forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
huge_memory.c
2254 lines (1990 loc) · 61.6 KB
/
huge_memory.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
/*
* Copyright (C) 2009 Red Hat, Inc.
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/swapops.h>
#include <linux/dax.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/pfn_t.h>
#include <linux/mman.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/migrate.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
/*
* By default transparent hugepage support is disabled in order that avoid
* to risk increase the memory footprint of applications without a guaranteed
* benefit. When transparent hugepage support is enabled, is for all mappings,
* and khugepaged scans all mappings.
* Defrag is invoked by khugepaged hugepage allocations and by page faults
* for all hugepage allocations.
*/
unsigned long transparent_hugepage_flags __read_mostly =
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
(1<<TRANSPARENT_HUGEPAGE_FLAG)|
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
static struct shrinker deferred_split_shrinker;
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
struct page *get_huge_zero_page(void)
{
struct page *zero_page;
retry:
if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
return READ_ONCE(huge_zero_page);
zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
HPAGE_PMD_ORDER);
if (!zero_page) {
count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
return NULL;
}
count_vm_event(THP_ZERO_PAGE_ALLOC);
preempt_disable();
if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
preempt_enable();
__free_pages(zero_page, compound_order(zero_page));
goto retry;
}
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
preempt_enable();
return READ_ONCE(huge_zero_page);
}
void put_huge_zero_page(void)
{
/*
* Counter should never go to zero here. Only shrinker can put
* last reference.
*/
BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}
static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
struct shrink_control *sc)
{
/* we can free zero page only if last reference remains */
return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
}
static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
__free_pages(zero_page, compound_order(zero_page));
return HPAGE_PMD_NR;
}
return 0;
}
static struct shrinker huge_zero_page_shrinker = {
.count_objects = shrink_huge_zero_page_count,
.scan_objects = shrink_huge_zero_page_scan,
.seeks = DEFAULT_SEEKS,
};
#ifdef CONFIG_SYSFS
static ssize_t triple_flag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count,
enum transparent_hugepage_flag enabled,
enum transparent_hugepage_flag deferred,
enum transparent_hugepage_flag req_madv)
{
if (!memcmp("defer", buf,
min(sizeof("defer")-1, count))) {
if (enabled == deferred)
return -EINVAL;
clear_bit(enabled, &transparent_hugepage_flags);
clear_bit(req_madv, &transparent_hugepage_flags);
set_bit(deferred, &transparent_hugepage_flags);
} else if (!memcmp("always", buf,
min(sizeof("always")-1, count))) {
clear_bit(deferred, &transparent_hugepage_flags);
clear_bit(req_madv, &transparent_hugepage_flags);
set_bit(enabled, &transparent_hugepage_flags);
} else if (!memcmp("madvise", buf,
min(sizeof("madvise")-1, count))) {
clear_bit(enabled, &transparent_hugepage_flags);
clear_bit(deferred, &transparent_hugepage_flags);
set_bit(req_madv, &transparent_hugepage_flags);
} else if (!memcmp("never", buf,
min(sizeof("never")-1, count))) {
clear_bit(enabled, &transparent_hugepage_flags);
clear_bit(req_madv, &transparent_hugepage_flags);
clear_bit(deferred, &transparent_hugepage_flags);
} else
return -EINVAL;
return count;
}
static ssize_t enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags))
return sprintf(buf, "[always] madvise never\n");
else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags))
return sprintf(buf, "always [madvise] never\n");
else
return sprintf(buf, "always madvise [never]\n");
}
static ssize_t enabled_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
ssize_t ret;
ret = triple_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
if (ret > 0) {
int err = start_stop_khugepaged();
if (err)
ret = err;
}
return ret;
}
static struct kobj_attribute enabled_attr =
__ATTR(enabled, 0644, enabled_show, enabled_store);
ssize_t single_hugepage_flag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf,
enum transparent_hugepage_flag flag)
{
return sprintf(buf, "%d\n",
!!test_bit(flag, &transparent_hugepage_flags));
}
ssize_t single_hugepage_flag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count,
enum transparent_hugepage_flag flag)
{
unsigned long value;
int ret;
ret = kstrtoul(buf, 10, &value);
if (ret < 0)
return ret;
if (value > 1)
return -EINVAL;
if (value)
set_bit(flag, &transparent_hugepage_flags);
else
clear_bit(flag, &transparent_hugepage_flags);
return count;
}
/*
* Currently defrag only disables __GFP_NOWAIT for allocation. A blind
* __GFP_REPEAT is too aggressive, it's never worth swapping tons of
* memory just to allocate one more hugepage.
*/
static ssize_t defrag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return sprintf(buf, "[always] defer madvise never\n");
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
return sprintf(buf, "always [defer] madvise never\n");
else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
return sprintf(buf, "always defer [madvise] never\n");
else
return sprintf(buf, "always defer madvise [never]\n");
}
static ssize_t defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
return triple_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
static struct kobj_attribute defrag_attr =
__ATTR(defrag, 0644, defrag_show, defrag_store);
static ssize_t use_zero_page_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_hugepage_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static ssize_t use_zero_page_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
return single_hugepage_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static struct kobj_attribute use_zero_page_attr =
__ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);
#ifdef CONFIG_DEBUG_VM
static ssize_t debug_cow_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_hugepage_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
}
static ssize_t debug_cow_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
return single_hugepage_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
}
static struct kobj_attribute debug_cow_attr =
__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
#endif /* CONFIG_DEBUG_VM */
static struct attribute *hugepage_attr[] = {
&enabled_attr.attr,
&defrag_attr.attr,
&use_zero_page_attr.attr,
#if defined(CONFIG_SHMEM) && defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE)
&shmem_enabled_attr.attr,
#endif
#ifdef CONFIG_DEBUG_VM
&debug_cow_attr.attr,
#endif
NULL,
};
static struct attribute_group hugepage_attr_group = {
.attrs = hugepage_attr,
};
static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
int err;
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
pr_err("failed to create transparent hugepage kobject\n");
return -ENOMEM;
}
err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
if (err) {
pr_err("failed to register transparent hugepage group\n");
goto delete_obj;
}
err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
if (err) {
pr_err("failed to register transparent hugepage group\n");
goto remove_hp_group;
}
return 0;
remove_hp_group:
sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
delete_obj:
kobject_put(*hugepage_kobj);
return err;
}
static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
kobject_put(hugepage_kobj);
}
#else
static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
return 0;
}
static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
}
#endif /* CONFIG_SYSFS */
static int __init hugepage_init(void)
{
int err;
struct kobject *hugepage_kobj;
if (!has_transparent_hugepage()) {
transparent_hugepage_flags = 0;
return -EINVAL;
}
/*
* hugepages can't be allocated by the buddy allocator
*/
MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER);
/*
* we use page->mapping and page->index in second tail page
* as list_head: assuming THP order >= 2
*/
MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);
err = hugepage_init_sysfs(&hugepage_kobj);
if (err)
goto err_sysfs;
err = khugepaged_init();
if (err)
goto err_slab;
err = register_shrinker(&huge_zero_page_shrinker);
if (err)
goto err_hzp_shrinker;
err = register_shrinker(&deferred_split_shrinker);
if (err)
goto err_split_shrinker;
/*
* By default disable transparent hugepages on smaller systems,
* where the extra memory used could hurt more than TLB overhead
* is likely to save. The admin can still enable it through /sys.
*/
if (totalram_pages < (512 << (20 - PAGE_SHIFT))) {
transparent_hugepage_flags = 0;
return 0;
}
err = start_stop_khugepaged();
if (err)
goto err_khugepaged;
return 0;
err_khugepaged:
unregister_shrinker(&deferred_split_shrinker);
err_split_shrinker:
unregister_shrinker(&huge_zero_page_shrinker);
err_hzp_shrinker:
khugepaged_destroy();
err_slab:
hugepage_exit_sysfs(hugepage_kobj);
err_sysfs:
return err;
}
subsys_initcall(hugepage_init);
static int __init setup_transparent_hugepage(char *str)
{
int ret = 0;
if (!str)
goto out;
if (!strcmp(str, "always")) {
set_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
ret = 1;
} else if (!strcmp(str, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
ret = 1;
} else if (!strcmp(str, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
&transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
&transparent_hugepage_flags);
ret = 1;
}
out:
if (!ret)
pr_warn("transparent_hugepage= cannot parse, ignored\n");
return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
pmd = pmd_mkwrite(pmd);
return pmd;
}
static inline struct list_head *page_deferred_list(struct page *page)
{
/*
* ->lru in the tail pages is occupied by compound_head.
* Let's use ->mapping + ->index in the second tail page as list_head.
*/
return (struct list_head *)&page[2].mapping;
}
void prep_transhuge_page(struct page *page)
{
/*
* we use page->mapping and page->indexlru in second tail page
* as list_head: assuming THP order >= 2
*/
INIT_LIST_HEAD(page_deferred_list(page));
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
gfp_t gfp)
{
struct vm_area_struct *vma = fe->vma;
struct mem_cgroup *memcg;
pgtable_t pgtable;
unsigned long haddr = fe->address & HPAGE_PMD_MASK;
VM_BUG_ON_PAGE(!PageCompound(page), page);
if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
}
pgtable = pte_alloc_one(vma->vm_mm, haddr);
if (unlikely(!pgtable)) {
mem_cgroup_cancel_charge(page, memcg, true);
put_page(page);
return VM_FAULT_OOM;
}
clear_huge_page(page, haddr, HPAGE_PMD_NR);
/*
* The memory barrier inside __SetPageUptodate makes sure that
* clear_huge_page writes become visible before the set_pmd_at()
* write.
*/
__SetPageUptodate(page);
fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
if (unlikely(!pmd_none(*fe->pmd))) {
spin_unlock(fe->ptl);
mem_cgroup_cancel_charge(page, memcg, true);
put_page(page);
pte_free(vma->vm_mm, pgtable);
} else {
pmd_t entry;
/* Deliver the page fault to userland */
if (userfaultfd_missing(vma)) {
int ret;
spin_unlock(fe->ptl);
mem_cgroup_cancel_charge(page, memcg, true);
put_page(page);
pte_free(vma->vm_mm, pgtable);
ret = handle_userfault(fe, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
return ret;
}
entry = mk_huge_pmd(page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
page_add_new_anon_rmap(page, vma, haddr, true);
mem_cgroup_commit_charge(page, memcg, false, true);
lru_cache_add_active_or_unevictable(page, vma);
pgtable_trans_huge_deposit(vma->vm_mm, fe->pmd, pgtable);
set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
atomic_long_inc(&vma->vm_mm->nr_ptes);
spin_unlock(fe->ptl);
count_vm_event(THP_FAULT_ALLOC);
}
return 0;
}
/*
* If THP defrag is set to always then directly reclaim/compact as necessary
* If set to defer then do only background reclaim/compact and defer to khugepaged
* If set to madvise and the VMA is flagged then directly reclaim/compact
* When direct reclaim/compact is allowed, don't retry except for flagged VMA's
*/
static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
{
bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
&transparent_hugepage_flags) && vma_madvised)
return GFP_TRANSHUGE;
else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
&transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
&transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
return GFP_TRANSHUGE_LIGHT;
}
/* Caller must hold page table lock. */
static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
struct page *zero_page)
{
pmd_t entry;
if (!pmd_none(*pmd))
return false;
entry = mk_pmd(zero_page, vma->vm_page_prot);
entry = pmd_mkhuge(entry);
if (pgtable)
pgtable_trans_huge_deposit(mm, pmd, pgtable);
set_pmd_at(mm, haddr, pmd, entry);
atomic_long_inc(&mm->nr_ptes);
return true;
}
int do_huge_pmd_anonymous_page(struct fault_env *fe)
{
struct vm_area_struct *vma = fe->vma;
gfp_t gfp;
struct page *page;
unsigned long haddr = fe->address & HPAGE_PMD_MASK;
if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
return VM_FAULT_FALLBACK;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
return VM_FAULT_OOM;
if (!(fe->flags & FAULT_FLAG_WRITE) &&
!mm_forbids_zeropage(vma->vm_mm) &&
transparent_hugepage_use_zero_page()) {
pgtable_t pgtable;
struct page *zero_page;
bool set;
int ret;
pgtable = pte_alloc_one(vma->vm_mm, haddr);
if (unlikely(!pgtable))
return VM_FAULT_OOM;
zero_page = get_huge_zero_page();
if (unlikely(!zero_page)) {
pte_free(vma->vm_mm, pgtable);
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
}
fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
ret = 0;
set = false;
if (pmd_none(*fe->pmd)) {
if (userfaultfd_missing(vma)) {
spin_unlock(fe->ptl);
ret = handle_userfault(fe, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
} else {
set_huge_zero_page(pgtable, vma->vm_mm, vma,
haddr, fe->pmd, zero_page);
spin_unlock(fe->ptl);
set = true;
}
} else
spin_unlock(fe->ptl);
if (!set) {
pte_free(vma->vm_mm, pgtable);
put_huge_zero_page();
}
return ret;
}
gfp = alloc_hugepage_direct_gfpmask(vma);
page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
}
prep_transhuge_page(page);
return __do_huge_pmd_anonymous_page(fe, page, gfp);
}
static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write)
{
struct mm_struct *mm = vma->vm_mm;
pmd_t entry;
spinlock_t *ptl;
ptl = pmd_lock(mm, pmd);
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
if (write) {
entry = pmd_mkyoung(pmd_mkdirty(entry));
entry = maybe_pmd_mkwrite(entry, vma);
}
set_pmd_at(mm, addr, pmd, entry);
update_mmu_cache_pmd(vma, addr, pmd);
spin_unlock(ptl);
}
int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, pfn_t pfn, bool write)
{
pgprot_t pgprot = vma->vm_page_prot;
/*
* If we had pmd_special, we could avoid all these restrictions,
* but we need to be consistent with PTEs and architectures that
* can't support a 'special' bit.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
BUG_ON(!pfn_t_devmap(pfn));
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (track_pfn_insert(vma, &pgprot, pfn))
return VM_FAULT_SIGBUS;
insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd)
{
pmd_t _pmd;
/*
* We should set the dirty bit only for FOLL_WRITE but for now
* the dirty bit in the pmd is meaningless. And if the dirty
* bit will become meaningful and we'll only set it with
* FOLL_WRITE, an atomic set_bit will be required on the pmd to
* set the young bit, instead of the current set_pmd_at.
*/
_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
pmd, _pmd, 1))
update_mmu_cache_pmd(vma, addr, pmd);
}
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, int flags)
{
unsigned long pfn = pmd_pfn(*pmd);
struct mm_struct *mm = vma->vm_mm;
struct dev_pagemap *pgmap;
struct page *page;
assert_spin_locked(pmd_lockptr(mm, pmd));
if (flags & FOLL_WRITE && !pmd_write(*pmd))
return NULL;
if (pmd_present(*pmd) && pmd_devmap(*pmd))
/* pass */;
else
return NULL;
if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd);
/*
* device mapped pages can only be returned if the
* caller will manage the page reference count.
*/
if (!(flags & FOLL_GET))
return ERR_PTR(-EEXIST);
pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
pgmap = get_dev_pagemap(pfn, NULL);
if (!pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
get_page(page);
put_dev_pagemap(pgmap);
return page;
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
struct vm_area_struct *vma)
{
spinlock_t *dst_ptl, *src_ptl;
struct page *src_page;
pmd_t pmd;
pgtable_t pgtable = NULL;
int ret = -ENOMEM;
/* Skip if can be re-fill on fault */
if (!vma_is_anonymous(vma))
return 0;
pgtable = pte_alloc_one(dst_mm, addr);
if (unlikely(!pgtable))
goto out;
dst_ptl = pmd_lock(dst_mm, dst_pmd);
src_ptl = pmd_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
ret = -EAGAIN;
pmd = *src_pmd;
if (unlikely(!pmd_trans_huge(pmd))) {
pte_free(dst_mm, pgtable);
goto out_unlock;
}
/*
* When page table lock is held, the huge zero pmd should not be
* under splitting since we don't split the page itself, only pmd to
* a page table.
*/
if (is_huge_zero_pmd(pmd)) {
struct page *zero_page;
/*
* get_huge_zero_page() will never allocate a new page here,
* since we already have a zero page to copy. It just takes a
* reference.
*/
zero_page = get_huge_zero_page();
set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
zero_page);
ret = 0;
goto out_unlock;
}
src_page = pmd_page(pmd);
VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
get_page(src_page);
page_dup_rmap(src_page, true);
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
atomic_long_inc(&dst_mm->nr_ptes);
pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
pmdp_set_wrprotect(src_mm, addr, src_pmd);
pmd = pmd_mkold(pmd_wrprotect(pmd));
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
ret = 0;
out_unlock:
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
out:
return ret;
}
void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd)
{
pmd_t entry;
unsigned long haddr;
fe->ptl = pmd_lock(fe->vma->vm_mm, fe->pmd);
if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
goto unlock;
entry = pmd_mkyoung(orig_pmd);
haddr = fe->address & HPAGE_PMD_MASK;
if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry,
fe->flags & FAULT_FLAG_WRITE))
update_mmu_cache_pmd(fe->vma, fe->address, fe->pmd);
unlock:
spin_unlock(fe->ptl);
}
static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd,
struct page *page)
{
struct vm_area_struct *vma = fe->vma;
unsigned long haddr = fe->address & HPAGE_PMD_MASK;
struct mem_cgroup *memcg;
pgtable_t pgtable;
pmd_t _pmd;
int ret = 0, i;
struct page **pages;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR,
GFP_KERNEL);
if (unlikely(!pages)) {
ret |= VM_FAULT_OOM;
goto out;
}
for (i = 0; i < HPAGE_PMD_NR; i++) {
pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
__GFP_OTHER_NODE, vma,
fe->address, page_to_nid(page));
if (unlikely(!pages[i] ||
mem_cgroup_try_charge(pages[i], vma->vm_mm,
GFP_KERNEL, &memcg, false))) {
if (pages[i])
put_page(pages[i]);
while (--i >= 0) {
memcg = (void *)page_private(pages[i]);
set_page_private(pages[i], 0);
mem_cgroup_cancel_charge(pages[i], memcg,
false);
put_page(pages[i]);
}
kfree(pages);
ret |= VM_FAULT_OOM;
goto out;
}
set_page_private(pages[i], (unsigned long)memcg);
}
for (i = 0; i < HPAGE_PMD_NR; i++) {
copy_user_highpage(pages[i], page + i,
haddr + PAGE_SIZE * i, vma);
__SetPageUptodate(pages[i]);
cond_resched();
}
mmun_start = haddr;
mmun_end = haddr + HPAGE_PMD_SIZE;
mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
goto out_free_pages;
VM_BUG_ON_PAGE(!PageHead(page), page);
pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd);
/* leave pmd empty until pte is filled */
pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, fe->pmd);
pmd_populate(vma->vm_mm, &_pmd, pgtable);
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
pte_t entry;
entry = mk_pte(pages[i], vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
memcg = (void *)page_private(pages[i]);
set_page_private(pages[i], 0);
page_add_new_anon_rmap(pages[i], fe->vma, haddr, false);
mem_cgroup_commit_charge(pages[i], memcg, false, false);
lru_cache_add_active_or_unevictable(pages[i], vma);
fe->pte = pte_offset_map(&_pmd, haddr);
VM_BUG_ON(!pte_none(*fe->pte));
set_pte_at(vma->vm_mm, haddr, fe->pte, entry);
pte_unmap(fe->pte);
}
kfree(pages);
smp_wmb(); /* make pte visible before pmd */
pmd_populate(vma->vm_mm, fe->pmd, pgtable);
page_remove_rmap(page, true);
spin_unlock(fe->ptl);
mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
ret |= VM_FAULT_WRITE;
put_page(page);
out:
return ret;
out_free_pages:
spin_unlock(fe->ptl);
mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
for (i = 0; i < HPAGE_PMD_NR; i++) {
memcg = (void *)page_private(pages[i]);
set_page_private(pages[i], 0);
mem_cgroup_cancel_charge(pages[i], memcg, false);
put_page(pages[i]);
}
kfree(pages);
goto out;
}
int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd)
{
struct vm_area_struct *vma = fe->vma;
struct page *page = NULL, *new_page;
struct mem_cgroup *memcg;
unsigned long haddr = fe->address & HPAGE_PMD_MASK;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
gfp_t huge_gfp; /* for allocation and charge */
int ret = 0;
fe->ptl = pmd_lockptr(vma->vm_mm, fe->pmd);
VM_BUG_ON_VMA(!vma->anon_vma, vma);
if (is_huge_zero_pmd(orig_pmd))
goto alloc;
spin_lock(fe->ptl);
if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
goto out_unlock;
page = pmd_page(orig_pmd);
VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page);
/*
* We can only reuse the page if nobody else maps the huge page or it's
* part.
*/
if (page_trans_huge_mapcount(page, NULL) == 1) {
pmd_t entry;
entry = pmd_mkyoung(orig_pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
if (pmdp_set_access_flags(vma, haddr, fe->pmd, entry, 1))
update_mmu_cache_pmd(vma, fe->address, fe->pmd);
ret |= VM_FAULT_WRITE;
goto out_unlock;
}
get_page(page);
spin_unlock(fe->ptl);
alloc:
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
huge_gfp = alloc_hugepage_direct_gfpmask(vma);
new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
} else
new_page = NULL;
if (likely(new_page)) {
prep_transhuge_page(new_page);
} else {
if (!page) {
split_huge_pmd(vma, fe->pmd, fe->address);
ret |= VM_FAULT_FALLBACK;
} else {
ret = do_huge_pmd_wp_page_fallback(fe, orig_pmd, page);
if (ret & VM_FAULT_OOM) {
split_huge_pmd(vma, fe->pmd, fe->address);
ret |= VM_FAULT_FALLBACK;
}
put_page(page);
}
count_vm_event(THP_FAULT_FALLBACK);
goto out;
}
if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
huge_gfp, &memcg, true))) {
put_page(new_page);