aboutsummaryrefslogtreecommitdiffstats
path: root/crypto/sha512_generic.c
blob: 71fcf361102dcee35e0fcff0bd332ed4f4e77215 (plain) (blame)
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
/* SHA-512 code by Jean-Luc Cooke <jlcooke@certainkey.com>
 *
 * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
 * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
 * Copyright (c) 2003 Kyle McMartin <kyle@debian.org>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation; either version 2, or (at your option) any
 * later version.
 *
 */
#include <crypto/internal/hash.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/crypto.h>
#include <linux/types.h>
#include <crypto/sha.h>
#include <linux/percpu.h>
#include <asm/byteorder.h>

static inline u64 Ch(u64 x, u64 y, u64 z)
{
        return z ^ (x & (y ^ z));
}

static inline u64 Maj(u64 x, u64 y, u64 z)
{
        return (x & y) | (z & (x | y));
}

static const u64 sha512_K[80] = {
        0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
        0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
        0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL, 0xd807aa98a3030242ULL,
        0x12835b0145706fbeULL, 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
        0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL, 0x9bdc06a725c71235ULL,
        0xc19bf174cf692694ULL, 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
        0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL, 0x2de92c6f592b0275ULL,
        0x4a7484aa6ea6e483ULL, 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
        0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL, 0xb00327c898fb213fULL,
        0xbf597fc7beef0ee4ULL, 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
        0x06ca6351e003826fULL, 0x142929670a0e6e70ULL, 0x27b70a8546d22ffcULL,
        0x2e1b21385c26c926ULL, 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
        0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL, 0x81c2c92e47edaee6ULL,
        0x92722c851482353bULL, 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
        0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL, 0xd192e819d6ef5218ULL,
        0xd69906245565a910ULL, 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
        0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL, 0x2748774cdf8eeb99ULL,
        0x34b0bcb5e19b48a8ULL, 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
        0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL, 0x748f82ee5defb2fcULL,
        0x78a5636f43172f60ULL, 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
        0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL, 0xbef9a3f7b2c67915ULL,
        0xc67178f2e372532bULL, 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
        0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL, 0x06f067aa72176fbaULL,
        0x0a637dc5a2c898a6ULL, 0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
        0x28db77f523047d84ULL, 0x32caab7b40c72493ULL, 0x3c9ebe0a15c9bebcULL,
        0x431d67c49c100d4cULL, 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
        0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL,
};

#define e0(x)       (ror64(x,28) ^ ror64(x,34) ^ ror64(x,39))
#define e1(x)       (ror64(x,14) ^ ror64(x,18) ^ ror64(x,41))
#define s0(x)       (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
#define s1(x)       (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))

static inline void LOAD_OP(int I, u64 *W, const u8 *input)
{
	W[I] = __be64_to_cpu( ((__be64*)(input))[I] );
}

static inline void BLEND_OP(int I, u64 *W)
{
	W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]);
}

static void
sha512_transform(u64 *state, const u8 *input)
{
	u64 a, b, c, d, e, f, g, h, t1, t2;

	int i;
	u64 W[16];

	/* load the state into our registers */
	a=state[0];   b=state[1];   c=state[2];   d=state[3];
	e=state[4];   f=state[5];   g=state[6];   h=state[7];

	/* now iterate */
	for (i=0; i<80; i+=8) {
		if (!(i & 8)) {
			int j;

			if (i < 16) {
				/* load the input */
				for (j = 0; j < 16; j++)
					LOAD_OP(i + j, W, input);
			} else {
				for (j = 0; j < 16; j++) {
					BLEND_OP(i + j, W);
				}
			}
		}

		t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i  ] + W[(i & 15)];
		t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
		t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1];
		t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
		t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2];
		t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
		t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3];
		t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
		t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[(i & 15) + 4];
		t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
		t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5];
		t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
		t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6];
		t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
		t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7];
		t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
	}

	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
	state[4] += e; state[5] += f; state[6] += g; state[7] += h;

	/* erase our data */
	a = b = c = d = e = f = g = h = t1 = t2 = 0;
}

static int
sha512_init(struct shash_desc *desc)
{
	struct sha512_state *sctx = shash_desc_ctx(desc);
	sctx->state[0] = SHA512_H0;
	sctx->state[1] = SHA512_H1;
	sctx->state[2] = SHA512_H2;
	sctx->state[3] = SHA512_H3;
	sctx->state[4] = SHA512_H4;
	sctx->state[5] = SHA512_H5;
	sctx->state[6] = SHA512_H6;
	sctx->state[7] = SHA512_H7;
	sctx->count[0] = sctx->count[1] = 0;

	return 0;
}

static int
sha384_init(struct shash_desc *desc)
{
	struct sha512_state *sctx = shash_desc_ctx(desc);
	sctx->state[0] = SHA384_H0;
	sctx->state[1] = SHA384_H1;
	sctx->state[2] = SHA384_H2;
	sctx->state[3] = SHA384_H3;
	sctx->state[4] = SHA384_H4;
	sctx->state[5] = SHA384_H5;
	sctx->state[6] = SHA384_H6;
	sctx->state[7] = SHA384_H7;
	sctx->count[0] = sctx->count[1] = 0;

	return 0;
}

static int
sha512_update(struct shash_desc *desc, const u8 *data, unsigned int len)
{
	struct sha512_state *sctx = shash_desc_ctx(desc);

	unsigned int i, index, part_len;

	/* Compute number of bytes mod 128 */
	index = sctx->count[0] & 0x7f;

	/* Update number of bytes */
	if ((sctx->count[0] += len) < len)
		sctx->count[1]++;

        part_len = 128 - index;

	/* Transform as many times as possible. */
	if (len >= part_len) {
		memcpy(&sctx->buf[index], data, part_len);
		sha512_transform(sctx->state, sctx->buf);

		for (i = part_len; i + 127 < len; i+=128)
			sha512_transform(sctx->state, &data[i]);

		index = 0;
	} else {
		i = 0;
	}

	/* Buffer remaining input */
	memcpy(&sctx->buf[index], &data[i], len - i);

	return 0;
}

static int
sha512_final(struct shash_desc *desc, u8 *hash)
{
	struct sha512_state *sctx = shash_desc_ctx(desc);
        static u8 padding[128] = { 0x80, };
	__be64 *dst = (__be64 *)hash;
	__be64 bits[2];
	unsigned int index, pad_len;
	int i;

	/* Save number of bits */
	bits[1] = cpu_to_be64(sctx->count[0] << 3);
	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);

	/* Pad out to 112 mod 128. */
	index = sctx->count[0] & 0x7f;
	pad_len = (index < 112) ? (112 - index) : ((128+112) - index);
	sha512_update(desc, padding, pad_len);

	/* Append length (before padding) */
	sha512_update(desc, (const u8 *)bits, sizeof(bits));

	/* Store state in digest */
	for (i = 0; i < 8; i++)
		dst[i] = cpu_to_be64(sctx->state[i]);

	/* Zeroize sensitive information. */
	memset(sctx, 0, sizeof(struct sha512_state));

	return 0;
}

static int sha384_final(struct shash_desc *desc, u8 *hash)
{
	u8 D[64];

	sha512_final(desc, D);

	memcpy(hash, D, 48);
	memset(D, 0, 64);

	return 0;
}

static struct shash_alg sha512_algs[2] = { {
	.digestsize	=	SHA512_DIGEST_SIZE,
	.init		=	sha512_init,
	.update		=	sha512_update,
	.final		=	sha512_final,
	.descsize	=	sizeof(struct sha512_state),
	.base		=	{
		.cra_name	=	"sha512",
		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	=	SHA512_BLOCK_SIZE,
		.cra_module	=	THIS_MODULE,
	}
}, {
	.digestsize	=	SHA384_DIGEST_SIZE,
	.init		=	sha384_init,
	.update		=	sha512_update,
	.final		=	sha384_final,
	.descsize	=	sizeof(struct sha512_state),
	.base		=	{
		.cra_name	=	"sha384",
		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
		.cra_blocksize	=	SHA384_BLOCK_SIZE,
		.cra_module	=	THIS_MODULE,
	}
} };

static int __init sha512_generic_mod_init(void)
{
	return crypto_register_shashes(sha512_algs, ARRAY_SIZE(sha512_algs));
}

static void __exit sha512_generic_mod_fini(void)
{
	crypto_unregister_shashes(sha512_algs, ARRAY_SIZE(sha512_algs));
}

module_init(sha512_generic_mod_init);
module_exit(sha512_generic_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms");

MODULE_ALIAS("sha384");
MODULE_ALIAS("sha512");
1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589
/*
 *  linux/fs/fat/inode.c
 *
 *  Written 1992,1993 by Werner Almesberger
 *  VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner
 *  Rewritten for the constant inumbers support by Al Viro
 *
 *  Fixes:
 *
 *	Max Cohan: Fixed invalid FSINFO offset when info_sector is 0
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/pagemap.h>
#include <linux/mpage.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/parser.h>
#include <linux/uio.h>
#include <linux/writeback.h>
#include <linux/log2.h>
#include <linux/hash.h>
#include <asm/unaligned.h>
#include "fat.h"

#ifndef CONFIG_FAT_DEFAULT_IOCHARSET
/* if user don't select VFAT, this is undefined. */
#define CONFIG_FAT_DEFAULT_IOCHARSET	""
#endif

static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE;
static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET;


static int fat_add_cluster(struct inode *inode)
{
	int err, cluster;

	err = fat_alloc_clusters(inode, &cluster, 1);
	if (err)
		return err;
	/* FIXME: this cluster should be added after data of this
	 * cluster is writed */
	err = fat_chain_add(inode, cluster, 1);
	if (err)
		fat_free_clusters(inode, cluster);
	return err;
}

static inline int __fat_get_block(struct inode *inode, sector_t iblock,
				  unsigned long *max_blocks,
				  struct buffer_head *bh_result, int create)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	unsigned long mapped_blocks;
	sector_t phys;
	int err, offset;

	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
	if (err)
		return err;
	if (phys) {
		map_bh(bh_result, sb, phys);
		*max_blocks = min(mapped_blocks, *max_blocks);
		return 0;
	}
	if (!create)
		return 0;

	if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) {
		fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)",
			MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private);
		return -EIO;
	}

	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
	if (!offset) {
		/* TODO: multiple cluster allocation would be desirable. */
		err = fat_add_cluster(inode);
		if (err)
			return err;
	}
	/* available blocks on this cluster */
	mapped_blocks = sbi->sec_per_clus - offset;

	*max_blocks = min(mapped_blocks, *max_blocks);
	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;

	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
	if (err)
		return err;

	BUG_ON(!phys);
	BUG_ON(*max_blocks != mapped_blocks);
	set_buffer_new(bh_result);
	map_bh(bh_result, sb, phys);

	return 0;
}

static int fat_get_block(struct inode *inode, sector_t iblock,
			 struct buffer_head *bh_result, int create)
{
	struct super_block *sb = inode->i_sb;
	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
	int err;

	err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create);
	if (err)
		return err;
	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
	return 0;
}

static int fat_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, fat_get_block, wbc);
}

static int fat_writepages(struct address_space *mapping,
			  struct writeback_control *wbc)
{
	return mpage_writepages(mapping, wbc, fat_get_block);
}

static int fat_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, fat_get_block);
}

static int fat_readpages(struct file *file, struct address_space *mapping,
			 struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
}

static int fat_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	*pagep = NULL;
	return cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				fat_get_block,
				&MSDOS_I(mapping->host)->mmu_private);
}

static int fat_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *pagep, void *fsdata)
{
	struct inode *inode = mapping->host;
	int err;
	err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata);
	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
		MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
		mark_inode_dirty(inode);
	}
	return err;
}

static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
			     const struct iovec *iov,
			     loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	if (rw == WRITE) {
		/*
		 * FIXME: blockdev_direct_IO() doesn't use ->write_begin(),
		 * so we need to update the ->mmu_private to block boundary.
		 *
		 * But we must fill the remaining area or hole by nul for
		 * updating ->mmu_private.
		 *
		 * Return 0, and fallback to normal buffered write.
		 */
		loff_t size = offset + iov_length(iov, nr_segs);
		if (MSDOS_I(inode)->mmu_private < size)
			return 0;
	}

	/*
	 * FAT need to use the DIO_LOCKING for avoiding the race
	 * condition of fat_get_block() and ->truncate().
	 */
	return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				  offset, nr_segs, fat_get_block, NULL);
}

static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
{
	sector_t blocknr;

	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
	down_read(&mapping->host->i_alloc_sem);
	blocknr = generic_block_bmap(mapping, block, fat_get_block);
	up_read(&mapping->host->i_alloc_sem);

	return blocknr;
}

static const struct address_space_operations fat_aops = {
	.readpage	= fat_readpage,
	.readpages	= fat_readpages,
	.writepage	= fat_writepage,
	.writepages	= fat_writepages,
	.sync_page	= block_sync_page,
	.write_begin	= fat_write_begin,
	.write_end	= fat_write_end,
	.direct_IO	= fat_direct_IO,
	.bmap		= _fat_bmap
};

/*
 * New FAT inode stuff. We do the following:
 *	a) i_ino is constant and has nothing with on-disk location.
 *	b) FAT manages its own cache of directory entries.
 *	c) *This* cache is indexed by on-disk location.
 *	d) inode has an associated directory entry, all right, but
 *		it may be unhashed.
 *	e) currently entries are stored within struct inode. That should
 *		change.
 *	f) we deal with races in the following way:
 *		1. readdir() and lookup() do FAT-dir-cache lookup.
 *		2. rename() unhashes the F-d-c entry and rehashes it in
 *			a new place.
 *		3. unlink() and rmdir() unhash F-d-c entry.
 *		4. fat_write_inode() checks whether the thing is unhashed.
 *			If it is we silently return. If it isn't we do bread(),
 *			check if the location is still valid and retry if it
 *			isn't. Otherwise we do changes.
 *		5. Spinlock is used to protect hash/unhash/location check/lookup
 *		6. fat_clear_inode() unhashes the F-d-c entry.
 *		7. lookup() and readdir() do igrab() if they find a F-d-c entry
 *			and consider negative result as cache miss.
 */

static void fat_hash_init(struct super_block *sb)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	int i;

	spin_lock_init(&sbi->inode_hash_lock);
	for (i = 0; i < FAT_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&sbi->inode_hashtable[i]);
}

static inline unsigned long fat_hash(loff_t i_pos)
{
	return hash_32(i_pos, FAT_HASH_BITS);
}

void fat_attach(struct inode *inode, loff_t i_pos)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);

	spin_lock(&sbi->inode_hash_lock);
	MSDOS_I(inode)->i_pos = i_pos;
	hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head);
	spin_unlock(&sbi->inode_hash_lock);
}
EXPORT_SYMBOL_GPL(fat_attach);

void fat_detach(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	spin_lock(&sbi->inode_hash_lock);
	MSDOS_I(inode)->i_pos = 0;
	hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
	spin_unlock(&sbi->inode_hash_lock);
}
EXPORT_SYMBOL_GPL(fat_detach);

struct inode *fat_iget(struct super_block *sb, loff_t i_pos)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);
	struct hlist_node *_p;
	struct msdos_inode_info *i;
	struct inode *inode = NULL;

	spin_lock(&sbi->inode_hash_lock);
	hlist_for_each_entry(i, _p, head, i_fat_hash) {
		BUG_ON(i->vfs_inode.i_sb != sb);
		if (i->i_pos != i_pos)
			continue;
		inode = igrab(&i->vfs_inode);
		if (inode)
			break;
	}
	spin_unlock(&sbi->inode_hash_lock);
	return inode;
}

static int is_exec(unsigned char *extension)
{
	unsigned char *exe_extensions = "EXECOMBAT", *walk;

	for (walk = exe_extensions; *walk; walk += 3)
		if (!strncmp(extension, walk, 3))
			return 1;
	return 0;
}

static int fat_calc_dir_size(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	int ret, fclus, dclus;

	inode->i_size = 0;
	if (MSDOS_I(inode)->i_start == 0)
		return 0;

	ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus);
	if (ret < 0)
		return ret;
	inode->i_size = (fclus + 1) << sbi->cluster_bits;

	return 0;
}

/* doesn't deal with root inode */
static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	int error;

	MSDOS_I(inode)->i_pos = 0;
	inode->i_uid = sbi->options.fs_uid;
	inode->i_gid = sbi->options.fs_gid;
	inode->i_version++;
	inode->i_generation = get_seconds();

	if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) {
		inode->i_generation &= ~1;
		inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO);
		inode->i_op = sbi->dir_ops;
		inode->i_fop = &fat_dir_operations;

		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
		if (sbi->fat_bits == 32)
			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);

		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
		error = fat_calc_dir_size(inode);
		if (error < 0)
			return error;
		MSDOS_I(inode)->mmu_private = inode->i_size;

		inode->i_nlink = fat_subdirs(inode);
	} else { /* not a directory */
		inode->i_generation |= 1;
		inode->i_mode = fat_make_mode(sbi, de->attr,
			((sbi->options.showexec && !is_exec(de->name + 8))
			 ? S_IRUGO|S_IWUGO : S_IRWXUGO));
		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
		if (sbi->fat_bits == 32)
			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);

		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
		inode->i_size = le32_to_cpu(de->size);
		inode->i_op = &fat_file_inode_operations;
		inode->i_fop = &fat_file_operations;
		inode->i_mapping->a_ops = &fat_aops;
		MSDOS_I(inode)->mmu_private = inode->i_size;
	}
	if (de->attr & ATTR_SYS) {
		if (sbi->options.sys_immutable)
			inode->i_flags |= S_IMMUTABLE;
	}
	fat_save_attrs(inode, de->attr);

	inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;

	fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0);
	if (sbi->options.isvfat) {
		fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime,
				  de->cdate, de->ctime_cs);
		fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0);
	} else
		inode->i_ctime = inode->i_atime = inode->i_mtime;

	return 0;
}

struct inode *fat_build_inode(struct super_block *sb,
			struct msdos_dir_entry *de, loff_t i_pos)
{
	struct inode *inode;
	int err;

	inode = fat_iget(sb, i_pos);
	if (inode)
		goto out;
	inode = new_inode(sb);
	if (!inode) {
		inode = ERR_PTR(-ENOMEM);
		goto out;
	}
	inode->i_ino = iunique(sb, MSDOS_ROOT_INO);
	inode->i_version = 1;
	err = fat_fill_inode(inode, de);
	if (err) {
		iput(inode);
		inode = ERR_PTR(err);
		goto out;
	}
	fat_attach(inode, i_pos);
	insert_inode_hash(inode);
out:
	return inode;
}

EXPORT_SYMBOL_GPL(fat_build_inode);

static void fat_delete_inode(struct inode *inode)
{
	truncate_inode_pages(&inode->i_data, 0);
	inode->i_size = 0;
	fat_truncate(inode);
	clear_inode(inode);
}

static void fat_clear_inode(struct inode *inode)
{
	fat_cache_inval_inode(inode);
	fat_detach(inode);
}

static void fat_write_super(struct super_block *sb)
{
	lock_super(sb);
	sb->s_dirt = 0;

	if (!(sb->s_flags & MS_RDONLY))
		fat_clusters_flush(sb);
	unlock_super(sb);
}

static int fat_sync_fs(struct super_block *sb, int wait)
{
	int err = 0;

	if (sb->s_dirt) {
		lock_super(sb);
		sb->s_dirt = 0;
		err = fat_clusters_flush(sb);
		unlock_super(sb);
	}

	return err;
}

static void fat_put_super(struct super_block *sb)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);

	lock_kernel();

	if (sb->s_dirt)
		fat_write_super(sb);

	iput(sbi->fat_inode);

	unload_nls(sbi->nls_disk);
	unload_nls(sbi->nls_io);

	if (sbi->options.iocharset != fat_default_iocharset)
		kfree(sbi->options.iocharset);

	sb->s_fs_info = NULL;
	kfree(sbi);

	unlock_kernel();
}

static struct kmem_cache *fat_inode_cachep;

static struct inode *fat_alloc_inode(struct super_block *sb)
{
	struct msdos_inode_info *ei;
	ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void fat_destroy_inode(struct inode *inode)
{
	kmem_cache_free(fat_inode_cachep, MSDOS_I(inode));
}

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

	spin_lock_init(&ei->cache_lru_lock);
	ei->nr_caches = 0;
	ei->cache_valid_id = FAT_CACHE_VALID + 1;
	INIT_LIST_HEAD(&ei->cache_lru);
	INIT_HLIST_NODE(&ei->i_fat_hash);
	inode_init_once(&ei->vfs_inode);
}

static int __init fat_init_inodecache(void)
{
	fat_inode_cachep = kmem_cache_create("fat_inode_cache",
					     sizeof(struct msdos_inode_info),
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
					     init_once);
	if (fat_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void __exit fat_destroy_inodecache(void)
{
	kmem_cache_destroy(fat_inode_cachep);
}

static int fat_remount(struct super_block *sb, int *flags, char *data)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	*flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
	return 0;
}

static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);

	/* If the count of free cluster is still unknown, counts it here. */
	if (sbi->free_clusters == -1 || !sbi->free_clus_valid) {
		int err = fat_count_free_clusters(dentry->d_sb);
		if (err)
			return err;
	}

	buf->f_type = dentry->d_sb->s_magic;
	buf->f_bsize = sbi->cluster_size;
	buf->f_blocks = sbi->max_cluster - FAT_START_ENT;
	buf->f_bfree = sbi->free_clusters;
	buf->f_bavail = sbi->free_clusters;
	buf->f_fsid.val[0] = (u32)id;
	buf->f_fsid.val[1] = (u32)(id >> 32);
	buf->f_namelen = sbi->options.isvfat ? FAT_LFN_LEN : 12;

	return 0;
}

static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi,
				    struct inode *inode)
{
	loff_t i_pos;
#if BITS_PER_LONG == 32
	spin_lock(&sbi->inode_hash_lock);
#endif
	i_pos = MSDOS_I(inode)->i_pos;
#if BITS_PER_LONG == 32
	spin_unlock(&sbi->inode_hash_lock);
#endif
	return i_pos;
}

static int __fat_write_inode(struct inode *inode, int wait)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	struct buffer_head *bh;
	struct msdos_dir_entry *raw_entry;
	loff_t i_pos;
	int err;

	if (inode->i_ino == MSDOS_ROOT_INO)
		return 0;

retry:
	i_pos = fat_i_pos_read(sbi, inode);
	if (!i_pos)
		return 0;

	bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits);
	if (!bh) {
		printk(KERN_ERR "FAT: unable to read inode block "
		       "for updating (i_pos %lld)\n", i_pos);
		return -EIO;
	}
	spin_lock(&sbi->inode_hash_lock);
	if (i_pos != MSDOS_I(inode)->i_pos) {
		spin_unlock(&sbi->inode_hash_lock);
		brelse(bh);
		goto retry;
	}

	raw_entry = &((struct msdos_dir_entry *) (bh->b_data))
	    [i_pos & (sbi->dir_per_block - 1)];
	if (S_ISDIR(inode->i_mode))
		raw_entry->size = 0;
	else
		raw_entry->size = cpu_to_le32(inode->i_size);
	raw_entry->attr = fat_make_attrs(inode);
	raw_entry->start = cpu_to_le16(MSDOS_I(inode)->i_logstart);
	raw_entry->starthi = cpu_to_le16(MSDOS_I(inode)->i_logstart >> 16);
	fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time,
			  &raw_entry->date, NULL);
	if (sbi->options.isvfat) {
		__le16 atime;
		fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime,
				  &raw_entry->cdate, &raw_entry->ctime_cs);
		fat_time_unix2fat(sbi, &inode->i_atime, &atime,
				  &raw_entry->adate, NULL);
	}
	spin_unlock(&sbi->inode_hash_lock);
	mark_buffer_dirty(bh);
	err = 0;
	if (wait)
		err = sync_dirty_buffer(bh);
	brelse(bh);
	return err;
}

static int fat_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	return __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
}

int fat_sync_inode(struct inode *inode)
{
	return __fat_write_inode(inode, 1);
}

EXPORT_SYMBOL_GPL(fat_sync_inode);

static int fat_show_options(struct seq_file *m, struct vfsmount *mnt);
static const struct super_operations fat_sops = {
	.alloc_inode	= fat_alloc_inode,
	.destroy_inode	= fat_destroy_inode,
	.write_inode	= fat_write_inode,
	.delete_inode	= fat_delete_inode,
	.put_super	= fat_put_super,
	.write_super	= fat_write_super,
	.sync_fs	= fat_sync_fs,
	.statfs		= fat_statfs,
	.clear_inode	= fat_clear_inode,
	.remount_fs	= fat_remount,

	.show_options	= fat_show_options,
};

/*
 * a FAT file handle with fhtype 3 is
 *  0/  i_ino - for fast, reliable lookup if still in the cache
 *  1/  i_generation - to see if i_ino is still valid
 *          bit 0 == 0 iff directory
 *  2/  i_pos(8-39) - if ino has changed, but still in cache
 *  3/  i_pos(4-7)|i_logstart - to semi-verify inode found at i_pos
 *  4/  i_pos(0-3)|parent->i_logstart - maybe used to hunt for the file on disc
 *
 * Hack for NFSv2: Maximum FAT entry number is 28bits and maximum
 * i_pos is 40bits (blocknr(32) + dir offset(8)), so two 4bits
 * of i_logstart is used to store the directory entry offset.
 */

static struct dentry *fat_fh_to_dentry(struct super_block *sb,
		struct fid *fid, int fh_len, int fh_type)
{
	struct inode *inode = NULL;
	struct dentry *result;
	u32 *fh = fid->raw;

	if (fh_len < 5 || fh_type != 3)
		return NULL;

	inode = ilookup(sb, fh[0]);
	if (!inode || inode->i_generation != fh[1]) {
		if (inode)
			iput(inode);
		inode = NULL;
	}
	if (!inode) {
		loff_t i_pos;
		int i_logstart = fh[3] & 0x0fffffff;

		i_pos = (loff_t)fh[2] << 8;
		i_pos |= ((fh[3] >> 24) & 0xf0) | (fh[4] >> 28);

		/* try 2 - see if i_pos is in F-d-c
		 * require i_logstart to be the same
		 * Will fail if you truncate and then re-write
		 */

		inode = fat_iget(sb, i_pos);
		if (inode && MSDOS_I(inode)->i_logstart != i_logstart) {
			iput(inode);
			inode = NULL;
		}
	}

	/*
	 * For now, do nothing if the inode is not found.
	 *
	 * What we could do is:
	 *
	 *	- follow the file starting at fh[4], and record the ".." entry,
	 *	  and the name of the fh[2] entry.
	 *	- then follow the ".." file finding the next step up.
	 *
	 * This way we build a path to the root of the tree. If this works, we
	 * lookup the path and so get this inode into the cache.  Finally try
	 * the fat_iget lookup again.  If that fails, then we are totally out
	 * of luck.  But all that is for another day
	 */
	result = d_obtain_alias(inode);
	if (!IS_ERR(result))
		result->d_op = sb->s_root->d_op;
	return result;
}

static int
fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable)
{
	int len = *lenp;
	struct inode *inode =  de->d_inode;
	u32 ipos_h, ipos_m, ipos_l;

	if (len < 5)
		return 255; /* no room */

	ipos_h = MSDOS_I(inode)->i_pos >> 8;
	ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
	ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28;
	*lenp = 5;
	fh[0] = inode->i_ino;
	fh[1] = inode->i_generation;
	fh[2] = ipos_h;
	fh[3] = ipos_m | MSDOS_I(inode)->i_logstart;
	spin_lock(&de->d_lock);
	fh[4] = ipos_l | MSDOS_I(de->d_parent->d_inode)->i_logstart;
	spin_unlock(&de->d_lock);
	return 3;
}

static struct dentry *fat_get_parent(struct dentry *child)
{
	struct super_block *sb = child->d_sb;
	struct buffer_head *bh;
	struct msdos_dir_entry *de;
	loff_t i_pos;
	struct dentry *parent;
	struct inode *inode;
	int err;

	lock_super(sb);

	err = fat_get_dotdot_entry(child->d_inode, &bh, &de, &i_pos);
	if (err) {
		parent = ERR_PTR(err);
		goto out;
	}
	inode = fat_build_inode(sb, de, i_pos);
	brelse(bh);

	parent = d_obtain_alias(inode);
	if (!IS_ERR(parent))
		parent->d_op = sb->s_root->d_op;
out:
	unlock_super(sb);

	return parent;
}

static const struct export_operations fat_export_ops = {
	.encode_fh	= fat_encode_fh,
	.fh_to_dentry	= fat_fh_to_dentry,
	.get_parent	= fat_get_parent,
};

static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	struct msdos_sb_info *sbi = MSDOS_SB(mnt->mnt_sb);
	struct fat_mount_options *opts = &sbi->options;
	int isvfat = opts->isvfat;

	if (opts->fs_uid != 0)
		seq_printf(m, ",uid=%u", opts->fs_uid);
	if (opts->fs_gid != 0)
		seq_printf(m, ",gid=%u", opts->fs_gid);
	seq_printf(m, ",fmask=%04o", opts->fs_fmask);
	seq_printf(m, ",dmask=%04o", opts->fs_dmask);
	if (opts->allow_utime)
		seq_printf(m, ",allow_utime=%04o", opts->allow_utime);
	if (sbi->nls_disk)
		seq_printf(m, ",codepage=%s", sbi->nls_disk->charset);
	if (isvfat) {
		if (sbi->nls_io)
			seq_printf(m, ",iocharset=%s", sbi->nls_io->charset);

		switch (opts->shortname) {
		case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95:
			seq_puts(m, ",shortname=win95");
			break;
		case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT:
			seq_puts(m, ",shortname=winnt");
			break;
		case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95:
			seq_puts(m, ",shortname=mixed");
			break;
		case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95:
			seq_puts(m, ",shortname=lower");
			break;
		default:
			seq_puts(m, ",shortname=unknown");
			break;
		}
	}
	if (opts->name_check != 'n')
		seq_printf(m, ",check=%c", opts->name_check);
	if (opts->usefree)
		seq_puts(m, ",usefree");
	if (opts->quiet)
		seq_puts(m, ",quiet");
	if (opts->showexec)
		seq_puts(m, ",showexec");
	if (opts->sys_immutable)
		seq_puts(m, ",sys_immutable");
	if (!isvfat) {
		if (opts->dotsOK)
			seq_puts(m, ",dotsOK=yes");
		if (opts->nocase)
			seq_puts(m, ",nocase");
	} else {
		if (opts->utf8)
			seq_puts(m, ",utf8");
		if (opts->unicode_xlate)
			seq_puts(m, ",uni_xlate");
		if (!opts->numtail)
			seq_puts(m, ",nonumtail");
		if (opts->rodir)
			seq_puts(m, ",rodir");
	}
	if (opts->flush)
		seq_puts(m, ",flush");
	if (opts->tz_utc)
		seq_puts(m, ",tz=UTC");
	if (opts->errors == FAT_ERRORS_CONT)
		seq_puts(m, ",errors=continue");
	else if (opts->errors == FAT_ERRORS_PANIC)
		seq_puts(m, ",errors=panic");
	else
		seq_puts(m, ",errors=remount-ro");
	if (opts->discard)
		seq_puts(m, ",discard");

	return 0;
}

enum {
	Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid,
	Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_codepage,
	Opt_usefree, Opt_nocase, Opt_quiet, Opt_showexec, Opt_debug,
	Opt_immutable, Opt_dots, Opt_nodots,
	Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
	Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
	Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
	Opt_obsolate, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont,
	Opt_err_panic, Opt_err_ro, Opt_discard, Opt_err,
};

static const match_table_t fat_tokens = {
	{Opt_check_r, "check=relaxed"},
	{Opt_check_s, "check=strict"},
	{Opt_check_n, "check=normal"},
	{Opt_check_r, "check=r"},
	{Opt_check_s, "check=s"},
	{Opt_check_n, "check=n"},
	{Opt_uid, "uid=%u"},
	{Opt_gid, "gid=%u"},
	{Opt_umask, "umask=%o"},
	{Opt_dmask, "dmask=%o"},
	{Opt_fmask, "fmask=%o"},
	{Opt_allow_utime, "allow_utime=%o"},
	{Opt_codepage, "codepage=%u"},
	{Opt_usefree, "usefree"},
	{Opt_nocase, "nocase"},
	{Opt_quiet, "quiet"},
	{Opt_showexec, "showexec"},
	{Opt_debug, "debug"},
	{Opt_immutable, "sys_immutable"},
	{Opt_flush, "flush"},
	{Opt_tz_utc, "tz=UTC"},
	{Opt_err_cont, "errors=continue"},
	{Opt_err_panic, "errors=panic"},
	{Opt_err_ro, "errors=remount-ro"},
	{Opt_discard, "discard"},
	{Opt_obsolate, "conv=binary"},
	{Opt_obsolate, "conv=text"},
	{Opt_obsolate, "conv=auto"},
	{Opt_obsolate, "conv=b"},
	{Opt_obsolate, "conv=t"},
	{Opt_obsolate, "conv=a"},
	{Opt_obsolate, "fat=%u"},
	{Opt_obsolate, "blocksize=%u"},
	{Opt_obsolate, "cvf_format=%20s"},
	{Opt_obsolate, "cvf_options=%100s"},
	{Opt_obsolate, "posix"},
	{Opt_err, NULL},
};
static const match_table_t msdos_tokens = {
	{Opt_nodots, "nodots"},
	{Opt_nodots, "dotsOK=no"},
	{Opt_dots, "dots"},
	{Opt_dots, "dotsOK=yes"},
	{Opt_err, NULL}
};
static const match_table_t vfat_tokens = {
	{Opt_charset, "iocharset=%s"},
	{Opt_shortname_lower, "shortname=lower"},
	{Opt_shortname_win95, "shortname=win95"},
	{Opt_shortname_winnt, "shortname=winnt"},
	{Opt_shortname_mixed, "shortname=mixed"},
	{Opt_utf8_no, "utf8=0"},		/* 0 or no or false */
	{Opt_utf8_no, "utf8=no"},
	{Opt_utf8_no, "utf8=false"},
	{Opt_utf8_yes, "utf8=1"},		/* empty or 1 or yes or true */
	{Opt_utf8_yes, "utf8=yes"},
	{Opt_utf8_yes, "utf8=true"},
	{Opt_utf8_yes, "utf8"},
	{Opt_uni_xl_no, "uni_xlate=0"},		/* 0 or no or false */
	{Opt_uni_xl_no, "uni_xlate=no"},
	{Opt_uni_xl_no, "uni_xlate=false"},
	{Opt_uni_xl_yes, "uni_xlate=1"},	/* empty or 1 or yes or true */
	{Opt_uni_xl_yes, "uni_xlate=yes"},
	{Opt_uni_xl_yes, "uni_xlate=true"},
	{Opt_uni_xl_yes, "uni_xlate"},
	{Opt_nonumtail_no, "nonumtail=0"},	/* 0 or no or false */
	{Opt_nonumtail_no, "nonumtail=no"},
	{Opt_nonumtail_no, "nonumtail=false"},
	{Opt_nonumtail_yes, "nonumtail=1"},	/* empty or 1 or yes or true */
	{Opt_nonumtail_yes, "nonumtail=yes"},
	{Opt_nonumtail_yes, "nonumtail=true"},
	{Opt_nonumtail_yes, "nonumtail"},
	{Opt_rodir, "rodir"},
	{Opt_err, NULL}
};

static int parse_options(char *options, int is_vfat, int silent, int *debug,
			 struct fat_mount_options *opts)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;
	char *iocharset;

	opts->isvfat = is_vfat;

	opts->fs_uid = current_uid();
	opts->fs_gid = current_gid();
	opts->fs_fmask = opts->fs_dmask = current_umask();
	opts->allow_utime = -1;
	opts->codepage = fat_default_codepage;
	opts->iocharset = fat_default_iocharset;
	if (is_vfat) {
		opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95;
		opts->rodir = 0;
	} else {
		opts->shortname = 0;
		opts->rodir = 1;
	}
	opts->name_check = 'n';
	opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK =  0;
	opts->utf8 = opts->unicode_xlate = 0;
	opts->numtail = 1;
	opts->usefree = opts->nocase = 0;
	opts->tz_utc = 0;
	opts->errors = FAT_ERRORS_RO;
	*debug = 0;

	if (!options)
		goto out;

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

		token = match_token(p, fat_tokens, args);
		if (token == Opt_err) {
			if (is_vfat)
				token = match_token(p, vfat_tokens, args);
			else
				token = match_token(p, msdos_tokens, args);
		}
		switch (token) {
		case Opt_check_s:
			opts->name_check = 's';
			break;
		case Opt_check_r:
			opts->name_check = 'r';
			break;
		case Opt_check_n:
			opts->name_check = 'n';
			break;
		case Opt_usefree:
			opts->usefree = 1;
			break;
		case Opt_nocase:
			if (!is_vfat)
				opts->nocase = 1;
			else {
				/* for backward compatibility */
				opts->shortname = VFAT_SFN_DISPLAY_WIN95
					| VFAT_SFN_CREATE_WIN95;
			}
			break;
		case Opt_quiet:
			opts->quiet = 1;
			break;
		case Opt_showexec:
			opts->showexec = 1;
			break;
		case Opt_debug:
			*debug = 1;
			break;
		case Opt_immutable:
			opts->sys_immutable = 1;
			break;
		case Opt_uid:
			if (match_int(&args[0], &option))
				return 0;
			opts->fs_uid = option;
			break;
		case Opt_gid:
			if (match_int(&args[0], &option))
				return 0;
			opts->fs_gid = option;
			break;
		case Opt_umask:
			if (match_octal(&args[0], &option))
				return 0;
			opts->fs_fmask = opts->fs_dmask = option;
			break;
		case Opt_dmask:
			if (match_octal(&args[0], &option))
				return 0;
			opts->fs_dmask = option;
			break;
		case Opt_fmask:
			if (match_octal(&args[0], &option))
				return 0;
			opts->fs_fmask = option;
			break;
		case Opt_allow_utime:
			if (match_octal(&args[0], &option))
				return 0;
			opts->allow_utime = option & (S_IWGRP | S_IWOTH);
			break;
		case Opt_codepage:
			if (match_int(&args[0], &option))
				return 0;
			opts->codepage = option;
			break;
		case Opt_flush:
			opts->flush = 1;
			break;
		case Opt_tz_utc:
			opts->tz_utc = 1;
			break;
		case Opt_err_cont:
			opts->errors = FAT_ERRORS_CONT;
			break;
		case Opt_err_panic:
			opts->errors = FAT_ERRORS_PANIC;
			break;
		case Opt_err_ro:
			opts->errors = FAT_ERRORS_RO;
			break;

		/* msdos specific */
		case Opt_dots:
			opts->dotsOK = 1;
			break;
		case Opt_nodots:
			opts->dotsOK = 0;
			break;

		/* vfat specific */
		case Opt_charset:
			if (opts->iocharset != fat_default_iocharset)
				kfree(opts->iocharset);
			iocharset = match_strdup(&args[0]);
			if (!iocharset)
				return -ENOMEM;
			opts->iocharset = iocharset;
			break;
		case Opt_shortname_lower:
			opts->shortname = VFAT_SFN_DISPLAY_LOWER
					| VFAT_SFN_CREATE_WIN95;
			break;
		case Opt_shortname_win95:
			opts->shortname = VFAT_SFN_DISPLAY_WIN95
					| VFAT_SFN_CREATE_WIN95;
			break;
		case Opt_shortname_winnt:
			opts->shortname = VFAT_SFN_DISPLAY_WINNT
					| VFAT_SFN_CREATE_WINNT;
			break;
		case Opt_shortname_mixed:
			opts->shortname = VFAT_SFN_DISPLAY_WINNT
					| VFAT_SFN_CREATE_WIN95;
			break;
		case Opt_utf8_no:		/* 0 or no or false */
			opts->utf8 = 0;
			break;
		case Opt_utf8_yes:		/* empty or 1 or yes or true */
			opts->utf8 = 1;
			break;
		case Opt_uni_xl_no:		/* 0 or no or false */
			opts->unicode_xlate = 0;
			break;
		case Opt_uni_xl_yes:		/* empty or 1 or yes or true */
			opts->unicode_xlate = 1;
			break;
		case Opt_nonumtail_no:		/* 0 or no or false */
			opts->numtail = 1;	/* negated option */
			break;
		case Opt_nonumtail_yes:		/* empty or 1 or yes or true */
			opts->numtail = 0;	/* negated option */
			break;
		case Opt_rodir:
			opts->rodir = 1;
			break;
		case Opt_discard:
			opts->discard = 1;
			break;

		/* obsolete mount options */
		case Opt_obsolate:
			printk(KERN_INFO "FAT: \"%s\" option is obsolete, "
			       "not supported now\n", p);
			break;
		/* unknown option */
		default:
			if (!silent) {
				printk(KERN_ERR
				       "FAT: Unrecognized mount option \"%s\" "
				       "or missing value\n", p);
			}
			return -EINVAL;
		}
	}

out:
	/* UTF-8 doesn't provide FAT semantics */
	if (!strcmp(opts->iocharset, "utf8")) {
		printk(KERN_ERR "FAT: utf8 is not a recommended IO charset"
		       " for FAT filesystems, filesystem will be "
		       "case sensitive!\n");
	}

	/* If user doesn't specify allow_utime, it's initialized from dmask. */
	if (opts->allow_utime == (unsigned short)-1)
		opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH);
	if (opts->unicode_xlate)
		opts->utf8 = 0;

	return 0;
}

static int fat_read_root(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	int error;

	MSDOS_I(inode)->i_pos = 0;
	inode->i_uid = sbi->options.fs_uid;
	inode->i_gid = sbi->options.fs_gid;
	inode->i_version++;
	inode->i_generation = 0;
	inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO);
	inode->i_op = sbi->dir_ops;
	inode->i_fop = &fat_dir_operations;
	if (sbi->fat_bits == 32) {
		MSDOS_I(inode)->i_start = sbi->root_cluster;
		error = fat_calc_dir_size(inode);
		if (error < 0)
			return error;
	} else {
		MSDOS_I(inode)->i_start = 0;
		inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry);
	}
	inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;
	MSDOS_I(inode)->i_logstart = 0;
	MSDOS_I(inode)->mmu_private = inode->i_size;

	fat_save_attrs(inode, ATTR_DIR);
	inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0;
	inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0;
	inode->i_nlink = fat_subdirs(inode)+2;

	return 0;
}

/*
 * Read the super block of an MS-DOS FS.
 */
int fat_fill_super(struct super_block *sb, void *data, int silent,
		   const struct inode_operations *fs_dir_inode_ops, int isvfat)
{
	struct inode *root_inode = NULL, *fat_inode = NULL;
	struct buffer_head *bh;
	struct fat_boot_sector *b;
	struct msdos_sb_info *sbi;
	u16 logical_sector_size;
	u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors;
	int debug;
	unsigned int media;
	long error;
	char buf[50];

	/*
	 * GFP_KERNEL is ok here, because while we do hold the
	 * supeblock lock, memory pressure can't call back into
	 * the filesystem, since we're only just about to mount
	 * it and have no inodes etc active!
	 */
	sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;

	sb->s_flags |= MS_NODIRATIME;
	sb->s_magic = MSDOS_SUPER_MAGIC;
	sb->s_op = &fat_sops;
	sb->s_export_op = &fat_export_ops;
	sbi->dir_ops = fs_dir_inode_ops;

	error = parse_options(data, isvfat, silent, &debug, &sbi->options);
	if (error)
		goto out_fail;

	error = -EIO;
	sb_min_blocksize(sb, 512);
	bh = sb_bread(sb, 0);
	if (bh == NULL) {
		printk(KERN_ERR "FAT: unable to read boot sector\n");
		goto out_fail;
	}

	b = (struct fat_boot_sector *) bh->b_data;
	if (!b->reserved) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus number of reserved sectors\n");
		brelse(bh);
		goto out_invalid;
	}
	if (!b->fats) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus number of FAT structure\n");
		brelse(bh);
		goto out_invalid;
	}

	/*
	 * Earlier we checked here that b->secs_track and b->head are nonzero,
	 * but it turns out valid FAT filesystems can have zero there.
	 */

	media = b->media;
	if (!fat_valid_media(media)) {
		if (!silent)
			printk(KERN_ERR "FAT: invalid media value (0x%02x)\n",
			       media);
		brelse(bh);
		goto out_invalid;
	}
	logical_sector_size = get_unaligned_le16(&b->sector_size);
	if (!is_power_of_2(logical_sector_size)
	    || (logical_sector_size < 512)
	    || (logical_sector_size > 4096)) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus logical sector size %u\n",
			       logical_sector_size);
		brelse(bh);
		goto out_invalid;
	}
	sbi->sec_per_clus = b->sec_per_clus;
	if (!is_power_of_2(sbi->sec_per_clus)) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus sectors per cluster %u\n",
			       sbi->sec_per_clus);
		brelse(bh);
		goto out_invalid;
	}

	if (logical_sector_size < sb->s_blocksize) {
		printk(KERN_ERR "FAT: logical sector size too small for device"
		       " (logical sector size = %u)\n", logical_sector_size);
		brelse(bh);
		goto out_fail;
	}
	if (logical_sector_size > sb->s_blocksize) {
		brelse(bh);

		if (!sb_set_blocksize(sb, logical_sector_size)) {
			printk(KERN_ERR "FAT: unable to set blocksize %u\n",
			       logical_sector_size);
			goto out_fail;
		}
		bh = sb_bread(sb, 0);
		if (bh == NULL) {
			printk(KERN_ERR "FAT: unable to read boot sector"
			       " (logical sector size = %lu)\n",
			       sb->s_blocksize);
			goto out_fail;
		}
		b = (struct fat_boot_sector *) bh->b_data;
	}

	sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus;
	sbi->cluster_bits = ffs(sbi->cluster_size) - 1;
	sbi->fats = b->fats;
	sbi->fat_bits = 0;		/* Don't know yet */
	sbi->fat_start = le16_to_cpu(b->reserved);
	sbi->fat_length = le16_to_cpu(b->fat_length);
	sbi->root_cluster = 0;
	sbi->free_clusters = -1;	/* Don't know yet */
	sbi->free_clus_valid = 0;
	sbi->prev_free = FAT_START_ENT;

	if (!sbi->fat_length && b->fat32_length) {
		struct fat_boot_fsinfo *fsinfo;
		struct buffer_head *fsinfo_bh;

		/* Must be FAT32 */
		sbi->fat_bits = 32;
		sbi->fat_length = le32_to_cpu(b->fat32_length);
		sbi->root_cluster = le32_to_cpu(b->root_cluster);

		sb->s_maxbytes = 0xffffffff;

		/* MC - if info_sector is 0, don't multiply by 0 */
		sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
		if (sbi->fsinfo_sector == 0)
			sbi->fsinfo_sector = 1;

		fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector);
		if (fsinfo_bh == NULL) {
			printk(KERN_ERR "FAT: bread failed, FSINFO block"
			       " (sector = %lu)\n", sbi->fsinfo_sector);
			brelse(bh);
			goto out_fail;
		}

		fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data;
		if (!IS_FSINFO(fsinfo)) {
			printk(KERN_WARNING "FAT: Invalid FSINFO signature: "
			       "0x%08x, 0x%08x (sector = %lu)\n",
			       le32_to_cpu(fsinfo->signature1),
			       le32_to_cpu(fsinfo->signature2),
			       sbi->fsinfo_sector);
		} else {
			if (sbi->options.usefree)
				sbi->free_clus_valid = 1;
			sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters);
			sbi->prev_free = le32_to_cpu(fsinfo->next_cluster);
		}

		brelse(fsinfo_bh);
	}

	sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
	sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;

	sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length;
	sbi->dir_entries = get_unaligned_le16(&b->dir_entries);
	if (sbi->dir_entries & (sbi->dir_per_block - 1)) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus directroy-entries per block"
			       " (%u)\n", sbi->dir_entries);
		brelse(bh);
		goto out_invalid;
	}

	rootdir_sectors = sbi->dir_entries
		* sizeof(struct msdos_dir_entry) / sb->s_blocksize;
	sbi->data_start = sbi->dir_start + rootdir_sectors;
	total_sectors = get_unaligned_le16(&b->sectors);
	if (total_sectors == 0)
		total_sectors = le32_to_cpu(b->total_sect);

	total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus;

	if (sbi->fat_bits != 32)
		sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12;

	/* check that FAT table does not overflow */
	fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
	total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT);
	if (total_clusters > MAX_FAT(sb)) {
		if (!silent)
			printk(KERN_ERR "FAT: count of clusters too big (%u)\n",
			       total_clusters);
		brelse(bh);
		goto out_invalid;
	}

	sbi->max_cluster = total_clusters + FAT_START_ENT;
	/* check the free_clusters, it's not necessarily correct */
	if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters)
		sbi->free_clusters = -1;
	/* check the prev_free, it's not necessarily correct */
	sbi->prev_free %= sbi->max_cluster;
	if (sbi->prev_free < FAT_START_ENT)
		sbi->prev_free = FAT_START_ENT;

	brelse(bh);

	/* set up enough so that it can read an inode */
	fat_hash_init(sb);
	fat_ent_access_init(sb);

	/*
	 * The low byte of FAT's first entry must have same value with
	 * media-field.  But in real world, too many devices is
	 * writing wrong value.  So, removed that validity check.
	 *
	 * if (FAT_FIRST_ENT(sb, media) != first)
	 */

	error = -EINVAL;
	sprintf(buf, "cp%d", sbi->options.codepage);
	sbi->nls_disk = load_nls(buf);
	if (!sbi->nls_disk) {
		printk(KERN_ERR "FAT: codepage %s not found\n", buf);
		goto out_fail;
	}

	/* FIXME: utf8 is using iocharset for upper/lower conversion */
	if (sbi->options.isvfat) {
		sbi->nls_io = load_nls(sbi->options.iocharset);
		if (!sbi->nls_io) {
			printk(KERN_ERR "FAT: IO charset %s not found\n",
			       sbi->options.iocharset);
			goto out_fail;
		}
	}

	error = -ENOMEM;
	fat_inode = new_inode(sb);
	if (!fat_inode)
		goto out_fail;
	MSDOS_I(fat_inode)->i_pos = 0;
	sbi->fat_inode = fat_inode;
	root_inode = new_inode(sb);
	if (!root_inode)
		goto out_fail;
	root_inode->i_ino = MSDOS_ROOT_INO;
	root_inode->i_version = 1;
	error = fat_read_root(root_inode);
	if (error < 0)
		goto out_fail;
	error = -ENOMEM;
	insert_inode_hash(root_inode);
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root) {
		printk(KERN_ERR "FAT: get root inode failed\n");
		goto out_fail;
	}

	return 0;

out_invalid:
	error = -EINVAL;
	if (!silent)
		printk(KERN_INFO "VFS: Can't find a valid FAT filesystem"
		       " on dev %s.\n", sb->s_id);

out_fail:
	if (fat_inode)
		iput(fat_inode);
	if (root_inode)
		iput(root_inode);
	unload_nls(sbi->nls_io);
	unload_nls(sbi->nls_disk);
	if (sbi->options.iocharset != fat_default_iocharset)
		kfree(sbi->options.iocharset);
	sb->s_fs_info = NULL;
	kfree(sbi);
	return error;
}

EXPORT_SYMBOL_GPL(fat_fill_super);

/*
 * helper function for fat_flush_inodes.  This writes both the inode
 * and the file data blocks, waiting for in flight data blocks before
 * the start of the call.  It does not wait for any io started
 * during the call
 */
static int writeback_inode(struct inode *inode)
{

	int ret;
	struct address_space *mapping = inode->i_mapping;
	struct writeback_control wbc = {
	       .sync_mode = WB_SYNC_NONE,
	      .nr_to_write = 0,
	};
	/* if we used WB_SYNC_ALL, sync_inode waits for the io for the
	* inode to finish.  So WB_SYNC_NONE is sent down to sync_inode
	* and filemap_fdatawrite is used for the data blocks
	*/
	ret = sync_inode(inode, &wbc);
	if (!ret)
	       ret = filemap_fdatawrite(mapping);
	return ret;
}

/*
 * write data and metadata corresponding to i1 and i2.  The io is
 * started but we do not wait for any of it to finish.
 *
 * filemap_flush is used for the block device, so if there is a dirty
 * page for a block already in flight, we will not wait and start the
 * io over again
 */
int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2)
{
	int ret = 0;
	if (!MSDOS_SB(sb)->options.flush)
		return 0;
	if (i1)
		ret = writeback_inode(i1);
	if (!ret && i2)
		ret = writeback_inode(i2);
	if (!ret) {
		struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
		ret = filemap_flush(mapping);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(fat_flush_inodes);

static int __init init_fat_fs(void)
{
	int err;

	err = fat_cache_init();
	if (err)
		return err;

	err = fat_init_inodecache();
	if (err)
		goto failed;

	return 0;

failed:
	fat_cache_destroy();
	return err;
}

static void __exit exit_fat_fs(void)
{
	fat_cache_destroy();
	fat_destroy_inodecache();
}

module_init(init_fat_fs)
module_exit(exit_fat_fs)

MODULE_LICENSE("GPL");