]>
Commit | Line | Data |
---|---|---|
0c5527e5 | 1 | diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX |
82260373 | 2 | index 8c624a1..4aa288b 100644 |
0c5527e5 AM |
3 | --- a/Documentation/filesystems/00-INDEX |
4 | +++ b/Documentation/filesystems/00-INDEX | |
82260373 | 5 | @@ -110,6 +110,8 @@ udf.txt |
2380c486 JR |
6 | - info and mount options for the UDF filesystem. |
7 | ufs.txt | |
8 | - info on the ufs filesystem. | |
9 | +unionfs/ | |
10 | + - info on the unionfs filesystem | |
11 | vfat.txt | |
12 | - info on using the VFAT filesystem used in Windows NT and Windows 95 | |
13 | vfs.txt | |
0c5527e5 AM |
14 | diff --git a/Documentation/filesystems/unionfs/00-INDEX b/Documentation/filesystems/unionfs/00-INDEX |
15 | new file mode 100644 | |
16 | index 0000000..96fdf67 | |
17 | --- /dev/null | |
18 | +++ b/Documentation/filesystems/unionfs/00-INDEX | |
2380c486 JR |
19 | @@ -0,0 +1,10 @@ |
20 | +00-INDEX | |
21 | + - this file. | |
22 | +concepts.txt | |
23 | + - A brief introduction of concepts. | |
24 | +issues.txt | |
25 | + - A summary of known issues with unionfs. | |
26 | +rename.txt | |
27 | + - Information regarding rename operations. | |
28 | +usage.txt | |
29 | + - Usage information and examples. | |
0c5527e5 AM |
30 | diff --git a/Documentation/filesystems/unionfs/concepts.txt b/Documentation/filesystems/unionfs/concepts.txt |
31 | new file mode 100644 | |
32 | index 0000000..b853788 | |
33 | --- /dev/null | |
34 | +++ b/Documentation/filesystems/unionfs/concepts.txt | |
2380c486 JR |
35 | @@ -0,0 +1,287 @@ |
36 | +Unionfs 2.x CONCEPTS: | |
37 | +===================== | |
38 | + | |
39 | +This file describes the concepts needed by a namespace unification file | |
40 | +system. | |
41 | + | |
42 | + | |
43 | +Branch Priority: | |
44 | +================ | |
45 | + | |
46 | +Each branch is assigned a unique priority - starting from 0 (highest | |
47 | +priority). No two branches can have the same priority. | |
48 | + | |
49 | + | |
50 | +Branch Mode: | |
51 | +============ | |
52 | + | |
53 | +Each branch is assigned a mode - read-write or read-only. This allows | |
54 | +directories on media mounted read-write to be used in a read-only manner. | |
55 | + | |
56 | + | |
57 | +Whiteouts: | |
58 | +========== | |
59 | + | |
60 | +A whiteout removes a file name from the namespace. Whiteouts are needed when | |
61 | +one attempts to remove a file on a read-only branch. | |
62 | + | |
63 | +Suppose we have a two-branch union, where branch 0 is read-write and branch | |
64 | +1 is read-only. And a file 'foo' on branch 1: | |
65 | + | |
66 | +./b0/ | |
67 | +./b1/ | |
68 | +./b1/foo | |
69 | + | |
70 | +The unified view would simply be: | |
71 | + | |
72 | +./union/ | |
73 | +./union/foo | |
74 | + | |
75 | +Since 'foo' is stored on a read-only branch, it cannot be removed. A | |
76 | +whiteout is used to remove the name 'foo' from the unified namespace. Again, | |
77 | +since branch 1 is read-only, the whiteout cannot be created there. So, we | |
78 | +try on a higher priority (lower numerically) branch and create the whiteout | |
79 | +there. | |
80 | + | |
81 | +./b0/ | |
82 | +./b0/.wh.foo | |
83 | +./b1/ | |
84 | +./b1/foo | |
85 | + | |
86 | +Later, when Unionfs traverses branches (due to lookup or readdir), it | |
87 | +eliminate 'foo' from the namespace (as well as the whiteout itself.) | |
88 | + | |
89 | + | |
90 | +Opaque Directories: | |
91 | +=================== | |
92 | + | |
93 | +Assume we have a unionfs mount comprising of two branches. Branch 0 is | |
94 | +empty; branch 1 has the directory /a and file /a/f. Let's say we mount a | |
95 | +union of branch 0 as read-write and branch 1 as read-only. Now, let's say | |
96 | +we try to perform the following operation in the union: | |
97 | + | |
98 | + rm -fr a | |
99 | + | |
100 | +Because branch 1 is not writable, we cannot physically remove the file /a/f | |
101 | +or the directory /a. So instead, we will create a whiteout in branch 0 | |
102 | +named /.wh.a, masking out the name "a" from branch 1. Next, let's say we | |
103 | +try to create a directory named "a" as follows: | |
104 | + | |
105 | + mkdir a | |
106 | + | |
107 | +Because we have a whiteout for "a" already, Unionfs behaves as if "a" | |
108 | +doesn't exist, and thus will delete the whiteout and replace it with an | |
109 | +actual directory named "a". | |
110 | + | |
111 | +The problem now is that if you try to "ls" in the union, Unionfs will | |
112 | +perform is normal directory name unification, for *all* directories named | |
113 | +"a" in all branches. This will cause the file /a/f from branch 1 to | |
114 | +re-appear in the union's namespace, which violates Unix semantics. | |
115 | + | |
116 | +To avoid this problem, we have a different form of whiteouts for | |
117 | +directories, called "opaque directories" (same as BSD Union Mount does). | |
118 | +Whenever we replace a whiteout with a directory, that directory is marked as | |
119 | +opaque. In Unionfs 2.x, it means that we create a file named | |
120 | +/a/.wh.__dir_opaque in branch 0, after having created directory /a there. | |
121 | +When unionfs notices that a directory is opaque, it stops all namespace | |
122 | +operations (including merging readdir contents) at that opaque directory. | |
123 | +This prevents re-exposing names from masked out directories. | |
124 | + | |
125 | + | |
126 | +Duplicate Elimination: | |
127 | +====================== | |
128 | + | |
129 | +It is possible for files on different branches to have the same name. | |
130 | +Unionfs then has to select which instance of the file to show to the user. | |
131 | +Given the fact that each branch has a priority associated with it, the | |
132 | +simplest solution is to take the instance from the highest priority | |
133 | +(numerically lowest value) and "hide" the others. | |
134 | + | |
135 | + | |
136 | +Unlinking: | |
137 | +========= | |
138 | + | |
139 | +Unlink operation on non-directory instances is optimized to remove the | |
140 | +maximum possible objects in case multiple underlying branches have the same | |
141 | +file name. The unlink operation will first try to delete file instances | |
142 | +from highest priority branch and then move further to delete from remaining | |
143 | +branches in order of their decreasing priority. Consider a case (F..D..F), | |
144 | +where F is a file and D is a directory of the same name; here, some | |
145 | +intermediate branch could have an empty directory instance with the same | |
146 | +name, so this operation also tries to delete this directory instance and | |
147 | +proceed further to delete from next possible lower priority branch. The | |
148 | +unionfs unlink operation will smoothly delete the files with same name from | |
149 | +all possible underlying branches. In case if some error occurs, it creates | |
150 | +whiteout in highest priority branch that will hide file instance in rest of | |
151 | +the branches. An error could occur either if an unlink operations in any of | |
152 | +the underlying branch failed or if a branch has no write permission. | |
153 | + | |
154 | +This unlinking policy is known as "delete all" and it has the benefit of | |
155 | +overall reducing the number of inodes used by duplicate files, and further | |
156 | +reducing the total number of inodes consumed by whiteouts. The cost is of | |
157 | +extra processing, but testing shows this extra processing is well worth the | |
158 | +savings. | |
159 | + | |
160 | + | |
161 | +Copyup: | |
162 | +======= | |
163 | + | |
164 | +When a change is made to the contents of a file's data or meta-data, they | |
165 | +have to be stored somewhere. The best way is to create a copy of the | |
166 | +original file on a branch that is writable, and then redirect the write | |
167 | +though to this copy. The copy must be made on a higher priority branch so | |
168 | +that lookup and readdir return this newer "version" of the file rather than | |
169 | +the original (see duplicate elimination). | |
170 | + | |
171 | +An entire unionfs mount can be read-only or read-write. If it's read-only, | |
172 | +then none of the branches will be written to, even if some of the branches | |
173 | +are physically writeable. If the unionfs mount is read-write, then the | |
174 | +leftmost (highest priority) branch must be writeable (for copyup to take | |
175 | +place); the remaining branches can be any mix of read-write and read-only. | |
176 | + | |
177 | +In a writeable mount, unionfs will create new files/dir in the leftmost | |
178 | +branch. If one tries to modify a file in a read-only branch/media, unionfs | |
179 | +will copyup the file to the leftmost branch and modify it there. If you try | |
180 | +to modify a file from a writeable branch which is not the leftmost branch, | |
181 | +then unionfs will modify it in that branch; this is useful if you, say, | |
182 | +unify differnet packages (e.g., apache, sendmail, ftpd, etc.) and you want | |
183 | +changes to specific package files to remain logically in the directory where | |
184 | +they came from. | |
185 | + | |
186 | +Cache Coherency: | |
187 | +================ | |
188 | + | |
189 | +Unionfs users often want to be able to modify files and directories directly | |
190 | +on the lower branches, and have those changes be visible at the Unionfs | |
191 | +level. This means that data (e.g., pages) and meta-data (dentries, inodes, | |
192 | +open files, etc.) have to be synchronized between the upper and lower | |
193 | +layers. In other words, the newest changes from a layer below have to be | |
194 | +propagated to the Unionfs layer above. If the two layers are not in sync, a | |
195 | +cache incoherency ensues, which could lead to application failures and even | |
196 | +oopses. The Linux kernel, however, has a rather limited set of mechanisms | |
197 | +to ensure this inter-layer cache coherency---so Unionfs has to do most of | |
198 | +the hard work on its own. | |
199 | + | |
200 | +Maintaining Invariants: | |
201 | + | |
202 | +The way Unionfs ensures cache coherency is as follows. At each entry point | |
203 | +to a Unionfs file system method, we call a utility function to validate the | |
204 | +primary objects of this method. Generally, we call unionfs_file_revalidate | |
205 | +on open files, and __unionfs_d_revalidate_chain on dentries (which also | |
206 | +validates inodes). These utility functions check to see whether the upper | |
207 | +Unionfs object is in sync with any of the lower objects that it represents. | |
208 | +The checks we perform include whether the Unionfs superblock has a newer | |
209 | +generation number, or if any of the lower objects mtime's or ctime's are | |
210 | +newer. (Note: generation numbers change when branch-management commands are | |
211 | +issued, so in a way, maintaining cache coherency is also very important for | |
212 | +branch-management.) If indeed we determine that any Unionfs object is no | |
213 | +longer in sync with its lower counterparts, then we rebuild that object | |
214 | +similarly to how we do so for branch-management. | |
215 | + | |
216 | +While rebuilding Unionfs's objects, we also purge any page mappings and | |
217 | +truncate inode pages (see fs/unionfs/dentry.c:purge_inode_data). This is to | |
218 | +ensure that Unionfs will re-get the newer data from the lower branches. We | |
219 | +perform this purging only if the Unionfs operation in question is a reading | |
220 | +operation; if Unionfs is performing a data writing operation (e.g., ->write, | |
221 | +->commit_write, etc.) then we do NOT flush the lower mappings/pages: this is | |
222 | +because (1) a self-deadlock could occur and (2) the upper Unionfs pages are | |
223 | +considered more authoritative anyway, as they are newer and will overwrite | |
224 | +any lower pages. | |
225 | + | |
226 | +Unionfs maintains the following important invariant regarding mtime's, | |
227 | +ctime's, and atime's: the upper inode object's times are the max() of all of | |
228 | +the lower ones. For non-directory objects, there's only one object below, | |
229 | +so the mapping is simple; for directory objects, there could me multiple | |
230 | +lower objects and we have to sync up with the newest one of all the lower | |
231 | +ones. This invariant is important to maintain, especially for directories | |
232 | +(besides, we need this to be POSIX compliant). A union could comprise | |
233 | +multiple writable branches, each of which could change. If we don't reflect | |
234 | +the newest possible mtime/ctime, some applications could fail. For example, | |
235 | +NFSv2/v3 exports check for newer directory mtimes on the server to determine | |
236 | +if the client-side attribute cache should be purged. | |
237 | + | |
238 | +To maintain these important invariants, of course, Unionfs carefully | |
239 | +synchronizes upper and lower times in various places. For example, if we | |
240 | +copy-up a file to a top-level branch, the parent directory where the file | |
241 | +was copied up to will now have a new mtime: so after a successful copy-up, | |
242 | +we sync up with the new top-level branch's parent directory mtime. | |
243 | + | |
244 | +Implementation: | |
245 | + | |
246 | +This cache-coherency implementation is efficient because it defers any | |
247 | +synchronizing between the upper and lower layers until absolutely needed. | |
248 | +Consider the example a common situation where users perform a lot of lower | |
249 | +changes, such as untarring a whole package. While these take place, | |
250 | +typically the user doesn't access the files via Unionfs; only after the | |
251 | +lower changes are done, does the user try to access the lower files. With | |
252 | +our cache-coherency implementation, the entirety of the changes to the lower | |
253 | +branches will not result in a single CPU cycle spent at the Unionfs level | |
254 | +until the user invokes a system call that goes through Unionfs. | |
255 | + | |
256 | +We have considered two alternate cache-coherency designs. (1) Using the | |
257 | +dentry/inode notify functionality to register interest in finding out about | |
258 | +any lower changes. This is a somewhat limited and also a heavy-handed | |
259 | +approach which could result in many notifications to the Unionfs layer upon | |
260 | +each small change at the lower layer (imagine a file being modified multiple | |
261 | +times in rapid succession). (2) Rewriting the VFS to support explicit | |
262 | +callbacks from lower objects to upper objects. We began exploring such an | |
263 | +implementation, but found it to be very complicated--it would have resulted | |
264 | +in massive VFS/MM changes which are unlikely to be accepted by the LKML | |
265 | +community. We therefore believe that our current cache-coherency design and | |
266 | +implementation represent the best approach at this time. | |
267 | + | |
268 | +Limitations: | |
269 | + | |
270 | +Our implementation works in that as long as a user process will have caused | |
271 | +Unionfs to be called, directly or indirectly, even to just do | |
272 | +->d_revalidate; then we will have purged the current Unionfs data and the | |
273 | +process will see the new data. For example, a process that continually | |
274 | +re-reads the same file's data will see the NEW data as soon as the lower | |
275 | +file had changed, upon the next read(2) syscall (even if the file is still | |
276 | +open!) However, this doesn't work when the process re-reads the open file's | |
277 | +data via mmap(2) (unless the user unmaps/closes the file and remaps/reopens | |
278 | +it). Once we respond to ->readpage(s), then the kernel maps the page into | |
279 | +the process's address space and there doesn't appear to be a way to force | |
280 | +the kernel to invalidate those pages/mappings, and force the process to | |
281 | +re-issue ->readpage. If there's a way to invalidate active mappings and | |
282 | +force a ->readpage, let us know please (invalidate_inode_pages2 doesn't do | |
283 | +the trick). | |
284 | + | |
285 | +Our current Unionfs code has to perform many file-revalidation calls. It | |
286 | +would be really nice if the VFS would export an optional file system hook | |
287 | +->file_revalidate (similarly to dentry->d_revalidate) that will be called | |
288 | +before each VFS op that has a "struct file" in it. | |
289 | + | |
290 | +Certain file systems have micro-second granularity (or better) for inode | |
291 | +times, and asynchronous actions could cause those times to change with some | |
292 | +small delay. In such cases, Unionfs may see a changed inode time that only | |
293 | +differs by a tiny fraction of a second: such a change may be a false | |
294 | +positive indication that the lower object has changed, whereas if unionfs | |
295 | +waits a little longer, that false indication will not be seen. (These false | |
296 | +positives are harmless, because they would at most cause unionfs to | |
297 | +re-validate an object that may need no revalidation, and print a debugging | |
298 | +message that clutters the console/logs.) Therefore, to minimize the chances | |
299 | +of these situations, we delay the detection of changed times by a small | |
300 | +factor of a few seconds, called UNIONFS_MIN_CC_TIME (which defaults to 3 | |
301 | +seconds, as does NFS). This means that we will detect the change, only a | |
302 | +couple of seconds later, if indeed the time change persists in the lower | |
303 | +file object. This delayed detection has an added performance benefit: we | |
304 | +reduce the number of times that unionfs has to revalidate objects, in case | |
305 | +there's a lot of concurrent activity on both the upper and lower objects, | |
306 | +for the same file(s). Lastly, this delayed time attribute detection is | |
307 | +similar to how NFS clients operate (e.g., acregmin). | |
308 | + | |
309 | +Finally, there is no way currently in Linux to prevent lower directories | |
310 | +from being moved around (i.e., topology changes); there's no way to prevent | |
311 | +modifications to directory sub-trees of whole file systems which are mounted | |
312 | +read-write. It is therefore possible for in-flight operations in unionfs to | |
313 | +take place, while a lower directory is being moved around. Therefore, if | |
314 | +you try to, say, create a new file in a directory through unionfs, while the | |
315 | +directory is being moved around directly, then the new file may get created | |
316 | +in the new location where that directory was moved to. This is a somewhat | |
317 | +similar behaviour in NFS: an NFS client could be creating a new file while | |
318 | +th NFS server is moving th directory around; the file will get successfully | |
319 | +created in the new location. (The one exception in unionfs is that if the | |
320 | +branch is marked read-only by unionfs, then a copyup will take place.) | |
321 | + | |
322 | +For more information, see <http://unionfs.filesystems.org/>. | |
0c5527e5 AM |
323 | diff --git a/Documentation/filesystems/unionfs/issues.txt b/Documentation/filesystems/unionfs/issues.txt |
324 | new file mode 100644 | |
325 | index 0000000..f4b7e7e | |
326 | --- /dev/null | |
327 | +++ b/Documentation/filesystems/unionfs/issues.txt | |
2380c486 JR |
328 | @@ -0,0 +1,28 @@ |
329 | +KNOWN Unionfs 2.x ISSUES: | |
330 | +========================= | |
331 | + | |
332 | +1. Unionfs should not use lookup_one_len() on the underlying f/s as it | |
333 | + confuses NFSv4. Currently, unionfs_lookup() passes lookup intents to the | |
334 | + lower file-system, this eliminates part of the problem. The remaining | |
335 | + calls to lookup_one_len may need to be changed to pass an intent. We are | |
336 | + currently introducing VFS changes to fs/namei.c's do_path_lookup() to | |
337 | + allow proper file lookup and opening in stackable file systems. | |
338 | + | |
339 | +2. Lockdep (a debugging feature) isn't aware of stacking, and so it | |
340 | + incorrectly complains about locking problems. The problem boils down to | |
341 | + this: Lockdep considers all objects of a certain type to be in the same | |
342 | + class, for example, all inodes. Lockdep doesn't like to see a lock held | |
343 | + on two inodes within the same task, and warns that it could lead to a | |
344 | + deadlock. However, stackable file systems do precisely that: they lock | |
345 | + an upper object, and then a lower object, in a strict order to avoid | |
346 | + locking problems; in addition, Unionfs, as a fan-out file system, may | |
347 | + have to lock several lower inodes. We are currently looking into Lockdep | |
348 | + to see how to make it aware of stackable file systems. For now, we | |
349 | + temporarily disable lockdep when calling vfs methods on lower objects, | |
350 | + but only for those places where lockdep complained. While this solution | |
351 | + may seem unclean, it is not without precedent: other places in the kernel | |
352 | + also do similar temporary disabling, of course after carefully having | |
353 | + checked that it is the right thing to do. Anyway, you get any warnings | |
354 | + from Lockdep, please report them to the Unionfs maintainers. | |
355 | + | |
356 | +For more information, see <http://unionfs.filesystems.org/>. | |
0c5527e5 AM |
357 | diff --git a/Documentation/filesystems/unionfs/rename.txt b/Documentation/filesystems/unionfs/rename.txt |
358 | new file mode 100644 | |
359 | index 0000000..e20bb82 | |
360 | --- /dev/null | |
361 | +++ b/Documentation/filesystems/unionfs/rename.txt | |
2380c486 JR |
362 | @@ -0,0 +1,31 @@ |
363 | +Rename is a complex beast. The following table shows which rename(2) operations | |
364 | +should succeed and which should fail. | |
365 | + | |
366 | +o: success | |
367 | +E: error (either unionfs or vfs) | |
368 | +X: EXDEV | |
369 | + | |
370 | +none = file does not exist | |
371 | +file = file is a file | |
372 | +dir = file is a empty directory | |
373 | +child= file is a non-empty directory | |
374 | +wh = file is a directory containing only whiteouts; this makes it logically | |
375 | + empty | |
376 | + | |
377 | + none file dir child wh | |
378 | +file o o E E E | |
379 | +dir o E o E o | |
380 | +child X E X E X | |
381 | +wh o E o E o | |
382 | + | |
383 | + | |
384 | +Renaming directories: | |
385 | +===================== | |
386 | + | |
387 | +Whenever a empty (either physically or logically) directory is being renamed, | |
388 | +the following sequence of events should take place: | |
389 | + | |
390 | +1) Remove whiteouts from both source and destination directory | |
391 | +2) Rename source to destination | |
392 | +3) Make destination opaque to prevent anything under it from showing up | |
393 | + | |
0c5527e5 AM |
394 | diff --git a/Documentation/filesystems/unionfs/usage.txt b/Documentation/filesystems/unionfs/usage.txt |
395 | new file mode 100644 | |
396 | index 0000000..1adde69 | |
397 | --- /dev/null | |
398 | +++ b/Documentation/filesystems/unionfs/usage.txt | |
2380c486 JR |
399 | @@ -0,0 +1,134 @@ |
400 | +Unionfs is a stackable unification file system, which can appear to merge | |
401 | +the contents of several directories (branches), while keeping their physical | |
402 | +content separate. Unionfs is useful for unified source tree management, | |
403 | +merged contents of split CD-ROM, merged separate software package | |
404 | +directories, data grids, and more. Unionfs allows any mix of read-only and | |
405 | +read-write branches, as well as insertion and deletion of branches anywhere | |
406 | +in the fan-out. To maintain Unix semantics, Unionfs handles elimination of | |
407 | +duplicates, partial-error conditions, and more. | |
408 | + | |
409 | +GENERAL SYNTAX | |
410 | +============== | |
411 | + | |
412 | +# mount -t unionfs -o <OPTIONS>,<BRANCH-OPTIONS> none MOUNTPOINT | |
413 | + | |
414 | +OPTIONS can be any legal combination of: | |
415 | + | |
416 | +- ro # mount file system read-only | |
417 | +- rw # mount file system read-write | |
418 | +- remount # remount the file system (see Branch Management below) | |
419 | +- incgen # increment generation no. (see Cache Consistency below) | |
420 | + | |
421 | +BRANCH-OPTIONS can be either (1) a list of branches given to the "dirs=" | |
422 | +option, or (2) a list of individual branch manipulation commands, combined | |
423 | +with the "remount" option, and is further described in the "Branch | |
424 | +Management" section below. | |
425 | + | |
426 | +The syntax for the "dirs=" mount option is: | |
427 | + | |
428 | + dirs=branch[=ro|=rw][:...] | |
429 | + | |
430 | +The "dirs=" option takes a colon-delimited list of directories to compose | |
431 | +the union, with an optional branch mode for each of those directories. | |
432 | +Directories that come earlier (specified first, on the left) in the list | |
433 | +have a higher precedence than those which come later. Additionally, | |
434 | +read-only or read-write permissions of the branch can be specified by | |
435 | +appending =ro or =rw (default) to each directory. See the Copyup section in | |
436 | +concepts.txt, for a description of Unionfs's behavior when mixing read-only | |
437 | +and read-write branches and mounts. | |
438 | + | |
439 | +Syntax: | |
440 | + | |
441 | + dirs=/branch1[=ro|=rw]:/branch2[=ro|=rw]:...:/branchN[=ro|=rw] | |
442 | + | |
443 | +Example: | |
444 | + | |
445 | + dirs=/writable_branch=rw:/read-only_branch=ro | |
446 | + | |
447 | + | |
448 | +BRANCH MANAGEMENT | |
449 | +================= | |
450 | + | |
451 | +Once you mount your union for the first time, using the "dirs=" option, you | |
452 | +can then change the union's overall mode or reconfigure the branches, using | |
453 | +the remount option, as follows. | |
454 | + | |
455 | +To downgrade a union from read-write to read-only: | |
456 | + | |
457 | +# mount -t unionfs -o remount,ro none MOUNTPOINT | |
458 | + | |
459 | +To upgrade a union from read-only to read-write: | |
460 | + | |
461 | +# mount -t unionfs -o remount,rw none MOUNTPOINT | |
462 | + | |
463 | +To delete a branch /foo, regardless where it is in the current union: | |
464 | + | |
465 | +# mount -t unionfs -o remount,del=/foo none MOUNTPOINT | |
466 | + | |
467 | +To insert (add) a branch /foo before /bar: | |
468 | + | |
469 | +# mount -t unionfs -o remount,add=/bar:/foo none MOUNTPOINT | |
470 | + | |
471 | +To insert (add) a branch /foo (with the "rw" mode flag) before /bar: | |
472 | + | |
473 | +# mount -t unionfs -o remount,add=/bar:/foo=rw none MOUNTPOINT | |
474 | + | |
475 | +To insert (add) a branch /foo (in "rw" mode) at the very beginning (i.e., a | |
476 | +new highest-priority branch), you can use the above syntax, or use a short | |
477 | +hand version as follows: | |
478 | + | |
479 | +# mount -t unionfs -o remount,add=/foo none MOUNTPOINT | |
480 | + | |
481 | +To append a branch to the very end (new lowest-priority branch): | |
482 | + | |
483 | +# mount -t unionfs -o remount,add=:/foo none MOUNTPOINT | |
484 | + | |
485 | +To append a branch to the very end (new lowest-priority branch), in | |
486 | +read-only mode: | |
487 | + | |
488 | +# mount -t unionfs -o remount,add=:/foo=ro none MOUNTPOINT | |
489 | + | |
490 | +Finally, to change the mode of one existing branch, say /foo, from read-only | |
491 | +to read-write, and change /bar from read-write to read-only: | |
492 | + | |
493 | +# mount -t unionfs -o remount,mode=/foo=rw,mode=/bar=ro none MOUNTPOINT | |
494 | + | |
495 | +Note: in Unionfs 2.x, you cannot set the leftmost branch to readonly because | |
496 | +then Unionfs won't have any writable place for copyups to take place. | |
497 | +Moreover, the VFS can get confused when it tries to modify something in a | |
498 | +file system mounted read-write, but isn't permitted to write to it. | |
499 | +Instead, you should set the whole union as readonly, as described above. | |
500 | +If, however, you must set the leftmost branch as readonly, perhaps so you | |
501 | +can get a snapshot of it at a point in time, then you should insert a new | |
502 | +writable top-level branch, and mark the one you want as readonly. This can | |
503 | +be accomplished as follows, assuming that /foo is your current leftmost | |
504 | +branch: | |
505 | + | |
506 | +# mount -t tmpfs -o size=NNN /new | |
507 | +# mount -t unionfs -o remount,add=/new,mode=/foo=ro none MOUNTPOINT | |
508 | +<do what you want safely in /foo> | |
509 | +# mount -t unionfs -o remount,del=/new,mode=/foo=rw none MOUNTPOINT | |
510 | +<check if there's anything in /new you want to preserve> | |
511 | +# umount /new | |
512 | + | |
513 | +CACHE CONSISTENCY | |
514 | +================= | |
515 | + | |
516 | +If you modify any file on any of the lower branches directly, while there is | |
517 | +a Unionfs 2.x mounted above any of those branches, you should tell Unionfs | |
518 | +to purge its caches and re-get the objects. To do that, you have to | |
519 | +increment the generation number of the superblock using the following | |
520 | +command: | |
521 | + | |
522 | +# mount -t unionfs -o remount,incgen none MOUNTPOINT | |
523 | + | |
524 | +Note that the older way of incrementing the generation number using an | |
525 | +ioctl, is no longer supported in Unionfs 2.0 and newer. Ioctls in general | |
526 | +are not encouraged. Plus, an ioctl is per-file concept, whereas the | |
527 | +generation number is a per-file-system concept. Worse, such an ioctl | |
528 | +requires an open file, which then has to be invalidated by the very nature | |
529 | +of the generation number increase (read: the old generation increase ioctl | |
530 | +was pretty racy). | |
531 | + | |
532 | + | |
533 | +For more information, see <http://unionfs.filesystems.org/>. | |
0c5527e5 | 534 | diff --git a/MAINTAINERS b/MAINTAINERS |
92d182d2 | 535 | index 9a648eb..81b24a8 100644 |
0c5527e5 AM |
536 | --- a/MAINTAINERS |
537 | +++ b/MAINTAINERS | |
92d182d2 | 538 | @@ -6765,6 +6765,14 @@ F: Documentation/cdrom/ |
0c5527e5 AM |
539 | F: drivers/cdrom/cdrom.c |
540 | F: include/linux/cdrom.h | |
541 | ||
542 | +UNIONFS | |
543 | +P: Erez Zadok | |
544 | +M: ezk@cs.sunysb.edu | |
545 | +L: unionfs@filesystems.org | |
546 | +W: http://unionfs.filesystems.org/ | |
547 | +T: git git.kernel.org/pub/scm/linux/kernel/git/ezk/unionfs.git | |
548 | +S: Maintained | |
549 | + | |
550 | UNSORTED BLOCK IMAGES (UBI) | |
551 | M: Artem Bityutskiy <dedekind1@gmail.com> | |
552 | W: http://www.linux-mtd.infradead.org/ | |
553 | diff --git a/fs/Kconfig b/fs/Kconfig | |
92d182d2 | 554 | index d621f02..c12677d 100644 |
0c5527e5 AM |
555 | --- a/fs/Kconfig |
556 | +++ b/fs/Kconfig | |
6b53c3da | 557 | @@ -194,6 +194,7 @@ if MISC_FILESYSTEMS |
2380c486 JR |
558 | source "fs/adfs/Kconfig" |
559 | source "fs/affs/Kconfig" | |
560 | source "fs/ecryptfs/Kconfig" | |
561 | +source "fs/unionfs/Kconfig" | |
562 | source "fs/hfs/Kconfig" | |
563 | source "fs/hfsplus/Kconfig" | |
564 | source "fs/befs/Kconfig" | |
0c5527e5 | 565 | diff --git a/fs/Makefile b/fs/Makefile |
92d182d2 | 566 | index 93804d4..3ff10bb 100644 |
0c5527e5 AM |
567 | --- a/fs/Makefile |
568 | +++ b/fs/Makefile | |
92d182d2 | 569 | @@ -83,6 +83,7 @@ obj-$(CONFIG_ISO9660_FS) += isofs/ |
2380c486 JR |
570 | obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+ |
571 | obj-$(CONFIG_HFS_FS) += hfs/ | |
572 | obj-$(CONFIG_ECRYPT_FS) += ecryptfs/ | |
573 | +obj-$(CONFIG_UNION_FS) += unionfs/ | |
574 | obj-$(CONFIG_VXFS_FS) += freevxfs/ | |
575 | obj-$(CONFIG_NFS_FS) += nfs/ | |
576 | obj-$(CONFIG_EXPORTFS) += exportfs/ | |
0c5527e5 | 577 | diff --git a/fs/namei.c b/fs/namei.c |
92d182d2 | 578 | index 208c6aa..050eded 100644 |
0c5527e5 AM |
579 | --- a/fs/namei.c |
580 | +++ b/fs/namei.c | |
92d182d2 | 581 | @@ -491,6 +491,7 @@ void release_open_intent(struct nameidata *nd) |
82260373 AM |
582 | fput(file); |
583 | } | |
2380c486 JR |
584 | } |
585 | +EXPORT_SYMBOL_GPL(release_open_intent); | |
586 | ||
82260373 AM |
587 | static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd) |
588 | { | |
92d182d2 | 589 | @@ -1804,6 +1805,42 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) |
63b09289 JR |
590 | return __lookup_hash(&this, base, NULL); |
591 | } | |
592 | ||
593 | +/* pass nameidata from caller (useful for NFS) */ | |
594 | +struct dentry *lookup_one_len_nd(const char *name, struct dentry *base, | |
595 | + int len, struct nameidata *nd) | |
596 | +{ | |
597 | + struct qstr this; | |
598 | + unsigned long hash; | |
599 | + unsigned int c; | |
600 | + | |
601 | + WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex)); | |
602 | + | |
603 | + this.name = name; | |
604 | + this.len = len; | |
605 | + if (!len) | |
606 | + return ERR_PTR(-EACCES); | |
607 | + | |
608 | + hash = init_name_hash(); | |
609 | + while (len--) { | |
610 | + c = *(const unsigned char *)name++; | |
611 | + if (c == '/' || c == '\0') | |
612 | + return ERR_PTR(-EACCES); | |
613 | + hash = partial_name_hash(c, hash); | |
614 | + } | |
615 | + this.hash = end_name_hash(hash); | |
616 | + /* | |
617 | + * See if the low-level filesystem might want | |
618 | + * to use its own hash.. | |
619 | + */ | |
620 | + if (base->d_flags & DCACHE_OP_HASH) { | |
621 | + int err = base->d_op->d_hash(base, base->d_inode, &this); | |
622 | + if (err < 0) | |
623 | + return ERR_PTR(err); | |
624 | + } | |
625 | + | |
626 | + return __lookup_hash(&this, base, nd); | |
627 | +} | |
628 | + | |
f6c5ef8b AM |
629 | int user_path_at_empty(int dfd, const char __user *name, unsigned flags, |
630 | struct path *path, int *empty) | |
63b09289 | 631 | { |
92d182d2 | 632 | @@ -3384,6 +3421,7 @@ EXPORT_SYMBOL(get_write_access); /* binfmt_aout */ |
63b09289 JR |
633 | EXPORT_SYMBOL(getname); |
634 | EXPORT_SYMBOL(lock_rename); | |
635 | EXPORT_SYMBOL(lookup_one_len); | |
636 | +EXPORT_SYMBOL(lookup_one_len_nd); | |
637 | EXPORT_SYMBOL(page_follow_link_light); | |
638 | EXPORT_SYMBOL(page_put_link); | |
639 | EXPORT_SYMBOL(page_readlink); | |
0c5527e5 | 640 | diff --git a/fs/splice.c b/fs/splice.c |
92d182d2 | 641 | index 1ec0493..3215728 100644 |
0c5527e5 AM |
642 | --- a/fs/splice.c |
643 | +++ b/fs/splice.c | |
92d182d2 | 644 | @@ -1084,8 +1084,8 @@ EXPORT_SYMBOL(generic_splice_sendpage); |
2380c486 JR |
645 | /* |
646 | * Attempt to initiate a splice from pipe to file. | |
647 | */ | |
648 | -static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, | |
649 | - loff_t *ppos, size_t len, unsigned int flags) | |
650 | +long vfs_splice_from(struct pipe_inode_info *pipe, struct file *out, | |
651 | + loff_t *ppos, size_t len, unsigned int flags) | |
652 | { | |
4ae1df7a JR |
653 | ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, |
654 | loff_t *, size_t, unsigned int); | |
92d182d2 | 655 | @@ -1108,13 +1108,14 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, |
2380c486 | 656 | |
4ae1df7a | 657 | return splice_write(pipe, out, ppos, len, flags); |
2380c486 JR |
658 | } |
659 | +EXPORT_SYMBOL_GPL(vfs_splice_from); | |
660 | ||
661 | /* | |
662 | * Attempt to initiate a splice from a file to a pipe. | |
663 | */ | |
664 | -static long do_splice_to(struct file *in, loff_t *ppos, | |
665 | - struct pipe_inode_info *pipe, size_t len, | |
666 | - unsigned int flags) | |
667 | +long vfs_splice_to(struct file *in, loff_t *ppos, | |
668 | + struct pipe_inode_info *pipe, size_t len, | |
669 | + unsigned int flags) | |
670 | { | |
4ae1df7a JR |
671 | ssize_t (*splice_read)(struct file *, loff_t *, |
672 | struct pipe_inode_info *, size_t, unsigned int); | |
92d182d2 | 673 | @@ -1134,6 +1135,7 @@ static long do_splice_to(struct file *in, loff_t *ppos, |
2380c486 | 674 | |
4ae1df7a | 675 | return splice_read(in, ppos, pipe, len, flags); |
2380c486 JR |
676 | } |
677 | +EXPORT_SYMBOL_GPL(vfs_splice_to); | |
678 | ||
679 | /** | |
680 | * splice_direct_to_actor - splices data directly between two non-pipes | |
92d182d2 | 681 | @@ -1203,7 +1205,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, |
2380c486 JR |
682 | size_t read_len; |
683 | loff_t pos = sd->pos, prev_pos = pos; | |
684 | ||
685 | - ret = do_splice_to(in, &pos, pipe, len, flags); | |
686 | + ret = vfs_splice_to(in, &pos, pipe, len, flags); | |
687 | if (unlikely(ret <= 0)) | |
688 | goto out_release; | |
689 | ||
92d182d2 | 690 | @@ -1262,8 +1264,8 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, |
2380c486 JR |
691 | { |
692 | struct file *file = sd->u.file; | |
693 | ||
76514441 | 694 | - return do_splice_from(pipe, file, &file->f_pos, sd->total_len, |
0c5527e5 | 695 | - sd->flags); |
76514441 | 696 | + return vfs_splice_from(pipe, file, &file->f_pos, sd->total_len, |
0c5527e5 | 697 | + sd->flags); |
2380c486 JR |
698 | } |
699 | ||
0c5527e5 | 700 | /** |
92d182d2 | 701 | @@ -1348,7 +1350,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, |
2380c486 JR |
702 | } else |
703 | off = &out->f_pos; | |
704 | ||
13e5c3b1 AM |
705 | - ret = do_splice_from(ipipe, out, off, len, flags); |
706 | + ret = vfs_splice_from(ipipe, out, off, len, flags); | |
2380c486 JR |
707 | |
708 | if (off_out && copy_to_user(off_out, off, sizeof(loff_t))) | |
709 | ret = -EFAULT; | |
92d182d2 | 710 | @@ -1368,7 +1370,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, |
2380c486 JR |
711 | } else |
712 | off = &in->f_pos; | |
713 | ||
13e5c3b1 AM |
714 | - ret = do_splice_to(in, off, opipe, len, flags); |
715 | + ret = vfs_splice_to(in, off, opipe, len, flags); | |
2380c486 JR |
716 | |
717 | if (off_in && copy_to_user(off_in, off, sizeof(loff_t))) | |
718 | ret = -EFAULT; | |
0c5527e5 AM |
719 | diff --git a/fs/unionfs/Kconfig b/fs/unionfs/Kconfig |
720 | new file mode 100644 | |
721 | index 0000000..f3c1ac4 | |
722 | --- /dev/null | |
723 | +++ b/fs/unionfs/Kconfig | |
724 | @@ -0,0 +1,24 @@ | |
725 | +config UNION_FS | |
726 | + tristate "Union file system (EXPERIMENTAL)" | |
727 | + depends on EXPERIMENTAL | |
728 | + help | |
729 | + Unionfs is a stackable unification file system, which appears to | |
730 | + merge the contents of several directories (branches), while keeping | |
731 | + their physical content separate. | |
732 | + | |
733 | + See <http://unionfs.filesystems.org> for details | |
734 | + | |
735 | +config UNION_FS_XATTR | |
736 | + bool "Unionfs extended attributes" | |
737 | + depends on UNION_FS | |
738 | + help | |
739 | + Extended attributes are name:value pairs associated with inodes by | |
740 | + the kernel or by users (see the attr(5) manual page). | |
741 | + | |
742 | + If unsure, say N. | |
743 | + | |
744 | +config UNION_FS_DEBUG | |
745 | + bool "Debug Unionfs" | |
746 | + depends on UNION_FS | |
747 | + help | |
748 | + If you say Y here, you can turn on debugging output from Unionfs. | |
749 | diff --git a/fs/unionfs/Makefile b/fs/unionfs/Makefile | |
750 | new file mode 100644 | |
92d182d2 | 751 | index 0000000..60b6060 |
0c5527e5 AM |
752 | --- /dev/null |
753 | +++ b/fs/unionfs/Makefile | |
754 | @@ -0,0 +1,17 @@ | |
92d182d2 | 755 | +UNIONFS_VERSION="2.5.11 (for 3.3.0-rc3)" |
0c5527e5 AM |
756 | + |
757 | +EXTRA_CFLAGS += -DUNIONFS_VERSION=\"$(UNIONFS_VERSION)\" | |
758 | + | |
759 | +obj-$(CONFIG_UNION_FS) += unionfs.o | |
760 | + | |
761 | +unionfs-y := subr.o dentry.o file.o inode.o main.o super.o \ | |
762 | + rdstate.o copyup.o dirhelper.o rename.o unlink.o \ | |
763 | + lookup.o commonfops.o dirfops.o sioq.o mmap.o whiteout.o | |
764 | + | |
765 | +unionfs-$(CONFIG_UNION_FS_XATTR) += xattr.o | |
766 | + | |
767 | +unionfs-$(CONFIG_UNION_FS_DEBUG) += debug.o | |
768 | + | |
769 | +ifeq ($(CONFIG_UNION_FS_DEBUG),y) | |
770 | +EXTRA_CFLAGS += -DDEBUG | |
771 | +endif | |
772 | diff --git a/fs/unionfs/commonfops.c b/fs/unionfs/commonfops.c | |
773 | new file mode 100644 | |
6b53c3da | 774 | index 0000000..71cacfe |
0c5527e5 AM |
775 | --- /dev/null |
776 | +++ b/fs/unionfs/commonfops.c | |
6b53c3da | 777 | @@ -0,0 +1,901 @@ |
2380c486 | 778 | +/* |
63b09289 | 779 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
780 | + * Copyright (c) 2003-2006 Charles P. Wright |
781 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
782 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
783 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
784 | + * Copyright (c) 2004-2006 David P. Quigley | |
785 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
786 | + * Copyright (c) 2003 Puja Gupta | |
787 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
788 | + * Copyright (c) 2003-2011 Stony Brook University |
789 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
790 | + * |
791 | + * This program is free software; you can redistribute it and/or modify | |
792 | + * it under the terms of the GNU General Public License version 2 as | |
793 | + * published by the Free Software Foundation. | |
794 | + */ | |
795 | + | |
796 | +#include "union.h" | |
797 | + | |
798 | +/* | |
799 | + * 1) Copyup the file | |
800 | + * 2) Rename the file to '.unionfs<original inode#><counter>' - obviously | |
801 | + * stolen from NFS's silly rename | |
802 | + */ | |
803 | +static int copyup_deleted_file(struct file *file, struct dentry *dentry, | |
804 | + struct dentry *parent, int bstart, int bindex) | |
805 | +{ | |
806 | + static unsigned int counter; | |
807 | + const int i_inosize = sizeof(dentry->d_inode->i_ino) * 2; | |
808 | + const int countersize = sizeof(counter) * 2; | |
809 | + const int nlen = sizeof(".unionfs") + i_inosize + countersize - 1; | |
810 | + char name[nlen + 1]; | |
811 | + int err; | |
812 | + struct dentry *tmp_dentry = NULL; | |
813 | + struct dentry *lower_dentry; | |
814 | + struct dentry *lower_dir_dentry = NULL; | |
815 | + | |
816 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bstart); | |
817 | + | |
818 | + sprintf(name, ".unionfs%*.*lx", | |
819 | + i_inosize, i_inosize, lower_dentry->d_inode->i_ino); | |
820 | + | |
821 | + /* | |
822 | + * Loop, looking for an unused temp name to copyup to. | |
823 | + * | |
824 | + * It's somewhat silly that we look for a free temp tmp name in the | |
825 | + * source branch (bstart) instead of the dest branch (bindex), where | |
826 | + * the final name will be created. We _will_ catch it if somehow | |
827 | + * the name exists in the dest branch, but it'd be nice to catch it | |
828 | + * sooner than later. | |
829 | + */ | |
830 | +retry: | |
831 | + tmp_dentry = NULL; | |
832 | + do { | |
833 | + char *suffix = name + nlen - countersize; | |
834 | + | |
835 | + dput(tmp_dentry); | |
836 | + counter++; | |
837 | + sprintf(suffix, "%*.*x", countersize, countersize, counter); | |
838 | + | |
839 | + pr_debug("unionfs: trying to rename %s to %s\n", | |
840 | + dentry->d_name.name, name); | |
841 | + | |
4ae1df7a | 842 | + tmp_dentry = lookup_lck_len(name, lower_dentry->d_parent, |
2380c486 JR |
843 | + nlen); |
844 | + if (IS_ERR(tmp_dentry)) { | |
845 | + err = PTR_ERR(tmp_dentry); | |
846 | + goto out; | |
847 | + } | |
848 | + } while (tmp_dentry->d_inode != NULL); /* need negative dentry */ | |
849 | + dput(tmp_dentry); | |
850 | + | |
851 | + err = copyup_named_file(parent->d_inode, file, name, bstart, bindex, | |
852 | + i_size_read(file->f_path.dentry->d_inode)); | |
853 | + if (err) { | |
854 | + if (unlikely(err == -EEXIST)) | |
855 | + goto retry; | |
856 | + goto out; | |
857 | + } | |
858 | + | |
859 | + /* bring it to the same state as an unlinked file */ | |
860 | + lower_dentry = unionfs_lower_dentry_idx(dentry, dbstart(dentry)); | |
861 | + if (!unionfs_lower_inode_idx(dentry->d_inode, bindex)) { | |
862 | + atomic_inc(&lower_dentry->d_inode->i_count); | |
863 | + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, | |
864 | + lower_dentry->d_inode); | |
865 | + } | |
866 | + lower_dir_dentry = lock_parent(lower_dentry); | |
867 | + err = vfs_unlink(lower_dir_dentry->d_inode, lower_dentry); | |
868 | + unlock_dir(lower_dir_dentry); | |
869 | + | |
870 | +out: | |
871 | + if (!err) | |
872 | + unionfs_check_dentry(dentry); | |
873 | + return err; | |
874 | +} | |
875 | + | |
876 | +/* | |
877 | + * put all references held by upper struct file and free lower file pointer | |
878 | + * array | |
879 | + */ | |
880 | +static void cleanup_file(struct file *file) | |
881 | +{ | |
882 | + int bindex, bstart, bend; | |
883 | + struct file **lower_files; | |
884 | + struct file *lower_file; | |
885 | + struct super_block *sb = file->f_path.dentry->d_sb; | |
886 | + | |
887 | + lower_files = UNIONFS_F(file)->lower_files; | |
888 | + bstart = fbstart(file); | |
889 | + bend = fbend(file); | |
890 | + | |
891 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
892 | + int i; /* holds (possibly) updated branch index */ | |
893 | + int old_bid; | |
894 | + | |
895 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
896 | + if (!lower_file) | |
897 | + continue; | |
898 | + | |
899 | + /* | |
900 | + * Find new index of matching branch with an open | |
901 | + * file, since branches could have been added or | |
902 | + * deleted causing the one with open files to shift. | |
903 | + */ | |
904 | + old_bid = UNIONFS_F(file)->saved_branch_ids[bindex]; | |
905 | + i = branch_id_to_idx(sb, old_bid); | |
906 | + if (unlikely(i < 0)) { | |
907 | + printk(KERN_ERR "unionfs: no superblock for " | |
908 | + "file %p\n", file); | |
909 | + continue; | |
910 | + } | |
911 | + | |
912 | + /* decrement count of open files */ | |
913 | + branchput(sb, i); | |
914 | + /* | |
915 | + * fput will perform an mntput for us on the correct branch. | |
916 | + * Although we're using the file's old branch configuration, | |
917 | + * bindex, which is the old index, correctly points to the | |
918 | + * right branch in the file's branch list. In other words, | |
919 | + * we're going to mntput the correct branch even if branches | |
920 | + * have been added/removed. | |
921 | + */ | |
922 | + fput(lower_file); | |
923 | + UNIONFS_F(file)->lower_files[bindex] = NULL; | |
924 | + UNIONFS_F(file)->saved_branch_ids[bindex] = -1; | |
925 | + } | |
926 | + | |
927 | + UNIONFS_F(file)->lower_files = NULL; | |
928 | + kfree(lower_files); | |
929 | + kfree(UNIONFS_F(file)->saved_branch_ids); | |
930 | + /* set to NULL because caller needs to know if to kfree on error */ | |
931 | + UNIONFS_F(file)->saved_branch_ids = NULL; | |
932 | +} | |
933 | + | |
934 | +/* open all lower files for a given file */ | |
935 | +static int open_all_files(struct file *file) | |
936 | +{ | |
937 | + int bindex, bstart, bend, err = 0; | |
938 | + struct file *lower_file; | |
939 | + struct dentry *lower_dentry; | |
940 | + struct dentry *dentry = file->f_path.dentry; | |
941 | + struct super_block *sb = dentry->d_sb; | |
942 | + | |
943 | + bstart = dbstart(dentry); | |
944 | + bend = dbend(dentry); | |
945 | + | |
946 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
947 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
948 | + if (!lower_dentry) | |
949 | + continue; | |
950 | + | |
951 | + dget(lower_dentry); | |
952 | + unionfs_mntget(dentry, bindex); | |
953 | + branchget(sb, bindex); | |
954 | + | |
955 | + lower_file = | |
956 | + dentry_open(lower_dentry, | |
957 | + unionfs_lower_mnt_idx(dentry, bindex), | |
958 | + file->f_flags, current_cred()); | |
959 | + if (IS_ERR(lower_file)) { | |
960 | + branchput(sb, bindex); | |
961 | + err = PTR_ERR(lower_file); | |
962 | + goto out; | |
963 | + } else { | |
964 | + unionfs_set_lower_file_idx(file, bindex, lower_file); | |
965 | + } | |
966 | + } | |
967 | +out: | |
968 | + return err; | |
969 | +} | |
970 | + | |
971 | +/* open the highest priority file for a given upper file */ | |
972 | +static int open_highest_file(struct file *file, bool willwrite) | |
973 | +{ | |
974 | + int bindex, bstart, bend, err = 0; | |
975 | + struct file *lower_file; | |
976 | + struct dentry *lower_dentry; | |
977 | + struct dentry *dentry = file->f_path.dentry; | |
978 | + struct dentry *parent = dget_parent(dentry); | |
979 | + struct inode *parent_inode = parent->d_inode; | |
980 | + struct super_block *sb = dentry->d_sb; | |
981 | + | |
982 | + bstart = dbstart(dentry); | |
983 | + bend = dbend(dentry); | |
984 | + | |
985 | + lower_dentry = unionfs_lower_dentry(dentry); | |
986 | + if (willwrite && IS_WRITE_FLAG(file->f_flags) && is_robranch(dentry)) { | |
987 | + for (bindex = bstart - 1; bindex >= 0; bindex--) { | |
988 | + err = copyup_file(parent_inode, file, bstart, bindex, | |
989 | + i_size_read(dentry->d_inode)); | |
990 | + if (!err) | |
991 | + break; | |
992 | + } | |
993 | + atomic_set(&UNIONFS_F(file)->generation, | |
994 | + atomic_read(&UNIONFS_I(dentry->d_inode)-> | |
995 | + generation)); | |
996 | + goto out; | |
997 | + } | |
998 | + | |
999 | + dget(lower_dentry); | |
1000 | + unionfs_mntget(dentry, bstart); | |
1001 | + lower_file = dentry_open(lower_dentry, | |
1002 | + unionfs_lower_mnt_idx(dentry, bstart), | |
1003 | + file->f_flags, current_cred()); | |
1004 | + if (IS_ERR(lower_file)) { | |
1005 | + err = PTR_ERR(lower_file); | |
1006 | + goto out; | |
1007 | + } | |
1008 | + branchget(sb, bstart); | |
1009 | + unionfs_set_lower_file(file, lower_file); | |
1010 | + /* Fix up the position. */ | |
1011 | + lower_file->f_pos = file->f_pos; | |
1012 | + | |
1013 | + memcpy(&lower_file->f_ra, &file->f_ra, sizeof(struct file_ra_state)); | |
1014 | +out: | |
1015 | + dput(parent); | |
1016 | + return err; | |
1017 | +} | |
1018 | + | |
1019 | +/* perform a delayed copyup of a read-write file on a read-only branch */ | |
1020 | +static int do_delayed_copyup(struct file *file, struct dentry *parent) | |
1021 | +{ | |
1022 | + int bindex, bstart, bend, err = 0; | |
1023 | + struct dentry *dentry = file->f_path.dentry; | |
1024 | + struct inode *parent_inode = parent->d_inode; | |
1025 | + | |
1026 | + bstart = fbstart(file); | |
1027 | + bend = fbend(file); | |
1028 | + | |
1029 | + BUG_ON(!S_ISREG(dentry->d_inode->i_mode)); | |
1030 | + | |
1031 | + unionfs_check_file(file); | |
1032 | + for (bindex = bstart - 1; bindex >= 0; bindex--) { | |
1033 | + if (!d_deleted(dentry)) | |
1034 | + err = copyup_file(parent_inode, file, bstart, | |
1035 | + bindex, | |
1036 | + i_size_read(dentry->d_inode)); | |
1037 | + else | |
1038 | + err = copyup_deleted_file(file, dentry, parent, | |
1039 | + bstart, bindex); | |
1040 | + /* if succeeded, set lower open-file flags and break */ | |
1041 | + if (!err) { | |
1042 | + struct file *lower_file; | |
1043 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
1044 | + lower_file->f_flags = file->f_flags; | |
1045 | + break; | |
1046 | + } | |
1047 | + } | |
1048 | + if (err || (bstart <= fbstart(file))) | |
1049 | + goto out; | |
1050 | + bend = fbend(file); | |
1051 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
1052 | + if (unionfs_lower_file_idx(file, bindex)) { | |
1053 | + branchput(dentry->d_sb, bindex); | |
1054 | + fput(unionfs_lower_file_idx(file, bindex)); | |
1055 | + unionfs_set_lower_file_idx(file, bindex, NULL); | |
1056 | + } | |
1057 | + } | |
1058 | + path_put_lowers(dentry, bstart, bend, false); | |
1059 | + iput_lowers(dentry->d_inode, bstart, bend, false); | |
1060 | + /* for reg file, we only open it "once" */ | |
1061 | + fbend(file) = fbstart(file); | |
1062 | + dbend(dentry) = dbstart(dentry); | |
1063 | + ibend(dentry->d_inode) = ibstart(dentry->d_inode); | |
1064 | + | |
1065 | +out: | |
1066 | + unionfs_check_file(file); | |
1067 | + return err; | |
1068 | +} | |
1069 | + | |
1070 | +/* | |
1071 | + * Helper function for unionfs_file_revalidate/locked. | |
1072 | + * Expects dentry/parent to be locked already, and revalidated. | |
1073 | + */ | |
1074 | +static int __unionfs_file_revalidate(struct file *file, struct dentry *dentry, | |
1075 | + struct dentry *parent, | |
1076 | + struct super_block *sb, int sbgen, | |
1077 | + int dgen, bool willwrite) | |
1078 | +{ | |
1079 | + int fgen; | |
1080 | + int bstart, bend, orig_brid; | |
1081 | + int size; | |
1082 | + int err = 0; | |
1083 | + | |
1084 | + fgen = atomic_read(&UNIONFS_F(file)->generation); | |
1085 | + | |
1086 | + /* | |
1087 | + * There are two cases we are interested in. The first is if the | |
1088 | + * generation is lower than the super-block. The second is if | |
1089 | + * someone has copied up this file from underneath us, we also need | |
1090 | + * to refresh things. | |
1091 | + */ | |
6b53c3da | 1092 | + if (d_deleted(dentry) || |
2380c486 JR |
1093 | + (sbgen <= fgen && |
1094 | + dbstart(dentry) == fbstart(file) && | |
1095 | + unionfs_lower_file(file))) | |
1096 | + goto out_may_copyup; | |
1097 | + | |
1098 | + /* save orig branch ID */ | |
1099 | + orig_brid = UNIONFS_F(file)->saved_branch_ids[fbstart(file)]; | |
1100 | + | |
1101 | + /* First we throw out the existing files. */ | |
1102 | + cleanup_file(file); | |
1103 | + | |
1104 | + /* Now we reopen the file(s) as in unionfs_open. */ | |
1105 | + bstart = fbstart(file) = dbstart(dentry); | |
1106 | + bend = fbend(file) = dbend(dentry); | |
1107 | + | |
1108 | + size = sizeof(struct file *) * sbmax(sb); | |
1109 | + UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL); | |
1110 | + if (unlikely(!UNIONFS_F(file)->lower_files)) { | |
1111 | + err = -ENOMEM; | |
1112 | + goto out; | |
1113 | + } | |
1114 | + size = sizeof(int) * sbmax(sb); | |
1115 | + UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL); | |
1116 | + if (unlikely(!UNIONFS_F(file)->saved_branch_ids)) { | |
1117 | + err = -ENOMEM; | |
1118 | + goto out; | |
1119 | + } | |
1120 | + | |
1121 | + if (S_ISDIR(dentry->d_inode->i_mode)) { | |
1122 | + /* We need to open all the files. */ | |
1123 | + err = open_all_files(file); | |
1124 | + if (err) | |
1125 | + goto out; | |
1126 | + } else { | |
1127 | + int new_brid; | |
1128 | + /* We only open the highest priority branch. */ | |
1129 | + err = open_highest_file(file, willwrite); | |
1130 | + if (err) | |
1131 | + goto out; | |
1132 | + new_brid = UNIONFS_F(file)->saved_branch_ids[fbstart(file)]; | |
1133 | + if (unlikely(new_brid != orig_brid && sbgen > fgen)) { | |
1134 | + /* | |
1135 | + * If we re-opened the file on a different branch | |
1136 | + * than the original one, and this was due to a new | |
1137 | + * branch inserted, then update the mnt counts of | |
1138 | + * the old and new branches accordingly. | |
1139 | + */ | |
1140 | + unionfs_mntget(dentry, bstart); | |
1141 | + unionfs_mntput(sb->s_root, | |
1142 | + branch_id_to_idx(sb, orig_brid)); | |
1143 | + } | |
1144 | + /* regular files have only one open lower file */ | |
1145 | + fbend(file) = fbstart(file); | |
1146 | + } | |
1147 | + atomic_set(&UNIONFS_F(file)->generation, | |
1148 | + atomic_read(&UNIONFS_I(dentry->d_inode)->generation)); | |
1149 | + | |
1150 | +out_may_copyup: | |
1151 | + /* Copyup on the first write to a file on a readonly branch. */ | |
1152 | + if (willwrite && IS_WRITE_FLAG(file->f_flags) && | |
1153 | + !IS_WRITE_FLAG(unionfs_lower_file(file)->f_flags) && | |
1154 | + is_robranch(dentry)) { | |
1155 | + pr_debug("unionfs: do delay copyup of \"%s\"\n", | |
1156 | + dentry->d_name.name); | |
1157 | + err = do_delayed_copyup(file, parent); | |
1158 | + /* regular files have only one open lower file */ | |
1159 | + if (!err && !S_ISDIR(dentry->d_inode->i_mode)) | |
1160 | + fbend(file) = fbstart(file); | |
1161 | + } | |
1162 | + | |
1163 | +out: | |
1164 | + if (err) { | |
1165 | + kfree(UNIONFS_F(file)->lower_files); | |
1166 | + kfree(UNIONFS_F(file)->saved_branch_ids); | |
1167 | + } | |
1168 | + return err; | |
1169 | +} | |
1170 | + | |
1171 | +/* | |
1172 | + * Revalidate the struct file | |
1173 | + * @file: file to revalidate | |
1174 | + * @parent: parent dentry (locked by caller) | |
1175 | + * @willwrite: true if caller may cause changes to the file; false otherwise. | |
1176 | + * Caller must lock/unlock dentry's branch configuration. | |
1177 | + */ | |
1178 | +int unionfs_file_revalidate(struct file *file, struct dentry *parent, | |
1179 | + bool willwrite) | |
1180 | +{ | |
1181 | + struct super_block *sb; | |
1182 | + struct dentry *dentry; | |
1183 | + int sbgen, dgen; | |
1184 | + int err = 0; | |
1185 | + | |
1186 | + dentry = file->f_path.dentry; | |
1187 | + sb = dentry->d_sb; | |
1188 | + verify_locked(dentry); | |
1189 | + verify_locked(parent); | |
1190 | + | |
1191 | + /* | |
1192 | + * First revalidate the dentry inside struct file, | |
1193 | + * but not unhashed dentries. | |
1194 | + */ | |
1195 | + if (!d_deleted(dentry) && | |
1196 | + !__unionfs_d_revalidate(dentry, parent, willwrite)) { | |
1197 | + err = -ESTALE; | |
1198 | + goto out; | |
1199 | + } | |
1200 | + | |
1201 | + sbgen = atomic_read(&UNIONFS_SB(sb)->generation); | |
1202 | + dgen = atomic_read(&UNIONFS_D(dentry)->generation); | |
1203 | + | |
1204 | + if (unlikely(sbgen > dgen)) { /* XXX: should never happen */ | |
1205 | + pr_debug("unionfs: failed to revalidate dentry (%s)\n", | |
1206 | + dentry->d_name.name); | |
1207 | + err = -ESTALE; | |
1208 | + goto out; | |
1209 | + } | |
1210 | + | |
1211 | + err = __unionfs_file_revalidate(file, dentry, parent, sb, | |
1212 | + sbgen, dgen, willwrite); | |
1213 | +out: | |
1214 | + return err; | |
1215 | +} | |
1216 | + | |
1217 | +/* unionfs_open helper function: open a directory */ | |
6b53c3da AM |
1218 | +static int __open_dir(struct inode *inode, struct file *file, |
1219 | + struct dentry *parent) | |
2380c486 JR |
1220 | +{ |
1221 | + struct dentry *lower_dentry; | |
1222 | + struct file *lower_file; | |
1223 | + int bindex, bstart, bend; | |
6b53c3da AM |
1224 | + struct vfsmount *lower_mnt; |
1225 | + struct dentry *dentry = file->f_path.dentry; | |
2380c486 | 1226 | + |
6b53c3da AM |
1227 | + bstart = fbstart(file) = dbstart(dentry); |
1228 | + bend = fbend(file) = dbend(dentry); | |
2380c486 JR |
1229 | + |
1230 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
1231 | + lower_dentry = | |
6b53c3da | 1232 | + unionfs_lower_dentry_idx(dentry, bindex); |
2380c486 JR |
1233 | + if (!lower_dentry) |
1234 | + continue; | |
1235 | + | |
1236 | + dget(lower_dentry); | |
6b53c3da AM |
1237 | + lower_mnt = unionfs_mntget(dentry, bindex); |
1238 | + if (!lower_mnt) | |
1239 | + lower_mnt = unionfs_mntget(parent, bindex); | |
1240 | + lower_file = dentry_open(lower_dentry, lower_mnt, file->f_flags, | |
2380c486 JR |
1241 | + current_cred()); |
1242 | + if (IS_ERR(lower_file)) | |
1243 | + return PTR_ERR(lower_file); | |
1244 | + | |
1245 | + unionfs_set_lower_file_idx(file, bindex, lower_file); | |
6b53c3da AM |
1246 | + if (!unionfs_lower_mnt_idx(dentry, bindex)) |
1247 | + unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt); | |
2380c486 JR |
1248 | + |
1249 | + /* | |
1250 | + * The branchget goes after the open, because otherwise | |
1251 | + * we would miss the reference on release. | |
1252 | + */ | |
1253 | + branchget(inode->i_sb, bindex); | |
1254 | + } | |
1255 | + | |
1256 | + return 0; | |
1257 | +} | |
1258 | + | |
1259 | +/* unionfs_open helper function: open a file */ | |
1260 | +static int __open_file(struct inode *inode, struct file *file, | |
1261 | + struct dentry *parent) | |
1262 | +{ | |
1263 | + struct dentry *lower_dentry; | |
1264 | + struct file *lower_file; | |
1265 | + int lower_flags; | |
1266 | + int bindex, bstart, bend; | |
6b53c3da AM |
1267 | + struct dentry *dentry = file->f_path.dentry; |
1268 | + struct vfsmount *lower_mnt; | |
2380c486 | 1269 | + |
6b53c3da | 1270 | + lower_dentry = unionfs_lower_dentry(dentry); |
2380c486 JR |
1271 | + lower_flags = file->f_flags; |
1272 | + | |
6b53c3da AM |
1273 | + bstart = fbstart(file) = dbstart(dentry); |
1274 | + bend = fbend(file) = dbend(dentry); | |
2380c486 JR |
1275 | + |
1276 | + /* | |
1277 | + * check for the permission for lower file. If the error is | |
1278 | + * COPYUP_ERR, copyup the file. | |
1279 | + */ | |
6b53c3da | 1280 | + if (lower_dentry->d_inode && is_robranch(dentry)) { |
2380c486 JR |
1281 | + /* |
1282 | + * if the open will change the file, copy it up otherwise | |
1283 | + * defer it. | |
1284 | + */ | |
1285 | + if (lower_flags & O_TRUNC) { | |
1286 | + int size = 0; | |
1287 | + int err = -EROFS; | |
1288 | + | |
1289 | + /* copyup the file */ | |
1290 | + for (bindex = bstart - 1; bindex >= 0; bindex--) { | |
1291 | + err = copyup_file(parent->d_inode, file, | |
1292 | + bstart, bindex, size); | |
63b09289 JR |
1293 | + if (!err) { |
1294 | + /* only one regular file open */ | |
1295 | + fbend(file) = fbstart(file); | |
2380c486 | 1296 | + break; |
63b09289 | 1297 | + } |
2380c486 JR |
1298 | + } |
1299 | + return err; | |
1300 | + } else { | |
1301 | + /* | |
1302 | + * turn off writeable flags, to force delayed copyup | |
1303 | + * by caller. | |
1304 | + */ | |
1305 | + lower_flags &= ~(OPEN_WRITE_FLAGS); | |
1306 | + } | |
1307 | + } | |
1308 | + | |
1309 | + dget(lower_dentry); | |
1310 | + | |
1311 | + /* | |
1312 | + * dentry_open will decrement mnt refcnt if err. | |
1313 | + * otherwise fput() will do an mntput() for us upon file close. | |
1314 | + */ | |
6b53c3da AM |
1315 | + lower_mnt = unionfs_mntget(dentry, bstart); |
1316 | + lower_file = dentry_open(lower_dentry, lower_mnt, lower_flags, | |
1317 | + current_cred()); | |
2380c486 JR |
1318 | + if (IS_ERR(lower_file)) |
1319 | + return PTR_ERR(lower_file); | |
1320 | + | |
1321 | + unionfs_set_lower_file(file, lower_file); | |
1322 | + branchget(inode->i_sb, bstart); | |
1323 | + | |
1324 | + return 0; | |
1325 | +} | |
1326 | + | |
1327 | +int unionfs_open(struct inode *inode, struct file *file) | |
1328 | +{ | |
1329 | + int err = 0; | |
1330 | + struct file *lower_file = NULL; | |
1331 | + struct dentry *dentry = file->f_path.dentry; | |
1332 | + struct dentry *parent; | |
1333 | + int bindex = 0, bstart = 0, bend = 0; | |
1334 | + int size; | |
1335 | + int valid = 0; | |
1336 | + | |
1337 | + unionfs_read_lock(inode->i_sb, UNIONFS_SMUTEX_PARENT); | |
1338 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
1339 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
1340 | + | |
1341 | + /* don't open unhashed/deleted files */ | |
1342 | + if (d_deleted(dentry)) { | |
1343 | + err = -ENOENT; | |
1344 | + goto out_nofree; | |
1345 | + } | |
1346 | + | |
1347 | + /* XXX: should I change 'false' below to the 'willwrite' flag? */ | |
1348 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
1349 | + if (unlikely(!valid)) { | |
1350 | + err = -ESTALE; | |
1351 | + goto out_nofree; | |
1352 | + } | |
1353 | + | |
1354 | + file->private_data = | |
1355 | + kzalloc(sizeof(struct unionfs_file_info), GFP_KERNEL); | |
1356 | + if (unlikely(!UNIONFS_F(file))) { | |
1357 | + err = -ENOMEM; | |
1358 | + goto out_nofree; | |
1359 | + } | |
1360 | + fbstart(file) = -1; | |
1361 | + fbend(file) = -1; | |
1362 | + atomic_set(&UNIONFS_F(file)->generation, | |
1363 | + atomic_read(&UNIONFS_I(inode)->generation)); | |
1364 | + | |
1365 | + size = sizeof(struct file *) * sbmax(inode->i_sb); | |
1366 | + UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL); | |
1367 | + if (unlikely(!UNIONFS_F(file)->lower_files)) { | |
1368 | + err = -ENOMEM; | |
1369 | + goto out; | |
1370 | + } | |
1371 | + size = sizeof(int) * sbmax(inode->i_sb); | |
1372 | + UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL); | |
1373 | + if (unlikely(!UNIONFS_F(file)->saved_branch_ids)) { | |
1374 | + err = -ENOMEM; | |
1375 | + goto out; | |
1376 | + } | |
1377 | + | |
1378 | + bstart = fbstart(file) = dbstart(dentry); | |
1379 | + bend = fbend(file) = dbend(dentry); | |
1380 | + | |
1381 | + /* | |
1382 | + * open all directories and make the unionfs file struct point to | |
1383 | + * these lower file structs | |
1384 | + */ | |
1385 | + if (S_ISDIR(inode->i_mode)) | |
6b53c3da | 1386 | + err = __open_dir(inode, file, parent); /* open a dir */ |
2380c486 JR |
1387 | + else |
1388 | + err = __open_file(inode, file, parent); /* open a file */ | |
1389 | + | |
1390 | + /* freeing the allocated resources, and fput the opened files */ | |
1391 | + if (err) { | |
1392 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
1393 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
1394 | + if (!lower_file) | |
1395 | + continue; | |
1396 | + | |
1397 | + branchput(dentry->d_sb, bindex); | |
1398 | + /* fput calls dput for lower_dentry */ | |
1399 | + fput(lower_file); | |
1400 | + } | |
1401 | + } | |
1402 | + | |
1403 | +out: | |
1404 | + if (err) { | |
1405 | + kfree(UNIONFS_F(file)->lower_files); | |
1406 | + kfree(UNIONFS_F(file)->saved_branch_ids); | |
1407 | + kfree(UNIONFS_F(file)); | |
1408 | + } | |
1409 | +out_nofree: | |
1410 | + if (!err) { | |
1411 | + unionfs_postcopyup_setmnt(dentry); | |
1412 | + unionfs_copy_attr_times(inode); | |
1413 | + unionfs_check_file(file); | |
1414 | + unionfs_check_inode(inode); | |
1415 | + } | |
1416 | + unionfs_unlock_dentry(dentry); | |
1417 | + unionfs_unlock_parent(dentry, parent); | |
1418 | + unionfs_read_unlock(inode->i_sb); | |
1419 | + return err; | |
1420 | +} | |
1421 | + | |
1422 | +/* | |
1423 | + * release all lower object references & free the file info structure | |
1424 | + * | |
1425 | + * No need to grab sb info's rwsem. | |
1426 | + */ | |
1427 | +int unionfs_file_release(struct inode *inode, struct file *file) | |
1428 | +{ | |
1429 | + struct file *lower_file = NULL; | |
1430 | + struct unionfs_file_info *fileinfo; | |
1431 | + struct unionfs_inode_info *inodeinfo; | |
1432 | + struct super_block *sb = inode->i_sb; | |
1433 | + struct dentry *dentry = file->f_path.dentry; | |
1434 | + struct dentry *parent; | |
1435 | + int bindex, bstart, bend; | |
63b09289 | 1436 | + int err = 0; |
2380c486 | 1437 | + |
4ae1df7a JR |
1438 | + /* |
1439 | + * Since mm/memory.c:might_fault() (under PROVE_LOCKING) was | |
1440 | + * modified in 2.6.29-rc1 to call might_lock_read on mmap_sem, this | |
1441 | + * has been causing false positives in file system stacking layers. | |
1442 | + * In particular, our ->mmap is called after sys_mmap2 already holds | |
1443 | + * mmap_sem, then we lock our own mutexes; but earlier, it's | |
1444 | + * possible for lockdep to have locked our mutexes first, and then | |
1445 | + * we call a lower ->readdir which could call might_fault. The | |
1446 | + * different ordering of the locks is what lockdep complains about | |
1447 | + * -- unnecessarily. Therefore, we have no choice but to tell | |
1448 | + * lockdep to temporarily turn off lockdep here. Note: the comments | |
1449 | + * inside might_sleep also suggest that it would have been | |
1450 | + * nicer to only annotate paths that needs that might_lock_read. | |
1451 | + */ | |
1452 | + lockdep_off(); | |
2380c486 JR |
1453 | + unionfs_read_lock(sb, UNIONFS_SMUTEX_PARENT); |
1454 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
1455 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
1456 | + | |
1457 | + /* | |
1458 | + * We try to revalidate, but the VFS ignores return return values | |
1459 | + * from file->release, so we must always try to succeed here, | |
1460 | + * including to do the kfree and dput below. So if revalidation | |
1461 | + * failed, all we can do is print some message and keep going. | |
1462 | + */ | |
1463 | + err = unionfs_file_revalidate(file, parent, | |
1464 | + UNIONFS_F(file)->wrote_to_file); | |
1465 | + if (!err) | |
1466 | + unionfs_check_file(file); | |
1467 | + fileinfo = UNIONFS_F(file); | |
1468 | + BUG_ON(file->f_path.dentry->d_inode != inode); | |
1469 | + inodeinfo = UNIONFS_I(inode); | |
1470 | + | |
1471 | + /* fput all the lower files */ | |
2380c486 JR |
1472 | + bstart = fbstart(file); |
1473 | + bend = fbend(file); | |
1474 | + | |
1475 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
1476 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
1477 | + | |
1478 | + if (lower_file) { | |
1479 | + unionfs_set_lower_file_idx(file, bindex, NULL); | |
1480 | + fput(lower_file); | |
1481 | + branchput(sb, bindex); | |
1482 | + } | |
1483 | + | |
1484 | + /* if there are no more refs to the dentry, dput it */ | |
1485 | + if (d_deleted(dentry)) { | |
1486 | + dput(unionfs_lower_dentry_idx(dentry, bindex)); | |
1487 | + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); | |
1488 | + } | |
1489 | + } | |
1490 | + | |
1491 | + kfree(fileinfo->lower_files); | |
1492 | + kfree(fileinfo->saved_branch_ids); | |
1493 | + | |
1494 | + if (fileinfo->rdstate) { | |
1495 | + fileinfo->rdstate->access = jiffies; | |
1496 | + spin_lock(&inodeinfo->rdlock); | |
1497 | + inodeinfo->rdcount++; | |
1498 | + list_add_tail(&fileinfo->rdstate->cache, | |
1499 | + &inodeinfo->readdircache); | |
1500 | + mark_inode_dirty(inode); | |
1501 | + spin_unlock(&inodeinfo->rdlock); | |
1502 | + fileinfo->rdstate = NULL; | |
1503 | + } | |
1504 | + kfree(fileinfo); | |
1505 | + | |
1506 | + unionfs_unlock_dentry(dentry); | |
1507 | + unionfs_unlock_parent(dentry, parent); | |
1508 | + unionfs_read_unlock(sb); | |
4ae1df7a | 1509 | + lockdep_on(); |
2380c486 JR |
1510 | + return err; |
1511 | +} | |
1512 | + | |
1513 | +/* pass the ioctl to the lower fs */ | |
1514 | +static long do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) | |
1515 | +{ | |
1516 | + struct file *lower_file; | |
1517 | + int err; | |
1518 | + | |
1519 | + lower_file = unionfs_lower_file(file); | |
1520 | + | |
1521 | + err = -ENOTTY; | |
1522 | + if (!lower_file || !lower_file->f_op) | |
1523 | + goto out; | |
1524 | + if (lower_file->f_op->unlocked_ioctl) { | |
1525 | + err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); | |
0c5527e5 | 1526 | +#ifdef CONFIG_COMPAT |
63b09289 JR |
1527 | + } else if (lower_file->f_op->compat_ioctl) { |
1528 | + err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg); | |
0c5527e5 | 1529 | +#endif |
2380c486 JR |
1530 | + } |
1531 | + | |
1532 | +out: | |
1533 | + return err; | |
1534 | +} | |
1535 | + | |
1536 | +/* | |
1537 | + * return to user-space the branch indices containing the file in question | |
1538 | + * | |
1539 | + * We use fd_set and therefore we are limited to the number of the branches | |
1540 | + * to FD_SETSIZE, which is currently 1024 - plenty for most people | |
1541 | + */ | |
1542 | +static int unionfs_ioctl_queryfile(struct file *file, struct dentry *parent, | |
1543 | + unsigned int cmd, unsigned long arg) | |
1544 | +{ | |
1545 | + int err = 0; | |
1546 | + fd_set branchlist; | |
1547 | + int bstart = 0, bend = 0, bindex = 0; | |
1548 | + int orig_bstart, orig_bend; | |
1549 | + struct dentry *dentry, *lower_dentry; | |
1550 | + struct vfsmount *mnt; | |
1551 | + | |
1552 | + dentry = file->f_path.dentry; | |
1553 | + orig_bstart = dbstart(dentry); | |
1554 | + orig_bend = dbend(dentry); | |
1555 | + err = unionfs_partial_lookup(dentry, parent); | |
1556 | + if (err) | |
1557 | + goto out; | |
1558 | + bstart = dbstart(dentry); | |
1559 | + bend = dbend(dentry); | |
1560 | + | |
1561 | + FD_ZERO(&branchlist); | |
1562 | + | |
1563 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
1564 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
1565 | + if (!lower_dentry) | |
1566 | + continue; | |
1567 | + if (likely(lower_dentry->d_inode)) | |
1568 | + FD_SET(bindex, &branchlist); | |
1569 | + /* purge any lower objects after partial_lookup */ | |
1570 | + if (bindex < orig_bstart || bindex > orig_bend) { | |
1571 | + dput(lower_dentry); | |
1572 | + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); | |
1573 | + iput(unionfs_lower_inode_idx(dentry->d_inode, bindex)); | |
1574 | + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, | |
1575 | + NULL); | |
1576 | + mnt = unionfs_lower_mnt_idx(dentry, bindex); | |
1577 | + if (!mnt) | |
1578 | + continue; | |
1579 | + unionfs_mntput(dentry, bindex); | |
1580 | + unionfs_set_lower_mnt_idx(dentry, bindex, NULL); | |
1581 | + } | |
1582 | + } | |
1583 | + /* restore original dentry's offsets */ | |
1584 | + dbstart(dentry) = orig_bstart; | |
1585 | + dbend(dentry) = orig_bend; | |
1586 | + ibstart(dentry->d_inode) = orig_bstart; | |
1587 | + ibend(dentry->d_inode) = orig_bend; | |
1588 | + | |
1589 | + err = copy_to_user((void __user *)arg, &branchlist, sizeof(fd_set)); | |
1590 | + if (unlikely(err)) | |
1591 | + err = -EFAULT; | |
1592 | + | |
1593 | +out: | |
1594 | + return err < 0 ? err : bend; | |
1595 | +} | |
1596 | + | |
1597 | +long unionfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) | |
1598 | +{ | |
1599 | + long err; | |
1600 | + struct dentry *dentry = file->f_path.dentry; | |
1601 | + struct dentry *parent; | |
1602 | + | |
1603 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
1604 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
1605 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
1606 | + | |
1607 | + err = unionfs_file_revalidate(file, parent, true); | |
1608 | + if (unlikely(err)) | |
1609 | + goto out; | |
1610 | + | |
1611 | + /* check if asked for local commands */ | |
1612 | + switch (cmd) { | |
1613 | + case UNIONFS_IOCTL_INCGEN: | |
1614 | + /* Increment the superblock generation count */ | |
1615 | + pr_info("unionfs: incgen ioctl deprecated; " | |
1616 | + "use \"-o remount,incgen\"\n"); | |
1617 | + err = -ENOSYS; | |
1618 | + break; | |
1619 | + | |
1620 | + case UNIONFS_IOCTL_QUERYFILE: | |
1621 | + /* Return list of branches containing the given file */ | |
1622 | + err = unionfs_ioctl_queryfile(file, parent, cmd, arg); | |
1623 | + break; | |
1624 | + | |
1625 | + default: | |
1626 | + /* pass the ioctl down */ | |
1627 | + err = do_ioctl(file, cmd, arg); | |
1628 | + break; | |
1629 | + } | |
1630 | + | |
1631 | +out: | |
1632 | + unionfs_check_file(file); | |
1633 | + unionfs_unlock_dentry(dentry); | |
1634 | + unionfs_unlock_parent(dentry, parent); | |
1635 | + unionfs_read_unlock(dentry->d_sb); | |
1636 | + return err; | |
1637 | +} | |
1638 | + | |
1639 | +int unionfs_flush(struct file *file, fl_owner_t id) | |
1640 | +{ | |
1641 | + int err = 0; | |
1642 | + struct file *lower_file = NULL; | |
1643 | + struct dentry *dentry = file->f_path.dentry; | |
1644 | + struct dentry *parent; | |
1645 | + int bindex, bstart, bend; | |
1646 | + | |
1647 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
1648 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
1649 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
1650 | + | |
1651 | + err = unionfs_file_revalidate(file, parent, | |
1652 | + UNIONFS_F(file)->wrote_to_file); | |
1653 | + if (unlikely(err)) | |
1654 | + goto out; | |
1655 | + unionfs_check_file(file); | |
1656 | + | |
1657 | + bstart = fbstart(file); | |
1658 | + bend = fbend(file); | |
1659 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
1660 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
1661 | + | |
1662 | + if (lower_file && lower_file->f_op && | |
1663 | + lower_file->f_op->flush) { | |
1664 | + err = lower_file->f_op->flush(lower_file, id); | |
1665 | + if (err) | |
1666 | + goto out; | |
1667 | + } | |
1668 | + | |
1669 | + } | |
1670 | + | |
1671 | +out: | |
1672 | + if (!err) | |
1673 | + unionfs_check_file(file); | |
1674 | + unionfs_unlock_dentry(dentry); | |
1675 | + unionfs_unlock_parent(dentry, parent); | |
1676 | + unionfs_read_unlock(dentry->d_sb); | |
1677 | + return err; | |
1678 | +} | |
0c5527e5 AM |
1679 | diff --git a/fs/unionfs/copyup.c b/fs/unionfs/copyup.c |
1680 | new file mode 100644 | |
6b53c3da | 1681 | index 0000000..078ca27 |
0c5527e5 AM |
1682 | --- /dev/null |
1683 | +++ b/fs/unionfs/copyup.c | |
6b53c3da | 1684 | @@ -0,0 +1,899 @@ |
2380c486 | 1685 | +/* |
63b09289 | 1686 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
1687 | + * Copyright (c) 2003-2006 Charles P. Wright |
1688 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
1689 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
1690 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
1691 | + * Copyright (c) 2004-2006 David P. Quigley | |
1692 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
1693 | + * Copyright (c) 2003 Puja Gupta | |
1694 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
1695 | + * Copyright (c) 2003-2011 Stony Brook University |
1696 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
1697 | + * |
1698 | + * This program is free software; you can redistribute it and/or modify | |
1699 | + * it under the terms of the GNU General Public License version 2 as | |
1700 | + * published by the Free Software Foundation. | |
1701 | + */ | |
1702 | + | |
1703 | +#include "union.h" | |
1704 | + | |
1705 | +/* | |
1706 | + * For detailed explanation of copyup see: | |
1707 | + * Documentation/filesystems/unionfs/concepts.txt | |
1708 | + */ | |
1709 | + | |
1710 | +#ifdef CONFIG_UNION_FS_XATTR | |
1711 | +/* copyup all extended attrs for a given dentry */ | |
1712 | +static int copyup_xattrs(struct dentry *old_lower_dentry, | |
1713 | + struct dentry *new_lower_dentry) | |
1714 | +{ | |
1715 | + int err = 0; | |
1716 | + ssize_t list_size = -1; | |
1717 | + char *name_list = NULL; | |
1718 | + char *attr_value = NULL; | |
1719 | + char *name_list_buf = NULL; | |
1720 | + | |
1721 | + /* query the actual size of the xattr list */ | |
1722 | + list_size = vfs_listxattr(old_lower_dentry, NULL, 0); | |
1723 | + if (list_size <= 0) { | |
1724 | + err = list_size; | |
1725 | + goto out; | |
1726 | + } | |
1727 | + | |
1728 | + /* allocate space for the actual list */ | |
1729 | + name_list = unionfs_xattr_alloc(list_size + 1, XATTR_LIST_MAX); | |
1730 | + if (unlikely(!name_list || IS_ERR(name_list))) { | |
1731 | + err = PTR_ERR(name_list); | |
1732 | + goto out; | |
1733 | + } | |
1734 | + | |
1735 | + name_list_buf = name_list; /* save for kfree at end */ | |
1736 | + | |
1737 | + /* now get the actual xattr list of the source file */ | |
1738 | + list_size = vfs_listxattr(old_lower_dentry, name_list, list_size); | |
1739 | + if (list_size <= 0) { | |
1740 | + err = list_size; | |
1741 | + goto out; | |
1742 | + } | |
1743 | + | |
1744 | + /* allocate space to hold each xattr's value */ | |
1745 | + attr_value = unionfs_xattr_alloc(XATTR_SIZE_MAX, XATTR_SIZE_MAX); | |
1746 | + if (unlikely(!attr_value || IS_ERR(attr_value))) { | |
1747 | + err = PTR_ERR(name_list); | |
1748 | + goto out; | |
1749 | + } | |
1750 | + | |
1751 | + /* in a loop, get and set each xattr from src to dst file */ | |
1752 | + while (*name_list) { | |
1753 | + ssize_t size; | |
1754 | + | |
1755 | + /* Lock here since vfs_getxattr doesn't lock for us */ | |
1756 | + mutex_lock(&old_lower_dentry->d_inode->i_mutex); | |
1757 | + size = vfs_getxattr(old_lower_dentry, name_list, | |
1758 | + attr_value, XATTR_SIZE_MAX); | |
1759 | + mutex_unlock(&old_lower_dentry->d_inode->i_mutex); | |
1760 | + if (size < 0) { | |
1761 | + err = size; | |
1762 | + goto out; | |
1763 | + } | |
1764 | + if (size > XATTR_SIZE_MAX) { | |
1765 | + err = -E2BIG; | |
1766 | + goto out; | |
1767 | + } | |
1768 | + /* Don't lock here since vfs_setxattr does it for us. */ | |
1769 | + err = vfs_setxattr(new_lower_dentry, name_list, attr_value, | |
1770 | + size, 0); | |
1771 | + /* | |
1772 | + * Selinux depends on "security.*" xattrs, so to maintain | |
1773 | + * the security of copied-up files, if Selinux is active, | |
1774 | + * then we must copy these xattrs as well. So we need to | |
1775 | + * temporarily get FOWNER privileges. | |
1776 | + * XXX: move entire copyup code to SIOQ. | |
1777 | + */ | |
1778 | + if (err == -EPERM && !capable(CAP_FOWNER)) { | |
1779 | + const struct cred *old_creds; | |
1780 | + struct cred *new_creds; | |
1781 | + | |
1782 | + new_creds = prepare_creds(); | |
1783 | + if (unlikely(!new_creds)) { | |
1784 | + err = -ENOMEM; | |
1785 | + goto out; | |
1786 | + } | |
1787 | + cap_raise(new_creds->cap_effective, CAP_FOWNER); | |
1788 | + old_creds = override_creds(new_creds); | |
1789 | + err = vfs_setxattr(new_lower_dentry, name_list, | |
1790 | + attr_value, size, 0); | |
1791 | + revert_creds(old_creds); | |
1792 | + } | |
1793 | + if (err < 0) | |
1794 | + goto out; | |
1795 | + name_list += strlen(name_list) + 1; | |
1796 | + } | |
1797 | +out: | |
1798 | + unionfs_xattr_kfree(name_list_buf); | |
1799 | + unionfs_xattr_kfree(attr_value); | |
1800 | + /* Ignore if xattr isn't supported */ | |
1801 | + if (err == -ENOTSUPP || err == -EOPNOTSUPP) | |
1802 | + err = 0; | |
1803 | + return err; | |
1804 | +} | |
1805 | +#endif /* CONFIG_UNION_FS_XATTR */ | |
1806 | + | |
1807 | +/* | |
1808 | + * Determine the mode based on the copyup flags, and the existing dentry. | |
1809 | + * | |
1810 | + * Handle file systems which may not support certain options. For example | |
1811 | + * jffs2 doesn't allow one to chmod a symlink. So we ignore such harmless | |
1812 | + * errors, rather than propagating them up, which results in copyup errors | |
1813 | + * and errors returned back to users. | |
1814 | + */ | |
1815 | +static int copyup_permissions(struct super_block *sb, | |
1816 | + struct dentry *old_lower_dentry, | |
1817 | + struct dentry *new_lower_dentry) | |
1818 | +{ | |
1819 | + struct inode *i = old_lower_dentry->d_inode; | |
1820 | + struct iattr newattrs; | |
1821 | + int err; | |
1822 | + | |
1823 | + newattrs.ia_atime = i->i_atime; | |
1824 | + newattrs.ia_mtime = i->i_mtime; | |
1825 | + newattrs.ia_ctime = i->i_ctime; | |
1826 | + newattrs.ia_gid = i->i_gid; | |
1827 | + newattrs.ia_uid = i->i_uid; | |
1828 | + newattrs.ia_valid = ATTR_CTIME | ATTR_ATIME | ATTR_MTIME | | |
1829 | + ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_FORCE | | |
1830 | + ATTR_GID | ATTR_UID; | |
1831 | + mutex_lock(&new_lower_dentry->d_inode->i_mutex); | |
1832 | + err = notify_change(new_lower_dentry, &newattrs); | |
1833 | + if (err) | |
1834 | + goto out; | |
1835 | + | |
1836 | + /* now try to change the mode and ignore EOPNOTSUPP on symlinks */ | |
1837 | + newattrs.ia_mode = i->i_mode; | |
1838 | + newattrs.ia_valid = ATTR_MODE | ATTR_FORCE; | |
1839 | + err = notify_change(new_lower_dentry, &newattrs); | |
1840 | + if (err == -EOPNOTSUPP && | |
1841 | + S_ISLNK(new_lower_dentry->d_inode->i_mode)) { | |
1842 | + printk(KERN_WARNING | |
1843 | + "unionfs: changing \"%s\" symlink mode unsupported\n", | |
1844 | + new_lower_dentry->d_name.name); | |
1845 | + err = 0; | |
1846 | + } | |
1847 | + | |
1848 | +out: | |
1849 | + mutex_unlock(&new_lower_dentry->d_inode->i_mutex); | |
1850 | + return err; | |
1851 | +} | |
1852 | + | |
1853 | +/* | |
1854 | + * create the new device/file/directory - use copyup_permission to copyup | |
1855 | + * times, and mode | |
1856 | + * | |
1857 | + * if the object being copied up is a regular file, the file is only created, | |
1858 | + * the contents have to be copied up separately | |
1859 | + */ | |
1860 | +static int __copyup_ndentry(struct dentry *old_lower_dentry, | |
1861 | + struct dentry *new_lower_dentry, | |
1862 | + struct dentry *new_lower_parent_dentry, | |
1863 | + char *symbuf) | |
1864 | +{ | |
1865 | + int err = 0; | |
1866 | + umode_t old_mode = old_lower_dentry->d_inode->i_mode; | |
1867 | + struct sioq_args args; | |
1868 | + | |
1869 | + if (S_ISDIR(old_mode)) { | |
1870 | + args.mkdir.parent = new_lower_parent_dentry->d_inode; | |
1871 | + args.mkdir.dentry = new_lower_dentry; | |
1872 | + args.mkdir.mode = old_mode; | |
1873 | + | |
1874 | + run_sioq(__unionfs_mkdir, &args); | |
1875 | + err = args.err; | |
1876 | + } else if (S_ISLNK(old_mode)) { | |
1877 | + args.symlink.parent = new_lower_parent_dentry->d_inode; | |
1878 | + args.symlink.dentry = new_lower_dentry; | |
1879 | + args.symlink.symbuf = symbuf; | |
1880 | + | |
1881 | + run_sioq(__unionfs_symlink, &args); | |
1882 | + err = args.err; | |
1883 | + } else if (S_ISBLK(old_mode) || S_ISCHR(old_mode) || | |
1884 | + S_ISFIFO(old_mode) || S_ISSOCK(old_mode)) { | |
1885 | + args.mknod.parent = new_lower_parent_dentry->d_inode; | |
1886 | + args.mknod.dentry = new_lower_dentry; | |
1887 | + args.mknod.mode = old_mode; | |
1888 | + args.mknod.dev = old_lower_dentry->d_inode->i_rdev; | |
1889 | + | |
1890 | + run_sioq(__unionfs_mknod, &args); | |
1891 | + err = args.err; | |
1892 | + } else if (S_ISREG(old_mode)) { | |
1893 | + struct nameidata nd; | |
1894 | + err = init_lower_nd(&nd, LOOKUP_CREATE); | |
1895 | + if (unlikely(err < 0)) | |
1896 | + goto out; | |
1897 | + args.create.nd = &nd; | |
1898 | + args.create.parent = new_lower_parent_dentry->d_inode; | |
1899 | + args.create.dentry = new_lower_dentry; | |
1900 | + args.create.mode = old_mode; | |
1901 | + | |
1902 | + run_sioq(__unionfs_create, &args); | |
1903 | + err = args.err; | |
1904 | + release_lower_nd(&nd, err); | |
1905 | + } else { | |
1906 | + printk(KERN_CRIT "unionfs: unknown inode type %d\n", | |
1907 | + old_mode); | |
1908 | + BUG(); | |
1909 | + } | |
1910 | + | |
1911 | +out: | |
1912 | + return err; | |
1913 | +} | |
1914 | + | |
1915 | +static int __copyup_reg_data(struct dentry *dentry, | |
1916 | + struct dentry *new_lower_dentry, int new_bindex, | |
1917 | + struct dentry *old_lower_dentry, int old_bindex, | |
1918 | + struct file **copyup_file, loff_t len) | |
1919 | +{ | |
1920 | + struct super_block *sb = dentry->d_sb; | |
1921 | + struct file *input_file; | |
1922 | + struct file *output_file; | |
1923 | + struct vfsmount *output_mnt; | |
1924 | + mm_segment_t old_fs; | |
1925 | + char *buf = NULL; | |
1926 | + ssize_t read_bytes, write_bytes; | |
1927 | + loff_t size; | |
1928 | + int err = 0; | |
1929 | + | |
1930 | + /* open old file */ | |
1931 | + unionfs_mntget(dentry, old_bindex); | |
1932 | + branchget(sb, old_bindex); | |
1933 | + /* dentry_open calls dput and mntput if it returns an error */ | |
1934 | + input_file = dentry_open(old_lower_dentry, | |
1935 | + unionfs_lower_mnt_idx(dentry, old_bindex), | |
1936 | + O_RDONLY | O_LARGEFILE, current_cred()); | |
1937 | + if (IS_ERR(input_file)) { | |
1938 | + dput(old_lower_dentry); | |
1939 | + err = PTR_ERR(input_file); | |
1940 | + goto out; | |
1941 | + } | |
1942 | + if (unlikely(!input_file->f_op || !input_file->f_op->read)) { | |
1943 | + err = -EINVAL; | |
1944 | + goto out_close_in; | |
1945 | + } | |
1946 | + | |
1947 | + /* open new file */ | |
1948 | + dget(new_lower_dentry); | |
1949 | + output_mnt = unionfs_mntget(sb->s_root, new_bindex); | |
1950 | + branchget(sb, new_bindex); | |
1951 | + output_file = dentry_open(new_lower_dentry, output_mnt, | |
1952 | + O_RDWR | O_LARGEFILE, current_cred()); | |
1953 | + if (IS_ERR(output_file)) { | |
1954 | + err = PTR_ERR(output_file); | |
1955 | + goto out_close_in2; | |
1956 | + } | |
1957 | + if (unlikely(!output_file->f_op || !output_file->f_op->write)) { | |
1958 | + err = -EINVAL; | |
1959 | + goto out_close_out; | |
1960 | + } | |
1961 | + | |
1962 | + /* allocating a buffer */ | |
1963 | + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); | |
1964 | + if (unlikely(!buf)) { | |
1965 | + err = -ENOMEM; | |
1966 | + goto out_close_out; | |
1967 | + } | |
1968 | + | |
1969 | + input_file->f_pos = 0; | |
1970 | + output_file->f_pos = 0; | |
1971 | + | |
1972 | + old_fs = get_fs(); | |
1973 | + set_fs(KERNEL_DS); | |
1974 | + | |
1975 | + size = len; | |
1976 | + err = 0; | |
1977 | + do { | |
1978 | + if (len >= PAGE_SIZE) | |
1979 | + size = PAGE_SIZE; | |
1980 | + else if ((len < PAGE_SIZE) && (len > 0)) | |
1981 | + size = len; | |
1982 | + | |
1983 | + len -= PAGE_SIZE; | |
1984 | + | |
1985 | + read_bytes = | |
1986 | + input_file->f_op->read(input_file, | |
1987 | + (char __user *)buf, size, | |
1988 | + &input_file->f_pos); | |
1989 | + if (read_bytes <= 0) { | |
1990 | + err = read_bytes; | |
1991 | + break; | |
1992 | + } | |
1993 | + | |
1994 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
1995 | + lockdep_off(); | |
1996 | + write_bytes = | |
1997 | + output_file->f_op->write(output_file, | |
1998 | + (char __user *)buf, | |
1999 | + read_bytes, | |
2000 | + &output_file->f_pos); | |
2001 | + lockdep_on(); | |
2002 | + if ((write_bytes < 0) || (write_bytes < read_bytes)) { | |
2003 | + err = write_bytes; | |
2004 | + break; | |
2005 | + } | |
2006 | + } while ((read_bytes > 0) && (len > 0)); | |
2007 | + | |
2008 | + set_fs(old_fs); | |
2009 | + | |
2010 | + kfree(buf); | |
2011 | + | |
6b53c3da AM |
2012 | +#if 0 |
2013 | + /* XXX: code no longer needed? */ | |
2380c486 | 2014 | + if (!err) |
0c5527e5 | 2015 | + err = output_file->f_op->fsync(output_file, 0); |
6b53c3da | 2016 | +#endif |
2380c486 JR |
2017 | + |
2018 | + if (err) | |
2019 | + goto out_close_out; | |
2020 | + | |
2021 | + if (copyup_file) { | |
2022 | + *copyup_file = output_file; | |
2023 | + goto out_close_in; | |
2024 | + } | |
2025 | + | |
2026 | +out_close_out: | |
2027 | + fput(output_file); | |
2028 | + | |
2029 | +out_close_in2: | |
2030 | + branchput(sb, new_bindex); | |
2031 | + | |
2032 | +out_close_in: | |
2033 | + fput(input_file); | |
2034 | + | |
2035 | +out: | |
2036 | + branchput(sb, old_bindex); | |
2037 | + | |
2038 | + return err; | |
2039 | +} | |
2040 | + | |
2041 | +/* | |
2042 | + * dput the lower references for old and new dentry & clear a lower dentry | |
2043 | + * pointer | |
2044 | + */ | |
2045 | +static void __clear(struct dentry *dentry, struct dentry *old_lower_dentry, | |
2046 | + int old_bstart, int old_bend, | |
2047 | + struct dentry *new_lower_dentry, int new_bindex) | |
2048 | +{ | |
2049 | + /* get rid of the lower dentry and all its traces */ | |
2050 | + unionfs_set_lower_dentry_idx(dentry, new_bindex, NULL); | |
2051 | + dbstart(dentry) = old_bstart; | |
2052 | + dbend(dentry) = old_bend; | |
2053 | + | |
2054 | + dput(new_lower_dentry); | |
2055 | + dput(old_lower_dentry); | |
2056 | +} | |
2057 | + | |
2058 | +/* | |
2059 | + * Copy up a dentry to a file of specified name. | |
2060 | + * | |
2061 | + * @dir: used to pull the ->i_sb to access other branches | |
2062 | + * @dentry: the non-negative dentry whose lower_inode we should copy | |
2063 | + * @bstart: the branch of the lower_inode to copy from | |
2064 | + * @new_bindex: the branch to create the new file in | |
2065 | + * @name: the name of the file to create | |
2066 | + * @namelen: length of @name | |
2067 | + * @copyup_file: the "struct file" to return (optional) | |
2068 | + * @len: how many bytes to copy-up? | |
2069 | + */ | |
2070 | +int copyup_dentry(struct inode *dir, struct dentry *dentry, int bstart, | |
2071 | + int new_bindex, const char *name, int namelen, | |
2072 | + struct file **copyup_file, loff_t len) | |
2073 | +{ | |
2074 | + struct dentry *new_lower_dentry; | |
2075 | + struct dentry *old_lower_dentry = NULL; | |
2076 | + struct super_block *sb; | |
2077 | + int err = 0; | |
2078 | + int old_bindex; | |
2079 | + int old_bstart; | |
2080 | + int old_bend; | |
2081 | + struct dentry *new_lower_parent_dentry = NULL; | |
2082 | + mm_segment_t oldfs; | |
2083 | + char *symbuf = NULL; | |
2084 | + | |
2085 | + verify_locked(dentry); | |
2086 | + | |
2087 | + old_bindex = bstart; | |
2088 | + old_bstart = dbstart(dentry); | |
2089 | + old_bend = dbend(dentry); | |
2090 | + | |
2091 | + BUG_ON(new_bindex < 0); | |
2092 | + BUG_ON(new_bindex >= old_bindex); | |
2093 | + | |
2094 | + sb = dir->i_sb; | |
2095 | + | |
2096 | + err = is_robranch_super(sb, new_bindex); | |
2097 | + if (err) | |
2098 | + goto out; | |
2099 | + | |
2100 | + /* Create the directory structure above this dentry. */ | |
2101 | + new_lower_dentry = create_parents(dir, dentry, name, new_bindex); | |
2102 | + if (IS_ERR(new_lower_dentry)) { | |
2103 | + err = PTR_ERR(new_lower_dentry); | |
2104 | + goto out; | |
2105 | + } | |
2106 | + | |
2107 | + old_lower_dentry = unionfs_lower_dentry_idx(dentry, old_bindex); | |
2108 | + /* we conditionally dput this old_lower_dentry at end of function */ | |
2109 | + dget(old_lower_dentry); | |
2110 | + | |
2111 | + /* For symlinks, we must read the link before we lock the directory. */ | |
2112 | + if (S_ISLNK(old_lower_dentry->d_inode->i_mode)) { | |
2113 | + | |
2114 | + symbuf = kmalloc(PATH_MAX, GFP_KERNEL); | |
2115 | + if (unlikely(!symbuf)) { | |
2116 | + __clear(dentry, old_lower_dentry, | |
2117 | + old_bstart, old_bend, | |
2118 | + new_lower_dentry, new_bindex); | |
2119 | + err = -ENOMEM; | |
2120 | + goto out_free; | |
2121 | + } | |
2122 | + | |
2123 | + oldfs = get_fs(); | |
2124 | + set_fs(KERNEL_DS); | |
2125 | + err = old_lower_dentry->d_inode->i_op->readlink( | |
2126 | + old_lower_dentry, | |
2127 | + (char __user *)symbuf, | |
2128 | + PATH_MAX); | |
2129 | + set_fs(oldfs); | |
2130 | + if (err < 0) { | |
2131 | + __clear(dentry, old_lower_dentry, | |
2132 | + old_bstart, old_bend, | |
2133 | + new_lower_dentry, new_bindex); | |
2134 | + goto out_free; | |
2135 | + } | |
2136 | + symbuf[err] = '\0'; | |
2137 | + } | |
2138 | + | |
2139 | + /* Now we lock the parent, and create the object in the new branch. */ | |
2140 | + new_lower_parent_dentry = lock_parent(new_lower_dentry); | |
2141 | + | |
2142 | + /* create the new inode */ | |
2143 | + err = __copyup_ndentry(old_lower_dentry, new_lower_dentry, | |
2144 | + new_lower_parent_dentry, symbuf); | |
2145 | + | |
2146 | + if (err) { | |
2147 | + __clear(dentry, old_lower_dentry, | |
2148 | + old_bstart, old_bend, | |
2149 | + new_lower_dentry, new_bindex); | |
2150 | + goto out_unlock; | |
2151 | + } | |
2152 | + | |
2153 | + /* We actually copyup the file here. */ | |
2154 | + if (S_ISREG(old_lower_dentry->d_inode->i_mode)) | |
2155 | + err = __copyup_reg_data(dentry, new_lower_dentry, new_bindex, | |
2156 | + old_lower_dentry, old_bindex, | |
2157 | + copyup_file, len); | |
2158 | + if (err) | |
2159 | + goto out_unlink; | |
2160 | + | |
2161 | + /* Set permissions. */ | |
2162 | + err = copyup_permissions(sb, old_lower_dentry, new_lower_dentry); | |
2163 | + if (err) | |
2164 | + goto out_unlink; | |
2165 | + | |
2166 | +#ifdef CONFIG_UNION_FS_XATTR | |
2167 | + /* Selinux uses extended attributes for permissions. */ | |
2168 | + err = copyup_xattrs(old_lower_dentry, new_lower_dentry); | |
2169 | + if (err) | |
2170 | + goto out_unlink; | |
2171 | +#endif /* CONFIG_UNION_FS_XATTR */ | |
2172 | + | |
2173 | + /* do not allow files getting deleted to be re-interposed */ | |
2174 | + if (!d_deleted(dentry)) | |
2175 | + unionfs_reinterpose(dentry); | |
2176 | + | |
2177 | + goto out_unlock; | |
2178 | + | |
2179 | +out_unlink: | |
2180 | + /* | |
2181 | + * copyup failed, because we possibly ran out of space or | |
2182 | + * quota, or something else happened so let's unlink; we don't | |
2183 | + * really care about the return value of vfs_unlink | |
2184 | + */ | |
2185 | + vfs_unlink(new_lower_parent_dentry->d_inode, new_lower_dentry); | |
2186 | + | |
2187 | + if (copyup_file) { | |
2188 | + /* need to close the file */ | |
2189 | + | |
2190 | + fput(*copyup_file); | |
2191 | + branchput(sb, new_bindex); | |
2192 | + } | |
2193 | + | |
2194 | + /* | |
2195 | + * TODO: should we reset the error to something like -EIO? | |
2196 | + * | |
2197 | + * If we don't reset, the user may get some nonsensical errors, but | |
2198 | + * on the other hand, if we reset to EIO, we guarantee that the user | |
2199 | + * will get a "confusing" error message. | |
2200 | + */ | |
2201 | + | |
2202 | +out_unlock: | |
2203 | + unlock_dir(new_lower_parent_dentry); | |
2204 | + | |
2205 | +out_free: | |
2206 | + /* | |
2207 | + * If old_lower_dentry was not a file, then we need to dput it. If | |
2208 | + * it was a file, then it was already dput indirectly by other | |
2209 | + * functions we call above which operate on regular files. | |
2210 | + */ | |
2211 | + if (old_lower_dentry && old_lower_dentry->d_inode && | |
2212 | + !S_ISREG(old_lower_dentry->d_inode->i_mode)) | |
2213 | + dput(old_lower_dentry); | |
2214 | + kfree(symbuf); | |
2215 | + | |
2216 | + if (err) { | |
2217 | + /* | |
2218 | + * if directory creation succeeded, but inode copyup failed, | |
2219 | + * then purge new dentries. | |
2220 | + */ | |
2221 | + if (dbstart(dentry) < old_bstart && | |
2222 | + ibstart(dentry->d_inode) > dbstart(dentry)) | |
2223 | + __clear(dentry, NULL, old_bstart, old_bend, | |
2224 | + unionfs_lower_dentry(dentry), dbstart(dentry)); | |
2225 | + goto out; | |
2226 | + } | |
2227 | + if (!S_ISDIR(dentry->d_inode->i_mode)) { | |
2228 | + unionfs_postcopyup_release(dentry); | |
2229 | + if (!unionfs_lower_inode(dentry->d_inode)) { | |
2230 | + /* | |
2231 | + * If we got here, then we copied up to an | |
2232 | + * unlinked-open file, whose name is .unionfsXXXXX. | |
2233 | + */ | |
2234 | + struct inode *inode = new_lower_dentry->d_inode; | |
2235 | + atomic_inc(&inode->i_count); | |
2236 | + unionfs_set_lower_inode_idx(dentry->d_inode, | |
2237 | + ibstart(dentry->d_inode), | |
2238 | + inode); | |
2239 | + } | |
2240 | + } | |
2241 | + unionfs_postcopyup_setmnt(dentry); | |
2242 | + /* sync inode times from copied-up inode to our inode */ | |
2243 | + unionfs_copy_attr_times(dentry->d_inode); | |
2244 | + unionfs_check_inode(dir); | |
2245 | + unionfs_check_dentry(dentry); | |
2246 | +out: | |
2247 | + return err; | |
2248 | +} | |
2249 | + | |
2250 | +/* | |
2251 | + * This function creates a copy of a file represented by 'file' which | |
2252 | + * currently resides in branch 'bstart' to branch 'new_bindex.' The copy | |
2253 | + * will be named "name". | |
2254 | + */ | |
2255 | +int copyup_named_file(struct inode *dir, struct file *file, char *name, | |
2256 | + int bstart, int new_bindex, loff_t len) | |
2257 | +{ | |
2258 | + int err = 0; | |
2259 | + struct file *output_file = NULL; | |
2260 | + | |
2261 | + err = copyup_dentry(dir, file->f_path.dentry, bstart, new_bindex, | |
2262 | + name, strlen(name), &output_file, len); | |
2263 | + if (!err) { | |
2264 | + fbstart(file) = new_bindex; | |
2265 | + unionfs_set_lower_file_idx(file, new_bindex, output_file); | |
2266 | + } | |
2267 | + | |
2268 | + return err; | |
2269 | +} | |
2270 | + | |
2271 | +/* | |
2272 | + * This function creates a copy of a file represented by 'file' which | |
2273 | + * currently resides in branch 'bstart' to branch 'new_bindex'. | |
2274 | + */ | |
2275 | +int copyup_file(struct inode *dir, struct file *file, int bstart, | |
2276 | + int new_bindex, loff_t len) | |
2277 | +{ | |
2278 | + int err = 0; | |
2279 | + struct file *output_file = NULL; | |
2280 | + struct dentry *dentry = file->f_path.dentry; | |
2281 | + | |
2282 | + err = copyup_dentry(dir, dentry, bstart, new_bindex, | |
2283 | + dentry->d_name.name, dentry->d_name.len, | |
2284 | + &output_file, len); | |
2285 | + if (!err) { | |
2286 | + fbstart(file) = new_bindex; | |
2287 | + unionfs_set_lower_file_idx(file, new_bindex, output_file); | |
2288 | + } | |
2289 | + | |
2290 | + return err; | |
2291 | +} | |
2292 | + | |
2293 | +/* purge a dentry's lower-branch states (dput/mntput, etc.) */ | |
2294 | +static void __cleanup_dentry(struct dentry *dentry, int bindex, | |
2295 | + int old_bstart, int old_bend) | |
2296 | +{ | |
2297 | + int loop_start; | |
2298 | + int loop_end; | |
2299 | + int new_bstart = -1; | |
2300 | + int new_bend = -1; | |
2301 | + int i; | |
2302 | + | |
2303 | + loop_start = min(old_bstart, bindex); | |
2304 | + loop_end = max(old_bend, bindex); | |
2305 | + | |
2306 | + /* | |
2307 | + * This loop sets the bstart and bend for the new dentry by | |
2308 | + * traversing from left to right. It also dputs all negative | |
2309 | + * dentries except bindex | |
2310 | + */ | |
2311 | + for (i = loop_start; i <= loop_end; i++) { | |
2312 | + if (!unionfs_lower_dentry_idx(dentry, i)) | |
2313 | + continue; | |
2314 | + | |
2315 | + if (i == bindex) { | |
2316 | + new_bend = i; | |
2317 | + if (new_bstart < 0) | |
2318 | + new_bstart = i; | |
2319 | + continue; | |
2320 | + } | |
2321 | + | |
2322 | + if (!unionfs_lower_dentry_idx(dentry, i)->d_inode) { | |
2323 | + dput(unionfs_lower_dentry_idx(dentry, i)); | |
2324 | + unionfs_set_lower_dentry_idx(dentry, i, NULL); | |
2325 | + | |
2326 | + unionfs_mntput(dentry, i); | |
2327 | + unionfs_set_lower_mnt_idx(dentry, i, NULL); | |
2328 | + } else { | |
2329 | + if (new_bstart < 0) | |
2330 | + new_bstart = i; | |
2331 | + new_bend = i; | |
2332 | + } | |
2333 | + } | |
2334 | + | |
2335 | + if (new_bstart < 0) | |
2336 | + new_bstart = bindex; | |
2337 | + if (new_bend < 0) | |
2338 | + new_bend = bindex; | |
2339 | + dbstart(dentry) = new_bstart; | |
2340 | + dbend(dentry) = new_bend; | |
2341 | + | |
2342 | +} | |
2343 | + | |
2344 | +/* set lower inode ptr and update bstart & bend if necessary */ | |
2345 | +static void __set_inode(struct dentry *upper, struct dentry *lower, | |
2346 | + int bindex) | |
2347 | +{ | |
2348 | + unionfs_set_lower_inode_idx(upper->d_inode, bindex, | |
2349 | + igrab(lower->d_inode)); | |
2350 | + if (likely(ibstart(upper->d_inode) > bindex)) | |
2351 | + ibstart(upper->d_inode) = bindex; | |
2352 | + if (likely(ibend(upper->d_inode) < bindex)) | |
2353 | + ibend(upper->d_inode) = bindex; | |
2354 | + | |
2355 | +} | |
2356 | + | |
2357 | +/* set lower dentry ptr and update bstart & bend if necessary */ | |
2358 | +static void __set_dentry(struct dentry *upper, struct dentry *lower, | |
2359 | + int bindex) | |
2360 | +{ | |
2361 | + unionfs_set_lower_dentry_idx(upper, bindex, lower); | |
2362 | + if (likely(dbstart(upper) > bindex)) | |
2363 | + dbstart(upper) = bindex; | |
2364 | + if (likely(dbend(upper) < bindex)) | |
2365 | + dbend(upper) = bindex; | |
2366 | +} | |
2367 | + | |
2368 | +/* | |
2369 | + * This function replicates the directory structure up-to given dentry | |
2370 | + * in the bindex branch. | |
2371 | + */ | |
2372 | +struct dentry *create_parents(struct inode *dir, struct dentry *dentry, | |
2373 | + const char *name, int bindex) | |
2374 | +{ | |
2375 | + int err; | |
2376 | + struct dentry *child_dentry; | |
2377 | + struct dentry *parent_dentry; | |
2378 | + struct dentry *lower_parent_dentry = NULL; | |
2379 | + struct dentry *lower_dentry = NULL; | |
2380 | + const char *childname; | |
2381 | + unsigned int childnamelen; | |
2382 | + int nr_dentry; | |
2383 | + int count = 0; | |
2384 | + int old_bstart; | |
2385 | + int old_bend; | |
2386 | + struct dentry **path = NULL; | |
2387 | + struct super_block *sb; | |
2388 | + | |
2389 | + verify_locked(dentry); | |
2390 | + | |
2391 | + err = is_robranch_super(dir->i_sb, bindex); | |
2392 | + if (err) { | |
2393 | + lower_dentry = ERR_PTR(err); | |
2394 | + goto out; | |
2395 | + } | |
2396 | + | |
2397 | + old_bstart = dbstart(dentry); | |
2398 | + old_bend = dbend(dentry); | |
2399 | + | |
2400 | + lower_dentry = ERR_PTR(-ENOMEM); | |
2401 | + | |
2402 | + /* There is no sense allocating any less than the minimum. */ | |
2403 | + nr_dentry = 1; | |
2404 | + path = kmalloc(nr_dentry * sizeof(struct dentry *), GFP_KERNEL); | |
2405 | + if (unlikely(!path)) | |
2406 | + goto out; | |
2407 | + | |
2408 | + /* assume the negative dentry of unionfs as the parent dentry */ | |
2409 | + parent_dentry = dentry; | |
2410 | + | |
2411 | + /* | |
2412 | + * This loop finds the first parent that exists in the given branch. | |
2413 | + * We start building the directory structure from there. At the end | |
2414 | + * of the loop, the following should hold: | |
2415 | + * - child_dentry is the first nonexistent child | |
2416 | + * - parent_dentry is the first existent parent | |
2417 | + * - path[0] is the = deepest child | |
2418 | + * - path[count] is the first child to create | |
2419 | + */ | |
2420 | + do { | |
2421 | + child_dentry = parent_dentry; | |
2422 | + | |
2423 | + /* find the parent directory dentry in unionfs */ | |
2424 | + parent_dentry = dget_parent(child_dentry); | |
2425 | + | |
2426 | + /* find out the lower_parent_dentry in the given branch */ | |
2427 | + lower_parent_dentry = | |
2428 | + unionfs_lower_dentry_idx(parent_dentry, bindex); | |
2429 | + | |
2430 | + /* grow path table */ | |
2431 | + if (count == nr_dentry) { | |
2432 | + void *p; | |
2433 | + | |
2434 | + nr_dentry *= 2; | |
2435 | + p = krealloc(path, nr_dentry * sizeof(struct dentry *), | |
2436 | + GFP_KERNEL); | |
2437 | + if (unlikely(!p)) { | |
2438 | + lower_dentry = ERR_PTR(-ENOMEM); | |
2439 | + goto out; | |
2440 | + } | |
2441 | + path = p; | |
2442 | + } | |
2443 | + | |
2444 | + /* store the child dentry */ | |
2445 | + path[count++] = child_dentry; | |
2446 | + } while (!lower_parent_dentry); | |
2447 | + count--; | |
2448 | + | |
2449 | + sb = dentry->d_sb; | |
2450 | + | |
2451 | + /* | |
2452 | + * This code goes between the begin/end labels and basically | |
2453 | + * emulates a while(child_dentry != dentry), only cleaner and | |
2454 | + * shorter than what would be a much longer while loop. | |
2455 | + */ | |
2456 | +begin: | |
2457 | + /* get lower parent dir in the current branch */ | |
2458 | + lower_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex); | |
2459 | + dput(parent_dentry); | |
2460 | + | |
2461 | + /* init the values to lookup */ | |
2462 | + childname = child_dentry->d_name.name; | |
2463 | + childnamelen = child_dentry->d_name.len; | |
2464 | + | |
2465 | + if (child_dentry != dentry) { | |
2466 | + /* lookup child in the underlying file system */ | |
4ae1df7a | 2467 | + lower_dentry = lookup_lck_len(childname, lower_parent_dentry, |
2380c486 JR |
2468 | + childnamelen); |
2469 | + if (IS_ERR(lower_dentry)) | |
2470 | + goto out; | |
2471 | + } else { | |
2472 | + /* | |
2473 | + * Is the name a whiteout of the child name ? lookup the | |
2474 | + * whiteout child in the underlying file system | |
2475 | + */ | |
4ae1df7a | 2476 | + lower_dentry = lookup_lck_len(name, lower_parent_dentry, |
2380c486 JR |
2477 | + strlen(name)); |
2478 | + if (IS_ERR(lower_dentry)) | |
2479 | + goto out; | |
2480 | + | |
2481 | + /* Replace the current dentry (if any) with the new one */ | |
2482 | + dput(unionfs_lower_dentry_idx(dentry, bindex)); | |
2483 | + unionfs_set_lower_dentry_idx(dentry, bindex, | |
2484 | + lower_dentry); | |
2485 | + | |
2486 | + __cleanup_dentry(dentry, bindex, old_bstart, old_bend); | |
2487 | + goto out; | |
2488 | + } | |
2489 | + | |
2490 | + if (lower_dentry->d_inode) { | |
2491 | + /* | |
2492 | + * since this already exists we dput to avoid | |
2493 | + * multiple references on the same dentry | |
2494 | + */ | |
2495 | + dput(lower_dentry); | |
2496 | + } else { | |
2497 | + struct sioq_args args; | |
2498 | + | |
2499 | + /* it's a negative dentry, create a new dir */ | |
2500 | + lower_parent_dentry = lock_parent(lower_dentry); | |
2501 | + | |
2502 | + args.mkdir.parent = lower_parent_dentry->d_inode; | |
2503 | + args.mkdir.dentry = lower_dentry; | |
2504 | + args.mkdir.mode = child_dentry->d_inode->i_mode; | |
2505 | + | |
2506 | + run_sioq(__unionfs_mkdir, &args); | |
2507 | + err = args.err; | |
2508 | + | |
2509 | + if (!err) | |
2510 | + err = copyup_permissions(dir->i_sb, child_dentry, | |
2511 | + lower_dentry); | |
2512 | + unlock_dir(lower_parent_dentry); | |
2513 | + if (err) { | |
2514 | + dput(lower_dentry); | |
2515 | + lower_dentry = ERR_PTR(err); | |
2516 | + goto out; | |
2517 | + } | |
2518 | + | |
2519 | + } | |
2520 | + | |
2521 | + __set_inode(child_dentry, lower_dentry, bindex); | |
2522 | + __set_dentry(child_dentry, lower_dentry, bindex); | |
2523 | + /* | |
2524 | + * update times of this dentry, but also the parent, because if | |
2525 | + * we changed, the parent may have changed too. | |
2526 | + */ | |
2527 | + fsstack_copy_attr_times(parent_dentry->d_inode, | |
2528 | + lower_parent_dentry->d_inode); | |
2529 | + unionfs_copy_attr_times(child_dentry->d_inode); | |
2530 | + | |
2531 | + parent_dentry = child_dentry; | |
2532 | + child_dentry = path[--count]; | |
2533 | + goto begin; | |
2534 | +out: | |
2535 | + /* cleanup any leftover locks from the do/while loop above */ | |
2536 | + if (IS_ERR(lower_dentry)) | |
2537 | + while (count) | |
2538 | + dput(path[count--]); | |
2539 | + kfree(path); | |
2540 | + return lower_dentry; | |
2541 | +} | |
2542 | + | |
2543 | +/* | |
2544 | + * Post-copyup helper to ensure we have valid mnts: set lower mnt of | |
2545 | + * dentry+parents to the first parent node that has an mnt. | |
2546 | + */ | |
2547 | +void unionfs_postcopyup_setmnt(struct dentry *dentry) | |
2548 | +{ | |
2549 | + struct dentry *parent, *hasone; | |
2550 | + int bindex = dbstart(dentry); | |
2551 | + | |
2552 | + if (unionfs_lower_mnt_idx(dentry, bindex)) | |
2553 | + return; | |
2554 | + hasone = dentry->d_parent; | |
2555 | + /* this loop should stop at root dentry */ | |
2556 | + while (!unionfs_lower_mnt_idx(hasone, bindex)) | |
2557 | + hasone = hasone->d_parent; | |
2558 | + parent = dentry; | |
2559 | + while (!unionfs_lower_mnt_idx(parent, bindex)) { | |
2560 | + unionfs_set_lower_mnt_idx(parent, bindex, | |
2561 | + unionfs_mntget(hasone, bindex)); | |
2562 | + parent = parent->d_parent; | |
2563 | + } | |
2564 | +} | |
2565 | + | |
2566 | +/* | |
2567 | + * Post-copyup helper to release all non-directory source objects of a | |
2568 | + * copied-up file. Regular files should have only one lower object. | |
2569 | + */ | |
2570 | +void unionfs_postcopyup_release(struct dentry *dentry) | |
2571 | +{ | |
2572 | + int bstart, bend; | |
2573 | + | |
2574 | + BUG_ON(S_ISDIR(dentry->d_inode->i_mode)); | |
2575 | + bstart = dbstart(dentry); | |
2576 | + bend = dbend(dentry); | |
2577 | + | |
2578 | + path_put_lowers(dentry, bstart + 1, bend, false); | |
2579 | + iput_lowers(dentry->d_inode, bstart + 1, bend, false); | |
2580 | + | |
2581 | + dbend(dentry) = bstart; | |
2582 | + ibend(dentry->d_inode) = ibstart(dentry->d_inode) = bstart; | |
2583 | +} | |
0c5527e5 AM |
2584 | diff --git a/fs/unionfs/debug.c b/fs/unionfs/debug.c |
2585 | new file mode 100644 | |
92d182d2 | 2586 | index 0000000..21ce90c |
0c5527e5 AM |
2587 | --- /dev/null |
2588 | +++ b/fs/unionfs/debug.c | |
92d182d2 | 2589 | @@ -0,0 +1,551 @@ |
2380c486 | 2590 | +/* |
63b09289 | 2591 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 | 2592 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek |
63b09289 JR |
2593 | + * Copyright (c) 2003-2011 Stony Brook University |
2594 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
2595 | + * |
2596 | + * This program is free software; you can redistribute it and/or modify | |
2597 | + * it under the terms of the GNU General Public License version 2 as | |
2598 | + * published by the Free Software Foundation. | |
2599 | + */ | |
2600 | + | |
2601 | +#include "union.h" | |
92d182d2 | 2602 | +#include "../mount.h" |
2380c486 JR |
2603 | + |
2604 | +/* | |
2605 | + * Helper debugging functions for maintainers (and for users to report back | |
2606 | + * useful information back to maintainers) | |
2607 | + */ | |
2608 | + | |
2609 | +/* it's always useful to know what part of the code called us */ | |
2610 | +#define PRINT_CALLER(fname, fxn, line) \ | |
2611 | + do { \ | |
2612 | + if (!printed_caller) { \ | |
2613 | + pr_debug("PC:%s:%s:%d\n", (fname), (fxn), (line)); \ | |
2614 | + printed_caller = 1; \ | |
2615 | + } \ | |
2616 | + } while (0) | |
2617 | + | |
2618 | +/* | |
2619 | + * __unionfs_check_{inode,dentry,file} perform exhaustive sanity checking on | |
2620 | + * the fan-out of various Unionfs objects. We check that no lower objects | |
2621 | + * exist outside the start/end branch range; that all objects within are | |
2622 | + * non-NULL (with some allowed exceptions); that for every lower file | |
2623 | + * there's a lower dentry+inode; that the start/end ranges match for all | |
2624 | + * corresponding lower objects; that open files/symlinks have only one lower | |
2625 | + * objects, but directories can have several; and more. | |
2626 | + */ | |
2627 | +void __unionfs_check_inode(const struct inode *inode, | |
2628 | + const char *fname, const char *fxn, int line) | |
2629 | +{ | |
2630 | + int bindex; | |
2631 | + int istart, iend; | |
2632 | + struct inode *lower_inode; | |
2633 | + struct super_block *sb; | |
2634 | + int printed_caller = 0; | |
2635 | + void *poison_ptr; | |
2636 | + | |
2637 | + /* for inodes now */ | |
2638 | + BUG_ON(!inode); | |
2639 | + sb = inode->i_sb; | |
2640 | + istart = ibstart(inode); | |
2641 | + iend = ibend(inode); | |
2642 | + /* don't check inode if no lower branches */ | |
2643 | + if (istart < 0 && iend < 0) | |
2644 | + return; | |
2645 | + if (unlikely(istart > iend)) { | |
2646 | + PRINT_CALLER(fname, fxn, line); | |
2647 | + pr_debug(" Ci0: inode=%p istart/end=%d:%d\n", | |
2648 | + inode, istart, iend); | |
2649 | + } | |
2650 | + if (unlikely((istart == -1 && iend != -1) || | |
2651 | + (istart != -1 && iend == -1))) { | |
2652 | + PRINT_CALLER(fname, fxn, line); | |
2653 | + pr_debug(" Ci1: inode=%p istart/end=%d:%d\n", | |
2654 | + inode, istart, iend); | |
2655 | + } | |
2656 | + if (!S_ISDIR(inode->i_mode)) { | |
2657 | + if (unlikely(iend != istart)) { | |
2658 | + PRINT_CALLER(fname, fxn, line); | |
2659 | + pr_debug(" Ci2: inode=%p istart=%d iend=%d\n", | |
2660 | + inode, istart, iend); | |
2661 | + } | |
2662 | + } | |
2663 | + | |
2664 | + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { | |
2665 | + if (unlikely(!UNIONFS_I(inode))) { | |
2666 | + PRINT_CALLER(fname, fxn, line); | |
2667 | + pr_debug(" Ci3: no inode_info %p\n", inode); | |
2668 | + return; | |
2669 | + } | |
2670 | + if (unlikely(!UNIONFS_I(inode)->lower_inodes)) { | |
2671 | + PRINT_CALLER(fname, fxn, line); | |
2672 | + pr_debug(" Ci4: no lower_inodes %p\n", inode); | |
2673 | + return; | |
2674 | + } | |
2675 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
2676 | + if (lower_inode) { | |
2677 | + memset(&poison_ptr, POISON_INUSE, sizeof(void *)); | |
2678 | + if (unlikely(bindex < istart || bindex > iend)) { | |
2679 | + PRINT_CALLER(fname, fxn, line); | |
2680 | + pr_debug(" Ci5: inode/linode=%p:%p bindex=%d " | |
2681 | + "istart/end=%d:%d\n", inode, | |
2682 | + lower_inode, bindex, istart, iend); | |
2683 | + } else if (unlikely(lower_inode == poison_ptr)) { | |
2684 | + /* freed inode! */ | |
2685 | + PRINT_CALLER(fname, fxn, line); | |
2686 | + pr_debug(" Ci6: inode/linode=%p:%p bindex=%d " | |
2687 | + "istart/end=%d:%d\n", inode, | |
2688 | + lower_inode, bindex, istart, iend); | |
2689 | + } | |
2690 | + continue; | |
2691 | + } | |
2692 | + /* if we get here, then lower_inode == NULL */ | |
2693 | + if (bindex < istart || bindex > iend) | |
2694 | + continue; | |
2695 | + /* | |
2696 | + * directories can have NULL lower inodes in b/t start/end, | |
2697 | + * but NOT if at the start/end range. | |
2698 | + */ | |
2699 | + if (unlikely(S_ISDIR(inode->i_mode) && | |
2700 | + bindex > istart && bindex < iend)) | |
2701 | + continue; | |
2702 | + PRINT_CALLER(fname, fxn, line); | |
2703 | + pr_debug(" Ci7: inode/linode=%p:%p " | |
2704 | + "bindex=%d istart/end=%d:%d\n", | |
2705 | + inode, lower_inode, bindex, istart, iend); | |
2706 | + } | |
2707 | +} | |
2708 | + | |
2709 | +void __unionfs_check_dentry(const struct dentry *dentry, | |
2710 | + const char *fname, const char *fxn, int line) | |
2711 | +{ | |
2712 | + int bindex; | |
2713 | + int dstart, dend, istart, iend; | |
2714 | + struct dentry *lower_dentry; | |
2715 | + struct inode *inode, *lower_inode; | |
2716 | + struct super_block *sb; | |
2717 | + struct vfsmount *lower_mnt; | |
2718 | + int printed_caller = 0; | |
2719 | + void *poison_ptr; | |
2720 | + | |
2721 | + BUG_ON(!dentry); | |
2722 | + sb = dentry->d_sb; | |
2723 | + inode = dentry->d_inode; | |
2724 | + dstart = dbstart(dentry); | |
2725 | + dend = dbend(dentry); | |
2726 | + /* don't check dentry/mnt if no lower branches */ | |
2727 | + if (dstart < 0 && dend < 0) | |
2728 | + goto check_inode; | |
2729 | + BUG_ON(dstart > dend); | |
2730 | + | |
2731 | + if (unlikely((dstart == -1 && dend != -1) || | |
2732 | + (dstart != -1 && dend == -1))) { | |
2733 | + PRINT_CALLER(fname, fxn, line); | |
2734 | + pr_debug(" CD0: dentry=%p dstart/end=%d:%d\n", | |
2735 | + dentry, dstart, dend); | |
2736 | + } | |
2737 | + /* | |
2738 | + * check for NULL dentries inside the start/end range, or | |
2739 | + * non-NULL dentries outside the start/end range. | |
2740 | + */ | |
2741 | + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { | |
2742 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
2743 | + if (lower_dentry) { | |
2744 | + if (unlikely(bindex < dstart || bindex > dend)) { | |
2745 | + PRINT_CALLER(fname, fxn, line); | |
2746 | + pr_debug(" CD1: dentry/lower=%p:%p(%p) " | |
2747 | + "bindex=%d dstart/end=%d:%d\n", | |
2748 | + dentry, lower_dentry, | |
2749 | + (lower_dentry ? lower_dentry->d_inode : | |
2750 | + (void *) -1L), | |
2751 | + bindex, dstart, dend); | |
2752 | + } | |
2753 | + } else { /* lower_dentry == NULL */ | |
2754 | + if (bindex < dstart || bindex > dend) | |
2755 | + continue; | |
2756 | + /* | |
2757 | + * Directories can have NULL lower inodes in b/t | |
2758 | + * start/end, but NOT if at the start/end range. | |
2759 | + * Ignore this rule, however, if this is a NULL | |
2760 | + * dentry or a deleted dentry. | |
2761 | + */ | |
2762 | + if (unlikely(!d_deleted((struct dentry *) dentry) && | |
2763 | + inode && | |
2764 | + !(inode && S_ISDIR(inode->i_mode) && | |
2765 | + bindex > dstart && bindex < dend))) { | |
2766 | + PRINT_CALLER(fname, fxn, line); | |
2767 | + pr_debug(" CD2: dentry/lower=%p:%p(%p) " | |
2768 | + "bindex=%d dstart/end=%d:%d\n", | |
2769 | + dentry, lower_dentry, | |
2770 | + (lower_dentry ? | |
2771 | + lower_dentry->d_inode : | |
2772 | + (void *) -1L), | |
2773 | + bindex, dstart, dend); | |
2774 | + } | |
2775 | + } | |
2776 | + } | |
2777 | + | |
2778 | + /* check for vfsmounts same as for dentries */ | |
2779 | + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { | |
2780 | + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); | |
2781 | + if (lower_mnt) { | |
2782 | + if (unlikely(bindex < dstart || bindex > dend)) { | |
2783 | + PRINT_CALLER(fname, fxn, line); | |
2784 | + pr_debug(" CM0: dentry/lmnt=%p:%p bindex=%d " | |
2785 | + "dstart/end=%d:%d\n", dentry, | |
2786 | + lower_mnt, bindex, dstart, dend); | |
2787 | + } | |
2788 | + } else { /* lower_mnt == NULL */ | |
2789 | + if (bindex < dstart || bindex > dend) | |
2790 | + continue; | |
2791 | + /* | |
2792 | + * Directories can have NULL lower inodes in b/t | |
2793 | + * start/end, but NOT if at the start/end range. | |
2794 | + * Ignore this rule, however, if this is a NULL | |
2795 | + * dentry. | |
2796 | + */ | |
2797 | + if (unlikely(inode && | |
2798 | + !(inode && S_ISDIR(inode->i_mode) && | |
2799 | + bindex > dstart && bindex < dend))) { | |
2800 | + PRINT_CALLER(fname, fxn, line); | |
2801 | + pr_debug(" CM1: dentry/lmnt=%p:%p " | |
2802 | + "bindex=%d dstart/end=%d:%d\n", | |
2803 | + dentry, lower_mnt, bindex, | |
2804 | + dstart, dend); | |
2805 | + } | |
2806 | + } | |
2807 | + } | |
2808 | + | |
2809 | +check_inode: | |
2810 | + /* for inodes now */ | |
2811 | + if (!inode) | |
2812 | + return; | |
2813 | + istart = ibstart(inode); | |
2814 | + iend = ibend(inode); | |
2815 | + /* don't check inode if no lower branches */ | |
2816 | + if (istart < 0 && iend < 0) | |
2817 | + return; | |
2818 | + BUG_ON(istart > iend); | |
2819 | + if (unlikely((istart == -1 && iend != -1) || | |
2820 | + (istart != -1 && iend == -1))) { | |
2821 | + PRINT_CALLER(fname, fxn, line); | |
2822 | + pr_debug(" CI0: dentry/inode=%p:%p istart/end=%d:%d\n", | |
2823 | + dentry, inode, istart, iend); | |
2824 | + } | |
2825 | + if (unlikely(istart != dstart)) { | |
2826 | + PRINT_CALLER(fname, fxn, line); | |
2827 | + pr_debug(" CI1: dentry/inode=%p:%p istart=%d dstart=%d\n", | |
2828 | + dentry, inode, istart, dstart); | |
2829 | + } | |
2830 | + if (unlikely(iend != dend)) { | |
2831 | + PRINT_CALLER(fname, fxn, line); | |
2832 | + pr_debug(" CI2: dentry/inode=%p:%p iend=%d dend=%d\n", | |
2833 | + dentry, inode, iend, dend); | |
2834 | + } | |
2835 | + | |
2836 | + if (!S_ISDIR(inode->i_mode)) { | |
2837 | + if (unlikely(dend != dstart)) { | |
2838 | + PRINT_CALLER(fname, fxn, line); | |
2839 | + pr_debug(" CI3: dentry/inode=%p:%p dstart=%d dend=%d\n", | |
2840 | + dentry, inode, dstart, dend); | |
2841 | + } | |
2842 | + if (unlikely(iend != istart)) { | |
2843 | + PRINT_CALLER(fname, fxn, line); | |
2844 | + pr_debug(" CI4: dentry/inode=%p:%p istart=%d iend=%d\n", | |
2845 | + dentry, inode, istart, iend); | |
2846 | + } | |
2847 | + } | |
2848 | + | |
2849 | + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { | |
2850 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
2851 | + if (lower_inode) { | |
2852 | + memset(&poison_ptr, POISON_INUSE, sizeof(void *)); | |
2853 | + if (unlikely(bindex < istart || bindex > iend)) { | |
2854 | + PRINT_CALLER(fname, fxn, line); | |
2855 | + pr_debug(" CI5: dentry/linode=%p:%p bindex=%d " | |
2856 | + "istart/end=%d:%d\n", dentry, | |
2857 | + lower_inode, bindex, istart, iend); | |
2858 | + } else if (unlikely(lower_inode == poison_ptr)) { | |
2859 | + /* freed inode! */ | |
2860 | + PRINT_CALLER(fname, fxn, line); | |
2861 | + pr_debug(" CI6: dentry/linode=%p:%p bindex=%d " | |
2862 | + "istart/end=%d:%d\n", dentry, | |
2863 | + lower_inode, bindex, istart, iend); | |
2864 | + } | |
2865 | + continue; | |
2866 | + } | |
2867 | + /* if we get here, then lower_inode == NULL */ | |
2868 | + if (bindex < istart || bindex > iend) | |
2869 | + continue; | |
2870 | + /* | |
2871 | + * directories can have NULL lower inodes in b/t start/end, | |
2872 | + * but NOT if at the start/end range. | |
2873 | + */ | |
2874 | + if (unlikely(S_ISDIR(inode->i_mode) && | |
2875 | + bindex > istart && bindex < iend)) | |
2876 | + continue; | |
2877 | + PRINT_CALLER(fname, fxn, line); | |
2878 | + pr_debug(" CI7: dentry/linode=%p:%p " | |
2879 | + "bindex=%d istart/end=%d:%d\n", | |
2880 | + dentry, lower_inode, bindex, istart, iend); | |
2881 | + } | |
2882 | + | |
2883 | + /* | |
2884 | + * If it's a directory, then intermediate objects b/t start/end can | |
2885 | + * be NULL. But, check that all three are NULL: lower dentry, mnt, | |
2886 | + * and inode. | |
2887 | + */ | |
2888 | + if (dstart >= 0 && dend >= 0 && S_ISDIR(inode->i_mode)) | |
2889 | + for (bindex = dstart+1; bindex < dend; bindex++) { | |
2890 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
2891 | + lower_dentry = unionfs_lower_dentry_idx(dentry, | |
2892 | + bindex); | |
2893 | + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); | |
2894 | + if (unlikely(!((lower_inode && lower_dentry && | |
2895 | + lower_mnt) || | |
2896 | + (!lower_inode && | |
2897 | + !lower_dentry && !lower_mnt)))) { | |
2898 | + PRINT_CALLER(fname, fxn, line); | |
2899 | + pr_debug(" Cx: lmnt/ldentry/linode=%p:%p:%p " | |
2900 | + "bindex=%d dstart/end=%d:%d\n", | |
2901 | + lower_mnt, lower_dentry, lower_inode, | |
2902 | + bindex, dstart, dend); | |
2903 | + } | |
2904 | + } | |
2905 | + /* check if lower inode is newer than upper one (it shouldn't) */ | |
2906 | + if (unlikely(is_newer_lower(dentry) && !is_negative_lower(dentry))) { | |
2907 | + PRINT_CALLER(fname, fxn, line); | |
2908 | + for (bindex = ibstart(inode); bindex <= ibend(inode); | |
2909 | + bindex++) { | |
2910 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
2911 | + if (unlikely(!lower_inode)) | |
2912 | + continue; | |
2913 | + pr_debug(" CI8: bindex=%d mtime/lmtime=%lu.%lu/%lu.%lu " | |
2914 | + "ctime/lctime=%lu.%lu/%lu.%lu\n", | |
2915 | + bindex, | |
2916 | + inode->i_mtime.tv_sec, | |
2917 | + inode->i_mtime.tv_nsec, | |
2918 | + lower_inode->i_mtime.tv_sec, | |
2919 | + lower_inode->i_mtime.tv_nsec, | |
2920 | + inode->i_ctime.tv_sec, | |
2921 | + inode->i_ctime.tv_nsec, | |
2922 | + lower_inode->i_ctime.tv_sec, | |
2923 | + lower_inode->i_ctime.tv_nsec); | |
2924 | + } | |
2925 | + } | |
2926 | +} | |
2927 | + | |
2928 | +void __unionfs_check_file(const struct file *file, | |
2929 | + const char *fname, const char *fxn, int line) | |
2930 | +{ | |
2931 | + int bindex; | |
2932 | + int dstart, dend, fstart, fend; | |
2933 | + struct dentry *dentry; | |
2934 | + struct file *lower_file; | |
2935 | + struct inode *inode; | |
2936 | + struct super_block *sb; | |
2937 | + int printed_caller = 0; | |
2938 | + | |
2939 | + BUG_ON(!file); | |
2940 | + dentry = file->f_path.dentry; | |
2941 | + sb = dentry->d_sb; | |
2942 | + dstart = dbstart(dentry); | |
2943 | + dend = dbend(dentry); | |
2944 | + BUG_ON(dstart > dend); | |
2945 | + fstart = fbstart(file); | |
2946 | + fend = fbend(file); | |
2947 | + BUG_ON(fstart > fend); | |
2948 | + | |
2949 | + if (unlikely((fstart == -1 && fend != -1) || | |
2950 | + (fstart != -1 && fend == -1))) { | |
2951 | + PRINT_CALLER(fname, fxn, line); | |
2952 | + pr_debug(" CF0: file/dentry=%p:%p fstart/end=%d:%d\n", | |
2953 | + file, dentry, fstart, fend); | |
2954 | + } | |
6b53c3da AM |
2955 | + /* d_deleted dentries can be ignored for this test */ |
2956 | + if (unlikely(fstart != dstart) && !d_deleted(dentry)) { | |
2380c486 JR |
2957 | + PRINT_CALLER(fname, fxn, line); |
2958 | + pr_debug(" CF1: file/dentry=%p:%p fstart=%d dstart=%d\n", | |
2959 | + file, dentry, fstart, dstart); | |
2960 | + } | |
6b53c3da | 2961 | + if (unlikely(fend != dend) && !d_deleted(dentry)) { |
2380c486 JR |
2962 | + PRINT_CALLER(fname, fxn, line); |
2963 | + pr_debug(" CF2: file/dentry=%p:%p fend=%d dend=%d\n", | |
2964 | + file, dentry, fend, dend); | |
2965 | + } | |
2966 | + inode = dentry->d_inode; | |
2967 | + if (!S_ISDIR(inode->i_mode)) { | |
2968 | + if (unlikely(fend != fstart)) { | |
2969 | + PRINT_CALLER(fname, fxn, line); | |
2970 | + pr_debug(" CF3: file/inode=%p:%p fstart=%d fend=%d\n", | |
2971 | + file, inode, fstart, fend); | |
2972 | + } | |
2973 | + if (unlikely(dend != dstart)) { | |
2974 | + PRINT_CALLER(fname, fxn, line); | |
2975 | + pr_debug(" CF4: file/dentry=%p:%p dstart=%d dend=%d\n", | |
2976 | + file, dentry, dstart, dend); | |
2977 | + } | |
2978 | + } | |
2979 | + | |
2980 | + /* | |
2981 | + * check for NULL dentries inside the start/end range, or | |
2982 | + * non-NULL dentries outside the start/end range. | |
2983 | + */ | |
2984 | + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { | |
2985 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
2986 | + if (lower_file) { | |
2987 | + if (unlikely(bindex < fstart || bindex > fend)) { | |
2988 | + PRINT_CALLER(fname, fxn, line); | |
2989 | + pr_debug(" CF5: file/lower=%p:%p bindex=%d " | |
2990 | + "fstart/end=%d:%d\n", file, | |
2991 | + lower_file, bindex, fstart, fend); | |
2992 | + } | |
2993 | + } else { /* lower_file == NULL */ | |
2994 | + if (bindex >= fstart && bindex <= fend) { | |
2995 | + /* | |
2996 | + * directories can have NULL lower inodes in | |
2997 | + * b/t start/end, but NOT if at the | |
2998 | + * start/end range. | |
2999 | + */ | |
3000 | + if (unlikely(!(S_ISDIR(inode->i_mode) && | |
3001 | + bindex > fstart && | |
3002 | + bindex < fend))) { | |
3003 | + PRINT_CALLER(fname, fxn, line); | |
3004 | + pr_debug(" CF6: file/lower=%p:%p " | |
3005 | + "bindex=%d fstart/end=%d:%d\n", | |
3006 | + file, lower_file, bindex, | |
3007 | + fstart, fend); | |
3008 | + } | |
3009 | + } | |
3010 | + } | |
3011 | + } | |
3012 | + | |
3013 | + __unionfs_check_dentry(dentry, fname, fxn, line); | |
3014 | +} | |
3015 | + | |
3016 | +void __unionfs_check_nd(const struct nameidata *nd, | |
3017 | + const char *fname, const char *fxn, int line) | |
3018 | +{ | |
3019 | + struct file *file; | |
3020 | + int printed_caller = 0; | |
3021 | + | |
3022 | + if (unlikely(!nd)) | |
3023 | + return; | |
3024 | + if (nd->flags & LOOKUP_OPEN) { | |
3025 | + file = nd->intent.open.file; | |
3026 | + if (unlikely(file->f_path.dentry && | |
3027 | + strcmp(file->f_path.dentry->d_sb->s_type->name, | |
3028 | + UNIONFS_NAME))) { | |
3029 | + PRINT_CALLER(fname, fxn, line); | |
3030 | + pr_debug(" CND1: lower_file of type %s\n", | |
3031 | + file->f_path.dentry->d_sb->s_type->name); | |
2380c486 JR |
3032 | + } |
3033 | + } | |
3034 | +} | |
3035 | + | |
82260373 AM |
3036 | +static unsigned int __mnt_get_count(struct vfsmount *mnt) |
3037 | +{ | |
92d182d2 | 3038 | + struct mount *m = real_mount(mnt); |
82260373 AM |
3039 | +#ifdef CONFIG_SMP |
3040 | + unsigned int count = 0; | |
3041 | + int cpu; | |
3042 | + | |
3043 | + for_each_possible_cpu(cpu) { | |
92d182d2 | 3044 | + count += per_cpu_ptr(m->mnt_pcp, cpu)->mnt_count; |
82260373 AM |
3045 | + } |
3046 | + | |
3047 | + return count; | |
3048 | +#else | |
92d182d2 | 3049 | + return m->mnt_count; |
82260373 AM |
3050 | +#endif |
3051 | +} | |
3052 | + | |
2380c486 JR |
3053 | +/* useful to track vfsmount leaks that could cause EBUSY on unmount */ |
3054 | +void __show_branch_counts(const struct super_block *sb, | |
3055 | + const char *file, const char *fxn, int line) | |
3056 | +{ | |
3057 | + int i; | |
3058 | + struct vfsmount *mnt; | |
3059 | + | |
3060 | + pr_debug("BC:"); | |
3061 | + for (i = 0; i < sbmax(sb); i++) { | |
3062 | + if (likely(sb->s_root)) | |
3063 | + mnt = UNIONFS_D(sb->s_root)->lower_paths[i].mnt; | |
3064 | + else | |
3065 | + mnt = NULL; | |
3066 | + printk(KERN_CONT "%d:", | |
82260373 | 3067 | + (mnt ? __mnt_get_count(mnt) : -99)); |
2380c486 JR |
3068 | + } |
3069 | + printk(KERN_CONT "%s:%s:%d\n", file, fxn, line); | |
3070 | +} | |
3071 | + | |
3072 | +void __show_inode_times(const struct inode *inode, | |
3073 | + const char *file, const char *fxn, int line) | |
3074 | +{ | |
3075 | + struct inode *lower_inode; | |
3076 | + int bindex; | |
3077 | + | |
3078 | + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { | |
3079 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
3080 | + if (unlikely(!lower_inode)) | |
3081 | + continue; | |
3082 | + pr_debug("IT(%lu:%d): %s:%s:%d " | |
3083 | + "um=%lu/%lu lm=%lu/%lu uc=%lu/%lu lc=%lu/%lu\n", | |
3084 | + inode->i_ino, bindex, | |
3085 | + file, fxn, line, | |
3086 | + inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, | |
3087 | + lower_inode->i_mtime.tv_sec, | |
3088 | + lower_inode->i_mtime.tv_nsec, | |
3089 | + inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, | |
3090 | + lower_inode->i_ctime.tv_sec, | |
3091 | + lower_inode->i_ctime.tv_nsec); | |
3092 | + } | |
3093 | +} | |
3094 | + | |
3095 | +void __show_dinode_times(const struct dentry *dentry, | |
3096 | + const char *file, const char *fxn, int line) | |
3097 | +{ | |
3098 | + struct inode *inode = dentry->d_inode; | |
3099 | + struct inode *lower_inode; | |
3100 | + int bindex; | |
3101 | + | |
3102 | + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { | |
3103 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
3104 | + if (!lower_inode) | |
3105 | + continue; | |
3106 | + pr_debug("DT(%s:%lu:%d): %s:%s:%d " | |
3107 | + "um=%lu/%lu lm=%lu/%lu uc=%lu/%lu lc=%lu/%lu\n", | |
3108 | + dentry->d_name.name, inode->i_ino, bindex, | |
3109 | + file, fxn, line, | |
3110 | + inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, | |
3111 | + lower_inode->i_mtime.tv_sec, | |
3112 | + lower_inode->i_mtime.tv_nsec, | |
3113 | + inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, | |
3114 | + lower_inode->i_ctime.tv_sec, | |
3115 | + lower_inode->i_ctime.tv_nsec); | |
3116 | + } | |
3117 | +} | |
3118 | + | |
3119 | +void __show_inode_counts(const struct inode *inode, | |
3120 | + const char *file, const char *fxn, int line) | |
3121 | +{ | |
3122 | + struct inode *lower_inode; | |
3123 | + int bindex; | |
3124 | + | |
3125 | + if (unlikely(!inode)) { | |
3126 | + pr_debug("SiC: Null inode\n"); | |
3127 | + return; | |
3128 | + } | |
3129 | + for (bindex = sbstart(inode->i_sb); bindex <= sbend(inode->i_sb); | |
3130 | + bindex++) { | |
3131 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
3132 | + if (unlikely(!lower_inode)) | |
3133 | + continue; | |
3134 | + pr_debug("SIC(%lu:%d:%d): lc=%d %s:%s:%d\n", | |
3135 | + inode->i_ino, bindex, | |
3136 | + atomic_read(&(inode)->i_count), | |
3137 | + atomic_read(&(lower_inode)->i_count), | |
3138 | + file, fxn, line); | |
3139 | + } | |
3140 | +} | |
0c5527e5 AM |
3141 | diff --git a/fs/unionfs/dentry.c b/fs/unionfs/dentry.c |
3142 | new file mode 100644 | |
6b53c3da | 3143 | index 0000000..1628dad |
0c5527e5 AM |
3144 | --- /dev/null |
3145 | +++ b/fs/unionfs/dentry.c | |
6b53c3da | 3146 | @@ -0,0 +1,409 @@ |
2380c486 | 3147 | +/* |
63b09289 | 3148 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
3149 | + * Copyright (c) 2003-2006 Charles P. Wright |
3150 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
3151 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
3152 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
3153 | + * Copyright (c) 2004-2006 David P. Quigley | |
3154 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
3155 | + * Copyright (c) 2003 Puja Gupta | |
3156 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
3157 | + * Copyright (c) 2003-2011 Stony Brook University |
3158 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
3159 | + * |
3160 | + * This program is free software; you can redistribute it and/or modify | |
3161 | + * it under the terms of the GNU General Public License version 2 as | |
3162 | + * published by the Free Software Foundation. | |
3163 | + */ | |
3164 | + | |
3165 | +#include "union.h" | |
3166 | + | |
3167 | +bool is_negative_lower(const struct dentry *dentry) | |
3168 | +{ | |
3169 | + int bindex; | |
3170 | + struct dentry *lower_dentry; | |
3171 | + | |
3172 | + BUG_ON(!dentry); | |
3173 | + /* cache coherency: check if file was deleted on lower branch */ | |
3174 | + if (dbstart(dentry) < 0) | |
3175 | + return true; | |
3176 | + for (bindex = dbstart(dentry); bindex <= dbend(dentry); bindex++) { | |
3177 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
3178 | + /* unhashed (i.e., unlinked) lower dentries don't count */ | |
3179 | + if (lower_dentry && lower_dentry->d_inode && | |
3180 | + !d_deleted(lower_dentry) && | |
3181 | + !(lower_dentry->d_flags & DCACHE_NFSFS_RENAMED)) | |
3182 | + return false; | |
3183 | + } | |
3184 | + return true; | |
3185 | +} | |
3186 | + | |
3187 | +static inline void __dput_lowers(struct dentry *dentry, int start, int end) | |
3188 | +{ | |
3189 | + struct dentry *lower_dentry; | |
3190 | + int bindex; | |
3191 | + | |
3192 | + if (start < 0) | |
3193 | + return; | |
3194 | + for (bindex = start; bindex <= end; bindex++) { | |
3195 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
3196 | + if (!lower_dentry) | |
3197 | + continue; | |
3198 | + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); | |
3199 | + dput(lower_dentry); | |
3200 | + } | |
3201 | +} | |
3202 | + | |
3203 | +/* | |
3204 | + * Purge and invalidate as many data pages of a unionfs inode. This is | |
3205 | + * called when the lower inode has changed, and we want to force processes | |
3206 | + * to re-get the new data. | |
3207 | + */ | |
3208 | +static inline void purge_inode_data(struct inode *inode) | |
3209 | +{ | |
3210 | + /* remove all non-private mappings */ | |
3211 | + unmap_mapping_range(inode->i_mapping, 0, 0, 0); | |
3212 | + /* invalidate as many pages as possible */ | |
3213 | + invalidate_mapping_pages(inode->i_mapping, 0, -1); | |
3214 | + /* | |
3215 | + * Don't try to truncate_inode_pages here, because this could lead | |
3216 | + * to a deadlock between some of address_space ops and dentry | |
3217 | + * revalidation: the address space op is invoked with a lock on our | |
3218 | + * own page, and truncate_inode_pages will block on locked pages. | |
3219 | + */ | |
3220 | +} | |
3221 | + | |
3222 | +/* | |
3223 | + * Revalidate a single file/symlink/special dentry. Assume that info nodes | |
3224 | + * of the @dentry and its @parent are locked. Assume parent is valid, | |
3225 | + * otherwise return false (and let's hope the VFS will try to re-lookup this | |
3226 | + * dentry). Returns true if valid, false otherwise. | |
3227 | + */ | |
3228 | +bool __unionfs_d_revalidate(struct dentry *dentry, struct dentry *parent, | |
3229 | + bool willwrite) | |
3230 | +{ | |
3231 | + bool valid = true; /* default is valid */ | |
3232 | + struct dentry *lower_dentry; | |
3233 | + struct dentry *result; | |
3234 | + int bindex, bstart, bend; | |
3235 | + int sbgen, dgen, pdgen; | |
3236 | + int positive = 0; | |
3237 | + int interpose_flag; | |
3238 | + | |
3239 | + verify_locked(dentry); | |
3240 | + verify_locked(parent); | |
3241 | + | |
3242 | + /* if the dentry is unhashed, do NOT revalidate */ | |
3243 | + if (d_deleted(dentry)) | |
3244 | + goto out; | |
3245 | + | |
3246 | + dgen = atomic_read(&UNIONFS_D(dentry)->generation); | |
3247 | + | |
3248 | + if (is_newer_lower(dentry)) { | |
3249 | + /* root dentry is always valid */ | |
3250 | + if (IS_ROOT(dentry)) { | |
3251 | + unionfs_copy_attr_times(dentry->d_inode); | |
3252 | + } else { | |
3253 | + /* | |
3254 | + * reset generation number to zero, guaranteed to be | |
3255 | + * "old" | |
3256 | + */ | |
3257 | + dgen = 0; | |
3258 | + atomic_set(&UNIONFS_D(dentry)->generation, dgen); | |
3259 | + } | |
3260 | + if (!willwrite) | |
3261 | + purge_inode_data(dentry->d_inode); | |
3262 | + } | |
3263 | + | |
3264 | + sbgen = atomic_read(&UNIONFS_SB(dentry->d_sb)->generation); | |
3265 | + | |
3266 | + BUG_ON(dbstart(dentry) == -1); | |
3267 | + if (dentry->d_inode) | |
3268 | + positive = 1; | |
3269 | + | |
3270 | + /* if our dentry is valid, then validate all lower ones */ | |
3271 | + if (sbgen == dgen) | |
3272 | + goto validate_lowers; | |
3273 | + | |
3274 | + /* The root entry should always be valid */ | |
3275 | + BUG_ON(IS_ROOT(dentry)); | |
3276 | + | |
3277 | + /* We can't work correctly if our parent isn't valid. */ | |
3278 | + pdgen = atomic_read(&UNIONFS_D(parent)->generation); | |
3279 | + | |
3280 | + /* Free the pointers for our inodes and this dentry. */ | |
3281 | + path_put_lowers_all(dentry, false); | |
3282 | + | |
3283 | + interpose_flag = INTERPOSE_REVAL_NEG; | |
3284 | + if (positive) { | |
3285 | + interpose_flag = INTERPOSE_REVAL; | |
3286 | + iput_lowers_all(dentry->d_inode, true); | |
3287 | + } | |
3288 | + | |
3289 | + if (realloc_dentry_private_data(dentry) != 0) { | |
3290 | + valid = false; | |
3291 | + goto out; | |
3292 | + } | |
3293 | + | |
3294 | + result = unionfs_lookup_full(dentry, parent, interpose_flag); | |
3295 | + if (result) { | |
3296 | + if (IS_ERR(result)) { | |
3297 | + valid = false; | |
3298 | + goto out; | |
3299 | + } | |
3300 | + /* | |
3301 | + * current unionfs_lookup_backend() doesn't return | |
3302 | + * a valid dentry | |
3303 | + */ | |
3304 | + dput(dentry); | |
3305 | + dentry = result; | |
3306 | + } | |
3307 | + | |
3308 | + if (unlikely(positive && is_negative_lower(dentry))) { | |
3309 | + /* call make_bad_inode here ? */ | |
3310 | + d_drop(dentry); | |
3311 | + valid = false; | |
3312 | + goto out; | |
3313 | + } | |
3314 | + | |
3315 | + /* | |
3316 | + * if we got here then we have revalidated our dentry and all lower | |
3317 | + * ones, so we can return safely. | |
3318 | + */ | |
3319 | + if (!valid) /* lower dentry revalidation failed */ | |
3320 | + goto out; | |
3321 | + | |
3322 | + /* | |
3323 | + * If the parent's gen no. matches the superblock's gen no., then | |
3324 | + * we can update our denty's gen no. If they didn't match, then it | |
3325 | + * was OK to revalidate this dentry with a stale parent, but we'll | |
3326 | + * purposely not update our dentry's gen no. (so it can be redone); | |
3327 | + * and, we'll mark our parent dentry as invalid so it'll force it | |
3328 | + * (and our dentry) to be revalidated. | |
3329 | + */ | |
3330 | + if (pdgen == sbgen) | |
3331 | + atomic_set(&UNIONFS_D(dentry)->generation, sbgen); | |
3332 | + goto out; | |
3333 | + | |
3334 | +validate_lowers: | |
3335 | + | |
3336 | + /* The revalidation must occur across all branches */ | |
3337 | + bstart = dbstart(dentry); | |
3338 | + bend = dbend(dentry); | |
3339 | + BUG_ON(bstart == -1); | |
3340 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
63b09289 JR |
3341 | + int err; |
3342 | + struct nameidata lower_nd; | |
3343 | + | |
2380c486 JR |
3344 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); |
3345 | + if (!lower_dentry || !lower_dentry->d_op | |
3346 | + || !lower_dentry->d_op->d_revalidate) | |
3347 | + continue; | |
3348 | + /* | |
3349 | + * Don't pass nameidata to lower file system, because we | |
3350 | + * don't want an arbitrary lower file being opened or | |
3351 | + * returned to us: it may be useless to us because of the | |
3352 | + * fanout nature of unionfs (cf. file/directory open-file | |
3353 | + * invariants). We will open lower files as and when needed | |
3354 | + * later on. | |
3355 | + */ | |
63b09289 JR |
3356 | + err = init_lower_nd(&lower_nd, LOOKUP_OPEN); |
3357 | + if (unlikely(err < 0)) { | |
2380c486 | 3358 | + valid = false; |
63b09289 JR |
3359 | + break; |
3360 | + } | |
3361 | + if (!lower_dentry->d_op->d_revalidate(lower_dentry, &lower_nd)) | |
3362 | + valid = false; | |
3363 | + release_lower_nd(&lower_nd, err); | |
2380c486 JR |
3364 | + } |
3365 | + | |
3366 | + if (!dentry->d_inode || | |
3367 | + ibstart(dentry->d_inode) < 0 || | |
3368 | + ibend(dentry->d_inode) < 0) { | |
3369 | + valid = false; | |
3370 | + goto out; | |
3371 | + } | |
3372 | + | |
3373 | + if (valid) { | |
3374 | + /* | |
3375 | + * If we get here, and we copy the meta-data from the lower | |
3376 | + * inode to our inode, then it is vital that we have already | |
3377 | + * purged all unionfs-level file data. We do that in the | |
3378 | + * caller (__unionfs_d_revalidate) by calling | |
3379 | + * purge_inode_data. | |
3380 | + */ | |
3381 | + unionfs_copy_attr_all(dentry->d_inode, | |
3382 | + unionfs_lower_inode(dentry->d_inode)); | |
3383 | + fsstack_copy_inode_size(dentry->d_inode, | |
3384 | + unionfs_lower_inode(dentry->d_inode)); | |
3385 | + } | |
3386 | + | |
3387 | +out: | |
3388 | + return valid; | |
3389 | +} | |
3390 | + | |
3391 | +/* | |
3392 | + * Determine if the lower inode objects have changed from below the unionfs | |
3393 | + * inode. Return true if changed, false otherwise. | |
3394 | + * | |
3395 | + * We check if the mtime or ctime have changed. However, the inode times | |
3396 | + * can be changed by anyone without much protection, including | |
3397 | + * asynchronously. This can sometimes cause unionfs to find that the lower | |
3398 | + * file system doesn't change its inode times quick enough, resulting in a | |
3399 | + * false positive indication (which is harmless, it just makes unionfs do | |
3400 | + * extra work in re-validating the objects). To minimize the chances of | |
3401 | + * these situations, we still consider such small time changes valid, but we | |
3402 | + * don't print debugging messages unless the time changes are greater than | |
3403 | + * UNIONFS_MIN_CC_TIME (which defaults to 3 seconds, as with NFS's acregmin) | |
3404 | + * because significant changes are more likely due to users manually | |
3405 | + * touching lower files. | |
3406 | + */ | |
3407 | +bool is_newer_lower(const struct dentry *dentry) | |
3408 | +{ | |
3409 | + int bindex; | |
3410 | + struct inode *inode; | |
3411 | + struct inode *lower_inode; | |
3412 | + | |
3413 | + /* ignore if we're called on semi-initialized dentries/inodes */ | |
3414 | + if (!dentry || !UNIONFS_D(dentry)) | |
3415 | + return false; | |
3416 | + inode = dentry->d_inode; | |
3417 | + if (!inode || !UNIONFS_I(inode)->lower_inodes || | |
3418 | + ibstart(inode) < 0 || ibend(inode) < 0) | |
3419 | + return false; | |
3420 | + | |
3421 | + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { | |
3422 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
3423 | + if (!lower_inode) | |
3424 | + continue; | |
3425 | + | |
3426 | + /* check if mtime/ctime have changed */ | |
3427 | + if (unlikely(timespec_compare(&inode->i_mtime, | |
3428 | + &lower_inode->i_mtime) < 0)) { | |
3429 | + if ((lower_inode->i_mtime.tv_sec - | |
3430 | + inode->i_mtime.tv_sec) > UNIONFS_MIN_CC_TIME) { | |
3431 | + pr_info("unionfs: new lower inode mtime " | |
3432 | + "(bindex=%d, name=%s)\n", bindex, | |
3433 | + dentry->d_name.name); | |
3434 | + show_dinode_times(dentry); | |
3435 | + } | |
3436 | + return true; | |
3437 | + } | |
3438 | + if (unlikely(timespec_compare(&inode->i_ctime, | |
3439 | + &lower_inode->i_ctime) < 0)) { | |
3440 | + if ((lower_inode->i_ctime.tv_sec - | |
3441 | + inode->i_ctime.tv_sec) > UNIONFS_MIN_CC_TIME) { | |
3442 | + pr_info("unionfs: new lower inode ctime " | |
3443 | + "(bindex=%d, name=%s)\n", bindex, | |
3444 | + dentry->d_name.name); | |
3445 | + show_dinode_times(dentry); | |
3446 | + } | |
3447 | + return true; | |
3448 | + } | |
3449 | + } | |
3450 | + | |
3451 | + /* | |
3452 | + * Last check: if this is a positive dentry, but somehow all lower | |
3453 | + * dentries are negative or unhashed, then this dentry needs to be | |
3454 | + * revalidated, because someone probably deleted the objects from | |
3455 | + * the lower branches directly. | |
3456 | + */ | |
3457 | + if (is_negative_lower(dentry)) | |
3458 | + return true; | |
3459 | + | |
3460 | + return false; /* default: lower is not newer */ | |
3461 | +} | |
3462 | + | |
3463 | +static int unionfs_d_revalidate(struct dentry *dentry, | |
6b53c3da | 3464 | + struct nameidata *nd) |
2380c486 JR |
3465 | +{ |
3466 | + bool valid = true; | |
3467 | + int err = 1; /* 1 means valid for the VFS */ | |
3468 | + struct dentry *parent; | |
3469 | + | |
6b53c3da AM |
3470 | + if (nd && nd->flags & LOOKUP_RCU) |
3471 | + return -ECHILD; | |
3472 | + | |
2380c486 JR |
3473 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); |
3474 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
3475 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
3476 | + | |
3477 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
3478 | + if (valid) { | |
3479 | + unionfs_postcopyup_setmnt(dentry); | |
3480 | + unionfs_check_dentry(dentry); | |
3481 | + } else { | |
3482 | + d_drop(dentry); | |
3483 | + err = valid; | |
3484 | + } | |
3485 | + unionfs_unlock_dentry(dentry); | |
3486 | + unionfs_unlock_parent(dentry, parent); | |
3487 | + unionfs_read_unlock(dentry->d_sb); | |
3488 | + | |
3489 | + return err; | |
3490 | +} | |
3491 | + | |
3492 | +static void unionfs_d_release(struct dentry *dentry) | |
3493 | +{ | |
3494 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
3495 | + if (unlikely(!UNIONFS_D(dentry))) | |
3496 | + goto out; /* skip if no lower branches */ | |
3497 | + /* must lock our branch configuration here */ | |
3498 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
3499 | + | |
3500 | + unionfs_check_dentry(dentry); | |
3501 | + /* this could be a negative dentry, so check first */ | |
3502 | + if (dbstart(dentry) < 0) { | |
3503 | + unionfs_unlock_dentry(dentry); | |
3504 | + goto out; /* due to a (normal) failed lookup */ | |
3505 | + } | |
3506 | + | |
3507 | + /* Release all the lower dentries */ | |
3508 | + path_put_lowers_all(dentry, true); | |
3509 | + | |
3510 | + unionfs_unlock_dentry(dentry); | |
3511 | + | |
3512 | +out: | |
3513 | + free_dentry_private_data(dentry); | |
3514 | + unionfs_read_unlock(dentry->d_sb); | |
3515 | + return; | |
3516 | +} | |
3517 | + | |
3518 | +/* | |
3519 | + * Called when we're removing the last reference to our dentry. So we | |
3520 | + * should drop all lower references too. | |
3521 | + */ | |
3522 | +static void unionfs_d_iput(struct dentry *dentry, struct inode *inode) | |
3523 | +{ | |
3524 | + int rc; | |
3525 | + | |
3526 | + BUG_ON(!dentry); | |
3527 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
3528 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
3529 | + | |
3530 | + if (!UNIONFS_D(dentry) || dbstart(dentry) < 0) | |
3531 | + goto drop_lower_inodes; | |
3532 | + path_put_lowers_all(dentry, false); | |
3533 | + | |
3534 | +drop_lower_inodes: | |
3535 | + rc = atomic_read(&inode->i_count); | |
3536 | + if (rc == 1 && inode->i_nlink == 1 && ibstart(inode) >= 0) { | |
3537 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
3538 | + lockdep_off(); | |
3539 | + iput(unionfs_lower_inode(inode)); | |
3540 | + lockdep_on(); | |
3541 | + unionfs_set_lower_inode(inode, NULL); | |
3542 | + /* XXX: may need to set start/end to -1? */ | |
3543 | + } | |
3544 | + | |
3545 | + iput(inode); | |
3546 | + | |
3547 | + unionfs_unlock_dentry(dentry); | |
3548 | + unionfs_read_unlock(dentry->d_sb); | |
3549 | +} | |
3550 | + | |
3551 | +struct dentry_operations unionfs_dops = { | |
3552 | + .d_revalidate = unionfs_d_revalidate, | |
3553 | + .d_release = unionfs_d_release, | |
3554 | + .d_iput = unionfs_d_iput, | |
3555 | +}; | |
0c5527e5 AM |
3556 | diff --git a/fs/unionfs/dirfops.c b/fs/unionfs/dirfops.c |
3557 | new file mode 100644 | |
63b09289 | 3558 | index 0000000..72a9c1a |
0c5527e5 AM |
3559 | --- /dev/null |
3560 | +++ b/fs/unionfs/dirfops.c | |
2380c486 JR |
3561 | @@ -0,0 +1,302 @@ |
3562 | +/* | |
63b09289 | 3563 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
3564 | + * Copyright (c) 2003-2006 Charles P. Wright |
3565 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
3566 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
3567 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
3568 | + * Copyright (c) 2004-2006 David P. Quigley | |
3569 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
3570 | + * Copyright (c) 2003 Puja Gupta | |
3571 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
3572 | + * Copyright (c) 2003-2011 Stony Brook University |
3573 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
3574 | + * |
3575 | + * This program is free software; you can redistribute it and/or modify | |
3576 | + * it under the terms of the GNU General Public License version 2 as | |
3577 | + * published by the Free Software Foundation. | |
3578 | + */ | |
3579 | + | |
3580 | +#include "union.h" | |
3581 | + | |
3582 | +/* Make sure our rdstate is playing by the rules. */ | |
3583 | +static void verify_rdstate_offset(struct unionfs_dir_state *rdstate) | |
3584 | +{ | |
3585 | + BUG_ON(rdstate->offset >= DIREOF); | |
3586 | + BUG_ON(rdstate->cookie >= MAXRDCOOKIE); | |
3587 | +} | |
3588 | + | |
3589 | +struct unionfs_getdents_callback { | |
3590 | + struct unionfs_dir_state *rdstate; | |
3591 | + void *dirent; | |
3592 | + int entries_written; | |
3593 | + int filldir_called; | |
3594 | + int filldir_error; | |
3595 | + filldir_t filldir; | |
3596 | + struct super_block *sb; | |
3597 | +}; | |
3598 | + | |
3599 | +/* based on generic filldir in fs/readir.c */ | |
3600 | +static int unionfs_filldir(void *dirent, const char *oname, int namelen, | |
3601 | + loff_t offset, u64 ino, unsigned int d_type) | |
3602 | +{ | |
3603 | + struct unionfs_getdents_callback *buf = dirent; | |
3604 | + struct filldir_node *found = NULL; | |
3605 | + int err = 0; | |
3606 | + int is_whiteout; | |
3607 | + char *name = (char *) oname; | |
3608 | + | |
3609 | + buf->filldir_called++; | |
3610 | + | |
3611 | + is_whiteout = is_whiteout_name(&name, &namelen); | |
3612 | + | |
3613 | + found = find_filldir_node(buf->rdstate, name, namelen, is_whiteout); | |
3614 | + | |
3615 | + if (found) { | |
3616 | + /* | |
3617 | + * If we had non-whiteout entry in dir cache, then mark it | |
3618 | + * as a whiteout and but leave it in the dir cache. | |
3619 | + */ | |
3620 | + if (is_whiteout && !found->whiteout) | |
3621 | + found->whiteout = is_whiteout; | |
3622 | + goto out; | |
3623 | + } | |
3624 | + | |
3625 | + /* if 'name' isn't a whiteout, filldir it. */ | |
3626 | + if (!is_whiteout) { | |
3627 | + off_t pos = rdstate2offset(buf->rdstate); | |
3628 | + u64 unionfs_ino = ino; | |
3629 | + | |
3630 | + err = buf->filldir(buf->dirent, name, namelen, pos, | |
3631 | + unionfs_ino, d_type); | |
3632 | + buf->rdstate->offset++; | |
3633 | + verify_rdstate_offset(buf->rdstate); | |
3634 | + } | |
3635 | + /* | |
3636 | + * If we did fill it, stuff it in our hash, otherwise return an | |
3637 | + * error. | |
3638 | + */ | |
3639 | + if (err) { | |
3640 | + buf->filldir_error = err; | |
3641 | + goto out; | |
3642 | + } | |
3643 | + buf->entries_written++; | |
3644 | + err = add_filldir_node(buf->rdstate, name, namelen, | |
3645 | + buf->rdstate->bindex, is_whiteout); | |
3646 | + if (err) | |
3647 | + buf->filldir_error = err; | |
3648 | + | |
3649 | +out: | |
3650 | + return err; | |
3651 | +} | |
3652 | + | |
3653 | +static int unionfs_readdir(struct file *file, void *dirent, filldir_t filldir) | |
3654 | +{ | |
3655 | + int err = 0; | |
3656 | + struct file *lower_file = NULL; | |
3657 | + struct dentry *dentry = file->f_path.dentry; | |
3658 | + struct dentry *parent; | |
3659 | + struct inode *inode = NULL; | |
3660 | + struct unionfs_getdents_callback buf; | |
3661 | + struct unionfs_dir_state *uds; | |
3662 | + int bend; | |
3663 | + loff_t offset; | |
3664 | + | |
3665 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
3666 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
3667 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
3668 | + | |
3669 | + err = unionfs_file_revalidate(file, parent, false); | |
3670 | + if (unlikely(err)) | |
3671 | + goto out; | |
3672 | + | |
3673 | + inode = dentry->d_inode; | |
3674 | + | |
3675 | + uds = UNIONFS_F(file)->rdstate; | |
3676 | + if (!uds) { | |
3677 | + if (file->f_pos == DIREOF) { | |
3678 | + goto out; | |
3679 | + } else if (file->f_pos > 0) { | |
3680 | + uds = find_rdstate(inode, file->f_pos); | |
3681 | + if (unlikely(!uds)) { | |
3682 | + err = -ESTALE; | |
3683 | + goto out; | |
3684 | + } | |
3685 | + UNIONFS_F(file)->rdstate = uds; | |
3686 | + } else { | |
3687 | + init_rdstate(file); | |
3688 | + uds = UNIONFS_F(file)->rdstate; | |
3689 | + } | |
3690 | + } | |
3691 | + bend = fbend(file); | |
3692 | + | |
3693 | + while (uds->bindex <= bend) { | |
3694 | + lower_file = unionfs_lower_file_idx(file, uds->bindex); | |
3695 | + if (!lower_file) { | |
3696 | + uds->bindex++; | |
3697 | + uds->dirpos = 0; | |
3698 | + continue; | |
3699 | + } | |
3700 | + | |
3701 | + /* prepare callback buffer */ | |
3702 | + buf.filldir_called = 0; | |
3703 | + buf.filldir_error = 0; | |
3704 | + buf.entries_written = 0; | |
3705 | + buf.dirent = dirent; | |
3706 | + buf.filldir = filldir; | |
3707 | + buf.rdstate = uds; | |
3708 | + buf.sb = inode->i_sb; | |
3709 | + | |
3710 | + /* Read starting from where we last left off. */ | |
3711 | + offset = vfs_llseek(lower_file, uds->dirpos, SEEK_SET); | |
3712 | + if (offset < 0) { | |
3713 | + err = offset; | |
3714 | + goto out; | |
3715 | + } | |
3716 | + err = vfs_readdir(lower_file, unionfs_filldir, &buf); | |
3717 | + | |
3718 | + /* Save the position for when we continue. */ | |
3719 | + offset = vfs_llseek(lower_file, 0, SEEK_CUR); | |
3720 | + if (offset < 0) { | |
3721 | + err = offset; | |
3722 | + goto out; | |
3723 | + } | |
3724 | + uds->dirpos = offset; | |
3725 | + | |
3726 | + /* Copy the atime. */ | |
3727 | + fsstack_copy_attr_atime(inode, | |
3728 | + lower_file->f_path.dentry->d_inode); | |
3729 | + | |
3730 | + if (err < 0) | |
3731 | + goto out; | |
3732 | + | |
3733 | + if (buf.filldir_error) | |
3734 | + break; | |
3735 | + | |
3736 | + if (!buf.entries_written) { | |
3737 | + uds->bindex++; | |
3738 | + uds->dirpos = 0; | |
3739 | + } | |
3740 | + } | |
3741 | + | |
3742 | + if (!buf.filldir_error && uds->bindex >= bend) { | |
3743 | + /* Save the number of hash entries for next time. */ | |
3744 | + UNIONFS_I(inode)->hashsize = uds->hashentries; | |
3745 | + free_rdstate(uds); | |
3746 | + UNIONFS_F(file)->rdstate = NULL; | |
3747 | + file->f_pos = DIREOF; | |
3748 | + } else { | |
3749 | + file->f_pos = rdstate2offset(uds); | |
3750 | + } | |
3751 | + | |
3752 | +out: | |
3753 | + if (!err) | |
3754 | + unionfs_check_file(file); | |
3755 | + unionfs_unlock_dentry(dentry); | |
3756 | + unionfs_unlock_parent(dentry, parent); | |
3757 | + unionfs_read_unlock(dentry->d_sb); | |
3758 | + return err; | |
3759 | +} | |
3760 | + | |
3761 | +/* | |
3762 | + * This is not meant to be a generic repositioning function. If you do | |
3763 | + * things that aren't supported, then we return EINVAL. | |
3764 | + * | |
3765 | + * What is allowed: | |
3766 | + * (1) seeking to the same position that you are currently at | |
3767 | + * This really has no effect, but returns where you are. | |
3768 | + * (2) seeking to the beginning of the file | |
3769 | + * This throws out all state, and lets you begin again. | |
3770 | + */ | |
3771 | +static loff_t unionfs_dir_llseek(struct file *file, loff_t offset, int origin) | |
3772 | +{ | |
3773 | + struct unionfs_dir_state *rdstate; | |
3774 | + struct dentry *dentry = file->f_path.dentry; | |
3775 | + struct dentry *parent; | |
3776 | + loff_t err; | |
3777 | + | |
3778 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
3779 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
3780 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
3781 | + | |
3782 | + err = unionfs_file_revalidate(file, parent, false); | |
3783 | + if (unlikely(err)) | |
3784 | + goto out; | |
3785 | + | |
3786 | + rdstate = UNIONFS_F(file)->rdstate; | |
3787 | + | |
3788 | + /* | |
3789 | + * we let users seek to their current position, but not anywhere | |
3790 | + * else. | |
3791 | + */ | |
3792 | + if (!offset) { | |
3793 | + switch (origin) { | |
3794 | + case SEEK_SET: | |
3795 | + if (rdstate) { | |
3796 | + free_rdstate(rdstate); | |
3797 | + UNIONFS_F(file)->rdstate = NULL; | |
3798 | + } | |
3799 | + init_rdstate(file); | |
3800 | + err = 0; | |
3801 | + break; | |
3802 | + case SEEK_CUR: | |
3803 | + err = file->f_pos; | |
3804 | + break; | |
3805 | + case SEEK_END: | |
3806 | + /* Unsupported, because we would break everything. */ | |
3807 | + err = -EINVAL; | |
3808 | + break; | |
3809 | + } | |
3810 | + } else { | |
3811 | + switch (origin) { | |
3812 | + case SEEK_SET: | |
3813 | + if (rdstate) { | |
3814 | + if (offset == rdstate2offset(rdstate)) | |
3815 | + err = offset; | |
3816 | + else if (file->f_pos == DIREOF) | |
3817 | + err = DIREOF; | |
3818 | + else | |
3819 | + err = -EINVAL; | |
3820 | + } else { | |
3821 | + struct inode *inode; | |
3822 | + inode = dentry->d_inode; | |
3823 | + rdstate = find_rdstate(inode, offset); | |
3824 | + if (rdstate) { | |
3825 | + UNIONFS_F(file)->rdstate = rdstate; | |
3826 | + err = rdstate->offset; | |
3827 | + } else { | |
3828 | + err = -EINVAL; | |
3829 | + } | |
3830 | + } | |
3831 | + break; | |
3832 | + case SEEK_CUR: | |
3833 | + case SEEK_END: | |
3834 | + /* Unsupported, because we would break everything. */ | |
3835 | + err = -EINVAL; | |
3836 | + break; | |
3837 | + } | |
3838 | + } | |
3839 | + | |
3840 | +out: | |
3841 | + if (!err) | |
3842 | + unionfs_check_file(file); | |
3843 | + unionfs_unlock_dentry(dentry); | |
3844 | + unionfs_unlock_parent(dentry, parent); | |
3845 | + unionfs_read_unlock(dentry->d_sb); | |
3846 | + return err; | |
3847 | +} | |
3848 | + | |
3849 | +/* | |
3850 | + * Trimmed directory options, we shouldn't pass everything down since | |
3851 | + * we don't want to operate on partial directories. | |
3852 | + */ | |
3853 | +struct file_operations unionfs_dir_fops = { | |
3854 | + .llseek = unionfs_dir_llseek, | |
3855 | + .read = generic_read_dir, | |
3856 | + .readdir = unionfs_readdir, | |
3857 | + .unlocked_ioctl = unionfs_ioctl, | |
3858 | + .open = unionfs_open, | |
3859 | + .release = unionfs_file_release, | |
3860 | + .flush = unionfs_flush, | |
3861 | + .fsync = unionfs_fsync, | |
3862 | + .fasync = unionfs_fasync, | |
3863 | +}; | |
0c5527e5 AM |
3864 | diff --git a/fs/unionfs/dirhelper.c b/fs/unionfs/dirhelper.c |
3865 | new file mode 100644 | |
63b09289 | 3866 | index 0000000..62ec9af |
0c5527e5 AM |
3867 | --- /dev/null |
3868 | +++ b/fs/unionfs/dirhelper.c | |
2380c486 JR |
3869 | @@ -0,0 +1,158 @@ |
3870 | +/* | |
63b09289 | 3871 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
3872 | + * Copyright (c) 2003-2006 Charles P. Wright |
3873 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
3874 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
3875 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
3876 | + * Copyright (c) 2004-2006 David P. Quigley | |
3877 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
3878 | + * Copyright (c) 2003 Puja Gupta | |
3879 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
3880 | + * Copyright (c) 2003-2011 Stony Brook University |
3881 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
3882 | + * |
3883 | + * This program is free software; you can redistribute it and/or modify | |
3884 | + * it under the terms of the GNU General Public License version 2 as | |
3885 | + * published by the Free Software Foundation. | |
3886 | + */ | |
3887 | + | |
3888 | +#include "union.h" | |
3889 | + | |
3890 | +#define RD_NONE 0 | |
3891 | +#define RD_CHECK_EMPTY 1 | |
3892 | +/* The callback structure for check_empty. */ | |
3893 | +struct unionfs_rdutil_callback { | |
3894 | + int err; | |
3895 | + int filldir_called; | |
3896 | + struct unionfs_dir_state *rdstate; | |
3897 | + int mode; | |
3898 | +}; | |
3899 | + | |
3900 | +/* This filldir function makes sure only whiteouts exist within a directory. */ | |
3901 | +static int readdir_util_callback(void *dirent, const char *oname, int namelen, | |
3902 | + loff_t offset, u64 ino, unsigned int d_type) | |
3903 | +{ | |
3904 | + int err = 0; | |
3905 | + struct unionfs_rdutil_callback *buf = dirent; | |
3906 | + int is_whiteout; | |
3907 | + struct filldir_node *found; | |
3908 | + char *name = (char *) oname; | |
3909 | + | |
3910 | + buf->filldir_called = 1; | |
3911 | + | |
3912 | + if (name[0] == '.' && (namelen == 1 || | |
3913 | + (name[1] == '.' && namelen == 2))) | |
3914 | + goto out; | |
3915 | + | |
3916 | + is_whiteout = is_whiteout_name(&name, &namelen); | |
3917 | + | |
3918 | + found = find_filldir_node(buf->rdstate, name, namelen, is_whiteout); | |
3919 | + /* If it was found in the table there was a previous whiteout. */ | |
3920 | + if (found) | |
3921 | + goto out; | |
3922 | + | |
3923 | + /* | |
3924 | + * if it wasn't found and isn't a whiteout, the directory isn't | |
3925 | + * empty. | |
3926 | + */ | |
3927 | + err = -ENOTEMPTY; | |
3928 | + if ((buf->mode == RD_CHECK_EMPTY) && !is_whiteout) | |
3929 | + goto out; | |
3930 | + | |
3931 | + err = add_filldir_node(buf->rdstate, name, namelen, | |
3932 | + buf->rdstate->bindex, is_whiteout); | |
3933 | + | |
3934 | +out: | |
3935 | + buf->err = err; | |
3936 | + return err; | |
3937 | +} | |
3938 | + | |
3939 | +/* Is a directory logically empty? */ | |
3940 | +int check_empty(struct dentry *dentry, struct dentry *parent, | |
3941 | + struct unionfs_dir_state **namelist) | |
3942 | +{ | |
3943 | + int err = 0; | |
3944 | + struct dentry *lower_dentry = NULL; | |
3945 | + struct vfsmount *mnt; | |
3946 | + struct super_block *sb; | |
3947 | + struct file *lower_file; | |
3948 | + struct unionfs_rdutil_callback *buf = NULL; | |
3949 | + int bindex, bstart, bend, bopaque; | |
3950 | + | |
3951 | + sb = dentry->d_sb; | |
3952 | + | |
3953 | + | |
3954 | + BUG_ON(!S_ISDIR(dentry->d_inode->i_mode)); | |
3955 | + | |
3956 | + err = unionfs_partial_lookup(dentry, parent); | |
3957 | + if (err) | |
3958 | + goto out; | |
3959 | + | |
3960 | + bstart = dbstart(dentry); | |
3961 | + bend = dbend(dentry); | |
3962 | + bopaque = dbopaque(dentry); | |
3963 | + if (0 <= bopaque && bopaque < bend) | |
3964 | + bend = bopaque; | |
3965 | + | |
3966 | + buf = kmalloc(sizeof(struct unionfs_rdutil_callback), GFP_KERNEL); | |
3967 | + if (unlikely(!buf)) { | |
3968 | + err = -ENOMEM; | |
3969 | + goto out; | |
3970 | + } | |
3971 | + buf->err = 0; | |
3972 | + buf->mode = RD_CHECK_EMPTY; | |
3973 | + buf->rdstate = alloc_rdstate(dentry->d_inode, bstart); | |
3974 | + if (unlikely(!buf->rdstate)) { | |
3975 | + err = -ENOMEM; | |
3976 | + goto out; | |
3977 | + } | |
3978 | + | |
3979 | + /* Process the lower directories with rdutil_callback as a filldir. */ | |
3980 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
3981 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
3982 | + if (!lower_dentry) | |
3983 | + continue; | |
3984 | + if (!lower_dentry->d_inode) | |
3985 | + continue; | |
3986 | + if (!S_ISDIR(lower_dentry->d_inode->i_mode)) | |
3987 | + continue; | |
3988 | + | |
3989 | + dget(lower_dentry); | |
3990 | + mnt = unionfs_mntget(dentry, bindex); | |
3991 | + branchget(sb, bindex); | |
3992 | + lower_file = dentry_open(lower_dentry, mnt, O_RDONLY, current_cred()); | |
3993 | + if (IS_ERR(lower_file)) { | |
3994 | + err = PTR_ERR(lower_file); | |
3995 | + branchput(sb, bindex); | |
3996 | + goto out; | |
3997 | + } | |
3998 | + | |
3999 | + do { | |
4000 | + buf->filldir_called = 0; | |
4001 | + buf->rdstate->bindex = bindex; | |
4002 | + err = vfs_readdir(lower_file, | |
4003 | + readdir_util_callback, buf); | |
4004 | + if (buf->err) | |
4005 | + err = buf->err; | |
4006 | + } while ((err >= 0) && buf->filldir_called); | |
4007 | + | |
4008 | + /* fput calls dput for lower_dentry */ | |
4009 | + fput(lower_file); | |
4010 | + branchput(sb, bindex); | |
4011 | + | |
4012 | + if (err < 0) | |
4013 | + goto out; | |
4014 | + } | |
4015 | + | |
4016 | +out: | |
4017 | + if (buf) { | |
4018 | + if (namelist && !err) | |
4019 | + *namelist = buf->rdstate; | |
4020 | + else if (buf->rdstate) | |
4021 | + free_rdstate(buf->rdstate); | |
4022 | + kfree(buf); | |
4023 | + } | |
4024 | + | |
4025 | + | |
4026 | + return err; | |
4027 | +} | |
0c5527e5 AM |
4028 | diff --git a/fs/unionfs/fanout.h b/fs/unionfs/fanout.h |
4029 | new file mode 100644 | |
63b09289 | 4030 | index 0000000..ae1b86a |
0c5527e5 AM |
4031 | --- /dev/null |
4032 | +++ b/fs/unionfs/fanout.h | |
2380c486 JR |
4033 | @@ -0,0 +1,407 @@ |
4034 | +/* | |
63b09289 | 4035 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
4036 | + * Copyright (c) 2003-2006 Charles P. Wright |
4037 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
4038 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
4039 | + * Copyright (c) 2004-2006 David P. Quigley | |
4040 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
4041 | + * Copyright (c) 2003 Puja Gupta | |
4042 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
4043 | + * Copyright (c) 2003-2011 Stony Brook University |
4044 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
4045 | + * |
4046 | + * This program is free software; you can redistribute it and/or modify | |
4047 | + * it under the terms of the GNU General Public License version 2 as | |
4048 | + * published by the Free Software Foundation. | |
4049 | + */ | |
4050 | + | |
4051 | +#ifndef _FANOUT_H_ | |
4052 | +#define _FANOUT_H_ | |
4053 | + | |
4054 | +/* | |
4055 | + * Inode to private data | |
4056 | + * | |
4057 | + * Since we use containers and the struct inode is _inside_ the | |
4058 | + * unionfs_inode_info structure, UNIONFS_I will always (given a non-NULL | |
4059 | + * inode pointer), return a valid non-NULL pointer. | |
4060 | + */ | |
4061 | +static inline struct unionfs_inode_info *UNIONFS_I(const struct inode *inode) | |
4062 | +{ | |
4063 | + return container_of(inode, struct unionfs_inode_info, vfs_inode); | |
4064 | +} | |
4065 | + | |
4066 | +#define ibstart(ino) (UNIONFS_I(ino)->bstart) | |
4067 | +#define ibend(ino) (UNIONFS_I(ino)->bend) | |
4068 | + | |
4069 | +/* Dentry to private data */ | |
4070 | +#define UNIONFS_D(dent) ((struct unionfs_dentry_info *)(dent)->d_fsdata) | |
4071 | +#define dbstart(dent) (UNIONFS_D(dent)->bstart) | |
4072 | +#define dbend(dent) (UNIONFS_D(dent)->bend) | |
4073 | +#define dbopaque(dent) (UNIONFS_D(dent)->bopaque) | |
4074 | + | |
4075 | +/* Superblock to private data */ | |
4076 | +#define UNIONFS_SB(super) ((struct unionfs_sb_info *)(super)->s_fs_info) | |
4077 | +#define sbstart(sb) 0 | |
4078 | +#define sbend(sb) (UNIONFS_SB(sb)->bend) | |
4079 | +#define sbmax(sb) (UNIONFS_SB(sb)->bend + 1) | |
4080 | +#define sbhbid(sb) (UNIONFS_SB(sb)->high_branch_id) | |
4081 | + | |
4082 | +/* File to private Data */ | |
4083 | +#define UNIONFS_F(file) ((struct unionfs_file_info *)((file)->private_data)) | |
4084 | +#define fbstart(file) (UNIONFS_F(file)->bstart) | |
4085 | +#define fbend(file) (UNIONFS_F(file)->bend) | |
4086 | + | |
4087 | +/* macros to manipulate branch IDs in stored in our superblock */ | |
4088 | +static inline int branch_id(struct super_block *sb, int index) | |
4089 | +{ | |
4090 | + BUG_ON(!sb || index < 0); | |
4091 | + return UNIONFS_SB(sb)->data[index].branch_id; | |
4092 | +} | |
4093 | + | |
4094 | +static inline void set_branch_id(struct super_block *sb, int index, int val) | |
4095 | +{ | |
4096 | + BUG_ON(!sb || index < 0); | |
4097 | + UNIONFS_SB(sb)->data[index].branch_id = val; | |
4098 | +} | |
4099 | + | |
4100 | +static inline void new_branch_id(struct super_block *sb, int index) | |
4101 | +{ | |
4102 | + BUG_ON(!sb || index < 0); | |
4103 | + set_branch_id(sb, index, ++UNIONFS_SB(sb)->high_branch_id); | |
4104 | +} | |
4105 | + | |
4106 | +/* | |
4107 | + * Find new index of matching branch with an existing superblock of a known | |
4108 | + * (possibly old) id. This is needed because branches could have been | |
4109 | + * added/deleted causing the branches of any open files to shift. | |
4110 | + * | |
4111 | + * @sb: the new superblock which may have new/different branch IDs | |
4112 | + * @id: the old/existing id we're looking for | |
4113 | + * Returns index of newly found branch (0 or greater), -1 otherwise. | |
4114 | + */ | |
4115 | +static inline int branch_id_to_idx(struct super_block *sb, int id) | |
4116 | +{ | |
4117 | + int i; | |
4118 | + for (i = 0; i < sbmax(sb); i++) { | |
4119 | + if (branch_id(sb, i) == id) | |
4120 | + return i; | |
4121 | + } | |
4122 | + /* in the non-ODF code, this should really never happen */ | |
4123 | + printk(KERN_WARNING "unionfs: cannot find branch with id %d\n", id); | |
4124 | + return -1; | |
4125 | +} | |
4126 | + | |
4127 | +/* File to lower file. */ | |
4128 | +static inline struct file *unionfs_lower_file(const struct file *f) | |
4129 | +{ | |
4130 | + BUG_ON(!f); | |
4131 | + return UNIONFS_F(f)->lower_files[fbstart(f)]; | |
4132 | +} | |
4133 | + | |
4134 | +static inline struct file *unionfs_lower_file_idx(const struct file *f, | |
4135 | + int index) | |
4136 | +{ | |
4137 | + BUG_ON(!f || index < 0); | |
4138 | + return UNIONFS_F(f)->lower_files[index]; | |
4139 | +} | |
4140 | + | |
4141 | +static inline void unionfs_set_lower_file_idx(struct file *f, int index, | |
4142 | + struct file *val) | |
4143 | +{ | |
4144 | + BUG_ON(!f || index < 0); | |
4145 | + UNIONFS_F(f)->lower_files[index] = val; | |
4146 | + /* save branch ID (may be redundant?) */ | |
4147 | + UNIONFS_F(f)->saved_branch_ids[index] = | |
4148 | + branch_id((f)->f_path.dentry->d_sb, index); | |
4149 | +} | |
4150 | + | |
4151 | +static inline void unionfs_set_lower_file(struct file *f, struct file *val) | |
4152 | +{ | |
4153 | + BUG_ON(!f); | |
4154 | + unionfs_set_lower_file_idx((f), fbstart(f), (val)); | |
4155 | +} | |
4156 | + | |
4157 | +/* Inode to lower inode. */ | |
4158 | +static inline struct inode *unionfs_lower_inode(const struct inode *i) | |
4159 | +{ | |
4160 | + BUG_ON(!i); | |
4161 | + return UNIONFS_I(i)->lower_inodes[ibstart(i)]; | |
4162 | +} | |
4163 | + | |
4164 | +static inline struct inode *unionfs_lower_inode_idx(const struct inode *i, | |
4165 | + int index) | |
4166 | +{ | |
4167 | + BUG_ON(!i || index < 0); | |
4168 | + return UNIONFS_I(i)->lower_inodes[index]; | |
4169 | +} | |
4170 | + | |
4171 | +static inline void unionfs_set_lower_inode_idx(struct inode *i, int index, | |
4172 | + struct inode *val) | |
4173 | +{ | |
4174 | + BUG_ON(!i || index < 0); | |
4175 | + UNIONFS_I(i)->lower_inodes[index] = val; | |
4176 | +} | |
4177 | + | |
4178 | +static inline void unionfs_set_lower_inode(struct inode *i, struct inode *val) | |
4179 | +{ | |
4180 | + BUG_ON(!i); | |
4181 | + UNIONFS_I(i)->lower_inodes[ibstart(i)] = val; | |
4182 | +} | |
4183 | + | |
4184 | +/* Superblock to lower superblock. */ | |
4185 | +static inline struct super_block *unionfs_lower_super( | |
4186 | + const struct super_block *sb) | |
4187 | +{ | |
4188 | + BUG_ON(!sb); | |
4189 | + return UNIONFS_SB(sb)->data[sbstart(sb)].sb; | |
4190 | +} | |
4191 | + | |
4192 | +static inline struct super_block *unionfs_lower_super_idx( | |
4193 | + const struct super_block *sb, | |
4194 | + int index) | |
4195 | +{ | |
4196 | + BUG_ON(!sb || index < 0); | |
4197 | + return UNIONFS_SB(sb)->data[index].sb; | |
4198 | +} | |
4199 | + | |
4200 | +static inline void unionfs_set_lower_super_idx(struct super_block *sb, | |
4201 | + int index, | |
4202 | + struct super_block *val) | |
4203 | +{ | |
4204 | + BUG_ON(!sb || index < 0); | |
4205 | + UNIONFS_SB(sb)->data[index].sb = val; | |
4206 | +} | |
4207 | + | |
4208 | +static inline void unionfs_set_lower_super(struct super_block *sb, | |
4209 | + struct super_block *val) | |
4210 | +{ | |
4211 | + BUG_ON(!sb); | |
4212 | + UNIONFS_SB(sb)->data[sbstart(sb)].sb = val; | |
4213 | +} | |
4214 | + | |
4215 | +/* Branch count macros. */ | |
4216 | +static inline int branch_count(const struct super_block *sb, int index) | |
4217 | +{ | |
4218 | + BUG_ON(!sb || index < 0); | |
4219 | + return atomic_read(&UNIONFS_SB(sb)->data[index].open_files); | |
4220 | +} | |
4221 | + | |
4222 | +static inline void set_branch_count(struct super_block *sb, int index, int val) | |
4223 | +{ | |
4224 | + BUG_ON(!sb || index < 0); | |
4225 | + atomic_set(&UNIONFS_SB(sb)->data[index].open_files, val); | |
4226 | +} | |
4227 | + | |
4228 | +static inline void branchget(struct super_block *sb, int index) | |
4229 | +{ | |
4230 | + BUG_ON(!sb || index < 0); | |
4231 | + atomic_inc(&UNIONFS_SB(sb)->data[index].open_files); | |
4232 | +} | |
4233 | + | |
4234 | +static inline void branchput(struct super_block *sb, int index) | |
4235 | +{ | |
4236 | + BUG_ON(!sb || index < 0); | |
4237 | + atomic_dec(&UNIONFS_SB(sb)->data[index].open_files); | |
4238 | +} | |
4239 | + | |
4240 | +/* Dentry macros */ | |
4241 | +static inline void unionfs_set_lower_dentry_idx(struct dentry *dent, int index, | |
4242 | + struct dentry *val) | |
4243 | +{ | |
4244 | + BUG_ON(!dent || index < 0); | |
4245 | + UNIONFS_D(dent)->lower_paths[index].dentry = val; | |
4246 | +} | |
4247 | + | |
4248 | +static inline struct dentry *unionfs_lower_dentry_idx( | |
4249 | + const struct dentry *dent, | |
4250 | + int index) | |
4251 | +{ | |
4252 | + BUG_ON(!dent || index < 0); | |
4253 | + return UNIONFS_D(dent)->lower_paths[index].dentry; | |
4254 | +} | |
4255 | + | |
4256 | +static inline struct dentry *unionfs_lower_dentry(const struct dentry *dent) | |
4257 | +{ | |
4258 | + BUG_ON(!dent); | |
4259 | + return unionfs_lower_dentry_idx(dent, dbstart(dent)); | |
4260 | +} | |
4261 | + | |
4262 | +static inline void unionfs_set_lower_mnt_idx(struct dentry *dent, int index, | |
4263 | + struct vfsmount *mnt) | |
4264 | +{ | |
4265 | + BUG_ON(!dent || index < 0); | |
4266 | + UNIONFS_D(dent)->lower_paths[index].mnt = mnt; | |
4267 | +} | |
4268 | + | |
4269 | +static inline struct vfsmount *unionfs_lower_mnt_idx( | |
4270 | + const struct dentry *dent, | |
4271 | + int index) | |
4272 | +{ | |
4273 | + BUG_ON(!dent || index < 0); | |
4274 | + return UNIONFS_D(dent)->lower_paths[index].mnt; | |
4275 | +} | |
4276 | + | |
4277 | +static inline struct vfsmount *unionfs_lower_mnt(const struct dentry *dent) | |
4278 | +{ | |
4279 | + BUG_ON(!dent); | |
4280 | + return unionfs_lower_mnt_idx(dent, dbstart(dent)); | |
4281 | +} | |
4282 | + | |
4283 | +/* Macros for locking a dentry. */ | |
4284 | +enum unionfs_dentry_lock_class { | |
4285 | + UNIONFS_DMUTEX_NORMAL, | |
4286 | + UNIONFS_DMUTEX_ROOT, | |
4287 | + UNIONFS_DMUTEX_PARENT, | |
4288 | + UNIONFS_DMUTEX_CHILD, | |
4289 | + UNIONFS_DMUTEX_WHITEOUT, | |
4290 | + UNIONFS_DMUTEX_REVAL_PARENT, /* for file/dentry revalidate */ | |
4291 | + UNIONFS_DMUTEX_REVAL_CHILD, /* for file/dentry revalidate */ | |
4292 | +}; | |
4293 | + | |
4294 | +static inline void unionfs_lock_dentry(struct dentry *d, | |
4295 | + unsigned int subclass) | |
4296 | +{ | |
4297 | + BUG_ON(!d); | |
4298 | + mutex_lock_nested(&UNIONFS_D(d)->lock, subclass); | |
4299 | +} | |
4300 | + | |
4301 | +static inline void unionfs_unlock_dentry(struct dentry *d) | |
4302 | +{ | |
4303 | + BUG_ON(!d); | |
4304 | + mutex_unlock(&UNIONFS_D(d)->lock); | |
4305 | +} | |
4306 | + | |
4307 | +static inline struct dentry *unionfs_lock_parent(struct dentry *d, | |
4308 | + unsigned int subclass) | |
4309 | +{ | |
4310 | + struct dentry *p; | |
4311 | + | |
4312 | + BUG_ON(!d); | |
4313 | + p = dget_parent(d); | |
4314 | + if (p != d) | |
4315 | + mutex_lock_nested(&UNIONFS_D(p)->lock, subclass); | |
4316 | + return p; | |
4317 | +} | |
4318 | + | |
4319 | +static inline void unionfs_unlock_parent(struct dentry *d, struct dentry *p) | |
4320 | +{ | |
4321 | + BUG_ON(!d); | |
4322 | + BUG_ON(!p); | |
4323 | + if (p != d) { | |
4324 | + BUG_ON(!mutex_is_locked(&UNIONFS_D(p)->lock)); | |
4325 | + mutex_unlock(&UNIONFS_D(p)->lock); | |
4326 | + } | |
4327 | + dput(p); | |
4328 | +} | |
4329 | + | |
4330 | +static inline void verify_locked(struct dentry *d) | |
4331 | +{ | |
4332 | + BUG_ON(!d); | |
4333 | + BUG_ON(!mutex_is_locked(&UNIONFS_D(d)->lock)); | |
4334 | +} | |
4335 | + | |
4336 | +/* macros to put lower objects */ | |
4337 | + | |
4338 | +/* | |
4339 | + * iput lower inodes of an unionfs dentry, from bstart to bend. If | |
4340 | + * @free_lower is true, then also kfree the memory used to hold the lower | |
4341 | + * object pointers. | |
4342 | + */ | |
4343 | +static inline void iput_lowers(struct inode *inode, | |
4344 | + int bstart, int bend, bool free_lower) | |
4345 | +{ | |
4346 | + struct inode *lower_inode; | |
4347 | + int bindex; | |
4348 | + | |
4349 | + BUG_ON(!inode); | |
4350 | + BUG_ON(!UNIONFS_I(inode)); | |
4351 | + BUG_ON(bstart < 0); | |
4352 | + | |
4353 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
4354 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
4355 | + if (lower_inode) { | |
4356 | + unionfs_set_lower_inode_idx(inode, bindex, NULL); | |
4357 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
4358 | + lockdep_off(); | |
4359 | + iput(lower_inode); | |
4360 | + lockdep_on(); | |
4361 | + } | |
4362 | + } | |
4363 | + | |
4364 | + if (free_lower) { | |
4365 | + kfree(UNIONFS_I(inode)->lower_inodes); | |
4366 | + UNIONFS_I(inode)->lower_inodes = NULL; | |
4367 | + } | |
4368 | +} | |
4369 | + | |
4370 | +/* iput all lower inodes, and reset start/end branch indices to -1 */ | |
4371 | +static inline void iput_lowers_all(struct inode *inode, bool free_lower) | |
4372 | +{ | |
4373 | + int bstart, bend; | |
4374 | + | |
4375 | + BUG_ON(!inode); | |
4376 | + BUG_ON(!UNIONFS_I(inode)); | |
4377 | + bstart = ibstart(inode); | |
4378 | + bend = ibend(inode); | |
4379 | + BUG_ON(bstart < 0); | |
4380 | + | |
4381 | + iput_lowers(inode, bstart, bend, free_lower); | |
4382 | + ibstart(inode) = ibend(inode) = -1; | |
4383 | +} | |
4384 | + | |
4385 | +/* | |
4386 | + * dput/mntput all lower dentries and vfsmounts of an unionfs dentry, from | |
4387 | + * bstart to bend. If @free_lower is true, then also kfree the memory used | |
4388 | + * to hold the lower object pointers. | |
4389 | + * | |
4390 | + * XXX: implement using path_put VFS macros | |
4391 | + */ | |
4392 | +static inline void path_put_lowers(struct dentry *dentry, | |
4393 | + int bstart, int bend, bool free_lower) | |
4394 | +{ | |
4395 | + struct dentry *lower_dentry; | |
4396 | + struct vfsmount *lower_mnt; | |
4397 | + int bindex; | |
4398 | + | |
4399 | + BUG_ON(!dentry); | |
4400 | + BUG_ON(!UNIONFS_D(dentry)); | |
4401 | + BUG_ON(bstart < 0); | |
4402 | + | |
4403 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
4404 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
4405 | + if (lower_dentry) { | |
4406 | + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); | |
4407 | + dput(lower_dentry); | |
4408 | + } | |
4409 | + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); | |
4410 | + if (lower_mnt) { | |
4411 | + unionfs_set_lower_mnt_idx(dentry, bindex, NULL); | |
4412 | + mntput(lower_mnt); | |
4413 | + } | |
4414 | + } | |
4415 | + | |
4416 | + if (free_lower) { | |
4417 | + kfree(UNIONFS_D(dentry)->lower_paths); | |
4418 | + UNIONFS_D(dentry)->lower_paths = NULL; | |
4419 | + } | |
4420 | +} | |
4421 | + | |
4422 | +/* | |
4423 | + * dput/mntput all lower dentries and vfsmounts, and reset start/end branch | |
4424 | + * indices to -1. | |
4425 | + */ | |
4426 | +static inline void path_put_lowers_all(struct dentry *dentry, bool free_lower) | |
4427 | +{ | |
4428 | + int bstart, bend; | |
4429 | + | |
4430 | + BUG_ON(!dentry); | |
4431 | + BUG_ON(!UNIONFS_D(dentry)); | |
4432 | + bstart = dbstart(dentry); | |
4433 | + bend = dbend(dentry); | |
4434 | + BUG_ON(bstart < 0); | |
4435 | + | |
4436 | + path_put_lowers(dentry, bstart, bend, free_lower); | |
4437 | + dbstart(dentry) = dbend(dentry) = -1; | |
4438 | +} | |
4439 | + | |
4440 | +#endif /* not _FANOUT_H */ | |
0c5527e5 AM |
4441 | diff --git a/fs/unionfs/file.c b/fs/unionfs/file.c |
4442 | new file mode 100644 | |
6b53c3da | 4443 | index 0000000..f583c8f |
0c5527e5 AM |
4444 | --- /dev/null |
4445 | +++ b/fs/unionfs/file.c | |
6b53c3da | 4446 | @@ -0,0 +1,386 @@ |
2380c486 | 4447 | +/* |
63b09289 | 4448 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
4449 | + * Copyright (c) 2003-2006 Charles P. Wright |
4450 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
4451 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
4452 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
4453 | + * Copyright (c) 2004-2006 David P. Quigley | |
4454 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
4455 | + * Copyright (c) 2003 Puja Gupta | |
4456 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
4457 | + * Copyright (c) 2003-2011 Stony Brook University |
4458 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
4459 | + * |
4460 | + * This program is free software; you can redistribute it and/or modify | |
4461 | + * it under the terms of the GNU General Public License version 2 as | |
4462 | + * published by the Free Software Foundation. | |
4463 | + */ | |
4464 | + | |
4465 | +#include "union.h" | |
4466 | + | |
4467 | +static ssize_t unionfs_read(struct file *file, char __user *buf, | |
4468 | + size_t count, loff_t *ppos) | |
4469 | +{ | |
4470 | + int err; | |
4471 | + struct file *lower_file; | |
4472 | + struct dentry *dentry = file->f_path.dentry; | |
4473 | + struct dentry *parent; | |
4474 | + | |
4475 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
4476 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4477 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4478 | + | |
4479 | + err = unionfs_file_revalidate(file, parent, false); | |
4480 | + if (unlikely(err)) | |
4481 | + goto out; | |
4482 | + | |
4483 | + lower_file = unionfs_lower_file(file); | |
4484 | + err = vfs_read(lower_file, buf, count, ppos); | |
4485 | + /* update our inode atime upon a successful lower read */ | |
4486 | + if (err >= 0) { | |
4487 | + fsstack_copy_attr_atime(dentry->d_inode, | |
4488 | + lower_file->f_path.dentry->d_inode); | |
4489 | + unionfs_check_file(file); | |
4490 | + } | |
4491 | + | |
4492 | +out: | |
4493 | + unionfs_unlock_dentry(dentry); | |
4494 | + unionfs_unlock_parent(dentry, parent); | |
4495 | + unionfs_read_unlock(dentry->d_sb); | |
4496 | + return err; | |
4497 | +} | |
4498 | + | |
4499 | +static ssize_t unionfs_write(struct file *file, const char __user *buf, | |
4500 | + size_t count, loff_t *ppos) | |
4501 | +{ | |
4502 | + int err = 0; | |
4503 | + struct file *lower_file; | |
4504 | + struct dentry *dentry = file->f_path.dentry; | |
4505 | + struct dentry *parent; | |
4506 | + | |
4507 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
4508 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4509 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4510 | + | |
4511 | + err = unionfs_file_revalidate(file, parent, true); | |
4512 | + if (unlikely(err)) | |
4513 | + goto out; | |
4514 | + | |
4515 | + lower_file = unionfs_lower_file(file); | |
4516 | + err = vfs_write(lower_file, buf, count, ppos); | |
4517 | + /* update our inode times+sizes upon a successful lower write */ | |
4518 | + if (err >= 0) { | |
4519 | + fsstack_copy_inode_size(dentry->d_inode, | |
4520 | + lower_file->f_path.dentry->d_inode); | |
4521 | + fsstack_copy_attr_times(dentry->d_inode, | |
4522 | + lower_file->f_path.dentry->d_inode); | |
4523 | + UNIONFS_F(file)->wrote_to_file = true; /* for delayed copyup */ | |
4524 | + unionfs_check_file(file); | |
4525 | + } | |
4526 | + | |
4527 | +out: | |
4528 | + unionfs_unlock_dentry(dentry); | |
4529 | + unionfs_unlock_parent(dentry, parent); | |
4530 | + unionfs_read_unlock(dentry->d_sb); | |
4531 | + return err; | |
4532 | +} | |
4533 | + | |
4534 | +static int unionfs_file_readdir(struct file *file, void *dirent, | |
4535 | + filldir_t filldir) | |
4536 | +{ | |
4537 | + return -ENOTDIR; | |
4538 | +} | |
4539 | + | |
4540 | +static int unionfs_mmap(struct file *file, struct vm_area_struct *vma) | |
4541 | +{ | |
4542 | + int err = 0; | |
4543 | + bool willwrite; | |
4544 | + struct file *lower_file; | |
4545 | + struct dentry *dentry = file->f_path.dentry; | |
4546 | + struct dentry *parent; | |
7670a7fc | 4547 | + const struct vm_operations_struct *saved_vm_ops = NULL; |
2380c486 JR |
4548 | + |
4549 | + /* | |
4550 | + * Since mm/memory.c:might_fault() (under PROVE_LOCKING) was | |
4551 | + * modified in 2.6.29-rc1 to call might_lock_read on mmap_sem, this | |
4552 | + * has been causing false positives in file system stacking layers. | |
4553 | + * In particular, our ->mmap is called after sys_mmap2 already holds | |
4554 | + * mmap_sem, then we lock our own mutexes; but earlier, it's | |
4555 | + * possible for lockdep to have locked our mutexes first, and then | |
4556 | + * we call a lower ->readdir which could call might_fault. The | |
4557 | + * different ordering of the locks is what lockdep complains about | |
4558 | + * -- unnecessarily. Therefore, we have no choice but to tell | |
4559 | + * lockdep to temporarily turn off lockdep here. Note: the comments | |
4560 | + * inside might_sleep also suggest that it would have been | |
4561 | + * nicer to only annotate paths that needs that might_lock_read. | |
4562 | + */ | |
4563 | + lockdep_off(); | |
4564 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
4565 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4566 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4567 | + | |
4568 | + /* This might be deferred to mmap's writepage */ | |
4569 | + willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags); | |
4570 | + err = unionfs_file_revalidate(file, parent, willwrite); | |
4571 | + if (unlikely(err)) | |
4572 | + goto out; | |
4573 | + unionfs_check_file(file); | |
4574 | + | |
4575 | + /* | |
4576 | + * File systems which do not implement ->writepage may use | |
4577 | + * generic_file_readonly_mmap as their ->mmap op. If you call | |
4578 | + * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL. | |
4579 | + * But we cannot call the lower ->mmap op, so we can't tell that | |
4580 | + * writeable mappings won't work. Therefore, our only choice is to | |
4581 | + * check if the lower file system supports the ->writepage, and if | |
4582 | + * not, return EINVAL (the same error that | |
4583 | + * generic_file_readonly_mmap returns in that case). | |
4584 | + */ | |
4585 | + lower_file = unionfs_lower_file(file); | |
4586 | + if (willwrite && !lower_file->f_mapping->a_ops->writepage) { | |
4587 | + err = -EINVAL; | |
4588 | + printk(KERN_ERR "unionfs: branch %d file system does not " | |
4589 | + "support writeable mmap\n", fbstart(file)); | |
4590 | + goto out; | |
4591 | + } | |
4592 | + | |
4593 | + /* | |
4594 | + * find and save lower vm_ops. | |
4595 | + * | |
4596 | + * XXX: the VFS should have a cleaner way of finding the lower vm_ops | |
4597 | + */ | |
4598 | + if (!UNIONFS_F(file)->lower_vm_ops) { | |
4599 | + err = lower_file->f_op->mmap(lower_file, vma); | |
4600 | + if (err) { | |
4601 | + printk(KERN_ERR "unionfs: lower mmap failed %d\n", err); | |
4602 | + goto out; | |
4603 | + } | |
4604 | + saved_vm_ops = vma->vm_ops; | |
4605 | + err = do_munmap(current->mm, vma->vm_start, | |
4606 | + vma->vm_end - vma->vm_start); | |
4607 | + if (err) { | |
4608 | + printk(KERN_ERR "unionfs: do_munmap failed %d\n", err); | |
4609 | + goto out; | |
4610 | + } | |
4611 | + } | |
4612 | + | |
4613 | + file->f_mapping->a_ops = &unionfs_dummy_aops; | |
4614 | + err = generic_file_mmap(file, vma); | |
4615 | + file->f_mapping->a_ops = &unionfs_aops; | |
4616 | + if (err) { | |
4617 | + printk(KERN_ERR "unionfs: generic_file_mmap failed %d\n", err); | |
4618 | + goto out; | |
4619 | + } | |
4620 | + vma->vm_ops = &unionfs_vm_ops; | |
4621 | + if (!UNIONFS_F(file)->lower_vm_ops) | |
4622 | + UNIONFS_F(file)->lower_vm_ops = saved_vm_ops; | |
4623 | + | |
4624 | +out: | |
4625 | + if (!err) { | |
4626 | + /* copyup could cause parent dir times to change */ | |
4627 | + unionfs_copy_attr_times(parent->d_inode); | |
4628 | + unionfs_check_file(file); | |
4629 | + } | |
4630 | + unionfs_unlock_dentry(dentry); | |
4631 | + unionfs_unlock_parent(dentry, parent); | |
4632 | + unionfs_read_unlock(dentry->d_sb); | |
4633 | + lockdep_on(); | |
4634 | + return err; | |
4635 | +} | |
4636 | + | |
6b53c3da | 4637 | +int unionfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) |
2380c486 JR |
4638 | +{ |
4639 | + int bindex, bstart, bend; | |
4640 | + struct file *lower_file; | |
0c5527e5 | 4641 | + struct dentry *dentry = file->f_path.dentry; |
2380c486 JR |
4642 | + struct dentry *lower_dentry; |
4643 | + struct dentry *parent; | |
4644 | + struct inode *lower_inode, *inode; | |
4645 | + int err = -EINVAL; | |
4646 | + | |
6b53c3da | 4647 | + lockdep_off(); |
2380c486 JR |
4648 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); |
4649 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4650 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4651 | + | |
4652 | + err = unionfs_file_revalidate(file, parent, true); | |
4653 | + if (unlikely(err)) | |
4654 | + goto out; | |
4655 | + unionfs_check_file(file); | |
4656 | + | |
6b53c3da AM |
4657 | + err = generic_file_fsync(file, start, end, datasync); |
4658 | + if (err) | |
4659 | + goto out; | |
4660 | + | |
2380c486 JR |
4661 | + bstart = fbstart(file); |
4662 | + bend = fbend(file); | |
4663 | + if (bstart < 0 || bend < 0) | |
4664 | + goto out; | |
4665 | + | |
4666 | + inode = dentry->d_inode; | |
4667 | + if (unlikely(!inode)) { | |
4668 | + printk(KERN_ERR | |
4669 | + "unionfs: null lower inode in unionfs_fsync\n"); | |
4670 | + goto out; | |
4671 | + } | |
4672 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
4673 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
4674 | + if (!lower_inode || !lower_inode->i_fop->fsync) | |
4675 | + continue; | |
4676 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
4677 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
6b53c3da | 4678 | + err = vfs_fsync_range(lower_file, start, end, datasync); |
2380c486 JR |
4679 | + if (!err && bindex == bstart) |
4680 | + fsstack_copy_attr_times(inode, lower_inode); | |
2380c486 JR |
4681 | + if (err) |
4682 | + goto out; | |
4683 | + } | |
4684 | + | |
4685 | +out: | |
4686 | + if (!err) | |
4687 | + unionfs_check_file(file); | |
4688 | + unionfs_unlock_dentry(dentry); | |
4689 | + unionfs_unlock_parent(dentry, parent); | |
4690 | + unionfs_read_unlock(dentry->d_sb); | |
6b53c3da | 4691 | + lockdep_on(); |
2380c486 JR |
4692 | + return err; |
4693 | +} | |
4694 | + | |
4695 | +int unionfs_fasync(int fd, struct file *file, int flag) | |
4696 | +{ | |
4697 | + int bindex, bstart, bend; | |
4698 | + struct file *lower_file; | |
4699 | + struct dentry *dentry = file->f_path.dentry; | |
4700 | + struct dentry *parent; | |
4701 | + struct inode *lower_inode, *inode; | |
4702 | + int err = 0; | |
4703 | + | |
4704 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
4705 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4706 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4707 | + | |
4708 | + err = unionfs_file_revalidate(file, parent, true); | |
4709 | + if (unlikely(err)) | |
4710 | + goto out; | |
4711 | + unionfs_check_file(file); | |
4712 | + | |
4713 | + bstart = fbstart(file); | |
4714 | + bend = fbend(file); | |
4715 | + if (bstart < 0 || bend < 0) | |
4716 | + goto out; | |
4717 | + | |
4718 | + inode = dentry->d_inode; | |
4719 | + if (unlikely(!inode)) { | |
4720 | + printk(KERN_ERR | |
4721 | + "unionfs: null lower inode in unionfs_fasync\n"); | |
4722 | + goto out; | |
4723 | + } | |
4724 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
4725 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
4726 | + if (!lower_inode || !lower_inode->i_fop->fasync) | |
4727 | + continue; | |
4728 | + lower_file = unionfs_lower_file_idx(file, bindex); | |
4729 | + mutex_lock(&lower_inode->i_mutex); | |
4730 | + err = lower_inode->i_fop->fasync(fd, lower_file, flag); | |
4731 | + if (!err && bindex == bstart) | |
4732 | + fsstack_copy_attr_times(inode, lower_inode); | |
4733 | + mutex_unlock(&lower_inode->i_mutex); | |
4734 | + if (err) | |
4735 | + goto out; | |
4736 | + } | |
4737 | + | |
4738 | +out: | |
4739 | + if (!err) | |
4740 | + unionfs_check_file(file); | |
4741 | + unionfs_unlock_dentry(dentry); | |
4742 | + unionfs_unlock_parent(dentry, parent); | |
4743 | + unionfs_read_unlock(dentry->d_sb); | |
4744 | + return err; | |
4745 | +} | |
4746 | + | |
4747 | +static ssize_t unionfs_splice_read(struct file *file, loff_t *ppos, | |
4748 | + struct pipe_inode_info *pipe, size_t len, | |
4749 | + unsigned int flags) | |
4750 | +{ | |
4751 | + ssize_t err; | |
4752 | + struct file *lower_file; | |
4753 | + struct dentry *dentry = file->f_path.dentry; | |
4754 | + struct dentry *parent; | |
4755 | + | |
4756 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
4757 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4758 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4759 | + | |
4760 | + err = unionfs_file_revalidate(file, parent, false); | |
4761 | + if (unlikely(err)) | |
4762 | + goto out; | |
4763 | + | |
4764 | + lower_file = unionfs_lower_file(file); | |
4765 | + err = vfs_splice_to(lower_file, ppos, pipe, len, flags); | |
4766 | + /* update our inode atime upon a successful lower splice-read */ | |
4767 | + if (err >= 0) { | |
4768 | + fsstack_copy_attr_atime(dentry->d_inode, | |
4769 | + lower_file->f_path.dentry->d_inode); | |
4770 | + unionfs_check_file(file); | |
4771 | + } | |
4772 | + | |
4773 | +out: | |
4774 | + unionfs_unlock_dentry(dentry); | |
4775 | + unionfs_unlock_parent(dentry, parent); | |
4776 | + unionfs_read_unlock(dentry->d_sb); | |
4777 | + return err; | |
4778 | +} | |
4779 | + | |
4780 | +static ssize_t unionfs_splice_write(struct pipe_inode_info *pipe, | |
4781 | + struct file *file, loff_t *ppos, | |
4782 | + size_t len, unsigned int flags) | |
4783 | +{ | |
4784 | + ssize_t err = 0; | |
4785 | + struct file *lower_file; | |
4786 | + struct dentry *dentry = file->f_path.dentry; | |
4787 | + struct dentry *parent; | |
4788 | + | |
4789 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); | |
4790 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4791 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4792 | + | |
4793 | + err = unionfs_file_revalidate(file, parent, true); | |
4794 | + if (unlikely(err)) | |
4795 | + goto out; | |
4796 | + | |
4797 | + lower_file = unionfs_lower_file(file); | |
4798 | + err = vfs_splice_from(pipe, lower_file, ppos, len, flags); | |
4799 | + /* update our inode times+sizes upon a successful lower write */ | |
4800 | + if (err >= 0) { | |
4801 | + fsstack_copy_inode_size(dentry->d_inode, | |
4802 | + lower_file->f_path.dentry->d_inode); | |
4803 | + fsstack_copy_attr_times(dentry->d_inode, | |
4804 | + lower_file->f_path.dentry->d_inode); | |
4805 | + unionfs_check_file(file); | |
4806 | + } | |
4807 | + | |
4808 | +out: | |
4809 | + unionfs_unlock_dentry(dentry); | |
4810 | + unionfs_unlock_parent(dentry, parent); | |
4811 | + unionfs_read_unlock(dentry->d_sb); | |
4812 | + return err; | |
4813 | +} | |
4814 | + | |
4815 | +struct file_operations unionfs_main_fops = { | |
4816 | + .llseek = generic_file_llseek, | |
4817 | + .read = unionfs_read, | |
4818 | + .write = unionfs_write, | |
4819 | + .readdir = unionfs_file_readdir, | |
4820 | + .unlocked_ioctl = unionfs_ioctl, | |
0c5527e5 AM |
4821 | +#ifdef CONFIG_COMPAT |
4822 | + .compat_ioctl = unionfs_ioctl, | |
4823 | +#endif | |
2380c486 JR |
4824 | + .mmap = unionfs_mmap, |
4825 | + .open = unionfs_open, | |
4826 | + .flush = unionfs_flush, | |
4827 | + .release = unionfs_file_release, | |
4828 | + .fsync = unionfs_fsync, | |
4829 | + .fasync = unionfs_fasync, | |
4830 | + .splice_read = unionfs_splice_read, | |
4831 | + .splice_write = unionfs_splice_write, | |
4832 | +}; | |
0c5527e5 AM |
4833 | diff --git a/fs/unionfs/inode.c b/fs/unionfs/inode.c |
4834 | new file mode 100644 | |
92d182d2 | 4835 | index 0000000..dd522c2 |
0c5527e5 AM |
4836 | --- /dev/null |
4837 | +++ b/fs/unionfs/inode.c | |
f6c5ef8b | 4838 | @@ -0,0 +1,1085 @@ |
2380c486 | 4839 | +/* |
63b09289 | 4840 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
4841 | + * Copyright (c) 2003-2006 Charles P. Wright |
4842 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
4843 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
4844 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
4845 | + * Copyright (c) 2004-2006 David P. Quigley | |
4846 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
4847 | + * Copyright (c) 2003 Puja Gupta | |
4848 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
4849 | + * Copyright (c) 2003-2011 Stony Brook University |
4850 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
4851 | + * |
4852 | + * This program is free software; you can redistribute it and/or modify | |
4853 | + * it under the terms of the GNU General Public License version 2 as | |
4854 | + * published by the Free Software Foundation. | |
4855 | + */ | |
4856 | + | |
4857 | +#include "union.h" | |
4858 | + | |
4859 | +/* | |
4860 | + * Find a writeable branch to create new object in. Checks all writeble | |
4861 | + * branches of the parent inode, from istart to iend order; if none are | |
4862 | + * suitable, also tries branch 0 (which may require a copyup). | |
4863 | + * | |
4864 | + * Return a lower_dentry we can use to create object in, or ERR_PTR. | |
4865 | + */ | |
4866 | +static struct dentry *find_writeable_branch(struct inode *parent, | |
4867 | + struct dentry *dentry) | |
4868 | +{ | |
4869 | + int err = -EINVAL; | |
4870 | + int bindex, istart, iend; | |
4871 | + struct dentry *lower_dentry = NULL; | |
4872 | + | |
4873 | + istart = ibstart(parent); | |
4874 | + iend = ibend(parent); | |
4875 | + if (istart < 0) | |
4876 | + goto out; | |
4877 | + | |
4878 | +begin: | |
4879 | + for (bindex = istart; bindex <= iend; bindex++) { | |
4880 | + /* skip non-writeable branches */ | |
4881 | + err = is_robranch_super(dentry->d_sb, bindex); | |
4882 | + if (err) { | |
4883 | + err = -EROFS; | |
4884 | + continue; | |
4885 | + } | |
4886 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
4887 | + if (!lower_dentry) | |
4888 | + continue; | |
4889 | + /* | |
4890 | + * check for whiteouts in writeable branch, and remove them | |
4891 | + * if necessary. | |
4892 | + */ | |
4893 | + err = check_unlink_whiteout(dentry, lower_dentry, bindex); | |
4894 | + if (err > 0) /* ignore if whiteout found and removed */ | |
4895 | + err = 0; | |
4896 | + if (err) | |
4897 | + continue; | |
4898 | + /* if get here, we can write to the branch */ | |
4899 | + break; | |
4900 | + } | |
4901 | + /* | |
4902 | + * If istart wasn't already branch 0, and we got any error, then try | |
4903 | + * branch 0 (which may require copyup) | |
4904 | + */ | |
4905 | + if (err && istart > 0) { | |
4906 | + istart = iend = 0; | |
4907 | + goto begin; | |
4908 | + } | |
4909 | + | |
4910 | + /* | |
4911 | + * If we tried even branch 0, and still got an error, abort. But if | |
4912 | + * the error was an EROFS, then we should try to copyup. | |
4913 | + */ | |
4914 | + if (err && err != -EROFS) | |
4915 | + goto out; | |
4916 | + | |
4917 | + /* | |
4918 | + * If we get here, then check if copyup needed. If lower_dentry is | |
4919 | + * NULL, create the entire dentry directory structure in branch 0. | |
4920 | + */ | |
4921 | + if (!lower_dentry) { | |
4922 | + bindex = 0; | |
4923 | + lower_dentry = create_parents(parent, dentry, | |
4924 | + dentry->d_name.name, bindex); | |
4925 | + if (IS_ERR(lower_dentry)) { | |
4926 | + err = PTR_ERR(lower_dentry); | |
4927 | + goto out; | |
4928 | + } | |
4929 | + } | |
4930 | + err = 0; /* all's well */ | |
4931 | +out: | |
4932 | + if (err) | |
4933 | + return ERR_PTR(err); | |
4934 | + return lower_dentry; | |
4935 | +} | |
4936 | + | |
4937 | +static int unionfs_create(struct inode *dir, struct dentry *dentry, | |
92d182d2 | 4938 | + umode_t mode, struct nameidata *nd_unused) |
2380c486 JR |
4939 | +{ |
4940 | + int err = 0; | |
4941 | + struct dentry *lower_dentry = NULL; | |
4942 | + struct dentry *lower_parent_dentry = NULL; | |
4943 | + struct dentry *parent; | |
4944 | + int valid = 0; | |
4945 | + struct nameidata lower_nd; | |
4946 | + | |
4947 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
4948 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
4949 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
4950 | + | |
4951 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
4952 | + if (unlikely(!valid)) { | |
4953 | + err = -ESTALE; /* same as what real_lookup does */ | |
4954 | + goto out; | |
4955 | + } | |
4956 | + | |
4957 | + lower_dentry = find_writeable_branch(dir, dentry); | |
4958 | + if (IS_ERR(lower_dentry)) { | |
4959 | + err = PTR_ERR(lower_dentry); | |
4960 | + goto out; | |
4961 | + } | |
4962 | + | |
4963 | + lower_parent_dentry = lock_parent(lower_dentry); | |
4964 | + if (IS_ERR(lower_parent_dentry)) { | |
4965 | + err = PTR_ERR(lower_parent_dentry); | |
7670a7fc | 4966 | + goto out_unlock; |
2380c486 JR |
4967 | + } |
4968 | + | |
4969 | + err = init_lower_nd(&lower_nd, LOOKUP_CREATE); | |
4970 | + if (unlikely(err < 0)) | |
7670a7fc | 4971 | + goto out_unlock; |
2380c486 JR |
4972 | + err = vfs_create(lower_parent_dentry->d_inode, lower_dentry, mode, |
4973 | + &lower_nd); | |
4974 | + release_lower_nd(&lower_nd, err); | |
4975 | + | |
4976 | + if (!err) { | |
4977 | + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); | |
4978 | + if (!err) { | |
4979 | + unionfs_copy_attr_times(dir); | |
4980 | + fsstack_copy_inode_size(dir, | |
4981 | + lower_parent_dentry->d_inode); | |
4982 | + /* update no. of links on parent directory */ | |
f4ea99f3 | 4983 | + set_nlink(dir, unionfs_get_nlinks(dir)); |
2380c486 JR |
4984 | + } |
4985 | + } | |
4986 | + | |
7670a7fc | 4987 | +out_unlock: |
2380c486 | 4988 | + unlock_dir(lower_parent_dentry); |
2380c486 JR |
4989 | +out: |
4990 | + if (!err) { | |
4991 | + unionfs_postcopyup_setmnt(dentry); | |
4992 | + unionfs_check_inode(dir); | |
4993 | + unionfs_check_dentry(dentry); | |
4994 | + } | |
4995 | + unionfs_unlock_dentry(dentry); | |
4996 | + unionfs_unlock_parent(dentry, parent); | |
4997 | + unionfs_read_unlock(dentry->d_sb); | |
4998 | + return err; | |
4999 | +} | |
5000 | + | |
5001 | +/* | |
5002 | + * unionfs_lookup is the only special function which takes a dentry, yet we | |
5003 | + * do NOT want to call __unionfs_d_revalidate_chain because by definition, | |
5004 | + * we don't have a valid dentry here yet. | |
5005 | + */ | |
5006 | +static struct dentry *unionfs_lookup(struct inode *dir, | |
5007 | + struct dentry *dentry, | |
5008 | + struct nameidata *nd_unused) | |
5009 | +{ | |
5010 | + struct dentry *ret, *parent; | |
5011 | + int err = 0; | |
5012 | + | |
5013 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5014 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5015 | + | |
5016 | + /* | |
5017 | + * As long as we lock/dget the parent, then can skip validating the | |
5018 | + * parent now; we may have to rebuild this dentry on the next | |
5019 | + * ->d_revalidate, however. | |
5020 | + */ | |
5021 | + | |
5022 | + /* allocate dentry private data. We free it in ->d_release */ | |
5023 | + err = new_dentry_private_data(dentry, UNIONFS_DMUTEX_CHILD); | |
5024 | + if (unlikely(err)) { | |
5025 | + ret = ERR_PTR(err); | |
5026 | + goto out; | |
5027 | + } | |
5028 | + | |
5029 | + ret = unionfs_lookup_full(dentry, parent, INTERPOSE_LOOKUP); | |
5030 | + | |
5031 | + if (!IS_ERR(ret)) { | |
5032 | + if (ret) | |
5033 | + dentry = ret; | |
5034 | + /* lookup_full can return multiple positive dentries */ | |
5035 | + if (dentry->d_inode && !S_ISDIR(dentry->d_inode->i_mode)) { | |
5036 | + BUG_ON(dbstart(dentry) < 0); | |
5037 | + unionfs_postcopyup_release(dentry); | |
5038 | + } | |
5039 | + unionfs_copy_attr_times(dentry->d_inode); | |
5040 | + } | |
5041 | + | |
5042 | + unionfs_check_inode(dir); | |
5043 | + if (!IS_ERR(ret)) | |
5044 | + unionfs_check_dentry(dentry); | |
5045 | + unionfs_check_dentry(parent); | |
5046 | + unionfs_unlock_dentry(dentry); /* locked in new_dentry_private data */ | |
5047 | + | |
5048 | +out: | |
5049 | + unionfs_unlock_parent(dentry, parent); | |
5050 | + unionfs_read_unlock(dentry->d_sb); | |
5051 | + | |
5052 | + return ret; | |
5053 | +} | |
5054 | + | |
5055 | +static int unionfs_link(struct dentry *old_dentry, struct inode *dir, | |
5056 | + struct dentry *new_dentry) | |
5057 | +{ | |
5058 | + int err = 0; | |
5059 | + struct dentry *lower_old_dentry = NULL; | |
5060 | + struct dentry *lower_new_dentry = NULL; | |
5061 | + struct dentry *lower_dir_dentry = NULL; | |
5062 | + struct dentry *old_parent, *new_parent; | |
5063 | + char *name = NULL; | |
5064 | + bool valid; | |
5065 | + | |
5066 | + unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5067 | + old_parent = dget_parent(old_dentry); | |
5068 | + new_parent = dget_parent(new_dentry); | |
5069 | + unionfs_double_lock_parents(old_parent, new_parent); | |
5070 | + unionfs_double_lock_dentry(old_dentry, new_dentry); | |
5071 | + | |
5072 | + valid = __unionfs_d_revalidate(old_dentry, old_parent, false); | |
5073 | + if (unlikely(!valid)) { | |
5074 | + err = -ESTALE; | |
5075 | + goto out; | |
5076 | + } | |
5077 | + if (new_dentry->d_inode) { | |
5078 | + valid = __unionfs_d_revalidate(new_dentry, new_parent, false); | |
5079 | + if (unlikely(!valid)) { | |
5080 | + err = -ESTALE; | |
5081 | + goto out; | |
5082 | + } | |
5083 | + } | |
5084 | + | |
5085 | + lower_new_dentry = unionfs_lower_dentry(new_dentry); | |
5086 | + | |
5087 | + /* check for a whiteout in new dentry branch, and delete it */ | |
5088 | + err = check_unlink_whiteout(new_dentry, lower_new_dentry, | |
5089 | + dbstart(new_dentry)); | |
5090 | + if (err > 0) { /* whiteout found and removed successfully */ | |
5091 | + lower_dir_dentry = dget_parent(lower_new_dentry); | |
5092 | + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); | |
5093 | + dput(lower_dir_dentry); | |
f4ea99f3 | 5094 | + set_nlink(dir, unionfs_get_nlinks(dir)); |
2380c486 JR |
5095 | + err = 0; |
5096 | + } | |
5097 | + if (err) | |
5098 | + goto out; | |
5099 | + | |
5100 | + /* check if parent hierachy is needed, then link in same branch */ | |
5101 | + if (dbstart(old_dentry) != dbstart(new_dentry)) { | |
5102 | + lower_new_dentry = create_parents(dir, new_dentry, | |
5103 | + new_dentry->d_name.name, | |
5104 | + dbstart(old_dentry)); | |
5105 | + err = PTR_ERR(lower_new_dentry); | |
5106 | + if (IS_COPYUP_ERR(err)) | |
5107 | + goto docopyup; | |
5108 | + if (!lower_new_dentry || IS_ERR(lower_new_dentry)) | |
5109 | + goto out; | |
5110 | + } | |
5111 | + lower_new_dentry = unionfs_lower_dentry(new_dentry); | |
5112 | + lower_old_dentry = unionfs_lower_dentry(old_dentry); | |
5113 | + | |
5114 | + BUG_ON(dbstart(old_dentry) != dbstart(new_dentry)); | |
5115 | + lower_dir_dentry = lock_parent(lower_new_dentry); | |
5116 | + err = is_robranch(old_dentry); | |
5117 | + if (!err) { | |
5118 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
5119 | + lockdep_off(); | |
5120 | + err = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode, | |
5121 | + lower_new_dentry); | |
5122 | + lockdep_on(); | |
5123 | + } | |
5124 | + unlock_dir(lower_dir_dentry); | |
5125 | + | |
5126 | +docopyup: | |
5127 | + if (IS_COPYUP_ERR(err)) { | |
5128 | + int old_bstart = dbstart(old_dentry); | |
5129 | + int bindex; | |
5130 | + | |
5131 | + for (bindex = old_bstart - 1; bindex >= 0; bindex--) { | |
5132 | + err = copyup_dentry(old_parent->d_inode, | |
5133 | + old_dentry, old_bstart, | |
5134 | + bindex, old_dentry->d_name.name, | |
5135 | + old_dentry->d_name.len, NULL, | |
5136 | + i_size_read(old_dentry->d_inode)); | |
5137 | + if (err) | |
5138 | + continue; | |
5139 | + lower_new_dentry = | |
5140 | + create_parents(dir, new_dentry, | |
5141 | + new_dentry->d_name.name, | |
5142 | + bindex); | |
5143 | + lower_old_dentry = unionfs_lower_dentry(old_dentry); | |
5144 | + lower_dir_dentry = lock_parent(lower_new_dentry); | |
5145 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
5146 | + lockdep_off(); | |
5147 | + /* do vfs_link */ | |
5148 | + err = vfs_link(lower_old_dentry, | |
5149 | + lower_dir_dentry->d_inode, | |
5150 | + lower_new_dentry); | |
5151 | + lockdep_on(); | |
5152 | + unlock_dir(lower_dir_dentry); | |
5153 | + goto check_link; | |
5154 | + } | |
5155 | + goto out; | |
5156 | + } | |
5157 | + | |
5158 | +check_link: | |
5159 | + if (err || !lower_new_dentry->d_inode) | |
5160 | + goto out; | |
5161 | + | |
5162 | + /* Its a hard link, so use the same inode */ | |
5163 | + new_dentry->d_inode = igrab(old_dentry->d_inode); | |
5164 | + d_add(new_dentry, new_dentry->d_inode); | |
5165 | + unionfs_copy_attr_all(dir, lower_new_dentry->d_parent->d_inode); | |
5166 | + fsstack_copy_inode_size(dir, lower_new_dentry->d_parent->d_inode); | |
5167 | + | |
5168 | + /* propagate number of hard-links */ | |
f6c5ef8b AM |
5169 | + set_nlink(old_dentry->d_inode, |
5170 | + unionfs_get_nlinks(old_dentry->d_inode)); | |
2380c486 JR |
5171 | + /* new dentry's ctime may have changed due to hard-link counts */ |
5172 | + unionfs_copy_attr_times(new_dentry->d_inode); | |
5173 | + | |
5174 | +out: | |
5175 | + if (!new_dentry->d_inode) | |
5176 | + d_drop(new_dentry); | |
5177 | + | |
5178 | + kfree(name); | |
5179 | + if (!err) | |
5180 | + unionfs_postcopyup_setmnt(new_dentry); | |
5181 | + | |
5182 | + unionfs_check_inode(dir); | |
5183 | + unionfs_check_dentry(new_dentry); | |
5184 | + unionfs_check_dentry(old_dentry); | |
5185 | + | |
5186 | + unionfs_double_unlock_dentry(old_dentry, new_dentry); | |
5187 | + unionfs_double_unlock_parents(old_parent, new_parent); | |
5188 | + dput(new_parent); | |
5189 | + dput(old_parent); | |
5190 | + unionfs_read_unlock(old_dentry->d_sb); | |
5191 | + | |
5192 | + return err; | |
5193 | +} | |
5194 | + | |
5195 | +static int unionfs_symlink(struct inode *dir, struct dentry *dentry, | |
5196 | + const char *symname) | |
5197 | +{ | |
5198 | + int err = 0; | |
5199 | + struct dentry *lower_dentry = NULL; | |
5200 | + struct dentry *wh_dentry = NULL; | |
5201 | + struct dentry *lower_parent_dentry = NULL; | |
5202 | + struct dentry *parent; | |
5203 | + char *name = NULL; | |
5204 | + int valid = 0; | |
5205 | + umode_t mode; | |
5206 | + | |
5207 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5208 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5209 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5210 | + | |
5211 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
5212 | + if (unlikely(!valid)) { | |
5213 | + err = -ESTALE; | |
5214 | + goto out; | |
5215 | + } | |
5216 | + | |
5217 | + /* | |
5218 | + * It's only a bug if this dentry was not negative and couldn't be | |
5219 | + * revalidated (shouldn't happen). | |
5220 | + */ | |
5221 | + BUG_ON(!valid && dentry->d_inode); | |
5222 | + | |
5223 | + lower_dentry = find_writeable_branch(dir, dentry); | |
5224 | + if (IS_ERR(lower_dentry)) { | |
5225 | + err = PTR_ERR(lower_dentry); | |
5226 | + goto out; | |
5227 | + } | |
5228 | + | |
5229 | + lower_parent_dentry = lock_parent(lower_dentry); | |
5230 | + if (IS_ERR(lower_parent_dentry)) { | |
5231 | + err = PTR_ERR(lower_parent_dentry); | |
7670a7fc | 5232 | + goto out_unlock; |
2380c486 JR |
5233 | + } |
5234 | + | |
5235 | + mode = S_IALLUGO; | |
5236 | + err = vfs_symlink(lower_parent_dentry->d_inode, lower_dentry, symname); | |
5237 | + if (!err) { | |
5238 | + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); | |
5239 | + if (!err) { | |
5240 | + unionfs_copy_attr_times(dir); | |
5241 | + fsstack_copy_inode_size(dir, | |
5242 | + lower_parent_dentry->d_inode); | |
5243 | + /* update no. of links on parent directory */ | |
1b6fc39e | 5244 | + set_nlink(dir, unionfs_get_nlinks(dir)); |
2380c486 JR |
5245 | + } |
5246 | + } | |
5247 | + | |
7670a7fc | 5248 | +out_unlock: |
2380c486 | 5249 | + unlock_dir(lower_parent_dentry); |
2380c486 JR |
5250 | +out: |
5251 | + dput(wh_dentry); | |
5252 | + kfree(name); | |
5253 | + | |
5254 | + if (!err) { | |
5255 | + unionfs_postcopyup_setmnt(dentry); | |
5256 | + unionfs_check_inode(dir); | |
5257 | + unionfs_check_dentry(dentry); | |
5258 | + } | |
5259 | + unionfs_unlock_dentry(dentry); | |
5260 | + unionfs_unlock_parent(dentry, parent); | |
5261 | + unionfs_read_unlock(dentry->d_sb); | |
5262 | + return err; | |
5263 | +} | |
5264 | + | |
92d182d2 | 5265 | +static int unionfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) |
2380c486 JR |
5266 | +{ |
5267 | + int err = 0; | |
5268 | + struct dentry *lower_dentry = NULL; | |
5269 | + struct dentry *lower_parent_dentry = NULL; | |
5270 | + struct dentry *parent; | |
5271 | + int bindex = 0, bstart; | |
5272 | + char *name = NULL; | |
5273 | + int valid; | |
5274 | + | |
5275 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5276 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5277 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5278 | + | |
5279 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
5280 | + if (unlikely(!valid)) { | |
5281 | + err = -ESTALE; /* same as what real_lookup does */ | |
5282 | + goto out; | |
5283 | + } | |
5284 | + | |
5285 | + bstart = dbstart(dentry); | |
5286 | + | |
5287 | + lower_dentry = unionfs_lower_dentry(dentry); | |
5288 | + | |
5289 | + /* check for a whiteout in new dentry branch, and delete it */ | |
5290 | + err = check_unlink_whiteout(dentry, lower_dentry, bstart); | |
5291 | + if (err > 0) /* whiteout found and removed successfully */ | |
5292 | + err = 0; | |
5293 | + if (err) { | |
5294 | + /* exit if the error returned was NOT -EROFS */ | |
5295 | + if (!IS_COPYUP_ERR(err)) | |
5296 | + goto out; | |
5297 | + bstart--; | |
5298 | + } | |
5299 | + | |
5300 | + /* check if copyup's needed, and mkdir */ | |
5301 | + for (bindex = bstart; bindex >= 0; bindex--) { | |
5302 | + int i; | |
5303 | + int bend = dbend(dentry); | |
5304 | + | |
5305 | + if (is_robranch_super(dentry->d_sb, bindex)) | |
5306 | + continue; | |
5307 | + | |
5308 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
5309 | + if (!lower_dentry) { | |
5310 | + lower_dentry = create_parents(dir, dentry, | |
5311 | + dentry->d_name.name, | |
5312 | + bindex); | |
5313 | + if (!lower_dentry || IS_ERR(lower_dentry)) { | |
5314 | + printk(KERN_ERR "unionfs: lower dentry " | |
5315 | + " NULL for bindex = %d\n", bindex); | |
5316 | + continue; | |
5317 | + } | |
5318 | + } | |
5319 | + | |
5320 | + lower_parent_dentry = lock_parent(lower_dentry); | |
5321 | + | |
5322 | + if (IS_ERR(lower_parent_dentry)) { | |
5323 | + err = PTR_ERR(lower_parent_dentry); | |
5324 | + goto out; | |
5325 | + } | |
5326 | + | |
5327 | + err = vfs_mkdir(lower_parent_dentry->d_inode, lower_dentry, | |
5328 | + mode); | |
5329 | + | |
5330 | + unlock_dir(lower_parent_dentry); | |
5331 | + | |
5332 | + /* did the mkdir succeed? */ | |
5333 | + if (err) | |
5334 | + break; | |
5335 | + | |
5336 | + for (i = bindex + 1; i <= bend; i++) { | |
5337 | + /* XXX: use path_put_lowers? */ | |
5338 | + if (unionfs_lower_dentry_idx(dentry, i)) { | |
5339 | + dput(unionfs_lower_dentry_idx(dentry, i)); | |
5340 | + unionfs_set_lower_dentry_idx(dentry, i, NULL); | |
5341 | + } | |
5342 | + } | |
5343 | + dbend(dentry) = bindex; | |
5344 | + | |
5345 | + /* | |
5346 | + * Only INTERPOSE_LOOKUP can return a value other than 0 on | |
5347 | + * err. | |
5348 | + */ | |
5349 | + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); | |
5350 | + if (!err) { | |
5351 | + unionfs_copy_attr_times(dir); | |
5352 | + fsstack_copy_inode_size(dir, | |
5353 | + lower_parent_dentry->d_inode); | |
5354 | + | |
5355 | + /* update number of links on parent directory */ | |
f4ea99f3 | 5356 | + set_nlink(dir, unionfs_get_nlinks(dir)); |
2380c486 JR |
5357 | + } |
5358 | + | |
5359 | + err = make_dir_opaque(dentry, dbstart(dentry)); | |
5360 | + if (err) { | |
5361 | + printk(KERN_ERR "unionfs: mkdir: error creating " | |
5362 | + ".wh.__dir_opaque: %d\n", err); | |
5363 | + goto out; | |
5364 | + } | |
5365 | + | |
5366 | + /* we are done! */ | |
5367 | + break; | |
5368 | + } | |
5369 | + | |
5370 | +out: | |
5371 | + if (!dentry->d_inode) | |
5372 | + d_drop(dentry); | |
5373 | + | |
5374 | + kfree(name); | |
5375 | + | |
5376 | + if (!err) { | |
5377 | + unionfs_copy_attr_times(dentry->d_inode); | |
5378 | + unionfs_postcopyup_setmnt(dentry); | |
5379 | + } | |
5380 | + unionfs_check_inode(dir); | |
5381 | + unionfs_check_dentry(dentry); | |
5382 | + unionfs_unlock_dentry(dentry); | |
5383 | + unionfs_unlock_parent(dentry, parent); | |
5384 | + unionfs_read_unlock(dentry->d_sb); | |
5385 | + | |
5386 | + return err; | |
5387 | +} | |
5388 | + | |
92d182d2 | 5389 | +static int unionfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, |
2380c486 JR |
5390 | + dev_t dev) |
5391 | +{ | |
5392 | + int err = 0; | |
5393 | + struct dentry *lower_dentry = NULL; | |
5394 | + struct dentry *wh_dentry = NULL; | |
5395 | + struct dentry *lower_parent_dentry = NULL; | |
5396 | + struct dentry *parent; | |
5397 | + char *name = NULL; | |
5398 | + int valid = 0; | |
5399 | + | |
5400 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5401 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5402 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5403 | + | |
5404 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
5405 | + if (unlikely(!valid)) { | |
5406 | + err = -ESTALE; | |
5407 | + goto out; | |
5408 | + } | |
5409 | + | |
5410 | + /* | |
5411 | + * It's only a bug if this dentry was not negative and couldn't be | |
5412 | + * revalidated (shouldn't happen). | |
5413 | + */ | |
5414 | + BUG_ON(!valid && dentry->d_inode); | |
5415 | + | |
5416 | + lower_dentry = find_writeable_branch(dir, dentry); | |
5417 | + if (IS_ERR(lower_dentry)) { | |
5418 | + err = PTR_ERR(lower_dentry); | |
5419 | + goto out; | |
5420 | + } | |
5421 | + | |
5422 | + lower_parent_dentry = lock_parent(lower_dentry); | |
5423 | + if (IS_ERR(lower_parent_dentry)) { | |
5424 | + err = PTR_ERR(lower_parent_dentry); | |
7670a7fc | 5425 | + goto out_unlock; |
2380c486 JR |
5426 | + } |
5427 | + | |
5428 | + err = vfs_mknod(lower_parent_dentry->d_inode, lower_dentry, mode, dev); | |
5429 | + if (!err) { | |
5430 | + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); | |
5431 | + if (!err) { | |
5432 | + unionfs_copy_attr_times(dir); | |
5433 | + fsstack_copy_inode_size(dir, | |
5434 | + lower_parent_dentry->d_inode); | |
5435 | + /* update no. of links on parent directory */ | |
f4ea99f3 | 5436 | + set_nlink(dir, unionfs_get_nlinks(dir)); |
2380c486 JR |
5437 | + } |
5438 | + } | |
5439 | + | |
7670a7fc | 5440 | +out_unlock: |
2380c486 | 5441 | + unlock_dir(lower_parent_dentry); |
2380c486 JR |
5442 | +out: |
5443 | + dput(wh_dentry); | |
5444 | + kfree(name); | |
5445 | + | |
5446 | + if (!err) { | |
5447 | + unionfs_postcopyup_setmnt(dentry); | |
5448 | + unionfs_check_inode(dir); | |
5449 | + unionfs_check_dentry(dentry); | |
5450 | + } | |
5451 | + unionfs_unlock_dentry(dentry); | |
5452 | + unionfs_unlock_parent(dentry, parent); | |
5453 | + unionfs_read_unlock(dentry->d_sb); | |
5454 | + return err; | |
5455 | +} | |
5456 | + | |
5457 | +/* requires sb, dentry, and parent to already be locked */ | |
5458 | +static int __unionfs_readlink(struct dentry *dentry, char __user *buf, | |
5459 | + int bufsiz) | |
5460 | +{ | |
5461 | + int err; | |
5462 | + struct dentry *lower_dentry; | |
5463 | + | |
5464 | + lower_dentry = unionfs_lower_dentry(dentry); | |
5465 | + | |
5466 | + if (!lower_dentry->d_inode->i_op || | |
5467 | + !lower_dentry->d_inode->i_op->readlink) { | |
5468 | + err = -EINVAL; | |
5469 | + goto out; | |
5470 | + } | |
5471 | + | |
5472 | + err = lower_dentry->d_inode->i_op->readlink(lower_dentry, | |
5473 | + buf, bufsiz); | |
5474 | + if (err >= 0) | |
5475 | + fsstack_copy_attr_atime(dentry->d_inode, | |
5476 | + lower_dentry->d_inode); | |
5477 | + | |
5478 | +out: | |
5479 | + return err; | |
5480 | +} | |
5481 | + | |
5482 | +static int unionfs_readlink(struct dentry *dentry, char __user *buf, | |
5483 | + int bufsiz) | |
5484 | +{ | |
5485 | + int err; | |
5486 | + struct dentry *parent; | |
5487 | + | |
5488 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5489 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5490 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5491 | + | |
5492 | + if (unlikely(!__unionfs_d_revalidate(dentry, parent, false))) { | |
5493 | + err = -ESTALE; | |
5494 | + goto out; | |
5495 | + } | |
5496 | + | |
5497 | + err = __unionfs_readlink(dentry, buf, bufsiz); | |
5498 | + | |
5499 | +out: | |
5500 | + unionfs_check_dentry(dentry); | |
5501 | + unionfs_unlock_dentry(dentry); | |
5502 | + unionfs_unlock_parent(dentry, parent); | |
5503 | + unionfs_read_unlock(dentry->d_sb); | |
5504 | + | |
5505 | + return err; | |
5506 | +} | |
5507 | + | |
5508 | +static void *unionfs_follow_link(struct dentry *dentry, struct nameidata *nd) | |
5509 | +{ | |
5510 | + char *buf; | |
5511 | + int len = PAGE_SIZE, err; | |
5512 | + mm_segment_t old_fs; | |
5513 | + struct dentry *parent; | |
5514 | + | |
5515 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5516 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5517 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5518 | + | |
5519 | + /* This is freed by the put_link method assuming a successful call. */ | |
5520 | + buf = kmalloc(len, GFP_KERNEL); | |
5521 | + if (unlikely(!buf)) { | |
5522 | + err = -ENOMEM; | |
5523 | + goto out; | |
5524 | + } | |
5525 | + | |
5526 | + /* read the symlink, and then we will follow it */ | |
5527 | + old_fs = get_fs(); | |
5528 | + set_fs(KERNEL_DS); | |
5529 | + err = __unionfs_readlink(dentry, buf, len); | |
5530 | + set_fs(old_fs); | |
5531 | + if (err < 0) { | |
5532 | + kfree(buf); | |
5533 | + buf = NULL; | |
5534 | + goto out; | |
5535 | + } | |
5536 | + buf[err] = 0; | |
5537 | + nd_set_link(nd, buf); | |
5538 | + err = 0; | |
5539 | + | |
5540 | +out: | |
5541 | + if (err >= 0) { | |
5542 | + unionfs_check_nd(nd); | |
5543 | + unionfs_check_dentry(dentry); | |
5544 | + } | |
5545 | + | |
5546 | + unionfs_unlock_dentry(dentry); | |
5547 | + unionfs_unlock_parent(dentry, parent); | |
5548 | + unionfs_read_unlock(dentry->d_sb); | |
5549 | + | |
5550 | + return ERR_PTR(err); | |
5551 | +} | |
5552 | + | |
5553 | +/* this @nd *IS* still used */ | |
5554 | +static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd, | |
5555 | + void *cookie) | |
5556 | +{ | |
5557 | + struct dentry *parent; | |
0c5527e5 | 5558 | + char *buf; |
2380c486 JR |
5559 | + |
5560 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5561 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5562 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5563 | + | |
5564 | + if (unlikely(!__unionfs_d_revalidate(dentry, parent, false))) | |
5565 | + printk(KERN_ERR | |
5566 | + "unionfs: put_link failed to revalidate dentry\n"); | |
5567 | + | |
5568 | + unionfs_check_dentry(dentry); | |
0c5527e5 AM |
5569 | +#if 0 |
5570 | + /* XXX: can't run this check b/c this fxn can receive a poisoned 'nd' PTR */ | |
2380c486 | 5571 | + unionfs_check_nd(nd); |
0c5527e5 AM |
5572 | +#endif |
5573 | + buf = nd_get_link(nd); | |
5574 | + if (!IS_ERR(buf)) | |
5575 | + kfree(buf); | |
2380c486 JR |
5576 | + unionfs_unlock_dentry(dentry); |
5577 | + unionfs_unlock_parent(dentry, parent); | |
5578 | + unionfs_read_unlock(dentry->d_sb); | |
5579 | +} | |
5580 | + | |
5581 | +/* | |
5582 | + * This is a variant of fs/namei.c:permission() or inode_permission() which | |
5583 | + * skips over EROFS tests (because we perform copyup on EROFS). | |
5584 | + */ | |
6b53c3da | 5585 | +static int __inode_permission(struct inode *inode, int mask) |
2380c486 JR |
5586 | +{ |
5587 | + int retval; | |
5588 | + | |
5589 | + /* nobody gets write access to an immutable file */ | |
5590 | + if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) | |
5591 | + return -EACCES; | |
5592 | + | |
5593 | + /* Ordinary permission routines do not understand MAY_APPEND. */ | |
5594 | + if (inode->i_op && inode->i_op->permission) { | |
6b53c3da | 5595 | + retval = inode->i_op->permission(inode, mask); |
2380c486 JR |
5596 | + if (!retval) { |
5597 | + /* | |
5598 | + * Exec permission on a regular file is denied if none | |
5599 | + * of the execute bits are set. | |
5600 | + * | |
5601 | + * This check should be done by the ->permission() | |
5602 | + * method. | |
5603 | + */ | |
5604 | + if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode) && | |
5605 | + !(inode->i_mode & S_IXUGO)) | |
5606 | + return -EACCES; | |
5607 | + } | |
5608 | + } else { | |
6b53c3da | 5609 | + retval = generic_permission(inode, mask); |
2380c486 JR |
5610 | + } |
5611 | + if (retval) | |
5612 | + return retval; | |
5613 | + | |
5614 | + return security_inode_permission(inode, | |
5615 | + mask & (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND)); | |
5616 | +} | |
5617 | + | |
5618 | +/* | |
5619 | + * Don't grab the superblock read-lock in unionfs_permission, which prevents | |
5620 | + * a deadlock with the branch-management "add branch" code (which grabbed | |
5621 | + * the write lock). It is safe to not grab the read lock here, because even | |
5622 | + * with branch management taking place, there is no chance that | |
5623 | + * unionfs_permission, or anything it calls, will use stale branch | |
5624 | + * information. | |
5625 | + */ | |
6b53c3da | 5626 | +static int unionfs_permission(struct inode *inode, int mask) |
2380c486 JR |
5627 | +{ |
5628 | + struct inode *lower_inode = NULL; | |
5629 | + int err = 0; | |
5630 | + int bindex, bstart, bend; | |
63b09289 | 5631 | + int is_file; |
2380c486 | 5632 | + const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ); |
63b09289 | 5633 | + struct inode *inode_grabbed; |
2380c486 | 5634 | + |
63b09289 JR |
5635 | + inode_grabbed = igrab(inode); |
5636 | + is_file = !S_ISDIR(inode->i_mode); | |
5637 | + | |
2380c486 JR |
5638 | + if (!UNIONFS_I(inode)->lower_inodes) { |
5639 | + if (is_file) /* dirs can be unlinked but chdir'ed to */ | |
5640 | + err = -ESTALE; /* force revalidate */ | |
5641 | + goto out; | |
5642 | + } | |
5643 | + bstart = ibstart(inode); | |
5644 | + bend = ibend(inode); | |
5645 | + if (unlikely(bstart < 0 || bend < 0)) { | |
5646 | + /* | |
5647 | + * With branch-management, we can get a stale inode here. | |
5648 | + * If so, we return ESTALE back to link_path_walk, which | |
5649 | + * would discard the dcache entry and re-lookup the | |
5650 | + * dentry+inode. This should be equivalent to issuing | |
5651 | + * __unionfs_d_revalidate_chain on nd.dentry here. | |
5652 | + */ | |
5653 | + if (is_file) /* dirs can be unlinked but chdir'ed to */ | |
5654 | + err = -ESTALE; /* force revalidate */ | |
5655 | + goto out; | |
5656 | + } | |
5657 | + | |
5658 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
5659 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
5660 | + if (!lower_inode) | |
5661 | + continue; | |
5662 | + | |
5663 | + /* | |
5664 | + * check the condition for D-F-D underlying files/directories, | |
5665 | + * we don't have to check for files, if we are checking for | |
5666 | + * directories. | |
5667 | + */ | |
5668 | + if (!is_file && !S_ISDIR(lower_inode->i_mode)) | |
5669 | + continue; | |
5670 | + | |
5671 | + /* | |
5672 | + * We check basic permissions, but we ignore any conditions | |
5673 | + * such as readonly file systems or branches marked as | |
5674 | + * readonly, because those conditions should lead to a | |
5675 | + * copyup taking place later on. However, if user never had | |
5676 | + * access to the file, then no copyup could ever take place. | |
5677 | + */ | |
6b53c3da | 5678 | + err = __inode_permission(lower_inode, mask); |
2380c486 JR |
5679 | + if (err && err != -EACCES && err != EPERM && bindex > 0) { |
5680 | + umode_t mode = lower_inode->i_mode; | |
5681 | + if ((is_robranch_super(inode->i_sb, bindex) || | |
4ae1df7a | 5682 | + __is_rdonly(lower_inode)) && |
2380c486 JR |
5683 | + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) |
5684 | + err = 0; | |
5685 | + if (IS_COPYUP_ERR(err)) | |
5686 | + err = 0; | |
5687 | + } | |
5688 | + | |
5689 | + /* | |
4ae1df7a JR |
5690 | + * NFS HACK: NFSv2/3 return EACCES on readonly-exported, |
5691 | + * locally readonly-mounted file systems, instead of EROFS | |
5692 | + * like other file systems do. So we have no choice here | |
5693 | + * but to intercept this and ignore it for NFS branches | |
5694 | + * marked readonly. Specifically, we avoid using NFS's own | |
5695 | + * "broken" ->permission method, and rely on | |
5696 | + * generic_permission() to do basic checking for us. | |
5697 | + */ | |
5698 | + if (err && err == -EACCES && | |
5699 | + is_robranch_super(inode->i_sb, bindex) && | |
5700 | + lower_inode->i_sb->s_magic == NFS_SUPER_MAGIC) | |
6b53c3da | 5701 | + err = generic_permission(lower_inode, mask); |
4ae1df7a JR |
5702 | + |
5703 | + /* | |
2380c486 JR |
5704 | + * The permissions are an intersection of the overall directory |
5705 | + * permissions, so we fail if one fails. | |
5706 | + */ | |
5707 | + if (err) | |
5708 | + goto out; | |
5709 | + | |
5710 | + /* only the leftmost file matters. */ | |
5711 | + if (is_file || write_mask) { | |
5712 | + if (is_file && write_mask) { | |
5713 | + err = get_write_access(lower_inode); | |
5714 | + if (!err) | |
5715 | + put_write_access(lower_inode); | |
5716 | + } | |
5717 | + break; | |
5718 | + } | |
5719 | + } | |
5720 | + /* sync times which may have changed (asynchronously) below */ | |
5721 | + unionfs_copy_attr_times(inode); | |
5722 | + | |
5723 | +out: | |
5724 | + unionfs_check_inode(inode); | |
2380c486 JR |
5725 | + iput(inode_grabbed); |
5726 | + return err; | |
5727 | +} | |
5728 | + | |
5729 | +static int unionfs_setattr(struct dentry *dentry, struct iattr *ia) | |
5730 | +{ | |
5731 | + int err = 0; | |
5732 | + struct dentry *lower_dentry; | |
5733 | + struct dentry *parent; | |
5734 | + struct inode *inode; | |
5735 | + struct inode *lower_inode; | |
5736 | + int bstart, bend, bindex; | |
5737 | + loff_t size; | |
82260373 AM |
5738 | + struct iattr lower_ia; |
5739 | + | |
5740 | + /* check if user has permission to change inode */ | |
5741 | + err = inode_change_ok(dentry->d_inode, ia); | |
5742 | + if (err) | |
5743 | + goto out_err; | |
2380c486 JR |
5744 | + |
5745 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
5746 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
5747 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
5748 | + | |
5749 | + if (unlikely(!__unionfs_d_revalidate(dentry, parent, false))) { | |
5750 | + err = -ESTALE; | |
5751 | + goto out; | |
5752 | + } | |
5753 | + | |
5754 | + bstart = dbstart(dentry); | |
5755 | + bend = dbend(dentry); | |
5756 | + inode = dentry->d_inode; | |
5757 | + | |
5758 | + /* | |
5759 | + * mode change is for clearing setuid/setgid. Allow lower filesystem | |
5760 | + * to reinterpret it in its own way. | |
5761 | + */ | |
5762 | + if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) | |
5763 | + ia->ia_valid &= ~ATTR_MODE; | |
5764 | + | |
5765 | + lower_dentry = unionfs_lower_dentry(dentry); | |
5766 | + if (!lower_dentry) { /* should never happen after above revalidate */ | |
5767 | + err = -EINVAL; | |
5768 | + goto out; | |
5769 | + } | |
63b09289 JR |
5770 | + |
5771 | + /* | |
5772 | + * Get the lower inode directly from lower dentry, in case ibstart | |
5773 | + * is -1 (which happens when the file is open but unlinked. | |
5774 | + */ | |
5775 | + lower_inode = lower_dentry->d_inode; | |
2380c486 JR |
5776 | + |
5777 | + /* check if user has permission to change lower inode */ | |
5778 | + err = inode_change_ok(lower_inode, ia); | |
5779 | + if (err) | |
5780 | + goto out; | |
5781 | + | |
5782 | + /* copyup if the file is on a read only branch */ | |
5783 | + if (is_robranch_super(dentry->d_sb, bstart) | |
4ae1df7a | 5784 | + || __is_rdonly(lower_inode)) { |
2380c486 JR |
5785 | + /* check if we have a branch to copy up to */ |
5786 | + if (bstart <= 0) { | |
5787 | + err = -EACCES; | |
5788 | + goto out; | |
5789 | + } | |
5790 | + | |
5791 | + if (ia->ia_valid & ATTR_SIZE) | |
5792 | + size = ia->ia_size; | |
5793 | + else | |
5794 | + size = i_size_read(inode); | |
5795 | + /* copyup to next available branch */ | |
5796 | + for (bindex = bstart - 1; bindex >= 0; bindex--) { | |
5797 | + err = copyup_dentry(parent->d_inode, | |
5798 | + dentry, bstart, bindex, | |
5799 | + dentry->d_name.name, | |
5800 | + dentry->d_name.len, | |
5801 | + NULL, size); | |
5802 | + if (!err) | |
5803 | + break; | |
5804 | + } | |
5805 | + if (err) | |
5806 | + goto out; | |
5807 | + /* get updated lower_dentry/inode after copyup */ | |
5808 | + lower_dentry = unionfs_lower_dentry(dentry); | |
5809 | + lower_inode = unionfs_lower_inode(inode); | |
63b09289 JR |
5810 | + /* |
5811 | + * check for whiteouts in writeable branch, and remove them | |
5812 | + * if necessary. | |
5813 | + */ | |
5814 | + if (lower_dentry) { | |
5815 | + err = check_unlink_whiteout(dentry, lower_dentry, | |
5816 | + bindex); | |
5817 | + if (err > 0) /* ignore if whiteout found and removed */ | |
5818 | + err = 0; | |
5819 | + } | |
2380c486 JR |
5820 | + } |
5821 | + | |
5822 | + /* | |
5823 | + * If shrinking, first truncate upper level to cancel writing dirty | |
5824 | + * pages beyond the new eof; and also if its' maxbytes is more | |
5825 | + * limiting (fail with -EFBIG before making any change to the lower | |
5826 | + * level). There is no need to vmtruncate the upper level | |
5827 | + * afterwards in the other cases: we fsstack_copy_inode_size from | |
5828 | + * the lower level. | |
5829 | + */ | |
5830 | + if (ia->ia_valid & ATTR_SIZE) { | |
5831 | + size = i_size_read(inode); | |
5832 | + if (ia->ia_size < size || (ia->ia_size > size && | |
5833 | + inode->i_sb->s_maxbytes < lower_inode->i_sb->s_maxbytes)) { | |
5834 | + err = vmtruncate(inode, ia->ia_size); | |
5835 | + if (err) | |
5836 | + goto out; | |
5837 | + } | |
5838 | + } | |
5839 | + | |
5840 | + /* notify the (possibly copied-up) lower inode */ | |
4ae1df7a JR |
5841 | + /* |
5842 | + * Note: we use lower_dentry->d_inode, because lower_inode may be | |
5843 | + * unlinked (no inode->i_sb and i_ino==0. This happens if someone | |
5844 | + * tries to open(), unlink(), then ftruncate() a file. | |
5845 | + */ | |
82260373 AM |
5846 | + /* prepare our own lower struct iattr (with our own lower file) */ |
5847 | + memcpy(&lower_ia, ia, sizeof(lower_ia)); | |
5848 | + if (ia->ia_valid & ATTR_FILE) { | |
5849 | + lower_ia.ia_file = unionfs_lower_file(ia->ia_file); | |
5850 | + BUG_ON(!lower_ia.ia_file); // XXX? | |
5851 | + } | |
5852 | + | |
4ae1df7a | 5853 | + mutex_lock(&lower_dentry->d_inode->i_mutex); |
82260373 | 5854 | + err = notify_change(lower_dentry, &lower_ia); |
4ae1df7a | 5855 | + mutex_unlock(&lower_dentry->d_inode->i_mutex); |
2380c486 JR |
5856 | + if (err) |
5857 | + goto out; | |
5858 | + | |
5859 | + /* get attributes from the first lower inode */ | |
4ae1df7a JR |
5860 | + if (ibstart(inode) >= 0) |
5861 | + unionfs_copy_attr_all(inode, lower_inode); | |
2380c486 JR |
5862 | + /* |
5863 | + * unionfs_copy_attr_all will copy the lower times to our inode if | |
5864 | + * the lower ones are newer (useful for cache coherency). However, | |
5865 | + * ->setattr is the only place in which we may have to copy the | |
5866 | + * lower inode times absolutely, to support utimes(2). | |
5867 | + */ | |
5868 | + if (ia->ia_valid & ATTR_MTIME_SET) | |
5869 | + inode->i_mtime = lower_inode->i_mtime; | |
5870 | + if (ia->ia_valid & ATTR_CTIME) | |
5871 | + inode->i_ctime = lower_inode->i_ctime; | |
5872 | + if (ia->ia_valid & ATTR_ATIME_SET) | |
5873 | + inode->i_atime = lower_inode->i_atime; | |
5874 | + fsstack_copy_inode_size(inode, lower_inode); | |
5875 | + | |
5876 | +out: | |
5877 | + if (!err) | |
5878 | + unionfs_check_dentry(dentry); | |
5879 | + unionfs_unlock_dentry(dentry); | |
5880 | + unionfs_unlock_parent(dentry, parent); | |
5881 | + unionfs_read_unlock(dentry->d_sb); | |
82260373 | 5882 | +out_err: |
2380c486 JR |
5883 | + return err; |
5884 | +} | |
5885 | + | |
5886 | +struct inode_operations unionfs_symlink_iops = { | |
5887 | + .readlink = unionfs_readlink, | |
5888 | + .permission = unionfs_permission, | |
5889 | + .follow_link = unionfs_follow_link, | |
5890 | + .setattr = unionfs_setattr, | |
5891 | + .put_link = unionfs_put_link, | |
5892 | +}; | |
5893 | + | |
5894 | +struct inode_operations unionfs_dir_iops = { | |
5895 | + .create = unionfs_create, | |
5896 | + .lookup = unionfs_lookup, | |
5897 | + .link = unionfs_link, | |
5898 | + .unlink = unionfs_unlink, | |
5899 | + .symlink = unionfs_symlink, | |
5900 | + .mkdir = unionfs_mkdir, | |
5901 | + .rmdir = unionfs_rmdir, | |
5902 | + .mknod = unionfs_mknod, | |
5903 | + .rename = unionfs_rename, | |
5904 | + .permission = unionfs_permission, | |
5905 | + .setattr = unionfs_setattr, | |
5906 | +#ifdef CONFIG_UNION_FS_XATTR | |
5907 | + .setxattr = unionfs_setxattr, | |
5908 | + .getxattr = unionfs_getxattr, | |
5909 | + .removexattr = unionfs_removexattr, | |
5910 | + .listxattr = unionfs_listxattr, | |
5911 | +#endif /* CONFIG_UNION_FS_XATTR */ | |
5912 | +}; | |
5913 | + | |
5914 | +struct inode_operations unionfs_main_iops = { | |
5915 | + .permission = unionfs_permission, | |
5916 | + .setattr = unionfs_setattr, | |
5917 | +#ifdef CONFIG_UNION_FS_XATTR | |
5918 | + .setxattr = unionfs_setxattr, | |
5919 | + .getxattr = unionfs_getxattr, | |
5920 | + .removexattr = unionfs_removexattr, | |
5921 | + .listxattr = unionfs_listxattr, | |
5922 | +#endif /* CONFIG_UNION_FS_XATTR */ | |
5923 | +}; | |
0c5527e5 AM |
5924 | diff --git a/fs/unionfs/lookup.c b/fs/unionfs/lookup.c |
5925 | new file mode 100644 | |
6b53c3da | 5926 | index 0000000..041d674 |
0c5527e5 AM |
5927 | --- /dev/null |
5928 | +++ b/fs/unionfs/lookup.c | |
6b53c3da | 5929 | @@ -0,0 +1,570 @@ |
2380c486 | 5930 | +/* |
63b09289 | 5931 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
5932 | + * Copyright (c) 2003-2006 Charles P. Wright |
5933 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
5934 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
5935 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
5936 | + * Copyright (c) 2004-2006 David P. Quigley | |
5937 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
5938 | + * Copyright (c) 2003 Puja Gupta | |
5939 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
5940 | + * Copyright (c) 2003-2011 Stony Brook University |
5941 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
5942 | + * |
5943 | + * This program is free software; you can redistribute it and/or modify | |
5944 | + * it under the terms of the GNU General Public License version 2 as | |
5945 | + * published by the Free Software Foundation. | |
5946 | + */ | |
5947 | + | |
5948 | +#include "union.h" | |
5949 | + | |
5950 | +/* | |
5951 | + * Lookup one path component @name relative to a <base,mnt> path pair. | |
5952 | + * Behaves nearly the same as lookup_one_len (i.e., return negative dentry | |
5953 | + * on ENOENT), but uses the @mnt passed, so it can cross bind mounts and | |
5954 | + * other lower mounts properly. If @new_mnt is non-null, will fill in the | |
5955 | + * new mnt there. Caller is responsible to dput/mntput/path_put returned | |
5956 | + * @dentry and @new_mnt. | |
5957 | + */ | |
5958 | +struct dentry *__lookup_one(struct dentry *base, struct vfsmount *mnt, | |
5959 | + const char *name, struct vfsmount **new_mnt) | |
5960 | +{ | |
5961 | + struct dentry *dentry = NULL; | |
6b53c3da | 5962 | + struct path lower_path = {NULL, NULL}; |
2380c486 JR |
5963 | + int err; |
5964 | + | |
5965 | + /* we use flags=0 to get basic lookup */ | |
6b53c3da | 5966 | + err = vfs_path_lookup(base, mnt, name, 0, &lower_path); |
2380c486 JR |
5967 | + |
5968 | + switch (err) { | |
5969 | + case 0: /* no error */ | |
6b53c3da | 5970 | + dentry = lower_path.dentry; |
2380c486 | 5971 | + if (new_mnt) |
6b53c3da | 5972 | + *new_mnt = lower_path.mnt; /* rc already inc'ed */ |
2380c486 JR |
5973 | + break; |
5974 | + case -ENOENT: | |
5975 | + /* | |
5976 | + * We don't consider ENOENT an error, and we want to return | |
5977 | + * a negative dentry (ala lookup_one_len). As we know | |
5978 | + * there was no inode for this name before (-ENOENT), then | |
5979 | + * it's safe to call lookup_one_len (which doesn't take a | |
5980 | + * vfsmount). | |
5981 | + */ | |
4ae1df7a | 5982 | + dentry = lookup_lck_len(name, base, strlen(name)); |
2380c486 | 5983 | + if (new_mnt) |
6b53c3da | 5984 | + *new_mnt = mntget(lower_path.mnt); |
2380c486 JR |
5985 | + break; |
5986 | + default: /* all other real errors */ | |
5987 | + dentry = ERR_PTR(err); | |
5988 | + break; | |
5989 | + } | |
5990 | + | |
5991 | + return dentry; | |
5992 | +} | |
5993 | + | |
5994 | +/* | |
5995 | + * This is a utility function that fills in a unionfs dentry. | |
5996 | + * Caller must lock this dentry with unionfs_lock_dentry. | |
5997 | + * | |
5998 | + * Returns: 0 (ok), or -ERRNO if an error occurred. | |
5999 | + * XXX: get rid of _partial_lookup and make callers call _lookup_full directly | |
6000 | + */ | |
6001 | +int unionfs_partial_lookup(struct dentry *dentry, struct dentry *parent) | |
6002 | +{ | |
6003 | + struct dentry *tmp; | |
6004 | + int err = -ENOSYS; | |
6005 | + | |
6006 | + tmp = unionfs_lookup_full(dentry, parent, INTERPOSE_PARTIAL); | |
6007 | + | |
6008 | + if (!tmp) { | |
6009 | + err = 0; | |
6010 | + goto out; | |
6011 | + } | |
6012 | + if (IS_ERR(tmp)) { | |
6013 | + err = PTR_ERR(tmp); | |
6014 | + goto out; | |
6015 | + } | |
6016 | + /* XXX: need to change the interface */ | |
6017 | + BUG_ON(tmp != dentry); | |
6018 | +out: | |
6019 | + return err; | |
6020 | +} | |
6021 | + | |
6022 | +/* The dentry cache is just so we have properly sized dentries. */ | |
6023 | +static struct kmem_cache *unionfs_dentry_cachep; | |
6024 | +int unionfs_init_dentry_cache(void) | |
6025 | +{ | |
6026 | + unionfs_dentry_cachep = | |
6027 | + kmem_cache_create("unionfs_dentry", | |
6028 | + sizeof(struct unionfs_dentry_info), | |
6029 | + 0, SLAB_RECLAIM_ACCOUNT, NULL); | |
6030 | + | |
6031 | + return (unionfs_dentry_cachep ? 0 : -ENOMEM); | |
6032 | +} | |
6033 | + | |
6034 | +void unionfs_destroy_dentry_cache(void) | |
6035 | +{ | |
6036 | + if (unionfs_dentry_cachep) | |
6037 | + kmem_cache_destroy(unionfs_dentry_cachep); | |
6038 | +} | |
6039 | + | |
6040 | +void free_dentry_private_data(struct dentry *dentry) | |
6041 | +{ | |
6042 | + if (!dentry || !dentry->d_fsdata) | |
6043 | + return; | |
6044 | + kfree(UNIONFS_D(dentry)->lower_paths); | |
6045 | + UNIONFS_D(dentry)->lower_paths = NULL; | |
6046 | + kmem_cache_free(unionfs_dentry_cachep, dentry->d_fsdata); | |
6047 | + dentry->d_fsdata = NULL; | |
6048 | +} | |
6049 | + | |
6050 | +static inline int __realloc_dentry_private_data(struct dentry *dentry) | |
6051 | +{ | |
6052 | + struct unionfs_dentry_info *info = UNIONFS_D(dentry); | |
6053 | + void *p; | |
6054 | + int size; | |
6055 | + | |
6056 | + BUG_ON(!info); | |
6057 | + | |
6058 | + size = sizeof(struct path) * sbmax(dentry->d_sb); | |
6059 | + p = krealloc(info->lower_paths, size, GFP_ATOMIC); | |
6060 | + if (unlikely(!p)) | |
6061 | + return -ENOMEM; | |
6062 | + | |
6063 | + info->lower_paths = p; | |
6064 | + | |
6065 | + info->bstart = -1; | |
6066 | + info->bend = -1; | |
6067 | + info->bopaque = -1; | |
6068 | + info->bcount = sbmax(dentry->d_sb); | |
6069 | + atomic_set(&info->generation, | |
6070 | + atomic_read(&UNIONFS_SB(dentry->d_sb)->generation)); | |
6071 | + | |
6072 | + memset(info->lower_paths, 0, size); | |
6073 | + | |
6074 | + return 0; | |
6075 | +} | |
6076 | + | |
6077 | +/* UNIONFS_D(dentry)->lock must be locked */ | |
6078 | +int realloc_dentry_private_data(struct dentry *dentry) | |
6079 | +{ | |
6080 | + if (!__realloc_dentry_private_data(dentry)) | |
6081 | + return 0; | |
6082 | + | |
6083 | + kfree(UNIONFS_D(dentry)->lower_paths); | |
6084 | + free_dentry_private_data(dentry); | |
6085 | + return -ENOMEM; | |
6086 | +} | |
6087 | + | |
6088 | +/* allocate new dentry private data */ | |
6089 | +int new_dentry_private_data(struct dentry *dentry, int subclass) | |
6090 | +{ | |
6091 | + struct unionfs_dentry_info *info = UNIONFS_D(dentry); | |
6092 | + | |
6093 | + BUG_ON(info); | |
6094 | + | |
6095 | + info = kmem_cache_alloc(unionfs_dentry_cachep, GFP_ATOMIC); | |
6096 | + if (unlikely(!info)) | |
6097 | + return -ENOMEM; | |
6098 | + | |
6099 | + mutex_init(&info->lock); | |
6100 | + mutex_lock_nested(&info->lock, subclass); | |
6101 | + | |
6102 | + info->lower_paths = NULL; | |
6103 | + | |
6104 | + dentry->d_fsdata = info; | |
6105 | + | |
6106 | + if (!__realloc_dentry_private_data(dentry)) | |
6107 | + return 0; | |
6108 | + | |
6109 | + mutex_unlock(&info->lock); | |
6110 | + free_dentry_private_data(dentry); | |
6111 | + return -ENOMEM; | |
6112 | +} | |
6113 | + | |
6114 | +/* | |
6115 | + * scan through the lower dentry objects, and set bstart to reflect the | |
6116 | + * starting branch | |
6117 | + */ | |
6118 | +void update_bstart(struct dentry *dentry) | |
6119 | +{ | |
6120 | + int bindex; | |
6121 | + int bstart = dbstart(dentry); | |
6122 | + int bend = dbend(dentry); | |
6123 | + struct dentry *lower_dentry; | |
6124 | + | |
6125 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
6126 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
6127 | + if (!lower_dentry) | |
6128 | + continue; | |
6129 | + if (lower_dentry->d_inode) { | |
6130 | + dbstart(dentry) = bindex; | |
6131 | + break; | |
6132 | + } | |
6133 | + dput(lower_dentry); | |
6134 | + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); | |
6135 | + } | |
6136 | +} | |
6137 | + | |
6138 | + | |
6139 | +/* | |
6140 | + * Initialize a nameidata structure (the intent part) we can pass to a lower | |
6141 | + * file system. Returns 0 on success or -error (only -ENOMEM possible). | |
6142 | + * Inside that nd structure, this function may also return an allocated | |
6143 | + * struct file (for open intents). The caller, when done with this nd, must | |
6144 | + * kfree the intent file (using release_lower_nd). | |
6145 | + * | |
6146 | + * XXX: this code, and the callers of this code, should be redone using | |
6147 | + * vfs_path_lookup() when (1) the nameidata structure is refactored into a | |
6148 | + * separate intent-structure, and (2) open_namei() is broken into a VFS-only | |
6149 | + * function and a method that other file systems can call. | |
6150 | + */ | |
6151 | +int init_lower_nd(struct nameidata *nd, unsigned int flags) | |
6152 | +{ | |
6153 | + int err = 0; | |
6154 | +#ifdef ALLOC_LOWER_ND_FILE | |
6155 | + /* | |
6156 | + * XXX: one day we may need to have the lower return an open file | |
6157 | + * for us. It is not needed in 2.6.23-rc1 for nfs2/nfs3, but may | |
6158 | + * very well be needed for nfs4. | |
6159 | + */ | |
6160 | + struct file *file; | |
6161 | +#endif /* ALLOC_LOWER_ND_FILE */ | |
6162 | + | |
6163 | + memset(nd, 0, sizeof(struct nameidata)); | |
6164 | + if (!flags) | |
6165 | + return err; | |
6166 | + | |
6167 | + switch (flags) { | |
6168 | + case LOOKUP_CREATE: | |
6169 | + nd->intent.open.flags |= O_CREAT; | |
6170 | + /* fall through: shared code for create/open cases */ | |
6171 | + case LOOKUP_OPEN: | |
6172 | + nd->flags = flags; | |
6173 | + nd->intent.open.flags |= (FMODE_READ | FMODE_WRITE); | |
6174 | +#ifdef ALLOC_LOWER_ND_FILE | |
6175 | + file = kzalloc(sizeof(struct file), GFP_KERNEL); | |
6176 | + if (unlikely(!file)) { | |
6177 | + err = -ENOMEM; | |
6178 | + break; /* exit switch statement and thus return */ | |
6179 | + } | |
6180 | + nd->intent.open.file = file; | |
6181 | +#endif /* ALLOC_LOWER_ND_FILE */ | |
6182 | + break; | |
6183 | + default: | |
6184 | + /* | |
6185 | + * We should never get here, for now. | |
6186 | + * We can add new cases here later on. | |
6187 | + */ | |
6188 | + pr_debug("unionfs: unknown nameidata flag 0x%x\n", flags); | |
6189 | + BUG(); | |
6190 | + break; | |
6191 | + } | |
6192 | + | |
6193 | + return err; | |
6194 | +} | |
6195 | + | |
6196 | +void release_lower_nd(struct nameidata *nd, int err) | |
6197 | +{ | |
6198 | + if (!nd->intent.open.file) | |
6199 | + return; | |
6200 | + else if (!err) | |
6201 | + release_open_intent(nd); | |
6202 | +#ifdef ALLOC_LOWER_ND_FILE | |
6203 | + kfree(nd->intent.open.file); | |
6204 | +#endif /* ALLOC_LOWER_ND_FILE */ | |
6205 | +} | |
6206 | + | |
6207 | +/* | |
6208 | + * Main (and complex) driver function for Unionfs's lookup | |
6209 | + * | |
6210 | + * Returns: NULL (ok), ERR_PTR if an error occurred, or a non-null non-error | |
6211 | + * PTR if d_splice returned a different dentry. | |
6212 | + * | |
6213 | + * If lookupmode is INTERPOSE_PARTIAL/REVAL/REVAL_NEG, the passed dentry's | |
6214 | + * inode info must be locked. If lookupmode is INTERPOSE_LOOKUP (i.e., a | |
6215 | + * newly looked-up dentry), then unionfs_lookup_backend will return a locked | |
6216 | + * dentry's info, which the caller must unlock. | |
6217 | + */ | |
6218 | +struct dentry *unionfs_lookup_full(struct dentry *dentry, | |
6219 | + struct dentry *parent, int lookupmode) | |
6220 | +{ | |
6221 | + int err = 0; | |
6222 | + struct dentry *lower_dentry = NULL; | |
6223 | + struct vfsmount *lower_mnt; | |
6224 | + struct vfsmount *lower_dir_mnt; | |
6225 | + struct dentry *wh_lower_dentry = NULL; | |
6226 | + struct dentry *lower_dir_dentry = NULL; | |
6227 | + struct dentry *d_interposed = NULL; | |
6228 | + int bindex, bstart, bend, bopaque; | |
6229 | + int opaque, num_positive = 0; | |
6230 | + const char *name; | |
6231 | + int namelen; | |
6232 | + int pos_start, pos_end; | |
6233 | + | |
6234 | + /* | |
6235 | + * We should already have a lock on this dentry in the case of a | |
6236 | + * partial lookup, or a revalidation. Otherwise it is returned from | |
6237 | + * new_dentry_private_data already locked. | |
6238 | + */ | |
6239 | + verify_locked(dentry); | |
6240 | + verify_locked(parent); | |
6241 | + | |
6242 | + /* must initialize dentry operations */ | |
6b53c3da AM |
6243 | + if (lookupmode == INTERPOSE_LOOKUP) |
6244 | + d_set_d_op(dentry, &unionfs_dops); | |
2380c486 JR |
6245 | + |
6246 | + /* We never partial lookup the root directory. */ | |
6247 | + if (IS_ROOT(dentry)) | |
6248 | + goto out; | |
6249 | + | |
6250 | + name = dentry->d_name.name; | |
6251 | + namelen = dentry->d_name.len; | |
6252 | + | |
6253 | + /* No dentries should get created for possible whiteout names. */ | |
6254 | + if (!is_validname(name)) { | |
6255 | + err = -EPERM; | |
6256 | + goto out_free; | |
6257 | + } | |
6258 | + | |
6259 | + /* Now start the actual lookup procedure. */ | |
6260 | + bstart = dbstart(parent); | |
6261 | + bend = dbend(parent); | |
6262 | + bopaque = dbopaque(parent); | |
6263 | + BUG_ON(bstart < 0); | |
6264 | + | |
6265 | + /* adjust bend to bopaque if needed */ | |
6266 | + if ((bopaque >= 0) && (bopaque < bend)) | |
6267 | + bend = bopaque; | |
6268 | + | |
6269 | + /* lookup all possible dentries */ | |
6270 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
6271 | + | |
6272 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
6273 | + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); | |
6274 | + | |
6275 | + /* skip if we already have a positive lower dentry */ | |
6276 | + if (lower_dentry) { | |
6277 | + if (dbstart(dentry) < 0) | |
6278 | + dbstart(dentry) = bindex; | |
6279 | + if (bindex > dbend(dentry)) | |
6280 | + dbend(dentry) = bindex; | |
6281 | + if (lower_dentry->d_inode) | |
6282 | + num_positive++; | |
6283 | + continue; | |
6284 | + } | |
6285 | + | |
6286 | + lower_dir_dentry = | |
6287 | + unionfs_lower_dentry_idx(parent, bindex); | |
6288 | + /* if the lower dentry's parent does not exist, skip this */ | |
6289 | + if (!lower_dir_dentry || !lower_dir_dentry->d_inode) | |
6290 | + continue; | |
6291 | + | |
6292 | + /* also skip it if the parent isn't a directory. */ | |
6293 | + if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode)) | |
6294 | + continue; /* XXX: should be BUG_ON */ | |
6295 | + | |
6296 | + /* check for whiteouts: stop lookup if found */ | |
6297 | + wh_lower_dentry = lookup_whiteout(name, lower_dir_dentry); | |
6298 | + if (IS_ERR(wh_lower_dentry)) { | |
6299 | + err = PTR_ERR(wh_lower_dentry); | |
6300 | + goto out_free; | |
6301 | + } | |
6302 | + if (wh_lower_dentry->d_inode) { | |
6303 | + dbend(dentry) = dbopaque(dentry) = bindex; | |
6304 | + if (dbstart(dentry) < 0) | |
6305 | + dbstart(dentry) = bindex; | |
6306 | + dput(wh_lower_dentry); | |
6307 | + break; | |
6308 | + } | |
6309 | + dput(wh_lower_dentry); | |
6310 | + | |
6311 | + /* Now do regular lookup; lookup @name */ | |
6312 | + lower_dir_mnt = unionfs_lower_mnt_idx(parent, bindex); | |
6313 | + lower_mnt = NULL; /* XXX: needed? */ | |
6314 | + | |
6315 | + lower_dentry = __lookup_one(lower_dir_dentry, lower_dir_mnt, | |
6316 | + name, &lower_mnt); | |
6317 | + | |
6318 | + if (IS_ERR(lower_dentry)) { | |
6319 | + err = PTR_ERR(lower_dentry); | |
6320 | + goto out_free; | |
6321 | + } | |
6322 | + unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry); | |
6323 | + if (!lower_mnt) | |
6324 | + lower_mnt = unionfs_mntget(dentry->d_sb->s_root, | |
6325 | + bindex); | |
6326 | + unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt); | |
6327 | + | |
6328 | + /* adjust dbstart/end */ | |
6329 | + if (dbstart(dentry) < 0) | |
6330 | + dbstart(dentry) = bindex; | |
6331 | + if (bindex > dbend(dentry)) | |
6332 | + dbend(dentry) = bindex; | |
6333 | + /* | |
6334 | + * We always store the lower dentries above, and update | |
6335 | + * dbstart/dbend, even if the whole unionfs dentry is | |
6336 | + * negative (i.e., no lower inodes). | |
6337 | + */ | |
6338 | + if (!lower_dentry->d_inode) | |
6339 | + continue; | |
6340 | + num_positive++; | |
6341 | + | |
6342 | + /* | |
6343 | + * check if we just found an opaque directory, if so, stop | |
6344 | + * lookups here. | |
6345 | + */ | |
6346 | + if (!S_ISDIR(lower_dentry->d_inode->i_mode)) | |
6347 | + continue; | |
6348 | + opaque = is_opaque_dir(dentry, bindex); | |
6349 | + if (opaque < 0) { | |
6350 | + err = opaque; | |
6351 | + goto out_free; | |
6352 | + } else if (opaque) { | |
6353 | + dbend(dentry) = dbopaque(dentry) = bindex; | |
6354 | + break; | |
6355 | + } | |
6356 | + dbend(dentry) = bindex; | |
6357 | + | |
6358 | + /* update parent directory's atime with the bindex */ | |
6359 | + fsstack_copy_attr_atime(parent->d_inode, | |
6360 | + lower_dir_dentry->d_inode); | |
6361 | + } | |
6362 | + | |
6363 | + /* sanity checks, then decide if to process a negative dentry */ | |
6364 | + BUG_ON(dbstart(dentry) < 0 && dbend(dentry) >= 0); | |
6365 | + BUG_ON(dbstart(dentry) >= 0 && dbend(dentry) < 0); | |
6366 | + | |
6367 | + if (num_positive > 0) | |
6368 | + goto out_positive; | |
6369 | + | |
6370 | + /*** handle NEGATIVE dentries ***/ | |
6371 | + | |
6372 | + /* | |
6373 | + * If negative, keep only first lower negative dentry, to save on | |
6374 | + * memory. | |
6375 | + */ | |
6376 | + if (dbstart(dentry) < dbend(dentry)) { | |
6377 | + path_put_lowers(dentry, dbstart(dentry) + 1, | |
6378 | + dbend(dentry), false); | |
6379 | + dbend(dentry) = dbstart(dentry); | |
6380 | + } | |
6381 | + if (lookupmode == INTERPOSE_PARTIAL) | |
6382 | + goto out; | |
6383 | + if (lookupmode == INTERPOSE_LOOKUP) { | |
6384 | + /* | |
6385 | + * If all we found was a whiteout in the first available | |
6386 | + * branch, then create a negative dentry for a possibly new | |
6387 | + * file to be created. | |
6388 | + */ | |
6389 | + if (dbopaque(dentry) < 0) | |
6390 | + goto out; | |
6391 | + /* XXX: need to get mnt here */ | |
6392 | + bindex = dbstart(dentry); | |
6393 | + if (unionfs_lower_dentry_idx(dentry, bindex)) | |
6394 | + goto out; | |
6395 | + lower_dir_dentry = | |
6396 | + unionfs_lower_dentry_idx(parent, bindex); | |
6397 | + if (!lower_dir_dentry || !lower_dir_dentry->d_inode) | |
6398 | + goto out; | |
6399 | + if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode)) | |
6400 | + goto out; /* XXX: should be BUG_ON */ | |
6401 | + /* XXX: do we need to cross bind mounts here? */ | |
4ae1df7a | 6402 | + lower_dentry = lookup_lck_len(name, lower_dir_dentry, namelen); |
2380c486 JR |
6403 | + if (IS_ERR(lower_dentry)) { |
6404 | + err = PTR_ERR(lower_dentry); | |
6405 | + goto out; | |
6406 | + } | |
6407 | + /* XXX: need to mntget/mntput as needed too! */ | |
6408 | + unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry); | |
6409 | + /* XXX: wrong mnt for crossing bind mounts! */ | |
6410 | + lower_mnt = unionfs_mntget(dentry->d_sb->s_root, bindex); | |
6411 | + unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt); | |
6412 | + | |
6413 | + goto out; | |
6414 | + } | |
6415 | + | |
6416 | + /* if we're revalidating a positive dentry, don't make it negative */ | |
6417 | + if (lookupmode != INTERPOSE_REVAL) | |
6418 | + d_add(dentry, NULL); | |
6419 | + | |
6420 | + goto out; | |
6421 | + | |
6422 | +out_positive: | |
6423 | + /*** handle POSITIVE dentries ***/ | |
6424 | + | |
6425 | + /* | |
6426 | + * This unionfs dentry is positive (at least one lower inode | |
6427 | + * exists), so scan entire dentry from beginning to end, and remove | |
6428 | + * any negative lower dentries, if any. Then, update dbstart/dbend | |
6429 | + * to reflect the start/end of positive dentries. | |
6430 | + */ | |
6431 | + pos_start = pos_end = -1; | |
6432 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
6433 | + lower_dentry = unionfs_lower_dentry_idx(dentry, | |
6434 | + bindex); | |
6435 | + if (lower_dentry && lower_dentry->d_inode) { | |
6436 | + if (pos_start < 0) | |
6437 | + pos_start = bindex; | |
6438 | + if (bindex > pos_end) | |
6439 | + pos_end = bindex; | |
6440 | + continue; | |
6441 | + } | |
6442 | + path_put_lowers(dentry, bindex, bindex, false); | |
6443 | + } | |
6444 | + if (pos_start >= 0) | |
6445 | + dbstart(dentry) = pos_start; | |
6446 | + if (pos_end >= 0) | |
6447 | + dbend(dentry) = pos_end; | |
6448 | + | |
6449 | + /* Partial lookups need to re-interpose, or throw away older negs. */ | |
6450 | + if (lookupmode == INTERPOSE_PARTIAL) { | |
6451 | + if (dentry->d_inode) { | |
6452 | + unionfs_reinterpose(dentry); | |
6453 | + goto out; | |
6454 | + } | |
6455 | + | |
6456 | + /* | |
6457 | + * This dentry was positive, so it is as if we had a | |
6458 | + * negative revalidation. | |
6459 | + */ | |
6460 | + lookupmode = INTERPOSE_REVAL_NEG; | |
6461 | + update_bstart(dentry); | |
6462 | + } | |
6463 | + | |
6464 | + /* | |
6465 | + * Interpose can return a dentry if d_splice returned a different | |
6466 | + * dentry. | |
6467 | + */ | |
6468 | + d_interposed = unionfs_interpose(dentry, dentry->d_sb, lookupmode); | |
6469 | + if (IS_ERR(d_interposed)) | |
6470 | + err = PTR_ERR(d_interposed); | |
6471 | + else if (d_interposed) | |
6472 | + dentry = d_interposed; | |
6473 | + | |
6474 | + if (!err) | |
6475 | + goto out; | |
6476 | + d_drop(dentry); | |
6477 | + | |
6478 | +out_free: | |
6479 | + /* should dput/mntput all the underlying dentries on error condition */ | |
6480 | + if (dbstart(dentry) >= 0) | |
6481 | + path_put_lowers_all(dentry, false); | |
6482 | + /* free lower_paths unconditionally */ | |
6483 | + kfree(UNIONFS_D(dentry)->lower_paths); | |
6484 | + UNIONFS_D(dentry)->lower_paths = NULL; | |
6485 | + | |
6486 | +out: | |
6487 | + if (dentry && UNIONFS_D(dentry)) { | |
6488 | + BUG_ON(dbstart(dentry) < 0 && dbend(dentry) >= 0); | |
6489 | + BUG_ON(dbstart(dentry) >= 0 && dbend(dentry) < 0); | |
6490 | + } | |
6491 | + if (d_interposed && UNIONFS_D(d_interposed)) { | |
6492 | + BUG_ON(dbstart(d_interposed) < 0 && dbend(d_interposed) >= 0); | |
6493 | + BUG_ON(dbstart(d_interposed) >= 0 && dbend(d_interposed) < 0); | |
6494 | + } | |
6495 | + | |
6496 | + if (!err && d_interposed) | |
6497 | + return d_interposed; | |
6498 | + return ERR_PTR(err); | |
6499 | +} | |
0c5527e5 AM |
6500 | diff --git a/fs/unionfs/main.c b/fs/unionfs/main.c |
6501 | new file mode 100644 | |
f6c5ef8b | 6502 | index 0000000..ee78f1d |
0c5527e5 AM |
6503 | --- /dev/null |
6504 | +++ b/fs/unionfs/main.c | |
6b53c3da | 6505 | @@ -0,0 +1,752 @@ |
2380c486 | 6506 | +/* |
63b09289 | 6507 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
6508 | + * Copyright (c) 2003-2006 Charles P. Wright |
6509 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
6510 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
6511 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
6512 | + * Copyright (c) 2004-2006 David P. Quigley | |
6513 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
6514 | + * Copyright (c) 2003 Puja Gupta | |
6515 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
6516 | + * Copyright (c) 2003-2011 Stony Brook University |
6517 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
6518 | + * |
6519 | + * This program is free software; you can redistribute it and/or modify | |
6520 | + * it under the terms of the GNU General Public License version 2 as | |
6521 | + * published by the Free Software Foundation. | |
6522 | + */ | |
6523 | + | |
6524 | +#include "union.h" | |
6525 | +#include <linux/module.h> | |
6526 | +#include <linux/moduleparam.h> | |
6527 | + | |
6528 | +static void unionfs_fill_inode(struct dentry *dentry, | |
6529 | + struct inode *inode) | |
6530 | +{ | |
6531 | + struct inode *lower_inode; | |
6532 | + struct dentry *lower_dentry; | |
6533 | + int bindex, bstart, bend; | |
6534 | + | |
6535 | + bstart = dbstart(dentry); | |
6536 | + bend = dbend(dentry); | |
6537 | + | |
6538 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
6539 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
6540 | + if (!lower_dentry) { | |
6541 | + unionfs_set_lower_inode_idx(inode, bindex, NULL); | |
6542 | + continue; | |
6543 | + } | |
6544 | + | |
6545 | + /* Initialize the lower inode to the new lower inode. */ | |
6546 | + if (!lower_dentry->d_inode) | |
6547 | + continue; | |
6548 | + | |
6549 | + unionfs_set_lower_inode_idx(inode, bindex, | |
6550 | + igrab(lower_dentry->d_inode)); | |
6551 | + } | |
6552 | + | |
6553 | + ibstart(inode) = dbstart(dentry); | |
6554 | + ibend(inode) = dbend(dentry); | |
6555 | + | |
6556 | + /* Use attributes from the first branch. */ | |
6557 | + lower_inode = unionfs_lower_inode(inode); | |
6558 | + | |
6559 | + /* Use different set of inode ops for symlinks & directories */ | |
6560 | + if (S_ISLNK(lower_inode->i_mode)) | |
6561 | + inode->i_op = &unionfs_symlink_iops; | |
6562 | + else if (S_ISDIR(lower_inode->i_mode)) | |
6563 | + inode->i_op = &unionfs_dir_iops; | |
6564 | + | |
6565 | + /* Use different set of file ops for directories */ | |
6566 | + if (S_ISDIR(lower_inode->i_mode)) | |
6567 | + inode->i_fop = &unionfs_dir_fops; | |
6568 | + | |
6569 | + /* properly initialize special inodes */ | |
6570 | + if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) || | |
6571 | + S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode)) | |
6572 | + init_special_inode(inode, lower_inode->i_mode, | |
6573 | + lower_inode->i_rdev); | |
6574 | + | |
6575 | + /* all well, copy inode attributes */ | |
6576 | + unionfs_copy_attr_all(inode, lower_inode); | |
6577 | + fsstack_copy_inode_size(inode, lower_inode); | |
6578 | +} | |
6579 | + | |
6580 | +/* | |
6581 | + * Connect a unionfs inode dentry/inode with several lower ones. This is | |
6582 | + * the classic stackable file system "vnode interposition" action. | |
6583 | + * | |
6584 | + * @sb: unionfs's super_block | |
6585 | + */ | |
6586 | +struct dentry *unionfs_interpose(struct dentry *dentry, struct super_block *sb, | |
6587 | + int flag) | |
6588 | +{ | |
6589 | + int err = 0; | |
6590 | + struct inode *inode; | |
6591 | + int need_fill_inode = 1; | |
6592 | + struct dentry *spliced = NULL; | |
6593 | + | |
6594 | + verify_locked(dentry); | |
6595 | + | |
6596 | + /* | |
6597 | + * We allocate our new inode below by calling unionfs_iget, | |
6598 | + * which will initialize some of the new inode's fields | |
6599 | + */ | |
6600 | + | |
6601 | + /* | |
6602 | + * On revalidate we've already got our own inode and just need | |
6603 | + * to fix it up. | |
6604 | + */ | |
6605 | + if (flag == INTERPOSE_REVAL) { | |
6606 | + inode = dentry->d_inode; | |
6607 | + UNIONFS_I(inode)->bstart = -1; | |
6608 | + UNIONFS_I(inode)->bend = -1; | |
6609 | + atomic_set(&UNIONFS_I(inode)->generation, | |
6610 | + atomic_read(&UNIONFS_SB(sb)->generation)); | |
6611 | + | |
6612 | + UNIONFS_I(inode)->lower_inodes = | |
6613 | + kcalloc(sbmax(sb), sizeof(struct inode *), GFP_KERNEL); | |
6614 | + if (unlikely(!UNIONFS_I(inode)->lower_inodes)) { | |
6615 | + err = -ENOMEM; | |
6616 | + goto out; | |
6617 | + } | |
6618 | + } else { | |
6619 | + /* get unique inode number for unionfs */ | |
6620 | + inode = unionfs_iget(sb, iunique(sb, UNIONFS_ROOT_INO)); | |
6621 | + if (IS_ERR(inode)) { | |
6622 | + err = PTR_ERR(inode); | |
6623 | + goto out; | |
6624 | + } | |
6625 | + if (atomic_read(&inode->i_count) > 1) | |
6626 | + goto skip; | |
6627 | + } | |
6628 | + | |
6629 | + need_fill_inode = 0; | |
6630 | + unionfs_fill_inode(dentry, inode); | |
6631 | + | |
6632 | +skip: | |
6633 | + /* only (our) lookup wants to do a d_add */ | |
6634 | + switch (flag) { | |
6635 | + case INTERPOSE_DEFAULT: | |
6636 | + /* for operations which create new inodes */ | |
6637 | + d_add(dentry, inode); | |
6638 | + break; | |
6639 | + case INTERPOSE_REVAL_NEG: | |
6640 | + d_instantiate(dentry, inode); | |
6641 | + break; | |
6642 | + case INTERPOSE_LOOKUP: | |
6643 | + spliced = d_splice_alias(inode, dentry); | |
6644 | + if (spliced && spliced != dentry) { | |
6645 | + /* | |
6646 | + * d_splice can return a dentry if it was | |
6647 | + * disconnected and had to be moved. We must ensure | |
6648 | + * that the private data of the new dentry is | |
6649 | + * correct and that the inode info was filled | |
6650 | + * properly. Finally we must return this new | |
6651 | + * dentry. | |
6652 | + */ | |
6b53c3da | 6653 | + d_set_d_op(spliced, &unionfs_dops); |
2380c486 JR |
6654 | + spliced->d_fsdata = dentry->d_fsdata; |
6655 | + dentry->d_fsdata = NULL; | |
6656 | + dentry = spliced; | |
6657 | + if (need_fill_inode) { | |
6658 | + need_fill_inode = 0; | |
6659 | + unionfs_fill_inode(dentry, inode); | |
6660 | + } | |
6661 | + goto out_spliced; | |
6662 | + } else if (!spliced) { | |
6663 | + if (need_fill_inode) { | |
6664 | + need_fill_inode = 0; | |
6665 | + unionfs_fill_inode(dentry, inode); | |
6666 | + goto out_spliced; | |
6667 | + } | |
6668 | + } | |
6669 | + break; | |
6670 | + case INTERPOSE_REVAL: | |
6671 | + /* Do nothing. */ | |
6672 | + break; | |
6673 | + default: | |
6674 | + printk(KERN_CRIT "unionfs: invalid interpose flag passed!\n"); | |
6675 | + BUG(); | |
6676 | + } | |
6677 | + goto out; | |
6678 | + | |
6679 | +out_spliced: | |
6680 | + if (!err) | |
6681 | + return spliced; | |
6682 | +out: | |
6683 | + return ERR_PTR(err); | |
6684 | +} | |
6685 | + | |
6686 | +/* like interpose above, but for an already existing dentry */ | |
6687 | +void unionfs_reinterpose(struct dentry *dentry) | |
6688 | +{ | |
6689 | + struct dentry *lower_dentry; | |
6690 | + struct inode *inode; | |
6691 | + int bindex, bstart, bend; | |
6692 | + | |
6693 | + verify_locked(dentry); | |
6694 | + | |
6695 | + /* This is pre-allocated inode */ | |
6696 | + inode = dentry->d_inode; | |
6697 | + | |
6698 | + bstart = dbstart(dentry); | |
6699 | + bend = dbend(dentry); | |
6700 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
6701 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
6702 | + if (!lower_dentry) | |
6703 | + continue; | |
6704 | + | |
6705 | + if (!lower_dentry->d_inode) | |
6706 | + continue; | |
6707 | + if (unionfs_lower_inode_idx(inode, bindex)) | |
6708 | + continue; | |
6709 | + unionfs_set_lower_inode_idx(inode, bindex, | |
6710 | + igrab(lower_dentry->d_inode)); | |
6711 | + } | |
6712 | + ibstart(inode) = dbstart(dentry); | |
6713 | + ibend(inode) = dbend(dentry); | |
6714 | +} | |
6715 | + | |
6716 | +/* | |
6717 | + * make sure the branch we just looked up (nd) makes sense: | |
6718 | + * | |
6719 | + * 1) we're not trying to stack unionfs on top of unionfs | |
6720 | + * 2) it exists | |
6721 | + * 3) is a directory | |
6722 | + */ | |
63b09289 | 6723 | +int check_branch(const struct path *path) |
2380c486 JR |
6724 | +{ |
6725 | + /* XXX: remove in ODF code -- stacking unions allowed there */ | |
63b09289 | 6726 | + if (!strcmp(path->dentry->d_sb->s_type->name, UNIONFS_NAME)) |
2380c486 | 6727 | + return -EINVAL; |
63b09289 | 6728 | + if (!path->dentry->d_inode) |
2380c486 | 6729 | + return -ENOENT; |
63b09289 | 6730 | + if (!S_ISDIR(path->dentry->d_inode->i_mode)) |
2380c486 JR |
6731 | + return -ENOTDIR; |
6732 | + return 0; | |
6733 | +} | |
6734 | + | |
6735 | +/* checks if two lower_dentries have overlapping branches */ | |
6736 | +static int is_branch_overlap(struct dentry *dent1, struct dentry *dent2) | |
6737 | +{ | |
6738 | + struct dentry *dent = NULL; | |
6739 | + | |
6740 | + dent = dent1; | |
6741 | + while ((dent != dent2) && (dent->d_parent != dent)) | |
6742 | + dent = dent->d_parent; | |
6743 | + | |
6744 | + if (dent == dent2) | |
6745 | + return 1; | |
6746 | + | |
6747 | + dent = dent2; | |
6748 | + while ((dent != dent1) && (dent->d_parent != dent)) | |
6749 | + dent = dent->d_parent; | |
6750 | + | |
6751 | + return (dent == dent1); | |
6752 | +} | |
6753 | + | |
6754 | +/* | |
6755 | + * Parse "ro" or "rw" options, but default to "rw" if no mode options was | |
6756 | + * specified. Fill the mode bits in @perms. If encounter an unknown | |
6757 | + * string, return -EINVAL. Otherwise return 0. | |
6758 | + */ | |
6759 | +int parse_branch_mode(const char *name, int *perms) | |
6760 | +{ | |
6761 | + if (!name || !strcmp(name, "rw")) { | |
6762 | + *perms = MAY_READ | MAY_WRITE; | |
6763 | + return 0; | |
6764 | + } | |
6765 | + if (!strcmp(name, "ro")) { | |
6766 | + *perms = MAY_READ; | |
6767 | + return 0; | |
6768 | + } | |
6769 | + return -EINVAL; | |
6770 | +} | |
6771 | + | |
6772 | +/* | |
6773 | + * parse the dirs= mount argument | |
6774 | + * | |
6775 | + * We don't need to lock the superblock private data's rwsem, as we get | |
6776 | + * called only by unionfs_read_super - it is still a long time before anyone | |
6777 | + * can even get a reference to us. | |
6778 | + */ | |
6779 | +static int parse_dirs_option(struct super_block *sb, struct unionfs_dentry_info | |
6780 | + *lower_root_info, char *options) | |
6781 | +{ | |
63b09289 | 6782 | + struct path path; |
2380c486 JR |
6783 | + char *name; |
6784 | + int err = 0; | |
6785 | + int branches = 1; | |
6786 | + int bindex = 0; | |
6787 | + int i = 0; | |
6788 | + int j = 0; | |
6789 | + struct dentry *dent1; | |
6790 | + struct dentry *dent2; | |
6791 | + | |
6792 | + if (options[0] == '\0') { | |
6793 | + printk(KERN_ERR "unionfs: no branches specified\n"); | |
6794 | + err = -EINVAL; | |
82260373 | 6795 | + goto out_return; |
2380c486 JR |
6796 | + } |
6797 | + | |
6798 | + /* | |
6799 | + * Each colon means we have a separator, this is really just a rough | |
6800 | + * guess, since strsep will handle empty fields for us. | |
6801 | + */ | |
6802 | + for (i = 0; options[i]; i++) | |
6803 | + if (options[i] == ':') | |
6804 | + branches++; | |
6805 | + | |
6806 | + /* allocate space for underlying pointers to lower dentry */ | |
6807 | + UNIONFS_SB(sb)->data = | |
6808 | + kcalloc(branches, sizeof(struct unionfs_data), GFP_KERNEL); | |
6809 | + if (unlikely(!UNIONFS_SB(sb)->data)) { | |
6810 | + err = -ENOMEM; | |
82260373 | 6811 | + goto out_return; |
2380c486 JR |
6812 | + } |
6813 | + | |
6814 | + lower_root_info->lower_paths = | |
6815 | + kcalloc(branches, sizeof(struct path), GFP_KERNEL); | |
6816 | + if (unlikely(!lower_root_info->lower_paths)) { | |
6817 | + err = -ENOMEM; | |
82260373 AM |
6818 | + /* free the underlying pointer array */ |
6819 | + kfree(UNIONFS_SB(sb)->data); | |
6820 | + UNIONFS_SB(sb)->data = NULL; | |
6821 | + goto out_return; | |
2380c486 JR |
6822 | + } |
6823 | + | |
6824 | + /* now parsing a string such as "b1:b2=rw:b3=ro:b4" */ | |
6825 | + branches = 0; | |
6826 | + while ((name = strsep(&options, ":")) != NULL) { | |
6827 | + int perms; | |
6828 | + char *mode = strchr(name, '='); | |
6829 | + | |
6830 | + if (!name) | |
6831 | + continue; | |
6832 | + if (!*name) { /* bad use of ':' (extra colons) */ | |
6833 | + err = -EINVAL; | |
6834 | + goto out; | |
6835 | + } | |
6836 | + | |
6837 | + branches++; | |
6838 | + | |
6839 | + /* strip off '=' if any */ | |
6840 | + if (mode) | |
6841 | + *mode++ = '\0'; | |
6842 | + | |
6843 | + err = parse_branch_mode(mode, &perms); | |
6844 | + if (err) { | |
6845 | + printk(KERN_ERR "unionfs: invalid mode \"%s\" for " | |
6846 | + "branch %d\n", mode, bindex); | |
6847 | + goto out; | |
6848 | + } | |
6849 | + /* ensure that leftmost branch is writeable */ | |
6850 | + if (!bindex && !(perms & MAY_WRITE)) { | |
6851 | + printk(KERN_ERR "unionfs: leftmost branch cannot be " | |
6852 | + "read-only (use \"-o ro\" to create a " | |
6853 | + "read-only union)\n"); | |
6854 | + err = -EINVAL; | |
6855 | + goto out; | |
6856 | + } | |
6857 | + | |
63b09289 | 6858 | + err = kern_path(name, LOOKUP_FOLLOW, &path); |
2380c486 JR |
6859 | + if (err) { |
6860 | + printk(KERN_ERR "unionfs: error accessing " | |
6861 | + "lower directory '%s' (error %d)\n", | |
6862 | + name, err); | |
6863 | + goto out; | |
6864 | + } | |
6865 | + | |
63b09289 | 6866 | + err = check_branch(&path); |
2380c486 JR |
6867 | + if (err) { |
6868 | + printk(KERN_ERR "unionfs: lower directory " | |
6869 | + "'%s' is not a valid branch\n", name); | |
63b09289 | 6870 | + path_put(&path); |
2380c486 JR |
6871 | + goto out; |
6872 | + } | |
6873 | + | |
63b09289 JR |
6874 | + lower_root_info->lower_paths[bindex].dentry = path.dentry; |
6875 | + lower_root_info->lower_paths[bindex].mnt = path.mnt; | |
2380c486 JR |
6876 | + |
6877 | + set_branchperms(sb, bindex, perms); | |
6878 | + set_branch_count(sb, bindex, 0); | |
6879 | + new_branch_id(sb, bindex); | |
6880 | + | |
6881 | + if (lower_root_info->bstart < 0) | |
6882 | + lower_root_info->bstart = bindex; | |
6883 | + lower_root_info->bend = bindex; | |
6884 | + bindex++; | |
6885 | + } | |
6886 | + | |
6887 | + if (branches == 0) { | |
6888 | + printk(KERN_ERR "unionfs: no branches specified\n"); | |
6889 | + err = -EINVAL; | |
6890 | + goto out; | |
6891 | + } | |
6892 | + | |
6893 | + BUG_ON(branches != (lower_root_info->bend + 1)); | |
6894 | + | |
6895 | + /* | |
6896 | + * Ensure that no overlaps exist in the branches. | |
6897 | + * | |
6898 | + * This test is required because the Linux kernel has no support | |
6899 | + * currently for ensuring coherency between stackable layers and | |
6900 | + * branches. If we were to allow overlapping branches, it would be | |
6901 | + * possible, for example, to delete a file via one branch, which | |
6902 | + * would not be reflected in another branch. Such incoherency could | |
6903 | + * lead to inconsistencies and even kernel oopses. Rather than | |
6904 | + * implement hacks to work around some of these cache-coherency | |
6905 | + * problems, we prevent branch overlapping, for now. A complete | |
6906 | + * solution will involve proper kernel/VFS support for cache | |
6907 | + * coherency, at which time we could safely remove this | |
6908 | + * branch-overlapping test. | |
6909 | + */ | |
6910 | + for (i = 0; i < branches; i++) { | |
6911 | + dent1 = lower_root_info->lower_paths[i].dentry; | |
6912 | + for (j = i + 1; j < branches; j++) { | |
6913 | + dent2 = lower_root_info->lower_paths[j].dentry; | |
6914 | + if (is_branch_overlap(dent1, dent2)) { | |
6915 | + printk(KERN_ERR "unionfs: branches %d and " | |
6916 | + "%d overlap\n", i, j); | |
6917 | + err = -EINVAL; | |
6918 | + goto out; | |
6919 | + } | |
6920 | + } | |
6921 | + } | |
6922 | + | |
6923 | +out: | |
6924 | + if (err) { | |
6925 | + for (i = 0; i < branches; i++) | |
6926 | + path_put(&lower_root_info->lower_paths[i]); | |
6927 | + | |
6928 | + kfree(lower_root_info->lower_paths); | |
6929 | + kfree(UNIONFS_SB(sb)->data); | |
6930 | + | |
6931 | + /* | |
6932 | + * MUST clear the pointers to prevent potential double free if | |
6933 | + * the caller dies later on | |
6934 | + */ | |
6935 | + lower_root_info->lower_paths = NULL; | |
6936 | + UNIONFS_SB(sb)->data = NULL; | |
6937 | + } | |
82260373 | 6938 | +out_return: |
2380c486 JR |
6939 | + return err; |
6940 | +} | |
6941 | + | |
6942 | +/* | |
6943 | + * Parse mount options. See the manual page for usage instructions. | |
6944 | + * | |
6945 | + * Returns the dentry object of the lower-level (lower) directory; | |
6946 | + * We want to mount our stackable file system on top of that lower directory. | |
6947 | + */ | |
6948 | +static struct unionfs_dentry_info *unionfs_parse_options( | |
6949 | + struct super_block *sb, | |
6950 | + char *options) | |
6951 | +{ | |
6952 | + struct unionfs_dentry_info *lower_root_info; | |
6953 | + char *optname; | |
6954 | + int err = 0; | |
6955 | + int bindex; | |
6956 | + int dirsfound = 0; | |
6957 | + | |
6958 | + /* allocate private data area */ | |
6959 | + err = -ENOMEM; | |
6960 | + lower_root_info = | |
6961 | + kzalloc(sizeof(struct unionfs_dentry_info), GFP_KERNEL); | |
6962 | + if (unlikely(!lower_root_info)) | |
6963 | + goto out_error; | |
6964 | + lower_root_info->bstart = -1; | |
6965 | + lower_root_info->bend = -1; | |
6966 | + lower_root_info->bopaque = -1; | |
6967 | + | |
6968 | + while ((optname = strsep(&options, ",")) != NULL) { | |
6969 | + char *optarg; | |
6970 | + | |
6971 | + if (!optname || !*optname) | |
6972 | + continue; | |
6973 | + | |
6974 | + optarg = strchr(optname, '='); | |
6975 | + if (optarg) | |
6976 | + *optarg++ = '\0'; | |
6977 | + | |
6978 | + /* | |
6979 | + * All of our options take an argument now. Insert ones that | |
6980 | + * don't, above this check. | |
6981 | + */ | |
6982 | + if (!optarg) { | |
6983 | + printk(KERN_ERR "unionfs: %s requires an argument\n", | |
6984 | + optname); | |
6985 | + err = -EINVAL; | |
6986 | + goto out_error; | |
6987 | + } | |
6988 | + | |
6989 | + if (!strcmp("dirs", optname)) { | |
6990 | + if (++dirsfound > 1) { | |
6991 | + printk(KERN_ERR | |
6992 | + "unionfs: multiple dirs specified\n"); | |
6993 | + err = -EINVAL; | |
6994 | + goto out_error; | |
6995 | + } | |
6996 | + err = parse_dirs_option(sb, lower_root_info, optarg); | |
6997 | + if (err) | |
6998 | + goto out_error; | |
6999 | + continue; | |
7000 | + } | |
7001 | + | |
7002 | + err = -EINVAL; | |
7003 | + printk(KERN_ERR | |
7004 | + "unionfs: unrecognized option '%s'\n", optname); | |
7005 | + goto out_error; | |
7006 | + } | |
7007 | + if (dirsfound != 1) { | |
7008 | + printk(KERN_ERR "unionfs: dirs option required\n"); | |
7009 | + err = -EINVAL; | |
7010 | + goto out_error; | |
7011 | + } | |
7012 | + goto out; | |
7013 | + | |
7014 | +out_error: | |
7015 | + if (lower_root_info && lower_root_info->lower_paths) { | |
7016 | + for (bindex = lower_root_info->bstart; | |
7017 | + bindex >= 0 && bindex <= lower_root_info->bend; | |
7018 | + bindex++) | |
7019 | + path_put(&lower_root_info->lower_paths[bindex]); | |
7020 | + } | |
7021 | + | |
7022 | + kfree(lower_root_info->lower_paths); | |
7023 | + kfree(lower_root_info); | |
7024 | + | |
7025 | + kfree(UNIONFS_SB(sb)->data); | |
7026 | + UNIONFS_SB(sb)->data = NULL; | |
7027 | + | |
7028 | + lower_root_info = ERR_PTR(err); | |
7029 | +out: | |
7030 | + return lower_root_info; | |
7031 | +} | |
7032 | + | |
7033 | +/* | |
2380c486 JR |
7034 | + * There is no need to lock the unionfs_super_info's rwsem as there is no |
7035 | + * way anyone can have a reference to the superblock at this point in time. | |
7036 | + */ | |
7037 | +static int unionfs_read_super(struct super_block *sb, void *raw_data, | |
7038 | + int silent) | |
7039 | +{ | |
7040 | + int err = 0; | |
7041 | + struct unionfs_dentry_info *lower_root_info = NULL; | |
7042 | + int bindex, bstart, bend; | |
6b53c3da | 7043 | + struct inode *inode = NULL; |
2380c486 JR |
7044 | + |
7045 | + if (!raw_data) { | |
7046 | + printk(KERN_ERR | |
7047 | + "unionfs: read_super: missing data argument\n"); | |
7048 | + err = -EINVAL; | |
7049 | + goto out; | |
7050 | + } | |
7051 | + | |
7052 | + /* Allocate superblock private data */ | |
7053 | + sb->s_fs_info = kzalloc(sizeof(struct unionfs_sb_info), GFP_KERNEL); | |
7054 | + if (unlikely(!UNIONFS_SB(sb))) { | |
7055 | + printk(KERN_CRIT "unionfs: read_super: out of memory\n"); | |
7056 | + err = -ENOMEM; | |
7057 | + goto out; | |
7058 | + } | |
7059 | + | |
7060 | + UNIONFS_SB(sb)->bend = -1; | |
7061 | + atomic_set(&UNIONFS_SB(sb)->generation, 1); | |
7062 | + init_rwsem(&UNIONFS_SB(sb)->rwsem); | |
7063 | + UNIONFS_SB(sb)->high_branch_id = -1; /* -1 == invalid branch ID */ | |
7064 | + | |
7065 | + lower_root_info = unionfs_parse_options(sb, raw_data); | |
7066 | + if (IS_ERR(lower_root_info)) { | |
7067 | + printk(KERN_ERR | |
7068 | + "unionfs: read_super: error while parsing options " | |
7069 | + "(err = %ld)\n", PTR_ERR(lower_root_info)); | |
7070 | + err = PTR_ERR(lower_root_info); | |
7071 | + lower_root_info = NULL; | |
7072 | + goto out_free; | |
7073 | + } | |
7074 | + if (lower_root_info->bstart == -1) { | |
7075 | + err = -ENOENT; | |
7076 | + goto out_free; | |
7077 | + } | |
7078 | + | |
7079 | + /* set the lower superblock field of upper superblock */ | |
7080 | + bstart = lower_root_info->bstart; | |
7081 | + BUG_ON(bstart != 0); | |
7082 | + sbend(sb) = bend = lower_root_info->bend; | |
7083 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
7084 | + struct dentry *d = lower_root_info->lower_paths[bindex].dentry; | |
7085 | + atomic_inc(&d->d_sb->s_active); | |
7086 | + unionfs_set_lower_super_idx(sb, bindex, d->d_sb); | |
7087 | + } | |
7088 | + | |
7089 | + /* max Bytes is the maximum bytes from highest priority branch */ | |
7090 | + sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes; | |
7091 | + | |
7092 | + /* | |
7093 | + * Our c/m/atime granularity is 1 ns because we may stack on file | |
7094 | + * systems whose granularity is as good. This is important for our | |
7095 | + * time-based cache coherency. | |
7096 | + */ | |
7097 | + sb->s_time_gran = 1; | |
7098 | + | |
7099 | + sb->s_op = &unionfs_sops; | |
7100 | + | |
6b53c3da AM |
7101 | + /* get a new inode and allocate our root dentry */ |
7102 | + inode = unionfs_iget(sb, iunique(sb, UNIONFS_ROOT_INO)); | |
7103 | + if (IS_ERR(inode)) { | |
7104 | + err = PTR_ERR(inode); | |
7105 | + goto out_dput; | |
7106 | + } | |
92d182d2 | 7107 | + sb->s_root = d_make_root(inode); |
2380c486 JR |
7108 | + if (unlikely(!sb->s_root)) { |
7109 | + err = -ENOMEM; | |
92d182d2 | 7110 | + goto out_dput; |
2380c486 | 7111 | + } |
6b53c3da | 7112 | + d_set_d_op(sb->s_root, &unionfs_dops); |
2380c486 JR |
7113 | + |
7114 | + /* link the upper and lower dentries */ | |
7115 | + sb->s_root->d_fsdata = NULL; | |
7116 | + err = new_dentry_private_data(sb->s_root, UNIONFS_DMUTEX_ROOT); | |
7117 | + if (unlikely(err)) | |
7118 | + goto out_freedpd; | |
7119 | + | |
6b53c3da AM |
7120 | + /* if get here: cannot have error */ |
7121 | + | |
2380c486 JR |
7122 | + /* Set the lower dentries for s_root */ |
7123 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
7124 | + struct dentry *d; | |
7125 | + struct vfsmount *m; | |
7126 | + | |
7127 | + d = lower_root_info->lower_paths[bindex].dentry; | |
7128 | + m = lower_root_info->lower_paths[bindex].mnt; | |
7129 | + | |
7130 | + unionfs_set_lower_dentry_idx(sb->s_root, bindex, d); | |
7131 | + unionfs_set_lower_mnt_idx(sb->s_root, bindex, m); | |
7132 | + } | |
7133 | + dbstart(sb->s_root) = bstart; | |
7134 | + dbend(sb->s_root) = bend; | |
7135 | + | |
7136 | + /* Set the generation number to one, since this is for the mount. */ | |
7137 | + atomic_set(&UNIONFS_D(sb->s_root)->generation, 1); | |
7138 | + | |
6b53c3da AM |
7139 | + if (atomic_read(&inode->i_count) <= 1) |
7140 | + unionfs_fill_inode(sb->s_root, inode); | |
7141 | + | |
2380c486 | 7142 | + /* |
6b53c3da AM |
7143 | + * No need to call interpose because we already have a positive |
7144 | + * dentry, which was instantiated by d_alloc_root. Just need to | |
7145 | + * d_rehash it. | |
2380c486 | 7146 | + */ |
6b53c3da AM |
7147 | + d_rehash(sb->s_root); |
7148 | + | |
2380c486 | 7149 | + unionfs_unlock_dentry(sb->s_root); |
6b53c3da | 7150 | + goto out; /* all is well */ |
2380c486 JR |
7151 | + |
7152 | +out_freedpd: | |
7153 | + if (UNIONFS_D(sb->s_root)) { | |
7154 | + kfree(UNIONFS_D(sb->s_root)->lower_paths); | |
7155 | + free_dentry_private_data(sb->s_root); | |
7156 | + } | |
7157 | + dput(sb->s_root); | |
7158 | + | |
6b53c3da AM |
7159 | +out_iput: |
7160 | + iput(inode); | |
7161 | + | |
2380c486 JR |
7162 | +out_dput: |
7163 | + if (lower_root_info && !IS_ERR(lower_root_info)) { | |
7164 | + for (bindex = lower_root_info->bstart; | |
7165 | + bindex <= lower_root_info->bend; bindex++) { | |
7166 | + struct dentry *d; | |
7167 | + d = lower_root_info->lower_paths[bindex].dentry; | |
7168 | + /* drop refs we took earlier */ | |
7169 | + atomic_dec(&d->d_sb->s_active); | |
7170 | + path_put(&lower_root_info->lower_paths[bindex]); | |
7171 | + } | |
7172 | + kfree(lower_root_info->lower_paths); | |
7173 | + kfree(lower_root_info); | |
7174 | + lower_root_info = NULL; | |
7175 | + } | |
7176 | + | |
7177 | +out_free: | |
7178 | + kfree(UNIONFS_SB(sb)->data); | |
7179 | + kfree(UNIONFS_SB(sb)); | |
7180 | + sb->s_fs_info = NULL; | |
7181 | + | |
7182 | +out: | |
7183 | + if (lower_root_info && !IS_ERR(lower_root_info)) { | |
7184 | + kfree(lower_root_info->lower_paths); | |
7185 | + kfree(lower_root_info); | |
7186 | + } | |
7187 | + return err; | |
7188 | +} | |
7189 | + | |
63b09289 JR |
7190 | +static struct dentry *unionfs_mount(struct file_system_type *fs_type, |
7191 | + int flags, const char *dev_name, | |
7192 | + void *raw_data) | |
2380c486 | 7193 | +{ |
63b09289 JR |
7194 | + struct dentry *dentry; |
7195 | + | |
7196 | + dentry = mount_nodev(fs_type, flags, raw_data, unionfs_read_super); | |
f6c5ef8b | 7197 | + if (!IS_ERR(dentry)) |
63b09289 | 7198 | + UNIONFS_SB(dentry->d_sb)->dev_name = |
2380c486 | 7199 | + kstrdup(dev_name, GFP_KERNEL); |
63b09289 | 7200 | + return dentry; |
2380c486 JR |
7201 | +} |
7202 | + | |
7203 | +static struct file_system_type unionfs_fs_type = { | |
7204 | + .owner = THIS_MODULE, | |
7205 | + .name = UNIONFS_NAME, | |
63b09289 | 7206 | + .mount = unionfs_mount, |
2380c486 JR |
7207 | + .kill_sb = generic_shutdown_super, |
7208 | + .fs_flags = FS_REVAL_DOT, | |
7209 | +}; | |
7210 | + | |
7211 | +static int __init init_unionfs_fs(void) | |
7212 | +{ | |
7213 | + int err; | |
7214 | + | |
7215 | + pr_info("Registering unionfs " UNIONFS_VERSION "\n"); | |
7216 | + | |
7217 | + err = unionfs_init_filldir_cache(); | |
7218 | + if (unlikely(err)) | |
7219 | + goto out; | |
7220 | + err = unionfs_init_inode_cache(); | |
7221 | + if (unlikely(err)) | |
7222 | + goto out; | |
7223 | + err = unionfs_init_dentry_cache(); | |
7224 | + if (unlikely(err)) | |
7225 | + goto out; | |
7226 | + err = init_sioq(); | |
7227 | + if (unlikely(err)) | |
7228 | + goto out; | |
7229 | + err = register_filesystem(&unionfs_fs_type); | |
7230 | +out: | |
7231 | + if (unlikely(err)) { | |
7232 | + stop_sioq(); | |
7233 | + unionfs_destroy_filldir_cache(); | |
7234 | + unionfs_destroy_inode_cache(); | |
7235 | + unionfs_destroy_dentry_cache(); | |
7236 | + } | |
7237 | + return err; | |
7238 | +} | |
7239 | + | |
7240 | +static void __exit exit_unionfs_fs(void) | |
7241 | +{ | |
7242 | + stop_sioq(); | |
7243 | + unionfs_destroy_filldir_cache(); | |
7244 | + unionfs_destroy_inode_cache(); | |
7245 | + unionfs_destroy_dentry_cache(); | |
7246 | + unregister_filesystem(&unionfs_fs_type); | |
7247 | + pr_info("Completed unionfs module unload\n"); | |
7248 | +} | |
7249 | + | |
7250 | +MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University" | |
7251 | + " (http://www.fsl.cs.sunysb.edu)"); | |
7252 | +MODULE_DESCRIPTION("Unionfs " UNIONFS_VERSION | |
7253 | + " (http://unionfs.filesystems.org)"); | |
7254 | +MODULE_LICENSE("GPL"); | |
7255 | + | |
7256 | +module_init(init_unionfs_fs); | |
7257 | +module_exit(exit_unionfs_fs); | |
0c5527e5 AM |
7258 | diff --git a/fs/unionfs/mmap.c b/fs/unionfs/mmap.c |
7259 | new file mode 100644 | |
63b09289 | 7260 | index 0000000..bcc5652 |
0c5527e5 AM |
7261 | --- /dev/null |
7262 | +++ b/fs/unionfs/mmap.c | |
2380c486 JR |
7263 | @@ -0,0 +1,89 @@ |
7264 | +/* | |
63b09289 | 7265 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
7266 | + * Copyright (c) 2003-2006 Charles P. Wright |
7267 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
7268 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
7269 | + * Copyright (c) 2006 Shaya Potter | |
7270 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
7271 | + * Copyright (c) 2004-2006 David P. Quigley | |
7272 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
7273 | + * Copyright (c) 2003 Puja Gupta | |
7274 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
7275 | + * Copyright (c) 2003-2011 Stony Brook University |
7276 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
7277 | + * |
7278 | + * This program is free software; you can redistribute it and/or modify | |
7279 | + * it under the terms of the GNU General Public License version 2 as | |
7280 | + * published by the Free Software Foundation. | |
7281 | + */ | |
7282 | + | |
7283 | +#include "union.h" | |
7284 | + | |
7285 | + | |
7286 | +/* | |
7287 | + * XXX: we need a dummy readpage handler because generic_file_mmap (which we | |
7288 | + * use in unionfs_mmap) checks for the existence of | |
7289 | + * mapping->a_ops->readpage, else it returns -ENOEXEC. The VFS will need to | |
7290 | + * be fixed to allow a file system to define vm_ops->fault without any | |
7291 | + * address_space_ops whatsoever. | |
7292 | + * | |
7293 | + * Otherwise, we don't want to use our readpage method at all. | |
7294 | + */ | |
7295 | +static int unionfs_readpage(struct file *file, struct page *page) | |
7296 | +{ | |
7297 | + BUG(); | |
7298 | + return -EINVAL; | |
7299 | +} | |
7300 | + | |
7301 | +static int unionfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf) | |
7302 | +{ | |
7303 | + int err; | |
7304 | + struct file *file, *lower_file; | |
7670a7fc | 7305 | + const struct vm_operations_struct *lower_vm_ops; |
2380c486 JR |
7306 | + struct vm_area_struct lower_vma; |
7307 | + | |
7308 | + BUG_ON(!vma); | |
7309 | + memcpy(&lower_vma, vma, sizeof(struct vm_area_struct)); | |
7310 | + file = lower_vma.vm_file; | |
7311 | + lower_vm_ops = UNIONFS_F(file)->lower_vm_ops; | |
7312 | + BUG_ON(!lower_vm_ops); | |
7313 | + | |
7314 | + lower_file = unionfs_lower_file(file); | |
7315 | + BUG_ON(!lower_file); | |
7316 | + /* | |
7317 | + * XXX: vm_ops->fault may be called in parallel. Because we have to | |
7318 | + * resort to temporarily changing the vma->vm_file to point to the | |
7319 | + * lower file, a concurrent invocation of unionfs_fault could see a | |
7320 | + * different value. In this workaround, we keep a different copy of | |
7321 | + * the vma structure in our stack, so we never expose a different | |
7322 | + * value of the vma->vm_file called to us, even temporarily. A | |
7323 | + * better fix would be to change the calling semantics of ->fault to | |
7324 | + * take an explicit file pointer. | |
7325 | + */ | |
7326 | + lower_vma.vm_file = lower_file; | |
7327 | + err = lower_vm_ops->fault(&lower_vma, vmf); | |
7328 | + return err; | |
7329 | +} | |
7330 | + | |
7331 | +/* | |
7332 | + * XXX: the default address_space_ops for unionfs is empty. We cannot set | |
7333 | + * our inode->i_mapping->a_ops to NULL because too many code paths expect | |
7334 | + * the a_ops vector to be non-NULL. | |
7335 | + */ | |
7336 | +struct address_space_operations unionfs_aops = { | |
7337 | + /* empty on purpose */ | |
7338 | +}; | |
7339 | + | |
7340 | +/* | |
7341 | + * XXX: we need a second, dummy address_space_ops vector, to be used | |
7342 | + * temporarily during unionfs_mmap, because the latter calls | |
7343 | + * generic_file_mmap, which checks if ->readpage exists, else returns | |
7344 | + * -ENOEXEC. | |
7345 | + */ | |
7346 | +struct address_space_operations unionfs_dummy_aops = { | |
7347 | + .readpage = unionfs_readpage, | |
7348 | +}; | |
7349 | + | |
7350 | +struct vm_operations_struct unionfs_vm_ops = { | |
7351 | + .fault = unionfs_fault, | |
7352 | +}; | |
0c5527e5 AM |
7353 | diff --git a/fs/unionfs/rdstate.c b/fs/unionfs/rdstate.c |
7354 | new file mode 100644 | |
63b09289 | 7355 | index 0000000..59b7333 |
0c5527e5 AM |
7356 | --- /dev/null |
7357 | +++ b/fs/unionfs/rdstate.c | |
2380c486 JR |
7358 | @@ -0,0 +1,285 @@ |
7359 | +/* | |
63b09289 | 7360 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
7361 | + * Copyright (c) 2003-2006 Charles P. Wright |
7362 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
7363 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
7364 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
7365 | + * Copyright (c) 2004-2006 David P. Quigley | |
7366 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
7367 | + * Copyright (c) 2003 Puja Gupta | |
7368 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
7369 | + * Copyright (c) 2003-2011 Stony Brook University |
7370 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
7371 | + * |
7372 | + * This program is free software; you can redistribute it and/or modify | |
7373 | + * it under the terms of the GNU General Public License version 2 as | |
7374 | + * published by the Free Software Foundation. | |
7375 | + */ | |
7376 | + | |
7377 | +#include "union.h" | |
7378 | + | |
7379 | +/* This file contains the routines for maintaining readdir state. */ | |
7380 | + | |
7381 | +/* | |
7382 | + * There are two structures here, rdstate which is a hash table | |
7383 | + * of the second structure which is a filldir_node. | |
7384 | + */ | |
7385 | + | |
7386 | +/* | |
7387 | + * This is a struct kmem_cache for filldir nodes, because we allocate a lot | |
7388 | + * of them and they shouldn't waste memory. If the node has a small name | |
7389 | + * (as defined by the dentry structure), then we use an inline name to | |
7390 | + * preserve kmalloc space. | |
7391 | + */ | |
7392 | +static struct kmem_cache *unionfs_filldir_cachep; | |
7393 | + | |
7394 | +int unionfs_init_filldir_cache(void) | |
7395 | +{ | |
7396 | + unionfs_filldir_cachep = | |
7397 | + kmem_cache_create("unionfs_filldir", | |
7398 | + sizeof(struct filldir_node), 0, | |
7399 | + SLAB_RECLAIM_ACCOUNT, NULL); | |
7400 | + | |
7401 | + return (unionfs_filldir_cachep ? 0 : -ENOMEM); | |
7402 | +} | |
7403 | + | |
7404 | +void unionfs_destroy_filldir_cache(void) | |
7405 | +{ | |
7406 | + if (unionfs_filldir_cachep) | |
7407 | + kmem_cache_destroy(unionfs_filldir_cachep); | |
7408 | +} | |
7409 | + | |
7410 | +/* | |
7411 | + * This is a tuning parameter that tells us roughly how big to make the | |
7412 | + * hash table in directory entries per page. This isn't perfect, but | |
7413 | + * at least we get a hash table size that shouldn't be too overloaded. | |
7414 | + * The following averages are based on my home directory. | |
7415 | + * 14.44693 Overall | |
7416 | + * 12.29 Single Page Directories | |
7417 | + * 117.93 Multi-page directories | |
7418 | + */ | |
7419 | +#define DENTPAGE 4096 | |
7420 | +#define DENTPERONEPAGE 12 | |
7421 | +#define DENTPERPAGE 118 | |
7422 | +#define MINHASHSIZE 1 | |
7423 | +static int guesstimate_hash_size(struct inode *inode) | |
7424 | +{ | |
7425 | + struct inode *lower_inode; | |
7426 | + int bindex; | |
7427 | + int hashsize = MINHASHSIZE; | |
7428 | + | |
7429 | + if (UNIONFS_I(inode)->hashsize > 0) | |
7430 | + return UNIONFS_I(inode)->hashsize; | |
7431 | + | |
7432 | + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { | |
7433 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
7434 | + if (!lower_inode) | |
7435 | + continue; | |
7436 | + | |
7437 | + if (i_size_read(lower_inode) == DENTPAGE) | |
7438 | + hashsize += DENTPERONEPAGE; | |
7439 | + else | |
7440 | + hashsize += (i_size_read(lower_inode) / DENTPAGE) * | |
7441 | + DENTPERPAGE; | |
7442 | + } | |
7443 | + | |
7444 | + return hashsize; | |
7445 | +} | |
7446 | + | |
7447 | +int init_rdstate(struct file *file) | |
7448 | +{ | |
7449 | + BUG_ON(sizeof(loff_t) != | |
7450 | + (sizeof(unsigned int) + sizeof(unsigned int))); | |
7451 | + BUG_ON(UNIONFS_F(file)->rdstate != NULL); | |
7452 | + | |
7453 | + UNIONFS_F(file)->rdstate = alloc_rdstate(file->f_path.dentry->d_inode, | |
7454 | + fbstart(file)); | |
7455 | + | |
7456 | + return (UNIONFS_F(file)->rdstate ? 0 : -ENOMEM); | |
7457 | +} | |
7458 | + | |
7459 | +struct unionfs_dir_state *find_rdstate(struct inode *inode, loff_t fpos) | |
7460 | +{ | |
7461 | + struct unionfs_dir_state *rdstate = NULL; | |
7462 | + struct list_head *pos; | |
7463 | + | |
7464 | + spin_lock(&UNIONFS_I(inode)->rdlock); | |
7465 | + list_for_each(pos, &UNIONFS_I(inode)->readdircache) { | |
7466 | + struct unionfs_dir_state *r = | |
7467 | + list_entry(pos, struct unionfs_dir_state, cache); | |
7468 | + if (fpos == rdstate2offset(r)) { | |
7469 | + UNIONFS_I(inode)->rdcount--; | |
7470 | + list_del(&r->cache); | |
7471 | + rdstate = r; | |
7472 | + break; | |
7473 | + } | |
7474 | + } | |
7475 | + spin_unlock(&UNIONFS_I(inode)->rdlock); | |
7476 | + return rdstate; | |
7477 | +} | |
7478 | + | |
7479 | +struct unionfs_dir_state *alloc_rdstate(struct inode *inode, int bindex) | |
7480 | +{ | |
7481 | + int i = 0; | |
7482 | + int hashsize; | |
7483 | + unsigned long mallocsize = sizeof(struct unionfs_dir_state); | |
7484 | + struct unionfs_dir_state *rdstate; | |
7485 | + | |
7486 | + hashsize = guesstimate_hash_size(inode); | |
7487 | + mallocsize += hashsize * sizeof(struct list_head); | |
7488 | + mallocsize = __roundup_pow_of_two(mallocsize); | |
7489 | + | |
7490 | + /* This should give us about 500 entries anyway. */ | |
7491 | + if (mallocsize > PAGE_SIZE) | |
7492 | + mallocsize = PAGE_SIZE; | |
7493 | + | |
7494 | + hashsize = (mallocsize - sizeof(struct unionfs_dir_state)) / | |
7495 | + sizeof(struct list_head); | |
7496 | + | |
7497 | + rdstate = kmalloc(mallocsize, GFP_KERNEL); | |
7498 | + if (unlikely(!rdstate)) | |
7499 | + return NULL; | |
7500 | + | |
7501 | + spin_lock(&UNIONFS_I(inode)->rdlock); | |
7502 | + if (UNIONFS_I(inode)->cookie >= (MAXRDCOOKIE - 1)) | |
7503 | + UNIONFS_I(inode)->cookie = 1; | |
7504 | + else | |
7505 | + UNIONFS_I(inode)->cookie++; | |
7506 | + | |
7507 | + rdstate->cookie = UNIONFS_I(inode)->cookie; | |
7508 | + spin_unlock(&UNIONFS_I(inode)->rdlock); | |
7509 | + rdstate->offset = 1; | |
7510 | + rdstate->access = jiffies; | |
7511 | + rdstate->bindex = bindex; | |
7512 | + rdstate->dirpos = 0; | |
7513 | + rdstate->hashentries = 0; | |
7514 | + rdstate->size = hashsize; | |
7515 | + for (i = 0; i < rdstate->size; i++) | |
7516 | + INIT_LIST_HEAD(&rdstate->list[i]); | |
7517 | + | |
7518 | + return rdstate; | |
7519 | +} | |
7520 | + | |
7521 | +static void free_filldir_node(struct filldir_node *node) | |
7522 | +{ | |
82260373 | 7523 | + if (node->namelen >= DNAME_INLINE_LEN) |
2380c486 JR |
7524 | + kfree(node->name); |
7525 | + kmem_cache_free(unionfs_filldir_cachep, node); | |
7526 | +} | |
7527 | + | |
7528 | +void free_rdstate(struct unionfs_dir_state *state) | |
7529 | +{ | |
7530 | + struct filldir_node *tmp; | |
7531 | + int i; | |
7532 | + | |
7533 | + for (i = 0; i < state->size; i++) { | |
7534 | + struct list_head *head = &(state->list[i]); | |
7535 | + struct list_head *pos, *n; | |
7536 | + | |
7537 | + /* traverse the list and deallocate space */ | |
7538 | + list_for_each_safe(pos, n, head) { | |
7539 | + tmp = list_entry(pos, struct filldir_node, file_list); | |
7540 | + list_del(&tmp->file_list); | |
7541 | + free_filldir_node(tmp); | |
7542 | + } | |
7543 | + } | |
7544 | + | |
7545 | + kfree(state); | |
7546 | +} | |
7547 | + | |
7548 | +struct filldir_node *find_filldir_node(struct unionfs_dir_state *rdstate, | |
7549 | + const char *name, int namelen, | |
7550 | + int is_whiteout) | |
7551 | +{ | |
7552 | + int index; | |
7553 | + unsigned int hash; | |
7554 | + struct list_head *head; | |
7555 | + struct list_head *pos; | |
7556 | + struct filldir_node *cursor = NULL; | |
7557 | + int found = 0; | |
7558 | + | |
7559 | + BUG_ON(namelen <= 0); | |
7560 | + | |
7561 | + hash = full_name_hash(name, namelen); | |
7562 | + index = hash % rdstate->size; | |
7563 | + | |
7564 | + head = &(rdstate->list[index]); | |
7565 | + list_for_each(pos, head) { | |
7566 | + cursor = list_entry(pos, struct filldir_node, file_list); | |
7567 | + | |
7568 | + if (cursor->namelen == namelen && cursor->hash == hash && | |
7569 | + !strncmp(cursor->name, name, namelen)) { | |
7570 | + /* | |
7571 | + * a duplicate exists, and hence no need to create | |
7572 | + * entry to the list | |
7573 | + */ | |
7574 | + found = 1; | |
7575 | + | |
7576 | + /* | |
7577 | + * if a duplicate is found in this branch, and is | |
7578 | + * not due to the caller looking for an entry to | |
7579 | + * whiteout, then the file system may be corrupted. | |
7580 | + */ | |
7581 | + if (unlikely(!is_whiteout && | |
7582 | + cursor->bindex == rdstate->bindex)) | |
7583 | + printk(KERN_ERR "unionfs: filldir: possible " | |
7584 | + "I/O error: a file is duplicated " | |
7585 | + "in the same branch %d: %s\n", | |
7586 | + rdstate->bindex, cursor->name); | |
7587 | + break; | |
7588 | + } | |
7589 | + } | |
7590 | + | |
7591 | + if (!found) | |
7592 | + cursor = NULL; | |
7593 | + | |
7594 | + return cursor; | |
7595 | +} | |
7596 | + | |
7597 | +int add_filldir_node(struct unionfs_dir_state *rdstate, const char *name, | |
7598 | + int namelen, int bindex, int whiteout) | |
7599 | +{ | |
7600 | + struct filldir_node *new; | |
7601 | + unsigned int hash; | |
7602 | + int index; | |
7603 | + int err = 0; | |
7604 | + struct list_head *head; | |
7605 | + | |
7606 | + BUG_ON(namelen <= 0); | |
7607 | + | |
7608 | + hash = full_name_hash(name, namelen); | |
7609 | + index = hash % rdstate->size; | |
7610 | + head = &(rdstate->list[index]); | |
7611 | + | |
7612 | + new = kmem_cache_alloc(unionfs_filldir_cachep, GFP_KERNEL); | |
7613 | + if (unlikely(!new)) { | |
7614 | + err = -ENOMEM; | |
7615 | + goto out; | |
7616 | + } | |
7617 | + | |
7618 | + INIT_LIST_HEAD(&new->file_list); | |
7619 | + new->namelen = namelen; | |
7620 | + new->hash = hash; | |
7621 | + new->bindex = bindex; | |
7622 | + new->whiteout = whiteout; | |
7623 | + | |
82260373 | 7624 | + if (namelen < DNAME_INLINE_LEN) { |
2380c486 JR |
7625 | + new->name = new->iname; |
7626 | + } else { | |
7627 | + new->name = kmalloc(namelen + 1, GFP_KERNEL); | |
7628 | + if (unlikely(!new->name)) { | |
7629 | + kmem_cache_free(unionfs_filldir_cachep, new); | |
7630 | + new = NULL; | |
7631 | + goto out; | |
7632 | + } | |
7633 | + } | |
7634 | + | |
7635 | + memcpy(new->name, name, namelen); | |
7636 | + new->name[namelen] = '\0'; | |
7637 | + | |
7638 | + rdstate->hashentries++; | |
7639 | + | |
7640 | + list_add(&(new->file_list), head); | |
7641 | +out: | |
7642 | + return err; | |
7643 | +} | |
0c5527e5 AM |
7644 | diff --git a/fs/unionfs/rename.c b/fs/unionfs/rename.c |
7645 | new file mode 100644 | |
f6c5ef8b | 7646 | index 0000000..ce85b84 |
0c5527e5 AM |
7647 | --- /dev/null |
7648 | +++ b/fs/unionfs/rename.c | |
63b09289 | 7649 | @@ -0,0 +1,522 @@ |
2380c486 | 7650 | +/* |
63b09289 | 7651 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
7652 | + * Copyright (c) 2003-2006 Charles P. Wright |
7653 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
7654 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
7655 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
7656 | + * Copyright (c) 2004-2006 David P. Quigley | |
7657 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
7658 | + * Copyright (c) 2003 Puja Gupta | |
7659 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
7660 | + * Copyright (c) 2003-2011 Stony Brook University |
7661 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
7662 | + * |
7663 | + * This program is free software; you can redistribute it and/or modify | |
7664 | + * it under the terms of the GNU General Public License version 2 as | |
7665 | + * published by the Free Software Foundation. | |
7666 | + */ | |
7667 | + | |
7668 | +#include "union.h" | |
7669 | + | |
7670 | +/* | |
7671 | + * This is a helper function for rename, used when rename ends up with hosed | |
7672 | + * over dentries and we need to revert. | |
7673 | + */ | |
7674 | +static int unionfs_refresh_lower_dentry(struct dentry *dentry, | |
7675 | + struct dentry *parent, int bindex) | |
7676 | +{ | |
7677 | + struct dentry *lower_dentry; | |
7678 | + struct dentry *lower_parent; | |
7679 | + int err = 0; | |
63b09289 | 7680 | + struct nameidata lower_nd; |
2380c486 JR |
7681 | + |
7682 | + verify_locked(dentry); | |
7683 | + | |
7684 | + lower_parent = unionfs_lower_dentry_idx(parent, bindex); | |
7685 | + | |
7686 | + BUG_ON(!S_ISDIR(lower_parent->d_inode->i_mode)); | |
7687 | + | |
63b09289 JR |
7688 | + err = init_lower_nd(&lower_nd, LOOKUP_OPEN); |
7689 | + if (unlikely(err < 0)) | |
7690 | + goto out; | |
7691 | + lower_dentry = lookup_one_len_nd(dentry->d_name.name, lower_parent, | |
7692 | + dentry->d_name.len, &lower_nd); | |
7693 | + release_lower_nd(&lower_nd, err); | |
2380c486 JR |
7694 | + if (IS_ERR(lower_dentry)) { |
7695 | + err = PTR_ERR(lower_dentry); | |
7696 | + goto out; | |
7697 | + } | |
7698 | + | |
7699 | + dput(unionfs_lower_dentry_idx(dentry, bindex)); | |
7700 | + iput(unionfs_lower_inode_idx(dentry->d_inode, bindex)); | |
7701 | + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, NULL); | |
7702 | + | |
7703 | + if (!lower_dentry->d_inode) { | |
7704 | + dput(lower_dentry); | |
7705 | + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); | |
7706 | + } else { | |
7707 | + unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry); | |
7708 | + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, | |
7709 | + igrab(lower_dentry->d_inode)); | |
7710 | + } | |
7711 | + | |
7712 | +out: | |
7713 | + return err; | |
7714 | +} | |
7715 | + | |
7716 | +static int __unionfs_rename(struct inode *old_dir, struct dentry *old_dentry, | |
7717 | + struct dentry *old_parent, | |
7718 | + struct inode *new_dir, struct dentry *new_dentry, | |
7719 | + struct dentry *new_parent, | |
7720 | + int bindex) | |
7721 | +{ | |
7722 | + int err = 0; | |
7723 | + struct dentry *lower_old_dentry; | |
7724 | + struct dentry *lower_new_dentry; | |
7725 | + struct dentry *lower_old_dir_dentry; | |
7726 | + struct dentry *lower_new_dir_dentry; | |
7727 | + struct dentry *trap; | |
7728 | + | |
7729 | + lower_new_dentry = unionfs_lower_dentry_idx(new_dentry, bindex); | |
7730 | + lower_old_dentry = unionfs_lower_dentry_idx(old_dentry, bindex); | |
7731 | + | |
7732 | + if (!lower_new_dentry) { | |
7733 | + lower_new_dentry = | |
7734 | + create_parents(new_parent->d_inode, | |
7735 | + new_dentry, new_dentry->d_name.name, | |
7736 | + bindex); | |
7737 | + if (IS_ERR(lower_new_dentry)) { | |
7738 | + err = PTR_ERR(lower_new_dentry); | |
7739 | + if (IS_COPYUP_ERR(err)) | |
7740 | + goto out; | |
7741 | + printk(KERN_ERR "unionfs: error creating directory " | |
7742 | + "tree for rename, bindex=%d err=%d\n", | |
7743 | + bindex, err); | |
7744 | + goto out; | |
7745 | + } | |
7746 | + } | |
7747 | + | |
7748 | + /* check for and remove whiteout, if any */ | |
7749 | + err = check_unlink_whiteout(new_dentry, lower_new_dentry, bindex); | |
7750 | + if (err > 0) /* ignore if whiteout found and successfully removed */ | |
7751 | + err = 0; | |
7752 | + if (err) | |
7753 | + goto out; | |
7754 | + | |
7755 | + /* check of old_dentry branch is writable */ | |
7756 | + err = is_robranch_super(old_dentry->d_sb, bindex); | |
7757 | + if (err) | |
7758 | + goto out; | |
7759 | + | |
7760 | + dget(lower_old_dentry); | |
7761 | + dget(lower_new_dentry); | |
7762 | + lower_old_dir_dentry = dget_parent(lower_old_dentry); | |
7763 | + lower_new_dir_dentry = dget_parent(lower_new_dentry); | |
7764 | + | |
2380c486 JR |
7765 | + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); |
7766 | + /* source should not be ancenstor of target */ | |
7767 | + if (trap == lower_old_dentry) { | |
7768 | + err = -EINVAL; | |
7769 | + goto out_err_unlock; | |
7770 | + } | |
7771 | + /* target should not be ancenstor of source */ | |
7772 | + if (trap == lower_new_dentry) { | |
7773 | + err = -ENOTEMPTY; | |
7774 | + goto out_err_unlock; | |
7775 | + } | |
7776 | + err = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry, | |
7777 | + lower_new_dir_dentry->d_inode, lower_new_dentry); | |
7778 | +out_err_unlock: | |
7779 | + if (!err) { | |
7780 | + /* update parent dir times */ | |
7781 | + fsstack_copy_attr_times(old_dir, lower_old_dir_dentry->d_inode); | |
7782 | + fsstack_copy_attr_times(new_dir, lower_new_dir_dentry->d_inode); | |
7783 | + } | |
7784 | + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); | |
2380c486 JR |
7785 | + |
7786 | + dput(lower_old_dir_dentry); | |
7787 | + dput(lower_new_dir_dentry); | |
7788 | + dput(lower_old_dentry); | |
7789 | + dput(lower_new_dentry); | |
7790 | + | |
7791 | +out: | |
7792 | + if (!err) { | |
7793 | + /* Fixup the new_dentry. */ | |
7794 | + if (bindex < dbstart(new_dentry)) | |
7795 | + dbstart(new_dentry) = bindex; | |
7796 | + else if (bindex > dbend(new_dentry)) | |
7797 | + dbend(new_dentry) = bindex; | |
7798 | + } | |
7799 | + | |
7800 | + return err; | |
7801 | +} | |
7802 | + | |
7803 | +/* | |
7804 | + * Main rename code. This is sufficiently complex, that it's documented in | |
7805 | + * Documentation/filesystems/unionfs/rename.txt. This routine calls | |
7806 | + * __unionfs_rename() above to perform some of the work. | |
7807 | + */ | |
7808 | +static int do_unionfs_rename(struct inode *old_dir, | |
7809 | + struct dentry *old_dentry, | |
7810 | + struct dentry *old_parent, | |
7811 | + struct inode *new_dir, | |
7812 | + struct dentry *new_dentry, | |
7813 | + struct dentry *new_parent) | |
7814 | +{ | |
7815 | + int err = 0; | |
7816 | + int bindex; | |
7817 | + int old_bstart, old_bend; | |
7818 | + int new_bstart, new_bend; | |
7819 | + int do_copyup = -1; | |
7820 | + int local_err = 0; | |
7821 | + int eio = 0; | |
7822 | + int revert = 0; | |
7823 | + | |
7824 | + old_bstart = dbstart(old_dentry); | |
7825 | + old_bend = dbend(old_dentry); | |
7826 | + | |
7827 | + new_bstart = dbstart(new_dentry); | |
7828 | + new_bend = dbend(new_dentry); | |
7829 | + | |
7830 | + /* Rename source to destination. */ | |
7831 | + err = __unionfs_rename(old_dir, old_dentry, old_parent, | |
7832 | + new_dir, new_dentry, new_parent, | |
7833 | + old_bstart); | |
7834 | + if (err) { | |
7835 | + if (!IS_COPYUP_ERR(err)) | |
7836 | + goto out; | |
7837 | + do_copyup = old_bstart - 1; | |
7838 | + } else { | |
7839 | + revert = 1; | |
7840 | + } | |
7841 | + | |
7842 | + /* | |
7843 | + * Unlink all instances of destination that exist to the left of | |
7844 | + * bstart of source. On error, revert back, goto out. | |
7845 | + */ | |
7846 | + for (bindex = old_bstart - 1; bindex >= new_bstart; bindex--) { | |
7847 | + struct dentry *unlink_dentry; | |
7848 | + struct dentry *unlink_dir_dentry; | |
7849 | + | |
7850 | + BUG_ON(bindex < 0); | |
7851 | + unlink_dentry = unionfs_lower_dentry_idx(new_dentry, bindex); | |
7852 | + if (!unlink_dentry) | |
7853 | + continue; | |
7854 | + | |
7855 | + unlink_dir_dentry = lock_parent(unlink_dentry); | |
7856 | + err = is_robranch_super(old_dir->i_sb, bindex); | |
7857 | + if (!err) | |
7858 | + err = vfs_unlink(unlink_dir_dentry->d_inode, | |
7859 | + unlink_dentry); | |
7860 | + | |
7861 | + fsstack_copy_attr_times(new_parent->d_inode, | |
7862 | + unlink_dir_dentry->d_inode); | |
7863 | + /* propagate number of hard-links */ | |
f4ea99f3 | 7864 | + set_nlink(new_parent->d_inode, |
f6c5ef8b | 7865 | + unionfs_get_nlinks(new_parent->d_inode)); |
2380c486 JR |
7866 | + |
7867 | + unlock_dir(unlink_dir_dentry); | |
7868 | + if (!err) { | |
7869 | + if (bindex != new_bstart) { | |
7870 | + dput(unlink_dentry); | |
7871 | + unionfs_set_lower_dentry_idx(new_dentry, | |
7872 | + bindex, NULL); | |
7873 | + } | |
7874 | + } else if (IS_COPYUP_ERR(err)) { | |
7875 | + do_copyup = bindex - 1; | |
7876 | + } else if (revert) { | |
7877 | + goto revert; | |
7878 | + } | |
7879 | + } | |
7880 | + | |
7881 | + if (do_copyup != -1) { | |
7882 | + for (bindex = do_copyup; bindex >= 0; bindex--) { | |
7883 | + /* | |
7884 | + * copyup the file into some left directory, so that | |
7885 | + * you can rename it | |
7886 | + */ | |
7887 | + err = copyup_dentry(old_parent->d_inode, | |
7888 | + old_dentry, old_bstart, bindex, | |
7889 | + old_dentry->d_name.name, | |
7890 | + old_dentry->d_name.len, NULL, | |
7891 | + i_size_read(old_dentry->d_inode)); | |
7892 | + /* if copyup failed, try next branch to the left */ | |
7893 | + if (err) | |
7894 | + continue; | |
7895 | + /* | |
7896 | + * create whiteout before calling __unionfs_rename | |
7897 | + * because the latter will change the old_dentry's | |
7898 | + * lower name and parent dir, resulting in the | |
7899 | + * whiteout getting created in the wrong dir. | |
7900 | + */ | |
7901 | + err = create_whiteout(old_dentry, bindex); | |
7902 | + if (err) { | |
7903 | + printk(KERN_ERR "unionfs: can't create a " | |
7904 | + "whiteout for %s in rename (err=%d)\n", | |
7905 | + old_dentry->d_name.name, err); | |
7906 | + continue; | |
7907 | + } | |
7908 | + err = __unionfs_rename(old_dir, old_dentry, old_parent, | |
7909 | + new_dir, new_dentry, new_parent, | |
7910 | + bindex); | |
7911 | + break; | |
7912 | + } | |
7913 | + } | |
7914 | + | |
7915 | + /* make it opaque */ | |
7916 | + if (S_ISDIR(old_dentry->d_inode->i_mode)) { | |
7917 | + err = make_dir_opaque(old_dentry, dbstart(old_dentry)); | |
7918 | + if (err) | |
7919 | + goto revert; | |
7920 | + } | |
7921 | + | |
7922 | + /* | |
7923 | + * Create whiteout for source, only if: | |
7924 | + * (1) There is more than one underlying instance of source. | |
7925 | + * (We did a copy_up is taken care of above). | |
7926 | + */ | |
7927 | + if ((old_bstart != old_bend) && (do_copyup == -1)) { | |
7928 | + err = create_whiteout(old_dentry, old_bstart); | |
7929 | + if (err) { | |
7930 | + /* can't fix anything now, so we exit with -EIO */ | |
7931 | + printk(KERN_ERR "unionfs: can't create a whiteout for " | |
7932 | + "%s in rename!\n", old_dentry->d_name.name); | |
7933 | + err = -EIO; | |
7934 | + } | |
7935 | + } | |
7936 | + | |
7937 | +out: | |
7938 | + return err; | |
7939 | + | |
7940 | +revert: | |
7941 | + /* Do revert here. */ | |
7942 | + local_err = unionfs_refresh_lower_dentry(new_dentry, new_parent, | |
7943 | + old_bstart); | |
7944 | + if (local_err) { | |
7945 | + printk(KERN_ERR "unionfs: revert failed in rename: " | |
7946 | + "the new refresh failed\n"); | |
7947 | + eio = -EIO; | |
7948 | + } | |
7949 | + | |
7950 | + local_err = unionfs_refresh_lower_dentry(old_dentry, old_parent, | |
7951 | + old_bstart); | |
7952 | + if (local_err) { | |
7953 | + printk(KERN_ERR "unionfs: revert failed in rename: " | |
7954 | + "the old refresh failed\n"); | |
7955 | + eio = -EIO; | |
7956 | + goto revert_out; | |
7957 | + } | |
7958 | + | |
7959 | + if (!unionfs_lower_dentry_idx(new_dentry, bindex) || | |
7960 | + !unionfs_lower_dentry_idx(new_dentry, bindex)->d_inode) { | |
7961 | + printk(KERN_ERR "unionfs: revert failed in rename: " | |
7962 | + "the object disappeared from under us!\n"); | |
7963 | + eio = -EIO; | |
7964 | + goto revert_out; | |
7965 | + } | |
7966 | + | |
7967 | + if (unionfs_lower_dentry_idx(old_dentry, bindex) && | |
7968 | + unionfs_lower_dentry_idx(old_dentry, bindex)->d_inode) { | |
7969 | + printk(KERN_ERR "unionfs: revert failed in rename: " | |
7970 | + "the object was created underneath us!\n"); | |
7971 | + eio = -EIO; | |
7972 | + goto revert_out; | |
7973 | + } | |
7974 | + | |
7975 | + local_err = __unionfs_rename(new_dir, new_dentry, new_parent, | |
7976 | + old_dir, old_dentry, old_parent, | |
7977 | + old_bstart); | |
7978 | + | |
7979 | + /* If we can't fix it, then we cop-out with -EIO. */ | |
7980 | + if (local_err) { | |
7981 | + printk(KERN_ERR "unionfs: revert failed in rename!\n"); | |
7982 | + eio = -EIO; | |
7983 | + } | |
7984 | + | |
7985 | + local_err = unionfs_refresh_lower_dentry(new_dentry, new_parent, | |
7986 | + bindex); | |
7987 | + if (local_err) | |
7988 | + eio = -EIO; | |
7989 | + local_err = unionfs_refresh_lower_dentry(old_dentry, old_parent, | |
7990 | + bindex); | |
7991 | + if (local_err) | |
7992 | + eio = -EIO; | |
7993 | + | |
7994 | +revert_out: | |
7995 | + if (eio) | |
7996 | + err = eio; | |
7997 | + return err; | |
7998 | +} | |
7999 | + | |
8000 | +/* | |
8001 | + * We can't copyup a directory, because it may involve huge numbers of | |
8002 | + * children, etc. Doing that in the kernel would be bad, so instead we | |
8003 | + * return EXDEV to the user-space utility that caused this, and let the | |
8004 | + * user-space recurse and ask us to copy up each file separately. | |
8005 | + */ | |
8006 | +static int may_rename_dir(struct dentry *dentry, struct dentry *parent) | |
8007 | +{ | |
8008 | + int err, bstart; | |
8009 | + | |
8010 | + err = check_empty(dentry, parent, NULL); | |
8011 | + if (err == -ENOTEMPTY) { | |
8012 | + if (is_robranch(dentry)) | |
8013 | + return -EXDEV; | |
8014 | + } else if (err) { | |
8015 | + return err; | |
8016 | + } | |
8017 | + | |
8018 | + bstart = dbstart(dentry); | |
8019 | + if (dbend(dentry) == bstart || dbopaque(dentry) == bstart) | |
8020 | + return 0; | |
8021 | + | |
8022 | + dbstart(dentry) = bstart + 1; | |
8023 | + err = check_empty(dentry, parent, NULL); | |
8024 | + dbstart(dentry) = bstart; | |
8025 | + if (err == -ENOTEMPTY) | |
8026 | + err = -EXDEV; | |
8027 | + return err; | |
8028 | +} | |
8029 | + | |
8030 | +/* | |
8031 | + * The locking rules in unionfs_rename are complex. We could use a simpler | |
8032 | + * superblock-level name-space lock for renames and copy-ups. | |
8033 | + */ | |
8034 | +int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry, | |
8035 | + struct inode *new_dir, struct dentry *new_dentry) | |
8036 | +{ | |
8037 | + int err = 0; | |
8038 | + struct dentry *wh_dentry; | |
8039 | + struct dentry *old_parent, *new_parent; | |
8040 | + int valid = true; | |
8041 | + | |
8042 | + unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
8043 | + old_parent = dget_parent(old_dentry); | |
8044 | + new_parent = dget_parent(new_dentry); | |
8045 | + /* un/lock parent dentries only if they differ from old/new_dentry */ | |
8046 | + if (old_parent != old_dentry && | |
8047 | + old_parent != new_dentry) | |
8048 | + unionfs_lock_dentry(old_parent, UNIONFS_DMUTEX_REVAL_PARENT); | |
8049 | + if (new_parent != old_dentry && | |
8050 | + new_parent != new_dentry && | |
8051 | + new_parent != old_parent) | |
8052 | + unionfs_lock_dentry(new_parent, UNIONFS_DMUTEX_REVAL_CHILD); | |
8053 | + unionfs_double_lock_dentry(old_dentry, new_dentry); | |
8054 | + | |
8055 | + valid = __unionfs_d_revalidate(old_dentry, old_parent, false); | |
8056 | + if (!valid) { | |
8057 | + err = -ESTALE; | |
8058 | + goto out; | |
8059 | + } | |
8060 | + if (!d_deleted(new_dentry) && new_dentry->d_inode) { | |
8061 | + valid = __unionfs_d_revalidate(new_dentry, new_parent, false); | |
8062 | + if (!valid) { | |
8063 | + err = -ESTALE; | |
8064 | + goto out; | |
8065 | + } | |
8066 | + } | |
8067 | + | |
8068 | + if (!S_ISDIR(old_dentry->d_inode->i_mode)) | |
8069 | + err = unionfs_partial_lookup(old_dentry, old_parent); | |
8070 | + else | |
8071 | + err = may_rename_dir(old_dentry, old_parent); | |
8072 | + | |
8073 | + if (err) | |
8074 | + goto out; | |
8075 | + | |
8076 | + err = unionfs_partial_lookup(new_dentry, new_parent); | |
8077 | + if (err) | |
8078 | + goto out; | |
8079 | + | |
8080 | + /* | |
8081 | + * if new_dentry is already lower because of whiteout, | |
8082 | + * simply override it even if the whited-out dir is not empty. | |
8083 | + */ | |
8084 | + wh_dentry = find_first_whiteout(new_dentry); | |
8085 | + if (!IS_ERR(wh_dentry)) { | |
8086 | + dput(wh_dentry); | |
8087 | + } else if (new_dentry->d_inode) { | |
8088 | + if (S_ISDIR(old_dentry->d_inode->i_mode) != | |
8089 | + S_ISDIR(new_dentry->d_inode->i_mode)) { | |
8090 | + err = S_ISDIR(old_dentry->d_inode->i_mode) ? | |
8091 | + -ENOTDIR : -EISDIR; | |
8092 | + goto out; | |
8093 | + } | |
8094 | + | |
8095 | + if (S_ISDIR(new_dentry->d_inode->i_mode)) { | |
8096 | + struct unionfs_dir_state *namelist = NULL; | |
8097 | + /* check if this unionfs directory is empty or not */ | |
8098 | + err = check_empty(new_dentry, new_parent, &namelist); | |
8099 | + if (err) | |
8100 | + goto out; | |
8101 | + | |
8102 | + if (!is_robranch(new_dentry)) | |
8103 | + err = delete_whiteouts(new_dentry, | |
8104 | + dbstart(new_dentry), | |
8105 | + namelist); | |
8106 | + | |
8107 | + free_rdstate(namelist); | |
8108 | + | |
8109 | + if (err) | |
8110 | + goto out; | |
8111 | + } | |
8112 | + } | |
8113 | + | |
8114 | + err = do_unionfs_rename(old_dir, old_dentry, old_parent, | |
8115 | + new_dir, new_dentry, new_parent); | |
8116 | + if (err) | |
8117 | + goto out; | |
8118 | + | |
8119 | + /* | |
8120 | + * force re-lookup since the dir on ro branch is not renamed, and | |
8121 | + * lower dentries still indicate the un-renamed ones. | |
8122 | + */ | |
8123 | + if (S_ISDIR(old_dentry->d_inode->i_mode)) | |
8124 | + atomic_dec(&UNIONFS_D(old_dentry)->generation); | |
8125 | + else | |
8126 | + unionfs_postcopyup_release(old_dentry); | |
8127 | + if (new_dentry->d_inode && !S_ISDIR(new_dentry->d_inode->i_mode)) { | |
8128 | + unionfs_postcopyup_release(new_dentry); | |
8129 | + unionfs_postcopyup_setmnt(new_dentry); | |
8130 | + if (!unionfs_lower_inode(new_dentry->d_inode)) { | |
8131 | + /* | |
8132 | + * If we get here, it means that no copyup was | |
8133 | + * needed, and that a file by the old name already | |
8134 | + * existing on the destination branch; that file got | |
8135 | + * renamed earlier in this function, so all we need | |
8136 | + * to do here is set the lower inode. | |
8137 | + */ | |
8138 | + struct inode *inode; | |
8139 | + inode = unionfs_lower_inode(old_dentry->d_inode); | |
8140 | + igrab(inode); | |
8141 | + unionfs_set_lower_inode_idx(new_dentry->d_inode, | |
8142 | + dbstart(new_dentry), | |
8143 | + inode); | |
8144 | + } | |
8145 | + } | |
8146 | + /* if all of this renaming succeeded, update our times */ | |
8147 | + unionfs_copy_attr_times(old_dentry->d_inode); | |
8148 | + unionfs_copy_attr_times(new_dentry->d_inode); | |
8149 | + unionfs_check_inode(old_dir); | |
8150 | + unionfs_check_inode(new_dir); | |
8151 | + unionfs_check_dentry(old_dentry); | |
8152 | + unionfs_check_dentry(new_dentry); | |
8153 | + | |
8154 | +out: | |
8155 | + if (err) /* clear the new_dentry stuff created */ | |
8156 | + d_drop(new_dentry); | |
8157 | + | |
8158 | + unionfs_double_unlock_dentry(old_dentry, new_dentry); | |
8159 | + if (new_parent != old_dentry && | |
8160 | + new_parent != new_dentry && | |
8161 | + new_parent != old_parent) | |
8162 | + unionfs_unlock_dentry(new_parent); | |
8163 | + if (old_parent != old_dentry && | |
8164 | + old_parent != new_dentry) | |
8165 | + unionfs_unlock_dentry(old_parent); | |
8166 | + dput(new_parent); | |
8167 | + dput(old_parent); | |
8168 | + unionfs_read_unlock(old_dentry->d_sb); | |
8169 | + | |
8170 | + return err; | |
8171 | +} | |
0c5527e5 AM |
8172 | diff --git a/fs/unionfs/sioq.c b/fs/unionfs/sioq.c |
8173 | new file mode 100644 | |
63b09289 | 8174 | index 0000000..b923742 |
0c5527e5 AM |
8175 | --- /dev/null |
8176 | +++ b/fs/unionfs/sioq.c | |
2380c486 JR |
8177 | @@ -0,0 +1,101 @@ |
8178 | +/* | |
63b09289 | 8179 | + * Copyright (c) 2006-2011 Erez Zadok |
2380c486 JR |
8180 | + * Copyright (c) 2006 Charles P. Wright |
8181 | + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek | |
8182 | + * Copyright (c) 2006 Junjiro Okajima | |
8183 | + * Copyright (c) 2006 David P. Quigley | |
63b09289 JR |
8184 | + * Copyright (c) 2006-2011 Stony Brook University |
8185 | + * Copyright (c) 2006-2011 The Research Foundation of SUNY | |
2380c486 JR |
8186 | + * |
8187 | + * This program is free software; you can redistribute it and/or modify | |
8188 | + * it under the terms of the GNU General Public License version 2 as | |
8189 | + * published by the Free Software Foundation. | |
8190 | + */ | |
8191 | + | |
8192 | +#include "union.h" | |
8193 | + | |
8194 | +/* | |
8195 | + * Super-user IO work Queue - sometimes we need to perform actions which | |
8196 | + * would fail due to the unix permissions on the parent directory (e.g., | |
8197 | + * rmdir a directory which appears empty, but in reality contains | |
8198 | + * whiteouts). | |
8199 | + */ | |
8200 | + | |
8201 | +static struct workqueue_struct *superio_workqueue; | |
8202 | + | |
8203 | +int __init init_sioq(void) | |
8204 | +{ | |
8205 | + int err; | |
8206 | + | |
8207 | + superio_workqueue = create_workqueue("unionfs_siod"); | |
8208 | + if (!IS_ERR(superio_workqueue)) | |
8209 | + return 0; | |
8210 | + | |
8211 | + err = PTR_ERR(superio_workqueue); | |
8212 | + printk(KERN_ERR "unionfs: create_workqueue failed %d\n", err); | |
8213 | + superio_workqueue = NULL; | |
8214 | + return err; | |
8215 | +} | |
8216 | + | |
8217 | +void stop_sioq(void) | |
8218 | +{ | |
8219 | + if (superio_workqueue) | |
8220 | + destroy_workqueue(superio_workqueue); | |
8221 | +} | |
8222 | + | |
8223 | +void run_sioq(work_func_t func, struct sioq_args *args) | |
8224 | +{ | |
8225 | + INIT_WORK(&args->work, func); | |
8226 | + | |
8227 | + init_completion(&args->comp); | |
8228 | + while (!queue_work(superio_workqueue, &args->work)) { | |
8229 | + /* TODO: do accounting if needed */ | |
8230 | + schedule(); | |
8231 | + } | |
8232 | + wait_for_completion(&args->comp); | |
8233 | +} | |
8234 | + | |
8235 | +void __unionfs_create(struct work_struct *work) | |
8236 | +{ | |
8237 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
8238 | + struct create_args *c = &args->create; | |
8239 | + | |
8240 | + args->err = vfs_create(c->parent, c->dentry, c->mode, c->nd); | |
8241 | + complete(&args->comp); | |
8242 | +} | |
8243 | + | |
8244 | +void __unionfs_mkdir(struct work_struct *work) | |
8245 | +{ | |
8246 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
8247 | + struct mkdir_args *m = &args->mkdir; | |
8248 | + | |
8249 | + args->err = vfs_mkdir(m->parent, m->dentry, m->mode); | |
8250 | + complete(&args->comp); | |
8251 | +} | |
8252 | + | |
8253 | +void __unionfs_mknod(struct work_struct *work) | |
8254 | +{ | |
8255 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
8256 | + struct mknod_args *m = &args->mknod; | |
8257 | + | |
8258 | + args->err = vfs_mknod(m->parent, m->dentry, m->mode, m->dev); | |
8259 | + complete(&args->comp); | |
8260 | +} | |
8261 | + | |
8262 | +void __unionfs_symlink(struct work_struct *work) | |
8263 | +{ | |
8264 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
8265 | + struct symlink_args *s = &args->symlink; | |
8266 | + | |
8267 | + args->err = vfs_symlink(s->parent, s->dentry, s->symbuf); | |
8268 | + complete(&args->comp); | |
8269 | +} | |
8270 | + | |
8271 | +void __unionfs_unlink(struct work_struct *work) | |
8272 | +{ | |
8273 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
8274 | + struct unlink_args *u = &args->unlink; | |
8275 | + | |
8276 | + args->err = vfs_unlink(u->parent, u->dentry); | |
8277 | + complete(&args->comp); | |
8278 | +} | |
0c5527e5 AM |
8279 | diff --git a/fs/unionfs/sioq.h b/fs/unionfs/sioq.h |
8280 | new file mode 100644 | |
63b09289 | 8281 | index 0000000..c2dfb94 |
0c5527e5 AM |
8282 | --- /dev/null |
8283 | +++ b/fs/unionfs/sioq.h | |
2380c486 JR |
8284 | @@ -0,0 +1,91 @@ |
8285 | +/* | |
63b09289 | 8286 | + * Copyright (c) 2006-2011 Erez Zadok |
2380c486 JR |
8287 | + * Copyright (c) 2006 Charles P. Wright |
8288 | + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek | |
8289 | + * Copyright (c) 2006 Junjiro Okajima | |
8290 | + * Copyright (c) 2006 David P. Quigley | |
63b09289 JR |
8291 | + * Copyright (c) 2006-2011 Stony Brook University |
8292 | + * Copyright (c) 2006-2011 The Research Foundation of SUNY | |
2380c486 JR |
8293 | + * |
8294 | + * This program is free software; you can redistribute it and/or modify | |
8295 | + * it under the terms of the GNU General Public License version 2 as | |
8296 | + * published by the Free Software Foundation. | |
8297 | + */ | |
8298 | + | |
8299 | +#ifndef _SIOQ_H | |
8300 | +#define _SIOQ_H | |
8301 | + | |
8302 | +struct deletewh_args { | |
8303 | + struct unionfs_dir_state *namelist; | |
8304 | + struct dentry *dentry; | |
8305 | + int bindex; | |
8306 | +}; | |
8307 | + | |
8308 | +struct is_opaque_args { | |
8309 | + struct dentry *dentry; | |
8310 | +}; | |
8311 | + | |
8312 | +struct create_args { | |
8313 | + struct inode *parent; | |
8314 | + struct dentry *dentry; | |
8315 | + umode_t mode; | |
8316 | + struct nameidata *nd; | |
8317 | +}; | |
8318 | + | |
8319 | +struct mkdir_args { | |
8320 | + struct inode *parent; | |
8321 | + struct dentry *dentry; | |
8322 | + umode_t mode; | |
8323 | +}; | |
8324 | + | |
8325 | +struct mknod_args { | |
8326 | + struct inode *parent; | |
8327 | + struct dentry *dentry; | |
8328 | + umode_t mode; | |
8329 | + dev_t dev; | |
8330 | +}; | |
8331 | + | |
8332 | +struct symlink_args { | |
8333 | + struct inode *parent; | |
8334 | + struct dentry *dentry; | |
8335 | + char *symbuf; | |
8336 | +}; | |
8337 | + | |
8338 | +struct unlink_args { | |
8339 | + struct inode *parent; | |
8340 | + struct dentry *dentry; | |
8341 | +}; | |
8342 | + | |
8343 | + | |
8344 | +struct sioq_args { | |
8345 | + struct completion comp; | |
8346 | + struct work_struct work; | |
8347 | + int err; | |
8348 | + void *ret; | |
8349 | + | |
8350 | + union { | |
8351 | + struct deletewh_args deletewh; | |
8352 | + struct is_opaque_args is_opaque; | |
8353 | + struct create_args create; | |
8354 | + struct mkdir_args mkdir; | |
8355 | + struct mknod_args mknod; | |
8356 | + struct symlink_args symlink; | |
8357 | + struct unlink_args unlink; | |
8358 | + }; | |
8359 | +}; | |
8360 | + | |
8361 | +/* Extern definitions for SIOQ functions */ | |
8362 | +extern int __init init_sioq(void); | |
8363 | +extern void stop_sioq(void); | |
8364 | +extern void run_sioq(work_func_t func, struct sioq_args *args); | |
8365 | + | |
8366 | +/* Extern definitions for our privilege escalation helpers */ | |
8367 | +extern void __unionfs_create(struct work_struct *work); | |
8368 | +extern void __unionfs_mkdir(struct work_struct *work); | |
8369 | +extern void __unionfs_mknod(struct work_struct *work); | |
8370 | +extern void __unionfs_symlink(struct work_struct *work); | |
8371 | +extern void __unionfs_unlink(struct work_struct *work); | |
8372 | +extern void __delete_whiteouts(struct work_struct *work); | |
8373 | +extern void __is_opaque_dir(struct work_struct *work); | |
8374 | + | |
8375 | +#endif /* not _SIOQ_H */ | |
0c5527e5 AM |
8376 | diff --git a/fs/unionfs/subr.c b/fs/unionfs/subr.c |
8377 | new file mode 100644 | |
f6c5ef8b | 8378 | index 0000000..e7fc5a5 |
0c5527e5 AM |
8379 | --- /dev/null |
8380 | +++ b/fs/unionfs/subr.c | |
2380c486 JR |
8381 | @@ -0,0 +1,95 @@ |
8382 | +/* | |
63b09289 | 8383 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
8384 | + * Copyright (c) 2003-2006 Charles P. Wright |
8385 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
8386 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
8387 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
8388 | + * Copyright (c) 2004-2006 David P. Quigley | |
8389 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
8390 | + * Copyright (c) 2003 Puja Gupta | |
8391 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
8392 | + * Copyright (c) 2003-2011 Stony Brook University |
8393 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
8394 | + * |
8395 | + * This program is free software; you can redistribute it and/or modify | |
8396 | + * it under the terms of the GNU General Public License version 2 as | |
8397 | + * published by the Free Software Foundation. | |
8398 | + */ | |
8399 | + | |
8400 | +#include "union.h" | |
8401 | + | |
8402 | +/* | |
8403 | + * returns the right n_link value based on the inode type | |
8404 | + */ | |
8405 | +int unionfs_get_nlinks(const struct inode *inode) | |
8406 | +{ | |
8407 | + /* don't bother to do all the work since we're unlinked */ | |
8408 | + if (inode->i_nlink == 0) | |
8409 | + return 0; | |
8410 | + | |
8411 | + if (!S_ISDIR(inode->i_mode)) | |
8412 | + return unionfs_lower_inode(inode)->i_nlink; | |
8413 | + | |
8414 | + /* | |
8415 | + * For directories, we return 1. The only place that could cares | |
8416 | + * about links is readdir, and there's d_type there so even that | |
8417 | + * doesn't matter. | |
8418 | + */ | |
8419 | + return 1; | |
8420 | +} | |
8421 | + | |
8422 | +/* copy a/m/ctime from the lower branch with the newest times */ | |
8423 | +void unionfs_copy_attr_times(struct inode *upper) | |
8424 | +{ | |
8425 | + int bindex; | |
8426 | + struct inode *lower; | |
8427 | + | |
8428 | + if (!upper) | |
8429 | + return; | |
8430 | + if (ibstart(upper) < 0) { | |
8431 | +#ifdef CONFIG_UNION_FS_DEBUG | |
8432 | + WARN_ON(ibstart(upper) < 0); | |
8433 | +#endif /* CONFIG_UNION_FS_DEBUG */ | |
8434 | + return; | |
8435 | + } | |
8436 | + for (bindex = ibstart(upper); bindex <= ibend(upper); bindex++) { | |
8437 | + lower = unionfs_lower_inode_idx(upper, bindex); | |
8438 | + if (!lower) | |
8439 | + continue; /* not all lower dir objects may exist */ | |
8440 | + if (unlikely(timespec_compare(&upper->i_mtime, | |
8441 | + &lower->i_mtime) < 0)) | |
8442 | + upper->i_mtime = lower->i_mtime; | |
8443 | + if (unlikely(timespec_compare(&upper->i_ctime, | |
8444 | + &lower->i_ctime) < 0)) | |
8445 | + upper->i_ctime = lower->i_ctime; | |
8446 | + if (unlikely(timespec_compare(&upper->i_atime, | |
8447 | + &lower->i_atime) < 0)) | |
8448 | + upper->i_atime = lower->i_atime; | |
8449 | + } | |
8450 | +} | |
8451 | + | |
8452 | +/* | |
8453 | + * A unionfs/fanout version of fsstack_copy_attr_all. Uses a | |
8454 | + * unionfs_get_nlinks to properly calcluate the number of links to a file. | |
8455 | + * Also, copies the max() of all a/m/ctimes for all lower inodes (which is | |
8456 | + * important if the lower inode is a directory type) | |
8457 | + */ | |
8458 | +void unionfs_copy_attr_all(struct inode *dest, | |
8459 | + const struct inode *src) | |
8460 | +{ | |
8461 | + dest->i_mode = src->i_mode; | |
8462 | + dest->i_uid = src->i_uid; | |
8463 | + dest->i_gid = src->i_gid; | |
8464 | + dest->i_rdev = src->i_rdev; | |
8465 | + | |
8466 | + unionfs_copy_attr_times(dest); | |
8467 | + | |
8468 | + dest->i_blkbits = src->i_blkbits; | |
8469 | + dest->i_flags = src->i_flags; | |
8470 | + | |
8471 | + /* | |
8472 | + * Update the nlinks AFTER updating the above fields, because the | |
8473 | + * get_links callback may depend on them. | |
8474 | + */ | |
f4ea99f3 | 8475 | + set_nlink(dest, unionfs_get_nlinks(dest)); |
2380c486 | 8476 | +} |
0c5527e5 AM |
8477 | diff --git a/fs/unionfs/super.c b/fs/unionfs/super.c |
8478 | new file mode 100644 | |
92d182d2 | 8479 | index 0000000..b99f14d |
0c5527e5 AM |
8480 | --- /dev/null |
8481 | +++ b/fs/unionfs/super.c | |
63b09289 | 8482 | @@ -0,0 +1,1030 @@ |
2380c486 | 8483 | +/* |
63b09289 | 8484 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
8485 | + * Copyright (c) 2003-2006 Charles P. Wright |
8486 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
8487 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
8488 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
8489 | + * Copyright (c) 2004-2006 David P. Quigley | |
8490 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
8491 | + * Copyright (c) 2003 Puja Gupta | |
8492 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
8493 | + * Copyright (c) 2003-2011 Stony Brook University |
8494 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
8495 | + * |
8496 | + * This program is free software; you can redistribute it and/or modify | |
8497 | + * it under the terms of the GNU General Public License version 2 as | |
8498 | + * published by the Free Software Foundation. | |
8499 | + */ | |
8500 | + | |
8501 | +#include "union.h" | |
8502 | + | |
8503 | +/* | |
8504 | + * The inode cache is used with alloc_inode for both our inode info and the | |
8505 | + * vfs inode. | |
8506 | + */ | |
8507 | +static struct kmem_cache *unionfs_inode_cachep; | |
8508 | + | |
8509 | +struct inode *unionfs_iget(struct super_block *sb, unsigned long ino) | |
8510 | +{ | |
8511 | + int size; | |
8512 | + struct unionfs_inode_info *info; | |
8513 | + struct inode *inode; | |
8514 | + | |
8515 | + inode = iget_locked(sb, ino); | |
8516 | + if (!inode) | |
8517 | + return ERR_PTR(-ENOMEM); | |
8518 | + if (!(inode->i_state & I_NEW)) | |
8519 | + return inode; | |
8520 | + | |
8521 | + info = UNIONFS_I(inode); | |
8522 | + memset(info, 0, offsetof(struct unionfs_inode_info, vfs_inode)); | |
8523 | + info->bstart = -1; | |
8524 | + info->bend = -1; | |
8525 | + atomic_set(&info->generation, | |
8526 | + atomic_read(&UNIONFS_SB(inode->i_sb)->generation)); | |
8527 | + spin_lock_init(&info->rdlock); | |
8528 | + info->rdcount = 1; | |
8529 | + info->hashsize = -1; | |
8530 | + INIT_LIST_HEAD(&info->readdircache); | |
8531 | + | |
8532 | + size = sbmax(inode->i_sb) * sizeof(struct inode *); | |
8533 | + info->lower_inodes = kzalloc(size, GFP_KERNEL); | |
8534 | + if (unlikely(!info->lower_inodes)) { | |
8535 | + printk(KERN_CRIT "unionfs: no kernel memory when allocating " | |
8536 | + "lower-pointer array!\n"); | |
8537 | + iget_failed(inode); | |
8538 | + return ERR_PTR(-ENOMEM); | |
8539 | + } | |
8540 | + | |
8541 | + inode->i_version++; | |
8542 | + inode->i_op = &unionfs_main_iops; | |
8543 | + inode->i_fop = &unionfs_main_fops; | |
8544 | + | |
8545 | + inode->i_mapping->a_ops = &unionfs_aops; | |
8546 | + | |
8547 | + /* | |
8548 | + * reset times so unionfs_copy_attr_all can keep out time invariants | |
8549 | + * right (upper inode time being the max of all lower ones). | |
8550 | + */ | |
8551 | + inode->i_atime.tv_sec = inode->i_atime.tv_nsec = 0; | |
8552 | + inode->i_mtime.tv_sec = inode->i_mtime.tv_nsec = 0; | |
8553 | + inode->i_ctime.tv_sec = inode->i_ctime.tv_nsec = 0; | |
8554 | + unlock_new_inode(inode); | |
8555 | + return inode; | |
8556 | +} | |
8557 | + | |
8558 | +/* | |
2380c486 JR |
8559 | + * final actions when unmounting a file system |
8560 | + * | |
8561 | + * No need to lock rwsem. | |
8562 | + */ | |
8563 | +static void unionfs_put_super(struct super_block *sb) | |
8564 | +{ | |
8565 | + int bindex, bstart, bend; | |
8566 | + struct unionfs_sb_info *spd; | |
8567 | + int leaks = 0; | |
8568 | + | |
8569 | + spd = UNIONFS_SB(sb); | |
8570 | + if (!spd) | |
8571 | + return; | |
8572 | + | |
8573 | + bstart = sbstart(sb); | |
8574 | + bend = sbend(sb); | |
8575 | + | |
8576 | + /* Make sure we have no leaks of branchget/branchput. */ | |
8577 | + for (bindex = bstart; bindex <= bend; bindex++) | |
8578 | + if (unlikely(branch_count(sb, bindex) != 0)) { | |
8579 | + printk(KERN_CRIT | |
8580 | + "unionfs: branch %d has %d references left!\n", | |
8581 | + bindex, branch_count(sb, bindex)); | |
8582 | + leaks = 1; | |
8583 | + } | |
8584 | + WARN_ON(leaks != 0); | |
8585 | + | |
8586 | + /* decrement lower super references */ | |
8587 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
8588 | + struct super_block *s; | |
8589 | + s = unionfs_lower_super_idx(sb, bindex); | |
8590 | + unionfs_set_lower_super_idx(sb, bindex, NULL); | |
8591 | + atomic_dec(&s->s_active); | |
8592 | + } | |
8593 | + | |
8594 | + kfree(spd->dev_name); | |
8595 | + kfree(spd->data); | |
8596 | + kfree(spd); | |
8597 | + sb->s_fs_info = NULL; | |
8598 | +} | |
8599 | + | |
8600 | +/* | |
8601 | + * Since people use this to answer the "How big of a file can I write?" | |
8602 | + * question, we report the size of the highest priority branch as the size of | |
8603 | + * the union. | |
8604 | + */ | |
8605 | +static int unionfs_statfs(struct dentry *dentry, struct kstatfs *buf) | |
8606 | +{ | |
8607 | + int err = 0; | |
8608 | + struct super_block *sb; | |
8609 | + struct dentry *lower_dentry; | |
8610 | + struct dentry *parent; | |
0c5527e5 | 8611 | + struct path lower_path; |
2380c486 JR |
8612 | + bool valid; |
8613 | + | |
8614 | + sb = dentry->d_sb; | |
8615 | + | |
8616 | + unionfs_read_lock(sb, UNIONFS_SMUTEX_CHILD); | |
8617 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
8618 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
8619 | + | |
8620 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
8621 | + if (unlikely(!valid)) { | |
8622 | + err = -ESTALE; | |
8623 | + goto out; | |
8624 | + } | |
8625 | + unionfs_check_dentry(dentry); | |
8626 | + | |
8627 | + lower_dentry = unionfs_lower_dentry(sb->s_root); | |
0c5527e5 AM |
8628 | + lower_path.dentry = lower_dentry; |
8629 | + lower_path.mnt = unionfs_mntget(sb->s_root, 0); | |
8630 | + err = vfs_statfs(&lower_path, buf); | |
8631 | + mntput(lower_path.mnt); | |
2380c486 JR |
8632 | + |
8633 | + /* set return buf to our f/s to avoid confusing user-level utils */ | |
8634 | + buf->f_type = UNIONFS_SUPER_MAGIC; | |
8635 | + /* | |
8636 | + * Our maximum file name can is shorter by a few bytes because every | |
8637 | + * file name could potentially be whited-out. | |
8638 | + * | |
8639 | + * XXX: this restriction goes away with ODF. | |
8640 | + */ | |
8641 | + unionfs_set_max_namelen(&buf->f_namelen); | |
8642 | + | |
8643 | + /* | |
8644 | + * reset two fields to avoid confusing user-land. | |
8645 | + * XXX: is this still necessary? | |
8646 | + */ | |
8647 | + memset(&buf->f_fsid, 0, sizeof(__kernel_fsid_t)); | |
8648 | + memset(&buf->f_spare, 0, sizeof(buf->f_spare)); | |
8649 | + | |
8650 | +out: | |
8651 | + unionfs_check_dentry(dentry); | |
8652 | + unionfs_unlock_dentry(dentry); | |
8653 | + unionfs_unlock_parent(dentry, parent); | |
8654 | + unionfs_read_unlock(sb); | |
8655 | + return err; | |
8656 | +} | |
8657 | + | |
8658 | +/* handle mode changing during remount */ | |
8659 | +static noinline_for_stack int do_remount_mode_option( | |
8660 | + char *optarg, | |
8661 | + int cur_branches, | |
8662 | + struct unionfs_data *new_data, | |
8663 | + struct path *new_lower_paths) | |
8664 | +{ | |
8665 | + int err = -EINVAL; | |
8666 | + int perms, idx; | |
8667 | + char *modename = strchr(optarg, '='); | |
63b09289 | 8668 | + struct path path; |
2380c486 JR |
8669 | + |
8670 | + /* by now, optarg contains the branch name */ | |
8671 | + if (!*optarg) { | |
8672 | + printk(KERN_ERR | |
8673 | + "unionfs: no branch specified for mode change\n"); | |
8674 | + goto out; | |
8675 | + } | |
8676 | + if (!modename) { | |
8677 | + printk(KERN_ERR "unionfs: branch \"%s\" requires a mode\n", | |
8678 | + optarg); | |
8679 | + goto out; | |
8680 | + } | |
8681 | + *modename++ = '\0'; | |
8682 | + err = parse_branch_mode(modename, &perms); | |
8683 | + if (err) { | |
8684 | + printk(KERN_ERR "unionfs: invalid mode \"%s\" for \"%s\"\n", | |
8685 | + modename, optarg); | |
8686 | + goto out; | |
8687 | + } | |
8688 | + | |
8689 | + /* | |
8690 | + * Find matching branch index. For now, this assumes that nothing | |
8691 | + * has been mounted on top of this Unionfs stack. Once we have /odf | |
8692 | + * and cache-coherency resolved, we'll address the branch-path | |
8693 | + * uniqueness. | |
8694 | + */ | |
63b09289 | 8695 | + err = kern_path(optarg, LOOKUP_FOLLOW, &path); |
2380c486 JR |
8696 | + if (err) { |
8697 | + printk(KERN_ERR "unionfs: error accessing " | |
8698 | + "lower directory \"%s\" (error %d)\n", | |
8699 | + optarg, err); | |
8700 | + goto out; | |
8701 | + } | |
8702 | + for (idx = 0; idx < cur_branches; idx++) | |
63b09289 JR |
8703 | + if (path.mnt == new_lower_paths[idx].mnt && |
8704 | + path.dentry == new_lower_paths[idx].dentry) | |
2380c486 | 8705 | + break; |
63b09289 | 8706 | + path_put(&path); /* no longer needed */ |
2380c486 JR |
8707 | + if (idx == cur_branches) { |
8708 | + err = -ENOENT; /* err may have been reset above */ | |
8709 | + printk(KERN_ERR "unionfs: branch \"%s\" " | |
8710 | + "not found\n", optarg); | |
8711 | + goto out; | |
8712 | + } | |
8713 | + /* check/change mode for existing branch */ | |
8714 | + /* we don't warn if perms==branchperms */ | |
8715 | + new_data[idx].branchperms = perms; | |
8716 | + err = 0; | |
8717 | +out: | |
8718 | + return err; | |
8719 | +} | |
8720 | + | |
8721 | +/* handle branch deletion during remount */ | |
8722 | +static noinline_for_stack int do_remount_del_option( | |
8723 | + char *optarg, int cur_branches, | |
8724 | + struct unionfs_data *new_data, | |
8725 | + struct path *new_lower_paths) | |
8726 | +{ | |
8727 | + int err = -EINVAL; | |
8728 | + int idx; | |
63b09289 | 8729 | + struct path path; |
2380c486 JR |
8730 | + |
8731 | + /* optarg contains the branch name to delete */ | |
8732 | + | |
8733 | + /* | |
8734 | + * Find matching branch index. For now, this assumes that nothing | |
8735 | + * has been mounted on top of this Unionfs stack. Once we have /odf | |
8736 | + * and cache-coherency resolved, we'll address the branch-path | |
8737 | + * uniqueness. | |
8738 | + */ | |
63b09289 | 8739 | + err = kern_path(optarg, LOOKUP_FOLLOW, &path); |
2380c486 JR |
8740 | + if (err) { |
8741 | + printk(KERN_ERR "unionfs: error accessing " | |
8742 | + "lower directory \"%s\" (error %d)\n", | |
8743 | + optarg, err); | |
8744 | + goto out; | |
8745 | + } | |
8746 | + for (idx = 0; idx < cur_branches; idx++) | |
63b09289 JR |
8747 | + if (path.mnt == new_lower_paths[idx].mnt && |
8748 | + path.dentry == new_lower_paths[idx].dentry) | |
2380c486 | 8749 | + break; |
63b09289 | 8750 | + path_put(&path); /* no longer needed */ |
2380c486 JR |
8751 | + if (idx == cur_branches) { |
8752 | + printk(KERN_ERR "unionfs: branch \"%s\" " | |
8753 | + "not found\n", optarg); | |
8754 | + err = -ENOENT; | |
8755 | + goto out; | |
8756 | + } | |
8757 | + /* check if there are any open files on the branch to be deleted */ | |
8758 | + if (atomic_read(&new_data[idx].open_files) > 0) { | |
8759 | + err = -EBUSY; | |
8760 | + goto out; | |
8761 | + } | |
8762 | + | |
8763 | + /* | |
8764 | + * Now we have to delete the branch. First, release any handles it | |
8765 | + * has. Then, move the remaining array indexes past "idx" in | |
8766 | + * new_data and new_lower_paths one to the left. Finally, adjust | |
8767 | + * cur_branches. | |
8768 | + */ | |
8769 | + path_put(&new_lower_paths[idx]); | |
8770 | + | |
8771 | + if (idx < cur_branches - 1) { | |
8772 | + /* if idx==cur_branches-1, we delete last branch: easy */ | |
8773 | + memmove(&new_data[idx], &new_data[idx+1], | |
8774 | + (cur_branches - 1 - idx) * | |
8775 | + sizeof(struct unionfs_data)); | |
8776 | + memmove(&new_lower_paths[idx], &new_lower_paths[idx+1], | |
8777 | + (cur_branches - 1 - idx) * sizeof(struct path)); | |
8778 | + } | |
8779 | + | |
8780 | + err = 0; | |
8781 | +out: | |
8782 | + return err; | |
8783 | +} | |
8784 | + | |
8785 | +/* handle branch insertion during remount */ | |
8786 | +static noinline_for_stack int do_remount_add_option( | |
8787 | + char *optarg, int cur_branches, | |
8788 | + struct unionfs_data *new_data, | |
8789 | + struct path *new_lower_paths, | |
8790 | + int *high_branch_id) | |
8791 | +{ | |
8792 | + int err = -EINVAL; | |
8793 | + int perms; | |
8794 | + int idx = 0; /* default: insert at beginning */ | |
8795 | + char *new_branch , *modename = NULL; | |
63b09289 | 8796 | + struct path path; |
2380c486 JR |
8797 | + |
8798 | + /* | |
8799 | + * optarg can be of several forms: | |
8800 | + * | |
8801 | + * /bar:/foo insert /foo before /bar | |
8802 | + * /bar:/foo=ro insert /foo in ro mode before /bar | |
8803 | + * /foo insert /foo in the beginning (prepend) | |
8804 | + * :/foo insert /foo at the end (append) | |
8805 | + */ | |
8806 | + if (*optarg == ':') { /* append? */ | |
8807 | + new_branch = optarg + 1; /* skip ':' */ | |
8808 | + idx = cur_branches; | |
8809 | + goto found_insertion_point; | |
8810 | + } | |
8811 | + new_branch = strchr(optarg, ':'); | |
8812 | + if (!new_branch) { /* prepend? */ | |
8813 | + new_branch = optarg; | |
8814 | + goto found_insertion_point; | |
8815 | + } | |
8816 | + *new_branch++ = '\0'; /* holds path+mode of new branch */ | |
8817 | + | |
8818 | + /* | |
8819 | + * Find matching branch index. For now, this assumes that nothing | |
8820 | + * has been mounted on top of this Unionfs stack. Once we have /odf | |
8821 | + * and cache-coherency resolved, we'll address the branch-path | |
8822 | + * uniqueness. | |
8823 | + */ | |
63b09289 | 8824 | + err = kern_path(optarg, LOOKUP_FOLLOW, &path); |
2380c486 JR |
8825 | + if (err) { |
8826 | + printk(KERN_ERR "unionfs: error accessing " | |
8827 | + "lower directory \"%s\" (error %d)\n", | |
8828 | + optarg, err); | |
8829 | + goto out; | |
8830 | + } | |
8831 | + for (idx = 0; idx < cur_branches; idx++) | |
63b09289 JR |
8832 | + if (path.mnt == new_lower_paths[idx].mnt && |
8833 | + path.dentry == new_lower_paths[idx].dentry) | |
2380c486 | 8834 | + break; |
63b09289 | 8835 | + path_put(&path); /* no longer needed */ |
2380c486 JR |
8836 | + if (idx == cur_branches) { |
8837 | + printk(KERN_ERR "unionfs: branch \"%s\" " | |
8838 | + "not found\n", optarg); | |
8839 | + err = -ENOENT; | |
8840 | + goto out; | |
8841 | + } | |
8842 | + | |
8843 | + /* | |
8844 | + * At this point idx will hold the index where the new branch should | |
8845 | + * be inserted before. | |
8846 | + */ | |
8847 | +found_insertion_point: | |
8848 | + /* find the mode for the new branch */ | |
8849 | + if (new_branch) | |
8850 | + modename = strchr(new_branch, '='); | |
8851 | + if (modename) | |
8852 | + *modename++ = '\0'; | |
8853 | + if (!new_branch || !*new_branch) { | |
8854 | + printk(KERN_ERR "unionfs: null new branch\n"); | |
8855 | + err = -EINVAL; | |
8856 | + goto out; | |
8857 | + } | |
8858 | + err = parse_branch_mode(modename, &perms); | |
8859 | + if (err) { | |
8860 | + printk(KERN_ERR "unionfs: invalid mode \"%s\" for " | |
8861 | + "branch \"%s\"\n", modename, new_branch); | |
8862 | + goto out; | |
8863 | + } | |
63b09289 | 8864 | + err = kern_path(new_branch, LOOKUP_FOLLOW, &path); |
2380c486 JR |
8865 | + if (err) { |
8866 | + printk(KERN_ERR "unionfs: error accessing " | |
8867 | + "lower directory \"%s\" (error %d)\n", | |
8868 | + new_branch, err); | |
8869 | + goto out; | |
8870 | + } | |
8871 | + /* | |
8872 | + * It's probably safe to check_mode the new branch to insert. Note: | |
8873 | + * we don't allow inserting branches which are unionfs's by | |
8874 | + * themselves (check_branch returns EINVAL in that case). This is | |
8875 | + * because this code base doesn't support stacking unionfs: the ODF | |
8876 | + * code base supports that correctly. | |
8877 | + */ | |
63b09289 | 8878 | + err = check_branch(&path); |
2380c486 JR |
8879 | + if (err) { |
8880 | + printk(KERN_ERR "unionfs: lower directory " | |
8881 | + "\"%s\" is not a valid branch\n", optarg); | |
63b09289 | 8882 | + path_put(&path); |
2380c486 JR |
8883 | + goto out; |
8884 | + } | |
8885 | + | |
8886 | + /* | |
8887 | + * Now we have to insert the new branch. But first, move the bits | |
8888 | + * to make space for the new branch, if needed. Finally, adjust | |
8889 | + * cur_branches. | |
8890 | + * We don't release nd here; it's kept until umount/remount. | |
8891 | + */ | |
8892 | + if (idx < cur_branches) { | |
8893 | + /* if idx==cur_branches, we append: easy */ | |
8894 | + memmove(&new_data[idx+1], &new_data[idx], | |
8895 | + (cur_branches - idx) * sizeof(struct unionfs_data)); | |
8896 | + memmove(&new_lower_paths[idx+1], &new_lower_paths[idx], | |
8897 | + (cur_branches - idx) * sizeof(struct path)); | |
8898 | + } | |
63b09289 JR |
8899 | + new_lower_paths[idx].dentry = path.dentry; |
8900 | + new_lower_paths[idx].mnt = path.mnt; | |
2380c486 | 8901 | + |
63b09289 | 8902 | + new_data[idx].sb = path.dentry->d_sb; |
2380c486 JR |
8903 | + atomic_set(&new_data[idx].open_files, 0); |
8904 | + new_data[idx].branchperms = perms; | |
8905 | + new_data[idx].branch_id = ++*high_branch_id; /* assign new branch ID */ | |
8906 | + | |
8907 | + err = 0; | |
8908 | +out: | |
8909 | + return err; | |
8910 | +} | |
8911 | + | |
8912 | + | |
8913 | +/* | |
8914 | + * Support branch management options on remount. | |
8915 | + * | |
8916 | + * See Documentation/filesystems/unionfs/ for details. | |
8917 | + * | |
8918 | + * @flags: numeric mount options | |
8919 | + * @options: mount options string | |
8920 | + * | |
8921 | + * This function can rearrange a mounted union dynamically, adding and | |
8922 | + * removing branches, including changing branch modes. Clearly this has to | |
8923 | + * be done safely and atomically. Luckily, the VFS already calls this | |
8924 | + * function with lock_super(sb) and lock_kernel() held, preventing | |
8925 | + * concurrent mixing of new mounts, remounts, and unmounts. Moreover, | |
8926 | + * do_remount_sb(), our caller function, already called shrink_dcache_sb(sb) | |
8927 | + * to purge dentries/inodes from our superblock, and also called | |
8928 | + * fsync_super(sb) to purge any dirty pages. So we're good. | |
8929 | + * | |
8930 | + * XXX: however, our remount code may also need to invalidate mapped pages | |
8931 | + * so as to force them to be re-gotten from the (newly reconfigured) lower | |
8932 | + * branches. This has to wait for proper mmap and cache coherency support | |
8933 | + * in the VFS. | |
8934 | + * | |
8935 | + */ | |
8936 | +static int unionfs_remount_fs(struct super_block *sb, int *flags, | |
8937 | + char *options) | |
8938 | +{ | |
8939 | + int err = 0; | |
8940 | + int i; | |
8941 | + char *optionstmp, *tmp_to_free; /* kstrdup'ed of "options" */ | |
8942 | + char *optname; | |
8943 | + int cur_branches = 0; /* no. of current branches */ | |
8944 | + int new_branches = 0; /* no. of branches actually left in the end */ | |
8945 | + int add_branches; /* est. no. of branches to add */ | |
8946 | + int del_branches; /* est. no. of branches to del */ | |
8947 | + int max_branches; /* max possible no. of branches */ | |
8948 | + struct unionfs_data *new_data = NULL, *tmp_data = NULL; | |
8949 | + struct path *new_lower_paths = NULL, *tmp_lower_paths = NULL; | |
8950 | + struct inode **new_lower_inodes = NULL; | |
8951 | + int new_high_branch_id; /* new high branch ID */ | |
8952 | + int size; /* memory allocation size, temp var */ | |
8953 | + int old_ibstart, old_ibend; | |
8954 | + | |
8955 | + unionfs_write_lock(sb); | |
8956 | + | |
8957 | + /* | |
8958 | + * The VFS will take care of "ro" and "rw" flags, and we can safely | |
8959 | + * ignore MS_SILENT, but anything else left over is an error. So we | |
8960 | + * need to check if any other flags may have been passed (none are | |
8961 | + * allowed/supported as of now). | |
8962 | + */ | |
8963 | + if ((*flags & ~(MS_RDONLY | MS_SILENT)) != 0) { | |
8964 | + printk(KERN_ERR | |
8965 | + "unionfs: remount flags 0x%x unsupported\n", *flags); | |
8966 | + err = -EINVAL; | |
8967 | + goto out_error; | |
8968 | + } | |
8969 | + | |
8970 | + /* | |
8971 | + * If 'options' is NULL, it's probably because the user just changed | |
8972 | + * the union to a "ro" or "rw" and the VFS took care of it. So | |
8973 | + * nothing to do and we're done. | |
8974 | + */ | |
8975 | + if (!options || options[0] == '\0') | |
8976 | + goto out_error; | |
8977 | + | |
8978 | + /* | |
8979 | + * Find out how many branches we will have in the end, counting | |
8980 | + * "add" and "del" commands. Copy the "options" string because | |
8981 | + * strsep modifies the string and we need it later. | |
8982 | + */ | |
8983 | + tmp_to_free = kstrdup(options, GFP_KERNEL); | |
8984 | + optionstmp = tmp_to_free; | |
8985 | + if (unlikely(!optionstmp)) { | |
8986 | + err = -ENOMEM; | |
8987 | + goto out_free; | |
8988 | + } | |
8989 | + cur_branches = sbmax(sb); /* current no. branches */ | |
8990 | + new_branches = sbmax(sb); | |
8991 | + del_branches = 0; | |
8992 | + add_branches = 0; | |
8993 | + new_high_branch_id = sbhbid(sb); /* save current high_branch_id */ | |
8994 | + while ((optname = strsep(&optionstmp, ",")) != NULL) { | |
8995 | + char *optarg; | |
8996 | + | |
8997 | + if (!optname || !*optname) | |
8998 | + continue; | |
8999 | + | |
9000 | + optarg = strchr(optname, '='); | |
9001 | + if (optarg) | |
9002 | + *optarg++ = '\0'; | |
9003 | + | |
9004 | + if (!strcmp("add", optname)) | |
9005 | + add_branches++; | |
9006 | + else if (!strcmp("del", optname)) | |
9007 | + del_branches++; | |
9008 | + } | |
9009 | + kfree(tmp_to_free); | |
9010 | + /* after all changes, will we have at least one branch left? */ | |
9011 | + if ((new_branches + add_branches - del_branches) < 1) { | |
9012 | + printk(KERN_ERR | |
9013 | + "unionfs: no branches left after remount\n"); | |
9014 | + err = -EINVAL; | |
9015 | + goto out_free; | |
9016 | + } | |
9017 | + | |
9018 | + /* | |
9019 | + * Since we haven't actually parsed all the add/del options, nor | |
9020 | + * have we checked them for errors, we don't know for sure how many | |
9021 | + * branches we will have after all changes have taken place. In | |
9022 | + * fact, the total number of branches left could be less than what | |
9023 | + * we have now. So we need to allocate space for a temporary | |
9024 | + * placeholder that is at least as large as the maximum number of | |
9025 | + * branches we *could* have, which is the current number plus all | |
9026 | + * the additions. Once we're done with these temp placeholders, we | |
9027 | + * may have to re-allocate the final size, copy over from the temp, | |
9028 | + * and then free the temps (done near the end of this function). | |
9029 | + */ | |
9030 | + max_branches = cur_branches + add_branches; | |
9031 | + /* allocate space for new pointers to lower dentry */ | |
9032 | + tmp_data = kcalloc(max_branches, | |
9033 | + sizeof(struct unionfs_data), GFP_KERNEL); | |
9034 | + if (unlikely(!tmp_data)) { | |
9035 | + err = -ENOMEM; | |
9036 | + goto out_free; | |
9037 | + } | |
9038 | + /* allocate space for new pointers to lower paths */ | |
9039 | + tmp_lower_paths = kcalloc(max_branches, | |
9040 | + sizeof(struct path), GFP_KERNEL); | |
9041 | + if (unlikely(!tmp_lower_paths)) { | |
9042 | + err = -ENOMEM; | |
9043 | + goto out_free; | |
9044 | + } | |
9045 | + /* copy current info into new placeholders, incrementing refcnts */ | |
9046 | + memcpy(tmp_data, UNIONFS_SB(sb)->data, | |
9047 | + cur_branches * sizeof(struct unionfs_data)); | |
9048 | + memcpy(tmp_lower_paths, UNIONFS_D(sb->s_root)->lower_paths, | |
9049 | + cur_branches * sizeof(struct path)); | |
9050 | + for (i = 0; i < cur_branches; i++) | |
9051 | + path_get(&tmp_lower_paths[i]); /* drop refs at end of fxn */ | |
9052 | + | |
9053 | + /******************************************************************* | |
63b09289 | 9054 | + * For each branch command, do kern_path on the requested branch, |
2380c486 JR |
9055 | + * and apply the change to a temp branch list. To handle errors, we |
9056 | + * already dup'ed the old arrays (above), and increased the refcnts | |
63b09289 | 9057 | + * on various f/s objects. So now we can do all the kern_path'ss |
2380c486 JR |
9058 | + * and branch-management commands on the new arrays. If it fail mid |
9059 | + * way, we free the tmp arrays and *put all objects. If we succeed, | |
9060 | + * then we free old arrays and *put its objects, and then replace | |
9061 | + * the arrays with the new tmp list (we may have to re-allocate the | |
9062 | + * memory because the temp lists could have been larger than what we | |
9063 | + * actually needed). | |
9064 | + *******************************************************************/ | |
9065 | + | |
9066 | + while ((optname = strsep(&options, ",")) != NULL) { | |
9067 | + char *optarg; | |
9068 | + | |
9069 | + if (!optname || !*optname) | |
9070 | + continue; | |
9071 | + /* | |
9072 | + * At this stage optname holds a comma-delimited option, but | |
9073 | + * without the commas. Next, we need to break the string on | |
9074 | + * the '=' symbol to separate CMD=ARG, where ARG itself can | |
9075 | + * be KEY=VAL. For example, in mode=/foo=rw, CMD is "mode", | |
9076 | + * KEY is "/foo", and VAL is "rw". | |
9077 | + */ | |
9078 | + optarg = strchr(optname, '='); | |
9079 | + if (optarg) | |
9080 | + *optarg++ = '\0'; | |
9081 | + /* incgen remount option (instead of old ioctl) */ | |
9082 | + if (!strcmp("incgen", optname)) { | |
9083 | + err = 0; | |
9084 | + goto out_no_change; | |
9085 | + } | |
9086 | + | |
9087 | + /* | |
9088 | + * All of our options take an argument now. (Insert ones | |
9089 | + * that don't above this check.) So at this stage optname | |
9090 | + * contains the CMD part and optarg contains the ARG part. | |
9091 | + */ | |
9092 | + if (!optarg || !*optarg) { | |
9093 | + printk(KERN_ERR "unionfs: all remount options require " | |
9094 | + "an argument (%s)\n", optname); | |
9095 | + err = -EINVAL; | |
9096 | + goto out_release; | |
9097 | + } | |
9098 | + | |
9099 | + if (!strcmp("add", optname)) { | |
9100 | + err = do_remount_add_option(optarg, new_branches, | |
9101 | + tmp_data, | |
9102 | + tmp_lower_paths, | |
9103 | + &new_high_branch_id); | |
9104 | + if (err) | |
9105 | + goto out_release; | |
9106 | + new_branches++; | |
9107 | + if (new_branches > UNIONFS_MAX_BRANCHES) { | |
9108 | + printk(KERN_ERR "unionfs: command exceeds " | |
9109 | + "%d branches\n", UNIONFS_MAX_BRANCHES); | |
9110 | + err = -E2BIG; | |
9111 | + goto out_release; | |
9112 | + } | |
9113 | + continue; | |
9114 | + } | |
9115 | + if (!strcmp("del", optname)) { | |
9116 | + err = do_remount_del_option(optarg, new_branches, | |
9117 | + tmp_data, | |
9118 | + tmp_lower_paths); | |
9119 | + if (err) | |
9120 | + goto out_release; | |
9121 | + new_branches--; | |
9122 | + continue; | |
9123 | + } | |
9124 | + if (!strcmp("mode", optname)) { | |
9125 | + err = do_remount_mode_option(optarg, new_branches, | |
9126 | + tmp_data, | |
9127 | + tmp_lower_paths); | |
9128 | + if (err) | |
9129 | + goto out_release; | |
9130 | + continue; | |
9131 | + } | |
9132 | + | |
9133 | + /* | |
9134 | + * When you use "mount -o remount,ro", mount(8) will | |
9135 | + * reportedly pass the original dirs= string from | |
9136 | + * /proc/mounts. So for now, we have to ignore dirs= and | |
9137 | + * not consider it an error, unless we want to allow users | |
9138 | + * to pass dirs= in remount. Note that to allow the VFS to | |
9139 | + * actually process the ro/rw remount options, we have to | |
9140 | + * return 0 from this function. | |
9141 | + */ | |
9142 | + if (!strcmp("dirs", optname)) { | |
9143 | + printk(KERN_WARNING | |
9144 | + "unionfs: remount ignoring option \"%s\"\n", | |
9145 | + optname); | |
9146 | + continue; | |
9147 | + } | |
9148 | + | |
9149 | + err = -EINVAL; | |
9150 | + printk(KERN_ERR | |
9151 | + "unionfs: unrecognized option \"%s\"\n", optname); | |
9152 | + goto out_release; | |
9153 | + } | |
9154 | + | |
9155 | +out_no_change: | |
9156 | + | |
9157 | + /****************************************************************** | |
9158 | + * WE'RE ALMOST DONE: check if leftmost branch might be read-only, | |
9159 | + * see if we need to allocate a small-sized new vector, copy the | |
9160 | + * vectors to their correct place, release the refcnt of the older | |
9161 | + * ones, and return. Also handle invalidating any pages that will | |
9162 | + * have to be re-read. | |
9163 | + *******************************************************************/ | |
9164 | + | |
9165 | + if (!(tmp_data[0].branchperms & MAY_WRITE)) { | |
9166 | + printk(KERN_ERR "unionfs: leftmost branch cannot be read-only " | |
9167 | + "(use \"remount,ro\" to create a read-only union)\n"); | |
9168 | + err = -EINVAL; | |
9169 | + goto out_release; | |
9170 | + } | |
9171 | + | |
9172 | + /* (re)allocate space for new pointers to lower dentry */ | |
9173 | + size = new_branches * sizeof(struct unionfs_data); | |
9174 | + new_data = krealloc(tmp_data, size, GFP_KERNEL); | |
9175 | + if (unlikely(!new_data)) { | |
9176 | + err = -ENOMEM; | |
9177 | + goto out_release; | |
9178 | + } | |
9179 | + | |
9180 | + /* allocate space for new pointers to lower paths */ | |
9181 | + size = new_branches * sizeof(struct path); | |
9182 | + new_lower_paths = krealloc(tmp_lower_paths, size, GFP_KERNEL); | |
9183 | + if (unlikely(!new_lower_paths)) { | |
9184 | + err = -ENOMEM; | |
9185 | + goto out_release; | |
9186 | + } | |
9187 | + | |
9188 | + /* allocate space for new pointers to lower inodes */ | |
9189 | + new_lower_inodes = kcalloc(new_branches, | |
9190 | + sizeof(struct inode *), GFP_KERNEL); | |
9191 | + if (unlikely(!new_lower_inodes)) { | |
9192 | + err = -ENOMEM; | |
9193 | + goto out_release; | |
9194 | + } | |
9195 | + | |
9196 | + /* | |
9197 | + * OK, just before we actually put the new set of branches in place, | |
9198 | + * we need to ensure that our own f/s has no dirty objects left. | |
9199 | + * Luckily, do_remount_sb() already calls shrink_dcache_sb(sb) and | |
9200 | + * fsync_super(sb), taking care of dentries, inodes, and dirty | |
9201 | + * pages. So all that's left is for us to invalidate any leftover | |
9202 | + * (non-dirty) pages to ensure that they will be re-read from the | |
9203 | + * new lower branches (and to support mmap). | |
9204 | + */ | |
9205 | + | |
9206 | + /* | |
9207 | + * Once we finish the remounting successfully, our superblock | |
9208 | + * generation number will have increased. This will be detected by | |
9209 | + * our dentry-revalidation code upon subsequent f/s operations | |
9210 | + * through unionfs. The revalidation code will rebuild the union of | |
9211 | + * lower inodes for a given unionfs inode and invalidate any pages | |
9212 | + * of such "stale" inodes (by calling our purge_inode_data | |
9213 | + * function). This revalidation will happen lazily and | |
9214 | + * incrementally, as users perform operations on cached inodes. We | |
9215 | + * would like to encourage this revalidation to happen sooner if | |
9216 | + * possible, so we like to try to invalidate as many other pages in | |
9217 | + * our superblock as we can. We used to call drop_pagecache_sb() or | |
9218 | + * a variant thereof, but either method was racy (drop_caches alone | |
9219 | + * is known to be racy). So now we let the revalidation happen on a | |
9220 | + * per file basis in ->d_revalidate. | |
9221 | + */ | |
9222 | + | |
9223 | + /* grab new lower super references; release old ones */ | |
9224 | + for (i = 0; i < new_branches; i++) | |
9225 | + atomic_inc(&new_data[i].sb->s_active); | |
9226 | + for (i = 0; i < sbmax(sb); i++) | |
9227 | + atomic_dec(&UNIONFS_SB(sb)->data[i].sb->s_active); | |
9228 | + | |
9229 | + /* copy new vectors into their correct place */ | |
9230 | + tmp_data = UNIONFS_SB(sb)->data; | |
9231 | + UNIONFS_SB(sb)->data = new_data; | |
9232 | + new_data = NULL; /* so don't free good pointers below */ | |
9233 | + tmp_lower_paths = UNIONFS_D(sb->s_root)->lower_paths; | |
9234 | + UNIONFS_D(sb->s_root)->lower_paths = new_lower_paths; | |
9235 | + new_lower_paths = NULL; /* so don't free good pointers below */ | |
9236 | + | |
9237 | + /* update our unionfs_sb_info and root dentry index of last branch */ | |
9238 | + i = sbmax(sb); /* save no. of branches to release at end */ | |
9239 | + sbend(sb) = new_branches - 1; | |
9240 | + dbend(sb->s_root) = new_branches - 1; | |
9241 | + old_ibstart = ibstart(sb->s_root->d_inode); | |
9242 | + old_ibend = ibend(sb->s_root->d_inode); | |
9243 | + ibend(sb->s_root->d_inode) = new_branches - 1; | |
9244 | + UNIONFS_D(sb->s_root)->bcount = new_branches; | |
9245 | + new_branches = i; /* no. of branches to release below */ | |
9246 | + | |
9247 | + /* | |
9248 | + * Update lower inodes: 3 steps | |
9249 | + * 1. grab ref on all new lower inodes | |
9250 | + */ | |
9251 | + for (i = dbstart(sb->s_root); i <= dbend(sb->s_root); i++) { | |
9252 | + struct dentry *lower_dentry = | |
9253 | + unionfs_lower_dentry_idx(sb->s_root, i); | |
9254 | + igrab(lower_dentry->d_inode); | |
9255 | + new_lower_inodes[i] = lower_dentry->d_inode; | |
9256 | + } | |
9257 | + /* 2. release reference on all older lower inodes */ | |
9258 | + iput_lowers(sb->s_root->d_inode, old_ibstart, old_ibend, true); | |
9259 | + /* 3. update root dentry's inode to new lower_inodes array */ | |
9260 | + UNIONFS_I(sb->s_root->d_inode)->lower_inodes = new_lower_inodes; | |
9261 | + new_lower_inodes = NULL; | |
9262 | + | |
9263 | + /* maxbytes may have changed */ | |
9264 | + sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes; | |
9265 | + /* update high branch ID */ | |
9266 | + sbhbid(sb) = new_high_branch_id; | |
9267 | + | |
9268 | + /* update our sb->generation for revalidating objects */ | |
9269 | + i = atomic_inc_return(&UNIONFS_SB(sb)->generation); | |
9270 | + atomic_set(&UNIONFS_D(sb->s_root)->generation, i); | |
9271 | + atomic_set(&UNIONFS_I(sb->s_root->d_inode)->generation, i); | |
9272 | + if (!(*flags & MS_SILENT)) | |
9273 | + pr_info("unionfs: %s: new generation number %d\n", | |
9274 | + UNIONFS_SB(sb)->dev_name, i); | |
9275 | + /* finally, update the root dentry's times */ | |
9276 | + unionfs_copy_attr_times(sb->s_root->d_inode); | |
9277 | + err = 0; /* reset to success */ | |
9278 | + | |
9279 | + /* | |
9280 | + * The code above falls through to the next label, and releases the | |
9281 | + * refcnts of the older ones (stored in tmp_*): if we fell through | |
9282 | + * here, it means success. However, if we jump directly to this | |
9283 | + * label from any error above, then an error occurred after we | |
9284 | + * grabbed various refcnts, and so we have to release the | |
9285 | + * temporarily constructed structures. | |
9286 | + */ | |
9287 | +out_release: | |
9288 | + /* no need to cleanup/release anything in tmp_data */ | |
9289 | + if (tmp_lower_paths) | |
9290 | + for (i = 0; i < new_branches; i++) | |
9291 | + path_put(&tmp_lower_paths[i]); | |
9292 | +out_free: | |
9293 | + kfree(tmp_lower_paths); | |
9294 | + kfree(tmp_data); | |
9295 | + kfree(new_lower_paths); | |
9296 | + kfree(new_data); | |
9297 | + kfree(new_lower_inodes); | |
9298 | +out_error: | |
9299 | + unionfs_check_dentry(sb->s_root); | |
9300 | + unionfs_write_unlock(sb); | |
9301 | + return err; | |
9302 | +} | |
9303 | + | |
9304 | +/* | |
9305 | + * Called by iput() when the inode reference count reached zero | |
9306 | + * and the inode is not hashed anywhere. Used to clear anything | |
9307 | + * that needs to be, before the inode is completely destroyed and put | |
9308 | + * on the inode free list. | |
9309 | + * | |
9310 | + * No need to lock sb info's rwsem. | |
9311 | + */ | |
0c5527e5 | 9312 | +static void unionfs_evict_inode(struct inode *inode) |
2380c486 JR |
9313 | +{ |
9314 | + int bindex, bstart, bend; | |
9315 | + struct inode *lower_inode; | |
9316 | + struct list_head *pos, *n; | |
9317 | + struct unionfs_dir_state *rdstate; | |
9318 | + | |
0c5527e5 AM |
9319 | + truncate_inode_pages(&inode->i_data, 0); |
9320 | + end_writeback(inode); | |
9321 | + | |
2380c486 JR |
9322 | + list_for_each_safe(pos, n, &UNIONFS_I(inode)->readdircache) { |
9323 | + rdstate = list_entry(pos, struct unionfs_dir_state, cache); | |
9324 | + list_del(&rdstate->cache); | |
9325 | + free_rdstate(rdstate); | |
9326 | + } | |
9327 | + | |
9328 | + /* | |
9329 | + * Decrement a reference to a lower_inode, which was incremented | |
9330 | + * by our read_inode when it was created initially. | |
9331 | + */ | |
9332 | + bstart = ibstart(inode); | |
9333 | + bend = ibend(inode); | |
9334 | + if (bstart >= 0) { | |
9335 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
9336 | + lower_inode = unionfs_lower_inode_idx(inode, bindex); | |
9337 | + if (!lower_inode) | |
9338 | + continue; | |
9339 | + unionfs_set_lower_inode_idx(inode, bindex, NULL); | |
9340 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
9341 | + lockdep_off(); | |
9342 | + iput(lower_inode); | |
9343 | + lockdep_on(); | |
9344 | + } | |
9345 | + } | |
9346 | + | |
9347 | + kfree(UNIONFS_I(inode)->lower_inodes); | |
9348 | + UNIONFS_I(inode)->lower_inodes = NULL; | |
9349 | +} | |
9350 | + | |
9351 | +static struct inode *unionfs_alloc_inode(struct super_block *sb) | |
9352 | +{ | |
9353 | + struct unionfs_inode_info *i; | |
9354 | + | |
9355 | + i = kmem_cache_alloc(unionfs_inode_cachep, GFP_KERNEL); | |
9356 | + if (unlikely(!i)) | |
9357 | + return NULL; | |
9358 | + | |
9359 | + /* memset everything up to the inode to 0 */ | |
9360 | + memset(i, 0, offsetof(struct unionfs_inode_info, vfs_inode)); | |
9361 | + | |
9362 | + i->vfs_inode.i_version = 1; | |
9363 | + return &i->vfs_inode; | |
9364 | +} | |
9365 | + | |
9366 | +static void unionfs_destroy_inode(struct inode *inode) | |
9367 | +{ | |
9368 | + kmem_cache_free(unionfs_inode_cachep, UNIONFS_I(inode)); | |
9369 | +} | |
9370 | + | |
9371 | +/* unionfs inode cache constructor */ | |
9372 | +static void init_once(void *obj) | |
9373 | +{ | |
9374 | + struct unionfs_inode_info *i = obj; | |
9375 | + | |
9376 | + inode_init_once(&i->vfs_inode); | |
9377 | +} | |
9378 | + | |
9379 | +int unionfs_init_inode_cache(void) | |
9380 | +{ | |
9381 | + int err = 0; | |
9382 | + | |
9383 | + unionfs_inode_cachep = | |
9384 | + kmem_cache_create("unionfs_inode_cache", | |
9385 | + sizeof(struct unionfs_inode_info), 0, | |
9386 | + SLAB_RECLAIM_ACCOUNT, init_once); | |
9387 | + if (unlikely(!unionfs_inode_cachep)) | |
9388 | + err = -ENOMEM; | |
9389 | + return err; | |
9390 | +} | |
9391 | + | |
9392 | +/* unionfs inode cache destructor */ | |
9393 | +void unionfs_destroy_inode_cache(void) | |
9394 | +{ | |
9395 | + if (unionfs_inode_cachep) | |
9396 | + kmem_cache_destroy(unionfs_inode_cachep); | |
9397 | +} | |
9398 | + | |
9399 | +/* | |
9400 | + * Called when we have a dirty inode, right here we only throw out | |
9401 | + * parts of our readdir list that are too old. | |
9402 | + * | |
9403 | + * No need to grab sb info's rwsem. | |
9404 | + */ | |
0c5527e5 AM |
9405 | +static int unionfs_write_inode(struct inode *inode, |
9406 | + struct writeback_control *wbc) | |
2380c486 JR |
9407 | +{ |
9408 | + struct list_head *pos, *n; | |
9409 | + struct unionfs_dir_state *rdstate; | |
9410 | + | |
9411 | + spin_lock(&UNIONFS_I(inode)->rdlock); | |
9412 | + list_for_each_safe(pos, n, &UNIONFS_I(inode)->readdircache) { | |
9413 | + rdstate = list_entry(pos, struct unionfs_dir_state, cache); | |
9414 | + /* We keep this list in LRU order. */ | |
9415 | + if ((rdstate->access + RDCACHE_JIFFIES) > jiffies) | |
9416 | + break; | |
9417 | + UNIONFS_I(inode)->rdcount--; | |
9418 | + list_del(&rdstate->cache); | |
9419 | + free_rdstate(rdstate); | |
9420 | + } | |
9421 | + spin_unlock(&UNIONFS_I(inode)->rdlock); | |
9422 | + | |
9423 | + return 0; | |
9424 | +} | |
9425 | + | |
9426 | +/* | |
9427 | + * Used only in nfs, to kill any pending RPC tasks, so that subsequent | |
9428 | + * code can actually succeed and won't leave tasks that need handling. | |
9429 | + */ | |
9430 | +static void unionfs_umount_begin(struct super_block *sb) | |
9431 | +{ | |
9432 | + struct super_block *lower_sb; | |
9433 | + int bindex, bstart, bend; | |
9434 | + | |
9435 | + unionfs_read_lock(sb, UNIONFS_SMUTEX_CHILD); | |
9436 | + | |
9437 | + bstart = sbstart(sb); | |
9438 | + bend = sbend(sb); | |
9439 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
9440 | + lower_sb = unionfs_lower_super_idx(sb, bindex); | |
9441 | + | |
9442 | + if (lower_sb && lower_sb->s_op && | |
9443 | + lower_sb->s_op->umount_begin) | |
9444 | + lower_sb->s_op->umount_begin(lower_sb); | |
9445 | + } | |
9446 | + | |
9447 | + unionfs_read_unlock(sb); | |
9448 | +} | |
9449 | + | |
92d182d2 | 9450 | +static int unionfs_show_options(struct seq_file *m, struct dentry *root) |
2380c486 | 9451 | +{ |
92d182d2 | 9452 | + struct super_block *sb = root->d_sb; |
2380c486 JR |
9453 | + int ret = 0; |
9454 | + char *tmp_page; | |
9455 | + char *path; | |
9456 | + int bindex, bstart, bend; | |
9457 | + int perms; | |
9458 | + | |
63b09289 JR |
9459 | + /* to prevent a silly lockdep warning with namespace_sem */ |
9460 | + lockdep_off(); | |
2380c486 | 9461 | + unionfs_read_lock(sb, UNIONFS_SMUTEX_CHILD); |
2380c486 JR |
9462 | + unionfs_lock_dentry(sb->s_root, UNIONFS_DMUTEX_CHILD); |
9463 | + | |
9464 | + tmp_page = (char *) __get_free_page(GFP_KERNEL); | |
9465 | + if (unlikely(!tmp_page)) { | |
9466 | + ret = -ENOMEM; | |
9467 | + goto out; | |
9468 | + } | |
9469 | + | |
9470 | + bstart = sbstart(sb); | |
9471 | + bend = sbend(sb); | |
9472 | + | |
9473 | + seq_printf(m, ",dirs="); | |
9474 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
9475 | + struct path p; | |
9476 | + p.dentry = unionfs_lower_dentry_idx(sb->s_root, bindex); | |
9477 | + p.mnt = unionfs_lower_mnt_idx(sb->s_root, bindex); | |
9478 | + path = d_path(&p, tmp_page, PAGE_SIZE); | |
9479 | + if (IS_ERR(path)) { | |
9480 | + ret = PTR_ERR(path); | |
9481 | + goto out; | |
9482 | + } | |
9483 | + | |
9484 | + perms = branchperms(sb, bindex); | |
9485 | + | |
9486 | + seq_printf(m, "%s=%s", path, | |
9487 | + perms & MAY_WRITE ? "rw" : "ro"); | |
9488 | + if (bindex != bend) | |
9489 | + seq_printf(m, ":"); | |
9490 | + } | |
9491 | + | |
9492 | +out: | |
9493 | + free_page((unsigned long) tmp_page); | |
9494 | + | |
9495 | + unionfs_unlock_dentry(sb->s_root); | |
2380c486 | 9496 | + unionfs_read_unlock(sb); |
63b09289 | 9497 | + lockdep_on(); |
2380c486 JR |
9498 | + |
9499 | + return ret; | |
9500 | +} | |
9501 | + | |
9502 | +struct super_operations unionfs_sops = { | |
2380c486 JR |
9503 | + .put_super = unionfs_put_super, |
9504 | + .statfs = unionfs_statfs, | |
9505 | + .remount_fs = unionfs_remount_fs, | |
0c5527e5 | 9506 | + .evict_inode = unionfs_evict_inode, |
2380c486 JR |
9507 | + .umount_begin = unionfs_umount_begin, |
9508 | + .show_options = unionfs_show_options, | |
9509 | + .write_inode = unionfs_write_inode, | |
9510 | + .alloc_inode = unionfs_alloc_inode, | |
9511 | + .destroy_inode = unionfs_destroy_inode, | |
9512 | +}; | |
0c5527e5 AM |
9513 | diff --git a/fs/unionfs/union.h b/fs/unionfs/union.h |
9514 | new file mode 100644 | |
6b53c3da | 9515 | index 0000000..8e7fcfb |
0c5527e5 AM |
9516 | --- /dev/null |
9517 | +++ b/fs/unionfs/union.h | |
6b53c3da | 9518 | @@ -0,0 +1,681 @@ |
2380c486 | 9519 | +/* |
63b09289 | 9520 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
9521 | + * Copyright (c) 2003-2006 Charles P. Wright |
9522 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
9523 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
9524 | + * Copyright (c) 2004-2006 David P. Quigley | |
9525 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
9526 | + * Copyright (c) 2003 Puja Gupta | |
9527 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
9528 | + * Copyright (c) 2003-2011 Stony Brook University |
9529 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
9530 | + * |
9531 | + * This program is free software; you can redistribute it and/or modify | |
9532 | + * it under the terms of the GNU General Public License version 2 as | |
9533 | + * published by the Free Software Foundation. | |
9534 | + */ | |
9535 | + | |
9536 | +#ifndef _UNION_H_ | |
9537 | +#define _UNION_H_ | |
9538 | + | |
9539 | +#include <linux/dcache.h> | |
9540 | +#include <linux/file.h> | |
9541 | +#include <linux/list.h> | |
9542 | +#include <linux/fs.h> | |
9543 | +#include <linux/mm.h> | |
9544 | +#include <linux/module.h> | |
9545 | +#include <linux/mount.h> | |
9546 | +#include <linux/namei.h> | |
9547 | +#include <linux/page-flags.h> | |
9548 | +#include <linux/pagemap.h> | |
9549 | +#include <linux/poll.h> | |
9550 | +#include <linux/security.h> | |
9551 | +#include <linux/seq_file.h> | |
9552 | +#include <linux/slab.h> | |
9553 | +#include <linux/spinlock.h> | |
2380c486 JR |
9554 | +#include <linux/statfs.h> |
9555 | +#include <linux/string.h> | |
9556 | +#include <linux/vmalloc.h> | |
9557 | +#include <linux/writeback.h> | |
9558 | +#include <linux/buffer_head.h> | |
9559 | +#include <linux/xattr.h> | |
9560 | +#include <linux/fs_stack.h> | |
9561 | +#include <linux/magic.h> | |
9562 | +#include <linux/log2.h> | |
9563 | +#include <linux/poison.h> | |
9564 | +#include <linux/mman.h> | |
9565 | +#include <linux/backing-dev.h> | |
9566 | +#include <linux/splice.h> | |
63b09289 | 9567 | +#include <linux/sched.h> |
2380c486 | 9568 | + |
92d182d2 | 9569 | + |
2380c486 JR |
9570 | + |
9571 | +#include <linux/union_fs.h> | |
9572 | + | |
9573 | +/* the file system name */ | |
9574 | +#define UNIONFS_NAME "unionfs" | |
9575 | + | |
9576 | +/* unionfs root inode number */ | |
9577 | +#define UNIONFS_ROOT_INO 1 | |
9578 | + | |
9579 | +/* number of times we try to get a unique temporary file name */ | |
9580 | +#define GET_TMPNAM_MAX_RETRY 5 | |
9581 | + | |
9582 | +/* maximum number of branches we support, to avoid memory blowup */ | |
9583 | +#define UNIONFS_MAX_BRANCHES 128 | |
9584 | + | |
9585 | +/* minimum time (seconds) required for time-based cache-coherency */ | |
9586 | +#define UNIONFS_MIN_CC_TIME 3 | |
9587 | + | |
9588 | +/* Operations vectors defined in specific files. */ | |
9589 | +extern struct file_operations unionfs_main_fops; | |
9590 | +extern struct file_operations unionfs_dir_fops; | |
9591 | +extern struct inode_operations unionfs_main_iops; | |
9592 | +extern struct inode_operations unionfs_dir_iops; | |
9593 | +extern struct inode_operations unionfs_symlink_iops; | |
9594 | +extern struct super_operations unionfs_sops; | |
9595 | +extern struct dentry_operations unionfs_dops; | |
9596 | +extern struct address_space_operations unionfs_aops, unionfs_dummy_aops; | |
9597 | +extern struct vm_operations_struct unionfs_vm_ops; | |
9598 | + | |
9599 | +/* How long should an entry be allowed to persist */ | |
9600 | +#define RDCACHE_JIFFIES (5*HZ) | |
9601 | + | |
9602 | +/* compatibility with Real-Time patches */ | |
9603 | +#ifdef CONFIG_PREEMPT_RT | |
9604 | +# define unionfs_rw_semaphore compat_rw_semaphore | |
9605 | +#else /* not CONFIG_PREEMPT_RT */ | |
9606 | +# define unionfs_rw_semaphore rw_semaphore | |
9607 | +#endif /* not CONFIG_PREEMPT_RT */ | |
9608 | + | |
9609 | +/* file private data. */ | |
9610 | +struct unionfs_file_info { | |
9611 | + int bstart; | |
9612 | + int bend; | |
9613 | + atomic_t generation; | |
9614 | + | |
9615 | + struct unionfs_dir_state *rdstate; | |
9616 | + struct file **lower_files; | |
9617 | + int *saved_branch_ids; /* IDs of branches when file was opened */ | |
7670a7fc | 9618 | + const struct vm_operations_struct *lower_vm_ops; |
2380c486 JR |
9619 | + bool wrote_to_file; /* for delayed copyup */ |
9620 | +}; | |
9621 | + | |
9622 | +/* unionfs inode data in memory */ | |
9623 | +struct unionfs_inode_info { | |
9624 | + int bstart; | |
9625 | + int bend; | |
9626 | + atomic_t generation; | |
9627 | + /* Stuff for readdir over NFS. */ | |
9628 | + spinlock_t rdlock; | |
9629 | + struct list_head readdircache; | |
9630 | + int rdcount; | |
9631 | + int hashsize; | |
9632 | + int cookie; | |
9633 | + | |
9634 | + /* The lower inodes */ | |
9635 | + struct inode **lower_inodes; | |
9636 | + | |
9637 | + struct inode vfs_inode; | |
9638 | +}; | |
9639 | + | |
9640 | +/* unionfs dentry data in memory */ | |
9641 | +struct unionfs_dentry_info { | |
9642 | + /* | |
9643 | + * The semaphore is used to lock the dentry as soon as we get into a | |
9644 | + * unionfs function from the VFS. Our lock ordering is that children | |
9645 | + * go before their parents. | |
9646 | + */ | |
9647 | + struct mutex lock; | |
9648 | + int bstart; | |
9649 | + int bend; | |
9650 | + int bopaque; | |
9651 | + int bcount; | |
9652 | + atomic_t generation; | |
9653 | + struct path *lower_paths; | |
9654 | +}; | |
9655 | + | |
9656 | +/* These are the pointers to our various objects. */ | |
9657 | +struct unionfs_data { | |
9658 | + struct super_block *sb; /* lower super_block */ | |
9659 | + atomic_t open_files; /* number of open files on branch */ | |
9660 | + int branchperms; | |
9661 | + int branch_id; /* unique branch ID at re/mount time */ | |
9662 | +}; | |
9663 | + | |
9664 | +/* unionfs super-block data in memory */ | |
9665 | +struct unionfs_sb_info { | |
9666 | + int bend; | |
9667 | + | |
9668 | + atomic_t generation; | |
9669 | + | |
9670 | + /* | |
9671 | + * This rwsem is used to make sure that a branch management | |
9672 | + * operation... | |
9673 | + * 1) will not begin before all currently in-flight operations | |
9674 | + * complete. | |
9675 | + * 2) any new operations do not execute until the currently | |
9676 | + * running branch management operation completes. | |
9677 | + * | |
9678 | + * The write_lock_owner records the PID of the task which grabbed | |
9679 | + * the rw_sem for writing. If the same task also tries to grab the | |
9680 | + * read lock, we allow it. This prevents a self-deadlock when | |
9681 | + * branch-management is used on a pivot_root'ed union, because we | |
9682 | + * have to ->lookup paths which belong to the same union. | |
9683 | + */ | |
9684 | + struct unionfs_rw_semaphore rwsem; | |
9685 | + pid_t write_lock_owner; /* PID of rw_sem owner (write lock) */ | |
9686 | + int high_branch_id; /* last unique branch ID given */ | |
9687 | + char *dev_name; /* to identify different unions in pr_debug */ | |
9688 | + struct unionfs_data *data; | |
9689 | +}; | |
9690 | + | |
9691 | +/* | |
9692 | + * structure for making the linked list of entries by readdir on left branch | |
9693 | + * to compare with entries on right branch | |
9694 | + */ | |
9695 | +struct filldir_node { | |
9696 | + struct list_head file_list; /* list for directory entries */ | |
9697 | + char *name; /* name entry */ | |
9698 | + int hash; /* name hash */ | |
9699 | + int namelen; /* name len since name is not 0 terminated */ | |
9700 | + | |
9701 | + /* | |
9702 | + * we can check for duplicate whiteouts and files in the same branch | |
9703 | + * in order to return -EIO. | |
9704 | + */ | |
9705 | + int bindex; | |
9706 | + | |
9707 | + /* is this a whiteout entry? */ | |
9708 | + int whiteout; | |
9709 | + | |
9710 | + /* Inline name, so we don't need to separately kmalloc small ones */ | |
82260373 | 9711 | + char iname[DNAME_INLINE_LEN]; |
2380c486 JR |
9712 | +}; |
9713 | + | |
9714 | +/* Directory hash table. */ | |
9715 | +struct unionfs_dir_state { | |
9716 | + unsigned int cookie; /* the cookie, based off of rdversion */ | |
9717 | + unsigned int offset; /* The entry we have returned. */ | |
9718 | + int bindex; | |
9719 | + loff_t dirpos; /* offset within the lower level directory */ | |
9720 | + int size; /* How big is the hash table? */ | |
9721 | + int hashentries; /* How many entries have been inserted? */ | |
9722 | + unsigned long access; | |
9723 | + | |
9724 | + /* This cache list is used when the inode keeps us around. */ | |
9725 | + struct list_head cache; | |
9726 | + struct list_head list[0]; | |
9727 | +}; | |
9728 | + | |
9729 | +/* externs needed for fanout.h or sioq.h */ | |
9730 | +extern int unionfs_get_nlinks(const struct inode *inode); | |
9731 | +extern void unionfs_copy_attr_times(struct inode *upper); | |
9732 | +extern void unionfs_copy_attr_all(struct inode *dest, const struct inode *src); | |
9733 | + | |
9734 | +/* include miscellaneous macros */ | |
9735 | +#include "fanout.h" | |
9736 | +#include "sioq.h" | |
9737 | + | |
9738 | +/* externs for cache creation/deletion routines */ | |
9739 | +extern void unionfs_destroy_filldir_cache(void); | |
9740 | +extern int unionfs_init_filldir_cache(void); | |
9741 | +extern int unionfs_init_inode_cache(void); | |
9742 | +extern void unionfs_destroy_inode_cache(void); | |
9743 | +extern int unionfs_init_dentry_cache(void); | |
9744 | +extern void unionfs_destroy_dentry_cache(void); | |
9745 | + | |
9746 | +/* Initialize and free readdir-specific state. */ | |
9747 | +extern int init_rdstate(struct file *file); | |
9748 | +extern struct unionfs_dir_state *alloc_rdstate(struct inode *inode, | |
9749 | + int bindex); | |
9750 | +extern struct unionfs_dir_state *find_rdstate(struct inode *inode, | |
9751 | + loff_t fpos); | |
9752 | +extern void free_rdstate(struct unionfs_dir_state *state); | |
9753 | +extern int add_filldir_node(struct unionfs_dir_state *rdstate, | |
9754 | + const char *name, int namelen, int bindex, | |
9755 | + int whiteout); | |
9756 | +extern struct filldir_node *find_filldir_node(struct unionfs_dir_state *rdstate, | |
9757 | + const char *name, int namelen, | |
9758 | + int is_whiteout); | |
9759 | + | |
9760 | +extern struct dentry **alloc_new_dentries(int objs); | |
9761 | +extern struct unionfs_data *alloc_new_data(int objs); | |
9762 | + | |
9763 | +/* We can only use 32-bits of offset for rdstate --- blech! */ | |
9764 | +#define DIREOF (0xfffff) | |
9765 | +#define RDOFFBITS 20 /* This is the number of bits in DIREOF. */ | |
9766 | +#define MAXRDCOOKIE (0xfff) | |
9767 | +/* Turn an rdstate into an offset. */ | |
9768 | +static inline off_t rdstate2offset(struct unionfs_dir_state *buf) | |
9769 | +{ | |
9770 | + off_t tmp; | |
9771 | + | |
9772 | + tmp = ((buf->cookie & MAXRDCOOKIE) << RDOFFBITS) | |
9773 | + | (buf->offset & DIREOF); | |
9774 | + return tmp; | |
9775 | +} | |
9776 | + | |
9777 | +/* Macros for locking a super_block. */ | |
9778 | +enum unionfs_super_lock_class { | |
9779 | + UNIONFS_SMUTEX_NORMAL, | |
9780 | + UNIONFS_SMUTEX_PARENT, /* when locking on behalf of file */ | |
9781 | + UNIONFS_SMUTEX_CHILD, /* when locking on behalf of dentry */ | |
9782 | +}; | |
9783 | +static inline void unionfs_read_lock(struct super_block *sb, int subclass) | |
9784 | +{ | |
9785 | + if (UNIONFS_SB(sb)->write_lock_owner && | |
9786 | + UNIONFS_SB(sb)->write_lock_owner == current->pid) | |
9787 | + return; | |
9788 | + down_read_nested(&UNIONFS_SB(sb)->rwsem, subclass); | |
9789 | +} | |
9790 | +static inline void unionfs_read_unlock(struct super_block *sb) | |
9791 | +{ | |
9792 | + if (UNIONFS_SB(sb)->write_lock_owner && | |
9793 | + UNIONFS_SB(sb)->write_lock_owner == current->pid) | |
9794 | + return; | |
9795 | + up_read(&UNIONFS_SB(sb)->rwsem); | |
9796 | +} | |
9797 | +static inline void unionfs_write_lock(struct super_block *sb) | |
9798 | +{ | |
9799 | + down_write(&UNIONFS_SB(sb)->rwsem); | |
9800 | + UNIONFS_SB(sb)->write_lock_owner = current->pid; | |
9801 | +} | |
9802 | +static inline void unionfs_write_unlock(struct super_block *sb) | |
9803 | +{ | |
9804 | + up_write(&UNIONFS_SB(sb)->rwsem); | |
9805 | + UNIONFS_SB(sb)->write_lock_owner = 0; | |
9806 | +} | |
9807 | + | |
9808 | +static inline void unionfs_double_lock_dentry(struct dentry *d1, | |
9809 | + struct dentry *d2) | |
9810 | +{ | |
9811 | + BUG_ON(d1 == d2); | |
9812 | + if (d1 < d2) { | |
9813 | + unionfs_lock_dentry(d1, UNIONFS_DMUTEX_PARENT); | |
9814 | + unionfs_lock_dentry(d2, UNIONFS_DMUTEX_CHILD); | |
9815 | + } else { | |
9816 | + unionfs_lock_dentry(d2, UNIONFS_DMUTEX_PARENT); | |
9817 | + unionfs_lock_dentry(d1, UNIONFS_DMUTEX_CHILD); | |
9818 | + } | |
9819 | +} | |
9820 | + | |
9821 | +static inline void unionfs_double_unlock_dentry(struct dentry *d1, | |
9822 | + struct dentry *d2) | |
9823 | +{ | |
9824 | + BUG_ON(d1 == d2); | |
9825 | + if (d1 < d2) { /* unlock in reverse order than double_lock_dentry */ | |
9826 | + unionfs_unlock_dentry(d1); | |
9827 | + unionfs_unlock_dentry(d2); | |
9828 | + } else { | |
9829 | + unionfs_unlock_dentry(d2); | |
9830 | + unionfs_unlock_dentry(d1); | |
9831 | + } | |
9832 | +} | |
9833 | + | |
9834 | +static inline void unionfs_double_lock_parents(struct dentry *p1, | |
9835 | + struct dentry *p2) | |
9836 | +{ | |
9837 | + if (p1 == p2) { | |
9838 | + unionfs_lock_dentry(p1, UNIONFS_DMUTEX_REVAL_PARENT); | |
9839 | + return; | |
9840 | + } | |
9841 | + if (p1 < p2) { | |
9842 | + unionfs_lock_dentry(p1, UNIONFS_DMUTEX_REVAL_PARENT); | |
9843 | + unionfs_lock_dentry(p2, UNIONFS_DMUTEX_REVAL_CHILD); | |
9844 | + } else { | |
9845 | + unionfs_lock_dentry(p2, UNIONFS_DMUTEX_REVAL_PARENT); | |
9846 | + unionfs_lock_dentry(p1, UNIONFS_DMUTEX_REVAL_CHILD); | |
9847 | + } | |
9848 | +} | |
9849 | + | |
9850 | +static inline void unionfs_double_unlock_parents(struct dentry *p1, | |
9851 | + struct dentry *p2) | |
9852 | +{ | |
9853 | + if (p1 == p2) { | |
9854 | + unionfs_unlock_dentry(p1); | |
9855 | + return; | |
9856 | + } | |
9857 | + if (p1 < p2) { /* unlock in reverse order of double_lock_parents */ | |
9858 | + unionfs_unlock_dentry(p1); | |
9859 | + unionfs_unlock_dentry(p2); | |
9860 | + } else { | |
9861 | + unionfs_unlock_dentry(p2); | |
9862 | + unionfs_unlock_dentry(p1); | |
9863 | + } | |
9864 | +} | |
9865 | + | |
9866 | +extern int new_dentry_private_data(struct dentry *dentry, int subclass); | |
9867 | +extern int realloc_dentry_private_data(struct dentry *dentry); | |
9868 | +extern void free_dentry_private_data(struct dentry *dentry); | |
9869 | +extern void update_bstart(struct dentry *dentry); | |
9870 | +extern int init_lower_nd(struct nameidata *nd, unsigned int flags); | |
9871 | +extern void release_lower_nd(struct nameidata *nd, int err); | |
9872 | + | |
9873 | +/* | |
9874 | + * EXTERNALS: | |
9875 | + */ | |
9876 | + | |
9877 | +/* replicates the directory structure up to given dentry in given branch */ | |
9878 | +extern struct dentry *create_parents(struct inode *dir, struct dentry *dentry, | |
9879 | + const char *name, int bindex); | |
9880 | + | |
9881 | +/* partial lookup */ | |
9882 | +extern int unionfs_partial_lookup(struct dentry *dentry, | |
9883 | + struct dentry *parent); | |
9884 | +extern struct dentry *unionfs_lookup_full(struct dentry *dentry, | |
9885 | + struct dentry *parent, | |
9886 | + int lookupmode); | |
9887 | + | |
9888 | +/* copies a file from dbstart to newbindex branch */ | |
9889 | +extern int copyup_file(struct inode *dir, struct file *file, int bstart, | |
9890 | + int newbindex, loff_t size); | |
9891 | +extern int copyup_named_file(struct inode *dir, struct file *file, | |
9892 | + char *name, int bstart, int new_bindex, | |
9893 | + loff_t len); | |
9894 | +/* copies a dentry from dbstart to newbindex branch */ | |
9895 | +extern int copyup_dentry(struct inode *dir, struct dentry *dentry, | |
9896 | + int bstart, int new_bindex, const char *name, | |
9897 | + int namelen, struct file **copyup_file, loff_t len); | |
9898 | +/* helper functions for post-copyup actions */ | |
9899 | +extern void unionfs_postcopyup_setmnt(struct dentry *dentry); | |
9900 | +extern void unionfs_postcopyup_release(struct dentry *dentry); | |
9901 | + | |
9902 | +/* Is this directory empty: 0 if it is empty, -ENOTEMPTY if not. */ | |
9903 | +extern int check_empty(struct dentry *dentry, struct dentry *parent, | |
9904 | + struct unionfs_dir_state **namelist); | |
9905 | +/* whiteout and opaque directory helpers */ | |
9906 | +extern char *alloc_whname(const char *name, int len); | |
9907 | +extern bool is_whiteout_name(char **namep, int *namelenp); | |
9908 | +extern bool is_validname(const char *name); | |
9909 | +extern struct dentry *lookup_whiteout(const char *name, | |
9910 | + struct dentry *lower_parent); | |
9911 | +extern struct dentry *find_first_whiteout(struct dentry *dentry); | |
9912 | +extern int unlink_whiteout(struct dentry *wh_dentry); | |
9913 | +extern int check_unlink_whiteout(struct dentry *dentry, | |
9914 | + struct dentry *lower_dentry, int bindex); | |
9915 | +extern int create_whiteout(struct dentry *dentry, int start); | |
9916 | +extern int delete_whiteouts(struct dentry *dentry, int bindex, | |
9917 | + struct unionfs_dir_state *namelist); | |
9918 | +extern int is_opaque_dir(struct dentry *dentry, int bindex); | |
9919 | +extern int make_dir_opaque(struct dentry *dir, int bindex); | |
9920 | +extern void unionfs_set_max_namelen(long *namelen); | |
9921 | + | |
9922 | +extern void unionfs_reinterpose(struct dentry *this_dentry); | |
9923 | +extern struct super_block *unionfs_duplicate_super(struct super_block *sb); | |
9924 | + | |
9925 | +/* Locking functions. */ | |
9926 | +extern int unionfs_setlk(struct file *file, int cmd, struct file_lock *fl); | |
9927 | +extern int unionfs_getlk(struct file *file, struct file_lock *fl); | |
9928 | + | |
9929 | +/* Common file operations. */ | |
9930 | +extern int unionfs_file_revalidate(struct file *file, struct dentry *parent, | |
9931 | + bool willwrite); | |
9932 | +extern int unionfs_open(struct inode *inode, struct file *file); | |
9933 | +extern int unionfs_file_release(struct inode *inode, struct file *file); | |
9934 | +extern int unionfs_flush(struct file *file, fl_owner_t id); | |
9935 | +extern long unionfs_ioctl(struct file *file, unsigned int cmd, | |
9936 | + unsigned long arg); | |
6b53c3da AM |
9937 | +extern int unionfs_fsync(struct file *file, loff_t start, loff_t end, |
9938 | + int datasync); | |
2380c486 JR |
9939 | +extern int unionfs_fasync(int fd, struct file *file, int flag); |
9940 | + | |
9941 | +/* Inode operations */ | |
9942 | +extern struct inode *unionfs_iget(struct super_block *sb, unsigned long ino); | |
9943 | +extern int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry, | |
9944 | + struct inode *new_dir, struct dentry *new_dentry); | |
9945 | +extern int unionfs_unlink(struct inode *dir, struct dentry *dentry); | |
9946 | +extern int unionfs_rmdir(struct inode *dir, struct dentry *dentry); | |
9947 | + | |
9948 | +extern bool __unionfs_d_revalidate(struct dentry *dentry, | |
9949 | + struct dentry *parent, bool willwrite); | |
9950 | +extern bool is_negative_lower(const struct dentry *dentry); | |
9951 | +extern bool is_newer_lower(const struct dentry *dentry); | |
9952 | +extern void purge_sb_data(struct super_block *sb); | |
9953 | + | |
9954 | +/* The values for unionfs_interpose's flag. */ | |
9955 | +#define INTERPOSE_DEFAULT 0 | |
9956 | +#define INTERPOSE_LOOKUP 1 | |
9957 | +#define INTERPOSE_REVAL 2 | |
9958 | +#define INTERPOSE_REVAL_NEG 3 | |
9959 | +#define INTERPOSE_PARTIAL 4 | |
9960 | + | |
9961 | +extern struct dentry *unionfs_interpose(struct dentry *this_dentry, | |
9962 | + struct super_block *sb, int flag); | |
9963 | + | |
9964 | +#ifdef CONFIG_UNION_FS_XATTR | |
9965 | +/* Extended attribute functions. */ | |
9966 | +extern void *unionfs_xattr_alloc(size_t size, size_t limit); | |
9967 | +static inline void unionfs_xattr_kfree(const void *p) | |
9968 | +{ | |
9969 | + kfree(p); | |
9970 | +} | |
9971 | +extern ssize_t unionfs_getxattr(struct dentry *dentry, const char *name, | |
9972 | + void *value, size_t size); | |
9973 | +extern int unionfs_removexattr(struct dentry *dentry, const char *name); | |
9974 | +extern ssize_t unionfs_listxattr(struct dentry *dentry, char *list, | |
9975 | + size_t size); | |
9976 | +extern int unionfs_setxattr(struct dentry *dentry, const char *name, | |
9977 | + const void *value, size_t size, int flags); | |
9978 | +#endif /* CONFIG_UNION_FS_XATTR */ | |
9979 | + | |
9980 | +/* The root directory is unhashed, but isn't deleted. */ | |
9981 | +static inline int d_deleted(struct dentry *d) | |
9982 | +{ | |
9983 | + return d_unhashed(d) && (d != d->d_sb->s_root); | |
9984 | +} | |
9985 | + | |
9986 | +/* unionfs_permission, check if we should bypass error to facilitate copyup */ | |
9987 | +#define IS_COPYUP_ERR(err) ((err) == -EROFS) | |
9988 | + | |
9989 | +/* unionfs_open, check if we need to copyup the file */ | |
9990 | +#define OPEN_WRITE_FLAGS (O_WRONLY | O_RDWR | O_APPEND) | |
9991 | +#define IS_WRITE_FLAG(flag) ((flag) & OPEN_WRITE_FLAGS) | |
9992 | + | |
9993 | +static inline int branchperms(const struct super_block *sb, int index) | |
9994 | +{ | |
9995 | + BUG_ON(index < 0); | |
9996 | + return UNIONFS_SB(sb)->data[index].branchperms; | |
9997 | +} | |
9998 | + | |
9999 | +static inline int set_branchperms(struct super_block *sb, int index, int perms) | |
10000 | +{ | |
10001 | + BUG_ON(index < 0); | |
10002 | + UNIONFS_SB(sb)->data[index].branchperms = perms; | |
10003 | + return perms; | |
10004 | +} | |
10005 | + | |
4ae1df7a JR |
10006 | +/* check if readonly lower inode, but possibly unlinked (no inode->i_sb) */ |
10007 | +static inline int __is_rdonly(const struct inode *inode) | |
10008 | +{ | |
10009 | + /* if unlinked, can't be readonly (?) */ | |
10010 | + if (!inode->i_sb) | |
10011 | + return 0; | |
10012 | + return IS_RDONLY(inode); | |
10013 | + | |
10014 | +} | |
2380c486 JR |
10015 | +/* Is this file on a read-only branch? */ |
10016 | +static inline int is_robranch_super(const struct super_block *sb, int index) | |
10017 | +{ | |
10018 | + int ret; | |
10019 | + | |
10020 | + ret = (!(branchperms(sb, index) & MAY_WRITE)) ? -EROFS : 0; | |
10021 | + return ret; | |
10022 | +} | |
10023 | + | |
10024 | +/* Is this file on a read-only branch? */ | |
10025 | +static inline int is_robranch_idx(const struct dentry *dentry, int index) | |
10026 | +{ | |
10027 | + struct super_block *lower_sb; | |
10028 | + | |
10029 | + BUG_ON(index < 0); | |
10030 | + | |
10031 | + if (!(branchperms(dentry->d_sb, index) & MAY_WRITE)) | |
10032 | + return -EROFS; | |
10033 | + | |
10034 | + lower_sb = unionfs_lower_super_idx(dentry->d_sb, index); | |
10035 | + BUG_ON(lower_sb == NULL); | |
10036 | + /* | |
10037 | + * test sb flags directly, not IS_RDONLY(lower_inode) because the | |
10038 | + * lower_dentry could be a negative. | |
10039 | + */ | |
10040 | + if (lower_sb->s_flags & MS_RDONLY) | |
10041 | + return -EROFS; | |
10042 | + | |
10043 | + return 0; | |
10044 | +} | |
10045 | + | |
10046 | +static inline int is_robranch(const struct dentry *dentry) | |
10047 | +{ | |
10048 | + int index; | |
10049 | + | |
10050 | + index = UNIONFS_D(dentry)->bstart; | |
10051 | + BUG_ON(index < 0); | |
10052 | + | |
10053 | + return is_robranch_idx(dentry, index); | |
10054 | +} | |
10055 | + | |
10056 | +/* | |
10057 | + * EXTERNALS: | |
10058 | + */ | |
63b09289 | 10059 | +extern int check_branch(const struct path *path); |
2380c486 JR |
10060 | +extern int parse_branch_mode(const char *name, int *perms); |
10061 | + | |
10062 | +/* locking helpers */ | |
10063 | +static inline struct dentry *lock_parent(struct dentry *dentry) | |
10064 | +{ | |
10065 | + struct dentry *dir = dget_parent(dentry); | |
10066 | + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); | |
10067 | + return dir; | |
10068 | +} | |
10069 | +static inline struct dentry *lock_parent_wh(struct dentry *dentry) | |
10070 | +{ | |
10071 | + struct dentry *dir = dget_parent(dentry); | |
10072 | + | |
10073 | + mutex_lock_nested(&dir->d_inode->i_mutex, UNIONFS_DMUTEX_WHITEOUT); | |
10074 | + return dir; | |
10075 | +} | |
10076 | + | |
10077 | +static inline void unlock_dir(struct dentry *dir) | |
10078 | +{ | |
10079 | + mutex_unlock(&dir->d_inode->i_mutex); | |
10080 | + dput(dir); | |
10081 | +} | |
10082 | + | |
4ae1df7a JR |
10083 | +/* lock base inode mutex before calling lookup_one_len */ |
10084 | +static inline struct dentry *lookup_lck_len(const char *name, | |
10085 | + struct dentry *base, int len) | |
10086 | +{ | |
10087 | + struct dentry *d; | |
63b09289 JR |
10088 | + struct nameidata lower_nd; |
10089 | + int err; | |
10090 | + | |
10091 | + err = init_lower_nd(&lower_nd, LOOKUP_OPEN); | |
10092 | + if (unlikely(err < 0)) { | |
10093 | + d = ERR_PTR(err); | |
10094 | + goto out; | |
10095 | + } | |
4ae1df7a | 10096 | + mutex_lock(&base->d_inode->i_mutex); |
63b09289 JR |
10097 | + d = lookup_one_len_nd(name, base, len, &lower_nd); |
10098 | + release_lower_nd(&lower_nd, err); | |
4ae1df7a | 10099 | + mutex_unlock(&base->d_inode->i_mutex); |
63b09289 | 10100 | +out: |
4ae1df7a JR |
10101 | + return d; |
10102 | +} | |
10103 | + | |
2380c486 JR |
10104 | +static inline struct vfsmount *unionfs_mntget(struct dentry *dentry, |
10105 | + int bindex) | |
10106 | +{ | |
10107 | + struct vfsmount *mnt; | |
10108 | + | |
10109 | + BUG_ON(!dentry || bindex < 0); | |
10110 | + | |
10111 | + mnt = mntget(unionfs_lower_mnt_idx(dentry, bindex)); | |
10112 | +#ifdef CONFIG_UNION_FS_DEBUG | |
10113 | + if (!mnt) | |
10114 | + pr_debug("unionfs: mntget: mnt=%p bindex=%d\n", | |
10115 | + mnt, bindex); | |
10116 | +#endif /* CONFIG_UNION_FS_DEBUG */ | |
10117 | + | |
10118 | + return mnt; | |
10119 | +} | |
10120 | + | |
10121 | +static inline void unionfs_mntput(struct dentry *dentry, int bindex) | |
10122 | +{ | |
10123 | + struct vfsmount *mnt; | |
10124 | + | |
10125 | + if (!dentry && bindex < 0) | |
10126 | + return; | |
10127 | + BUG_ON(!dentry || bindex < 0); | |
10128 | + | |
10129 | + mnt = unionfs_lower_mnt_idx(dentry, bindex); | |
10130 | +#ifdef CONFIG_UNION_FS_DEBUG | |
10131 | + /* | |
10132 | + * Directories can have NULL lower objects in between start/end, but | |
10133 | + * NOT if at the start/end range. We cannot verify that this dentry | |
10134 | + * is a type=DIR, because it may already be a negative dentry. But | |
10135 | + * if dbstart is greater than dbend, we know that this couldn't have | |
10136 | + * been a regular file: it had to have been a directory. | |
10137 | + */ | |
10138 | + if (!mnt && !(bindex > dbstart(dentry) && bindex < dbend(dentry))) | |
10139 | + pr_debug("unionfs: mntput: mnt=%p bindex=%d\n", mnt, bindex); | |
10140 | +#endif /* CONFIG_UNION_FS_DEBUG */ | |
10141 | + mntput(mnt); | |
10142 | +} | |
10143 | + | |
10144 | +#ifdef CONFIG_UNION_FS_DEBUG | |
10145 | + | |
10146 | +/* useful for tracking code reachability */ | |
10147 | +#define UDBG pr_debug("DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) | |
10148 | + | |
10149 | +#define unionfs_check_inode(i) __unionfs_check_inode((i), \ | |
10150 | + __FILE__, __func__, __LINE__) | |
10151 | +#define unionfs_check_dentry(d) __unionfs_check_dentry((d), \ | |
10152 | + __FILE__, __func__, __LINE__) | |
10153 | +#define unionfs_check_file(f) __unionfs_check_file((f), \ | |
10154 | + __FILE__, __func__, __LINE__) | |
10155 | +#define unionfs_check_nd(n) __unionfs_check_nd((n), \ | |
10156 | + __FILE__, __func__, __LINE__) | |
10157 | +#define show_branch_counts(sb) __show_branch_counts((sb), \ | |
10158 | + __FILE__, __func__, __LINE__) | |
10159 | +#define show_inode_times(i) __show_inode_times((i), \ | |
10160 | + __FILE__, __func__, __LINE__) | |
10161 | +#define show_dinode_times(d) __show_dinode_times((d), \ | |
10162 | + __FILE__, __func__, __LINE__) | |
10163 | +#define show_inode_counts(i) __show_inode_counts((i), \ | |
10164 | + __FILE__, __func__, __LINE__) | |
10165 | + | |
10166 | +extern void __unionfs_check_inode(const struct inode *inode, const char *fname, | |
10167 | + const char *fxn, int line); | |
10168 | +extern void __unionfs_check_dentry(const struct dentry *dentry, | |
10169 | + const char *fname, const char *fxn, | |
10170 | + int line); | |
10171 | +extern void __unionfs_check_file(const struct file *file, | |
10172 | + const char *fname, const char *fxn, int line); | |
10173 | +extern void __unionfs_check_nd(const struct nameidata *nd, | |
10174 | + const char *fname, const char *fxn, int line); | |
10175 | +extern void __show_branch_counts(const struct super_block *sb, | |
10176 | + const char *file, const char *fxn, int line); | |
10177 | +extern void __show_inode_times(const struct inode *inode, | |
10178 | + const char *file, const char *fxn, int line); | |
10179 | +extern void __show_dinode_times(const struct dentry *dentry, | |
10180 | + const char *file, const char *fxn, int line); | |
10181 | +extern void __show_inode_counts(const struct inode *inode, | |
10182 | + const char *file, const char *fxn, int line); | |
10183 | + | |
10184 | +#else /* not CONFIG_UNION_FS_DEBUG */ | |
10185 | + | |
10186 | +/* we leave useful hooks for these check functions throughout the code */ | |
10187 | +#define unionfs_check_inode(i) do { } while (0) | |
10188 | +#define unionfs_check_dentry(d) do { } while (0) | |
10189 | +#define unionfs_check_file(f) do { } while (0) | |
10190 | +#define unionfs_check_nd(n) do { } while (0) | |
10191 | +#define show_branch_counts(sb) do { } while (0) | |
10192 | +#define show_inode_times(i) do { } while (0) | |
10193 | +#define show_dinode_times(d) do { } while (0) | |
10194 | +#define show_inode_counts(i) do { } while (0) | |
6b53c3da | 10195 | +#define UDBG do { } while (0) |
2380c486 JR |
10196 | + |
10197 | +#endif /* not CONFIG_UNION_FS_DEBUG */ | |
10198 | + | |
10199 | +#endif /* not _UNION_H_ */ | |
0c5527e5 AM |
10200 | diff --git a/fs/unionfs/unlink.c b/fs/unionfs/unlink.c |
10201 | new file mode 100644 | |
f6c5ef8b | 10202 | index 0000000..25943a5 |
0c5527e5 AM |
10203 | --- /dev/null |
10204 | +++ b/fs/unionfs/unlink.c | |
7670a7fc | 10205 | @@ -0,0 +1,278 @@ |
2380c486 | 10206 | +/* |
63b09289 | 10207 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
10208 | + * Copyright (c) 2003-2006 Charles P. Wright |
10209 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
10210 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
10211 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
10212 | + * Copyright (c) 2004-2006 David P. Quigley | |
10213 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
10214 | + * Copyright (c) 2003 Puja Gupta | |
10215 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
10216 | + * Copyright (c) 2003-2011 Stony Brook University |
10217 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
10218 | + * |
10219 | + * This program is free software; you can redistribute it and/or modify | |
10220 | + * it under the terms of the GNU General Public License version 2 as | |
10221 | + * published by the Free Software Foundation. | |
10222 | + */ | |
10223 | + | |
10224 | +#include "union.h" | |
10225 | + | |
10226 | +/* | |
10227 | + * Helper function for Unionfs's unlink operation. | |
10228 | + * | |
10229 | + * The main goal of this function is to optimize the unlinking of non-dir | |
10230 | + * objects in unionfs by deleting all possible lower inode objects from the | |
10231 | + * underlying branches having same dentry name as the non-dir dentry on | |
10232 | + * which this unlink operation is called. This way we delete as many lower | |
10233 | + * inodes as possible, and save space. Whiteouts need to be created in | |
10234 | + * branch0 only if unlinking fails on any of the lower branch other than | |
10235 | + * branch0, or if a lower branch is marked read-only. | |
10236 | + * | |
10237 | + * Also, while unlinking a file, if we encounter any dir type entry in any | |
10238 | + * intermediate branch, then we remove the directory by calling vfs_rmdir. | |
10239 | + * The following special cases are also handled: | |
10240 | + | |
10241 | + * (1) If an error occurs in branch0 during vfs_unlink, then we return | |
10242 | + * appropriate error. | |
10243 | + * | |
10244 | + * (2) If we get an error during unlink in any of other lower branch other | |
10245 | + * than branch0, then we create a whiteout in branch0. | |
10246 | + * | |
10247 | + * (3) If a whiteout already exists in any intermediate branch, we delete | |
10248 | + * all possible inodes only up to that branch (this is an "opaqueness" | |
10249 | + * as as per Documentation/filesystems/unionfs/concepts.txt). | |
10250 | + * | |
10251 | + */ | |
10252 | +static int unionfs_unlink_whiteout(struct inode *dir, struct dentry *dentry, | |
10253 | + struct dentry *parent) | |
10254 | +{ | |
10255 | + struct dentry *lower_dentry; | |
10256 | + struct dentry *lower_dir_dentry; | |
10257 | + int bindex; | |
10258 | + int err = 0; | |
10259 | + | |
10260 | + err = unionfs_partial_lookup(dentry, parent); | |
10261 | + if (err) | |
10262 | + goto out; | |
10263 | + | |
10264 | + /* trying to unlink all possible valid instances */ | |
10265 | + for (bindex = dbstart(dentry); bindex <= dbend(dentry); bindex++) { | |
10266 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
10267 | + if (!lower_dentry || !lower_dentry->d_inode) | |
10268 | + continue; | |
10269 | + | |
10270 | + lower_dir_dentry = lock_parent(lower_dentry); | |
10271 | + | |
10272 | + /* avoid destroying the lower inode if the object is in use */ | |
10273 | + dget(lower_dentry); | |
10274 | + err = is_robranch_super(dentry->d_sb, bindex); | |
10275 | + if (!err) { | |
10276 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
10277 | + lockdep_off(); | |
10278 | + if (!S_ISDIR(lower_dentry->d_inode->i_mode)) | |
10279 | + err = vfs_unlink(lower_dir_dentry->d_inode, | |
10280 | + lower_dentry); | |
10281 | + else | |
10282 | + err = vfs_rmdir(lower_dir_dentry->d_inode, | |
10283 | + lower_dentry); | |
10284 | + lockdep_on(); | |
10285 | + } | |
10286 | + | |
10287 | + /* if lower object deletion succeeds, update inode's times */ | |
10288 | + if (!err) | |
10289 | + unionfs_copy_attr_times(dentry->d_inode); | |
10290 | + dput(lower_dentry); | |
10291 | + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); | |
10292 | + unlock_dir(lower_dir_dentry); | |
10293 | + | |
10294 | + if (err) | |
10295 | + break; | |
10296 | + } | |
10297 | + | |
10298 | + /* | |
10299 | + * Create the whiteout in branch 0 (highest priority) only if (a) | |
10300 | + * there was an error in any intermediate branch other than branch 0 | |
10301 | + * due to failure of vfs_unlink/vfs_rmdir or (b) a branch marked or | |
10302 | + * mounted read-only. | |
10303 | + */ | |
10304 | + if (err) { | |
10305 | + if ((bindex == 0) || | |
10306 | + ((bindex == dbstart(dentry)) && | |
10307 | + (!IS_COPYUP_ERR(err)))) | |
10308 | + goto out; | |
10309 | + else { | |
10310 | + if (!IS_COPYUP_ERR(err)) | |
10311 | + pr_debug("unionfs: lower object deletion " | |
10312 | + "failed in branch:%d\n", bindex); | |
10313 | + err = create_whiteout(dentry, sbstart(dentry->d_sb)); | |
10314 | + } | |
10315 | + } | |
10316 | + | |
10317 | +out: | |
10318 | + if (!err) | |
10319 | + inode_dec_link_count(dentry->d_inode); | |
10320 | + | |
10321 | + /* We don't want to leave negative leftover dentries for revalidate. */ | |
10322 | + if (!err && (dbopaque(dentry) != -1)) | |
10323 | + update_bstart(dentry); | |
10324 | + | |
10325 | + return err; | |
10326 | +} | |
10327 | + | |
10328 | +int unionfs_unlink(struct inode *dir, struct dentry *dentry) | |
10329 | +{ | |
10330 | + int err = 0; | |
10331 | + struct inode *inode = dentry->d_inode; | |
10332 | + struct dentry *parent; | |
10333 | + int valid; | |
10334 | + | |
10335 | + BUG_ON(S_ISDIR(inode->i_mode)); | |
10336 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
10337 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
10338 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
10339 | + | |
10340 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
10341 | + if (unlikely(!valid)) { | |
10342 | + err = -ESTALE; | |
10343 | + goto out; | |
10344 | + } | |
10345 | + unionfs_check_dentry(dentry); | |
10346 | + | |
10347 | + err = unionfs_unlink_whiteout(dir, dentry, parent); | |
10348 | + /* call d_drop so the system "forgets" about us */ | |
10349 | + if (!err) { | |
10350 | + unionfs_postcopyup_release(dentry); | |
10351 | + unionfs_postcopyup_setmnt(parent); | |
10352 | + if (inode->i_nlink == 0) /* drop lower inodes */ | |
10353 | + iput_lowers_all(inode, false); | |
10354 | + d_drop(dentry); | |
10355 | + /* | |
10356 | + * if unlink/whiteout succeeded, parent dir mtime has | |
10357 | + * changed | |
10358 | + */ | |
10359 | + unionfs_copy_attr_times(dir); | |
10360 | + } | |
10361 | + | |
10362 | +out: | |
10363 | + if (!err) { | |
10364 | + unionfs_check_dentry(dentry); | |
10365 | + unionfs_check_inode(dir); | |
10366 | + } | |
10367 | + unionfs_unlock_dentry(dentry); | |
10368 | + unionfs_unlock_parent(dentry, parent); | |
10369 | + unionfs_read_unlock(dentry->d_sb); | |
10370 | + return err; | |
10371 | +} | |
10372 | + | |
10373 | +static int unionfs_rmdir_first(struct inode *dir, struct dentry *dentry, | |
10374 | + struct unionfs_dir_state *namelist) | |
10375 | +{ | |
10376 | + int err; | |
10377 | + struct dentry *lower_dentry; | |
10378 | + struct dentry *lower_dir_dentry = NULL; | |
10379 | + | |
10380 | + /* Here we need to remove whiteout entries. */ | |
10381 | + err = delete_whiteouts(dentry, dbstart(dentry), namelist); | |
10382 | + if (err) | |
10383 | + goto out; | |
10384 | + | |
10385 | + lower_dentry = unionfs_lower_dentry(dentry); | |
10386 | + | |
10387 | + lower_dir_dentry = lock_parent(lower_dentry); | |
10388 | + | |
10389 | + /* avoid destroying the lower inode if the file is in use */ | |
10390 | + dget(lower_dentry); | |
10391 | + err = is_robranch(dentry); | |
7670a7fc | 10392 | + if (!err) |
2380c486 | 10393 | + err = vfs_rmdir(lower_dir_dentry->d_inode, lower_dentry); |
2380c486 JR |
10394 | + dput(lower_dentry); |
10395 | + | |
10396 | + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); | |
10397 | + /* propagate number of hard-links */ | |
f4ea99f3 | 10398 | + set_nlink(dentry->d_inode, unionfs_get_nlinks(dentry->d_inode)); |
2380c486 JR |
10399 | + |
10400 | +out: | |
10401 | + if (lower_dir_dentry) | |
10402 | + unlock_dir(lower_dir_dentry); | |
10403 | + return err; | |
10404 | +} | |
10405 | + | |
10406 | +int unionfs_rmdir(struct inode *dir, struct dentry *dentry) | |
10407 | +{ | |
10408 | + int err = 0; | |
10409 | + struct unionfs_dir_state *namelist = NULL; | |
10410 | + struct dentry *parent; | |
10411 | + int dstart, dend; | |
10412 | + bool valid; | |
10413 | + | |
10414 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
10415 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
10416 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
10417 | + | |
10418 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
10419 | + if (unlikely(!valid)) { | |
10420 | + err = -ESTALE; | |
10421 | + goto out; | |
10422 | + } | |
10423 | + unionfs_check_dentry(dentry); | |
10424 | + | |
10425 | + /* check if this unionfs directory is empty or not */ | |
10426 | + err = check_empty(dentry, parent, &namelist); | |
10427 | + if (err) | |
10428 | + goto out; | |
10429 | + | |
10430 | + err = unionfs_rmdir_first(dir, dentry, namelist); | |
10431 | + dstart = dbstart(dentry); | |
10432 | + dend = dbend(dentry); | |
10433 | + /* | |
10434 | + * We create a whiteout for the directory if there was an error to | |
10435 | + * rmdir the first directory entry in the union. Otherwise, we | |
10436 | + * create a whiteout only if there is no chance that a lower | |
10437 | + * priority branch might also have the same named directory. IOW, | |
10438 | + * if there is not another same-named directory at a lower priority | |
10439 | + * branch, then we don't need to create a whiteout for it. | |
10440 | + */ | |
10441 | + if (!err) { | |
10442 | + if (dstart < dend) | |
10443 | + err = create_whiteout(dentry, dstart); | |
10444 | + } else { | |
10445 | + int new_err; | |
10446 | + | |
10447 | + if (dstart == 0) | |
10448 | + goto out; | |
10449 | + | |
10450 | + /* exit if the error returned was NOT -EROFS */ | |
10451 | + if (!IS_COPYUP_ERR(err)) | |
10452 | + goto out; | |
10453 | + | |
10454 | + new_err = create_whiteout(dentry, dstart - 1); | |
10455 | + if (new_err != -EEXIST) | |
10456 | + err = new_err; | |
10457 | + } | |
10458 | + | |
10459 | +out: | |
10460 | + /* | |
10461 | + * Drop references to lower dentry/inode so storage space for them | |
10462 | + * can be reclaimed. Then, call d_drop so the system "forgets" | |
10463 | + * about us. | |
10464 | + */ | |
10465 | + if (!err) { | |
10466 | + iput_lowers_all(dentry->d_inode, false); | |
10467 | + dput(unionfs_lower_dentry_idx(dentry, dstart)); | |
10468 | + unionfs_set_lower_dentry_idx(dentry, dstart, NULL); | |
10469 | + d_drop(dentry); | |
10470 | + /* update our lower vfsmnts, in case a copyup took place */ | |
10471 | + unionfs_postcopyup_setmnt(dentry); | |
10472 | + unionfs_check_dentry(dentry); | |
10473 | + unionfs_check_inode(dir); | |
10474 | + } | |
10475 | + | |
10476 | + if (namelist) | |
10477 | + free_rdstate(namelist); | |
10478 | + | |
10479 | + unionfs_unlock_dentry(dentry); | |
10480 | + unionfs_unlock_parent(dentry, parent); | |
10481 | + unionfs_read_unlock(dentry->d_sb); | |
10482 | + return err; | |
10483 | +} | |
0c5527e5 AM |
10484 | diff --git a/fs/unionfs/whiteout.c b/fs/unionfs/whiteout.c |
10485 | new file mode 100644 | |
63b09289 | 10486 | index 0000000..582cef2 |
0c5527e5 AM |
10487 | --- /dev/null |
10488 | +++ b/fs/unionfs/whiteout.c | |
63b09289 | 10489 | @@ -0,0 +1,601 @@ |
2380c486 | 10490 | +/* |
63b09289 | 10491 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
10492 | + * Copyright (c) 2003-2006 Charles P. Wright |
10493 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
10494 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
10495 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
10496 | + * Copyright (c) 2004-2006 David P. Quigley | |
10497 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
10498 | + * Copyright (c) 2003 Puja Gupta | |
10499 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
10500 | + * Copyright (c) 2003-2011 Stony Brook University |
10501 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
10502 | + * |
10503 | + * This program is free software; you can redistribute it and/or modify | |
10504 | + * it under the terms of the GNU General Public License version 2 as | |
10505 | + * published by the Free Software Foundation. | |
10506 | + */ | |
10507 | + | |
10508 | +#include "union.h" | |
10509 | + | |
10510 | +/* | |
10511 | + * whiteout and opaque directory helpers | |
10512 | + */ | |
10513 | + | |
10514 | +/* What do we use for whiteouts. */ | |
10515 | +#define UNIONFS_WHPFX ".wh." | |
10516 | +#define UNIONFS_WHLEN 4 | |
10517 | +/* | |
10518 | + * If a directory contains this file, then it is opaque. We start with the | |
10519 | + * .wh. flag so that it is blocked by lookup. | |
10520 | + */ | |
10521 | +#define UNIONFS_DIR_OPAQUE_NAME "__dir_opaque" | |
10522 | +#define UNIONFS_DIR_OPAQUE UNIONFS_WHPFX UNIONFS_DIR_OPAQUE_NAME | |
10523 | + | |
10524 | +/* construct whiteout filename */ | |
10525 | +char *alloc_whname(const char *name, int len) | |
10526 | +{ | |
10527 | + char *buf; | |
10528 | + | |
10529 | + buf = kmalloc(len + UNIONFS_WHLEN + 1, GFP_KERNEL); | |
10530 | + if (unlikely(!buf)) | |
10531 | + return ERR_PTR(-ENOMEM); | |
10532 | + | |
10533 | + strcpy(buf, UNIONFS_WHPFX); | |
10534 | + strlcat(buf, name, len + UNIONFS_WHLEN + 1); | |
10535 | + | |
10536 | + return buf; | |
10537 | +} | |
10538 | + | |
10539 | +/* | |
10540 | + * XXX: this can be inline or CPP macro, but is here to keep all whiteout | |
10541 | + * code in one place. | |
10542 | + */ | |
10543 | +void unionfs_set_max_namelen(long *namelen) | |
10544 | +{ | |
10545 | + *namelen -= UNIONFS_WHLEN; | |
10546 | +} | |
10547 | + | |
10548 | +/* check if @namep is a whiteout, update @namep and @namelenp accordingly */ | |
10549 | +bool is_whiteout_name(char **namep, int *namelenp) | |
10550 | +{ | |
10551 | + if (*namelenp > UNIONFS_WHLEN && | |
10552 | + !strncmp(*namep, UNIONFS_WHPFX, UNIONFS_WHLEN)) { | |
10553 | + *namep += UNIONFS_WHLEN; | |
10554 | + *namelenp -= UNIONFS_WHLEN; | |
10555 | + return true; | |
10556 | + } | |
10557 | + return false; | |
10558 | +} | |
10559 | + | |
10560 | +/* is the filename valid == !(whiteout for a file or opaque dir marker) */ | |
10561 | +bool is_validname(const char *name) | |
10562 | +{ | |
10563 | + if (!strncmp(name, UNIONFS_WHPFX, UNIONFS_WHLEN)) | |
10564 | + return false; | |
10565 | + if (!strncmp(name, UNIONFS_DIR_OPAQUE_NAME, | |
10566 | + sizeof(UNIONFS_DIR_OPAQUE_NAME) - 1)) | |
10567 | + return false; | |
10568 | + return true; | |
10569 | +} | |
10570 | + | |
10571 | +/* | |
10572 | + * Look for a whiteout @name in @lower_parent directory. If error, return | |
10573 | + * ERR_PTR. Caller must dput() the returned dentry if not an error. | |
10574 | + * | |
10575 | + * XXX: some callers can reuse the whname allocated buffer to avoid repeated | |
10576 | + * free then re-malloc calls. Need to provide a different API for those | |
10577 | + * callers. | |
10578 | + */ | |
10579 | +struct dentry *lookup_whiteout(const char *name, struct dentry *lower_parent) | |
10580 | +{ | |
10581 | + char *whname = NULL; | |
10582 | + int err = 0, namelen; | |
10583 | + struct dentry *wh_dentry = NULL; | |
10584 | + | |
10585 | + namelen = strlen(name); | |
10586 | + whname = alloc_whname(name, namelen); | |
10587 | + if (unlikely(IS_ERR(whname))) { | |
10588 | + err = PTR_ERR(whname); | |
10589 | + goto out; | |
10590 | + } | |
10591 | + | |
10592 | + /* check if whiteout exists in this branch: lookup .wh.foo */ | |
4ae1df7a | 10593 | + wh_dentry = lookup_lck_len(whname, lower_parent, strlen(whname)); |
2380c486 JR |
10594 | + if (IS_ERR(wh_dentry)) { |
10595 | + err = PTR_ERR(wh_dentry); | |
10596 | + goto out; | |
10597 | + } | |
10598 | + | |
10599 | + /* check if negative dentry (ENOENT) */ | |
10600 | + if (!wh_dentry->d_inode) | |
10601 | + goto out; | |
10602 | + | |
10603 | + /* whiteout found: check if valid type */ | |
10604 | + if (!S_ISREG(wh_dentry->d_inode->i_mode)) { | |
10605 | + printk(KERN_ERR "unionfs: invalid whiteout %s entry type %d\n", | |
10606 | + whname, wh_dentry->d_inode->i_mode); | |
10607 | + dput(wh_dentry); | |
10608 | + err = -EIO; | |
10609 | + goto out; | |
10610 | + } | |
10611 | + | |
10612 | +out: | |
10613 | + kfree(whname); | |
10614 | + if (err) | |
10615 | + wh_dentry = ERR_PTR(err); | |
10616 | + return wh_dentry; | |
10617 | +} | |
10618 | + | |
10619 | +/* find and return first whiteout in parent directory, else ENOENT */ | |
10620 | +struct dentry *find_first_whiteout(struct dentry *dentry) | |
10621 | +{ | |
10622 | + int bindex, bstart, bend; | |
10623 | + struct dentry *parent, *lower_parent, *wh_dentry; | |
10624 | + | |
10625 | + parent = dget_parent(dentry); | |
10626 | + | |
10627 | + bstart = dbstart(parent); | |
10628 | + bend = dbend(parent); | |
10629 | + wh_dentry = ERR_PTR(-ENOENT); | |
10630 | + | |
10631 | + for (bindex = bstart; bindex <= bend; bindex++) { | |
10632 | + lower_parent = unionfs_lower_dentry_idx(parent, bindex); | |
10633 | + if (!lower_parent) | |
10634 | + continue; | |
10635 | + wh_dentry = lookup_whiteout(dentry->d_name.name, lower_parent); | |
10636 | + if (IS_ERR(wh_dentry)) | |
10637 | + continue; | |
10638 | + if (wh_dentry->d_inode) | |
10639 | + break; | |
10640 | + dput(wh_dentry); | |
10641 | + wh_dentry = ERR_PTR(-ENOENT); | |
10642 | + } | |
10643 | + | |
10644 | + dput(parent); | |
10645 | + | |
10646 | + return wh_dentry; | |
10647 | +} | |
10648 | + | |
10649 | +/* | |
10650 | + * Unlink a whiteout dentry. Returns 0 or -errno. Caller must hold and | |
10651 | + * release dentry reference. | |
10652 | + */ | |
10653 | +int unlink_whiteout(struct dentry *wh_dentry) | |
10654 | +{ | |
10655 | + int err; | |
10656 | + struct dentry *lower_dir_dentry; | |
10657 | + | |
10658 | + /* dget and lock parent dentry */ | |
10659 | + lower_dir_dentry = lock_parent_wh(wh_dentry); | |
10660 | + | |
10661 | + /* see Documentation/filesystems/unionfs/issues.txt */ | |
10662 | + lockdep_off(); | |
10663 | + err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry); | |
10664 | + lockdep_on(); | |
10665 | + unlock_dir(lower_dir_dentry); | |
10666 | + | |
10667 | + /* | |
10668 | + * Whiteouts are special files and should be deleted no matter what | |
10669 | + * (as if they never existed), in order to allow this create | |
10670 | + * operation to succeed. This is especially important in sticky | |
10671 | + * directories: a whiteout may have been created by one user, but | |
10672 | + * the newly created file may be created by another user. | |
10673 | + * Therefore, in order to maintain Unix semantics, if the vfs_unlink | |
10674 | + * above failed, then we have to try to directly unlink the | |
10675 | + * whiteout. Note: in the ODF version of unionfs, whiteout are | |
10676 | + * handled much more cleanly. | |
10677 | + */ | |
10678 | + if (err == -EPERM) { | |
10679 | + struct inode *inode = lower_dir_dentry->d_inode; | |
10680 | + err = inode->i_op->unlink(inode, wh_dentry); | |
10681 | + } | |
10682 | + if (err) | |
10683 | + printk(KERN_ERR "unionfs: could not unlink whiteout %s, " | |
10684 | + "err = %d\n", wh_dentry->d_name.name, err); | |
10685 | + | |
10686 | + return err; | |
10687 | + | |
10688 | +} | |
10689 | + | |
10690 | +/* | |
10691 | + * Helper function when creating new objects (create, symlink, mknod, etc.). | |
10692 | + * Checks to see if there's a whiteout in @lower_dentry's parent directory, | |
10693 | + * whose name is taken from @dentry. Then tries to remove that whiteout, if | |
10694 | + * found. If <dentry,bindex> is a branch marked readonly, return -EROFS. | |
63b09289 JR |
10695 | + * If it finds both a regular file and a whiteout, delete whiteout (this |
10696 | + * should never happen). | |
2380c486 JR |
10697 | + * |
10698 | + * Return 0 if no whiteout was found. Return 1 if one was found and | |
10699 | + * successfully removed. Therefore a value >= 0 tells the caller that | |
10700 | + * @lower_dentry belongs to a good branch to create the new object in). | |
10701 | + * Return -ERRNO if an error occurred during whiteout lookup or in trying to | |
10702 | + * unlink the whiteout. | |
10703 | + */ | |
10704 | +int check_unlink_whiteout(struct dentry *dentry, struct dentry *lower_dentry, | |
10705 | + int bindex) | |
10706 | +{ | |
10707 | + int err; | |
10708 | + struct dentry *wh_dentry = NULL; | |
10709 | + struct dentry *lower_dir_dentry = NULL; | |
10710 | + | |
10711 | + /* look for whiteout dentry first */ | |
10712 | + lower_dir_dentry = dget_parent(lower_dentry); | |
10713 | + wh_dentry = lookup_whiteout(dentry->d_name.name, lower_dir_dentry); | |
10714 | + dput(lower_dir_dentry); | |
10715 | + if (IS_ERR(wh_dentry)) { | |
10716 | + err = PTR_ERR(wh_dentry); | |
10717 | + goto out; | |
10718 | + } | |
10719 | + | |
10720 | + if (!wh_dentry->d_inode) { /* no whiteout exists*/ | |
10721 | + err = 0; | |
10722 | + goto out_dput; | |
10723 | + } | |
10724 | + | |
10725 | + /* check if regular file and whiteout were both found */ | |
63b09289 JR |
10726 | + if (unlikely(lower_dentry->d_inode)) |
10727 | + printk(KERN_WARNING "unionfs: removing whiteout; regular " | |
10728 | + "file exists in directory %s (branch %d)\n", | |
2380c486 | 10729 | + lower_dir_dentry->d_name.name, bindex); |
2380c486 JR |
10730 | + |
10731 | + /* check if branch is writeable */ | |
10732 | + err = is_robranch_super(dentry->d_sb, bindex); | |
10733 | + if (err) | |
10734 | + goto out_dput; | |
10735 | + | |
10736 | + /* .wh.foo has been found, so let's unlink it */ | |
10737 | + err = unlink_whiteout(wh_dentry); | |
10738 | + if (!err) | |
10739 | + err = 1; /* a whiteout was found and successfully removed */ | |
10740 | +out_dput: | |
10741 | + dput(wh_dentry); | |
10742 | +out: | |
10743 | + return err; | |
10744 | +} | |
10745 | + | |
10746 | +/* | |
10747 | + * Pass an unionfs dentry and an index. It will try to create a whiteout | |
10748 | + * for the filename in dentry, and will try in branch 'index'. On error, | |
10749 | + * it will proceed to a branch to the left. | |
10750 | + */ | |
10751 | +int create_whiteout(struct dentry *dentry, int start) | |
10752 | +{ | |
10753 | + int bstart, bend, bindex; | |
10754 | + struct dentry *lower_dir_dentry; | |
10755 | + struct dentry *lower_dentry; | |
10756 | + struct dentry *lower_wh_dentry; | |
10757 | + struct nameidata nd; | |
10758 | + char *name = NULL; | |
10759 | + int err = -EINVAL; | |
10760 | + | |
10761 | + verify_locked(dentry); | |
10762 | + | |
10763 | + bstart = dbstart(dentry); | |
10764 | + bend = dbend(dentry); | |
10765 | + | |
10766 | + /* create dentry's whiteout equivalent */ | |
10767 | + name = alloc_whname(dentry->d_name.name, dentry->d_name.len); | |
10768 | + if (unlikely(IS_ERR(name))) { | |
10769 | + err = PTR_ERR(name); | |
10770 | + goto out; | |
10771 | + } | |
10772 | + | |
10773 | + for (bindex = start; bindex >= 0; bindex--) { | |
10774 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
10775 | + | |
10776 | + if (!lower_dentry) { | |
10777 | + /* | |
10778 | + * if lower dentry is not present, create the | |
10779 | + * entire lower dentry directory structure and go | |
10780 | + * ahead. Since we want to just create whiteout, we | |
10781 | + * only want the parent dentry, and hence get rid of | |
10782 | + * this dentry. | |
10783 | + */ | |
10784 | + lower_dentry = create_parents(dentry->d_inode, | |
10785 | + dentry, | |
10786 | + dentry->d_name.name, | |
10787 | + bindex); | |
10788 | + if (!lower_dentry || IS_ERR(lower_dentry)) { | |
10789 | + int ret = PTR_ERR(lower_dentry); | |
10790 | + if (!IS_COPYUP_ERR(ret)) | |
10791 | + printk(KERN_ERR | |
10792 | + "unionfs: create_parents for " | |
10793 | + "whiteout failed: bindex=%d " | |
10794 | + "err=%d\n", bindex, ret); | |
10795 | + continue; | |
10796 | + } | |
10797 | + } | |
10798 | + | |
10799 | + lower_wh_dentry = | |
4ae1df7a | 10800 | + lookup_lck_len(name, lower_dentry->d_parent, |
2380c486 JR |
10801 | + dentry->d_name.len + UNIONFS_WHLEN); |
10802 | + if (IS_ERR(lower_wh_dentry)) | |
10803 | + continue; | |
10804 | + | |
10805 | + /* | |
10806 | + * The whiteout already exists. This used to be impossible, | |
10807 | + * but now is possible because of opaqueness. | |
10808 | + */ | |
10809 | + if (lower_wh_dentry->d_inode) { | |
10810 | + dput(lower_wh_dentry); | |
10811 | + err = 0; | |
10812 | + goto out; | |
10813 | + } | |
10814 | + | |
10815 | + err = init_lower_nd(&nd, LOOKUP_CREATE); | |
10816 | + if (unlikely(err < 0)) | |
10817 | + goto out; | |
10818 | + lower_dir_dentry = lock_parent_wh(lower_wh_dentry); | |
10819 | + err = is_robranch_super(dentry->d_sb, bindex); | |
10820 | + if (!err) | |
10821 | + err = vfs_create(lower_dir_dentry->d_inode, | |
10822 | + lower_wh_dentry, | |
4ae1df7a | 10823 | + current_umask() & S_IRUGO, |
2380c486 JR |
10824 | + &nd); |
10825 | + unlock_dir(lower_dir_dentry); | |
10826 | + dput(lower_wh_dentry); | |
10827 | + release_lower_nd(&nd, err); | |
10828 | + | |
10829 | + if (!err || !IS_COPYUP_ERR(err)) | |
10830 | + break; | |
10831 | + } | |
10832 | + | |
10833 | + /* set dbopaque so that lookup will not proceed after this branch */ | |
10834 | + if (!err) | |
10835 | + dbopaque(dentry) = bindex; | |
10836 | + | |
10837 | +out: | |
10838 | + kfree(name); | |
10839 | + return err; | |
10840 | +} | |
10841 | + | |
10842 | +/* | |
10843 | + * Delete all of the whiteouts in a given directory for rmdir. | |
10844 | + * | |
10845 | + * lower directory inode should be locked | |
10846 | + */ | |
10847 | +static int do_delete_whiteouts(struct dentry *dentry, int bindex, | |
10848 | + struct unionfs_dir_state *namelist) | |
10849 | +{ | |
10850 | + int err = 0; | |
10851 | + struct dentry *lower_dir_dentry = NULL; | |
10852 | + struct dentry *lower_dentry; | |
10853 | + char *name = NULL, *p; | |
10854 | + struct inode *lower_dir; | |
10855 | + int i; | |
10856 | + struct list_head *pos; | |
10857 | + struct filldir_node *cursor; | |
10858 | + | |
10859 | + /* Find out lower parent dentry */ | |
10860 | + lower_dir_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
10861 | + BUG_ON(!S_ISDIR(lower_dir_dentry->d_inode->i_mode)); | |
10862 | + lower_dir = lower_dir_dentry->d_inode; | |
10863 | + BUG_ON(!S_ISDIR(lower_dir->i_mode)); | |
10864 | + | |
10865 | + err = -ENOMEM; | |
10866 | + name = __getname(); | |
10867 | + if (unlikely(!name)) | |
10868 | + goto out; | |
10869 | + strcpy(name, UNIONFS_WHPFX); | |
10870 | + p = name + UNIONFS_WHLEN; | |
10871 | + | |
10872 | + err = 0; | |
10873 | + for (i = 0; !err && i < namelist->size; i++) { | |
10874 | + list_for_each(pos, &namelist->list[i]) { | |
10875 | + cursor = | |
10876 | + list_entry(pos, struct filldir_node, | |
10877 | + file_list); | |
10878 | + /* Only operate on whiteouts in this branch. */ | |
10879 | + if (cursor->bindex != bindex) | |
10880 | + continue; | |
10881 | + if (!cursor->whiteout) | |
10882 | + continue; | |
10883 | + | |
10884 | + strlcpy(p, cursor->name, PATH_MAX - UNIONFS_WHLEN); | |
10885 | + lower_dentry = | |
4ae1df7a | 10886 | + lookup_lck_len(name, lower_dir_dentry, |
2380c486 JR |
10887 | + cursor->namelen + |
10888 | + UNIONFS_WHLEN); | |
10889 | + if (IS_ERR(lower_dentry)) { | |
10890 | + err = PTR_ERR(lower_dentry); | |
10891 | + break; | |
10892 | + } | |
10893 | + if (lower_dentry->d_inode) | |
10894 | + err = vfs_unlink(lower_dir, lower_dentry); | |
10895 | + dput(lower_dentry); | |
10896 | + if (err) | |
10897 | + break; | |
10898 | + } | |
10899 | + } | |
10900 | + | |
10901 | + __putname(name); | |
10902 | + | |
10903 | + /* After all of the removals, we should copy the attributes once. */ | |
10904 | + fsstack_copy_attr_times(dentry->d_inode, lower_dir_dentry->d_inode); | |
10905 | + | |
10906 | +out: | |
10907 | + return err; | |
10908 | +} | |
10909 | + | |
10910 | + | |
10911 | +void __delete_whiteouts(struct work_struct *work) | |
10912 | +{ | |
10913 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
10914 | + struct deletewh_args *d = &args->deletewh; | |
10915 | + | |
10916 | + args->err = do_delete_whiteouts(d->dentry, d->bindex, d->namelist); | |
10917 | + complete(&args->comp); | |
10918 | +} | |
10919 | + | |
10920 | +/* delete whiteouts in a dir (for rmdir operation) using sioq if necessary */ | |
10921 | +int delete_whiteouts(struct dentry *dentry, int bindex, | |
10922 | + struct unionfs_dir_state *namelist) | |
10923 | +{ | |
10924 | + int err; | |
10925 | + struct super_block *sb; | |
10926 | + struct dentry *lower_dir_dentry; | |
10927 | + struct inode *lower_dir; | |
10928 | + struct sioq_args args; | |
10929 | + | |
10930 | + sb = dentry->d_sb; | |
10931 | + | |
10932 | + BUG_ON(!S_ISDIR(dentry->d_inode->i_mode)); | |
10933 | + BUG_ON(bindex < dbstart(dentry)); | |
10934 | + BUG_ON(bindex > dbend(dentry)); | |
10935 | + err = is_robranch_super(sb, bindex); | |
10936 | + if (err) | |
10937 | + goto out; | |
10938 | + | |
10939 | + lower_dir_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
10940 | + BUG_ON(!S_ISDIR(lower_dir_dentry->d_inode->i_mode)); | |
10941 | + lower_dir = lower_dir_dentry->d_inode; | |
10942 | + BUG_ON(!S_ISDIR(lower_dir->i_mode)); | |
10943 | + | |
10944 | + if (!inode_permission(lower_dir, MAY_WRITE | MAY_EXEC)) { | |
10945 | + err = do_delete_whiteouts(dentry, bindex, namelist); | |
10946 | + } else { | |
10947 | + args.deletewh.namelist = namelist; | |
10948 | + args.deletewh.dentry = dentry; | |
10949 | + args.deletewh.bindex = bindex; | |
10950 | + run_sioq(__delete_whiteouts, &args); | |
10951 | + err = args.err; | |
10952 | + } | |
10953 | + | |
10954 | +out: | |
10955 | + return err; | |
10956 | +} | |
10957 | + | |
10958 | +/**************************************************************************** | |
10959 | + * Opaque directory helpers * | |
10960 | + ****************************************************************************/ | |
10961 | + | |
10962 | +/* | |
10963 | + * is_opaque_dir: returns 0 if it is NOT an opaque dir, 1 if it is, and | |
10964 | + * -errno if an error occurred trying to figure this out. | |
10965 | + */ | |
10966 | +int is_opaque_dir(struct dentry *dentry, int bindex) | |
10967 | +{ | |
10968 | + int err = 0; | |
10969 | + struct dentry *lower_dentry; | |
10970 | + struct dentry *wh_lower_dentry; | |
10971 | + struct inode *lower_inode; | |
10972 | + struct sioq_args args; | |
63b09289 | 10973 | + struct nameidata lower_nd; |
2380c486 JR |
10974 | + |
10975 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
10976 | + lower_inode = lower_dentry->d_inode; | |
10977 | + | |
10978 | + BUG_ON(!S_ISDIR(lower_inode->i_mode)); | |
10979 | + | |
10980 | + mutex_lock(&lower_inode->i_mutex); | |
10981 | + | |
10982 | + if (!inode_permission(lower_inode, MAY_EXEC)) { | |
63b09289 JR |
10983 | + err = init_lower_nd(&lower_nd, LOOKUP_OPEN); |
10984 | + if (unlikely(err < 0)) { | |
10985 | + mutex_unlock(&lower_inode->i_mutex); | |
10986 | + goto out; | |
10987 | + } | |
2380c486 | 10988 | + wh_lower_dentry = |
63b09289 JR |
10989 | + lookup_one_len_nd(UNIONFS_DIR_OPAQUE, lower_dentry, |
10990 | + sizeof(UNIONFS_DIR_OPAQUE) - 1, | |
10991 | + &lower_nd); | |
10992 | + release_lower_nd(&lower_nd, err); | |
2380c486 JR |
10993 | + } else { |
10994 | + args.is_opaque.dentry = lower_dentry; | |
10995 | + run_sioq(__is_opaque_dir, &args); | |
10996 | + wh_lower_dentry = args.ret; | |
10997 | + } | |
10998 | + | |
10999 | + mutex_unlock(&lower_inode->i_mutex); | |
11000 | + | |
11001 | + if (IS_ERR(wh_lower_dentry)) { | |
11002 | + err = PTR_ERR(wh_lower_dentry); | |
11003 | + goto out; | |
11004 | + } | |
11005 | + | |
11006 | + /* This is an opaque dir iff wh_lower_dentry is positive */ | |
11007 | + err = !!wh_lower_dentry->d_inode; | |
11008 | + | |
11009 | + dput(wh_lower_dentry); | |
11010 | +out: | |
11011 | + return err; | |
11012 | +} | |
11013 | + | |
11014 | +void __is_opaque_dir(struct work_struct *work) | |
11015 | +{ | |
11016 | + struct sioq_args *args = container_of(work, struct sioq_args, work); | |
63b09289 JR |
11017 | + struct nameidata lower_nd; |
11018 | + int err; | |
2380c486 | 11019 | + |
63b09289 JR |
11020 | + err = init_lower_nd(&lower_nd, LOOKUP_OPEN); |
11021 | + if (unlikely(err < 0)) | |
11022 | + return; | |
11023 | + args->ret = lookup_one_len_nd(UNIONFS_DIR_OPAQUE, | |
11024 | + args->is_opaque.dentry, | |
11025 | + sizeof(UNIONFS_DIR_OPAQUE) - 1, | |
11026 | + &lower_nd); | |
11027 | + release_lower_nd(&lower_nd, err); | |
2380c486 JR |
11028 | + complete(&args->comp); |
11029 | +} | |
11030 | + | |
11031 | +int make_dir_opaque(struct dentry *dentry, int bindex) | |
11032 | +{ | |
11033 | + int err = 0; | |
11034 | + struct dentry *lower_dentry, *diropq; | |
11035 | + struct inode *lower_dir; | |
11036 | + struct nameidata nd; | |
11037 | + const struct cred *old_creds; | |
11038 | + struct cred *new_creds; | |
11039 | + | |
11040 | + /* | |
11041 | + * Opaque directory whiteout markers are special files (like regular | |
11042 | + * whiteouts), and should appear to the users as if they don't | |
11043 | + * exist. They should be created/deleted regardless of directory | |
11044 | + * search/create permissions, but only for the duration of this | |
11045 | + * creation of the .wh.__dir_opaque: file. Note, this does not | |
11046 | + * circumvent normal ->permission). | |
11047 | + */ | |
11048 | + new_creds = prepare_creds(); | |
11049 | + if (unlikely(!new_creds)) { | |
11050 | + err = -ENOMEM; | |
11051 | + goto out_err; | |
11052 | + } | |
11053 | + cap_raise(new_creds->cap_effective, CAP_DAC_READ_SEARCH); | |
11054 | + cap_raise(new_creds->cap_effective, CAP_DAC_OVERRIDE); | |
11055 | + old_creds = override_creds(new_creds); | |
11056 | + | |
11057 | + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); | |
11058 | + lower_dir = lower_dentry->d_inode; | |
11059 | + BUG_ON(!S_ISDIR(dentry->d_inode->i_mode) || | |
11060 | + !S_ISDIR(lower_dir->i_mode)); | |
11061 | + | |
11062 | + mutex_lock(&lower_dir->i_mutex); | |
63b09289 JR |
11063 | + err = init_lower_nd(&nd, LOOKUP_OPEN); |
11064 | + if (unlikely(err < 0)) | |
11065 | + goto out; | |
11066 | + diropq = lookup_one_len_nd(UNIONFS_DIR_OPAQUE, lower_dentry, | |
11067 | + sizeof(UNIONFS_DIR_OPAQUE) - 1, &nd); | |
11068 | + release_lower_nd(&nd, err); | |
2380c486 JR |
11069 | + if (IS_ERR(diropq)) { |
11070 | + err = PTR_ERR(diropq); | |
11071 | + goto out; | |
11072 | + } | |
11073 | + | |
11074 | + err = init_lower_nd(&nd, LOOKUP_CREATE); | |
11075 | + if (unlikely(err < 0)) | |
11076 | + goto out; | |
11077 | + if (!diropq->d_inode) | |
11078 | + err = vfs_create(lower_dir, diropq, S_IRUGO, &nd); | |
11079 | + if (!err) | |
11080 | + dbopaque(dentry) = bindex; | |
11081 | + release_lower_nd(&nd, err); | |
11082 | + | |
11083 | + dput(diropq); | |
11084 | + | |
11085 | +out: | |
11086 | + mutex_unlock(&lower_dir->i_mutex); | |
11087 | + revert_creds(old_creds); | |
11088 | +out_err: | |
11089 | + return err; | |
11090 | +} | |
0c5527e5 AM |
11091 | diff --git a/fs/unionfs/xattr.c b/fs/unionfs/xattr.c |
11092 | new file mode 100644 | |
63b09289 | 11093 | index 0000000..a93d803 |
0c5527e5 AM |
11094 | --- /dev/null |
11095 | +++ b/fs/unionfs/xattr.c | |
2380c486 JR |
11096 | @@ -0,0 +1,173 @@ |
11097 | +/* | |
63b09289 | 11098 | + * Copyright (c) 2003-2011 Erez Zadok |
2380c486 JR |
11099 | + * Copyright (c) 2003-2006 Charles P. Wright |
11100 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
11101 | + * Copyright (c) 2005-2006 Junjiro Okajima | |
11102 | + * Copyright (c) 2005 Arun M. Krishnakumar | |
11103 | + * Copyright (c) 2004-2006 David P. Quigley | |
11104 | + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair | |
11105 | + * Copyright (c) 2003 Puja Gupta | |
11106 | + * Copyright (c) 2003 Harikesavan Krishnan | |
63b09289 JR |
11107 | + * Copyright (c) 2003-2011 Stony Brook University |
11108 | + * Copyright (c) 2003-2011 The Research Foundation of SUNY | |
2380c486 JR |
11109 | + * |
11110 | + * This program is free software; you can redistribute it and/or modify | |
11111 | + * it under the terms of the GNU General Public License version 2 as | |
11112 | + * published by the Free Software Foundation. | |
11113 | + */ | |
11114 | + | |
11115 | +#include "union.h" | |
11116 | + | |
11117 | +/* This is lifted from fs/xattr.c */ | |
11118 | +void *unionfs_xattr_alloc(size_t size, size_t limit) | |
11119 | +{ | |
11120 | + void *ptr; | |
11121 | + | |
11122 | + if (size > limit) | |
11123 | + return ERR_PTR(-E2BIG); | |
11124 | + | |
11125 | + if (!size) /* size request, no buffer is needed */ | |
11126 | + return NULL; | |
11127 | + | |
11128 | + ptr = kmalloc(size, GFP_KERNEL); | |
11129 | + if (unlikely(!ptr)) | |
11130 | + return ERR_PTR(-ENOMEM); | |
11131 | + return ptr; | |
11132 | +} | |
11133 | + | |
11134 | +/* | |
11135 | + * BKL held by caller. | |
11136 | + * dentry->d_inode->i_mutex locked | |
11137 | + */ | |
11138 | +ssize_t unionfs_getxattr(struct dentry *dentry, const char *name, void *value, | |
11139 | + size_t size) | |
11140 | +{ | |
11141 | + struct dentry *lower_dentry = NULL; | |
11142 | + struct dentry *parent; | |
11143 | + int err = -EOPNOTSUPP; | |
11144 | + bool valid; | |
11145 | + | |
11146 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
11147 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
11148 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
11149 | + | |
11150 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
11151 | + if (unlikely(!valid)) { | |
11152 | + err = -ESTALE; | |
11153 | + goto out; | |
11154 | + } | |
11155 | + | |
11156 | + lower_dentry = unionfs_lower_dentry(dentry); | |
11157 | + | |
11158 | + err = vfs_getxattr(lower_dentry, (char *) name, value, size); | |
11159 | + | |
11160 | +out: | |
11161 | + unionfs_check_dentry(dentry); | |
11162 | + unionfs_unlock_dentry(dentry); | |
11163 | + unionfs_unlock_parent(dentry, parent); | |
11164 | + unionfs_read_unlock(dentry->d_sb); | |
11165 | + return err; | |
11166 | +} | |
11167 | + | |
11168 | +/* | |
11169 | + * BKL held by caller. | |
11170 | + * dentry->d_inode->i_mutex locked | |
11171 | + */ | |
11172 | +int unionfs_setxattr(struct dentry *dentry, const char *name, | |
11173 | + const void *value, size_t size, int flags) | |
11174 | +{ | |
11175 | + struct dentry *lower_dentry = NULL; | |
11176 | + struct dentry *parent; | |
11177 | + int err = -EOPNOTSUPP; | |
11178 | + bool valid; | |
11179 | + | |
11180 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
11181 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
11182 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
11183 | + | |
11184 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
11185 | + if (unlikely(!valid)) { | |
11186 | + err = -ESTALE; | |
11187 | + goto out; | |
11188 | + } | |
11189 | + | |
11190 | + lower_dentry = unionfs_lower_dentry(dentry); | |
11191 | + | |
11192 | + err = vfs_setxattr(lower_dentry, (char *) name, (void *) value, | |
11193 | + size, flags); | |
11194 | + | |
11195 | +out: | |
11196 | + unionfs_check_dentry(dentry); | |
11197 | + unionfs_unlock_dentry(dentry); | |
11198 | + unionfs_unlock_parent(dentry, parent); | |
11199 | + unionfs_read_unlock(dentry->d_sb); | |
11200 | + return err; | |
11201 | +} | |
11202 | + | |
11203 | +/* | |
11204 | + * BKL held by caller. | |
11205 | + * dentry->d_inode->i_mutex locked | |
11206 | + */ | |
11207 | +int unionfs_removexattr(struct dentry *dentry, const char *name) | |
11208 | +{ | |
11209 | + struct dentry *lower_dentry = NULL; | |
11210 | + struct dentry *parent; | |
11211 | + int err = -EOPNOTSUPP; | |
11212 | + bool valid; | |
11213 | + | |
11214 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
11215 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
11216 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
11217 | + | |
11218 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
11219 | + if (unlikely(!valid)) { | |
11220 | + err = -ESTALE; | |
11221 | + goto out; | |
11222 | + } | |
11223 | + | |
11224 | + lower_dentry = unionfs_lower_dentry(dentry); | |
11225 | + | |
11226 | + err = vfs_removexattr(lower_dentry, (char *) name); | |
11227 | + | |
11228 | +out: | |
11229 | + unionfs_check_dentry(dentry); | |
11230 | + unionfs_unlock_dentry(dentry); | |
11231 | + unionfs_unlock_parent(dentry, parent); | |
11232 | + unionfs_read_unlock(dentry->d_sb); | |
11233 | + return err; | |
11234 | +} | |
11235 | + | |
11236 | +/* | |
11237 | + * BKL held by caller. | |
11238 | + * dentry->d_inode->i_mutex locked | |
11239 | + */ | |
11240 | +ssize_t unionfs_listxattr(struct dentry *dentry, char *list, size_t size) | |
11241 | +{ | |
11242 | + struct dentry *lower_dentry = NULL; | |
11243 | + struct dentry *parent; | |
11244 | + int err = -EOPNOTSUPP; | |
11245 | + char *encoded_list = NULL; | |
11246 | + bool valid; | |
11247 | + | |
11248 | + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); | |
11249 | + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); | |
11250 | + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); | |
11251 | + | |
11252 | + valid = __unionfs_d_revalidate(dentry, parent, false); | |
11253 | + if (unlikely(!valid)) { | |
11254 | + err = -ESTALE; | |
11255 | + goto out; | |
11256 | + } | |
11257 | + | |
11258 | + lower_dentry = unionfs_lower_dentry(dentry); | |
11259 | + | |
11260 | + encoded_list = list; | |
11261 | + err = vfs_listxattr(lower_dentry, encoded_list, size); | |
11262 | + | |
11263 | +out: | |
11264 | + unionfs_check_dentry(dentry); | |
11265 | + unionfs_unlock_dentry(dentry); | |
11266 | + unionfs_unlock_parent(dentry, parent); | |
11267 | + unionfs_read_unlock(dentry->d_sb); | |
11268 | + return err; | |
11269 | +} | |
0c5527e5 AM |
11270 | diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h |
11271 | index da317c7..64f1ced 100644 | |
11272 | --- a/include/linux/fs_stack.h | |
11273 | +++ b/include/linux/fs_stack.h | |
7670a7fc AM |
11274 | @@ -1,7 +1,19 @@ |
11275 | +/* | |
11276 | + * Copyright (c) 2006-2009 Erez Zadok | |
11277 | + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek | |
11278 | + * Copyright (c) 2006-2009 Stony Brook University | |
11279 | + * Copyright (c) 2006-2009 The Research Foundation of SUNY | |
11280 | + * | |
11281 | + * This program is free software; you can redistribute it and/or modify | |
11282 | + * it under the terms of the GNU General Public License version 2 as | |
11283 | + * published by the Free Software Foundation. | |
11284 | + */ | |
11285 | + | |
11286 | #ifndef _LINUX_FS_STACK_H | |
11287 | #define _LINUX_FS_STACK_H | |
11288 | ||
11289 | -/* This file defines generic functions used primarily by stackable | |
11290 | +/* | |
11291 | + * This file defines generic functions used primarily by stackable | |
11292 | * filesystems; none of these functions require i_mutex to be held. | |
11293 | */ | |
11294 | ||
0c5527e5 | 11295 | diff --git a/include/linux/magic.h b/include/linux/magic.h |
f6c5ef8b | 11296 | index 2d4beab..39f5798 100644 |
0c5527e5 AM |
11297 | --- a/include/linux/magic.h |
11298 | +++ b/include/linux/magic.h | |
63b09289 | 11299 | @@ -50,6 +50,8 @@ |
2380c486 JR |
11300 | #define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs" |
11301 | #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" | |
11302 | ||
11303 | +#define UNIONFS_SUPER_MAGIC 0xf15f083d | |
11304 | + | |
11305 | #define SMB_SUPER_MAGIC 0x517B | |
11306 | #define USBDEVICE_SUPER_MAGIC 0x9fa2 | |
11307 | #define CGROUP_SUPER_MAGIC 0x27e0eb | |
0c5527e5 | 11308 | diff --git a/include/linux/namei.h b/include/linux/namei.h |
f6c5ef8b | 11309 | index ffc0213..99802c3 100644 |
0c5527e5 AM |
11310 | --- a/include/linux/namei.h |
11311 | +++ b/include/linux/namei.h | |
f6c5ef8b | 11312 | @@ -84,8 +84,11 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, |
7670a7fc AM |
11313 | |
11314 | extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, | |
11315 | int (*open)(struct inode *, struct file *)); | |
11316 | +extern void release_open_intent(struct nameidata *); | |
11317 | ||
11318 | extern struct dentry *lookup_one_len(const char *, struct dentry *, int); | |
63b09289 JR |
11319 | +extern struct dentry *lookup_one_len_nd(const char *, struct dentry *, int, |
11320 | + struct nameidata *nd); | |
7670a7fc | 11321 | |
63b09289 JR |
11322 | extern int follow_down_one(struct path *); |
11323 | extern int follow_down(struct path *); | |
0c5527e5 | 11324 | diff --git a/include/linux/splice.h b/include/linux/splice.h |
6b53c3da | 11325 | index 26e5b61..28213e6 100644 |
0c5527e5 AM |
11326 | --- a/include/linux/splice.h |
11327 | +++ b/include/linux/splice.h | |
11328 | @@ -81,6 +81,11 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *, | |
2380c486 JR |
11329 | struct splice_pipe_desc *); |
11330 | extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, | |
11331 | splice_direct_actor *); | |
11332 | +extern long vfs_splice_from(struct pipe_inode_info *pipe, struct file *out, | |
11333 | + loff_t *ppos, size_t len, unsigned int flags); | |
11334 | +extern long vfs_splice_to(struct file *in, loff_t *ppos, | |
11335 | + struct pipe_inode_info *pipe, size_t len, | |
11336 | + unsigned int flags); | |
11337 | ||
76514441 AM |
11338 | /* |
11339 | * for dynamic pipe sizing | |
0c5527e5 AM |
11340 | diff --git a/include/linux/union_fs.h b/include/linux/union_fs.h |
11341 | new file mode 100644 | |
11342 | index 0000000..c84d97e | |
11343 | --- /dev/null | |
11344 | +++ b/include/linux/union_fs.h | |
2380c486 JR |
11345 | @@ -0,0 +1,22 @@ |
11346 | +/* | |
11347 | + * Copyright (c) 2003-2009 Erez Zadok | |
11348 | + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek | |
11349 | + * Copyright (c) 2003-2009 Stony Brook University | |
11350 | + * Copyright (c) 2003-2009 The Research Foundation of SUNY | |
11351 | + * | |
11352 | + * This program is free software; you can redistribute it and/or modify | |
11353 | + * it under the terms of the GNU General Public License version 2 as | |
11354 | + * published by the Free Software Foundation. | |
11355 | + */ | |
11356 | + | |
11357 | +#ifndef _LINUX_UNION_FS_H | |
11358 | +#define _LINUX_UNION_FS_H | |
11359 | + | |
11360 | +/* | |
11361 | + * DEFINITIONS FOR USER AND KERNEL CODE: | |
11362 | + */ | |
11363 | +# define UNIONFS_IOCTL_INCGEN _IOR(0x15, 11, int) | |
11364 | +# define UNIONFS_IOCTL_QUERYFILE _IOR(0x15, 15, int) | |
11365 | + | |
11366 | +#endif /* _LINUX_UNIONFS_H */ | |
11367 | + | |
0c5527e5 | 11368 | diff --git a/security/security.c b/security/security.c |
92d182d2 | 11369 | index d754249..f7e8373 100644 |
0c5527e5 AM |
11370 | --- a/security/security.c |
11371 | +++ b/security/security.c | |
92d182d2 | 11372 | @@ -538,6 +538,7 @@ int security_inode_permission(struct inode *inode, int mask) |
2380c486 | 11373 | return 0; |
6b53c3da | 11374 | return security_ops->inode_permission(inode, mask); |
2380c486 JR |
11375 | } |
11376 | +EXPORT_SYMBOL(security_inode_permission); | |
11377 | ||
6b53c3da | 11378 | int security_inode_setattr(struct dentry *dentry, struct iattr *attr) |
2380c486 | 11379 | { |