aboutsummaryrefslogtreecommitdiff
path: root/fs/hugetlbfs/inode.c
blob: 8d0607b3726618f9f6ca58506c17670e8e5ca879 (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
/*
 * hugetlbpage-backed filesystem.  Based on ramfs.
 *
 * William Irwin, 2002
 *
 * Copyright (C) 2002 Linus Torvalds.
 */

#include <linux/module.h>
#include <linux/thread_info.h>
#include <asm/current.h>
#include <linux/sched.h>		/* remove ASAP */
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/kernel.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/ctype.h>
#include <linux/backing-dev.h>
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
#include <linux/parser.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
#include <linux/magic.h>

#include <asm/uaccess.h>

static const struct super_operations hugetlbfs_ops;
static const struct address_space_operations hugetlbfs_aops;
const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;

static struct backing_dev_info hugetlbfs_backing_dev_info = {
	.name		= "hugetlbfs",
	.ra_pages	= 0,	/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

int sysctl_hugetlb_shm_group;

enum {
	Opt_size, Opt_nr_inodes,
	Opt_mode, Opt_uid, Opt_gid,
	Opt_pagesize,
	Opt_err,
};

static const match_table_t tokens = {
	{Opt_size,	"size=%s"},
	{Opt_nr_inodes,	"nr_inodes=%s"},
	{Opt_mode,	"mode=%o"},
	{Opt_uid,	"uid=%u"},
	{Opt_gid,	"gid=%u"},
	{Opt_pagesize,	"pagesize=%s"},
	{Opt_err,	NULL},
};

static void huge_pagevec_release(struct pagevec *pvec)
{
	int i;

	for (i = 0; i < pagevec_count(pvec); ++i)
		put_page(pvec->pages[i]);

	pagevec_reinit(pvec);
}

static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	loff_t len, vma_len;
	int ret;
	struct hstate *h = hstate_file(file);

	/*
	 * vma address alignment (but not the pgoff alignment) has
	 * already been checked by prepare_hugepage_range.  If you add
	 * any error returns here, do so after setting VM_HUGETLB, so
	 * is_vm_hugetlb_page tests below unmap_region go the right
	 * way when do_mmap_pgoff unwinds (may be important on powerpc
	 * and ia64).
	 */
	vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
	vma->vm_ops = &hugetlb_vm_ops;

	if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT))
		return -EINVAL;

	vma_len = (loff_t)(vma->vm_end - vma->vm_start);

	mutex_lock(&inode->i_mutex);
	file_accessed(file);

	ret = -ENOMEM;
	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);

	if (hugetlb_reserve_pages(inode,
				vma->vm_pgoff >> huge_page_order(h),
				len >> huge_page_shift(h), vma,
				vma->vm_flags))
		goto out;

	ret = 0;
	hugetlb_prefault_arch_hook(vma->vm_mm);
	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
		inode->i_size = len;
out:
	mutex_unlock(&inode->i_mutex);

	return ret;
}

/*
 * Called under down_write(mmap_sem).
 */

#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
static unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long start_addr;
	struct hstate *h = hstate_file(file);

	if (len & ~huge_page_mask(h))
		return -EINVAL;
	if (len > TASK_SIZE)
		return -ENOMEM;

	if (flags & MAP_FIXED) {
		if (prepare_hugepage_range(file, addr, len))
			return -EINVAL;
		return addr;
	}

	if (addr) {
		addr = ALIGN(addr, huge_page_size(h));
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}

	start_addr = mm->free_area_cache;

	if (len <= mm->cached_hole_size)
		start_addr = TASK_UNMAPPED_BASE;

full_search:
	addr = ALIGN(start_addr, huge_page_size(h));

	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (TASK_SIZE - len < addr) {
			/*
			 * Start a new search - just in case we missed
			 * some holes.
			 */
			if (start_addr != TASK_UNMAPPED_BASE) {
				start_addr = TASK_UNMAPPED_BASE;
				goto full_search;
			}
			return -ENOMEM;
		}

		if (!vma || addr + len <= vma->vm_start)
			return addr;
		addr = ALIGN(vma->vm_end, huge_page_size(h));
	}
}
#endif

static int
hugetlbfs_read_actor(struct page *page, unsigned long offset,
			char __user *buf, unsigned long count,
			unsigned long size)
{
	char *kaddr;
	unsigned long left, copied = 0;
	int i, chunksize;

	if (size > count)
		size = count;

	/* Find which 4k chunk and offset with in that chunk */
	i = offset >> PAGE_CACHE_SHIFT;
	offset = offset & ~PAGE_CACHE_MASK;

	while (size) {
		chunksize = PAGE_CACHE_SIZE;
		if (offset)
			chunksize -= offset;
		if (chunksize > size)
			chunksize = size;
		kaddr = kmap(&page[i]);
		left = __copy_to_user(buf, kaddr + offset, chunksize);
		kunmap(&page[i]);
		if (left) {
			copied += (chunksize - left);
			break;
		}
		offset = 0;
		size -= chunksize;
		buf += chunksize;
		copied += chunksize;
		i++;
	}
	return copied ? copied : -EFAULT;
}

/*
 * Support for read() - Find the page attached to f_mapping and copy out the
 * data. Its *very* similar to do_generic_mapping_read(), we can't use that
 * since it has PAGE_CACHE_SIZE assumptions.
 */
static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
			      size_t len, loff_t *ppos)
{
	struct hstate *h = hstate_file(filp);
	struct address_space *mapping = filp->f_mapping;
	struct inode *inode = mapping->host;
	unsigned long index = *ppos >> huge_page_shift(h);
	unsigned long offset = *ppos & ~huge_page_mask(h);
	unsigned long end_index;
	loff_t isize;
	ssize_t retval = 0;

	mutex_lock(&inode->i_mutex);

	/* validate length */
	if (len == 0)
		goto out;

	isize = i_size_read(inode);
	if (!isize)
		goto out;

	end_index = (isize - 1) >> huge_page_shift(h);
	for (;;) {
		struct page *page;
		unsigned long nr, ret;
		int ra;

		/* nr is the maximum number of bytes to copy from this page */
		nr = huge_page_size(h);
		if (index >= end_index) {
			if (index > end_index)
				goto out;
			nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
			if (nr <= offset) {
				goto out;
			}
		}
		nr = nr - offset;

		/* Find the page */
		page = find_get_page(mapping, index);
		if (unlikely(page == NULL)) {
			/*
			 * We have a HOLE, zero out the user-buffer for the
			 * length of the hole or request.
			 */
			ret = len < nr ? len : nr;
			if (clear_user(buf, ret))
				ra = -EFAULT;
			else
				ra = 0;
		} else {
			/*
			 * We have the page, copy it to user space buffer.
			 */
			ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
			ret = ra;
		}
		if (ra < 0) {
			if (retval == 0)
				retval = ra;
			if (page)
				page_cache_release(page);
			goto out;
		}

		offset += ret;
		retval += ret;
		len -= ret;
		index += offset >> huge_page_shift(h);
		offset &= ~huge_page_mask(h);

		if (page)
			page_cache_release(page);

		/* short read or no more work */
		if ((ret != nr) || (len == 0))
			break;
	}
out:
	*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
	mutex_unlock(&inode->i_mutex);
	return retval;
}

static int hugetlbfs_write_begin(struct file *file,
			struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	return -EINVAL;
}

static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	BUG();
	return -EINVAL;
}

static void truncate_huge_page(struct page *page)
{
	cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
	ClearPageUptodate(page);
	remove_from_page_cache(page);
	put_page(page);
}

static void truncate_hugepages(struct inode *inode, loff_t lstart)
{
	struct hstate *h = hstate_inode(inode);
	struct address_space *mapping = &inode->i_data;
	const pgoff_t start = lstart >> huge_page_shift(h);
	struct pagevec pvec;
	pgoff_t next;
	int i, freed = 0;

	pagevec_init(&pvec, 0);
	next = start;
	while (1) {
		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
			if (next == start)
				break;
			next = start;
			continue;
		}

		for (i = 0; i < pagevec_count(&pvec); ++i) {
			struct page *page = pvec.pages[i];

			lock_page(page);
			if (page->index > next)
				next = page->index;
			++next;
			truncate_huge_page(page);
			unlock_page(page);
			freed++;
		}
		huge_pagevec_release(&pvec);
	}
	BUG_ON(!lstart && mapping->nrpages);
	hugetlb_unreserve_pages(inode, start, freed);
}

static void hugetlbfs_evict_inode(struct inode *inode)
{
	truncate_hugepages(inode, 0);
	end_writeback(inode);
}

static inline void
hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;

	vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) {
		unsigned long v_offset;

		/*
		 * Can the expression below overflow on 32-bit arches?
		 * No, because the prio_tree returns us only those vmas
		 * which overlap the truncated area starting at pgoff,
		 * and no vma on a 32-bit arch can span beyond the 4GB.
		 */
		if (vma->vm_pgoff < pgoff)
			v_offset = (pgoff - vma->vm_pgoff) << PAGE_SHIFT;
		else
			v_offset = 0;

		__unmap_hugepage_range(vma,
				vma->vm_start + v_offset, vma->vm_end, NULL);
	}
}

static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
{
	pgoff_t pgoff;
	struct address_space *mapping = inode->i_mapping;
	struct hstate *h = hstate_inode(inode);

	BUG_ON(offset & ~huge_page_mask(h));
	pgoff = offset >> PAGE_SHIFT;

	i_size_write(inode, offset);
	spin_lock(&mapping->i_mmap_lock);
	if (!prio_tree_empty(&mapping->i_mmap))
		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
	spin_unlock(&mapping->i_mmap_lock);
	truncate_hugepages(inode, offset);
	return 0;
}

static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct hstate *h = hstate_inode(inode);
	int error;
	unsigned int ia_valid = attr->ia_valid;

	BUG_ON(!inode);

	error = inode_change_ok(inode, attr);
	if (error)
		return error;

	if (ia_valid & ATTR_SIZE) {
		error = -EINVAL;
		if (attr->ia_size & ~huge_page_mask(h))
			return -EINVAL;
		error = hugetlb_vmtruncate(inode, attr->ia_size);
		if (error)
			return error;
	}

	setattr_copy(inode, attr);
	mark_inode_dirty(inode);
	return 0;
}

static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, 
					gid_t gid, int mode, dev_t dev)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode) {
		struct hugetlbfs_inode_info *info;
		inode->i_ino = get_next_ino();
		inode->i_mode = mode;
		inode->i_uid = uid;
		inode->i_gid = gid;
		inode->i_mapping->a_ops = &hugetlbfs_aops;
		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		INIT_LIST_HEAD(&inode->i_mapping->private_list);
		info = HUGETLBFS_I(inode);
		/*
		 * The policy is initialized here even if we are creating a
		 * private inode because initialization simply creates an
		 * an empty rb tree and calls spin_lock_init(), later when we
		 * call mpol_free_shared_policy() it will just return because
		 * the rb tree will still be empty.
		 */
		mpol_shared_policy_init(&info->policy, NULL);
		switch (mode & S_IFMT) {
		default:
			init_special_inode(inode, mode, dev);
			break;
		case S_IFREG:
			inode->i_op = &hugetlbfs_inode_operations;
			inode->i_fop = &hugetlbfs_file_operations;
			break;
		case S_IFDIR:
			inode->i_op = &hugetlbfs_dir_inode_operations;
			inode->i_fop = &simple_dir_operations;

			/* directory inodes start off with i_nlink == 2 (for "." entry) */
			inc_nlink(inode);
			break;
		case S_IFLNK:
			inode->i_op = &page_symlink_inode_operations;
			break;
		}
	}
	return inode;
}

/*
 * File creation. Allocate an inode, and we're done..
 */
static int hugetlbfs_mknod(struct inode *dir,
			struct dentry *dentry, int mode, dev_t dev)
{
	struct inode *inode;
	int error = -ENOSPC;
	gid_t gid;

	if (dir->i_mode & S_ISGID) {
		gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else {
		gid = current_fsgid();
	}
	inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, mode, dev);
	if (inode) {
		dir->i_ctime = dir->i_mtime = CURRENT_TIME;
		d_instantiate(dentry, inode);
		dget(dentry);	/* Extra count - pin the dentry in core */
		error = 0;
	}
	return error;
}

static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
	if (!retval)
		inc_nlink(dir);
	return retval;
}

static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
{
	return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}

static int hugetlbfs_symlink(struct inode *dir,
			struct dentry *dentry, const char *symname)
{
	struct inode *inode;
	int error = -ENOSPC;
	gid_t gid;

	if (dir->i_mode & S_ISGID)
		gid = dir->i_gid;
	else
		gid = current_fsgid();

	inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(),
					gid, S_IFLNK|S_IRWXUGO, 0);
	if (inode) {
		int l = strlen(symname)+1;
		error = page_symlink(inode, symname, l);
		if (!error) {
			d_instantiate(dentry, inode);
			dget(dentry);
		} else
			iput(inode);
	}
	dir->i_ctime = dir->i_mtime = CURRENT_TIME;

	return error;
}

/*
 * mark the head page dirty
 */
static int hugetlbfs_set_page_dirty(struct page *page)
{
	struct page *head = compound_head(page);

	SetPageDirty(head);
	return 0;
}

static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
	struct hstate *h = hstate_inode(dentry->d_inode);

	buf->f_type = HUGETLBFS_MAGIC;
	buf->f_bsize = huge_page_size(h);
	if (sbinfo) {
		spin_lock(&sbinfo->stat_lock);
		/* If no limits set, just report 0 for max/free/used
		 * blocks, like simple_statfs() */
		if (sbinfo->max_blocks >= 0) {
			buf->f_blocks = sbinfo->max_blocks;
			buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
			buf->f_files = sbinfo->max_inodes;
			buf->f_ffree = sbinfo->free_inodes;
		}
		spin_unlock(&sbinfo->stat_lock);
	}
	buf->f_namelen = NAME_MAX;
	return 0;
}

static void hugetlbfs_put_super(struct super_block *sb)
{
	struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb);

	if (sbi) {
		sb->s_fs_info = NULL;
		kfree(sbi);
	}
}

static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		if (unlikely(!sbinfo->free_inodes)) {
			spin_unlock(&sbinfo->stat_lock);
			return 0;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	return 1;
}

static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
}


static struct kmem_cache *hugetlbfs_inode_cachep;

static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);
	struct hugetlbfs_inode_info *p;

	if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
		return NULL;
	p = kmem_cache_alloc(hugetlbfs_inode_cachep, GFP_KERNEL);
	if (unlikely(!p)) {
		hugetlbfs_inc_free_inodes(sbinfo);
		return NULL;
	}
	return &p->vfs_inode;
}

static void hugetlbfs_destroy_inode(struct inode *inode)
{
	hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
	mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}

static const struct address_space_operations hugetlbfs_aops = {
	.write_begin	= hugetlbfs_write_begin,
	.write_end	= hugetlbfs_write_end,
	.set_page_dirty	= hugetlbfs_set_page_dirty,
};


static void init_once(void *foo)
{
	struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;

	inode_init_once(&ei->vfs_inode);
}

const struct file_operations hugetlbfs_file_operations = {
	.read			= hugetlbfs_read,
	.mmap			= hugetlbfs_file_mmap,
	.fsync			= noop_fsync,
	.get_unmapped_area	= hugetlb_get_unmapped_area,
	.llseek		= default_llseek,
};

static const struct inode_operations hugetlbfs_dir_inode_operations = {
	.create		= hugetlbfs_create,
	.lookup		= simple_lookup,
	.link		= simple_link,
	.unlink		= simple_unlink,
	.symlink	= hugetlbfs_symlink,
	.mkdir		= hugetlbfs_mkdir,
	.rmdir		= simple_rmdir,
	.mknod		= hugetlbfs_mknod,
	.rename		= simple_rename,
	.setattr	= hugetlbfs_setattr,
};

static const struct inode_operations hugetlbfs_inode_operations = {
	.setattr	= hugetlbfs_setattr,
};

static const struct super_operations hugetlbfs_ops = {
	.alloc_inode    = hugetlbfs_alloc_inode,
	.destroy_inode  = hugetlbfs_destroy_inode,
	.evict_inode	= hugetlbfs_evict_inode,
	.statfs		= hugetlbfs_statfs,
	.put_super	= hugetlbfs_put_super,
	.show_options	= generic_show_options,
};

static int
hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
{
	char *p, *rest;
	substring_t args[MAX_OPT_ARGS];
	int option;
	unsigned long long size = 0;
	enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE;

	if (!options)
		return 0;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_uid:
			if (match_int(&args[0], &option))
 				goto bad_val;
			pconfig->uid = option;
			break;

		case Opt_gid:
			if (match_int(&args[0], &option))
 				goto bad_val;
			pconfig->gid = option;
			break;

		case Opt_mode:
			if (match_octal(&args[0], &option))
 				goto bad_val;
			pconfig->mode = option & 01777U;
			break;

		case Opt_size: {
			/* memparse() will accept a K/M/G without a digit */
			if (!isdigit(*args[0].from))
				goto bad_val;
			size = memparse(args[0].from, &rest);
			setsize = SIZE_STD;
			if (*rest == '%')
				setsize = SIZE_PERCENT;
			break;
		}

		case Opt_nr_inodes:
			/* memparse() will accept a K/M/G without a digit */
			if (!isdigit(*args[0].from))
				goto bad_val;
			pconfig->nr_inodes = memparse(args[0].from, &rest);
			break;

		case Opt_pagesize: {
			unsigned long ps;
			ps = memparse(args[0].from, &rest);
			pconfig->hstate = size_to_hstate(ps);
			if (!pconfig->hstate) {
				printk(KERN_ERR
				"hugetlbfs: Unsupported page size %lu MB\n",
					ps >> 20);
				return -EINVAL;
			}
			break;
		}

		default:
			printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
				 p);
			return -EINVAL;
			break;
		}
	}

	/* Do size after hstate is set up */
	if (setsize > NO_SIZE) {
		struct hstate *h = pconfig->hstate;
		if (setsize == SIZE_PERCENT) {
			size <<= huge_page_shift(h);
			size *= h->max_huge_pages;
			do_div(size, 100);
		}
		pconfig->nr_blocks = (size >> huge_page_shift(h));
	}

	return 0;

bad_val:
 	printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
	       args[0].from, p);
 	return -EINVAL;
}

static int
hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode * inode;
	struct dentry * root;
	int ret;
	struct hugetlbfs_config config;
	struct hugetlbfs_sb_info *sbinfo;

	save_mount_options(sb, data);

	config.nr_blocks = -1; /* No limit on size by default */
	config.nr_inodes = -1; /* No limit on number of inodes by default */
	config.uid = current_fsuid();
	config.gid = current_fsgid();
	config.mode = 0755;
	config.hstate = &default_hstate;
	ret = hugetlbfs_parse_options(data, &config);
	if (ret)
		return ret;

	sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL);
	if (!sbinfo)
		return -ENOMEM;
	sb->s_fs_info = sbinfo;
	sbinfo->hstate = config.hstate;
	spin_lock_init(&sbinfo->stat_lock);
	sbinfo->max_blocks = config.nr_blocks;
	sbinfo->free_blocks = config.nr_blocks;
	sbinfo->max_inodes = config.nr_inodes;
	sbinfo->free_inodes = config.nr_inodes;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_blocksize = huge_page_size(config.hstate);
	sb->s_blocksize_bits = huge_page_shift(config.hstate);
	sb->s_magic = HUGETLBFS_MAGIC;
	sb->s_op = &hugetlbfs_ops;
	sb->s_time_gran = 1;
	inode = hugetlbfs_get_inode(sb, config.uid, config.gid,
					S_IFDIR | config.mode, 0);
	if (!inode)
		goto out_free;

	root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		goto out_free;
	}
	sb->s_root = root;
	return 0;
out_free:
	kfree(sbinfo);
	return -ENOMEM;
}

int hugetlb_get_quota(struct address_space *mapping, long delta)
{
	int ret = 0;
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);

	if (sbinfo->free_blocks > -1) {
		spin_lock(&sbinfo->stat_lock);
		if (sbinfo->free_blocks - delta >= 0)
			sbinfo->free_blocks -= delta;
		else
			ret = -ENOMEM;
		spin_unlock(&sbinfo->stat_lock);
	}

	return ret;
}

void hugetlb_put_quota(struct address_space *mapping, long delta)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);

	if (sbinfo->free_blocks > -1) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_blocks += delta;
		spin_unlock(&sbinfo->stat_lock);
	}
}

static int hugetlbfs_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_nodev(fs_type, flags, data, hugetlbfs_fill_super, mnt);
}

static struct file_system_type hugetlbfs_fs_type = {
	.name		= "hugetlbfs",
	.get_sb		= hugetlbfs_get_sb,
	.kill_sb	= kill_litter_super,
};

static struct vfsmount *hugetlbfs_vfsmount;

static int can_do_hugetlb_shm(void)
{
	return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
}

struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
				struct user_struct **user, int creat_flags)
{
	int error = -ENOMEM;
	struct file *file;
	struct inode *inode;
	struct path path;
	struct dentry *root;
	struct qstr quick_string;

	*user = NULL;
	if (!hugetlbfs_vfsmount)
		return ERR_PTR(-ENOENT);

	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
		*user = current_user();
		if (user_shm_lock(size, *user)) {
			WARN_ONCE(1,
			  "Using mlock ulimits for SHM_HUGETLB deprecated\n");
		} else {
			*user = NULL;
			return ERR_PTR(-EPERM);
		}
	}

	root = hugetlbfs_vfsmount->mnt_root;
	quick_string.name = name;
	quick_string.len = strlen(quick_string.name);
	quick_string.hash = 0;
	path.dentry = d_alloc(root, &quick_string);
	if (!path.dentry)
		goto out_shm_unlock;

	path.mnt = mntget(hugetlbfs_vfsmount);
	error = -ENOSPC;
	inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(),
				current_fsgid(), S_IFREG | S_IRWXUGO, 0);
	if (!inode)
		goto out_dentry;

	error = -ENOMEM;
	if (hugetlb_reserve_pages(inode, 0,
			size >> huge_page_shift(hstate_inode(inode)), NULL,
			acctflag))
		goto out_inode;

	d_instantiate(path.dentry, inode);
	inode->i_size = size;
	inode->i_nlink = 0;

	error = -ENFILE;
	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
			&hugetlbfs_file_operations);
	if (!file)
		goto out_dentry; /* inode is already attached */

	return file;

out_inode:
	iput(inode);
out_dentry:
	path_put(&path);
out_shm_unlock:
	if (*user) {
		user_shm_unlock(size, *user);
		*user = NULL;
	}
	return ERR_PTR(error);
}

static int __init init_hugetlbfs_fs(void)
{
	int error;
	struct vfsmount *vfsmount;

	error = bdi_init(&hugetlbfs_backing_dev_info);
	if (error)
		return error;

	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
					sizeof(struct hugetlbfs_inode_info),
					0, 0, init_once);
	if (hugetlbfs_inode_cachep == NULL)
		goto out2;

	error = register_filesystem(&hugetlbfs_fs_type);
	if (error)
		goto out;

	vfsmount = kern_mount(&hugetlbfs_fs_type);

	if (!IS_ERR(vfsmount)) {
		hugetlbfs_vfsmount = vfsmount;
		return 0;
	}

	error = PTR_ERR(vfsmount);

 out:
	if (error)
		kmem_cache_destroy(hugetlbfs_inode_cachep);
 out2:
	bdi_destroy(&hugetlbfs_backing_dev_info);
	return error;
}

static void __exit exit_hugetlbfs_fs(void)
{
	kmem_cache_destroy(hugetlbfs_inode_cachep);
	unregister_filesystem(&hugetlbfs_fs_type);
	bdi_destroy(&hugetlbfs_backing_dev_info);
}

module_init(init_hugetlbfs_fs)
module_exit(exit_hugetlbfs_fs)

MODULE_LICENSE("GPL");