-
Notifications
You must be signed in to change notification settings - Fork 8
/
Copy pathhuge_memory.c
2015 lines (1770 loc) · 51.7 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.
*/
#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/mm_inline.h>
#include <linux/kthread.h>
#include <linux/khugepaged.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
/*
* By default transparent hugepage support is enabled for all mappings
* and khugepaged scans all mappings. Defrag is only invoked by
* khugepaged hugepage allocations and by page faults inside
* MADV_HUGEPAGE regions to avoid the risk of slowing down short lived
* allocations.
*/
unsigned long transparent_hugepage_flags __read_mostly =
(1<<TRANSPARENT_HUGEPAGE_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
/* during fragmentation poll the hugepage allocator once every minute */
static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
static struct task_struct *khugepaged_thread __read_mostly;
static DEFINE_MUTEX(khugepaged_mutex);
static DEFINE_SPINLOCK(khugepaged_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
/*
* default collapse hugepages if there is at least one pte mapped like
* it would have happened if the vma was large enough during page
* fault.
*/
static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
static int khugepaged(void *none);
static int mm_slots_hash_init(void);
static int khugepaged_slab_init(void);
static void khugepaged_slab_free(void);
#define MM_SLOTS_HASH_HEADS 1024
static struct hlist_head *mm_slots_hash __read_mostly;
static struct kmem_cache *mm_slot_cache __read_mostly;
/**
* struct mm_slot - hash lookup from mm to mm_slot
* @hash: hash collision list
* @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head
* @mm: the mm that this information is valid for
*/
struct mm_slot {
struct hlist_node hash;
struct list_head mm_node;
struct mm_struct *mm;
};
/**
* struct khugepaged_scan - cursor for scanning
* @mm_head: the head of the mm list to scan
* @mm_slot: the current mm_slot we are scanning
* @address: the next address inside that to be scanned
*
* There is only the one khugepaged_scan instance of this cursor structure.
*/
struct khugepaged_scan {
struct list_head mm_head;
struct mm_slot *mm_slot;
unsigned long address;
} khugepaged_scan = {
.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
};
static int start_khugepaged(void)
{
int err = 0;
if (khugepaged_enabled()) {
int wakeup;
if (unlikely(!mm_slot_cache || !mm_slots_hash)) {
err = -ENOMEM;
goto out;
}
mutex_lock(&khugepaged_mutex);
if (!khugepaged_thread)
khugepaged_thread = kthread_run(khugepaged, NULL,
"khugepaged");
if (unlikely(IS_ERR(khugepaged_thread))) {
printk(KERN_ERR
"khugepaged: kthread_run(khugepaged) failed\n");
err = PTR_ERR(khugepaged_thread);
khugepaged_thread = NULL;
}
wakeup = !list_empty(&khugepaged_scan.mm_head);
mutex_unlock(&khugepaged_mutex);
if (wakeup)
wake_up_interruptible(&khugepaged_wait);
} else
/* wakeup to exit */
wake_up_interruptible(&khugepaged_wait);
out:
return err;
}
#ifdef CONFIG_SYSFS
static ssize_t double_flag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf,
enum transparent_hugepage_flag enabled,
enum transparent_hugepage_flag req_madv)
{
if (test_bit(enabled, &transparent_hugepage_flags)) {
VM_BUG_ON(test_bit(req_madv, &transparent_hugepage_flags));
return sprintf(buf, "[always] madvise never\n");
} else if (test_bit(req_madv, &transparent_hugepage_flags))
return sprintf(buf, "always [madvise] never\n");
else
return sprintf(buf, "always madvise [never]\n");
}
static ssize_t double_flag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count,
enum transparent_hugepage_flag enabled,
enum transparent_hugepage_flag req_madv)
{
if (!memcmp("always", buf,
min(sizeof("always")-1, count))) {
set_bit(enabled, &transparent_hugepage_flags);
clear_bit(req_madv, &transparent_hugepage_flags);
} else if (!memcmp("madvise", buf,
min(sizeof("madvise")-1, count))) {
clear_bit(enabled, &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);
} else
return -EINVAL;
return count;
}
static ssize_t enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return double_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
}
static ssize_t enabled_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
ssize_t ret;
ret = double_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
if (ret > 0) {
int err = start_khugepaged();
if (err)
ret = err;
}
return ret;
}
static struct kobj_attribute enabled_attr =
__ATTR(enabled, 0644, enabled_show, enabled_store);
static ssize_t single_flag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf,
enum transparent_hugepage_flag flag)
{
if (test_bit(flag, &transparent_hugepage_flags))
return sprintf(buf, "[yes] no\n");
else
return sprintf(buf, "yes [no]\n");
}
static ssize_t single_flag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count,
enum transparent_hugepage_flag flag)
{
if (!memcmp("yes", buf,
min(sizeof("yes")-1, count))) {
set_bit(flag, &transparent_hugepage_flags);
} else if (!memcmp("no", buf,
min(sizeof("no")-1, count))) {
clear_bit(flag, &transparent_hugepage_flags);
} else
return -EINVAL;
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)
{
return double_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
static ssize_t defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
return double_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
}
static struct kobj_attribute defrag_attr =
__ATTR(defrag, 0644, defrag_show, defrag_store);
#ifdef CONFIG_DEBUG_VM
static ssize_t debug_cow_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_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_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,
#ifdef CONFIG_DEBUG_VM
&debug_cow_attr.attr,
#endif
NULL,
};
static struct attribute_group hugepage_attr_group = {
.attrs = hugepage_attr,
};
static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs);
}
static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned long msecs;
int err;
err = strict_strtoul(buf, 10, &msecs);
if (err || msecs > UINT_MAX)
return -EINVAL;
khugepaged_scan_sleep_millisecs = msecs;
wake_up_interruptible(&khugepaged_wait);
return count;
}
static struct kobj_attribute scan_sleep_millisecs_attr =
__ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show,
scan_sleep_millisecs_store);
static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs);
}
static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
unsigned long msecs;
int err;
err = strict_strtoul(buf, 10, &msecs);
if (err || msecs > UINT_MAX)
return -EINVAL;
khugepaged_alloc_sleep_millisecs = msecs;
wake_up_interruptible(&khugepaged_wait);
return count;
}
static struct kobj_attribute alloc_sleep_millisecs_attr =
__ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show,
alloc_sleep_millisecs_store);
static ssize_t pages_to_scan_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_pages_to_scan);
}
static ssize_t pages_to_scan_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long pages;
err = strict_strtoul(buf, 10, &pages);
if (err || !pages || pages > UINT_MAX)
return -EINVAL;
khugepaged_pages_to_scan = pages;
return count;
}
static struct kobj_attribute pages_to_scan_attr =
__ATTR(pages_to_scan, 0644, pages_to_scan_show,
pages_to_scan_store);
static ssize_t pages_collapsed_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_pages_collapsed);
}
static struct kobj_attribute pages_collapsed_attr =
__ATTR_RO(pages_collapsed);
static ssize_t full_scans_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_full_scans);
}
static struct kobj_attribute full_scans_attr =
__ATTR_RO(full_scans);
static ssize_t khugepaged_defrag_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return single_flag_show(kobj, attr, buf,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static ssize_t khugepaged_defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
return single_flag_store(kobj, attr, buf, count,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
}
static struct kobj_attribute khugepaged_defrag_attr =
__ATTR(defrag, 0644, khugepaged_defrag_show,
khugepaged_defrag_store);
/*
* max_ptes_none controls if khugepaged should collapse hugepages over
* any unmapped ptes in turn potentially increasing the memory
* footprint of the vmas. When max_ptes_none is 0 khugepaged will not
* reduce the available free memory in the system as it
* runs. Increasing max_ptes_none will instead potentially reduce the
* free memory in the system during the khugepaged scan.
*/
static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_max_ptes_none);
}
static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_none;
err = strict_strtoul(buf, 10, &max_ptes_none);
if (err || max_ptes_none > HPAGE_PMD_NR-1)
return -EINVAL;
khugepaged_max_ptes_none = max_ptes_none;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_none_attr =
__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
khugepaged_max_ptes_none_store);
static struct attribute *khugepaged_attr[] = {
&khugepaged_defrag_attr.attr,
&khugepaged_max_ptes_none_attr.attr,
&pages_to_scan_attr.attr,
&pages_collapsed_attr.attr,
&full_scans_attr.attr,
&scan_sleep_millisecs_attr.attr,
&alloc_sleep_millisecs_attr.attr,
NULL,
};
static struct attribute_group khugepaged_attr_group = {
.attrs = khugepaged_attr,
.name = "khugepaged",
};
#endif /* CONFIG_SYSFS */
static int __init hugepage_init(void)
{
int err;
#ifdef CONFIG_SYSFS
static struct kobject *hugepage_kobj;
err = -ENOMEM;
hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!hugepage_kobj)) {
printk(KERN_ERR "hugepage: failed kobject create\n");
goto out;
}
err = sysfs_create_group(hugepage_kobj, &hugepage_attr_group);
if (err) {
printk(KERN_ERR "hugepage: failed register hugeage group\n");
goto out;
}
err = sysfs_create_group(hugepage_kobj, &khugepaged_attr_group);
if (err) {
printk(KERN_ERR "hugepage: failed register hugeage group\n");
goto out;
}
#endif
err = khugepaged_slab_init();
if (err)
goto out;
err = mm_slots_hash_init();
if (err) {
khugepaged_slab_free();
goto out;
}
start_khugepaged();
out:
return err;
}
module_init(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)
printk(KERN_WARNING
"transparent_hugepage= cannot parse, ignored\n");
return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
static void prepare_pmd_huge_pte(pgtable_t pgtable,
struct mm_struct *mm)
{
assert_spin_locked(&mm->page_table_lock);
/* FIFO */
if (!mm->pmd_huge_pte)
INIT_LIST_HEAD(&pgtable->lru);
else
list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
mm->pmd_huge_pte = pgtable;
}
static inline 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 int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long haddr, pmd_t *pmd,
struct page *page)
{
int ret = 0;
pgtable_t pgtable;
VM_BUG_ON(!PageCompound(page));
pgtable = pte_alloc_one(mm, haddr);
if (unlikely(!pgtable)) {
mem_cgroup_uncharge_page(page);
put_page(page);
return VM_FAULT_OOM;
}
clear_huge_page(page, haddr, HPAGE_PMD_NR);
__SetPageUptodate(page);
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_none(*pmd))) {
spin_unlock(&mm->page_table_lock);
mem_cgroup_uncharge_page(page);
put_page(page);
pte_free(mm, pgtable);
} else {
pmd_t entry;
entry = mk_pmd(page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
entry = pmd_mkhuge(entry);
/*
* The spinlocking to take the lru_lock inside
* page_add_new_anon_rmap() acts as a full memory
* barrier to be sure clear_huge_page writes become
* visible after the set_pmd_at() write.
*/
page_add_new_anon_rmap(page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
prepare_pmd_huge_pte(pgtable, mm);
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
spin_unlock(&mm->page_table_lock);
}
return ret;
}
static inline struct page *alloc_hugepage(int defrag)
{
return alloc_pages(GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT),
HPAGE_PMD_ORDER);
}
int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
unsigned int flags)
{
struct page *page;
unsigned long haddr = address & HPAGE_PMD_MASK;
pte_t *pte;
if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
if (unlikely(khugepaged_enter(vma)))
return VM_FAULT_OOM;
page = alloc_hugepage(transparent_hugepage_defrag(vma));
if (unlikely(!page))
goto out;
if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
put_page(page);
goto out;
}
return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
}
out:
/*
* Use __pte_alloc instead of pte_alloc_map, because we can't
* run pte_offset_map on the pmd, if an huge pmd could
* materialize from under us from a different thread.
*/
if (unlikely(__pte_alloc(mm, vma, pmd, address)))
return VM_FAULT_OOM;
/* if an huge pmd materialized from under us just retry later */
if (unlikely(pmd_trans_huge(*pmd)))
return 0;
/*
* A regular pmd is established and it can't morph into a huge pmd
* from under us anymore at this point because we hold the mmap_sem
* read mode and khugepaged takes it in write mode. So now it's
* safe to run pte_offset_map().
*/
pte = pte_offset_map(pmd, address);
return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}
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)
{
struct page *src_page;
pmd_t pmd;
pgtable_t pgtable;
int ret;
ret = -ENOMEM;
pgtable = pte_alloc_one(dst_mm, addr);
if (unlikely(!pgtable))
goto out;
spin_lock(&dst_mm->page_table_lock);
spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING);
ret = -EAGAIN;
pmd = *src_pmd;
if (unlikely(!pmd_trans_huge(pmd))) {
pte_free(dst_mm, pgtable);
goto out_unlock;
}
if (unlikely(pmd_trans_splitting(pmd))) {
/* split huge page running from under us */
spin_unlock(&src_mm->page_table_lock);
spin_unlock(&dst_mm->page_table_lock);
pte_free(dst_mm, pgtable);
wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
goto out;
}
src_page = pmd_page(pmd);
VM_BUG_ON(!PageHead(src_page));
get_page(src_page);
page_dup_rmap(src_page);
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
pmdp_set_wrprotect(src_mm, addr, src_pmd);
pmd = pmd_mkold(pmd_wrprotect(pmd));
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
prepare_pmd_huge_pte(pgtable, dst_mm);
ret = 0;
out_unlock:
spin_unlock(&src_mm->page_table_lock);
spin_unlock(&dst_mm->page_table_lock);
out:
return ret;
}
/* no "address" argument so destroys page coloring of some arch */
pgtable_t get_pmd_huge_pte(struct mm_struct *mm)
{
pgtable_t pgtable;
assert_spin_locked(&mm->page_table_lock);
/* FIFO */
pgtable = mm->pmd_huge_pte;
if (list_empty(&pgtable->lru))
mm->pmd_huge_pte = NULL;
else {
mm->pmd_huge_pte = list_entry(pgtable->lru.next,
struct page, lru);
list_del(&pgtable->lru);
}
return pgtable;
}
static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmd, pmd_t orig_pmd,
struct page *page,
unsigned long haddr)
{
pgtable_t pgtable;
pmd_t _pmd;
int ret = 0, i;
struct page **pages;
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(GFP_HIGHUSER_MOVABLE,
vma, address);
if (unlikely(!pages[i] ||
mem_cgroup_newpage_charge(pages[i], mm,
GFP_KERNEL))) {
if (pages[i])
put_page(pages[i]);
mem_cgroup_uncharge_start();
while (--i >= 0) {
mem_cgroup_uncharge_page(pages[i]);
put_page(pages[i]);
}
mem_cgroup_uncharge_end();
kfree(pages);
ret |= VM_FAULT_OOM;
goto out;
}
}
for (i = 0; i < HPAGE_PMD_NR; i++) {
copy_user_highpage(pages[i], page + i,
haddr + PAGE_SHIFT*i, vma);
__SetPageUptodate(pages[i]);
cond_resched();
}
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(*pmd, orig_pmd)))
goto out_free_pages;
VM_BUG_ON(!PageHead(page));
pmdp_clear_flush_notify(vma, haddr, pmd);
/* leave pmd empty until pte is filled */
pgtable = get_pmd_huge_pte(mm);
pmd_populate(mm, &_pmd, pgtable);
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
pte_t *pte, entry;
entry = mk_pte(pages[i], vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
page_add_new_anon_rmap(pages[i], vma, haddr);
pte = pte_offset_map(&_pmd, haddr);
VM_BUG_ON(!pte_none(*pte));
set_pte_at(mm, haddr, pte, entry);
pte_unmap(pte);
}
kfree(pages);
mm->nr_ptes++;
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
page_remove_rmap(page);
spin_unlock(&mm->page_table_lock);
ret |= VM_FAULT_WRITE;
put_page(page);
out:
return ret;
out_free_pages:
spin_unlock(&mm->page_table_lock);
mem_cgroup_uncharge_start();
for (i = 0; i < HPAGE_PMD_NR; i++) {
mem_cgroup_uncharge_page(pages[i]);
put_page(pages[i]);
}
mem_cgroup_uncharge_end();
kfree(pages);
goto out;
}
int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, pmd_t orig_pmd)
{
int ret = 0;
struct page *page, *new_page;
unsigned long haddr;
VM_BUG_ON(!vma->anon_vma);
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(*pmd, orig_pmd)))
goto out_unlock;
page = pmd_page(orig_pmd);
VM_BUG_ON(!PageCompound(page) || !PageHead(page));
haddr = address & HPAGE_PMD_MASK;
if (page_mapcount(page) == 1) {
pmd_t entry;
entry = pmd_mkyoung(orig_pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
if (pmdp_set_access_flags(vma, haddr, pmd, entry, 1))
update_mmu_cache(vma, address, entry);
ret |= VM_FAULT_WRITE;
goto out_unlock;
}
get_page(page);
spin_unlock(&mm->page_table_lock);
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow())
new_page = alloc_hugepage(transparent_hugepage_defrag(vma));
else
new_page = NULL;
if (unlikely(!new_page)) {
ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
pmd, orig_pmd, page, haddr);
put_page(page);
goto out;
}
if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
put_page(new_page);
put_page(page);
ret |= VM_FAULT_OOM;
goto out;
}
copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
__SetPageUptodate(new_page);
spin_lock(&mm->page_table_lock);
put_page(page);
if (unlikely(!pmd_same(*pmd, orig_pmd))) {
mem_cgroup_uncharge_page(new_page);
put_page(new_page);
} else {
pmd_t entry;
VM_BUG_ON(!PageHead(page));
entry = mk_pmd(new_page, vma->vm_page_prot);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
entry = pmd_mkhuge(entry);
pmdp_clear_flush_notify(vma, haddr, pmd);
page_add_new_anon_rmap(new_page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
update_mmu_cache(vma, address, entry);
page_remove_rmap(page);
put_page(page);
ret |= VM_FAULT_WRITE;
}
out_unlock:
spin_unlock(&mm->page_table_lock);
out:
return ret;
}
struct page *follow_trans_huge_pmd(struct mm_struct *mm,
unsigned long addr,
pmd_t *pmd,
unsigned int flags)
{
struct page *page = NULL;
assert_spin_locked(&mm->page_table_lock);
if (flags & FOLL_WRITE && !pmd_write(*pmd))
goto out;
page = pmd_page(*pmd);
VM_BUG_ON(!PageHead(page));
if (flags & FOLL_TOUCH) {
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));
set_pmd_at(mm, addr & HPAGE_PMD_MASK, pmd, _pmd);
}
page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
VM_BUG_ON(!PageCompound(page));
if (flags & FOLL_GET)
get_page(page);
out:
return page;
}
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd)
{
int ret = 0;
spin_lock(&tlb->mm->page_table_lock);
if (likely(pmd_trans_huge(*pmd))) {
if (unlikely(pmd_trans_splitting(*pmd))) {
spin_unlock(&tlb->mm->page_table_lock);
wait_split_huge_page(vma->anon_vma,
pmd);
} else {
struct page *page;
pgtable_t pgtable;
pgtable = get_pmd_huge_pte(tlb->mm);
page = pmd_page(*pmd);
pmd_clear(pmd);
page_remove_rmap(page);
VM_BUG_ON(page_mapcount(page) < 0);
add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
VM_BUG_ON(!PageHead(page));
spin_unlock(&tlb->mm->page_table_lock);
tlb_remove_page(tlb, page);
pte_free(tlb->mm, pgtable);
ret = 1;
}
} else
spin_unlock(&tlb->mm->page_table_lock);
return ret;
}
pmd_t *page_check_address_pmd(struct page *page,
struct mm_struct *mm,
unsigned long address,
enum page_check_address_pmd_flag flag)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd, *ret = NULL;
if (address & ~HPAGE_PMD_MASK)
goto out;
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
goto out;
pud = pud_offset(pgd, address);
if (!pud_present(*pud))
goto out;
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
goto out;
if (pmd_page(*pmd) != page)
goto out;
VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
pmd_trans_splitting(*pmd));
if (pmd_trans_huge(*pmd)) {
VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
!pmd_trans_splitting(*pmd));
ret = pmd;
}
out:
return ret;
}
static int __split_huge_page_splitting(struct page *page,
struct vm_area_struct *vma,
unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
pmd_t *pmd;
int ret = 0;
spin_lock(&mm->page_table_lock);
pmd = page_check_address_pmd(page, mm, address,
PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
if (pmd) {
/*
* We can't temporarily set the pmd to null in order
* to split it, the pmd must remain marked huge at all
* times or the VM won't take the pmd_trans_huge paths
* and it won't wait on the anon_vma->root->lock to
* serialize against split_huge_page*.
*/
pmdp_splitting_flush_notify(vma, address, pmd);
ret = 1;
}
spin_unlock(&mm->page_table_lock);
return ret;
}
static void __split_huge_page_refcount(struct page *page)
{
int i;
unsigned long head_index = page->index;
struct zone *zone = page_zone(page);
/* prevent PageLRU to go away from under us, and freeze lru stats */
spin_lock_irq(&zone->lru_lock);
compound_lock(page);
for (i = 1; i < HPAGE_PMD_NR; i++) {
struct page *page_tail = page + i;