summaryrefslogtreecommitdiff
path: root/fs/erofs/data.c
blob: 252f4ee977d56965ce463f917e9a36456bccc023 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2021, Alibaba Cloud
 */
#include "internal.h"
#include <linux/prefetch.h>
#include <linux/sched/mm.h>
#include <linux/dax.h>
#include <trace/events/erofs.h>

void erofs_unmap_metabuf(struct erofs_buf *buf)
{
	if (buf->kmap_type == EROFS_KMAP)
		kunmap(buf->page);
	else if (buf->kmap_type == EROFS_KMAP_ATOMIC)
		kunmap_atomic(buf->base);
	buf->base = NULL;
	buf->kmap_type = EROFS_NO_KMAP;
}

void erofs_put_metabuf(struct erofs_buf *buf)
{
	if (!buf->page)
		return;
	erofs_unmap_metabuf(buf);
	put_page(buf->page);
	buf->page = NULL;
}

void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
		  erofs_blk_t blkaddr, enum erofs_kmap_type type)
{
	struct address_space *const mapping = inode->i_mapping;
	erofs_off_t offset = blknr_to_addr(blkaddr);
	pgoff_t index = offset >> PAGE_SHIFT;
	struct page *page = buf->page;
	struct folio *folio;
	unsigned int nofs_flag;

	if (!page || page->index != index) {
		erofs_put_metabuf(buf);

		nofs_flag = memalloc_nofs_save();
		folio = read_cache_folio(mapping, index, NULL, NULL);
		memalloc_nofs_restore(nofs_flag);
		if (IS_ERR(folio))
			return folio;

		/* should already be PageUptodate, no need to lock page */
		page = folio_file_page(folio, index);
		buf->page = page;
	}
	if (buf->kmap_type == EROFS_NO_KMAP) {
		if (type == EROFS_KMAP)
			buf->base = kmap(page);
		else if (type == EROFS_KMAP_ATOMIC)
			buf->base = kmap_atomic(page);
		buf->kmap_type = type;
	} else if (buf->kmap_type != type) {
		DBG_BUGON(1);
		return ERR_PTR(-EFAULT);
	}
	if (type == EROFS_NO_KMAP)
		return NULL;
	return buf->base + (offset & ~PAGE_MASK);
}

void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
			 erofs_blk_t blkaddr, enum erofs_kmap_type type)
{
	if (erofs_is_fscache_mode(sb))
		return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode,
				   blkaddr, type);

	return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type);
}

static int erofs_map_blocks_flatmode(struct inode *inode,
				     struct erofs_map_blocks *map,
				     int flags)
{
	erofs_blk_t nblocks, lastblk;
	u64 offset = map->m_la;
	struct erofs_inode *vi = EROFS_I(inode);
	bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE);

	nblocks = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
	lastblk = nblocks - tailendpacking;

	/* there is no hole in flatmode */
	map->m_flags = EROFS_MAP_MAPPED;
	if (offset < blknr_to_addr(lastblk)) {
		map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
		map->m_plen = blknr_to_addr(lastblk) - offset;
	} else if (tailendpacking) {
		/* 2 - inode inline B: inode, [xattrs], inline last blk... */
		struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);

		map->m_pa = iloc(sbi, vi->nid) + vi->inode_isize +
			vi->xattr_isize + erofs_blkoff(map->m_la);
		map->m_plen = inode->i_size - offset;

		/* inline data should be located in the same meta block */
		if (erofs_blkoff(map->m_pa) + map->m_plen > EROFS_BLKSIZ) {
			erofs_err(inode->i_sb,
				  "inline data cross block boundary @ nid %llu",
				  vi->nid);
			DBG_BUGON(1);
			return -EFSCORRUPTED;
		}
		map->m_flags |= EROFS_MAP_META;
	} else {
		erofs_err(inode->i_sb,
			  "internal error @ nid: %llu (size %llu), m_la 0x%llx",
			  vi->nid, inode->i_size, map->m_la);
		DBG_BUGON(1);
		return -EIO;
	}
	return 0;
}

int erofs_map_blocks(struct inode *inode,
		     struct erofs_map_blocks *map, int flags)
{
	struct super_block *sb = inode->i_sb;
	struct erofs_inode *vi = EROFS_I(inode);
	struct erofs_inode_chunk_index *idx;
	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
	u64 chunknr;
	unsigned int unit;
	erofs_off_t pos;
	void *kaddr;
	int err = 0;

	trace_erofs_map_blocks_enter(inode, map, flags);
	map->m_deviceid = 0;
	if (map->m_la >= inode->i_size) {
		/* leave out-of-bound access unmapped */
		map->m_flags = 0;
		map->m_plen = 0;
		goto out;
	}

	if (vi->datalayout != EROFS_INODE_CHUNK_BASED) {
		err = erofs_map_blocks_flatmode(inode, map, flags);
		goto out;
	}

	if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)
		unit = sizeof(*idx);			/* chunk index */
	else
		unit = EROFS_BLOCK_MAP_ENTRY_SIZE;	/* block map */

	chunknr = map->m_la >> vi->chunkbits;
	pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
		    vi->xattr_isize, unit) + unit * chunknr;

	kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP);
	if (IS_ERR(kaddr)) {
		err = PTR_ERR(kaddr);
		goto out;
	}
	map->m_la = chunknr << vi->chunkbits;
	map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits,
			    roundup(inode->i_size - map->m_la, EROFS_BLKSIZ));

	/* handle block map */
	if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) {
		__le32 *blkaddr = kaddr + erofs_blkoff(pos);

		if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) {
			map->m_flags = 0;
		} else {
			map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr));
			map->m_flags = EROFS_MAP_MAPPED;
		}
		goto out_unlock;
	}
	/* parse chunk indexes */
	idx = kaddr + erofs_blkoff(pos);
	switch (le32_to_cpu(idx->blkaddr)) {
	case EROFS_NULL_ADDR:
		map->m_flags = 0;
		break;
	default:
		map->m_deviceid = le16_to_cpu(idx->device_id) &
			EROFS_SB(sb)->device_id_mask;
		map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr));
		map->m_flags = EROFS_MAP_MAPPED;
		break;
	}
out_unlock:
	erofs_put_metabuf(&buf);
out:
	if (!err)
		map->m_llen = map->m_plen;
	trace_erofs_map_blocks_exit(inode, map, flags, 0);
	return err;
}

int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
{
	struct erofs_dev_context *devs = EROFS_SB(sb)->devs;
	struct erofs_device_info *dif;
	int id;

	/* primary device by default */
	map->m_bdev = sb->s_bdev;
	map->m_daxdev = EROFS_SB(sb)->dax_dev;
	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
	map->m_fscache = EROFS_SB(sb)->s_fscache;

	if (map->m_deviceid) {
		down_read(&devs->rwsem);
		dif = idr_find(&devs->tree, map->m_deviceid - 1);
		if (!dif) {
			up_read(&devs->rwsem);
			return -ENODEV;
		}
		map->m_bdev = dif->bdev;
		map->m_daxdev = dif->dax_dev;
		map->m_dax_part_off = dif->dax_part_off;
		map->m_fscache = dif->fscache;
		up_read(&devs->rwsem);
	} else if (devs->extra_devices) {
		down_read(&devs->rwsem);
		idr_for_each_entry(&devs->tree, dif, id) {
			erofs_off_t startoff, length;

			if (!dif->mapped_blkaddr)
				continue;
			startoff = blknr_to_addr(dif->mapped_blkaddr);
			length = blknr_to_addr(dif->blocks);

			if (map->m_pa >= startoff &&
			    map->m_pa < startoff + length) {
				map->m_pa -= startoff;
				map->m_bdev = dif->bdev;
				map->m_daxdev = dif->dax_dev;
				map->m_dax_part_off = dif->dax_part_off;
				map->m_fscache = dif->fscache;
				break;
			}
		}
		up_read(&devs->rwsem);
	}
	return 0;
}

static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
		unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
{
	int ret;
	struct erofs_map_blocks map;
	struct erofs_map_dev mdev;

	map.m_la = offset;
	map.m_llen = length;

	ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
	if (ret < 0)
		return ret;

	mdev = (struct erofs_map_dev) {
		.m_deviceid = map.m_deviceid,
		.m_pa = map.m_pa,
	};
	ret = erofs_map_dev(inode->i_sb, &mdev);
	if (ret)
		return ret;

	iomap->offset = map.m_la;
	if (flags & IOMAP_DAX)
		iomap->dax_dev = mdev.m_daxdev;
	else
		iomap->bdev = mdev.m_bdev;
	iomap->length = map.m_llen;
	iomap->flags = 0;
	iomap->private = NULL;

	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
		iomap->type = IOMAP_HOLE;
		iomap->addr = IOMAP_NULL_ADDR;
		if (!iomap->length)
			iomap->length = length;
		return 0;
	}

	if (map.m_flags & EROFS_MAP_META) {
		void *ptr;
		struct erofs_buf buf = __EROFS_BUF_INITIALIZER;

		iomap->type = IOMAP_INLINE;
		ptr = erofs_read_metabuf(&buf, inode->i_sb,
					 erofs_blknr(mdev.m_pa), EROFS_KMAP);
		if (IS_ERR(ptr))
			return PTR_ERR(ptr);
		iomap->inline_data = ptr + erofs_blkoff(mdev.m_pa);
		iomap->private = buf.base;
	} else {
		iomap->type = IOMAP_MAPPED;
		iomap->addr = mdev.m_pa;
		if (flags & IOMAP_DAX)
			iomap->addr += mdev.m_dax_part_off;
	}
	return 0;
}

static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length,
		ssize_t written, unsigned int flags, struct iomap *iomap)
{
	void *ptr = iomap->private;

	if (ptr) {
		struct erofs_buf buf = {
			.page = kmap_to_page(ptr),
			.base = ptr,
			.kmap_type = EROFS_KMAP,
		};

		DBG_BUGON(iomap->type != IOMAP_INLINE);
		erofs_put_metabuf(&buf);
	} else {
		DBG_BUGON(iomap->type == IOMAP_INLINE);
	}
	return written;
}

static const struct iomap_ops erofs_iomap_ops = {
	.iomap_begin = erofs_iomap_begin,
	.iomap_end = erofs_iomap_end,
};

int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		 u64 start, u64 len)
{
	if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
#ifdef CONFIG_EROFS_FS_ZIP
		return iomap_fiemap(inode, fieinfo, start, len,
				    &z_erofs_iomap_report_ops);
#else
		return -EOPNOTSUPP;
#endif
	}
	return iomap_fiemap(inode, fieinfo, start, len, &erofs_iomap_ops);
}

/*
 * since we dont have write or truncate flows, so no inode
 * locking needs to be held at the moment.
 */
static int erofs_readpage(struct file *file, struct page *page)
{
	return iomap_readpage(page, &erofs_iomap_ops);
}

static void erofs_readahead(struct readahead_control *rac)
{
	return iomap_readahead(rac, &erofs_iomap_ops);
}

static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
{
	return iomap_bmap(mapping, block, &erofs_iomap_ops);
}

static int erofs_prepare_dio(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	loff_t align = iocb->ki_pos | iov_iter_count(to) |
		iov_iter_alignment(to);
	struct block_device *bdev = inode->i_sb->s_bdev;
	unsigned int blksize_mask;

	if (bdev)
		blksize_mask = (1 << ilog2(bdev_logical_block_size(bdev))) - 1;
	else
		blksize_mask = (1 << inode->i_blkbits) - 1;

	if (align & blksize_mask)
		return -EINVAL;
	return 0;
}

static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	/* no need taking (shared) inode lock since it's a ro filesystem */
	if (!iov_iter_count(to))
		return 0;

#ifdef CONFIG_FS_DAX
	if (IS_DAX(iocb->ki_filp->f_mapping->host))
		return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
#endif
	if (iocb->ki_flags & IOCB_DIRECT) {
		int err = erofs_prepare_dio(iocb, to);

		if (!err)
			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
					    NULL, 0, NULL, 0);
		if (err < 0)
			return err;
	}
	return filemap_read(iocb, to, 0);
}

/* for uncompressed (aligned) files and raw access for other files */
const struct address_space_operations erofs_raw_access_aops = {
	.readpage = erofs_readpage,
	.readahead = erofs_readahead,
	.bmap = erofs_bmap,
	.direct_IO = noop_direct_IO,
};

#ifdef CONFIG_FS_DAX
static vm_fault_t erofs_dax_huge_fault(struct vm_fault *vmf,
		enum page_entry_size pe_size)
{
	return dax_iomap_fault(vmf, pe_size, NULL, NULL, &erofs_iomap_ops);
}

static vm_fault_t erofs_dax_fault(struct vm_fault *vmf)
{
	return erofs_dax_huge_fault(vmf, PE_SIZE_PTE);
}

static const struct vm_operations_struct erofs_dax_vm_ops = {
	.fault		= erofs_dax_fault,
	.huge_fault	= erofs_dax_huge_fault,
};

static int erofs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	if (!IS_DAX(file_inode(file)))
		return generic_file_readonly_mmap(file, vma);

	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
		return -EINVAL;

	vma->vm_ops = &erofs_dax_vm_ops;
	vma->vm_flags |= VM_HUGEPAGE;
	return 0;
}
#else
#define erofs_file_mmap	generic_file_readonly_mmap
#endif

const struct file_operations erofs_file_fops = {
	.llseek		= generic_file_llseek,
	.read_iter	= erofs_file_read_iter,
	.mmap		= erofs_file_mmap,
	.splice_read	= generic_file_splice_read,
};