-
Notifications
You must be signed in to change notification settings - Fork 6
/
mmap.c
566 lines (491 loc) · 16.4 KB
/
mmap.c
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
/*
* Copyright (c) 1998-2011 Erez Zadok
* Copyright (c) 2009 Shrikar Archak
* Copyright (c) 2003-2011 Stony Brook University
* Copyright (c) 2003-2011 The Research Foundation of SUNY
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include "wrapfs.h"
#include <linux/page-flags.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/crypto.h>
/**
* wrapfs_read_lower
* @data: The read data is stored here by this function
* @offset: Byte offset in the lower file from which to read the data
* @size: Number of bytes to read from @offset of the lower file and
* store into @data
* @wrapfs_inode: The wrapfs inode
*
* Read @size bytes of data at byte offset @offset from the lower
* inode into memory location @data.
*
* Returns bytes read on success; 0 on EOF; less than zero on error
*/
int wrapfs_read_lower(char *data, loff_t offset, size_t size,
struct inode *wrapfs_inode, struct file *file)
{
struct file *lower_file;
mm_segment_t fs_save;
ssize_t rc;
mode_t previous_mode;
printk(KERN_INFO "wrapfs_read_lower");
lower_file = wrapfs_lower_file(file);
if (!lower_file)
return -EIO;
fs_save = get_fs();
set_fs(get_ds());
previous_mode = lower_file->f_mode;
lower_file->f_mode |= FMODE_READ;
rc = vfs_read(lower_file, data, size, &offset);
lower_file->f_mode = previous_mode;
set_fs(fs_save);
return rc;
}
int wrapfs_write_lower(struct inode *wrapfs_inode, char *data,
loff_t offset, size_t size, struct file *file)
{
struct file *lower_file;
mm_segment_t fs_save;
ssize_t rc;
printk(KERN_INFO "wrapfs_write_lower");
lower_file = wrapfs_lower_file(file);
if (!lower_file)
return -EIO;
fs_save = get_fs();
set_fs(get_ds());
rc = vfs_write(lower_file, data, size, &offset);
set_fs(fs_save);
mark_inode_dirty_sync(wrapfs_inode);
return rc;
}
/**
* wrapfs_read_lower_page_segment
* @page_for_wrapfs: The page into which data for wrapfs will be
* written
* @offset_in_page: Offset in @page_for_wrapfs from which to start
* writing
* @size: The number of bytes to write into @page_for_wrapfs
* @wrapfs_inode: The wrapfs inode
*
* Determines the byte offset in the file for the given page and
* offset within the page, maps the page, and makes the call to read
* the contents of @page_for_wrapfs from the lower inode.
*
* Returns zero on success; non-zero otherwise
*/
int wrapfs_read_lower_page_segment(struct page *page_for_wrapfs,
pgoff_t page_index,
size_t offset_in_page, size_t size,
struct inode *wrapfs_inode,
struct file *file)
{
char *virt;
loff_t offset;
int rc;
#ifdef WRAPFS_CRYPTO
char *encrypted;
struct page *encrypted_page = alloc_page(GFP_KERNEL);
if (IS_ERR(encrypted_page))
{
rc = PTR_ERR(encrypted_page);
return rc;
}
encrypted = kmap(encrypted_page);
#endif
printk(KERN_INFO "wrapfs_read_lower_page_segment");
offset = ((((loff_t)page_index) << PAGE_CACHE_SHIFT) + offset_in_page);
virt = kmap(page_for_wrapfs);
#ifdef WRAPFS_CRYPTO
rc = wrapfs_read_lower(encrypted, offset, size, wrapfs_inode, file);
rc = encrypt_decrypt(WRAPFS_SB(file->f_dentry->d_sb)->key, virt, encrypted, size, 0);
if(rc < 0)
goto out_crypto;
#else
rc = wrapfs_read_lower(virt, offset, size, wrapfs_inode, file);
#endif
if (rc > 0)
rc = 0;
#ifdef WRAPFS_CRYPTO
out_crypto:
kunmap(encrypted_page);
__free_page(encrypted_page);
#endif
kunmap(page_for_wrapfs);
flush_dcache_page(page_for_wrapfs);
return rc;
}
/**
* wrapfs_write_lower_page_segment
* @wrapfs_inode: The wrapfs inode
* @page_for_lower: The page containing the data to be written to the
* lower file
* @offset_in_page: The offset in the @page_for_lower from which to
* start writing the data
* @size: The amount of data from @page_for_lower to write to the
* lower file
*
* Determines the byte offset in the file for the given page and
* offset within the page, maps the page, and makes the call to write
* the contents of @page_for_lower to the lower inode.
*
* Returns zero on success; non-zero otherwise
*/
int wrapfs_write_lower_page_segment(struct inode *wrapfs_inode,
struct page *page_for_lower,
size_t offset_in_page, size_t size,
struct file *file)
{
char *virt;
loff_t offset;
int rc = -1;
#ifdef WRAPFS_CRYPTO
char *encrypted;
struct page *encrypted_page = alloc_page(GFP_KERNEL);
if(IS_ERR(encrypted_page))
{
rc = PTR_ERR(encrypted_page);
return rc;
}
encrypted = kmap(encrypted_page);
#endif
printk(KERN_INFO "wrapfs_write_lower_page_segment");
offset = ((((loff_t)page_for_lower->index) << PAGE_CACHE_SHIFT)
+ offset_in_page);
virt = kmap(page_for_lower);
#ifdef WRAPFS_CRYPTO
rc = encrypt_decrypt(WRAPFS_SB(file->f_dentry->d_sb)->key, encrypted, virt, size, 1);
if(rc < 0)
goto out_crypto;
rc = wrapfs_write_lower(wrapfs_inode, encrypted, offset, size, file);
#else
rc = wrapfs_write_lower(wrapfs_inode, virt, offset, size, file);
#endif
if (rc > 0)
rc = 0;
kunmap(page_for_lower);
#ifdef WRAPFS_CRYPTO
out_crypto:
kunmap(encrypted_page);
__free_page(encrypted_page);
#endif
return rc;
}
/**
* wrapfs_writepage
* @page: Page that is locked before this call is made
*
* Returns zero on success; non-zero otherwise
*/
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
#ifdef WRAPFS_CRYPTO
char *encrypted;
char *data;
#endif
printk(KERN_INFO "wrapfs_writepage");
BUG_ON(!PageUptodate(page));
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
//lower_page = grab_cache_page(lower_inode->i_mapping, page->index);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
#ifdef WRAPFS_CRYPTO
data = kmap(page);
encrypted = kmap(lower_page);
err = encrypt_decrypt(WRAPFS_SB(inode->i_sb)->key, encrypted, data, PAGE_CACHE_SIZE, 1);
if(err < 0)
goto out_crypto;
#else
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
#endif
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE)
{
err = 0;
unlock_page(lower_page);
}
#ifdef WRAPFS_CRYPTO
out_crypto:
kunmap(page);
kunmap(lower_page);
#endif
out_release:
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
return err;
}
static int wrapfs_readpage(struct file *file, struct page *page)
{
int err=0;
printk(KERN_INFO "wrapfs_readpage");
err = wrapfs_read_lower_page_segment(
page, page->index, 0, PAGE_CACHE_SIZE,
page->mapping->host,file);
if (err) {
printk(KERN_ERR "Error reading page; err = "
"[%d]\n", err);
goto out;
}
out:
if (err)
ClearPageUptodate(page);
else
SetPageUptodate(page);
unlock_page(page);
return err;
}
static int wrapfs_write_begin(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct page *page;
loff_t prev_page_end_size;
int rc = 0;
printk(KERN_INFO "write_begin");
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
prev_page_end_size = ((loff_t)index << PAGE_CACHE_SHIFT);
if (!PageUptodate(page))
{
rc = wrapfs_read_lower_page_segment(
page, index, 0, PAGE_CACHE_SIZE,
mapping->host, file);
if (rc)
{
printk(KERN_ERR "%s: Error reading "
"page; rc = [%d]\n",
__func__, rc);
ClearPageUptodate(page);
goto out;
}
SetPageUptodate(page);
}
/* Writing to a new page, and creating a small hole from start
* of page? Zero it out. */
if ((i_size_read(mapping->host) == prev_page_end_size) && (pos != 0))
zero_user(page, 0, PAGE_CACHE_SIZE);
out:
if (unlikely(rc))
{
unlock_page(page);
page_cache_release(page);
*pagep = NULL;
}
return rc;
}
/**
* @file: The wrapfs file object
* @mapping: The wrapfs object
* @pos: The file position
* @len: The length of the data (unused)
* @copied: The amount of data copied
* @page: The wrapfs page
* @fsdata: The fsdata (unused)
*
* This is where we encrypt the data and pass the encrypted data to
* the lower filesystem.
*/
static int wrapfs_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
unsigned to = from + copied;
struct inode *wrapfs_inode = mapping->host;
int rc;
printk(KERN_INFO "wrapfs_write_end");
rc = wrapfs_write_lower_page_segment(wrapfs_inode, page, 0, to, file);
if (!rc)
{
rc = copied;
fsstack_copy_inode_size(wrapfs_inode,
wrapfs_lower_inode(wrapfs_inode));
}
//out:
unlock_page(page);
page_cache_release(page);
return rc;
}
static sector_t wrapfs_bmap(struct address_space *mapping, sector_t block)
{
int rc = 0;
struct inode *inode;
struct inode *lower_inode;
printk(KERN_INFO "wrapfs_bmap");
inode = (struct inode *)mapping->host;
lower_inode = wrapfs_lower_inode(inode);
if (lower_inode->i_mapping->a_ops->bmap)
rc = lower_inode->i_mapping->a_ops->bmap(lower_inode->i_mapping,
block);
return rc;
}
static int wrapfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int err;
struct file *file, *lower_file;
const struct vm_operations_struct *lower_vm_ops;
struct vm_area_struct lower_vma;
printk(KERN_INFO "in wrapfs_fault");
memcpy(&lower_vma, vma, sizeof(struct vm_area_struct));
file = lower_vma.vm_file;
lower_vm_ops = WRAPFS_F(file)->lower_vm_ops;
BUG_ON(!lower_vm_ops);
lower_file = wrapfs_lower_file(file);
/*
* XXX: vm_ops->fault may be called in parallel. Because we have to
* resort to temporarily changing the vma->vm_file to point to the
* lower file, a concurrent invocation of wrapfs_fault could see a
* different value. In this workaround, we keep a different copy of
* the vma structure in our stack, so we never expose a different
* value of the vma->vm_file called to us, even temporarily. A
* better fix would be to change the calling semantics of ->fault to
* take an explicit file pointer.
*/
lower_vma.vm_file = lower_file;
err = lower_vm_ops->fault(&lower_vma, vmf);
return err;
}
static int wrapfs_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
int err = 0;
struct file *file, *lower_file;
const struct vm_operations_struct *lower_vm_ops;
struct vm_area_struct lower_vma;
memcpy(&lower_vma, vma, sizeof(struct vm_area_struct));
file = lower_vma.vm_file;
lower_vm_ops = WRAPFS_F(file)->lower_vm_ops;
BUG_ON(!lower_vm_ops);
if (!lower_vm_ops->page_mkwrite)
goto out;
lower_file = wrapfs_lower_file(file);
/*
* XXX: vm_ops->page_mkwrite may be called in parallel.
* Because we have to resort to temporarily changing the
* vma->vm_file to point to the lower file, a concurrent
* invocation of wrapfs_page_mkwrite could see a different
* value. In this workaround, we keep a different copy of the
* vma structure in our stack, so we never expose a different
* value of the vma->vm_file called to us, even temporarily.
* A better fix would be to change the calling semantics of
* ->page_mkwrite to take an explicit file pointer.
*/
lower_vma.vm_file = lower_file;
err = lower_vm_ops->page_mkwrite(&lower_vma, vmf);
out:
return err;
}
static ssize_t wrapfs_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
/*
* This function should never be called directly. We need it
* to exist, to get past a check in open_check_o_direct(),
* which is called from do_last().
*/
return -EINVAL;
}
/*
* XXX: the default address_space_ops for wrapfs is empty. We cannot set
* our inode->i_mapping->a_ops to NULL because too many code paths expect
* the a_ops vector to be non-NULL.
*/
const struct address_space_operations wrapfs_dummy_aops = {
/* empty on purpose */
.direct_IO = wrapfs_direct_IO,
};
const struct address_space_operations wrapfs_aops = {
/* empty on purpose */
.readpage = wrapfs_readpage,
.writepage = wrapfs_writepage,
.write_begin = wrapfs_write_begin,
.write_end = wrapfs_write_end,
.bmap = wrapfs_bmap,
};
const struct vm_operations_struct wrapfs_vm_ops = {
.fault = wrapfs_fault,
.page_mkwrite = wrapfs_page_mkwrite,
};