summaryrefslogtreecommitdiff
path: root/fs/xfs/scrub/xfile.c
blob: d98e8e77c684fa2bfca3232a60c115f905d8a6da (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2018-2023 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <djwong@kernel.org>
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_format.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/scrub.h"
#include "scrub/trace.h"
#include <linux/shmem_fs.h>

/*
 * Swappable Temporary Memory
 * ==========================
 *
 * Online checking sometimes needs to be able to stage a large amount of data
 * in memory.  This information might not fit in the available memory and it
 * doesn't all need to be accessible at all times.  In other words, we want an
 * indexed data buffer to store data that can be paged out.
 *
 * When CONFIG_TMPFS=y, shmemfs is enough of a filesystem to meet those
 * requirements.  Therefore, the xfile mechanism uses an unlinked shmem file to
 * store our staging data.  This file is not installed in the file descriptor
 * table so that user programs cannot access the data, which means that the
 * xfile must be freed with xfile_destroy.
 *
 * xfiles assume that the caller will handle all required concurrency
 * management; standard vfs locks (freezer and inode) are not taken.  Reads
 * and writes are satisfied directly from the page cache.
 *
 * NOTE: The current shmemfs implementation has a quirk that in-kernel reads
 * of a hole cause a page to be mapped into the file.  If you are going to
 * create a sparse xfile, please be careful about reading from uninitialized
 * parts of the file.  These pages are !Uptodate and will eventually be
 * reclaimed if not written, but in the short term this boosts memory
 * consumption.
 */

/*
 * xfiles must not be exposed to userspace and require upper layers to
 * coordinate access to the one handle returned by the constructor, so
 * establish a separate lock class for xfiles to avoid confusing lockdep.
 */
static struct lock_class_key xfile_i_mutex_key;

/*
 * Create an xfile of the given size.  The description will be used in the
 * trace output.
 */
int
xfile_create(
	const char		*description,
	loff_t			isize,
	struct xfile		**xfilep)
{
	struct inode		*inode;
	struct xfile		*xf;
	int			error = -ENOMEM;

	xf = kmalloc(sizeof(struct xfile), XCHK_GFP_FLAGS);
	if (!xf)
		return -ENOMEM;

	xf->file = shmem_file_setup(description, isize, 0);
	if (!xf->file)
		goto out_xfile;
	if (IS_ERR(xf->file)) {
		error = PTR_ERR(xf->file);
		goto out_xfile;
	}

	/*
	 * We want a large sparse file that we can pread, pwrite, and seek.
	 * xfile users are responsible for keeping the xfile hidden away from
	 * all other callers, so we skip timestamp updates and security checks.
	 * Make the inode only accessible by root, just in case the xfile ever
	 * escapes.
	 */
	xf->file->f_mode |= FMODE_PREAD | FMODE_PWRITE | FMODE_NOCMTIME |
			    FMODE_LSEEK;
	xf->file->f_flags |= O_RDWR | O_LARGEFILE | O_NOATIME;
	inode = file_inode(xf->file);
	inode->i_flags |= S_PRIVATE | S_NOCMTIME | S_NOATIME;
	inode->i_mode &= ~0177;
	inode->i_uid = GLOBAL_ROOT_UID;
	inode->i_gid = GLOBAL_ROOT_GID;

	lockdep_set_class(&inode->i_rwsem, &xfile_i_mutex_key);

	trace_xfile_create(xf);

	*xfilep = xf;
	return 0;
out_xfile:
	kfree(xf);
	return error;
}

/* Close the file and release all resources. */
void
xfile_destroy(
	struct xfile		*xf)
{
	struct inode		*inode = file_inode(xf->file);

	trace_xfile_destroy(xf);

	lockdep_set_class(&inode->i_rwsem, &inode->i_sb->s_type->i_mutex_key);
	fput(xf->file);
	kfree(xf);
}

/*
 * Read a memory object directly from the xfile's page cache.  Unlike regular
 * pread, we return -E2BIG and -EFBIG for reads that are too large or at too
 * high an offset, instead of truncating the read.  Otherwise, we return
 * bytes read or an error code, like regular pread.
 */
ssize_t
xfile_pread(
	struct xfile		*xf,
	void			*buf,
	size_t			count,
	loff_t			pos)
{
	struct inode		*inode = file_inode(xf->file);
	struct address_space	*mapping = inode->i_mapping;
	struct page		*page = NULL;
	ssize_t			read = 0;
	unsigned int		pflags;
	int			error = 0;

	if (count > MAX_RW_COUNT)
		return -E2BIG;
	if (inode->i_sb->s_maxbytes - pos < count)
		return -EFBIG;

	trace_xfile_pread(xf, pos, count);

	pflags = memalloc_nofs_save();
	while (count > 0) {
		void		*p, *kaddr;
		unsigned int	len;

		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));

		/*
		 * In-kernel reads of a shmem file cause it to allocate a page
		 * if the mapping shows a hole.  Therefore, if we hit ENOMEM
		 * we can continue by zeroing the caller's buffer.
		 */
		page = shmem_read_mapping_page_gfp(mapping, pos >> PAGE_SHIFT,
				__GFP_NOWARN);
		if (IS_ERR(page)) {
			error = PTR_ERR(page);
			if (error != -ENOMEM)
				break;

			memset(buf, 0, len);
			goto advance;
		}

		if (PageUptodate(page)) {
			/*
			 * xfile pages must never be mapped into userspace, so
			 * we skip the dcache flush.
			 */
			kaddr = kmap_local_page(page);
			p = kaddr + offset_in_page(pos);
			memcpy(buf, p, len);
			kunmap_local(kaddr);
		} else {
			memset(buf, 0, len);
		}
		put_page(page);

advance:
		count -= len;
		pos += len;
		buf += len;
		read += len;
	}
	memalloc_nofs_restore(pflags);

	if (read > 0)
		return read;
	return error;
}

/*
 * Write a memory object directly to the xfile's page cache.  Unlike regular
 * pwrite, we return -E2BIG and -EFBIG for writes that are too large or at too
 * high an offset, instead of truncating the write.  Otherwise, we return
 * bytes written or an error code, like regular pwrite.
 */
ssize_t
xfile_pwrite(
	struct xfile		*xf,
	const void		*buf,
	size_t			count,
	loff_t			pos)
{
	struct inode		*inode = file_inode(xf->file);
	struct address_space	*mapping = inode->i_mapping;
	const struct address_space_operations *aops = mapping->a_ops;
	struct page		*page = NULL;
	ssize_t			written = 0;
	unsigned int		pflags;
	int			error = 0;

	if (count > MAX_RW_COUNT)
		return -E2BIG;
	if (inode->i_sb->s_maxbytes - pos < count)
		return -EFBIG;

	trace_xfile_pwrite(xf, pos, count);

	pflags = memalloc_nofs_save();
	while (count > 0) {
		void		*fsdata = NULL;
		void		*p, *kaddr;
		unsigned int	len;
		int		ret;

		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));

		/*
		 * We call write_begin directly here to avoid all the freezer
		 * protection lock-taking that happens in the normal path.
		 * shmem doesn't support fs freeze, but lockdep doesn't know
		 * that and will trip over that.
		 */
		error = aops->write_begin(NULL, mapping, pos, len, &page,
				&fsdata);
		if (error)
			break;

		/*
		 * xfile pages must never be mapped into userspace, so we skip
		 * the dcache flush.  If the page is not uptodate, zero it
		 * before writing data.
		 */
		kaddr = kmap_local_page(page);
		if (!PageUptodate(page)) {
			memset(kaddr, 0, PAGE_SIZE);
			SetPageUptodate(page);
		}
		p = kaddr + offset_in_page(pos);
		memcpy(p, buf, len);
		kunmap_local(kaddr);

		ret = aops->write_end(NULL, mapping, pos, len, len, page,
				fsdata);
		if (ret < 0) {
			error = ret;
			break;
		}

		written += ret;
		if (ret != len)
			break;

		count -= ret;
		pos += ret;
		buf += ret;
	}
	memalloc_nofs_restore(pflags);

	if (written > 0)
		return written;
	return error;
}

/* Find the next written area in the xfile data for a given offset. */
loff_t
xfile_seek_data(
	struct xfile		*xf,
	loff_t			pos)
{
	loff_t			ret;

	ret = vfs_llseek(xf->file, pos, SEEK_DATA);
	trace_xfile_seek_data(xf, pos, ret);
	return ret;
}

/* Query stat information for an xfile. */
int
xfile_stat(
	struct xfile		*xf,
	struct xfile_stat	*statbuf)
{
	struct kstat		ks;
	int			error;

	error = vfs_getattr_nosec(&xf->file->f_path, &ks,
			STATX_SIZE | STATX_BLOCKS, AT_STATX_DONT_SYNC);
	if (error)
		return error;

	statbuf->size = ks.size;
	statbuf->bytes = ks.blocks << SECTOR_SHIFT;
	return 0;
}

/*
 * Grab the (locked) page for a memory object.  The object cannot span a page
 * boundary.  Returns 0 (and a locked page) if successful, -ENOTBLK if we
 * cannot grab the page, or the usual negative errno.
 */
int
xfile_get_page(
	struct xfile		*xf,
	loff_t			pos,
	unsigned int		len,
	struct xfile_page	*xfpage)
{
	struct inode		*inode = file_inode(xf->file);
	struct address_space	*mapping = inode->i_mapping;
	const struct address_space_operations *aops = mapping->a_ops;
	struct page		*page = NULL;
	void			*fsdata = NULL;
	loff_t			key = round_down(pos, PAGE_SIZE);
	unsigned int		pflags;
	int			error;

	if (inode->i_sb->s_maxbytes - pos < len)
		return -ENOMEM;
	if (len > PAGE_SIZE - offset_in_page(pos))
		return -ENOTBLK;

	trace_xfile_get_page(xf, pos, len);

	pflags = memalloc_nofs_save();

	/*
	 * We call write_begin directly here to avoid all the freezer
	 * protection lock-taking that happens in the normal path.  shmem
	 * doesn't support fs freeze, but lockdep doesn't know that and will
	 * trip over that.
	 */
	error = aops->write_begin(NULL, mapping, key, PAGE_SIZE, &page,
			&fsdata);
	if (error)
		goto out_pflags;

	/* We got the page, so make sure we push out EOF. */
	if (i_size_read(inode) < pos + len)
		i_size_write(inode, pos + len);

	/*
	 * If the page isn't up to date, fill it with zeroes before we hand it
	 * to the caller and make sure the backing store will hold on to them.
	 */
	if (!PageUptodate(page)) {
		void	*kaddr;

		kaddr = kmap_local_page(page);
		memset(kaddr, 0, PAGE_SIZE);
		kunmap_local(kaddr);
		SetPageUptodate(page);
	}

	/*
	 * Mark each page dirty so that the contents are written to some
	 * backing store when we drop this buffer, and take an extra reference
	 * to prevent the xfile page from being swapped or removed from the
	 * page cache by reclaim if the caller unlocks the page.
	 */
	set_page_dirty(page);
	get_page(page);

	xfpage->page = page;
	xfpage->fsdata = fsdata;
	xfpage->pos = key;
out_pflags:
	memalloc_nofs_restore(pflags);
	return error;
}

/*
 * Release the (locked) page for a memory object.  Returns 0 or a negative
 * errno.
 */
int
xfile_put_page(
	struct xfile		*xf,
	struct xfile_page	*xfpage)
{
	struct inode		*inode = file_inode(xf->file);
	struct address_space	*mapping = inode->i_mapping;
	const struct address_space_operations *aops = mapping->a_ops;
	unsigned int		pflags;
	int			ret;

	trace_xfile_put_page(xf, xfpage->pos, PAGE_SIZE);

	/* Give back the reference that we took in xfile_get_page. */
	put_page(xfpage->page);

	pflags = memalloc_nofs_save();
	ret = aops->write_end(NULL, mapping, xfpage->pos, PAGE_SIZE, PAGE_SIZE,
			xfpage->page, xfpage->fsdata);
	memalloc_nofs_restore(pflags);
	memset(xfpage, 0, sizeof(struct xfile_page));

	if (ret < 0)
		return ret;
	if (ret != PAGE_SIZE)
		return -EIO;
	return 0;
}