summaryrefslogtreecommitdiffstats
path: root/fs/verity/open.c
blob: 6c31a871b84bccb472b5008fe304c0dab0ca725f (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Opening fs-verity files
 *
 * Copyright 2019 Google LLC
 */

#include "fsverity_private.h"

#include <linux/mm.h>
#include <linux/slab.h>

static struct kmem_cache *fsverity_info_cachep;

/**
 * fsverity_init_merkle_tree_params() - initialize Merkle tree parameters
 * @params: the parameters struct to initialize
 * @inode: the inode for which the Merkle tree is being built
 * @hash_algorithm: number of hash algorithm to use
 * @log_blocksize: log base 2 of block size to use
 * @salt: pointer to salt (optional)
 * @salt_size: size of salt, possibly 0
 *
 * Validate the hash algorithm and block size, then compute the tree topology
 * (num levels, num blocks in each level, etc.) and initialize @params.
 *
 * Return: 0 on success, -errno on failure
 */
int fsverity_init_merkle_tree_params(struct merkle_tree_params *params,
				     const struct inode *inode,
				     unsigned int hash_algorithm,
				     unsigned int log_blocksize,
				     const u8 *salt, size_t salt_size)
{
	const struct fsverity_hash_alg *hash_alg;
	int err;
	u64 blocks;
	u64 blocks_in_level[FS_VERITY_MAX_LEVELS];
	u64 offset;
	int level;

	memset(params, 0, sizeof(*params));

	hash_alg = fsverity_get_hash_alg(inode, hash_algorithm);
	if (IS_ERR(hash_alg))
		return PTR_ERR(hash_alg);
	params->hash_alg = hash_alg;
	params->digest_size = hash_alg->digest_size;

	params->hashstate = fsverity_prepare_hash_state(hash_alg, salt,
							salt_size);
	if (IS_ERR(params->hashstate)) {
		err = PTR_ERR(params->hashstate);
		params->hashstate = NULL;
		fsverity_err(inode, "Error %d preparing hash state", err);
		goto out_err;
	}

	/*
	 * fs/verity/ directly assumes that the Merkle tree block size is a
	 * power of 2 less than or equal to PAGE_SIZE.  Another restriction
	 * arises from the interaction between fs/verity/ and the filesystems
	 * themselves: filesystems expect to be able to verify a single
	 * filesystem block of data at a time.  Therefore, the Merkle tree block
	 * size must also be less than or equal to the filesystem block size.
	 *
	 * The above are the only hard limitations, so in theory the Merkle tree
	 * block size could be as small as twice the digest size.  However,
	 * that's not useful, and it would result in some unusually deep and
	 * large Merkle trees.  So we currently require that the Merkle tree
	 * block size be at least 1024 bytes.  That's small enough to test the
	 * sub-page block case on systems with 4K pages, but not too small.
	 */
	if (log_blocksize < 10 || log_blocksize > PAGE_SHIFT ||
	    log_blocksize > inode->i_blkbits) {
		fsverity_warn(inode, "Unsupported log_blocksize: %u",
			      log_blocksize);
		err = -EINVAL;
		goto out_err;
	}
	params->log_blocksize = log_blocksize;
	params->block_size = 1 << log_blocksize;
	params->log_blocks_per_page = PAGE_SHIFT - log_blocksize;
	params->blocks_per_page = 1 << params->log_blocks_per_page;

	if (WARN_ON_ONCE(!is_power_of_2(params->digest_size))) {
		err = -EINVAL;
		goto out_err;
	}
	if (params->block_size < 2 * params->digest_size) {
		fsverity_warn(inode,
			      "Merkle tree block size (%u) too small for hash algorithm \"%s\"",
			      params->block_size, hash_alg->name);
		err = -EINVAL;
		goto out_err;
	}
	params->log_digestsize = ilog2(params->digest_size);
	params->log_arity = log_blocksize - params->log_digestsize;
	params->hashes_per_block = 1 << params->log_arity;

	/*
	 * Compute the number of levels in the Merkle tree and create a map from
	 * level to the starting block of that level.  Level 'num_levels - 1' is
	 * the root and is stored first.  Level 0 is the level directly "above"
	 * the data blocks and is stored last.
	 */

	/* Compute number of levels and the number of blocks in each level */
	blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize;
	while (blocks > 1) {
		if (params->num_levels >= FS_VERITY_MAX_LEVELS) {
			fsverity_err(inode, "Too many levels in Merkle tree");
			err = -EFBIG;
			goto out_err;
		}
		blocks = (blocks + params->hashes_per_block - 1) >>
			 params->log_arity;
		blocks_in_level[params->num_levels++] = blocks;
	}

	/* Compute the starting block of each level */
	offset = 0;
	for (level = (int)params->num_levels - 1; level >= 0; level--) {
		params->level_start[level] = offset;
		offset += blocks_in_level[level];
	}

	/*
	 * With block_size != PAGE_SIZE, an in-memory bitmap will need to be
	 * allocated to track the "verified" status of hash blocks.  Don't allow
	 * this bitmap to get too large.  For now, limit it to 1 MiB, which
	 * limits the file size to about 4.4 TB with SHA-256 and 4K blocks.
	 *
	 * Together with the fact that the data, and thus also the Merkle tree,
	 * cannot have more than ULONG_MAX pages, this implies that hash block
	 * indices can always fit in an 'unsigned long'.  But to be safe, we
	 * explicitly check for that too.  Note, this is only for hash block
	 * indices; data block indices might not fit in an 'unsigned long'.
	 */
	if ((params->block_size != PAGE_SIZE && offset > 1 << 23) ||
	    offset > ULONG_MAX) {
		fsverity_err(inode, "Too many blocks in Merkle tree");
		err = -EFBIG;
		goto out_err;
	}

	params->tree_size = offset << log_blocksize;
	params->tree_pages = PAGE_ALIGN(params->tree_size) >> PAGE_SHIFT;
	return 0;

out_err:
	kfree(params->hashstate);
	memset(params, 0, sizeof(*params));
	return err;
}

/*
 * Compute the file digest by hashing the fsverity_descriptor excluding the
 * builtin signature and with the sig_size field set to 0.
 */
static int compute_file_digest(const struct fsverity_hash_alg *hash_alg,
			       struct fsverity_descriptor *desc,
			       u8 *file_digest)
{
	__le32 sig_size = desc->sig_size;
	int err;

	desc->sig_size = 0;
	err = fsverity_hash_buffer(hash_alg, desc, sizeof(*desc), file_digest);
	desc->sig_size = sig_size;

	return err;
}

/*
 * Create a new fsverity_info from the given fsverity_descriptor (with optional
 * appended builtin signature), and check the signature if present.  The
 * fsverity_descriptor must have already undergone basic validation.
 */
struct fsverity_info *fsverity_create_info(const struct inode *inode,
					   struct fsverity_descriptor *desc)
{
	struct fsverity_info *vi;
	int err;

	vi = kmem_cache_zalloc(fsverity_info_cachep, GFP_KERNEL);
	if (!vi)
		return ERR_PTR(-ENOMEM);
	vi->inode = inode;

	err = fsverity_init_merkle_tree_params(&vi->tree_params, inode,
					       desc->hash_algorithm,
					       desc->log_blocksize,
					       desc->salt, desc->salt_size);
	if (err) {
		fsverity_err(inode,
			     "Error %d initializing Merkle tree parameters",
			     err);
		goto fail;
	}

	memcpy(vi->root_hash, desc->root_hash, vi->tree_params.digest_size);

	err = compute_file_digest(vi->tree_params.hash_alg, desc,
				  vi->file_digest);
	if (err) {
		fsverity_err(inode, "Error %d computing file digest", err);
		goto fail;
	}

	err = fsverity_verify_signature(vi, desc->signature,
					le32_to_cpu(desc->sig_size));
	if (err)
		goto fail;

	if (vi->tree_params.block_size != PAGE_SIZE) {
		/*
		 * When the Merkle tree block size and page size differ, we use
		 * a bitmap to keep track of which hash blocks have been
		 * verified.  This bitmap must contain one bit per hash block,
		 * including alignment to a page boundary at the end.
		 *
		 * Eventually, to support extremely large files in an efficient
		 * way, it might be necessary to make pages of this bitmap
		 * reclaimable.  But for now, simply allocating the whole bitmap
		 * is a simple solution that works well on the files on which
		 * fsverity is realistically used.  E.g., with SHA-256 and 4K
		 * blocks, a 100MB file only needs a 24-byte bitmap, and the
		 * bitmap for any file under 17GB fits in a 4K page.
		 */
		unsigned long num_bits =
			vi->tree_params.tree_pages <<
			vi->tree_params.log_blocks_per_page;

		vi->hash_block_verified = kvcalloc(BITS_TO_LONGS(num_bits),
						   sizeof(unsigned long),
						   GFP_KERNEL);
		if (!vi->hash_block_verified) {
			err = -ENOMEM;
			goto fail;
		}
		spin_lock_init(&vi->hash_page_init_lock);
	}

	return vi;

fail:
	fsverity_free_info(vi);
	return ERR_PTR(err);
}

void fsverity_set_info(struct inode *inode, struct fsverity_info *vi)
{
	/*
	 * Multiple tasks may race to set ->i_verity_info, so use
	 * cmpxchg_release().  This pairs with the smp_load_acquire() in
	 * fsverity_get_info().  I.e., here we publish ->i_verity_info with a
	 * RELEASE barrier so that other tasks can ACQUIRE it.
	 */
	if (cmpxchg_release(&inode->i_verity_info, NULL, vi) != NULL) {
		/* Lost the race, so free the fsverity_info we allocated. */
		fsverity_free_info(vi);
		/*
		 * Afterwards, the caller may access ->i_verity_info directly,
		 * so make sure to ACQUIRE the winning fsverity_info.
		 */
		(void)fsverity_get_info(inode);
	}
}

void fsverity_free_info(struct fsverity_info *vi)
{
	if (!vi)
		return;
	kfree(vi->tree_params.hashstate);
	kvfree(vi->hash_block_verified);
	kmem_cache_free(fsverity_info_cachep, vi);
}

static bool validate_fsverity_descriptor(struct inode *inode,
					 const struct fsverity_descriptor *desc,
					 size_t desc_size)
{
	if (desc_size < sizeof(*desc)) {
		fsverity_err(inode, "Unrecognized descriptor size: %zu bytes",
			     desc_size);
		return false;
	}

	if (desc->version != 1) {
		fsverity_err(inode, "Unrecognized descriptor version: %u",
			     desc->version);
		return false;
	}

	if (memchr_inv(desc->__reserved, 0, sizeof(desc->__reserved))) {
		fsverity_err(inode, "Reserved bits set in descriptor");
		return false;
	}

	if (desc->salt_size > sizeof(desc->salt)) {
		fsverity_err(inode, "Invalid salt_size: %u", desc->salt_size);
		return false;
	}

	if (le64_to_cpu(desc->data_size) != inode->i_size) {
		fsverity_err(inode,
			     "Wrong data_size: %llu (desc) != %lld (inode)",
			     le64_to_cpu(desc->data_size), inode->i_size);
		return false;
	}

	if (le32_to_cpu(desc->sig_size) > desc_size - sizeof(*desc)) {
		fsverity_err(inode, "Signature overflows verity descriptor");
		return false;
	}

	return true;
}

/*
 * Read the inode's fsverity_descriptor (with optional appended builtin
 * signature) from the filesystem, and do basic validation of it.
 */
int fsverity_get_descriptor(struct inode *inode,
			    struct fsverity_descriptor **desc_ret)
{
	int res;
	struct fsverity_descriptor *desc;

	res = inode->i_sb->s_vop->get_verity_descriptor(inode, NULL, 0);
	if (res < 0) {
		fsverity_err(inode,
			     "Error %d getting verity descriptor size", res);
		return res;
	}
	if (res > FS_VERITY_MAX_DESCRIPTOR_SIZE) {
		fsverity_err(inode, "Verity descriptor is too large (%d bytes)",
			     res);
		return -EMSGSIZE;
	}
	desc = kmalloc(res, GFP_KERNEL);
	if (!desc)
		return -ENOMEM;
	res = inode->i_sb->s_vop->get_verity_descriptor(inode, desc, res);
	if (res < 0) {
		fsverity_err(inode, "Error %d reading verity descriptor", res);
		kfree(desc);
		return res;
	}

	if (!validate_fsverity_descriptor(inode, desc, res)) {
		kfree(desc);
		return -EINVAL;
	}

	*desc_ret = desc;
	return 0;
}

/* Ensure the inode has an ->i_verity_info */
static int ensure_verity_info(struct inode *inode)
{
	struct fsverity_info *vi = fsverity_get_info(inode);
	struct fsverity_descriptor *desc;
	int err;

	if (vi)
		return 0;

	err = fsverity_get_descriptor(inode, &desc);
	if (err)
		return err;

	vi = fsverity_create_info(inode, desc);
	if (IS_ERR(vi)) {
		err = PTR_ERR(vi);
		goto out_free_desc;
	}

	fsverity_set_info(inode, vi);
	err = 0;
out_free_desc:
	kfree(desc);
	return err;
}

int __fsverity_file_open(struct inode *inode, struct file *filp)
{
	if (filp->f_mode & FMODE_WRITE)
		return -EPERM;
	return ensure_verity_info(inode);
}
EXPORT_SYMBOL_GPL(__fsverity_file_open);

int __fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr)
{
	if (attr->ia_valid & ATTR_SIZE)
		return -EPERM;
	return 0;
}
EXPORT_SYMBOL_GPL(__fsverity_prepare_setattr);

void __fsverity_cleanup_inode(struct inode *inode)
{
	fsverity_free_info(inode->i_verity_info);
	inode->i_verity_info = NULL;
}
EXPORT_SYMBOL_GPL(__fsverity_cleanup_inode);

void __init fsverity_init_info_cache(void)
{
	fsverity_info_cachep = KMEM_CACHE_USERCOPY(
					fsverity_info,
					SLAB_RECLAIM_ACCOUNT | SLAB_PANIC,
					file_digest);
}