
u32 hwpoison_filter_dev_major = ~0U;
u32 hwpoison_filter_dev_minor = ~0U;
u64 hwpoison_filter_flags_mask;
u64 hwpoison_filter_flags_value;
EXPORT_SYMBOL_GPL(hwpoison_filter_enable);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_major);
EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);
EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);
static int hwpoison_filter_dev(struct page *p)
{
struct address_space *mapping;
dev_t dev;
if (hwpoison_filter_dev_major == ~0U &&
hwpoison_filter_dev_minor == ~0U)
return 0;
/*
* page_mapping() does not accept slab pages.
*/
if (PageSlab(p))
return -EINVAL;
mapping = page_mapping(p);
if (mapping == NULL || mapping->host == NULL)
return -EINVAL;
dev = mapping->host->i_sb->s_dev;
if (hwpoison_filter_dev_major != ~0U &&
hwpoison_filter_dev_major != MAJOR(dev))
return -EINVAL;
if (hwpoison_filter_dev_minor != ~0U &&
hwpoison_filter_dev_minor != MINOR(dev))
return -EINVAL;
return 0;
}
static int hwpoison_filter_flags(struct page *p)
{
if (!hwpoison_filter_flags_mask)
return 0;
if ((stable_page_flags(p) & hwpoison_filter_flags_mask) ==
hwpoison_filter_flags_value)
return 0;
else
return -EINVAL;
}
/*
* This allows stress tests to limit test scope to a collection of tasks
* by putting them under some memcg. This prevents killing unrelated/important
* processes such as /sbin/init. Note that the target task may share clean
* pages with init (eg. libc text), which is harmless. If the target task
* share _dirty_ pages with another task B, the test scheme must make sure B
* is also included in the memcg. At last, due to race conditions this filter
* can only guarantee that the page either belongs to the memcg tasks, or is
* a freed page.
*/
#ifdef CONFIG_MEMCG
u64 hwpoison_filter_memcg;
EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p)
{
if (!hwpoison_filter_memcg)
return 0;
if (page_cgroup_ino(p) != hwpoison_filter_memcg)
return -EINVAL;
return 0;
}
#else
static int hwpoison_filter_task(struct page *p) { return 0; }
#endif
int hwpoison_filter(struct page *p)
{
if (!hwpoison_filter_enable)
return 0;
if (hwpoison_filter_dev(p))
return -EINVAL;
if (hwpoison_filter_flags(p))
return -EINVAL;
if (hwpoison_filter_task(p))
return -EINVAL;
return 0;
}
#else
int hwpoison_filter(struct page *p)
{
return 0;
}
#endif
EXPORT_SYMBOL_GPL(hwpoison_filter);
/*
* Kill all processes that have a poisoned page mapped and then isolate
* the page.
*
* General strategy:
* Find all processes having the page mapped and kill them.
* But we keep a page reference around so that the page is not
* actually freed yet.
* Then stash the page away
*
* There's no convenient way to get back to mapped processes
* from the VMAs. So do a brute-force search over all
* running processes.
*
* Remember that machine checks are not common (or rather
* if they are common you have other problems), so this shouldn't
* be a performance issue.
*
* Also there are some races possible while we get from the
* error detection to actually handle it.
*/
struct to_kill {
struct list_head nd;
struct task_struct *tsk;
unsigned long addr;
short size_shift;
};
/*
* Send all the processes who have the page mapped a signal.
* ``action optional'' if they are not immediately affected by the error
* ``action required'' if error happened in current execution context
*/
static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
{
struct task_struct *t = tk->tsk;
short addr_lsb = tk->size_shift;
int ret;
pr_err("Memory failure: %#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
pfn, t->comm, t->pid);
if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)tk->addr,
addr_lsb);
} else {
/*
* Don't use force here, it's convenient if the signal
* can be temporarily blocked.
* This could cause a loop when the user sets SIGBUS
* to SIG_IGN, but hopefully no one will do that?
*/
ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr,
addr_lsb, t); /* synchronous? */
}
if (ret < 0)
pr_info("Memory failure: Error sending signal to %s:%d: %d\n",
t->comm, t->pid, ret);
return ret;
}
/*
* When a unknown page type is encountered drain as many buffers as possible
* in the hope to turn the page into a LRU or free page, which we can handle.
*/
void shake_page(struct page *p, int access)
{
if (PageHuge(p))
return;
if (!PageSlab(p)) {
lru_add_drain_all();
if (PageLRU(p))
return;
drain_all_pages(page_zone(p));
if (PageLRU(p) || is_free_buddy_page(p))
return;
}
/*
* Only call shrink_node_slabs here (which would also shrink
* other caches) if access is not potentially fatal.
*/
if (access)
drop_slab_node(page_to_nid(p));
}
EXPORT_SYMBOL_GPL(shake_page);
static unsigned long dev_pagemap_mapping_shift(struct page *page,
struct vm_area_struct *vma)
{
unsigned long address = vma_address(page, vma);
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
pgd = pgd_offset(vma->vm_mm, address);
if (!pgd_present(*pgd))
return 0;
p4d = p4d_offset(pgd, address);
if (!p4d_present(*p4d))
return 0;
pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return 0;
if (pud_devmap(*pud))
return PUD_SHIFT;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return 0;
if (pmd_devmap(*pmd))
return PMD_SHIFT;
pte = pte_offset_map(pmd, address);
if (!pte_present(*pte))
return 0;
if (pte_devmap(*pte))
return PAGE_SHIFT;
return 0;
}
/*
* Failure handling: if we can't find or can't kill a process there's
* not much we can do. We just print a message and ignore otherwise.
*/
/*
* Schedule a process for later kill.
* Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
*/
static void add_to_kill(struct task_struct *tsk, struct page *p,
struct vm_area_struct *vma,
struct list_head *to_kill)
{
struct to_kill *tk;
tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
if (!tk) {
pr_err("Memory failure: Out of memory while machine check handling\n");
return;
}
tk->addr = page_address_in_vma(p, vma);
if (is_zone_device_page(p))
tk->size_shift = dev_pagemap_mapping_shift(p, vma);
else
tk->size_shift = page_shift(compound_head(p));
/*
* Send SIGKILL if "tk->addr == -EFAULT". Also, as
* "tk->size_shift" is always non-zero for !is_zone_device_page(),
* so "tk->size_shift == 0" effectively checks no mapping on
* ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
* to a process' address space, it's possible not all N VMAs
* contain mappings for the page, but at least one VMA does.
* Only deliver SIGBUS with payload derived from the VMA that
* has a mapping for the page.
*/
if (tk->addr == -EFAULT) {
pr_info("Memory failure: Unable to find user space address %lx in %s\n",
page_to_pfn(p), tsk->comm);
} else if (tk->size_shift == 0) {
kfree(tk);
return;
}
get_task_struct(tsk);
tk->tsk = tsk;
list_add_tail(&tk->nd, to_kill);
}
/*
* Kill the processes that have been collected earlier.
*
* Only do anything when DOIT is set, otherwise just free the list
* (this is used for clean pages which do not need killing)
* Also when FAIL is set do a force kill because something went
* wrong earlier.
*/
static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
unsigned long pfn, int flags)
{
struct to_kill *tk, *next;
list_for_each_entry_safe (tk, next, to_kill, nd) {
if (forcekill) {
/*
* In case something went wrong with munmapping
* make sure the process doesn't catch the
* signal and then access the memory. Just kill it.
*/
if (fail || tk->addr == -EFAULT) {
pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
pfn, tk->tsk->comm, tk->tsk->pid);
do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
tk->tsk, PIDTYPE_PID);
}
/*
* In theory the process could have mapped
* something else on the address in-between. We could
* check for that, but we need to tell the
* process anyways.
*/
else if (kill_proc(tk, pfn, flags) < 0)
pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n",
pfn, tk->tsk->comm, tk->tsk->pid);
}
put_task_struct(tk->tsk);
kfree(tk);
}
}
/*
* Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
* on behalf of the thread group. Return task_struct of the (first found)
* dedicated thread if found, and return NULL otherwise.
*
* We already hold read_lock(&tasklist_lock) in the caller, so we don't
* have to call rcu_read_lock/unlock() in this function.
*/
static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
{
struct task_struct *t;
for_each_thread(tsk, t)
if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY))
return t;
return NULL;
}
/*
* Determine whether a given process is "early kill" process which expects
* to be signaled when some page under the process is hwpoisoned.
* Return task_struct of the dedicated thread (main thread unless explicitly
* specified) if the process is "early kill," and otherwise returns NULL.
*/
static struct task_struct *task_early_kill(struct task_struct *tsk,
int force_early)
{
struct task_struct *t;
if (!tsk->mm)
return NULL;
if (force_early)
return tsk;
t = find_early_kill_thread(tsk);
if (t)
return t;
if (sysctl_memory_failure_early_kill)
return tsk;
return NULL;
}
/*
* Collect processes when the error hit an anonymous page.
*/
static void collect_procs_anon(struct page *page, struct list_head *to_kill,
int force_early)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
struct anon_vma *av;
pgoff_t pgoff;
av = page_lock_anon_vma_read(page);
if (av == NULL) /* Not actually mapped anymore */
return;
pgoff = page_to_pgoff(page);
read_lock(&tasklist_lock);
for_each_process (tsk) {
struct anon_vma_chain *vmac;
struct task_struct *t = task_early_kill(tsk, force_early);
if (!t)
continue;
anon_vma_interval_tree_foreach(vmac, &av->rb_root,
pgoff, pgoff) {
vma = vmac->vma;
if (!page_mapped_in_vma(page, vma))
continue;
if (vma->vm_mm == t->mm)
add_to_kill(t, page, vma, to_kill);
}
}
read_unlock(&tasklist_lock);
page_unlock_anon_vma_read(av);
}
/*
* Collect processes when the error hit a file mapped page.
*/
static void collect_procs_file(struct page *page, struct list_head *to_kill,
int force_early)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
struct address_space *mapping = page->mapping;
i_mmap_lock_read(mapping);
read_lock(&tasklist_lock);
for_each_process(tsk) {
pgoff_t pgoff = page_to_pgoff(page);
struct task_struct *t = task_early_kill(tsk, force_early);
if (!t)
continue;
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
pgoff) {
/*
* Send early kill signal to tasks where a vma covers
* the page but the corrupted page is not necessarily
* mapped it in its pte.
* Assume applications who requested early kill want
* to be informed of all such data corruptions.
*/
if (vma->vm_mm == t->mm)
add_to_kill(t, page, vma, to_kill);
}
}
read_unlock(&tasklist_lock);
i_mmap_unlock_read(mapping);
}
/*
* Collect the processes who have the corrupted page mapped to kill.
*/
static void collect_procs(struct page *page, struct list_head *tokill,
int force_early)
{
if (!page->mapping)
return;
if (PageAnon(page))
collect_procs_anon(page, tokill, force_early);
else
collect_procs_file(page, tokill, force_early);
}
static const char *action_name[] = {
[MF_IGNORED] = "Ignored",
[MF_FAILED] = "Failed",
[MF_DELAYED] = "Delayed",
[MF_RECOVERED] = "Recovered",
};
static const char * const action_page_types[] = {
[MF_MSG_KERNEL] = "reserved kernel page",
[MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page",
[MF_MSG_SLAB] = "kernel slab page",
[MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking",
[MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned",
[MF_MSG_HUGE] = "huge page",
[MF_MSG_FREE_HUGE] = "free huge page",
[MF_MSG_NON_PMD_HUGE] = "non-pmd-sized huge page",
[MF_MSG_UNMAP_FAILED] = "unmapping failed page",
[MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page",
[MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page",
[MF_MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page",
[MF_MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page",
[MF_MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page",
[MF_MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page",
[MF_MSG_DIRTY_LRU] = "dirty LRU page",
[MF_MSG_CLEAN_LRU] = "clean LRU page",
[MF_MSG_TRUNCATED_LRU] = "already truncated LRU page",
[MF_MSG_BUDDY] = "free buddy page",
[MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)",
[MF_MSG_DAX] = "dax page",
[MF_MSG_UNKNOWN] = "unknown page",
};
/*
* XXX: It is possible that a page is isolated from LRU cache,
* and then kept in swap cache or failed to remove from page cache.
* The page count will stop it from being freed by unpoison.
* Stress tests should be aware of this memory leak problem.
*/
static int delete_from_lru_cache(struct page *p)
{
if (!isolate_lru_page(p)) {
/*
* Clear sensible page flags, so that the buddy system won't
* complain when the page is unpoison-and-freed.
*/
ClearPageActive(p);
ClearPageUnevictable(p);
/*
* Poisoned page might never drop its ref count to 0 so we have
* to uncharge it manually from its memcg.
*/
mem_cgroup_uncharge(p);
/*
* drop the page count elevated by isolate_lru_page()
*/
put_page(p);
return 0;
}
return -EIO;
}
static int truncate_error_page(struct page *p, unsigned long pfn,
struct address_space *mapping)
{
int ret = MF_FAILED;
if (mapping->a_ops->error_remove_page) {
int err = mapping->a_ops->error_remove_page(mapping, p);
if (err != 0) {
pr_info("Memory failure: %#lx: Failed to punch page: %d\n",
pfn, err);
} else if (page_has_private(p) &&
!try_to_release_page(p, GFP_NOIO)) {
pr_info("Memory failure: %#lx: failed to release buffers\n",
pfn);
} else {
ret = MF_RECOVERED;
}
} else {
/*
* If the file system doesn't support it just invalidate
* This fails on dirty or anything with private pages
*/
if (invalidate_inode_page(p))
ret = MF_RECOVERED;
else
pr_info("Memory failure: %#lx: Failed to invalidate\n",
pfn);
}
return ret;
}
/*
* Error hit kernel page.
* Do nothing, try to be lucky and not touch this instead. For a few cases we
* could be more sophisticated.
*/
static int me_kernel(struct page *p, unsigned long pfn)
{
return MF_IGNORED;
}
/*
* Page in unknown state. Do nothing.
*/
static int me_unknown(struct page *p, unsigned long pfn)
{
pr_err("Memory failure: %#lx: Unknown page state\n", pfn);
return MF_FAILED;
}
/*
* Clean (or cleaned) page cache page.
*/
static int me_pagecache_clean(struct page *p, unsigned long pfn)
{
struct address_space *mapping;
delete_from_lru_cache(p);
/*
* For anonymous pages we're done the only reference left
* should be the one m_f() holds.
*/
if (PageAnon(p))
return MF_RECOVERED;
/*
* Now truncate the page in the page cache. This is really
* more like a "temporary hole punch"
* Don't do this for block devices when someone else
* has a reference, because it could be file system metadata
* and that's not safe to truncate.
*/
mapping = page_mapping(p);
if (!mapping) {
/*
* Page has been teared down in the meanwhile
*/
return MF_FAILED;
}
/*
* Truncation is a bit tricky. Enable it per file system for now.
*
* Open: to take i_mutex or not for this? Right now we don't.
*/
return truncate_error_page(p, pfn, mapping);
}
/*
* Dirty pagecache page
* Issues: when the error hit a hole page the error is not properly
* propagated.
*/
static int me_pagecache_dirty(struct page *p, unsigned long pfn)
{
struct address_space *mapping = page_mapping(p);
SetPageError(p);
/* TBD: print more information about the file. */
if (mapping) {
/*
* IO error will be reported by write(), fsync(), etc.
* who check the mapping.
* This way the application knows that something went
* wrong with its dirty file data.
*
* There's one open issue:
*
* The EIO will be only reported on the next IO
* operation and then cleared through the IO map.
* Normally Linux has two mechanisms to pass IO error
* first through the AS_EIO flag in the address space
* and then through the PageError flag in the page.
* Since we drop pages on memory failure handling the
* only mechanism open to use is through AS_AIO.
*
* This has the disadvantage that it gets cleared on
* the first operation that returns an error, while
* the PageError bit is more sticky and only cleared
* when the page is reread or dropped. If an
* application assumes it will always get error on
* fsync, but does other operations on the fd before
* and the page is dropped between then the error
* will not be properly reported.
*
* This can already happen even without hwpoisoned
* pages: first on metadata IO errors (which only
* report through AS_EIO) or when the page is dropped
* at the wrong time.
*
* So right now we assume that the application DTRT on
* the first EIO, but we're not worse than other parts
* of the kernel.
*/
mapping_set_error(mapping, -EIO);
}
return me_pagecache_clean(p, pfn);
}
/*
* Clean and dirty swap cache.
*
* Dirty swap cache page is tricky to handle. The page could live both in page
* cache and swap cache(ie. page is freshly swapped in). So it could be
* referenced concurrently by 2 types of PTEs:
* normal PTEs and swap PTEs. We try to handle them consistently by calling
* try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs,
* and then
* - clear dirty bit to prevent IO
* - remove from LRU
* - but keep in the swap cache, so that when we return to it on
* a later page fault, we know the application is accessing
* corrupted data and shall be killed (we installed simple
* interception code in do_swap_page to catch it).
*
* Clean swap cache pages can be directly isolated. A later page fault will
* bring in the known good data from disk.
*/
static int me_swapcache_dirty(struct page *p, unsigned long pfn)
{
ClearPageDirty(p);
/* Trigger EIO in shmem: */
ClearPageUptodate(p);
if (!delete_from_lru_cache(p))
return MF_DELAYED;
else
return MF_FAILED;
}
static int me_swapcache_clean(struct page *p, unsigned long pfn)
{
delete_from_swap_cache(p);
if (!delete_from_lru_cache(p))
return MF_RECOVERED;
else
return MF_FAILED;
}
/*
* Huge pages. Needs work.
* Issues:
* - Error on hugepage is contained in hugepage unit (not in raw page unit.)
* To narrow down kill region to one page, we need to break up pmd.
*/
static int me_huge_page(struct page *p, unsigned long pfn)
{
int res = 0;
struct page *hpage = compound_head(p);
struct address_space *mapping;
if (!PageHuge(hpage))
return MF_DELAYED;
mapping = page_mapping(hpage);
if (mapping) {
res = truncate_error_page(hpage, pfn, mapping);
} else {
unlock_page(hpage);
/*
* migration entry prevents later access on error anonymous
* hugepage, so we can free and dissolve it into buddy to
* save healthy subpages.
*/
if (PageAnon(hpage))
put_page(hpage);
dissolve_free_huge_page(p);
res = MF_RECOVERED;
lock_page(hpage);
}
return res;
}
/*
* Various page states we can handle.
*
* A page state is defined by its current page->flags bits.
* The table matches them in order and calls the right handler.
*
* This is quite tricky because we can access page at any time
* in its live cycle, so all accesses have to be extremely careful.
*
* This is not complete. More states could be added.
* For any missing state don't attempt recovery.
*/
#define dirty (1UL << PG_dirty)
#define sc ((1UL << PG_swapcache) | (1UL << PG_swapbacked))
#define unevict (1UL << PG_unevictable)
#define mlock (1UL << PG_mlocked)
#define writeback (1UL << PG_writeback)
#define lru (1UL << PG_lru)
#define head (1UL << PG_head)
#define slab (1UL << PG_slab)
#define reserved (1UL << PG_reserved)
static struct page_state {
unsigned long mask;
unsigned long res;
enum mf_action_page_type type;
int (*action)(struct page *p, unsigned long pfn);
} error_states[] = {
{ reserved, reserved, MF_MSG_KERNEL, me_kernel },
/*
* free pages are specially detected outside this table:
* PG_buddy pages only make a small fraction of all free pages.
*/
/*
* Could in theory check if slab page is free or if we can drop
* currently unused objects without touching them. But just
* treat it as standard kernel for now.
*/
{ slab, slab, MF_MSG_SLAB, me_kernel },
{ head, head, MF_MSG_HUGE, me_huge_page },
{ sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty },
{ sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean },
{ mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty },
{ mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean },
{ unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty },
{ unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean },
{ lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty },
{ lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean },
/*
* Catchall entry: must be at end.
*/
{ 0, 0, MF_MSG_UNKNOWN, me_unknown },
};
#undef dirty
#undef sc
#undef unevict
#undef mlock
#undef writeback
#undef lru
#undef head
#undef slab
#undef reserved
/*
* "Dirty/Clean" indication is not 100% accurate due to the possibility of
* setting PG_dirty outside page lock. See also comment above set_page_dirty().
*/
static void action_result(unsigned long pfn, enum mf_action_page_type type,
enum mf_result result)
{
trace_memory_failure_event(pfn, type, result);
pr_err("Memory failure: %#lx: recovery action for %s: %s\n",
pfn, action_page_types[type], action_name[result]);
}
static int page_action(struct page_state *ps, struct page *p,
unsigned long pfn)
{
int result;
int count;
result = ps->action(p, pfn);
count = page_count(p) - 1;
if (ps->action == me_swapcache_dirty && result == MF_DELAYED)
count--;
if (count > 0) {
pr_err("Memory failure: %#lx: %s still referenced by %d users\n",
pfn, action_page_types[ps->type], count);
result = MF_FAILED;
}
action_result(pfn, ps->type, result);
/* Could do more checks here if page looks ok */
/*
* Could adjust zone counters here to correct for the missing page.
*/
return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
}
/**
* get_hwpoison_page() - Get refcount for memory error handling:
* @page: raw error page (hit by memory error)
*
* Return: return 0 if failed to grab the refcount, otherwise true (some
* non-zero value.)
*/
int get_hwpoison_page(struct page *page)
{
struct page *head = compound_head(page);
if (!PageHuge(head) && PageTransHuge(head)) {
/*
* Non anonymous thp exists only in allocation/free time. We
* can't handle such a case correctly, so let's give it up.
* This should be better than triggering BUG_ON when kernel
* tries to touch the "partially handled" page.
*/
if (!PageAnon(head)) {
pr_err("Memory failure: %#lx: non anonymous thp\n",
page_to_pfn(page));
return 0;
}
}
if (get_page_unless_zero(head)) {
if (head == compound_head(page))
return 1;
pr_info("Memory failure: %#lx cannot catch tail\n",
page_to_pfn(page));
put_page(head);
}
return 0;
}
EXPORT_SYMBOL_GPL(get_hwpoison_page);
/*
* Do all that is necessary to remove user space mappings. Unmap
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
int flags, struct page **hpagep)
{
enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
LIST_HEAD(tokill);
bool unmap_success;
int kill = 1, forcekill;
struct page *hpage = *hpagep;
bool mlocked = PageMlocked(hpage);
/*
* Here we are interested only in user-mapped pages, so skip any
* other types of pages.
*/
if (PageReserved(p) || PageSlab(p))
return true;
if (!(PageLRU(hpage) || PageHuge(p)))
return true;
/*
* This check implies we don't kill processes if their pages
* are in the swap cache early. Those are always late kills.
*/
if (!page_mapped(hpage))
return true;
if (PageKsm(p)) {
pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn);
return false;
}
if (PageSwapCache(p)) {
pr_err("Memory failure: %#lx: keeping poisoned page in swap cache\n",
pfn);
ttu |= TTU_IGNORE_HWPOISON;
}
/*
* Propagate the dirty bit from PTEs to struct page first, because we
* need this to decide if we should kill or just drop the page.
* XXX: the dirty test could be racy: set_page_dirty() may not always
* be called inside page lock (it's recommended but not enforced).
*/
mapping = page_mapping(hpage);
if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
mapping_cap_writeback_dirty(mapping)) {
if (page_mkclean(hpage)) {
SetPageDirty(hpage);
} else {