summaryrefslogtreecommitdiff
path: root/include/linux/hugetlb.h
blob: d1897a69c5406835b62635b82ce18768ebdc598f (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_HUGETLB_H
#define _LINUX_HUGETLB_H

#include <linux/mm_types.h>
#include <linux/mmdebug.h>
#include <linux/fs.h>
#include <linux/hugetlb_inline.h>
#include <linux/cgroup.h>
#include <linux/list.h>
#include <linux/kref.h>
#include <linux/pgtable.h>
#include <linux/gfp.h>
#include <linux/userfaultfd_k.h>

struct ctl_table;
struct user_struct;
struct mmu_gather;

#ifndef is_hugepd
typedef struct { unsigned long pd; } hugepd_t;
#define is_hugepd(hugepd) (0)
#define __hugepd(x) ((hugepd_t) { (x) })
#endif

#ifdef CONFIG_HUGETLB_PAGE

#include <linux/mempolicy.h>
#include <linux/shm.h>
#include <asm/tlbflush.h>

/*
 * For HugeTLB page, there are more metadata to save in the struct page. But
 * the head struct page cannot meet our needs, so we have to abuse other tail
 * struct page to store the metadata. In order to avoid conflicts caused by
 * subsequent use of more tail struct pages, we gather these discrete indexes
 * of tail struct page here.
 */
enum {
	SUBPAGE_INDEX_SUBPOOL = 1,	/* reuse page->private */
#ifdef CONFIG_CGROUP_HUGETLB
	SUBPAGE_INDEX_CGROUP,		/* reuse page->private */
	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
#endif
	__NR_USED_SUBPAGE,
};

struct hugepage_subpool {
	spinlock_t lock;
	long count;
	long max_hpages;	/* Maximum huge pages or -1 if no maximum. */
	long used_hpages;	/* Used count against maximum, includes */
				/* both allocated and reserved pages. */
	struct hstate *hstate;
	long min_hpages;	/* Minimum huge pages or -1 if no minimum. */
	long rsv_hpages;	/* Pages reserved against global pool to */
				/* satisfy minimum size. */
};

struct resv_map {
	struct kref refs;
	spinlock_t lock;
	struct list_head regions;
	long adds_in_progress;
	struct list_head region_cache;
	long region_cache_count;
#ifdef CONFIG_CGROUP_HUGETLB
	/*
	 * On private mappings, the counter to uncharge reservations is stored
	 * here. If these fields are 0, then either the mapping is shared, or
	 * cgroup accounting is disabled for this resv_map.
	 */
	struct page_counter *reservation_counter;
	unsigned long pages_per_hpage;
	struct cgroup_subsys_state *css;
#endif
};

/*
 * Region tracking -- allows tracking of reservations and instantiated pages
 *                    across the pages in a mapping.
 *
 * The region data structures are embedded into a resv_map and protected
 * by a resv_map's lock.  The set of regions within the resv_map represent
 * reservations for huge pages, or huge pages that have already been
 * instantiated within the map.  The from and to elements are huge page
 * indices into the associated mapping.  from indicates the starting index
 * of the region.  to represents the first index past the end of  the region.
 *
 * For example, a file region structure with from == 0 and to == 4 represents
 * four huge pages in a mapping.  It is important to note that the to element
 * represents the first element past the end of the region. This is used in
 * arithmetic as 4(to) - 0(from) = 4 huge pages in the region.
 *
 * Interval notation of the form [from, to) will be used to indicate that
 * the endpoint from is inclusive and to is exclusive.
 */
struct file_region {
	struct list_head link;
	long from;
	long to;
#ifdef CONFIG_CGROUP_HUGETLB
	/*
	 * On shared mappings, each reserved region appears as a struct
	 * file_region in resv_map. These fields hold the info needed to
	 * uncharge each reservation.
	 */
	struct page_counter *reservation_counter;
	struct cgroup_subsys_state *css;
#endif
};

extern struct resv_map *resv_map_alloc(void);
void resv_map_release(struct kref *ref);

extern spinlock_t hugetlb_lock;
extern int hugetlb_max_hstate __read_mostly;
#define for_each_hstate(h) \
	for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)

struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
						long min_hpages);
void hugepage_put_subpool(struct hugepage_subpool *spool);

void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
void clear_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *);
int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *,
		loff_t *);
int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *,
		loff_t *);
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *,
		loff_t *);

int move_hugetlb_page_tables(struct vm_area_struct *vma,
			     struct vm_area_struct *new_vma,
			     unsigned long old_addr, unsigned long new_addr,
			     unsigned long len);
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
			 struct page **, struct vm_area_struct **,
			 unsigned long *, unsigned long *, long, unsigned int,
			 int *);
void unmap_hugepage_range(struct vm_area_struct *,
			  unsigned long, unsigned long, struct page *);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
			  struct vm_area_struct *vma,
			  unsigned long start, unsigned long end,
			  struct page *ref_page);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(char *buf, int len, int nid);
void hugetlb_show_meminfo(void);
unsigned long hugetlb_total_pages(void);
vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, unsigned int flags);
#ifdef CONFIG_USERFAULTFD
int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte,
				struct vm_area_struct *dst_vma,
				unsigned long dst_addr,
				unsigned long src_addr,
				enum mcopy_atomic_mode mode,
				struct page **pagep);
#endif /* CONFIG_USERFAULTFD */
bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
						struct vm_area_struct *vma,
						vm_flags_t vm_flags);
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
						long freed);
bool isolate_huge_page(struct page *page, struct list_head *list);
int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
void putback_active_hugepage(struct page *page);
void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
void free_huge_page(struct page *page);
void hugetlb_fix_reserve_counts(struct inode *inode);
extern struct mutex *hugetlb_fault_mutex_table;
u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);

pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
		      unsigned long addr, pud_t *pud);

struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage);

extern int sysctl_hugetlb_shm_group;
extern struct list_head huge_boot_pages;

/* arch callbacks */

pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long addr, unsigned long sz);
pte_t *huge_pte_offset(struct mm_struct *mm,
		       unsigned long addr, unsigned long sz);
int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
				unsigned long *addr, pte_t *ptep);
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
				unsigned long *start, unsigned long *end);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
			      int write);
struct page *follow_huge_pd(struct vm_area_struct *vma,
			    unsigned long address, hugepd_t hpd,
			    int flags, int pdshift);
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
				pmd_t *pmd, int flags);
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
				pud_t *pud, int flags);
struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
			     pgd_t *pgd, int flags);

int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pud);
unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
		unsigned long address, unsigned long end, pgprot_t newprot);

bool is_hugetlb_entry_migration(pte_t pte);
void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);

#else /* !CONFIG_HUGETLB_PAGE */

static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}

static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}

static inline unsigned long hugetlb_total_pages(void)
{
	return 0;
}

static inline struct address_space *hugetlb_page_mapping_lock_write(
							struct page *hpage)
{
	return NULL;
}

static inline int huge_pmd_unshare(struct mm_struct *mm,
					struct vm_area_struct *vma,
					unsigned long *addr, pte_t *ptep)
{
	return 0;
}

static inline void adjust_range_if_pmd_sharing_possible(
				struct vm_area_struct *vma,
				unsigned long *start, unsigned long *end)
{
}

static inline long follow_hugetlb_page(struct mm_struct *mm,
			struct vm_area_struct *vma, struct page **pages,
			struct vm_area_struct **vmas, unsigned long *position,
			unsigned long *nr_pages, long i, unsigned int flags,
			int *nonblocking)
{
	BUG();
	return 0;
}

static inline struct page *follow_huge_addr(struct mm_struct *mm,
					unsigned long address, int write)
{
	return ERR_PTR(-EINVAL);
}

static inline int copy_hugetlb_page_range(struct mm_struct *dst,
			struct mm_struct *src, struct vm_area_struct *vma)
{
	BUG();
	return 0;
}

static inline int move_hugetlb_page_tables(struct vm_area_struct *vma,
					   struct vm_area_struct *new_vma,
					   unsigned long old_addr,
					   unsigned long new_addr,
					   unsigned long len)
{
	BUG();
	return 0;
}

static inline void hugetlb_report_meminfo(struct seq_file *m)
{
}

static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid)
{
	return 0;
}

static inline void hugetlb_show_meminfo(void)
{
}

static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
				unsigned long address, hugepd_t hpd, int flags,
				int pdshift)
{
	return NULL;
}

static inline struct page *follow_huge_pmd(struct mm_struct *mm,
				unsigned long address, pmd_t *pmd, int flags)
{
	return NULL;
}

static inline struct page *follow_huge_pud(struct mm_struct *mm,
				unsigned long address, pud_t *pud, int flags)
{
	return NULL;
}

static inline struct page *follow_huge_pgd(struct mm_struct *mm,
				unsigned long address, pgd_t *pgd, int flags)
{
	return NULL;
}

static inline int prepare_hugepage_range(struct file *file,
				unsigned long addr, unsigned long len)
{
	return -EINVAL;
}

static inline int pmd_huge(pmd_t pmd)
{
	return 0;
}

static inline int pud_huge(pud_t pud)
{
	return 0;
}

static inline int is_hugepage_only_range(struct mm_struct *mm,
					unsigned long addr, unsigned long len)
{
	return 0;
}

static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
{
	BUG();
}

#ifdef CONFIG_USERFAULTFD
static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
						pte_t *dst_pte,
						struct vm_area_struct *dst_vma,
						unsigned long dst_addr,
						unsigned long src_addr,
						enum mcopy_atomic_mode mode,
						struct page **pagep)
{
	BUG();
	return 0;
}
#endif /* CONFIG_USERFAULTFD */

static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
					unsigned long sz)
{
	return NULL;
}

static inline bool isolate_huge_page(struct page *page, struct list_head *list)
{
	return false;
}

static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
{
	return 0;
}

static inline void putback_active_hugepage(struct page *page)
{
}

static inline void move_hugetlb_state(struct page *oldpage,
					struct page *newpage, int reason)
{
}

static inline unsigned long hugetlb_change_protection(
			struct vm_area_struct *vma, unsigned long address,
			unsigned long end, pgprot_t newprot)
{
	return 0;
}

static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
			struct vm_area_struct *vma, unsigned long start,
			unsigned long end, struct page *ref_page)
{
	BUG();
}

static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
			struct vm_area_struct *vma, unsigned long address,
			unsigned int flags)
{
	BUG();
	return 0;
}

static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { }

#endif /* !CONFIG_HUGETLB_PAGE */
/*
 * hugepages at page global directory. If arch support
 * hugepages at pgd level, they need to define this.
 */
#ifndef pgd_huge
#define pgd_huge(x)	0
#endif
#ifndef p4d_huge
#define p4d_huge(x)	0
#endif

#ifndef pgd_write
static inline int pgd_write(pgd_t pgd)
{
	BUG();
	return 0;
}
#endif

#define HUGETLB_ANON_FILE "anon_hugepage"

enum {
	/*
	 * The file will be used as an shm file so shmfs accounting rules
	 * apply
	 */
	HUGETLB_SHMFS_INODE     = 1,
	/*
	 * The file is being created on the internal vfs mount and shmfs
	 * accounting rules do not apply
	 */
	HUGETLB_ANONHUGE_INODE  = 2,
};

#ifdef CONFIG_HUGETLBFS
struct hugetlbfs_sb_info {
	long	max_inodes;   /* inodes allowed */
	long	free_inodes;  /* inodes free */
	spinlock_t	stat_lock;
	struct hstate *hstate;
	struct hugepage_subpool *spool;
	kuid_t	uid;
	kgid_t	gid;
	umode_t mode;
};

static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
{
	return sb->s_fs_info;
}

struct hugetlbfs_inode_info {
	struct shared_policy policy;
	struct inode vfs_inode;
	unsigned int seals;
};

static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
{
	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
}

extern const struct file_operations hugetlbfs_file_operations;
extern const struct vm_operations_struct hugetlb_vm_ops;
struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
				int creat_flags, int page_size_log);

static inline bool is_file_hugepages(struct file *file)
{
	if (file->f_op == &hugetlbfs_file_operations)
		return true;

	return is_file_shm_hugepages(file);
}

static inline struct hstate *hstate_inode(struct inode *i)
{
	return HUGETLBFS_SB(i->i_sb)->hstate;
}
#else /* !CONFIG_HUGETLBFS */

#define is_file_hugepages(file)			false
static inline struct file *
hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
		int creat_flags, int page_size_log)
{
	return ERR_PTR(-ENOSYS);
}

static inline struct hstate *hstate_inode(struct inode *i)
{
	return NULL;
}
#endif /* !CONFIG_HUGETLBFS */

#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
					unsigned long len, unsigned long pgoff,
					unsigned long flags);
#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */

/*
 * huegtlb page specific state flags.  These flags are located in page.private
 * of the hugetlb head page.  Functions created via the below macros should be
 * used to manipulate these flags.
 *
 * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at
 *	allocation time.  Cleared when page is fully instantiated.  Free
 *	routine checks flag to restore a reservation on error paths.
 *	Synchronization:  Examined or modified by code that knows it has
 *	the only reference to page.  i.e. After allocation but before use
 *	or when the page is being freed.
 * HPG_migratable  - Set after a newly allocated page is added to the page
 *	cache and/or page tables.  Indicates the page is a candidate for
 *	migration.
 *	Synchronization:  Initially set after new page allocation with no
 *	locking.  When examined and modified during migration processing
 *	(isolate, migrate, putback) the hugetlb_lock is held.
 * HPG_temporary - - Set on a page that is temporarily allocated from the buddy
 *	allocator.  Typically used for migration target pages when no pages
 *	are available in the pool.  The hugetlb free page path will
 *	immediately free pages with this flag set to the buddy allocator.
 *	Synchronization: Can be set after huge page allocation from buddy when
 *	code knows it has only reference.  All other examinations and
 *	modifications require hugetlb_lock.
 * HPG_freed - Set when page is on the free lists.
 *	Synchronization: hugetlb_lock held for examination and modification.
 * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed.
 */
enum hugetlb_page_flags {
	HPG_restore_reserve = 0,
	HPG_migratable,
	HPG_temporary,
	HPG_freed,
	HPG_vmemmap_optimized,
	__NR_HPAGEFLAGS,
};

/*
 * Macros to create test, set and clear function definitions for
 * hugetlb specific page flags.
 */
#ifdef CONFIG_HUGETLB_PAGE
#define TESTHPAGEFLAG(uname, flname)				\
static inline int HPage##uname(struct page *page)		\
	{ return test_bit(HPG_##flname, &(page->private)); }

#define SETHPAGEFLAG(uname, flname)				\
static inline void SetHPage##uname(struct page *page)		\
	{ set_bit(HPG_##flname, &(page->private)); }

#define CLEARHPAGEFLAG(uname, flname)				\
static inline void ClearHPage##uname(struct page *page)		\
	{ clear_bit(HPG_##flname, &(page->private)); }
#else
#define TESTHPAGEFLAG(uname, flname)				\
static inline int HPage##uname(struct page *page)		\
	{ return 0; }

#define SETHPAGEFLAG(uname, flname)				\
static inline void SetHPage##uname(struct page *page)		\
	{ }

#define CLEARHPAGEFLAG(uname, flname)				\
static inline void ClearHPage##uname(struct page *page)		\
	{ }
#endif

#define HPAGEFLAG(uname, flname)				\
	TESTHPAGEFLAG(uname, flname)				\
	SETHPAGEFLAG(uname, flname)				\
	CLEARHPAGEFLAG(uname, flname)				\

/*
 * Create functions associated with hugetlb page flags
 */
HPAGEFLAG(RestoreReserve, restore_reserve)
HPAGEFLAG(Migratable, migratable)
HPAGEFLAG(Temporary, temporary)
HPAGEFLAG(Freed, freed)
HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)

#ifdef CONFIG_HUGETLB_PAGE

#define HSTATE_NAME_LEN 32
/* Defines one hugetlb page size */
struct hstate {
	struct mutex resize_lock;
	int next_nid_to_alloc;
	int next_nid_to_free;
	unsigned int order;
	unsigned int demote_order;
	unsigned long mask;
	unsigned long max_huge_pages;
	unsigned long nr_huge_pages;
	unsigned long free_huge_pages;
	unsigned long resv_huge_pages;
	unsigned long surplus_huge_pages;
	unsigned long nr_overcommit_huge_pages;
	struct list_head hugepage_activelist;
	struct list_head hugepage_freelists[MAX_NUMNODES];
	unsigned int max_huge_pages_node[MAX_NUMNODES];
	unsigned int nr_huge_pages_node[MAX_NUMNODES];
	unsigned int free_huge_pages_node[MAX_NUMNODES];
	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
	unsigned int nr_free_vmemmap_pages;
#endif
#ifdef CONFIG_CGROUP_HUGETLB
	/* cgroup control files */
	struct cftype cgroup_files_dfl[8];
	struct cftype cgroup_files_legacy[10];
#endif
	char name[HSTATE_NAME_LEN];
};

struct huge_bootmem_page {
	struct list_head list;
	struct hstate *hstate;
};

int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
struct page *alloc_huge_page(struct vm_area_struct *vma,
				unsigned long addr, int avoid_reserve);
struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
				nodemask_t *nmask, gfp_t gfp_mask);
struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
				unsigned long address);
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
			pgoff_t idx);
void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
				unsigned long address, struct page *page);

/* arch callback */
int __init __alloc_bootmem_huge_page(struct hstate *h, int nid);
int __init alloc_bootmem_huge_page(struct hstate *h, int nid);
bool __init hugetlb_node_alloc_supported(void);

void __init hugetlb_add_hstate(unsigned order);
bool __init arch_hugetlb_valid_size(unsigned long size);
struct hstate *size_to_hstate(unsigned long size);

#ifndef HUGE_MAX_HSTATE
#define HUGE_MAX_HSTATE 1
#endif

extern struct hstate hstates[HUGE_MAX_HSTATE];
extern unsigned int default_hstate_idx;

#define default_hstate (hstates[default_hstate_idx])

/*
 * hugetlb page subpool pointer located in hpage[1].private
 */
static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
{
	return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL);
}

static inline void hugetlb_set_page_subpool(struct page *hpage,
					struct hugepage_subpool *subpool)
{
	set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool);
}

static inline struct hstate *hstate_file(struct file *f)
{
	return hstate_inode(file_inode(f));
}

static inline struct hstate *hstate_sizelog(int page_size_log)
{
	if (!page_size_log)
		return &default_hstate;

	return size_to_hstate(1UL << page_size_log);
}

static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
	return hstate_file(vma->vm_file);
}

static inline unsigned long huge_page_size(struct hstate *h)
{
	return (unsigned long)PAGE_SIZE << h->order;
}

extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma);

extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma);

static inline unsigned long huge_page_mask(struct hstate *h)
{
	return h->mask;
}

static inline unsigned int huge_page_order(struct hstate *h)
{
	return h->order;
}

static inline unsigned huge_page_shift(struct hstate *h)
{
	return h->order + PAGE_SHIFT;
}

static inline bool hstate_is_gigantic(struct hstate *h)
{
	return huge_page_order(h) >= MAX_ORDER;
}

static inline unsigned int pages_per_huge_page(struct hstate *h)
{
	return 1 << h->order;
}

static inline unsigned int blocks_per_huge_page(struct hstate *h)
{
	return huge_page_size(h) / 512;
}

#include <asm/hugetlb.h>

#ifndef is_hugepage_only_range
static inline int is_hugepage_only_range(struct mm_struct *mm,
					unsigned long addr, unsigned long len)
{
	return 0;
}
#define is_hugepage_only_range is_hugepage_only_range
#endif

#ifndef arch_clear_hugepage_flags
static inline void arch_clear_hugepage_flags(struct page *page) { }
#define arch_clear_hugepage_flags arch_clear_hugepage_flags
#endif

#ifndef arch_make_huge_pte
static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
				       vm_flags_t flags)
{
	return entry;
}
#endif

static inline struct hstate *page_hstate(struct page *page)
{
	VM_BUG_ON_PAGE(!PageHuge(page), page);
	return size_to_hstate(page_size(page));
}

static inline unsigned hstate_index_to_shift(unsigned index)
{
	return hstates[index].order + PAGE_SHIFT;
}

static inline int hstate_index(struct hstate *h)
{
	return h - hstates;
}

extern int dissolve_free_huge_page(struct page *page);
extern int dissolve_free_huge_pages(unsigned long start_pfn,
				    unsigned long end_pfn);

#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
#ifndef arch_hugetlb_migration_supported
static inline bool arch_hugetlb_migration_supported(struct hstate *h)
{
	if ((huge_page_shift(h) == PMD_SHIFT) ||
		(huge_page_shift(h) == PUD_SHIFT) ||
			(huge_page_shift(h) == PGDIR_SHIFT))
		return true;
	else
		return false;
}
#endif
#else
static inline bool arch_hugetlb_migration_supported(struct hstate *h)
{
	return false;
}
#endif

static inline bool hugepage_migration_supported(struct hstate *h)
{
	return arch_hugetlb_migration_supported(h);
}

/*
 * Movability check is different as compared to migration check.
 * It determines whether or not a huge page should be placed on
 * movable zone or not. Movability of any huge page should be
 * required only if huge page size is supported for migration.
 * There won't be any reason for the huge page to be movable if
 * it is not migratable to start with. Also the size of the huge
 * page should be large enough to be placed under a movable zone
 * and still feasible enough to be migratable. Just the presence
 * in movable zone does not make the migration feasible.
 *
 * So even though large huge page sizes like the gigantic ones
 * are migratable they should not be movable because its not
 * feasible to migrate them from movable zone.
 */
static inline bool hugepage_movable_supported(struct hstate *h)
{
	if (!hugepage_migration_supported(h))
		return false;

	if (hstate_is_gigantic(h))
		return false;
	return true;
}

/* Movability of hugepages depends on migration support. */
static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
	if (hugepage_movable_supported(h))
		return GFP_HIGHUSER_MOVABLE;
	else
		return GFP_HIGHUSER;
}

static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
{
	gfp_t modified_mask = htlb_alloc_mask(h);

	/* Some callers might want to enforce node */
	modified_mask |= (gfp_mask & __GFP_THISNODE);

	modified_mask |= (gfp_mask & __GFP_NOWARN);

	return modified_mask;
}

static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
					   struct mm_struct *mm, pte_t *pte)
{
	if (huge_page_size(h) == PMD_SIZE)
		return pmd_lockptr(mm, (pmd_t *) pte);
	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
	return &mm->page_table_lock;
}

#ifndef hugepages_supported
/*
 * Some platform decide whether they support huge pages at boot
 * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0
 * when there is no such support
 */
#define hugepages_supported() (HPAGE_SHIFT != 0)
#endif

void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);

static inline void hugetlb_count_init(struct mm_struct *mm)
{
	atomic_long_set(&mm->hugetlb_usage, 0);
}

static inline void hugetlb_count_add(long l, struct mm_struct *mm)
{
	atomic_long_add(l, &mm->hugetlb_usage);
}

static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
{
	atomic_long_sub(l, &mm->hugetlb_usage);
}

#ifndef set_huge_swap_pte_at
static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
					pte_t *ptep, pte_t pte, unsigned long sz)
{
	set_huge_pte_at(mm, addr, ptep, pte);
}
#endif

#ifndef huge_ptep_modify_prot_start
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
						unsigned long addr, pte_t *ptep)
{
	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
#endif

#ifndef huge_ptep_modify_prot_commit
#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
						unsigned long addr, pte_t *ptep,
						pte_t old_pte, pte_t pte)
{
	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}
#endif

#else	/* CONFIG_HUGETLB_PAGE */
struct hstate {};

static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
{
	return NULL;
}

static inline int isolate_or_dissolve_huge_page(struct page *page,
						struct list_head *list)
{
	return -ENOMEM;
}

static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
					   unsigned long addr,
					   int avoid_reserve)
{
	return NULL;
}

static inline struct page *
alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
			nodemask_t *nmask, gfp_t gfp_mask)
{
	return NULL;
}

static inline struct page *alloc_huge_page_vma(struct hstate *h,
					       struct vm_area_struct *vma,
					       unsigned long address)
{
	return NULL;
}

static inline int __alloc_bootmem_huge_page(struct hstate *h)
{
	return 0;
}

static inline struct hstate *hstate_file(struct file *f)
{
	return NULL;
}

static inline struct hstate *hstate_sizelog(int page_size_log)
{
	return NULL;
}

static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
	return NULL;
}

static inline struct hstate *page_hstate(struct page *page)
{
	return NULL;
}

static inline unsigned long huge_page_size(struct hstate *h)
{
	return PAGE_SIZE;
}

static inline unsigned long huge_page_mask(struct hstate *h)
{
	return PAGE_MASK;
}

static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
	return PAGE_SIZE;
}

static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
	return PAGE_SIZE;
}

static inline unsigned int huge_page_order(struct hstate *h)
{
	return 0;
}

static inline unsigned int huge_page_shift(struct hstate *h)
{
	return PAGE_SHIFT;
}

static inline bool hstate_is_gigantic(struct hstate *h)
{
	return false;
}

static inline unsigned int pages_per_huge_page(struct hstate *h)
{
	return 1;
}

static inline unsigned hstate_index_to_shift(unsigned index)
{
	return 0;
}

static inline int hstate_index(struct hstate *h)
{
	return 0;
}

static inline int dissolve_free_huge_page(struct page *page)
{
	return 0;
}

static inline int dissolve_free_huge_pages(unsigned long start_pfn,
					   unsigned long end_pfn)
{
	return 0;
}

static inline bool hugepage_migration_supported(struct hstate *h)
{
	return false;
}

static inline bool hugepage_movable_supported(struct hstate *h)
{
	return false;
}

static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
	return 0;
}

static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
{
	return 0;
}

static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
					   struct mm_struct *mm, pte_t *pte)
{
	return &mm->page_table_lock;
}

static inline void hugetlb_count_init(struct mm_struct *mm)
{
}

static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
{
}

static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
{
}

static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
					pte_t *ptep, pte_t pte, unsigned long sz)
{
}
#endif	/* CONFIG_HUGETLB_PAGE */

#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
extern bool hugetlb_free_vmemmap_enabled;
#else
#define hugetlb_free_vmemmap_enabled	false
#endif

static inline spinlock_t *huge_pte_lock(struct hstate *h,
					struct mm_struct *mm, pte_t *pte)
{
	spinlock_t *ptl;

	ptl = huge_pte_lockptr(h, mm, pte);
	spin_lock(ptl);
	return ptl;
}

#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
extern void __init hugetlb_cma_reserve(int order);
extern void __init hugetlb_cma_check(void);
#else
static inline __init void hugetlb_cma_reserve(int order)
{
}
static inline __init void hugetlb_cma_check(void)
{
}
#endif

bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);

#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
/*
 * ARCHes with special requirements for evicting HUGETLB backing TLB entries can
 * implement this.
 */
#define flush_hugetlb_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
#endif

#endif /* _LINUX_HUGETLB_H */