summaryrefslogtreecommitdiffstats
path: root/fs/cramfs/inode.c
blob: d7a600e00f289ab16ba9a9709007a6acdb832ddf (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
/*
 * Compressed rom filesystem for Linux.
 *
 * Copyright (C) 1999 Linus Torvalds.
 *
 * This file is released under the GPL.
 */

/*
 * These are the VFS interfaces to the compressed rom filesystem.
 * The actual compression is based on zlib, see the other files.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/pfn_t.h>
#include <linux/ramfs.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/blkdev.h>
#include <linux/mtd/mtd.h>
#include <linux/mtd/super.h>
#include <linux/slab.h>
#include <linux/vfs.h>
#include <linux/mutex.h>
#include <uapi/linux/cramfs_fs.h>
#include <linux/uaccess.h>

#include "internal.h"

/*
 * cramfs super-block data in memory
 */
struct cramfs_sb_info {
	unsigned long magic;
	unsigned long size;
	unsigned long blocks;
	unsigned long files;
	unsigned long flags;
	void *linear_virt_addr;
	resource_size_t linear_phys_addr;
	size_t mtd_point_size;
};

static inline struct cramfs_sb_info *CRAMFS_SB(struct super_block *sb)
{
	return sb->s_fs_info;
}

static const struct super_operations cramfs_ops;
static const struct inode_operations cramfs_dir_inode_operations;
static const struct file_operations cramfs_directory_operations;
static const struct file_operations cramfs_physmem_fops;
static const struct address_space_operations cramfs_aops;

static DEFINE_MUTEX(read_mutex);


/* These macros may change in future, to provide better st_ino semantics. */
#define OFFSET(x)	((x)->i_ino)

static unsigned long cramino(const struct cramfs_inode *cino, unsigned int offset)
{
	if (!cino->offset)
		return offset + 1;
	if (!cino->size)
		return offset + 1;

	/*
	 * The file mode test fixes buggy mkcramfs implementations where
	 * cramfs_inode->offset is set to a non zero value for entries
	 * which did not contain data, like devices node and fifos.
	 */
	switch (cino->mode & S_IFMT) {
	case S_IFREG:
	case S_IFDIR:
	case S_IFLNK:
		return cino->offset << 2;
	default:
		break;
	}
	return offset + 1;
}

static struct inode *get_cramfs_inode(struct super_block *sb,
	const struct cramfs_inode *cramfs_inode, unsigned int offset)
{
	struct inode *inode;
	static struct timespec64 zerotime;

	inode = iget_locked(sb, cramino(cramfs_inode, offset));
	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	switch (cramfs_inode->mode & S_IFMT) {
	case S_IFREG:
		inode->i_fop = &generic_ro_fops;
		inode->i_data.a_ops = &cramfs_aops;
		if (IS_ENABLED(CONFIG_CRAMFS_MTD) &&
		    CRAMFS_SB(sb)->flags & CRAMFS_FLAG_EXT_BLOCK_POINTERS &&
		    CRAMFS_SB(sb)->linear_phys_addr)
			inode->i_fop = &cramfs_physmem_fops;
		break;
	case S_IFDIR:
		inode->i_op = &cramfs_dir_inode_operations;
		inode->i_fop = &cramfs_directory_operations;
		break;
	case S_IFLNK:
		inode->i_op = &page_symlink_inode_operations;
		inode_nohighmem(inode);
		inode->i_data.a_ops = &cramfs_aops;
		break;
	default:
		init_special_inode(inode, cramfs_inode->mode,
				old_decode_dev(cramfs_inode->size));
	}

	inode->i_mode = cramfs_inode->mode;
	i_uid_write(inode, cramfs_inode->uid);
	i_gid_write(inode, cramfs_inode->gid);

	/* if the lower 2 bits are zero, the inode contains data */
	if (!(inode->i_ino & 3)) {
		inode->i_size = cramfs_inode->size;
		inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1;
	}

	/* Struct copy intentional */
	inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime;
	/* inode->i_nlink is left 1 - arguably wrong for directories,
	   but it's the best we can do without reading the directory
	   contents.  1 yields the right result in GNU find, even
	   without -noleaf option. */

	unlock_new_inode(inode);

	return inode;
}

/*
 * We have our own block cache: don't fill up the buffer cache
 * with the rom-image, because the way the filesystem is set
 * up the accesses should be fairly regular and cached in the
 * page cache and dentry tree anyway..
 *
 * This also acts as a way to guarantee contiguous areas of up to
 * BLKS_PER_BUF*PAGE_SIZE, so that the caller doesn't need to
 * worry about end-of-buffer issues even when decompressing a full
 * page cache.
 *
 * Note: This is all optimized away at compile time when
 *       CONFIG_CRAMFS_BLOCKDEV=n.
 */
#define READ_BUFFERS (2)
/* NEXT_BUFFER(): Loop over [0..(READ_BUFFERS-1)]. */
#define NEXT_BUFFER(_ix) ((_ix) ^ 1)

/*
 * BLKS_PER_BUF_SHIFT should be at least 2 to allow for "compressed"
 * data that takes up more space than the original and with unlucky
 * alignment.
 */
#define BLKS_PER_BUF_SHIFT	(2)
#define BLKS_PER_BUF		(1 << BLKS_PER_BUF_SHIFT)
#define BUFFER_SIZE		(BLKS_PER_BUF*PAGE_SIZE)

static unsigned char read_buffers[READ_BUFFERS][BUFFER_SIZE];
static unsigned buffer_blocknr[READ_BUFFERS];
static struct super_block *buffer_dev[READ_BUFFERS];
static int next_buffer;

/*
 * Populate our block cache and return a pointer to it.
 */
static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset,
				unsigned int len)
{
	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
	struct page *pages[BLKS_PER_BUF];
	unsigned i, blocknr, buffer;
	unsigned long devsize;
	char *data;

	if (!len)
		return NULL;
	blocknr = offset >> PAGE_SHIFT;
	offset &= PAGE_SIZE - 1;

	/* Check if an existing buffer already has the data.. */
	for (i = 0; i < READ_BUFFERS; i++) {
		unsigned int blk_offset;

		if (buffer_dev[i] != sb)
			continue;
		if (blocknr < buffer_blocknr[i])
			continue;
		blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_SHIFT;
		blk_offset += offset;
		if (blk_offset + len > BUFFER_SIZE)
			continue;
		return read_buffers[i] + blk_offset;
	}

	devsize = mapping->host->i_size >> PAGE_SHIFT;

	/* Ok, read in BLKS_PER_BUF pages completely first. */
	for (i = 0; i < BLKS_PER_BUF; i++) {
		struct page *page = NULL;

		if (blocknr + i < devsize) {
			page = read_mapping_page(mapping, blocknr + i, NULL);
			/* synchronous error? */
			if (IS_ERR(page))
				page = NULL;
		}
		pages[i] = page;
	}

	for (i = 0; i < BLKS_PER_BUF; i++) {
		struct page *page = pages[i];

		if (page) {
			wait_on_page_locked(page);
			if (!PageUptodate(page)) {
				/* asynchronous error */
				put_page(page);
				pages[i] = NULL;
			}
		}
	}

	buffer = next_buffer;
	next_buffer = NEXT_BUFFER(buffer);
	buffer_blocknr[buffer] = blocknr;
	buffer_dev[buffer] = sb;

	data = read_buffers[buffer];
	for (i = 0; i < BLKS_PER_BUF; i++) {
		struct page *page = pages[i];

		if (page) {
			memcpy(data, kmap(page), PAGE_SIZE);
			kunmap(page);
			put_page(page);
		} else
			memset(data, 0, PAGE_SIZE);
		data += PAGE_SIZE;
	}
	return read_buffers[buffer] + offset;
}

/*
 * Return a pointer to the linearly addressed cramfs image in memory.
 */
static void *cramfs_direct_read(struct super_block *sb, unsigned int offset,
				unsigned int len)
{
	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);

	if (!len)
		return NULL;
	if (len > sbi->size || offset > sbi->size - len)
		return page_address(ZERO_PAGE(0));
	return sbi->linear_virt_addr + offset;
}

/*
 * Returns a pointer to a buffer containing at least LEN bytes of
 * filesystem starting at byte offset OFFSET into the filesystem.
 */
static void *cramfs_read(struct super_block *sb, unsigned int offset,
			 unsigned int len)
{
	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);

	if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sbi->linear_virt_addr)
		return cramfs_direct_read(sb, offset, len);
	else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV))
		return cramfs_blkdev_read(sb, offset, len);
	else
		return NULL;
}

/*
 * For a mapping to be possible, we need a range of uncompressed and
 * contiguous blocks. Return the offset for the first block and number of
 * valid blocks for which that is true, or zero otherwise.
 */
static u32 cramfs_get_block_range(struct inode *inode, u32 pgoff, u32 *pages)
{
	struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb);
	int i;
	u32 *blockptrs, first_block_addr;

	/*
	 * We can dereference memory directly here as this code may be
	 * reached only when there is a direct filesystem image mapping
	 * available in memory.
	 */
	blockptrs = (u32 *)(sbi->linear_virt_addr + OFFSET(inode) + pgoff * 4);
	first_block_addr = blockptrs[0] & ~CRAMFS_BLK_FLAGS;
	i = 0;
	do {
		u32 block_off = i * (PAGE_SIZE >> CRAMFS_BLK_DIRECT_PTR_SHIFT);
		u32 expect = (first_block_addr + block_off) |
			     CRAMFS_BLK_FLAG_DIRECT_PTR |
			     CRAMFS_BLK_FLAG_UNCOMPRESSED;
		if (blockptrs[i] != expect) {
			pr_debug("range: block %d/%d got %#x expects %#x\n",
				 pgoff+i, pgoff + *pages - 1,
				 blockptrs[i], expect);
			if (i == 0)
				return 0;
			break;
		}
	} while (++i < *pages);

	*pages = i;
	return first_block_addr << CRAMFS_BLK_DIRECT_PTR_SHIFT;
}

#ifdef CONFIG_MMU

/*
 * Return true if the last page of a file in the filesystem image contains
 * some other data that doesn't belong to that file. It is assumed that the
 * last block is CRAMFS_BLK_FLAG_DIRECT_PTR | CRAMFS_BLK_FLAG_UNCOMPRESSED
 * (verified by cramfs_get_block_range() and directly accessible in memory.
 */
static bool cramfs_last_page_is_shared(struct inode *inode)
{
	struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb);
	u32 partial, last_page, blockaddr, *blockptrs;
	char *tail_data;

	partial = offset_in_page(inode->i_size);
	if (!partial)
		return false;
	last_page = inode->i_size >> PAGE_SHIFT;
	blockptrs = (u32 *)(sbi->linear_virt_addr + OFFSET(inode));
	blockaddr = blockptrs[last_page] & ~CRAMFS_BLK_FLAGS;
	blockaddr <<= CRAMFS_BLK_DIRECT_PTR_SHIFT;
	tail_data = sbi->linear_virt_addr + blockaddr + partial;
	return memchr_inv(tail_data, 0, PAGE_SIZE - partial) ? true : false;
}

static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file_inode(file);
	struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb);
	unsigned int pages, max_pages, offset;
	unsigned long address, pgoff = vma->vm_pgoff;
	char *bailout_reason;
	int ret;

	ret = generic_file_readonly_mmap(file, vma);
	if (ret)
		return ret;

	/*
	 * Now try to pre-populate ptes for this vma with a direct
	 * mapping avoiding memory allocation when possible.
	 */

	/* Could COW work here? */
	bailout_reason = "vma is writable";
	if (vma->vm_flags & VM_WRITE)
		goto bailout;

	max_pages = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	bailout_reason = "beyond file limit";
	if (pgoff >= max_pages)
		goto bailout;
	pages = min(vma_pages(vma), max_pages - pgoff);

	offset = cramfs_get_block_range(inode, pgoff, &pages);
	bailout_reason = "unsuitable block layout";
	if (!offset)
		goto bailout;
	address = sbi->linear_phys_addr + offset;
	bailout_reason = "data is not page aligned";
	if (!PAGE_ALIGNED(address))
		goto bailout;

	/* Don't map the last page if it contains some other data */
	if (pgoff + pages == max_pages && cramfs_last_page_is_shared(inode)) {
		pr_debug("mmap: %s: last page is shared\n",
			 file_dentry(file)->d_name.name);
		pages--;
	}

	if (!pages) {
		bailout_reason = "no suitable block remaining";
		goto bailout;
	}

	if (pages == vma_pages(vma)) {
		/*
		 * The entire vma is mappable. remap_pfn_range() will
		 * make it distinguishable from a non-direct mapping
		 * in /proc/<pid>/maps by substituting the file offset
		 * with the actual physical address.
		 */
		ret = remap_pfn_range(vma, vma->vm_start, address >> PAGE_SHIFT,
				      pages * PAGE_SIZE, vma->vm_page_prot);
	} else {
		/*
		 * Let's create a mixed map if we can't map it all.
		 * The normal paging machinery will take care of the
		 * unpopulated ptes via cramfs_readpage().
		 */
		int i;
		vma->vm_flags |= VM_MIXEDMAP;
		for (i = 0; i < pages && !ret; i++) {
			unsigned long off = i * PAGE_SIZE;
			pfn_t pfn = phys_to_pfn_t(address + off, PFN_DEV);
			ret = vm_insert_mixed(vma, vma->vm_start + off, pfn);
		}
	}

	if (!ret)
		pr_debug("mapped %s[%lu] at 0x%08lx (%u/%lu pages) "
			 "to vma 0x%08lx, page_prot 0x%llx\n",
			 file_dentry(file)->d_name.name, pgoff,
			 address, pages, vma_pages(vma), vma->vm_start,
			 (unsigned long long)pgprot_val(vma->vm_page_prot));
	return ret;

bailout:
	pr_debug("%s[%lu]: direct mmap impossible: %s\n",
		 file_dentry(file)->d_name.name, pgoff, bailout_reason);
	/* Didn't manage any direct map, but normal paging is still possible */
	return 0;
}

#else /* CONFIG_MMU */

static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
{
	return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS;
}

static unsigned long cramfs_physmem_get_unmapped_area(struct file *file,
			unsigned long addr, unsigned long len,
			unsigned long pgoff, unsigned long flags)
{
	struct inode *inode = file_inode(file);
	struct super_block *sb = inode->i_sb;
	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
	unsigned int pages, block_pages, max_pages, offset;

	pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	max_pages = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (pgoff >= max_pages || pages > max_pages - pgoff)
		return -EINVAL;
	block_pages = pages;
	offset = cramfs_get_block_range(inode, pgoff, &block_pages);
	if (!offset || block_pages != pages)
		return -ENOSYS;
	addr = sbi->linear_phys_addr + offset;
	pr_debug("get_unmapped for %s ofs %#lx siz %lu at 0x%08lx\n",
		 file_dentry(file)->d_name.name, pgoff*PAGE_SIZE, len, addr);
	return addr;
}

static unsigned int cramfs_physmem_mmap_capabilities(struct file *file)
{
	return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT |
	       NOMMU_MAP_READ | NOMMU_MAP_EXEC;
}

#endif /* CONFIG_MMU */

static const struct file_operations cramfs_physmem_fops = {
	.llseek			= generic_file_llseek,
	.read_iter		= generic_file_read_iter,
	.splice_read		= generic_file_splice_read,
	.mmap			= cramfs_physmem_mmap,
#ifndef CONFIG_MMU
	.get_unmapped_area	= cramfs_physmem_get_unmapped_area,
	.mmap_capabilities	= cramfs_physmem_mmap_capabilities,
#endif
};

static void cramfs_kill_sb(struct super_block *sb)
{
	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);

	if (IS_ENABLED(CCONFIG_CRAMFS_MTD) && sb->s_mtd) {
		if (sbi && sbi->mtd_point_size)
			mtd_unpoint(sb->s_mtd, 0, sbi->mtd_point_size);
		kill_mtd_super(sb);
	} else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) {
		kill_block_super(sb);
	}
	kfree(sbi);
}

static int cramfs_remount(struct super_block *sb, int *flags, char *data)
{
	sync_filesystem(sb);
	*flags |= SB_RDONLY;
	return 0;
}

static int cramfs_read_super(struct super_block *sb,
			     struct cramfs_super *super, int silent)
{
	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
	unsigned long root_offset;

	/* We don't know the real size yet */
	sbi->size = PAGE_SIZE;

	/* Read the first block and get the superblock from it */
	mutex_lock(&read_mutex);
	memcpy(super, cramfs_read(sb, 0, sizeof(*super)), sizeof(*super));
	mutex_unlock(&read_mutex);

	/* Do sanity checks on the superblock */
	if (super->magic != CRAMFS_MAGIC) {
		/* check for wrong endianness */
		if (super->magic == CRAMFS_MAGIC_WEND) {
			if (!silent)
				pr_err("wrong endianness\n");
			return -EINVAL;
		}

		/* check at 512 byte offset */
		mutex_lock(&read_mutex);
		memcpy(super,
		       cramfs_read(sb, 512, sizeof(*super)),
		       sizeof(*super));
		mutex_unlock(&read_mutex);
		if (super->magic != CRAMFS_MAGIC) {
			if (super->magic == CRAMFS_MAGIC_WEND && !silent)
				pr_err("wrong endianness\n");
			else if (!silent)
				pr_err("wrong magic\n");
			return -EINVAL;
		}
	}

	/* get feature flags first */
	if (super->flags & ~CRAMFS_SUPPORTED_FLAGS) {
		pr_err("unsupported filesystem features\n");
		return -EINVAL;
	}

	/* Check that the root inode is in a sane state */
	if (!S_ISDIR(super->root.mode)) {
		pr_err("root is not a directory\n");
		return -EINVAL;
	}
	/* correct strange, hard-coded permissions of mkcramfs */
	super->root.mode |= 0555;

	root_offset = super->root.offset << 2;
	if (super->flags & CRAMFS_FLAG_FSID_VERSION_2) {
		sbi->size = super->size;
		sbi->blocks = super->fsid.blocks;
		sbi->files = super->fsid.files;
	} else {
		sbi->size = 1<<28;
		sbi->blocks = 0;
		sbi->files = 0;
	}
	sbi->magic = super->magic;
	sbi->flags = super->flags;
	if (root_offset == 0)
		pr_info("empty filesystem");
	else if (!(super->flags & CRAMFS_FLAG_SHIFTED_ROOT_OFFSET) &&
		 ((root_offset != sizeof(struct cramfs_super)) &&
		  (root_offset != 512 + sizeof(struct cramfs_super))))
	{
		pr_err("bad root offset %lu\n", root_offset);
		return -EINVAL;
	}

	return 0;
}

static int cramfs_finalize_super(struct super_block *sb,
				 struct cramfs_inode *cramfs_root)
{
	struct inode *root;

	/* Set it all up.. */
	sb->s_flags |= SB_RDONLY;
	sb->s_op = &cramfs_ops;
	root = get_cramfs_inode(sb, cramfs_root, 0);
	if (IS_ERR(root))
		return PTR_ERR(root);
	sb->s_root = d_make_root(root);
	if (!sb->s_root)
		return -ENOMEM;
	return 0;
}

static int cramfs_blkdev_fill_super(struct super_block *sb, void *data,
				    int silent)
{
	struct cramfs_sb_info *sbi;
	struct cramfs_super super;
	int i, err;

	sbi = kzalloc(sizeof(struct cramfs_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;

	/* Invalidate the read buffers on mount: think disk change.. */
	for (i = 0; i < READ_BUFFERS; i++)
		buffer_blocknr[i] = -1;

	err = cramfs_read_super(sb, &super, silent);
	if (err)
		return err;
	return cramfs_finalize_super(sb, &super.root);
}

static int cramfs_mtd_fill_super(struct super_block *sb, void *data,
				 int silent)
{
	struct cramfs_sb_info *sbi;
	struct cramfs_super super;
	int err;

	sbi = kzalloc(sizeof(struct cramfs_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;

	/* Map only one page for now.  Will remap it when fs size is known. */
	err = mtd_point(sb->s_mtd, 0, PAGE_SIZE, &sbi->mtd_point_size,
			&sbi->linear_virt_addr, &sbi->linear_phys_addr);
	if (err || sbi->mtd_point_size != PAGE_SIZE) {
		pr_err("unable to get direct memory access to mtd:%s\n",
		       sb->s_mtd->name);
		return err ? : -ENODATA;
	}

	pr_info("checking physical address %pap for linear cramfs image\n",
		&sbi->linear_phys_addr);
	err = cramfs_read_super(sb, &super, silent);
	if (err)
		return err;

	/* Remap the whole filesystem now */
	pr_info("linear cramfs image on mtd:%s appears to be %lu KB in size\n",
		sb->s_mtd->name, sbi->size/1024);
	mtd_unpoint(sb->s_mtd, 0, PAGE_SIZE);
	err = mtd_point(sb->s_mtd, 0, sbi->size, &sbi->mtd_point_size,
			&sbi->linear_virt_addr, &sbi->linear_phys_addr);
	if (err || sbi->mtd_point_size != sbi->size) {
		pr_err("unable to get direct memory access to mtd:%s\n",
		       sb->s_mtd->name);
		return err ? : -ENODATA;
	}

	return cramfs_finalize_super(sb, &super.root);
}

static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	u64 id = 0;

	if (sb->s_bdev)
		id = huge_encode_dev(sb->s_bdev->bd_dev);
	else if (sb->s_dev)
		id = huge_encode_dev(sb->s_dev);

	buf->f_type = CRAMFS_MAGIC;
	buf->f_bsize = PAGE_SIZE;
	buf->f_blocks = CRAMFS_SB(sb)->blocks;
	buf->f_bfree = 0;
	buf->f_bavail = 0;
	buf->f_files = CRAMFS_SB(sb)->files;
	buf->f_ffree = 0;
	buf->f_fsid.val[0] = (u32)id;
	buf->f_fsid.val[1] = (u32)(id >> 32);
	buf->f_namelen = CRAMFS_MAXPATHLEN;
	return 0;
}

/*
 * Read a cramfs directory entry.
 */
static int cramfs_readdir(struct file *file, struct dir_context *ctx)
{
	struct inode *inode = file_inode(file);
	struct super_block *sb = inode->i_sb;
	char *buf;
	unsigned int offset;

	/* Offset within the thing. */
	if (ctx->pos >= inode->i_size)
		return 0;
	offset = ctx->pos;
	/* Directory entries are always 4-byte aligned */
	if (offset & 3)
		return -EINVAL;

	buf = kmalloc(CRAMFS_MAXPATHLEN, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	while (offset < inode->i_size) {
		struct cramfs_inode *de;
		unsigned long nextoffset;
		char *name;
		ino_t ino;
		umode_t mode;
		int namelen;

		mutex_lock(&read_mutex);
		de = cramfs_read(sb, OFFSET(inode) + offset, sizeof(*de)+CRAMFS_MAXPATHLEN);
		name = (char *)(de+1);

		/*
		 * Namelengths on disk are shifted by two
		 * and the name padded out to 4-byte boundaries
		 * with zeroes.
		 */
		namelen = de->namelen << 2;
		memcpy(buf, name, namelen);
		ino = cramino(de, OFFSET(inode) + offset);
		mode = de->mode;
		mutex_unlock(&read_mutex);
		nextoffset = offset + sizeof(*de) + namelen;
		for (;;) {
			if (!namelen) {
				kfree(buf);
				return -EIO;
			}
			if (buf[namelen-1])
				break;
			namelen--;
		}
		if (!dir_emit(ctx, buf, namelen, ino, mode >> 12))
			break;

		ctx->pos = offset = nextoffset;
	}
	kfree(buf);
	return 0;
}

/*
 * Lookup and fill in the inode data..
 */
static struct dentry *cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
	unsigned int offset = 0;
	struct inode *inode = NULL;
	int sorted;

	mutex_lock(&read_mutex);
	sorted = CRAMFS_SB(dir->i_sb)->flags & CRAMFS_FLAG_SORTED_DIRS;
	while (offset < dir->i_size) {
		struct cramfs_inode *de;
		char *name;
		int namelen, retval;
		int dir_off = OFFSET(dir) + offset;

		de = cramfs_read(dir->i_sb, dir_off, sizeof(*de)+CRAMFS_MAXPATHLEN);
		name = (char *)(de+1);

		/* Try to take advantage of sorted directories */
		if (sorted && (dentry->d_name.name[0] < name[0]))
			break;

		namelen = de->namelen << 2;
		offset += sizeof(*de) + namelen;

		/* Quick check that the name is roughly the right length */
		if (((dentry->d_name.len + 3) & ~3) != namelen)
			continue;

		for (;;) {
			if (!namelen) {
				inode = ERR_PTR(-EIO);
				goto out;
			}
			if (name[namelen-1])
				break;
			namelen--;
		}
		if (namelen != dentry->d_name.len)
			continue;
		retval = memcmp(dentry->d_name.name, name, namelen);
		if (retval > 0)
			continue;
		if (!retval) {
			inode = get_cramfs_inode(dir->i_sb, de, dir_off);
			break;
		}
		/* else (retval < 0) */
		if (sorted)
			break;
	}
out:
	mutex_unlock(&read_mutex);
	if (IS_ERR(inode))
		return ERR_CAST(inode);
	d_add(dentry, inode);
	return NULL;
}

static int cramfs_readpage(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	u32 maxblock;
	int bytes_filled;
	void *pgdata;

	maxblock = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	bytes_filled = 0;
	pgdata = kmap(page);

	if (page->index < maxblock) {
		struct super_block *sb = inode->i_sb;
		u32 blkptr_offset = OFFSET(inode) + page->index * 4;
		u32 block_ptr, block_start, block_len;
		bool uncompressed, direct;

		mutex_lock(&read_mutex);
		block_ptr = *(u32 *) cramfs_read(sb, blkptr_offset, 4);
		uncompressed = (block_ptr & CRAMFS_BLK_FLAG_UNCOMPRESSED);
		direct = (block_ptr & CRAMFS_BLK_FLAG_DIRECT_PTR);
		block_ptr &= ~CRAMFS_BLK_FLAGS;

		if (direct) {
			/*
			 * The block pointer is an absolute start pointer,
			 * shifted by 2 bits. The size is included in the
			 * first 2 bytes of the data block when compressed,
			 * or PAGE_SIZE otherwise.
			 */
			block_start = block_ptr << CRAMFS_BLK_DIRECT_PTR_SHIFT;
			if (uncompressed) {
				block_len = PAGE_SIZE;
				/* if last block: cap to file length */
				if (page->index == maxblock - 1)
					block_len =
						offset_in_page(inode->i_size);
			} else {
				block_len = *(u16 *)
					cramfs_read(sb, block_start, 2);
				block_start += 2;
			}
		} else {
			/*
			 * The block pointer indicates one past the end of
			 * the current block (start of next block). If this
			 * is the first block then it starts where the block
			 * pointer table ends, otherwise its start comes
			 * from the previous block's pointer.
			 */
			block_start = OFFSET(inode) + maxblock * 4;
			if (page->index)
				block_start = *(u32 *)
					cramfs_read(sb, blkptr_offset - 4, 4);
			/* Beware... previous ptr might be a direct ptr */
			if (unlikely(block_start & CRAMFS_BLK_FLAG_DIRECT_PTR)) {
				/* See comments on earlier code. */
				u32 prev_start = block_start;
			       block_start = prev_start & ~CRAMFS_BLK_FLAGS;
			       block_start <<= CRAMFS_BLK_DIRECT_PTR_SHIFT;
				if (prev_start & CRAMFS_BLK_FLAG_UNCOMPRESSED) {
					block_start += PAGE_SIZE;
				} else {
					block_len = *(u16 *)
						cramfs_read(sb, block_start, 2);
					block_start += 2 + block_len;
				}
			}
			block_start &= ~CRAMFS_BLK_FLAGS;
			block_len = block_ptr - block_start;
		}

		if (block_len == 0)
			; /* hole */
		else if (unlikely(block_len > 2*PAGE_SIZE ||
				  (uncompressed && block_len > PAGE_SIZE))) {
			mutex_unlock(&read_mutex);
			pr_err("bad data blocksize %u\n", block_len);
			goto err;
		} else if (uncompressed) {
			memcpy(pgdata,
			       cramfs_read(sb, block_start, block_len),
			       block_len);
			bytes_filled = block_len;
		} else {
			bytes_filled = cramfs_uncompress_block(pgdata,
				 PAGE_SIZE,
				 cramfs_read(sb, block_start, block_len),
				 block_len);
		}
		mutex_unlock(&read_mutex);
		if (unlikely(bytes_filled < 0))
			goto err;
	}

	memset(pgdata + bytes_filled, 0, PAGE_SIZE - bytes_filled);
	flush_dcache_page(page);
	kunmap(page);
	SetPageUptodate(page);
	unlock_page(page);
	return 0;

err:
	kunmap(page);
	ClearPageUptodate(page);
	SetPageError(page);
	unlock_page(page);
	return 0;
}

static const struct address_space_operations cramfs_aops = {
	.readpage = cramfs_readpage
};

/*
 * Our operations:
 */

/*
 * A directory can only readdir
 */
static const struct file_operations cramfs_directory_operations = {
	.llseek		= generic_file_llseek,
	.read		= generic_read_dir,
	.iterate_shared	= cramfs_readdir,
};

static const struct inode_operations cramfs_dir_inode_operations = {
	.lookup		= cramfs_lookup,
};

static const struct super_operations cramfs_ops = {
	.remount_fs	= cramfs_remount,
	.statfs		= cramfs_statfs,
};

static struct dentry *cramfs_mount(struct file_system_type *fs_type, int flags,
				   const char *dev_name, void *data)
{
	struct dentry *ret = ERR_PTR(-ENOPROTOOPT);

	if (IS_ENABLED(CONFIG_CRAMFS_MTD)) {
		ret = mount_mtd(fs_type, flags, dev_name, data,
				cramfs_mtd_fill_super);
		if (!IS_ERR(ret))
			return ret;
	}
	if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV)) {
		ret = mount_bdev(fs_type, flags, dev_name, data,
				 cramfs_blkdev_fill_super);
	}
	return ret;
}

static struct file_system_type cramfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "cramfs",
	.mount		= cramfs_mount,
	.kill_sb	= cramfs_kill_sb,
	.fs_flags	= FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("cramfs");

static int __init init_cramfs_fs(void)
{
	int rv;

	rv = cramfs_uncompress_init();
	if (rv < 0)
		return rv;
	rv = register_filesystem(&cramfs_fs_type);
	if (rv < 0)
		cramfs_uncompress_exit();
	return rv;
}

static void __exit exit_cramfs_fs(void)
{
	cramfs_uncompress_exit();
	unregister_filesystem(&cramfs_fs_type);
}

module_init(init_cramfs_fs)
module_exit(exit_cramfs_fs)
MODULE_LICENSE("GPL");