]>
Commit | Line | Data |
---|---|---|
4e97e4e9 | 1 | diff --git a/Documentation/power/tuxonice-internals.txt b/Documentation/power/tuxonice-internals.txt |
2 | new file mode 100644 | |
f3e0dcc9 | 3 | index 0000000..68c0454 |
4e97e4e9 | 4 | --- /dev/null |
5 | +++ b/Documentation/power/tuxonice-internals.txt | |
f3e0dcc9 | 6 | @@ -0,0 +1,474 @@ |
7f9d2ee0 | 7 | + TuxOnIce 3.0 Internal Documentation. |
8 | + Updated to 11 March 2008 | |
24613191 | 9 | + |
10 | +1. Introduction. | |
11 | + | |
7f9d2ee0 | 12 | + TuxOnIce 3.0 is an addition to the Linux Kernel, designed to |
24613191 | 13 | + allow the user to quickly shutdown and quickly boot a computer, without |
14 | + needing to close documents or programs. It is equivalent to the | |
15 | + hibernate facility in some laptops. This implementation, however, | |
16 | + requires no special BIOS or hardware support. | |
17 | + | |
18 | + The code in these files is based upon the original implementation | |
19 | + prepared by Gabor Kuti and additional work by Pavel Machek and a | |
20 | + host of others. This code has been substantially reworked by Nigel | |
21 | + Cunningham, again with the help and testing of many others, not the | |
22 | + least of whom is Michael Frank. At its heart, however, the operation is | |
23 | + essentially the same as Gabor's version. | |
24 | + | |
25 | +2. Overview of operation. | |
26 | + | |
27 | + The basic sequence of operations is as follows: | |
28 | + | |
29 | + a. Quiesce all other activity. | |
30 | + b. Ensure enough memory and storage space are available, and attempt | |
31 | + to free memory/storage if necessary. | |
32 | + c. Allocate the required memory and storage space. | |
33 | + d. Write the image. | |
34 | + e. Power down. | |
35 | + | |
36 | + There are a number of complicating factors which mean that things are | |
37 | + not as simple as the above would imply, however... | |
38 | + | |
39 | + o The activity of each process must be stopped at a point where it will | |
40 | + not be holding locks necessary for saving the image, or unexpectedly | |
41 | + restart operations due to something like a timeout and thereby make | |
42 | + our image inconsistent. | |
43 | + | |
44 | + o It is desirous that we sync outstanding I/O to disk before calculating | |
45 | + image statistics. This reduces corruption if one should suspend but | |
46 | + then not resume, and also makes later parts of the operation safer (see | |
47 | + below). | |
48 | + | |
49 | + o We need to get as close as we can to an atomic copy of the data. | |
50 | + Inconsistencies in the image will result in inconsistent memory contents at | |
51 | + resume time, and thus in instability of the system and/or file system | |
52 | + corruption. This would appear to imply a maximum image size of one half of | |
53 | + the amount of RAM, but we have a solution... (again, below). | |
54 | + | |
55 | + o In 2.6, we choose to play nicely with the other suspend-to-disk | |
56 | + implementations. | |
57 | + | |
58 | +3. Detailed description of internals. | |
59 | + | |
60 | + a. Quiescing activity. | |
61 | + | |
4e97e4e9 | 62 | + Safely quiescing the system is achieved using three separate but related |
63 | + aspects. | |
24613191 | 64 | + |
65 | + First, we note that the vast majority of processes don't need to run during | |
66 | + suspend. They can be 'frozen'. We therefore implement a refrigerator | |
67 | + routine, which processes enter and in which they remain until the cycle is | |
68 | + complete. Processes enter the refrigerator via try_to_freeze() invocations | |
69 | + at appropriate places. A process cannot be frozen in any old place. It | |
70 | + must not be holding locks that will be needed for writing the image or | |
71 | + freezing other processes. For this reason, userspace processes generally | |
72 | + enter the refrigerator via the signal handling code, and kernel threads at | |
73 | + the place in their event loops where they drop locks and yield to other | |
74 | + processes or sleep. | |
75 | + | |
4e97e4e9 | 76 | + The task of freezing processes is complicated by the fact that there can be |
77 | + interdependencies between processes. Freezing process A before process B may | |
78 | + mean that process B cannot be frozen, because it stops at waiting for | |
79 | + process A rather than in the refrigerator. This issue is seen where | |
80 | + userspace waits on freezeable kernel threads or fuse filesystem threads. To | |
81 | + address this issue, we implement the following algorithm for quiescing | |
82 | + activity: | |
83 | + | |
84 | + - Freeze filesystems (including fuse - userspace programs starting | |
85 | + new requests are immediately frozen; programs already running | |
86 | + requests complete their work before being frozen in the next | |
87 | + step) | |
24613191 | 88 | + - Freeze userspace |
4e97e4e9 | 89 | + - Thaw filesystems (this is safe now that userspace is frozen and no |
90 | + fuse requests are outstanding). | |
91 | + - Invoke sys_sync (noop on fuse). | |
24613191 | 92 | + - Freeze filesystems |
93 | + - Freeze kernel threads | |
94 | + | |
95 | + If we need to free memory, we thaw kernel threads and filesystems, but not | |
96 | + userspace. We can then free caches without worrying about deadlocks due to | |
97 | + swap files being on frozen filesystems or such like. | |
98 | + | |
24613191 | 99 | + b. Ensure enough memory & storage are available. |
100 | + | |
101 | + We have a number of constraints to meet in order to be able to successfully | |
102 | + suspend and resume. | |
103 | + | |
104 | + First, the image will be written in two parts, described below. One of these | |
105 | + parts needs to have an atomic copy made, which of course implies a maximum | |
106 | + size of one half of the amount of system memory. The other part ('pageset') | |
107 | + is not atomically copied, and can therefore be as large or small as desired. | |
108 | + | |
109 | + Second, we have constraints on the amount of storage available. In these | |
110 | + calculations, we may also consider any compression that will be done. The | |
111 | + cryptoapi module allows the user to configure an expected compression ratio. | |
112 | + | |
113 | + Third, the user can specify an arbitrary limit on the image size, in | |
114 | + megabytes. This limit is treated as a soft limit, so that we don't fail the | |
115 | + attempt to suspend if we cannot meet this constraint. | |
116 | + | |
117 | + c. Allocate the required memory and storage space. | |
118 | + | |
119 | + Having done the initial freeze, we determine whether the above constraints | |
120 | + are met, and seek to allocate the metadata for the image. If the constraints | |
121 | + are not met, or we fail to allocate the required space for the metadata, we | |
122 | + seek to free the amount of memory that we calculate is needed and try again. | |
123 | + We allow up to four iterations of this loop before aborting the cycle. If we | |
7f9d2ee0 | 124 | + do fail, it should only be because of a bug in TuxOnIce's calculations. |
24613191 | 125 | + |
126 | + These steps are merged together in the prepare_image function, found in | |
127 | + prepare_image.c. The functions are merged because of the cyclical nature | |
128 | + of the problem of calculating how much memory and storage is needed. Since | |
129 | + the data structures containing the information about the image must | |
130 | + themselves take memory and use storage, the amount of memory and storage | |
131 | + required changes as we prepare the image. Since the changes are not large, | |
132 | + only one or two iterations will be required to achieve a solution. | |
133 | + | |
134 | + The recursive nature of the algorithm is miminised by keeping user space | |
135 | + frozen while preparing the image, and by the fact that our records of which | |
136 | + pages are to be saved and which pageset they are saved in use bitmaps (so | |
137 | + that changes in number or fragmentation of the pages to be saved don't | |
138 | + feedback via changes in the amount of memory needed for metadata). The | |
139 | + recursiveness is thus limited to any extra slab pages allocated to store the | |
f3e0dcc9 | 140 | + extents that record storage used, and the effects of seeking to free memory. |
24613191 | 141 | + |
142 | + d. Write the image. | |
143 | + | |
144 | + We previously mentioned the need to create an atomic copy of the data, and | |
145 | + the half-of-memory limitation that is implied in this. This limitation is | |
146 | + circumvented by dividing the memory to be saved into two parts, called | |
147 | + pagesets. | |
148 | + | |
149 | + Pageset2 contains the page cache - the pages on the active and inactive | |
4e97e4e9 | 150 | + lists. These pages aren't needed or modifed while TuxOnIce is running, so |
24613191 | 151 | + they can be safely written without an atomic copy. They are therefore |
4e97e4e9 | 152 | + saved first and reloaded last. While saving these pages, TuxOnIce carefully |
24613191 | 153 | + ensures that the work of writing the pages doesn't make the image |
154 | + inconsistent. | |
155 | + | |
156 | + Once pageset2 has been saved, we prepare to do the atomic copy of remaining | |
157 | + memory. As part of the preparation, we power down drivers, thereby providing | |
158 | + them with the opportunity to have their state recorded in the image. The | |
159 | + amount of memory allocated by drivers for this is usually negligible, but if | |
160 | + DRI is in use, video drivers may require significants amounts. Ideally we | |
161 | + would be able to query drivers while preparing the image as to the amount of | |
162 | + memory they will need. Unfortunately no such mechanism exists at the time of | |
4e97e4e9 | 163 | + writing. For this reason, TuxOnIce allows the user to set an |
24613191 | 164 | + 'extra_pages_allowance', which is used to seek to ensure sufficient memory |
4e97e4e9 | 165 | + is available for drivers at this point. TuxOnIce also lets the user set this |
24613191 | 166 | + value to 0. In this case, a test driver suspend is done while preparing the |
167 | + image, and the difference (plus a margin) used instead. | |
168 | + | |
169 | + Having suspended the drivers, we save the CPU context before making an | |
170 | + atomic copy of pageset1, resuming the drivers and saving the atomic copy. | |
171 | + After saving the two pagesets, we just need to save our metadata before | |
172 | + powering down. | |
173 | + | |
174 | + As we mentioned earlier, the contents of pageset2 pages aren't needed once | |
175 | + they've been saved. We therefore use them as the destination of our atomic | |
176 | + copy. In the unlikely event that pageset1 is larger, extra pages are | |
177 | + allocated while the image is being prepared. This is normally only a real | |
178 | + possibility when the system has just been booted and the page cache is | |
179 | + small. | |
180 | + | |
181 | + This is where we need to be careful about syncing, however. Pageset2 will | |
182 | + probably contain filesystem meta data. If this is overwritten with pageset1 | |
183 | + and then a sync occurs, the filesystem will be corrupted - at least until | |
184 | + resume time and another sync of the restored data. Since there is a | |
185 | + possibility that the user might not resume or (may it never be!) that | |
186 | + suspend might oops, we do our utmost to avoid syncing filesystems after | |
187 | + copying pageset1. | |
188 | + | |
189 | + e. Power down. | |
190 | + | |
4e97e4e9 | 191 | + Powering down uses standard kernel routines. TuxOnIce supports powering down |
24613191 | 192 | + using the ACPI S3, S4 and S5 methods or the kernel's non-ACPI power-off. |
193 | + Supporting suspend to ram (S3) as a power off option might sound strange, | |
194 | + but it allows the user to quickly get their system up and running again if | |
195 | + the battery doesn't run out (we just need to re-read the overwritten pages) | |
196 | + and if the battery does run out (or the user removes power), they can still | |
197 | + resume. | |
198 | + | |
199 | +4. Data Structures. | |
200 | + | |
4e97e4e9 | 201 | + TuxOnIce uses three main structures to store its metadata and configuration |
24613191 | 202 | + information: |
203 | + | |
204 | + a) Pageflags bitmaps. | |
205 | + | |
7f9d2ee0 | 206 | + TuxOnIce records which pages will be in pageset1, pageset2, the destination |
24613191 | 207 | + of the atomic copy and the source of the atomically restored image using |
208 | + bitmaps. These bitmaps are created from order zero allocations to maximise | |
209 | + reliability. The individual pages are combined together with pointers to | |
210 | + form per-zone bitmaps, which are in turn combined with another layer of | |
211 | + pointers to construct the overall bitmap. | |
212 | + | |
213 | + The pageset1 bitmap is thus easily stored in the image header for use at | |
214 | + resume time. | |
215 | + | |
216 | + As mentioned above, using bitmaps also means that the amount of memory and | |
217 | + storage required for recording the above information is constant. This | |
218 | + greatly simplifies the work of preparing the image. In earlier versions of | |
4e97e4e9 | 219 | + TuxOnIce, extents were used to record which pages would be stored. In that |
24613191 | 220 | + case, however, eating memory could result in greater fragmentation of the |
221 | + lists of pages, which in turn required more memory to store the extents and | |
222 | + more storage in the image header. These could in turn require further | |
223 | + freeing of memory, and another iteration. All of this complexity is removed | |
224 | + by having bitmaps. | |
225 | + | |
4e97e4e9 | 226 | + Bitmaps also make a lot of sense because TuxOnIce only ever iterates |
24613191 | 227 | + through the lists. There is therefore no cost to not being able to find the |
228 | + nth page in order 0 time. We only need to worry about the cost of finding | |
229 | + the n+1th page, given the location of the nth page. Bitwise optimisations | |
230 | + help here. | |
231 | + | |
232 | + The data structure is: unsigned long ***. | |
233 | + | |
234 | + b) Extents for block data. | |
235 | + | |
4e97e4e9 | 236 | + TuxOnIce supports writing the image to multiple block devices. In the case |
24613191 | 237 | + of swap, multiple partitions and/or files may be in use, and we happily use |
238 | + them all. This is accomplished as follows: | |
239 | + | |
240 | + Whatever the actual source of the allocated storage, the destination of the | |
241 | + image can be viewed in terms of one or more block devices, and on each | |
242 | + device, a list of sectors. To simplify matters, we only use contiguous, | |
243 | + PAGE_SIZE aligned sectors, like the swap code does. | |
244 | + | |
245 | + Since sector numbers on each bdev may well not start at 0, it makes much | |
246 | + more sense to use extents here. Contiguous ranges of pages can thus be | |
247 | + represented in the extents by contiguous values. | |
248 | + | |
249 | + Variations in block size are taken account of in transforming this data | |
250 | + into the parameters for bio submission. | |
251 | + | |
4e97e4e9 | 252 | + We can thus implement a layer of abstraction wherein the core of TuxOnIce |
24613191 | 253 | + doesn't have to worry about which device we're currently writing to or |
254 | + where in the device we are. It simply requests that the next page in the | |
255 | + pageset or header be written, leaving the details to this lower layer. | |
256 | + The lower layer remembers where in the sequence of devices and blocks each | |
257 | + pageset starts. The header always starts at the beginning of the allocated | |
258 | + storage. | |
259 | + | |
260 | + So extents are: | |
261 | + | |
262 | + struct extent { | |
263 | + unsigned long minimum, maximum; | |
264 | + struct extent *next; | |
265 | + } | |
266 | + | |
267 | + These are combined into chains of extents for a device: | |
268 | + | |
269 | + struct extent_chain { | |
270 | + int size; /* size of the extent ie sum (max-min+1) */ | |
271 | + int allocs, frees; | |
272 | + char *name; | |
273 | + struct extent *first, *last_touched; | |
274 | + }; | |
275 | + | |
276 | + For each bdev, we need to store a little more info: | |
277 | + | |
278 | + struct suspend_bdev_info { | |
279 | + struct block_device *bdev; | |
280 | + dev_t dev_t; | |
281 | + int bmap_shift; | |
282 | + int blocks_per_page; | |
283 | + }; | |
284 | + | |
285 | + The dev_t is used to identify the device in the stored image. As a result, | |
286 | + we expect devices at resume time to have the same major and minor numbers | |
287 | + as they had while suspending. This is primarily a concern where the user | |
288 | + utilises LVM for storage, as they will need to dmsetup their partitions in | |
289 | + such a way as to maintain this consistency at resume time. | |
290 | + | |
291 | + bmap_shift and blocks_per_page record apply the effects of variations in | |
292 | + blocks per page settings for the filesystem and underlying bdev. For most | |
293 | + filesystems, these are the same, but for xfs, they can have independant | |
294 | + values. | |
295 | + | |
296 | + Combining these two structures together, we have everything we need to | |
297 | + record what devices and what blocks on each device are being used to | |
298 | + store the image, and to submit i/o using bio_submit. | |
299 | + | |
300 | + The last elements in the picture are a means of recording how the storage | |
301 | + is being used. | |
302 | + | |
303 | + We do this first and foremost by implementing a layer of abstraction on | |
304 | + top of the devices and extent chains which allows us to view however many | |
305 | + devices there might be as one long storage tape, with a single 'head' that | |
306 | + tracks a 'current position' on the tape: | |
307 | + | |
308 | + struct extent_iterate_state { | |
309 | + struct extent_chain *chains; | |
310 | + int num_chains; | |
311 | + int current_chain; | |
312 | + struct extent *current_extent; | |
313 | + unsigned long current_offset; | |
314 | + }; | |
315 | + | |
316 | + That is, *chains points to an array of size num_chains of extent chains. | |
317 | + For the filewriter, this is always a single chain. For the swapwriter, the | |
318 | + array is of size MAX_SWAPFILES. | |
319 | + | |
320 | + current_chain, current_extent and current_offset thus point to the current | |
321 | + index in the chains array (and into a matching array of struct | |
322 | + suspend_bdev_info), the current extent in that chain (to optimise access), | |
323 | + and the current value in the offset. | |
324 | + | |
325 | + The image is divided into three parts: | |
326 | + - The header | |
327 | + - Pageset 1 | |
328 | + - Pageset 2 | |
329 | + | |
330 | + The header always starts at the first device and first block. We know its | |
331 | + size before we begin to save the image because we carefully account for | |
332 | + everything that will be stored in it. | |
333 | + | |
334 | + The second pageset (LRU) is stored first. It begins on the next page after | |
335 | + the end of the header. | |
336 | + | |
337 | + The first pageset is stored second. It's start location is only known once | |
338 | + pageset2 has been saved, since pageset2 may be compressed as it is written. | |
339 | + This location is thus recorded at the end of saving pageset2. It is page | |
340 | + aligned also. | |
341 | + | |
342 | + Since this information is needed at resume time, and the location of extents | |
343 | + in memory will differ at resume time, this needs to be stored in a portable | |
344 | + way: | |
345 | + | |
346 | + struct extent_iterate_saved_state { | |
347 | + int chain_num; | |
348 | + int extent_num; | |
349 | + unsigned long offset; | |
350 | + }; | |
351 | + | |
4e97e4e9 | 352 | + We can thus implement a layer of abstraction wherein the core of TuxOnIce |
24613191 | 353 | + doesn't have to worry about which device we're currently writing to or |
354 | + where in the device we are. It simply requests that the next page in the | |
355 | + pageset or header be written, leaving the details to this layer, and | |
356 | + invokes the routines to remember and restore the position, without having | |
357 | + to worry about the details of how the data is arranged on disk or such like. | |
358 | + | |
359 | + c) Modules | |
360 | + | |
4e97e4e9 | 361 | + One aim in designing TuxOnIce was to make it flexible. We wanted to allow |
24613191 | 362 | + for the implementation of different methods of transforming a page to be |
363 | + written to disk and different methods of getting the pages stored. | |
364 | + | |
365 | + In early versions (the betas and perhaps Suspend1), compression support was | |
366 | + inlined in the image writing code, and the data structures and code for | |
367 | + managing swap were intertwined with the rest of the code. A number of people | |
368 | + had expressed interest in implementing image encryption, and alternative | |
369 | + methods of storing the image. | |
370 | + | |
4e97e4e9 | 371 | + In order to achieve this, TuxOnIce was given a modular design. |
24613191 | 372 | + |
373 | + A module is a single file which encapsulates the functionality needed | |
374 | + to transform a pageset of data (encryption or compression, for example), | |
375 | + or to write the pageset to a device. The former type of module is called | |
376 | + a 'page-transformer', the later a 'writer'. | |
377 | + | |
378 | + Modules are linked together in pipeline fashion. There may be zero or more | |
379 | + page transformers in a pipeline, and there is always exactly one writer. | |
380 | + The pipeline follows this pattern: | |
381 | + | |
382 | + --------------------------------- | |
4e97e4e9 | 383 | + | TuxOnIce Core | |
24613191 | 384 | + --------------------------------- |
385 | + | | |
386 | + | | |
387 | + --------------------------------- | |
388 | + | Page transformer 1 | | |
389 | + --------------------------------- | |
390 | + | | |
391 | + | | |
392 | + --------------------------------- | |
393 | + | Page transformer 2 | | |
394 | + --------------------------------- | |
395 | + | | |
396 | + | | |
397 | + --------------------------------- | |
398 | + | Writer | | |
399 | + --------------------------------- | |
400 | + | |
401 | + During the writing of an image, the core code feeds pages one at a time | |
402 | + to the first module. This module performs whatever transformations it | |
403 | + implements on the incoming data, completely consuming the incoming data and | |
404 | + feeding output in a similar manner to the next module. A module may buffer | |
405 | + its output. | |
406 | + | |
f3e0dcc9 PS |
407 | + All routines are SMP safe, and the final result of the transformations is |
408 | + written with an index (provided by the core) and size of the output by the | |
409 | + writer. As a result, we can have multithreaded I/O without needing to | |
410 | + worry about the sequence in which pages are written (or read). | |
411 | + | |
24613191 | 412 | + During reading, the pipeline works in the reverse direction. The core code |
413 | + calls the first module with the address of a buffer which should be filled. | |
414 | + (Note that the buffer size is always PAGE_SIZE at this time). This module | |
415 | + will in turn request data from the next module and so on down until the | |
416 | + writer is made to read from the stored image. | |
417 | + | |
418 | + Part of definition of the structure of a module thus looks like this: | |
419 | + | |
420 | + int (*rw_init) (int rw, int stream_number); | |
421 | + int (*rw_cleanup) (int rw); | |
422 | + int (*write_chunk) (struct page *buffer_page); | |
423 | + int (*read_chunk) (struct page *buffer_page, int sync); | |
424 | + | |
425 | + It should be noted that the _cleanup routine may be called before the | |
426 | + full stream of data has been read or written. While writing the image, | |
427 | + the user may (depending upon settings) choose to abort suspending, and | |
428 | + if we are in the midst of writing the last portion of the image, a portion | |
429 | + of the second pageset may be reread. This may also happen if an error | |
430 | + occurs and we seek to abort the process of writing the image. | |
431 | + | |
432 | + The modular design is also useful in a number of other ways. It provides | |
433 | + a means where by we can add support for: | |
434 | + | |
435 | + - providing overall initialisation and cleanup routines; | |
436 | + - serialising configuration information in the image header; | |
437 | + - providing debugging information to the user; | |
438 | + - determining memory and image storage requirements; | |
439 | + - dis/enabling components at run-time; | |
440 | + - configuring the module (see below); | |
441 | + | |
442 | + ...and routines for writers specific to their work: | |
4e97e4e9 | 443 | + - Parsing a resume= location; |
24613191 | 444 | + - Determining whether an image exists; |
445 | + - Marking a resume as having been attempted; | |
446 | + - Invalidating an image; | |
447 | + | |
448 | + Since some parts of the core - the user interface and storage manager | |
449 | + support - have use for some of these functions, they are registered as | |
450 | + 'miscellaneous' modules as well. | |
451 | + | |
452 | + d) Sysfs data structures. | |
453 | + | |
4e97e4e9 | 454 | + This brings us naturally to support for configuring TuxOnIce. We desired to |
455 | + provide a way to make TuxOnIce as flexible and configurable as possible. | |
24613191 | 456 | + The user shouldn't have to reboot just because they want to now suspend to |
457 | + a file instead of a partition, for example. | |
458 | + | |
4e97e4e9 | 459 | + To accomplish this, TuxOnIce implements a very generic means whereby the |
460 | + core and modules can register new sysfs entries. All TuxOnIce entries use | |
24613191 | 461 | + a single _store and _show routine, both of which are found in sysfs.c in |
462 | + the kernel/power directory. These routines handle the most common operations | |
463 | + - getting and setting the values of bits, integers, longs, unsigned longs | |
464 | + and strings in one place, and allow overrides for customised get and set | |
465 | + options as well as side-effect routines for all reads and writes. | |
466 | + | |
467 | + When combined with some simple macros, a new sysfs entry can then be defined | |
468 | + in just a couple of lines: | |
469 | + | |
4e97e4e9 | 470 | + { TOI_ATTR("progress_granularity", SYSFS_RW), |
24613191 | 471 | + SYSFS_INT(&progress_granularity, 1, 2048) |
472 | + }, | |
473 | + | |
474 | + This defines a sysfs entry named "progress_granularity" which is rw and | |
475 | + allows the user to access an integer stored at &progress_granularity, giving | |
476 | + it a value between 1 and 2048 inclusive. | |
477 | + | |
4e97e4e9 | 478 | + Sysfs entries are registered under /sys/power/tuxonice, and entries for |
24613191 | 479 | + modules are located in a subdirectory named after the module. |
480 | + | |
4e97e4e9 | 481 | diff --git a/Documentation/power/tuxonice.txt b/Documentation/power/tuxonice.txt |
482 | new file mode 100644 | |
f3e0dcc9 | 483 | index 0000000..d13ce85 |
4e97e4e9 | 484 | --- /dev/null |
485 | +++ b/Documentation/power/tuxonice.txt | |
f3e0dcc9 | 486 | @@ -0,0 +1,750 @@ |
7f9d2ee0 | 487 | + --- TuxOnIce, version 3.0 --- |
24613191 | 488 | + |
489 | +1. What is it? | |
490 | +2. Why would you want it? | |
491 | +3. What do you need to use it? | |
492 | +4. Why not just use the version already in the kernel? | |
493 | +5. How do you use it? | |
4e97e4e9 | 494 | +6. What do all those entries in /sys/power/tuxonice do? |
24613191 | 495 | +7. How do you get support? |
496 | +8. I think I've found a bug. What should I do? | |
497 | +9. When will XXX be supported? | |
498 | +10 How does it work? | |
4e97e4e9 | 499 | +11. Who wrote TuxOnIce? |
24613191 | 500 | + |
501 | +1. What is it? | |
502 | + | |
503 | + Imagine you're sitting at your computer, working away. For some reason, you | |
504 | + need to turn off your computer for a while - perhaps it's time to go home | |
505 | + for the day. When you come back to your computer next, you're going to want | |
506 | + to carry on where you left off. Now imagine that you could push a button and | |
507 | + have your computer store the contents of its memory to disk and power down. | |
508 | + Then, when you next start up your computer, it loads that image back into | |
509 | + memory and you can carry on from where you were, just as if you'd never | |
7f9d2ee0 | 510 | + turned the computer off. You have far less time to start up, no reopening of |
511 | + applications or finding what directory you put that file in yesterday. | |
4e97e4e9 | 512 | + That's what TuxOnIce does. |
24613191 | 513 | + |
4e97e4e9 | 514 | + TuxOnIce has a long heritage. It began life as work by Gabor Kuti, who, |
24613191 | 515 | + with some help from Pavel Machek, got an early version going in 1999. The |
516 | + project was then taken over by Florent Chabaud while still in alpha version | |
517 | + numbers. Nigel Cunningham came on the scene when Florent was unable to | |
518 | + continue, moving the project into betas, then 1.0, 2.0 and so on up to | |
4e97e4e9 | 519 | + the present series. During the 2.0 series, the name was contracted to |
520 | + Suspend2 and the website suspend2.net created. Beginning around July 2007, | |
521 | + a transition to calling the software TuxOnIce was made, to seek to help | |
522 | + make it clear that TuxOnIce is more concerned with hibernation than suspend | |
523 | + to ram. | |
524 | + | |
525 | + Pavel Machek's swsusp code, which was merged around 2.5.17 retains the | |
526 | + original name, and was essentially a fork of the beta code until Rafael | |
527 | + Wysocki came on the scene in 2005 and began to improve it further. | |
24613191 | 528 | + |
529 | +2. Why would you want it? | |
530 | + | |
531 | + Why wouldn't you want it? | |
532 | + | |
533 | + Being able to save the state of your system and quickly restore it improves | |
534 | + your productivity - you get a useful system in far less time than through | |
f3e0dcc9 PS |
535 | + the normal boot process. You also get to be completely 'green', using zero |
536 | + power, or as close to that as possible (the computer may still provide | |
537 | + minimal power to some devices, so they can initiate a power on, but that | |
538 | + will be the same amount of power as would be used if you told the computer | |
539 | + to shutdown. | |
24613191 | 540 | + |
541 | +3. What do you need to use it? | |
542 | + | |
543 | + a. Kernel Support. | |
544 | + | |
4e97e4e9 | 545 | + i) The TuxOnIce patch. |
24613191 | 546 | + |
4e97e4e9 | 547 | + TuxOnIce is part of the Linux Kernel. This version is not part of Linus's |
24613191 | 548 | + 2.6 tree at the moment, so you will need to download the kernel source and |
549 | + apply the latest patch. Having done that, enable the appropriate options in | |
7f9d2ee0 | 550 | + make [menu|x]config (under Power Management Options - look for "Enhanced |
551 | + Hibernation"), compile and install your kernel. TuxOnIce works with SMP, | |
552 | + Highmem, preemption, fuse filesystems, x86-32, PPC and x86_64. | |
24613191 | 553 | + |
4e97e4e9 | 554 | + TuxOnIce patches are available from http://tuxonice.net. |
24613191 | 555 | + |
4e97e4e9 | 556 | + ii) Compression support. |
24613191 | 557 | + |
4e97e4e9 | 558 | + Compression support is implemented via the cryptoapi. You will therefore want |
559 | + to select any Cryptoapi transforms that you want to use on your image from | |
7f9d2ee0 | 560 | + the Cryptoapi menu while configuring your kernel. Part of the TuxOnIce patch |
561 | + adds a new cryptoapi compression called LZF. We recommend the use of this | |
562 | + compression method - it is very fast and still achieves good compression. | |
24613191 | 563 | + |
4e97e4e9 | 564 | + You can also tell TuxOnIce to write it's image to an encrypted and/or |
24613191 | 565 | + compressed filesystem/swap partition. In that case, you don't need to do |
4e97e4e9 | 566 | + anything special for TuxOnIce when it comes to kernel configuration. |
24613191 | 567 | + |
568 | + iii) Configuring other options. | |
569 | + | |
570 | + While you're configuring your kernel, try to configure as much as possible | |
571 | + to build as modules. We recommend this because there are a number of drivers | |
572 | + that are still in the process of implementing proper power management | |
573 | + support. In those cases, the best way to work around their current lack is | |
7f9d2ee0 | 574 | + to build them as modules and remove the modules while hibernating. You might |
24613191 | 575 | + also bug the driver authors to get their support up to speed, or even help! |
576 | + | |
577 | + b. Storage. | |
578 | + | |
579 | + i) Swap. | |
580 | + | |
7f9d2ee0 | 581 | + TuxOnIce can store the hibernation image in your swap partition, a swap file or |
24613191 | 582 | + a combination thereof. Whichever combination you choose, you will probably |
583 | + want to create enough swap space to store the largest image you could have, | |
584 | + plus the space you'd normally use for swap. A good rule of thumb would be | |
4e97e4e9 | 585 | + to calculate the amount of swap you'd want without using TuxOnIce, and then |
24613191 | 586 | + add the amount of memory you have. This swapspace can be arranged in any way |
587 | + you'd like. It can be in one partition or file, or spread over a number. The | |
7f9d2ee0 | 588 | + only requirement is that they be active when you start a hibernation cycle. |
24613191 | 589 | + |
4e97e4e9 | 590 | + There is one exception to this requirement. TuxOnIce has the ability to turn |
7f9d2ee0 | 591 | + on one swap file or partition at the start of hibernating and turn it back off |
24613191 | 592 | + at the end. If you want to ensure you have enough memory to store a image |
593 | + when your memory is fully used, you might want to make one swap partition or | |
4e97e4e9 | 594 | + file for 'normal' use, and another for TuxOnIce to activate & deactivate |
24613191 | 595 | + automatically. (Further details below). |
596 | + | |
597 | + ii) Normal files. | |
598 | + | |
4e97e4e9 | 599 | + TuxOnIce includes a 'file allocator'. The file allocator can store your |
600 | + image in a simple file. Since Linux has the concept of everything being a | |
601 | + file, this is more powerful than it initially sounds. If, for example, you | |
7f9d2ee0 | 602 | + were to set up a network block device file, you could hibernate to a network |
4e97e4e9 | 603 | + server. This has been tested and works to a point, but nbd itself isn't |
604 | + stateless enough for our purposes. | |
24613191 | 605 | + |
4e97e4e9 | 606 | + Take extra care when setting up the file allocator. If you just type |
7f9d2ee0 | 607 | + commands without thinking and then try to hibernate, you could cause |
4e97e4e9 | 608 | + irreversible corruption on your filesystems! Make sure you have backups. |
24613191 | 609 | + |
7f9d2ee0 | 610 | + Most people will only want to hibernate to a local file. To achieve that, do |
24613191 | 611 | + something along the lines of: |
612 | + | |
7f9d2ee0 | 613 | + echo "TuxOnIce" > /hibernation-file |
614 | + dd if=/dev/zero bs=1M count=512 >> hibernation-file | |
24613191 | 615 | + |
7f9d2ee0 | 616 | + This will create a 512MB file called /hibernation-file. To get TuxOnIce to use |
24613191 | 617 | + it: |
618 | + | |
7f9d2ee0 | 619 | + echo /hibernation-file > /sys/power/tuxonice/file/target |
24613191 | 620 | + |
621 | + Then | |
622 | + | |
4e97e4e9 | 623 | + cat /sys/power/tuxonice/resume |
24613191 | 624 | + |
625 | + Put the results of this into your bootloader's configuration (see also step | |
7f9d2ee0 | 626 | + C, below): |
24613191 | 627 | + |
628 | + ---EXAMPLE-ONLY-DON'T-COPY-AND-PASTE--- | |
4e97e4e9 | 629 | + # cat /sys/power/tuxonice/resume |
24613191 | 630 | + file:/dev/hda2:0x1e001 |
631 | + | |
632 | + In this example, we would edit the append= line of our lilo.conf|menu.lst | |
633 | + so that it included: | |
634 | + | |
4e97e4e9 | 635 | + resume=file:/dev/hda2:0x1e001 |
24613191 | 636 | + ---EXAMPLE-ONLY-DON'T-COPY-AND-PASTE--- |
637 | + | |
638 | + For those who are thinking 'Could I make the file sparse?', the answer is | |
4e97e4e9 | 639 | + 'No!'. At the moment, there is no way for TuxOnIce to fill in the holes in |
7f9d2ee0 | 640 | + a sparse file while hibernating. In the longer term (post merge!), I'd like |
641 | + to change things so that the file could be dynamically resized and have | |
642 | + holes filled as needed. Right now, however, that's not possible and not a | |
643 | + priority. | |
24613191 | 644 | + |
645 | + c. Bootloader configuration. | |
646 | + | |
4e97e4e9 | 647 | + Using TuxOnIce also requires that you add an extra parameter to |
24613191 | 648 | + your lilo.conf or equivalent. Here's an example for a swap partition: |
649 | + | |
4e97e4e9 | 650 | + append="resume=swap:/dev/hda1" |
24613191 | 651 | + |
4e97e4e9 | 652 | + This would tell TuxOnIce that /dev/hda1 is a swap partition you |
653 | + have. TuxOnIce will use the swap signature of this partition as a | |
7f9d2ee0 | 654 | + pointer to your data when you hibernate. This means that (in this example) |
24613191 | 655 | + /dev/hda1 doesn't need to be _the_ swap partition where all of your data |
656 | + is actually stored. It just needs to be a swap partition that has a | |
657 | + valid signature. | |
658 | + | |
4e97e4e9 | 659 | + You don't need to have a swap partition for this purpose. TuxOnIce |
24613191 | 660 | + can also use a swap file, but usage is a little more complex. Having made |
661 | + your swap file, turn it on and do | |
662 | + | |
4e97e4e9 | 663 | + cat /sys/power/tuxonice/swap/headerlocations |
24613191 | 664 | + |
4e97e4e9 | 665 | + (this assumes you've already compiled your kernel with TuxOnIce |
24613191 | 666 | + support and booted it). The results of the cat command will tell you |
667 | + what you need to put in lilo.conf: | |
668 | + | |
4e97e4e9 | 669 | + For swap partitions like /dev/hda1, simply use resume=/dev/hda1. |
670 | + For swapfile `swapfile`, use resume=swap:/dev/hda2:0x242d. | |
24613191 | 671 | + |
672 | + If the swapfile changes for any reason (it is moved to a different | |
673 | + location, it is deleted and recreated, or the filesystem is | |
674 | + defragmented) then you will have to check | |
4e97e4e9 | 675 | + /sys/power/tuxonice/swap/headerlocations for a new resume_block value. |
24613191 | 676 | + |
677 | + Once you've compiled and installed the kernel and adjusted your bootloader | |
678 | + configuration, you should only need to reboot for the most basic part | |
4e97e4e9 | 679 | + of TuxOnIce to be ready. |
24613191 | 680 | + |
4e97e4e9 | 681 | + If you only compile in the swap allocator, or only compile in the file |
682 | + allocator, you don't need to add the "swap:" part of the resume= | |
7f9d2ee0 | 683 | + parameters above. resume=/dev/hda2:0x242d will work just as well. If you |
684 | + have compiled both and your storage is on swap, you can also use this | |
685 | + format (the swap allocator is the default allocator). | |
686 | + | |
687 | + When compiling your kernel, one of the options in the 'Power Management | |
688 | + Support' menu, just above the 'Enhanced Hibernation (TuxOnIce)' entry is | |
689 | + called 'Default resume partition'. This can be used to set a default value | |
690 | + for the resume= parameter. | |
24613191 | 691 | + |
692 | + d. The hibernate script. | |
693 | + | |
694 | + Since the driver model in 2.6 kernels is still being developed, you may need | |
7f9d2ee0 | 695 | + to do more than just configure TuxOnIce. Users of TuxOnIce usually start the |
696 | + process via a script which prepares for the hibernation cycle, tells the | |
697 | + kernel to do its stuff and then restore things afterwards. This script might | |
698 | + involve: | |
24613191 | 699 | + |
700 | + - Switching to a text console and back if X doesn't like the video card | |
701 | + status on resume. | |
7f9d2ee0 | 702 | + - Un/reloading drivers that don't play well with hibernation. |
24613191 | 703 | + |
704 | + Note that you might not be able to unload some drivers if there are | |
705 | + processes using them. You might have to kill off processes that hold | |
706 | + devices open. Hint: if your X server accesses an USB mouse, doing a | |
707 | + 'chvt' to a text console releases the device and you can unload the | |
708 | + module. | |
709 | + | |
4e97e4e9 | 710 | + Check out the latest script (available on tuxonice.net). |
7f9d2ee0 | 711 | + |
712 | + e. The userspace user interface. | |
713 | + | |
714 | + TuxOnIce has very limited support for displaying status if you only apply | |
715 | + the kernel patch - it can printk messages, but that is all. In addition, | |
716 | + some of the functions mentioned in this document (such as cancelling a cycle | |
717 | + or performing interactive debugging) are unavailable. To utilise these | |
718 | + functions, or simply get a nice display, you need the 'userui' component. | |
719 | + Userui comes in three flavours, usplash, fbsplash and text. Text should | |
720 | + work on any console. Usplash and fbsplash require the appropriate | |
721 | + (distro specific?) support. | |
722 | + | |
723 | + To utilise a userui, TuxOnIce just needs to be told where to find the | |
724 | + userspace binary: | |
725 | + | |
726 | + echo "/usr/local/sbin/tuxoniceui_fbsplash" > /sys/power/tuxonice/user_interface/program | |
727 | + | |
728 | + The hibernate script can do this for you, and a default value for this | |
729 | + setting can be configured when compiling the kernel. This path is also | |
730 | + stored in the image header, so if you have an initrd or initramfs, you can | |
731 | + use the userui during the first part of resuming (prior to the atomic | |
732 | + restore) by putting the binary in the same path in your initrd/ramfs. | |
733 | + Alternatively, you can put it in a different location and do an echo | |
734 | + similar to the above prior to the echo > do_resume. The value saved in the | |
735 | + image header will then be ignored. | |
736 | + | |
24613191 | 737 | +4. Why not just use the version already in the kernel? |
738 | + | |
7f9d2ee0 | 739 | + The version in the vanilla kernel has a number of drawbacks. The most |
740 | + serious of these are: | |
f3e0dcc9 | 741 | + - it has a maximum image size of 1/2 total memory; |
24613191 | 742 | + - it doesn't allocate storage until after it has snapshotted memory. |
7f9d2ee0 | 743 | + This means that you can't be sure hibernating will work until you |
f3e0dcc9 PS |
744 | + see it start to write the image; |
745 | + - it does not allow you to press escape to cancel a cycle; | |
746 | + - it does not allow you to press escape to cancel resuming; | |
24613191 | 747 | + - it does not allow you to automatically swapon a file when |
f3e0dcc9 PS |
748 | + starting a cycle; |
749 | + - it does not allow you to use multiple swap partitions or files; | |
750 | + - it does not allow you to use ordinary files; | |
24613191 | 751 | + - it just invalidates an image and continues to boot if you |
f3e0dcc9 PS |
752 | + accidentally boot the wrong kernel after hibernating; |
753 | + - it doesn't support any sort of nice display while hibernating; | |
24613191 | 754 | + - it is moving toward requiring that you have an initrd/initramfs |
755 | + to ever have a hope of resuming (uswsusp). While uswsusp will | |
7f9d2ee0 | 756 | + address some of the concerns above, it won't address all of them, |
f3e0dcc9 PS |
757 | + and will be more complicated to get set up; |
758 | + - it doesn't have support for suspend-to-both (write a hibernation | |
759 | + image, then suspend to ram; I think this is known as ReadySafe | |
760 | + under M$). | |
24613191 | 761 | + |
762 | +5. How do you use it? | |
763 | + | |
7f9d2ee0 | 764 | + A hibernation cycle can be started directly by doing: |
24613191 | 765 | + |
ad8f4a28 | 766 | + echo > /sys/power/tuxonice/do_hibernate |
24613191 | 767 | + |
768 | + In practice, though, you'll probably want to use the hibernate script | |
769 | + to unload modules, configure the kernel the way you like it and so on. | |
770 | + In that case, you'd do (as root): | |
771 | + | |
772 | + hibernate | |
773 | + | |
774 | + See the hibernate script's man page for more details on the options it | |
775 | + takes. | |
776 | + | |
7f9d2ee0 | 777 | + If you're using the text or splash user interface modules, one feature of |
778 | + TuxOnIce that you might find useful is that you can press Escape at any time | |
779 | + during hibernating, and the process will be aborted. | |
780 | + | |
781 | + Due to the way hibernation works, this means you'll have your system back and | |
24613191 | 782 | + perfectly usable almost instantly. The only exception is when it's at the |
7f9d2ee0 | 783 | + very end of writing the image. Then it will need to reload a small (usually |
784 | + 4-50MBs, depending upon the image characteristics) portion first. | |
24613191 | 785 | + |
7f9d2ee0 | 786 | + Likewise, when resuming, you can press escape and resuming will be aborted. |
787 | + The computer will then powerdown again according to settings at that time for | |
788 | + the powerdown method or rebooting. | |
789 | + | |
790 | + You can change the settings for powering down while the image is being | |
791 | + written by pressing 'R' to toggle rebooting and 'O' to toggle between | |
792 | + suspending to ram and powering down completely). | |
793 | + | |
4e97e4e9 | 794 | + If you run into problems with resuming, adding the "noresume" option to |
24613191 | 795 | + the kernel command line will let you skip the resume step and recover your |
7f9d2ee0 | 796 | + system. This option shouldn't normally be needed, because TuxOnIce modifies |
797 | + the image header prior to the atomic restore, and will thus prompt you | |
798 | + if it detects that you've tried to resume an image before (this flag is | |
799 | + removed if you press Escape to cancel a resume, so you won't be prompted | |
800 | + then). | |
801 | + | |
802 | + Recent kernels (2.6.24 onwards) add support for resuming from a different | |
803 | + kernel to the one that was hibernated (thanks to Rafael for his work on | |
804 | + this - I've just embraced and enhanced the support for TuxOnIce). This | |
805 | + should further reduce the need for you to use the noresume option. | |
24613191 | 806 | + |
4e97e4e9 | 807 | +6. What do all those entries in /sys/power/tuxonice do? |
24613191 | 808 | + |
4e97e4e9 | 809 | + /sys/power/tuxonice is the directory which contains files you can use to |
810 | + tune and configure TuxOnIce to your liking. The exact contents of | |
811 | + the directory will depend upon the version of TuxOnIce you're | |
24613191 | 812 | + running and the options you selected at compile time. In the following |
813 | + descriptions, names in brackets refer to compile time options. | |
7f9d2ee0 | 814 | + (Note that they're all dependant upon you having selected CONFIG_TUXONICE |
24613191 | 815 | + in the first place!). |
816 | + | |
7f9d2ee0 | 817 | + Since the values of these settings can open potential security risks, the |
818 | + writeable ones are accessible only to the root user. You may want to | |
819 | + configure sudo to allow you to invoke your hibernate script as an ordinary | |
820 | + user. | |
24613191 | 821 | + |
822 | + - checksum/enabled | |
823 | + | |
824 | + Use cryptoapi hashing routines to verify that Pageset2 pages don't change | |
825 | + while we're saving the first part of the image, and to get any pages that | |
826 | + do change resaved in the atomic copy. This should normally not be needed, | |
827 | + but if you're seeing issues, please enable this. If your issues stop you | |
7f9d2ee0 | 828 | + being able to resume, enable this option, hibernate and cancel the cycle |
24613191 | 829 | + after the atomic copy is done. If the debugging info shows a non-zero |
830 | + number of pages resaved, please report this to Nigel. | |
831 | + | |
832 | + - compression/algorithm | |
833 | + | |
834 | + Set the cryptoapi algorithm used for compressing the image. | |
835 | + | |
836 | + - compression/expected_compression | |
837 | + | |
7f9d2ee0 | 838 | + These values allow you to set an expected compression ratio, which TuxOnice |
839 | + will use in calculating whether it meets constraints on the image size. If | |
840 | + this expected compression ratio is not attained, the hibernation cycle will | |
24613191 | 841 | + abort, so it is wise to allow some spare. You can see what compression |
7f9d2ee0 | 842 | + ratio is achieved in the logs after hibernating. |
24613191 | 843 | + |
844 | + - debug_info: | |
845 | + | |
846 | + This file returns information about your configuration that may be helpful | |
7f9d2ee0 | 847 | + in diagnosing problems with hibernating. |
24613191 | 848 | + |
7f9d2ee0 | 849 | + - do_hibernate: |
24613191 | 850 | + |
4e97e4e9 | 851 | + When anything is written to this file, the kernel side of TuxOnIce will |
24613191 | 852 | + begin to attempt to write an image to disk and power down. You'll normally |
853 | + want to run the hibernate script instead, to get modules unloaded first. | |
854 | + | |
7f9d2ee0 | 855 | + - do_resume: |
24613191 | 856 | + |
7f9d2ee0 | 857 | + When anything is written to this file TuxOnIce will attempt to read and |
858 | + restore an image. If there is no image, it will return almost immediately. | |
859 | + If an image exists, the echo > will never return. Instead, the original | |
860 | + kernel context will be restored and the original echo > do_hibernate will | |
861 | + return. | |
24613191 | 862 | + |
863 | + - */enabled | |
864 | + | |
7f9d2ee0 | 865 | + These option can be used to temporarily disable various parts of TuxOnIce. |
24613191 | 866 | + |
24613191 | 867 | + - extra_pages_allowance |
868 | + | |
4e97e4e9 | 869 | + When TuxOnIce does its atomic copy, it calls the driver model suspend |
24613191 | 870 | + and resume methods. If you have DRI enabled with a driver such as fglrx, |
871 | + this can result in the driver allocating a substantial amount of memory | |
7f9d2ee0 | 872 | + for storing its state. Extra_pages_allowance tells TuxOnIce how much |
24613191 | 873 | + extra memory it should ensure is available for those allocations. If |
7f9d2ee0 | 874 | + your attempts at hibernating end with a message in dmesg indicating that |
24613191 | 875 | + insufficient extra pages were allowed, you need to increase this value. |
876 | + | |
4e97e4e9 | 877 | + - file/target: |
24613191 | 878 | + |
7f9d2ee0 | 879 | + Read this value to get the current setting. Write to it to point TuxOnice |
880 | + at a new storage location for the file allocator. See section 3.b.ii above | |
881 | + for details of how to set up the file allocator. | |
24613191 | 882 | + |
883 | + - freezer_test | |
884 | + | |
7f9d2ee0 | 885 | + This entry can be used to get TuxOnIce to just test the freezer and prepare |
886 | + an image without actually doing a hibernation cycle. It is useful for | |
887 | + diagnosing freezing and image preparation issues. | |
24613191 | 888 | + |
889 | + - image_exists: | |
890 | + | |
891 | + Can be used in a script to determine whether a valid image exists at the | |
4e97e4e9 | 892 | + location currently pointed to by resume=. Returns up to three lines. |
24613191 | 893 | + The first is whether an image exists (-1 for unsure, otherwise 0 or 1). |
894 | + If an image eixsts, additional lines will return the machine and version. | |
895 | + Echoing anything to this entry removes any current image. | |
896 | + | |
897 | + - image_size_limit: | |
898 | + | |
7f9d2ee0 | 899 | + The maximum size of hibernation image written to disk, measured in megabytes |
24613191 | 900 | + (1024*1024). |
901 | + | |
24613191 | 902 | + - last_result: |
903 | + | |
7f9d2ee0 | 904 | + The result of the last hibernation cycle, as defined in |
24613191 | 905 | + include/linux/suspend-debug.h with the values SUSPEND_ABORTED to |
906 | + SUSPEND_KEPT_IMAGE. This is a bitmask. | |
907 | + | |
908 | + - log_everything (CONFIG_PM_DEBUG): | |
909 | + | |
910 | + Setting this option results in all messages printed being logged. Normally, | |
911 | + only a subset are logged, so as to not slow the process and not clutter the | |
912 | + logs. Useful for debugging. It can be toggled during a cycle by pressing | |
913 | + 'L'. | |
914 | + | |
915 | + - pause_between_steps (CONFIG_PM_DEBUG): | |
916 | + | |
4e97e4e9 | 917 | + This option is used during debugging, to make TuxOnIce pause between |
24613191 | 918 | + each step of the process. It is ignored when the nice display is on. |
919 | + | |
920 | + - powerdown_method: | |
921 | + | |
4e97e4e9 | 922 | + Used to select a method by which TuxOnIce should powerdown after writing the |
24613191 | 923 | + image. Currently: |
924 | + | |
925 | + 0: Don't use ACPI to power off. | |
926 | + 3: Attempt to enter Suspend-to-ram. | |
927 | + 4: Attempt to enter ACPI S4 mode. | |
928 | + 5: Attempt to power down via ACPI S5 mode. | |
929 | + | |
930 | + Note that these options are highly dependant upon your hardware & software: | |
931 | + | |
7f9d2ee0 | 932 | + 3: When succesful, your machine suspends to ram instead of powering off. |
24613191 | 933 | + The advantage of using this mode is that it doesn't matter whether your |
934 | + battery has enough charge to make it through to your next resume. If it | |
935 | + lasts, you will simply resume from suspend to ram (and the image on disk | |
936 | + will be discarded). If the battery runs out, you will resume from disk | |
937 | + instead. The disadvantage is that it takes longer than a normal | |
938 | + suspend-to-ram to enter the state, since the suspend-to-disk image needs | |
939 | + to be written first. | |
940 | + 4/5: When successful, your machine will be off and comsume (almost) no power. | |
941 | + But it might still react to some external events like opening the lid or | |
942 | + trafic on a network or usb device. For the bios, resume is then the same | |
943 | + as warm boot, similar to a situation where you used the command `reboot' | |
944 | + to reboot your machine. If your machine has problems on warm boot or if | |
945 | + you want to protect your machine with the bios password, this is probably | |
946 | + not the right choice. Mode 4 may be necessary on some machines where ACPI | |
947 | + wake up methods need to be run to properly reinitialise hardware after a | |
7f9d2ee0 | 948 | + hibernation cycle. |
24613191 | 949 | + 0: Switch the machine completely off. The only possible wakeup is the power |
950 | + button. For the bios, resume is then the same as a cold boot, in | |
951 | + particular you would have to provide your bios boot password if your | |
952 | + machine uses that feature for booting. | |
953 | + | |
954 | + - progressbar_granularity_limit: | |
955 | + | |
956 | + This option can be used to limit the granularity of the progress bar | |
957 | + displayed with a bootsplash screen. The value is the maximum number of | |
958 | + steps. That is, 10 will make the progress bar jump in 10% increments. | |
959 | + | |
960 | + - reboot: | |
961 | + | |
4e97e4e9 | 962 | + This option causes TuxOnIce to reboot rather than powering down |
24613191 | 963 | + at the end of saving an image. It can be toggled during a cycle by pressing |
964 | + 'R'. | |
965 | + | |
966 | + - resume_commandline: | |
967 | + | |
968 | + This entry can be read after resuming to see the commandline that was used | |
969 | + when resuming began. You might use this to set up two bootloader entries | |
970 | + that are the same apart from the fact that one includes a extra append= | |
971 | + argument "at_work=1". You could then grep resume_commandline in your | |
972 | + post-resume scripts and configure networking (for example) differently | |
973 | + depending upon whether you're at home or work. resume_commandline can be | |
974 | + set to arbitrary text if you wish to remove sensitive contents. | |
975 | + | |
4e97e4e9 | 976 | + - swap/swapfilename: |
24613191 | 977 | + |
978 | + This entry is used to specify the swapfile or partition that | |
4e97e4e9 | 979 | + TuxOnIce will attempt to swapon/swapoff automatically. Thus, if |
24613191 | 980 | + I normally use /dev/hda1 for swap, and want to use /dev/hda2 for specifically |
7f9d2ee0 | 981 | + for my hibernation image, I would |
24613191 | 982 | + |
4e97e4e9 | 983 | + echo /dev/hda2 > /sys/power/tuxonice/swap/swapfile |
24613191 | 984 | + |
985 | + /dev/hda2 would then be automatically swapon'd and swapoff'd. Note that the | |
986 | + swapon and swapoff occur while other processes are frozen (including kswapd) | |
987 | + so this swap file will not be used up when attempting to free memory. The | |
988 | + parition/file is also given the highest priority, so other swapfiles/partitions | |
989 | + will only be used to save the image when this one is filled. | |
990 | + | |
991 | + The value of this file is used by headerlocations along with any currently | |
992 | + activated swapfiles/partitions. | |
993 | + | |
4e97e4e9 | 994 | + - swap/headerlocations: |
24613191 | 995 | + |
4e97e4e9 | 996 | + This option tells you the resume= options to use for swap devices you |
24613191 | 997 | + currently have activated. It is particularly useful when you only want to |
998 | + use a swap file to store your image. See above for further details. | |
999 | + | |
24613191 | 1000 | + - userui_program |
1001 | + | |
7f9d2ee0 | 1002 | + This entry is used to tell TuxOnice what userspace program to use for |
1003 | + providing a user interface while hibernating. The program uses a netlink | |
24613191 | 1004 | + socket to pass messages back and forward to the kernel, allowing all of the |
1005 | + functions formerly implemented in the kernel user interface components. | |
1006 | + | |
1007 | + - user_interface/debug_sections (CONFIG_PM_DEBUG): | |
1008 | + | |
1009 | + This value, together with the console log level, controls what debugging | |
1010 | + information is displayed. The console log level determines the level of | |
1011 | + detail, and this value determines what detail is displayed. This value is | |
1012 | + a bit vector, and the meaning of the bits can be found in the kernel tree | |
4e97e4e9 | 1013 | + in include/linux/tuxonice.h. It can be overridden using the kernel's |
24613191 | 1014 | + command line option suspend_dbg. |
1015 | + | |
1016 | + - user_interface/default_console_level (CONFIG_PM_DEBUG): | |
1017 | + | |
1018 | + This determines the value of the console log level at the start of a | |
7f9d2ee0 | 1019 | + hibernation cycle. If debugging is compiled in, the console log level can be |
24613191 | 1020 | + changed during a cycle by pressing the digit keys. Meanings are: |
1021 | + | |
1022 | + 0: Nice display. | |
1023 | + 1: Nice display plus numerical progress. | |
1024 | + 2: Errors only. | |
1025 | + 3: Low level debugging info. | |
1026 | + 4: Medium level debugging info. | |
1027 | + 5: High level debugging info. | |
1028 | + 6: Verbose debugging info. | |
1029 | + | |
1030 | + - user_interface/enable_escape: | |
1031 | + | |
7f9d2ee0 | 1032 | + Setting this to "1" will enable you abort a hibernation cycle or resuming by |
24613191 | 1033 | + pressing escape, "0" (default) disables this feature. Note that enabling |
7f9d2ee0 | 1034 | + this option means that you cannot initiate a hibernation cycle and then walk |
1035 | +away | |
24613191 | 1036 | + from your computer, expecting it to be secure. With feature disabled, |
7f9d2ee0 | 1037 | + you can validly have this expectation once TuxOnice begins to write the |
1038 | + image to disk. (Prior to this point, it is possible that TuxOnice might | |
24613191 | 1039 | + about because of failure to freeze all processes or because constraints |
1040 | + on its ability to save the image are not met). | |
1041 | + | |
1042 | + - version: | |
1043 | + | |
7f9d2ee0 | 1044 | + The version of TuxOnIce you have compiled into the currently running kernel. |
24613191 | 1045 | + |
1046 | +7. How do you get support? | |
1047 | + | |
4e97e4e9 | 1048 | + Glad you asked. TuxOnIce is being actively maintained and supported |
24613191 | 1049 | + by Nigel (the guy doing most of the kernel coding at the moment), Bernard |
1050 | + (who maintains the hibernate script and userspace user interface components) | |
1051 | + and its users. | |
1052 | + | |
1053 | + Resources availble include HowTos, FAQs and a Wiki, all available via | |
4e97e4e9 | 1054 | + tuxonice.net. You can find the mailing lists there. |
24613191 | 1055 | + |
1056 | +8. I think I've found a bug. What should I do? | |
1057 | + | |
4e97e4e9 | 1058 | + By far and a way, the most common problems people have with TuxOnIce |
24613191 | 1059 | + related to drivers not having adequate power management support. In this |
4e97e4e9 | 1060 | + case, it is not a bug with TuxOnIce, but we can still help you. As we |
24613191 | 1061 | + mentioned above, such issues can usually be worked around by building the |
7f9d2ee0 | 1062 | + functionality as modules and unloading them while hibernating. Please visit |
24613191 | 1063 | + the Wiki for up-to-date lists of known issues and work arounds. |
1064 | + | |
1065 | + If this information doesn't help, try running: | |
1066 | + | |
1067 | + hibernate --bug-report | |
1068 | + | |
1069 | + ..and sending the output to the users mailing list. | |
1070 | + | |
1071 | + Good information on how to provide us with useful information from an | |
1072 | + oops is found in the file REPORTING-BUGS, in the top level directory | |
1073 | + of the kernel tree. If you get an oops, please especially note the | |
1074 | + information about running what is printed on the screen through ksymoops. | |
1075 | + The raw information is useless. | |
1076 | + | |
1077 | +9. When will XXX be supported? | |
1078 | + | |
4e97e4e9 | 1079 | + If there's a feature missing from TuxOnIce that you'd like, feel free to |
24613191 | 1080 | + ask. We try to be obliging, within reason. |
1081 | + | |
1082 | + Patches are welcome. Please send to the list. | |
1083 | + | |
1084 | +10. How does it work? | |
1085 | + | |
4e97e4e9 | 1086 | + TuxOnIce does its work in a number of steps. |
24613191 | 1087 | + |
1088 | + a. Freezing system activity. | |
1089 | + | |
7f9d2ee0 | 1090 | + The first main stage in hibernating is to stop all other activity. This is |
24613191 | 1091 | + achieved in stages. Processes are considered in fours groups, which we will |
1092 | + describe in reverse order for clarity's sake: Threads with the PF_NOFREEZE | |
1093 | + flag, kernel threads without this flag, userspace processes with the | |
1094 | + PF_SYNCTHREAD flag and all other processes. The first set (PF_NOFREEZE) are | |
7f9d2ee0 | 1095 | + untouched by the refrigerator code. They are allowed to run during hibernating |
24613191 | 1096 | + and resuming, and are used to support user interaction, storage access or the |
7f9d2ee0 | 1097 | + like. Other kernel threads (those unneeded while hibernating) are frozen last. |
24613191 | 1098 | + This leaves us with userspace processes that need to be frozen. When a |
1099 | + process enters one of the *_sync system calls, we set a PF_SYNCTHREAD flag on | |
1100 | + that process for the duration of that call. Processes that have this flag are | |
1101 | + frozen after processes without it, so that we can seek to ensure that dirty | |
1102 | + data is synced to disk as quickly as possible in a situation where other | |
1103 | + processes may be submitting writes at the same time. Freezing the processes | |
1104 | + that are submitting data stops new I/O from being submitted. Syncthreads can | |
1105 | + then cleanly finish their work. So the order is: | |
1106 | + | |
1107 | + - Userspace processes without PF_SYNCTHREAD or PF_NOFREEZE; | |
1108 | + - Userspace processes with PF_SYNCTHREAD (they won't have NOFREEZE); | |
1109 | + - Kernel processes without PF_NOFREEZE. | |
1110 | + | |
1111 | + b. Eating memory. | |
1112 | + | |
7f9d2ee0 | 1113 | + For a successful hibernation cycle, you need to have enough disk space to store the |
4e97e4e9 | 1114 | + image and enough memory for the various limitations of TuxOnIce's |
24613191 | 1115 | + algorithm. You can also specify a maximum image size. In order to attain |
4e97e4e9 | 1116 | + to those constraints, TuxOnIce may 'eat' memory. If, after freezing |
1117 | + processes, the constraints aren't met, TuxOnIce will thaw all the | |
24613191 | 1118 | + other processes and begin to eat memory until its calculations indicate |
1119 | + the constraints are met. It will then freeze processes again and recheck | |
1120 | + its calculations. | |
1121 | + | |
1122 | + c. Allocation of storage. | |
1123 | + | |
4e97e4e9 | 1124 | + Next, TuxOnIce allocates the storage that will be used to save |
24613191 | 1125 | + the image. |
1126 | + | |
4e97e4e9 | 1127 | + The core of TuxOnIce knows nothing about how or where pages are stored. We |
1128 | + therefore request the active allocator (remember you might have compiled in | |
24613191 | 1129 | + more than one!) to allocate enough storage for our expect image size. If |
1130 | + this request cannot be fulfilled, we eat more memory and try again. If it | |
1131 | + is fulfiled, we seek to allocate additional storage, just in case our | |
1132 | + expected compression ratio (if any) isn't achieved. This time, however, we | |
1133 | + just continue if we can't allocate enough storage. | |
1134 | + | |
4e97e4e9 | 1135 | + If these calls to our allocator change the characteristics of the image |
1136 | + such that we haven't allocated enough memory, we also loop. (The allocator | |
1137 | + may well need to allocate space for its storage information). | |
24613191 | 1138 | + |
1139 | + d. Write the first part of the image. | |
1140 | + | |
4e97e4e9 | 1141 | + TuxOnIce stores the image in two sets of pages called 'pagesets'. |
24613191 | 1142 | + Pageset 2 contains pages on the active and inactive lists; essentially |
1143 | + the page cache. Pageset 1 contains all other pages, including the kernel. | |
1144 | + We use two pagesets for one important reason: We need to make an atomic copy | |
1145 | + of the kernel to ensure consistency of the image. Without a second pageset, | |
1146 | + that would limit us to an image that was at most half the amount of memory | |
1147 | + available. Using two pagesets allows us to store a full image. Since pageset | |
1148 | + 2 pages won't be needed in saving pageset 1, we first save pageset 2 pages. | |
1149 | + We can then make our atomic copy of the remaining pages using both pageset 2 | |
1150 | + pages and any other pages that are free. While saving both pagesets, we are | |
1151 | + careful not to corrupt the image. Among other things, we use lowlevel block | |
1152 | + I/O routines that don't change the pagecache contents. | |
1153 | + | |
1154 | + The next step, then, is writing pageset 2. | |
1155 | + | |
1156 | + e. Suspending drivers and storing processor context. | |
1157 | + | |
4e97e4e9 | 1158 | + Having written pageset2, TuxOnIce calls the power management functions to |
7f9d2ee0 | 1159 | + notify drivers of the hibernation, and saves the processor state in preparation |
24613191 | 1160 | + for the atomic copy of memory we are about to make. |
1161 | + | |
1162 | + f. Atomic copy. | |
1163 | + | |
4e97e4e9 | 1164 | + At this stage, everything else but the TuxOnIce code is halted. Processes |
24613191 | 1165 | + are frozen or idling, drivers are quiesced and have stored (ideally and where |
1166 | + necessary) their configuration in memory we are about to atomically copy. | |
1167 | + In our lowlevel architecture specific code, we have saved the CPU state. | |
1168 | + We can therefore now do our atomic copy before resuming drivers etc. | |
1169 | + | |
1170 | + g. Save the atomic copy (pageset 1). | |
1171 | + | |
7f9d2ee0 | 1172 | + TuxOnice can then write the atomic copy of the remaining pages. Since we |
24613191 | 1173 | + have copied the pages into other locations, we can continue to use the |
1174 | + normal block I/O routines without fear of corruption our image. | |
1175 | + | |
7f9d2ee0 | 1176 | + f. Save the image header. |
24613191 | 1177 | + |
1178 | + Nearly there! We save our settings and other parameters needed for | |
7f9d2ee0 | 1179 | + reloading pageset 1 in an 'image header'. We also tell our allocator to |
24613191 | 1180 | + serialise its data at this stage, so that it can reread the image at resume |
4e97e4e9 | 1181 | + time. |
24613191 | 1182 | + |
1183 | + g. Set the image header. | |
1184 | + | |
4e97e4e9 | 1185 | + Finally, we edit the header at our resume= location. The signature is |
1186 | + changed by the allocator to reflect the fact that an image exists, and to | |
1187 | + point to the start of that data if necessary (swap allocator). | |
24613191 | 1188 | + |
1189 | + h. Power down. | |
1190 | + | |
1191 | + Or reboot if we're debugging and the appropriate option is selected. | |
1192 | + | |
1193 | + Whew! | |
1194 | + | |
1195 | + Reloading the image. | |
1196 | + -------------------- | |
1197 | + | |
1198 | + Reloading the image is essentially the reverse of all the above. We load | |
1199 | + our copy of pageset 1, being careful to choose locations that aren't going | |
1200 | + to be overwritten as we copy it back (We start very early in the boot | |
1201 | + process, so there are no other processes to quiesce here). We then copy | |
1202 | + pageset 1 back to its original location in memory and restore the process | |
1203 | + context. We are now running with the original kernel. Next, we reload the | |
4e97e4e9 | 1204 | + pageset 2 pages, free the memory and swap used by TuxOnIce, restore |
24613191 | 1205 | + the pageset header and restart processes. Sounds easy in comparison to |
7f9d2ee0 | 1206 | + hibernating, doesn't it! |
24613191 | 1207 | + |
4e97e4e9 | 1208 | + There is of course more to TuxOnIce than this, but this explanation |
24613191 | 1209 | + should be a good start. If there's interest, I'll write further |
1210 | + documentation on range pages and the low level I/O. | |
1211 | + | |
4e97e4e9 | 1212 | +11. Who wrote TuxOnIce? |
24613191 | 1213 | + |
1214 | + (Answer based on the writings of Florent Chabaud, credits in files and | |
1215 | + Nigel's limited knowledge; apologies to anyone missed out!) | |
1216 | + | |
4e97e4e9 | 1217 | + The main developers of TuxOnIce have been... |
24613191 | 1218 | + |
1219 | + Gabor Kuti | |
1220 | + Pavel Machek | |
1221 | + Florent Chabaud | |
1222 | + Bernard Blackham | |
1223 | + Nigel Cunningham | |
1224 | + | |
4e97e4e9 | 1225 | + Significant portions of swsusp, the code in the vanilla kernel which |
1226 | + TuxOnIce enhances, have been worked on by Rafael Wysocki. Thanks should | |
1227 | + also be expressed to him. | |
1228 | + | |
1229 | + The above mentioned developers have been aided in their efforts by a host | |
1230 | + of hundreds, if not thousands of testers and people who have submitted bug | |
1231 | + fixes & suggestions. Of special note are the efforts of Michael Frank, who | |
7f9d2ee0 | 1232 | + had his computers repetitively hibernate and resume for literally tens of |
4e97e4e9 | 1233 | + thousands of cycles and developed scripts to stress the system and test |
1234 | + TuxOnIce far beyond the point most of us (Nigel included!) would consider | |
1235 | + testing. His efforts have contributed as much to TuxOnIce as any of the | |
1236 | + names above. | |
1237 | diff --git a/MAINTAINERS b/MAINTAINERS | |
1838f965 | 1238 | index ff24d01..251eb14 100644 |
4e97e4e9 | 1239 | --- a/MAINTAINERS |
1240 | +++ b/MAINTAINERS | |
1838f965 | 1241 | @@ -4099,6 +4099,13 @@ P: Maciej W. Rozycki |
4e97e4e9 | 1242 | M: macro@linux-mips.org |
24613191 | 1243 | S: Maintained |
1244 | ||
4e97e4e9 | 1245 | +TUXONICE (ENHANCED HIBERNATION) |
24613191 | 1246 | +P: Nigel Cunningham |
4e97e4e9 | 1247 | +M: nigel@tuxonice.net |
1248 | +L: suspend2-devel@tuxonice.net | |
1249 | +W: http://tuxonice.net | |
24613191 | 1250 | +S: Maintained |
1251 | + | |
4e97e4e9 | 1252 | U14-34F SCSI DRIVER |
1253 | P: Dario Ballabio | |
1254 | M: ballabio_dario@emc.com | |
1838f965 | 1255 | diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c |
1256 | index 2001abd..78c6a4c 100644 | |
1257 | --- a/arch/powerpc/mm/pgtable_32.c | |
1258 | +++ b/arch/powerpc/mm/pgtable_32.c | |
1259 | @@ -397,6 +397,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) | |
1260 | ||
1261 | change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0)); | |
1262 | } | |
1263 | +EXPORT_SYMBOL_GPL(kernel_map_pages); | |
1264 | #endif /* CONFIG_DEBUG_PAGEALLOC */ | |
1265 | ||
1266 | static int fixmaps; | |
1267 | diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c | |
1268 | index 724adfc..a270c9e 100644 | |
1269 | --- a/arch/x86/kernel/reboot.c | |
1270 | +++ b/arch/x86/kernel/reboot.c | |
1271 | @@ -502,6 +502,7 @@ void machine_restart(char *cmd) | |
1272 | { | |
1273 | machine_ops.restart(cmd); | |
1274 | } | |
1275 | +EXPORT_SYMBOL_GPL(machine_restart); | |
1276 | ||
1277 | void machine_halt(void) | |
1278 | { | |
1279 | diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c | |
1280 | index 43e2f84..5783f37 100644 | |
1281 | --- a/arch/x86/mm/pageattr.c | |
1282 | +++ b/arch/x86/mm/pageattr.c | |
1283 | @@ -1031,6 +1031,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) | |
1284 | */ | |
1285 | cpa_fill_pool(NULL); | |
1286 | } | |
1287 | +EXPORT_SYMBOL_GPL(kernel_map_pages); | |
1288 | ||
1289 | #ifdef CONFIG_DEBUG_FS | |
1290 | static int dpa_show(struct seq_file *m, void *v) | |
1291 | @@ -1084,7 +1085,7 @@ bool kernel_page_present(struct page *page) | |
1292 | pte = lookup_address((unsigned long)page_address(page), &level); | |
1293 | return (pte_val(*pte) & _PAGE_PRESENT); | |
1294 | } | |
1295 | - | |
1296 | +EXPORT_SYMBOL_GPL(kernel_page_present); | |
1297 | #endif /* CONFIG_HIBERNATION */ | |
1298 | ||
1299 | #endif /* CONFIG_DEBUG_PAGEALLOC */ | |
1300 | diff --git a/arch/x86/power/cpu_64.c b/arch/x86/power/cpu_64.c | |
1301 | index 66bdfb5..77aae90 100644 | |
1302 | --- a/arch/x86/power/cpu_64.c | |
1303 | +++ b/arch/x86/power/cpu_64.c | |
1304 | @@ -10,6 +10,7 @@ | |
1305 | ||
1306 | #include <linux/smp.h> | |
1307 | #include <linux/suspend.h> | |
1308 | +#include <linux/module.h> | |
1309 | #include <asm/proto.h> | |
1310 | #include <asm/page.h> | |
1311 | #include <asm/pgtable.h> | |
1312 | @@ -75,6 +76,7 @@ void save_processor_state(void) | |
1313 | { | |
1314 | __save_processor_state(&saved_context); | |
1315 | } | |
1316 | +EXPORT_SYMBOL_GPL(save_processor_state); | |
1317 | ||
1318 | static void do_fpu_end(void) | |
1319 | { | |
1320 | diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c | |
1321 | index 81197c6..ff7e534 100644 | |
1322 | --- a/arch/x86/power/hibernate_32.c | |
1323 | +++ b/arch/x86/power/hibernate_32.c | |
1324 | @@ -8,6 +8,7 @@ | |
1325 | ||
1326 | #include <linux/suspend.h> | |
1327 | #include <linux/bootmem.h> | |
1328 | +#include <linux/module.h> | |
1329 | ||
1330 | #include <asm/system.h> | |
1331 | #include <asm/page.h> | |
1332 | @@ -163,6 +164,7 @@ int swsusp_arch_resume(void) | |
1333 | restore_image(); | |
1334 | return 0; | |
1335 | } | |
1336 | +EXPORT_SYMBOL_GPL(swsusp_arch_resume); | |
1337 | ||
1338 | /* | |
1339 | * pfn_is_nosave - check if given pfn is in the 'nosave' section | |
1340 | diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c | |
1341 | index 6dd000d..b42e72a 100644 | |
1342 | --- a/arch/x86/power/hibernate_64.c | |
1343 | +++ b/arch/x86/power/hibernate_64.c | |
1344 | @@ -10,6 +10,7 @@ | |
1345 | ||
1346 | #include <linux/smp.h> | |
1347 | #include <linux/suspend.h> | |
1348 | +#include <linux/module.h> | |
1349 | #include <asm/proto.h> | |
1350 | #include <asm/page.h> | |
1351 | #include <asm/pgtable.h> | |
1352 | @@ -117,6 +118,7 @@ int swsusp_arch_resume(void) | |
1353 | restore_image(); | |
1354 | return 0; | |
1355 | } | |
1356 | +EXPORT_SYMBOL_GPL(swsusp_arch_resume); | |
1357 | ||
1358 | /* | |
1359 | * pfn_is_nosave - check if given pfn is in the 'nosave' section | |
1360 | @@ -167,3 +169,4 @@ int arch_hibernation_header_restore(void *addr) | |
1361 | restore_cr3 = rdr->cr3; | |
1362 | return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; | |
1363 | } | |
1364 | +EXPORT_SYMBOL_GPL(arch_hibernation_header_restore); | |
4e97e4e9 | 1365 | diff --git a/crypto/Kconfig b/crypto/Kconfig |
1838f965 | 1366 | index d831859..f71cb00 100644 |
4e97e4e9 | 1367 | --- a/crypto/Kconfig |
1368 | +++ b/crypto/Kconfig | |
1838f965 | 1369 | @@ -233,6 +233,14 @@ config CRYPTO_MD5 |
f3e0dcc9 | 1370 | help |
1838f965 | 1371 | MD5 message digest algorithm (RFC1321). |
24613191 | 1372 | |
1373 | +config CRYPTO_LZF | |
1374 | + tristate "LZF compression algorithm" | |
1375 | + default y | |
1376 | + select CRYPTO_ALGAPI | |
1377 | + help | |
4e97e4e9 | 1378 | + This is the LZF algorithm. It is especially useful for TuxOnIce, |
24613191 | 1379 | + because it achieves good compression quickly. |
1380 | + | |
1838f965 | 1381 | config CRYPTO_MICHAEL_MIC |
1382 | tristate "Michael MIC keyed digest algorithm" | |
1383 | select CRYPTO_ALGAPI | |
4e97e4e9 | 1384 | diff --git a/crypto/Makefile b/crypto/Makefile |
fea155ea | 1385 | index d4f3ed8..fe05a9e 100644 |
4e97e4e9 | 1386 | --- a/crypto/Makefile |
1387 | +++ b/crypto/Makefile | |
fea155ea | 1388 | @@ -67,6 +67,7 @@ obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o |
24613191 | 1389 | obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o |
1390 | obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o | |
1391 | obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o | |
1392 | +obj-$(CONFIG_CRYPTO_LZF) += lzf.o | |
ad8f4a28 | 1393 | obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o |
7f9d2ee0 | 1394 | obj-$(CONFIG_CRYPTO_LZO) += lzo.o |
24613191 | 1395 | |
4e97e4e9 | 1396 | diff --git a/crypto/lzf.c b/crypto/lzf.c |
1397 | new file mode 100644 | |
1838f965 | 1398 | index 0000000..ccaf83a |
4e97e4e9 | 1399 | --- /dev/null |
1400 | +++ b/crypto/lzf.c | |
7f9d2ee0 | 1401 | @@ -0,0 +1,326 @@ |
ad8f4a28 | 1402 | +/* |
24613191 | 1403 | + * Cryptoapi LZF compression module. |
1404 | + * | |
1838f965 | 1405 | + * Copyright (c) 2004-2008 Nigel Cunningham <nigel at tuxonice net> |
24613191 | 1406 | + * |
1407 | + * based on the deflate.c file: | |
ad8f4a28 | 1408 | + * |
24613191 | 1409 | + * Copyright (c) 2003 James Morris <jmorris@intercode.com.au> |
ad8f4a28 | 1410 | + * |
4e97e4e9 | 1411 | + * and upon the LZF compression module donated to the TuxOnIce project with |
24613191 | 1412 | + * the following copyright: |
1413 | + * | |
1414 | + * This program is free software; you can redistribute it and/or modify it | |
1415 | + * under the terms of the GNU General Public License as published by the Free | |
ad8f4a28 | 1416 | + * Software Foundation; either version 2 of the License, or (at your option) |
24613191 | 1417 | + * any later version. |
1418 | + * Copyright (c) 2000-2003 Marc Alexander Lehmann <pcg@goof.com> | |
ad8f4a28 | 1419 | + * |
24613191 | 1420 | + * Redistribution and use in source and binary forms, with or without modifica- |
1421 | + * tion, are permitted provided that the following conditions are met: | |
ad8f4a28 | 1422 | + * |
24613191 | 1423 | + * 1. Redistributions of source code must retain the above copyright notice, |
1424 | + * this list of conditions and the following disclaimer. | |
ad8f4a28 | 1425 | + * |
24613191 | 1426 | + * 2. Redistributions in binary form must reproduce the above copyright |
1427 | + * notice, this list of conditions and the following disclaimer in the | |
1428 | + * documentation and/or other materials provided with the distribution. | |
ad8f4a28 | 1429 | + * |
24613191 | 1430 | + * 3. The name of the author may not be used to endorse or promote products |
1431 | + * derived from this software without specific prior written permission. | |
ad8f4a28 | 1432 | + * |
24613191 | 1433 | + * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED |
1434 | + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER- | |
1435 | + * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO | |
1436 | + * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE- | |
1437 | + * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, | |
1438 | + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; | |
1439 | + * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, | |
1440 | + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH- | |
1441 | + * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED | |
1442 | + * OF THE POSSIBILITY OF SUCH DAMAGE. | |
1443 | + * | |
1444 | + * Alternatively, the contents of this file may be used under the terms of | |
1445 | + * the GNU General Public License version 2 (the "GPL"), in which case the | |
1446 | + * provisions of the GPL are applicable instead of the above. If you wish to | |
1447 | + * allow the use of your version of this file only under the terms of the | |
1448 | + * GPL and not to allow others to use your version of this file under the | |
1449 | + * BSD license, indicate your decision by deleting the provisions above and | |
1450 | + * replace them with the notice and other provisions required by the GPL. If | |
1451 | + * you do not delete the provisions above, a recipient may use your version | |
1452 | + * of this file under either the BSD or the GPL. | |
1453 | + */ | |
1454 | + | |
1455 | +#include <linux/kernel.h> | |
1456 | +#include <linux/module.h> | |
1457 | +#include <linux/init.h> | |
1458 | +#include <linux/module.h> | |
1459 | +#include <linux/crypto.h> | |
1460 | +#include <linux/err.h> | |
1461 | +#include <linux/vmalloc.h> | |
1838f965 | 1462 | +#include <linux/string.h> |
24613191 | 1463 | + |
1464 | +struct lzf_ctx { | |
1465 | + void *hbuf; | |
1466 | + unsigned int bufofs; | |
1467 | +}; | |
1468 | + | |
1469 | +/* | |
1470 | + * size of hashtable is (1 << hlog) * sizeof (char *) | |
1471 | + * decompression is independent of the hash table size | |
1472 | + * the difference between 15 and 14 is very small | |
1473 | + * for small blocks (and 14 is also faster). | |
1474 | + * For a low-memory configuration, use hlog == 13; | |
1475 | + * For best compression, use 15 or 16. | |
1476 | + */ | |
ad8f4a28 | 1477 | +static const int hlog = 13; |
24613191 | 1478 | + |
1479 | +/* | |
1480 | + * don't play with this unless you benchmark! | |
1481 | + * decompression is not dependent on the hash function | |
1482 | + * the hashing function might seem strange, just believe me | |
1483 | + * it works ;) | |
1484 | + */ | |
1485 | +static inline u16 first(const u8 *p) | |
1486 | +{ | |
1487 | + return ((p[0]) << 8) + p[1]; | |
1488 | +} | |
1489 | + | |
1490 | +static inline u16 next(u8 v, const u8 *p) | |
1491 | +{ | |
1492 | + return ((v) << 8) + p[2]; | |
1493 | +} | |
1494 | + | |
1495 | +static inline u32 idx(unsigned int h) | |
1496 | +{ | |
1497 | + return (((h ^ (h << 5)) >> (3*8 - hlog)) + h*3) & ((1 << hlog) - 1); | |
1498 | +} | |
1499 | + | |
1500 | +/* | |
1501 | + * IDX works because it is very similar to a multiplicative hash, e.g. | |
1502 | + * (h * 57321 >> (3*8 - hlog)) | |
1503 | + * the next one is also quite good, albeit slow ;) | |
1504 | + * (int)(cos(h & 0xffffff) * 1e6) | |
1505 | + */ | |
1506 | + | |
1507 | +static const int max_lit = (1 << 5); | |
1508 | +static const int max_off = (1 << 13); | |
1509 | +static const int max_ref = ((1 << 8) + (1 << 3)); | |
1510 | + | |
1511 | +/* | |
1512 | + * compressed format | |
1513 | + * | |
1514 | + * 000LLLLL <L+1> ; literal | |
1515 | + * LLLOOOOO oooooooo ; backref L | |
1516 | + * 111OOOOO LLLLLLLL oooooooo ; backref L+7 | |
1517 | + * | |
1518 | + */ | |
1519 | + | |
1520 | +static void lzf_compress_exit(struct crypto_tfm *tfm) | |
1521 | +{ | |
1522 | + struct lzf_ctx *ctx = crypto_tfm_ctx(tfm); | |
1523 | + | |
e8d0ad9d | 1524 | + if (!ctx->hbuf) |
1525 | + return; | |
1526 | + | |
1527 | + vfree(ctx->hbuf); | |
1528 | + ctx->hbuf = NULL; | |
24613191 | 1529 | +} |
1530 | + | |
1531 | +static int lzf_compress_init(struct crypto_tfm *tfm) | |
1532 | +{ | |
1533 | + struct lzf_ctx *ctx = crypto_tfm_ctx(tfm); | |
1534 | + | |
1535 | + /* Get LZF ready to go */ | |
1536 | + ctx->hbuf = vmalloc_32((1 << hlog) * sizeof(char *)); | |
e8d0ad9d | 1537 | + if (ctx->hbuf) |
1538 | + return 0; | |
1539 | + | |
1540 | + printk(KERN_WARNING "Failed to allocate %ld bytes for lzf workspace\n", | |
1541 | + (long) ((1 << hlog) * sizeof(char *))); | |
1542 | + return -ENOMEM; | |
24613191 | 1543 | +} |
1544 | + | |
1545 | +static int lzf_compress(struct crypto_tfm *tfm, const u8 *in_data, | |
1546 | + unsigned int in_len, u8 *out_data, unsigned int *out_len) | |
1547 | +{ | |
1548 | + struct lzf_ctx *ctx = crypto_tfm_ctx(tfm); | |
1549 | + const u8 **htab = ctx->hbuf; | |
1550 | + const u8 **hslot; | |
1551 | + const u8 *ip = in_data; | |
1552 | + u8 *op = out_data; | |
1553 | + const u8 *in_end = ip + in_len; | |
1554 | + u8 *out_end = op + *out_len - 3; | |
1555 | + const u8 *ref; | |
1556 | + | |
1557 | + unsigned int hval = first(ip); | |
1558 | + unsigned long off; | |
1559 | + int lit = 0; | |
1560 | + | |
1561 | + memset(htab, 0, sizeof(htab)); | |
1562 | + | |
1563 | + for (;;) { | |
1564 | + if (ip < in_end - 2) { | |
1565 | + hval = next(hval, ip); | |
1566 | + hslot = htab + idx(hval); | |
1567 | + ref = *hslot; | |
1568 | + *hslot = ip; | |
1569 | + | |
ad8f4a28 AM |
1570 | + off = ip - ref - 1; |
1571 | + if (off < max_off | |
24613191 | 1572 | + && ip + 4 < in_end && ref > in_data |
1573 | + && *(u16 *) ref == *(u16 *) ip && ref[2] == ip[2] | |
1574 | + ) { | |
1575 | + /* match found at *ref++ */ | |
1576 | + unsigned int len = 2; | |
1577 | + unsigned int maxlen = in_end - ip - len; | |
1578 | + maxlen = maxlen > max_ref ? max_ref : maxlen; | |
1579 | + | |
1838f965 | 1580 | + do { |
24613191 | 1581 | + len++; |
1838f965 | 1582 | + } while (len < maxlen && ref[len] == ip[len]); |
24613191 | 1583 | + |
1584 | + if (op + lit + 1 + 3 >= out_end) { | |
1585 | + *out_len = PAGE_SIZE; | |
1586 | + return 0; | |
1587 | + } | |
1588 | + | |
1589 | + if (lit) { | |
1590 | + *op++ = lit - 1; | |
1591 | + lit = -lit; | |
ad8f4a28 | 1592 | + do { |
24613191 | 1593 | + *op++ = ip[lit]; |
ad8f4a28 | 1594 | + } while (++lit); |
24613191 | 1595 | + } |
1596 | + | |
1597 | + len -= 2; | |
1598 | + ip++; | |
1599 | + | |
1600 | + if (len < 7) { | |
1601 | + *op++ = (off >> 8) + (len << 5); | |
1602 | + } else { | |
1603 | + *op++ = (off >> 8) + (7 << 5); | |
1604 | + *op++ = len - 7; | |
1605 | + } | |
1606 | + | |
1607 | + *op++ = off; | |
1608 | + | |
1609 | + ip += len; | |
1610 | + hval = first(ip); | |
1611 | + hval = next(hval, ip); | |
1612 | + htab[idx(hval)] = ip; | |
1613 | + ip++; | |
1614 | + continue; | |
1615 | + } | |
1616 | + } else if (ip == in_end) | |
1617 | + break; | |
1618 | + | |
1619 | + /* one more literal byte we must copy */ | |
1620 | + lit++; | |
1621 | + ip++; | |
1622 | + | |
1623 | + if (lit == max_lit) { | |
1624 | + if (op + 1 + max_lit >= out_end) { | |
1625 | + *out_len = PAGE_SIZE; | |
1626 | + return 0; | |
1627 | + } | |
1628 | + | |
1629 | + *op++ = max_lit - 1; | |
1630 | + memcpy(op, ip - max_lit, max_lit); | |
1631 | + op += max_lit; | |
1632 | + lit = 0; | |
1633 | + } | |
1634 | + } | |
1635 | + | |
1636 | + if (lit) { | |
1637 | + if (op + lit + 1 >= out_end) { | |
1638 | + *out_len = PAGE_SIZE; | |
1639 | + return 0; | |
1640 | + } | |
1641 | + | |
1642 | + *op++ = lit - 1; | |
1643 | + lit = -lit; | |
ad8f4a28 | 1644 | + do { |
24613191 | 1645 | + *op++ = ip[lit]; |
ad8f4a28 | 1646 | + } while (++lit); |
24613191 | 1647 | + } |
1648 | + | |
1649 | + *out_len = op - out_data; | |
1650 | + return 0; | |
1651 | +} | |
1652 | + | |
1653 | +static int lzf_decompress(struct crypto_tfm *tfm, const u8 *src, | |
1654 | + unsigned int slen, u8 *dst, unsigned int *dlen) | |
1655 | +{ | |
1656 | + u8 const *ip = src; | |
1657 | + u8 *op = dst; | |
1658 | + u8 const *const in_end = ip + slen; | |
1659 | + u8 *const out_end = op + *dlen; | |
1660 | + | |
e8d0ad9d | 1661 | + *dlen = PAGE_SIZE; |
24613191 | 1662 | + do { |
1663 | + unsigned int ctrl = *ip++; | |
1664 | + | |
ad8f4a28 AM |
1665 | + if (ctrl < (1 << 5)) { |
1666 | + /* literal run */ | |
24613191 | 1667 | + ctrl++; |
1668 | + | |
e8d0ad9d | 1669 | + if (op + ctrl > out_end) |
24613191 | 1670 | + return 0; |
24613191 | 1671 | + memcpy(op, ip, ctrl); |
1672 | + op += ctrl; | |
1673 | + ip += ctrl; | |
1674 | + } else { /* back reference */ | |
1675 | + | |
1676 | + unsigned int len = ctrl >> 5; | |
1677 | + | |
1678 | + u8 *ref = op - ((ctrl & 0x1f) << 8) - 1; | |
1679 | + | |
1680 | + if (len == 7) | |
1681 | + len += *ip++; | |
1682 | + | |
1683 | + ref -= *ip++; | |
e8d0ad9d | 1684 | + len += 2; |
24613191 | 1685 | + |
e8d0ad9d | 1686 | + if (op + len > out_end || ref < (u8 *) dst) |
24613191 | 1687 | + return 0; |
24613191 | 1688 | + |
ad8f4a28 | 1689 | + do { |
24613191 | 1690 | + *op++ = *ref++; |
ad8f4a28 | 1691 | + } while (--len); |
24613191 | 1692 | + } |
7f9d2ee0 | 1693 | + } while (op < out_end && ip < in_end); |
24613191 | 1694 | + |
1695 | + *dlen = op - (u8 *) dst; | |
1696 | + return 0; | |
1697 | +} | |
1698 | + | |
1699 | +static struct crypto_alg alg = { | |
1700 | + .cra_name = "lzf", | |
1701 | + .cra_flags = CRYPTO_ALG_TYPE_COMPRESS, | |
4e97e4e9 | 1702 | + .cra_ctxsize = sizeof(struct lzf_ctx), |
24613191 | 1703 | + .cra_module = THIS_MODULE, |
1704 | + .cra_list = LIST_HEAD_INIT(alg.cra_list), | |
1705 | + .cra_init = lzf_compress_init, | |
1706 | + .cra_exit = lzf_compress_exit, | |
1707 | + .cra_u = { .compress = { | |
1708 | + .coa_compress = lzf_compress, | |
1709 | + .coa_decompress = lzf_decompress } } | |
1710 | +}; | |
1711 | + | |
1712 | +static int __init init(void) | |
1713 | +{ | |
1714 | + return crypto_register_alg(&alg); | |
1715 | +} | |
1716 | + | |
1717 | +static void __exit fini(void) | |
1718 | +{ | |
1719 | + crypto_unregister_alg(&alg); | |
1720 | +} | |
1721 | + | |
1722 | +module_init(init); | |
1723 | +module_exit(fini); | |
1724 | + | |
1725 | +MODULE_LICENSE("GPL"); | |
1726 | +MODULE_DESCRIPTION("LZF Compression Algorithm"); | |
1727 | +MODULE_AUTHOR("Marc Alexander Lehmann & Nigel Cunningham"); | |
fea155ea | 1728 | diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c |
1838f965 | 1729 | index 273a944..aee84df 100644 |
fea155ea PS |
1730 | --- a/drivers/base/power/main.c |
1731 | +++ b/drivers/base/power/main.c | |
1732 | @@ -54,6 +54,7 @@ void device_pm_lock(void) | |
1733 | { | |
1734 | mutex_lock(&dpm_list_mtx); | |
1735 | } | |
1838f965 | 1736 | +EXPORT_SYMBOL_GPL(device_pm_lock); |
fea155ea PS |
1737 | |
1738 | /** | |
1739 | * device_pm_unlock - unlock the list of active devices used by the PM core | |
1740 | @@ -62,6 +63,7 @@ void device_pm_unlock(void) | |
1741 | { | |
1742 | mutex_unlock(&dpm_list_mtx); | |
1743 | } | |
1838f965 | 1744 | +EXPORT_SYMBOL_GPL(device_pm_unlock); |
fea155ea PS |
1745 | |
1746 | /** | |
1747 | * device_pm_add - add a device to the list of active devices | |
1838f965 | 1748 | diff --git a/drivers/char/vt.c b/drivers/char/vt.c |
1749 | index d429499..9603d96 100644 | |
1750 | --- a/drivers/char/vt.c | |
1751 | +++ b/drivers/char/vt.c | |
1752 | @@ -187,6 +187,7 @@ int fg_console; | |
1753 | int last_console; | |
1754 | int want_console = -1; | |
1755 | int kmsg_redirect; | |
1756 | +EXPORT_SYMBOL_GPL(kmsg_redirect); | |
1757 | ||
1758 | /* | |
1759 | * For each existing display, we have a pointer to console currently visible | |
4e97e4e9 | 1760 | diff --git a/drivers/md/md.c b/drivers/md/md.c |
1838f965 | 1761 | index fe6eccd..3918848 100644 |
4e97e4e9 | 1762 | --- a/drivers/md/md.c |
1763 | +++ b/drivers/md/md.c | |
1838f965 | 1764 | @@ -5593,7 +5593,6 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok) |
1765 | } | |
1766 | } | |
1767 | ||
1768 | - | |
1769 | /* md_write_start(mddev, bi) | |
1770 | * If we need to update some array metadata (e.g. 'active' flag | |
1771 | * in superblock) before writing, schedule a superblock update | |
1772 | @@ -5738,6 +5737,9 @@ void md_do_sync(mddev_t *mddev) | |
1773 | mddev->curr_resync = 2; | |
1774 | ||
1775 | try_again: | |
1776 | + while (freezer_is_on()) | |
1777 | + yield(); | |
1778 | + | |
1779 | if (kthread_should_stop()) { | |
1780 | set_bit(MD_RECOVERY_INTR, &mddev->recovery); | |
1781 | goto skip; | |
1782 | @@ -5759,6 +5761,10 @@ void md_do_sync(mddev_t *mddev) | |
1783 | * time 'round when curr_resync == 2 | |
1784 | */ | |
1785 | continue; | |
1786 | + | |
1787 | + while (freezer_is_on()) | |
1788 | + yield(); | |
1789 | + | |
1790 | /* We need to wait 'interruptible' so as not to | |
1791 | * contribute to the load average, and not to | |
1792 | * be caught by 'softlockup' | |
1793 | @@ -5771,6 +5777,7 @@ void md_do_sync(mddev_t *mddev) | |
1794 | " share one or more physical units)\n", | |
1795 | desc, mdname(mddev), mdname(mddev2)); | |
1796 | mddev_put(mddev2); | |
1797 | + try_to_freeze(); | |
1798 | if (signal_pending(current)) | |
1799 | flush_signals(current); | |
1800 | schedule(); | |
1801 | @@ -5854,6 +5861,10 @@ void md_do_sync(mddev_t *mddev) | |
1802 | mddev->resync_max > j | |
1803 | || kthread_should_stop()); | |
1804 | } | |
1805 | + | |
1806 | + while (freezer_is_on()) | |
1807 | + yield(); | |
1808 | + | |
1809 | if (kthread_should_stop()) | |
1810 | goto interrupted; | |
1811 | sectors = mddev->pers->sync_request(mddev, j, &skipped, | |
1812 | @@ -5897,6 +5908,9 @@ void md_do_sync(mddev_t *mddev) | |
e8d0ad9d | 1813 | last_mark = next; |
1814 | } | |
1815 | ||
ad8f4a28 | 1816 | + while (freezer_is_on()) |
e8d0ad9d | 1817 | + yield(); |
1838f965 | 1818 | + |
e8d0ad9d | 1819 | |
7f9d2ee0 | 1820 | if (kthread_should_stop()) |
1821 | goto interrupted; | |
4e97e4e9 | 1822 | diff --git a/fs/buffer.c b/fs/buffer.c |
1838f965 | 1823 | index ac78d4c..7ae191b 100644 |
4e97e4e9 | 1824 | --- a/fs/buffer.c |
1825 | +++ b/fs/buffer.c | |
1838f965 | 1826 | @@ -247,6 +247,93 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) |
4e97e4e9 | 1827 | } |
1828 | EXPORT_SYMBOL(thaw_bdev); | |
24613191 | 1829 | |
1838f965 | 1830 | +#ifdef CONFIG_FS_FREEZER_DEBUG |
f3e0dcc9 PS |
1831 | +#define FS_PRINTK(fmt, args...) printk(fmt, ## args) |
1832 | +#else | |
1833 | +#define FS_PRINTK(fmt, args...) | |
1834 | +#endif | |
1835 | + | |
ad8f4a28 AM |
1836 | +/* #define DEBUG_FS_FREEZING */ |
1837 | + | |
4e97e4e9 | 1838 | +/** |
1839 | + * freeze_filesystems - lock all filesystems and force them into a consistent | |
1840 | + * state | |
1838f965 | 1841 | + * @which: What combination of fuse & non-fuse to freeze. |
4e97e4e9 | 1842 | + */ |
ad8f4a28 | 1843 | +void freeze_filesystems(int which) |
4e97e4e9 | 1844 | +{ |
1845 | + struct super_block *sb; | |
24613191 | 1846 | + |
4e97e4e9 | 1847 | + lockdep_off(); |
1848 | + | |
1849 | + /* | |
1850 | + * Freeze in reverse order so filesystems dependant upon others are | |
1851 | + * frozen in the right order (eg. loopback on ext3). | |
1852 | + */ | |
1853 | + list_for_each_entry_reverse(sb, &super_blocks, s_list) { | |
f3e0dcc9 | 1854 | + FS_PRINTK(KERN_INFO "Considering %s.%s: (root %p, bdev %x)", |
4e97e4e9 | 1855 | + sb->s_type->name ? sb->s_type->name : "?", |
1856 | + sb->s_subtype ? sb->s_subtype : "", sb->s_root, | |
1857 | + sb->s_bdev ? sb->s_bdev->bd_dev : 0); | |
4e97e4e9 | 1858 | + |
1859 | + if (sb->s_type->fs_flags & FS_IS_FUSE && | |
ad8f4a28 AM |
1860 | + sb->s_frozen == SB_UNFROZEN && |
1861 | + which & FS_FREEZER_FUSE) { | |
4e97e4e9 | 1862 | + sb->s_frozen = SB_FREEZE_TRANS; |
1863 | + sb->s_flags |= MS_FROZEN; | |
1838f965 | 1864 | + FS_PRINTK("Fuse filesystem done.\n"); |
4e97e4e9 | 1865 | + continue; |
1866 | + } | |
1867 | + | |
1868 | + if (!sb->s_root || !sb->s_bdev || | |
1869 | + (sb->s_frozen == SB_FREEZE_TRANS) || | |
1870 | + (sb->s_flags & MS_RDONLY) || | |
ad8f4a28 AM |
1871 | + (sb->s_flags & MS_FROZEN) || |
1872 | + !(which & FS_FREEZER_NORMAL)) { | |
f3e0dcc9 | 1873 | + FS_PRINTK(KERN_INFO "Nope.\n"); |
4e97e4e9 | 1874 | + continue; |
1875 | + } | |
1876 | + | |
f3e0dcc9 | 1877 | + FS_PRINTK(KERN_INFO "Freezing %x... ", sb->s_bdev->bd_dev); |
4e97e4e9 | 1878 | + freeze_bdev(sb->s_bdev); |
1879 | + sb->s_flags |= MS_FROZEN; | |
f3e0dcc9 | 1880 | + FS_PRINTK(KERN_INFO "Done.\n"); |
4e97e4e9 | 1881 | + } |
1882 | + | |
1883 | + lockdep_on(); | |
1884 | +} | |
1885 | + | |
1886 | +/** | |
1887 | + * thaw_filesystems - unlock all filesystems | |
1838f965 | 1888 | + * @which: What combination of fuse & non-fuse to thaw. |
4e97e4e9 | 1889 | + */ |
1890 | +void thaw_filesystems(int which) | |
1891 | +{ | |
1892 | + struct super_block *sb; | |
1893 | + | |
1894 | + lockdep_off(); | |
1895 | + | |
1896 | + list_for_each_entry(sb, &super_blocks, s_list) { | |
1897 | + if (!(sb->s_flags & MS_FROZEN)) | |
1898 | + continue; | |
ad8f4a28 | 1899 | + |
4e97e4e9 | 1900 | + if (sb->s_type->fs_flags & FS_IS_FUSE) { |
ad8f4a28 | 1901 | + if (!(which & FS_FREEZER_FUSE)) |
4e97e4e9 | 1902 | + continue; |
1903 | + | |
1904 | + sb->s_frozen = SB_UNFROZEN; | |
1905 | + } else { | |
ad8f4a28 | 1906 | + if (!(which & FS_FREEZER_NORMAL)) |
4e97e4e9 | 1907 | + continue; |
1908 | + | |
1909 | + thaw_bdev(sb->s_bdev, sb); | |
1910 | + } | |
1911 | + sb->s_flags &= ~MS_FROZEN; | |
1912 | + } | |
1913 | + | |
1914 | + lockdep_on(); | |
1915 | +} | |
1916 | + | |
1917 | /* | |
1918 | * Various filesystems appear to want __find_get_block to be non-blocking. | |
1919 | * But it's the page lock which protects the buffers. To get around this, | |
f3e0dcc9 | 1920 | diff --git a/fs/drop_caches.c b/fs/drop_caches.c |
1838f965 | 1921 | index 3e5637f..f3c5cd6 100644 |
f3e0dcc9 PS |
1922 | --- a/fs/drop_caches.c |
1923 | +++ b/fs/drop_caches.c | |
1838f965 | 1924 | @@ -8,6 +8,7 @@ |
1925 | #include <linux/writeback.h> | |
1926 | #include <linux/sysctl.h> | |
1927 | #include <linux/gfp.h> | |
1928 | +#include <linux/module.h> | |
1929 | ||
1930 | /* A global variable is a bit ugly, but it keeps the code simple */ | |
1931 | int sysctl_drop_caches; | |
1932 | @@ -33,7 +34,7 @@ static void drop_pagecache_sb(struct super_block *sb) | |
f3e0dcc9 PS |
1933 | iput(toput_inode); |
1934 | } | |
1935 | ||
1936 | -static void drop_pagecache(void) | |
1937 | +void drop_pagecache(void) | |
1938 | { | |
1939 | struct super_block *sb; | |
1940 | ||
1838f965 | 1941 | @@ -61,6 +62,7 @@ static void drop_slab(void) |
1942 | nr_objects = shrink_slab(1000, GFP_KERNEL, 1000); | |
1943 | } while (nr_objects > 10); | |
1944 | } | |
1945 | +EXPORT_SYMBOL_GPL(drop_pagecache); | |
1946 | ||
1947 | int drop_caches_sysctl_handler(ctl_table *table, int write, | |
1948 | struct file *file, void __user *buffer, size_t *length, loff_t *ppos) | |
4e97e4e9 | 1949 | diff --git a/fs/fuse/control.c b/fs/fuse/control.c |
f3e0dcc9 | 1950 | index 4f3cab3..f15b0c5 100644 |
4e97e4e9 | 1951 | --- a/fs/fuse/control.c |
1952 | +++ b/fs/fuse/control.c | |
1953 | @@ -207,6 +207,7 @@ static void fuse_ctl_kill_sb(struct super_block *sb) | |
1954 | static struct file_system_type fuse_ctl_fs_type = { | |
1955 | .owner = THIS_MODULE, | |
1956 | .name = "fusectl", | |
1957 | + .fs_flags = FS_IS_FUSE, | |
1958 | .get_sb = fuse_ctl_get_sb, | |
1959 | .kill_sb = fuse_ctl_kill_sb, | |
1960 | }; | |
1961 | diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c | |
f3e0dcc9 | 1962 | index 87250b6..7246e3d 100644 |
4e97e4e9 | 1963 | --- a/fs/fuse/dev.c |
1964 | +++ b/fs/fuse/dev.c | |
1965 | @@ -7,6 +7,7 @@ | |
1966 | */ | |
24613191 | 1967 | |
4e97e4e9 | 1968 | #include "fuse_i.h" |
1969 | +#include "fuse.h" | |
1970 | ||
1971 | #include <linux/init.h> | |
1972 | #include <linux/module.h> | |
1973 | @@ -16,6 +17,7 @@ | |
1974 | #include <linux/pagemap.h> | |
1975 | #include <linux/file.h> | |
1976 | #include <linux/slab.h> | |
1977 | +#include <linux/freezer.h> | |
1978 | ||
1979 | MODULE_ALIAS_MISCDEV(FUSE_MINOR); | |
1980 | ||
f3e0dcc9 | 1981 | @@ -743,6 +745,8 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov, |
4e97e4e9 | 1982 | if (!fc) |
1983 | return -EPERM; | |
1984 | ||
1985 | + FUSE_MIGHT_FREEZE(file->f_mapping->host->i_sb, "fuse_dev_read"); | |
1986 | + | |
1987 | restart: | |
1988 | spin_lock(&fc->lock); | |
1989 | err = -EAGAIN; | |
f3e0dcc9 | 1990 | @@ -869,6 +873,9 @@ static ssize_t fuse_dev_write(struct kiocb *iocb, const struct iovec *iov, |
4e97e4e9 | 1991 | if (!fc) |
1992 | return -EPERM; | |
1993 | ||
1994 | + FUSE_MIGHT_FREEZE(iocb->ki_filp->f_mapping->host->i_sb, | |
1995 | + "fuse_dev_write"); | |
1996 | + | |
1997 | fuse_copy_init(&cs, fc, 0, NULL, iov, nr_segs); | |
1998 | if (nbytes < sizeof(struct fuse_out_header)) | |
1999 | return -EINVAL; | |
2000 | diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c | |
1838f965 | 2001 | index fd03330..85fec3a 100644 |
4e97e4e9 | 2002 | --- a/fs/fuse/dir.c |
2003 | +++ b/fs/fuse/dir.c | |
2004 | @@ -7,12 +7,14 @@ | |
2005 | */ | |
2006 | ||
2007 | #include "fuse_i.h" | |
2008 | +#include "fuse.h" | |
2009 | ||
2010 | #include <linux/pagemap.h> | |
2011 | #include <linux/file.h> | |
2012 | #include <linux/gfp.h> | |
2013 | #include <linux/sched.h> | |
2014 | #include <linux/namei.h> | |
2015 | +#include <linux/freezer.h> | |
2016 | ||
2017 | #if BITS_PER_LONG >= 64 | |
2018 | static inline void fuse_dentry_settime(struct dentry *entry, u64 time) | |
fea155ea | 2019 | @@ -174,6 +176,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) |
4e97e4e9 | 2020 | return 0; |
2021 | ||
2022 | fc = get_fuse_conn(inode); | |
2023 | + | |
2024 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_dentry_revalidate"); | |
2025 | + | |
2026 | req = fuse_get_req(fc); | |
2027 | if (IS_ERR(req)) | |
2028 | return 0; | |
1838f965 | 2029 | @@ -268,6 +273,8 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name, |
2030 | if (name->len > FUSE_NAME_MAX) | |
fea155ea | 2031 | goto out; |
4e97e4e9 | 2032 | |
1838f965 | 2033 | + FUSE_MIGHT_FREEZE(sb, "fuse_lookup_name"); |
4e97e4e9 | 2034 | + |
1838f965 | 2035 | req = fuse_get_req(fc); |
2036 | err = PTR_ERR(req); | |
2037 | if (IS_ERR(req)) | |
2038 | @@ -331,6 +338,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, | |
2039 | if (err) | |
2040 | goto out_err; | |
2041 | ||
2042 | + FUSE_MIGHT_FREEZE(dir->i_sb, "fuse_lookup"); | |
2043 | + | |
2044 | err = -EIO; | |
2045 | if (inode && get_node_id(inode) == FUSE_ROOT_ID) | |
2046 | goto out_iput; | |
2047 | @@ -402,6 +411,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, | |
4e97e4e9 | 2048 | if (IS_ERR(forget_req)) |
2049 | return PTR_ERR(forget_req); | |
2050 | ||
2051 | + FUSE_MIGHT_FREEZE(dir->i_sb, "fuse_create_open"); | |
2052 | + | |
2053 | req = fuse_get_req(fc); | |
2054 | err = PTR_ERR(req); | |
2055 | if (IS_ERR(req)) | |
1838f965 | 2056 | @@ -488,6 +499,8 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, |
4e97e4e9 | 2057 | int err; |
2058 | struct fuse_req *forget_req; | |
2059 | ||
2060 | + FUSE_MIGHT_FREEZE(dir->i_sb, "create_new_entry"); | |
2061 | + | |
2062 | forget_req = fuse_get_req(fc); | |
2063 | if (IS_ERR(forget_req)) { | |
2064 | fuse_put_request(fc, req); | |
1838f965 | 2065 | @@ -585,7 +598,11 @@ static int fuse_mkdir(struct inode *dir, struct dentry *entry, int mode) |
4e97e4e9 | 2066 | { |
2067 | struct fuse_mkdir_in inarg; | |
2068 | struct fuse_conn *fc = get_fuse_conn(dir); | |
2069 | - struct fuse_req *req = fuse_get_req(fc); | |
2070 | + struct fuse_req *req; | |
2071 | + | |
2072 | + FUSE_MIGHT_FREEZE(dir->i_sb, "fuse_mkdir"); | |
2073 | + | |
2074 | + req = fuse_get_req(fc); | |
2075 | if (IS_ERR(req)) | |
2076 | return PTR_ERR(req); | |
2077 | ||
1838f965 | 2078 | @@ -605,7 +622,11 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry, |
4e97e4e9 | 2079 | { |
2080 | struct fuse_conn *fc = get_fuse_conn(dir); | |
2081 | unsigned len = strlen(link) + 1; | |
2082 | - struct fuse_req *req = fuse_get_req(fc); | |
2083 | + struct fuse_req *req; | |
2084 | + | |
2085 | + FUSE_MIGHT_FREEZE(dir->i_sb, "fuse_symlink"); | |
2086 | + | |
2087 | + req = fuse_get_req(fc); | |
2088 | if (IS_ERR(req)) | |
2089 | return PTR_ERR(req); | |
2090 | ||
1838f965 | 2091 | @@ -622,7 +643,11 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) |
4e97e4e9 | 2092 | { |
2093 | int err; | |
2094 | struct fuse_conn *fc = get_fuse_conn(dir); | |
2095 | - struct fuse_req *req = fuse_get_req(fc); | |
2096 | + struct fuse_req *req; | |
2097 | + | |
2098 | + FUSE_MIGHT_FREEZE(dir->i_sb, "fuse_unlink"); | |
2099 | + | |
2100 | + req = fuse_get_req(fc); | |
2101 | if (IS_ERR(req)) | |
2102 | return PTR_ERR(req); | |
2103 | ||
1838f965 | 2104 | @@ -653,7 +678,11 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) |
4e97e4e9 | 2105 | { |
2106 | int err; | |
2107 | struct fuse_conn *fc = get_fuse_conn(dir); | |
2108 | - struct fuse_req *req = fuse_get_req(fc); | |
2109 | + struct fuse_req *req; | |
2110 | + | |
2111 | + FUSE_MIGHT_FREEZE(dir->i_sb, "fuse_rmdir"); | |
2112 | + | |
2113 | + req = fuse_get_req(fc); | |
2114 | if (IS_ERR(req)) | |
2115 | return PTR_ERR(req); | |
2116 | ||
2117 | diff --git a/fs/fuse/file.c b/fs/fuse/file.c | |
1838f965 | 2118 | index 2bada6b..a2081c4 100644 |
4e97e4e9 | 2119 | --- a/fs/fuse/file.c |
2120 | +++ b/fs/fuse/file.c | |
2121 | @@ -7,11 +7,13 @@ | |
2122 | */ | |
2123 | ||
2124 | #include "fuse_i.h" | |
2125 | +#include "fuse.h" | |
2126 | ||
2127 | #include <linux/pagemap.h> | |
2128 | #include <linux/slab.h> | |
2129 | #include <linux/kernel.h> | |
2130 | #include <linux/sched.h> | |
2131 | +#include <linux/freezer.h> | |
2132 | ||
2133 | static const struct file_operations fuse_direct_io_file_operations; | |
2134 | ||
2135 | @@ -23,6 +25,8 @@ static int fuse_send_open(struct inode *inode, struct file *file, int isdir, | |
2136 | struct fuse_req *req; | |
2137 | int err; | |
2138 | ||
2139 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_send_open"); | |
2140 | + | |
2141 | req = fuse_get_req(fc); | |
2142 | if (IS_ERR(req)) | |
2143 | return PTR_ERR(req); | |
1838f965 | 2144 | @@ -268,6 +272,8 @@ static int fuse_flush(struct file *file, fl_owner_t id) |
2145 | if (fc->no_flush) | |
2146 | return 0; | |
2147 | ||
2148 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_flush"); | |
2149 | + | |
2150 | req = fuse_get_req_nofail(fc, file); | |
2151 | memset(&inarg, 0, sizeof(inarg)); | |
2152 | inarg.fh = ff->fh; | |
2153 | @@ -319,6 +325,8 @@ int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, | |
2154 | if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) | |
2155 | return 0; | |
2156 | ||
2157 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_fsync_common"); | |
2158 | + | |
2159 | /* | |
2160 | * Start writeback against all dirty pages of the inode, then | |
2161 | * wait for all outstanding writes, before sending the FSYNC | |
2162 | @@ -427,6 +435,8 @@ static int fuse_readpage(struct file *file, struct page *page) | |
2163 | if (is_bad_inode(inode)) | |
2164 | goto out; | |
2165 | ||
2166 | + FUSE_MIGHT_FREEZE(file->f_mapping->host->i_sb, "fuse_readpage"); | |
2167 | + | |
2168 | /* | |
2169 | * Page writeback can extend beyond the liftime of the | |
2170 | * page-cache page, so make sure we read a properly synced | |
2171 | @@ -527,6 +537,9 @@ static int fuse_readpages_fill(void *_data, struct page *page) | |
2172 | struct inode *inode = data->inode; | |
2173 | struct fuse_conn *fc = get_fuse_conn(inode); | |
2174 | ||
2175 | + FUSE_MIGHT_FREEZE(data->file->f_mapping->host->i_sb, | |
2176 | + "fuse_readpages_fill"); | |
2177 | + | |
2178 | fuse_wait_on_page_writeback(inode, page->index); | |
2179 | ||
2180 | if (req->num_pages && | |
2181 | @@ -557,6 +570,8 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, | |
2182 | if (is_bad_inode(inode)) | |
2183 | goto out; | |
2184 | ||
2185 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_readpages"); | |
2186 | + | |
2187 | data.file = file; | |
2188 | data.inode = inode; | |
2189 | data.req = fuse_get_req(fc); | |
2190 | @@ -674,6 +689,8 @@ static int fuse_buffered_write(struct file *file, struct inode *inode, | |
4e97e4e9 | 2191 | if (is_bad_inode(inode)) |
2192 | return -EIO; | |
2193 | ||
1838f965 | 2194 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_buffered_write"); |
4e97e4e9 | 2195 | + |
f3e0dcc9 PS |
2196 | /* |
2197 | * Make sure writepages on the same page are not mixed up with | |
2198 | * plain writes. | |
1838f965 | 2199 | @@ -828,6 +845,8 @@ static ssize_t fuse_perform_write(struct file *file, |
2200 | struct fuse_req *req; | |
2201 | ssize_t count; | |
2202 | ||
2203 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_perform_write"); | |
2204 | + | |
2205 | req = fuse_get_req(fc); | |
2206 | if (IS_ERR(req)) { | |
2207 | err = PTR_ERR(req); | |
2208 | @@ -962,6 +981,8 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf, | |
4e97e4e9 | 2209 | if (is_bad_inode(inode)) |
2210 | return -EIO; | |
2211 | ||
2212 | + FUSE_MIGHT_FREEZE(file->f_mapping->host->i_sb, "fuse_direct_io"); | |
2213 | + | |
2214 | req = fuse_get_req(fc); | |
2215 | if (IS_ERR(req)) | |
2216 | return PTR_ERR(req); | |
1838f965 | 2217 | @@ -1315,6 +1336,8 @@ static int fuse_getlk(struct file *file, struct file_lock *fl) |
4e97e4e9 | 2218 | struct fuse_lk_out outarg; |
2219 | int err; | |
24613191 | 2220 | |
4e97e4e9 | 2221 | + FUSE_MIGHT_FREEZE(file->f_mapping->host->i_sb, "fuse_getlk"); |
2222 | + | |
2223 | req = fuse_get_req(fc); | |
2224 | if (IS_ERR(req)) | |
2225 | return PTR_ERR(req); | |
1838f965 | 2226 | @@ -1350,6 +1373,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock) |
4e97e4e9 | 2227 | if (fl->fl_flags & FL_CLOSE) |
2228 | return 0; | |
2229 | ||
2230 | + FUSE_MIGHT_FREEZE(file->f_mapping->host->i_sb, "fuse_setlk"); | |
2231 | + | |
2232 | req = fuse_get_req(fc); | |
2233 | if (IS_ERR(req)) | |
2234 | return PTR_ERR(req); | |
1838f965 | 2235 | @@ -1416,6 +1441,8 @@ static sector_t fuse_bmap(struct address_space *mapping, sector_t block) |
4e97e4e9 | 2236 | if (!inode->i_sb->s_bdev || fc->no_bmap) |
2237 | return 0; | |
2238 | ||
2239 | + FUSE_MIGHT_FREEZE(inode->i_sb, "fuse_bmap"); | |
2240 | + | |
2241 | req = fuse_get_req(fc); | |
2242 | if (IS_ERR(req)) | |
2243 | return 0; | |
2244 | diff --git a/fs/fuse/fuse.h b/fs/fuse/fuse.h | |
2245 | new file mode 100644 | |
ad8f4a28 | 2246 | index 0000000..170e49a |
4e97e4e9 | 2247 | --- /dev/null |
2248 | +++ b/fs/fuse/fuse.h | |
ad8f4a28 | 2249 | @@ -0,0 +1,13 @@ |
4e97e4e9 | 2250 | +#define FUSE_MIGHT_FREEZE(superblock, desc) \ |
2251 | +do { \ | |
2252 | + int printed = 0; \ | |
ad8f4a28 | 2253 | + while (superblock->s_frozen != SB_UNFROZEN) { \ |
4e97e4e9 | 2254 | + if (!printed) { \ |
ad8f4a28 AM |
2255 | + printk(KERN_INFO "%d frozen in " desc ".\n", \ |
2256 | + current->pid); \ | |
4e97e4e9 | 2257 | + printed = 1; \ |
2258 | + } \ | |
2259 | + try_to_freeze(); \ | |
2260 | + yield(); \ | |
2261 | + } \ | |
ad8f4a28 | 2262 | +} while (0) |
4e97e4e9 | 2263 | diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c |
fea155ea | 2264 | index d2249f1..04ae6cb 100644 |
4e97e4e9 | 2265 | --- a/fs/fuse/inode.c |
2266 | +++ b/fs/fuse/inode.c | |
fea155ea | 2267 | @@ -914,7 +914,7 @@ static int fuse_get_sb(struct file_system_type *fs_type, |
4e97e4e9 | 2268 | static struct file_system_type fuse_fs_type = { |
2269 | .owner = THIS_MODULE, | |
2270 | .name = "fuse", | |
2271 | - .fs_flags = FS_HAS_SUBTYPE, | |
2272 | + .fs_flags = FS_HAS_SUBTYPE | FS_IS_FUSE, | |
2273 | .get_sb = fuse_get_sb, | |
2274 | .kill_sb = kill_anon_super, | |
2275 | }; | |
fea155ea | 2276 | @@ -933,7 +933,7 @@ static struct file_system_type fuseblk_fs_type = { |
4e97e4e9 | 2277 | .name = "fuseblk", |
2278 | .get_sb = fuse_get_sb_blk, | |
2279 | .kill_sb = kill_block_super, | |
2280 | - .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE, | |
2281 | + .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE | FS_IS_FUSE, | |
2282 | }; | |
2283 | ||
2284 | static inline int register_fuseblk(void) | |
ad8f4a28 | 2285 | diff --git a/fs/namei.c b/fs/namei.c |
fea155ea | 2286 | index 4ea63ed..65be6a6 100644 |
ad8f4a28 AM |
2287 | --- a/fs/namei.c |
2288 | +++ b/fs/namei.c | |
fea155ea | 2289 | @@ -2223,6 +2223,8 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) |
ad8f4a28 AM |
2290 | if (!dir->i_op || !dir->i_op->unlink) |
2291 | return -EPERM; | |
24613191 | 2292 | |
ad8f4a28 | 2293 | + vfs_check_frozen(dir->i_sb, SB_FREEZE_WRITE); |
24613191 | 2294 | + |
ad8f4a28 AM |
2295 | DQUOT_INIT(dir); |
2296 | ||
2297 | mutex_lock(&dentry->d_inode->i_mutex); | |
1838f965 | 2298 | diff --git a/fs/super.c b/fs/super.c |
2299 | index e931ae9..70145e2 100644 | |
2300 | --- a/fs/super.c | |
2301 | +++ b/fs/super.c | |
2302 | @@ -43,6 +43,8 @@ | |
2303 | ||
2304 | ||
2305 | LIST_HEAD(super_blocks); | |
2306 | +EXPORT_SYMBOL_GPL(super_blocks); | |
2307 | + | |
2308 | DEFINE_SPINLOCK(sb_lock); | |
2309 | ||
2310 | /** | |
4e97e4e9 | 2311 | diff --git a/include/linux/Kbuild b/include/linux/Kbuild |
fea155ea | 2312 | index b68ec09..6eebd34 100644 |
4e97e4e9 | 2313 | --- a/include/linux/Kbuild |
2314 | +++ b/include/linux/Kbuild | |
fea155ea | 2315 | @@ -208,6 +208,7 @@ unifdef-y += filter.h |
4e97e4e9 | 2316 | unifdef-y += flat.h |
2317 | unifdef-y += futex.h | |
2318 | unifdef-y += fs.h | |
2319 | +unifdef-y += freezer.h | |
2320 | unifdef-y += gameport.h | |
2321 | unifdef-y += generic_serial.h | |
f3e0dcc9 | 2322 | unifdef-y += hayesesp.h |
4e97e4e9 | 2323 | diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h |
fea155ea | 2324 | index eadaab4..7eb6655 100644 |
4e97e4e9 | 2325 | --- a/include/linux/buffer_head.h |
2326 | +++ b/include/linux/buffer_head.h | |
fea155ea | 2327 | @@ -171,6 +171,11 @@ wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); |
4e97e4e9 | 2328 | int fsync_bdev(struct block_device *); |
2329 | struct super_block *freeze_bdev(struct block_device *); | |
2330 | void thaw_bdev(struct block_device *, struct super_block *); | |
ad8f4a28 AM |
2331 | +#define FS_FREEZER_FUSE 1 |
2332 | +#define FS_FREEZER_NORMAL 2 | |
2333 | +#define FS_FREEZER_ALL (FS_FREEZER_FUSE | FS_FREEZER_NORMAL) | |
2334 | +void freeze_filesystems(int which); | |
4e97e4e9 | 2335 | +void thaw_filesystems(int which); |
2336 | int fsync_super(struct super_block *); | |
2337 | int fsync_no_super(struct block_device *); | |
2338 | struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, | |
4e97e4e9 | 2339 | diff --git a/include/linux/freezer.h b/include/linux/freezer.h |
1838f965 | 2340 | index deddeed..8c2dadf 100644 |
4e97e4e9 | 2341 | --- a/include/linux/freezer.h |
2342 | +++ b/include/linux/freezer.h | |
1838f965 | 2343 | @@ -127,6 +127,23 @@ static inline void set_freezable(void) |
4e97e4e9 | 2344 | current->flags &= ~PF_NOFREEZE; |
43540741 | 2345 | } |
24613191 | 2346 | |
1838f965 | 2347 | +#ifdef CONFIG_PM_SLEEP |
24613191 | 2348 | +extern int freezer_state; |
2349 | +#define FREEZER_OFF 0 | |
4e97e4e9 | 2350 | +#define FREEZER_FILESYSTEMS_FROZEN 1 |
2351 | +#define FREEZER_USERSPACE_FROZEN 2 | |
2352 | +#define FREEZER_FULLY_ON 3 | |
24613191 | 2353 | + |
2354 | +static inline int freezer_is_on(void) | |
2355 | +{ | |
1838f965 | 2356 | + return freezer_state == FREEZER_FULLY_ON; |
24613191 | 2357 | +} |
1838f965 | 2358 | +#else |
2359 | +static inline int freezer_is_on(void) { return 0; } | |
2360 | +#endif | |
24613191 | 2361 | + |
2362 | +extern void thaw_kernel_threads(void); | |
2363 | + | |
ad8f4a28 | 2364 | /* |
fea155ea PS |
2365 | * Tell the freezer that the current task should be frozen by it and that it |
2366 | * should send a fake signal to the task to freeze it. | |
1838f965 | 2367 | @@ -178,6 +195,8 @@ static inline int freeze_processes(void) { BUG(); return 0; } |
24613191 | 2368 | static inline void thaw_processes(void) {} |
2369 | ||
2370 | static inline int try_to_freeze(void) { return 0; } | |
2371 | +static inline int freezer_is_on(void) { return 0; } | |
2372 | +static inline void thaw_kernel_threads(void) { } | |
2373 | ||
43540741 | 2374 | static inline void freezer_do_not_count(void) {} |
2375 | static inline void freezer_count(void) {} | |
4e97e4e9 | 2376 | diff --git a/include/linux/fs.h b/include/linux/fs.h |
fea155ea | 2377 | index 580b513..e7a3169 100644 |
4e97e4e9 | 2378 | --- a/include/linux/fs.h |
2379 | +++ b/include/linux/fs.h | |
2380 | @@ -8,6 +8,7 @@ | |
2381 | ||
2382 | #include <linux/limits.h> | |
2383 | #include <linux/ioctl.h> | |
2384 | +#include <linux/freezer.h> | |
2385 | ||
2386 | /* | |
2387 | * It's silly to have NR_OPEN bigger than NR_FILE, but you can change | |
fea155ea | 2388 | @@ -96,6 +97,7 @@ extern int dir_notify_enable; |
4e97e4e9 | 2389 | #define FS_REQUIRES_DEV 1 |
2390 | #define FS_BINARY_MOUNTDATA 2 | |
2391 | #define FS_HAS_SUBTYPE 4 | |
2392 | +#define FS_IS_FUSE 8 /* Fuse filesystem - bdev freeze these too */ | |
2393 | #define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */ | |
2394 | #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() | |
2395 | * during rename() internally. | |
fea155ea | 2396 | @@ -128,6 +130,7 @@ extern int dir_notify_enable; |
4e97e4e9 | 2397 | #define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ |
ad8f4a28 | 2398 | #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ |
7f9d2ee0 | 2399 | #define MS_I_VERSION (1<<23) /* Update inode I_version field */ |
2400 | +#define MS_FROZEN (1<<24) /* Frozen by freeze_filesystems() */ | |
4e97e4e9 | 2401 | #define MS_ACTIVE (1<<30) |
2402 | #define MS_NOUSER (1<<31) | |
2403 | ||
fea155ea | 2404 | @@ -1141,8 +1144,11 @@ enum { |
4e97e4e9 | 2405 | SB_FREEZE_TRANS = 2, |
2406 | }; | |
2407 | ||
2408 | -#define vfs_check_frozen(sb, level) \ | |
2409 | - wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) | |
2410 | +#define vfs_check_frozen(sb, level) do { \ | |
2411 | + freezer_do_not_count(); \ | |
2412 | + wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))); \ | |
2413 | + freezer_count(); \ | |
ad8f4a28 | 2414 | +} while (0) |
4e97e4e9 | 2415 | |
2416 | #define get_fs_excl() atomic_inc(¤t->fs_excl) | |
2417 | #define put_fs_excl() atomic_dec(¤t->fs_excl) | |
f3e0dcc9 | 2418 | diff --git a/include/linux/mm.h b/include/linux/mm.h |
fea155ea | 2419 | index 72a15dc..01a7657 100644 |
f3e0dcc9 PS |
2420 | --- a/include/linux/mm.h |
2421 | +++ b/include/linux/mm.h | |
fea155ea | 2422 | @@ -1264,6 +1264,7 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, |
f3e0dcc9 PS |
2423 | void __user *, size_t *, loff_t *); |
2424 | unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, | |
2425 | unsigned long lru_pages); | |
2426 | +void drop_pagecache(void); | |
2427 | ||
2428 | #ifndef CONFIG_MMU | |
2429 | #define randomize_va_space 0 | |
4e97e4e9 | 2430 | diff --git a/include/linux/netlink.h b/include/linux/netlink.h |
fea155ea | 2431 | index 9ff1b54..100dc2e 100644 |
4e97e4e9 | 2432 | --- a/include/linux/netlink.h |
2433 | +++ b/include/linux/netlink.h | |
73c609d5 | 2434 | @@ -24,6 +24,8 @@ |
24613191 | 2435 | /* leave room for NETLINK_DM (DM Events) */ |
2436 | #define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ | |
73c609d5 | 2437 | #define NETLINK_ECRYPTFS 19 |
ad8f4a28 AM |
2438 | +#define NETLINK_TOI_USERUI 20 /* TuxOnIce's userui */ |
2439 | +#define NETLINK_TOI_USM 21 /* Userspace storage manager */ | |
24613191 | 2440 | |
2441 | #define MAX_LINKS 32 | |
2442 | ||
4e97e4e9 | 2443 | diff --git a/include/linux/suspend.h b/include/linux/suspend.h |
1838f965 | 2444 | index 2ce8207..f469faf 100644 |
4e97e4e9 | 2445 | --- a/include/linux/suspend.h |
2446 | +++ b/include/linux/suspend.h | |
1838f965 | 2447 | @@ -280,4 +280,70 @@ static inline void register_nosave_region_late(unsigned long b, unsigned long e) |
fea155ea PS |
2448 | |
2449 | extern struct mutex pm_mutex; | |
24613191 | 2450 | |
2451 | +enum { | |
4e97e4e9 | 2452 | + TOI_CAN_HIBERNATE, |
2453 | + TOI_CAN_RESUME, | |
2454 | + TOI_RESUME_DEVICE_OK, | |
2455 | + TOI_NORESUME_SPECIFIED, | |
2456 | + TOI_SANITY_CHECK_PROMPT, | |
2457 | + TOI_CONTINUE_REQ, | |
2458 | + TOI_RESUMED_BEFORE, | |
2459 | + TOI_BOOT_TIME, | |
2460 | + TOI_NOW_RESUMING, | |
2461 | + TOI_IGNORE_LOGLEVEL, | |
2462 | + TOI_TRYING_TO_RESUME, | |
2463 | + TOI_LOADING_ALT_IMAGE, | |
2464 | + TOI_STOP_RESUME, | |
2465 | + TOI_IO_STOPPED, | |
2466 | + TOI_NOTIFIERS_PREPARE, | |
ad8f4a28 | 2467 | + TOI_CLUSTER_MODE, |
1838f965 | 2468 | + TOI_BOOT_KERNEL, |
24613191 | 2469 | +}; |
2470 | + | |
4e97e4e9 | 2471 | +#ifdef CONFIG_TOI |
24613191 | 2472 | + |
2473 | +/* Used in init dir files */ | |
4e97e4e9 | 2474 | +extern unsigned long toi_state; |
2475 | +#define set_toi_state(bit) (set_bit(bit, &toi_state)) | |
2476 | +#define clear_toi_state(bit) (clear_bit(bit, &toi_state)) | |
2477 | +#define test_toi_state(bit) (test_bit(bit, &toi_state)) | |
2478 | +extern int toi_running; | |
2479 | + | |
1838f965 | 2480 | +#define test_action_state(bit) (test_bit(bit, &toi_bkd.toi_action)) |
2481 | +extern int toi_try_hibernate(void); | |
2482 | + | |
4e97e4e9 | 2483 | +#else /* !CONFIG_TOI */ |
2484 | + | |
2485 | +#define toi_state (0) | |
ad8f4a28 | 2486 | +#define set_toi_state(bit) do { } while (0) |
4e97e4e9 | 2487 | +#define clear_toi_state(bit) do { } while (0) |
2488 | +#define test_toi_state(bit) (0) | |
2489 | +#define toi_running (0) | |
1838f965 | 2490 | + |
2491 | +static inline int toi_try_hibernate(void) { return 0; } | |
2492 | +#define test_action_state(bit) (0) | |
2493 | + | |
4e97e4e9 | 2494 | +#endif /* CONFIG_TOI */ |
2495 | + | |
2496 | +#ifdef CONFIG_HIBERNATION | |
2497 | +#ifdef CONFIG_TOI | |
2498 | +extern void toi_try_resume(void); | |
e8d0ad9d | 2499 | +#else |
ad8f4a28 | 2500 | +#define toi_try_resume() do { } while (0) |
e8d0ad9d | 2501 | +#endif |
2502 | + | |
2503 | +extern int resume_attempted; | |
24613191 | 2504 | +extern int software_resume(void); |
e8d0ad9d | 2505 | + |
2506 | +static inline void check_resume_attempted(void) | |
2507 | +{ | |
2508 | + if (resume_attempted) | |
2509 | + return; | |
2510 | + | |
2511 | + software_resume(); | |
2512 | +} | |
2513 | +#else | |
ad8f4a28 | 2514 | +#define check_resume_attempted() do { } while (0) |
e8d0ad9d | 2515 | +#define resume_attempted (0) |
24613191 | 2516 | +#endif |
ad8f4a28 | 2517 | #endif /* _LINUX_SUSPEND_H */ |
4e97e4e9 | 2518 | diff --git a/include/linux/swap.h b/include/linux/swap.h |
1838f965 | 2519 | index de40f16..661d8d5 100644 |
4e97e4e9 | 2520 | --- a/include/linux/swap.h |
2521 | +++ b/include/linux/swap.h | |
7f9d2ee0 | 2522 | @@ -164,6 +164,7 @@ extern unsigned long totalram_pages; |
ad8f4a28 AM |
2523 | extern unsigned long totalreserve_pages; |
2524 | extern long nr_swap_pages; | |
2525 | extern unsigned int nr_free_buffer_pages(void); | |
2526 | +extern unsigned int nr_unallocated_buffer_pages(void); | |
2527 | extern unsigned int nr_free_pagecache_pages(void); | |
2528 | ||
2529 | /* Definition of global_page_state not available yet */ | |
4e97e4e9 | 2530 | diff --git a/init/do_mounts.c b/init/do_mounts.c |
1838f965 | 2531 | index 3715feb..facc15a 100644 |
4e97e4e9 | 2532 | --- a/init/do_mounts.c |
2533 | +++ b/init/do_mounts.c | |
1838f965 | 2534 | @@ -141,6 +141,7 @@ fail: |
2535 | done: | |
2536 | return res; | |
2537 | } | |
2538 | +EXPORT_SYMBOL_GPL(name_to_dev_t); | |
2539 | ||
2540 | static int __init root_dev_setup(char *line) | |
2541 | { | |
2542 | @@ -400,6 +401,8 @@ void __init prepare_namespace(void) | |
24613191 | 2543 | if (is_floppy && rd_doload && rd_load_disk(0)) |
2544 | ROOT_DEV = Root_RAM0; | |
2545 | ||
e8d0ad9d | 2546 | + check_resume_attempted(); |
2547 | + | |
2548 | mount_root(); | |
2549 | out: | |
2550 | sys_mount(".", "/", NULL, MS_MOVE, NULL); | |
4e97e4e9 | 2551 | diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c |
ad8f4a28 | 2552 | index 614241b..f3ea292 100644 |
4e97e4e9 | 2553 | --- a/init/do_mounts_initrd.c |
2554 | +++ b/init/do_mounts_initrd.c | |
24613191 | 2555 | @@ -6,6 +6,7 @@ |
2556 | #include <linux/romfs_fs.h> | |
2557 | #include <linux/initrd.h> | |
2558 | #include <linux/sched.h> | |
2559 | +#include <linux/suspend.h> | |
2560 | #include <linux/freezer.h> | |
2561 | ||
2562 | #include "do_mounts.h" | |
ad8f4a28 AM |
2563 | @@ -68,6 +69,11 @@ static void __init handle_initrd(void) |
2564 | ||
2565 | current->flags &= ~PF_FREEZER_SKIP; | |
24613191 | 2566 | |
e8d0ad9d | 2567 | + if (!resume_attempted) |
4e97e4e9 | 2568 | + printk(KERN_ERR "TuxOnIce: No attempt was made to resume from " |
73c609d5 | 2569 | + "any image that might exist.\n"); |
4e97e4e9 | 2570 | + clear_toi_state(TOI_BOOT_TIME); |
24613191 | 2571 | + |
2572 | /* move initrd to rootfs' /old */ | |
2573 | sys_fchdir(old_fd); | |
2574 | sys_mount("/", ".", NULL, MS_MOVE, NULL); | |
4e97e4e9 | 2575 | diff --git a/init/main.c b/init/main.c |
1838f965 | 2576 | index 3820323..5dcf9c3 100644 |
4e97e4e9 | 2577 | --- a/init/main.c |
2578 | +++ b/init/main.c | |
1838f965 | 2579 | @@ -120,6 +120,7 @@ extern void softirq_init(void); |
2580 | char __initdata boot_command_line[COMMAND_LINE_SIZE]; | |
2581 | /* Untouched saved command line (eg. for /proc) */ | |
2582 | char *saved_command_line; | |
2583 | +EXPORT_SYMBOL_GPL(saved_command_line); | |
2584 | /* Command line for parameter parsing */ | |
2585 | static char *static_command_line; | |
2586 | ||
2587 | diff --git a/kernel/cpu.c b/kernel/cpu.c | |
2588 | index f17e985..214686f 100644 | |
2589 | --- a/kernel/cpu.c | |
2590 | +++ b/kernel/cpu.c | |
2591 | @@ -427,6 +427,7 @@ int disable_nonboot_cpus(void) | |
2592 | cpu_maps_update_done(); | |
2593 | return error; | |
2594 | } | |
2595 | +EXPORT_SYMBOL_GPL(disable_nonboot_cpus); | |
2596 | ||
2597 | void __ref enable_nonboot_cpus(void) | |
2598 | { | |
2599 | @@ -451,6 +452,7 @@ void __ref enable_nonboot_cpus(void) | |
2600 | out: | |
2601 | cpu_maps_update_done(); | |
2602 | } | |
2603 | +EXPORT_SYMBOL_GPL(enable_nonboot_cpus); | |
2604 | #endif /* CONFIG_PM_SLEEP_SMP */ | |
2605 | ||
2606 | #endif /* CONFIG_SMP */ | |
2607 | diff --git a/kernel/fork.c b/kernel/fork.c | |
2608 | index d8ad2c6..0aa6946 100644 | |
2609 | --- a/kernel/fork.c | |
2610 | +++ b/kernel/fork.c | |
2611 | @@ -77,6 +77,7 @@ int max_threads; /* tunable limit on nr_threads */ | |
2612 | DEFINE_PER_CPU(unsigned long, process_counts) = 0; | |
2613 | ||
2614 | __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ | |
2615 | +EXPORT_SYMBOL_GPL(tasklist_lock); | |
2616 | ||
2617 | int nr_processes(void) | |
2618 | { | |
4e97e4e9 | 2619 | diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig |
1838f965 | 2620 | index dcd165f..5539ad0 100644 |
4e97e4e9 | 2621 | --- a/kernel/power/Kconfig |
2622 | +++ b/kernel/power/Kconfig | |
1838f965 | 2623 | @@ -38,6 +38,13 @@ config CAN_PM_TRACE |
2624 | def_bool y | |
2625 | depends on PM_DEBUG && PM_SLEEP && EXPERIMENTAL | |
24613191 | 2626 | |
1838f965 | 2627 | +config FS_FREEZER_DEBUG |
2628 | + bool "Filesystem freezer debugging" | |
2629 | + depends on PM_DEBUG | |
24613191 | 2630 | + default n |
2631 | + ---help--- | |
1838f965 | 2632 | + This option enables debugging of the filesystem freezing code. |
2633 | + | |
2634 | config PM_TRACE | |
2635 | bool | |
2636 | help | |
2637 | @@ -179,6 +186,256 @@ config PM_STD_PARTITION | |
4e97e4e9 | 2638 | suspended image to. It will simply pick the first available swap |
2639 | device. | |
2640 | ||
2641 | +menuconfig TOI_CORE | |
2642 | + tristate "Enhanced Hibernation (TuxOnIce)" | |
2643 | + depends on HIBERNATION | |
24613191 | 2644 | + default y |
2645 | + ---help--- | |
4e97e4e9 | 2646 | + TuxOnIce is the 'new and improved' suspend support. |
24613191 | 2647 | + |
4e97e4e9 | 2648 | + See the TuxOnIce home page (tuxonice.net) |
24613191 | 2649 | + for FAQs, HOWTOs and other documentation. |
2650 | + | |
2651 | + comment "Image Storage (you need at least one allocator)" | |
4e97e4e9 | 2652 | + depends on TOI_CORE |
24613191 | 2653 | + |
4e97e4e9 | 2654 | + config TOI_FILE |
24613191 | 2655 | + tristate "File Allocator" |
4e97e4e9 | 2656 | + depends on TOI_CORE |
24613191 | 2657 | + default y |
2658 | + ---help--- | |
2659 | + This option enables support for storing an image in a | |
2660 | + simple file. This should be possible, but we're still | |
2661 | + testing it. | |
2662 | + | |
4e97e4e9 | 2663 | + config TOI_SWAP |
24613191 | 2664 | + tristate "Swap Allocator" |
4e97e4e9 | 2665 | + depends on TOI_CORE && SWAP |
24613191 | 2666 | + default y |
24613191 | 2667 | + ---help--- |
2668 | + This option enables support for storing an image in your | |
2669 | + swap space. | |
2670 | + | |
2671 | + comment "General Options" | |
4e97e4e9 | 2672 | + depends on TOI_CORE |
24613191 | 2673 | + |
ad8f4a28 AM |
2674 | + config TOI_DEFAULT_PRE_HIBERNATE |
2675 | + string "Default pre-hibernate command" | |
2676 | + depends on TOI_CORE | |
2677 | + ---help--- | |
2678 | + This entry allows you to specify a command to be run prior | |
2679 | + to starting a hibernation cycle. If this command returns | |
7f9d2ee0 | 2680 | + a non-zero result code, hibernating will be aborted. If |
2681 | + you're starting hibernation via the hibernate script, | |
2682 | + this value should probably be blank. | |
ad8f4a28 AM |
2683 | + |
2684 | + config TOI_DEFAULT_POST_HIBERNATE | |
2685 | + string "Default post-resume command" | |
2686 | + depends on TOI_CORE | |
2687 | + ---help--- | |
2688 | + This entry allows you to specify a command to be run after | |
2689 | + completing a hibernation cycle. The return code of this | |
7f9d2ee0 | 2690 | + command is ignored. If you're starting hibernation via the |
2691 | + hibernate script, this value should probably be blank. | |
ad8f4a28 | 2692 | + |
4e97e4e9 | 2693 | + config TOI_CRYPTO |
24613191 | 2694 | + tristate "Compression support" |
4e97e4e9 | 2695 | + depends on TOI_CORE && CRYPTO |
24613191 | 2696 | + default y |
2697 | + ---help--- | |
2698 | + This option adds support for using cryptoapi compression | |
2699 | + algorithms. Compression is particularly useful as | |
4e97e4e9 | 2700 | + the LZF support that comes with the TuxOnIce patch can double |
24613191 | 2701 | + your suspend and resume speed. |
2702 | + | |
2703 | + You probably want this, so say Y here. | |
2704 | + | |
2705 | + comment "No compression support available without Cryptoapi support." | |
4e97e4e9 | 2706 | + depends on TOI_CORE && !CRYPTO |
24613191 | 2707 | + |
4e97e4e9 | 2708 | + config TOI_USERUI |
73c609d5 | 2709 | + tristate "Userspace User Interface support" |
4e97e4e9 | 2710 | + depends on TOI_CORE && NET && (VT || SERIAL_CONSOLE) |
73c609d5 | 2711 | + default y |
2712 | + ---help--- | |
2713 | + This option enabled support for a userspace based user interface | |
4e97e4e9 | 2714 | + to TuxOnIce, which allows you to have a nice display while suspending |
73c609d5 | 2715 | + and resuming, and also enables features such as pressing escape to |
2716 | + cancel a cycle or interactive debugging. | |
2717 | + | |
4e97e4e9 | 2718 | + config TOI_USERUI_DEFAULT_PATH |
2719 | + string "Default userui program location" | |
2720 | + default "/usr/local/sbin/tuxonice_fbsplash" | |
2721 | + depends on TOI_USERUI | |
24613191 | 2722 | + ---help--- |
4e97e4e9 | 2723 | + This entry allows you to specify a default path to the userui binary. |
24613191 | 2724 | + |
4e97e4e9 | 2725 | + config TOI_KEEP_IMAGE |
24613191 | 2726 | + bool "Allow Keep Image Mode" |
4e97e4e9 | 2727 | + depends on TOI_CORE |
24613191 | 2728 | + ---help--- |
2729 | + This option allows you to keep and image and reuse it. It is intended | |
2730 | + __ONLY__ for use with systems where all filesystems are mounted read- | |
2731 | + only (kiosks, for example). To use it, compile this option in and boot | |
4e97e4e9 | 2732 | + normally. Set the KEEP_IMAGE flag in /sys/power/tuxonice and suspend. |
24613191 | 2733 | + When you resume, the image will not be removed. You will be unable to turn |
2734 | + off swap partitions (assuming you are using the swap allocator), but future | |
2735 | + suspends simply do a power-down. The image can be updated using the | |
2736 | + kernel command line parameter suspend_act= to turn off the keep image | |
2737 | + bit. Keep image mode is a little less user friendly on purpose - it | |
2738 | + should not be used without thought! | |
2739 | + | |
4e97e4e9 | 2740 | + config TOI_REPLACE_SWSUSP |
24613191 | 2741 | + bool "Replace swsusp by default" |
2742 | + default y | |
4e97e4e9 | 2743 | + depends on TOI_CORE |
24613191 | 2744 | + ---help--- |
4e97e4e9 | 2745 | + TuxOnIce can replace swsusp. This option makes that the default state, |
2746 | + requiring you to echo 0 > /sys/power/tuxonice/replace_swsusp if you want | |
24613191 | 2747 | + to use the vanilla kernel functionality. Note that your initrd/ramfs will |
2748 | + need to do this before trying to resume, too. | |
ad8f4a28 AM |
2749 | + With overriding swsusp enabled, echoing disk to /sys/power/state will |
2750 | + start a TuxOnIce cycle. If resume= doesn't specify an allocator and both | |
2751 | + the swap and file allocators are compiled in, the swap allocator will be | |
2752 | + used by default. | |
2753 | + | |
1838f965 | 2754 | + config TOI_IGNORE_LATE_INITCALL |
2755 | + bool "Wait for initrd/ramfs to run, by default" | |
2756 | + default n | |
2757 | + depends on TOI_CORE | |
2758 | + ---help--- | |
2759 | + When booting, TuxOnIce can check for an image and start to resume prior | |
2760 | + to any initrd/ramfs running (via a late initcall). | |
2761 | + | |
2762 | + If you don't have an initrd/ramfs, this is what you want to happen - | |
2763 | + otherwise you won't be able to safely resume. You should set this option | |
2764 | + to 'No'. | |
2765 | + | |
2766 | + If, however, you want your initrd/ramfs to run anyway before resuming, | |
2767 | + you need to tell TuxOnIce to ignore that earlier opportunity to resume. | |
2768 | + This can be done either by using this compile time option, or by | |
2769 | + overriding this option with the boot-time parameter toi_initramfs_resume_only=1. | |
2770 | + | |
2771 | + Note that if TuxOnIce can't resume at the earlier opportunity, the | |
2772 | + value of this option won't matter - the initramfs/initrd (if any) will | |
2773 | + run anyway. | |
2774 | + | |
ad8f4a28 | 2775 | + menuconfig TOI_CLUSTER |
24613191 | 2776 | + tristate "Cluster support" |
2777 | + default n | |
7f9d2ee0 | 2778 | + depends on TOI_CORE && NET && BROKEN |
24613191 | 2779 | + ---help--- |
2780 | + Support for linking multiple machines in a cluster so that they suspend | |
2781 | + and resume together. | |
2782 | + | |
ad8f4a28 AM |
2783 | + config TOI_DEFAULT_CLUSTER_INTERFACE |
2784 | + string "Default cluster interface" | |
4e97e4e9 | 2785 | + depends on TOI_CLUSTER |
24613191 | 2786 | + ---help--- |
ad8f4a28 AM |
2787 | + The default interface on which to communicate with other nodes in |
2788 | + the cluster. | |
2789 | + | |
24613191 | 2790 | + If no value is set here, cluster support will be disabled by default. |
2791 | + | |
ad8f4a28 AM |
2792 | + config TOI_DEFAULT_CLUSTER_KEY |
2793 | + string "Default cluster key" | |
2794 | + default "Default" | |
2795 | + depends on TOI_CLUSTER | |
2796 | + ---help--- | |
2797 | + The default key used by this node. All nodes in the same cluster | |
2798 | + have the same key. Multiple clusters may coexist on the same lan | |
2799 | + by using different values for this key. | |
2800 | + | |
2801 | + config TOI_CLUSTER_IMAGE_TIMEOUT | |
2802 | + int "Timeout when checking for image" | |
2803 | + default 15 | |
2804 | + depends on TOI_CLUSTER | |
2805 | + ---help--- | |
2806 | + Timeout (seconds) before continuing to boot when waiting to see | |
2807 | + whether other nodes might have an image. Set to -1 to wait | |
2808 | + indefinitely. In WAIT_UNTIL_NODES is non zero, we might continue | |
2809 | + booting sooner than this timeout. | |
2810 | + | |
2811 | + config TOI_CLUSTER_WAIT_UNTIL_NODES | |
2812 | + int "Nodes without image before continuing" | |
2813 | + default 0 | |
2814 | + depends on TOI_CLUSTER | |
2815 | + ---help--- | |
2816 | + When booting and no image is found, we wait to see if other nodes | |
2817 | + have an image before continuing to boot. This value lets us | |
2818 | + continue after seeing a certain number of nodes without an image, | |
2819 | + instead of continuing to wait for the timeout. Set to 0 to only | |
2820 | + use the timeout. | |
2821 | + | |
2822 | + config TOI_DEFAULT_CLUSTER_PRE_HIBERNATE | |
2823 | + string "Default pre-hibernate script" | |
2824 | + depends on TOI_CLUSTER | |
2825 | + ---help--- | |
2826 | + The default script to be called when starting to hibernate. | |
2827 | + | |
2828 | + config TOI_DEFAULT_CLUSTER_POST_HIBERNATE | |
2829 | + string "Default post-hibernate script" | |
2830 | + depends on TOI_CLUSTER | |
2831 | + ---help--- | |
2832 | + The default script to be called after resuming from hibernation. | |
2833 | + | |
4e97e4e9 | 2834 | + config TOI_DEFAULT_WAIT |
2835 | + int "Default waiting time for emergency boot messages" | |
2836 | + default "25" | |
2837 | + range -1 32768 | |
2838 | + depends on TOI_CORE | |
2839 | + help | |
2840 | + TuxOnIce can display warnings very early in the process of resuming, | |
2841 | + if (for example) it appears that you have booted a kernel that doesn't | |
2842 | + match an image on disk. It can then give you the opportunity to either | |
2843 | + continue booting that kernel, or reboot the machine. This option can be | |
2844 | + used to control how long to wait in such circumstances. -1 means wait | |
2845 | + forever. 0 means don't wait at all (do the default action, which will | |
2846 | + generally be to continue booting and remove the image). Values of 1 or | |
2847 | + more indicate a number of seconds (up to 255) to wait before doing the | |
2848 | + default. | |
2849 | + | |
f3e0dcc9 PS |
2850 | + config TOI_DEFAULT_EXTRA_PAGES_ALLOWANCE |
2851 | + int "Default extra pages allowance" | |
2852 | + default "500" | |
2853 | + range 500 32768 | |
2854 | + depends on TOI_CORE | |
2855 | + help | |
2856 | + This value controls the default for the allowance TuxOnIce makes for | |
2857 | + drivers to allocate extra memory during the atomic copy. The default | |
2858 | + value of 500 will be okay if you're not using DRI. If you are using | |
2859 | + DRI, the easiest way to find what value to use is to try to hibernate | |
2860 | + and look at how many pages were actually needed in the sysfs entry | |
2861 | + /sys/power/tuxonice/debug_info (first number on the last line), adding | |
2862 | + a little extra because the value is not always the same. | |
2863 | + | |
1838f965 | 2864 | + config TOI_CHECKSUM |
2865 | + bool "Checksum pageset2" | |
2866 | + default n | |
ad8f4a28 | 2867 | + depends on TOI_CORE |
1838f965 | 2868 | + select CRYPTO |
2869 | + select CRYPTO_ALGAPI | |
2870 | + select CRYPTO_MD4 | |
2871 | + ---help--- | |
2872 | + Adds support for checksumming pageset2 pages, to ensure you really get an | |
2873 | + atomic copy. Since some filesystems (XFS especially) change metadata even | |
2874 | + when there's no other activity, we need this to check for pages that have | |
2875 | + been changed while we were saving the page cache. If your debugging output | |
2876 | + always says no pages were resaved, you may be able to safely disable this | |
2877 | + option. | |
24613191 | 2878 | + |
1838f965 | 2879 | +config TOI |
24613191 | 2880 | + bool |
1838f965 | 2881 | + depends on TOI_CORE!=n |
24613191 | 2882 | + default y |
2883 | + | |
4e97e4e9 | 2884 | +config TOI_EXPORTS |
24613191 | 2885 | + bool |
1838f965 | 2886 | + depends on TOI_SWAP=m || TOI_FILE=m || \ |
2887 | + TOI_CRYPTO=m || TOI_CLUSTER=m || \ | |
2888 | + TOI_USERUI=m || TOI_CORE=m | |
24613191 | 2889 | + default y |
2890 | + | |
4e97e4e9 | 2891 | config APM_EMULATION |
2892 | tristate "Advanced Power Management Emulation" | |
2893 | depends on PM && SYS_SUPPORTS_APM_EMULATION | |
2894 | diff --git a/kernel/power/Makefile b/kernel/power/Makefile | |
1838f965 | 2895 | index 597823b..61d7360 100644 |
4e97e4e9 | 2896 | --- a/kernel/power/Makefile |
2897 | +++ b/kernel/power/Makefile | |
1838f965 | 2898 | @@ -4,6 +4,35 @@ EXTRA_CFLAGS += -DDEBUG |
f3e0dcc9 | 2899 | endif |
24613191 | 2900 | |
f3e0dcc9 | 2901 | obj-y := main.o |
24613191 | 2902 | + |
4e97e4e9 | 2903 | +tuxonice_core-objs := tuxonice_modules.o tuxonice_sysfs.o tuxonice_highlevel.o \ |
2904 | + tuxonice_io.o tuxonice_pagedir.o tuxonice_prepare_image.o \ | |
2905 | + tuxonice_extent.o tuxonice_pageflags.o tuxonice_ui.o \ | |
2906 | + tuxonice_power_off.o tuxonice_atomic_copy.o | |
24613191 | 2907 | + |
4e97e4e9 | 2908 | +obj-$(CONFIG_TOI) += tuxonice_builtin.o |
24613191 | 2909 | + |
ad8f4a28 AM |
2910 | +ifdef CONFIG_PM_DEBUG |
2911 | +tuxonice_core-objs += tuxonice_alloc.o | |
2912 | +endif | |
2913 | + | |
4e97e4e9 | 2914 | +ifdef CONFIG_TOI_CHECKSUM |
2915 | +tuxonice_core-objs += tuxonice_checksum.o | |
24613191 | 2916 | +endif |
2917 | + | |
2918 | +ifdef CONFIG_NET | |
4e97e4e9 | 2919 | +tuxonice_core-objs += tuxonice_storage.o tuxonice_netlink.o |
24613191 | 2920 | +endif |
2921 | + | |
4e97e4e9 | 2922 | +obj-$(CONFIG_TOI_CORE) += tuxonice_core.o |
2923 | +obj-$(CONFIG_TOI_CRYPTO) += tuxonice_compress.o | |
24613191 | 2924 | + |
4e97e4e9 | 2925 | +obj-$(CONFIG_TOI_SWAP) += tuxonice_block_io.o tuxonice_swap.o |
2926 | +obj-$(CONFIG_TOI_FILE) += tuxonice_block_io.o tuxonice_file.o | |
2927 | +obj-$(CONFIG_TOI_CLUSTER) += tuxonice_cluster.o | |
24613191 | 2928 | + |
4e97e4e9 | 2929 | +obj-$(CONFIG_TOI_USERUI) += tuxonice_userui.o |
73c609d5 | 2930 | + |
f3e0dcc9 PS |
2931 | obj-$(CONFIG_PM_SLEEP) += process.o console.o |
2932 | obj-$(CONFIG_HIBERNATION) += swsusp.o disk.o snapshot.o swap.o user.o | |
2933 | ||
1838f965 | 2934 | diff --git a/kernel/power/console.c b/kernel/power/console.c |
2935 | index b8628be..0d11c15 100644 | |
2936 | --- a/kernel/power/console.c | |
2937 | +++ b/kernel/power/console.c | |
2938 | @@ -68,6 +68,7 @@ int pm_prepare_console(void) | |
2939 | kmsg_redirect = SUSPEND_CONSOLE; | |
2940 | return 0; | |
2941 | } | |
2942 | +EXPORT_SYMBOL_GPL(pm_prepare_console); | |
2943 | ||
2944 | void pm_restore_console(void) | |
2945 | { | |
2946 | @@ -80,4 +81,5 @@ void pm_restore_console(void) | |
2947 | release_console_sem(); | |
2948 | kmsg_redirect = orig_kmsg; | |
2949 | } | |
2950 | +EXPORT_SYMBOL_GPL(pm_restore_console); | |
2951 | #endif | |
4e97e4e9 | 2952 | diff --git a/kernel/power/disk.c b/kernel/power/disk.c |
1838f965 | 2953 | index bbd85c6..3953914 100644 |
4e97e4e9 | 2954 | --- a/kernel/power/disk.c |
2955 | +++ b/kernel/power/disk.c | |
1838f965 | 2956 | @@ -24,10 +24,12 @@ |
2957 | #include <linux/ftrace.h> | |
4e97e4e9 | 2958 | |
2959 | #include "power.h" | |
1838f965 | 2960 | - |
4e97e4e9 | 2961 | +#include "tuxonice.h" |
4e97e4e9 | 2962 | |
2963 | static int noresume = 0; | |
7f9d2ee0 | 2964 | -static char resume_file[256] = CONFIG_PM_STD_PARTITION; |
2965 | +char resume_file[256] = CONFIG_PM_STD_PARTITION; | |
1838f965 | 2966 | +EXPORT_SYMBOL_GPL(resume_file); |
2967 | + | |
7f9d2ee0 | 2968 | dev_t swsusp_resume_device; |
2969 | sector_t swsusp_resume_block; | |
2970 | ||
1838f965 | 2971 | @@ -105,55 +107,60 @@ static int hibernation_test(int level) { return 0; } |
ad8f4a28 AM |
2972 | * hibernation |
2973 | */ | |
2974 | ||
7f9d2ee0 | 2975 | -static int platform_begin(int platform_mode) |
2976 | +int platform_begin(int platform_mode) | |
ad8f4a28 AM |
2977 | { |
2978 | return (platform_mode && hibernation_ops) ? | |
7f9d2ee0 | 2979 | hibernation_ops->begin() : 0; |
1838f965 | 2980 | } |
2981 | +EXPORT_SYMBOL_GPL(platform_begin); | |
2982 | ||
2983 | /** | |
2984 | * platform_end - tell the platform driver that we've entered the | |
2985 | * working state | |
2986 | */ | |
2987 | ||
7f9d2ee0 | 2988 | -static void platform_end(int platform_mode) |
2989 | +void platform_end(int platform_mode) | |
2990 | { | |
2991 | if (platform_mode && hibernation_ops) | |
2992 | hibernation_ops->end(); | |
1838f965 | 2993 | } |
2994 | +EXPORT_SYMBOL_GPL(platform_end); | |
2995 | ||
2996 | /** | |
2997 | * platform_pre_snapshot - prepare the machine for hibernation using the | |
ad8f4a28 AM |
2998 | * platform driver if so configured and return an error code if it fails |
2999 | */ | |
4e97e4e9 | 3000 | |
ad8f4a28 AM |
3001 | -static int platform_pre_snapshot(int platform_mode) |
3002 | +int platform_pre_snapshot(int platform_mode) | |
3003 | { | |
3004 | return (platform_mode && hibernation_ops) ? | |
3005 | hibernation_ops->pre_snapshot() : 0; | |
1838f965 | 3006 | } |
3007 | +EXPORT_SYMBOL_GPL(platform_pre_snapshot); | |
3008 | ||
3009 | /** | |
3010 | * platform_leave - prepare the machine for switching to the normal mode | |
ad8f4a28 AM |
3011 | * of operation using the platform driver (called with interrupts disabled) |
3012 | */ | |
4e97e4e9 | 3013 | |
ad8f4a28 AM |
3014 | -static void platform_leave(int platform_mode) |
3015 | +void platform_leave(int platform_mode) | |
3016 | { | |
3017 | if (platform_mode && hibernation_ops) | |
3018 | hibernation_ops->leave(); | |
1838f965 | 3019 | } |
3020 | +EXPORT_SYMBOL_GPL(platform_leave); | |
3021 | ||
3022 | /** | |
3023 | * platform_finish - switch the machine to the normal mode of operation | |
ad8f4a28 AM |
3024 | * using the platform driver (must be called after platform_prepare()) |
3025 | */ | |
4e97e4e9 | 3026 | |
ad8f4a28 AM |
3027 | -static void platform_finish(int platform_mode) |
3028 | +void platform_finish(int platform_mode) | |
3029 | { | |
3030 | if (platform_mode && hibernation_ops) | |
3031 | hibernation_ops->finish(); | |
1838f965 | 3032 | } |
3033 | +EXPORT_SYMBOL_GPL(platform_finish); | |
3034 | ||
3035 | /** | |
3036 | * platform_pre_restore - prepare the platform for the restoration from a | |
3037 | @@ -161,11 +168,12 @@ static void platform_finish(int platform_mode) | |
ad8f4a28 AM |
3038 | * called, platform_restore_cleanup() must be called. |
3039 | */ | |
3040 | ||
3041 | -static int platform_pre_restore(int platform_mode) | |
3042 | +int platform_pre_restore(int platform_mode) | |
3043 | { | |
3044 | return (platform_mode && hibernation_ops) ? | |
3045 | hibernation_ops->pre_restore() : 0; | |
1838f965 | 3046 | } |
3047 | +EXPORT_SYMBOL_GPL(platform_pre_restore); | |
3048 | ||
3049 | /** | |
3050 | * platform_restore_cleanup - switch the platform to the normal mode of | |
3051 | @@ -174,22 +182,24 @@ static int platform_pre_restore(int platform_mode) | |
ad8f4a28 AM |
3052 | * regardless of the result of platform_pre_restore(). |
3053 | */ | |
3054 | ||
3055 | -static void platform_restore_cleanup(int platform_mode) | |
3056 | +void platform_restore_cleanup(int platform_mode) | |
3057 | { | |
3058 | if (platform_mode && hibernation_ops) | |
3059 | hibernation_ops->restore_cleanup(); | |
1838f965 | 3060 | } |
3061 | +EXPORT_SYMBOL_GPL(platform_restore_cleanup); | |
3062 | ||
3063 | /** | |
3064 | * platform_recover - recover the platform from a failure to suspend | |
3065 | * devices. | |
3066 | */ | |
3067 | ||
3068 | -static void platform_recover(int platform_mode) | |
3069 | +void platform_recover(int platform_mode) | |
3070 | { | |
3071 | if (platform_mode && hibernation_ops && hibernation_ops->recover) | |
3072 | hibernation_ops->recover(); | |
3073 | } | |
3074 | +EXPORT_SYMBOL_GPL(platform_recover); | |
3075 | ||
3076 | /** | |
3077 | * create_image - freeze devices that need to be frozen with interrupts | |
3078 | @@ -393,6 +403,7 @@ int hibernation_restore(int platform_mode) | |
3079 | pm_restore_console(); | |
3080 | return error; | |
3081 | } | |
3082 | +EXPORT_SYMBOL_GPL(hibernation_platform_enter); | |
3083 | ||
3084 | /** | |
3085 | * hibernation_platform_enter - enter the hibernation state using the | |
3086 | @@ -508,6 +519,9 @@ int hibernate(void) | |
4e97e4e9 | 3087 | { |
3088 | int error; | |
3089 | ||
4e97e4e9 | 3090 | + if (test_action_state(TOI_REPLACE_SWSUSP)) |
1838f965 | 3091 | + return toi_try_hibernate(); |
24613191 | 3092 | + |
4e97e4e9 | 3093 | mutex_lock(&pm_mutex); |
3094 | /* The snapshot device should not be opened while we're running */ | |
3095 | if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { | |
1838f965 | 3096 | @@ -580,10 +594,19 @@ int hibernate(void) |
4e97e4e9 | 3097 | * |
3098 | */ | |
3099 | ||
3100 | -static int software_resume(void) | |
3101 | +int software_resume(void) | |
3102 | { | |
3103 | int error; | |
3104 | unsigned int flags; | |
4e97e4e9 | 3105 | + resume_attempted = 1; |
24613191 | 3106 | + |
ad8f4a28 | 3107 | + /* |
4e97e4e9 | 3108 | + * We can't know (until an image header - if any - is loaded), whether |
3109 | + * we did override swsusp. We therefore ensure that both are tried. | |
3110 | + */ | |
3111 | + if (test_action_state(TOI_REPLACE_SWSUSP)) | |
ad8f4a28 | 3112 | + printk(KERN_INFO "Replacing swsusp.\n"); |
4e97e4e9 | 3113 | + toi_try_resume(); |
ad8f4a28 AM |
3114 | |
3115 | /* | |
3116 | * name_to_dev_t() below takes a sysfs buffer mutex when sysfs | |
1838f965 | 3117 | @@ -882,6 +905,7 @@ static int __init resume_offset_setup(char *str) |
4e97e4e9 | 3118 | static int __init noresume_setup(char *str) |
3119 | { | |
3120 | noresume = 1; | |
3121 | + set_toi_state(TOI_NORESUME_SPECIFIED); | |
3122 | return 1; | |
3123 | } | |
3124 | ||
1838f965 | 3125 | diff --git a/kernel/power/main.c b/kernel/power/main.c |
3126 | index 540b16b..f2ad48c 100644 | |
3127 | --- a/kernel/power/main.c | |
3128 | +++ b/kernel/power/main.c | |
3129 | @@ -26,6 +26,7 @@ | |
3130 | #include "power.h" | |
3131 | ||
3132 | DEFINE_MUTEX(pm_mutex); | |
3133 | +EXPORT_SYMBOL_GPL(pm_mutex); | |
3134 | ||
3135 | unsigned int pm_flags; | |
3136 | EXPORT_SYMBOL(pm_flags); | |
3137 | @@ -34,7 +35,8 @@ EXPORT_SYMBOL(pm_flags); | |
3138 | ||
3139 | /* Routines for PM-transition notifications */ | |
3140 | ||
3141 | -static BLOCKING_NOTIFIER_HEAD(pm_chain_head); | |
3142 | +BLOCKING_NOTIFIER_HEAD(pm_chain_head); | |
3143 | +EXPORT_SYMBOL_GPL(pm_chain_head); | |
3144 | ||
3145 | int register_pm_notifier(struct notifier_block *nb) | |
3146 | { | |
3147 | @@ -204,6 +206,7 @@ void suspend_set_ops(struct platform_suspend_ops *ops) | |
3148 | suspend_ops = ops; | |
3149 | mutex_unlock(&pm_mutex); | |
3150 | } | |
3151 | +EXPORT_SYMBOL_GPL(pm_notifier_call_chain); | |
3152 | ||
3153 | /** | |
3154 | * suspend_valid_only_mem - generic memory-only valid callback | |
3155 | @@ -441,6 +444,7 @@ static int enter_state(suspend_state_t state) | |
3156 | mutex_unlock(&pm_mutex); | |
3157 | return error; | |
3158 | } | |
3159 | +EXPORT_SYMBOL_GPL(suspend_devices_and_enter); | |
3160 | ||
3161 | ||
3162 | /** | |
3163 | @@ -463,6 +467,7 @@ EXPORT_SYMBOL(pm_suspend); | |
3164 | #endif /* CONFIG_SUSPEND */ | |
3165 | ||
3166 | struct kobject *power_kobj; | |
3167 | +EXPORT_SYMBOL_GPL(power_kobj); | |
3168 | ||
3169 | /** | |
3170 | * state - control system power state. | |
4e97e4e9 | 3171 | diff --git a/kernel/power/power.h b/kernel/power/power.h |
1838f965 | 3172 | index acc0c10..777fc05 100644 |
4e97e4e9 | 3173 | --- a/kernel/power/power.h |
3174 | +++ b/kernel/power/power.h | |
1838f965 | 3175 | @@ -1,3 +1,10 @@ |
24613191 | 3176 | +/* |
1838f965 | 3177 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 3178 | + */ |
ad8f4a28 AM |
3179 | + |
3180 | +#ifndef KERNEL_POWER_POWER_H | |
3181 | +#define KERNEL_POWER_POWER_H | |
24613191 | 3182 | + |
4e97e4e9 | 3183 | #include <linux/suspend.h> |
7f9d2ee0 | 3184 | #include <linux/suspend_ioctls.h> |
4e97e4e9 | 3185 | #include <linux/utsname.h> |
1838f965 | 3186 | @@ -21,18 +28,22 @@ struct swsusp_info { |
ad8f4a28 AM |
3187 | extern int arch_hibernation_header_save(void *addr, unsigned int max_size); |
3188 | extern int arch_hibernation_header_restore(void *addr); | |
3189 | ||
3190 | -static inline int init_header_complete(struct swsusp_info *info) | |
3191 | +static inline int init_swsusp_header_complete(struct swsusp_info *info) | |
3192 | { | |
3193 | return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE); | |
3194 | } | |
4e97e4e9 | 3195 | |
ad8f4a28 AM |
3196 | -static inline char *check_image_kernel(struct swsusp_info *info) |
3197 | +static inline char *check_swsusp_image_kernel(struct swsusp_info *info) | |
3198 | { | |
3199 | return arch_hibernation_header_restore(info) ? | |
3200 | "architecture specific data" : NULL; | |
3201 | } | |
3202 | +#else | |
3203 | +extern char *check_swsusp_image_kernel(struct swsusp_info *info); | |
3204 | #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ | |
3205 | +extern int init_swsusp_header(struct swsusp_info *info); | |
4e97e4e9 | 3206 | |
4e97e4e9 | 3207 | +extern char resume_file[256]; |
3208 | /* | |
3209 | * Keep some memory free so that I/O operations can succeed without paging | |
3210 | * [Might this be more than 4 MB?] | |
1838f965 | 3211 | @@ -49,6 +60,7 @@ static inline char *check_image_kernel(struct swsusp_info *info) |
3212 | extern int hibernation_snapshot(int platform_mode); | |
3213 | extern int hibernation_restore(int platform_mode); | |
3214 | extern int hibernation_platform_enter(void); | |
3215 | +extern void platform_recover(int platform_mode); | |
3216 | #endif | |
3217 | ||
3218 | extern int pfn_is_nosave(unsigned long); | |
3219 | @@ -63,6 +75,8 @@ static struct kobj_attribute _name##_attr = { \ | |
7f9d2ee0 | 3220 | .store = _name##_store, \ |
3221 | } | |
4e97e4e9 | 3222 | |
3223 | +extern struct pbe *restore_pblist; | |
3224 | + | |
3225 | /* Preferred image size in bytes (default 500 MB) */ | |
3226 | extern unsigned long image_size; | |
3227 | extern int in_suspend; | |
1838f965 | 3228 | @@ -223,3 +237,90 @@ static inline void suspend_thaw_processes(void) |
7f9d2ee0 | 3229 | { |
4e97e4e9 | 3230 | } |
7f9d2ee0 | 3231 | #endif |
4e97e4e9 | 3232 | + |
3233 | +extern struct page *saveable_page(unsigned long pfn); | |
24613191 | 3234 | +#ifdef CONFIG_HIGHMEM |
4e97e4e9 | 3235 | +extern struct page *saveable_highmem_page(unsigned long pfn); |
3236 | +#else | |
3237 | +static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; } | |
3238 | +#endif | |
24613191 | 3239 | + |
4e97e4e9 | 3240 | +#define PBES_PER_PAGE (PAGE_SIZE / sizeof(struct pbe)) |
ad8f4a28 AM |
3241 | +extern struct list_head nosave_regions; |
3242 | + | |
3243 | +/** | |
3244 | + * This structure represents a range of page frames the contents of which | |
3245 | + * should not be saved during the suspend. | |
3246 | + */ | |
3247 | + | |
3248 | +struct nosave_region { | |
3249 | + struct list_head list; | |
3250 | + unsigned long start_pfn; | |
3251 | + unsigned long end_pfn; | |
3252 | +}; | |
3253 | + | |
1838f965 | 3254 | +#ifndef PHYS_PFN_OFFSET |
3255 | +#define PHYS_PFN_OFFSET 0 | |
3256 | +#endif | |
3257 | + | |
3258 | +#define ZONE_START(thiszone) ((thiszone)->zone_start_pfn - PHYS_PFN_OFFSET) | |
3259 | + | |
3260 | +#define BM_END_OF_MAP (~0UL) | |
3261 | + | |
3262 | +#define BM_BITS_PER_BLOCK (PAGE_SIZE << 3) | |
3263 | + | |
3264 | +struct bm_block { | |
3265 | + struct bm_block *next; /* next element of the list */ | |
3266 | + unsigned long start_pfn; /* pfn represented by the first bit */ | |
3267 | + unsigned long end_pfn; /* pfn represented by the last bit plus 1 */ | |
3268 | + unsigned long *data; /* bitmap representing pages */ | |
3269 | +}; | |
3270 | + | |
3271 | +struct zone_bitmap { | |
3272 | + struct zone_bitmap *next; /* next element of the list */ | |
3273 | + unsigned long start_pfn; /* minimal pfn in this zone */ | |
3274 | + unsigned long end_pfn; /* maximal pfn in this zone plus 1 */ | |
3275 | + struct bm_block *bm_blocks; /* list of bitmap blocks */ | |
3276 | + struct bm_block *cur_block; /* recently used bitmap block */ | |
3277 | +}; | |
3278 | + | |
3279 | +/* strcut bm_position is used for browsing memory bitmaps */ | |
3280 | + | |
3281 | +struct bm_position { | |
3282 | + struct zone_bitmap *zone_bm; | |
3283 | + struct bm_block *block; | |
3284 | + int bit; | |
3285 | +}; | |
3286 | + | |
3287 | +struct memory_bitmap { | |
3288 | + struct zone_bitmap *zone_bm_list; /* list of zone bitmaps */ | |
3289 | + struct linked_page *p_list; /* list of pages used to store zone | |
3290 | + * bitmap objects and bitmap block | |
3291 | + * objects | |
3292 | + */ | |
3293 | + struct bm_position cur; /* most recently used bit position */ | |
3294 | +}; | |
3295 | + | |
3296 | +extern int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, | |
3297 | + int safe_needed); | |
3298 | +extern void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); | |
3299 | +extern void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn); | |
3300 | +extern void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn); | |
3301 | +extern int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn); | |
3302 | +extern unsigned long memory_bm_next_pfn(struct memory_bitmap *bm); | |
3303 | +extern void memory_bm_position_reset(struct memory_bitmap *bm); | |
3304 | +extern void memory_bm_clear(struct memory_bitmap *bm); | |
3305 | +extern void memory_bm_copy(struct memory_bitmap *source, | |
3306 | + struct memory_bitmap *dest); | |
3307 | +extern void memory_bm_dup(struct memory_bitmap *source, | |
3308 | + struct memory_bitmap *dest); | |
3309 | + | |
3310 | +#ifdef CONFIG_TOI | |
3311 | +struct toi_module_ops; | |
3312 | +extern int memory_bm_read(struct memory_bitmap *bm, int (*rw_chunk) | |
3313 | + (int rw, struct toi_module_ops *owner, char *buffer, int buffer_size)); | |
3314 | +extern int memory_bm_write(struct memory_bitmap *bm, int (*rw_chunk) | |
3315 | + (int rw, struct toi_module_ops *owner, char *buffer, int buffer_size)); | |
3316 | +#endif | |
3317 | + | |
ad8f4a28 | 3318 | +#endif |
4e97e4e9 | 3319 | diff --git a/kernel/power/process.c b/kernel/power/process.c |
1838f965 | 3320 | index 278946a..6035bbf 100644 |
4e97e4e9 | 3321 | --- a/kernel/power/process.c |
3322 | +++ b/kernel/power/process.c | |
ad8f4a28 | 3323 | @@ -13,6 +13,10 @@ |
4e97e4e9 | 3324 | #include <linux/module.h> |
3325 | #include <linux/syscalls.h> | |
3326 | #include <linux/freezer.h> | |
3327 | +#include <linux/buffer_head.h> | |
24613191 | 3328 | + |
ad8f4a28 | 3329 | +int freezer_state; |
1838f965 | 3330 | +EXPORT_SYMBOL_GPL(freezer_state); |
4e97e4e9 | 3331 | |
3332 | /* | |
3333 | * Timeout for stopping processes | |
fea155ea | 3334 | @@ -201,7 +205,8 @@ static int try_to_freeze_tasks(bool sig_only) |
4e97e4e9 | 3335 | do_each_thread(g, p) { |
3336 | task_lock(p); | |
3337 | if (freezing(p) && !freezer_should_skip(p)) | |
3338 | - printk(KERN_ERR " %s\n", p->comm); | |
ad8f4a28 AM |
3339 | + printk(KERN_ERR " %s (%d) failed to freeze.\n", |
3340 | + p->comm, p->pid); | |
4e97e4e9 | 3341 | cancel_freezing(p); |
3342 | task_unlock(p); | |
3343 | } while_each_thread(g, p); | |
1838f965 | 3344 | @@ -221,22 +226,31 @@ int freeze_processes(void) |
4e97e4e9 | 3345 | { |
3346 | int error; | |
3347 | ||
ad8f4a28 AM |
3348 | - printk("Freezing user space processes ... "); |
3349 | + printk(KERN_INFO "Stopping fuse filesystems.\n"); | |
3350 | + freeze_filesystems(FS_FREEZER_FUSE); | |
4e97e4e9 | 3351 | + freezer_state = FREEZER_FILESYSTEMS_FROZEN; |
ad8f4a28 | 3352 | + printk(KERN_INFO "Freezing user space processes ... "); |
fea155ea | 3353 | error = try_to_freeze_tasks(true); |
4e97e4e9 | 3354 | if (error) |
ad8f4a28 AM |
3355 | goto Exit; |
3356 | - printk("done.\n"); | |
3357 | + printk(KERN_INFO "done.\n"); | |
4e97e4e9 | 3358 | |
ad8f4a28 AM |
3359 | - printk("Freezing remaining freezable tasks ... "); |
3360 | + sys_sync(); | |
3361 | + printk(KERN_INFO "Stopping normal filesystems.\n"); | |
3362 | + freeze_filesystems(FS_FREEZER_NORMAL); | |
4e97e4e9 | 3363 | + freezer_state = FREEZER_USERSPACE_FROZEN; |
ad8f4a28 | 3364 | + printk(KERN_INFO "Freezing remaining freezable tasks ... "); |
fea155ea | 3365 | error = try_to_freeze_tasks(false); |
4e97e4e9 | 3366 | if (error) |
ad8f4a28 | 3367 | goto Exit; |
7f9d2ee0 | 3368 | printk("done."); |
4e97e4e9 | 3369 | + freezer_state = FREEZER_FULLY_ON; |
ad8f4a28 | 3370 | Exit: |
4e97e4e9 | 3371 | BUG_ON(in_atomic()); |
ad8f4a28 | 3372 | printk("\n"); |
1838f965 | 3373 | return error; |
3374 | } | |
3375 | +EXPORT_SYMBOL_GPL(freeze_processes); | |
3376 | ||
3377 | static void thaw_tasks(bool nosig_only) | |
3378 | { | |
3379 | @@ -257,11 +271,42 @@ static void thaw_tasks(bool nosig_only) | |
4e97e4e9 | 3380 | |
3381 | void thaw_processes(void) | |
3382 | { | |
ad8f4a28 | 3383 | - printk("Restarting tasks ... "); |
fea155ea | 3384 | - thaw_tasks(true); |
4e97e4e9 | 3385 | + int old_state = freezer_state; |
24613191 | 3386 | + |
4e97e4e9 | 3387 | + if (old_state == FREEZER_OFF) |
24613191 | 3388 | + return; |
3389 | + | |
ad8f4a28 | 3390 | + /* |
4e97e4e9 | 3391 | + * Change state beforehand because thawed tasks might submit I/O |
3392 | + * immediately. | |
3393 | + */ | |
3394 | + freezer_state = FREEZER_OFF; | |
24613191 | 3395 | + |
ad8f4a28 AM |
3396 | + printk(KERN_INFO "Restarting all filesystems ...\n"); |
3397 | + thaw_filesystems(FS_FREEZER_ALL); | |
24613191 | 3398 | + |
ad8f4a28 | 3399 | + printk(KERN_INFO "Restarting tasks ... "); |
24613191 | 3400 | + |
4e97e4e9 | 3401 | + if (old_state == FREEZER_FULLY_ON) |
fea155ea PS |
3402 | + thaw_tasks(true); |
3403 | thaw_tasks(false); | |
4e97e4e9 | 3404 | schedule(); |
3405 | printk("done.\n"); | |
3406 | } | |
1838f965 | 3407 | +EXPORT_SYMBOL_GPL(thaw_processes); |
4e97e4e9 | 3408 | |
fea155ea PS |
3409 | EXPORT_SYMBOL(refrigerator); |
3410 | + | |
4e97e4e9 | 3411 | +void thaw_kernel_threads(void) |
3412 | +{ | |
3413 | + freezer_state = FREEZER_USERSPACE_FROZEN; | |
ad8f4a28 AM |
3414 | + printk(KERN_INFO "Restarting normal filesystems.\n"); |
3415 | + thaw_filesystems(FS_FREEZER_NORMAL); | |
fea155ea | 3416 | + thaw_tasks(true); |
4e97e4e9 | 3417 | +} |
1838f965 | 3418 | + |
3419 | +/* | |
3420 | + * It's ugly putting this EXPORT down here, but it's necessary so that it | |
3421 | + * doesn't matter whether the fs-freezing patch is applied or not. | |
3422 | + */ | |
3423 | +EXPORT_SYMBOL_GPL(thaw_kernel_threads); | |
4e97e4e9 | 3424 | diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c |
1838f965 | 3425 | index 5d2ab83..8fc59e9 100644 |
4e97e4e9 | 3426 | --- a/kernel/power/snapshot.c |
3427 | +++ b/kernel/power/snapshot.c | |
1838f965 | 3428 | @@ -33,6 +33,8 @@ |
4e97e4e9 | 3429 | #include <asm/io.h> |
3430 | ||
3431 | #include "power.h" | |
3432 | +#include "tuxonice_builtin.h" | |
1838f965 | 3433 | +#include "tuxonice_pagedir.h" |
4e97e4e9 | 3434 | |
3435 | static int swsusp_page_is_free(struct page *); | |
3436 | static void swsusp_set_page_forbidden(struct page *); | |
1838f965 | 3437 | @@ -44,6 +46,10 @@ static void swsusp_unset_page_forbidden(struct page *); |
4e97e4e9 | 3438 | * directly to their "original" page frames. |
3439 | */ | |
3440 | struct pbe *restore_pblist; | |
1838f965 | 3441 | +EXPORT_SYMBOL_GPL(restore_pblist); |
3442 | + | |
4e97e4e9 | 3443 | +int resume_attempted; |
3444 | +EXPORT_SYMBOL_GPL(resume_attempted); | |
4e97e4e9 | 3445 | |
3446 | /* Pointer to an auxiliary buffer (1 page) */ | |
3447 | static void *buffer; | |
1838f965 | 3448 | @@ -86,6 +92,9 @@ static void *get_image_page(gfp_t gfp_mask, int safe_needed) |
4e97e4e9 | 3449 | |
3450 | unsigned long get_safe_page(gfp_t gfp_mask) | |
3451 | { | |
4e97e4e9 | 3452 | + if (toi_running) |
3453 | + return toi_get_nonconflicting_page(); | |
24613191 | 3454 | + |
4e97e4e9 | 3455 | return (unsigned long)get_image_page(gfp_mask, PG_SAFE); |
3456 | } | |
3457 | ||
1838f965 | 3458 | @@ -228,50 +237,14 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave) |
3459 | * the represented memory area. | |
3460 | */ | |
4e97e4e9 | 3461 | |
1838f965 | 3462 | -#define BM_END_OF_MAP (~0UL) |
ad8f4a28 | 3463 | - |
1838f965 | 3464 | -#define BM_BITS_PER_BLOCK (PAGE_SIZE << 3) |
3465 | - | |
3466 | -struct bm_block { | |
3467 | - struct bm_block *next; /* next element of the list */ | |
3468 | - unsigned long start_pfn; /* pfn represented by the first bit */ | |
3469 | - unsigned long end_pfn; /* pfn represented by the last bit plus 1 */ | |
3470 | - unsigned long *data; /* bitmap representing pages */ | |
ad8f4a28 AM |
3471 | -}; |
3472 | - | |
1838f965 | 3473 | static inline unsigned long bm_block_bits(struct bm_block *bb) |
3474 | { | |
3475 | return bb->end_pfn - bb->start_pfn; | |
3476 | } | |
4e97e4e9 | 3477 | |
1838f965 | 3478 | -struct zone_bitmap { |
3479 | - struct zone_bitmap *next; /* next element of the list */ | |
3480 | - unsigned long start_pfn; /* minimal pfn in this zone */ | |
3481 | - unsigned long end_pfn; /* maximal pfn in this zone plus 1 */ | |
3482 | - struct bm_block *bm_blocks; /* list of bitmap blocks */ | |
3483 | - struct bm_block *cur_block; /* recently used bitmap block */ | |
3484 | -}; | |
3485 | - | |
3486 | -/* strcut bm_position is used for browsing memory bitmaps */ | |
3487 | - | |
3488 | -struct bm_position { | |
3489 | - struct zone_bitmap *zone_bm; | |
3490 | - struct bm_block *block; | |
3491 | - int bit; | |
3492 | -}; | |
3493 | - | |
3494 | -struct memory_bitmap { | |
3495 | - struct zone_bitmap *zone_bm_list; /* list of zone bitmaps */ | |
3496 | - struct linked_page *p_list; /* list of pages used to store zone | |
3497 | - * bitmap objects and bitmap block | |
3498 | - * objects | |
3499 | - */ | |
3500 | - struct bm_position cur; /* most recently used bit position */ | |
3501 | -}; | |
3502 | - | |
3503 | /* Functions that operate on memory bitmaps */ | |
4e97e4e9 | 3504 | |
1838f965 | 3505 | -static void memory_bm_position_reset(struct memory_bitmap *bm) |
3506 | +void memory_bm_position_reset(struct memory_bitmap *bm) | |
4e97e4e9 | 3507 | { |
1838f965 | 3508 | struct zone_bitmap *zone_bm; |
4e97e4e9 | 3509 | |
1838f965 | 3510 | @@ -280,8 +253,9 @@ static void memory_bm_position_reset(struct memory_bitmap *bm) |
3511 | bm->cur.block = zone_bm->bm_blocks; | |
3512 | bm->cur.bit = 0; | |
4e97e4e9 | 3513 | } |
1838f965 | 3514 | +EXPORT_SYMBOL_GPL(memory_bm_position_reset); |
3515 | ||
3516 | -static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); | |
3517 | +void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); | |
4e97e4e9 | 3518 | |
7f9d2ee0 | 3519 | /** |
1838f965 | 3520 | * create_bm_block_list - create a list of block bitmap objects |
3521 | @@ -331,7 +305,7 @@ create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca) | |
3522 | * memory_bm_create - allocate memory for a memory bitmap | |
3523 | */ | |
4e97e4e9 | 3524 | |
1838f965 | 3525 | -static int |
3526 | +int | |
3527 | memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) | |
4e97e4e9 | 3528 | { |
1838f965 | 3529 | struct chain_allocator ca; |
3530 | @@ -406,15 +380,19 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) | |
3531 | memory_bm_free(bm, PG_UNSAFE_CLEAR); | |
3532 | return -ENOMEM; | |
3533 | } | |
3534 | +EXPORT_SYMBOL_GPL(memory_bm_create); | |
3535 | ||
3536 | /** | |
3537 | * memory_bm_free - free memory occupied by the memory bitmap @bm | |
3538 | */ | |
4e97e4e9 | 3539 | |
1838f965 | 3540 | -static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) |
3541 | +void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) | |
4e97e4e9 | 3542 | { |
1838f965 | 3543 | struct zone_bitmap *zone_bm; |
4e97e4e9 | 3544 | |
1838f965 | 3545 | + if (!bm->zone_bm_list) |
3546 | + return; | |
4e97e4e9 | 3547 | + |
1838f965 | 3548 | /* Free the list of bit blocks for each zone_bitmap object */ |
3549 | zone_bm = bm->zone_bm_list; | |
3550 | while (zone_bm) { | |
3551 | @@ -431,6 +409,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) | |
3552 | free_list_of_pages(bm->p_list, clear_nosave_free); | |
3553 | bm->zone_bm_list = NULL; | |
3554 | } | |
3555 | +EXPORT_SYMBOL_GPL(memory_bm_free); | |
4e97e4e9 | 3556 | |
1838f965 | 3557 | /** |
3558 | * memory_bm_find_bit - find the bit in the bitmap @bm that corresponds | |
3559 | @@ -474,7 +453,7 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, | |
3560 | return 0; | |
ad8f4a28 AM |
3561 | } |
3562 | ||
1838f965 | 3563 | -static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn) |
3564 | +void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn) | |
ad8f4a28 | 3565 | { |
1838f965 | 3566 | void *addr; |
3567 | unsigned int bit; | |
3568 | @@ -484,6 +463,7 @@ static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn) | |
3569 | BUG_ON(error); | |
3570 | set_bit(bit, addr); | |
ad8f4a28 | 3571 | } |
1838f965 | 3572 | +EXPORT_SYMBOL_GPL(memory_bm_set_bit); |
ad8f4a28 | 3573 | |
1838f965 | 3574 | static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn) |
ad8f4a28 | 3575 | { |
1838f965 | 3576 | @@ -497,7 +477,7 @@ static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn) |
3577 | return error; | |
ad8f4a28 | 3578 | } |
ad8f4a28 | 3579 | |
1838f965 | 3580 | -static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn) |
3581 | +void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn) | |
3582 | { | |
3583 | void *addr; | |
3584 | unsigned int bit; | |
3585 | @@ -507,8 +487,9 @@ static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn) | |
3586 | BUG_ON(error); | |
3587 | clear_bit(bit, addr); | |
7f9d2ee0 | 3588 | } |
1838f965 | 3589 | +EXPORT_SYMBOL_GPL(memory_bm_clear_bit); |
7f9d2ee0 | 3590 | |
1838f965 | 3591 | -static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) |
3592 | +int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) | |
ad8f4a28 | 3593 | { |
1838f965 | 3594 | void *addr; |
3595 | unsigned int bit; | |
3596 | @@ -518,6 +499,7 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) | |
3597 | BUG_ON(error); | |
3598 | return test_bit(bit, addr); | |
ad8f4a28 | 3599 | } |
1838f965 | 3600 | +EXPORT_SYMBOL_GPL(memory_bm_test_bit); |
ad8f4a28 AM |
3601 | |
3602 | /** | |
1838f965 | 3603 | * memory_bm_next_pfn - find the pfn that corresponds to the next set bit |
3604 | @@ -528,7 +510,7 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) | |
3605 | * this function. | |
3606 | */ | |
ad8f4a28 | 3607 | |
1838f965 | 3608 | -static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) |
3609 | +unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) | |
ad8f4a28 | 3610 | { |
1838f965 | 3611 | struct zone_bitmap *zone_bm; |
3612 | struct bm_block *bb; | |
3613 | @@ -560,19 +542,167 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) | |
3614 | bm->cur.bit = bit + 1; | |
3615 | return bb->start_pfn + bit; | |
3616 | } | |
3617 | +EXPORT_SYMBOL_GPL(memory_bm_next_pfn); | |
ad8f4a28 | 3618 | |
1838f965 | 3619 | -/** |
3620 | - * This structure represents a range of page frames the contents of which | |
3621 | - * should not be saved during the suspend. | |
3622 | - */ | |
3623 | +void memory_bm_clear(struct memory_bitmap *bm) | |
ad8f4a28 | 3624 | +{ |
1838f965 | 3625 | + unsigned long pfn; |
3626 | ||
3627 | -struct nosave_region { | |
3628 | - struct list_head list; | |
3629 | - unsigned long start_pfn; | |
3630 | - unsigned long end_pfn; | |
3631 | -}; | |
3632 | + memory_bm_position_reset(bm); | |
3633 | + pfn = memory_bm_next_pfn(bm); | |
3634 | + while (pfn != BM_END_OF_MAP) { | |
3635 | + memory_bm_clear_bit(bm, pfn); | |
3636 | + pfn = memory_bm_next_pfn(bm); | |
ad8f4a28 | 3637 | + } |
ad8f4a28 | 3638 | +} |
1838f965 | 3639 | +EXPORT_SYMBOL_GPL(memory_bm_clear); |
ad8f4a28 | 3640 | + |
1838f965 | 3641 | +void memory_bm_copy(struct memory_bitmap *source, struct memory_bitmap *dest) |
ad8f4a28 | 3642 | +{ |
1838f965 | 3643 | + unsigned long pfn; |
ad8f4a28 | 3644 | + |
1838f965 | 3645 | + memory_bm_position_reset(source); |
3646 | + pfn = memory_bm_next_pfn(source); | |
3647 | + while (pfn != BM_END_OF_MAP) { | |
3648 | + memory_bm_set_bit(dest, pfn); | |
3649 | + pfn = memory_bm_next_pfn(source); | |
3650 | + } | |
3651 | +} | |
3652 | +EXPORT_SYMBOL_GPL(memory_bm_copy); | |
ad8f4a28 | 3653 | + |
1838f965 | 3654 | +void memory_bm_dup(struct memory_bitmap *source, struct memory_bitmap *dest) |
3655 | +{ | |
3656 | + memory_bm_clear(dest); | |
3657 | + memory_bm_copy(source, dest); | |
3658 | +} | |
3659 | +EXPORT_SYMBOL_GPL(memory_bm_dup); | |
ad8f4a28 | 3660 | + |
1838f965 | 3661 | +#ifdef CONFIG_TOI |
3662 | +int memory_bm_write(struct memory_bitmap *bm, int (*rw_chunk) | |
3663 | + (int rw, struct toi_module_ops *owner, char *buffer, int buffer_size)) | |
3664 | +{ | |
3665 | + int result = 0; | |
3666 | + unsigned int nr = 0; | |
3667 | + struct zone_bitmap *zone_bm; | |
3668 | + struct bm_block *bb; | |
ad8f4a28 | 3669 | + |
1838f965 | 3670 | + if (!bm) |
3671 | + return result; | |
ad8f4a28 | 3672 | + |
1838f965 | 3673 | + for (zone_bm = bm->zone_bm_list; zone_bm; zone_bm = zone_bm->next) |
3674 | + nr++; | |
ad8f4a28 | 3675 | + |
1838f965 | 3676 | + result = (*rw_chunk)(WRITE, NULL, (char *) &nr, sizeof(unsigned int)); |
3677 | + if (result) | |
3678 | + return result; | |
ad8f4a28 | 3679 | + |
1838f965 | 3680 | + for (zone_bm = bm->zone_bm_list; zone_bm; zone_bm = zone_bm->next) { |
3681 | + result = (*rw_chunk)(WRITE, NULL, (char *) &zone_bm->start_pfn, | |
3682 | + 2 * sizeof(unsigned long)); | |
3683 | + if (result) | |
3684 | + return result; | |
ad8f4a28 | 3685 | + |
1838f965 | 3686 | + nr = 0; |
3687 | + for (bb = zone_bm->bm_blocks; bb; bb = bb->next) | |
3688 | + nr++; | |
ad8f4a28 | 3689 | + |
1838f965 | 3690 | + result = (*rw_chunk)(WRITE, NULL, (char *) &nr, |
3691 | + sizeof(unsigned int)); | |
3692 | ||
3693 | -static LIST_HEAD(nosave_regions); | |
3694 | + if (result) | |
3695 | + return result; | |
ad8f4a28 | 3696 | + |
1838f965 | 3697 | + for (bb = zone_bm->bm_blocks; bb; bb = bb->next) { |
3698 | + result = (*rw_chunk)(WRITE, NULL, (char *) bb->data, | |
3699 | + PAGE_SIZE); | |
3700 | + if (result) | |
3701 | + return result; | |
3702 | + } | |
ad8f4a28 AM |
3703 | + } |
3704 | + | |
ad8f4a28 AM |
3705 | + return 0; |
3706 | +} | |
1838f965 | 3707 | +EXPORT_SYMBOL_GPL(memory_bm_write); |
ad8f4a28 | 3708 | + |
1838f965 | 3709 | +int memory_bm_read(struct memory_bitmap *bm, int (*rw_chunk) |
3710 | + (int rw, struct toi_module_ops *owner, char *buffer, int buffer_size)) | |
ad8f4a28 | 3711 | +{ |
1838f965 | 3712 | + int result = 0; |
3713 | + unsigned int nr; | |
3714 | + struct zone_bitmap *zone_bm; | |
3715 | + struct bm_block *bb; | |
3716 | + struct chain_allocator ca; | |
ad8f4a28 | 3717 | + |
1838f965 | 3718 | + if (!bm) |
3719 | + return result; | |
3720 | + | |
3721 | + chain_init(&ca, GFP_ATOMIC, 0); | |
3722 | + | |
3723 | + result = (*rw_chunk)(READ, NULL, (char *) &nr, sizeof(unsigned int)); | |
3724 | + if (result) | |
3725 | + return result; | |
3726 | + | |
3727 | + zone_bm = create_zone_bm_list(nr, &ca); | |
3728 | + bm->zone_bm_list = zone_bm; | |
3729 | + if (!zone_bm) { | |
3730 | + chain_free(&ca, PG_ANY); | |
3731 | + return -ENOMEM; | |
3732 | + } | |
3733 | + | |
3734 | + for (zone_bm = bm->zone_bm_list; zone_bm; zone_bm = zone_bm->next) { | |
3735 | + unsigned long pfn; | |
3736 | + | |
3737 | + result = (*rw_chunk)(READ, NULL, (char *) &zone_bm->start_pfn, | |
3738 | + 2 * sizeof(unsigned long)); | |
3739 | + if (result) | |
3740 | + return result; | |
3741 | + | |
3742 | + result = (*rw_chunk)(READ, NULL, (char *) &nr, | |
3743 | + sizeof(unsigned int)); | |
3744 | + | |
3745 | + if (result) | |
3746 | + return result; | |
3747 | + | |
3748 | + bb = create_bm_block_list(nr, &ca); | |
3749 | + zone_bm->bm_blocks = bb; | |
3750 | + zone_bm->cur_block = bb; | |
3751 | + if (!bb) | |
3752 | + goto Free; | |
3753 | + | |
3754 | + pfn = zone_bm->start_pfn; | |
3755 | + | |
3756 | + for (bb = zone_bm->bm_blocks; bb; bb = bb->next) { | |
3757 | + bb->data = get_image_page(GFP_ATOMIC, 0); | |
3758 | + if (!bb->data) | |
3759 | + goto Free; | |
3760 | + | |
3761 | + bb->start_pfn = pfn; | |
3762 | + if (pfn + BM_BITS_PER_BLOCK > zone_bm->end_pfn) | |
3763 | + bb->end_pfn = zone_bm->end_pfn; | |
3764 | + else | |
3765 | + bb->end_pfn = bb->start_pfn + BM_BITS_PER_BLOCK; | |
3766 | + pfn = bb->end_pfn; | |
3767 | + result = (*rw_chunk)(READ, NULL, (char *) bb->data, | |
3768 | + PAGE_SIZE); | |
3769 | + if (result) | |
3770 | + return result; | |
3771 | + } | |
3772 | + } | |
3773 | + bm->p_list = ca.chain; | |
3774 | + memory_bm_position_reset(bm); | |
3775 | + | |
3776 | + return 0; | |
3777 | + | |
3778 | +Free: | |
3779 | + bm->p_list = ca.chain; | |
3780 | + memory_bm_free(bm, PG_ANY); | |
3781 | + return -ENOMEM; | |
3782 | +} | |
3783 | +EXPORT_SYMBOL_GPL(memory_bm_read); | |
ad8f4a28 | 3784 | +#endif |
1838f965 | 3785 | + |
3786 | +LIST_HEAD(nosave_regions); | |
3787 | +EXPORT_SYMBOL_GPL(nosave_regions); | |
3788 | ||
3789 | /** | |
3790 | * register_nosave_region - register a range of page frames the contents | |
3791 | @@ -809,7 +939,7 @@ static unsigned int count_free_highmem_pages(void) | |
3792 | * and it isn't a part of a free chunk of pages. | |
3793 | */ | |
3794 | ||
3795 | -static struct page *saveable_highmem_page(unsigned long pfn) | |
3796 | +struct page *saveable_highmem_page(unsigned long pfn) | |
3797 | { | |
3798 | struct page *page; | |
3799 | ||
3800 | @@ -826,6 +956,7 @@ static struct page *saveable_highmem_page(unsigned long pfn) | |
3801 | ||
3802 | return page; | |
3803 | } | |
3804 | +EXPORT_SYMBOL_GPL(saveable_highmem_page); | |
3805 | ||
3806 | /** | |
3807 | * count_highmem_pages - compute the total number of saveable highmem | |
3808 | @@ -851,8 +982,6 @@ unsigned int count_highmem_pages(void) | |
3809 | } | |
3810 | return n; | |
3811 | } | |
3812 | -#else | |
3813 | -static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; } | |
3814 | #endif /* CONFIG_HIGHMEM */ | |
3815 | ||
3816 | /** | |
3817 | @@ -864,7 +993,7 @@ static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; } | |
3818 | * a free chunk of pages. | |
3819 | */ | |
3820 | ||
3821 | -static struct page *saveable_page(unsigned long pfn) | |
3822 | +struct page *saveable_page(unsigned long pfn) | |
3823 | { | |
3824 | struct page *page; | |
3825 | ||
3826 | @@ -884,6 +1013,7 @@ static struct page *saveable_page(unsigned long pfn) | |
3827 | ||
3828 | return page; | |
3829 | } | |
3830 | +EXPORT_SYMBOL_GPL(saveable_page); | |
3831 | ||
3832 | /** | |
3833 | * count_data_pages - compute the total number of saveable non-highmem | |
3834 | @@ -1198,6 +1328,9 @@ asmlinkage int swsusp_save(void) | |
3835 | { | |
3836 | unsigned int nr_pages, nr_highmem; | |
3837 | ||
3838 | + if (toi_running) | |
3839 | + return toi_post_context_save(); | |
3840 | + | |
3841 | printk(KERN_INFO "PM: Creating hibernation image: \n"); | |
3842 | ||
3843 | drain_local_pages(NULL); | |
3844 | @@ -1238,14 +1371,14 @@ asmlinkage int swsusp_save(void) | |
3845 | } | |
3846 | ||
3847 | #ifndef CONFIG_ARCH_HIBERNATION_HEADER | |
3848 | -static int init_header_complete(struct swsusp_info *info) | |
3849 | +int init_swsusp_header_complete(struct swsusp_info *info) | |
3850 | { | |
3851 | memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname)); | |
3852 | info->version_code = LINUX_VERSION_CODE; | |
3853 | return 0; | |
3854 | } | |
3855 | ||
3856 | -static char *check_image_kernel(struct swsusp_info *info) | |
3857 | +char *check_swsusp_image_kernel(struct swsusp_info *info) | |
3858 | { | |
3859 | if (info->version_code != LINUX_VERSION_CODE) | |
3860 | return "kernel version"; | |
3861 | @@ -1259,6 +1392,7 @@ static char *check_image_kernel(struct swsusp_info *info) | |
3862 | return "machine"; | |
3863 | return NULL; | |
3864 | } | |
3865 | +EXPORT_SYMBOL_GPL(check_swsusp_image_kernel); | |
3866 | #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ | |
3867 | ||
3868 | unsigned long snapshot_get_image_size(void) | |
3869 | @@ -1266,7 +1400,7 @@ unsigned long snapshot_get_image_size(void) | |
3870 | return nr_copy_pages + nr_meta_pages + 1; | |
3871 | } | |
3872 | ||
3873 | -static int init_header(struct swsusp_info *info) | |
3874 | +int init_swsusp_header(struct swsusp_info *info) | |
3875 | { | |
3876 | memset(info, 0, sizeof(struct swsusp_info)); | |
3877 | info->num_physpages = num_physpages; | |
3878 | @@ -1274,8 +1408,9 @@ static int init_header(struct swsusp_info *info) | |
3879 | info->pages = snapshot_get_image_size(); | |
3880 | info->size = info->pages; | |
3881 | info->size <<= PAGE_SHIFT; | |
3882 | - return init_header_complete(info); | |
3883 | + return init_swsusp_header_complete(info); | |
3884 | } | |
3885 | +EXPORT_SYMBOL_GPL(init_swsusp_header); | |
3886 | ||
3887 | /** | |
3888 | * pack_pfns - pfns corresponding to the set bits found in the bitmap @bm | |
3889 | @@ -1330,7 +1465,7 @@ int snapshot_read_next(struct snapshot_handle *handle, size_t count) | |
3890 | if (!handle->offset) { | |
3891 | int error; | |
3892 | ||
3893 | - error = init_header((struct swsusp_info *)buffer); | |
3894 | + error = init_swsusp_header((struct swsusp_info *)buffer); | |
3895 | if (error) | |
3896 | return error; | |
3897 | handle->buffer = buffer; | |
3898 | @@ -1427,7 +1562,7 @@ static int check_header(struct swsusp_info *info) | |
3899 | { | |
3900 | char *reason; | |
3901 | ||
3902 | - reason = check_image_kernel(info); | |
3903 | + reason = check_swsusp_image_kernel(info); | |
3904 | if (!reason && info->num_physpages != num_physpages) | |
3905 | reason = "memory size"; | |
3906 | if (reason) { | |
4e97e4e9 | 3907 | diff --git a/kernel/power/tuxonice.h b/kernel/power/tuxonice.h |
3908 | new file mode 100644 | |
1838f965 | 3909 | index 0000000..34ddaa9 |
4e97e4e9 | 3910 | --- /dev/null |
3911 | +++ b/kernel/power/tuxonice.h | |
7f9d2ee0 | 3912 | @@ -0,0 +1,210 @@ |
4e97e4e9 | 3913 | +/* |
3914 | + * kernel/power/tuxonice.h | |
3915 | + * | |
1838f965 | 3916 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 3917 | + * |
3918 | + * This file is released under the GPLv2. | |
3919 | + * | |
3920 | + * It contains declarations used throughout swsusp. | |
3921 | + * | |
3922 | + */ | |
3923 | + | |
3924 | +#ifndef KERNEL_POWER_TOI_H | |
3925 | +#define KERNEL_POWER_TOI_H | |
3926 | + | |
3927 | +#include <linux/delay.h> | |
3928 | +#include <linux/bootmem.h> | |
3929 | +#include <linux/suspend.h> | |
4e97e4e9 | 3930 | +#include <linux/fs.h> |
ad8f4a28 | 3931 | +#include <linux/kmod.h> |
4e97e4e9 | 3932 | +#include <asm/setup.h> |
3933 | +#include "tuxonice_pageflags.h" | |
3934 | + | |
1838f965 | 3935 | +#define TOI_CORE_VERSION "3.0-rc8" |
ad8f4a28 AM |
3936 | + |
3937 | +#define MY_BOOT_KERNEL_DATA_VERSION 1 | |
3938 | + | |
3939 | +struct toi_boot_kernel_data { | |
3940 | + int version; | |
3941 | + int size; | |
3942 | + unsigned long toi_action; | |
3943 | + unsigned long toi_debug_state; | |
1838f965 | 3944 | + u32 toi_default_console_level; |
ad8f4a28 AM |
3945 | + int toi_io_time[2][2]; |
3946 | + char toi_nosave_commandline[COMMAND_LINE_SIZE]; | |
3947 | +}; | |
3948 | + | |
3949 | +extern struct toi_boot_kernel_data toi_bkd; | |
3950 | + | |
3951 | +/* Location of book kernel data struct in kernel being resumed */ | |
3952 | +extern unsigned long boot_kernel_data_buffer; | |
4e97e4e9 | 3953 | + |
3954 | +/* == Action states == */ | |
3955 | + | |
3956 | +enum { | |
3957 | + TOI_REBOOT, | |
3958 | + TOI_PAUSE, | |
4e97e4e9 | 3959 | + TOI_LOGALL, |
3960 | + TOI_CAN_CANCEL, | |
3961 | + TOI_KEEP_IMAGE, | |
3962 | + TOI_FREEZER_TEST, | |
3963 | + TOI_SINGLESTEP, | |
3964 | + TOI_PAUSE_NEAR_PAGESET_END, | |
3965 | + TOI_TEST_FILTER_SPEED, | |
3966 | + TOI_TEST_BIO, | |
3967 | + TOI_NO_PAGESET2, | |
3968 | + TOI_PM_PREPARE_CONSOLE, | |
3969 | + TOI_IGNORE_ROOTFS, | |
3970 | + TOI_REPLACE_SWSUSP, | |
3971 | + TOI_PAGESET2_FULL, | |
3972 | + TOI_ABORT_ON_RESAVE_NEEDED, | |
3973 | + TOI_NO_MULTITHREADED_IO, | |
3974 | + TOI_NO_DIRECT_LOAD, | |
3975 | + TOI_LATE_CPU_HOTPLUG, | |
7f9d2ee0 | 3976 | + TOI_GET_MAX_MEM_ALLOCD, |
3977 | + TOI_NO_FLUSHER_THREAD, | |
1838f965 | 3978 | + TOI_NO_PS2_IF_UNNEEDED |
4e97e4e9 | 3979 | +}; |
3980 | + | |
ad8f4a28 | 3981 | +#define clear_action_state(bit) (test_and_clear_bit(bit, &toi_bkd.toi_action)) |
4e97e4e9 | 3982 | + |
3983 | +/* == Result states == */ | |
3984 | + | |
3985 | +enum { | |
3986 | + TOI_ABORTED, | |
3987 | + TOI_ABORT_REQUESTED, | |
3988 | + TOI_NOSTORAGE_AVAILABLE, | |
3989 | + TOI_INSUFFICIENT_STORAGE, | |
3990 | + TOI_FREEZING_FAILED, | |
4e97e4e9 | 3991 | + TOI_KEPT_IMAGE, |
3992 | + TOI_WOULD_EAT_MEMORY, | |
3993 | + TOI_UNABLE_TO_FREE_ENOUGH_MEMORY, | |
3994 | + TOI_PM_SEM, | |
3995 | + TOI_DEVICE_REFUSED, | |
3996 | + TOI_EXTRA_PAGES_ALLOW_TOO_SMALL, | |
3997 | + TOI_UNABLE_TO_PREPARE_IMAGE, | |
3998 | + TOI_FAILED_MODULE_INIT, | |
3999 | + TOI_FAILED_MODULE_CLEANUP, | |
4000 | + TOI_FAILED_IO, | |
4001 | + TOI_OUT_OF_MEMORY, | |
4002 | + TOI_IMAGE_ERROR, | |
4003 | + TOI_PLATFORM_PREP_FAILED, | |
4004 | + TOI_CPU_HOTPLUG_FAILED, | |
4005 | + TOI_ARCH_PREPARE_FAILED, | |
4006 | + TOI_RESAVE_NEEDED, | |
4007 | + TOI_CANT_SUSPEND, | |
4008 | + TOI_NOTIFIERS_PREPARE_FAILED, | |
ad8f4a28 AM |
4009 | + TOI_PRE_SNAPSHOT_FAILED, |
4010 | + TOI_PRE_RESTORE_FAILED, | |
1838f965 | 4011 | + TOI_CANT_USE_ALT_RESUME, |
4012 | + TOI_NUM_RESULT_STATES /* Used in printing debug info only */ | |
4e97e4e9 | 4013 | +}; |
4014 | + | |
4015 | +extern unsigned long toi_result; | |
4016 | + | |
4017 | +#define set_result_state(bit) (test_and_set_bit(bit, &toi_result)) | |
ad8f4a28 | 4018 | +#define set_abort_result(bit) (test_and_set_bit(TOI_ABORTED, &toi_result), \ |
4e97e4e9 | 4019 | + test_and_set_bit(bit, &toi_result)) |
4020 | +#define clear_result_state(bit) (test_and_clear_bit(bit, &toi_result)) | |
4021 | +#define test_result_state(bit) (test_bit(bit, &toi_result)) | |
4022 | + | |
4023 | +/* == Debug sections and levels == */ | |
4024 | + | |
4025 | +/* debugging levels. */ | |
4026 | +enum { | |
4027 | + TOI_STATUS = 0, | |
4028 | + TOI_ERROR = 2, | |
4029 | + TOI_LOW, | |
4030 | + TOI_MEDIUM, | |
4031 | + TOI_HIGH, | |
4032 | + TOI_VERBOSE, | |
4033 | +}; | |
4034 | + | |
4035 | +enum { | |
4036 | + TOI_ANY_SECTION, | |
4037 | + TOI_EAT_MEMORY, | |
4038 | + TOI_IO, | |
4039 | + TOI_HEADER, | |
4040 | + TOI_WRITER, | |
4041 | + TOI_MEMORY, | |
4042 | +}; | |
4043 | + | |
ad8f4a28 | 4044 | +#define set_debug_state(bit) (test_and_set_bit(bit, &toi_bkd.toi_debug_state)) |
7f9d2ee0 | 4045 | +#define clear_debug_state(bit) \ |
4046 | + (test_and_clear_bit(bit, &toi_bkd.toi_debug_state)) | |
ad8f4a28 | 4047 | +#define test_debug_state(bit) (test_bit(bit, &toi_bkd.toi_debug_state)) |
4e97e4e9 | 4048 | + |
4049 | +/* == Steps in hibernating == */ | |
4050 | + | |
4051 | +enum { | |
4052 | + STEP_HIBERNATE_PREPARE_IMAGE, | |
4053 | + STEP_HIBERNATE_SAVE_IMAGE, | |
4054 | + STEP_HIBERNATE_POWERDOWN, | |
4055 | + STEP_RESUME_CAN_RESUME, | |
4056 | + STEP_RESUME_LOAD_PS1, | |
4057 | + STEP_RESUME_DO_RESTORE, | |
4058 | + STEP_RESUME_READ_PS2, | |
4059 | + STEP_RESUME_GO, | |
4060 | + STEP_RESUME_ALT_IMAGE, | |
ad8f4a28 AM |
4061 | + STEP_CLEANUP, |
4062 | + STEP_QUIET_CLEANUP | |
4e97e4e9 | 4063 | +}; |
4064 | + | |
4065 | +/* == TuxOnIce states == | |
4066 | + (see also include/linux/suspend.h) */ | |
4067 | + | |
4068 | +#define get_toi_state() (toi_state) | |
4069 | +#define restore_toi_state(saved_state) \ | |
ad8f4a28 | 4070 | + do { toi_state = saved_state; } while (0) |
4e97e4e9 | 4071 | + |
4072 | +/* == Module support == */ | |
4073 | + | |
4074 | +struct toi_core_fns { | |
4075 | + int (*post_context_save)(void); | |
4076 | + unsigned long (*get_nonconflicting_page)(void); | |
1838f965 | 4077 | + int (*try_hibernate)(void); |
4e97e4e9 | 4078 | + void (*try_resume)(void); |
4079 | +}; | |
4080 | + | |
4081 | +extern struct toi_core_fns *toi_core_fns; | |
4082 | + | |
4083 | +/* == All else == */ | |
4084 | +#define KB(x) ((x) << (PAGE_SHIFT - 10)) | |
4085 | +#define MB(x) ((x) >> (20 - PAGE_SHIFT)) | |
4086 | + | |
4087 | +extern int toi_start_anything(int toi_or_resume); | |
4088 | +extern void toi_finish_anything(int toi_or_resume); | |
4089 | + | |
4090 | +extern int save_image_part1(void); | |
4091 | +extern int toi_atomic_restore(void); | |
4092 | + | |
1838f965 | 4093 | +extern int _toi_try_hibernate(void); |
4e97e4e9 | 4094 | +extern void __toi_try_resume(void); |
4095 | + | |
4096 | +extern int __toi_post_context_save(void); | |
4097 | + | |
4098 | +extern unsigned int nr_hibernates; | |
4099 | +extern char alt_resume_param[256]; | |
4100 | + | |
4101 | +extern void copyback_post(void); | |
4102 | +extern int toi_hibernate(void); | |
7f9d2ee0 | 4103 | +extern long extra_pd1_pages_used; |
4e97e4e9 | 4104 | + |
4e97e4e9 | 4105 | +#define SECTOR_SIZE 512 |
4106 | + | |
ad8f4a28 AM |
4107 | +extern void toi_early_boot_message(int can_erase_image, int default_answer, |
4108 | + char *warning_reason, ...); | |
4e97e4e9 | 4109 | + |
4110 | +static inline int load_direct(struct page *page) | |
4111 | +{ | |
ad8f4a28 AM |
4112 | + return test_action_state(TOI_NO_DIRECT_LOAD) ? 0 : |
4113 | + PagePageset1Copy(page); | |
4e97e4e9 | 4114 | +} |
4115 | + | |
ad8f4a28 AM |
4116 | +extern int do_check_can_resume(void); |
4117 | +extern int do_toi_step(int step); | |
4118 | +extern int toi_launch_userspace_program(char *command, int channel_no, | |
1838f965 | 4119 | + enum umh_wait wait, int debug); |
7f9d2ee0 | 4120 | + |
f3e0dcc9 | 4121 | +extern char *tuxonice_signature; |
4e97e4e9 | 4122 | +#endif |
ad8f4a28 | 4123 | diff --git a/kernel/power/tuxonice_alloc.c b/kernel/power/tuxonice_alloc.c |
4e97e4e9 | 4124 | new file mode 100644 |
1838f965 | 4125 | index 0000000..5e3aae8 |
4e97e4e9 | 4126 | --- /dev/null |
ad8f4a28 | 4127 | +++ b/kernel/power/tuxonice_alloc.c |
1838f965 | 4128 | @@ -0,0 +1,287 @@ |
4e97e4e9 | 4129 | +/* |
ad8f4a28 | 4130 | + * kernel/power/tuxonice_alloc.c |
4e97e4e9 | 4131 | + * |
1838f965 | 4132 | + * Copyright (C) 2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 4133 | + * |
ad8f4a28 | 4134 | + * This file is released under the GPLv2. |
4e97e4e9 | 4135 | + * |
4e97e4e9 | 4136 | + */ |
4137 | + | |
ad8f4a28 | 4138 | +#ifdef CONFIG_PM_DEBUG |
ad8f4a28 | 4139 | +#include <linux/module.h> |
1838f965 | 4140 | +#include <linux/slab.h> |
ad8f4a28 | 4141 | +#include "tuxonice_modules.h" |
1838f965 | 4142 | +#include "tuxonice_alloc.h" |
ad8f4a28 | 4143 | +#include "tuxonice_sysfs.h" |
1838f965 | 4144 | +#include "tuxonice.h" |
4e97e4e9 | 4145 | + |
7f9d2ee0 | 4146 | +#define TOI_ALLOC_PATHS 39 |
ad8f4a28 | 4147 | + |
1838f965 | 4148 | +static DEFINE_MUTEX(toi_alloc_mutex); |
ad8f4a28 | 4149 | + |
7f9d2ee0 | 4150 | +static struct toi_module_ops toi_alloc_ops; |
4151 | + | |
ad8f4a28 AM |
4152 | +static int toi_fail_num; |
4153 | +static atomic_t toi_alloc_count[TOI_ALLOC_PATHS], | |
4154 | + toi_free_count[TOI_ALLOC_PATHS], | |
4155 | + toi_test_count[TOI_ALLOC_PATHS], | |
4156 | + toi_fail_count[TOI_ALLOC_PATHS]; | |
1838f965 | 4157 | +static int toi_cur_allocd[TOI_ALLOC_PATHS], toi_max_allocd[TOI_ALLOC_PATHS]; |
4158 | +static int cur_allocd, max_allocd; | |
ad8f4a28 AM |
4159 | + |
4160 | +static char *toi_alloc_desc[TOI_ALLOC_PATHS] = { | |
4161 | + "", /* 0 */ | |
4162 | + "get_io_info_struct", | |
4163 | + "extent", | |
4164 | + "extent (loading chain)", | |
4165 | + "userui channel", | |
4166 | + "userui arg", /* 5 */ | |
4167 | + "attention list metadata", | |
4168 | + "extra pagedir memory metadata", | |
4169 | + "bdev metadata", | |
4170 | + "extra pagedir memory", | |
4171 | + "header_locations_read", /* 10 */ | |
4172 | + "bio queue", | |
4173 | + "prepare_readahead", | |
4174 | + "i/o buffer", | |
4175 | + "writer buffer in bio_init", | |
4176 | + "checksum buffer", /* 15 */ | |
4177 | + "compression buffer", | |
4178 | + "filewriter signature op", | |
4179 | + "set resume param alloc1", | |
4180 | + "set resume param alloc2", | |
4181 | + "debugging info buffer", /* 20 */ | |
4182 | + "check can resume buffer", | |
4183 | + "write module config buffer", | |
4184 | + "read module config buffer", | |
4185 | + "write image header buffer", | |
4186 | + "read pageset1 buffer", /* 25 */ | |
4187 | + "get_have_image_data buffer", | |
4188 | + "checksum page", | |
4189 | + "worker rw loop", | |
4190 | + "get nonconflicting page", | |
4191 | + "ps1 load addresses", /* 30 */ | |
4192 | + "remove swap image", | |
4193 | + "swap image exists", | |
4194 | + "swap parse sig location", | |
4195 | + "sysfs kobj", | |
4196 | + "swap mark resume attempted buffer", /* 35 */ | |
4197 | + "cluster member", | |
7f9d2ee0 | 4198 | + "boot kernel data buffer", |
4199 | + "setting swap signature" | |
ad8f4a28 | 4200 | +}; |
24613191 | 4201 | + |
ad8f4a28 AM |
4202 | +#define MIGHT_FAIL(FAIL_NUM, FAIL_VAL) \ |
4203 | + do { \ | |
4204 | + BUG_ON(FAIL_NUM >= TOI_ALLOC_PATHS); \ | |
4205 | + \ | |
4206 | + if (FAIL_NUM == toi_fail_num) { \ | |
4207 | + atomic_inc(&toi_test_count[FAIL_NUM]); \ | |
4208 | + toi_fail_num = 0; \ | |
4209 | + return FAIL_VAL; \ | |
4210 | + } \ | |
4211 | + } while (0) | |
4212 | + | |
4213 | +static void alloc_update_stats(int fail_num, void *result) | |
24613191 | 4214 | +{ |
ad8f4a28 AM |
4215 | + if (!result) { |
4216 | + atomic_inc(&toi_fail_count[fail_num]); | |
4217 | + return; | |
4218 | + } | |
24613191 | 4219 | + |
ad8f4a28 AM |
4220 | + atomic_inc(&toi_alloc_count[fail_num]); |
4221 | + if (unlikely(test_action_state(TOI_GET_MAX_MEM_ALLOCD))) { | |
4222 | + mutex_lock(&toi_alloc_mutex); | |
4223 | + toi_cur_allocd[fail_num]++; | |
4224 | + cur_allocd++; | |
4225 | + if (unlikely(cur_allocd > max_allocd)) { | |
4226 | + int i; | |
4227 | + | |
4228 | + for (i = 0; i < TOI_ALLOC_PATHS; i++) | |
4229 | + toi_max_allocd[i] = toi_cur_allocd[i]; | |
4230 | + max_allocd = cur_allocd; | |
4231 | + } | |
4232 | + mutex_unlock(&toi_alloc_mutex); | |
4233 | + } | |
4234 | +} | |
4235 | + | |
4236 | +static void free_update_stats(int fail_num) | |
4237 | +{ | |
7f9d2ee0 | 4238 | + BUG_ON(fail_num >= TOI_ALLOC_PATHS); |
ad8f4a28 AM |
4239 | + atomic_inc(&toi_free_count[fail_num]); |
4240 | + if (unlikely(test_action_state(TOI_GET_MAX_MEM_ALLOCD))) { | |
4241 | + mutex_lock(&toi_alloc_mutex); | |
4242 | + cur_allocd--; | |
4243 | + toi_cur_allocd[fail_num]--; | |
4244 | + mutex_unlock(&toi_alloc_mutex); | |
4245 | + } | |
4246 | +} | |
4247 | + | |
4248 | +void *toi_kzalloc(int fail_num, size_t size, gfp_t flags) | |
4249 | +{ | |
4250 | + void *result; | |
4251 | + | |
7f9d2ee0 | 4252 | + if (toi_alloc_ops.enabled) |
4253 | + MIGHT_FAIL(fail_num, NULL); | |
ad8f4a28 | 4254 | + result = kzalloc(size, flags); |
7f9d2ee0 | 4255 | + if (toi_alloc_ops.enabled) |
4256 | + alloc_update_stats(fail_num, result); | |
ad8f4a28 AM |
4257 | + return result; |
4258 | +} | |
1838f965 | 4259 | +EXPORT_SYMBOL_GPL(toi_kzalloc); |
ad8f4a28 AM |
4260 | + |
4261 | +unsigned long toi_get_free_pages(int fail_num, gfp_t mask, | |
4262 | + unsigned int order) | |
4263 | +{ | |
4264 | + unsigned long result; | |
4265 | + | |
7f9d2ee0 | 4266 | + if (toi_alloc_ops.enabled) |
4267 | + MIGHT_FAIL(fail_num, 0); | |
ad8f4a28 | 4268 | + result = __get_free_pages(mask, order); |
7f9d2ee0 | 4269 | + if (toi_alloc_ops.enabled) |
4270 | + alloc_update_stats(fail_num, (void *) result); | |
ad8f4a28 AM |
4271 | + return result; |
4272 | +} | |
1838f965 | 4273 | +EXPORT_SYMBOL_GPL(toi_get_free_pages); |
ad8f4a28 AM |
4274 | + |
4275 | +struct page *toi_alloc_page(int fail_num, gfp_t mask) | |
4276 | +{ | |
4277 | + struct page *result; | |
4278 | + | |
7f9d2ee0 | 4279 | + if (toi_alloc_ops.enabled) |
1838f965 | 4280 | + MIGHT_FAIL(fail_num, NULL); |
ad8f4a28 | 4281 | + result = alloc_page(mask); |
7f9d2ee0 | 4282 | + if (toi_alloc_ops.enabled) |
4283 | + alloc_update_stats(fail_num, (void *) result); | |
ad8f4a28 AM |
4284 | + return result; |
4285 | +} | |
1838f965 | 4286 | +EXPORT_SYMBOL_GPL(toi_alloc_page); |
ad8f4a28 AM |
4287 | + |
4288 | +unsigned long toi_get_zeroed_page(int fail_num, gfp_t mask) | |
4289 | +{ | |
4290 | + unsigned long result; | |
4291 | + | |
7f9d2ee0 | 4292 | + if (toi_alloc_ops.enabled) |
4293 | + MIGHT_FAIL(fail_num, 0); | |
ad8f4a28 | 4294 | + result = get_zeroed_page(mask); |
7f9d2ee0 | 4295 | + if (toi_alloc_ops.enabled) |
4296 | + alloc_update_stats(fail_num, (void *) result); | |
ad8f4a28 AM |
4297 | + return result; |
4298 | +} | |
1838f965 | 4299 | +EXPORT_SYMBOL_GPL(toi_get_zeroed_page); |
ad8f4a28 AM |
4300 | + |
4301 | +void toi_kfree(int fail_num, const void *arg) | |
4302 | +{ | |
7f9d2ee0 | 4303 | + if (arg && toi_alloc_ops.enabled) |
ad8f4a28 AM |
4304 | + free_update_stats(fail_num); |
4305 | + | |
4306 | + kfree(arg); | |
4307 | +} | |
1838f965 | 4308 | +EXPORT_SYMBOL_GPL(toi_kfree); |
ad8f4a28 AM |
4309 | + |
4310 | +void toi_free_page(int fail_num, unsigned long virt) | |
4311 | +{ | |
7f9d2ee0 | 4312 | + if (virt && toi_alloc_ops.enabled) |
ad8f4a28 AM |
4313 | + free_update_stats(fail_num); |
4314 | + | |
4315 | + free_page(virt); | |
4316 | +} | |
1838f965 | 4317 | +EXPORT_SYMBOL_GPL(toi_free_page); |
ad8f4a28 AM |
4318 | + |
4319 | +void toi__free_page(int fail_num, struct page *page) | |
4320 | +{ | |
7f9d2ee0 | 4321 | + if (page && toi_alloc_ops.enabled) |
ad8f4a28 AM |
4322 | + free_update_stats(fail_num); |
4323 | + | |
4324 | + __free_page(page); | |
4325 | +} | |
1838f965 | 4326 | +EXPORT_SYMBOL_GPL(toi__free_page); |
ad8f4a28 AM |
4327 | + |
4328 | +void toi_free_pages(int fail_num, struct page *page, int order) | |
4329 | +{ | |
7f9d2ee0 | 4330 | + if (page && toi_alloc_ops.enabled) |
ad8f4a28 AM |
4331 | + free_update_stats(fail_num); |
4332 | + | |
4333 | + __free_pages(page, order); | |
4334 | +} | |
4335 | + | |
4336 | +void toi_alloc_print_debug_stats(void) | |
4337 | +{ | |
7f9d2ee0 | 4338 | + int i, header_done = 0; |
ad8f4a28 | 4339 | + |
7f9d2ee0 | 4340 | + if (!toi_alloc_ops.enabled) |
4341 | + return; | |
ad8f4a28 AM |
4342 | + |
4343 | + for (i = 0; i < TOI_ALLOC_PATHS; i++) | |
7f9d2ee0 | 4344 | + if (atomic_read(&toi_alloc_count[i]) != |
4345 | + atomic_read(&toi_free_count[i])) { | |
4346 | + if (!header_done) { | |
4347 | + printk(KERN_INFO "Idx Allocs Frees Tests " | |
4348 | + " Fails Max Description\n"); | |
4349 | + header_done = 1; | |
4350 | + } | |
4351 | + | |
ad8f4a28 AM |
4352 | + printk(KERN_INFO "%3d %7d %7d %7d %7d %7d %s\n", i, |
4353 | + atomic_read(&toi_alloc_count[i]), | |
4354 | + atomic_read(&toi_free_count[i]), | |
4355 | + atomic_read(&toi_test_count[i]), | |
4356 | + atomic_read(&toi_fail_count[i]), | |
4357 | + toi_max_allocd[i], | |
4358 | + toi_alloc_desc[i]); | |
7f9d2ee0 | 4359 | + } |
ad8f4a28 AM |
4360 | +} |
4361 | +EXPORT_SYMBOL_GPL(toi_alloc_print_debug_stats); | |
4362 | + | |
4363 | +static int toi_alloc_initialise(int starting_cycle) | |
4364 | +{ | |
4365 | + int i; | |
4366 | + | |
7f9d2ee0 | 4367 | + if (starting_cycle && toi_alloc_ops.enabled) { |
ad8f4a28 AM |
4368 | + for (i = 0; i < TOI_ALLOC_PATHS; i++) { |
4369 | + atomic_set(&toi_alloc_count[i], 0); | |
4370 | + atomic_set(&toi_free_count[i], 0); | |
4371 | + atomic_set(&toi_test_count[i], 0); | |
4372 | + atomic_set(&toi_fail_count[i], 0); | |
4373 | + toi_cur_allocd[i] = 0; | |
4374 | + toi_max_allocd[i] = 0; | |
4375 | + }; | |
4376 | + max_allocd = 0; | |
4377 | + cur_allocd = 0; | |
4378 | + } | |
4379 | + | |
4380 | + return 0; | |
4381 | +} | |
4382 | + | |
4383 | +static struct toi_sysfs_data sysfs_params[] = { | |
1838f965 | 4384 | + SYSFS_INT("failure_test", SYSFS_RW, &toi_fail_num, 0, 99, 0, NULL), |
4385 | + SYSFS_BIT("find_max_mem_allocated", SYSFS_RW, &toi_bkd.toi_action, | |
4386 | + TOI_GET_MAX_MEM_ALLOCD, 0), | |
4387 | + SYSFS_INT("enabled", SYSFS_RW, &toi_alloc_ops.enabled, 0, 1, 0, | |
4388 | + NULL) | |
ad8f4a28 AM |
4389 | +}; |
4390 | + | |
4391 | +static struct toi_module_ops toi_alloc_ops = { | |
4392 | + .type = MISC_HIDDEN_MODULE, | |
4393 | + .name = "allocation debugging", | |
4394 | + .directory = "alloc", | |
4395 | + .module = THIS_MODULE, | |
4396 | + .early = 1, | |
4397 | + .initialise = toi_alloc_initialise, | |
4398 | + | |
4399 | + .sysfs_data = sysfs_params, | |
4400 | + .num_sysfs_entries = sizeof(sysfs_params) / | |
4401 | + sizeof(struct toi_sysfs_data), | |
4402 | +}; | |
4403 | + | |
4404 | +int toi_alloc_init(void) | |
4405 | +{ | |
7f9d2ee0 | 4406 | + int result = toi_register_module(&toi_alloc_ops); |
4407 | + toi_alloc_ops.enabled = 0; | |
4408 | + return result; | |
ad8f4a28 AM |
4409 | +} |
4410 | + | |
4411 | +void toi_alloc_exit(void) | |
4412 | +{ | |
4413 | + toi_unregister_module(&toi_alloc_ops); | |
4414 | +} | |
ad8f4a28 AM |
4415 | +#endif |
4416 | diff --git a/kernel/power/tuxonice_alloc.h b/kernel/power/tuxonice_alloc.h | |
4417 | new file mode 100644 | |
1838f965 | 4418 | index 0000000..a1dd8ff |
ad8f4a28 AM |
4419 | --- /dev/null |
4420 | +++ b/kernel/power/tuxonice_alloc.h | |
4421 | @@ -0,0 +1,51 @@ | |
4422 | +/* | |
4423 | + * kernel/power/tuxonice_alloc.h | |
4424 | + * | |
1838f965 | 4425 | + * Copyright (C) 2008 Nigel Cunningham (nigel at tuxonice net) |
ad8f4a28 AM |
4426 | + * |
4427 | + * This file is released under the GPLv2. | |
4428 | + * | |
4429 | + */ | |
4430 | + | |
4431 | +#define TOI_WAIT_GFP (GFP_KERNEL | __GFP_NOWARN) | |
4432 | +#define TOI_ATOMIC_GFP (GFP_ATOMIC | __GFP_NOWARN) | |
4433 | + | |
4434 | +#ifdef CONFIG_PM_DEBUG | |
4435 | +extern void *toi_kzalloc(int fail_num, size_t size, gfp_t flags); | |
4436 | +extern void toi_kfree(int fail_num, const void *arg); | |
4437 | + | |
4438 | +extern unsigned long toi_get_free_pages(int fail_num, gfp_t mask, | |
4439 | + unsigned int order); | |
4440 | +#define toi_get_free_page(FAIL_NUM, MASK) toi_get_free_pages(FAIL_NUM, MASK, 0) | |
4441 | +extern unsigned long toi_get_zeroed_page(int fail_num, gfp_t mask); | |
4442 | +extern void toi_free_page(int fail_num, unsigned long buf); | |
4443 | +extern void toi__free_page(int fail_num, struct page *page); | |
4444 | +extern void toi_free_pages(int fail_num, struct page *page, int order); | |
4445 | +extern struct page *toi_alloc_page(int fail_num, gfp_t mask); | |
4446 | +extern int toi_alloc_init(void); | |
4447 | +extern void toi_alloc_exit(void); | |
4448 | + | |
4449 | +extern void toi_alloc_print_debug_stats(void); | |
4450 | + | |
4451 | +#else /* CONFIG_PM_DEBUG */ | |
4452 | + | |
4453 | +#define toi_kzalloc(FAIL, SIZE, FLAGS) (kzalloc(SIZE, FLAGS)) | |
4454 | +#define toi_kfree(FAIL, ALLOCN) (kfree(ALLOCN)) | |
4455 | + | |
4456 | +#define toi_get_free_pages(FAIL, FLAGS, ORDER) __get_free_pages(FLAGS, ORDER) | |
4457 | +#define toi_get_free_page(FAIL, FLAGS) __get_free_page(FLAGS) | |
4458 | +#define toi_get_zeroed_page(FAIL, FLAGS) get_zeroed_page(FLAGS) | |
4459 | +#define toi_free_page(FAIL, ALLOCN) do { free_page(ALLOCN); } while (0) | |
4460 | +#define toi__free_page(FAIL, PAGE) __free_page(PAGE) | |
4461 | +#define toi_free_pages(FAIL, PAGE, ORDER) __free_pages(PAGE, ORDER) | |
4462 | +#define toi_alloc_page(FAIL, MASK) alloc_page(MASK) | |
4463 | +static inline int toi_alloc_init(void) | |
4464 | +{ | |
4465 | + return 0; | |
4466 | +} | |
4467 | + | |
4468 | +static inline void toi_alloc_exit(void) { } | |
4469 | + | |
4470 | +static inline void toi_alloc_print_debug_stats(void) { } | |
4471 | + | |
4472 | +#endif | |
4473 | diff --git a/kernel/power/tuxonice_atomic_copy.c b/kernel/power/tuxonice_atomic_copy.c | |
4474 | new file mode 100644 | |
1838f965 | 4475 | index 0000000..64e5749 |
ad8f4a28 AM |
4476 | --- /dev/null |
4477 | +++ b/kernel/power/tuxonice_atomic_copy.c | |
1838f965 | 4478 | @@ -0,0 +1,398 @@ |
ad8f4a28 AM |
4479 | +/* |
4480 | + * kernel/power/tuxonice_atomic_copy.c | |
4481 | + * | |
1838f965 | 4482 | + * Copyright 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
ad8f4a28 AM |
4483 | + * Copyright (C) 2006 Red Hat, inc. |
4484 | + * | |
4485 | + * Distributed under GPLv2. | |
4486 | + * | |
4487 | + * Routines for doing the atomic save/restore. | |
4488 | + */ | |
4489 | + | |
4490 | +#include <linux/suspend.h> | |
4491 | +#include <linux/highmem.h> | |
4492 | +#include <linux/cpu.h> | |
4493 | +#include <linux/freezer.h> | |
4494 | +#include <linux/console.h> | |
1838f965 | 4495 | +#include <linux/ftrace.h> |
ad8f4a28 AM |
4496 | +#include "tuxonice.h" |
4497 | +#include "tuxonice_storage.h" | |
4498 | +#include "tuxonice_power_off.h" | |
4499 | +#include "tuxonice_ui.h" | |
4500 | +#include "power.h" | |
4501 | +#include "tuxonice_io.h" | |
4502 | +#include "tuxonice_prepare_image.h" | |
4503 | +#include "tuxonice_pageflags.h" | |
4504 | +#include "tuxonice_checksum.h" | |
4505 | +#include "tuxonice_builtin.h" | |
4506 | +#include "tuxonice_atomic_copy.h" | |
4507 | +#include "tuxonice_alloc.h" | |
4508 | + | |
7f9d2ee0 | 4509 | +long extra_pd1_pages_used; |
1838f965 | 4510 | +static int ftrace_save; |
ad8f4a28 AM |
4511 | + |
4512 | +/** | |
4513 | + * free_pbe_list: Free page backup entries used by the atomic copy code. | |
4514 | + * | |
4515 | + * Normally, this function isn't used. If, however, we need to abort before | |
4516 | + * doing the atomic copy, we use this to free the pbes previously allocated. | |
4517 | + **/ | |
4518 | +static void free_pbe_list(struct pbe **list, int highmem) | |
4519 | +{ | |
4520 | + while (*list) { | |
4521 | + int i; | |
4522 | + struct pbe *free_pbe, *next_page = NULL; | |
4523 | + struct page *page; | |
4524 | + | |
4525 | + if (highmem) { | |
4526 | + page = (struct page *) *list; | |
24613191 | 4527 | + free_pbe = (struct pbe *) kmap(page); |
e8d0ad9d | 4528 | + } else { |
4529 | + page = virt_to_page(*list); | |
4530 | + free_pbe = *list; | |
4531 | + } | |
24613191 | 4532 | + |
4533 | + for (i = 0; i < PBES_PER_PAGE; i++) { | |
4534 | + if (!free_pbe) | |
4535 | + break; | |
e8d0ad9d | 4536 | + if (highmem) |
ad8f4a28 | 4537 | + toi__free_page(29, free_pbe->address); |
e8d0ad9d | 4538 | + else |
ad8f4a28 AM |
4539 | + toi_free_page(29, |
4540 | + (unsigned long) free_pbe->address); | |
24613191 | 4541 | + free_pbe = free_pbe->next; |
4542 | + } | |
4543 | + | |
4544 | + if (highmem) { | |
24613191 | 4545 | + if (free_pbe) |
e8d0ad9d | 4546 | + next_page = free_pbe; |
24613191 | 4547 | + kunmap(page); |
e8d0ad9d | 4548 | + } else { |
4549 | + if (free_pbe) | |
4550 | + next_page = free_pbe; | |
24613191 | 4551 | + } |
4552 | + | |
ad8f4a28 | 4553 | + toi__free_page(29, page); |
e8d0ad9d | 4554 | + *list = (struct pbe *) next_page; |
4555 | + }; | |
24613191 | 4556 | +} |
4557 | + | |
4558 | +/** | |
4559 | + * copyback_post: Post atomic-restore actions. | |
4560 | + * | |
4561 | + * After doing the atomic restore, we have a few more things to do: | |
4562 | + * 1) We want to retain some values across the restore, so we now copy | |
4563 | + * these from the nosave variables to the normal ones. | |
4564 | + * 2) Set the status flags. | |
4565 | + * 3) Resume devices. | |
e8d0ad9d | 4566 | + * 4) Tell userui so it can redraw & restore settings. |
24613191 | 4567 | + * 5) Reread the page cache. |
4568 | + **/ | |
4569 | + | |
4570 | +void copyback_post(void) | |
4571 | +{ | |
ad8f4a28 AM |
4572 | + struct toi_boot_kernel_data *bkd = |
4573 | + (struct toi_boot_kernel_data *) boot_kernel_data_buffer; | |
24613191 | 4574 | + |
ad8f4a28 AM |
4575 | + /* |
4576 | + * The boot kernel's data may be larger (newer version) or | |
4577 | + * smaller (older version) than ours. Copy the minimum | |
4578 | + * of the two sizes, so that we don't overwrite valid values | |
4579 | + * from pre-atomic copy. | |
4580 | + */ | |
24613191 | 4581 | + |
ad8f4a28 AM |
4582 | + memcpy(&toi_bkd, (char *) boot_kernel_data_buffer, |
4583 | + min_t(int, sizeof(struct toi_boot_kernel_data), | |
4584 | + bkd->size)); | |
24613191 | 4585 | + |
4e97e4e9 | 4586 | + if (toi_activate_storage(1)) |
24613191 | 4587 | + panic("Failed to reactivate our storage."); |
4588 | + | |
4e97e4e9 | 4589 | + toi_ui_post_atomic_restore(); |
24613191 | 4590 | + |
4e97e4e9 | 4591 | + toi_cond_pause(1, "About to reload secondary pagedir."); |
24613191 | 4592 | + |
4593 | + if (read_pageset2(0)) | |
4594 | + panic("Unable to successfully reread the page cache."); | |
4595 | + | |
4e97e4e9 | 4596 | + /* |
4597 | + * If the user wants to sleep again after resuming from full-off, | |
4598 | + * it's most likely to be in order to suspend to ram, so we'll | |
4599 | + * do this check after loading pageset2, to give them the fastest | |
4600 | + * wakeup when they are ready to use the computer again. | |
4601 | + */ | |
4602 | + toi_check_resleep(); | |
24613191 | 4603 | +} |
4604 | + | |
4605 | +/** | |
4e97e4e9 | 4606 | + * toi_copy_pageset1: Do the atomic copy of pageset1. |
24613191 | 4607 | + * |
4608 | + * Make the atomic copy of pageset1. We can't use copy_page (as we once did) | |
4609 | + * because we can't be sure what side effects it has. On my old Duron, with | |
4610 | + * 3DNOW, kernel_fpu_begin increments preempt count, making our preempt | |
4611 | + * count at resume time 4 instead of 3. | |
ad8f4a28 | 4612 | + * |
24613191 | 4613 | + * We don't want to call kmap_atomic unconditionally because it has the side |
4614 | + * effect of incrementing the preempt count, which will leave it one too high | |
4615 | + * post resume (the page containing the preempt count will be copied after | |
4616 | + * its incremented. This is essentially the same problem. | |
4617 | + **/ | |
4618 | + | |
4e97e4e9 | 4619 | +void toi_copy_pageset1(void) |
24613191 | 4620 | +{ |
4621 | + int i; | |
4622 | + unsigned long source_index, dest_index; | |
4623 | + | |
1838f965 | 4624 | + memory_bm_position_reset(&pageset1_map); |
4625 | + memory_bm_position_reset(&pageset1_copy_map); | |
4626 | + | |
4627 | + source_index = memory_bm_next_pfn(&pageset1_map); | |
4628 | + dest_index = memory_bm_next_pfn(&pageset1_copy_map); | |
24613191 | 4629 | + |
4630 | + for (i = 0; i < pagedir1.size; i++) { | |
4631 | + unsigned long *origvirt, *copyvirt; | |
4632 | + struct page *origpage, *copypage; | |
fea155ea PS |
4633 | + int loop = (PAGE_SIZE / sizeof(unsigned long)) - 1, |
4634 | + was_present; | |
24613191 | 4635 | + |
4636 | + origpage = pfn_to_page(source_index); | |
4637 | + copypage = pfn_to_page(dest_index); | |
ad8f4a28 | 4638 | + |
24613191 | 4639 | + origvirt = PageHighMem(origpage) ? |
4640 | + kmap_atomic(origpage, KM_USER0) : | |
4641 | + page_address(origpage); | |
4642 | + | |
ad8f4a28 | 4643 | + copyvirt = PageHighMem(copypage) ? |
24613191 | 4644 | + kmap_atomic(copypage, KM_USER1) : |
4645 | + page_address(copypage); | |
4646 | + | |
fea155ea PS |
4647 | + was_present = kernel_page_present(origpage); |
4648 | + if (!was_present) | |
4649 | + kernel_map_pages(origpage, 1, 1); | |
4650 | + | |
24613191 | 4651 | + while (loop >= 0) { |
4652 | + *(copyvirt + loop) = *(origvirt + loop); | |
4653 | + loop--; | |
4654 | + } | |
ad8f4a28 | 4655 | + |
fea155ea PS |
4656 | + if (!was_present) |
4657 | + kernel_map_pages(origpage, 1, 0); | |
4658 | + | |
24613191 | 4659 | + if (PageHighMem(origpage)) |
4660 | + kunmap_atomic(origvirt, KM_USER0); | |
24613191 | 4661 | + |
4662 | + if (PageHighMem(copypage)) | |
4663 | + kunmap_atomic(copyvirt, KM_USER1); | |
ad8f4a28 | 4664 | + |
1838f965 | 4665 | + source_index = memory_bm_next_pfn(&pageset1_map); |
4666 | + dest_index = memory_bm_next_pfn(&pageset1_copy_map); | |
24613191 | 4667 | + } |
4668 | +} | |
4669 | + | |
4670 | +/** | |
4e97e4e9 | 4671 | + * __toi_post_context_save: Steps after saving the cpu context. |
24613191 | 4672 | + * |
4673 | + * Steps taken after saving the CPU state to make the actual | |
4674 | + * atomic copy. | |
4675 | + * | |
4e97e4e9 | 4676 | + * Called from swsusp_save in snapshot.c via toi_post_context_save. |
24613191 | 4677 | + **/ |
4678 | + | |
4e97e4e9 | 4679 | +int __toi_post_context_save(void) |
24613191 | 4680 | +{ |
7f9d2ee0 | 4681 | + long old_ps1_size = pagedir1.size; |
ad8f4a28 | 4682 | + |
4e97e4e9 | 4683 | + check_checksums(); |
24613191 | 4684 | + |
4685 | + free_checksum_pages(); | |
4686 | + | |
4e97e4e9 | 4687 | + toi_recalculate_image_contents(1); |
24613191 | 4688 | + |
4689 | + extra_pd1_pages_used = pagedir1.size - old_ps1_size; | |
4690 | + | |
4691 | + if (extra_pd1_pages_used > extra_pd1_pages_allowance) { | |
7f9d2ee0 | 4692 | + printk(KERN_INFO "Pageset1 has grown by %ld pages. " |
4693 | + "extra_pages_allowance is currently only %lu.\n", | |
24613191 | 4694 | + pagedir1.size - old_ps1_size, |
4695 | + extra_pd1_pages_allowance); | |
4e97e4e9 | 4696 | + set_abort_result(TOI_EXTRA_PAGES_ALLOW_TOO_SMALL); |
1838f965 | 4697 | + return 1; |
24613191 | 4698 | + } |
4699 | + | |
4e97e4e9 | 4700 | + if (!test_action_state(TOI_TEST_FILTER_SPEED) && |
4701 | + !test_action_state(TOI_TEST_BIO)) | |
4702 | + toi_copy_pageset1(); | |
24613191 | 4703 | + |
4704 | + return 0; | |
4705 | +} | |
4706 | + | |
4707 | +/** | |
4e97e4e9 | 4708 | + * toi_hibernate: High level code for doing the atomic copy. |
24613191 | 4709 | + * |
4710 | + * High-level code which prepares to do the atomic copy. Loosely based | |
4711 | + * on the swsusp version, but with the following twists: | |
4e97e4e9 | 4712 | + * - We set toi_running so the swsusp code uses our code paths. |
24613191 | 4713 | + * - We give better feedback regarding what goes wrong if there is a problem. |
4714 | + * - We use an extra function to call the assembly, just in case this code | |
4715 | + * is in a module (return address). | |
4716 | + **/ | |
4717 | + | |
4e97e4e9 | 4718 | +int toi_hibernate(void) |
24613191 | 4719 | +{ |
4720 | + int error; | |
4721 | + | |
4e97e4e9 | 4722 | + toi_running = 1; /* For the swsusp code we use :< */ |
24613191 | 4723 | + |
4e97e4e9 | 4724 | + error = toi_lowlevel_builtin(); |
24613191 | 4725 | + |
4e97e4e9 | 4726 | + toi_running = 0; |
24613191 | 4727 | + return error; |
4728 | +} | |
4729 | + | |
4730 | +/** | |
4e97e4e9 | 4731 | + * toi_atomic_restore: Prepare to do the atomic restore. |
24613191 | 4732 | + * |
4733 | + * Get ready to do the atomic restore. This part gets us into the same | |
4e97e4e9 | 4734 | + * state we are in prior to do calling do_toi_lowlevel while |
4735 | + * hibernating: hot-unplugging secondary cpus and freeze processes, | |
24613191 | 4736 | + * before starting the thread that will do the restore. |
4737 | + **/ | |
4738 | + | |
4e97e4e9 | 4739 | +int toi_atomic_restore(void) |
24613191 | 4740 | +{ |
ad8f4a28 | 4741 | + int error; |
24613191 | 4742 | + |
4e97e4e9 | 4743 | + toi_running = 1; |
24613191 | 4744 | + |
4e97e4e9 | 4745 | + toi_prepare_status(DONT_CLEAR_BAR, "Atomic restore."); |
73c609d5 | 4746 | + |
1838f965 | 4747 | + memcpy(&toi_bkd.toi_nosave_commandline, saved_command_line, |
4748 | + COMMAND_LINE_SIZE); | |
4749 | + | |
ad8f4a28 | 4750 | + if (add_boot_kernel_data_pbe()) |
4e97e4e9 | 4751 | + goto Failed; |
24613191 | 4752 | + |
fea155ea | 4753 | + if (toi_go_atomic(PMSG_QUIESCE, 0)) |
ad8f4a28 | 4754 | + goto Failed; |
24613191 | 4755 | + |
4756 | + /* We'll ignore saved state, but this gets preempt count (etc) right */ | |
4757 | + save_processor_state(); | |
4758 | + | |
4759 | + error = swsusp_arch_resume(); | |
ad8f4a28 | 4760 | + /* |
24613191 | 4761 | + * Code below is only ever reached in case of failure. Otherwise |
4762 | + * execution continues at place where swsusp_arch_suspend was called. | |
4763 | + * | |
4764 | + * We don't know whether it's safe to continue (this shouldn't happen), | |
4765 | + * so lets err on the side of caution. | |
ad8f4a28 | 4766 | + */ |
24613191 | 4767 | + BUG(); |
4768 | + | |
4e97e4e9 | 4769 | +Failed: |
24613191 | 4770 | + free_pbe_list(&restore_pblist, 0); |
4771 | +#ifdef CONFIG_HIGHMEM | |
4772 | + free_pbe_list(&restore_highmem_pblist, 1); | |
4773 | +#endif | |
4e97e4e9 | 4774 | + if (test_action_state(TOI_PM_PREPARE_CONSOLE)) |
e8d0ad9d | 4775 | + pm_restore_console(); |
4e97e4e9 | 4776 | + toi_running = 0; |
24613191 | 4777 | + return 1; |
4778 | +} | |
4e97e4e9 | 4779 | + |
4780 | +int toi_go_atomic(pm_message_t state, int suspend_time) | |
4781 | +{ | |
7f9d2ee0 | 4782 | + toi_prepare_status(DONT_CLEAR_BAR, "Doing atomic copy/restore."); |
4e97e4e9 | 4783 | + |
1838f965 | 4784 | + if (suspend_time && platform_begin(1)) { |
4e97e4e9 | 4785 | + set_abort_result(TOI_PLATFORM_PREP_FAILED); |
fea155ea | 4786 | + toi_end_atomic(ATOMIC_STEP_PLATFORM_END, suspend_time, 0); |
4e97e4e9 | 4787 | + return 1; |
4788 | + } | |
4789 | + | |
4790 | + suspend_console(); | |
1838f965 | 4791 | + ftrace_save = __ftrace_enabled_save(); |
4e97e4e9 | 4792 | + |
4793 | + if (device_suspend(state)) { | |
4794 | + set_abort_result(TOI_DEVICE_REFUSED); | |
1838f965 | 4795 | + toi_end_atomic(ATOMIC_STEP_DEVICE_RESUME, suspend_time, 3); |
4e97e4e9 | 4796 | + return 1; |
4797 | + } | |
4798 | + | |
1838f965 | 4799 | + if (suspend_time && platform_pre_snapshot(1)) { |
ad8f4a28 | 4800 | + set_abort_result(TOI_PRE_SNAPSHOT_FAILED); |
fea155ea | 4801 | + toi_end_atomic(ATOMIC_STEP_PLATFORM_FINISH, suspend_time, 0); |
ad8f4a28 AM |
4802 | + return 1; |
4803 | + } | |
4804 | + | |
1838f965 | 4805 | + if (!suspend_time && platform_pre_restore(1)) { |
ad8f4a28 | 4806 | + set_abort_result(TOI_PRE_RESTORE_FAILED); |
fea155ea | 4807 | + toi_end_atomic(ATOMIC_STEP_DEVICE_RESUME, suspend_time, 0); |
ad8f4a28 AM |
4808 | + return 1; |
4809 | + } | |
4810 | + | |
4e97e4e9 | 4811 | + if (test_action_state(TOI_LATE_CPU_HOTPLUG)) { |
4e97e4e9 | 4812 | + if (disable_nonboot_cpus()) { |
4813 | + set_abort_result(TOI_CPU_HOTPLUG_FAILED); | |
7f9d2ee0 | 4814 | + toi_end_atomic(ATOMIC_STEP_CPU_HOTPLUG, |
fea155ea | 4815 | + suspend_time, 0); |
4e97e4e9 | 4816 | + return 1; |
4817 | + } | |
4818 | + } | |
4819 | + | |
4820 | + if (suspend_time && arch_prepare_suspend()) { | |
4821 | + set_abort_result(TOI_ARCH_PREPARE_FAILED); | |
fea155ea | 4822 | + toi_end_atomic(ATOMIC_STEP_CPU_HOTPLUG, suspend_time, 0); |
4e97e4e9 | 4823 | + return 1; |
4824 | + } | |
4825 | + | |
fea155ea | 4826 | + device_pm_lock(); |
4e97e4e9 | 4827 | + local_irq_disable(); |
4828 | + | |
4829 | + /* At this point, device_suspend() has been called, but *not* | |
4830 | + * device_power_down(). We *must* device_power_down() now. | |
4831 | + * Otherwise, drivers for some devices (e.g. interrupt controllers) | |
4832 | + * become desynchronized with the actual state of the hardware | |
4833 | + * at resume time, and evil weirdness ensues. | |
4834 | + */ | |
4835 | + | |
4836 | + if (device_power_down(state)) { | |
4837 | + set_abort_result(TOI_DEVICE_REFUSED); | |
fea155ea | 4838 | + toi_end_atomic(ATOMIC_STEP_IRQS, suspend_time, 0); |
4e97e4e9 | 4839 | + return 1; |
4840 | + } | |
4841 | + | |
4842 | + return 0; | |
4843 | +} | |
4844 | + | |
fea155ea | 4845 | +void toi_end_atomic(int stage, int suspend_time, int error) |
4e97e4e9 | 4846 | +{ |
4847 | + switch (stage) { | |
ad8f4a28 AM |
4848 | + case ATOMIC_ALL_STEPS: |
4849 | + if (!suspend_time) | |
1838f965 | 4850 | + platform_leave(1); |
4851 | + device_power_up(suspend_time ? | |
4852 | + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); | |
ad8f4a28 AM |
4853 | + case ATOMIC_STEP_IRQS: |
4854 | + local_irq_enable(); | |
fea155ea | 4855 | + device_pm_unlock(); |
ad8f4a28 AM |
4856 | + case ATOMIC_STEP_CPU_HOTPLUG: |
4857 | + if (test_action_state(TOI_LATE_CPU_HOTPLUG)) | |
4858 | + enable_nonboot_cpus(); | |
f3e0dcc9 | 4859 | + case ATOMIC_STEP_PLATFORM_FINISH: |
1838f965 | 4860 | + platform_finish(1); |
7f9d2ee0 | 4861 | + case ATOMIC_STEP_DEVICE_RESUME: |
1838f965 | 4862 | + if (suspend_time && (error & 2)) { |
4863 | + platform_recover(1); | |
4864 | + } | |
4865 | + device_resume(suspend_time ? | |
4866 | + ((error & 1) ? PMSG_RECOVER : PMSG_THAW) : | |
4867 | + PMSG_RESTORE); | |
ad8f4a28 | 4868 | + case ATOMIC_STEP_RESUME_CONSOLE: |
1838f965 | 4869 | + __ftrace_enabled_restore(ftrace_save); |
ad8f4a28 | 4870 | + resume_console(); |
7f9d2ee0 | 4871 | + case ATOMIC_STEP_PLATFORM_END: |
1838f965 | 4872 | + platform_end(1); |
ad8f4a28 AM |
4873 | + |
4874 | + toi_prepare_status(DONT_CLEAR_BAR, "Post atomic."); | |
4e97e4e9 | 4875 | + } |
4876 | +} | |
4877 | diff --git a/kernel/power/tuxonice_atomic_copy.h b/kernel/power/tuxonice_atomic_copy.h | |
4878 | new file mode 100644 | |
1838f965 | 4879 | index 0000000..8df3552 |
4e97e4e9 | 4880 | --- /dev/null |
4881 | +++ b/kernel/power/tuxonice_atomic_copy.h | |
f3e0dcc9 | 4882 | @@ -0,0 +1,22 @@ |
24613191 | 4883 | +/* |
4e97e4e9 | 4884 | + * kernel/power/tuxonice_atomic_copy.h |
24613191 | 4885 | + * |
1838f965 | 4886 | + * Copyright 2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 4887 | + * |
4888 | + * Distributed under GPLv2. | |
4889 | + * | |
4e97e4e9 | 4890 | + * Routines for doing the atomic save/restore. |
24613191 | 4891 | + */ |
4892 | + | |
4e97e4e9 | 4893 | +enum { |
4894 | + ATOMIC_ALL_STEPS, | |
4895 | + ATOMIC_STEP_IRQS, | |
4896 | + ATOMIC_STEP_CPU_HOTPLUG, | |
f3e0dcc9 | 4897 | + ATOMIC_STEP_PLATFORM_FINISH, |
4e97e4e9 | 4898 | + ATOMIC_STEP_DEVICE_RESUME, |
4899 | + ATOMIC_STEP_RESUME_CONSOLE, | |
7f9d2ee0 | 4900 | + ATOMIC_STEP_PLATFORM_END, |
24613191 | 4901 | +}; |
4902 | + | |
4e97e4e9 | 4903 | +int toi_go_atomic(pm_message_t state, int toi_time); |
fea155ea | 4904 | +void toi_end_atomic(int stage, int toi_time, int error); |
4e97e4e9 | 4905 | diff --git a/kernel/power/tuxonice_block_io.c b/kernel/power/tuxonice_block_io.c |
4906 | new file mode 100644 | |
1838f965 | 4907 | index 0000000..0af7fc5 |
4e97e4e9 | 4908 | --- /dev/null |
4909 | +++ b/kernel/power/tuxonice_block_io.c | |
1838f965 | 4910 | @@ -0,0 +1,1211 @@ |
24613191 | 4911 | +/* |
4e97e4e9 | 4912 | + * kernel/power/tuxonice_block_io.c |
24613191 | 4913 | + * |
1838f965 | 4914 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 4915 | + * |
4e97e4e9 | 4916 | + * Distributed under GPLv2. |
4917 | + * | |
4918 | + * This file contains block io functions for TuxOnIce. These are | |
4919 | + * used by the swapwriter and it is planned that they will also | |
4920 | + * be used by the NFSwriter. | |
24613191 | 4921 | + * |
24613191 | 4922 | + */ |
4923 | + | |
4e97e4e9 | 4924 | +#include <linux/blkdev.h> |
4925 | +#include <linux/syscalls.h> | |
24613191 | 4926 | +#include <linux/suspend.h> |
24613191 | 4927 | + |
4e97e4e9 | 4928 | +#include "tuxonice.h" |
4929 | +#include "tuxonice_sysfs.h" | |
4930 | +#include "tuxonice_modules.h" | |
4931 | +#include "tuxonice_prepare_image.h" | |
4932 | +#include "tuxonice_block_io.h" | |
4933 | +#include "tuxonice_ui.h" | |
ad8f4a28 | 4934 | +#include "tuxonice_alloc.h" |
7f9d2ee0 | 4935 | +#include "tuxonice_io.h" |
24613191 | 4936 | + |
1838f965 | 4937 | +#define ANY_REASON 0 |
4938 | +#define MEMORY_ONLY 1 | |
24613191 | 4939 | + |
1838f965 | 4940 | +/* #define MEASURE_MUTEX_CONTENTION */ |
7f9d2ee0 | 4941 | +#ifndef MEASURE_MUTEX_CONTENTION |
4942 | +#define my_mutex_lock(index, the_lock) mutex_lock(the_lock) | |
4943 | +#define my_mutex_unlock(index, the_lock) mutex_unlock(the_lock) | |
4944 | +#else | |
4945 | +unsigned long mutex_times[2][2][NR_CPUS]; | |
4946 | +#define my_mutex_lock(index, the_lock) do { \ | |
4947 | + int have_mutex; \ | |
4948 | + have_mutex = mutex_trylock(the_lock); \ | |
4949 | + if (!have_mutex) { \ | |
4950 | + mutex_lock(the_lock); \ | |
4951 | + mutex_times[index][0][smp_processor_id()]++; \ | |
4952 | + } else { \ | |
4953 | + mutex_times[index][1][smp_processor_id()]++; \ | |
4954 | + } | |
4955 | + | |
4956 | +#define my_mutex_unlock(index, the_lock) \ | |
4957 | + mutex_unlock(the_lock); \ | |
4958 | +} while (0) | |
4959 | +#endif | |
4960 | + | |
4961 | +static int target_outstanding_io = 1024; | |
4962 | +static int max_outstanding_writes, max_outstanding_reads; | |
24613191 | 4963 | + |
4e97e4e9 | 4964 | +static struct page *bio_queue_head, *bio_queue_tail; |
1838f965 | 4965 | +static atomic_t toi_bio_queue_size; |
4e97e4e9 | 4966 | +static DEFINE_SPINLOCK(bio_queue_lock); |
24613191 | 4967 | + |
1838f965 | 4968 | +static int free_mem_throttle, throughput_throttle; |
7f9d2ee0 | 4969 | +static int more_readahead = 1; |
4970 | +static struct page *readahead_list_head, *readahead_list_tail; | |
24613191 | 4971 | + |
4e97e4e9 | 4972 | +static struct page *waiting_on; |
24613191 | 4973 | + |
1838f965 | 4974 | +static atomic_t toi_io_in_progress, toi_io_done; |
4e97e4e9 | 4975 | +static DECLARE_WAIT_QUEUE_HEAD(num_in_progress_wait); |
24613191 | 4976 | + |
ad8f4a28 | 4977 | +static int extra_page_forward; |
24613191 | 4978 | + |
4e97e4e9 | 4979 | +static int current_stream; |
7f9d2ee0 | 4980 | +/* 0 = Header, 1 = Pageset1, 2 = Pageset2, 3 = End of PS1 */ |
f3e0dcc9 | 4981 | +struct hibernate_extent_iterate_saved_state toi_writer_posn_save[4]; |
1838f965 | 4982 | +EXPORT_SYMBOL_GPL(toi_writer_posn_save); |
4e97e4e9 | 4983 | + |
4984 | +/* Pointer to current entry being loaded/saved. */ | |
1838f965 | 4985 | +struct toi_extent_iterate_state toi_writer_posn; |
4986 | +EXPORT_SYMBOL_GPL(toi_writer_posn); | |
24613191 | 4987 | + |
4e97e4e9 | 4988 | +/* Not static, so that the allocators can setup and complete |
4989 | + * writing the header */ | |
4990 | +char *toi_writer_buffer; | |
1838f965 | 4991 | +EXPORT_SYMBOL_GPL(toi_writer_buffer); |
4992 | + | |
4e97e4e9 | 4993 | +int toi_writer_buffer_posn; |
1838f965 | 4994 | +EXPORT_SYMBOL_GPL(toi_writer_buffer_posn); |
4e97e4e9 | 4995 | + |
4996 | +static struct toi_bdev_info *toi_devinfo; | |
4997 | + | |
1838f965 | 4998 | +static DEFINE_MUTEX(toi_bio_mutex); |
ad8f4a28 | 4999 | + |
7f9d2ee0 | 5000 | +static struct task_struct *toi_queue_flusher; |
5001 | +static int toi_bio_queue_flush_pages(int dedicated_thread); | |
5002 | + | |
1838f965 | 5003 | +#define TOTAL_OUTSTANDING_IO (atomic_read(&toi_io_in_progress) + \ |
5004 | + atomic_read(&toi_bio_queue_size)) | |
5005 | + | |
ad8f4a28 | 5006 | +/** |
1838f965 | 5007 | + * set_free_mem_throttle: Set the point where we pause to avoid oom. |
ad8f4a28 AM |
5008 | + * |
5009 | + * Initially, this value is zero, but when we first fail to allocate memory, | |
5010 | + * we set it (plus a buffer) and thereafter throttle i/o once that limit is | |
5011 | + * reached. | |
5012 | + */ | |
5013 | + | |
1838f965 | 5014 | +static void set_free_mem_throttle(void) |
ad8f4a28 | 5015 | +{ |
7f9d2ee0 | 5016 | + int new_throttle = nr_unallocated_buffer_pages() + 256; |
ad8f4a28 | 5017 | + |
7f9d2ee0 | 5018 | + if (new_throttle > free_mem_throttle) |
5019 | + free_mem_throttle = new_throttle; | |
24613191 | 5020 | +} |
5021 | + | |
1838f965 | 5022 | +#define NUM_REASONS 7 |
ad8f4a28 AM |
5023 | +static atomic_t reasons[NUM_REASONS]; |
5024 | +static char *reason_name[NUM_REASONS] = { | |
4e97e4e9 | 5025 | + "readahead not ready", |
5026 | + "bio allocation", | |
4e97e4e9 | 5027 | + "synchronous I/O", |
7f9d2ee0 | 5028 | + "toi_bio_get_new_page", |
5029 | + "memory low", | |
1838f965 | 5030 | + "readahead buffer allocation", |
5031 | + "throughput_throttle", | |
4e97e4e9 | 5032 | +}; |
5033 | + | |
5034 | +/** | |
5035 | + * do_bio_wait: Wait for some TuxOnIce i/o to complete. | |
5036 | + * | |
5037 | + * Submit any I/O that's batched up (if we're not already doing | |
5038 | + * that, schedule and clean up whatever we can. | |
5039 | + */ | |
5040 | +static void do_bio_wait(int reason) | |
24613191 | 5041 | +{ |
ad8f4a28 AM |
5042 | + struct page *was_waiting_on = waiting_on; |
5043 | + | |
5044 | + /* On SMP, waiting_on can be reset, so we make a copy */ | |
5045 | + if (was_waiting_on) { | |
5046 | + if (PageLocked(was_waiting_on)) { | |
5047 | + wait_on_page_bit(was_waiting_on, PG_locked); | |
5048 | + atomic_inc(&reasons[reason]); | |
5049 | + } | |
4e97e4e9 | 5050 | + } else { |
ad8f4a28 AM |
5051 | + atomic_inc(&reasons[reason]); |
5052 | + | |
ad8f4a28 | 5053 | + wait_event(num_in_progress_wait, |
7f9d2ee0 | 5054 | + !atomic_read(&toi_io_in_progress) || |
5055 | + nr_unallocated_buffer_pages() > free_mem_throttle); | |
4e97e4e9 | 5056 | + } |
24613191 | 5057 | +} |
5058 | + | |
1838f965 | 5059 | +static void throttle_if_needed(int reason) |
24613191 | 5060 | +{ |
7f9d2ee0 | 5061 | + int free_pages = nr_unallocated_buffer_pages(); |
24613191 | 5062 | + |
7f9d2ee0 | 5063 | + /* Getting low on memory and I/O is in progress? */ |
5064 | + while (unlikely(free_pages < free_mem_throttle) && | |
5065 | + atomic_read(&toi_io_in_progress)) { | |
1838f965 | 5066 | + do_bio_wait(4); |
7f9d2ee0 | 5067 | + free_pages = nr_unallocated_buffer_pages(); |
5068 | + } | |
1838f965 | 5069 | + |
5070 | + while (reason == ANY_REASON && throughput_throttle && | |
5071 | + TOTAL_OUTSTANDING_IO >= throughput_throttle) { | |
5072 | + atomic_inc(&reasons[6]); | |
5073 | + wait_event(num_in_progress_wait, | |
5074 | + !atomic_read(&toi_io_in_progress) || | |
5075 | + TOTAL_OUTSTANDING_IO < throughput_throttle); | |
5076 | + } | |
5077 | +} | |
5078 | + | |
5079 | +/** | |
5080 | + * toi_monitor_outstanding_io: Show the user how much I/O we're waiting for. | |
5081 | + */ | |
5082 | +static void toi_monitor_outstanding_io(void) | |
5083 | +{ | |
5084 | + int orig = TOTAL_OUTSTANDING_IO, step = orig / 5; | |
5085 | + | |
5086 | + while (orig) { | |
5087 | + int new_min = orig > step ? orig - step : 0, | |
5088 | + new_max = orig + step, | |
5089 | + mb = MB(orig); | |
5090 | + if (mb) | |
5091 | + toi_prepare_status(DONT_CLEAR_BAR, | |
5092 | + "Waiting on I/O completion (%d MB)", mb); | |
5093 | + wait_event(num_in_progress_wait, | |
5094 | + TOTAL_OUTSTANDING_IO <= new_min || | |
5095 | + TOTAL_OUTSTANDING_IO >= new_max); | |
5096 | + orig = TOTAL_OUTSTANDING_IO; | |
5097 | + } | |
5098 | +} | |
5099 | + | |
5100 | +/** | |
5101 | + * update_throughput_throttle: Update the raw throughput throttle. | |
5102 | + * | |
5103 | + * Called once per second by the core, used to limit the amount of I/O | |
5104 | + * we submit at once, spreading out our waiting through the whole job | |
5105 | + * and letting userui get an opportunity to do its work. | |
5106 | + * | |
5107 | + * We throttle to 1/10s worth of I/O. | |
5108 | + */ | |
5109 | +static void update_throughput_throttle(int jif_index) | |
5110 | +{ | |
5111 | + int done = atomic_read(&toi_io_done); | |
5112 | + throughput_throttle = done / jif_index; | |
24613191 | 5113 | +} |
5114 | + | |
4e97e4e9 | 5115 | +/** |
1838f965 | 5116 | + * toi_finish_all_io: Wait for all outstanding i/o to complete. |
24613191 | 5117 | + */ |
7f9d2ee0 | 5118 | +static void toi_finish_all_io(void) |
24613191 | 5119 | +{ |
1838f965 | 5120 | + toi_bio_queue_flush_pages(0); |
5121 | + wait_event(num_in_progress_wait, !TOTAL_OUTSTANDING_IO); | |
24613191 | 5122 | +} |
24613191 | 5123 | + |
4e97e4e9 | 5124 | +/** |
5125 | + * toi_end_bio: bio completion function. | |
5126 | + * | |
5127 | + * @bio: bio that has completed. | |
4e97e4e9 | 5128 | + * @err: Error value. Yes, like end_swap_bio_read, we ignore it. |
5129 | + * | |
5130 | + * Function called by block driver from interrupt context when I/O is completed. | |
7f9d2ee0 | 5131 | + * Nearly the fs/buffer.c version, but we want to do our cleanup too. We only |
5132 | + * free pages if they were buffers used when writing the image. | |
24613191 | 5133 | + */ |
ad8f4a28 | 5134 | +static void toi_end_bio(struct bio *bio, int err) |
24613191 | 5135 | +{ |
4e97e4e9 | 5136 | + struct page *page = bio->bi_io_vec[0].bv_page; |
24613191 | 5137 | + |
4e97e4e9 | 5138 | + BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); |
24613191 | 5139 | + |
7f9d2ee0 | 5140 | + unlock_page(page); |
5141 | + bio_put(bio); | |
5142 | + | |
5143 | + if (waiting_on == page) | |
5144 | + waiting_on = NULL; | |
24613191 | 5145 | + |
7f9d2ee0 | 5146 | + put_page(page); |
5147 | + | |
5148 | + if (bio->bi_private) | |
5149 | + toi__free_page((int) ((unsigned long) bio->bi_private) , page); | |
24613191 | 5150 | + |
4e97e4e9 | 5151 | + bio_put(bio); |
5152 | + | |
5153 | + atomic_dec(&toi_io_in_progress); | |
1838f965 | 5154 | + atomic_inc(&toi_io_done); |
4e97e4e9 | 5155 | + |
5156 | + wake_up(&num_in_progress_wait); | |
24613191 | 5157 | +} |
5158 | + | |
4e97e4e9 | 5159 | +/** |
5160 | + * submit - submit BIO request. | |
5161 | + * @writing: READ or WRITE. | |
4e97e4e9 | 5162 | + * |
5163 | + * Based on Patrick's pmdisk code from long ago: | |
5164 | + * "Straight from the textbook - allocate and initialize the bio. | |
5165 | + * If we're writing, make sure the page is marked as dirty. | |
5166 | + * Then submit it and carry on." | |
5167 | + * | |
5168 | + * With a twist, though - we handle block_size != PAGE_SIZE. | |
5169 | + * Caller has already checked that our page is not fragmented. | |
5170 | + */ | |
7f9d2ee0 | 5171 | +static int submit(int writing, struct block_device *dev, sector_t first_block, |
5172 | + struct page *page, int free_group) | |
4e97e4e9 | 5173 | +{ |
5174 | + struct bio *bio = NULL; | |
7f9d2ee0 | 5175 | + int cur_outstanding_io; |
5176 | + | |
1838f965 | 5177 | + throttle_if_needed(MEMORY_ONLY); |
24613191 | 5178 | + |
4e97e4e9 | 5179 | + while (!bio) { |
ad8f4a28 AM |
5180 | + bio = bio_alloc(TOI_ATOMIC_GFP, 1); |
5181 | + if (!bio) { | |
1838f965 | 5182 | + set_free_mem_throttle(); |
4e97e4e9 | 5183 | + do_bio_wait(1); |
ad8f4a28 | 5184 | + } |
24613191 | 5185 | + } |
24613191 | 5186 | + |
7f9d2ee0 | 5187 | + bio->bi_bdev = dev; |
5188 | + bio->bi_sector = first_block; | |
5189 | + bio->bi_private = (void *) ((unsigned long) free_group); | |
4e97e4e9 | 5190 | + bio->bi_end_io = toi_end_bio; |
24613191 | 5191 | + |
7f9d2ee0 | 5192 | + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { |
ad8f4a28 | 5193 | + printk(KERN_INFO "ERROR: adding page to bio at %lld\n", |
7f9d2ee0 | 5194 | + (unsigned long long) first_block); |
4e97e4e9 | 5195 | + bio_put(bio); |
5196 | + return -EFAULT; | |
5197 | + } | |
24613191 | 5198 | + |
4e97e4e9 | 5199 | + bio_get(bio); |
24613191 | 5200 | + |
7f9d2ee0 | 5201 | + cur_outstanding_io = atomic_add_return(1, &toi_io_in_progress); |
5202 | + if (writing) { | |
5203 | + if (cur_outstanding_io > max_outstanding_writes) | |
5204 | + max_outstanding_writes = cur_outstanding_io; | |
5205 | + } else { | |
5206 | + if (cur_outstanding_io > max_outstanding_reads) | |
5207 | + max_outstanding_reads = cur_outstanding_io; | |
5208 | + } | |
4e97e4e9 | 5209 | + |
4e97e4e9 | 5210 | + |
5211 | + if (unlikely(test_action_state(TOI_TEST_FILTER_SPEED))) { | |
5212 | + /* Fake having done the hard work */ | |
5213 | + set_bit(BIO_UPTODATE, &bio->bi_flags); | |
ad8f4a28 | 5214 | + toi_end_bio(bio, 0); |
4e97e4e9 | 5215 | + } else |
7f9d2ee0 | 5216 | + submit_bio(writing | (1 << BIO_RW_SYNC), bio); |
4e97e4e9 | 5217 | + |
5218 | + return 0; | |
24613191 | 5219 | +} |
5220 | + | |
4e97e4e9 | 5221 | +/** |
4e97e4e9 | 5222 | + * toi_do_io: Prepare to do some i/o on a page and submit or batch it. |
24613191 | 5223 | + * |
4e97e4e9 | 5224 | + * @writing: Whether reading or writing. |
5225 | + * @bdev: The block device which we're using. | |
5226 | + * @block0: The first sector we're reading or writing. | |
5227 | + * @page: The page on which I/O is being done. | |
5228 | + * @readahead_index: If doing readahead, the index (reset this flag when done). | |
5229 | + * @syncio: Whether the i/o is being done synchronously. | |
24613191 | 5230 | + * |
4e97e4e9 | 5231 | + * Prepare and start a read or write operation. |
24613191 | 5232 | + * |
4e97e4e9 | 5233 | + * Note that we always work with our own page. If writing, we might be given a |
5234 | + * compression buffer that will immediately be used to start compressing the | |
5235 | + * next page. For reading, we do readahead and therefore don't know the final | |
5236 | + * address where the data needs to go. | |
24613191 | 5237 | + */ |
7f9d2ee0 | 5238 | +static int toi_do_io(int writing, struct block_device *bdev, long block0, |
5239 | + struct page *page, int is_readahead, int syncio, int free_group) | |
4e97e4e9 | 5240 | +{ |
7f9d2ee0 | 5241 | + page->private = 0; |
24613191 | 5242 | + |
7f9d2ee0 | 5243 | + /* Do here so we don't race against toi_bio_get_next_page_read */ |
5244 | + lock_page(page); | |
24613191 | 5245 | + |
7f9d2ee0 | 5246 | + if (is_readahead) { |
5247 | + if (readahead_list_head) | |
5248 | + readahead_list_tail->private = (unsigned long) page; | |
5249 | + else | |
5250 | + readahead_list_head = page; | |
24613191 | 5251 | + |
7f9d2ee0 | 5252 | + readahead_list_tail = page; |
4e97e4e9 | 5253 | + } |
5254 | + | |
5255 | + /* Done before submitting to avoid races. */ | |
5256 | + if (syncio) | |
7f9d2ee0 | 5257 | + waiting_on = page; |
4e97e4e9 | 5258 | + |
5259 | + /* Submit the page */ | |
7f9d2ee0 | 5260 | + get_page(page); |
4e97e4e9 | 5261 | + |
7f9d2ee0 | 5262 | + if (submit(writing, bdev, block0, page, free_group)) |
5263 | + return -EFAULT; | |
4e97e4e9 | 5264 | + |
5265 | + if (syncio) | |
1838f965 | 5266 | + do_bio_wait(2); |
7f9d2ee0 | 5267 | + |
5268 | + return 0; | |
24613191 | 5269 | +} |
5270 | + | |
4e97e4e9 | 5271 | +/** |
5272 | + * toi_bdev_page_io: Simpler interface to do directly i/o on a single page. | |
24613191 | 5273 | + * |
4e97e4e9 | 5274 | + * @writing: Whether reading or writing. |
5275 | + * @bdev: Block device on which we're operating. | |
5276 | + * @pos: Sector at which page to read starts. | |
5277 | + * @page: Page to be read/written. | |
5278 | + * | |
5279 | + * We used to use bread here, but it doesn't correctly handle | |
5280 | + * blocksize != PAGE_SIZE. Now we create a submit_info to get the data we | |
5281 | + * want and use our normal routines (synchronously). | |
24613191 | 5282 | + */ |
7f9d2ee0 | 5283 | +static int toi_bdev_page_io(int writing, struct block_device *bdev, |
4e97e4e9 | 5284 | + long pos, struct page *page) |
24613191 | 5285 | +{ |
7f9d2ee0 | 5286 | + return toi_do_io(writing, bdev, pos, page, 0, 1, 0); |
24613191 | 5287 | +} |
5288 | + | |
4e97e4e9 | 5289 | +/** |
5290 | + * toi_bio_memory_needed: Report amount of memory needed for block i/o. | |
24613191 | 5291 | + * |
ad8f4a28 AM |
5292 | + * We want to have at least enough memory so as to have target_outstanding_io |
5293 | + * or more transactions on the fly at once. If we can do more, fine. | |
24613191 | 5294 | + */ |
4e97e4e9 | 5295 | +static int toi_bio_memory_needed(void) |
24613191 | 5296 | +{ |
f3e0dcc9 PS |
5297 | + return target_outstanding_io * (PAGE_SIZE + sizeof(struct request) + |
5298 | + sizeof(struct bio)); | |
24613191 | 5299 | +} |
5300 | + | |
ad8f4a28 AM |
5301 | +/* |
5302 | + * toi_bio_print_debug_stats | |
5303 | + * | |
5304 | + * Description: | |
5305 | + */ | |
5306 | +static int toi_bio_print_debug_stats(char *buffer, int size) | |
5307 | +{ | |
1838f965 | 5308 | + int len = scnprintf(buffer, size, "- Max outstanding reads %d. Max " |
7f9d2ee0 | 5309 | + "writes %d.\n", max_outstanding_reads, |
5310 | + max_outstanding_writes); | |
ad8f4a28 | 5311 | + |
1838f965 | 5312 | + len += scnprintf(buffer + len, size - len, |
7f9d2ee0 | 5313 | + " Memory_needed: %d x (%lu + %u + %u) = %d bytes.\n", |
5314 | + target_outstanding_io, | |
ad8f4a28 | 5315 | + PAGE_SIZE, (unsigned int) sizeof(struct request), |
7f9d2ee0 | 5316 | + (unsigned int) sizeof(struct bio), toi_bio_memory_needed()); |
ad8f4a28 | 5317 | + |
7f9d2ee0 | 5318 | +#ifdef MEASURE_MUTEX_CONTENTION |
5319 | + { | |
5320 | + int i; | |
5321 | + | |
1838f965 | 5322 | + len += scnprintf(buffer + len, size - len, |
7f9d2ee0 | 5323 | + " Mutex contention while reading:\n Contended Free\n"); |
5324 | + | |
f3e0dcc9 | 5325 | + for_each_online_cpu(i) |
1838f965 | 5326 | + len += scnprintf(buffer + len, size - len, |
7f9d2ee0 | 5327 | + " %9lu %9lu\n", |
5328 | + mutex_times[0][0][i], mutex_times[0][1][i]); | |
5329 | + | |
1838f965 | 5330 | + len += scnprintf(buffer + len, size - len, |
7f9d2ee0 | 5331 | + " Mutex contention while writing:\n Contended Free\n"); |
5332 | + | |
f3e0dcc9 | 5333 | + for_each_online_cpu(i) |
1838f965 | 5334 | + len += scnprintf(buffer + len, size - len, |
7f9d2ee0 | 5335 | + " %9lu %9lu\n", |
5336 | + mutex_times[1][0][i], mutex_times[1][1][i]); | |
5337 | + | |
5338 | + } | |
5339 | +#endif | |
5340 | + | |
1838f965 | 5341 | + return len + scnprintf(buffer + len, size - len, |
7f9d2ee0 | 5342 | + " Free mem throttle point reached %d.\n", free_mem_throttle); |
ad8f4a28 AM |
5343 | +} |
5344 | + | |
4e97e4e9 | 5345 | +/** |
5346 | + * toi_set_devinfo: Set the bdev info used for i/o. | |
24613191 | 5347 | + * |
4e97e4e9 | 5348 | + * @info: Pointer to array of struct toi_bdev_info - the list of |
5349 | + * bdevs and blocks on them in which the image is stored. | |
5350 | + * | |
5351 | + * Set the list of bdevs and blocks in which the image will be stored. | |
5352 | + * Sort of like putting a tape in the cassette player. | |
24613191 | 5353 | + */ |
4e97e4e9 | 5354 | +static void toi_set_devinfo(struct toi_bdev_info *info) |
24613191 | 5355 | +{ |
4e97e4e9 | 5356 | + toi_devinfo = info; |
24613191 | 5357 | +} |
5358 | + | |
4e97e4e9 | 5359 | +/** |
5360 | + * dump_block_chains: Print the contents of the bdev info array. | |
24613191 | 5361 | + */ |
4e97e4e9 | 5362 | +static void dump_block_chains(void) |
5363 | +{ | |
5364 | + int i; | |
24613191 | 5365 | + |
4e97e4e9 | 5366 | + for (i = 0; i < toi_writer_posn.num_chains; i++) { |
f3e0dcc9 | 5367 | + struct hibernate_extent *this; |
24613191 | 5368 | + |
4e97e4e9 | 5369 | + this = (toi_writer_posn.chains + i)->first; |
24613191 | 5370 | + |
4e97e4e9 | 5371 | + if (!this) |
ad8f4a28 AM |
5372 | + continue; |
5373 | + | |
5374 | + printk(KERN_INFO "Chain %d:", i); | |
24613191 | 5375 | + |
4e97e4e9 | 5376 | + while (this) { |
f3e0dcc9 PS |
5377 | + printk(" [%lu-%lu]%s", this->start, |
5378 | + this->end, this->next ? "," : ""); | |
4e97e4e9 | 5379 | + this = this->next; |
5380 | + } | |
5381 | + | |
5382 | + printk("\n"); | |
5383 | + } | |
5384 | + | |
7f9d2ee0 | 5385 | + for (i = 0; i < 4; i++) |
ad8f4a28 AM |
5386 | + printk(KERN_INFO "Posn %d: Chain %d, extent %d, offset %lu.\n", |
5387 | + i, toi_writer_posn_save[i].chain_num, | |
4e97e4e9 | 5388 | + toi_writer_posn_save[i].extent_num, |
5389 | + toi_writer_posn_save[i].offset); | |
5390 | +} | |
24613191 | 5391 | + |
4e97e4e9 | 5392 | +/** |
5393 | + * go_next_page: Skip blocks to the start of the next page. | |
5394 | + * | |
5395 | + * Go forward one page, or two if extra_page_forward is set. It only gets | |
5396 | + * set at the start of reading the image header, to skip the first page | |
5397 | + * of the header, which is read without using the extent chains. | |
5398 | + */ | |
ad8f4a28 | 5399 | +static int go_next_page(int writing) |
24613191 | 5400 | +{ |
4e97e4e9 | 5401 | + int i, max = (toi_writer_posn.current_chain == -1) ? 1 : |
5402 | + toi_devinfo[toi_writer_posn.current_chain].blocks_per_page; | |
24613191 | 5403 | + |
4e97e4e9 | 5404 | + for (i = 0; i < max; i++) |
5405 | + toi_extent_state_next(&toi_writer_posn); | |
5406 | + | |
5407 | + if (toi_extent_state_eof(&toi_writer_posn)) { | |
ad8f4a28 AM |
5408 | + /* Don't complain if readahead falls off the end */ |
5409 | + if (writing) { | |
5410 | + printk(KERN_INFO "Extent state eof. " | |
5411 | + "Expected compression ratio too optimistic?\n"); | |
5412 | + dump_block_chains(); | |
5413 | + } | |
4e97e4e9 | 5414 | + return -ENODATA; |
5415 | + } | |
5416 | + | |
5417 | + if (extra_page_forward) { | |
5418 | + extra_page_forward = 0; | |
ad8f4a28 | 5419 | + return go_next_page(writing); |
4e97e4e9 | 5420 | + } |
5421 | + | |
5422 | + return 0; | |
24613191 | 5423 | +} |
5424 | + | |
4e97e4e9 | 5425 | +/** |
5426 | + * set_extra_page_forward: Make us skip an extra page on next go_next_page. | |
5427 | + * | |
5428 | + * Used in reading header, to jump to 2nd page after getting 1st page | |
5429 | + * direct from image header. | |
5430 | + */ | |
5431 | +static void set_extra_page_forward(void) | |
24613191 | 5432 | +{ |
4e97e4e9 | 5433 | + extra_page_forward = 1; |
24613191 | 5434 | +} |
5435 | + | |
4e97e4e9 | 5436 | +/** |
5437 | + * toi_bio_rw_page: Do i/o on the next disk page in the image. | |
24613191 | 5438 | + * |
4e97e4e9 | 5439 | + * @writing: Whether reading or writing. |
5440 | + * @page: Page to do i/o on. | |
5441 | + * @readahead_index: -1 or the index in the readahead ring. | |
24613191 | 5442 | + * |
4e97e4e9 | 5443 | + * Submit a page for reading or writing, possibly readahead. |
24613191 | 5444 | + */ |
4e97e4e9 | 5445 | +static int toi_bio_rw_page(int writing, struct page *page, |
7f9d2ee0 | 5446 | + int is_readahead, int free_group) |
4e97e4e9 | 5447 | +{ |
5448 | + struct toi_bdev_info *dev_info; | |
7f9d2ee0 | 5449 | + int result; |
24613191 | 5450 | + |
ad8f4a28 AM |
5451 | + if (go_next_page(writing)) { |
5452 | + printk(KERN_INFO "Failed to advance a page in the extent " | |
5453 | + "data.\n"); | |
4e97e4e9 | 5454 | + return -ENODATA; |
5455 | + } | |
24613191 | 5456 | + |
4e97e4e9 | 5457 | + if (current_stream == 0 && writing && |
ad8f4a28 AM |
5458 | + toi_writer_posn.current_chain == |
5459 | + toi_writer_posn_save[2].chain_num && | |
5460 | + toi_writer_posn.current_offset == | |
5461 | + toi_writer_posn_save[2].offset) { | |
4e97e4e9 | 5462 | + dump_block_chains(); |
5463 | + BUG(); | |
5464 | + } | |
24613191 | 5465 | + |
4e97e4e9 | 5466 | + dev_info = &toi_devinfo[toi_writer_posn.current_chain]; |
e8d0ad9d | 5467 | + |
7f9d2ee0 | 5468 | + result = toi_do_io(writing, dev_info->bdev, |
4e97e4e9 | 5469 | + toi_writer_posn.current_offset << |
5470 | + dev_info->bmap_shift, | |
7f9d2ee0 | 5471 | + page, is_readahead, 0, free_group); |
5472 | + | |
5473 | + if (result) { | |
5474 | + more_readahead = 0; | |
5475 | + return result; | |
5476 | + } | |
5477 | + | |
5478 | + if (!writing) { | |
5479 | + int compare_to = 0; | |
24613191 | 5480 | + |
7f9d2ee0 | 5481 | + switch (current_stream) { |
5482 | + case 0: | |
5483 | + compare_to = 2; | |
5484 | + break; | |
5485 | + case 1: | |
5486 | + compare_to = 3; | |
5487 | + break; | |
5488 | + case 2: | |
5489 | + compare_to = 1; | |
5490 | + break; | |
5491 | + } | |
5492 | + | |
5493 | + if (toi_writer_posn.current_chain == | |
5494 | + toi_writer_posn_save[compare_to].chain_num && | |
5495 | + toi_writer_posn.current_offset == | |
5496 | + toi_writer_posn_save[compare_to].offset) | |
5497 | + more_readahead = 0; | |
5498 | + } | |
4e97e4e9 | 5499 | + return 0; |
5500 | +} | |
5501 | + | |
5502 | +/** | |
5503 | + * toi_rw_init: Prepare to read or write a stream in the image. | |
24613191 | 5504 | + * |
4e97e4e9 | 5505 | + * @writing: Whether reading or writing. |
5506 | + * @stream number: Section of the image being processed. | |
24613191 | 5507 | + */ |
4e97e4e9 | 5508 | +static int toi_rw_init(int writing, int stream_number) |
5509 | +{ | |
7f9d2ee0 | 5510 | + if (stream_number) |
5511 | + toi_extent_state_restore(&toi_writer_posn, | |
5512 | + &toi_writer_posn_save[stream_number]); | |
5513 | + else | |
5514 | + toi_extent_state_goto_start(&toi_writer_posn); | |
24613191 | 5515 | + |
1838f965 | 5516 | + atomic_set(&toi_io_done, 0); |
7f9d2ee0 | 5517 | + toi_writer_buffer = (char *) toi_get_zeroed_page(11, TOI_ATOMIC_GFP); |
4e97e4e9 | 5518 | + toi_writer_buffer_posn = writing ? 0 : PAGE_SIZE; |
5519 | + | |
5520 | + current_stream = stream_number; | |
5521 | + | |
7f9d2ee0 | 5522 | + more_readahead = 1; |
4e97e4e9 | 5523 | + |
7f9d2ee0 | 5524 | + return toi_writer_buffer ? 0 : -ENOMEM; |
4e97e4e9 | 5525 | +} |
24613191 | 5526 | + |
4e97e4e9 | 5527 | +/** |
5528 | + * toi_read_header_init: Prepare to read the image header. | |
24613191 | 5529 | + * |
4e97e4e9 | 5530 | + * Reset readahead indices prior to starting to read a section of the image. |
24613191 | 5531 | + */ |
4e97e4e9 | 5532 | +static void toi_read_header_init(void) |
24613191 | 5533 | +{ |
7f9d2ee0 | 5534 | + toi_writer_buffer = (char *) toi_get_zeroed_page(11, TOI_ATOMIC_GFP); |
5535 | + more_readahead = 1; | |
24613191 | 5536 | +} |
5537 | + | |
7f9d2ee0 | 5538 | +/* |
5539 | + * toi_bio_queue_write | |
5540 | + */ | |
5541 | +static void toi_bio_queue_write(char **full_buffer) | |
5542 | +{ | |
5543 | + struct page *page = virt_to_page(*full_buffer); | |
5544 | + unsigned long flags; | |
5545 | + | |
5546 | + page->private = 0; | |
5547 | + | |
5548 | + spin_lock_irqsave(&bio_queue_lock, flags); | |
5549 | + if (!bio_queue_head) | |
5550 | + bio_queue_head = page; | |
5551 | + else | |
5552 | + bio_queue_tail->private = (unsigned long) page; | |
5553 | + | |
5554 | + bio_queue_tail = page; | |
1838f965 | 5555 | + atomic_inc(&toi_bio_queue_size); |
7f9d2ee0 | 5556 | + |
5557 | + spin_unlock_irqrestore(&bio_queue_lock, flags); | |
5558 | + wake_up(&toi_io_queue_flusher); | |
5559 | + | |
5560 | + *full_buffer = NULL; | |
5561 | +} | |
5562 | + | |
5563 | +/** | |
5564 | + * toi_rw_cleanup: Cleanup after i/o. | |
24613191 | 5565 | + * |
4e97e4e9 | 5566 | + * @writing: Whether we were reading or writing. |
24613191 | 5567 | + */ |
4e97e4e9 | 5568 | +static int toi_rw_cleanup(int writing) |
24613191 | 5569 | +{ |
4e97e4e9 | 5570 | + int i; |
24613191 | 5571 | + |
ad8f4a28 | 5572 | + if (writing) { |
f3e0dcc9 PS |
5573 | + int result; |
5574 | + | |
ad8f4a28 | 5575 | + if (toi_writer_buffer_posn) |
7f9d2ee0 | 5576 | + toi_bio_queue_write(&toi_writer_buffer); |
5577 | + | |
f3e0dcc9 PS |
5578 | + result = toi_bio_queue_flush_pages(0); |
5579 | + | |
5580 | + if (result) | |
5581 | + return result; | |
24613191 | 5582 | + |
7f9d2ee0 | 5583 | + if (current_stream == 2) |
5584 | + toi_extent_state_save(&toi_writer_posn, | |
5585 | + &toi_writer_posn_save[1]); | |
5586 | + else if (current_stream == 1) | |
5587 | + toi_extent_state_save(&toi_writer_posn, | |
5588 | + &toi_writer_posn_save[3]); | |
5589 | + } | |
4e97e4e9 | 5590 | + |
5591 | + toi_finish_all_io(); | |
5592 | + | |
7f9d2ee0 | 5593 | + while (readahead_list_head) { |
5594 | + void *next = (void *) readahead_list_head->private; | |
5595 | + toi__free_page(12, readahead_list_head); | |
5596 | + readahead_list_head = next; | |
5597 | + } | |
5598 | + | |
5599 | + readahead_list_tail = NULL; | |
4e97e4e9 | 5600 | + |
7f9d2ee0 | 5601 | + if (!current_stream) |
5602 | + return 0; | |
4e97e4e9 | 5603 | + |
ad8f4a28 AM |
5604 | + for (i = 0; i < NUM_REASONS; i++) { |
5605 | + if (!atomic_read(&reasons[i])) | |
4e97e4e9 | 5606 | + continue; |
ad8f4a28 AM |
5607 | + printk(KERN_INFO "Waited for i/o due to %s %d times.\n", |
5608 | + reason_name[i], atomic_read(&reasons[i])); | |
5609 | + atomic_set(&reasons[i], 0); | |
24613191 | 5610 | + } |
7f9d2ee0 | 5611 | + |
5612 | + current_stream = 0; | |
4e97e4e9 | 5613 | + return 0; |
24613191 | 5614 | +} |
5615 | + | |
1838f965 | 5616 | +static int toi_start_one_readahead(int dedicated_thread) |
24613191 | 5617 | +{ |
7f9d2ee0 | 5618 | + char *buffer = NULL; |
5619 | + int oom = 0; | |
24613191 | 5620 | + |
1838f965 | 5621 | + throttle_if_needed(ANY_REASON); |
24613191 | 5622 | + |
7f9d2ee0 | 5623 | + while (!buffer) { |
5624 | + buffer = (char *) toi_get_zeroed_page(12, | |
5625 | + TOI_ATOMIC_GFP); | |
5626 | + if (!buffer) { | |
5627 | + if (oom && !dedicated_thread) | |
5628 | + return -EIO; | |
5629 | + | |
5630 | + oom = 1; | |
1838f965 | 5631 | + set_free_mem_throttle(); |
5632 | + do_bio_wait(5); | |
4e97e4e9 | 5633 | + } |
4e97e4e9 | 5634 | + } |
24613191 | 5635 | + |
7f9d2ee0 | 5636 | + return toi_bio_rw_page(READ, virt_to_page(buffer), 1, 0); |
5637 | +} | |
5638 | + | |
5639 | +/* | |
5640 | + * toi_start_new_readahead | |
5641 | + * | |
5642 | + * Start readahead of image pages. | |
5643 | + * | |
5644 | + * No mutex needed because this is only ever called by one cpu. | |
5645 | + */ | |
5646 | +static int toi_start_new_readahead(int dedicated_thread) | |
5647 | +{ | |
5648 | + int last_result, num_submitted = 0; | |
5649 | + | |
5650 | + /* Start a new readahead? */ | |
5651 | + if (!more_readahead) | |
5652 | + return 0; | |
5653 | + | |
4e97e4e9 | 5654 | + do { |
7f9d2ee0 | 5655 | + int result = toi_start_one_readahead(dedicated_thread); |
24613191 | 5656 | + |
7f9d2ee0 | 5657 | + if (result == -EIO) |
5658 | + return 0; | |
5659 | + else | |
5660 | + last_result = result; | |
ad8f4a28 | 5661 | + |
7f9d2ee0 | 5662 | + if (last_result == -ENODATA) |
5663 | + more_readahead = 0; | |
24613191 | 5664 | + |
7f9d2ee0 | 5665 | + if (!more_readahead && last_result) { |
5666 | + /* | |
ad8f4a28 AM |
5667 | + * Don't complain about failing to do readahead past |
5668 | + * the end of storage. | |
5669 | + */ | |
7f9d2ee0 | 5670 | + if (last_result != -ENODATA) |
5671 | + printk(KERN_INFO | |
5672 | + "Begin read chunk returned %d.\n", | |
5673 | + last_result); | |
5674 | + } else | |
5675 | + num_submitted++; | |
24613191 | 5676 | + |
7f9d2ee0 | 5677 | + } while (more_readahead && |
5678 | + (dedicated_thread || | |
5679 | + (num_submitted < target_outstanding_io && | |
5680 | + atomic_read(&toi_io_in_progress) < target_outstanding_io))); | |
5681 | + return 0; | |
5682 | +} | |
24613191 | 5683 | + |
7f9d2ee0 | 5684 | +static void bio_io_flusher(int writing) |
5685 | +{ | |
24613191 | 5686 | + |
7f9d2ee0 | 5687 | + if (writing) |
5688 | + toi_bio_queue_flush_pages(1); | |
5689 | + else | |
5690 | + toi_start_new_readahead(1); | |
5691 | +} | |
24613191 | 5692 | + |
7f9d2ee0 | 5693 | +/** |
5694 | + * toi_bio_get_next_page_read: Read a disk page with readahead. | |
5695 | + * | |
5696 | + * Read a page from disk, submitting readahead and cleaning up finished i/o | |
5697 | + * while we wait for the page we're after. | |
5698 | + */ | |
5699 | +static int toi_bio_get_next_page_read(int no_readahead) | |
5700 | +{ | |
5701 | + unsigned long *virt; | |
5702 | + struct page *next; | |
24613191 | 5703 | + |
7f9d2ee0 | 5704 | + /* |
5705 | + * When reading the second page of the header, we have to | |
5706 | + * delay submitting the read until after we've gotten the | |
5707 | + * extents out of the first page. | |
5708 | + */ | |
5709 | + if (unlikely(no_readahead && toi_start_one_readahead(0))) { | |
f3e0dcc9 PS |
5710 | + printk(KERN_INFO "No readahead and toi_start_one_readahead " |
5711 | + "returned non-zero.\n"); | |
7f9d2ee0 | 5712 | + return -EIO; |
5713 | + } | |
5714 | + | |
5715 | + /* | |
5716 | + * On SMP, we may need to wait for the first readahead | |
5717 | + * to be submitted. | |
5718 | + */ | |
5719 | + if (unlikely(!readahead_list_head)) { | |
5720 | + BUG_ON(!more_readahead); | |
5721 | + do { | |
5722 | + cpu_relax(); | |
5723 | + } while (!readahead_list_head); | |
5724 | + } | |
5725 | + | |
5726 | + if (PageLocked(readahead_list_head)) { | |
5727 | + waiting_on = readahead_list_head; | |
5728 | + do_bio_wait(0); | |
5729 | + } | |
24613191 | 5730 | + |
7f9d2ee0 | 5731 | + virt = page_address(readahead_list_head); |
5732 | + memcpy(toi_writer_buffer, virt, PAGE_SIZE); | |
24613191 | 5733 | + |
7f9d2ee0 | 5734 | + next = (struct page *) readahead_list_head->private; |
5735 | + toi__free_page(12, readahead_list_head); | |
5736 | + readahead_list_head = next; | |
24613191 | 5737 | + return 0; |
5738 | +} | |
5739 | + | |
4e97e4e9 | 5740 | +/* |
5741 | + * toi_bio_queue_flush_pages | |
24613191 | 5742 | + */ |
4e97e4e9 | 5743 | + |
7f9d2ee0 | 5744 | +static int toi_bio_queue_flush_pages(int dedicated_thread) |
24613191 | 5745 | +{ |
4e97e4e9 | 5746 | + unsigned long flags; |
5747 | + int result = 0; | |
24613191 | 5748 | + |
7f9d2ee0 | 5749 | +top: |
4e97e4e9 | 5750 | + spin_lock_irqsave(&bio_queue_lock, flags); |
5751 | + while (bio_queue_head) { | |
5752 | + struct page *page = bio_queue_head; | |
5753 | + bio_queue_head = (struct page *) page->private; | |
5754 | + if (bio_queue_tail == page) | |
5755 | + bio_queue_tail = NULL; | |
1838f965 | 5756 | + atomic_dec(&toi_bio_queue_size); |
4e97e4e9 | 5757 | + spin_unlock_irqrestore(&bio_queue_lock, flags); |
7f9d2ee0 | 5758 | + result = toi_bio_rw_page(WRITE, page, 0, 11); |
4e97e4e9 | 5759 | + if (result) |
7f9d2ee0 | 5760 | + return result; |
4e97e4e9 | 5761 | + spin_lock_irqsave(&bio_queue_lock, flags); |
24613191 | 5762 | + } |
4e97e4e9 | 5763 | + spin_unlock_irqrestore(&bio_queue_lock, flags); |
7f9d2ee0 | 5764 | + |
5765 | + if (dedicated_thread) { | |
5766 | + wait_event(toi_io_queue_flusher, bio_queue_head || | |
5767 | + toi_bio_queue_flusher_should_finish); | |
5768 | + if (likely(!toi_bio_queue_flusher_should_finish)) | |
5769 | + goto top; | |
5770 | + toi_bio_queue_flusher_should_finish = 0; | |
5771 | + } | |
5772 | + return 0; | |
4e97e4e9 | 5773 | +} |
24613191 | 5774 | + |
4e97e4e9 | 5775 | +/* |
7f9d2ee0 | 5776 | + * toi_bio_get_new_page |
4e97e4e9 | 5777 | + */ |
7f9d2ee0 | 5778 | +static void toi_bio_get_new_page(char **full_buffer) |
4e97e4e9 | 5779 | +{ |
1838f965 | 5780 | + throttle_if_needed(ANY_REASON); |
4e97e4e9 | 5781 | + |
5782 | + while (!*full_buffer) { | |
ad8f4a28 AM |
5783 | + *full_buffer = (char *) toi_get_zeroed_page(11, TOI_ATOMIC_GFP); |
5784 | + if (!*full_buffer) { | |
1838f965 | 5785 | + set_free_mem_throttle(); |
5786 | + do_bio_wait(3); | |
ad8f4a28 | 5787 | + } |
24613191 | 5788 | + } |
24613191 | 5789 | +} |
5790 | + | |
4e97e4e9 | 5791 | +/* |
5792 | + * toi_rw_buffer: Combine smaller buffers into PAGE_SIZE I/O. | |
24613191 | 5793 | + * |
4e97e4e9 | 5794 | + * @writing: Bool - whether writing (or reading). |
5795 | + * @buffer: The start of the buffer to write or fill. | |
5796 | + * @buffer_size: The size of the buffer to write or fill. | |
24613191 | 5797 | + */ |
f3e0dcc9 PS |
5798 | +static int toi_rw_buffer(int writing, char *buffer, int buffer_size, |
5799 | + int no_readahead) | |
24613191 | 5800 | +{ |
4e97e4e9 | 5801 | + int bytes_left = buffer_size; |
24613191 | 5802 | + |
4e97e4e9 | 5803 | + while (bytes_left) { |
5804 | + char *source_start = buffer + buffer_size - bytes_left; | |
5805 | + char *dest_start = toi_writer_buffer + toi_writer_buffer_posn; | |
5806 | + int capacity = PAGE_SIZE - toi_writer_buffer_posn; | |
5807 | + char *to = writing ? dest_start : source_start; | |
5808 | + char *from = writing ? source_start : dest_start; | |
24613191 | 5809 | + |
4e97e4e9 | 5810 | + if (bytes_left <= capacity) { |
5811 | + memcpy(to, from, bytes_left); | |
5812 | + toi_writer_buffer_posn += bytes_left; | |
5813 | + return 0; | |
24613191 | 5814 | + } |
4e97e4e9 | 5815 | + |
5816 | + /* Complete this page and start a new one */ | |
5817 | + memcpy(to, from, capacity); | |
5818 | + bytes_left -= capacity; | |
5819 | + | |
5820 | + if (!writing) { | |
7f9d2ee0 | 5821 | + int result = toi_bio_get_next_page_read(no_readahead); |
5822 | + if (result) | |
5823 | + return result; | |
5824 | + } else { | |
5825 | + toi_bio_queue_write(&toi_writer_buffer); | |
5826 | + toi_bio_get_new_page(&toi_writer_buffer); | |
5827 | + } | |
4e97e4e9 | 5828 | + |
5829 | + toi_writer_buffer_posn = 0; | |
5830 | + toi_cond_pause(0, NULL); | |
24613191 | 5831 | + } |
4e97e4e9 | 5832 | + |
24613191 | 5833 | + return 0; |
5834 | +} | |
5835 | + | |
4e97e4e9 | 5836 | +/** |
5837 | + * toi_bio_read_page - read a page of the image. | |
24613191 | 5838 | + * |
4e97e4e9 | 5839 | + * @pfn: The pfn where the data belongs. |
5840 | + * @buffer_page: The page containing the (possibly compressed) data. | |
5841 | + * @buf_size: The number of bytes on @buffer_page used. | |
24613191 | 5842 | + * |
4e97e4e9 | 5843 | + * Read a (possibly compressed) page from the image, into buffer_page, |
5844 | + * returning its pfn and the buffer size. | |
24613191 | 5845 | + */ |
4e97e4e9 | 5846 | +static int toi_bio_read_page(unsigned long *pfn, struct page *buffer_page, |
5847 | + unsigned int *buf_size) | |
24613191 | 5848 | +{ |
4e97e4e9 | 5849 | + int result = 0; |
5850 | + char *buffer_virt = kmap(buffer_page); | |
24613191 | 5851 | + |
7f9d2ee0 | 5852 | + /* Only call start_new_readahead if we don't have a dedicated thread */ |
5853 | + if (current == toi_queue_flusher && toi_start_new_readahead(0)) { | |
f3e0dcc9 PS |
5854 | + printk(KERN_INFO "Queue flusher and toi_start_one_readahead " |
5855 | + "returned non-zero.\n"); | |
7f9d2ee0 | 5856 | + return -EIO; |
5857 | + } | |
5858 | + | |
5859 | + my_mutex_lock(0, &toi_bio_mutex); | |
24613191 | 5860 | + |
7f9d2ee0 | 5861 | + if (toi_rw_buffer(READ, (char *) pfn, sizeof(unsigned long), 0) || |
5862 | + toi_rw_buffer(READ, (char *) buf_size, sizeof(int), 0) || | |
5863 | + toi_rw_buffer(READ, buffer_virt, *buf_size, 0)) { | |
4e97e4e9 | 5864 | + abort_hibernate(TOI_FAILED_IO, "Read of data failed."); |
5865 | + result = 1; | |
1838f965 | 5866 | + } |
24613191 | 5867 | + |
7f9d2ee0 | 5868 | + my_mutex_unlock(0, &toi_bio_mutex); |
4e97e4e9 | 5869 | + kunmap(buffer_page); |
5870 | + return result; | |
24613191 | 5871 | +} |
5872 | + | |
4e97e4e9 | 5873 | +/** |
5874 | + * toi_bio_write_page - Write a page of the image. | |
24613191 | 5875 | + * |
4e97e4e9 | 5876 | + * @pfn: The pfn where the data belongs. |
5877 | + * @buffer_page: The page containing the (possibly compressed) data. | |
5878 | + * @buf_size: The number of bytes on @buffer_page used. | |
5879 | + * | |
5880 | + * Write a (possibly compressed) page to the image from the buffer, together | |
5881 | + * with it's index and buffer size. | |
24613191 | 5882 | + */ |
4e97e4e9 | 5883 | +static int toi_bio_write_page(unsigned long pfn, struct page *buffer_page, |
5884 | + unsigned int buf_size) | |
24613191 | 5885 | +{ |
ad8f4a28 | 5886 | + char *buffer_virt; |
7f9d2ee0 | 5887 | + int result = 0, result2 = 0; |
4e97e4e9 | 5888 | + |
ad8f4a28 AM |
5889 | + if (unlikely(test_action_state(TOI_TEST_FILTER_SPEED))) |
5890 | + return 0; | |
5891 | + | |
7f9d2ee0 | 5892 | + my_mutex_lock(1, &toi_bio_mutex); |
ad8f4a28 | 5893 | + buffer_virt = kmap(buffer_page); |
4e97e4e9 | 5894 | + |
7f9d2ee0 | 5895 | + if (toi_rw_buffer(WRITE, (char *) &pfn, sizeof(unsigned long), 0) || |
5896 | + toi_rw_buffer(WRITE, (char *) &buf_size, sizeof(int), 0) || | |
5897 | + toi_rw_buffer(WRITE, buffer_virt, buf_size, 0)) { | |
f3e0dcc9 PS |
5898 | + printk(KERN_INFO "toi_rw_buffer returned non-zero to " |
5899 | + "toi_bio_write_page.\n"); | |
4e97e4e9 | 5900 | + result = -EIO; |
7f9d2ee0 | 5901 | + } |
4e97e4e9 | 5902 | + |
4e97e4e9 | 5903 | + kunmap(buffer_page); |
7f9d2ee0 | 5904 | + my_mutex_unlock(1, &toi_bio_mutex); |
5905 | + | |
5906 | + if (current == toi_queue_flusher) | |
5907 | + result2 = toi_bio_queue_flush_pages(0); | |
5908 | + | |
5909 | + return result ? result : result2; | |
24613191 | 5910 | +} |
5911 | + | |
4e97e4e9 | 5912 | +/** |
5913 | + * toi_rw_header_chunk: Read or write a portion of the image header. | |
24613191 | 5914 | + * |
4e97e4e9 | 5915 | + * @writing: Whether reading or writing. |
5916 | + * @owner: The module for which we're writing. Used for confirming that modules | |
5917 | + * don't use more header space than they asked for. | |
5918 | + * @buffer: Address of the data to write. | |
5919 | + * @buffer_size: Size of the data buffer. | |
7f9d2ee0 | 5920 | + * @no_readahead: Don't try to start readhead (when still getting extents) |
24613191 | 5921 | + */ |
7f9d2ee0 | 5922 | +static int _toi_rw_header_chunk(int writing, struct toi_module_ops *owner, |
5923 | + char *buffer, int buffer_size, int no_readahead) | |
24613191 | 5924 | +{ |
7f9d2ee0 | 5925 | + int result = 0; |
24613191 | 5926 | + |
4e97e4e9 | 5927 | + if (owner) { |
5928 | + owner->header_used += buffer_size; | |
5929 | + toi_message(TOI_HEADER, TOI_LOW, 1, | |
5930 | + "Header: %s : %d bytes (%d/%d).\n", | |
5931 | + buffer_size, owner->header_used, | |
5932 | + owner->header_requested); | |
5933 | + if (owner->header_used > owner->header_requested) { | |
7f9d2ee0 | 5934 | + printk(KERN_EMERG "TuxOnIce module %s is using more " |
4e97e4e9 | 5935 | + "header space (%u) than it requested (%u).\n", |
5936 | + owner->name, | |
5937 | + owner->header_used, | |
5938 | + owner->header_requested); | |
5939 | + return buffer_size; | |
5940 | + } | |
5941 | + } else | |
5942 | + toi_message(TOI_HEADER, TOI_LOW, 1, | |
5943 | + "Header: (No owner): %d bytes.\n", buffer_size); | |
24613191 | 5944 | + |
7f9d2ee0 | 5945 | + if (!writing && !no_readahead) |
5946 | + result = toi_start_new_readahead(0); | |
5947 | + | |
5948 | + if (!result) | |
f3e0dcc9 PS |
5949 | + result = toi_rw_buffer(writing, buffer, buffer_size, |
5950 | + no_readahead); | |
7f9d2ee0 | 5951 | + |
4e97e4e9 | 5952 | + return result; |
24613191 | 5953 | +} |
5954 | + | |
7f9d2ee0 | 5955 | +static int toi_rw_header_chunk(int writing, struct toi_module_ops *owner, |
5956 | + char *buffer, int size) | |
5957 | +{ | |
5958 | + return _toi_rw_header_chunk(writing, owner, buffer, size, 0); | |
5959 | +} | |
5960 | + | |
5961 | +static int toi_rw_header_chunk_noreadahead(int writing, | |
5962 | + struct toi_module_ops *owner, char *buffer, int size) | |
5963 | +{ | |
5964 | + return _toi_rw_header_chunk(writing, owner, buffer, size, 1); | |
5965 | +} | |
5966 | + | |
4e97e4e9 | 5967 | +/** |
5968 | + * write_header_chunk_finish: Flush any buffered header data. | |
24613191 | 5969 | + */ |
4e97e4e9 | 5970 | +static int write_header_chunk_finish(void) |
24613191 | 5971 | +{ |
ad8f4a28 AM |
5972 | + int result = 0; |
5973 | + | |
7f9d2ee0 | 5974 | + if (toi_writer_buffer_posn) |
5975 | + toi_bio_queue_write(&toi_writer_buffer); | |
ad8f4a28 | 5976 | + |
7f9d2ee0 | 5977 | + toi_bio_queue_flush_pages(0); |
ad8f4a28 | 5978 | + toi_finish_all_io(); |
24613191 | 5979 | + |
ad8f4a28 | 5980 | + return result; |
4e97e4e9 | 5981 | +} |
24613191 | 5982 | + |
4e97e4e9 | 5983 | +/** |
5984 | + * toi_bio_storage_needed: Get the amount of storage needed for my fns. | |
5985 | + */ | |
5986 | +static int toi_bio_storage_needed(void) | |
5987 | +{ | |
5988 | + return 2 * sizeof(int); | |
24613191 | 5989 | +} |
5990 | + | |
4e97e4e9 | 5991 | +/** |
5992 | + * toi_bio_save_config_info: Save block i/o config to image header. | |
24613191 | 5993 | + * |
4e97e4e9 | 5994 | + * @buf: PAGE_SIZE'd buffer into which data should be saved. |
5995 | + */ | |
5996 | +static int toi_bio_save_config_info(char *buf) | |
5997 | +{ | |
5998 | + int *ints = (int *) buf; | |
ad8f4a28 | 5999 | + ints[0] = target_outstanding_io; |
7f9d2ee0 | 6000 | + return sizeof(int); |
4e97e4e9 | 6001 | +} |
6002 | + | |
6003 | +/** | |
6004 | + * toi_bio_load_config_info: Restore block i/o config. | |
24613191 | 6005 | + * |
4e97e4e9 | 6006 | + * @buf: Data to be reloaded. |
6007 | + * @size: Size of the buffer saved. | |
6008 | + */ | |
6009 | +static void toi_bio_load_config_info(char *buf, int size) | |
6010 | +{ | |
6011 | + int *ints = (int *) buf; | |
ad8f4a28 | 6012 | + target_outstanding_io = ints[0]; |
4e97e4e9 | 6013 | +} |
6014 | + | |
6015 | +/** | |
6016 | + * toi_bio_initialise: Initialise bio code at start of some action. | |
24613191 | 6017 | + * |
4e97e4e9 | 6018 | + * @starting_cycle: Whether starting a hibernation cycle, or just reading or |
6019 | + * writing a sysfs value. | |
24613191 | 6020 | + */ |
4e97e4e9 | 6021 | +static int toi_bio_initialise(int starting_cycle) |
6022 | +{ | |
7f9d2ee0 | 6023 | + if (starting_cycle) { |
6024 | + max_outstanding_writes = 0; | |
6025 | + max_outstanding_reads = 0; | |
6026 | + toi_queue_flusher = current; | |
6027 | +#ifdef MEASURE_MUTEX_CONTENTION | |
6028 | + { | |
6029 | + int i, j, k; | |
24613191 | 6030 | + |
7f9d2ee0 | 6031 | + for (i = 0; i < 2; i++) |
6032 | + for (j = 0; j < 2; j++) | |
f3e0dcc9 | 6033 | + for_each_online_cpu(k) |
7f9d2ee0 | 6034 | + mutex_times[i][j][k] = 0; |
6035 | + } | |
6036 | +#endif | |
6037 | + } | |
ad8f4a28 | 6038 | + |
7f9d2ee0 | 6039 | + return 0; |
4e97e4e9 | 6040 | +} |
24613191 | 6041 | + |
4e97e4e9 | 6042 | +/** |
6043 | + * toi_bio_cleanup: Cleanup after some action. | |
6044 | + * | |
6045 | + * @finishing_cycle: Whether completing a cycle. | |
6046 | + */ | |
6047 | +static void toi_bio_cleanup(int finishing_cycle) | |
6048 | +{ | |
6049 | + if (toi_writer_buffer) { | |
7f9d2ee0 | 6050 | + toi_free_page(11, (unsigned long) toi_writer_buffer); |
4e97e4e9 | 6051 | + toi_writer_buffer = NULL; |
6052 | + } | |
4e97e4e9 | 6053 | +} |
24613191 | 6054 | + |
4e97e4e9 | 6055 | +struct toi_bio_ops toi_bio_ops = { |
6056 | + .bdev_page_io = toi_bdev_page_io, | |
6057 | + .finish_all_io = toi_finish_all_io, | |
1838f965 | 6058 | + .monitor_outstanding_io = toi_monitor_outstanding_io, |
6059 | + .update_throughput_throttle = update_throughput_throttle, | |
4e97e4e9 | 6060 | + .forward_one_page = go_next_page, |
6061 | + .set_extra_page_forward = set_extra_page_forward, | |
6062 | + .set_devinfo = toi_set_devinfo, | |
6063 | + .read_page = toi_bio_read_page, | |
6064 | + .write_page = toi_bio_write_page, | |
6065 | + .rw_init = toi_rw_init, | |
6066 | + .rw_cleanup = toi_rw_cleanup, | |
6067 | + .read_header_init = toi_read_header_init, | |
6068 | + .rw_header_chunk = toi_rw_header_chunk, | |
7f9d2ee0 | 6069 | + .rw_header_chunk_noreadahead = toi_rw_header_chunk_noreadahead, |
4e97e4e9 | 6070 | + .write_header_chunk_finish = write_header_chunk_finish, |
7f9d2ee0 | 6071 | + .io_flusher = bio_io_flusher, |
24613191 | 6072 | +}; |
1838f965 | 6073 | +EXPORT_SYMBOL_GPL(toi_bio_ops); |
24613191 | 6074 | + |
4e97e4e9 | 6075 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 6076 | + SYSFS_INT("target_outstanding_io", SYSFS_RW, &target_outstanding_io, |
6077 | + 0, 16384, 0, NULL), | |
24613191 | 6078 | +}; |
6079 | + | |
ad8f4a28 | 6080 | +static struct toi_module_ops toi_blockwriter_ops = { |
4e97e4e9 | 6081 | + .name = "lowlevel i/o", |
6082 | + .type = MISC_HIDDEN_MODULE, | |
6083 | + .directory = "block_io", | |
6084 | + .module = THIS_MODULE, | |
ad8f4a28 | 6085 | + .print_debug_info = toi_bio_print_debug_stats, |
4e97e4e9 | 6086 | + .memory_needed = toi_bio_memory_needed, |
6087 | + .storage_needed = toi_bio_storage_needed, | |
6088 | + .save_config_info = toi_bio_save_config_info, | |
6089 | + .load_config_info = toi_bio_load_config_info, | |
6090 | + .initialise = toi_bio_initialise, | |
6091 | + .cleanup = toi_bio_cleanup, | |
24613191 | 6092 | + |
4e97e4e9 | 6093 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
6094 | + .num_sysfs_entries = sizeof(sysfs_params) / |
6095 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 6096 | +}; |
24613191 | 6097 | + |
4e97e4e9 | 6098 | +/** |
6099 | + * toi_block_io_load: Load time routine for block i/o module. | |
6100 | + * | |
6101 | + * Register block i/o ops and sysfs entries. | |
6102 | + */ | |
6103 | +static __init int toi_block_io_load(void) | |
6104 | +{ | |
6105 | + return toi_register_module(&toi_blockwriter_ops); | |
6106 | +} | |
24613191 | 6107 | + |
4e97e4e9 | 6108 | +#ifdef MODULE |
6109 | +static __exit void toi_block_io_unload(void) | |
6110 | +{ | |
6111 | + toi_unregister_module(&toi_blockwriter_ops); | |
6112 | +} | |
24613191 | 6113 | + |
4e97e4e9 | 6114 | +module_init(toi_block_io_load); |
6115 | +module_exit(toi_block_io_unload); | |
6116 | +MODULE_LICENSE("GPL"); | |
6117 | +MODULE_AUTHOR("Nigel Cunningham"); | |
6118 | +MODULE_DESCRIPTION("TuxOnIce block io functions"); | |
6119 | +#else | |
6120 | +late_initcall(toi_block_io_load); | |
24613191 | 6121 | +#endif |
4e97e4e9 | 6122 | diff --git a/kernel/power/tuxonice_block_io.h b/kernel/power/tuxonice_block_io.h |
6123 | new file mode 100644 | |
1838f965 | 6124 | index 0000000..364e6e2 |
4e97e4e9 | 6125 | --- /dev/null |
6126 | +++ b/kernel/power/tuxonice_block_io.h | |
1838f965 | 6127 | @@ -0,0 +1,59 @@ |
24613191 | 6128 | +/* |
4e97e4e9 | 6129 | + * kernel/power/tuxonice_block_io.h |
24613191 | 6130 | + * |
1838f965 | 6131 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 6132 | + * Copyright (C) 2006 Red Hat, inc. |
24613191 | 6133 | + * |
4e97e4e9 | 6134 | + * Distributed under GPLv2. |
24613191 | 6135 | + * |
4e97e4e9 | 6136 | + * This file contains declarations for functions exported from |
6137 | + * tuxonice_block_io.c, which contains low level io functions. | |
24613191 | 6138 | + */ |
6139 | + | |
4e97e4e9 | 6140 | +#include <linux/buffer_head.h> |
6141 | +#include "tuxonice_extent.h" | |
24613191 | 6142 | + |
4e97e4e9 | 6143 | +struct toi_bdev_info { |
6144 | + struct block_device *bdev; | |
6145 | + dev_t dev_t; | |
6146 | + int bmap_shift; | |
6147 | + int blocks_per_page; | |
6148 | +}; | |
24613191 | 6149 | + |
ad8f4a28 | 6150 | +/* |
4e97e4e9 | 6151 | + * Our exported interface so the swapwriter and filewriter don't |
6152 | + * need these functions duplicated. | |
24613191 | 6153 | + */ |
4e97e4e9 | 6154 | +struct toi_bio_ops { |
7f9d2ee0 | 6155 | + int (*bdev_page_io) (int rw, struct block_device *bdev, long pos, |
4e97e4e9 | 6156 | + struct page *page); |
6157 | + void (*check_io_stats) (void); | |
6158 | + void (*reset_io_stats) (void); | |
1838f965 | 6159 | + void (*monitor_outstanding_io) (void); |
6160 | + void (*update_throughput_throttle) (int jif_index); | |
4e97e4e9 | 6161 | + void (*finish_all_io) (void); |
ad8f4a28 | 6162 | + int (*forward_one_page) (int writing); |
4e97e4e9 | 6163 | + void (*set_extra_page_forward) (void); |
6164 | + void (*set_devinfo) (struct toi_bdev_info *info); | |
6165 | + int (*read_page) (unsigned long *index, struct page *buffer_page, | |
6166 | + unsigned int *buf_size); | |
6167 | + int (*write_page) (unsigned long index, struct page *buffer_page, | |
6168 | + unsigned int buf_size); | |
6169 | + void (*read_header_init) (void); | |
6170 | + int (*rw_header_chunk) (int rw, struct toi_module_ops *owner, | |
6171 | + char *buffer, int buffer_size); | |
7f9d2ee0 | 6172 | + int (*rw_header_chunk_noreadahead) (int rw, |
6173 | + struct toi_module_ops *owner, | |
6174 | + char *buffer, int buffer_size); | |
4e97e4e9 | 6175 | + int (*write_header_chunk_finish) (void); |
6176 | + int (*rw_init) (int rw, int stream_number); | |
6177 | + int (*rw_cleanup) (int rw); | |
7f9d2ee0 | 6178 | + void (*io_flusher) (int rw); |
4e97e4e9 | 6179 | +}; |
24613191 | 6180 | + |
4e97e4e9 | 6181 | +extern struct toi_bio_ops toi_bio_ops; |
6182 | + | |
6183 | +extern char *toi_writer_buffer; | |
6184 | +extern int toi_writer_buffer_posn; | |
f3e0dcc9 | 6185 | +extern struct hibernate_extent_iterate_saved_state toi_writer_posn_save[4]; |
1838f965 | 6186 | +extern struct toi_extent_iterate_state toi_writer_posn; |
4e97e4e9 | 6187 | diff --git a/kernel/power/tuxonice_builtin.c b/kernel/power/tuxonice_builtin.c |
6188 | new file mode 100644 | |
1838f965 | 6189 | index 0000000..512a6e7 |
4e97e4e9 | 6190 | --- /dev/null |
6191 | +++ b/kernel/power/tuxonice_builtin.c | |
1838f965 | 6192 | @@ -0,0 +1,321 @@ |
4e97e4e9 | 6193 | +/* |
1838f965 | 6194 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 6195 | + * |
6196 | + * This file is released under the GPLv2. | |
6197 | + */ | |
6198 | +#include <linux/module.h> | |
6199 | +#include <linux/resume-trace.h> | |
4e97e4e9 | 6200 | +#include <linux/kernel.h> |
6201 | +#include <linux/swap.h> | |
6202 | +#include <linux/syscalls.h> | |
6203 | +#include <linux/bio.h> | |
6204 | +#include <linux/root_dev.h> | |
6205 | +#include <linux/freezer.h> | |
6206 | +#include <linux/reboot.h> | |
6207 | +#include <linux/writeback.h> | |
6208 | +#include <linux/tty.h> | |
6209 | +#include <linux/crypto.h> | |
6210 | +#include <linux/cpu.h> | |
ad8f4a28 | 6211 | +#include <linux/ctype.h> |
4e97e4e9 | 6212 | +#include "tuxonice_io.h" |
6213 | +#include "tuxonice.h" | |
6214 | +#include "tuxonice_extent.h" | |
6215 | +#include "tuxonice_block_io.h" | |
6216 | +#include "tuxonice_netlink.h" | |
6217 | +#include "tuxonice_prepare_image.h" | |
6218 | +#include "tuxonice_ui.h" | |
6219 | +#include "tuxonice_sysfs.h" | |
6220 | +#include "tuxonice_pagedir.h" | |
6221 | +#include "tuxonice_modules.h" | |
6222 | +#include "tuxonice_builtin.h" | |
ad8f4a28 | 6223 | +#include "tuxonice_power_off.h" |
24613191 | 6224 | + |
4e97e4e9 | 6225 | +/* |
6226 | + * Highmem related functions (x86 only). | |
6227 | + */ | |
24613191 | 6228 | + |
4e97e4e9 | 6229 | +#ifdef CONFIG_HIGHMEM |
24613191 | 6230 | + |
4e97e4e9 | 6231 | +/** |
6232 | + * copyback_high: Restore highmem pages. | |
6233 | + * | |
6234 | + * Highmem data and pbe lists are/can be stored in highmem. | |
6235 | + * The format is slightly different to the lowmem pbe lists | |
6236 | + * used for the assembly code: the last pbe in each page is | |
6237 | + * a struct page * instead of struct pbe *, pointing to the | |
6238 | + * next page where pbes are stored (or NULL if happens to be | |
6239 | + * the end of the list). Since we don't want to generate | |
6240 | + * unnecessary deltas against swsusp code, we use a cast | |
6241 | + * instead of a union. | |
6242 | + **/ | |
24613191 | 6243 | + |
4e97e4e9 | 6244 | +static void copyback_high(void) |
6245 | +{ | |
ad8f4a28 | 6246 | + struct page *pbe_page = (struct page *) restore_highmem_pblist; |
4e97e4e9 | 6247 | + struct pbe *this_pbe, *first_pbe; |
6248 | + unsigned long *origpage, *copypage; | |
6249 | + int pbe_index = 1; | |
24613191 | 6250 | + |
4e97e4e9 | 6251 | + if (!pbe_page) |
6252 | + return; | |
24613191 | 6253 | + |
4e97e4e9 | 6254 | + this_pbe = (struct pbe *) kmap_atomic(pbe_page, KM_BOUNCE_READ); |
6255 | + first_pbe = this_pbe; | |
6256 | + | |
6257 | + while (this_pbe) { | |
6258 | + int loop = (PAGE_SIZE / sizeof(unsigned long)) - 1; | |
6259 | + | |
6260 | + origpage = kmap_atomic((struct page *) this_pbe->orig_address, | |
6261 | + KM_BIO_DST_IRQ); | |
6262 | + copypage = kmap_atomic((struct page *) this_pbe->address, | |
6263 | + KM_BIO_SRC_IRQ); | |
6264 | + | |
6265 | + while (loop >= 0) { | |
6266 | + *(origpage + loop) = *(copypage + loop); | |
6267 | + loop--; | |
24613191 | 6268 | + } |
24613191 | 6269 | + |
4e97e4e9 | 6270 | + kunmap_atomic(origpage, KM_BIO_DST_IRQ); |
6271 | + kunmap_atomic(copypage, KM_BIO_SRC_IRQ); | |
24613191 | 6272 | + |
4e97e4e9 | 6273 | + if (!this_pbe->next) |
6274 | + break; | |
24613191 | 6275 | + |
4e97e4e9 | 6276 | + if (pbe_index < PBES_PER_PAGE) { |
6277 | + this_pbe++; | |
6278 | + pbe_index++; | |
6279 | + } else { | |
6280 | + pbe_page = (struct page *) this_pbe->next; | |
6281 | + kunmap_atomic(first_pbe, KM_BOUNCE_READ); | |
6282 | + if (!pbe_page) | |
6283 | + return; | |
6284 | + this_pbe = (struct pbe *) kmap_atomic(pbe_page, | |
6285 | + KM_BOUNCE_READ); | |
6286 | + first_pbe = this_pbe; | |
6287 | + pbe_index = 1; | |
6288 | + } | |
24613191 | 6289 | + } |
4e97e4e9 | 6290 | + kunmap_atomic(first_pbe, KM_BOUNCE_READ); |
24613191 | 6291 | +} |
6292 | + | |
4e97e4e9 | 6293 | +#else /* CONFIG_HIGHMEM */ |
1838f965 | 6294 | +static void copyback_high(void) { } |
4e97e4e9 | 6295 | +#endif |
24613191 | 6296 | + |
ad8f4a28 AM |
6297 | +char toi_wait_for_keypress_dev_console(int timeout) |
6298 | +{ | |
6299 | + int fd, this_timeout = 255; | |
6300 | + char key = '\0'; | |
6301 | + struct termios t, t_backup; | |
6302 | + | |
6303 | + /* We should be guaranteed /dev/console exists after populate_rootfs() | |
6304 | + * in init/main.c. | |
6305 | + */ | |
6306 | + fd = sys_open("/dev/console", O_RDONLY, 0); | |
6307 | + if (fd < 0) { | |
6308 | + printk(KERN_INFO "Couldn't open /dev/console.\n"); | |
6309 | + return key; | |
6310 | + } | |
6311 | + | |
6312 | + if (sys_ioctl(fd, TCGETS, (long)&t) < 0) | |
6313 | + goto out_close; | |
6314 | + | |
6315 | + memcpy(&t_backup, &t, sizeof(t)); | |
6316 | + | |
6317 | + t.c_lflag &= ~(ISIG|ICANON|ECHO); | |
6318 | + t.c_cc[VMIN] = 0; | |
6319 | + | |
6320 | +new_timeout: | |
6321 | + if (timeout > 0) { | |
6322 | + this_timeout = timeout < 26 ? timeout : 25; | |
6323 | + timeout -= this_timeout; | |
6324 | + this_timeout *= 10; | |
6325 | + } | |
6326 | + | |
6327 | + t.c_cc[VTIME] = this_timeout; | |
6328 | + | |
6329 | + if (sys_ioctl(fd, TCSETS, (long)&t) < 0) | |
6330 | + goto out_restore; | |
6331 | + | |
6332 | + while (1) { | |
6333 | + if (sys_read(fd, &key, 1) <= 0) { | |
6334 | + if (timeout) | |
6335 | + goto new_timeout; | |
6336 | + key = '\0'; | |
6337 | + break; | |
6338 | + } | |
6339 | + key = tolower(key); | |
6340 | + if (test_toi_state(TOI_SANITY_CHECK_PROMPT)) { | |
6341 | + if (key == 'c') { | |
6342 | + set_toi_state(TOI_CONTINUE_REQ); | |
6343 | + break; | |
6344 | + } else if (key == ' ') | |
6345 | + break; | |
6346 | + } else | |
6347 | + break; | |
6348 | + } | |
6349 | + | |
6350 | +out_restore: | |
6351 | + sys_ioctl(fd, TCSETS, (long)&t_backup); | |
6352 | +out_close: | |
6353 | + sys_close(fd); | |
6354 | + | |
6355 | + return key; | |
6356 | +} | |
1838f965 | 6357 | +EXPORT_SYMBOL_GPL(toi_wait_for_keypress_dev_console); |
ad8f4a28 | 6358 | + |
7f9d2ee0 | 6359 | +struct toi_boot_kernel_data toi_bkd __nosavedata |
ad8f4a28 | 6360 | + __attribute__((aligned(PAGE_SIZE))) = { |
7f9d2ee0 | 6361 | + MY_BOOT_KERNEL_DATA_VERSION, |
6362 | + 0, | |
ad8f4a28 | 6363 | +#ifdef CONFIG_TOI_REPLACE_SWSUSP |
7f9d2ee0 | 6364 | + (1 << TOI_REPLACE_SWSUSP) | |
ad8f4a28 | 6365 | +#endif |
f3e0dcc9 | 6366 | + (1 << TOI_NO_FLUSHER_THREAD) | |
7f9d2ee0 | 6367 | + (1 << TOI_PAGESET2_FULL) | (1 << TOI_LATE_CPU_HOTPLUG), |
ad8f4a28 AM |
6368 | +}; |
6369 | +EXPORT_SYMBOL_GPL(toi_bkd); | |
6370 | + | |
6371 | +struct block_device *toi_open_by_devnum(dev_t dev, unsigned mode) | |
6372 | +{ | |
6373 | + struct block_device *bdev = bdget(dev); | |
6374 | + int err = -ENOMEM; | |
6375 | + int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY; | |
6376 | + flags |= O_NONBLOCK; | |
6377 | + if (bdev) | |
6378 | + err = blkdev_get(bdev, mode, flags); | |
6379 | + return err ? ERR_PTR(err) : bdev; | |
6380 | +} | |
6381 | +EXPORT_SYMBOL_GPL(toi_open_by_devnum); | |
6382 | + | |
1838f965 | 6383 | +int toi_wait = CONFIG_TOI_DEFAULT_WAIT; |
6384 | +EXPORT_SYMBOL_GPL(toi_wait); | |
ad8f4a28 | 6385 | + |
1838f965 | 6386 | +struct toi_core_fns *toi_core_fns; |
6387 | +EXPORT_SYMBOL_GPL(toi_core_fns); | |
24613191 | 6388 | + |
1838f965 | 6389 | +struct memory_bitmap pageset1_map; |
6390 | +EXPORT_SYMBOL_GPL(pageset1_map); | |
4e97e4e9 | 6391 | + |
1838f965 | 6392 | +struct memory_bitmap pageset1_copy_map; |
4e97e4e9 | 6393 | +EXPORT_SYMBOL_GPL(pageset1_copy_map); |
6394 | + | |
ad8f4a28 | 6395 | +unsigned long toi_result; |
4e97e4e9 | 6396 | +EXPORT_SYMBOL_GPL(toi_result); |
1838f965 | 6397 | + |
6398 | +struct pagedir pagedir1 = {1}; | |
4e97e4e9 | 6399 | +EXPORT_SYMBOL_GPL(pagedir1); |
6400 | + | |
6401 | +unsigned long toi_get_nonconflicting_page(void) | |
6402 | +{ | |
6403 | + return toi_core_fns->get_nonconflicting_page(); | |
24613191 | 6404 | +} |
6405 | + | |
4e97e4e9 | 6406 | +int toi_post_context_save(void) |
6407 | +{ | |
6408 | + return toi_core_fns->post_context_save(); | |
6409 | +} | |
24613191 | 6410 | + |
1838f965 | 6411 | +int toi_try_hibernate(void) |
24613191 | 6412 | +{ |
4e97e4e9 | 6413 | + if (!toi_core_fns) |
6414 | + return -ENODEV; | |
24613191 | 6415 | + |
1838f965 | 6416 | + return toi_core_fns->try_hibernate(); |
24613191 | 6417 | +} |
6418 | + | |
1838f965 | 6419 | +static int num_resume_calls; |
6420 | +#ifdef CONFIG_TOI_IGNORE_LATE_INITCALL | |
6421 | +static int ignore_late_initcall = 1; | |
6422 | +#else | |
6423 | +static int ignore_late_initcall; | |
6424 | +#endif | |
6425 | + | |
4e97e4e9 | 6426 | +void toi_try_resume(void) |
6427 | +{ | |
1838f965 | 6428 | + /* Don't let it wrap around eventually */ |
6429 | + if (num_resume_calls < 2) | |
6430 | + num_resume_calls++; | |
6431 | + | |
6432 | + if (num_resume_calls == 1 && ignore_late_initcall) { | |
6433 | + printk(KERN_INFO "TuxOnIce: Ignoring late initcall, as requested.\n"); | |
6434 | + return; | |
6435 | + } | |
6436 | + | |
4e97e4e9 | 6437 | + if (toi_core_fns) |
6438 | + toi_core_fns->try_resume(); | |
ad8f4a28 AM |
6439 | + else |
6440 | + printk(KERN_INFO "TuxOnIce core not loaded yet.\n"); | |
4e97e4e9 | 6441 | +} |
24613191 | 6442 | + |
4e97e4e9 | 6443 | +int toi_lowlevel_builtin(void) |
24613191 | 6444 | +{ |
4e97e4e9 | 6445 | + int error = 0; |
24613191 | 6446 | + |
4e97e4e9 | 6447 | + save_processor_state(); |
ad8f4a28 AM |
6448 | + error = swsusp_arch_suspend(); |
6449 | + if (error) | |
4e97e4e9 | 6450 | + printk(KERN_ERR "Error %d hibernating\n", error); |
6451 | + | |
6452 | + /* Restore control flow appears here */ | |
6453 | + if (!toi_in_hibernate) { | |
6454 | + copyback_high(); | |
6455 | + set_toi_state(TOI_NOW_RESUMING); | |
6456 | + } | |
6457 | + | |
6458 | + restore_processor_state(); | |
6459 | + | |
6460 | + return error; | |
24613191 | 6461 | +} |
4e97e4e9 | 6462 | +EXPORT_SYMBOL_GPL(toi_lowlevel_builtin); |
24613191 | 6463 | + |
4e97e4e9 | 6464 | +unsigned long toi_compress_bytes_in, toi_compress_bytes_out; |
6465 | +EXPORT_SYMBOL_GPL(toi_compress_bytes_in); | |
6466 | +EXPORT_SYMBOL_GPL(toi_compress_bytes_out); | |
24613191 | 6467 | + |
4e97e4e9 | 6468 | +unsigned long toi_state = ((1 << TOI_BOOT_TIME) | |
6469 | + (1 << TOI_IGNORE_LOGLEVEL) | | |
6470 | + (1 << TOI_IO_STOPPED)); | |
6471 | +EXPORT_SYMBOL_GPL(toi_state); | |
24613191 | 6472 | + |
4e97e4e9 | 6473 | +/* The number of hibernates we have started (some may have been cancelled) */ |
6474 | +unsigned int nr_hibernates; | |
6475 | +EXPORT_SYMBOL_GPL(nr_hibernates); | |
24613191 | 6476 | + |
ad8f4a28 | 6477 | +int toi_running; |
4e97e4e9 | 6478 | +EXPORT_SYMBOL_GPL(toi_running); |
24613191 | 6479 | + |
4e97e4e9 | 6480 | +int toi_in_hibernate __nosavedata; |
6481 | +EXPORT_SYMBOL_GPL(toi_in_hibernate); | |
24613191 | 6482 | + |
4e97e4e9 | 6483 | +__nosavedata struct pbe *restore_highmem_pblist; |
4e97e4e9 | 6484 | +EXPORT_SYMBOL_GPL(restore_highmem_pblist); |
4e97e4e9 | 6485 | + |
6486 | +static int __init toi_wait_setup(char *str) | |
24613191 | 6487 | +{ |
4e97e4e9 | 6488 | + int value; |
24613191 | 6489 | + |
4e97e4e9 | 6490 | + if (sscanf(str, "=%d", &value)) { |
6491 | + if (value < -1 || value > 255) | |
ad8f4a28 AM |
6492 | + printk(KERN_INFO "TuxOnIce_wait outside range -1 to " |
6493 | + "255.\n"); | |
24613191 | 6494 | + else |
4e97e4e9 | 6495 | + toi_wait = value; |
24613191 | 6496 | + } |
6497 | + | |
4e97e4e9 | 6498 | + return 1; |
6499 | +} | |
24613191 | 6500 | + |
4e97e4e9 | 6501 | +__setup("toi_wait", toi_wait_setup); |
1838f965 | 6502 | + |
6503 | +static int __init toi_ignore_late_initcall_setup(char *str) | |
6504 | +{ | |
6505 | + int value; | |
6506 | + | |
6507 | + if (sscanf(str, "=%d", &value)) | |
6508 | + ignore_late_initcall = value; | |
6509 | + | |
6510 | + return 1; | |
6511 | +} | |
6512 | + | |
6513 | +__setup("toi_initramfs_resume_only", toi_ignore_late_initcall_setup); | |
4e97e4e9 | 6514 | diff --git a/kernel/power/tuxonice_builtin.h b/kernel/power/tuxonice_builtin.h |
6515 | new file mode 100644 | |
1838f965 | 6516 | index 0000000..20a35c6 |
4e97e4e9 | 6517 | --- /dev/null |
6518 | +++ b/kernel/power/tuxonice_builtin.h | |
1838f965 | 6519 | @@ -0,0 +1,27 @@ |
4e97e4e9 | 6520 | +/* |
1838f965 | 6521 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 6522 | + * |
6523 | + * This file is released under the GPLv2. | |
6524 | + */ | |
4e97e4e9 | 6525 | +#include <asm/setup.h> |
24613191 | 6526 | + |
4e97e4e9 | 6527 | +extern struct toi_core_fns *toi_core_fns; |
6528 | +extern unsigned long toi_compress_bytes_in, toi_compress_bytes_out; | |
4e97e4e9 | 6529 | +extern unsigned int nr_hibernates; |
6530 | +extern int toi_in_hibernate; | |
6531 | + | |
4e97e4e9 | 6532 | +extern __nosavedata struct pbe *restore_highmem_pblist; |
24613191 | 6533 | + |
4e97e4e9 | 6534 | +int toi_lowlevel_builtin(void); |
24613191 | 6535 | + |
4e97e4e9 | 6536 | +#ifdef CONFIG_HIGHMEM |
6537 | +extern __nosavedata struct zone_data *toi_nosave_zone_list; | |
6538 | +extern __nosavedata unsigned long toi_nosave_max_pfn; | |
6539 | +#endif | |
24613191 | 6540 | + |
4e97e4e9 | 6541 | +extern unsigned long toi_get_nonconflicting_page(void); |
6542 | +extern int toi_post_context_save(void); | |
1838f965 | 6543 | + |
ad8f4a28 AM |
6544 | +extern char toi_wait_for_keypress_dev_console(int timeout); |
6545 | +extern struct block_device *toi_open_by_devnum(dev_t dev, unsigned mode); | |
7f9d2ee0 | 6546 | +extern int toi_wait; |
4e97e4e9 | 6547 | diff --git a/kernel/power/tuxonice_checksum.c b/kernel/power/tuxonice_checksum.c |
6548 | new file mode 100644 | |
1838f965 | 6549 | index 0000000..1e5d62e |
4e97e4e9 | 6550 | --- /dev/null |
6551 | +++ b/kernel/power/tuxonice_checksum.c | |
1838f965 | 6552 | @@ -0,0 +1,373 @@ |
24613191 | 6553 | +/* |
4e97e4e9 | 6554 | + * kernel/power/tuxonice_checksum.c |
24613191 | 6555 | + * |
1838f965 | 6556 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 6557 | + * Copyright (C) 2006 Red Hat, inc. |
6558 | + * | |
6559 | + * This file is released under the GPLv2. | |
6560 | + * | |
6561 | + * This file contains data checksum routines for TuxOnIce, | |
6562 | + * using cryptoapi. They are used to locate any modifications | |
6563 | + * made to pageset 2 while we're saving it. | |
24613191 | 6564 | + */ |
24613191 | 6565 | + |
4e97e4e9 | 6566 | +#include <linux/suspend.h> |
4e97e4e9 | 6567 | +#include <linux/highmem.h> |
6568 | +#include <linux/vmalloc.h> | |
6569 | +#include <linux/crypto.h> | |
6570 | +#include <linux/scatterlist.h> | |
24613191 | 6571 | + |
4e97e4e9 | 6572 | +#include "tuxonice.h" |
6573 | +#include "tuxonice_modules.h" | |
6574 | +#include "tuxonice_sysfs.h" | |
6575 | +#include "tuxonice_io.h" | |
6576 | +#include "tuxonice_pageflags.h" | |
6577 | +#include "tuxonice_checksum.h" | |
6578 | +#include "tuxonice_pagedir.h" | |
ad8f4a28 | 6579 | +#include "tuxonice_alloc.h" |
24613191 | 6580 | + |
4e97e4e9 | 6581 | +static struct toi_module_ops toi_checksum_ops; |
24613191 | 6582 | + |
4e97e4e9 | 6583 | +/* Constant at the mo, but I might allow tuning later */ |
6584 | +static char toi_checksum_name[32] = "md4"; | |
6585 | +/* Bytes per checksum */ | |
6586 | +#define CHECKSUM_SIZE (16) | |
24613191 | 6587 | + |
4e97e4e9 | 6588 | +#define CHECKSUMS_PER_PAGE ((PAGE_SIZE - sizeof(void *)) / CHECKSUM_SIZE) |
24613191 | 6589 | + |
4e97e4e9 | 6590 | +struct cpu_context { |
6591 | + struct crypto_hash *transform; | |
6592 | + struct hash_desc desc; | |
6593 | + struct scatterlist sg[2]; | |
6594 | + char *buf; | |
6595 | +}; | |
24613191 | 6596 | + |
4e97e4e9 | 6597 | +static DEFINE_PER_CPU(struct cpu_context, contexts); |
6598 | +static int pages_allocated; | |
6599 | +static unsigned long page_list; | |
24613191 | 6600 | + |
ad8f4a28 AM |
6601 | +static int toi_num_resaved; |
6602 | + | |
6603 | +static unsigned long this_checksum, next_page; | |
6604 | +static int checksum_index; | |
24613191 | 6605 | + |
ad8f4a28 AM |
6606 | +static inline int checksum_pages_needed(void) |
6607 | +{ | |
6608 | + return DIV_ROUND_UP(pagedir2.size, CHECKSUMS_PER_PAGE); | |
6609 | +} | |
24613191 | 6610 | + |
4e97e4e9 | 6611 | +/* ---- Local buffer management ---- */ |
24613191 | 6612 | + |
ad8f4a28 | 6613 | +/* |
4e97e4e9 | 6614 | + * toi_checksum_cleanup |
6615 | + * | |
6616 | + * Frees memory allocated for our labours. | |
6617 | + */ | |
6618 | +static void toi_checksum_cleanup(int ending_cycle) | |
6619 | +{ | |
6620 | + int cpu; | |
24613191 | 6621 | + |
4e97e4e9 | 6622 | + if (ending_cycle) { |
6623 | + for_each_online_cpu(cpu) { | |
6624 | + struct cpu_context *this = &per_cpu(contexts, cpu); | |
6625 | + if (this->transform) { | |
6626 | + crypto_free_hash(this->transform); | |
6627 | + this->transform = NULL; | |
6628 | + this->desc.tfm = NULL; | |
24613191 | 6629 | + } |
6630 | + | |
4e97e4e9 | 6631 | + if (this->buf) { |
ad8f4a28 | 6632 | + toi_free_page(27, (unsigned long) this->buf); |
4e97e4e9 | 6633 | + this->buf = NULL; |
24613191 | 6634 | + } |
6635 | + } | |
4e97e4e9 | 6636 | + } |
6637 | +} | |
24613191 | 6638 | + |
ad8f4a28 AM |
6639 | +/* |
6640 | + * toi_crypto_initialise | |
4e97e4e9 | 6641 | + * |
6642 | + * Prepare to do some work by allocating buffers and transforms. | |
6643 | + * Returns: Int: Zero. Even if we can't set up checksum, we still | |
6644 | + * seek to hibernate. | |
6645 | + */ | |
ad8f4a28 | 6646 | +static int toi_checksum_initialise(int starting_cycle) |
4e97e4e9 | 6647 | +{ |
6648 | + int cpu; | |
24613191 | 6649 | + |
4e97e4e9 | 6650 | + if (!(starting_cycle & SYSFS_HIBERNATE) || !toi_checksum_ops.enabled) |
6651 | + return 0; | |
24613191 | 6652 | + |
4e97e4e9 | 6653 | + if (!*toi_checksum_name) { |
ad8f4a28 | 6654 | + printk(KERN_INFO "TuxOnIce: No checksum algorithm name set.\n"); |
4e97e4e9 | 6655 | + return 1; |
6656 | + } | |
24613191 | 6657 | + |
4e97e4e9 | 6658 | + for_each_online_cpu(cpu) { |
6659 | + struct cpu_context *this = &per_cpu(contexts, cpu); | |
6660 | + struct page *page; | |
24613191 | 6661 | + |
4e97e4e9 | 6662 | + this->transform = crypto_alloc_hash(toi_checksum_name, 0, 0); |
6663 | + if (IS_ERR(this->transform)) { | |
ad8f4a28 AM |
6664 | + printk(KERN_INFO "TuxOnIce: Failed to initialise the " |
6665 | + "%s checksum algorithm: %ld.\n", | |
4e97e4e9 | 6666 | + toi_checksum_name, (long) this->transform); |
6667 | + this->transform = NULL; | |
6668 | + return 1; | |
24613191 | 6669 | + } |
24613191 | 6670 | + |
4e97e4e9 | 6671 | + this->desc.tfm = this->transform; |
6672 | + this->desc.flags = 0; | |
24613191 | 6673 | + |
ad8f4a28 | 6674 | + page = toi_alloc_page(27, GFP_KERNEL); |
4e97e4e9 | 6675 | + if (!page) |
6676 | + return 1; | |
6677 | + this->buf = page_address(page); | |
f3e0dcc9 | 6678 | + sg_init_one(&this->sg[0], this->buf, PAGE_SIZE); |
4e97e4e9 | 6679 | + } |
6680 | + return 0; | |
6681 | +} | |
24613191 | 6682 | + |
ad8f4a28 | 6683 | +/* |
4e97e4e9 | 6684 | + * toi_checksum_print_debug_stats |
6685 | + * @buffer: Pointer to a buffer into which the debug info will be printed. | |
6686 | + * @size: Size of the buffer. | |
6687 | + * | |
6688 | + * Print information to be recorded for debugging purposes into a buffer. | |
6689 | + * Returns: Number of characters written to the buffer. | |
6690 | + */ | |
24613191 | 6691 | + |
4e97e4e9 | 6692 | +static int toi_checksum_print_debug_stats(char *buffer, int size) |
6693 | +{ | |
6694 | + int len; | |
24613191 | 6695 | + |
4e97e4e9 | 6696 | + if (!toi_checksum_ops.enabled) |
1838f965 | 6697 | + return scnprintf(buffer, size, |
4e97e4e9 | 6698 | + "- Checksumming disabled.\n"); |
ad8f4a28 | 6699 | + |
1838f965 | 6700 | + len = scnprintf(buffer, size, "- Checksum method is '%s'.\n", |
4e97e4e9 | 6701 | + toi_checksum_name); |
1838f965 | 6702 | + len += scnprintf(buffer + len, size - len, |
4e97e4e9 | 6703 | + " %d pages resaved in atomic copy.\n", toi_num_resaved); |
6704 | + return len; | |
24613191 | 6705 | +} |
6706 | + | |
ad8f4a28 AM |
6707 | +static int toi_checksum_memory_needed(void) |
6708 | +{ | |
6709 | + return toi_checksum_ops.enabled ? | |
6710 | + checksum_pages_needed() << PAGE_SHIFT : 0; | |
6711 | +} | |
6712 | + | |
4e97e4e9 | 6713 | +static int toi_checksum_storage_needed(void) |
24613191 | 6714 | +{ |
4e97e4e9 | 6715 | + if (toi_checksum_ops.enabled) |
6716 | + return strlen(toi_checksum_name) + sizeof(int) + 1; | |
6717 | + else | |
6718 | + return 0; | |
6719 | +} | |
24613191 | 6720 | + |
ad8f4a28 | 6721 | +/* |
4e97e4e9 | 6722 | + * toi_checksum_save_config_info |
6723 | + * @buffer: Pointer to a buffer of size PAGE_SIZE. | |
6724 | + * | |
6725 | + * Save informaton needed when reloading the image at resume time. | |
6726 | + * Returns: Number of bytes used for saving our data. | |
6727 | + */ | |
6728 | +static int toi_checksum_save_config_info(char *buffer) | |
6729 | +{ | |
6730 | + int namelen = strlen(toi_checksum_name) + 1; | |
6731 | + int total_len; | |
ad8f4a28 | 6732 | + |
4e97e4e9 | 6733 | + *((unsigned int *) buffer) = namelen; |
6734 | + strncpy(buffer + sizeof(unsigned int), toi_checksum_name, namelen); | |
6735 | + total_len = sizeof(unsigned int) + namelen; | |
6736 | + return total_len; | |
24613191 | 6737 | +} |
6738 | + | |
4e97e4e9 | 6739 | +/* toi_checksum_load_config_info |
6740 | + * @buffer: Pointer to the start of the data. | |
6741 | + * @size: Number of bytes that were saved. | |
24613191 | 6742 | + * |
4e97e4e9 | 6743 | + * Description: Reload information needed for dechecksuming the image at |
6744 | + * resume time. | |
24613191 | 6745 | + */ |
4e97e4e9 | 6746 | +static void toi_checksum_load_config_info(char *buffer, int size) |
24613191 | 6747 | +{ |
4e97e4e9 | 6748 | + int namelen; |
24613191 | 6749 | + |
4e97e4e9 | 6750 | + namelen = *((unsigned int *) (buffer)); |
6751 | + strncpy(toi_checksum_name, buffer + sizeof(unsigned int), | |
6752 | + namelen); | |
6753 | + return; | |
6754 | +} | |
24613191 | 6755 | + |
4e97e4e9 | 6756 | +/* |
6757 | + * Free Checksum Memory | |
6758 | + */ | |
24613191 | 6759 | + |
4e97e4e9 | 6760 | +void free_checksum_pages(void) |
6761 | +{ | |
6762 | + while (pages_allocated) { | |
6763 | + unsigned long next = *((unsigned long *) page_list); | |
6764 | + ClearPageNosave(virt_to_page(page_list)); | |
ad8f4a28 | 6765 | + toi_free_page(15, (unsigned long) page_list); |
4e97e4e9 | 6766 | + page_list = next; |
6767 | + pages_allocated--; | |
24613191 | 6768 | + } |
4e97e4e9 | 6769 | +} |
24613191 | 6770 | + |
4e97e4e9 | 6771 | +/* |
6772 | + * Allocate Checksum Memory | |
6773 | + */ | |
24613191 | 6774 | + |
4e97e4e9 | 6775 | +int allocate_checksum_pages(void) |
6776 | +{ | |
ad8f4a28 | 6777 | + int pages_needed = checksum_pages_needed(); |
24613191 | 6778 | + |
4e97e4e9 | 6779 | + if (!toi_checksum_ops.enabled) |
6780 | + return 0; | |
24613191 | 6781 | + |
4e97e4e9 | 6782 | + while (pages_allocated < pages_needed) { |
6783 | + unsigned long *new_page = | |
6784 | + (unsigned long *) toi_get_zeroed_page(15, TOI_ATOMIC_GFP); | |
ad8f4a28 AM |
6785 | + if (!new_page) { |
6786 | + printk("Unable to allocate checksum pages.\n"); | |
4e97e4e9 | 6787 | + return -ENOMEM; |
ad8f4a28 | 6788 | + } |
4e97e4e9 | 6789 | + SetPageNosave(virt_to_page(new_page)); |
6790 | + (*new_page) = page_list; | |
6791 | + page_list = (unsigned long) new_page; | |
6792 | + pages_allocated++; | |
24613191 | 6793 | + } |
6794 | + | |
4e97e4e9 | 6795 | + next_page = (unsigned long) page_list; |
6796 | + checksum_index = 0; | |
e8d0ad9d | 6797 | + |
4e97e4e9 | 6798 | + return 0; |
6799 | +} | |
24613191 | 6800 | + |
ad8f4a28 | 6801 | +char *tuxonice_get_next_checksum(void) |
4e97e4e9 | 6802 | +{ |
6803 | + if (!toi_checksum_ops.enabled) | |
6804 | + return NULL; | |
24613191 | 6805 | + |
4e97e4e9 | 6806 | + if (checksum_index % CHECKSUMS_PER_PAGE) |
6807 | + this_checksum += CHECKSUM_SIZE; | |
6808 | + else { | |
6809 | + this_checksum = next_page + sizeof(void *); | |
6810 | + next_page = *((unsigned long *) next_page); | |
24613191 | 6811 | + } |
6812 | + | |
4e97e4e9 | 6813 | + checksum_index++; |
6814 | + return (char *) this_checksum; | |
6815 | +} | |
24613191 | 6816 | + |
4e97e4e9 | 6817 | +int tuxonice_calc_checksum(struct page *page, char *checksum_locn) |
6818 | +{ | |
6819 | + char *pa; | |
6820 | + int result, cpu = smp_processor_id(); | |
6821 | + struct cpu_context *ctx = &per_cpu(contexts, cpu); | |
24613191 | 6822 | + |
4e97e4e9 | 6823 | + if (!toi_checksum_ops.enabled) |
6824 | + return 0; | |
24613191 | 6825 | + |
4e97e4e9 | 6826 | + pa = kmap(page); |
6827 | + memcpy(ctx->buf, pa, PAGE_SIZE); | |
6828 | + kunmap(page); | |
6829 | + result = crypto_hash_digest(&ctx->desc, ctx->sg, PAGE_SIZE, | |
6830 | + checksum_locn); | |
6831 | + return result; | |
24613191 | 6832 | +} |
4e97e4e9 | 6833 | +/* |
6834 | + * Calculate checksums | |
24613191 | 6835 | + */ |
6836 | + | |
4e97e4e9 | 6837 | +void check_checksums(void) |
24613191 | 6838 | +{ |
4e97e4e9 | 6839 | + int pfn, index = 0, cpu = smp_processor_id(); |
4e97e4e9 | 6840 | + char current_checksum[CHECKSUM_SIZE]; |
6841 | + struct cpu_context *ctx = &per_cpu(contexts, cpu); | |
24613191 | 6842 | + |
4e97e4e9 | 6843 | + if (!toi_checksum_ops.enabled) |
6844 | + return; | |
24613191 | 6845 | + |
4e97e4e9 | 6846 | + next_page = (unsigned long) page_list; |
24613191 | 6847 | + |
4e97e4e9 | 6848 | + toi_num_resaved = 0; |
1838f965 | 6849 | + this_checksum = 0; |
24613191 | 6850 | + |
1838f965 | 6851 | + BITMAP_FOR_EACH_SET(pageset2_map, pfn) { |
4e97e4e9 | 6852 | + int ret; |
6853 | + char *pa; | |
6854 | + struct page *page = pfn_to_page(pfn); | |
24613191 | 6855 | + |
4e97e4e9 | 6856 | + if (index % CHECKSUMS_PER_PAGE) { |
6857 | + this_checksum += CHECKSUM_SIZE; | |
6858 | + } else { | |
6859 | + this_checksum = next_page + sizeof(void *); | |
6860 | + next_page = *((unsigned long *) next_page); | |
6861 | + } | |
24613191 | 6862 | + |
4e97e4e9 | 6863 | + /* Done when IRQs disabled so must be atomic */ |
6864 | + pa = kmap_atomic(page, KM_USER1); | |
6865 | + memcpy(ctx->buf, pa, PAGE_SIZE); | |
6866 | + kunmap_atomic(pa, KM_USER1); | |
ad8f4a28 | 6867 | + ret = crypto_hash_digest(&ctx->desc, ctx->sg, PAGE_SIZE, |
4e97e4e9 | 6868 | + current_checksum); |
24613191 | 6869 | + |
4e97e4e9 | 6870 | + if (ret) { |
ad8f4a28 | 6871 | + printk(KERN_INFO "Digest failed. Returned %d.\n", ret); |
4e97e4e9 | 6872 | + return; |
24613191 | 6873 | + } |
24613191 | 6874 | + |
4e97e4e9 | 6875 | + if (memcmp(current_checksum, (char *) this_checksum, |
6876 | + CHECKSUM_SIZE)) { | |
6877 | + SetPageResave(pfn_to_page(pfn)); | |
6878 | + toi_num_resaved++; | |
6879 | + if (test_action_state(TOI_ABORT_ON_RESAVE_NEEDED)) | |
6880 | + set_abort_result(TOI_RESAVE_NEEDED); | |
6881 | + } | |
24613191 | 6882 | + |
4e97e4e9 | 6883 | + index++; |
24613191 | 6884 | + } |
4e97e4e9 | 6885 | +} |
24613191 | 6886 | + |
4e97e4e9 | 6887 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 6888 | + SYSFS_INT("enabled", SYSFS_RW, &toi_checksum_ops.enabled, 0, 1, 0, |
6889 | + NULL), | |
6890 | + SYSFS_BIT("abort_if_resave_needed", SYSFS_RW, &toi_bkd.toi_action, | |
6891 | + TOI_ABORT_ON_RESAVE_NEEDED, 0) | |
4e97e4e9 | 6892 | +}; |
6893 | + | |
6894 | +/* | |
6895 | + * Ops structure. | |
6896 | + */ | |
6897 | +static struct toi_module_ops toi_checksum_ops = { | |
6898 | + .type = MISC_MODULE, | |
6899 | + .name = "checksumming", | |
6900 | + .directory = "checksum", | |
6901 | + .module = THIS_MODULE, | |
ad8f4a28 | 6902 | + .initialise = toi_checksum_initialise, |
4e97e4e9 | 6903 | + .cleanup = toi_checksum_cleanup, |
6904 | + .print_debug_info = toi_checksum_print_debug_stats, | |
6905 | + .save_config_info = toi_checksum_save_config_info, | |
6906 | + .load_config_info = toi_checksum_load_config_info, | |
ad8f4a28 | 6907 | + .memory_needed = toi_checksum_memory_needed, |
4e97e4e9 | 6908 | + .storage_needed = toi_checksum_storage_needed, |
24613191 | 6909 | + |
4e97e4e9 | 6910 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
6911 | + .num_sysfs_entries = sizeof(sysfs_params) / |
6912 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 6913 | +}; |
6914 | + | |
6915 | +/* ---- Registration ---- */ | |
6916 | +int toi_checksum_init(void) | |
6917 | +{ | |
6918 | + int result = toi_register_module(&toi_checksum_ops); | |
24613191 | 6919 | + return result; |
6920 | +} | |
6921 | + | |
4e97e4e9 | 6922 | +void toi_checksum_exit(void) |
6923 | +{ | |
6924 | + toi_unregister_module(&toi_checksum_ops); | |
6925 | +} | |
6926 | diff --git a/kernel/power/tuxonice_checksum.h b/kernel/power/tuxonice_checksum.h | |
6927 | new file mode 100644 | |
1838f965 | 6928 | index 0000000..84a9174 |
4e97e4e9 | 6929 | --- /dev/null |
6930 | +++ b/kernel/power/tuxonice_checksum.h | |
6931 | @@ -0,0 +1,32 @@ | |
6932 | +/* | |
6933 | + * kernel/power/tuxonice_checksum.h | |
24613191 | 6934 | + * |
1838f965 | 6935 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 6936 | + * Copyright (C) 2006 Red Hat, inc. |
6937 | + * | |
6938 | + * This file is released under the GPLv2. | |
6939 | + * | |
6940 | + * This file contains data checksum routines for TuxOnIce, | |
6941 | + * using cryptoapi. They are used to locate any modifications | |
6942 | + * made to pageset 2 while we're saving it. | |
24613191 | 6943 | + */ |
24613191 | 6944 | + |
4e97e4e9 | 6945 | +#if defined(CONFIG_TOI_CHECKSUM) |
6946 | +extern int toi_checksum_init(void); | |
6947 | +extern void toi_checksum_exit(void); | |
6948 | +void check_checksums(void); | |
6949 | +int allocate_checksum_pages(void); | |
6950 | +void free_checksum_pages(void); | |
ad8f4a28 | 6951 | +char *tuxonice_get_next_checksum(void); |
4e97e4e9 | 6952 | +int tuxonice_calc_checksum(struct page *page, char *checksum_locn); |
6953 | +#else | |
6954 | +static inline int toi_checksum_init(void) { return 0; } | |
6955 | +static inline void toi_checksum_exit(void) { } | |
6956 | +static inline void check_checksums(void) { }; | |
6957 | +static inline int allocate_checksum_pages(void) { return 0; }; | |
6958 | +static inline void free_checksum_pages(void) { }; | |
6959 | +static inline char *tuxonice_get_next_checksum(void) { return NULL; }; | |
6960 | +static inline int tuxonice_calc_checksum(struct page *page, char *checksum_locn) | |
6961 | + { return 0; } | |
6962 | +#endif | |
24613191 | 6963 | + |
4e97e4e9 | 6964 | diff --git a/kernel/power/tuxonice_cluster.c b/kernel/power/tuxonice_cluster.c |
6965 | new file mode 100644 | |
1838f965 | 6966 | index 0000000..405a1a1 |
4e97e4e9 | 6967 | --- /dev/null |
6968 | +++ b/kernel/power/tuxonice_cluster.c | |
1838f965 | 6969 | @@ -0,0 +1,1069 @@ |
4e97e4e9 | 6970 | +/* |
6971 | + * kernel/power/tuxonice_cluster.c | |
6972 | + * | |
1838f965 | 6973 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 6974 | + * |
6975 | + * This file is released under the GPLv2. | |
6976 | + * | |
6977 | + * This file contains routines for cluster hibernation support. | |
6978 | + * | |
ad8f4a28 AM |
6979 | + * Based on ip autoconfiguration code in net/ipv4/ipconfig.c. |
6980 | + * | |
6981 | + * How does it work? | |
6982 | + * | |
6983 | + * There is no 'master' node that tells everyone else what to do. All nodes | |
6984 | + * send messages to the broadcast address/port, maintain a list of peers | |
6985 | + * and figure out when to progress to the next step in hibernating or resuming. | |
6986 | + * This makes us more fault tolerant when it comes to nodes coming and going | |
6987 | + * (which may be more of an issue if we're hibernating when power supplies | |
6988 | + * are being unreliable). | |
6989 | + * | |
6990 | + * At boot time, we start a ktuxonice thread that handles communication with | |
6991 | + * other nodes. This node maintains a state machine that controls our progress | |
6992 | + * through hibernating and resuming, keeping us in step with other nodes. Nodes | |
6993 | + * are identified by their hw address. | |
6994 | + * | |
6995 | + * On startup, the node sends CLUSTER_PING on the configured interface's | |
6996 | + * broadcast address, port $toi_cluster_port (see below) and begins to listen | |
6997 | + * for other broadcast messages. CLUSTER_PING messages are repeated at | |
6998 | + * intervals of 5 minutes, with a random offset to spread traffic out. | |
6999 | + * | |
7000 | + * A hibernation cycle is initiated from any node via | |
7001 | + * | |
7002 | + * echo > /sys/power/tuxonice/do_hibernate | |
7003 | + * | |
7004 | + * and (possibily) the hibernate script. At each step of the process, the node | |
7005 | + * completes its work, and waits for all other nodes to signal completion of | |
7006 | + * their work (or timeout) before progressing to the next step. | |
7007 | + * | |
7008 | + * Request/state Action before reply Possible reply Next state | |
7009 | + * HIBERNATE capable, pre-script HIBERNATE|ACK NODE_PREP | |
7010 | + * HIBERNATE|NACK INIT_0 | |
7011 | + * | |
7012 | + * PREP prepare_image PREP|ACK IMAGE_WRITE | |
7013 | + * PREP|NACK INIT_0 | |
7014 | + * ABORT RUNNING | |
7015 | + * | |
7016 | + * IO write image IO|ACK power off | |
7017 | + * ABORT POST_RESUME | |
7018 | + * | |
7019 | + * (Boot time) check for image IMAGE|ACK RESUME_PREP | |
7020 | + * (Note 1) | |
7021 | + * IMAGE|NACK (Note 2) | |
7022 | + * | |
7023 | + * PREP prepare read image PREP|ACK IMAGE_READ | |
7024 | + * PREP|NACK (As NACK_IMAGE) | |
7025 | + * | |
7026 | + * IO read image IO|ACK POST_RESUME | |
7027 | + * | |
7028 | + * POST_RESUME thaw, post-script RUNNING | |
7029 | + * | |
7030 | + * INIT_0 init 0 | |
7031 | + * | |
7032 | + * Other messages: | |
7033 | + * | |
7034 | + * - PING: Request for all other live nodes to send a PONG. Used at startup to | |
7035 | + * announce presence, when a node is suspected dead and periodically, in case | |
7036 | + * segments of the network are [un]plugged. | |
7037 | + * | |
7038 | + * - PONG: Response to a PING. | |
7039 | + * | |
7040 | + * - ABORT: Request to cancel writing an image. | |
7041 | + * | |
7042 | + * - BYE: Notification that this node is shutting down. | |
7043 | + * | |
7044 | + * Note 1: Repeated at 3s intervals until we continue to boot/resume, so that | |
7045 | + * nodes which are slower to start up can get state synchronised. If a node | |
7046 | + * starting up sees other nodes sending RESUME_PREP or IMAGE_READ, it may send | |
7047 | + * ACK_IMAGE and they will wait for it to catch up. If it sees ACK_READ, it | |
7048 | + * must invalidate its image (if any) and boot normally. | |
7049 | + * | |
7050 | + * Note 2: May occur when one node lost power or powered off while others | |
7051 | + * hibernated. This node waits for others to complete resuming (ACK_READ) | |
7052 | + * before completing its boot, so that it appears as a fail node restarting. | |
7053 | + * | |
7054 | + * If any node has an image, then it also has a list of nodes that hibernated | |
7055 | + * in synchronisation with it. The node will wait for other nodes to appear | |
7056 | + * or timeout before beginning its restoration. | |
7057 | + * | |
7058 | + * If a node has no image, it needs to wait, in case other nodes which do have | |
7059 | + * an image are going to resume, but are taking longer to announce their | |
7060 | + * presence. For this reason, the user can specify a timeout value and a number | |
7061 | + * of nodes detected before we just continue. (We might want to assume in a | |
7062 | + * cluster of, say, 15 nodes, if 8 others have booted without finding an image, | |
7063 | + * the remaining nodes will too. This might help in situations where some nodes | |
7064 | + * are much slower to boot, or more subject to hardware failures or such like). | |
4e97e4e9 | 7065 | + */ |
24613191 | 7066 | + |
4e97e4e9 | 7067 | +#include <linux/suspend.h> |
7068 | +#include <linux/module.h> | |
ad8f4a28 AM |
7069 | +#include <linux/moduleparam.h> |
7070 | +#include <linux/if.h> | |
7071 | +#include <linux/rtnetlink.h> | |
ad8f4a28 AM |
7072 | +#include <linux/ip.h> |
7073 | +#include <linux/udp.h> | |
7074 | +#include <linux/in.h> | |
7075 | +#include <linux/if_arp.h> | |
7076 | +#include <linux/kthread.h> | |
7077 | +#include <linux/wait.h> | |
7f9d2ee0 | 7078 | +#include <linux/netdevice.h> |
ad8f4a28 | 7079 | +#include <net/ip.h> |
24613191 | 7080 | + |
4e97e4e9 | 7081 | +#include "tuxonice.h" |
7082 | +#include "tuxonice_modules.h" | |
7083 | +#include "tuxonice_sysfs.h" | |
7f9d2ee0 | 7084 | +#include "tuxonice_alloc.h" |
4e97e4e9 | 7085 | +#include "tuxonice_io.h" |
24613191 | 7086 | + |
ad8f4a28 AM |
7087 | +#if 1 |
7088 | +#define PRINTK(a, b...) do { printk(a, ##b); } while (0) | |
7089 | +#else | |
7090 | +#define PRINTK(a, b...) do { } while (0) | |
7091 | +#endif | |
7092 | + | |
7093 | +static int loopback_mode; | |
7094 | +static int num_local_nodes = 1; | |
7095 | +#define MAX_LOCAL_NODES 8 | |
7096 | +#define SADDR (loopback_mode ? b->sid : h->saddr) | |
7097 | + | |
7098 | +#define MYNAME "TuxOnIce Clustering" | |
7099 | + | |
7100 | +enum cluster_message { | |
7101 | + MSG_ACK = 1, | |
7102 | + MSG_NACK = 2, | |
7103 | + MSG_PING = 4, | |
7104 | + MSG_ABORT = 8, | |
7105 | + MSG_BYE = 16, | |
7106 | + MSG_HIBERNATE = 32, | |
7107 | + MSG_IMAGE = 64, | |
7108 | + MSG_IO = 128, | |
7109 | + MSG_RUNNING = 256 | |
7110 | +}; | |
7111 | + | |
7112 | +static char *str_message(int message) | |
7113 | +{ | |
7114 | + switch (message) { | |
7115 | + case 4: | |
7116 | + return "Ping"; | |
7117 | + case 8: | |
7118 | + return "Abort"; | |
7119 | + case 9: | |
7120 | + return "Abort acked"; | |
7121 | + case 10: | |
7122 | + return "Abort nacked"; | |
7123 | + case 16: | |
7124 | + return "Bye"; | |
7125 | + case 17: | |
7126 | + return "Bye acked"; | |
7127 | + case 18: | |
7128 | + return "Bye nacked"; | |
7129 | + case 32: | |
7130 | + return "Hibernate request"; | |
7131 | + case 33: | |
7132 | + return "Hibernate ack"; | |
7133 | + case 34: | |
7134 | + return "Hibernate nack"; | |
7135 | + case 64: | |
7136 | + return "Image exists?"; | |
7137 | + case 65: | |
7138 | + return "Image does exist"; | |
7139 | + case 66: | |
7140 | + return "No image here"; | |
7141 | + case 128: | |
7142 | + return "I/O"; | |
7143 | + case 129: | |
7144 | + return "I/O okay"; | |
7145 | + case 130: | |
7146 | + return "I/O failed"; | |
7147 | + case 256: | |
7148 | + return "Running"; | |
7149 | + default: | |
7150 | + printk("Unrecognised message %d.\n", message); | |
7151 | + return "Unrecognised message (see dmesg)"; | |
7152 | + } | |
7153 | +} | |
7154 | + | |
7155 | +#define MSG_ACK_MASK (MSG_ACK | MSG_NACK) | |
7156 | +#define MSG_STATE_MASK (~MSG_ACK_MASK) | |
7157 | + | |
7158 | +struct node_info { | |
7159 | + struct list_head member_list; | |
7160 | + wait_queue_head_t member_events; | |
7161 | + spinlock_t member_list_lock; | |
7162 | + spinlock_t receive_lock; | |
7163 | + int peer_count, ignored_peer_count; | |
7164 | + struct toi_sysfs_data sysfs_data; | |
7165 | + enum cluster_message current_message; | |
7166 | +}; | |
7167 | + | |
7168 | +struct node_info node_array[MAX_LOCAL_NODES]; | |
7169 | + | |
7170 | +struct cluster_member { | |
7171 | + __be32 addr; | |
7172 | + enum cluster_message message; | |
7173 | + struct list_head list; | |
7174 | + int ignore; | |
7175 | +}; | |
24613191 | 7176 | + |
ad8f4a28 AM |
7177 | +#define toi_cluster_port_send 3501 |
7178 | +#define toi_cluster_port_recv 3502 | |
7179 | + | |
7180 | +static struct net_device *net_dev; | |
4e97e4e9 | 7181 | +static struct toi_module_ops toi_cluster_ops; |
24613191 | 7182 | + |
ad8f4a28 AM |
7183 | +static int toi_recv(struct sk_buff *skb, struct net_device *dev, |
7184 | + struct packet_type *pt, struct net_device *orig_dev); | |
7185 | + | |
7186 | +static struct packet_type toi_cluster_packet_type = { | |
7187 | + .type = __constant_htons(ETH_P_IP), | |
7188 | + .func = toi_recv, | |
7189 | +}; | |
7190 | + | |
7191 | +struct toi_pkt { /* BOOTP packet format */ | |
7192 | + struct iphdr iph; /* IP header */ | |
7193 | + struct udphdr udph; /* UDP header */ | |
7194 | + u8 htype; /* HW address type */ | |
7195 | + u8 hlen; /* HW address length */ | |
7196 | + __be32 xid; /* Transaction ID */ | |
7197 | + __be16 secs; /* Seconds since we started */ | |
7198 | + __be16 flags; /* Just what it says */ | |
7199 | + u8 hw_addr[16]; /* Sender's HW address */ | |
7200 | + u16 message; /* Message */ | |
7201 | + unsigned long sid; /* Source ID for loopback testing */ | |
7202 | +}; | |
7203 | + | |
7204 | +static char toi_cluster_iface[IFNAMSIZ] = CONFIG_TOI_DEFAULT_CLUSTER_INTERFACE; | |
7205 | + | |
7206 | +static int added_pack; | |
7207 | + | |
7f9d2ee0 | 7208 | +static int others_have_image; |
ad8f4a28 AM |
7209 | + |
7210 | +/* Key used to allow multiple clusters on the same lan */ | |
7211 | +static char toi_cluster_key[32] = CONFIG_TOI_DEFAULT_CLUSTER_KEY; | |
7212 | +static char pre_hibernate_script[255] = | |
7213 | + CONFIG_TOI_DEFAULT_CLUSTER_PRE_HIBERNATE; | |
7214 | +static char post_hibernate_script[255] = | |
7215 | + CONFIG_TOI_DEFAULT_CLUSTER_POST_HIBERNATE; | |
7216 | + | |
7217 | +/* List of cluster members */ | |
7218 | +static unsigned long continue_delay = 5 * HZ; | |
7219 | +static unsigned long cluster_message_timeout = 3 * HZ; | |
7220 | + | |
7221 | +/* === Membership list === */ | |
7222 | + | |
7223 | +static void print_member_info(int index) | |
7224 | +{ | |
7225 | + struct cluster_member *this; | |
7226 | + | |
7227 | + printk(KERN_INFO "==> Dumping node %d.\n", index); | |
7228 | + | |
7229 | + list_for_each_entry(this, &node_array[index].member_list, list) | |
7230 | + printk(KERN_INFO "%d.%d.%d.%d last message %s. %s\n", | |
7231 | + NIPQUAD(this->addr), | |
7232 | + str_message(this->message), | |
7233 | + this->ignore ? "(Ignored)" : ""); | |
7234 | + printk(KERN_INFO "== Done ==\n"); | |
7235 | +} | |
7236 | + | |
7237 | +static struct cluster_member *__find_member(int index, __be32 addr) | |
7238 | +{ | |
7239 | + struct cluster_member *this; | |
7240 | + | |
7241 | + list_for_each_entry(this, &node_array[index].member_list, list) { | |
7242 | + if (this->addr != addr) | |
7243 | + continue; | |
7244 | + | |
7245 | + return this; | |
7246 | + } | |
7247 | + | |
7248 | + return NULL; | |
7249 | +} | |
7250 | + | |
7251 | +static void set_ignore(int index, __be32 addr, struct cluster_member *this) | |
7252 | +{ | |
7253 | + if (this->ignore) { | |
7254 | + PRINTK("Node %d already ignoring %d.%d.%d.%d.\n", | |
7255 | + index, NIPQUAD(addr)); | |
7256 | + return; | |
7257 | + } | |
7258 | + | |
7259 | + PRINTK("Node %d sees node %d.%d.%d.%d now being ignored.\n", | |
7260 | + index, NIPQUAD(addr)); | |
7261 | + this->ignore = 1; | |
7262 | + node_array[index].ignored_peer_count++; | |
7263 | +} | |
7264 | + | |
7265 | +static int __add_update_member(int index, __be32 addr, int message) | |
7266 | +{ | |
7267 | + struct cluster_member *this; | |
7268 | + | |
7269 | + this = __find_member(index, addr); | |
7270 | + if (this) { | |
7271 | + if (this->message != message) { | |
7272 | + this->message = message; | |
7273 | + if ((message & MSG_NACK) && | |
7274 | + (message & (MSG_HIBERNATE | MSG_IMAGE | MSG_IO))) | |
7275 | + set_ignore(index, addr, this); | |
7276 | + PRINTK("Node %d sees node %d.%d.%d.%d now sending " | |
7277 | + "%s.\n", index, NIPQUAD(addr), | |
7278 | + str_message(message)); | |
7279 | + wake_up(&node_array[index].member_events); | |
7280 | + } | |
7281 | + return 0; | |
7282 | + } | |
7283 | + | |
7284 | + this = (struct cluster_member *) toi_kzalloc(36, | |
7285 | + sizeof(struct cluster_member), GFP_KERNEL); | |
7286 | + | |
7287 | + if (!this) | |
7288 | + return -1; | |
7289 | + | |
7290 | + this->addr = addr; | |
7291 | + this->message = message; | |
7292 | + this->ignore = 0; | |
7293 | + INIT_LIST_HEAD(&this->list); | |
7294 | + | |
7295 | + node_array[index].peer_count++; | |
7296 | + | |
7297 | + PRINTK("Node %d sees node %d.%d.%d.%d sending %s.\n", index, | |
7298 | + NIPQUAD(addr), str_message(message)); | |
7299 | + | |
7300 | + if ((message & MSG_NACK) && | |
7301 | + (message & (MSG_HIBERNATE | MSG_IMAGE | MSG_IO))) | |
7302 | + set_ignore(index, addr, this); | |
7303 | + list_add_tail(&this->list, &node_array[index].member_list); | |
7304 | + return 1; | |
7305 | +} | |
7306 | + | |
7307 | +static int add_update_member(int index, __be32 addr, int message) | |
7308 | +{ | |
7309 | + int result; | |
7310 | + unsigned long flags; | |
7311 | + spin_lock_irqsave(&node_array[index].member_list_lock, flags); | |
7312 | + result = __add_update_member(index, addr, message); | |
7313 | + spin_unlock_irqrestore(&node_array[index].member_list_lock, flags); | |
7314 | + | |
7315 | + print_member_info(index); | |
7316 | + | |
7317 | + wake_up(&node_array[index].member_events); | |
7318 | + | |
7319 | + return result; | |
7320 | +} | |
7321 | + | |
7322 | +static void del_member(int index, __be32 addr) | |
7323 | +{ | |
7324 | + struct cluster_member *this; | |
7325 | + unsigned long flags; | |
7326 | + | |
7327 | + spin_lock_irqsave(&node_array[index].member_list_lock, flags); | |
7328 | + this = __find_member(index, addr); | |
7329 | + | |
7330 | + if (this) { | |
7331 | + list_del_init(&this->list); | |
7332 | + toi_kfree(36, this); | |
7333 | + node_array[index].peer_count--; | |
7334 | + } | |
7335 | + | |
7336 | + spin_unlock_irqrestore(&node_array[index].member_list_lock, flags); | |
7337 | +} | |
7338 | + | |
7339 | +/* === Message transmission === */ | |
7340 | + | |
7341 | +static void toi_send_if(int message, unsigned long my_id); | |
7342 | + | |
7343 | +/* | |
7344 | + * Process received TOI packet. | |
7345 | + */ | |
7346 | +static int toi_recv(struct sk_buff *skb, struct net_device *dev, | |
7347 | + struct packet_type *pt, struct net_device *orig_dev) | |
7348 | +{ | |
7349 | + struct toi_pkt *b; | |
7350 | + struct iphdr *h; | |
7351 | + int len, result, index; | |
7352 | + unsigned long addr, message, ack; | |
7353 | + | |
7354 | + /* Perform verifications before taking the lock. */ | |
7355 | + if (skb->pkt_type == PACKET_OTHERHOST) | |
7356 | + goto drop; | |
7357 | + | |
7358 | + if (dev != net_dev) | |
7359 | + goto drop; | |
7360 | + | |
7f9d2ee0 | 7361 | + skb = skb_share_check(skb, GFP_ATOMIC); |
ad8f4a28 AM |
7362 | + if (!skb) |
7363 | + return NET_RX_DROP; | |
7364 | + | |
7365 | + if (!pskb_may_pull(skb, | |
7366 | + sizeof(struct iphdr) + | |
7367 | + sizeof(struct udphdr))) | |
7368 | + goto drop; | |
7369 | + | |
7370 | + b = (struct toi_pkt *)skb_network_header(skb); | |
7371 | + h = &b->iph; | |
7372 | + | |
7373 | + if (h->ihl != 5 || h->version != 4 || h->protocol != IPPROTO_UDP) | |
7374 | + goto drop; | |
7375 | + | |
7376 | + /* Fragments are not supported */ | |
7377 | + if (h->frag_off & htons(IP_OFFSET | IP_MF)) { | |
7378 | + if (net_ratelimit()) | |
7379 | + printk(KERN_ERR "TuxOnIce: Ignoring fragmented " | |
7380 | + "cluster message.\n"); | |
7381 | + goto drop; | |
7382 | + } | |
7383 | + | |
7384 | + if (skb->len < ntohs(h->tot_len)) | |
7385 | + goto drop; | |
7386 | + | |
7387 | + if (ip_fast_csum((char *) h, h->ihl)) | |
7388 | + goto drop; | |
7389 | + | |
7390 | + if (b->udph.source != htons(toi_cluster_port_send) || | |
7391 | + b->udph.dest != htons(toi_cluster_port_recv)) | |
7392 | + goto drop; | |
7393 | + | |
7394 | + if (ntohs(h->tot_len) < ntohs(b->udph.len) + sizeof(struct iphdr)) | |
7395 | + goto drop; | |
7396 | + | |
7397 | + len = ntohs(b->udph.len) - sizeof(struct udphdr); | |
7398 | + | |
7399 | + /* Ok the front looks good, make sure we can get at the rest. */ | |
7400 | + if (!pskb_may_pull(skb, skb->len)) | |
7401 | + goto drop; | |
7402 | + | |
7403 | + b = (struct toi_pkt *)skb_network_header(skb); | |
7404 | + h = &b->iph; | |
7405 | + | |
7406 | + addr = SADDR; | |
7407 | + PRINTK(">>> Message %s received from " NIPQUAD_FMT ".\n", | |
7408 | + str_message(b->message), NIPQUAD(addr)); | |
7409 | + | |
7410 | + message = b->message & MSG_STATE_MASK; | |
7411 | + ack = b->message & MSG_ACK_MASK; | |
7412 | + | |
7413 | + for (index = 0; index < num_local_nodes; index++) { | |
7414 | + int new_message = node_array[index].current_message, | |
7415 | + old_message = new_message; | |
7416 | + | |
7417 | + if (index == SADDR || !old_message) { | |
7418 | + PRINTK("Ignoring node %d (offline or self).\n", index); | |
7419 | + continue; | |
7420 | + } | |
7421 | + | |
7422 | + /* One message at a time, please. */ | |
7423 | + spin_lock(&node_array[index].receive_lock); | |
7424 | + | |
7425 | + result = add_update_member(index, SADDR, b->message); | |
7426 | + if (result == -1) { | |
7427 | + printk(KERN_INFO "Failed to add new cluster member " | |
7428 | + NIPQUAD_FMT ".\n", | |
7429 | + NIPQUAD(addr)); | |
7430 | + goto drop_unlock; | |
7431 | + } | |
7432 | + | |
7433 | + switch (b->message & MSG_STATE_MASK) { | |
7434 | + case MSG_PING: | |
7435 | + break; | |
7436 | + case MSG_ABORT: | |
7437 | + break; | |
7438 | + case MSG_BYE: | |
7439 | + break; | |
7440 | + case MSG_HIBERNATE: | |
7441 | + /* Can I hibernate? */ | |
7442 | + new_message = MSG_HIBERNATE | | |
7443 | + ((index & 1) ? MSG_NACK : MSG_ACK); | |
7444 | + break; | |
7445 | + case MSG_IMAGE: | |
7446 | + /* Can I resume? */ | |
7447 | + new_message = MSG_IMAGE | | |
7448 | + ((index & 1) ? MSG_NACK : MSG_ACK); | |
7449 | + if (new_message != old_message) | |
7450 | + printk("Setting whether I can resume to %d.\n", | |
7451 | + new_message); | |
7452 | + break; | |
7453 | + case MSG_IO: | |
7454 | + new_message = MSG_IO | MSG_ACK; | |
7455 | + break; | |
7456 | + case MSG_RUNNING: | |
7457 | + break; | |
7458 | + default: | |
7459 | + if (net_ratelimit()) | |
7460 | + printk(KERN_ERR "Unrecognised TuxOnIce cluster" | |
7461 | + " message %d from " NIPQUAD_FMT ".\n", | |
7462 | + b->message, NIPQUAD(addr)); | |
7463 | + }; | |
7464 | + | |
7465 | + if (old_message != new_message) { | |
7466 | + node_array[index].current_message = new_message; | |
7467 | + printk(KERN_INFO ">>> Sending new message for node " | |
7468 | + "%d.\n", index); | |
7469 | + toi_send_if(new_message, index); | |
7470 | + } else if (!ack) { | |
7471 | + printk(KERN_INFO ">>> Resending message for node %d.\n", | |
7472 | + index); | |
7473 | + toi_send_if(new_message, index); | |
7474 | + } | |
7475 | +drop_unlock: | |
7476 | + spin_unlock(&node_array[index].receive_lock); | |
7477 | + }; | |
7478 | + | |
7479 | +drop: | |
7480 | + /* Throw the packet out. */ | |
7481 | + kfree_skb(skb); | |
7482 | + | |
7483 | + return 0; | |
7484 | +} | |
7485 | + | |
7486 | +/* | |
7487 | + * Send cluster message to single interface. | |
7488 | + */ | |
7489 | +static void toi_send_if(int message, unsigned long my_id) | |
7490 | +{ | |
7491 | + struct sk_buff *skb; | |
7492 | + struct toi_pkt *b; | |
7493 | + int hh_len = LL_RESERVED_SPACE(net_dev); | |
7494 | + struct iphdr *h; | |
7495 | + | |
7496 | + /* Allocate packet */ | |
7497 | + skb = alloc_skb(sizeof(struct toi_pkt) + hh_len + 15, GFP_KERNEL); | |
7498 | + if (!skb) | |
7499 | + return; | |
7500 | + skb_reserve(skb, hh_len); | |
7501 | + b = (struct toi_pkt *) skb_put(skb, sizeof(struct toi_pkt)); | |
7502 | + memset(b, 0, sizeof(struct toi_pkt)); | |
7503 | + | |
7504 | + /* Construct IP header */ | |
7505 | + skb_reset_network_header(skb); | |
7506 | + h = ip_hdr(skb); | |
7507 | + h->version = 4; | |
7508 | + h->ihl = 5; | |
7509 | + h->tot_len = htons(sizeof(struct toi_pkt)); | |
7510 | + h->frag_off = htons(IP_DF); | |
7511 | + h->ttl = 64; | |
7512 | + h->protocol = IPPROTO_UDP; | |
7513 | + h->daddr = htonl(INADDR_BROADCAST); | |
7514 | + h->check = ip_fast_csum((unsigned char *) h, h->ihl); | |
7515 | + | |
7516 | + /* Construct UDP header */ | |
7517 | + b->udph.source = htons(toi_cluster_port_send); | |
7518 | + b->udph.dest = htons(toi_cluster_port_recv); | |
7519 | + b->udph.len = htons(sizeof(struct toi_pkt) - sizeof(struct iphdr)); | |
7520 | + /* UDP checksum not calculated -- explicitly allowed in BOOTP RFC */ | |
7521 | + | |
7522 | + /* Construct message */ | |
7523 | + b->message = message; | |
7524 | + b->sid = my_id; | |
7525 | + b->htype = net_dev->type; /* can cause undefined behavior */ | |
7526 | + b->hlen = net_dev->addr_len; | |
7527 | + memcpy(b->hw_addr, net_dev->dev_addr, net_dev->addr_len); | |
7528 | + b->secs = htons(3); /* 3 seconds */ | |
7529 | + | |
7530 | + /* Chain packet down the line... */ | |
7531 | + skb->dev = net_dev; | |
7532 | + skb->protocol = htons(ETH_P_IP); | |
7f9d2ee0 | 7533 | + if ((dev_hard_header(skb, net_dev, ntohs(skb->protocol), |
ad8f4a28 AM |
7534 | + net_dev->broadcast, net_dev->dev_addr, skb->len) < 0) || |
7535 | + dev_queue_xmit(skb) < 0) | |
7536 | + printk(KERN_INFO "E"); | |
7537 | +} | |
7538 | + | |
7539 | +/* ========================================= */ | |
7540 | + | |
7541 | +/* kTOICluster */ | |
7542 | + | |
7543 | +static atomic_t num_cluster_threads; | |
7544 | +static DECLARE_WAIT_QUEUE_HEAD(clusterd_events); | |
7545 | + | |
7546 | +static int kTOICluster(void *data) | |
7547 | +{ | |
7548 | + unsigned long my_id; | |
7549 | + | |
7550 | + my_id = atomic_add_return(1, &num_cluster_threads) - 1; | |
7551 | + node_array[my_id].current_message = (unsigned long) data; | |
7552 | + | |
7553 | + PRINTK("kTOICluster daemon %lu starting.\n", my_id); | |
7554 | + | |
7555 | + current->flags |= PF_NOFREEZE; | |
7556 | + | |
7557 | + while (node_array[my_id].current_message) { | |
7558 | + toi_send_if(node_array[my_id].current_message, my_id); | |
7559 | + sleep_on_timeout(&clusterd_events, | |
7560 | + cluster_message_timeout); | |
7561 | + PRINTK("Link state %lu is %d.\n", my_id, | |
7562 | + node_array[my_id].current_message); | |
7563 | + } | |
7564 | + | |
7565 | + toi_send_if(MSG_BYE, my_id); | |
7566 | + atomic_dec(&num_cluster_threads); | |
7567 | + wake_up(&clusterd_events); | |
7568 | + | |
7569 | + PRINTK("kTOICluster daemon %lu exiting.\n", my_id); | |
7570 | + __set_current_state(TASK_RUNNING); | |
7571 | + return 0; | |
7572 | +} | |
7573 | + | |
7574 | +static void kill_clusterd(void) | |
7575 | +{ | |
7576 | + int i; | |
7577 | + | |
7578 | + for (i = 0; i < num_local_nodes; i++) { | |
7579 | + if (node_array[i].current_message) { | |
7580 | + PRINTK("Seeking to kill clusterd %d.\n", i); | |
7581 | + node_array[i].current_message = 0; | |
7582 | + } | |
7583 | + } | |
7584 | + wait_event(clusterd_events, | |
7585 | + !atomic_read(&num_cluster_threads)); | |
7586 | + PRINTK("All cluster daemons have exited.\n"); | |
7587 | +} | |
7588 | + | |
7589 | +static int peers_not_in_message(int index, int message, int precise) | |
7590 | +{ | |
7591 | + struct cluster_member *this; | |
7592 | + unsigned long flags; | |
7593 | + int result = 0; | |
7594 | + | |
7595 | + spin_lock_irqsave(&node_array[index].member_list_lock, flags); | |
7596 | + list_for_each_entry(this, &node_array[index].member_list, list) { | |
7597 | + if (this->ignore) | |
7598 | + continue; | |
7599 | + | |
7600 | + PRINTK("Peer %d.%d.%d.%d sending %s. " | |
7601 | + "Seeking %s.\n", | |
7602 | + NIPQUAD(this->addr), | |
7603 | + str_message(this->message), str_message(message)); | |
7604 | + if ((precise ? this->message : | |
7605 | + this->message & MSG_STATE_MASK) != | |
7606 | + message) | |
7607 | + result++; | |
7608 | + } | |
7609 | + spin_unlock_irqrestore(&node_array[index].member_list_lock, flags); | |
7610 | + PRINTK("%d peers in sought message.\n", result); | |
7611 | + return result; | |
7612 | +} | |
7613 | + | |
7614 | +static void reset_ignored(int index) | |
7615 | +{ | |
7616 | + struct cluster_member *this; | |
7617 | + unsigned long flags; | |
7618 | + | |
7619 | + spin_lock_irqsave(&node_array[index].member_list_lock, flags); | |
7620 | + list_for_each_entry(this, &node_array[index].member_list, list) | |
7621 | + this->ignore = 0; | |
7622 | + node_array[index].ignored_peer_count = 0; | |
7623 | + spin_unlock_irqrestore(&node_array[index].member_list_lock, flags); | |
7624 | +} | |
7625 | + | |
7626 | +static int peers_in_message(int index, int message, int precise) | |
7627 | +{ | |
7628 | + return node_array[index].peer_count - | |
7629 | + node_array[index].ignored_peer_count - | |
7630 | + peers_not_in_message(index, message, precise); | |
7631 | +} | |
7632 | + | |
7633 | +static int time_to_continue(int index, unsigned long start, int message) | |
7634 | +{ | |
7635 | + int first = peers_not_in_message(index, message, 0); | |
7636 | + int second = peers_in_message(index, message, 1); | |
7637 | + | |
7638 | + PRINTK("First part returns %d, second returns %d.\n", first, second); | |
7639 | + | |
7640 | + if (!first && !second) { | |
7641 | + PRINTK("All peers answered message %d.\n", | |
7642 | + message); | |
7643 | + return 1; | |
7644 | + } | |
7645 | + | |
7646 | + if (time_after(jiffies, start + continue_delay)) { | |
7647 | + PRINTK("Timeout reached.\n"); | |
7648 | + return 1; | |
7649 | + } | |
7650 | + | |
7651 | + PRINTK("Not time to continue yet (%lu < %lu).\n", jiffies, | |
7652 | + start + continue_delay); | |
7653 | + return 0; | |
7654 | +} | |
7655 | + | |
7656 | +void toi_initiate_cluster_hibernate(void) | |
7657 | +{ | |
7658 | + int result; | |
7659 | + unsigned long start; | |
7660 | + | |
7661 | + result = do_toi_step(STEP_HIBERNATE_PREPARE_IMAGE); | |
7662 | + if (result) | |
7663 | + return; | |
7664 | + | |
7665 | + toi_send_if(MSG_HIBERNATE, 0); | |
7666 | + | |
7667 | + start = jiffies; | |
7668 | + wait_event(node_array[0].member_events, | |
7669 | + time_to_continue(0, start, MSG_HIBERNATE)); | |
7670 | + | |
7671 | + if (test_action_state(TOI_FREEZER_TEST)) { | |
7672 | + toi_send_if(MSG_ABORT, 0); | |
7673 | + | |
7674 | + start = jiffies; | |
7675 | + wait_event(node_array[0].member_events, | |
7676 | + time_to_continue(0, start, MSG_RUNNING)); | |
7677 | + | |
7678 | + do_toi_step(STEP_QUIET_CLEANUP); | |
7679 | + return; | |
7680 | + } | |
7681 | + | |
7682 | + toi_send_if(MSG_IO, 0); | |
7683 | + | |
7684 | + result = do_toi_step(STEP_HIBERNATE_SAVE_IMAGE); | |
7685 | + if (result) | |
7686 | + return; | |
7687 | + | |
7688 | + /* This code runs at resume time too! */ | |
7689 | + if (toi_in_hibernate) | |
7690 | + result = do_toi_step(STEP_HIBERNATE_POWERDOWN); | |
7691 | +} | |
7692 | +EXPORT_SYMBOL_GPL(toi_initiate_cluster_hibernate); | |
7693 | + | |
4e97e4e9 | 7694 | +/* toi_cluster_print_debug_stats |
7695 | + * | |
7696 | + * Description: Print information to be recorded for debugging purposes into a | |
7697 | + * buffer. | |
7698 | + * Arguments: buffer: Pointer to a buffer into which the debug info will be | |
7699 | + * printed. | |
7700 | + * size: Size of the buffer. | |
7701 | + * Returns: Number of characters written to the buffer. | |
7702 | + */ | |
7703 | +static int toi_cluster_print_debug_stats(char *buffer, int size) | |
7704 | +{ | |
7705 | + int len; | |
ad8f4a28 AM |
7706 | + |
7707 | + if (strlen(toi_cluster_iface)) | |
1838f965 | 7708 | + len = scnprintf(buffer, size, |
ad8f4a28 AM |
7709 | + "- Cluster interface is '%s'.\n", |
7710 | + toi_cluster_iface); | |
4e97e4e9 | 7711 | + else |
1838f965 | 7712 | + len = scnprintf(buffer, size, |
ad8f4a28 | 7713 | + "- Cluster support is disabled.\n"); |
4e97e4e9 | 7714 | + return len; |
7715 | +} | |
7716 | + | |
7717 | +/* cluster_memory_needed | |
7718 | + * | |
7719 | + * Description: Tell the caller how much memory we need to operate during | |
7720 | + * hibernate/resume. | |
7721 | + * Returns: Unsigned long. Maximum number of bytes of memory required for | |
7722 | + * operation. | |
7723 | + */ | |
7724 | +static int toi_cluster_memory_needed(void) | |
7725 | +{ | |
24613191 | 7726 | + return 0; |
7727 | +} | |
7728 | + | |
4e97e4e9 | 7729 | +static int toi_cluster_storage_needed(void) |
7730 | +{ | |
ad8f4a28 | 7731 | + return 1 + strlen(toi_cluster_iface); |
4e97e4e9 | 7732 | +} |
ad8f4a28 | 7733 | + |
4e97e4e9 | 7734 | +/* toi_cluster_save_config_info |
24613191 | 7735 | + * |
4e97e4e9 | 7736 | + * Description: Save informaton needed when reloading the image at resume time. |
7737 | + * Arguments: Buffer: Pointer to a buffer of size PAGE_SIZE. | |
7738 | + * Returns: Number of bytes used for saving our data. | |
24613191 | 7739 | + */ |
4e97e4e9 | 7740 | +static int toi_cluster_save_config_info(char *buffer) |
7741 | +{ | |
ad8f4a28 AM |
7742 | + strcpy(buffer, toi_cluster_iface); |
7743 | + return strlen(toi_cluster_iface + 1); | |
4e97e4e9 | 7744 | +} |
24613191 | 7745 | + |
4e97e4e9 | 7746 | +/* toi_cluster_load_config_info |
7747 | + * | |
ad8f4a28 | 7748 | + * Description: Reload information needed for declustering the image at |
4e97e4e9 | 7749 | + * resume time. |
7750 | + * Arguments: Buffer: Pointer to the start of the data. | |
7751 | + * Size: Number of bytes that were saved. | |
7752 | + */ | |
7753 | +static void toi_cluster_load_config_info(char *buffer, int size) | |
24613191 | 7754 | +{ |
ad8f4a28 | 7755 | + strncpy(toi_cluster_iface, buffer, size); |
4e97e4e9 | 7756 | + return; |
7757 | +} | |
24613191 | 7758 | + |
ad8f4a28 AM |
7759 | +static void cluster_startup(void) |
7760 | +{ | |
7761 | + int have_image = do_check_can_resume(), i; | |
7762 | + unsigned long start = jiffies, initial_message; | |
7763 | + struct task_struct *p; | |
7764 | + | |
7765 | + initial_message = MSG_IMAGE; | |
7766 | + | |
7767 | + have_image = 1; | |
7768 | + | |
7769 | + for (i = 0; i < num_local_nodes; i++) { | |
7770 | + PRINTK("Starting ktoiclusterd %d.\n", i); | |
7771 | + p = kthread_create(kTOICluster, (void *) initial_message, | |
7772 | + "ktoiclusterd/%d", i); | |
7773 | + if (IS_ERR(p)) { | |
7774 | + printk("Failed to start ktoiclusterd.\n"); | |
7775 | + return; | |
7776 | + } | |
7777 | + | |
7778 | + wake_up_process(p); | |
7779 | + } | |
7780 | + | |
7781 | + /* Wait for delay or someone else sending first message */ | |
7782 | + wait_event(node_array[0].member_events, time_to_continue(0, start, | |
7783 | + MSG_IMAGE)); | |
7784 | + | |
7785 | + others_have_image = peers_in_message(0, MSG_IMAGE | MSG_ACK, 1); | |
7786 | + | |
7787 | + printk(KERN_INFO "Continuing. I %shave an image. Peers with image:" | |
7788 | + " %d.\n", have_image ? "" : "don't ", others_have_image); | |
7789 | + | |
7790 | + if (have_image) { | |
7791 | + int result; | |
7792 | + | |
7793 | + /* Start to resume */ | |
7794 | + printk(KERN_INFO " === Starting to resume === \n"); | |
7795 | + node_array[0].current_message = MSG_IO; | |
7796 | + toi_send_if(MSG_IO, 0); | |
7797 | + | |
7798 | + /* result = do_toi_step(STEP_RESUME_LOAD_PS1); */ | |
7799 | + result = 0; | |
7800 | + | |
7801 | + if (!result) { | |
7802 | + /* | |
7803 | + * Atomic restore - we'll come back in the hibernation | |
7804 | + * path. | |
7805 | + */ | |
7806 | + | |
7807 | + /* result = do_toi_step(STEP_RESUME_DO_RESTORE); */ | |
7808 | + result = 0; | |
7809 | + | |
7810 | + /* do_toi_step(STEP_QUIET_CLEANUP); */ | |
7811 | + } | |
7812 | + | |
7813 | + node_array[0].current_message |= MSG_NACK; | |
7814 | + | |
7815 | + /* For debugging - disable for real life? */ | |
7816 | + wait_event(node_array[0].member_events, | |
7817 | + time_to_continue(0, start, MSG_IO)); | |
7818 | + } | |
7819 | + | |
7820 | + if (others_have_image) { | |
7821 | + /* Wait for them to resume */ | |
7822 | + printk(KERN_INFO "Waiting for other nodes to resume.\n"); | |
7823 | + start = jiffies; | |
7824 | + wait_event(node_array[0].member_events, | |
7825 | + time_to_continue(0, start, MSG_RUNNING)); | |
7826 | + if (peers_not_in_message(0, MSG_RUNNING, 0)) | |
7827 | + printk(KERN_INFO "Timed out while waiting for other " | |
7828 | + "nodes to resume.\n"); | |
7829 | + } | |
7830 | + | |
7831 | + /* Find out whether an image exists here. Send ACK_IMAGE or NACK_IMAGE | |
7832 | + * as appropriate. | |
7833 | + * | |
7834 | + * If we don't have an image: | |
7835 | + * - Wait until someone else says they have one, or conditions are met | |
7836 | + * for continuing to boot (n machines or t seconds). | |
7837 | + * - If anyone has an image, wait for them to resume before continuing | |
7838 | + * to boot. | |
7839 | + * | |
7840 | + * If we have an image: | |
7841 | + * - Wait until conditions are met before continuing to resume (n | |
7842 | + * machines or t seconds). Send RESUME_PREP and freeze processes. | |
7843 | + * NACK_PREP if freezing fails (shouldn't) and follow logic for | |
7844 | + * us having no image above. On success, wait for [N]ACK_PREP from | |
7845 | + * other machines. Read image (including atomic restore) until done. | |
7846 | + * Wait for ACK_READ from others (should never fail). Thaw processes | |
7847 | + * and do post-resume. (The section after the atomic restore is done | |
7848 | + * via the code for hibernating). | |
7849 | + */ | |
7850 | + | |
7851 | + node_array[0].current_message = MSG_RUNNING; | |
7852 | +} | |
7853 | + | |
7854 | +/* toi_cluster_open_iface | |
7855 | + * | |
7856 | + * Description: Prepare to use an interface. | |
7857 | + */ | |
7858 | + | |
7859 | +static int toi_cluster_open_iface(void) | |
7860 | +{ | |
7861 | + struct net_device *dev; | |
7862 | + | |
7863 | + rtnl_lock(); | |
7864 | + | |
7f9d2ee0 | 7865 | + for_each_netdev(&init_net, dev) { |
7866 | + if (/* dev == &init_net.loopback_dev || */ | |
ad8f4a28 AM |
7867 | + strcmp(dev->name, toi_cluster_iface)) |
7868 | + continue; | |
7869 | + | |
7870 | + net_dev = dev; | |
7871 | + break; | |
7872 | + } | |
7873 | + | |
7874 | + rtnl_unlock(); | |
7875 | + | |
7876 | + if (!net_dev) { | |
7877 | + printk(KERN_ERR MYNAME ": Device %s not found.\n", | |
7878 | + toi_cluster_iface); | |
7879 | + return -ENODEV; | |
7880 | + } | |
7881 | + | |
7882 | + dev_add_pack(&toi_cluster_packet_type); | |
7883 | + added_pack = 1; | |
7884 | + | |
7f9d2ee0 | 7885 | + loopback_mode = (net_dev == init_net.loopback_dev); |
ad8f4a28 AM |
7886 | + num_local_nodes = loopback_mode ? 8 : 1; |
7887 | + | |
7888 | + PRINTK("Loopback mode is %s. Number of local nodes is %d.\n", | |
7889 | + loopback_mode ? "on" : "off", num_local_nodes); | |
7890 | + | |
7891 | + cluster_startup(); | |
7892 | + return 0; | |
7893 | +} | |
7894 | + | |
7895 | +/* toi_cluster_close_iface | |
7896 | + * | |
7897 | + * Description: Stop using an interface. | |
7898 | + */ | |
7899 | + | |
7900 | +static int toi_cluster_close_iface(void) | |
7901 | +{ | |
7902 | + kill_clusterd(); | |
7903 | + if (added_pack) { | |
7904 | + dev_remove_pack(&toi_cluster_packet_type); | |
7905 | + added_pack = 0; | |
7906 | + } | |
7907 | + return 0; | |
7908 | +} | |
7909 | + | |
7910 | +static void write_side_effect(void) | |
7911 | +{ | |
7912 | + if (toi_cluster_ops.enabled) { | |
7913 | + toi_cluster_open_iface(); | |
7914 | + set_toi_state(TOI_CLUSTER_MODE); | |
7915 | + } else { | |
7916 | + toi_cluster_close_iface(); | |
7917 | + clear_toi_state(TOI_CLUSTER_MODE); | |
7918 | + } | |
7919 | +} | |
7920 | + | |
7921 | +static void node_write_side_effect(void) | |
7922 | +{ | |
7923 | +} | |
7924 | + | |
7925 | +/* | |
7926 | + * data for our sysfs entries. | |
7927 | + */ | |
7928 | +static struct toi_sysfs_data sysfs_params[] = { | |
1838f965 | 7929 | + SYSFS_STRING("interface", SYSFS_RW, toi_cluster_iface, IFNAMSIZ, 0, |
7930 | + NULL), | |
7931 | + SYSFS_INT("enabled", SYSFS_RW, &toi_cluster_ops.enabled, 0, 1, 0, | |
7932 | + write_side_effect), | |
7933 | + SYSFS_STRING("cluster_name", SYSFS_RW, toi_cluster_key, 32, 0, NULL), | |
7934 | + SYSFS_STRING("pre-hibernate-script", SYSFS_RW, pre_hibernate_script, | |
7935 | + 256, 0, NULL), | |
7936 | + SYSFS_STRING("post-hibernate-script", SYSFS_RW, post_hibernate_script, | |
7937 | + 256, 0, STRING), | |
7938 | + SYSFS_UL("continue_delay", SYSFS_RW, &continue_delay, HZ / 2, 60 * HZ, | |
7939 | + 0) | |
4e97e4e9 | 7940 | +}; |
7941 | + | |
7942 | +/* | |
7943 | + * Ops structure. | |
7944 | + */ | |
7945 | + | |
7946 | +static struct toi_module_ops toi_cluster_ops = { | |
7947 | + .type = FILTER_MODULE, | |
7948 | + .name = "Cluster", | |
7949 | + .directory = "cluster", | |
7950 | + .module = THIS_MODULE, | |
7951 | + .memory_needed = toi_cluster_memory_needed, | |
7952 | + .print_debug_info = toi_cluster_print_debug_stats, | |
7953 | + .save_config_info = toi_cluster_save_config_info, | |
7954 | + .load_config_info = toi_cluster_load_config_info, | |
7955 | + .storage_needed = toi_cluster_storage_needed, | |
ad8f4a28 | 7956 | + |
4e97e4e9 | 7957 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
7958 | + .num_sysfs_entries = sizeof(sysfs_params) / |
7959 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 7960 | +}; |
24613191 | 7961 | + |
4e97e4e9 | 7962 | +/* ---- Registration ---- */ |
24613191 | 7963 | + |
4e97e4e9 | 7964 | +#ifdef MODULE |
4e97e4e9 | 7965 | +#define INIT static __init |
7966 | +#define EXIT static __exit | |
7967 | +#else | |
7968 | +#define INIT | |
7969 | +#define EXIT | |
7970 | +#endif | |
24613191 | 7971 | + |
4e97e4e9 | 7972 | +INIT int toi_cluster_init(void) |
7973 | +{ | |
ad8f4a28 AM |
7974 | + int temp = toi_register_module(&toi_cluster_ops), i; |
7975 | + struct kobject *kobj = toi_cluster_ops.dir_kobj; | |
7976 | + | |
7977 | + for (i = 0; i < MAX_LOCAL_NODES; i++) { | |
7978 | + node_array[i].current_message = 0; | |
7979 | + INIT_LIST_HEAD(&node_array[i].member_list); | |
7980 | + init_waitqueue_head(&node_array[i].member_events); | |
7981 | + spin_lock_init(&node_array[i].member_list_lock); | |
7982 | + spin_lock_init(&node_array[i].receive_lock); | |
7983 | + | |
7984 | + /* Set up sysfs entry */ | |
7f9d2ee0 | 7985 | + node_array[i].sysfs_data.attr.name = toi_kzalloc(8, |
7986 | + sizeof(node_array[i].sysfs_data.attr.name), | |
7987 | + GFP_KERNEL); | |
ad8f4a28 AM |
7988 | + sprintf((char *) node_array[i].sysfs_data.attr.name, "node_%d", |
7989 | + i); | |
7990 | + node_array[i].sysfs_data.attr.mode = SYSFS_RW; | |
7991 | + node_array[i].sysfs_data.type = TOI_SYSFS_DATA_INTEGER; | |
7992 | + node_array[i].sysfs_data.flags = 0; | |
7993 | + node_array[i].sysfs_data.data.integer.variable = | |
7f9d2ee0 | 7994 | + (int *) &node_array[i].current_message; |
ad8f4a28 AM |
7995 | + node_array[i].sysfs_data.data.integer.minimum = 0; |
7996 | + node_array[i].sysfs_data.data.integer.maximum = INT_MAX; | |
7997 | + node_array[i].sysfs_data.write_side_effect = | |
7998 | + node_write_side_effect; | |
7999 | + toi_register_sysfs_file(kobj, &node_array[i].sysfs_data); | |
8000 | + } | |
8001 | + | |
8002 | + toi_cluster_ops.enabled = (strlen(toi_cluster_iface) > 0); | |
24613191 | 8003 | + |
ad8f4a28 AM |
8004 | + if (toi_cluster_ops.enabled) |
8005 | + toi_cluster_open_iface(); | |
8006 | + | |
8007 | + return temp; | |
4e97e4e9 | 8008 | +} |
24613191 | 8009 | + |
4e97e4e9 | 8010 | +EXIT void toi_cluster_exit(void) |
8011 | +{ | |
ad8f4a28 AM |
8012 | + int i; |
8013 | + toi_cluster_close_iface(); | |
8014 | + | |
8015 | + for (i = 0; i < MAX_LOCAL_NODES; i++) | |
8016 | + toi_unregister_sysfs_file(toi_cluster_ops.dir_kobj, | |
8017 | + &node_array[i].sysfs_data); | |
4e97e4e9 | 8018 | + toi_unregister_module(&toi_cluster_ops); |
24613191 | 8019 | +} |
8020 | + | |
ad8f4a28 AM |
8021 | +static int __init toi_cluster_iface_setup(char *iface) |
8022 | +{ | |
8023 | + toi_cluster_ops.enabled = (*iface && | |
8024 | + strcmp(iface, "off")); | |
8025 | + | |
8026 | + if (toi_cluster_ops.enabled) | |
8027 | + strncpy(toi_cluster_iface, iface, strlen(iface)); | |
8028 | +} | |
8029 | + | |
8030 | +__setup("toi_cluster=", toi_cluster_iface_setup); | |
8031 | + | |
4e97e4e9 | 8032 | +#ifdef MODULE |
8033 | +MODULE_LICENSE("GPL"); | |
8034 | +module_init(toi_cluster_init); | |
8035 | +module_exit(toi_cluster_exit); | |
8036 | +MODULE_AUTHOR("Nigel Cunningham"); | |
8037 | +MODULE_DESCRIPTION("Cluster Support for TuxOnIce"); | |
8038 | +#endif | |
8039 | diff --git a/kernel/power/tuxonice_cluster.h b/kernel/power/tuxonice_cluster.h | |
8040 | new file mode 100644 | |
1838f965 | 8041 | index 0000000..b0f8918 |
4e97e4e9 | 8042 | --- /dev/null |
8043 | +++ b/kernel/power/tuxonice_cluster.h | |
ad8f4a28 | 8044 | @@ -0,0 +1,19 @@ |
4e97e4e9 | 8045 | +/* |
8046 | + * kernel/power/tuxonice_cluster.h | |
24613191 | 8047 | + * |
1838f965 | 8048 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 8049 | + * Copyright (C) 2006 Red Hat, inc. |
8050 | + * | |
8051 | + * This file is released under the GPLv2. | |
24613191 | 8052 | + */ |
8053 | + | |
4e97e4e9 | 8054 | +#ifdef CONFIG_TOI_CLUSTER |
8055 | +extern int toi_cluster_init(void); | |
8056 | +extern void toi_cluster_exit(void); | |
ad8f4a28 | 8057 | +extern void toi_initiate_cluster_hibernate(void); |
4e97e4e9 | 8058 | +#else |
8059 | +static inline int toi_cluster_init(void) { return 0; } | |
8060 | +static inline void toi_cluster_exit(void) { } | |
ad8f4a28 | 8061 | +static inline void toi_initiate_cluster_hibernate(void) { } |
4e97e4e9 | 8062 | +#endif |
24613191 | 8063 | + |
4e97e4e9 | 8064 | diff --git a/kernel/power/tuxonice_compress.c b/kernel/power/tuxonice_compress.c |
8065 | new file mode 100644 | |
1838f965 | 8066 | index 0000000..2c934d3 |
4e97e4e9 | 8067 | --- /dev/null |
8068 | +++ b/kernel/power/tuxonice_compress.c | |
1838f965 | 8069 | @@ -0,0 +1,432 @@ |
4e97e4e9 | 8070 | +/* |
8071 | + * kernel/power/compression.c | |
8072 | + * | |
1838f965 | 8073 | + * Copyright (C) 2003-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 8074 | + * |
8075 | + * This file is released under the GPLv2. | |
8076 | + * | |
8077 | + * This file contains data compression routines for TuxOnIce, | |
8078 | + * using cryptoapi. | |
8079 | + */ | |
24613191 | 8080 | + |
4e97e4e9 | 8081 | +#include <linux/module.h> |
8082 | +#include <linux/suspend.h> | |
8083 | +#include <linux/highmem.h> | |
8084 | +#include <linux/vmalloc.h> | |
8085 | +#include <linux/crypto.h> | |
24613191 | 8086 | + |
4e97e4e9 | 8087 | +#include "tuxonice_builtin.h" |
8088 | +#include "tuxonice.h" | |
8089 | +#include "tuxonice_modules.h" | |
8090 | +#include "tuxonice_sysfs.h" | |
8091 | +#include "tuxonice_io.h" | |
8092 | +#include "tuxonice_ui.h" | |
ad8f4a28 | 8093 | +#include "tuxonice_alloc.h" |
24613191 | 8094 | + |
ad8f4a28 | 8095 | +static int toi_expected_compression; |
24613191 | 8096 | + |
4e97e4e9 | 8097 | +static struct toi_module_ops toi_compression_ops; |
8098 | +static struct toi_module_ops *next_driver; | |
24613191 | 8099 | + |
4e97e4e9 | 8100 | +static char toi_compressor_name[32] = "lzf"; |
24613191 | 8101 | + |
4e97e4e9 | 8102 | +static DEFINE_MUTEX(stats_lock); |
24613191 | 8103 | + |
4e97e4e9 | 8104 | +struct cpu_context { |
ad8f4a28 | 8105 | + u8 *page_buffer; |
4e97e4e9 | 8106 | + struct crypto_comp *transform; |
8107 | + unsigned int len; | |
8108 | + char *buffer_start; | |
8109 | +}; | |
24613191 | 8110 | + |
4e97e4e9 | 8111 | +static DEFINE_PER_CPU(struct cpu_context, contexts); |
24613191 | 8112 | + |
4e97e4e9 | 8113 | +static int toi_compress_prepare_result; |
24613191 | 8114 | + |
ad8f4a28 | 8115 | +/* |
4e97e4e9 | 8116 | + * toi_compress_cleanup |
24613191 | 8117 | + * |
4e97e4e9 | 8118 | + * Frees memory allocated for our labours. |
24613191 | 8119 | + */ |
4e97e4e9 | 8120 | +static void toi_compress_cleanup(int toi_or_resume) |
24613191 | 8121 | +{ |
4e97e4e9 | 8122 | + int cpu; |
24613191 | 8123 | + |
4e97e4e9 | 8124 | + if (!toi_or_resume) |
8125 | + return; | |
24613191 | 8126 | + |
4e97e4e9 | 8127 | + for_each_online_cpu(cpu) { |
8128 | + struct cpu_context *this = &per_cpu(contexts, cpu); | |
8129 | + if (this->transform) { | |
8130 | + crypto_free_comp(this->transform); | |
8131 | + this->transform = NULL; | |
8132 | + } | |
24613191 | 8133 | + |
4e97e4e9 | 8134 | + if (this->page_buffer) |
ad8f4a28 | 8135 | + toi_free_page(16, (unsigned long) this->page_buffer); |
24613191 | 8136 | + |
4e97e4e9 | 8137 | + this->page_buffer = NULL; |
24613191 | 8138 | + } |
24613191 | 8139 | +} |
8140 | + | |
ad8f4a28 | 8141 | +/* |
4e97e4e9 | 8142 | + * toi_crypto_prepare |
24613191 | 8143 | + * |
4e97e4e9 | 8144 | + * Prepare to do some work by allocating buffers and transforms. |
24613191 | 8145 | + */ |
4e97e4e9 | 8146 | +static int toi_compress_crypto_prepare(void) |
8147 | +{ | |
8148 | + int cpu; | |
24613191 | 8149 | + |
4e97e4e9 | 8150 | + if (!*toi_compressor_name) { |
ad8f4a28 AM |
8151 | + printk(KERN_INFO "TuxOnIce: Compression enabled but no " |
8152 | + "compressor name set.\n"); | |
4e97e4e9 | 8153 | + return 1; |
24613191 | 8154 | + } |
8155 | + | |
4e97e4e9 | 8156 | + for_each_online_cpu(cpu) { |
8157 | + struct cpu_context *this = &per_cpu(contexts, cpu); | |
8158 | + this->transform = crypto_alloc_comp(toi_compressor_name, 0, 0); | |
8159 | + if (IS_ERR(this->transform)) { | |
ad8f4a28 AM |
8160 | + printk(KERN_INFO "TuxOnIce: Failed to initialise the " |
8161 | + "%s compression transform.\n", | |
4e97e4e9 | 8162 | + toi_compressor_name); |
8163 | + this->transform = NULL; | |
8164 | + return 1; | |
24613191 | 8165 | + } |
24613191 | 8166 | + |
4e97e4e9 | 8167 | + this->page_buffer = |
8168 | + (char *) toi_get_zeroed_page(16, TOI_ATOMIC_GFP); | |
ad8f4a28 | 8169 | + |
4e97e4e9 | 8170 | + if (!this->page_buffer) { |
8171 | + printk(KERN_ERR | |
8172 | + "Failed to allocate a page buffer for TuxOnIce " | |
8173 | + "encryption driver.\n"); | |
8174 | + return -ENOMEM; | |
8175 | + } | |
24613191 | 8176 | + } |
8177 | + | |
4e97e4e9 | 8178 | + return 0; |
8179 | +} | |
24613191 | 8180 | + |
4e97e4e9 | 8181 | +/* |
8182 | + * toi_compress_init | |
8183 | + */ | |
24613191 | 8184 | + |
4e97e4e9 | 8185 | +static int toi_compress_init(int toi_or_resume) |
8186 | +{ | |
8187 | + if (!toi_or_resume) | |
8188 | + return 0; | |
24613191 | 8189 | + |
4e97e4e9 | 8190 | + toi_compress_bytes_in = toi_compress_bytes_out = 0; |
24613191 | 8191 | + |
4e97e4e9 | 8192 | + next_driver = toi_get_next_filter(&toi_compression_ops); |
e8d0ad9d | 8193 | + |
ad8f4a28 | 8194 | + if (!next_driver) |
4e97e4e9 | 8195 | + return -ECHILD; |
24613191 | 8196 | + |
4e97e4e9 | 8197 | + toi_compress_prepare_result = toi_compress_crypto_prepare(); |
24613191 | 8198 | + |
4e97e4e9 | 8199 | + return 0; |
8200 | +} | |
e8d0ad9d | 8201 | + |
4e97e4e9 | 8202 | +/* |
8203 | + * toi_compress_rw_init() | |
8204 | + */ | |
24613191 | 8205 | + |
1838f965 | 8206 | +static int toi_compress_rw_init(int rw, int stream_number) |
4e97e4e9 | 8207 | +{ |
8208 | + if (toi_compress_prepare_result) { | |
8209 | + printk("Failed to initialise compression algorithm.\n"); | |
8210 | + if (rw == READ) | |
8211 | + return -ENODEV; | |
8212 | + else | |
8213 | + toi_compression_ops.enabled = 0; | |
24613191 | 8214 | + } |
8215 | + | |
4e97e4e9 | 8216 | + return 0; |
8217 | +} | |
24613191 | 8218 | + |
ad8f4a28 | 8219 | +/* |
4e97e4e9 | 8220 | + * toi_compress_write_page() |
8221 | + * | |
8222 | + * Compress a page of data, buffering output and passing on filled | |
8223 | + * pages to the next module in the pipeline. | |
ad8f4a28 | 8224 | + * |
4e97e4e9 | 8225 | + * Buffer_page: Pointer to a buffer of size PAGE_SIZE, containing |
8226 | + * data to be compressed. | |
8227 | + * | |
8228 | + * Returns: 0 on success. Otherwise the error is that returned by later | |
8229 | + * modules, -ECHILD if we have a broken pipeline or -EIO if | |
8230 | + * zlib errs. | |
8231 | + */ | |
8232 | +static int toi_compress_write_page(unsigned long index, | |
8233 | + struct page *buffer_page, unsigned int buf_size) | |
8234 | +{ | |
8235 | + int ret, cpu = smp_processor_id(); | |
8236 | + struct cpu_context *ctx = &per_cpu(contexts, cpu); | |
ad8f4a28 | 8237 | + |
4e97e4e9 | 8238 | + if (!ctx->transform) |
8239 | + return next_driver->write_page(index, buffer_page, buf_size); | |
24613191 | 8240 | + |
4e97e4e9 | 8241 | + ctx->buffer_start = kmap(buffer_page); |
24613191 | 8242 | + |
4e97e4e9 | 8243 | + ctx->len = buf_size; |
24613191 | 8244 | + |
4e97e4e9 | 8245 | + ret = crypto_comp_compress(ctx->transform, |
8246 | + ctx->buffer_start, buf_size, | |
8247 | + ctx->page_buffer, &ctx->len); | |
ad8f4a28 | 8248 | + |
4e97e4e9 | 8249 | + kunmap(buffer_page); |
24613191 | 8250 | + |
4e97e4e9 | 8251 | + if (ret) { |
ad8f4a28 | 8252 | + printk(KERN_INFO "Compression failed.\n"); |
4e97e4e9 | 8253 | + goto failure; |
8254 | + } | |
ad8f4a28 | 8255 | + |
4e97e4e9 | 8256 | + mutex_lock(&stats_lock); |
8257 | + toi_compress_bytes_in += buf_size; | |
8258 | + toi_compress_bytes_out += ctx->len; | |
8259 | + mutex_unlock(&stats_lock); | |
24613191 | 8260 | + |
4e97e4e9 | 8261 | + if (ctx->len < buf_size) /* some compression */ |
8262 | + ret = next_driver->write_page(index, | |
8263 | + virt_to_page(ctx->page_buffer), | |
8264 | + ctx->len); | |
8265 | + else | |
8266 | + ret = next_driver->write_page(index, buffer_page, buf_size); | |
24613191 | 8267 | + |
4e97e4e9 | 8268 | +failure: |
8269 | + return ret; | |
24613191 | 8270 | +} |
8271 | + | |
ad8f4a28 | 8272 | +/* |
4e97e4e9 | 8273 | + * toi_compress_read_page() |
8274 | + * @buffer_page: struct page *. Pointer to a buffer of size PAGE_SIZE. | |
24613191 | 8275 | + * |
4e97e4e9 | 8276 | + * Retrieve data from later modules and decompress it until the input buffer |
8277 | + * is filled. | |
8278 | + * Zero if successful. Error condition from me or from downstream on failure. | |
24613191 | 8279 | + */ |
4e97e4e9 | 8280 | +static int toi_compress_read_page(unsigned long *index, |
8281 | + struct page *buffer_page, unsigned int *buf_size) | |
24613191 | 8282 | +{ |
ad8f4a28 | 8283 | + int ret, cpu = smp_processor_id(); |
4e97e4e9 | 8284 | + unsigned int len; |
8285 | + unsigned int outlen = PAGE_SIZE; | |
8286 | + char *buffer_start; | |
8287 | + struct cpu_context *ctx = &per_cpu(contexts, cpu); | |
24613191 | 8288 | + |
4e97e4e9 | 8289 | + if (!ctx->transform) |
8290 | + return next_driver->read_page(index, buffer_page, buf_size); | |
24613191 | 8291 | + |
ad8f4a28 | 8292 | + /* |
4e97e4e9 | 8293 | + * All our reads must be synchronous - we can't decompress |
8294 | + * data that hasn't been read yet. | |
8295 | + */ | |
24613191 | 8296 | + |
4e97e4e9 | 8297 | + *buf_size = PAGE_SIZE; |
24613191 | 8298 | + |
4e97e4e9 | 8299 | + ret = next_driver->read_page(index, buffer_page, &len); |
24613191 | 8300 | + |
4e97e4e9 | 8301 | + /* Error or uncompressed data */ |
8302 | + if (ret || len == PAGE_SIZE) | |
8303 | + return ret; | |
24613191 | 8304 | + |
4e97e4e9 | 8305 | + buffer_start = kmap(buffer_page); |
8306 | + memcpy(ctx->page_buffer, buffer_start, len); | |
8307 | + ret = crypto_comp_decompress( | |
8308 | + ctx->transform, | |
8309 | + ctx->page_buffer, | |
8310 | + len, buffer_start, &outlen); | |
8311 | + if (ret) | |
8312 | + abort_hibernate(TOI_FAILED_IO, | |
8313 | + "Compress_read returned %d.\n", ret); | |
8314 | + else if (outlen != PAGE_SIZE) { | |
8315 | + abort_hibernate(TOI_FAILED_IO, | |
8316 | + "Decompression yielded %d bytes instead of %ld.\n", | |
8317 | + outlen, PAGE_SIZE); | |
1838f965 | 8318 | + printk(KERN_ERR "Decompression yielded %d bytes instead of " |
8319 | + "%ld.\n", outlen, PAGE_SIZE); | |
4e97e4e9 | 8320 | + ret = -EIO; |
8321 | + *buf_size = outlen; | |
24613191 | 8322 | + } |
4e97e4e9 | 8323 | + kunmap(buffer_page); |
8324 | + return ret; | |
8325 | +} | |
24613191 | 8326 | + |
ad8f4a28 | 8327 | +/* |
4e97e4e9 | 8328 | + * toi_compress_print_debug_stats |
8329 | + * @buffer: Pointer to a buffer into which the debug info will be printed. | |
8330 | + * @size: Size of the buffer. | |
8331 | + * | |
8332 | + * Print information to be recorded for debugging purposes into a buffer. | |
8333 | + * Returns: Number of characters written to the buffer. | |
8334 | + */ | |
24613191 | 8335 | + |
4e97e4e9 | 8336 | +static int toi_compress_print_debug_stats(char *buffer, int size) |
8337 | +{ | |
8338 | + unsigned long pages_in = toi_compress_bytes_in >> PAGE_SHIFT, | |
8339 | + pages_out = toi_compress_bytes_out >> PAGE_SHIFT; | |
8340 | + int len; | |
ad8f4a28 | 8341 | + |
4e97e4e9 | 8342 | + /* Output the compression ratio achieved. */ |
8343 | + if (*toi_compressor_name) | |
1838f965 | 8344 | + len = scnprintf(buffer, size, "- Compressor is '%s'.\n", |
4e97e4e9 | 8345 | + toi_compressor_name); |
8346 | + else | |
1838f965 | 8347 | + len = scnprintf(buffer, size, "- Compressor is not set.\n"); |
24613191 | 8348 | + |
4e97e4e9 | 8349 | + if (pages_in) |
1838f965 | 8350 | + len += scnprintf(buffer+len, size - len, |
8351 | + " Compressed %lu bytes into %lu (%ld percent compression).\n", | |
4e97e4e9 | 8352 | + toi_compress_bytes_in, |
8353 | + toi_compress_bytes_out, | |
8354 | + (pages_in - pages_out) * 100 / pages_in); | |
8355 | + return len; | |
24613191 | 8356 | +} |
8357 | + | |
ad8f4a28 | 8358 | +/* |
4e97e4e9 | 8359 | + * toi_compress_compression_memory_needed |
24613191 | 8360 | + * |
4e97e4e9 | 8361 | + * Tell the caller how much memory we need to operate during hibernate/resume. |
8362 | + * Returns: Unsigned long. Maximum number of bytes of memory required for | |
8363 | + * operation. | |
24613191 | 8364 | + */ |
4e97e4e9 | 8365 | +static int toi_compress_memory_needed(void) |
24613191 | 8366 | +{ |
4e97e4e9 | 8367 | + return 2 * PAGE_SIZE; |
8368 | +} | |
24613191 | 8369 | + |
4e97e4e9 | 8370 | +static int toi_compress_storage_needed(void) |
8371 | +{ | |
8372 | + return 4 * sizeof(unsigned long) + strlen(toi_compressor_name) + 1; | |
24613191 | 8373 | +} |
8374 | + | |
ad8f4a28 | 8375 | +/* |
4e97e4e9 | 8376 | + * toi_compress_save_config_info |
8377 | + * @buffer: Pointer to a buffer of size PAGE_SIZE. | |
8378 | + * | |
8379 | + * Save informaton needed when reloading the image at resume time. | |
8380 | + * Returns: Number of bytes used for saving our data. | |
24613191 | 8381 | + */ |
4e97e4e9 | 8382 | +static int toi_compress_save_config_info(char *buffer) |
24613191 | 8383 | +{ |
4e97e4e9 | 8384 | + int namelen = strlen(toi_compressor_name) + 1; |
8385 | + int total_len; | |
ad8f4a28 | 8386 | + |
4e97e4e9 | 8387 | + *((unsigned long *) buffer) = toi_compress_bytes_in; |
8388 | + *((unsigned long *) (buffer + 1 * sizeof(unsigned long))) = | |
8389 | + toi_compress_bytes_out; | |
8390 | + *((unsigned long *) (buffer + 2 * sizeof(unsigned long))) = | |
8391 | + toi_expected_compression; | |
8392 | + *((unsigned long *) (buffer + 3 * sizeof(unsigned long))) = namelen; | |
ad8f4a28 | 8393 | + strncpy(buffer + 4 * sizeof(unsigned long), toi_compressor_name, |
4e97e4e9 | 8394 | + namelen); |
8395 | + total_len = 4 * sizeof(unsigned long) + namelen; | |
8396 | + return total_len; | |
24613191 | 8397 | +} |
8398 | + | |
4e97e4e9 | 8399 | +/* toi_compress_load_config_info |
8400 | + * @buffer: Pointer to the start of the data. | |
8401 | + * @size: Number of bytes that were saved. | |
8402 | + * | |
8403 | + * Description: Reload information needed for decompressing the image at | |
8404 | + * resume time. | |
24613191 | 8405 | + */ |
4e97e4e9 | 8406 | +static void toi_compress_load_config_info(char *buffer, int size) |
24613191 | 8407 | +{ |
4e97e4e9 | 8408 | + int namelen; |
ad8f4a28 | 8409 | + |
4e97e4e9 | 8410 | + toi_compress_bytes_in = *((unsigned long *) buffer); |
ad8f4a28 AM |
8411 | + toi_compress_bytes_out = *((unsigned long *) (buffer + 1 * |
8412 | + sizeof(unsigned long))); | |
4e97e4e9 | 8413 | + toi_expected_compression = *((unsigned long *) (buffer + 2 * |
8414 | + sizeof(unsigned long))); | |
8415 | + namelen = *((unsigned long *) (buffer + 3 * sizeof(unsigned long))); | |
f3e0dcc9 PS |
8416 | + if (strncmp(toi_compressor_name, buffer + 4 * sizeof(unsigned long), |
8417 | + namelen)) { | |
8418 | + toi_compress_cleanup(1); | |
8419 | + strncpy(toi_compressor_name, buffer + 4 * sizeof(unsigned long), | |
4e97e4e9 | 8420 | + namelen); |
f3e0dcc9 PS |
8421 | + toi_compress_crypto_prepare(); |
8422 | + } | |
4e97e4e9 | 8423 | + return; |
8424 | +} | |
24613191 | 8425 | + |
ad8f4a28 | 8426 | +/* |
4e97e4e9 | 8427 | + * toi_expected_compression_ratio |
ad8f4a28 | 8428 | + * |
4e97e4e9 | 8429 | + * Description: Returns the expected ratio between data passed into this module |
8430 | + * and the amount of data output when writing. | |
8431 | + * Returns: 100 if the module is disabled. Otherwise the value set by the | |
8432 | + * user via our sysfs entry. | |
8433 | + */ | |
24613191 | 8434 | + |
4e97e4e9 | 8435 | +static int toi_compress_expected_ratio(void) |
8436 | +{ | |
8437 | + if (!toi_compression_ops.enabled) | |
8438 | + return 100; | |
8439 | + else | |
8440 | + return 100 - toi_expected_compression; | |
24613191 | 8441 | +} |
8442 | + | |
24613191 | 8443 | +/* |
4e97e4e9 | 8444 | + * data for our sysfs entries. |
24613191 | 8445 | + */ |
4e97e4e9 | 8446 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 8447 | + SYSFS_INT("expected_compression", SYSFS_RW, &toi_expected_compression, |
8448 | + 0, 99, 0, NULL), | |
8449 | + SYSFS_INT("enabled", SYSFS_RW, &toi_compression_ops.enabled, 0, 1, 0, | |
8450 | + NULL), | |
8451 | + SYSFS_STRING("algorithm", SYSFS_RW, toi_compressor_name, 31, 0, NULL), | |
24613191 | 8452 | +}; |
8453 | + | |
4e97e4e9 | 8454 | +/* |
8455 | + * Ops structure. | |
8456 | + */ | |
8457 | +static struct toi_module_ops toi_compression_ops = { | |
8458 | + .type = FILTER_MODULE, | |
8459 | + .name = "compression", | |
8460 | + .directory = "compression", | |
8461 | + .module = THIS_MODULE, | |
8462 | + .initialise = toi_compress_init, | |
8463 | + .cleanup = toi_compress_cleanup, | |
8464 | + .memory_needed = toi_compress_memory_needed, | |
8465 | + .print_debug_info = toi_compress_print_debug_stats, | |
8466 | + .save_config_info = toi_compress_save_config_info, | |
8467 | + .load_config_info = toi_compress_load_config_info, | |
8468 | + .storage_needed = toi_compress_storage_needed, | |
8469 | + .expected_compression = toi_compress_expected_ratio, | |
ad8f4a28 | 8470 | + |
4e97e4e9 | 8471 | + .rw_init = toi_compress_rw_init, |
24613191 | 8472 | + |
4e97e4e9 | 8473 | + .write_page = toi_compress_write_page, |
8474 | + .read_page = toi_compress_read_page, | |
e8d0ad9d | 8475 | + |
4e97e4e9 | 8476 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
8477 | + .num_sysfs_entries = sizeof(sysfs_params) / |
8478 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 8479 | +}; |
e8d0ad9d | 8480 | + |
4e97e4e9 | 8481 | +/* ---- Registration ---- */ |
24613191 | 8482 | + |
4e97e4e9 | 8483 | +static __init int toi_compress_load(void) |
8484 | +{ | |
8485 | + return toi_register_module(&toi_compression_ops); | |
8486 | +} | |
8487 | + | |
8488 | +#ifdef MODULE | |
8489 | +static __exit void toi_compress_unload(void) | |
8490 | +{ | |
8491 | + toi_unregister_module(&toi_compression_ops); | |
8492 | +} | |
8493 | + | |
8494 | +module_init(toi_compress_load); | |
8495 | +module_exit(toi_compress_unload); | |
8496 | +MODULE_LICENSE("GPL"); | |
8497 | +MODULE_AUTHOR("Nigel Cunningham"); | |
8498 | +MODULE_DESCRIPTION("Compression Support for TuxOnIce"); | |
8499 | +#else | |
8500 | +late_initcall(toi_compress_load); | |
8501 | +#endif | |
8502 | diff --git a/kernel/power/tuxonice_extent.c b/kernel/power/tuxonice_extent.c | |
8503 | new file mode 100644 | |
1838f965 | 8504 | index 0000000..3abf881 |
4e97e4e9 | 8505 | --- /dev/null |
8506 | +++ b/kernel/power/tuxonice_extent.c | |
1838f965 | 8507 | @@ -0,0 +1,299 @@ |
ad8f4a28 | 8508 | +/* |
4e97e4e9 | 8509 | + * kernel/power/tuxonice_extent.c |
ad8f4a28 | 8510 | + * |
1838f965 | 8511 | + * Copyright (C) 2003-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 8512 | + * |
4e97e4e9 | 8513 | + * Distributed under GPLv2. |
ad8f4a28 | 8514 | + * |
1838f965 | 8515 | + * These functions encapsulate the manipulation of storage metadata. |
24613191 | 8516 | + */ |
8517 | + | |
24613191 | 8518 | +#include <linux/module.h> |
4e97e4e9 | 8519 | +#include <linux/suspend.h> |
8520 | +#include "tuxonice_modules.h" | |
8521 | +#include "tuxonice_extent.h" | |
ad8f4a28 | 8522 | +#include "tuxonice_alloc.h" |
4e97e4e9 | 8523 | +#include "tuxonice_ui.h" |
8524 | +#include "tuxonice.h" | |
24613191 | 8525 | + |
4e97e4e9 | 8526 | +/* toi_get_extent |
24613191 | 8527 | + * |
4e97e4e9 | 8528 | + * Returns a free extent. May fail, returning NULL instead. |
24613191 | 8529 | + */ |
f3e0dcc9 | 8530 | +static struct hibernate_extent *toi_get_extent(void) |
24613191 | 8531 | +{ |
f3e0dcc9 PS |
8532 | + return (struct hibernate_extent *) toi_kzalloc(2, |
8533 | + sizeof(struct hibernate_extent), TOI_ATOMIC_GFP); | |
24613191 | 8534 | +} |
8535 | + | |
4e97e4e9 | 8536 | +/* toi_put_extent_chain. |
24613191 | 8537 | + * |
4e97e4e9 | 8538 | + * Frees a whole chain of extents. |
24613191 | 8539 | + */ |
f3e0dcc9 | 8540 | +void toi_put_extent_chain(struct hibernate_extent_chain *chain) |
24613191 | 8541 | +{ |
f3e0dcc9 | 8542 | + struct hibernate_extent *this; |
24613191 | 8543 | + |
4e97e4e9 | 8544 | + this = chain->first; |
24613191 | 8545 | + |
ad8f4a28 | 8546 | + while (this) { |
f3e0dcc9 | 8547 | + struct hibernate_extent *next = this->next; |
ad8f4a28 | 8548 | + toi_kfree(2, this); |
4e97e4e9 | 8549 | + chain->num_extents--; |
8550 | + this = next; | |
8551 | + } | |
ad8f4a28 | 8552 | + |
f3e0dcc9 PS |
8553 | + chain->first = NULL; |
8554 | + chain->last_touched = NULL; | |
4e97e4e9 | 8555 | + chain->size = 0; |
24613191 | 8556 | +} |
1838f965 | 8557 | +EXPORT_SYMBOL_GPL(toi_put_extent_chain); |
24613191 | 8558 | + |
ad8f4a28 | 8559 | +/* |
4e97e4e9 | 8560 | + * toi_add_to_extent_chain |
24613191 | 8561 | + * |
4e97e4e9 | 8562 | + * Add an extent to an existing chain. |
24613191 | 8563 | + */ |
f3e0dcc9 PS |
8564 | +int toi_add_to_extent_chain(struct hibernate_extent_chain *chain, |
8565 | + unsigned long start, unsigned long end) | |
24613191 | 8566 | +{ |
f3e0dcc9 | 8567 | + struct hibernate_extent *new_ext = NULL, *cur_ext = NULL; |
24613191 | 8568 | + |
4e97e4e9 | 8569 | + /* Find the right place in the chain */ |
f3e0dcc9 PS |
8570 | + if (chain->last_touched && chain->last_touched->start < start) |
8571 | + cur_ext = chain->last_touched; | |
8572 | + else if (chain->first && chain->first->start < start) | |
8573 | + cur_ext = chain->first; | |
8574 | + | |
8575 | + if (cur_ext) { | |
8576 | + while (cur_ext->next && cur_ext->next->start < start) | |
8577 | + cur_ext = cur_ext->next; | |
8578 | + | |
8579 | + if (cur_ext->end == (start - 1)) { | |
8580 | + struct hibernate_extent *next_ext = cur_ext->next; | |
8581 | + cur_ext->end = end; | |
8582 | + | |
8583 | + /* Merge with the following one? */ | |
8584 | + if (next_ext && cur_ext->end + 1 == next_ext->start) { | |
8585 | + cur_ext->end = next_ext->end; | |
8586 | + cur_ext->next = next_ext->next; | |
8587 | + toi_kfree(2, next_ext); | |
8588 | + chain->num_extents--; | |
8589 | + } | |
4e97e4e9 | 8590 | + |
f3e0dcc9 PS |
8591 | + chain->last_touched = cur_ext; |
8592 | + chain->size += (end - start + 1); | |
4e97e4e9 | 8593 | + |
f3e0dcc9 PS |
8594 | + return 0; |
8595 | + } | |
24613191 | 8596 | + } |
8597 | + | |
f3e0dcc9 PS |
8598 | + new_ext = toi_get_extent(); |
8599 | + if (!new_ext) { | |
ad8f4a28 AM |
8600 | + printk(KERN_INFO "Error unable to append a new extent to the " |
8601 | + "chain.\n"); | |
7f9d2ee0 | 8602 | + return -ENOMEM; |
4e97e4e9 | 8603 | + } |
24613191 | 8604 | + |
4e97e4e9 | 8605 | + chain->num_extents++; |
f3e0dcc9 PS |
8606 | + chain->size += (end - start + 1); |
8607 | + new_ext->start = start; | |
8608 | + new_ext->end = end; | |
24613191 | 8609 | + |
f3e0dcc9 | 8610 | + chain->last_touched = new_ext; |
4e97e4e9 | 8611 | + |
f3e0dcc9 PS |
8612 | + if (cur_ext) { |
8613 | + new_ext->next = cur_ext->next; | |
8614 | + cur_ext->next = new_ext; | |
4e97e4e9 | 8615 | + } else { |
8616 | + if (chain->first) | |
f3e0dcc9 PS |
8617 | + new_ext->next = chain->first; |
8618 | + chain->first = new_ext; | |
24613191 | 8619 | + } |
8620 | + | |
4e97e4e9 | 8621 | + return 0; |
24613191 | 8622 | +} |
1838f965 | 8623 | +EXPORT_SYMBOL_GPL(toi_add_to_extent_chain); |
24613191 | 8624 | + |
4e97e4e9 | 8625 | +/* toi_serialise_extent_chain |
8626 | + * | |
8627 | + * Write a chain in the image. | |
24613191 | 8628 | + */ |
4e97e4e9 | 8629 | +int toi_serialise_extent_chain(struct toi_module_ops *owner, |
f3e0dcc9 | 8630 | + struct hibernate_extent_chain *chain) |
24613191 | 8631 | +{ |
f3e0dcc9 | 8632 | + struct hibernate_extent *this; |
4e97e4e9 | 8633 | + int ret, i = 0; |
ad8f4a28 AM |
8634 | + |
8635 | + ret = toiActiveAllocator->rw_header_chunk(WRITE, owner, (char *) chain, | |
8636 | + 2 * sizeof(int)); | |
8637 | + if (ret) | |
4e97e4e9 | 8638 | + return ret; |
24613191 | 8639 | + |
4e97e4e9 | 8640 | + this = chain->first; |
8641 | + while (this) { | |
ad8f4a28 AM |
8642 | + ret = toiActiveAllocator->rw_header_chunk(WRITE, owner, |
8643 | + (char *) this, 2 * sizeof(unsigned long)); | |
8644 | + if (ret) | |
4e97e4e9 | 8645 | + return ret; |
8646 | + this = this->next; | |
8647 | + i++; | |
24613191 | 8648 | + } |
8649 | + | |
4e97e4e9 | 8650 | + if (i != chain->num_extents) { |
ad8f4a28 AM |
8651 | + printk(KERN_EMERG "Saved %d extents but chain metadata says " |
8652 | + "there should be %d.\n", i, chain->num_extents); | |
4e97e4e9 | 8653 | + return 1; |
8654 | + } | |
24613191 | 8655 | + |
4e97e4e9 | 8656 | + return ret; |
24613191 | 8657 | +} |
1838f965 | 8658 | +EXPORT_SYMBOL_GPL(toi_serialise_extent_chain); |
24613191 | 8659 | + |
4e97e4e9 | 8660 | +/* toi_load_extent_chain |
24613191 | 8661 | + * |
4e97e4e9 | 8662 | + * Read back a chain saved in the image. |
24613191 | 8663 | + */ |
f3e0dcc9 | 8664 | +int toi_load_extent_chain(struct hibernate_extent_chain *chain) |
24613191 | 8665 | +{ |
f3e0dcc9 | 8666 | + struct hibernate_extent *this, *last = NULL; |
4e97e4e9 | 8667 | + int i, ret; |
24613191 | 8668 | + |
7f9d2ee0 | 8669 | + ret = toiActiveAllocator->rw_header_chunk_noreadahead(READ, NULL, |
8670 | + (char *) chain, 2 * sizeof(int)); | |
ad8f4a28 | 8671 | + if (ret) { |
4e97e4e9 | 8672 | + printk("Failed to read size of extent chain.\n"); |
8673 | + return 1; | |
24613191 | 8674 | + } |
8675 | + | |
4e97e4e9 | 8676 | + for (i = 0; i < chain->num_extents; i++) { |
f3e0dcc9 PS |
8677 | + this = toi_kzalloc(3, sizeof(struct hibernate_extent), |
8678 | + TOI_ATOMIC_GFP); | |
4e97e4e9 | 8679 | + if (!this) { |
ad8f4a28 | 8680 | + printk(KERN_INFO "Failed to allocate a new extent.\n"); |
4e97e4e9 | 8681 | + return -ENOMEM; |
8682 | + } | |
8683 | + this->next = NULL; | |
7f9d2ee0 | 8684 | + ret = toiActiveAllocator->rw_header_chunk_noreadahead(READ, |
8685 | + NULL, (char *) this, 2 * sizeof(unsigned long)); | |
ad8f4a28 AM |
8686 | + if (ret) { |
8687 | + printk(KERN_INFO "Failed to an extent.\n"); | |
4e97e4e9 | 8688 | + return 1; |
8689 | + } | |
8690 | + if (last) | |
8691 | + last->next = this; | |
8692 | + else | |
8693 | + chain->first = this; | |
8694 | + last = this; | |
24613191 | 8695 | + } |
4e97e4e9 | 8696 | + return 0; |
8697 | +} | |
1838f965 | 8698 | +EXPORT_SYMBOL_GPL(toi_load_extent_chain); |
24613191 | 8699 | + |
4e97e4e9 | 8700 | +/* toi_extent_state_next |
8701 | + * | |
8702 | + * Given a state, progress to the next valid entry. We may begin in an | |
8703 | + * invalid state, as we do when invoked after extent_state_goto_start below. | |
8704 | + * | |
8705 | + * When using compression and expected_compression > 0, we let the image size | |
8706 | + * be larger than storage, so we can validly run out of data to return. | |
8707 | + */ | |
1838f965 | 8708 | +unsigned long toi_extent_state_next(struct toi_extent_iterate_state *state) |
4e97e4e9 | 8709 | +{ |
8710 | + if (state->current_chain == state->num_chains) | |
8711 | + return 0; | |
24613191 | 8712 | + |
4e97e4e9 | 8713 | + if (state->current_extent) { |
f3e0dcc9 | 8714 | + if (state->current_offset == state->current_extent->end) { |
4e97e4e9 | 8715 | + if (state->current_extent->next) { |
ad8f4a28 AM |
8716 | + state->current_extent = |
8717 | + state->current_extent->next; | |
8718 | + state->current_offset = | |
f3e0dcc9 | 8719 | + state->current_extent->start; |
4e97e4e9 | 8720 | + } else { |
8721 | + state->current_extent = NULL; | |
8722 | + state->current_offset = 0; | |
73c609d5 | 8723 | + } |
73c609d5 | 8724 | + } else |
4e97e4e9 | 8725 | + state->current_offset++; |
24613191 | 8726 | + } |
73c609d5 | 8727 | + |
ad8f4a28 | 8728 | + while (!state->current_extent) { |
4e97e4e9 | 8729 | + int chain_num = ++(state->current_chain); |
24613191 | 8730 | + |
4e97e4e9 | 8731 | + if (chain_num == state->num_chains) |
8732 | + return 0; | |
24613191 | 8733 | + |
4e97e4e9 | 8734 | + state->current_extent = (state->chains + chain_num)->first; |
24613191 | 8735 | + |
4e97e4e9 | 8736 | + if (!state->current_extent) |
8737 | + continue; | |
24613191 | 8738 | + |
f3e0dcc9 | 8739 | + state->current_offset = state->current_extent->start; |
24613191 | 8740 | + } |
4e97e4e9 | 8741 | + |
8742 | + return state->current_offset; | |
24613191 | 8743 | +} |
1838f965 | 8744 | +EXPORT_SYMBOL_GPL(toi_extent_state_next); |
24613191 | 8745 | + |
4e97e4e9 | 8746 | +/* toi_extent_state_goto_start |
24613191 | 8747 | + * |
4e97e4e9 | 8748 | + * Find the first valid value in a group of chains. |
24613191 | 8749 | + */ |
1838f965 | 8750 | +void toi_extent_state_goto_start(struct toi_extent_iterate_state *state) |
24613191 | 8751 | +{ |
4e97e4e9 | 8752 | + state->current_chain = -1; |
8753 | + state->current_extent = NULL; | |
8754 | + state->current_offset = 0; | |
24613191 | 8755 | +} |
1838f965 | 8756 | +EXPORT_SYMBOL_GPL(toi_extent_state_goto_start); |
24613191 | 8757 | + |
4e97e4e9 | 8758 | +/* toi_extent_start_save |
24613191 | 8759 | + * |
f3e0dcc9 | 8760 | + * Given a state and a struct hibernate_extent_state_store, save the current |
4e97e4e9 | 8761 | + * position in a format that can be used with relocated chains (at |
8762 | + * resume time). | |
24613191 | 8763 | + */ |
1838f965 | 8764 | +void toi_extent_state_save(struct toi_extent_iterate_state *state, |
f3e0dcc9 | 8765 | + struct hibernate_extent_iterate_saved_state *saved_state) |
24613191 | 8766 | +{ |
f3e0dcc9 | 8767 | + struct hibernate_extent *extent; |
24613191 | 8768 | + |
4e97e4e9 | 8769 | + saved_state->chain_num = state->current_chain; |
8770 | + saved_state->extent_num = 0; | |
8771 | + saved_state->offset = state->current_offset; | |
24613191 | 8772 | + |
4e97e4e9 | 8773 | + if (saved_state->chain_num == -1) |
8774 | + return; | |
ad8f4a28 | 8775 | + |
4e97e4e9 | 8776 | + extent = (state->chains + state->current_chain)->first; |
8777 | + | |
8778 | + while (extent != state->current_extent) { | |
8779 | + saved_state->extent_num++; | |
8780 | + extent = extent->next; | |
24613191 | 8781 | + } |
8782 | +} | |
1838f965 | 8783 | +EXPORT_SYMBOL_GPL(toi_extent_state_save); |
24613191 | 8784 | + |
4e97e4e9 | 8785 | +/* toi_extent_start_restore |
24613191 | 8786 | + * |
4e97e4e9 | 8787 | + * Restore the position saved by extent_state_save. |
24613191 | 8788 | + */ |
1838f965 | 8789 | +void toi_extent_state_restore(struct toi_extent_iterate_state *state, |
f3e0dcc9 | 8790 | + struct hibernate_extent_iterate_saved_state *saved_state) |
24613191 | 8791 | +{ |
4e97e4e9 | 8792 | + int posn = saved_state->extent_num; |
24613191 | 8793 | + |
4e97e4e9 | 8794 | + if (saved_state->chain_num == -1) { |
8795 | + toi_extent_state_goto_start(state); | |
8796 | + return; | |
24613191 | 8797 | + } |
8798 | + | |
4e97e4e9 | 8799 | + state->current_chain = saved_state->chain_num; |
8800 | + state->current_extent = (state->chains + state->current_chain)->first; | |
8801 | + state->current_offset = saved_state->offset; | |
24613191 | 8802 | + |
4e97e4e9 | 8803 | + while (posn--) |
8804 | + state->current_extent = state->current_extent->next; | |
24613191 | 8805 | +} |
4e97e4e9 | 8806 | +EXPORT_SYMBOL_GPL(toi_extent_state_restore); |
4e97e4e9 | 8807 | diff --git a/kernel/power/tuxonice_extent.h b/kernel/power/tuxonice_extent.h |
8808 | new file mode 100644 | |
1838f965 | 8809 | index 0000000..22ffb9b |
4e97e4e9 | 8810 | --- /dev/null |
8811 | +++ b/kernel/power/tuxonice_extent.h | |
f3e0dcc9 | 8812 | @@ -0,0 +1,72 @@ |
24613191 | 8813 | +/* |
4e97e4e9 | 8814 | + * kernel/power/tuxonice_extent.h |
24613191 | 8815 | + * |
1838f965 | 8816 | + * Copyright (C) 2003-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 8817 | + * |
8818 | + * This file is released under the GPLv2. | |
8819 | + * | |
4e97e4e9 | 8820 | + * It contains declarations related to extents. Extents are |
8821 | + * TuxOnIce's method of storing some of the metadata for the image. | |
8822 | + * See tuxonice_extent.c for more info. | |
24613191 | 8823 | + * |
8824 | + */ | |
8825 | + | |
4e97e4e9 | 8826 | +#include "tuxonice_modules.h" |
24613191 | 8827 | + |
4e97e4e9 | 8828 | +#ifndef EXTENT_H |
8829 | +#define EXTENT_H | |
24613191 | 8830 | + |
f3e0dcc9 PS |
8831 | +struct hibernate_extent { |
8832 | + unsigned long start, end; | |
8833 | + struct hibernate_extent *next; | |
24613191 | 8834 | +}; |
8835 | + | |
f3e0dcc9 | 8836 | +struct hibernate_extent_chain { |
4e97e4e9 | 8837 | + int size; /* size of the chain ie sum (max-min+1) */ |
8838 | + int num_extents; | |
f3e0dcc9 | 8839 | + struct hibernate_extent *first, *last_touched; |
24613191 | 8840 | +}; |
8841 | + | |
1838f965 | 8842 | +struct toi_extent_iterate_state { |
f3e0dcc9 | 8843 | + struct hibernate_extent_chain *chains; |
4e97e4e9 | 8844 | + int num_chains; |
8845 | + int current_chain; | |
f3e0dcc9 | 8846 | + struct hibernate_extent *current_extent; |
4e97e4e9 | 8847 | + unsigned long current_offset; |
24613191 | 8848 | +}; |
8849 | + | |
f3e0dcc9 | 8850 | +struct hibernate_extent_iterate_saved_state { |
4e97e4e9 | 8851 | + int chain_num; |
8852 | + int extent_num; | |
8853 | + unsigned long offset; | |
8854 | +}; | |
24613191 | 8855 | + |
ad8f4a28 AM |
8856 | +#define toi_extent_state_eof(state) \ |
8857 | + ((state)->num_chains == (state)->current_chain) | |
24613191 | 8858 | + |
4e97e4e9 | 8859 | +/* Simplify iterating through all the values in an extent chain */ |
8860 | +#define toi_extent_for_each(extent_chain, extentpointer, value) \ | |
8861 | +if ((extent_chain)->first) \ | |
8862 | + for ((extentpointer) = (extent_chain)->first, (value) = \ | |
f3e0dcc9 | 8863 | + (extentpointer)->start; \ |
4e97e4e9 | 8864 | + ((extentpointer) && ((extentpointer)->next || (value) <= \ |
f3e0dcc9 PS |
8865 | + (extentpointer)->end)); \ |
8866 | + (((value) == (extentpointer)->end) ? \ | |
4e97e4e9 | 8867 | + ((extentpointer) = (extentpointer)->next, (value) = \ |
f3e0dcc9 | 8868 | + ((extentpointer) ? (extentpointer)->start : 0)) : \ |
4e97e4e9 | 8869 | + (value)++)) |
24613191 | 8870 | + |
f3e0dcc9 PS |
8871 | +void toi_put_extent_chain(struct hibernate_extent_chain *chain); |
8872 | +int toi_add_to_extent_chain(struct hibernate_extent_chain *chain, | |
8873 | + unsigned long start, unsigned long end); | |
4e97e4e9 | 8874 | +int toi_serialise_extent_chain(struct toi_module_ops *owner, |
f3e0dcc9 PS |
8875 | + struct hibernate_extent_chain *chain); |
8876 | +int toi_load_extent_chain(struct hibernate_extent_chain *chain); | |
8877 | + | |
1838f965 | 8878 | +void toi_extent_state_save(struct toi_extent_iterate_state *state, |
f3e0dcc9 | 8879 | + struct hibernate_extent_iterate_saved_state *saved_state); |
1838f965 | 8880 | +void toi_extent_state_restore(struct toi_extent_iterate_state *state, |
f3e0dcc9 | 8881 | + struct hibernate_extent_iterate_saved_state *saved_state); |
1838f965 | 8882 | +void toi_extent_state_goto_start(struct toi_extent_iterate_state *state); |
8883 | +unsigned long toi_extent_state_next(struct toi_extent_iterate_state *state); | |
4e97e4e9 | 8884 | +#endif |
8885 | diff --git a/kernel/power/tuxonice_file.c b/kernel/power/tuxonice_file.c | |
8886 | new file mode 100644 | |
1838f965 | 8887 | index 0000000..0bb3e2e |
4e97e4e9 | 8888 | --- /dev/null |
8889 | +++ b/kernel/power/tuxonice_file.c | |
1838f965 | 8890 | @@ -0,0 +1,1122 @@ |
4e97e4e9 | 8891 | +/* |
8892 | + * kernel/power/tuxonice_file.c | |
8893 | + * | |
1838f965 | 8894 | + * Copyright (C) 2005-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 8895 | + * |
8896 | + * Distributed under GPLv2. | |
ad8f4a28 | 8897 | + * |
4e97e4e9 | 8898 | + * This file encapsulates functions for usage of a simple file as a |
8899 | + * backing store. It is based upon the swapallocator, and shares the | |
8900 | + * same basic working. Here, though, we have nothing to do with | |
8901 | + * swapspace, and only one device to worry about. | |
8902 | + * | |
8903 | + * The user can just | |
8904 | + * | |
8905 | + * echo TuxOnIce > /path/to/my_file | |
8906 | + * | |
8907 | + * dd if=/dev/zero bs=1M count=<file_size_desired> >> /path/to/my_file | |
8908 | + * | |
8909 | + * and | |
8910 | + * | |
8911 | + * echo /path/to/my_file > /sys/power/tuxonice/file/target | |
8912 | + * | |
8913 | + * then put what they find in /sys/power/tuxonice/resume | |
8914 | + * as their resume= parameter in lilo.conf (and rerun lilo if using it). | |
8915 | + * | |
8916 | + * Having done this, they're ready to hibernate and resume. | |
8917 | + * | |
8918 | + * TODO: | |
8919 | + * - File resizing. | |
8920 | + */ | |
24613191 | 8921 | + |
4e97e4e9 | 8922 | +#include <linux/suspend.h> |
8923 | +#include <linux/module.h> | |
8924 | +#include <linux/blkdev.h> | |
8925 | +#include <linux/file.h> | |
8926 | +#include <linux/stat.h> | |
8927 | +#include <linux/mount.h> | |
8928 | +#include <linux/statfs.h> | |
8929 | +#include <linux/syscalls.h> | |
8930 | +#include <linux/namei.h> | |
8931 | +#include <linux/fs.h> | |
8932 | +#include <linux/root_dev.h> | |
24613191 | 8933 | + |
4e97e4e9 | 8934 | +#include "tuxonice.h" |
8935 | +#include "tuxonice_sysfs.h" | |
8936 | +#include "tuxonice_modules.h" | |
8937 | +#include "tuxonice_ui.h" | |
8938 | +#include "tuxonice_extent.h" | |
8939 | +#include "tuxonice_io.h" | |
8940 | +#include "tuxonice_storage.h" | |
8941 | +#include "tuxonice_block_io.h" | |
ad8f4a28 | 8942 | +#include "tuxonice_alloc.h" |
1838f965 | 8943 | +#include "tuxonice_builtin.h" |
24613191 | 8944 | + |
4e97e4e9 | 8945 | +static struct toi_module_ops toi_fileops; |
24613191 | 8946 | + |
4e97e4e9 | 8947 | +/* Details of our target. */ |
24613191 | 8948 | + |
1838f965 | 8949 | +static char toi_file_target[256]; |
4e97e4e9 | 8950 | +static struct inode *target_inode; |
8951 | +static struct file *target_file; | |
8952 | +static struct block_device *toi_file_target_bdev; | |
8953 | +static dev_t resume_file_dev_t; | |
ad8f4a28 AM |
8954 | +static int used_devt; |
8955 | +static int setting_toi_file_target; | |
8956 | +static sector_t target_firstblock, target_header_start; | |
8957 | +static int target_storage_available; | |
8958 | +static int target_claim; | |
24613191 | 8959 | + |
7f9d2ee0 | 8960 | +/* Old signatures */ |
4e97e4e9 | 8961 | +static char HaveImage[] = "HaveImage\n"; |
8962 | +static char NoImage[] = "TuxOnIce\n"; | |
8963 | +#define sig_size (sizeof(HaveImage) + 1) | |
8964 | + | |
8965 | +struct toi_file_header { | |
8966 | + char sig[sig_size]; | |
8967 | + int resumed_before; | |
8968 | + unsigned long first_header_block; | |
7f9d2ee0 | 8969 | + int have_image; |
24613191 | 8970 | +}; |
8971 | + | |
4e97e4e9 | 8972 | +/* Header Page Information */ |
7f9d2ee0 | 8973 | +static int header_pages_reserved; |
4e97e4e9 | 8974 | + |
8975 | +/* Main Storage Pages */ | |
8976 | +static int main_pages_allocated, main_pages_requested; | |
24613191 | 8977 | + |
4e97e4e9 | 8978 | +#define target_is_normal_file() (S_ISREG(target_inode->i_mode)) |
24613191 | 8979 | + |
4e97e4e9 | 8980 | +static struct toi_bdev_info devinfo; |
24613191 | 8981 | + |
4e97e4e9 | 8982 | +/* Extent chain for blocks */ |
f3e0dcc9 | 8983 | +static struct hibernate_extent_chain block_chain; |
24613191 | 8984 | + |
4e97e4e9 | 8985 | +/* Signature operations */ |
8986 | +enum { | |
8987 | + GET_IMAGE_EXISTS, | |
8988 | + INVALIDATE, | |
8989 | + MARK_RESUME_ATTEMPTED, | |
8990 | + UNMARK_RESUME_ATTEMPTED, | |
8991 | +}; | |
24613191 | 8992 | + |
4e97e4e9 | 8993 | +static void set_devinfo(struct block_device *bdev, int target_blkbits) |
8994 | +{ | |
8995 | + devinfo.bdev = bdev; | |
8996 | + if (!target_blkbits) { | |
8997 | + devinfo.bmap_shift = devinfo.blocks_per_page = 0; | |
8998 | + } else { | |
8999 | + devinfo.bmap_shift = target_blkbits - 9; | |
9000 | + devinfo.blocks_per_page = (1 << (PAGE_SHIFT - target_blkbits)); | |
9001 | + } | |
9002 | +} | |
24613191 | 9003 | + |
7f9d2ee0 | 9004 | +static long raw_to_real(long raw) |
4e97e4e9 | 9005 | +{ |
7f9d2ee0 | 9006 | + long result; |
9007 | + | |
9008 | + result = raw - (raw * (sizeof(unsigned long) + sizeof(int)) + | |
9009 | + (PAGE_SIZE + sizeof(unsigned long) + sizeof(int) + 1)) / | |
9010 | + (PAGE_SIZE + sizeof(unsigned long) + sizeof(int)); | |
9011 | + | |
9012 | + return result < 0 ? 0 : result; | |
4e97e4e9 | 9013 | +} |
24613191 | 9014 | + |
4e97e4e9 | 9015 | +static int toi_file_storage_available(void) |
9016 | +{ | |
9017 | + int result = 0; | |
ad8f4a28 | 9018 | + struct block_device *bdev = toi_file_target_bdev; |
24613191 | 9019 | + |
4e97e4e9 | 9020 | + if (!target_inode) |
9021 | + return 0; | |
24613191 | 9022 | + |
4e97e4e9 | 9023 | + switch (target_inode->i_mode & S_IFMT) { |
ad8f4a28 AM |
9024 | + case S_IFSOCK: |
9025 | + case S_IFCHR: | |
9026 | + case S_IFIFO: /* Socket, Char, Fifo */ | |
9027 | + return -1; | |
9028 | + case S_IFREG: /* Regular file: current size - holes + free | |
9029 | + space on part */ | |
9030 | + result = target_storage_available; | |
9031 | + break; | |
9032 | + case S_IFBLK: /* Block device */ | |
9033 | + if (!bdev->bd_disk) { | |
9034 | + printk(KERN_INFO "bdev->bd_disk null.\n"); | |
9035 | + return 0; | |
9036 | + } | |
24613191 | 9037 | + |
ad8f4a28 AM |
9038 | + result = (bdev->bd_part ? |
9039 | + bdev->bd_part->nr_sects : | |
9040 | + bdev->bd_disk->capacity) >> (PAGE_SHIFT - 9); | |
4e97e4e9 | 9041 | + } |
24613191 | 9042 | + |
7f9d2ee0 | 9043 | + return raw_to_real(result); |
4e97e4e9 | 9044 | +} |
24613191 | 9045 | + |
4e97e4e9 | 9046 | +static int has_contiguous_blocks(int page_num) |
24613191 | 9047 | +{ |
4e97e4e9 | 9048 | + int j; |
9049 | + sector_t last = 0; | |
24613191 | 9050 | + |
4e97e4e9 | 9051 | + for (j = 0; j < devinfo.blocks_per_page; j++) { |
9052 | + sector_t this = bmap(target_inode, | |
9053 | + page_num * devinfo.blocks_per_page + j); | |
9054 | + | |
9055 | + if (!this || (last && (last + 1) != this)) | |
24613191 | 9056 | + break; |
9057 | + | |
4e97e4e9 | 9058 | + last = this; |
24613191 | 9059 | + } |
ad8f4a28 | 9060 | + |
f3e0dcc9 | 9061 | + return j == devinfo.blocks_per_page; |
24613191 | 9062 | +} |
9063 | + | |
4e97e4e9 | 9064 | +static int size_ignoring_ignored_pages(void) |
24613191 | 9065 | +{ |
4e97e4e9 | 9066 | + int mappable = 0, i; |
ad8f4a28 | 9067 | + |
4e97e4e9 | 9068 | + if (!target_is_normal_file()) |
9069 | + return toi_file_storage_available(); | |
24613191 | 9070 | + |
4e97e4e9 | 9071 | + for (i = 0; i < (target_inode->i_size >> PAGE_SHIFT) ; i++) |
9072 | + if (has_contiguous_blocks(i)) | |
9073 | + mappable++; | |
ad8f4a28 | 9074 | + |
4e97e4e9 | 9075 | + return mappable; |
24613191 | 9076 | +} |
9077 | + | |
7f9d2ee0 | 9078 | +static int __populate_block_list(int min, int max) |
24613191 | 9079 | +{ |
4e97e4e9 | 9080 | + if (test_action_state(TOI_TEST_BIO)) |
ad8f4a28 AM |
9081 | + printk(KERN_INFO "Adding extent %d-%d.\n", |
9082 | + min << devinfo.bmap_shift, | |
9083 | + ((max + 1) << devinfo.bmap_shift) - 1); | |
4e97e4e9 | 9084 | + |
7f9d2ee0 | 9085 | + return toi_add_to_extent_chain(&block_chain, min, max); |
24613191 | 9086 | +} |
9087 | + | |
7f9d2ee0 | 9088 | +static int apply_header_reservation(void) |
24613191 | 9089 | +{ |
4e97e4e9 | 9090 | + int i; |
7f9d2ee0 | 9091 | + |
9092 | + /* Apply header space reservation */ | |
9093 | + toi_extent_state_goto_start(&toi_writer_posn); | |
9094 | + toi_bio_ops.forward_one_page(1); /* To first page */ | |
9095 | + | |
9096 | + for (i = 0; i < header_pages_reserved; i++) | |
9097 | + if (toi_bio_ops.forward_one_page(1)) | |
9098 | + return -ENOSPC; | |
9099 | + | |
9100 | + /* The end of header pages will be the start of pageset 2 */ | |
9101 | + toi_extent_state_save(&toi_writer_posn, &toi_writer_posn_save[2]); | |
9102 | + | |
9103 | + return 0; | |
9104 | +} | |
9105 | + | |
9106 | +static int populate_block_list(void) | |
9107 | +{ | |
9108 | + int i, extent_min = -1, extent_max = -1, got_header = 0, result = 0; | |
ad8f4a28 | 9109 | + |
4e97e4e9 | 9110 | + if (block_chain.first) |
9111 | + toi_put_extent_chain(&block_chain); | |
24613191 | 9112 | + |
4e97e4e9 | 9113 | + if (!target_is_normal_file()) { |
7f9d2ee0 | 9114 | + return (target_storage_available > 0) ? |
ad8f4a28 | 9115 | + __populate_block_list(devinfo.blocks_per_page, |
4e97e4e9 | 9116 | + (target_storage_available + 1) * |
7f9d2ee0 | 9117 | + devinfo.blocks_per_page - 1) : 0; |
24613191 | 9118 | + } |
9119 | + | |
4e97e4e9 | 9120 | + for (i = 0; i < (target_inode->i_size >> PAGE_SHIFT); i++) { |
9121 | + sector_t new_sector; | |
24613191 | 9122 | + |
4e97e4e9 | 9123 | + if (!has_contiguous_blocks(i)) |
9124 | + continue; | |
24613191 | 9125 | + |
4e97e4e9 | 9126 | + new_sector = bmap(target_inode, |
9127 | + (i * devinfo.blocks_per_page)); | |
24613191 | 9128 | + |
ad8f4a28 | 9129 | + /* |
4e97e4e9 | 9130 | + * Ignore the first block in the file. |
9131 | + * It gets the header. | |
9132 | + */ | |
9133 | + if (new_sector == target_firstblock >> devinfo.bmap_shift) { | |
9134 | + got_header = 1; | |
9135 | + continue; | |
9136 | + } | |
24613191 | 9137 | + |
ad8f4a28 AM |
9138 | + /* |
9139 | + * I'd love to be able to fill in holes and resize | |
4e97e4e9 | 9140 | + * files, but not yet... |
9141 | + */ | |
24613191 | 9142 | + |
4e97e4e9 | 9143 | + if (new_sector == extent_max + 1) |
ad8f4a28 | 9144 | + extent_max += devinfo.blocks_per_page; |
4e97e4e9 | 9145 | + else { |
7f9d2ee0 | 9146 | + if (extent_min > -1) { |
9147 | + result = __populate_block_list(extent_min, | |
4e97e4e9 | 9148 | + extent_max); |
7f9d2ee0 | 9149 | + if (result) |
9150 | + return result; | |
9151 | + } | |
24613191 | 9152 | + |
4e97e4e9 | 9153 | + extent_min = new_sector; |
9154 | + extent_max = extent_min + | |
9155 | + devinfo.blocks_per_page - 1; | |
9156 | + } | |
9157 | + } | |
9158 | + | |
7f9d2ee0 | 9159 | + if (extent_min > -1) { |
9160 | + result = __populate_block_list(extent_min, extent_max); | |
9161 | + if (result) | |
9162 | + return result; | |
9163 | + } | |
9164 | + | |
9165 | + return apply_header_reservation(); | |
24613191 | 9166 | +} |
9167 | + | |
4e97e4e9 | 9168 | +static void toi_file_cleanup(int finishing_cycle) |
24613191 | 9169 | +{ |
4e97e4e9 | 9170 | + if (toi_file_target_bdev) { |
9171 | + if (target_claim) { | |
9172 | + bd_release(toi_file_target_bdev); | |
9173 | + target_claim = 0; | |
9174 | + } | |
24613191 | 9175 | + |
4e97e4e9 | 9176 | + if (used_devt) { |
9177 | + blkdev_put(toi_file_target_bdev); | |
9178 | + used_devt = 0; | |
9179 | + } | |
9180 | + toi_file_target_bdev = NULL; | |
9181 | + target_inode = NULL; | |
9182 | + set_devinfo(NULL, 0); | |
9183 | + target_storage_available = 0; | |
9184 | + } | |
9185 | + | |
1838f965 | 9186 | + if (target_file && !IS_ERR(target_file)) |
4e97e4e9 | 9187 | + filp_close(target_file, NULL); |
1838f965 | 9188 | + |
9189 | + target_file = NULL; | |
24613191 | 9190 | +} |
9191 | + | |
ad8f4a28 | 9192 | +/* |
4e97e4e9 | 9193 | + * reopen_resume_devt |
9194 | + * | |
9195 | + * Having opened resume= once, we remember the major and | |
9196 | + * minor nodes and use them to reopen the bdev for checking | |
9197 | + * whether an image exists (possibly when starting a resume). | |
24613191 | 9198 | + */ |
4e97e4e9 | 9199 | +static void reopen_resume_devt(void) |
24613191 | 9200 | +{ |
7f9d2ee0 | 9201 | + toi_file_target_bdev = toi_open_by_devnum(resume_file_dev_t, |
9202 | + FMODE_READ); | |
4e97e4e9 | 9203 | + if (IS_ERR(toi_file_target_bdev)) { |
ad8f4a28 | 9204 | + printk(KERN_INFO "Got a dev_num (%lx) but failed to open it.\n", |
4e97e4e9 | 9205 | + (unsigned long) resume_file_dev_t); |
9206 | + return; | |
24613191 | 9207 | + } |
4e97e4e9 | 9208 | + target_inode = toi_file_target_bdev->bd_inode; |
9209 | + set_devinfo(toi_file_target_bdev, target_inode->i_blkbits); | |
9210 | +} | |
24613191 | 9211 | + |
4e97e4e9 | 9212 | +static void toi_file_get_target_info(char *target, int get_size, |
9213 | + int resume_param) | |
9214 | +{ | |
9215 | + if (target_file) | |
9216 | + toi_file_cleanup(0); | |
24613191 | 9217 | + |
4e97e4e9 | 9218 | + if (!target || !strlen(target)) |
9219 | + return; | |
24613191 | 9220 | + |
4e97e4e9 | 9221 | + target_file = filp_open(target, O_RDWR|O_LARGEFILE, 0); |
24613191 | 9222 | + |
4e97e4e9 | 9223 | + if (IS_ERR(target_file) || !target_file) { |
24613191 | 9224 | + |
4e97e4e9 | 9225 | + if (!resume_param) { |
ad8f4a28 | 9226 | + printk(KERN_INFO "Open file %s returned %p.\n", |
4e97e4e9 | 9227 | + target, target_file); |
9228 | + target_file = NULL; | |
9229 | + return; | |
9230 | + } | |
24613191 | 9231 | + |
4e97e4e9 | 9232 | + target_file = NULL; |
9233 | + resume_file_dev_t = name_to_dev_t(target); | |
9234 | + if (!resume_file_dev_t) { | |
9235 | + struct kstat stat; | |
9236 | + int error = vfs_stat(target, &stat); | |
ad8f4a28 AM |
9237 | + printk(KERN_INFO "Open file %s returned %p and " |
9238 | + "name_to_devt failed.\n", target, | |
9239 | + target_file); | |
4e97e4e9 | 9240 | + if (error) |
ad8f4a28 | 9241 | + printk(KERN_INFO "Stating the file also failed." |
4e97e4e9 | 9242 | + " Nothing more we can do.\n"); |
9243 | + else | |
9244 | + resume_file_dev_t = stat.rdev; | |
9245 | + return; | |
9246 | + } | |
24613191 | 9247 | + |
ad8f4a28 | 9248 | + toi_file_target_bdev = toi_open_by_devnum(resume_file_dev_t, |
4e97e4e9 | 9249 | + FMODE_READ); |
9250 | + if (IS_ERR(toi_file_target_bdev)) { | |
ad8f4a28 AM |
9251 | + printk(KERN_INFO "Got a dev_num (%lx) but failed to " |
9252 | + "open it.\n", | |
4e97e4e9 | 9253 | + (unsigned long) resume_file_dev_t); |
9254 | + return; | |
9255 | + } | |
9256 | + used_devt = 1; | |
9257 | + target_inode = toi_file_target_bdev->bd_inode; | |
9258 | + } else | |
9259 | + target_inode = target_file->f_mapping->host; | |
24613191 | 9260 | + |
4e97e4e9 | 9261 | + if (S_ISLNK(target_inode->i_mode) || S_ISDIR(target_inode->i_mode) || |
9262 | + S_ISSOCK(target_inode->i_mode) || S_ISFIFO(target_inode->i_mode)) { | |
ad8f4a28 AM |
9263 | + printk(KERN_INFO "File support works with regular files," |
9264 | + " character files and block devices.\n"); | |
4e97e4e9 | 9265 | + goto cleanup; |
24613191 | 9266 | + } |
9267 | + | |
4e97e4e9 | 9268 | + if (!used_devt) { |
9269 | + if (S_ISBLK(target_inode->i_mode)) { | |
9270 | + toi_file_target_bdev = I_BDEV(target_inode); | |
9271 | + if (!bd_claim(toi_file_target_bdev, &toi_fileops)) | |
9272 | + target_claim = 1; | |
9273 | + } else | |
9274 | + toi_file_target_bdev = target_inode->i_sb->s_bdev; | |
9275 | + resume_file_dev_t = toi_file_target_bdev->bd_dev; | |
24613191 | 9276 | + } |
9277 | + | |
4e97e4e9 | 9278 | + set_devinfo(toi_file_target_bdev, target_inode->i_blkbits); |
24613191 | 9279 | + |
4e97e4e9 | 9280 | + if (get_size) |
9281 | + target_storage_available = size_ignoring_ignored_pages(); | |
9282 | + | |
9283 | + if (!resume_param) | |
9284 | + target_firstblock = bmap(target_inode, 0) << devinfo.bmap_shift; | |
ad8f4a28 | 9285 | + |
4e97e4e9 | 9286 | + return; |
9287 | +cleanup: | |
9288 | + target_inode = NULL; | |
9289 | + if (target_file) { | |
9290 | + filp_close(target_file, NULL); | |
9291 | + target_file = NULL; | |
9292 | + } | |
9293 | + set_devinfo(NULL, 0); | |
9294 | + target_storage_available = 0; | |
24613191 | 9295 | +} |
9296 | + | |
7f9d2ee0 | 9297 | +static void toi_file_noresume_reset(void) |
9298 | +{ | |
9299 | + toi_bio_ops.rw_cleanup(READ); | |
9300 | +} | |
9301 | + | |
4e97e4e9 | 9302 | +static int parse_signature(struct toi_file_header *header) |
24613191 | 9303 | +{ |
4e97e4e9 | 9304 | + int have_image = !memcmp(HaveImage, header->sig, sizeof(HaveImage) - 1); |
ad8f4a28 AM |
9305 | + int no_image_header = !memcmp(NoImage, header->sig, |
9306 | + sizeof(NoImage) - 1); | |
7f9d2ee0 | 9307 | + int binary_sig = !memcmp(tuxonice_signature, header->sig, |
9308 | + sizeof(tuxonice_signature)); | |
24613191 | 9309 | + |
7f9d2ee0 | 9310 | + if (no_image_header || (binary_sig && !header->have_image)) |
4e97e4e9 | 9311 | + return 0; |
24613191 | 9312 | + |
7f9d2ee0 | 9313 | + if (!have_image && !binary_sig) |
4e97e4e9 | 9314 | + return -1; |
24613191 | 9315 | + |
4e97e4e9 | 9316 | + if (header->resumed_before) |
9317 | + set_toi_state(TOI_RESUMED_BEFORE); | |
9318 | + else | |
9319 | + clear_toi_state(TOI_RESUMED_BEFORE); | |
24613191 | 9320 | + |
4e97e4e9 | 9321 | + target_header_start = header->first_header_block; |
9322 | + return 1; | |
9323 | +} | |
24613191 | 9324 | + |
4e97e4e9 | 9325 | +/* prepare_signature */ |
9326 | + | |
9327 | +static int prepare_signature(struct toi_file_header *current_header, | |
9328 | + unsigned long first_header_block) | |
9329 | +{ | |
7f9d2ee0 | 9330 | + strncpy(current_header->sig, tuxonice_signature, |
9331 | + sizeof(tuxonice_signature)); | |
4e97e4e9 | 9332 | + current_header->resumed_before = 0; |
9333 | + current_header->first_header_block = first_header_block; | |
7f9d2ee0 | 9334 | + current_header->have_image = 1; |
24613191 | 9335 | + return 0; |
9336 | +} | |
9337 | + | |
4e97e4e9 | 9338 | +static int toi_file_storage_allocated(void) |
24613191 | 9339 | +{ |
4e97e4e9 | 9340 | + if (!target_inode) |
9341 | + return 0; | |
24613191 | 9342 | + |
4e97e4e9 | 9343 | + if (target_is_normal_file()) |
7f9d2ee0 | 9344 | + return (int) raw_to_real(target_storage_available); |
4e97e4e9 | 9345 | + else |
7f9d2ee0 | 9346 | + return (int) raw_to_real(main_pages_requested); |
4e97e4e9 | 9347 | +} |
24613191 | 9348 | + |
4e97e4e9 | 9349 | +static int toi_file_release_storage(void) |
9350 | +{ | |
9351 | + if (test_action_state(TOI_KEEP_IMAGE) && | |
9352 | + test_toi_state(TOI_NOW_RESUMING)) | |
9353 | + return 0; | |
24613191 | 9354 | + |
4e97e4e9 | 9355 | + toi_put_extent_chain(&block_chain); |
24613191 | 9356 | + |
7f9d2ee0 | 9357 | + header_pages_reserved = 0; |
4e97e4e9 | 9358 | + main_pages_allocated = 0; |
9359 | + main_pages_requested = 0; | |
9360 | + return 0; | |
24613191 | 9361 | +} |
9362 | + | |
7f9d2ee0 | 9363 | +static void toi_file_reserve_header_space(int request) |
24613191 | 9364 | +{ |
7f9d2ee0 | 9365 | + header_pages_reserved = request; |
9366 | + apply_header_reservation(); | |
24613191 | 9367 | +} |
9368 | + | |
7f9d2ee0 | 9369 | +static int toi_file_allocate_storage(int main_space_requested) |
24613191 | 9370 | +{ |
4e97e4e9 | 9371 | + int result = 0; |
24613191 | 9372 | + |
4e97e4e9 | 9373 | + int extra_pages = DIV_ROUND_UP(main_space_requested * |
9374 | + (sizeof(unsigned long) + sizeof(int)), PAGE_SIZE); | |
9375 | + int pages_to_get = main_space_requested + extra_pages + | |
7f9d2ee0 | 9376 | + header_pages_reserved; |
4e97e4e9 | 9377 | + int blocks_to_get = pages_to_get - block_chain.size; |
ad8f4a28 | 9378 | + |
4e97e4e9 | 9379 | + /* Only release_storage reduces the size */ |
9380 | + if (blocks_to_get < 1) | |
9381 | + return 0; | |
24613191 | 9382 | + |
7f9d2ee0 | 9383 | + result = populate_block_list(); |
9384 | + | |
9385 | + if (result) | |
9386 | + return result; | |
24613191 | 9387 | + |
4e97e4e9 | 9388 | + toi_message(TOI_WRITER, TOI_MEDIUM, 0, |
9389 | + "Finished with block_chain.size == %d.\n", | |
9390 | + block_chain.size); | |
24613191 | 9391 | + |
4e97e4e9 | 9392 | + if (block_chain.size < pages_to_get) { |
ad8f4a28 AM |
9393 | + printk("Block chain size (%d) < header pages (%d) + extra " |
9394 | + "pages (%d) + main pages (%d) (=%d pages).\n", | |
7f9d2ee0 | 9395 | + block_chain.size, header_pages_reserved, extra_pages, |
4e97e4e9 | 9396 | + main_space_requested, pages_to_get); |
9397 | + result = -ENOSPC; | |
24613191 | 9398 | + } |
9399 | + | |
4e97e4e9 | 9400 | + main_pages_requested = main_space_requested; |
9401 | + main_pages_allocated = main_space_requested + extra_pages; | |
4e97e4e9 | 9402 | + return result; |
24613191 | 9403 | +} |
9404 | + | |
4e97e4e9 | 9405 | +static int toi_file_write_header_init(void) |
24613191 | 9406 | +{ |
7f9d2ee0 | 9407 | + int result; |
24613191 | 9408 | + |
7f9d2ee0 | 9409 | + toi_bio_ops.rw_init(WRITE, 0); |
4e97e4e9 | 9410 | + toi_writer_buffer_posn = 0; |
24613191 | 9411 | + |
4e97e4e9 | 9412 | + /* Info needed to bootstrap goes at the start of the header. |
9413 | + * First we save the basic info needed for reading, including the number | |
9414 | + * of header pages. Then we save the structs containing data needed | |
9415 | + * for reading the header pages back. | |
9416 | + * Note that even if header pages take more than one page, when we | |
9417 | + * read back the info, we will have restored the location of the | |
9418 | + * next header page by the time we go to use it. | |
9419 | + */ | |
24613191 | 9420 | + |
7f9d2ee0 | 9421 | + result = toi_bio_ops.rw_header_chunk(WRITE, &toi_fileops, |
ad8f4a28 | 9422 | + (char *) &toi_writer_posn_save, |
4e97e4e9 | 9423 | + sizeof(toi_writer_posn_save)); |
9424 | + | |
7f9d2ee0 | 9425 | + if (result) |
9426 | + return result; | |
9427 | + | |
9428 | + result = toi_bio_ops.rw_header_chunk(WRITE, &toi_fileops, | |
4e97e4e9 | 9429 | + (char *) &devinfo, sizeof(devinfo)); |
24613191 | 9430 | + |
7f9d2ee0 | 9431 | + if (result) |
9432 | + return result; | |
9433 | + | |
4e97e4e9 | 9434 | + toi_serialise_extent_chain(&toi_fileops, &block_chain); |
ad8f4a28 | 9435 | + |
24613191 | 9436 | + return 0; |
9437 | +} | |
73c609d5 | 9438 | + |
4e97e4e9 | 9439 | +static int toi_file_write_header_cleanup(void) |
9440 | +{ | |
9441 | + struct toi_file_header *header; | |
7f9d2ee0 | 9442 | + int result; |
9443 | + unsigned long sig_page = toi_get_zeroed_page(38, TOI_ATOMIC_GFP); | |
24613191 | 9444 | + |
4e97e4e9 | 9445 | + /* Write any unsaved data */ |
9446 | + if (toi_writer_buffer_posn) | |
9447 | + toi_bio_ops.write_header_chunk_finish(); | |
24613191 | 9448 | + |
4e97e4e9 | 9449 | + toi_bio_ops.finish_all_io(); |
24613191 | 9450 | + |
4e97e4e9 | 9451 | + toi_extent_state_goto_start(&toi_writer_posn); |
ad8f4a28 | 9452 | + toi_bio_ops.forward_one_page(1); |
24613191 | 9453 | + |
4e97e4e9 | 9454 | + /* Adjust image header */ |
7f9d2ee0 | 9455 | + result = toi_bio_ops.bdev_page_io(READ, toi_file_target_bdev, |
4e97e4e9 | 9456 | + target_firstblock, |
7f9d2ee0 | 9457 | + virt_to_page(sig_page)); |
9458 | + if (result) | |
9459 | + goto out; | |
24613191 | 9460 | + |
7f9d2ee0 | 9461 | + header = (struct toi_file_header *) sig_page; |
4e97e4e9 | 9462 | + |
9463 | + prepare_signature(header, | |
9464 | + toi_writer_posn.current_offset << | |
9465 | + devinfo.bmap_shift); | |
ad8f4a28 | 9466 | + |
7f9d2ee0 | 9467 | + result = toi_bio_ops.bdev_page_io(WRITE, toi_file_target_bdev, |
4e97e4e9 | 9468 | + target_firstblock, |
7f9d2ee0 | 9469 | + virt_to_page(sig_page)); |
4e97e4e9 | 9470 | + |
7f9d2ee0 | 9471 | +out: |
4e97e4e9 | 9472 | + toi_bio_ops.finish_all_io(); |
7f9d2ee0 | 9473 | + toi_free_page(38, sig_page); |
4e97e4e9 | 9474 | + |
7f9d2ee0 | 9475 | + return result; |
4e97e4e9 | 9476 | +} |
9477 | + | |
9478 | +/* HEADER READING */ | |
9479 | + | |
24613191 | 9480 | +/* |
4e97e4e9 | 9481 | + * read_header_init() |
ad8f4a28 | 9482 | + * |
4e97e4e9 | 9483 | + * Description: |
9484 | + * 1. Attempt to read the device specified with resume=. | |
9485 | + * 2. Check the contents of the header for our signature. | |
9486 | + * 3. Warn, ignore, reset and/or continue as appropriate. | |
9487 | + * 4. If continuing, read the toi_file configuration section | |
9488 | + * of the header and set up block device info so we can read | |
9489 | + * the rest of the header & image. | |
24613191 | 9490 | + * |
4e97e4e9 | 9491 | + * Returns: |
9492 | + * May not return if user choose to reboot at a warning. | |
9493 | + * -EINVAL if cannot resume at this time. Booting should continue | |
9494 | + * normally. | |
24613191 | 9495 | + */ |
9496 | + | |
4e97e4e9 | 9497 | +static int toi_file_read_header_init(void) |
9498 | +{ | |
9499 | + int result; | |
9500 | + struct block_device *tmp; | |
24613191 | 9501 | + |
7f9d2ee0 | 9502 | + toi_bio_ops.read_header_init(); |
9503 | + | |
9504 | + /* Read toi_file configuration */ | |
9505 | + result = toi_bio_ops.bdev_page_io(READ, toi_file_target_bdev, | |
9506 | + target_header_start, | |
9507 | + virt_to_page((unsigned long) toi_writer_buffer)); | |
ad8f4a28 | 9508 | + |
4e97e4e9 | 9509 | + if (result) { |
9510 | + printk("FileAllocator read header init: Failed to initialise " | |
9511 | + "reading the first page of data.\n"); | |
7f9d2ee0 | 9512 | + toi_bio_ops.rw_cleanup(READ); |
4e97e4e9 | 9513 | + return result; |
9514 | + } | |
24613191 | 9515 | + |
7f9d2ee0 | 9516 | + memcpy(&toi_writer_posn_save, toi_writer_buffer, |
4e97e4e9 | 9517 | + sizeof(toi_writer_posn_save)); |
ad8f4a28 | 9518 | + |
7f9d2ee0 | 9519 | + toi_writer_buffer_posn = sizeof(toi_writer_posn_save); |
24613191 | 9520 | + |
4e97e4e9 | 9521 | + tmp = devinfo.bdev; |
24613191 | 9522 | + |
4e97e4e9 | 9523 | + memcpy(&devinfo, |
9524 | + toi_writer_buffer + toi_writer_buffer_posn, | |
9525 | + sizeof(devinfo)); | |
24613191 | 9526 | + |
4e97e4e9 | 9527 | + devinfo.bdev = tmp; |
9528 | + toi_writer_buffer_posn += sizeof(devinfo); | |
24613191 | 9529 | + |
4e97e4e9 | 9530 | + toi_extent_state_goto_start(&toi_writer_posn); |
9531 | + toi_bio_ops.set_extra_page_forward(); | |
24613191 | 9532 | + |
4e97e4e9 | 9533 | + return toi_load_extent_chain(&block_chain); |
9534 | +} | |
24613191 | 9535 | + |
4e97e4e9 | 9536 | +static int toi_file_read_header_cleanup(void) |
9537 | +{ | |
9538 | + toi_bio_ops.rw_cleanup(READ); | |
9539 | + return 0; | |
9540 | +} | |
9541 | + | |
9542 | +static int toi_file_signature_op(int op) | |
9543 | +{ | |
9544 | + char *cur; | |
9545 | + int result = 0, changed = 0; | |
9546 | + struct toi_file_header *header; | |
ad8f4a28 | 9547 | + |
1838f965 | 9548 | + if (IS_ERR(toi_file_target_bdev)) |
4e97e4e9 | 9549 | + return -1; |
24613191 | 9550 | + |
4e97e4e9 | 9551 | + cur = (char *) toi_get_zeroed_page(17, TOI_ATOMIC_GFP); |
9552 | + if (!cur) { | |
9553 | + printk("Unable to allocate a page for reading the image " | |
9554 | + "signature.\n"); | |
9555 | + return -ENOMEM; | |
9556 | + } | |
24613191 | 9557 | + |
7f9d2ee0 | 9558 | + result = toi_bio_ops.bdev_page_io(READ, toi_file_target_bdev, |
4e97e4e9 | 9559 | + target_firstblock, |
9560 | + virt_to_page(cur)); | |
24613191 | 9561 | + |
7f9d2ee0 | 9562 | + if (result) |
9563 | + goto out; | |
9564 | + | |
4e97e4e9 | 9565 | + header = (struct toi_file_header *) cur; |
9566 | + result = parse_signature(header); | |
ad8f4a28 | 9567 | + |
4e97e4e9 | 9568 | + switch (op) { |
ad8f4a28 AM |
9569 | + case INVALIDATE: |
9570 | + if (result == -1) | |
9571 | + goto out; | |
24613191 | 9572 | + |
f3e0dcc9 PS |
9573 | + memcpy(header->sig, tuxonice_signature, |
9574 | + sizeof(tuxonice_signature)); | |
ad8f4a28 | 9575 | + header->resumed_before = 0; |
7f9d2ee0 | 9576 | + header->have_image = 0; |
ad8f4a28 AM |
9577 | + result = changed = 1; |
9578 | + break; | |
9579 | + case MARK_RESUME_ATTEMPTED: | |
9580 | + if (result == 1) { | |
9581 | + header->resumed_before = 1; | |
9582 | + changed = 1; | |
9583 | + } | |
9584 | + break; | |
9585 | + case UNMARK_RESUME_ATTEMPTED: | |
9586 | + if (result == 1) { | |
4e97e4e9 | 9587 | + header->resumed_before = 0; |
ad8f4a28 AM |
9588 | + changed = 1; |
9589 | + } | |
9590 | + break; | |
24613191 | 9591 | + } |
9592 | + | |
7f9d2ee0 | 9593 | + if (changed) { |
9594 | + int io_result = toi_bio_ops.bdev_page_io(WRITE, | |
9595 | + toi_file_target_bdev, target_firstblock, | |
4e97e4e9 | 9596 | + virt_to_page(cur)); |
7f9d2ee0 | 9597 | + if (io_result) |
9598 | + result = io_result; | |
9599 | + } | |
24613191 | 9600 | + |
4e97e4e9 | 9601 | +out: |
9602 | + toi_bio_ops.finish_all_io(); | |
ad8f4a28 | 9603 | + toi_free_page(17, (unsigned long) cur); |
4e97e4e9 | 9604 | + return result; |
24613191 | 9605 | +} |
9606 | + | |
4e97e4e9 | 9607 | +/* Print debug info |
24613191 | 9608 | + * |
4e97e4e9 | 9609 | + * Description: |
24613191 | 9610 | + */ |
9611 | + | |
4e97e4e9 | 9612 | +static int toi_file_print_debug_stats(char *buffer, int size) |
24613191 | 9613 | +{ |
4e97e4e9 | 9614 | + int len = 0; |
ad8f4a28 | 9615 | + |
4e97e4e9 | 9616 | + if (toiActiveAllocator != &toi_fileops) { |
1838f965 | 9617 | + len = scnprintf(buffer, size, |
ad8f4a28 | 9618 | + "- FileAllocator inactive.\n"); |
4e97e4e9 | 9619 | + return len; |
e8d0ad9d | 9620 | + } |
9621 | + | |
1838f965 | 9622 | + len = scnprintf(buffer, size, "- FileAllocator active.\n"); |
24613191 | 9623 | + |
1838f965 | 9624 | + len += scnprintf(buffer+len, size-len, " Storage available for " |
9625 | + "image: %d pages.\n", | |
4e97e4e9 | 9626 | + toi_file_storage_allocated()); |
24613191 | 9627 | + |
4e97e4e9 | 9628 | + return len; |
24613191 | 9629 | +} |
9630 | + | |
4e97e4e9 | 9631 | +/* |
9632 | + * Storage needed | |
9633 | + * | |
9634 | + * Returns amount of space in the image header required | |
9635 | + * for the toi_file's data. | |
9636 | + * | |
9637 | + * We ensure the space is allocated, but actually save the | |
9638 | + * data from write_header_init and therefore don't also define a | |
9639 | + * save_config_info routine. | |
9640 | + */ | |
9641 | +static int toi_file_storage_needed(void) | |
24613191 | 9642 | +{ |
4e97e4e9 | 9643 | + return sig_size + strlen(toi_file_target) + 1 + |
7f9d2ee0 | 9644 | + sizeof(toi_writer_posn_save) + |
4e97e4e9 | 9645 | + sizeof(devinfo) + |
f3e0dcc9 | 9646 | + sizeof(struct hibernate_extent_chain) - 2 * sizeof(void *) + |
4e97e4e9 | 9647 | + (2 * sizeof(unsigned long) * block_chain.num_extents); |
24613191 | 9648 | +} |
9649 | + | |
ad8f4a28 | 9650 | +/* |
4e97e4e9 | 9651 | + * toi_file_remove_image |
ad8f4a28 | 9652 | + * |
4e97e4e9 | 9653 | + */ |
9654 | +static int toi_file_remove_image(void) | |
9655 | +{ | |
9656 | + toi_file_release_storage(); | |
9657 | + return toi_file_signature_op(INVALIDATE); | |
9658 | +} | |
24613191 | 9659 | + |
9660 | +/* | |
4e97e4e9 | 9661 | + * Image_exists |
9662 | + * | |
24613191 | 9663 | + */ |
9664 | + | |
7f9d2ee0 | 9665 | +static int toi_file_image_exists(int quiet) |
24613191 | 9666 | +{ |
4e97e4e9 | 9667 | + if (!toi_file_target_bdev) |
9668 | + reopen_resume_devt(); | |
9669 | + | |
9670 | + return toi_file_signature_op(GET_IMAGE_EXISTS); | |
24613191 | 9671 | +} |
9672 | + | |
4e97e4e9 | 9673 | +/* |
9674 | + * Mark resume attempted. | |
24613191 | 9675 | + * |
4e97e4e9 | 9676 | + * Record that we tried to resume from this image. |
24613191 | 9677 | + */ |
9678 | + | |
7f9d2ee0 | 9679 | +static int toi_file_mark_resume_attempted(int mark) |
24613191 | 9680 | +{ |
1838f965 | 9681 | + return toi_file_signature_op(mark ? MARK_RESUME_ATTEMPTED : |
4e97e4e9 | 9682 | + UNMARK_RESUME_ATTEMPTED); |
9683 | +} | |
24613191 | 9684 | + |
4e97e4e9 | 9685 | +static void toi_file_set_resume_param(void) |
9686 | +{ | |
9687 | + char *buffer = (char *) toi_get_zeroed_page(18, TOI_ATOMIC_GFP); | |
9688 | + char *buffer2 = (char *) toi_get_zeroed_page(19, TOI_ATOMIC_GFP); | |
9689 | + unsigned long sector = bmap(target_inode, 0); | |
9690 | + int offset = 0; | |
24613191 | 9691 | + |
4e97e4e9 | 9692 | + if (!buffer || !buffer2) { |
9693 | + if (buffer) | |
ad8f4a28 | 9694 | + toi_free_page(18, (unsigned long) buffer); |
4e97e4e9 | 9695 | + if (buffer2) |
ad8f4a28 | 9696 | + toi_free_page(19, (unsigned long) buffer2); |
4e97e4e9 | 9697 | + printk("TuxOnIce: Failed to allocate memory while setting " |
9698 | + "resume= parameter.\n"); | |
9699 | + return; | |
24613191 | 9700 | + } |
9701 | + | |
4e97e4e9 | 9702 | + if (toi_file_target_bdev) { |
9703 | + set_devinfo(toi_file_target_bdev, target_inode->i_blkbits); | |
24613191 | 9704 | + |
4e97e4e9 | 9705 | + bdevname(toi_file_target_bdev, buffer2); |
ad8f4a28 | 9706 | + offset += snprintf(buffer + offset, PAGE_SIZE - offset, |
4e97e4e9 | 9707 | + "/dev/%s", buffer2); |
ad8f4a28 | 9708 | + |
4e97e4e9 | 9709 | + if (sector) |
9710 | + offset += snprintf(buffer + offset, PAGE_SIZE - offset, | |
9711 | + ":0x%lx", sector << devinfo.bmap_shift); | |
9712 | + } else | |
9713 | + offset += snprintf(buffer + offset, PAGE_SIZE - offset, | |
9714 | + "%s is not a valid target.", toi_file_target); | |
ad8f4a28 | 9715 | + |
4e97e4e9 | 9716 | + sprintf(resume_file, "file:%s", buffer); |
24613191 | 9717 | + |
ad8f4a28 AM |
9718 | + toi_free_page(18, (unsigned long) buffer); |
9719 | + toi_free_page(19, (unsigned long) buffer2); | |
4e97e4e9 | 9720 | + |
9721 | + toi_attempt_to_parse_resume_device(1); | |
24613191 | 9722 | +} |
9723 | + | |
4e97e4e9 | 9724 | +static int __test_toi_file_target(char *target, int resume_time, int quiet) |
24613191 | 9725 | +{ |
4e97e4e9 | 9726 | + toi_file_get_target_info(target, 0, resume_time); |
9727 | + if (toi_file_signature_op(GET_IMAGE_EXISTS) > -1) { | |
9728 | + if (!quiet) | |
ad8f4a28 AM |
9729 | + printk(KERN_INFO "TuxOnIce: FileAllocator: File " |
9730 | + "signature found.\n"); | |
4e97e4e9 | 9731 | + if (!resume_time) |
9732 | + toi_file_set_resume_param(); | |
ad8f4a28 | 9733 | + |
4e97e4e9 | 9734 | + toi_bio_ops.set_devinfo(&devinfo); |
9735 | + toi_writer_posn.chains = &block_chain; | |
9736 | + toi_writer_posn.num_chains = 1; | |
24613191 | 9737 | + |
4e97e4e9 | 9738 | + if (!resume_time) |
9739 | + set_toi_state(TOI_CAN_HIBERNATE); | |
9740 | + return 0; | |
9741 | + } | |
24613191 | 9742 | + |
4e97e4e9 | 9743 | + clear_toi_state(TOI_CAN_HIBERNATE); |
24613191 | 9744 | + |
4e97e4e9 | 9745 | + if (quiet) |
9746 | + return 1; | |
24613191 | 9747 | + |
4e97e4e9 | 9748 | + if (*target) |
ad8f4a28 AM |
9749 | + printk(KERN_INFO "TuxOnIce: FileAllocator: Sorry. No signature " |
9750 | + "found at %s.\n", target); | |
4e97e4e9 | 9751 | + else |
9752 | + if (!resume_time) | |
ad8f4a28 AM |
9753 | + printk(KERN_INFO "TuxOnIce: FileAllocator: Sorry. " |
9754 | + "Target is not set for hibernating.\n"); | |
24613191 | 9755 | + |
4e97e4e9 | 9756 | + return 1; |
9757 | +} | |
24613191 | 9758 | + |
4e97e4e9 | 9759 | +static void test_toi_file_target(void) |
9760 | +{ | |
9761 | + setting_toi_file_target = 1; | |
ad8f4a28 AM |
9762 | + |
9763 | + printk(KERN_INFO "TuxOnIce: Hibernating %sabled.\n", | |
4e97e4e9 | 9764 | + __test_toi_file_target(toi_file_target, 0, 1) ? |
9765 | + "dis" : "en"); | |
ad8f4a28 | 9766 | + |
4e97e4e9 | 9767 | + setting_toi_file_target = 0; |
9768 | +} | |
24613191 | 9769 | + |
4e97e4e9 | 9770 | +/* |
9771 | + * Parse Image Location | |
9772 | + * | |
9773 | + * Attempt to parse a resume= parameter. | |
9774 | + * File Allocator accepts: | |
9775 | + * resume=file:DEVNAME[:FIRSTBLOCK] | |
9776 | + * | |
9777 | + * Where: | |
9778 | + * DEVNAME is convertable to a dev_t by name_to_dev_t | |
9779 | + * FIRSTBLOCK is the location of the first block in the file. | |
ad8f4a28 | 9780 | + * BLOCKSIZE is the logical blocksize >= SECTOR_SIZE & <= PAGE_SIZE, |
4e97e4e9 | 9781 | + * mod SECTOR_SIZE == 0 of the device. |
9782 | + * Data is validated by attempting to read a header from the | |
9783 | + * location given. Failure will result in toi_file refusing to | |
9784 | + * save an image, and a reboot with correct parameters will be | |
9785 | + * necessary. | |
9786 | + */ | |
9787 | + | |
9788 | +static int toi_file_parse_sig_location(char *commandline, | |
9789 | + int only_writer, int quiet) | |
9790 | +{ | |
9791 | + char *thischar, *devstart = NULL, *colon = NULL, *at_symbol = NULL; | |
9792 | + int result = -EINVAL, target_blocksize = 0; | |
9793 | + | |
9794 | + if (strncmp(commandline, "file:", 5)) { | |
9795 | + if (!only_writer) | |
9796 | + return 1; | |
9797 | + } else | |
9798 | + commandline += 5; | |
24613191 | 9799 | + |
ad8f4a28 | 9800 | + /* |
4e97e4e9 | 9801 | + * Don't check signature again if we're beginning a cycle. If we already |
ad8f4a28 AM |
9802 | + * did the initialisation successfully, assume we'll be okay when it |
9803 | + * comes to resuming. | |
24613191 | 9804 | + */ |
4e97e4e9 | 9805 | + if (toi_file_target_bdev) |
9806 | + return 0; | |
ad8f4a28 | 9807 | + |
4e97e4e9 | 9808 | + devstart = thischar = commandline; |
9809 | + while ((*thischar != ':') && (*thischar != '@') && | |
9810 | + ((thischar - commandline) < 250) && (*thischar)) | |
9811 | + thischar++; | |
24613191 | 9812 | + |
4e97e4e9 | 9813 | + if (*thischar == ':') { |
9814 | + colon = thischar; | |
9815 | + *colon = 0; | |
9816 | + thischar++; | |
24613191 | 9817 | + } |
9818 | + | |
ad8f4a28 AM |
9819 | + while ((*thischar != '@') && ((thischar - commandline) < 250) |
9820 | + && (*thischar)) | |
4e97e4e9 | 9821 | + thischar++; |
24613191 | 9822 | + |
4e97e4e9 | 9823 | + if (*thischar == '@') { |
9824 | + at_symbol = thischar; | |
9825 | + *at_symbol = 0; | |
24613191 | 9826 | + } |
ad8f4a28 AM |
9827 | + |
9828 | + /* | |
4e97e4e9 | 9829 | + * For the toi_file, you can be able to resume, but not hibernate, |
9830 | + * because the resume= is set correctly, but the toi_file_target | |
ad8f4a28 | 9831 | + * isn't. |
4e97e4e9 | 9832 | + * |
9833 | + * We may have come here as a result of setting resume or | |
9834 | + * toi_file_target. We only test the toi_file target in the | |
9835 | + * former case (it's already done in the later), and we do it before | |
9836 | + * setting the block number ourselves. It will overwrite the values | |
9837 | + * given on the command line if we don't. | |
24613191 | 9838 | + */ |
24613191 | 9839 | + |
4e97e4e9 | 9840 | + if (!setting_toi_file_target) |
9841 | + __test_toi_file_target(toi_file_target, 1, 0); | |
24613191 | 9842 | + |
4e97e4e9 | 9843 | + if (colon) |
9844 | + target_firstblock = (int) simple_strtoul(colon + 1, NULL, 0); | |
9845 | + else | |
9846 | + target_firstblock = 0; | |
24613191 | 9847 | + |
4e97e4e9 | 9848 | + if (at_symbol) { |
9849 | + target_blocksize = (int) simple_strtoul(at_symbol + 1, NULL, 0); | |
9850 | + if (target_blocksize & (SECTOR_SIZE - 1)) { | |
ad8f4a28 AM |
9851 | + printk(KERN_INFO "FileAllocator: Blocksizes are " |
9852 | + "multiples of %d.\n", SECTOR_SIZE); | |
4e97e4e9 | 9853 | + result = -EINVAL; |
9854 | + goto out; | |
24613191 | 9855 | + } |
9856 | + } | |
ad8f4a28 | 9857 | + |
4e97e4e9 | 9858 | + if (!quiet) |
ad8f4a28 AM |
9859 | + printk(KERN_INFO "TuxOnIce FileAllocator: Testing whether you" |
9860 | + " can resume:\n"); | |
24613191 | 9861 | + |
4e97e4e9 | 9862 | + toi_file_get_target_info(commandline, 0, 1); |
24613191 | 9863 | + |
4e97e4e9 | 9864 | + if (!toi_file_target_bdev || IS_ERR(toi_file_target_bdev)) { |
9865 | + toi_file_target_bdev = NULL; | |
9866 | + result = -1; | |
9867 | + goto out; | |
24613191 | 9868 | + } |
9869 | + | |
4e97e4e9 | 9870 | + if (target_blocksize) |
9871 | + set_devinfo(toi_file_target_bdev, ffs(target_blocksize)); | |
24613191 | 9872 | + |
4e97e4e9 | 9873 | + result = __test_toi_file_target(commandline, 1, 0); |
9874 | + | |
9875 | +out: | |
9876 | + if (result) | |
9877 | + clear_toi_state(TOI_CAN_HIBERNATE); | |
9878 | + | |
9879 | + if (!quiet) | |
ad8f4a28 | 9880 | + printk(KERN_INFO "Resuming %sabled.\n", result ? "dis" : "en"); |
4e97e4e9 | 9881 | + |
9882 | + if (colon) | |
9883 | + *colon = ':'; | |
9884 | + if (at_symbol) | |
9885 | + *at_symbol = '@'; | |
9886 | + | |
9887 | + return result; | |
24613191 | 9888 | +} |
4e97e4e9 | 9889 | + |
9890 | +/* toi_file_save_config_info | |
24613191 | 9891 | + * |
ad8f4a28 AM |
9892 | + * Description: Save the target's name, not for resume time, but for |
9893 | + * all_settings. | |
4e97e4e9 | 9894 | + * Arguments: Buffer: Pointer to a buffer of size PAGE_SIZE. |
9895 | + * Returns: Number of bytes used for saving our data. | |
24613191 | 9896 | + */ |
9897 | + | |
4e97e4e9 | 9898 | +static int toi_file_save_config_info(char *buffer) |
9899 | +{ | |
9900 | + strcpy(buffer, toi_file_target); | |
9901 | + return strlen(toi_file_target) + 1; | |
9902 | +} | |
24613191 | 9903 | + |
4e97e4e9 | 9904 | +/* toi_file_load_config_info |
24613191 | 9905 | + * |
4e97e4e9 | 9906 | + * Description: Reload target's name. |
9907 | + * Arguments: Buffer: Pointer to the start of the data. | |
9908 | + * Size: Number of bytes that were saved. | |
24613191 | 9909 | + */ |
9910 | + | |
4e97e4e9 | 9911 | +static void toi_file_load_config_info(char *buffer, int size) |
9912 | +{ | |
9913 | + strcpy(toi_file_target, buffer); | |
9914 | +} | |
24613191 | 9915 | + |
4e97e4e9 | 9916 | +static int toi_file_initialise(int starting_cycle) |
9917 | +{ | |
9918 | + if (starting_cycle) { | |
9919 | + if (toiActiveAllocator != &toi_fileops) | |
9920 | + return 0; | |
24613191 | 9921 | + |
4e97e4e9 | 9922 | + if (starting_cycle & SYSFS_HIBERNATE && !*toi_file_target) { |
ad8f4a28 | 9923 | + printk(KERN_INFO "FileAllocator is the active writer, " |
4e97e4e9 | 9924 | + "but no filename has been set.\n"); |
9925 | + return 1; | |
9926 | + } | |
9927 | + } | |
9928 | + | |
7f9d2ee0 | 9929 | + if (*toi_file_target) |
4e97e4e9 | 9930 | + toi_file_get_target_info(toi_file_target, starting_cycle, 0); |
9931 | + | |
7f9d2ee0 | 9932 | + if (starting_cycle && (toi_file_image_exists(1) == -1)) { |
ad8f4a28 AM |
9933 | + printk("%s is does not have a valid signature for " |
9934 | + "hibernating.\n", toi_file_target); | |
4e97e4e9 | 9935 | + return 1; |
9936 | + } | |
9937 | + | |
9938 | + return 0; | |
9939 | +} | |
9940 | + | |
9941 | +static struct toi_sysfs_data sysfs_params[] = { | |
9942 | + | |
1838f965 | 9943 | + SYSFS_STRING("target", SYSFS_RW, toi_file_target, 256, |
9944 | + SYSFS_NEEDS_SM_FOR_WRITE, test_toi_file_target), | |
9945 | + SYSFS_INT("enabled", SYSFS_RW, &toi_fileops.enabled, 0, 1, 0, | |
9946 | + attempt_to_parse_resume_device2) | |
4e97e4e9 | 9947 | +}; |
9948 | + | |
9949 | +static struct toi_module_ops toi_fileops = { | |
9950 | + .type = WRITER_MODULE, | |
9951 | + .name = "file storage", | |
9952 | + .directory = "file", | |
9953 | + .module = THIS_MODULE, | |
9954 | + .print_debug_info = toi_file_print_debug_stats, | |
9955 | + .save_config_info = toi_file_save_config_info, | |
9956 | + .load_config_info = toi_file_load_config_info, | |
9957 | + .storage_needed = toi_file_storage_needed, | |
9958 | + .initialise = toi_file_initialise, | |
9959 | + .cleanup = toi_file_cleanup, | |
9960 | + | |
7f9d2ee0 | 9961 | + .noresume_reset = toi_file_noresume_reset, |
4e97e4e9 | 9962 | + .storage_available = toi_file_storage_available, |
9963 | + .storage_allocated = toi_file_storage_allocated, | |
9964 | + .release_storage = toi_file_release_storage, | |
7f9d2ee0 | 9965 | + .reserve_header_space = toi_file_reserve_header_space, |
4e97e4e9 | 9966 | + .allocate_storage = toi_file_allocate_storage, |
9967 | + .image_exists = toi_file_image_exists, | |
9968 | + .mark_resume_attempted = toi_file_mark_resume_attempted, | |
9969 | + .write_header_init = toi_file_write_header_init, | |
9970 | + .write_header_cleanup = toi_file_write_header_cleanup, | |
9971 | + .read_header_init = toi_file_read_header_init, | |
9972 | + .read_header_cleanup = toi_file_read_header_cleanup, | |
9973 | + .remove_image = toi_file_remove_image, | |
9974 | + .parse_sig_location = toi_file_parse_sig_location, | |
24613191 | 9975 | + |
4e97e4e9 | 9976 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
9977 | + .num_sysfs_entries = sizeof(sysfs_params) / |
9978 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 9979 | +}; |
24613191 | 9980 | + |
4e97e4e9 | 9981 | +/* ---- Registration ---- */ |
9982 | +static __init int toi_file_load(void) | |
9983 | +{ | |
9984 | + toi_fileops.rw_init = toi_bio_ops.rw_init; | |
9985 | + toi_fileops.rw_cleanup = toi_bio_ops.rw_cleanup; | |
9986 | + toi_fileops.read_page = toi_bio_ops.read_page; | |
9987 | + toi_fileops.write_page = toi_bio_ops.write_page; | |
9988 | + toi_fileops.rw_header_chunk = toi_bio_ops.rw_header_chunk; | |
7f9d2ee0 | 9989 | + toi_fileops.rw_header_chunk_noreadahead = |
9990 | + toi_bio_ops.rw_header_chunk_noreadahead; | |
9991 | + toi_fileops.io_flusher = toi_bio_ops.io_flusher; | |
1838f965 | 9992 | + toi_fileops.update_throughput_throttle = toi_bio_ops.update_throughput_throttle; |
9993 | + toi_fileops.monitor_outstanding_io = toi_bio_ops.monitor_outstanding_io; | |
9994 | + toi_fileops.finish_all_io = toi_bio_ops.finish_all_io; | |
24613191 | 9995 | + |
4e97e4e9 | 9996 | + return toi_register_module(&toi_fileops); |
9997 | +} | |
24613191 | 9998 | + |
4e97e4e9 | 9999 | +#ifdef MODULE |
10000 | +static __exit void toi_file_unload(void) | |
10001 | +{ | |
10002 | + toi_unregister_module(&toi_fileops); | |
10003 | +} | |
24613191 | 10004 | + |
4e97e4e9 | 10005 | +module_init(toi_file_load); |
10006 | +module_exit(toi_file_unload); | |
10007 | +MODULE_LICENSE("GPL"); | |
10008 | +MODULE_AUTHOR("Nigel Cunningham"); | |
10009 | +MODULE_DESCRIPTION("TuxOnIce FileAllocator"); | |
10010 | +#else | |
10011 | +late_initcall(toi_file_load); | |
24613191 | 10012 | +#endif |
4e97e4e9 | 10013 | diff --git a/kernel/power/tuxonice_highlevel.c b/kernel/power/tuxonice_highlevel.c |
10014 | new file mode 100644 | |
1838f965 | 10015 | index 0000000..5a6f96d |
4e97e4e9 | 10016 | --- /dev/null |
10017 | +++ b/kernel/power/tuxonice_highlevel.c | |
1838f965 | 10018 | @@ -0,0 +1,1269 @@ |
24613191 | 10019 | +/* |
4e97e4e9 | 10020 | + * kernel/power/tuxonice_highlevel.c |
10021 | + */ | |
10022 | +/** \mainpage TuxOnIce. | |
24613191 | 10023 | + * |
4e97e4e9 | 10024 | + * TuxOnIce provides support for saving and restoring an image of |
10025 | + * system memory to an arbitrary storage device, either on the local computer, | |
10026 | + * or across some network. The support is entirely OS based, so TuxOnIce | |
10027 | + * works without requiring BIOS, APM or ACPI support. The vast majority of the | |
10028 | + * code is also architecture independant, so it should be very easy to port | |
10029 | + * the code to new architectures. TuxOnIce includes support for SMP, 4G HighMem | |
10030 | + * and preemption. Initramfses and initrds are also supported. | |
24613191 | 10031 | + * |
4e97e4e9 | 10032 | + * TuxOnIce uses a modular design, in which the method of storing the image is |
10033 | + * completely abstracted from the core code, as are transformations on the data | |
10034 | + * such as compression and/or encryption (multiple 'modules' can be used to | |
10035 | + * provide arbitrary combinations of functionality). The user interface is also | |
10036 | + * modular, so that arbitrarily simple or complex interfaces can be used to | |
10037 | + * provide anything from debugging information through to eye candy. | |
10038 | + * | |
10039 | + * \section Copyright | |
10040 | + * | |
10041 | + * TuxOnIce is released under the GPLv2. | |
10042 | + * | |
10043 | + * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu><BR> | |
10044 | + * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz><BR> | |
10045 | + * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr><BR> | |
1838f965 | 10046 | + * Copyright (C) 2002-2008 Nigel Cunningham (nigel at tuxonice net)<BR> |
4e97e4e9 | 10047 | + * |
10048 | + * \section Credits | |
10049 | + * | |
10050 | + * Nigel would like to thank the following people for their work: | |
10051 | + * | |
10052 | + * Bernard Blackham <bernard@blackham.com.au><BR> | |
10053 | + * Web page & Wiki administration, some coding. A person without whom | |
10054 | + * TuxOnIce would not be where it is. | |
10055 | + * | |
10056 | + * Michael Frank <mhf@linuxmail.org><BR> | |
10057 | + * Extensive testing and help with improving stability. I was constantly | |
10058 | + * amazed by the quality and quantity of Michael's help. | |
10059 | + * | |
10060 | + * Pavel Machek <pavel@ucw.cz><BR> | |
ad8f4a28 AM |
10061 | + * Modifications, defectiveness pointing, being with Gabor at the very |
10062 | + * beginning, suspend to swap space, stop all tasks. Port to 2.4.18-ac and | |
10063 | + * 2.5.17. Even though Pavel and I disagree on the direction suspend to | |
10064 | + * disk should take, I appreciate the valuable work he did in helping Gabor | |
10065 | + * get the concept working. | |
4e97e4e9 | 10066 | + * |
10067 | + * ..and of course the myriads of TuxOnIce users who have helped diagnose | |
10068 | + * and fix bugs, made suggestions on how to improve the code, proofread | |
10069 | + * documentation, and donated time and money. | |
10070 | + * | |
10071 | + * Thanks also to corporate sponsors: | |
10072 | + * | |
10073 | + * <B>Redhat.</B>Sometime employer from May 2006 (my fault, not Redhat's!). | |
10074 | + * | |
10075 | + * <B>Cyclades.com.</B> Nigel's employers from Dec 2004 until May 2006, who | |
10076 | + * allowed him to work on TuxOnIce and PM related issues on company time. | |
10077 | + * | |
ad8f4a28 AM |
10078 | + * <B>LinuxFund.org.</B> Sponsored Nigel's work on TuxOnIce for four months Oct |
10079 | + * 2003 to Jan 2004. | |
4e97e4e9 | 10080 | + * |
10081 | + * <B>LAC Linux.</B> Donated P4 hardware that enabled development and ongoing | |
10082 | + * maintenance of SMP and Highmem support. | |
10083 | + * | |
ad8f4a28 AM |
10084 | + * <B>OSDL.</B> Provided access to various hardware configurations, make |
10085 | + * occasional small donations to the project. | |
24613191 | 10086 | + */ |
10087 | + | |
24613191 | 10088 | +#include <linux/suspend.h> |
4e97e4e9 | 10089 | +#include <linux/module.h> |
10090 | +#include <linux/freezer.h> | |
10091 | +#include <linux/utsrelease.h> | |
10092 | +#include <linux/cpu.h> | |
10093 | +#include <linux/console.h> | |
ad8f4a28 | 10094 | +#include <linux/writeback.h> |
1838f965 | 10095 | +#include <linux/uaccess.h> /* for get/set_fs & KERNEL_DS on i386 */ |
24613191 | 10096 | + |
1838f965 | 10097 | +#include "tuxonice.h" |
4e97e4e9 | 10098 | +#include "tuxonice_modules.h" |
10099 | +#include "tuxonice_sysfs.h" | |
10100 | +#include "tuxonice_prepare_image.h" | |
10101 | +#include "tuxonice_io.h" | |
10102 | +#include "tuxonice_ui.h" | |
10103 | +#include "tuxonice_power_off.h" | |
10104 | +#include "tuxonice_storage.h" | |
10105 | +#include "tuxonice_checksum.h" | |
4e97e4e9 | 10106 | +#include "tuxonice_builtin.h" |
10107 | +#include "tuxonice_atomic_copy.h" | |
ad8f4a28 | 10108 | +#include "tuxonice_alloc.h" |
1838f965 | 10109 | +#include "tuxonice_cluster.h" |
24613191 | 10110 | + |
4e97e4e9 | 10111 | +/*! Pageset metadata. */ |
10112 | +struct pagedir pagedir2 = {2}; | |
1838f965 | 10113 | +EXPORT_SYMBOL_GPL(pagedir2); |
24613191 | 10114 | + |
4e97e4e9 | 10115 | +static mm_segment_t oldfs; |
f3e0dcc9 | 10116 | +static DEFINE_MUTEX(tuxonice_in_use); |
4e97e4e9 | 10117 | +static int block_dump_save; |
ad8f4a28 AM |
10118 | +static char pre_hibernate_command[256]; |
10119 | +static char post_hibernate_command[256]; | |
24613191 | 10120 | + |
7f9d2ee0 | 10121 | +char *tuxonice_signature = "\xed\xc3\x02\xe9\x98\x56\xe5\x0c"; |
1838f965 | 10122 | +EXPORT_SYMBOL_GPL(tuxonice_signature); |
24613191 | 10123 | + |
4e97e4e9 | 10124 | +int do_toi_step(int step); |
24613191 | 10125 | + |
ad8f4a28 AM |
10126 | +unsigned long boot_kernel_data_buffer; |
10127 | + | |
1838f965 | 10128 | +static char *result_strings[] = { |
10129 | + "Hiberation was aborted", | |
10130 | + "The user requested that we cancel the hibernation", | |
10131 | + "No storage was available", | |
10132 | + "Insufficient storage was available", | |
10133 | + "Freezing filesystems and/or tasks failed", | |
10134 | + "A pre-existing image was used", | |
10135 | + "We would free memory, but image size limit doesn't allow this", | |
10136 | + "Unable to free enough memory to hibernate", | |
10137 | + "Unable to obtain the Power Management Semaphore", | |
10138 | + "A device suspend/resume returned an error", | |
10139 | + "The extra pages allowance is too small", | |
10140 | + "We were unable to successfully prepare an image", | |
10141 | + "TuxOnIce module initialisation failed", | |
10142 | + "TuxOnIce module cleanup failed", | |
10143 | + "I/O errors were encountered", | |
10144 | + "Ran out of memory", | |
10145 | + "An error was encountered while reading the image", | |
10146 | + "Platform preparation failed", | |
10147 | + "CPU Hotplugging failed", | |
10148 | + "Architecture specific preparation failed", | |
10149 | + "Pages needed resaving, but we were told to abort if this happens", | |
10150 | + "We can't hibernate at the moment (invalid resume= or filewriter " | |
10151 | + "target?)", | |
10152 | + "A hibernation preparation notifier chain member cancelled the " | |
10153 | + "hibernation", | |
10154 | + "Pre-snapshot preparation failed", | |
10155 | + "Post-snapshot cleanup failed", | |
10156 | + "Can't resume from alternate image", | |
10157 | +}; | |
10158 | + | |
4e97e4e9 | 10159 | +/** |
10160 | + * toi_finish_anything - Cleanup after doing anything. | |
24613191 | 10161 | + * |
1838f965 | 10162 | + * @hibernate_or_resume: Whether finishing a cycle or attempt at resuming. |
4e97e4e9 | 10163 | + * |
10164 | + * This is our basic clean-up routine, matching start_anything below. We | |
10165 | + * call cleanup routines, drop module references and restore process fs and | |
10166 | + * cpus allowed masks, together with the global block_dump variable's value. | |
24613191 | 10167 | + */ |
ad8f4a28 | 10168 | +void toi_finish_anything(int hibernate_or_resume) |
24613191 | 10169 | +{ |
ad8f4a28 | 10170 | + toi_cleanup_modules(hibernate_or_resume); |
4e97e4e9 | 10171 | + toi_put_modules(); |
ad8f4a28 | 10172 | + if (hibernate_or_resume) { |
4e97e4e9 | 10173 | + block_dump = block_dump_save; |
10174 | + set_cpus_allowed(current, CPU_MASK_ALL); | |
ad8f4a28 AM |
10175 | + toi_alloc_print_debug_stats(); |
10176 | + | |
10177 | + if (hibernate_or_resume == SYSFS_HIBERNATE && | |
10178 | + strlen(post_hibernate_command)) | |
10179 | + toi_launch_userspace_program(post_hibernate_command, | |
1838f965 | 10180 | + 0, UMH_WAIT_PROC, 0); |
10181 | + atomic_inc(&snapshot_device_available); | |
10182 | + mutex_unlock(&pm_mutex); | |
24613191 | 10183 | + } |
f3e0dcc9 PS |
10184 | + |
10185 | + set_fs(oldfs); | |
10186 | + mutex_unlock(&tuxonice_in_use); | |
24613191 | 10187 | +} |
10188 | + | |
4e97e4e9 | 10189 | +/** |
10190 | + * toi_start_anything - Basic initialisation for TuxOnIce. | |
24613191 | 10191 | + * |
4e97e4e9 | 10192 | + * @toi_or_resume: Whether starting a cycle or attempt at resuming. |
10193 | + * | |
10194 | + * Our basic initialisation routine. Take references on modules, use the | |
10195 | + * kernel segment, recheck resume= if no active allocator is set, initialise | |
10196 | + * modules, save and reset block_dump and ensure we're running on CPU0. | |
24613191 | 10197 | + */ |
ad8f4a28 | 10198 | +int toi_start_anything(int hibernate_or_resume) |
24613191 | 10199 | +{ |
1838f965 | 10200 | + int starting_cycle = (hibernate_or_resume == SYSFS_HIBERNATE); |
10201 | + | |
f3e0dcc9 | 10202 | + mutex_lock(&tuxonice_in_use); |
24613191 | 10203 | + |
4e97e4e9 | 10204 | + oldfs = get_fs(); |
10205 | + set_fs(KERNEL_DS); | |
24613191 | 10206 | + |
1838f965 | 10207 | + if (hibernate_or_resume) { |
10208 | + mutex_lock(&pm_mutex); | |
10209 | + | |
10210 | + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) | |
10211 | + goto snapshotdevice_unavailable; | |
10212 | + } | |
10213 | + | |
10214 | + if (starting_cycle && strlen(pre_hibernate_command)) { | |
ad8f4a28 | 10215 | + int result = toi_launch_userspace_program(pre_hibernate_command, |
1838f965 | 10216 | + 0, UMH_WAIT_PROC, 0); |
ad8f4a28 | 10217 | + if (result) { |
1838f965 | 10218 | + printk(KERN_INFO "Pre-hibernate command '%s' returned" |
10219 | + " %d. Aborting.\n", | |
f3e0dcc9 PS |
10220 | + pre_hibernate_command, result); |
10221 | + goto prehibernate_err; | |
ad8f4a28 AM |
10222 | + } |
10223 | + } | |
7f9d2ee0 | 10224 | + |
ad8f4a28 AM |
10225 | + if (hibernate_or_resume == SYSFS_HIBERNATE) |
10226 | + toi_print_modules(); | |
24613191 | 10227 | + |
4e97e4e9 | 10228 | + if (toi_get_modules()) { |
10229 | + printk("TuxOnIce: Get modules failed!\n"); | |
1838f965 | 10230 | + goto prehibernate_err; |
4e97e4e9 | 10231 | + } |
24613191 | 10232 | + |
ad8f4a28 | 10233 | + if (hibernate_or_resume) { |
4e97e4e9 | 10234 | + block_dump_save = block_dump; |
10235 | + block_dump = 0; | |
7f9d2ee0 | 10236 | + set_cpus_allowed(current, |
10237 | + cpumask_of_cpu(first_cpu(cpu_online_map))); | |
24613191 | 10238 | + } |
10239 | + | |
ad8f4a28 | 10240 | + if (toi_initialise_modules_early(hibernate_or_resume)) |
f3e0dcc9 | 10241 | + goto early_init_err; |
ad8f4a28 AM |
10242 | + |
10243 | + if (!toiActiveAllocator) | |
10244 | + toi_attempt_to_parse_resume_device(!hibernate_or_resume); | |
10245 | + | |
1838f965 | 10246 | + if (!toi_initialise_modules_late(hibernate_or_resume)) |
10247 | + return 0; | |
4e97e4e9 | 10248 | + |
f3e0dcc9 PS |
10249 | + toi_cleanup_modules(hibernate_or_resume); |
10250 | +early_init_err: | |
10251 | + if (hibernate_or_resume) { | |
4e97e4e9 | 10252 | + block_dump_save = block_dump; |
f3e0dcc9 PS |
10253 | + set_cpus_allowed(current, CPU_MASK_ALL); |
10254 | + } | |
f3e0dcc9 | 10255 | +prehibernate_err: |
1838f965 | 10256 | + if (hibernate_or_resume) |
10257 | + atomic_inc(&snapshot_device_available); | |
10258 | +snapshotdevice_unavailable: | |
10259 | + if (hibernate_or_resume) | |
10260 | + mutex_unlock(&pm_mutex); | |
f3e0dcc9 PS |
10261 | + set_fs(oldfs); |
10262 | + mutex_unlock(&tuxonice_in_use); | |
4e97e4e9 | 10263 | + return -EBUSY; |
24613191 | 10264 | +} |
4e97e4e9 | 10265 | + |
24613191 | 10266 | +/* |
4e97e4e9 | 10267 | + * Nosave page tracking. |
24613191 | 10268 | + * |
4e97e4e9 | 10269 | + * Here rather than in prepare_image because we want to do it once only at the |
10270 | + * start of a cycle. | |
10271 | + */ | |
4e97e4e9 | 10272 | + |
10273 | +/** | |
10274 | + * mark_nosave_pages - Set up our Nosave bitmap. | |
24613191 | 10275 | + * |
4e97e4e9 | 10276 | + * Build a bitmap of Nosave pages from the list. The bitmap allows faster |
10277 | + * use when preparing the image. | |
24613191 | 10278 | + */ |
4e97e4e9 | 10279 | +static void mark_nosave_pages(void) |
10280 | +{ | |
10281 | + struct nosave_region *region; | |
24613191 | 10282 | + |
4e97e4e9 | 10283 | + list_for_each_entry(region, &nosave_regions, list) { |
10284 | + unsigned long pfn; | |
24613191 | 10285 | + |
4e97e4e9 | 10286 | + for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++) |
1838f965 | 10287 | + if (pfn_valid(pfn)) |
10288 | + SetPageNosave(pfn_to_page(pfn)); | |
4e97e4e9 | 10289 | + } |
10290 | +} | |
24613191 | 10291 | + |
4e97e4e9 | 10292 | +/** |
10293 | + * allocate_bitmaps: Allocate bitmaps used to record page states. | |
10294 | + * | |
10295 | + * Allocate the bitmaps we use to record the various TuxOnIce related | |
10296 | + * page states. | |
10297 | + */ | |
10298 | +static int allocate_bitmaps(void) | |
10299 | +{ | |
1838f965 | 10300 | + if (memory_bm_create(&pageset1_map, GFP_KERNEL, 0) || |
10301 | + memory_bm_create(&pageset1_copy_map, GFP_KERNEL, 0) || | |
10302 | + memory_bm_create(&pageset2_map, GFP_KERNEL, 0) || | |
10303 | + memory_bm_create(&io_map, GFP_KERNEL, 0) || | |
10304 | + memory_bm_create(&nosave_map, GFP_KERNEL, 0) || | |
10305 | + memory_bm_create(&free_map, GFP_KERNEL, 0) || | |
10306 | + memory_bm_create(&page_resave_map, GFP_KERNEL, 0)) | |
4e97e4e9 | 10307 | + return 1; |
24613191 | 10308 | + |
4e97e4e9 | 10309 | + return 0; |
10310 | +} | |
24613191 | 10311 | + |
4e97e4e9 | 10312 | +/** |
10313 | + * free_bitmaps: Free the bitmaps used to record page states. | |
10314 | + * | |
10315 | + * Free the bitmaps allocated above. It is not an error to call | |
1838f965 | 10316 | + * memory_bm_free on a bitmap that isn't currently allocated. |
4e97e4e9 | 10317 | + */ |
10318 | +static void free_bitmaps(void) | |
10319 | +{ | |
1838f965 | 10320 | + memory_bm_free(&pageset1_map, 0); |
10321 | + memory_bm_free(&pageset1_copy_map, 0); | |
10322 | + memory_bm_free(&pageset2_map, 0); | |
10323 | + memory_bm_free(&io_map, 0); | |
10324 | + memory_bm_free(&nosave_map, 0); | |
10325 | + memory_bm_free(&free_map, 0); | |
10326 | + memory_bm_free(&page_resave_map, 0); | |
4e97e4e9 | 10327 | +} |
24613191 | 10328 | + |
4e97e4e9 | 10329 | +/** |
10330 | + * io_MB_per_second: Return the number of MB/s read or written. | |
10331 | + * | |
10332 | + * @write: Whether to return the speed at which we wrote. | |
10333 | + * | |
10334 | + * Calculate the number of megabytes per second that were read or written. | |
10335 | + */ | |
10336 | +static int io_MB_per_second(int write) | |
10337 | +{ | |
ad8f4a28 AM |
10338 | + return (toi_bkd.toi_io_time[write][1]) ? |
10339 | + MB((unsigned long) toi_bkd.toi_io_time[write][0]) * HZ / | |
10340 | + toi_bkd.toi_io_time[write][1] : 0; | |
4e97e4e9 | 10341 | +} |
24613191 | 10342 | + |
4e97e4e9 | 10343 | +/** |
10344 | + * get_debug_info: Fill a buffer with debugging information. | |
10345 | + * | |
10346 | + * @buffer: The buffer to be filled. | |
10347 | + * @count: The size of the buffer, in bytes. | |
10348 | + * | |
10349 | + * Fill a (usually PAGE_SIZEd) buffer with the debugging info that we will | |
10350 | + * either printk or return via sysfs. | |
10351 | + */ | |
1838f965 | 10352 | +#define SNPRINTF(a...) do { len += scnprintf(((char *) buffer) + len, \ |
f3e0dcc9 PS |
10353 | + count - len - 1, ## a); } while (0) |
10354 | + | |
4e97e4e9 | 10355 | +static int get_toi_debug_info(const char *buffer, int count) |
10356 | +{ | |
1838f965 | 10357 | + int len = 0, i, first_result = 1; |
24613191 | 10358 | + |
4e97e4e9 | 10359 | + SNPRINTF("TuxOnIce debugging info:\n"); |
10360 | + SNPRINTF("- TuxOnIce core : " TOI_CORE_VERSION "\n"); | |
10361 | + SNPRINTF("- Kernel Version : " UTS_RELEASE "\n"); | |
10362 | + SNPRINTF("- Compiler vers. : %d.%d\n", __GNUC__, __GNUC_MINOR__); | |
10363 | + SNPRINTF("- Attempt number : %d\n", nr_hibernates); | |
10364 | + SNPRINTF("- Parameters : %ld %ld %ld %d %d %ld\n", | |
10365 | + toi_result, | |
ad8f4a28 AM |
10366 | + toi_bkd.toi_action, |
10367 | + toi_bkd.toi_debug_state, | |
10368 | + toi_bkd.toi_default_console_level, | |
4e97e4e9 | 10369 | + image_size_limit, |
10370 | + toi_poweroff_method); | |
10371 | + SNPRINTF("- Overall expected compression percentage: %d.\n", | |
10372 | + 100 - toi_expected_compression_ratio()); | |
ad8f4a28 | 10373 | + len += toi_print_module_debug_info(((char *) buffer) + len, |
4e97e4e9 | 10374 | + count - len - 1); |
ad8f4a28 | 10375 | + if (toi_bkd.toi_io_time[0][1]) { |
4e97e4e9 | 10376 | + if ((io_MB_per_second(0) < 5) || (io_MB_per_second(1) < 5)) { |
1838f965 | 10377 | + SNPRINTF("- I/O speed: Write %ld KB/s", |
ad8f4a28 AM |
10378 | + (KB((unsigned long) toi_bkd.toi_io_time[0][0]) * HZ / |
10379 | + toi_bkd.toi_io_time[0][1])); | |
10380 | + if (toi_bkd.toi_io_time[1][1]) | |
1838f965 | 10381 | + SNPRINTF(", Read %ld KB/s", |
ad8f4a28 AM |
10382 | + (KB((unsigned long) |
10383 | + toi_bkd.toi_io_time[1][0]) * HZ / | |
10384 | + toi_bkd.toi_io_time[1][1])); | |
4e97e4e9 | 10385 | + } else { |
1838f965 | 10386 | + SNPRINTF("- I/O speed: Write %ld MB/s", |
ad8f4a28 AM |
10387 | + (MB((unsigned long) toi_bkd.toi_io_time[0][0]) * HZ / |
10388 | + toi_bkd.toi_io_time[0][1])); | |
10389 | + if (toi_bkd.toi_io_time[1][1]) | |
1838f965 | 10390 | + SNPRINTF(", Read %ld MB/s", |
ad8f4a28 AM |
10391 | + (MB((unsigned long) |
10392 | + toi_bkd.toi_io_time[1][0]) * HZ / | |
10393 | + toi_bkd.toi_io_time[1][1])); | |
4e97e4e9 | 10394 | + } |
10395 | + SNPRINTF(".\n"); | |
ad8f4a28 | 10396 | + } else |
4e97e4e9 | 10397 | + SNPRINTF("- No I/O speed stats available.\n"); |
7f9d2ee0 | 10398 | + SNPRINTF("- Extra pages : %ld used/%ld.\n", |
4e97e4e9 | 10399 | + extra_pd1_pages_used, extra_pd1_pages_allowance); |
43540741 | 10400 | + |
1838f965 | 10401 | + for (i = 0; i < TOI_NUM_RESULT_STATES; i++) |
10402 | + if (test_result_state(i)) { | |
10403 | + SNPRINTF("%s: %s.\n", first_result ? | |
10404 | + "- Result " : | |
10405 | + " ", | |
10406 | + result_strings[i]); | |
10407 | + first_result = 0; | |
10408 | + } | |
10409 | + if (first_result) | |
10410 | + SNPRINTF("- Result : %s.\n", nr_hibernates ? | |
10411 | + "Succeeded" : | |
10412 | + "No hibernation attempts so far"); | |
4e97e4e9 | 10413 | + return len; |
10414 | +} | |
43540741 | 10415 | + |
4e97e4e9 | 10416 | +/** |
10417 | + * do_cleanup: Cleanup after attempting to hibernate or resume. | |
10418 | + * | |
10419 | + * @get_debug_info: Whether to allocate and return debugging info. | |
10420 | + * | |
10421 | + * Cleanup after attempting to hibernate or resume, possibly getting | |
10422 | + * debugging info as we do so. | |
24613191 | 10423 | + */ |
4e97e4e9 | 10424 | +static void do_cleanup(int get_debug_info) |
10425 | +{ | |
10426 | + int i = 0; | |
10427 | + char *buffer = NULL; | |
24613191 | 10428 | + |
4e97e4e9 | 10429 | + if (get_debug_info) |
10430 | + toi_prepare_status(DONT_CLEAR_BAR, "Cleaning up..."); | |
43540741 | 10431 | + |
4e97e4e9 | 10432 | + free_checksum_pages(); |
43540741 | 10433 | + |
4e97e4e9 | 10434 | + if (get_debug_info) |
10435 | + buffer = (char *) toi_get_zeroed_page(20, TOI_ATOMIC_GFP); | |
24613191 | 10436 | + |
4e97e4e9 | 10437 | + if (buffer) |
10438 | + i = get_toi_debug_info(buffer, PAGE_SIZE); | |
10439 | + | |
10440 | + toi_free_extra_pagedir_memory(); | |
10441 | + | |
10442 | + pagedir1.size = pagedir2.size = 0; | |
10443 | + set_highmem_size(pagedir1, 0); | |
10444 | + set_highmem_size(pagedir2, 0); | |
10445 | + | |
ad8f4a28 | 10446 | + if (boot_kernel_data_buffer) { |
1838f965 | 10447 | + if (!test_toi_state(TOI_BOOT_KERNEL)) |
10448 | + toi_free_page(37, boot_kernel_data_buffer); | |
ad8f4a28 AM |
10449 | + boot_kernel_data_buffer = 0; |
10450 | + } | |
10451 | + | |
1838f965 | 10452 | + clear_toi_state(TOI_BOOT_KERNEL); |
4e97e4e9 | 10453 | + thaw_processes(); |
10454 | + | |
10455 | +#ifdef CONFIG_TOI_KEEP_IMAGE | |
10456 | + if (test_action_state(TOI_KEEP_IMAGE) && | |
10457 | + !test_result_state(TOI_ABORTED)) { | |
10458 | + toi_message(TOI_ANY_SECTION, TOI_LOW, 1, | |
10459 | + "TuxOnIce: Not invalidating the image due " | |
10460 | + "to Keep Image being enabled.\n"); | |
10461 | + set_result_state(TOI_KEPT_IMAGE); | |
10462 | + } else | |
24613191 | 10463 | +#endif |
4e97e4e9 | 10464 | + if (toiActiveAllocator) |
10465 | + toiActiveAllocator->remove_image(); | |
24613191 | 10466 | + |
4e97e4e9 | 10467 | + free_bitmaps(); |
24613191 | 10468 | + |
1838f965 | 10469 | + if (test_toi_state(TOI_NOTIFIERS_PREPARE)) { |
10470 | + pm_notifier_call_chain(PM_POST_HIBERNATION); | |
10471 | + clear_toi_state(TOI_NOTIFIERS_PREPARE); | |
10472 | + } | |
10473 | + | |
4e97e4e9 | 10474 | + if (buffer && i) { |
10475 | + /* Printk can only handle 1023 bytes, including | |
10476 | + * its level mangling. */ | |
10477 | + for (i = 0; i < 3; i++) | |
10478 | + printk("%s", buffer + (1023 * i)); | |
ad8f4a28 | 10479 | + toi_free_page(20, (unsigned long) buffer); |
4e97e4e9 | 10480 | + } |
24613191 | 10481 | + |
4e97e4e9 | 10482 | + if (!test_action_state(TOI_LATE_CPU_HOTPLUG)) |
10483 | + enable_nonboot_cpus(); | |
10484 | + toi_cleanup_console(); | |
24613191 | 10485 | + |
4e97e4e9 | 10486 | + free_attention_list(); |
43540741 | 10487 | + |
4e97e4e9 | 10488 | + toi_deactivate_storage(0); |
43540741 | 10489 | + |
4e97e4e9 | 10490 | + clear_toi_state(TOI_IGNORE_LOGLEVEL); |
10491 | + clear_toi_state(TOI_TRYING_TO_RESUME); | |
10492 | + clear_toi_state(TOI_NOW_RESUMING); | |
43540741 | 10493 | +} |
10494 | + | |
4e97e4e9 | 10495 | +/** |
10496 | + * check_still_keeping_image: We kept an image; check whether to reuse it. | |
10497 | + * | |
10498 | + * We enter this routine when we have kept an image. If the user has said they | |
10499 | + * want to still keep it, all we need to do is powerdown. If powering down | |
10500 | + * means hibernating to ram and the power doesn't run out, we'll return 1. | |
10501 | + * If we do power off properly or the battery runs out, we'll resume via the | |
10502 | + * normal paths. | |
10503 | + * | |
10504 | + * If the user has said they want to remove the previously kept image, we | |
10505 | + * remove it, and return 0. We'll then store a new image. | |
24613191 | 10506 | + */ |
4e97e4e9 | 10507 | +static int check_still_keeping_image(void) |
24613191 | 10508 | +{ |
4e97e4e9 | 10509 | + if (test_action_state(TOI_KEEP_IMAGE)) { |
10510 | + printk("Image already stored: powering down immediately."); | |
10511 | + do_toi_step(STEP_HIBERNATE_POWERDOWN); | |
10512 | + return 1; /* Just in case we're using S3 */ | |
24613191 | 10513 | + } |
10514 | + | |
4e97e4e9 | 10515 | + printk("Invalidating previous image.\n"); |
10516 | + toiActiveAllocator->remove_image(); | |
e8d0ad9d | 10517 | + |
4e97e4e9 | 10518 | + return 0; |
10519 | +} | |
24613191 | 10520 | + |
4e97e4e9 | 10521 | +/** |
10522 | + * toi_init: Prepare to hibernate to disk. | |
10523 | + * | |
10524 | + * Initialise variables & data structures, in preparation for | |
10525 | + * hibernating to disk. | |
10526 | + */ | |
10527 | +static int toi_init(void) | |
10528 | +{ | |
f3e0dcc9 | 10529 | + int result, i, j; |
24613191 | 10530 | + |
4e97e4e9 | 10531 | + toi_result = 0; |
e8d0ad9d | 10532 | + |
4e97e4e9 | 10533 | + printk(KERN_INFO "Initiating a hibernation cycle.\n"); |
e8d0ad9d | 10534 | + |
4e97e4e9 | 10535 | + nr_hibernates++; |
e8d0ad9d | 10536 | + |
f3e0dcc9 PS |
10537 | + for (i = 0; i < 2; i++) |
10538 | + for (j = 0; j < 2; j++) | |
10539 | + toi_bkd.toi_io_time[i][j] = 0; | |
e8d0ad9d | 10540 | + |
4e97e4e9 | 10541 | + if (!test_toi_state(TOI_CAN_HIBERNATE) || |
10542 | + allocate_bitmaps()) | |
10543 | + return 1; | |
e8d0ad9d | 10544 | + |
4e97e4e9 | 10545 | + mark_nosave_pages(); |
e8d0ad9d | 10546 | + |
4e97e4e9 | 10547 | + toi_prepare_console(); |
e8d0ad9d | 10548 | + |
4e97e4e9 | 10549 | + result = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); |
10550 | + if (result) { | |
10551 | + set_result_state(TOI_NOTIFIERS_PREPARE_FAILED); | |
10552 | + return 1; | |
e8d0ad9d | 10553 | + } |
4e97e4e9 | 10554 | + set_toi_state(TOI_NOTIFIERS_PREPARE); |
24613191 | 10555 | + |
ad8f4a28 AM |
10556 | + boot_kernel_data_buffer = toi_get_zeroed_page(37, TOI_ATOMIC_GFP); |
10557 | + if (!boot_kernel_data_buffer) { | |
7f9d2ee0 | 10558 | + printk(KERN_ERR "TuxOnIce: Failed to allocate " |
10559 | + "boot_kernel_data_buffer.\n"); | |
ad8f4a28 AM |
10560 | + set_result_state(TOI_OUT_OF_MEMORY); |
10561 | + return 1; | |
10562 | + } | |
10563 | + | |
4e97e4e9 | 10564 | + if (test_action_state(TOI_LATE_CPU_HOTPLUG) || |
10565 | + !disable_nonboot_cpus()) | |
10566 | + return 1; | |
73c609d5 | 10567 | + |
4e97e4e9 | 10568 | + set_abort_result(TOI_CPU_HOTPLUG_FAILED); |
10569 | + return 0; | |
43540741 | 10570 | +} |
10571 | + | |
4e97e4e9 | 10572 | +/** |
10573 | + * can_hibernate: Perform basic 'Can we hibernate?' tests. | |
24613191 | 10574 | + * |
4e97e4e9 | 10575 | + * Perform basic tests that must pass if we're going to be able to hibernate: |
10576 | + * Can we get the pm_mutex? Is resume= valid (we need to know where to write | |
10577 | + * the image header). | |
24613191 | 10578 | + */ |
4e97e4e9 | 10579 | +static int can_hibernate(void) |
10580 | +{ | |
4e97e4e9 | 10581 | + if (!test_toi_state(TOI_CAN_HIBERNATE)) |
10582 | + toi_attempt_to_parse_resume_device(0); | |
24613191 | 10583 | + |
4e97e4e9 | 10584 | + if (!test_toi_state(TOI_CAN_HIBERNATE)) { |
ad8f4a28 | 10585 | + printk(KERN_INFO "TuxOnIce: Hibernation is disabled.\n" |
4e97e4e9 | 10586 | + "This may be because you haven't put something along " |
10587 | + "the lines of\n\nresume=swap:/dev/hda1\n\n" | |
10588 | + "in lilo.conf or equivalent. (Where /dev/hda1 is your " | |
10589 | + "swap partition).\n"); | |
10590 | + set_abort_result(TOI_CANT_SUSPEND); | |
4e97e4e9 | 10591 | + return 0; |
10592 | + } | |
24613191 | 10593 | + |
1838f965 | 10594 | + if (strlen(alt_resume_param)) { |
10595 | + attempt_to_parse_alt_resume_param(); | |
10596 | + | |
10597 | + if (!strlen(alt_resume_param)) { | |
10598 | + printk(KERN_INFO "Alternate resume parameter now " | |
10599 | + "invalid. Aborting.\n"); | |
10600 | + set_abort_result(TOI_CANT_USE_ALT_RESUME); | |
10601 | + return 0; | |
10602 | + } | |
10603 | + } | |
10604 | + | |
4e97e4e9 | 10605 | + return 1; |
10606 | +} | |
e8d0ad9d | 10607 | + |
4e97e4e9 | 10608 | +/** |
10609 | + * do_post_image_write: Having written an image, figure out what to do next. | |
10610 | + * | |
10611 | + * After writing an image, we might load an alternate image or power down. | |
10612 | + * Powering down might involve hibernating to ram, in which case we also | |
10613 | + * need to handle reloading pageset2. | |
e8d0ad9d | 10614 | + */ |
4e97e4e9 | 10615 | +static int do_post_image_write(void) |
10616 | +{ | |
10617 | + /* If switching images fails, do normal powerdown */ | |
10618 | + if (alt_resume_param[0]) | |
10619 | + do_toi_step(STEP_RESUME_ALT_IMAGE); | |
24613191 | 10620 | + |
4e97e4e9 | 10621 | + toi_power_down(); |
24613191 | 10622 | + |
4e97e4e9 | 10623 | + barrier(); |
10624 | + mb(); | |
10625 | + do_cleanup(1); | |
10626 | + return 0; | |
10627 | +} | |
24613191 | 10628 | + |
4e97e4e9 | 10629 | +/** |
10630 | + * __save_image: Do the hard work of saving the image. | |
e8d0ad9d | 10631 | + * |
4e97e4e9 | 10632 | + * High level routine for getting the image saved. The key assumptions made |
10633 | + * are that processes have been frozen and sufficient memory is available. | |
10634 | + * | |
10635 | + * We also exit through here at resume time, coming back from toi_hibernate | |
10636 | + * after the atomic restore. This is the reason for the toi_in_hibernate | |
10637 | + * test. | |
24613191 | 10638 | + */ |
4e97e4e9 | 10639 | +static int __save_image(void) |
24613191 | 10640 | +{ |
4e97e4e9 | 10641 | + int temp_result, did_copy = 0; |
24613191 | 10642 | + |
4e97e4e9 | 10643 | + toi_prepare_status(DONT_CLEAR_BAR, "Starting to save the image.."); |
24613191 | 10644 | + |
4e97e4e9 | 10645 | + toi_message(TOI_ANY_SECTION, TOI_LOW, 1, |
10646 | + " - Final values: %d and %d.\n", | |
10647 | + pagedir1.size, pagedir2.size); | |
e8d0ad9d | 10648 | + |
4e97e4e9 | 10649 | + toi_cond_pause(1, "About to write pagedir2."); |
24613191 | 10650 | + |
4e97e4e9 | 10651 | + temp_result = write_pageset(&pagedir2); |
24613191 | 10652 | + |
4e97e4e9 | 10653 | + if (temp_result == -1 || test_result_state(TOI_ABORTED)) |
10654 | + return 1; | |
24613191 | 10655 | + |
4e97e4e9 | 10656 | + toi_cond_pause(1, "About to copy pageset 1."); |
24613191 | 10657 | + |
4e97e4e9 | 10658 | + if (test_result_state(TOI_ABORTED)) |
10659 | + return 1; | |
24613191 | 10660 | + |
4e97e4e9 | 10661 | + toi_deactivate_storage(1); |
e8d0ad9d | 10662 | + |
4e97e4e9 | 10663 | + toi_prepare_status(DONT_CLEAR_BAR, "Doing atomic copy."); |
e8d0ad9d | 10664 | + |
4e97e4e9 | 10665 | + toi_in_hibernate = 1; |
24613191 | 10666 | + |
4e97e4e9 | 10667 | + if (toi_go_atomic(PMSG_FREEZE, 1)) |
10668 | + goto Failed; | |
24613191 | 10669 | + |
4e97e4e9 | 10670 | + temp_result = toi_hibernate(); |
10671 | + if (!temp_result) | |
10672 | + did_copy = 1; | |
24613191 | 10673 | + |
4e97e4e9 | 10674 | + /* We return here at resume time too! */ |
fea155ea | 10675 | + toi_end_atomic(ATOMIC_ALL_STEPS, toi_in_hibernate, temp_result); |
24613191 | 10676 | + |
4e97e4e9 | 10677 | +Failed: |
10678 | + if (toi_activate_storage(1)) | |
10679 | + panic("Failed to reactivate our storage."); | |
24613191 | 10680 | + |
4e97e4e9 | 10681 | + /* Resume time? */ |
10682 | + if (!toi_in_hibernate) { | |
10683 | + copyback_post(); | |
10684 | + return 0; | |
10685 | + } | |
24613191 | 10686 | + |
4e97e4e9 | 10687 | + /* Nope. Hibernating. So, see if we can save the image... */ |
24613191 | 10688 | + |
4e97e4e9 | 10689 | + if (temp_result || test_result_state(TOI_ABORTED)) { |
10690 | + if (did_copy) | |
10691 | + goto abort_reloading_pagedir_two; | |
10692 | + else | |
10693 | + return 1; | |
24613191 | 10694 | + } |
10695 | + | |
f3e0dcc9 | 10696 | + toi_update_status(pagedir2.size, pagedir1.size + pagedir2.size, |
4e97e4e9 | 10697 | + NULL); |
e8d0ad9d | 10698 | + |
4e97e4e9 | 10699 | + if (test_result_state(TOI_ABORTED)) |
10700 | + goto abort_reloading_pagedir_two; | |
e8d0ad9d | 10701 | + |
4e97e4e9 | 10702 | + toi_cond_pause(1, "About to write pageset1."); |
e8d0ad9d | 10703 | + |
f3e0dcc9 | 10704 | + toi_message(TOI_ANY_SECTION, TOI_LOW, 1, "-- Writing pageset1\n"); |
e8d0ad9d | 10705 | + |
4e97e4e9 | 10706 | + temp_result = write_pageset(&pagedir1); |
e8d0ad9d | 10707 | + |
4e97e4e9 | 10708 | + /* We didn't overwrite any memory, so no reread needs to be done. */ |
10709 | + if (test_action_state(TOI_TEST_FILTER_SPEED)) | |
10710 | + return 1; | |
e8d0ad9d | 10711 | + |
4e97e4e9 | 10712 | + if (temp_result == 1 || test_result_state(TOI_ABORTED)) |
10713 | + goto abort_reloading_pagedir_two; | |
e8d0ad9d | 10714 | + |
4e97e4e9 | 10715 | + toi_cond_pause(1, "About to write header."); |
e8d0ad9d | 10716 | + |
4e97e4e9 | 10717 | + if (test_result_state(TOI_ABORTED)) |
10718 | + goto abort_reloading_pagedir_two; | |
e8d0ad9d | 10719 | + |
4e97e4e9 | 10720 | + temp_result = write_image_header(); |
e8d0ad9d | 10721 | + |
4e97e4e9 | 10722 | + if (test_action_state(TOI_TEST_BIO)) |
10723 | + return 1; | |
24613191 | 10724 | + |
4e97e4e9 | 10725 | + if (!temp_result && !test_result_state(TOI_ABORTED)) |
10726 | + return 0; | |
24613191 | 10727 | + |
4e97e4e9 | 10728 | +abort_reloading_pagedir_two: |
10729 | + temp_result = read_pageset2(1); | |
24613191 | 10730 | + |
4e97e4e9 | 10731 | + /* If that failed, we're sunk. Panic! */ |
10732 | + if (temp_result) | |
10733 | + panic("Attempt to reload pagedir 2 while aborting " | |
10734 | + "a hibernate failed."); | |
10735 | + | |
10736 | + return 1; | |
24613191 | 10737 | +} |
10738 | + | |
4e97e4e9 | 10739 | +/** |
10740 | + * do_save_image: Save the image and handle the result. | |
e8d0ad9d | 10741 | + * |
4e97e4e9 | 10742 | + * Save the prepared image. If we fail or we're in the path returning |
10743 | + * from the atomic restore, cleanup. | |
e8d0ad9d | 10744 | + */ |
24613191 | 10745 | + |
4e97e4e9 | 10746 | +static int do_save_image(void) |
24613191 | 10747 | +{ |
4e97e4e9 | 10748 | + int result = __save_image(); |
10749 | + if (!toi_in_hibernate || result) | |
10750 | + do_cleanup(1); | |
10751 | + return result; | |
24613191 | 10752 | +} |
10753 | + | |
4e97e4e9 | 10754 | +/** |
10755 | + * do_prepare_image: Try to prepare an image. | |
10756 | + * | |
10757 | + * Seek to initialise and prepare an image to be saved. On failure, | |
10758 | + * cleanup. | |
10759 | + */ | |
24613191 | 10760 | + |
4e97e4e9 | 10761 | +static int do_prepare_image(void) |
10762 | +{ | |
10763 | + if (toi_activate_storage(0)) | |
10764 | + return 1; | |
24613191 | 10765 | + |
4e97e4e9 | 10766 | + /* |
10767 | + * If kept image and still keeping image and hibernating to RAM, we will | |
10768 | + * return 1 after hibernating and resuming (provided the power doesn't | |
10769 | + * run out. In that case, we skip directly to cleaning up and exiting. | |
10770 | + */ | |
10771 | + | |
10772 | + if (!can_hibernate() || | |
10773 | + (test_result_state(TOI_KEPT_IMAGE) && | |
10774 | + check_still_keeping_image())) | |
10775 | + goto cleanup; | |
10776 | + | |
10777 | + if (toi_init() && !toi_prepare_image() && | |
10778 | + !test_result_state(TOI_ABORTED)) | |
10779 | + return 0; | |
10780 | + | |
10781 | +cleanup: | |
10782 | + do_cleanup(0); | |
10783 | + return 1; | |
24613191 | 10784 | +} |
10785 | + | |
4e97e4e9 | 10786 | +/** |
10787 | + * do_check_can_resume: Find out whether an image has been stored. | |
e8d0ad9d | 10788 | + * |
4e97e4e9 | 10789 | + * Read whether an image exists. We use the same routine as the |
10790 | + * image_exists sysfs entry, and just look to see whether the | |
10791 | + * first character in the resulting buffer is a '1'. | |
e8d0ad9d | 10792 | + */ |
ad8f4a28 | 10793 | +int do_check_can_resume(void) |
24613191 | 10794 | +{ |
4e97e4e9 | 10795 | + char *buf = (char *) toi_get_zeroed_page(21, TOI_ATOMIC_GFP); |
10796 | + int result = 0; | |
10797 | + | |
10798 | + if (!buf) | |
10799 | + return 0; | |
10800 | + | |
10801 | + /* Only interested in first byte, so throw away return code. */ | |
10802 | + image_exists_read(buf, PAGE_SIZE); | |
10803 | + | |
10804 | + if (buf[0] == '1') | |
10805 | + result = 1; | |
10806 | + | |
ad8f4a28 | 10807 | + toi_free_page(21, (unsigned long) buf); |
4e97e4e9 | 10808 | + return result; |
24613191 | 10809 | +} |
1838f965 | 10810 | +EXPORT_SYMBOL_GPL(do_check_can_resume); |
24613191 | 10811 | + |
4e97e4e9 | 10812 | +/** |
10813 | + * do_load_atomic_copy: Load the first part of an image, if it exists. | |
10814 | + * | |
10815 | + * Check whether we have an image. If one exists, do sanity checking | |
10816 | + * (possibly invalidating the image or even rebooting if the user | |
10817 | + * requests that) before loading it into memory in preparation for the | |
10818 | + * atomic restore. | |
10819 | + * | |
10820 | + * If and only if we have an image loaded and ready to restore, we return 1. | |
10821 | + */ | |
10822 | +static int do_load_atomic_copy(void) | |
24613191 | 10823 | +{ |
4e97e4e9 | 10824 | + int read_image_result = 0; |
10825 | + | |
10826 | + if (sizeof(swp_entry_t) != sizeof(long)) { | |
10827 | + printk(KERN_WARNING "TuxOnIce: The size of swp_entry_t != size" | |
10828 | + " of long. Please report this!\n"); | |
10829 | + return 1; | |
10830 | + } | |
24613191 | 10831 | + |
4e97e4e9 | 10832 | + if (!resume_file[0]) |
10833 | + printk(KERN_WARNING "TuxOnIce: " | |
10834 | + "You need to use a resume= command line parameter to " | |
10835 | + "tell TuxOnIce where to look for an image.\n"); | |
e8d0ad9d | 10836 | + |
4e97e4e9 | 10837 | + toi_activate_storage(0); |
24613191 | 10838 | + |
4e97e4e9 | 10839 | + if (!(test_toi_state(TOI_RESUME_DEVICE_OK)) && |
10840 | + !toi_attempt_to_parse_resume_device(0)) { | |
10841 | + /* | |
10842 | + * Without a usable storage device we can do nothing - | |
10843 | + * even if noresume is given | |
10844 | + */ | |
24613191 | 10845 | + |
4e97e4e9 | 10846 | + if (!toiNumAllocators) |
10847 | + printk(KERN_ALERT "TuxOnIce: " | |
10848 | + "No storage allocators have been registered.\n"); | |
10849 | + else | |
10850 | + printk(KERN_ALERT "TuxOnIce: " | |
10851 | + "Missing or invalid storage location " | |
10852 | + "(resume= parameter). Please correct and " | |
10853 | + "rerun lilo (or equivalent) before " | |
10854 | + "hibernating.\n"); | |
10855 | + toi_deactivate_storage(0); | |
10856 | + return 1; | |
10857 | + } | |
24613191 | 10858 | + |
4e97e4e9 | 10859 | + read_image_result = read_pageset1(); /* non fatal error ignored */ |
24613191 | 10860 | + |
4e97e4e9 | 10861 | + if (test_toi_state(TOI_NORESUME_SPECIFIED)) |
10862 | + clear_toi_state(TOI_NORESUME_SPECIFIED); | |
24613191 | 10863 | + |
4e97e4e9 | 10864 | + toi_deactivate_storage(0); |
24613191 | 10865 | + |
4e97e4e9 | 10866 | + if (read_image_result) |
10867 | + return 1; | |
10868 | + | |
10869 | + return 0; | |
24613191 | 10870 | +} |
10871 | + | |
4e97e4e9 | 10872 | +/** |
10873 | + * prepare_restore_load_alt_image: Save & restore alt image variables. | |
24613191 | 10874 | + * |
4e97e4e9 | 10875 | + * Save and restore the pageset1 maps, when loading an alternate image. |
24613191 | 10876 | + */ |
4e97e4e9 | 10877 | +static void prepare_restore_load_alt_image(int prepare) |
24613191 | 10878 | +{ |
1838f965 | 10879 | + static struct memory_bitmap pageset1_map_save, pageset1_copy_map_save; |
24613191 | 10880 | + |
4e97e4e9 | 10881 | + if (prepare) { |
10882 | + memcpy(&pageset1_map_save, &pageset1_map, | |
1838f965 | 10883 | + sizeof(struct memory_bitmap)); |
10884 | + memset(&pageset1_map, 0, sizeof(struct memory_bitmap)); | |
4e97e4e9 | 10885 | + memcpy(&pageset1_copy_map_save, &pageset1_copy_map, |
1838f965 | 10886 | + sizeof(struct memory_bitmap)); |
10887 | + memset(&pageset1_copy_map, 0, sizeof(struct memory_bitmap)); | |
4e97e4e9 | 10888 | + set_toi_state(TOI_LOADING_ALT_IMAGE); |
10889 | + toi_reset_alt_image_pageset2_pfn(); | |
10890 | + } else { | |
1838f965 | 10891 | + memory_bm_free(&pageset1_map, 0); |
4e97e4e9 | 10892 | + memcpy(&pageset1_map, &pageset1_map_save, |
1838f965 | 10893 | + sizeof(struct memory_bitmap)); |
10894 | + memory_bm_free(&pageset1_copy_map, 0); | |
4e97e4e9 | 10895 | + memcpy(&pageset1_copy_map, &pageset1_copy_map_save, |
1838f965 | 10896 | + sizeof(struct memory_bitmap)); |
4e97e4e9 | 10897 | + clear_toi_state(TOI_NOW_RESUMING); |
10898 | + clear_toi_state(TOI_LOADING_ALT_IMAGE); | |
10899 | + } | |
10900 | +} | |
24613191 | 10901 | + |
4e97e4e9 | 10902 | +/** |
4e97e4e9 | 10903 | + * do_toi_step: Perform a step in hibernating or resuming. |
10904 | + * | |
10905 | + * Perform a step in hibernating or resuming an image. This abstraction | |
10906 | + * is in preparation for implementing cluster support, and perhaps replacing | |
10907 | + * uswsusp too (haven't looked whether that's possible yet). | |
24613191 | 10908 | + */ |
4e97e4e9 | 10909 | +int do_toi_step(int step) |
24613191 | 10910 | +{ |
4e97e4e9 | 10911 | + switch (step) { |
ad8f4a28 AM |
10912 | + case STEP_HIBERNATE_PREPARE_IMAGE: |
10913 | + return do_prepare_image(); | |
10914 | + case STEP_HIBERNATE_SAVE_IMAGE: | |
10915 | + return do_save_image(); | |
10916 | + case STEP_HIBERNATE_POWERDOWN: | |
10917 | + return do_post_image_write(); | |
10918 | + case STEP_RESUME_CAN_RESUME: | |
10919 | + return do_check_can_resume(); | |
10920 | + case STEP_RESUME_LOAD_PS1: | |
10921 | + return do_load_atomic_copy(); | |
10922 | + case STEP_RESUME_DO_RESTORE: | |
10923 | + /* | |
10924 | + * If we succeed, this doesn't return. | |
10925 | + * Instead, we return from do_save_image() in the | |
10926 | + * hibernated kernel. | |
10927 | + */ | |
10928 | + return toi_atomic_restore(); | |
10929 | + case STEP_RESUME_ALT_IMAGE: | |
10930 | + printk(KERN_INFO "Trying to resume alternate image.\n"); | |
10931 | + toi_in_hibernate = 0; | |
10932 | + save_restore_alt_param(SAVE, NOQUIET); | |
10933 | + prepare_restore_load_alt_image(1); | |
10934 | + if (!do_check_can_resume()) { | |
10935 | + printk(KERN_INFO "Nothing to resume from.\n"); | |
10936 | + goto out; | |
10937 | + } | |
10938 | + if (!do_load_atomic_copy()) | |
10939 | + toi_atomic_restore(); | |
10940 | + | |
10941 | + printk(KERN_INFO "Failed to load image.\n"); | |
4e97e4e9 | 10942 | +out: |
ad8f4a28 AM |
10943 | + prepare_restore_load_alt_image(0); |
10944 | + save_restore_alt_param(RESTORE, NOQUIET); | |
10945 | + break; | |
10946 | + case STEP_CLEANUP: | |
10947 | + do_cleanup(1); | |
10948 | + break; | |
10949 | + case STEP_QUIET_CLEANUP: | |
10950 | + do_cleanup(0); | |
10951 | + break; | |
4e97e4e9 | 10952 | + } |
24613191 | 10953 | + |
4e97e4e9 | 10954 | + return 0; |
24613191 | 10955 | +} |
ad8f4a28 | 10956 | +EXPORT_SYMBOL_GPL(do_toi_step); |
24613191 | 10957 | + |
4e97e4e9 | 10958 | +/* -- Functions for kickstarting a hibernate or resume --- */ |
10959 | + | |
10960 | +/** | |
10961 | + * __toi_try_resume: Try to do the steps in resuming. | |
24613191 | 10962 | + * |
4e97e4e9 | 10963 | + * Check if we have an image and if so try to resume. Clear the status |
10964 | + * flags too. | |
24613191 | 10965 | + */ |
4e97e4e9 | 10966 | +void __toi_try_resume(void) |
24613191 | 10967 | +{ |
4e97e4e9 | 10968 | + set_toi_state(TOI_TRYING_TO_RESUME); |
10969 | + resume_attempted = 1; | |
24613191 | 10970 | + |
4e97e4e9 | 10971 | + current->flags |= PF_MEMALLOC; |
24613191 | 10972 | + |
4e97e4e9 | 10973 | + if (do_toi_step(STEP_RESUME_CAN_RESUME) && |
1838f965 | 10974 | + !do_toi_step(STEP_RESUME_LOAD_PS1)) |
10975 | + do_toi_step(STEP_RESUME_DO_RESTORE); | |
24613191 | 10976 | + |
4e97e4e9 | 10977 | + do_cleanup(0); |
24613191 | 10978 | + |
4e97e4e9 | 10979 | + current->flags &= ~PF_MEMALLOC; |
24613191 | 10980 | + |
4e97e4e9 | 10981 | + clear_toi_state(TOI_IGNORE_LOGLEVEL); |
10982 | + clear_toi_state(TOI_TRYING_TO_RESUME); | |
10983 | + clear_toi_state(TOI_NOW_RESUMING); | |
10984 | +} | |
24613191 | 10985 | + |
4e97e4e9 | 10986 | +/** |
10987 | + * _toi_try_resume: Wrapper calling __toi_try_resume from do_mounts. | |
10988 | + * | |
10989 | + * Wrapper for when __toi_try_resume is called from init/do_mounts.c, | |
10990 | + * rather than from echo > /sys/power/tuxonice/do_resume. | |
10991 | + */ | |
1838f965 | 10992 | +static void _toi_try_resume(void) |
4e97e4e9 | 10993 | +{ |
10994 | + resume_attempted = 1; | |
24613191 | 10995 | + |
7f9d2ee0 | 10996 | + /* |
10997 | + * There's a comment in kernel/power/disk.c that indicates | |
10998 | + * we should be able to use mutex_lock_nested below. That | |
10999 | + * doesn't seem to cut it, though, so let's just turn lockdep | |
11000 | + * off for now. | |
11001 | + */ | |
11002 | + lockdep_off(); | |
11003 | + | |
4e97e4e9 | 11004 | + if (toi_start_anything(SYSFS_RESUMING)) |
7f9d2ee0 | 11005 | + goto out; |
24613191 | 11006 | + |
4e97e4e9 | 11007 | + __toi_try_resume(); |
24613191 | 11008 | + |
4e97e4e9 | 11009 | + /* |
11010 | + * For initramfs, we have to clear the boot time | |
11011 | + * flag after trying to resume | |
11012 | + */ | |
11013 | + clear_toi_state(TOI_BOOT_TIME); | |
7f9d2ee0 | 11014 | + |
4e97e4e9 | 11015 | + toi_finish_anything(SYSFS_RESUMING); |
1838f965 | 11016 | +out: |
7f9d2ee0 | 11017 | + lockdep_on(); |
4e97e4e9 | 11018 | +} |
24613191 | 11019 | + |
4e97e4e9 | 11020 | +/** |
11021 | + * _toi_try_hibernate: Try to start a hibernation cycle. | |
11022 | + * | |
11023 | + * have_pmsem: Whther the pm_sem is already taken. | |
11024 | + * | |
11025 | + * Start a hibernation cycle, coming in from either | |
11026 | + * echo > /sys/power/tuxonice/do_suspend | |
11027 | + * | |
11028 | + * or | |
11029 | + * | |
11030 | + * echo disk > /sys/power/state | |
11031 | + * | |
11032 | + * In the later case, we come in without pm_sem taken; in the | |
11033 | + * former, it has been taken. | |
11034 | + */ | |
1838f965 | 11035 | +int _toi_try_hibernate(void) |
4e97e4e9 | 11036 | +{ |
11037 | + int result = 0, sys_power_disk = 0; | |
24613191 | 11038 | + |
f3e0dcc9 | 11039 | + if (!mutex_is_locked(&tuxonice_in_use)) { |
4e97e4e9 | 11040 | + /* Came in via /sys/power/disk */ |
11041 | + if (toi_start_anything(SYSFS_HIBERNATING)) | |
11042 | + return -EBUSY; | |
11043 | + sys_power_disk = 1; | |
11044 | + } | |
24613191 | 11045 | + |
4e97e4e9 | 11046 | + current->flags |= PF_MEMALLOC; |
e8d0ad9d | 11047 | + |
ad8f4a28 AM |
11048 | + if (test_toi_state(TOI_CLUSTER_MODE)) { |
11049 | + toi_initiate_cluster_hibernate(); | |
11050 | + goto out; | |
11051 | + } | |
11052 | + | |
11053 | + result = do_toi_step(STEP_HIBERNATE_PREPARE_IMAGE); | |
11054 | + if (result) | |
4e97e4e9 | 11055 | + goto out; |
24613191 | 11056 | + |
4e97e4e9 | 11057 | + if (test_action_state(TOI_FREEZER_TEST)) { |
11058 | + do_cleanup(0); | |
11059 | + goto out; | |
24613191 | 11060 | + } |
24613191 | 11061 | + |
ad8f4a28 | 11062 | + result = do_toi_step(STEP_HIBERNATE_SAVE_IMAGE); |
ad8f4a28 AM |
11063 | + |
11064 | + /* This code runs at resume time too! */ | |
1838f965 | 11065 | + if (!result && toi_in_hibernate) |
ad8f4a28 AM |
11066 | + result = do_toi_step(STEP_HIBERNATE_POWERDOWN); |
11067 | +out: | |
11068 | + current->flags &= ~PF_MEMALLOC; | |
11069 | + | |
11070 | + if (sys_power_disk) | |
11071 | + toi_finish_anything(SYSFS_HIBERNATING); | |
11072 | + | |
11073 | + return result; | |
11074 | +} | |
11075 | + | |
11076 | +/* | |
11077 | + * channel_no: If !0, -c <channel_no> is added to args (userui). | |
11078 | + */ | |
11079 | +int toi_launch_userspace_program(char *command, int channel_no, | |
1838f965 | 11080 | + enum umh_wait wait, int debug) |
ad8f4a28 AM |
11081 | +{ |
11082 | + int retval; | |
11083 | + static char *envp[] = { | |
11084 | + "HOME=/", | |
11085 | + "TERM=linux", | |
11086 | + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", | |
11087 | + NULL }; | |
11088 | + static char *argv[] = | |
11089 | + { NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL }; | |
11090 | + char *channel = NULL; | |
11091 | + int arg = 0, size; | |
11092 | + char test_read[255]; | |
11093 | + char *orig_posn = command; | |
11094 | + | |
11095 | + if (!strlen(orig_posn)) | |
11096 | + return 1; | |
11097 | + | |
11098 | + if (channel_no) { | |
11099 | + channel = toi_kzalloc(4, 6, GFP_KERNEL); | |
11100 | + if (!channel) { | |
11101 | + printk(KERN_INFO "Failed to allocate memory in " | |
11102 | + "preparing to launch userspace program.\n"); | |
11103 | + return 1; | |
11104 | + } | |
11105 | + } | |
11106 | + | |
1838f965 | 11107 | + /* Up to 6 args supported */ |
11108 | + while (arg < 6) { | |
ad8f4a28 AM |
11109 | + sscanf(orig_posn, "%s", test_read); |
11110 | + size = strlen(test_read); | |
11111 | + if (!(size)) | |
11112 | + break; | |
11113 | + argv[arg] = toi_kzalloc(5, size + 1, TOI_ATOMIC_GFP); | |
11114 | + strcpy(argv[arg], test_read); | |
11115 | + orig_posn += size + 1; | |
11116 | + *test_read = 0; | |
11117 | + arg++; | |
11118 | + } | |
11119 | + | |
11120 | + if (channel_no) { | |
11121 | + sprintf(channel, "-c%d", channel_no); | |
11122 | + argv[arg] = channel; | |
11123 | + } else | |
11124 | + arg--; | |
11125 | + | |
1838f965 | 11126 | + if (debug) { |
11127 | + argv[++arg] = toi_kzalloc(5, 8, TOI_ATOMIC_GFP); | |
11128 | + strcpy(argv[arg], "--debug"); | |
11129 | + } | |
11130 | + | |
ad8f4a28 AM |
11131 | + retval = call_usermodehelper(argv[0], argv, envp, wait); |
11132 | + | |
7f9d2ee0 | 11133 | + /* |
ad8f4a28 AM |
11134 | + * If the program reports an error, retval = 256. Don't complain |
11135 | + * about that here. | |
11136 | + */ | |
11137 | + if (retval && retval != 256) | |
11138 | + printk("Failed to launch userspace program '%s': Error %d\n", | |
11139 | + command, retval); | |
11140 | + | |
11141 | + { | |
11142 | + int i; | |
11143 | + for (i = 0; i < arg; i++) | |
11144 | + if (argv[i] && argv[i] != channel) | |
11145 | + toi_kfree(5, argv[i]); | |
11146 | + } | |
11147 | + | |
11148 | + toi_kfree(4, channel); | |
4e97e4e9 | 11149 | + |
ad8f4a28 | 11150 | + return retval; |
24613191 | 11151 | +} |
11152 | + | |
4e97e4e9 | 11153 | +/* |
11154 | + * This array contains entries that are automatically registered at | |
11155 | + * boot. Modules and the console code register their own entries separately. | |
24613191 | 11156 | + */ |
4e97e4e9 | 11157 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 11158 | + SYSFS_LONG("extra_pages_allowance", SYSFS_RW, |
11159 | + &extra_pd1_pages_allowance, 0, LONG_MAX, 0), | |
11160 | + SYSFS_CUSTOM("image_exists", SYSFS_RW, image_exists_read, | |
11161 | + image_exists_write, SYSFS_NEEDS_SM_FOR_BOTH, NULL), | |
11162 | + SYSFS_STRING("resume", SYSFS_RW, resume_file, 255, | |
11163 | + SYSFS_NEEDS_SM_FOR_WRITE, | |
11164 | + attempt_to_parse_resume_device2), | |
11165 | + SYSFS_STRING("alt_resume_param", SYSFS_RW, alt_resume_param, 255, | |
11166 | + SYSFS_NEEDS_SM_FOR_WRITE, | |
11167 | + attempt_to_parse_alt_resume_param), | |
11168 | + SYSFS_CUSTOM("debug_info", SYSFS_READONLY, get_toi_debug_info, NULL, 0, | |
11169 | + NULL), | |
11170 | + SYSFS_BIT("ignore_rootfs", SYSFS_RW, &toi_bkd.toi_action, | |
11171 | + TOI_IGNORE_ROOTFS, 0), | |
11172 | + SYSFS_INT("image_size_limit", SYSFS_RW, &image_size_limit, -2, | |
11173 | + INT_MAX, 0, NULL), | |
11174 | + SYSFS_UL("last_result", SYSFS_RW, &toi_result, 0, 0, 0), | |
11175 | + SYSFS_BIT("no_multithreaded_io", SYSFS_RW, &toi_bkd.toi_action, | |
11176 | + TOI_NO_MULTITHREADED_IO, 0), | |
11177 | + SYSFS_BIT("no_flusher_thread", SYSFS_RW, &toi_bkd.toi_action, | |
11178 | + TOI_NO_FLUSHER_THREAD, 0), | |
11179 | + SYSFS_BIT("full_pageset2", SYSFS_RW, &toi_bkd.toi_action, | |
11180 | + TOI_PAGESET2_FULL, 0), | |
11181 | + SYSFS_BIT("reboot", SYSFS_RW, &toi_bkd.toi_action, TOI_REBOOT, 0), | |
11182 | + SYSFS_BIT("replace_swsusp", SYSFS_RW, &toi_bkd.toi_action, | |
11183 | + TOI_REPLACE_SWSUSP, 0), | |
11184 | + SYSFS_STRING("resume_commandline", SYSFS_RW, | |
11185 | + toi_bkd.toi_nosave_commandline, COMMAND_LINE_SIZE, 0, | |
11186 | + NULL), | |
11187 | + SYSFS_STRING("version", SYSFS_READONLY, TOI_CORE_VERSION, 0, 0, NULL), | |
11188 | + SYSFS_BIT("no_load_direct", SYSFS_RW, &toi_bkd.toi_action, | |
11189 | + TOI_NO_DIRECT_LOAD, 0), | |
11190 | + SYSFS_BIT("freezer_test", SYSFS_RW, &toi_bkd.toi_action, | |
11191 | + TOI_FREEZER_TEST, 0), | |
11192 | + SYSFS_BIT("test_bio", SYSFS_RW, &toi_bkd.toi_action, TOI_TEST_BIO, 0), | |
11193 | + SYSFS_BIT("test_filter_speed", SYSFS_RW, &toi_bkd.toi_action, | |
11194 | + TOI_TEST_FILTER_SPEED, 0), | |
11195 | + SYSFS_BIT("no_pageset2", SYSFS_RW, &toi_bkd.toi_action, | |
11196 | + TOI_NO_PAGESET2, 0), | |
11197 | + SYSFS_BIT("no_pageset2_if_unneeded", SYSFS_RW, &toi_bkd.toi_action, | |
11198 | + TOI_NO_PS2_IF_UNNEEDED, 0), | |
11199 | + SYSFS_BIT("late_cpu_hotplug", SYSFS_RW, &toi_bkd.toi_action, | |
11200 | + TOI_LATE_CPU_HOTPLUG, 0), | |
11201 | + SYSFS_STRING("pre_hibernate_command", SYSFS_RW, pre_hibernate_command, | |
11202 | + 0, 255, NULL), | |
11203 | + SYSFS_STRING("post_hibernate_command", SYSFS_RW, post_hibernate_command, | |
11204 | + 0, 255, NULL), | |
4e97e4e9 | 11205 | +#ifdef CONFIG_TOI_KEEP_IMAGE |
1838f965 | 11206 | + SYSFS_BIT("keep_image", SYSFS_RW , &toi_bkd.toi_action, TOI_KEEP_IMAGE, |
11207 | + 0), | |
4e97e4e9 | 11208 | +#endif |
11209 | +}; | |
e8d0ad9d | 11210 | + |
1838f965 | 11211 | +static struct toi_core_fns my_fns = { |
4e97e4e9 | 11212 | + .get_nonconflicting_page = __toi_get_nonconflicting_page, |
11213 | + .post_context_save = __toi_post_context_save, | |
11214 | + .try_hibernate = _toi_try_hibernate, | |
11215 | + .try_resume = _toi_try_resume, | |
11216 | +}; | |
e8d0ad9d | 11217 | + |
4e97e4e9 | 11218 | +/** |
11219 | + * core_load: Initialisation of TuxOnIce core. | |
11220 | + * | |
11221 | + * Initialise the core, beginning with sysfs. Checksum and so on are part of | |
11222 | + * the core, but have their own initialisation routines because they either | |
11223 | + * aren't compiled in all the time or have their own subdirectories. | |
11224 | + */ | |
11225 | +static __init int core_load(void) | |
11226 | +{ | |
11227 | + int i, | |
11228 | + numfiles = sizeof(sysfs_params) / sizeof(struct toi_sysfs_data); | |
24613191 | 11229 | + |
f3e0dcc9 PS |
11230 | + printk(KERN_INFO "TuxOnIce " TOI_CORE_VERSION |
11231 | + " (http://tuxonice.net)\n"); | |
ad8f4a28 AM |
11232 | + strncpy(pre_hibernate_command, CONFIG_TOI_DEFAULT_PRE_HIBERNATE, 255); |
11233 | + strncpy(post_hibernate_command, CONFIG_TOI_DEFAULT_POST_HIBERNATE, 255); | |
11234 | + | |
4e97e4e9 | 11235 | + if (toi_sysfs_init()) |
11236 | + return 1; | |
24613191 | 11237 | + |
ad8f4a28 | 11238 | + for (i = 0; i < numfiles; i++) |
7f9d2ee0 | 11239 | + toi_register_sysfs_file(tuxonice_kobj, &sysfs_params[i]); |
24613191 | 11240 | + |
4e97e4e9 | 11241 | + toi_core_fns = &my_fns; |
24613191 | 11242 | + |
ad8f4a28 AM |
11243 | + if (toi_alloc_init()) |
11244 | + return 1; | |
4e97e4e9 | 11245 | + if (toi_checksum_init()) |
11246 | + return 1; | |
4e97e4e9 | 11247 | + if (toi_usm_init()) |
11248 | + return 1; | |
11249 | + if (toi_ui_init()) | |
11250 | + return 1; | |
11251 | + if (toi_poweroff_init()) | |
11252 | + return 1; | |
1838f965 | 11253 | + if (toi_cluster_init()) |
11254 | + return 1; | |
24613191 | 11255 | + |
4e97e4e9 | 11256 | + return 0; |
11257 | +} | |
24613191 | 11258 | + |
4e97e4e9 | 11259 | +#ifdef MODULE |
11260 | +/** | |
11261 | + * core_unload: Prepare to unload the core code. | |
11262 | + */ | |
11263 | +static __exit void core_unload(void) | |
11264 | +{ | |
11265 | + int i, | |
11266 | + numfiles = sizeof(sysfs_params) / sizeof(struct toi_sysfs_data); | |
24613191 | 11267 | + |
ad8f4a28 | 11268 | + toi_alloc_exit(); |
1838f965 | 11269 | + toi_checksum_exit(); |
4e97e4e9 | 11270 | + toi_poweroff_exit(); |
11271 | + toi_ui_exit(); | |
4e97e4e9 | 11272 | + toi_usm_exit(); |
1838f965 | 11273 | + toi_cluster_exit(); |
24613191 | 11274 | + |
ad8f4a28 | 11275 | + for (i = 0; i < numfiles; i++) |
7f9d2ee0 | 11276 | + toi_unregister_sysfs_file(tuxonice_kobj, &sysfs_params[i]); |
24613191 | 11277 | + |
4e97e4e9 | 11278 | + toi_core_fns = NULL; |
24613191 | 11279 | + |
4e97e4e9 | 11280 | + toi_sysfs_exit(); |
24613191 | 11281 | +} |
4e97e4e9 | 11282 | +MODULE_LICENSE("GPL"); |
11283 | +module_init(core_load); | |
11284 | +module_exit(core_unload); | |
11285 | +#else | |
11286 | +late_initcall(core_load); | |
11287 | +#endif | |
4e97e4e9 | 11288 | diff --git a/kernel/power/tuxonice_io.c b/kernel/power/tuxonice_io.c |
11289 | new file mode 100644 | |
1838f965 | 11290 | index 0000000..2ea20bf |
4e97e4e9 | 11291 | --- /dev/null |
11292 | +++ b/kernel/power/tuxonice_io.c | |
1838f965 | 11293 | @@ -0,0 +1,1470 @@ |
4e97e4e9 | 11294 | +/* |
11295 | + * kernel/power/tuxonice_io.c | |
24613191 | 11296 | + * |
4e97e4e9 | 11297 | + * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu> |
11298 | + * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz> | |
11299 | + * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr> | |
1838f965 | 11300 | + * Copyright (C) 2002-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 11301 | + * |
11302 | + * This file is released under the GPLv2. | |
11303 | + * | |
11304 | + * It contains high level IO routines for hibernating. | |
24613191 | 11305 | + * |
24613191 | 11306 | + */ |
24613191 | 11307 | + |
4e97e4e9 | 11308 | +#include <linux/suspend.h> |
11309 | +#include <linux/version.h> | |
11310 | +#include <linux/utsname.h> | |
11311 | +#include <linux/mount.h> | |
11312 | +#include <linux/highmem.h> | |
11313 | +#include <linux/module.h> | |
11314 | +#include <linux/kthread.h> | |
1838f965 | 11315 | +#include <linux/cpu.h> |
4e97e4e9 | 11316 | +#include <asm/tlbflush.h> |
24613191 | 11317 | + |
4e97e4e9 | 11318 | +#include "tuxonice.h" |
11319 | +#include "tuxonice_modules.h" | |
11320 | +#include "tuxonice_pageflags.h" | |
11321 | +#include "tuxonice_io.h" | |
11322 | +#include "tuxonice_ui.h" | |
11323 | +#include "tuxonice_storage.h" | |
11324 | +#include "tuxonice_prepare_image.h" | |
11325 | +#include "tuxonice_extent.h" | |
11326 | +#include "tuxonice_sysfs.h" | |
11327 | +#include "tuxonice_builtin.h" | |
11328 | +#include "tuxonice_checksum.h" | |
ad8f4a28 | 11329 | +#include "tuxonice_alloc.h" |
4e97e4e9 | 11330 | +char alt_resume_param[256]; |
24613191 | 11331 | + |
4e97e4e9 | 11332 | +/* Variables shared between threads and updated under the mutex */ |
11333 | +static int io_write, io_finish_at, io_base, io_barmax, io_pageset, io_result; | |
1838f965 | 11334 | +static int io_index, io_nextupdate, io_pc, io_pc_step, first_to_finish; |
4e97e4e9 | 11335 | +static unsigned long pfn, other_pfn; |
11336 | +static DEFINE_MUTEX(io_mutex); | |
11337 | +static DEFINE_PER_CPU(struct page *, last_sought); | |
11338 | +static DEFINE_PER_CPU(struct page *, last_high_page); | |
11339 | +static DEFINE_PER_CPU(char *, checksum_locn); | |
11340 | +static DEFINE_PER_CPU(struct pbe *, last_low_page); | |
4e97e4e9 | 11341 | +static atomic_t io_count; |
7f9d2ee0 | 11342 | +atomic_t toi_io_workers; |
1838f965 | 11343 | +EXPORT_SYMBOL_GPL(toi_io_workers); |
11344 | + | |
7f9d2ee0 | 11345 | +DECLARE_WAIT_QUEUE_HEAD(toi_io_queue_flusher); |
1838f965 | 11346 | +EXPORT_SYMBOL_GPL(toi_io_queue_flusher); |
11347 | + | |
7f9d2ee0 | 11348 | +int toi_bio_queue_flusher_should_finish; |
1838f965 | 11349 | +EXPORT_SYMBOL_GPL(toi_bio_queue_flusher_should_finish); |
11350 | + | |
11351 | +/* Indicates that this thread should be used for checking throughput */ | |
11352 | +#define MONITOR ((void *) 1) | |
24613191 | 11353 | + |
4e97e4e9 | 11354 | +/* toi_attempt_to_parse_resume_device |
11355 | + * | |
11356 | + * Can we hibernate, using the current resume= parameter? | |
11357 | + */ | |
11358 | +int toi_attempt_to_parse_resume_device(int quiet) | |
11359 | +{ | |
11360 | + struct list_head *Allocator; | |
11361 | + struct toi_module_ops *thisAllocator; | |
11362 | + int result, returning = 0; | |
24613191 | 11363 | + |
4e97e4e9 | 11364 | + if (toi_activate_storage(0)) |
11365 | + return 0; | |
11366 | + | |
11367 | + toiActiveAllocator = NULL; | |
11368 | + clear_toi_state(TOI_RESUME_DEVICE_OK); | |
11369 | + clear_toi_state(TOI_CAN_RESUME); | |
11370 | + clear_result_state(TOI_ABORTED); | |
11371 | + | |
11372 | + if (!toiNumAllocators) { | |
11373 | + if (!quiet) | |
ad8f4a28 AM |
11374 | + printk(KERN_INFO "TuxOnIce: No storage allocators have " |
11375 | + "been registered. Hibernating will be " | |
11376 | + "disabled.\n"); | |
4e97e4e9 | 11377 | + goto cleanup; |
11378 | + } | |
ad8f4a28 | 11379 | + |
4e97e4e9 | 11380 | + if (!resume_file[0]) { |
11381 | + if (!quiet) | |
11382 | + printk("TuxOnIce: Resume= parameter is empty." | |
11383 | + " Hibernating will be disabled.\n"); | |
11384 | + goto cleanup; | |
11385 | + } | |
24613191 | 11386 | + |
4e97e4e9 | 11387 | + list_for_each(Allocator, &toiAllocators) { |
11388 | + thisAllocator = list_entry(Allocator, struct toi_module_ops, | |
11389 | + type_list); | |
24613191 | 11390 | + |
ad8f4a28 | 11391 | + /* |
4e97e4e9 | 11392 | + * Not sure why you'd want to disable an allocator, but |
11393 | + * we should honour the flag if we're providing it | |
11394 | + */ | |
11395 | + if (!thisAllocator->enabled) | |
11396 | + continue; | |
24613191 | 11397 | + |
4e97e4e9 | 11398 | + result = thisAllocator->parse_sig_location( |
11399 | + resume_file, (toiNumAllocators == 1), | |
11400 | + quiet); | |
24613191 | 11401 | + |
4e97e4e9 | 11402 | + switch (result) { |
ad8f4a28 AM |
11403 | + case -EINVAL: |
11404 | + /* For this allocator, but not a valid | |
11405 | + * configuration. Error already printed. */ | |
11406 | + goto cleanup; | |
11407 | + | |
11408 | + case 0: | |
11409 | + /* For this allocator and valid. */ | |
11410 | + toiActiveAllocator = thisAllocator; | |
11411 | + | |
11412 | + set_toi_state(TOI_RESUME_DEVICE_OK); | |
11413 | + set_toi_state(TOI_CAN_RESUME); | |
11414 | + returning = 1; | |
11415 | + goto cleanup; | |
24613191 | 11416 | + } |
11417 | + } | |
4e97e4e9 | 11418 | + if (!quiet) |
11419 | + printk("TuxOnIce: No matching enabled allocator found. " | |
11420 | + "Resuming disabled.\n"); | |
11421 | +cleanup: | |
11422 | + toi_deactivate_storage(0); | |
11423 | + return returning; | |
24613191 | 11424 | +} |
1838f965 | 11425 | +EXPORT_SYMBOL_GPL(toi_attempt_to_parse_resume_device); |
24613191 | 11426 | + |
4e97e4e9 | 11427 | +void attempt_to_parse_resume_device2(void) |
11428 | +{ | |
11429 | + toi_prepare_usm(); | |
11430 | + toi_attempt_to_parse_resume_device(0); | |
11431 | + toi_cleanup_usm(); | |
11432 | +} | |
1838f965 | 11433 | +EXPORT_SYMBOL_GPL(attempt_to_parse_resume_device2); |
24613191 | 11434 | + |
4e97e4e9 | 11435 | +void save_restore_alt_param(int replace, int quiet) |
11436 | +{ | |
11437 | + static char resume_param_save[255]; | |
11438 | + static unsigned long toi_state_save; | |
e8d0ad9d | 11439 | + |
4e97e4e9 | 11440 | + if (replace) { |
11441 | + toi_state_save = toi_state; | |
11442 | + strcpy(resume_param_save, resume_file); | |
ad8f4a28 | 11443 | + strcpy(resume_file, alt_resume_param); |
4e97e4e9 | 11444 | + } else { |
11445 | + strcpy(resume_file, resume_param_save); | |
11446 | + toi_state = toi_state_save; | |
11447 | + } | |
11448 | + toi_attempt_to_parse_resume_device(quiet); | |
11449 | +} | |
24613191 | 11450 | + |
4e97e4e9 | 11451 | +void attempt_to_parse_alt_resume_param(void) |
11452 | +{ | |
11453 | + int ok = 0; | |
24613191 | 11454 | + |
4e97e4e9 | 11455 | + /* Temporarily set resume_param to the poweroff value */ |
11456 | + if (!strlen(alt_resume_param)) | |
11457 | + return; | |
24613191 | 11458 | + |
4e97e4e9 | 11459 | + printk("=== Trying Poweroff Resume2 ===\n"); |
11460 | + save_restore_alt_param(SAVE, NOQUIET); | |
11461 | + if (test_toi_state(TOI_CAN_RESUME)) | |
11462 | + ok = 1; | |
ad8f4a28 AM |
11463 | + |
11464 | + printk(KERN_INFO "=== Done ===\n"); | |
4e97e4e9 | 11465 | + save_restore_alt_param(RESTORE, QUIET); |
ad8f4a28 | 11466 | + |
4e97e4e9 | 11467 | + /* If not ok, clear the string */ |
11468 | + if (ok) | |
24613191 | 11469 | + return; |
11470 | + | |
ad8f4a28 AM |
11471 | + printk(KERN_INFO "Can't resume from that location; clearing " |
11472 | + "alt_resume_param.\n"); | |
4e97e4e9 | 11473 | + alt_resume_param[0] = '\0'; |
11474 | +} | |
24613191 | 11475 | + |
4e97e4e9 | 11476 | +/* noresume_reset_modules |
11477 | + * | |
11478 | + * Description: When we read the start of an image, modules (and especially the | |
11479 | + * active allocator) might need to reset data structures if we | |
11480 | + * decide to remove the image rather than resuming from it. | |
11481 | + */ | |
24613191 | 11482 | + |
4e97e4e9 | 11483 | +static void noresume_reset_modules(void) |
24613191 | 11484 | +{ |
4e97e4e9 | 11485 | + struct toi_module_ops *this_filter; |
ad8f4a28 | 11486 | + |
4e97e4e9 | 11487 | + list_for_each_entry(this_filter, &toi_filters, type_list) |
11488 | + if (this_filter->noresume_reset) | |
11489 | + this_filter->noresume_reset(); | |
11490 | + | |
11491 | + if (toiActiveAllocator && toiActiveAllocator->noresume_reset) | |
11492 | + toiActiveAllocator->noresume_reset(); | |
24613191 | 11493 | +} |
11494 | + | |
4e97e4e9 | 11495 | +/* fill_toi_header() |
ad8f4a28 | 11496 | + * |
4e97e4e9 | 11497 | + * Description: Fill the hibernate header structure. |
11498 | + * Arguments: struct toi_header: Header data structure to be filled. | |
11499 | + */ | |
e8d0ad9d | 11500 | + |
ad8f4a28 | 11501 | +static int fill_toi_header(struct toi_header *sh) |
4e97e4e9 | 11502 | +{ |
ad8f4a28 AM |
11503 | + int i, error; |
11504 | + | |
11505 | + error = init_swsusp_header((struct swsusp_info *) sh); | |
11506 | + if (error) | |
11507 | + return error; | |
24613191 | 11508 | + |
4e97e4e9 | 11509 | + sh->pagedir = pagedir1; |
11510 | + sh->pageset_2_size = pagedir2.size; | |
11511 | + sh->param0 = toi_result; | |
ad8f4a28 AM |
11512 | + sh->param1 = toi_bkd.toi_action; |
11513 | + sh->param2 = toi_bkd.toi_debug_state; | |
11514 | + sh->param3 = toi_bkd.toi_default_console_level; | |
7f9d2ee0 | 11515 | + sh->root_fs = current->fs->root.mnt->mnt_sb->s_dev; |
4e97e4e9 | 11516 | + for (i = 0; i < 4; i++) |
ad8f4a28 AM |
11517 | + sh->io_time[i/2][i%2] = toi_bkd.toi_io_time[i/2][i%2]; |
11518 | + sh->bkd = boot_kernel_data_buffer; | |
11519 | + return 0; | |
4e97e4e9 | 11520 | +} |
43540741 | 11521 | + |
24613191 | 11522 | +/* |
4e97e4e9 | 11523 | + * rw_init_modules |
24613191 | 11524 | + * |
4e97e4e9 | 11525 | + * Iterate over modules, preparing the ones that will be used to read or write |
11526 | + * data. | |
24613191 | 11527 | + */ |
4e97e4e9 | 11528 | +static int rw_init_modules(int rw, int which) |
24613191 | 11529 | +{ |
4e97e4e9 | 11530 | + struct toi_module_ops *this_module; |
11531 | + /* Initialise page transformers */ | |
11532 | + list_for_each_entry(this_module, &toi_filters, type_list) { | |
11533 | + if (!this_module->enabled) | |
11534 | + continue; | |
11535 | + if (this_module->rw_init && this_module->rw_init(rw, which)) { | |
11536 | + abort_hibernate(TOI_FAILED_MODULE_INIT, | |
11537 | + "Failed to initialise the %s filter.", | |
11538 | + this_module->name); | |
11539 | + return 1; | |
11540 | + } | |
11541 | + } | |
24613191 | 11542 | + |
4e97e4e9 | 11543 | + /* Initialise allocator */ |
11544 | + if (toiActiveAllocator->rw_init(rw, which)) { | |
11545 | + abort_hibernate(TOI_FAILED_MODULE_INIT, | |
ad8f4a28 | 11546 | + "Failed to initialise the allocator."); |
4e97e4e9 | 11547 | + return 1; |
11548 | + } | |
24613191 | 11549 | + |
4e97e4e9 | 11550 | + /* Initialise other modules */ |
11551 | + list_for_each_entry(this_module, &toi_modules, module_list) { | |
11552 | + if (!this_module->enabled || | |
11553 | + this_module->type == FILTER_MODULE || | |
11554 | + this_module->type == WRITER_MODULE) | |
11555 | + continue; | |
11556 | + if (this_module->rw_init && this_module->rw_init(rw, which)) { | |
11557 | + set_abort_result(TOI_FAILED_MODULE_INIT); | |
ad8f4a28 AM |
11558 | + printk(KERN_INFO "Setting aborted flag due to module " |
11559 | + "init failure.\n"); | |
4e97e4e9 | 11560 | + return 1; |
11561 | + } | |
24613191 | 11562 | + } |
11563 | + | |
4e97e4e9 | 11564 | + return 0; |
24613191 | 11565 | +} |
11566 | + | |
4e97e4e9 | 11567 | +/* |
11568 | + * rw_cleanup_modules | |
11569 | + * | |
11570 | + * Cleanup components after reading or writing a set of pages. | |
11571 | + * Only the allocator may fail. | |
11572 | + */ | |
11573 | +static int rw_cleanup_modules(int rw) | |
24613191 | 11574 | +{ |
4e97e4e9 | 11575 | + struct toi_module_ops *this_module; |
11576 | + int result = 0; | |
24613191 | 11577 | + |
4e97e4e9 | 11578 | + /* Cleanup other modules */ |
11579 | + list_for_each_entry(this_module, &toi_modules, module_list) { | |
11580 | + if (!this_module->enabled || | |
11581 | + this_module->type == FILTER_MODULE || | |
11582 | + this_module->type == WRITER_MODULE) | |
11583 | + continue; | |
11584 | + if (this_module->rw_cleanup) | |
11585 | + result |= this_module->rw_cleanup(rw); | |
11586 | + } | |
24613191 | 11587 | + |
4e97e4e9 | 11588 | + /* Flush data and cleanup */ |
11589 | + list_for_each_entry(this_module, &toi_filters, type_list) { | |
11590 | + if (!this_module->enabled) | |
11591 | + continue; | |
11592 | + if (this_module->rw_cleanup) | |
11593 | + result |= this_module->rw_cleanup(rw); | |
11594 | + } | |
24613191 | 11595 | + |
4e97e4e9 | 11596 | + result |= toiActiveAllocator->rw_cleanup(rw); |
24613191 | 11597 | + |
4e97e4e9 | 11598 | + return result; |
11599 | +} | |
24613191 | 11600 | + |
4e97e4e9 | 11601 | +static struct page *copy_page_from_orig_page(struct page *orig_page) |
11602 | +{ | |
11603 | + int is_high = PageHighMem(orig_page), index, min, max; | |
11604 | + struct page *high_page = NULL, | |
11605 | + **my_last_high_page = &__get_cpu_var(last_high_page), | |
11606 | + **my_last_sought = &__get_cpu_var(last_sought); | |
11607 | + struct pbe *this, **my_last_low_page = &__get_cpu_var(last_low_page); | |
11608 | + void *compare; | |
24613191 | 11609 | + |
4e97e4e9 | 11610 | + if (is_high) { |
ad8f4a28 AM |
11611 | + if (*my_last_sought && *my_last_high_page && |
11612 | + *my_last_sought < orig_page) | |
4e97e4e9 | 11613 | + high_page = *my_last_high_page; |
11614 | + else | |
11615 | + high_page = (struct page *) restore_highmem_pblist; | |
11616 | + this = (struct pbe *) kmap(high_page); | |
11617 | + compare = orig_page; | |
11618 | + } else { | |
ad8f4a28 AM |
11619 | + if (*my_last_sought && *my_last_low_page && |
11620 | + *my_last_sought < orig_page) | |
4e97e4e9 | 11621 | + this = *my_last_low_page; |
11622 | + else | |
11623 | + this = restore_pblist; | |
11624 | + compare = page_address(orig_page); | |
11625 | + } | |
24613191 | 11626 | + |
4e97e4e9 | 11627 | + *my_last_sought = orig_page; |
24613191 | 11628 | + |
4e97e4e9 | 11629 | + /* Locate page containing pbe */ |
ad8f4a28 AM |
11630 | + while (this[PBES_PER_PAGE - 1].next && |
11631 | + this[PBES_PER_PAGE - 1].orig_address < compare) { | |
4e97e4e9 | 11632 | + if (is_high) { |
11633 | + struct page *next_high_page = (struct page *) | |
11634 | + this[PBES_PER_PAGE - 1].next; | |
11635 | + kunmap(high_page); | |
11636 | + this = kmap(next_high_page); | |
11637 | + high_page = next_high_page; | |
11638 | + } else | |
11639 | + this = this[PBES_PER_PAGE - 1].next; | |
24613191 | 11640 | + } |
11641 | + | |
4e97e4e9 | 11642 | + /* Do a binary search within the page */ |
11643 | + min = 0; | |
11644 | + max = PBES_PER_PAGE; | |
11645 | + index = PBES_PER_PAGE / 2; | |
11646 | + while (max - min) { | |
11647 | + if (!this[index].orig_address || | |
11648 | + this[index].orig_address > compare) | |
11649 | + max = index; | |
11650 | + else if (this[index].orig_address == compare) { | |
11651 | + if (is_high) { | |
11652 | + struct page *page = this[index].address; | |
11653 | + *my_last_high_page = high_page; | |
11654 | + kunmap(high_page); | |
11655 | + return page; | |
11656 | + } | |
11657 | + *my_last_low_page = this; | |
11658 | + return virt_to_page(this[index].address); | |
11659 | + } else | |
11660 | + min = index; | |
11661 | + index = ((max + min) / 2); | |
11662 | + }; | |
11663 | + | |
11664 | + if (is_high) | |
11665 | + kunmap(high_page); | |
11666 | + | |
11667 | + abort_hibernate(TOI_FAILED_IO, "Failed to get destination page for" | |
11668 | + " orig page %p. This[min].orig_address=%p.\n", orig_page, | |
11669 | + this[index].orig_address); | |
11670 | + return NULL; | |
24613191 | 11671 | +} |
11672 | + | |
4e97e4e9 | 11673 | +/* |
11674 | + * do_rw_loop | |
11675 | + * | |
11676 | + * The main I/O loop for reading or writing pages. | |
11677 | + */ | |
11678 | +static int worker_rw_loop(void *data) | |
24613191 | 11679 | +{ |
1838f965 | 11680 | + unsigned long orig_pfn, write_pfn, next_jiffies = jiffies + HZ / 10, jif_index = 1; |
11681 | + int result, my_io_index = 0, temp, last_worker, i_finished_first = 0; | |
4e97e4e9 | 11682 | + struct toi_module_ops *first_filter = toi_get_next_filter(NULL); |
ad8f4a28 | 11683 | + struct page *buffer = toi_alloc_page(28, TOI_ATOMIC_GFP); |
24613191 | 11684 | + |
7f9d2ee0 | 11685 | + atomic_inc(&toi_io_workers); |
4e97e4e9 | 11686 | + mutex_lock(&io_mutex); |
24613191 | 11687 | + |
4e97e4e9 | 11688 | + do { |
1838f965 | 11689 | + unsigned int buf_size; |
11690 | + | |
11691 | + if (data && jiffies > next_jiffies) { | |
11692 | + next_jiffies += HZ / 10; | |
11693 | + if (toiActiveAllocator->update_throughput_throttle) | |
11694 | + toiActiveAllocator->update_throughput_throttle(jif_index); | |
11695 | + jif_index++; | |
11696 | + } | |
24613191 | 11697 | + |
4e97e4e9 | 11698 | + /* |
11699 | + * What page to use? If reading, don't know yet which page's | |
11700 | + * data will be read, so always use the buffer. If writing, | |
11701 | + * use the copy (Pageset1) or original page (Pageset2), but | |
11702 | + * always write the pfn of the original page. | |
11703 | + */ | |
11704 | + if (io_write) { | |
11705 | + struct page *page; | |
11706 | + char **my_checksum_locn = &__get_cpu_var(checksum_locn); | |
24613191 | 11707 | + |
1838f965 | 11708 | + pfn = memory_bm_next_pfn(&io_map); |
24613191 | 11709 | + |
4e97e4e9 | 11710 | + /* Another thread could have beaten us to it. */ |
11711 | + if (pfn == max_pfn + 1) { | |
11712 | + if (atomic_read(&io_count)) { | |
ad8f4a28 AM |
11713 | + printk("Ran out of pfns but io_count " |
11714 | + "is still %d.\n", | |
11715 | + atomic_read(&io_count)); | |
4e97e4e9 | 11716 | + BUG(); |
11717 | + } | |
11718 | + break; | |
11719 | + } | |
24613191 | 11720 | + |
7f9d2ee0 | 11721 | + my_io_index = io_finish_at - |
11722 | + atomic_sub_return(1, &io_count); | |
24613191 | 11723 | + |
4e97e4e9 | 11724 | + orig_pfn = pfn; |
11725 | + write_pfn = pfn; | |
24613191 | 11726 | + |
ad8f4a28 | 11727 | + /* |
4e97e4e9 | 11728 | + * Other_pfn is updated by all threads, so we're not |
11729 | + * writing the same page multiple times. | |
11730 | + */ | |
1838f965 | 11731 | + memory_bm_clear_bit(&io_map, pfn); |
4e97e4e9 | 11732 | + if (io_pageset == 1) { |
1838f965 | 11733 | + other_pfn = memory_bm_next_pfn(&pageset1_map); |
4e97e4e9 | 11734 | + write_pfn = other_pfn; |
11735 | + } | |
11736 | + page = pfn_to_page(pfn); | |
24613191 | 11737 | + |
4e97e4e9 | 11738 | + if (io_pageset == 2) |
ad8f4a28 AM |
11739 | + *my_checksum_locn = |
11740 | + tuxonice_get_next_checksum(); | |
24613191 | 11741 | + |
4e97e4e9 | 11742 | + mutex_unlock(&io_mutex); |
24613191 | 11743 | + |
4e97e4e9 | 11744 | + if (io_pageset == 2 && |
11745 | + tuxonice_calc_checksum(page, *my_checksum_locn)) | |
11746 | + return 1; | |
24613191 | 11747 | + |
4e97e4e9 | 11748 | + result = first_filter->write_page(write_pfn, page, |
11749 | + PAGE_SIZE); | |
11750 | + } else { | |
7f9d2ee0 | 11751 | + my_io_index = io_finish_at - |
11752 | + atomic_sub_return(1, &io_count); | |
4e97e4e9 | 11753 | + mutex_unlock(&io_mutex); |
24613191 | 11754 | + |
ad8f4a28 | 11755 | + /* |
4e97e4e9 | 11756 | + * Are we aborting? If so, don't submit any more I/O as |
11757 | + * resetting the resume_attempted flag (from ui.c) will | |
11758 | + * clear the bdev flags, making this thread oops. | |
11759 | + */ | |
11760 | + if (unlikely(test_toi_state(TOI_STOP_RESUME))) { | |
7f9d2ee0 | 11761 | + atomic_dec(&toi_io_workers); |
11762 | + if (!atomic_read(&toi_io_workers)) | |
4e97e4e9 | 11763 | + set_toi_state(TOI_IO_STOPPED); |
11764 | + while (1) | |
11765 | + schedule(); | |
11766 | + } | |
24613191 | 11767 | + |
4e97e4e9 | 11768 | + result = first_filter->read_page(&write_pfn, buffer, |
11769 | + &buf_size); | |
11770 | + if (buf_size != PAGE_SIZE) { | |
11771 | + abort_hibernate(TOI_FAILED_IO, | |
ad8f4a28 | 11772 | + "I/O pipeline returned %d bytes instead" |
1838f965 | 11773 | + " of %ud.\n", buf_size, PAGE_SIZE); |
4e97e4e9 | 11774 | + mutex_lock(&io_mutex); |
11775 | + break; | |
11776 | + } | |
11777 | + } | |
24613191 | 11778 | + |
4e97e4e9 | 11779 | + if (result) { |
11780 | + io_result = result; | |
11781 | + if (io_write) { | |
ad8f4a28 AM |
11782 | + printk(KERN_INFO "Write chunk returned %d.\n", |
11783 | + result); | |
4e97e4e9 | 11784 | + abort_hibernate(TOI_FAILED_IO, |
11785 | + "Failed to write a chunk of the " | |
11786 | + "image."); | |
11787 | + mutex_lock(&io_mutex); | |
11788 | + break; | |
11789 | + } | |
11790 | + panic("Read chunk returned (%d)", result); | |
11791 | + } | |
24613191 | 11792 | + |
ad8f4a28 | 11793 | + /* |
4e97e4e9 | 11794 | + * Discard reads of resaved pages while reading ps2 |
11795 | + * and unwanted pages while rereading ps2 when aborting. | |
11796 | + */ | |
11797 | + if (!io_write && !PageResave(pfn_to_page(write_pfn))) { | |
11798 | + struct page *final_page = pfn_to_page(write_pfn), | |
11799 | + *copy_page = final_page; | |
11800 | + char *virt, *buffer_virt; | |
24613191 | 11801 | + |
4e97e4e9 | 11802 | + if (io_pageset == 1 && !load_direct(final_page)) { |
ad8f4a28 AM |
11803 | + copy_page = |
11804 | + copy_page_from_orig_page(final_page); | |
4e97e4e9 | 11805 | + BUG_ON(!copy_page); |
11806 | + } | |
24613191 | 11807 | + |
1838f965 | 11808 | + if (memory_bm_test_bit(&io_map, write_pfn)) { |
4e97e4e9 | 11809 | + virt = kmap(copy_page); |
11810 | + buffer_virt = kmap(buffer); | |
11811 | + memcpy(virt, buffer_virt, PAGE_SIZE); | |
11812 | + kunmap(copy_page); | |
11813 | + kunmap(buffer); | |
1838f965 | 11814 | + memory_bm_clear_bit(&io_map, write_pfn); |
4e97e4e9 | 11815 | + } else { |
11816 | + mutex_lock(&io_mutex); | |
11817 | + atomic_inc(&io_count); | |
11818 | + mutex_unlock(&io_mutex); | |
11819 | + } | |
11820 | + } | |
24613191 | 11821 | + |
7f9d2ee0 | 11822 | + temp = my_io_index + io_base - io_nextupdate; |
11823 | + | |
11824 | + if (my_io_index + io_base == io_nextupdate) | |
4e97e4e9 | 11825 | + io_nextupdate = toi_update_status(my_io_index + |
11826 | + io_base, io_barmax, " %d/%d MB ", | |
11827 | + MB(io_base+my_io_index+1), MB(io_barmax)); | |
24613191 | 11828 | + |
7f9d2ee0 | 11829 | + if (my_io_index == io_pc) { |
11830 | + printk("%s%d%%...", io_pc_step == 1 ? KERN_ERR : "", | |
ad8f4a28 | 11831 | + 20 * io_pc_step); |
4e97e4e9 | 11832 | + io_pc_step++; |
11833 | + io_pc = io_finish_at * io_pc_step / 5; | |
11834 | + } | |
ad8f4a28 | 11835 | + |
4e97e4e9 | 11836 | + toi_cond_pause(0, NULL); |
24613191 | 11837 | + |
ad8f4a28 | 11838 | + /* |
4e97e4e9 | 11839 | + * Subtle: If there's less I/O still to be done than threads |
11840 | + * running, quit. This stops us doing I/O beyond the end of | |
11841 | + * the image when reading. | |
11842 | + * | |
11843 | + * Possible race condition. Two threads could do the test at | |
11844 | + * the same time; one should exit and one should continue. | |
11845 | + * Therefore we take the mutex before comparing and exiting. | |
11846 | + */ | |
24613191 | 11847 | + |
4e97e4e9 | 11848 | + mutex_lock(&io_mutex); |
24613191 | 11849 | + |
7f9d2ee0 | 11850 | + } while (atomic_read(&io_count) >= atomic_read(&toi_io_workers) && |
4e97e4e9 | 11851 | + !(io_write && test_result_state(TOI_ABORTED))); |
24613191 | 11852 | + |
1838f965 | 11853 | + last_worker = atomic_dec_and_test(&toi_io_workers); |
11854 | + if (!first_to_finish) { | |
11855 | + first_to_finish = 1; | |
11856 | + i_finished_first = 1; | |
11857 | + } | |
11858 | + mutex_unlock(&io_mutex); | |
11859 | + | |
11860 | + if (last_worker) { | |
7f9d2ee0 | 11861 | + toi_bio_queue_flusher_should_finish = 1; |
11862 | + wake_up(&toi_io_queue_flusher); | |
1838f965 | 11863 | + toiActiveAllocator->finish_all_io(); |
11864 | + } else { | |
11865 | + /* Yes, there's still I/O above, but it's the last | |
11866 | + * pages being submitted, so switch to displaying | |
11867 | + * how much I/O we're waiting on. | |
11868 | + */ | |
11869 | + if (i_finished_first && | |
11870 | + toiActiveAllocator->monitor_outstanding_io) | |
11871 | + toiActiveAllocator->monitor_outstanding_io(); | |
7f9d2ee0 | 11872 | + } |
24613191 | 11873 | + |
ad8f4a28 | 11874 | + toi__free_page(28, buffer); |
24613191 | 11875 | + |
4e97e4e9 | 11876 | + return 0; |
11877 | +} | |
24613191 | 11878 | + |
1838f965 | 11879 | +static int start_other_threads(void) |
24613191 | 11880 | +{ |
7f9d2ee0 | 11881 | + int cpu, num_started = 0; |
4e97e4e9 | 11882 | + struct task_struct *p; |
24613191 | 11883 | + |
4e97e4e9 | 11884 | + for_each_online_cpu(cpu) { |
11885 | + if (cpu == smp_processor_id()) | |
11886 | + continue; | |
24613191 | 11887 | + |
1838f965 | 11888 | + p = kthread_create(worker_rw_loop, num_started ? NULL : MONITOR, |
11889 | + "ks2io/%d", cpu); | |
4e97e4e9 | 11890 | + if (IS_ERR(p)) { |
11891 | + printk("ks2io for %i failed\n", cpu); | |
11892 | + continue; | |
11893 | + } | |
11894 | + kthread_bind(p, cpu); | |
ad8f4a28 | 11895 | + p->flags |= PF_MEMALLOC; |
4e97e4e9 | 11896 | + wake_up_process(p); |
7f9d2ee0 | 11897 | + num_started++; |
4e97e4e9 | 11898 | + } |
7f9d2ee0 | 11899 | + |
11900 | + return num_started; | |
24613191 | 11901 | +} |
4e97e4e9 | 11902 | + |
24613191 | 11903 | +/* |
4e97e4e9 | 11904 | + * do_rw_loop |
24613191 | 11905 | + * |
4e97e4e9 | 11906 | + * The main I/O loop for reading or writing pages. |
24613191 | 11907 | + */ |
1838f965 | 11908 | +static int do_rw_loop(int write, int finish_at, struct memory_bitmap *pageflags, |
4e97e4e9 | 11909 | + int base, int barmax, int pageset) |
24613191 | 11910 | +{ |
7f9d2ee0 | 11911 | + int index = 0, cpu, num_other_threads = 0; |
24613191 | 11912 | + |
4e97e4e9 | 11913 | + if (!finish_at) |
11914 | + return 0; | |
24613191 | 11915 | + |
4e97e4e9 | 11916 | + io_write = write; |
11917 | + io_finish_at = finish_at; | |
11918 | + io_base = base; | |
11919 | + io_barmax = barmax; | |
11920 | + io_pageset = pageset; | |
11921 | + io_index = 0; | |
11922 | + io_pc = io_finish_at / 5; | |
11923 | + io_pc_step = 1; | |
11924 | + io_result = 0; | |
7f9d2ee0 | 11925 | + io_nextupdate = base + 1; |
11926 | + toi_bio_queue_flusher_should_finish = 0; | |
1838f965 | 11927 | + first_to_finish = 0; |
24613191 | 11928 | + |
4e97e4e9 | 11929 | + for_each_online_cpu(cpu) { |
11930 | + per_cpu(last_sought, cpu) = NULL; | |
11931 | + per_cpu(last_low_page, cpu) = NULL; | |
11932 | + per_cpu(last_high_page, cpu) = NULL; | |
11933 | + } | |
24613191 | 11934 | + |
4e97e4e9 | 11935 | + /* Ensure all bits clear */ |
1838f965 | 11936 | + memory_bm_clear(&io_map); |
24613191 | 11937 | + |
4e97e4e9 | 11938 | + /* Set the bits for the pages to write */ |
1838f965 | 11939 | + memory_bm_position_reset(pageflags); |
11940 | + | |
11941 | + pfn = memory_bm_next_pfn(pageflags); | |
24613191 | 11942 | + |
4e97e4e9 | 11943 | + while (pfn < max_pfn + 1 && index < finish_at) { |
1838f965 | 11944 | + memory_bm_set_bit(&io_map, pfn); |
11945 | + pfn = memory_bm_next_pfn(pageflags); | |
4e97e4e9 | 11946 | + index++; |
11947 | + } | |
24613191 | 11948 | + |
4e97e4e9 | 11949 | + BUG_ON(index < finish_at); |
24613191 | 11950 | + |
4e97e4e9 | 11951 | + atomic_set(&io_count, finish_at); |
24613191 | 11952 | + |
4e97e4e9 | 11953 | + pfn = max_pfn + 1; |
11954 | + other_pfn = pfn; | |
24613191 | 11955 | + |
1838f965 | 11956 | + memory_bm_position_reset(&pageset1_map); |
11957 | + | |
4e97e4e9 | 11958 | + clear_toi_state(TOI_IO_STOPPED); |
1838f965 | 11959 | + memory_bm_position_reset(&io_map); |
24613191 | 11960 | + |
4e97e4e9 | 11961 | + if (!test_action_state(TOI_NO_MULTITHREADED_IO)) |
7f9d2ee0 | 11962 | + num_other_threads = start_other_threads(); |
4e97e4e9 | 11963 | + |
7f9d2ee0 | 11964 | + if (!num_other_threads || !toiActiveAllocator->io_flusher || |
11965 | + test_action_state(TOI_NO_FLUSHER_THREAD)) | |
1838f965 | 11966 | + worker_rw_loop(num_other_threads ? NULL : MONITOR); |
7f9d2ee0 | 11967 | + else |
11968 | + toiActiveAllocator->io_flusher(write); | |
11969 | + | |
11970 | + while (atomic_read(&toi_io_workers)) | |
4e97e4e9 | 11971 | + schedule(); |
11972 | + | |
11973 | + set_toi_state(TOI_IO_STOPPED); | |
11974 | + if (unlikely(test_toi_state(TOI_STOP_RESUME))) { | |
11975 | + while (1) | |
11976 | + schedule(); | |
11977 | + } | |
11978 | + | |
11979 | + if (!io_result) { | |
11980 | + printk("done.\n"); | |
11981 | + | |
ad8f4a28 AM |
11982 | + toi_update_status(io_base + io_finish_at, io_barmax, |
11983 | + " %d/%d MB ", | |
4e97e4e9 | 11984 | + MB(io_base + io_finish_at), MB(io_barmax)); |
11985 | + } | |
11986 | + | |
11987 | + if (io_write && test_result_state(TOI_ABORTED)) | |
11988 | + io_result = 1; | |
11989 | + else { /* All I/O done? */ | |
1838f965 | 11990 | + if (memory_bm_next_pfn(&io_map) != BM_END_OF_MAP) { |
ad8f4a28 AM |
11991 | + printk(KERN_INFO "Finished I/O loop but still work to " |
11992 | + "do?\nFinish at = %d. io_count = %d.\n", | |
11993 | + finish_at, atomic_read(&io_count)); | |
4e97e4e9 | 11994 | + BUG(); |
11995 | + } | |
73c609d5 | 11996 | + } |
4e97e4e9 | 11997 | + |
11998 | + return io_result; | |
24613191 | 11999 | +} |
12000 | + | |
4e97e4e9 | 12001 | +/* write_pageset() |
12002 | + * | |
12003 | + * Description: Write a pageset to disk. | |
12004 | + * Arguments: pagedir: Which pagedir to write.. | |
12005 | + * Returns: Zero on success or -1 on failure. | |
24613191 | 12006 | + */ |
24613191 | 12007 | + |
4e97e4e9 | 12008 | +int write_pageset(struct pagedir *pagedir) |
12009 | +{ | |
12010 | + int finish_at, base = 0, start_time, end_time; | |
12011 | + int barmax = pagedir1.size + pagedir2.size; | |
12012 | + long error = 0; | |
1838f965 | 12013 | + struct memory_bitmap *pageflags; |
24613191 | 12014 | + |
ad8f4a28 | 12015 | + /* |
4e97e4e9 | 12016 | + * Even if there is nothing to read or write, the allocator |
12017 | + * may need the init/cleanup for it's housekeeping. (eg: | |
12018 | + * Pageset1 may start where pageset2 ends when writing). | |
12019 | + */ | |
12020 | + finish_at = pagedir->size; | |
24613191 | 12021 | + |
4e97e4e9 | 12022 | + if (pagedir->id == 1) { |
12023 | + toi_prepare_status(DONT_CLEAR_BAR, | |
12024 | + "Writing kernel & process data..."); | |
12025 | + base = pagedir2.size; | |
12026 | + if (test_action_state(TOI_TEST_FILTER_SPEED) || | |
12027 | + test_action_state(TOI_TEST_BIO)) | |
12028 | + pageflags = &pageset1_map; | |
12029 | + else | |
12030 | + pageflags = &pageset1_copy_map; | |
12031 | + } else { | |
1838f965 | 12032 | + toi_prepare_status(DONT_CLEAR_BAR, "Writing caches..."); |
4e97e4e9 | 12033 | + pageflags = &pageset2_map; |
ad8f4a28 AM |
12034 | + } |
12035 | + | |
4e97e4e9 | 12036 | + start_time = jiffies; |
24613191 | 12037 | + |
4e97e4e9 | 12038 | + if (rw_init_modules(1, pagedir->id)) { |
12039 | + abort_hibernate(TOI_FAILED_MODULE_INIT, | |
12040 | + "Failed to initialise modules for writing."); | |
12041 | + error = 1; | |
24613191 | 12042 | + } |
12043 | + | |
4e97e4e9 | 12044 | + if (!error) |
12045 | + error = do_rw_loop(1, finish_at, pageflags, base, barmax, | |
12046 | + pagedir->id); | |
24613191 | 12047 | + |
4e97e4e9 | 12048 | + if (rw_cleanup_modules(WRITE) && !error) { |
12049 | + abort_hibernate(TOI_FAILED_MODULE_CLEANUP, | |
12050 | + "Failed to cleanup after writing."); | |
12051 | + error = 1; | |
24613191 | 12052 | + } |
12053 | + | |
4e97e4e9 | 12054 | + end_time = jiffies; |
ad8f4a28 | 12055 | + |
4e97e4e9 | 12056 | + if ((end_time - start_time) && (!test_result_state(TOI_ABORTED))) { |
ad8f4a28 AM |
12057 | + toi_bkd.toi_io_time[0][0] += finish_at, |
12058 | + toi_bkd.toi_io_time[0][1] += (end_time - start_time); | |
4e97e4e9 | 12059 | + } |
24613191 | 12060 | + |
4e97e4e9 | 12061 | + return error; |
24613191 | 12062 | +} |
12063 | + | |
4e97e4e9 | 12064 | +/* read_pageset() |
43540741 | 12065 | + * |
4e97e4e9 | 12066 | + * Description: Read a pageset from disk. |
12067 | + * Arguments: whichtowrite: Controls what debugging output is printed. | |
12068 | + * overwrittenpagesonly: Whether to read the whole pageset or | |
12069 | + * only part. | |
12070 | + * Returns: Zero on success or -1 on failure. | |
43540741 | 12071 | + */ |
43540741 | 12072 | + |
4e97e4e9 | 12073 | +static int read_pageset(struct pagedir *pagedir, int overwrittenpagesonly) |
43540741 | 12074 | +{ |
4e97e4e9 | 12075 | + int result = 0, base = 0, start_time, end_time; |
12076 | + int finish_at = pagedir->size; | |
12077 | + int barmax = pagedir1.size + pagedir2.size; | |
1838f965 | 12078 | + struct memory_bitmap *pageflags; |
43540741 | 12079 | + |
4e97e4e9 | 12080 | + if (pagedir->id == 1) { |
1838f965 | 12081 | + toi_prepare_status(DONT_CLEAR_BAR, |
4e97e4e9 | 12082 | + "Reading kernel & process data..."); |
12083 | + pageflags = &pageset1_map; | |
12084 | + } else { | |
12085 | + toi_prepare_status(DONT_CLEAR_BAR, "Reading caches..."); | |
12086 | + if (overwrittenpagesonly) | |
ad8f4a28 | 12087 | + barmax = finish_at = min(pagedir1.size, |
4e97e4e9 | 12088 | + pagedir2.size); |
ad8f4a28 | 12089 | + else |
4e97e4e9 | 12090 | + base = pagedir1.size; |
4e97e4e9 | 12091 | + pageflags = &pageset2_map; |
ad8f4a28 AM |
12092 | + } |
12093 | + | |
4e97e4e9 | 12094 | + start_time = jiffies; |
43540741 | 12095 | + |
4e97e4e9 | 12096 | + if (rw_init_modules(0, pagedir->id)) { |
12097 | + toiActiveAllocator->remove_image(); | |
12098 | + result = 1; | |
12099 | + } else | |
12100 | + result = do_rw_loop(0, finish_at, pageflags, base, barmax, | |
12101 | + pagedir->id); | |
12102 | + | |
12103 | + if (rw_cleanup_modules(READ) && !result) { | |
12104 | + abort_hibernate(TOI_FAILED_MODULE_CLEANUP, | |
12105 | + "Failed to cleanup after reading."); | |
12106 | + result = 1; | |
43540741 | 12107 | + } |
4e97e4e9 | 12108 | + |
12109 | + /* Statistics */ | |
ad8f4a28 | 12110 | + end_time = jiffies; |
4e97e4e9 | 12111 | + |
12112 | + if ((end_time - start_time) && (!test_result_state(TOI_ABORTED))) { | |
ad8f4a28 AM |
12113 | + toi_bkd.toi_io_time[1][0] += finish_at, |
12114 | + toi_bkd.toi_io_time[1][1] += (end_time - start_time); | |
4e97e4e9 | 12115 | + } |
12116 | + | |
12117 | + return result; | |
43540741 | 12118 | +} |
12119 | + | |
4e97e4e9 | 12120 | +/* write_module_configs() |
12121 | + * | |
12122 | + * Description: Store the configuration for each module in the image header. | |
12123 | + * Returns: Int: Zero on success, Error value otherwise. | |
e8d0ad9d | 12124 | + */ |
4e97e4e9 | 12125 | +static int write_module_configs(void) |
24613191 | 12126 | +{ |
4e97e4e9 | 12127 | + struct toi_module_ops *this_module; |
12128 | + char *buffer = (char *) toi_get_zeroed_page(22, TOI_ATOMIC_GFP); | |
12129 | + int len, index = 1; | |
12130 | + struct toi_module_header toi_module_header; | |
24613191 | 12131 | + |
4e97e4e9 | 12132 | + if (!buffer) { |
ad8f4a28 | 12133 | + printk(KERN_INFO "Failed to allocate a buffer for saving " |
4e97e4e9 | 12134 | + "module configuration info.\n"); |
12135 | + return -ENOMEM; | |
12136 | + } | |
ad8f4a28 AM |
12137 | + |
12138 | + /* | |
4e97e4e9 | 12139 | + * We have to know which data goes with which module, so we at |
12140 | + * least write a length of zero for a module. Note that we are | |
12141 | + * also assuming every module's config data takes <= PAGE_SIZE. | |
12142 | + */ | |
24613191 | 12143 | + |
4e97e4e9 | 12144 | + /* For each module (in registration order) */ |
12145 | + list_for_each_entry(this_module, &toi_modules, module_list) { | |
12146 | + if (!this_module->enabled || !this_module->storage_needed || | |
12147 | + (this_module->type == WRITER_MODULE && | |
12148 | + toiActiveAllocator != this_module)) | |
12149 | + continue; | |
24613191 | 12150 | + |
4e97e4e9 | 12151 | + /* Get the data from the module */ |
12152 | + len = 0; | |
12153 | + if (this_module->save_config_info) | |
12154 | + len = this_module->save_config_info(buffer); | |
24613191 | 12155 | + |
4e97e4e9 | 12156 | + /* Save the details of the module */ |
12157 | + toi_module_header.enabled = this_module->enabled; | |
12158 | + toi_module_header.type = this_module->type; | |
12159 | + toi_module_header.index = index++; | |
ad8f4a28 | 12160 | + strncpy(toi_module_header.name, this_module->name, |
4e97e4e9 | 12161 | + sizeof(toi_module_header.name)); |
12162 | + toiActiveAllocator->rw_header_chunk(WRITE, | |
12163 | + this_module, | |
12164 | + (char *) &toi_module_header, | |
12165 | + sizeof(toi_module_header)); | |
24613191 | 12166 | + |
4e97e4e9 | 12167 | + /* Save the size of the data and any data returned */ |
12168 | + toiActiveAllocator->rw_header_chunk(WRITE, | |
12169 | + this_module, | |
12170 | + (char *) &len, sizeof(int)); | |
12171 | + if (len) | |
12172 | + toiActiveAllocator->rw_header_chunk( | |
12173 | + WRITE, this_module, buffer, len); | |
24613191 | 12174 | + } |
24613191 | 12175 | + |
4e97e4e9 | 12176 | + /* Write a blank header to terminate the list */ |
12177 | + toi_module_header.name[0] = '\0'; | |
ad8f4a28 AM |
12178 | + toiActiveAllocator->rw_header_chunk(WRITE, NULL, |
12179 | + (char *) &toi_module_header, sizeof(toi_module_header)); | |
4e97e4e9 | 12180 | + |
ad8f4a28 | 12181 | + toi_free_page(22, (unsigned long) buffer); |
4e97e4e9 | 12182 | + return 0; |
24613191 | 12183 | +} |
12184 | + | |
1838f965 | 12185 | +/* read_one_module_config() |
4e97e4e9 | 12186 | + * |
1838f965 | 12187 | + * Description: Read the configuration for one module, and configure the module |
12188 | + * to match if it is loaded. | |
12189 | + * Returns: Int. Zero on success or an error code. | |
e8d0ad9d | 12190 | + */ |
12191 | + | |
1838f965 | 12192 | +static int read_one_module_config(struct toi_module_header *header) |
24613191 | 12193 | +{ |
4e97e4e9 | 12194 | + struct toi_module_ops *this_module; |
1838f965 | 12195 | + int result, len; |
12196 | + char *buffer; | |
12197 | + | |
12198 | + /* Find the module */ | |
12199 | + this_module = toi_find_module_given_name(header->name); | |
12200 | + | |
12201 | + if (!this_module) { | |
12202 | + if (header->enabled) { | |
12203 | + toi_early_boot_message(1, TOI_CONTINUE_REQ, | |
12204 | + "It looks like we need module %s for reading " | |
12205 | + "the image but it hasn't been registered.\n", | |
12206 | + header->name); | |
12207 | + if (!(test_toi_state(TOI_CONTINUE_REQ))) | |
12208 | + return -EINVAL; | |
12209 | + } else | |
12210 | + printk(KERN_INFO "Module %s configuration data found, " | |
12211 | + "but the module hasn't registered. Looks like " | |
12212 | + "it was disabled, so we're ignoring its data.", | |
12213 | + header->name); | |
12214 | + } | |
12215 | + | |
12216 | + /* Get the length of the data (if any) */ | |
12217 | + result = toiActiveAllocator->rw_header_chunk(READ, NULL, (char *) &len, | |
12218 | + sizeof(int)); | |
12219 | + if (result) { | |
12220 | + printk("Failed to read the length of the module %s's" | |
12221 | + " configuration data.\n", | |
12222 | + header->name); | |
12223 | + return -EINVAL; | |
12224 | + } | |
12225 | + | |
12226 | + /* Read any data and pass to the module (if we found one) */ | |
12227 | + if (!len) | |
12228 | + return 0; | |
12229 | + | |
12230 | + buffer = (char *) toi_get_zeroed_page(23, TOI_ATOMIC_GFP); | |
e8d0ad9d | 12231 | + |
4e97e4e9 | 12232 | + if (!buffer) { |
12233 | + printk("Failed to allocate a buffer for reloading module " | |
12234 | + "configuration info.\n"); | |
12235 | + return -ENOMEM; | |
12236 | + } | |
ad8f4a28 | 12237 | + |
1838f965 | 12238 | + toiActiveAllocator->rw_header_chunk(READ, NULL, buffer, len); |
12239 | + | |
12240 | + if (!this_module) | |
12241 | + goto out; | |
12242 | + | |
12243 | + if (!this_module->save_config_info) | |
12244 | + printk("Huh? Module %s appears to have a save_config_info, but" | |
12245 | + " not a load_config_info function!\n", | |
12246 | + this_module->name); | |
12247 | + else | |
12248 | + this_module->load_config_info(buffer, len); | |
12249 | + | |
12250 | + /* | |
12251 | + * Now move this module to the tail of its lists. This will put it in | |
12252 | + * order. Any new modules will end up at the top of the lists. They | |
12253 | + * should have been set to disabled when loaded (people will | |
12254 | + * normally not edit an initrd to load a new module and then hibernate | |
12255 | + * without using it!). | |
12256 | + */ | |
12257 | + | |
12258 | + toi_move_module_tail(this_module); | |
12259 | + | |
12260 | + this_module->enabled = header->enabled; | |
12261 | + | |
12262 | +out: | |
12263 | + toi_free_page(23, (unsigned long) buffer); | |
12264 | + return 0; | |
12265 | +} | |
12266 | + | |
12267 | +/* read_module_configs() | |
12268 | + * | |
12269 | + * Description: Reload module configurations from the image header. | |
12270 | + * Returns: Int. Zero on success, error value otherwise. | |
12271 | + */ | |
12272 | + | |
12273 | +static int read_module_configs(void) | |
12274 | +{ | |
12275 | + int result = 0; | |
12276 | + struct toi_module_header toi_module_header; | |
12277 | + struct toi_module_ops *this_module; | |
12278 | + | |
4e97e4e9 | 12279 | + /* All modules are initially disabled. That way, if we have a module |
12280 | + * loaded now that wasn't loaded when we hibernated, it won't be used | |
12281 | + * in trying to read the data. | |
12282 | + */ | |
12283 | + list_for_each_entry(this_module, &toi_modules, module_list) | |
12284 | + this_module->enabled = 0; | |
ad8f4a28 | 12285 | + |
4e97e4e9 | 12286 | + /* Get the first module header */ |
12287 | + result = toiActiveAllocator->rw_header_chunk(READ, NULL, | |
12288 | + (char *) &toi_module_header, | |
12289 | + sizeof(toi_module_header)); | |
12290 | + if (result) { | |
12291 | + printk("Failed to read the next module header.\n"); | |
4e97e4e9 | 12292 | + return -EINVAL; |
12293 | + } | |
24613191 | 12294 | + |
4e97e4e9 | 12295 | + /* For each module (in registration order) */ |
12296 | + while (toi_module_header.name[0]) { | |
1838f965 | 12297 | + result = read_one_module_config(&toi_module_header); |
24613191 | 12298 | + |
1838f965 | 12299 | + if (result) |
4e97e4e9 | 12300 | + return -EINVAL; |
24613191 | 12301 | + |
4e97e4e9 | 12302 | + /* Get the next module header */ |
12303 | + result = toiActiveAllocator->rw_header_chunk(READ, NULL, | |
12304 | + (char *) &toi_module_header, | |
12305 | + sizeof(toi_module_header)); | |
12306 | + | |
12307 | + if (result) { | |
12308 | + printk("Failed to read the next module header.\n"); | |
4e97e4e9 | 12309 | + return -EINVAL; |
12310 | + } | |
24613191 | 12311 | + } |
12312 | + | |
4e97e4e9 | 12313 | + return 0; |
12314 | +} | |
24613191 | 12315 | + |
4e97e4e9 | 12316 | +/* write_image_header() |
12317 | + * | |
12318 | + * Description: Write the image header after write the image proper. | |
12319 | + * Returns: Int. Zero on success or -1 on failure. | |
12320 | + */ | |
e8d0ad9d | 12321 | + |
4e97e4e9 | 12322 | +int write_image_header(void) |
12323 | +{ | |
12324 | + int ret; | |
12325 | + int total = pagedir1.size + pagedir2.size+2; | |
12326 | + char *header_buffer = NULL; | |
24613191 | 12327 | + |
4e97e4e9 | 12328 | + /* Now prepare to write the header */ |
ad8f4a28 AM |
12329 | + ret = toiActiveAllocator->write_header_init(); |
12330 | + if (ret) { | |
4e97e4e9 | 12331 | + abort_hibernate(TOI_FAILED_MODULE_INIT, |
12332 | + "Active allocator's write_header_init" | |
12333 | + " function failed."); | |
12334 | + goto write_image_header_abort; | |
e8d0ad9d | 12335 | + } |
e8d0ad9d | 12336 | + |
4e97e4e9 | 12337 | + /* Get a buffer */ |
12338 | + header_buffer = (char *) toi_get_zeroed_page(24, TOI_ATOMIC_GFP); | |
12339 | + if (!header_buffer) { | |
12340 | + abort_hibernate(TOI_OUT_OF_MEMORY, | |
12341 | + "Out of memory when trying to get page for header!"); | |
12342 | + goto write_image_header_abort; | |
e8d0ad9d | 12343 | + } |
12344 | + | |
4e97e4e9 | 12345 | + /* Write hibernate header */ |
ad8f4a28 AM |
12346 | + if (fill_toi_header((struct toi_header *) header_buffer)) { |
12347 | + abort_hibernate(TOI_OUT_OF_MEMORY, | |
12348 | + "Failure to fill header information!"); | |
12349 | + goto write_image_header_abort; | |
12350 | + } | |
4e97e4e9 | 12351 | + toiActiveAllocator->rw_header_chunk(WRITE, NULL, |
12352 | + header_buffer, sizeof(struct toi_header)); | |
e8d0ad9d | 12353 | + |
ad8f4a28 | 12354 | + toi_free_page(24, (unsigned long) header_buffer); |
e8d0ad9d | 12355 | + |
4e97e4e9 | 12356 | + /* Write module configurations */ |
ad8f4a28 AM |
12357 | + ret = write_module_configs(); |
12358 | + if (ret) { | |
4e97e4e9 | 12359 | + abort_hibernate(TOI_FAILED_IO, |
12360 | + "Failed to write module configs."); | |
12361 | + goto write_image_header_abort; | |
12362 | + } | |
e8d0ad9d | 12363 | + |
1838f965 | 12364 | + memory_bm_write(&pageset1_map, toiActiveAllocator->rw_header_chunk); |
43540741 | 12365 | + |
4e97e4e9 | 12366 | + /* Flush data and let allocator cleanup */ |
12367 | + if (toiActiveAllocator->write_header_cleanup()) { | |
12368 | + abort_hibernate(TOI_FAILED_IO, | |
12369 | + "Failed to cleanup writing header."); | |
12370 | + goto write_image_header_abort_no_cleanup; | |
12371 | + } | |
e8d0ad9d | 12372 | + |
4e97e4e9 | 12373 | + if (test_result_state(TOI_ABORTED)) |
12374 | + goto write_image_header_abort_no_cleanup; | |
43540741 | 12375 | + |
4e97e4e9 | 12376 | + toi_update_status(total, total, NULL); |
e8d0ad9d | 12377 | + |
e8d0ad9d | 12378 | + return 0; |
4e97e4e9 | 12379 | + |
12380 | +write_image_header_abort: | |
12381 | + toiActiveAllocator->write_header_cleanup(); | |
12382 | +write_image_header_abort_no_cleanup: | |
12383 | + return -1; | |
e8d0ad9d | 12384 | +} |
12385 | + | |
4e97e4e9 | 12386 | +/* sanity_check() |
12387 | + * | |
12388 | + * Description: Perform a few checks, seeking to ensure that the kernel being | |
12389 | + * booted matches the one hibernated. They need to match so we can | |
12390 | + * be _sure_ things will work. It is not absolutely impossible for | |
12391 | + * resuming from a different kernel to work, just not assured. | |
12392 | + * Arguments: Struct toi_header. The header which was saved at hibernate | |
12393 | + * time. | |
12394 | + */ | |
12395 | +static char *sanity_check(struct toi_header *sh) | |
e8d0ad9d | 12396 | +{ |
ad8f4a28 | 12397 | + char *reason = check_swsusp_image_kernel((struct swsusp_info *) sh); |
e8d0ad9d | 12398 | + |
ad8f4a28 AM |
12399 | + if (reason) |
12400 | + return reason; | |
4e97e4e9 | 12401 | + |
12402 | + if (!test_action_state(TOI_IGNORE_ROOTFS)) { | |
12403 | + const struct super_block *sb; | |
12404 | + list_for_each_entry(sb, &super_blocks, s_list) { | |
12405 | + if ((!(sb->s_flags & MS_RDONLY)) && | |
12406 | + (sb->s_type->fs_flags & FS_REQUIRES_DEV)) | |
12407 | + return "Device backed fs has been mounted " | |
12408 | + "rw prior to resume or initrd/ramfs " | |
12409 | + "is mounted rw."; | |
12410 | + } | |
12411 | + } | |
e8d0ad9d | 12412 | + |
1838f965 | 12413 | + return NULL; |
24613191 | 12414 | +} |
12415 | + | |
4e97e4e9 | 12416 | +/* __read_pageset1 |
12417 | + * | |
12418 | + * Description: Test for the existence of an image and attempt to load it. | |
12419 | + * Returns: Int. Zero if image found and pageset1 successfully loaded. | |
12420 | + * Error if no image found or loaded. | |
24613191 | 12421 | + */ |
4e97e4e9 | 12422 | +static int __read_pageset1(void) |
ad8f4a28 | 12423 | +{ |
4e97e4e9 | 12424 | + int i, result = 0; |
12425 | + char *header_buffer = (char *) toi_get_zeroed_page(25, TOI_ATOMIC_GFP), | |
12426 | + *sanity_error = NULL; | |
12427 | + struct toi_header *toi_header; | |
24613191 | 12428 | + |
4e97e4e9 | 12429 | + if (!header_buffer) { |
ad8f4a28 AM |
12430 | + printk(KERN_INFO "Unable to allocate a page for reading the " |
12431 | + "signature.\n"); | |
4e97e4e9 | 12432 | + return -ENOMEM; |
12433 | + } | |
ad8f4a28 | 12434 | + |
4e97e4e9 | 12435 | + /* Check for an image */ |
7f9d2ee0 | 12436 | + result = toiActiveAllocator->image_exists(1); |
ad8f4a28 | 12437 | + if (!result) { |
4e97e4e9 | 12438 | + result = -ENODATA; |
12439 | + noresume_reset_modules(); | |
ad8f4a28 | 12440 | + printk(KERN_INFO "TuxOnIce: No image found.\n"); |
4e97e4e9 | 12441 | + goto out; |
12442 | + } | |
24613191 | 12443 | + |
7f9d2ee0 | 12444 | + /* |
12445 | + * Prepare the active allocator for reading the image header. The | |
12446 | + * activate allocator might read its own configuration. | |
12447 | + * | |
12448 | + * NB: This call may never return because there might be a signature | |
12449 | + * for a different image such that we warn the user and they choose | |
12450 | + * to reboot. (If the device ids look erroneous (2.4 vs 2.6) or the | |
12451 | + * location of the image might be unavailable if it was stored on a | |
12452 | + * network connection). | |
12453 | + */ | |
12454 | + | |
12455 | + result = toiActiveAllocator->read_header_init(); | |
12456 | + if (result) { | |
f3e0dcc9 PS |
12457 | + printk(KERN_INFO "TuxOnIce: Failed to initialise, reading the " |
12458 | + "image header.\n"); | |
7f9d2ee0 | 12459 | + goto out_remove_image; |
12460 | + } | |
12461 | + | |
4e97e4e9 | 12462 | + /* Check for noresume command line option */ |
12463 | + if (test_toi_state(TOI_NORESUME_SPECIFIED)) { | |
ad8f4a28 AM |
12464 | + printk(KERN_INFO "TuxOnIce: Noresume on command line. Removed " |
12465 | + "image.\n"); | |
4e97e4e9 | 12466 | + goto out_remove_image; |
12467 | + } | |
24613191 | 12468 | + |
4e97e4e9 | 12469 | + /* Check whether we've resumed before */ |
12470 | + if (test_toi_state(TOI_RESUMED_BEFORE)) { | |
12471 | + toi_early_boot_message(1, 0, NULL); | |
12472 | + if (!(test_toi_state(TOI_CONTINUE_REQ))) { | |
ad8f4a28 | 12473 | + printk(KERN_INFO "TuxOnIce: Tried to resume before: " |
4e97e4e9 | 12474 | + "Invalidated image.\n"); |
12475 | + goto out_remove_image; | |
12476 | + } | |
12477 | + } | |
24613191 | 12478 | + |
4e97e4e9 | 12479 | + clear_toi_state(TOI_CONTINUE_REQ); |
24613191 | 12480 | + |
4e97e4e9 | 12481 | + /* Read hibernate header */ |
ad8f4a28 AM |
12482 | + result = toiActiveAllocator->rw_header_chunk(READ, NULL, |
12483 | + header_buffer, sizeof(struct toi_header)); | |
12484 | + if (result < 0) { | |
4e97e4e9 | 12485 | + printk("TuxOnIce: Failed to read the image signature.\n"); |
12486 | + goto out_remove_image; | |
12487 | + } | |
ad8f4a28 | 12488 | + |
4e97e4e9 | 12489 | + toi_header = (struct toi_header *) header_buffer; |
24613191 | 12490 | + |
4e97e4e9 | 12491 | + /* |
12492 | + * NB: This call may also result in a reboot rather than returning. | |
12493 | + */ | |
e8d0ad9d | 12494 | + |
4e97e4e9 | 12495 | + sanity_error = sanity_check(toi_header); |
12496 | + if (sanity_error) { | |
12497 | + toi_early_boot_message(1, TOI_CONTINUE_REQ, | |
12498 | + sanity_error); | |
ad8f4a28 | 12499 | + printk(KERN_INFO "TuxOnIce: Sanity check failed.\n"); |
4e97e4e9 | 12500 | + goto out_remove_image; |
12501 | + } | |
43540741 | 12502 | + |
4e97e4e9 | 12503 | + /* |
12504 | + * We have an image and it looks like it will load okay. | |
12505 | + * | |
12506 | + * Get metadata from header. Don't override commandline parameters. | |
12507 | + * | |
12508 | + * We don't need to save the image size limit because it's not used | |
12509 | + * during resume and will be restored with the image anyway. | |
12510 | + */ | |
ad8f4a28 | 12511 | + |
4e97e4e9 | 12512 | + memcpy((char *) &pagedir1, |
12513 | + (char *) &toi_header->pagedir, sizeof(pagedir1)); | |
12514 | + toi_result = toi_header->param0; | |
ad8f4a28 AM |
12515 | + toi_bkd.toi_action = toi_header->param1; |
12516 | + toi_bkd.toi_debug_state = toi_header->param2; | |
12517 | + toi_bkd.toi_default_console_level = toi_header->param3; | |
4e97e4e9 | 12518 | + clear_toi_state(TOI_IGNORE_LOGLEVEL); |
12519 | + pagedir2.size = toi_header->pageset_2_size; | |
12520 | + for (i = 0; i < 4; i++) | |
ad8f4a28 | 12521 | + toi_bkd.toi_io_time[i/2][i%2] = |
4e97e4e9 | 12522 | + toi_header->io_time[i/2][i%2]; |
1838f965 | 12523 | + |
12524 | + set_toi_state(TOI_BOOT_KERNEL); | |
ad8f4a28 | 12525 | + boot_kernel_data_buffer = toi_header->bkd; |
4e97e4e9 | 12526 | + |
12527 | + /* Read module configurations */ | |
ad8f4a28 AM |
12528 | + result = read_module_configs(); |
12529 | + if (result) { | |
4e97e4e9 | 12530 | + pagedir1.size = pagedir2.size = 0; |
ad8f4a28 | 12531 | + printk(KERN_INFO "TuxOnIce: Failed to read TuxOnIce module " |
4e97e4e9 | 12532 | + "configurations.\n"); |
12533 | + clear_action_state(TOI_KEEP_IMAGE); | |
12534 | + goto out_remove_image; | |
24613191 | 12535 | + } |
12536 | + | |
4e97e4e9 | 12537 | + toi_prepare_console(); |
24613191 | 12538 | + |
4e97e4e9 | 12539 | + set_toi_state(TOI_NOW_RESUMING); |
24613191 | 12540 | + |
1838f965 | 12541 | + if (!test_action_state(TOI_LATE_CPU_HOTPLUG)) { |
12542 | + toi_prepare_status(DONT_CLEAR_BAR, "Disable nonboot cpus."); | |
12543 | + if (disable_nonboot_cpus()) { | |
12544 | + set_abort_result(TOI_CPU_HOTPLUG_FAILED); | |
12545 | + goto out_reset_console; | |
12546 | + } | |
12547 | + } | |
12548 | + | |
12549 | + toi_prepare_status(DONT_CLEAR_BAR, "Freeze processes."); | |
24613191 | 12550 | + |
1838f965 | 12551 | + if (freeze_processes()) { |
12552 | + printk("Some processes failed to stop.\n"); | |
12553 | + goto out_thaw; | |
12554 | + } | |
4e97e4e9 | 12555 | + toi_cond_pause(1, "About to read original pageset1 locations."); |
24613191 | 12556 | + |
4e97e4e9 | 12557 | + /* |
12558 | + * Read original pageset1 locations. These are the addresses we can't | |
12559 | + * use for the data to be restored. | |
12560 | + */ | |
24613191 | 12561 | + |
1838f965 | 12562 | + if (memory_bm_create(&pageset1_copy_map, GFP_KERNEL, 0) || |
12563 | + memory_bm_create(&io_map, GFP_KERNEL, 0)) | |
12564 | + goto out_thaw; | |
24613191 | 12565 | + |
1838f965 | 12566 | + if (memory_bm_read(&pageset1_map, toiActiveAllocator->rw_header_chunk)) |
12567 | + goto out_thaw; | |
24613191 | 12568 | + |
4e97e4e9 | 12569 | + /* Clean up after reading the header */ |
ad8f4a28 AM |
12570 | + result = toiActiveAllocator->read_header_cleanup(); |
12571 | + if (result) { | |
4e97e4e9 | 12572 | + printk("TuxOnIce: Failed to cleanup after reading the image " |
12573 | + "header.\n"); | |
1838f965 | 12574 | + goto out_thaw; |
4e97e4e9 | 12575 | + } |
24613191 | 12576 | + |
4e97e4e9 | 12577 | + toi_cond_pause(1, "About to read pagedir."); |
24613191 | 12578 | + |
ad8f4a28 | 12579 | + /* |
4e97e4e9 | 12580 | + * Get the addresses of pages into which we will load the kernel to |
12581 | + * be copied back | |
12582 | + */ | |
12583 | + if (toi_get_pageset1_load_addresses()) { | |
ad8f4a28 AM |
12584 | + printk(KERN_INFO "TuxOnIce: Failed to get load addresses for " |
12585 | + "pageset1.\n"); | |
1838f965 | 12586 | + goto out_thaw; |
4e97e4e9 | 12587 | + } |
24613191 | 12588 | + |
4e97e4e9 | 12589 | + /* Read the original kernel back */ |
12590 | + toi_cond_pause(1, "About to read pageset 1."); | |
24613191 | 12591 | + |
4e97e4e9 | 12592 | + if (read_pageset(&pagedir1, 0)) { |
1838f965 | 12593 | + toi_prepare_status(DONT_CLEAR_BAR, "Failed to read pageset 1."); |
4e97e4e9 | 12594 | + result = -EIO; |
ad8f4a28 | 12595 | + printk(KERN_INFO "TuxOnIce: Failed to get load pageset1.\n"); |
1838f965 | 12596 | + goto out_thaw; |
4e97e4e9 | 12597 | + } |
24613191 | 12598 | + |
4e97e4e9 | 12599 | + toi_cond_pause(1, "About to restore original kernel."); |
12600 | + result = 0; | |
24613191 | 12601 | + |
4e97e4e9 | 12602 | + if (!test_action_state(TOI_KEEP_IMAGE) && |
12603 | + toiActiveAllocator->mark_resume_attempted) | |
12604 | + toiActiveAllocator->mark_resume_attempted(1); | |
24613191 | 12605 | + |
4e97e4e9 | 12606 | +out: |
ad8f4a28 | 12607 | + toi_free_page(25, (unsigned long) header_buffer); |
4e97e4e9 | 12608 | + return result; |
12609 | + | |
1838f965 | 12610 | +out_thaw: |
12611 | + thaw_processes(); | |
12612 | + enable_nonboot_cpus(); | |
4e97e4e9 | 12613 | +out_reset_console: |
12614 | + toi_cleanup_console(); | |
4e97e4e9 | 12615 | +out_remove_image: |
1838f965 | 12616 | + memory_bm_free(&pageset1_map, 0); |
12617 | + memory_bm_free(&pageset1_copy_map, 0); | |
12618 | + memory_bm_free(&io_map, 0); | |
4e97e4e9 | 12619 | + result = -EINVAL; |
12620 | + if (!test_action_state(TOI_KEEP_IMAGE)) | |
12621 | + toiActiveAllocator->remove_image(); | |
12622 | + toiActiveAllocator->read_header_cleanup(); | |
12623 | + noresume_reset_modules(); | |
12624 | + goto out; | |
24613191 | 12625 | +} |
12626 | + | |
4e97e4e9 | 12627 | +/* read_pageset1() |
24613191 | 12628 | + * |
4e97e4e9 | 12629 | + * Description: Attempt to read the header and pageset1 of a hibernate image. |
12630 | + * Handle the outcome, complaining where appropriate. | |
24613191 | 12631 | + */ |
12632 | + | |
4e97e4e9 | 12633 | +int read_pageset1(void) |
24613191 | 12634 | +{ |
4e97e4e9 | 12635 | + int error; |
24613191 | 12636 | + |
4e97e4e9 | 12637 | + error = __read_pageset1(); |
24613191 | 12638 | + |
ad8f4a28 AM |
12639 | + if (error && error != -ENODATA && error != -EINVAL && |
12640 | + !test_result_state(TOI_ABORTED)) | |
12641 | + abort_hibernate(TOI_IMAGE_ERROR, | |
12642 | + "TuxOnIce: Error %d resuming\n", error); | |
24613191 | 12643 | + |
4e97e4e9 | 12644 | + return error; |
12645 | +} | |
12646 | + | |
12647 | +/* | |
12648 | + * get_have_image_data() | |
12649 | + */ | |
12650 | +static char *get_have_image_data(void) | |
24613191 | 12651 | +{ |
4e97e4e9 | 12652 | + char *output_buffer = (char *) toi_get_zeroed_page(26, TOI_ATOMIC_GFP); |
12653 | + struct toi_header *toi_header; | |
24613191 | 12654 | + |
4e97e4e9 | 12655 | + if (!output_buffer) { |
ad8f4a28 | 12656 | + printk(KERN_INFO "Output buffer null.\n"); |
4e97e4e9 | 12657 | + return NULL; |
12658 | + } | |
24613191 | 12659 | + |
4e97e4e9 | 12660 | + /* Check for an image */ |
7f9d2ee0 | 12661 | + if (!toiActiveAllocator->image_exists(1) || |
4e97e4e9 | 12662 | + toiActiveAllocator->read_header_init() || |
12663 | + toiActiveAllocator->rw_header_chunk(READ, NULL, | |
12664 | + output_buffer, sizeof(struct toi_header))) { | |
12665 | + sprintf(output_buffer, "0\n"); | |
ad8f4a28 AM |
12666 | + /* |
12667 | + * From an initrd/ramfs, catting have_image and | |
12668 | + * getting a result of 0 is sufficient. | |
12669 | + */ | |
12670 | + clear_toi_state(TOI_BOOT_TIME); | |
4e97e4e9 | 12671 | + goto out; |
12672 | + } | |
24613191 | 12673 | + |
4e97e4e9 | 12674 | + toi_header = (struct toi_header *) output_buffer; |
24613191 | 12675 | + |
4e97e4e9 | 12676 | + sprintf(output_buffer, "1\n%s\n%s\n", |
12677 | + toi_header->uts.machine, | |
12678 | + toi_header->uts.version); | |
12679 | + | |
12680 | + /* Check whether we've resumed before */ | |
12681 | + if (test_toi_state(TOI_RESUMED_BEFORE)) | |
12682 | + strcat(output_buffer, "Resumed before.\n"); | |
12683 | + | |
12684 | +out: | |
12685 | + noresume_reset_modules(); | |
12686 | + return output_buffer; | |
24613191 | 12687 | +} |
12688 | + | |
4e97e4e9 | 12689 | +/* read_pageset2() |
12690 | + * | |
12691 | + * Description: Read in part or all of pageset2 of an image, depending upon | |
12692 | + * whether we are hibernating and have only overwritten a portion | |
ad8f4a28 | 12693 | + * with pageset1 pages, or are resuming and need to read them |
4e97e4e9 | 12694 | + * all. |
12695 | + * Arguments: Int. Boolean. Read only pages which would have been | |
12696 | + * overwritten by pageset1? | |
12697 | + * Returns: Int. Zero if no error, otherwise the error value. | |
12698 | + */ | |
12699 | +int read_pageset2(int overwrittenpagesonly) | |
24613191 | 12700 | +{ |
24613191 | 12701 | + int result = 0; |
12702 | + | |
4e97e4e9 | 12703 | + if (!pagedir2.size) |
24613191 | 12704 | + return 0; |
12705 | + | |
4e97e4e9 | 12706 | + result = read_pageset(&pagedir2, overwrittenpagesonly); |
24613191 | 12707 | + |
4e97e4e9 | 12708 | + toi_cond_pause(1, "Pagedir 2 read."); |
24613191 | 12709 | + |
24613191 | 12710 | + return result; |
12711 | +} | |
12712 | + | |
4e97e4e9 | 12713 | +/* image_exists_read |
ad8f4a28 | 12714 | + * |
4e97e4e9 | 12715 | + * Return 0 or 1, depending on whether an image is found. |
12716 | + * Incoming buffer is PAGE_SIZE and result is guaranteed | |
12717 | + * to be far less than that, so we don't worry about | |
12718 | + * overflow. | |
12719 | + */ | |
12720 | +int image_exists_read(const char *page, int count) | |
12721 | +{ | |
12722 | + int len = 0; | |
12723 | + char *result; | |
ad8f4a28 | 12724 | + |
4e97e4e9 | 12725 | + if (toi_activate_storage(0)) |
12726 | + return count; | |
24613191 | 12727 | + |
4e97e4e9 | 12728 | + if (!test_toi_state(TOI_RESUME_DEVICE_OK)) |
12729 | + toi_attempt_to_parse_resume_device(0); | |
24613191 | 12730 | + |
4e97e4e9 | 12731 | + if (!toiActiveAllocator) { |
12732 | + len = sprintf((char *) page, "-1\n"); | |
12733 | + } else { | |
12734 | + result = get_have_image_data(); | |
12735 | + if (result) { | |
12736 | + len = sprintf((char *) page, "%s", result); | |
ad8f4a28 | 12737 | + toi_free_page(26, (unsigned long) result); |
4e97e4e9 | 12738 | + } |
24613191 | 12739 | + } |
12740 | + | |
4e97e4e9 | 12741 | + toi_deactivate_storage(0); |
24613191 | 12742 | + |
4e97e4e9 | 12743 | + return len; |
24613191 | 12744 | +} |
12745 | + | |
4e97e4e9 | 12746 | +/* image_exists_write |
ad8f4a28 | 12747 | + * |
4e97e4e9 | 12748 | + * Invalidate an image if one exists. |
12749 | + */ | |
12750 | +int image_exists_write(const char *buffer, int count) | |
24613191 | 12751 | +{ |
4e97e4e9 | 12752 | + if (toi_activate_storage(0)) |
12753 | + return count; | |
24613191 | 12754 | + |
7f9d2ee0 | 12755 | + if (toiActiveAllocator && toiActiveAllocator->image_exists(1)) |
4e97e4e9 | 12756 | + toiActiveAllocator->remove_image(); |
12757 | + | |
12758 | + toi_deactivate_storage(0); | |
12759 | + | |
12760 | + clear_result_state(TOI_KEPT_IMAGE); | |
12761 | + | |
12762 | + return count; | |
24613191 | 12763 | +} |
4e97e4e9 | 12764 | diff --git a/kernel/power/tuxonice_io.h b/kernel/power/tuxonice_io.h |
12765 | new file mode 100644 | |
1838f965 | 12766 | index 0000000..86e8996 |
4e97e4e9 | 12767 | --- /dev/null |
12768 | +++ b/kernel/power/tuxonice_io.h | |
7f9d2ee0 | 12769 | @@ -0,0 +1,71 @@ |
4e97e4e9 | 12770 | +/* |
12771 | + * kernel/power/tuxonice_io.h | |
12772 | + * | |
1838f965 | 12773 | + * Copyright (C) 2005-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 12774 | + * |
12775 | + * This file is released under the GPLv2. | |
12776 | + * | |
12777 | + * It contains high level IO routines for hibernating. | |
12778 | + * | |
12779 | + */ | |
e8d0ad9d | 12780 | + |
4e97e4e9 | 12781 | +#include <linux/utsname.h> |
12782 | +#include "tuxonice_pagedir.h" | |
ad8f4a28 | 12783 | +#include "power.h" |
e8d0ad9d | 12784 | + |
4e97e4e9 | 12785 | +/* Non-module data saved in our image header */ |
12786 | +struct toi_header { | |
ad8f4a28 AM |
12787 | + /* |
12788 | + * Mirror struct swsusp_info, but without | |
12789 | + * the page aligned attribute | |
12790 | + */ | |
12791 | + struct new_utsname uts; | |
4e97e4e9 | 12792 | + u32 version_code; |
12793 | + unsigned long num_physpages; | |
ad8f4a28 AM |
12794 | + int cpus; |
12795 | + unsigned long image_pages; | |
12796 | + unsigned long pages; | |
12797 | + unsigned long size; | |
12798 | + | |
12799 | + /* Our own data */ | |
4e97e4e9 | 12800 | + unsigned long orig_mem_free; |
4e97e4e9 | 12801 | + int page_size; |
12802 | + int pageset_2_size; | |
12803 | + int param0; | |
12804 | + int param1; | |
12805 | + int param2; | |
12806 | + int param3; | |
12807 | + int progress0; | |
12808 | + int progress1; | |
12809 | + int progress2; | |
12810 | + int progress3; | |
12811 | + int io_time[2][2]; | |
12812 | + struct pagedir pagedir; | |
12813 | + dev_t root_fs; | |
ad8f4a28 | 12814 | + unsigned long bkd; /* Boot kernel data locn */ |
4e97e4e9 | 12815 | +}; |
e8d0ad9d | 12816 | + |
4e97e4e9 | 12817 | +extern int write_pageset(struct pagedir *pagedir); |
12818 | +extern int write_image_header(void); | |
12819 | +extern int read_pageset1(void); | |
12820 | +extern int read_pageset2(int overwrittenpagesonly); | |
e8d0ad9d | 12821 | + |
4e97e4e9 | 12822 | +extern int toi_attempt_to_parse_resume_device(int quiet); |
12823 | +extern void attempt_to_parse_resume_device2(void); | |
12824 | +extern void attempt_to_parse_alt_resume_param(void); | |
12825 | +int image_exists_read(const char *page, int count); | |
12826 | +int image_exists_write(const char *buffer, int count); | |
12827 | +extern void save_restore_alt_param(int replace, int quiet); | |
7f9d2ee0 | 12828 | +extern atomic_t toi_io_workers; |
e8d0ad9d | 12829 | + |
4e97e4e9 | 12830 | +/* Args to save_restore_alt_param */ |
12831 | +#define RESTORE 0 | |
12832 | +#define SAVE 1 | |
24613191 | 12833 | + |
4e97e4e9 | 12834 | +#define NOQUIET 0 |
12835 | +#define QUIET 1 | |
24613191 | 12836 | + |
4e97e4e9 | 12837 | +extern dev_t name_to_dev_t(char *line); |
7f9d2ee0 | 12838 | + |
12839 | +extern wait_queue_head_t toi_io_queue_flusher; | |
12840 | +extern int toi_bio_queue_flusher_should_finish; | |
4e97e4e9 | 12841 | diff --git a/kernel/power/tuxonice_modules.c b/kernel/power/tuxonice_modules.c |
12842 | new file mode 100644 | |
1838f965 | 12843 | index 0000000..29d9100 |
4e97e4e9 | 12844 | --- /dev/null |
12845 | +++ b/kernel/power/tuxonice_modules.c | |
1838f965 | 12846 | @@ -0,0 +1,464 @@ |
4e97e4e9 | 12847 | +/* |
12848 | + * kernel/power/tuxonice_modules.c | |
12849 | + * | |
1838f965 | 12850 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 12851 | + * |
12852 | + */ | |
24613191 | 12853 | + |
4e97e4e9 | 12854 | +#include <linux/suspend.h> |
12855 | +#include <linux/module.h> | |
12856 | +#include "tuxonice.h" | |
12857 | +#include "tuxonice_modules.h" | |
12858 | +#include "tuxonice_sysfs.h" | |
12859 | +#include "tuxonice_ui.h" | |
12860 | + | |
12861 | +LIST_HEAD(toi_filters); | |
12862 | +LIST_HEAD(toiAllocators); | |
12863 | +LIST_HEAD(toi_modules); | |
12864 | + | |
12865 | +struct toi_module_ops *toiActiveAllocator; | |
1838f965 | 12866 | +EXPORT_SYMBOL_GPL(toiActiveAllocator); |
12867 | + | |
12868 | +static int toi_num_filters; | |
4e97e4e9 | 12869 | +int toiNumAllocators, toi_num_modules; |
ad8f4a28 | 12870 | + |
24613191 | 12871 | +/* |
4e97e4e9 | 12872 | + * toi_header_storage_for_modules |
12873 | + * | |
12874 | + * Returns the amount of space needed to store configuration | |
12875 | + * data needed by the modules prior to copying back the original | |
12876 | + * kernel. We can exclude data for pageset2 because it will be | |
12877 | + * available anyway once the kernel is copied back. | |
24613191 | 12878 | + */ |
7f9d2ee0 | 12879 | +long toi_header_storage_for_modules(void) |
24613191 | 12880 | +{ |
4e97e4e9 | 12881 | + struct toi_module_ops *this_module; |
12882 | + int bytes = 0; | |
ad8f4a28 | 12883 | + |
4e97e4e9 | 12884 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
12885 | + if (!this_module->enabled || | |
12886 | + (this_module->type == WRITER_MODULE && | |
12887 | + toiActiveAllocator != this_module)) | |
12888 | + continue; | |
12889 | + if (this_module->storage_needed) { | |
12890 | + int this = this_module->storage_needed() + | |
12891 | + sizeof(struct toi_module_header) + | |
12892 | + sizeof(int); | |
12893 | + this_module->header_requested = this; | |
12894 | + bytes += this; | |
12895 | + } | |
12896 | + } | |
24613191 | 12897 | + |
4e97e4e9 | 12898 | + /* One more for the empty terminator */ |
12899 | + return bytes + sizeof(struct toi_module_header); | |
24613191 | 12900 | +} |
12901 | + | |
4e97e4e9 | 12902 | +/* |
12903 | + * toi_memory_for_modules | |
12904 | + * | |
12905 | + * Returns the amount of memory requested by modules for | |
12906 | + * doing their work during the cycle. | |
12907 | + */ | |
24613191 | 12908 | + |
7f9d2ee0 | 12909 | +long toi_memory_for_modules(int print_parts) |
4e97e4e9 | 12910 | +{ |
7f9d2ee0 | 12911 | + long bytes = 0, result; |
4e97e4e9 | 12912 | + struct toi_module_ops *this_module; |
e8d0ad9d | 12913 | + |
ad8f4a28 AM |
12914 | + if (print_parts) |
12915 | + printk(KERN_INFO "Memory for modules:\n===================\n"); | |
4e97e4e9 | 12916 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
ad8f4a28 | 12917 | + int this; |
4e97e4e9 | 12918 | + if (!this_module->enabled) |
12919 | + continue; | |
ad8f4a28 AM |
12920 | + if (this_module->memory_needed) { |
12921 | + this = this_module->memory_needed(); | |
12922 | + if (print_parts) | |
7f9d2ee0 | 12923 | + printk(KERN_INFO "%10d bytes (%5ld pages) for " |
12924 | + "module '%s'.\n", this, | |
12925 | + DIV_ROUND_UP(this, PAGE_SIZE), | |
ad8f4a28 AM |
12926 | + this_module->name); |
12927 | + bytes += this; | |
12928 | + } | |
4e97e4e9 | 12929 | + } |
24613191 | 12930 | + |
7f9d2ee0 | 12931 | + result = DIV_ROUND_UP(bytes, PAGE_SIZE); |
ad8f4a28 | 12932 | + if (print_parts) |
7f9d2ee0 | 12933 | + printk(KERN_INFO " => %ld bytes, %ld pages.\n", bytes, result); |
ad8f4a28 AM |
12934 | + |
12935 | + return result; | |
24613191 | 12936 | +} |
12937 | + | |
12938 | +/* | |
4e97e4e9 | 12939 | + * toi_expected_compression_ratio |
12940 | + * | |
12941 | + * Returns the compression ratio expected when saving the image. | |
24613191 | 12942 | + */ |
4e97e4e9 | 12943 | + |
12944 | +int toi_expected_compression_ratio(void) | |
24613191 | 12945 | +{ |
4e97e4e9 | 12946 | + int ratio = 100; |
12947 | + struct toi_module_ops *this_module; | |
24613191 | 12948 | + |
4e97e4e9 | 12949 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
12950 | + if (!this_module->enabled) | |
12951 | + continue; | |
12952 | + if (this_module->expected_compression) | |
ad8f4a28 AM |
12953 | + ratio = ratio * this_module->expected_compression() |
12954 | + / 100; | |
24613191 | 12955 | + } |
12956 | + | |
4e97e4e9 | 12957 | + return ratio; |
12958 | +} | |
24613191 | 12959 | + |
4e97e4e9 | 12960 | +/* toi_find_module_given_dir |
12961 | + * Functionality : Return a module (if found), given a pointer | |
12962 | + * to its directory name | |
12963 | + */ | |
24613191 | 12964 | + |
4e97e4e9 | 12965 | +static struct toi_module_ops *toi_find_module_given_dir(char *name) |
12966 | +{ | |
12967 | + struct toi_module_ops *this_module, *found_module = NULL; | |
ad8f4a28 | 12968 | + |
4e97e4e9 | 12969 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
12970 | + if (!strcmp(name, this_module->directory)) { | |
12971 | + found_module = this_module; | |
12972 | + break; | |
ad8f4a28 | 12973 | + } |
24613191 | 12974 | + } |
12975 | + | |
4e97e4e9 | 12976 | + return found_module; |
12977 | +} | |
24613191 | 12978 | + |
4e97e4e9 | 12979 | +/* toi_find_module_given_name |
12980 | + * Functionality : Return a module (if found), given a pointer | |
12981 | + * to its name | |
12982 | + */ | |
24613191 | 12983 | + |
4e97e4e9 | 12984 | +struct toi_module_ops *toi_find_module_given_name(char *name) |
12985 | +{ | |
12986 | + struct toi_module_ops *this_module, *found_module = NULL; | |
ad8f4a28 | 12987 | + |
4e97e4e9 | 12988 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
12989 | + if (!strcmp(name, this_module->name)) { | |
12990 | + found_module = this_module; | |
12991 | + break; | |
ad8f4a28 | 12992 | + } |
4e97e4e9 | 12993 | + } |
24613191 | 12994 | + |
4e97e4e9 | 12995 | + return found_module; |
24613191 | 12996 | +} |
12997 | + | |
12998 | +/* | |
4e97e4e9 | 12999 | + * toi_print_module_debug_info |
13000 | + * Functionality : Get debugging info from modules into a buffer. | |
24613191 | 13001 | + */ |
4e97e4e9 | 13002 | +int toi_print_module_debug_info(char *buffer, int buffer_size) |
13003 | +{ | |
13004 | + struct toi_module_ops *this_module; | |
13005 | + int len = 0; | |
24613191 | 13006 | + |
4e97e4e9 | 13007 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
13008 | + if (!this_module->enabled) | |
13009 | + continue; | |
13010 | + if (this_module->print_debug_info) { | |
13011 | + int result; | |
ad8f4a28 | 13012 | + result = this_module->print_debug_info(buffer + len, |
4e97e4e9 | 13013 | + buffer_size - len); |
13014 | + len += result; | |
13015 | + } | |
13016 | + } | |
24613191 | 13017 | + |
4e97e4e9 | 13018 | + /* Ensure null terminated */ |
13019 | + buffer[buffer_size] = 0; | |
24613191 | 13020 | + |
4e97e4e9 | 13021 | + return len; |
13022 | +} | |
24613191 | 13023 | + |
4e97e4e9 | 13024 | +/* |
13025 | + * toi_register_module | |
13026 | + * | |
13027 | + * Register a module. | |
13028 | + */ | |
13029 | +int toi_register_module(struct toi_module_ops *module) | |
24613191 | 13030 | +{ |
4e97e4e9 | 13031 | + int i; |
13032 | + struct kobject *kobj; | |
24613191 | 13033 | + |
4e97e4e9 | 13034 | + module->enabled = 1; |
ad8f4a28 | 13035 | + |
4e97e4e9 | 13036 | + if (toi_find_module_given_name(module->name)) { |
ad8f4a28 | 13037 | + printk(KERN_INFO "TuxOnIce: Trying to load module %s," |
4e97e4e9 | 13038 | + " which is already registered.\n", |
13039 | + module->name); | |
13040 | + return -EBUSY; | |
13041 | + } | |
24613191 | 13042 | + |
4e97e4e9 | 13043 | + switch (module->type) { |
ad8f4a28 AM |
13044 | + case FILTER_MODULE: |
13045 | + list_add_tail(&module->type_list, &toi_filters); | |
13046 | + toi_num_filters++; | |
13047 | + break; | |
13048 | + case WRITER_MODULE: | |
13049 | + list_add_tail(&module->type_list, &toiAllocators); | |
13050 | + toiNumAllocators++; | |
13051 | + break; | |
13052 | + case MISC_MODULE: | |
13053 | + case MISC_HIDDEN_MODULE: | |
13054 | + break; | |
13055 | + default: | |
13056 | + printk("Hmmm. Module '%s' has an invalid type." | |
13057 | + " It has been ignored.\n", module->name); | |
13058 | + return -EINVAL; | |
4e97e4e9 | 13059 | + } |
13060 | + list_add_tail(&module->module_list, &toi_modules); | |
13061 | + toi_num_modules++; | |
24613191 | 13062 | + |
1838f965 | 13063 | + if ((!module->directory && !module->shared_directory) || |
13064 | + !module->sysfs_data || !module->num_sysfs_entries) | |
ad8f4a28 AM |
13065 | + return 0; |
13066 | + | |
13067 | + /* | |
13068 | + * Modules may share a directory, but those with shared_dir | |
13069 | + * set must be loaded (via symbol dependencies) after parents | |
13070 | + * and unloaded beforehand. | |
13071 | + */ | |
13072 | + if (module->shared_directory) { | |
13073 | + struct toi_module_ops *shared = | |
13074 | + toi_find_module_given_dir(module->shared_directory); | |
13075 | + if (!shared) { | |
13076 | + printk("TuxOnIce: Module %s wants to share %s's " | |
13077 | + "directory but %s isn't loaded.\n", | |
13078 | + module->name, module->shared_directory, | |
13079 | + module->shared_directory); | |
13080 | + toi_unregister_module(module); | |
13081 | + return -ENODEV; | |
4e97e4e9 | 13082 | + } |
ad8f4a28 AM |
13083 | + kobj = shared->dir_kobj; |
13084 | + } else { | |
13085 | + if (!strncmp(module->directory, "[ROOT]", 6)) | |
7f9d2ee0 | 13086 | + kobj = tuxonice_kobj; |
ad8f4a28 AM |
13087 | + else |
13088 | + kobj = make_toi_sysdir(module->directory); | |
13089 | + } | |
13090 | + module->dir_kobj = kobj; | |
13091 | + for (i = 0; i < module->num_sysfs_entries; i++) { | |
13092 | + int result = toi_register_sysfs_file(kobj, | |
13093 | + &module->sysfs_data[i]); | |
13094 | + if (result) | |
13095 | + return result; | |
4e97e4e9 | 13096 | + } |
24613191 | 13097 | + return 0; |
13098 | +} | |
1838f965 | 13099 | +EXPORT_SYMBOL_GPL(toi_register_module); |
24613191 | 13100 | + |
4e97e4e9 | 13101 | +/* |
13102 | + * toi_unregister_module | |
13103 | + * | |
13104 | + * Remove a module. | |
13105 | + */ | |
13106 | +void toi_unregister_module(struct toi_module_ops *module) | |
24613191 | 13107 | +{ |
4e97e4e9 | 13108 | + int i; |
24613191 | 13109 | + |
4e97e4e9 | 13110 | + if (module->dir_kobj) |
ad8f4a28 AM |
13111 | + for (i = 0; i < module->num_sysfs_entries; i++) |
13112 | + toi_unregister_sysfs_file(module->dir_kobj, | |
13113 | + &module->sysfs_data[i]); | |
24613191 | 13114 | + |
4e97e4e9 | 13115 | + if (!module->shared_directory && module->directory && |
13116 | + strncmp(module->directory, "[ROOT]", 6)) | |
13117 | + remove_toi_sysdir(module->dir_kobj); | |
24613191 | 13118 | + |
4e97e4e9 | 13119 | + switch (module->type) { |
ad8f4a28 AM |
13120 | + case FILTER_MODULE: |
13121 | + list_del(&module->type_list); | |
13122 | + toi_num_filters--; | |
13123 | + break; | |
13124 | + case WRITER_MODULE: | |
13125 | + list_del(&module->type_list); | |
13126 | + toiNumAllocators--; | |
13127 | + if (toiActiveAllocator == module) { | |
13128 | + toiActiveAllocator = NULL; | |
13129 | + clear_toi_state(TOI_CAN_RESUME); | |
13130 | + clear_toi_state(TOI_CAN_HIBERNATE); | |
13131 | + } | |
13132 | + break; | |
13133 | + case MISC_MODULE: | |
13134 | + case MISC_HIDDEN_MODULE: | |
13135 | + break; | |
13136 | + default: | |
13137 | + printk("Hmmm. Module '%s' has an invalid type." | |
13138 | + " It has been ignored.\n", module->name); | |
13139 | + return; | |
4e97e4e9 | 13140 | + } |
13141 | + list_del(&module->module_list); | |
13142 | + toi_num_modules--; | |
24613191 | 13143 | +} |
1838f965 | 13144 | +EXPORT_SYMBOL_GPL(toi_unregister_module); |
24613191 | 13145 | + |
24613191 | 13146 | +/* |
4e97e4e9 | 13147 | + * toi_move_module_tail |
24613191 | 13148 | + * |
4e97e4e9 | 13149 | + * Rearrange modules when reloading the config. |
24613191 | 13150 | + */ |
4e97e4e9 | 13151 | +void toi_move_module_tail(struct toi_module_ops *module) |
e8d0ad9d | 13152 | +{ |
4e97e4e9 | 13153 | + switch (module->type) { |
ad8f4a28 AM |
13154 | + case FILTER_MODULE: |
13155 | + if (toi_num_filters > 1) | |
13156 | + list_move_tail(&module->type_list, &toi_filters); | |
13157 | + break; | |
13158 | + case WRITER_MODULE: | |
13159 | + if (toiNumAllocators > 1) | |
13160 | + list_move_tail(&module->type_list, &toiAllocators); | |
13161 | + break; | |
13162 | + case MISC_MODULE: | |
13163 | + case MISC_HIDDEN_MODULE: | |
13164 | + break; | |
13165 | + default: | |
13166 | + printk("Hmmm. Module '%s' has an invalid type." | |
13167 | + " It has been ignored.\n", module->name); | |
13168 | + return; | |
4e97e4e9 | 13169 | + } |
13170 | + if ((toi_num_filters + toiNumAllocators) > 1) | |
13171 | + list_move_tail(&module->module_list, &toi_modules); | |
e8d0ad9d | 13172 | +} |
13173 | + | |
e8d0ad9d | 13174 | +/* |
4e97e4e9 | 13175 | + * toi_initialise_modules |
e8d0ad9d | 13176 | + * |
4e97e4e9 | 13177 | + * Get ready to do some work! |
e8d0ad9d | 13178 | + */ |
ad8f4a28 | 13179 | +int toi_initialise_modules(int starting_cycle, int early) |
4e97e4e9 | 13180 | +{ |
13181 | + struct toi_module_ops *this_module; | |
13182 | + int result; | |
ad8f4a28 | 13183 | + |
4e97e4e9 | 13184 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
13185 | + this_module->header_requested = 0; | |
13186 | + this_module->header_used = 0; | |
13187 | + if (!this_module->enabled) | |
13188 | + continue; | |
ad8f4a28 AM |
13189 | + if (this_module->early != early) |
13190 | + continue; | |
4e97e4e9 | 13191 | + if (this_module->initialise) { |
13192 | + toi_message(TOI_MEMORY, TOI_MEDIUM, 1, | |
13193 | + "Initialising module %s.\n", | |
13194 | + this_module->name); | |
ad8f4a28 | 13195 | + result = this_module->initialise(starting_cycle); |
f3e0dcc9 PS |
13196 | + if (result) { |
13197 | + toi_cleanup_modules(starting_cycle); | |
4e97e4e9 | 13198 | + return result; |
f3e0dcc9 PS |
13199 | + } |
13200 | + this_module->initialised = 1; | |
4e97e4e9 | 13201 | + } |
13202 | + } | |
43540741 | 13203 | + |
4e97e4e9 | 13204 | + return 0; |
13205 | +} | |
43540741 | 13206 | + |
ad8f4a28 | 13207 | +/* |
4e97e4e9 | 13208 | + * toi_cleanup_modules |
13209 | + * | |
13210 | + * Tell modules the work is done. | |
13211 | + */ | |
13212 | +void toi_cleanup_modules(int finishing_cycle) | |
43540741 | 13213 | +{ |
4e97e4e9 | 13214 | + struct toi_module_ops *this_module; |
ad8f4a28 | 13215 | + |
4e97e4e9 | 13216 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
f3e0dcc9 | 13217 | + if (!this_module->enabled || !this_module->initialised) |
4e97e4e9 | 13218 | + continue; |
13219 | + if (this_module->cleanup) { | |
13220 | + toi_message(TOI_MEMORY, TOI_MEDIUM, 1, | |
13221 | + "Cleaning up module %s.\n", | |
13222 | + this_module->name); | |
13223 | + this_module->cleanup(finishing_cycle); | |
13224 | + } | |
f3e0dcc9 | 13225 | + this_module->initialised = 0; |
43540741 | 13226 | + } |
43540741 | 13227 | +} |
e8d0ad9d | 13228 | + |
4e97e4e9 | 13229 | +/* |
13230 | + * toi_get_next_filter | |
13231 | + * | |
13232 | + * Get the next filter in the pipeline. | |
13233 | + */ | |
13234 | +struct toi_module_ops *toi_get_next_filter(struct toi_module_ops *filter_sought) | |
13235 | +{ | |
13236 | + struct toi_module_ops *last_filter = NULL, *this_filter = NULL; | |
e8d0ad9d | 13237 | + |
4e97e4e9 | 13238 | + list_for_each_entry(this_filter, &toi_filters, type_list) { |
13239 | + if (!this_filter->enabled) | |
13240 | + continue; | |
13241 | + if ((last_filter == filter_sought) || (!filter_sought)) | |
13242 | + return this_filter; | |
13243 | + last_filter = this_filter; | |
13244 | + } | |
e8d0ad9d | 13245 | + |
4e97e4e9 | 13246 | + return toiActiveAllocator; |
e8d0ad9d | 13247 | +} |
1838f965 | 13248 | +EXPORT_SYMBOL_GPL(toi_get_next_filter); |
e8d0ad9d | 13249 | + |
4e97e4e9 | 13250 | +/** |
13251 | + * toi_show_modules: Printk what support is loaded. | |
13252 | + */ | |
13253 | +void toi_print_modules(void) | |
e8d0ad9d | 13254 | +{ |
4e97e4e9 | 13255 | + struct toi_module_ops *this_module; |
13256 | + int prev = 0; | |
e8d0ad9d | 13257 | + |
4e97e4e9 | 13258 | + printk("TuxOnIce " TOI_CORE_VERSION ", with support for"); |
ad8f4a28 | 13259 | + |
4e97e4e9 | 13260 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
13261 | + if (this_module->type == MISC_HIDDEN_MODULE) | |
13262 | + continue; | |
13263 | + printk("%s %s%s%s", prev ? "," : "", | |
13264 | + this_module->enabled ? "" : "[", | |
13265 | + this_module->name, | |
13266 | + this_module->enabled ? "" : "]"); | |
13267 | + prev = 1; | |
13268 | + } | |
e8d0ad9d | 13269 | + |
4e97e4e9 | 13270 | + printk(".\n"); |
e8d0ad9d | 13271 | +} |
13272 | + | |
4e97e4e9 | 13273 | +/* toi_get_modules |
ad8f4a28 | 13274 | + * |
4e97e4e9 | 13275 | + * Take a reference to modules so they can't go away under us. |
13276 | + */ | |
e8d0ad9d | 13277 | + |
4e97e4e9 | 13278 | +int toi_get_modules(void) |
e8d0ad9d | 13279 | +{ |
4e97e4e9 | 13280 | + struct toi_module_ops *this_module; |
ad8f4a28 | 13281 | + |
4e97e4e9 | 13282 | + list_for_each_entry(this_module, &toi_modules, module_list) { |
ad8f4a28 AM |
13283 | + struct toi_module_ops *this_module2; |
13284 | + | |
13285 | + if (try_module_get(this_module->module)) | |
13286 | + continue; | |
13287 | + | |
13288 | + /* Failed! Reverse gets and return error */ | |
13289 | + list_for_each_entry(this_module2, &toi_modules, | |
13290 | + module_list) { | |
13291 | + if (this_module == this_module2) | |
13292 | + return -EINVAL; | |
13293 | + module_put(this_module2->module); | |
4e97e4e9 | 13294 | + } |
13295 | + } | |
4e97e4e9 | 13296 | + return 0; |
e8d0ad9d | 13297 | +} |
13298 | + | |
4e97e4e9 | 13299 | +/* toi_put_modules |
13300 | + * | |
13301 | + * Release our references to modules we used. | |
13302 | + */ | |
13303 | + | |
13304 | +void toi_put_modules(void) | |
43540741 | 13305 | +{ |
4e97e4e9 | 13306 | + struct toi_module_ops *this_module; |
ad8f4a28 | 13307 | + |
4e97e4e9 | 13308 | + list_for_each_entry(this_module, &toi_modules, module_list) |
13309 | + module_put(this_module->module); | |
43540741 | 13310 | +} |
4e97e4e9 | 13311 | diff --git a/kernel/power/tuxonice_modules.h b/kernel/power/tuxonice_modules.h |
13312 | new file mode 100644 | |
1838f965 | 13313 | index 0000000..1c13561 |
4e97e4e9 | 13314 | --- /dev/null |
13315 | +++ b/kernel/power/tuxonice_modules.h | |
1838f965 | 13316 | @@ -0,0 +1,185 @@ |
4e97e4e9 | 13317 | +/* |
13318 | + * kernel/power/tuxonice_modules.h | |
13319 | + * | |
1838f965 | 13320 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 13321 | + * |
13322 | + * This file is released under the GPLv2. | |
13323 | + * | |
13324 | + * It contains declarations for modules. Modules are additions to | |
13325 | + * TuxOnIce that provide facilities such as image compression or | |
13326 | + * encryption, backends for storage of the image and user interfaces. | |
13327 | + * | |
13328 | + */ | |
43540741 | 13329 | + |
4e97e4e9 | 13330 | +#ifndef TOI_MODULES_H |
13331 | +#define TOI_MODULES_H | |
e8d0ad9d | 13332 | + |
4e97e4e9 | 13333 | +/* This is the maximum size we store in the image header for a module name */ |
13334 | +#define TOI_MAX_MODULE_NAME_LENGTH 30 | |
e8d0ad9d | 13335 | + |
4e97e4e9 | 13336 | +/* Per-module metadata */ |
13337 | +struct toi_module_header { | |
13338 | + char name[TOI_MAX_MODULE_NAME_LENGTH]; | |
13339 | + int enabled; | |
13340 | + int type; | |
13341 | + int index; | |
13342 | + int data_length; | |
13343 | + unsigned long signature; | |
13344 | +}; | |
e8d0ad9d | 13345 | + |
4e97e4e9 | 13346 | +enum { |
13347 | + FILTER_MODULE, | |
13348 | + WRITER_MODULE, | |
13349 | + MISC_MODULE, /* Block writer, eg. */ | |
13350 | + MISC_HIDDEN_MODULE, | |
13351 | +}; | |
e8d0ad9d | 13352 | + |
4e97e4e9 | 13353 | +enum { |
13354 | + TOI_ASYNC, | |
13355 | + TOI_SYNC | |
13356 | +}; | |
e8d0ad9d | 13357 | + |
4e97e4e9 | 13358 | +struct toi_module_ops { |
13359 | + /* Functions common to all modules */ | |
13360 | + int type; | |
13361 | + char *name; | |
13362 | + char *directory; | |
13363 | + char *shared_directory; | |
13364 | + struct kobject *dir_kobj; | |
13365 | + struct module *module; | |
f3e0dcc9 | 13366 | + int enabled, early, initialised; |
4e97e4e9 | 13367 | + struct list_head module_list; |
e8d0ad9d | 13368 | + |
4e97e4e9 | 13369 | + /* List of filters or allocators */ |
13370 | + struct list_head list, type_list; | |
e8d0ad9d | 13371 | + |
4e97e4e9 | 13372 | + /* |
13373 | + * Requirements for memory and storage in | |
13374 | + * the image header.. | |
13375 | + */ | |
13376 | + int (*memory_needed) (void); | |
13377 | + int (*storage_needed) (void); | |
e8d0ad9d | 13378 | + |
4e97e4e9 | 13379 | + int header_requested, header_used; |
e8d0ad9d | 13380 | + |
4e97e4e9 | 13381 | + int (*expected_compression) (void); |
ad8f4a28 AM |
13382 | + |
13383 | + /* | |
4e97e4e9 | 13384 | + * Debug info |
13385 | + */ | |
13386 | + int (*print_debug_info) (char *buffer, int size); | |
13387 | + int (*save_config_info) (char *buffer); | |
13388 | + void (*load_config_info) (char *buffer, int len); | |
e8d0ad9d | 13389 | + |
ad8f4a28 | 13390 | + /* |
4e97e4e9 | 13391 | + * Initialise & cleanup - general routines called |
13392 | + * at the start and end of a cycle. | |
13393 | + */ | |
13394 | + int (*initialise) (int starting_cycle); | |
13395 | + void (*cleanup) (int finishing_cycle); | |
e8d0ad9d | 13396 | + |
ad8f4a28 | 13397 | + /* |
4e97e4e9 | 13398 | + * Calls for allocating storage (allocators only). |
13399 | + * | |
13400 | + * Header space is allocated separately. Note that allocation | |
ad8f4a28 | 13401 | + * of space for the header might result in allocated space |
4e97e4e9 | 13402 | + * being stolen from the main pool if there is no unallocated |
13403 | + * space. We have to be able to allocate enough space for | |
13404 | + * the header. We can eat memory to ensure there is enough | |
13405 | + * for the main pool. | |
13406 | + */ | |
e8d0ad9d | 13407 | + |
4e97e4e9 | 13408 | + int (*storage_available) (void); |
7f9d2ee0 | 13409 | + void (*reserve_header_space) (int space_requested); |
4e97e4e9 | 13410 | + int (*allocate_storage) (int space_requested); |
13411 | + int (*storage_allocated) (void); | |
13412 | + int (*release_storage) (void); | |
ad8f4a28 | 13413 | + |
4e97e4e9 | 13414 | + /* |
13415 | + * Routines used in image I/O. | |
13416 | + */ | |
13417 | + int (*rw_init) (int rw, int stream_number); | |
13418 | + int (*rw_cleanup) (int rw); | |
13419 | + int (*write_page) (unsigned long index, struct page *buffer_page, | |
13420 | + unsigned int buf_size); | |
13421 | + int (*read_page) (unsigned long *index, struct page *buffer_page, | |
13422 | + unsigned int *buf_size); | |
7f9d2ee0 | 13423 | + void (*io_flusher) (int rw); |
e8d0ad9d | 13424 | + |
4e97e4e9 | 13425 | + /* Reset module if image exists but reading aborted */ |
13426 | + void (*noresume_reset) (void); | |
e8d0ad9d | 13427 | + |
ad8f4a28 | 13428 | + /* Read and write the metadata */ |
4e97e4e9 | 13429 | + int (*write_header_init) (void); |
13430 | + int (*write_header_cleanup) (void); | |
e8d0ad9d | 13431 | + |
4e97e4e9 | 13432 | + int (*read_header_init) (void); |
13433 | + int (*read_header_cleanup) (void); | |
13434 | + | |
13435 | + int (*rw_header_chunk) (int rw, struct toi_module_ops *owner, | |
13436 | + char *buffer_start, int buffer_size); | |
ad8f4a28 | 13437 | + |
7f9d2ee0 | 13438 | + int (*rw_header_chunk_noreadahead) (int rw, |
13439 | + struct toi_module_ops *owner, char *buffer_start, | |
13440 | + int buffer_size); | |
13441 | + | |
4e97e4e9 | 13442 | + /* Attempt to parse an image location */ |
13443 | + int (*parse_sig_location) (char *buffer, int only_writer, int quiet); | |
e8d0ad9d | 13444 | + |
1838f965 | 13445 | + /* Throttle I/O according to throughput */ |
13446 | + void (*update_throughput_throttle) (int jif_index); | |
13447 | + | |
13448 | + /* Monitor outstanding I/O */ | |
13449 | + void (*monitor_outstanding_io) (void); | |
13450 | + | |
13451 | + /* Flush outstanding I/O */ | |
13452 | + void (*finish_all_io) (void); | |
13453 | + | |
4e97e4e9 | 13454 | + /* Determine whether image exists that we can restore */ |
7f9d2ee0 | 13455 | + int (*image_exists) (int quiet); |
ad8f4a28 | 13456 | + |
4e97e4e9 | 13457 | + /* Mark the image as having tried to resume */ |
7f9d2ee0 | 13458 | + int (*mark_resume_attempted) (int); |
e8d0ad9d | 13459 | + |
4e97e4e9 | 13460 | + /* Destroy image if one exists */ |
13461 | + int (*remove_image) (void); | |
ad8f4a28 | 13462 | + |
4e97e4e9 | 13463 | + /* Sysfs Data */ |
13464 | + struct toi_sysfs_data *sysfs_data; | |
13465 | + int num_sysfs_entries; | |
13466 | +}; | |
e8d0ad9d | 13467 | + |
4e97e4e9 | 13468 | +extern int toi_num_modules, toiNumAllocators; |
e8d0ad9d | 13469 | + |
4e97e4e9 | 13470 | +extern struct toi_module_ops *toiActiveAllocator; |
13471 | +extern struct list_head toi_filters, toiAllocators, toi_modules; | |
24613191 | 13472 | + |
4e97e4e9 | 13473 | +extern void toi_prepare_console_modules(void); |
13474 | +extern void toi_cleanup_console_modules(void); | |
24613191 | 13475 | + |
4e97e4e9 | 13476 | +extern struct toi_module_ops *toi_find_module_given_name(char *name); |
13477 | +extern struct toi_module_ops *toi_get_next_filter(struct toi_module_ops *); | |
24613191 | 13478 | + |
4e97e4e9 | 13479 | +extern int toi_register_module(struct toi_module_ops *module); |
13480 | +extern void toi_move_module_tail(struct toi_module_ops *module); | |
13481 | + | |
7f9d2ee0 | 13482 | +extern long toi_header_storage_for_modules(void); |
13483 | +extern long toi_memory_for_modules(int print_parts); | |
4e97e4e9 | 13484 | +extern int toi_expected_compression_ratio(void); |
13485 | + | |
13486 | +extern int toi_print_module_debug_info(char *buffer, int buffer_size); | |
13487 | +extern int toi_register_module(struct toi_module_ops *module); | |
13488 | +extern void toi_unregister_module(struct toi_module_ops *module); | |
e8d0ad9d | 13489 | + |
ad8f4a28 AM |
13490 | +extern int toi_initialise_modules(int starting_cycle, int early); |
13491 | +#define toi_initialise_modules_early(starting) \ | |
13492 | + toi_initialise_modules(starting, 1) | |
13493 | +#define toi_initialise_modules_late(starting) \ | |
13494 | + toi_initialise_modules(starting, 0) | |
4e97e4e9 | 13495 | +extern void toi_cleanup_modules(int finishing_cycle); |
13496 | + | |
13497 | +extern void toi_print_modules(void); | |
13498 | + | |
13499 | +int toi_get_modules(void); | |
13500 | +void toi_put_modules(void); | |
13501 | +#endif | |
13502 | diff --git a/kernel/power/tuxonice_netlink.c b/kernel/power/tuxonice_netlink.c | |
13503 | new file mode 100644 | |
1838f965 | 13504 | index 0000000..bb027a7 |
4e97e4e9 | 13505 | --- /dev/null |
13506 | +++ b/kernel/power/tuxonice_netlink.c | |
1838f965 | 13507 | @@ -0,0 +1,343 @@ |
24613191 | 13508 | +/* |
4e97e4e9 | 13509 | + * kernel/power/tuxonice_netlink.c |
24613191 | 13510 | + * |
1838f965 | 13511 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 13512 | + * |
4e97e4e9 | 13513 | + * This file is released under the GPLv2. |
24613191 | 13514 | + * |
4e97e4e9 | 13515 | + * Functions for communicating with a userspace helper via netlink. |
24613191 | 13516 | + */ |
13517 | + | |
4e97e4e9 | 13518 | + |
24613191 | 13519 | +#include <linux/suspend.h> |
4e97e4e9 | 13520 | +#include "tuxonice_netlink.h" |
13521 | +#include "tuxonice.h" | |
13522 | +#include "tuxonice_modules.h" | |
ad8f4a28 | 13523 | +#include "tuxonice_alloc.h" |
24613191 | 13524 | + |
1838f965 | 13525 | +static struct user_helper_data *uhd_list; |
24613191 | 13526 | + |
ad8f4a28 AM |
13527 | +/* |
13528 | + * Refill our pool of SKBs for use in emergencies (eg, when eating memory and | |
13529 | + * none can be allocated). | |
4e97e4e9 | 13530 | + */ |
13531 | +static void toi_fill_skb_pool(struct user_helper_data *uhd) | |
13532 | +{ | |
13533 | + while (uhd->pool_level < uhd->pool_limit) { | |
13534 | + struct sk_buff *new_skb = | |
13535 | + alloc_skb(NLMSG_SPACE(uhd->skb_size), TOI_ATOMIC_GFP); | |
24613191 | 13536 | + |
4e97e4e9 | 13537 | + if (!new_skb) |
13538 | + break; | |
24613191 | 13539 | + |
4e97e4e9 | 13540 | + new_skb->next = uhd->emerg_skbs; |
13541 | + uhd->emerg_skbs = new_skb; | |
13542 | + uhd->pool_level++; | |
13543 | + } | |
13544 | +} | |
e8d0ad9d | 13545 | + |
ad8f4a28 | 13546 | +/* |
4e97e4e9 | 13547 | + * Try to allocate a single skb. If we can't get one, try to use one from |
13548 | + * our pool. | |
13549 | + */ | |
13550 | +static struct sk_buff *toi_get_skb(struct user_helper_data *uhd) | |
13551 | +{ | |
13552 | + struct sk_buff *skb = | |
13553 | + alloc_skb(NLMSG_SPACE(uhd->skb_size), TOI_ATOMIC_GFP); | |
24613191 | 13554 | + |
4e97e4e9 | 13555 | + if (skb) |
13556 | + return skb; | |
13557 | + | |
13558 | + skb = uhd->emerg_skbs; | |
13559 | + if (skb) { | |
13560 | + uhd->pool_level--; | |
13561 | + uhd->emerg_skbs = skb->next; | |
13562 | + skb->next = NULL; | |
13563 | + } | |
13564 | + | |
13565 | + return skb; | |
13566 | +} | |
13567 | + | |
13568 | +static void put_skb(struct user_helper_data *uhd, struct sk_buff *skb) | |
13569 | +{ | |
13570 | + if (uhd->pool_level < uhd->pool_limit) { | |
13571 | + skb->next = uhd->emerg_skbs; | |
13572 | + uhd->emerg_skbs = skb; | |
13573 | + } else | |
13574 | + kfree_skb(skb); | |
13575 | +} | |
13576 | + | |
13577 | +void toi_send_netlink_message(struct user_helper_data *uhd, | |
ad8f4a28 | 13578 | + int type, void *params, size_t len) |
4e97e4e9 | 13579 | +{ |
13580 | + struct sk_buff *skb; | |
13581 | + struct nlmsghdr *nlh; | |
13582 | + void *dest; | |
13583 | + struct task_struct *t; | |
24613191 | 13584 | + |
4e97e4e9 | 13585 | + if (uhd->pid == -1) |
13586 | + return; | |
24613191 | 13587 | + |
1838f965 | 13588 | + if (uhd->debug) |
13589 | + printk(KERN_ERR "toi_send_netlink_message: Send " | |
13590 | + "message type %d.\n", type); | |
13591 | + | |
4e97e4e9 | 13592 | + skb = toi_get_skb(uhd); |
13593 | + if (!skb) { | |
ad8f4a28 | 13594 | + printk(KERN_INFO "toi_netlink: Can't allocate skb!\n"); |
4e97e4e9 | 13595 | + return; |
13596 | + } | |
24613191 | 13597 | + |
4e97e4e9 | 13598 | + /* NLMSG_PUT contains a hidden goto nlmsg_failure */ |
13599 | + nlh = NLMSG_PUT(skb, 0, uhd->sock_seq, type, len); | |
13600 | + uhd->sock_seq++; | |
24613191 | 13601 | + |
4e97e4e9 | 13602 | + dest = NLMSG_DATA(nlh); |
13603 | + if (params && len > 0) | |
13604 | + memcpy(dest, params, len); | |
24613191 | 13605 | + |
4e97e4e9 | 13606 | + netlink_unicast(uhd->nl, skb, uhd->pid, 0); |
24613191 | 13607 | + |
4e97e4e9 | 13608 | + read_lock(&tasklist_lock); |
fea155ea | 13609 | + t = find_task_by_pid_type_ns(PIDTYPE_PID, uhd->pid, &init_pid_ns); |
ad8f4a28 | 13610 | + if (!t) { |
4e97e4e9 | 13611 | + read_unlock(&tasklist_lock); |
13612 | + if (uhd->pid > -1) | |
ad8f4a28 AM |
13613 | + printk(KERN_INFO "Hmm. Can't find the userspace task" |
13614 | + " %d.\n", uhd->pid); | |
4e97e4e9 | 13615 | + return; |
13616 | + } | |
13617 | + wake_up_process(t); | |
13618 | + read_unlock(&tasklist_lock); | |
24613191 | 13619 | + |
4e97e4e9 | 13620 | + yield(); |
24613191 | 13621 | + |
4e97e4e9 | 13622 | + return; |
24613191 | 13623 | + |
4e97e4e9 | 13624 | +nlmsg_failure: |
13625 | + if (skb) | |
13626 | + put_skb(uhd, skb); | |
1838f965 | 13627 | + |
13628 | + if (uhd->debug) | |
13629 | + printk(KERN_ERR "toi_send_netlink_message: Failed to send " | |
13630 | + "message type %d.\n", type); | |
4e97e4e9 | 13631 | +} |
ad8f4a28 | 13632 | +EXPORT_SYMBOL_GPL(toi_send_netlink_message); |
24613191 | 13633 | + |
4e97e4e9 | 13634 | +static void send_whether_debugging(struct user_helper_data *uhd) |
13635 | +{ | |
1838f965 | 13636 | + static u8 is_debugging = 1; |
24613191 | 13637 | + |
4e97e4e9 | 13638 | + toi_send_netlink_message(uhd, NETLINK_MSG_IS_DEBUGGING, |
1838f965 | 13639 | + &is_debugging, sizeof(u8)); |
4e97e4e9 | 13640 | +} |
13641 | + | |
13642 | +/* | |
13643 | + * Set the PF_NOFREEZE flag on the given process to ensure it can run whilst we | |
13644 | + * are hibernating. | |
13645 | + */ | |
1838f965 | 13646 | +static int nl_set_nofreeze(struct user_helper_data *uhd, __u32 pid) |
4e97e4e9 | 13647 | +{ |
13648 | + struct task_struct *t; | |
24613191 | 13649 | + |
1838f965 | 13650 | + if (uhd->debug) |
13651 | + printk(KERN_ERR "nl_set_nofreeze for pid %d.\n", pid); | |
13652 | + | |
4e97e4e9 | 13653 | + read_lock(&tasklist_lock); |
fea155ea | 13654 | + t = find_task_by_pid_type_ns(PIDTYPE_PID, pid, &init_pid_ns); |
ad8f4a28 | 13655 | + if (!t) { |
4e97e4e9 | 13656 | + read_unlock(&tasklist_lock); |
ad8f4a28 AM |
13657 | + printk(KERN_INFO "Strange. Can't find the userspace task %d.\n", |
13658 | + pid); | |
4e97e4e9 | 13659 | + return -EINVAL; |
13660 | + } | |
13661 | + | |
13662 | + t->flags |= PF_NOFREEZE; | |
24613191 | 13663 | + |
4e97e4e9 | 13664 | + read_unlock(&tasklist_lock); |
13665 | + uhd->pid = pid; | |
24613191 | 13666 | + |
4e97e4e9 | 13667 | + toi_send_netlink_message(uhd, NETLINK_MSG_NOFREEZE_ACK, NULL, 0); |
24613191 | 13668 | + |
4e97e4e9 | 13669 | + return 0; |
13670 | +} | |
24613191 | 13671 | + |
13672 | +/* | |
4e97e4e9 | 13673 | + * Called when the userspace process has informed us that it's ready to roll. |
24613191 | 13674 | + */ |
1838f965 | 13675 | +static int nl_ready(struct user_helper_data *uhd, u32 version) |
24613191 | 13676 | +{ |
4e97e4e9 | 13677 | + if (version != uhd->interface_version) { |
ad8f4a28 | 13678 | + printk(KERN_INFO "%s userspace process using invalid interface" |
1838f965 | 13679 | + " version (%d - kernel wants %d). Trying to " |
13680 | + "continue without it.\n", | |
13681 | + uhd->name, version, uhd->interface_version); | |
4e97e4e9 | 13682 | + if (uhd->not_ready) |
13683 | + uhd->not_ready(); | |
ad8f4a28 | 13684 | + return -EINVAL; |
24613191 | 13685 | + } |
13686 | + | |
4e97e4e9 | 13687 | + complete(&uhd->wait_for_process); |
13688 | + | |
13689 | + return 0; | |
24613191 | 13690 | +} |
13691 | + | |
4e97e4e9 | 13692 | +void toi_netlink_close_complete(struct user_helper_data *uhd) |
13693 | +{ | |
13694 | + if (uhd->nl) { | |
1838f965 | 13695 | + netlink_kernel_release(uhd->nl); |
4e97e4e9 | 13696 | + uhd->nl = NULL; |
13697 | + } | |
13698 | + | |
13699 | + while (uhd->emerg_skbs) { | |
13700 | + struct sk_buff *next = uhd->emerg_skbs->next; | |
13701 | + kfree_skb(uhd->emerg_skbs); | |
13702 | + uhd->emerg_skbs = next; | |
13703 | + } | |
24613191 | 13704 | + |
4e97e4e9 | 13705 | + uhd->pid = -1; |
4e97e4e9 | 13706 | +} |
f3e0dcc9 | 13707 | +EXPORT_SYMBOL_GPL(toi_netlink_close_complete); |
4e97e4e9 | 13708 | + |
13709 | +static int toi_nl_gen_rcv_msg(struct user_helper_data *uhd, | |
13710 | + struct sk_buff *skb, struct nlmsghdr *nlh) | |
24613191 | 13711 | +{ |
1838f965 | 13712 | + int type = nlh->nlmsg_type; |
4e97e4e9 | 13713 | + int *data; |
13714 | + int err; | |
24613191 | 13715 | + |
1838f965 | 13716 | + if (uhd->debug) |
13717 | + printk(KERN_ERR "toi_user_rcv_skb: Received message %d.\n", | |
13718 | + type); | |
13719 | + | |
4e97e4e9 | 13720 | + /* Let the more specific handler go first. It returns |
13721 | + * 1 for valid messages that it doesn't know. */ | |
ad8f4a28 AM |
13722 | + err = uhd->rcv_msg(skb, nlh); |
13723 | + if (err != 1) | |
4e97e4e9 | 13724 | + return err; |
ad8f4a28 | 13725 | + |
4e97e4e9 | 13726 | + /* Only allow one task to receive NOFREEZE privileges */ |
13727 | + if (type == NETLINK_MSG_NOFREEZE_ME && uhd->pid != -1) { | |
1838f965 | 13728 | + printk(KERN_INFO "Received extra nofreeze me requests.\n"); |
4e97e4e9 | 13729 | + return -EBUSY; |
24613191 | 13730 | + } |
ad8f4a28 | 13731 | + |
1838f965 | 13732 | + data = NLMSG_DATA(nlh); |
ad8f4a28 AM |
13733 | + |
13734 | + switch (type) { | |
13735 | + case NETLINK_MSG_NOFREEZE_ME: | |
13736 | + return nl_set_nofreeze(uhd, nlh->nlmsg_pid); | |
13737 | + case NETLINK_MSG_GET_DEBUGGING: | |
13738 | + send_whether_debugging(uhd); | |
13739 | + return 0; | |
13740 | + case NETLINK_MSG_READY: | |
1838f965 | 13741 | + if (nlh->nlmsg_len != NLMSG_LENGTH(sizeof(u32))) { |
ad8f4a28 | 13742 | + printk(KERN_INFO "Invalid ready mesage.\n"); |
1838f965 | 13743 | + if (uhd->not_ready) |
13744 | + uhd->not_ready(); | |
ad8f4a28 AM |
13745 | + return -EINVAL; |
13746 | + } | |
1838f965 | 13747 | + return nl_ready(uhd, (u32) *data); |
ad8f4a28 AM |
13748 | + case NETLINK_MSG_CLEANUP: |
13749 | + toi_netlink_close_complete(uhd); | |
13750 | + return 0; | |
4e97e4e9 | 13751 | + } |
24613191 | 13752 | + |
ad8f4a28 | 13753 | + return -EINVAL; |
4e97e4e9 | 13754 | +} |
13755 | + | |
ad8f4a28 | 13756 | +static void toi_user_rcv_skb(struct sk_buff *skb) |
24613191 | 13757 | +{ |
4e97e4e9 | 13758 | + int err; |
13759 | + struct nlmsghdr *nlh; | |
ad8f4a28 AM |
13760 | + struct user_helper_data *uhd = uhd_list; |
13761 | + | |
13762 | + while (uhd && uhd->netlink_id != skb->sk->sk_protocol) | |
13763 | + uhd = uhd->next; | |
13764 | + | |
13765 | + if (!uhd) | |
13766 | + return; | |
24613191 | 13767 | + |
4e97e4e9 | 13768 | + while (skb->len >= NLMSG_SPACE(0)) { |
13769 | + u32 rlen; | |
24613191 | 13770 | + |
4e97e4e9 | 13771 | + nlh = (struct nlmsghdr *) skb->data; |
13772 | + if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) | |
13773 | + return; | |
24613191 | 13774 | + |
4e97e4e9 | 13775 | + rlen = NLMSG_ALIGN(nlh->nlmsg_len); |
13776 | + if (rlen > skb->len) | |
13777 | + rlen = skb->len; | |
24613191 | 13778 | + |
ad8f4a28 AM |
13779 | + err = toi_nl_gen_rcv_msg(uhd, skb, nlh); |
13780 | + if (err) | |
4e97e4e9 | 13781 | + netlink_ack(skb, nlh, err); |
13782 | + else if (nlh->nlmsg_flags & NLM_F_ACK) | |
13783 | + netlink_ack(skb, nlh, 0); | |
13784 | + skb_pull(skb, rlen); | |
24613191 | 13785 | + } |
24613191 | 13786 | +} |
13787 | + | |
4e97e4e9 | 13788 | +static int netlink_prepare(struct user_helper_data *uhd) |
24613191 | 13789 | +{ |
4e97e4e9 | 13790 | + uhd->next = uhd_list; |
13791 | + uhd_list = uhd; | |
13792 | + | |
13793 | + uhd->sock_seq = 0x42c0ffee; | |
ad8f4a28 AM |
13794 | + uhd->nl = netlink_kernel_create(&init_net, uhd->netlink_id, 0, |
13795 | + toi_user_rcv_skb, NULL, THIS_MODULE); | |
4e97e4e9 | 13796 | + if (!uhd->nl) { |
ad8f4a28 | 13797 | + printk(KERN_INFO "Failed to allocate netlink socket for %s.\n", |
4e97e4e9 | 13798 | + uhd->name); |
13799 | + return -ENOMEM; | |
13800 | + } | |
13801 | + | |
13802 | + toi_fill_skb_pool(uhd); | |
13803 | + | |
13804 | + return 0; | |
24613191 | 13805 | +} |
13806 | + | |
4e97e4e9 | 13807 | +void toi_netlink_close(struct user_helper_data *uhd) |
24613191 | 13808 | +{ |
4e97e4e9 | 13809 | + struct task_struct *t; |
13810 | + | |
13811 | + read_lock(&tasklist_lock); | |
fea155ea | 13812 | + t = find_task_by_pid_type_ns(PIDTYPE_PID, uhd->pid, &init_pid_ns); |
ad8f4a28 | 13813 | + if (t) |
4e97e4e9 | 13814 | + t->flags &= ~PF_NOFREEZE; |
13815 | + read_unlock(&tasklist_lock); | |
24613191 | 13816 | + |
4e97e4e9 | 13817 | + toi_send_netlink_message(uhd, NETLINK_MSG_CLEANUP, NULL, 0); |
24613191 | 13818 | +} |
ad8f4a28 | 13819 | +EXPORT_SYMBOL_GPL(toi_netlink_close); |
24613191 | 13820 | + |
4e97e4e9 | 13821 | +int toi_netlink_setup(struct user_helper_data *uhd) |
24613191 | 13822 | +{ |
f3e0dcc9 PS |
13823 | + /* In case userui didn't cleanup properly on us */ |
13824 | + toi_netlink_close_complete(uhd); | |
13825 | + | |
4e97e4e9 | 13826 | + if (netlink_prepare(uhd) < 0) { |
ad8f4a28 | 13827 | + printk(KERN_INFO "Netlink prepare failed.\n"); |
4e97e4e9 | 13828 | + return 1; |
13829 | + } | |
24613191 | 13830 | + |
ad8f4a28 | 13831 | + if (toi_launch_userspace_program(uhd->program, uhd->netlink_id, |
1838f965 | 13832 | + UMH_WAIT_EXEC, uhd->debug) < 0) { |
ad8f4a28 | 13833 | + printk(KERN_INFO "Launch userspace program failed.\n"); |
4e97e4e9 | 13834 | + toi_netlink_close_complete(uhd); |
13835 | + return 1; | |
13836 | + } | |
24613191 | 13837 | + |
4e97e4e9 | 13838 | + /* Wait 2 seconds for the userspace process to make contact */ |
13839 | + wait_for_completion_timeout(&uhd->wait_for_process, 2*HZ); | |
24613191 | 13840 | + |
4e97e4e9 | 13841 | + if (uhd->pid == -1) { |
ad8f4a28 | 13842 | + printk(KERN_INFO "%s: Failed to contact userspace process.\n", |
4e97e4e9 | 13843 | + uhd->name); |
13844 | + toi_netlink_close_complete(uhd); | |
13845 | + return 1; | |
13846 | + } | |
24613191 | 13847 | + |
24613191 | 13848 | + return 0; |
13849 | +} | |
4e97e4e9 | 13850 | +EXPORT_SYMBOL_GPL(toi_netlink_setup); |
4e97e4e9 | 13851 | diff --git a/kernel/power/tuxonice_netlink.h b/kernel/power/tuxonice_netlink.h |
13852 | new file mode 100644 | |
1838f965 | 13853 | index 0000000..37e174b |
4e97e4e9 | 13854 | --- /dev/null |
13855 | +++ b/kernel/power/tuxonice_netlink.h | |
1838f965 | 13856 | @@ -0,0 +1,62 @@ |
4e97e4e9 | 13857 | +/* |
13858 | + * kernel/power/tuxonice_netlink.h | |
24613191 | 13859 | + * |
1838f965 | 13860 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 13861 | + * |
4e97e4e9 | 13862 | + * This file is released under the GPLv2. |
13863 | + * | |
13864 | + * Declarations for functions for communicating with a userspace helper | |
13865 | + * via netlink. | |
24613191 | 13866 | + */ |
13867 | + | |
4e97e4e9 | 13868 | +#include <linux/netlink.h> |
13869 | +#include <net/sock.h> | |
24613191 | 13870 | + |
4e97e4e9 | 13871 | +#define NETLINK_MSG_BASE 0x10 |
24613191 | 13872 | + |
4e97e4e9 | 13873 | +#define NETLINK_MSG_READY 0x10 |
13874 | +#define NETLINK_MSG_NOFREEZE_ME 0x16 | |
13875 | +#define NETLINK_MSG_GET_DEBUGGING 0x19 | |
13876 | +#define NETLINK_MSG_CLEANUP 0x24 | |
13877 | +#define NETLINK_MSG_NOFREEZE_ACK 0x27 | |
13878 | +#define NETLINK_MSG_IS_DEBUGGING 0x28 | |
24613191 | 13879 | + |
4e97e4e9 | 13880 | +struct user_helper_data { |
13881 | + int (*rcv_msg) (struct sk_buff *skb, struct nlmsghdr *nlh); | |
ad8f4a28 | 13882 | + void (*not_ready) (void); |
4e97e4e9 | 13883 | + struct sock *nl; |
13884 | + u32 sock_seq; | |
13885 | + pid_t pid; | |
13886 | + char *comm; | |
13887 | + char program[256]; | |
13888 | + int pool_level; | |
13889 | + int pool_limit; | |
13890 | + struct sk_buff *emerg_skbs; | |
13891 | + int skb_size; | |
ad8f4a28 | 13892 | + int netlink_id; |
4e97e4e9 | 13893 | + char *name; |
13894 | + struct user_helper_data *next; | |
13895 | + struct completion wait_for_process; | |
1838f965 | 13896 | + u32 interface_version; |
4e97e4e9 | 13897 | + int must_init; |
1838f965 | 13898 | + int debug; |
4e97e4e9 | 13899 | +}; |
24613191 | 13900 | + |
4e97e4e9 | 13901 | +#ifdef CONFIG_NET |
13902 | +int toi_netlink_setup(struct user_helper_data *uhd); | |
13903 | +void toi_netlink_close(struct user_helper_data *uhd); | |
13904 | +void toi_send_netlink_message(struct user_helper_data *uhd, | |
ad8f4a28 | 13905 | + int type, void *params, size_t len); |
f3e0dcc9 | 13906 | +void toi_netlink_close_complete(struct user_helper_data *uhd); |
4e97e4e9 | 13907 | +#else |
13908 | +static inline int toi_netlink_setup(struct user_helper_data *uhd) | |
13909 | +{ | |
24613191 | 13910 | + return 0; |
13911 | +} | |
13912 | + | |
4e97e4e9 | 13913 | +static inline void toi_netlink_close(struct user_helper_data *uhd) { }; |
13914 | +static inline void toi_send_netlink_message(struct user_helper_data *uhd, | |
ad8f4a28 | 13915 | + int type, void *params, size_t len) { }; |
f3e0dcc9 PS |
13916 | +static inline void toi_netlink_close_complete(struct user_helper_data *uhd) |
13917 | + { }; | |
4e97e4e9 | 13918 | +#endif |
13919 | diff --git a/kernel/power/tuxonice_pagedir.c b/kernel/power/tuxonice_pagedir.c | |
13920 | new file mode 100644 | |
1838f965 | 13921 | index 0000000..934bb27 |
4e97e4e9 | 13922 | --- /dev/null |
13923 | +++ b/kernel/power/tuxonice_pagedir.c | |
1838f965 | 13924 | @@ -0,0 +1,361 @@ |
4e97e4e9 | 13925 | +/* |
13926 | + * kernel/power/tuxonice_pagedir.c | |
13927 | + * | |
13928 | + * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu> | |
13929 | + * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz> | |
13930 | + * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr> | |
1838f965 | 13931 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 13932 | + * |
13933 | + * This file is released under the GPLv2. | |
13934 | + * | |
13935 | + * Routines for handling pagesets. | |
13936 | + * Note that pbes aren't actually stored as such. They're stored as | |
13937 | + * bitmaps and extents. | |
24613191 | 13938 | + */ |
24613191 | 13939 | + |
4e97e4e9 | 13940 | +#include <linux/suspend.h> |
13941 | +#include <linux/highmem.h> | |
13942 | +#include <linux/bootmem.h> | |
13943 | +#include <linux/hardirq.h> | |
13944 | +#include <linux/sched.h> | |
13945 | +#include <asm/tlbflush.h> | |
24613191 | 13946 | + |
4e97e4e9 | 13947 | +#include "tuxonice_pageflags.h" |
13948 | +#include "tuxonice_ui.h" | |
13949 | +#include "tuxonice_pagedir.h" | |
13950 | +#include "tuxonice_prepare_image.h" | |
13951 | +#include "tuxonice.h" | |
13952 | +#include "power.h" | |
13953 | +#include "tuxonice_builtin.h" | |
ad8f4a28 | 13954 | +#include "tuxonice_alloc.h" |
24613191 | 13955 | + |
4e97e4e9 | 13956 | +static int ptoi_pfn; |
ad8f4a28 AM |
13957 | +static struct pbe *this_low_pbe; |
13958 | +static struct pbe **last_low_pbe_ptr; | |
1838f965 | 13959 | +static struct memory_bitmap dup_map1, dup_map2; |
24613191 | 13960 | + |
4e97e4e9 | 13961 | +void toi_reset_alt_image_pageset2_pfn(void) |
24613191 | 13962 | +{ |
1838f965 | 13963 | + memory_bm_position_reset(&pageset2_map); |
24613191 | 13964 | +} |
13965 | + | |
4e97e4e9 | 13966 | +static struct page *first_conflicting_page; |
13967 | + | |
24613191 | 13968 | +/* |
4e97e4e9 | 13969 | + * free_conflicting_pages |
24613191 | 13970 | + */ |
24613191 | 13971 | + |
1838f965 | 13972 | +static void free_conflicting_pages(void) |
24613191 | 13973 | +{ |
4e97e4e9 | 13974 | + while (first_conflicting_page) { |
ad8f4a28 AM |
13975 | + struct page *next = |
13976 | + *((struct page **) kmap(first_conflicting_page)); | |
4e97e4e9 | 13977 | + kunmap(first_conflicting_page); |
ad8f4a28 | 13978 | + toi__free_page(29, first_conflicting_page); |
4e97e4e9 | 13979 | + first_conflicting_page = next; |
13980 | + } | |
13981 | +} | |
24613191 | 13982 | + |
4e97e4e9 | 13983 | +/* __toi_get_nonconflicting_page |
13984 | + * | |
13985 | + * Description: Gets order zero pages that won't be overwritten | |
13986 | + * while copying the original pages. | |
13987 | + */ | |
24613191 | 13988 | + |
ad8f4a28 | 13989 | +struct page *___toi_get_nonconflicting_page(int can_be_highmem) |
4e97e4e9 | 13990 | +{ |
13991 | + struct page *page; | |
1838f965 | 13992 | + gfp_t flags = TOI_ATOMIC_GFP; |
4e97e4e9 | 13993 | + if (can_be_highmem) |
13994 | + flags |= __GFP_HIGHMEM; | |
24613191 | 13995 | + |
24613191 | 13996 | + |
1838f965 | 13997 | + if (test_toi_state(TOI_LOADING_ALT_IMAGE) && |
13998 | + pageset2_map.zone_bm_list && | |
13999 | + (ptoi_pfn != BM_END_OF_MAP)) { | |
4e97e4e9 | 14000 | + do { |
1838f965 | 14001 | + ptoi_pfn = memory_bm_next_pfn(&pageset2_map); |
14002 | + if (ptoi_pfn != BM_END_OF_MAP) { | |
4e97e4e9 | 14003 | + page = pfn_to_page(ptoi_pfn); |
14004 | + if (!PagePageset1(page) && | |
14005 | + (can_be_highmem || !PageHighMem(page))) | |
14006 | + return page; | |
1838f965 | 14007 | + } |
14008 | + } while (ptoi_pfn != BM_END_OF_MAP); | |
24613191 | 14009 | + } |
14010 | + | |
4e97e4e9 | 14011 | + do { |
ad8f4a28 | 14012 | + page = toi_alloc_page(29, flags); |
4e97e4e9 | 14013 | + if (!page) { |
ad8f4a28 AM |
14014 | + printk(KERN_INFO "Failed to get nonconflicting " |
14015 | + "page.\n"); | |
1838f965 | 14016 | + return NULL; |
4e97e4e9 | 14017 | + } |
14018 | + if (PagePageset1(page)) { | |
14019 | + struct page **next = (struct page **) kmap(page); | |
14020 | + *next = first_conflicting_page; | |
14021 | + first_conflicting_page = page; | |
14022 | + kunmap(page); | |
14023 | + } | |
ad8f4a28 | 14024 | + } while (PagePageset1(page)); |
24613191 | 14025 | + |
4e97e4e9 | 14026 | + return page; |
24613191 | 14027 | +} |
14028 | + | |
4e97e4e9 | 14029 | +unsigned long __toi_get_nonconflicting_page(void) |
24613191 | 14030 | +{ |
4e97e4e9 | 14031 | + struct page *page = ___toi_get_nonconflicting_page(0); |
14032 | + return page ? (unsigned long) page_address(page) : 0; | |
24613191 | 14033 | +} |
14034 | + | |
1838f965 | 14035 | +static struct pbe *get_next_pbe(struct page **page_ptr, struct pbe *this_pbe, |
ad8f4a28 | 14036 | + int highmem) |
24613191 | 14037 | +{ |
ad8f4a28 | 14038 | + if (((((unsigned long) this_pbe) & (PAGE_SIZE - 1)) |
4e97e4e9 | 14039 | + + 2 * sizeof(struct pbe)) > PAGE_SIZE) { |
14040 | + struct page *new_page = | |
14041 | + ___toi_get_nonconflicting_page(highmem); | |
14042 | + if (!new_page) | |
14043 | + return ERR_PTR(-ENOMEM); | |
14044 | + this_pbe = (struct pbe *) kmap(new_page); | |
14045 | + memset(this_pbe, 0, PAGE_SIZE); | |
14046 | + *page_ptr = new_page; | |
14047 | + } else | |
14048 | + this_pbe++; | |
24613191 | 14049 | + |
4e97e4e9 | 14050 | + return this_pbe; |
24613191 | 14051 | +} |
14052 | + | |
4e97e4e9 | 14053 | +/* get_pageset1_load_addresses |
ad8f4a28 | 14054 | + * |
4e97e4e9 | 14055 | + * Description: We check here that pagedir & pages it points to won't collide |
14056 | + * with pages where we're going to restore from the loaded pages | |
14057 | + * later. | |
14058 | + * Returns: Zero on success, one if couldn't find enough pages (shouldn't | |
14059 | + * happen). | |
14060 | + */ | |
14061 | + | |
14062 | +int toi_get_pageset1_load_addresses(void) | |
73c609d5 | 14063 | +{ |
4e97e4e9 | 14064 | + int pfn, highallocd = 0, lowallocd = 0; |
14065 | + int low_needed = pagedir1.size - get_highmem_size(pagedir1); | |
14066 | + int high_needed = get_highmem_size(pagedir1); | |
14067 | + int low_pages_for_highmem = 0; | |
1838f965 | 14068 | + gfp_t flags = GFP_ATOMIC | __GFP_NOWARN | __GFP_HIGHMEM; |
4e97e4e9 | 14069 | + struct page *page, *high_pbe_page = NULL, *last_high_pbe_page = NULL, |
14070 | + *low_pbe_page; | |
ad8f4a28 AM |
14071 | + struct pbe **last_high_pbe_ptr = &restore_highmem_pblist, |
14072 | + *this_high_pbe = NULL; | |
1838f965 | 14073 | + int orig_low_pfn, orig_high_pfn; |
ad8f4a28 | 14074 | + int high_pbes_done = 0, low_pbes_done = 0; |
4e97e4e9 | 14075 | + int low_direct = 0, high_direct = 0; |
1838f965 | 14076 | + int high_to_free, low_to_free, result = 0; |
14077 | + | |
14078 | + /* | |
14079 | + * We need to duplicate pageset1's map because memory_bm_next_pfn's state | |
14080 | + * gets stomped on by the PagePageset1() test in setup_pbes. | |
14081 | + */ | |
14082 | + memory_bm_create(&dup_map1, GFP_KERNEL, 0); | |
14083 | + memory_bm_dup(&pageset1_map, &dup_map1); | |
14084 | + | |
14085 | + memory_bm_create(&dup_map2, GFP_KERNEL, 0); | |
14086 | + memory_bm_dup(&pageset1_map, &dup_map2); | |
14087 | + | |
14088 | + memory_bm_position_reset(&pageset1_map); | |
14089 | + memory_bm_position_reset(&dup_map1); | |
14090 | + memory_bm_position_reset(&dup_map2); | |
73c609d5 | 14091 | + |
ad8f4a28 AM |
14092 | + last_low_pbe_ptr = &restore_pblist; |
14093 | + | |
4e97e4e9 | 14094 | + /* First, allocate pages for the start of our pbe lists. */ |
14095 | + if (high_needed) { | |
14096 | + high_pbe_page = ___toi_get_nonconflicting_page(1); | |
1838f965 | 14097 | + if (!high_pbe_page) { |
14098 | + result = -ENOMEM; | |
14099 | + goto out; | |
14100 | + } | |
4e97e4e9 | 14101 | + this_high_pbe = (struct pbe *) kmap(high_pbe_page); |
14102 | + memset(this_high_pbe, 0, PAGE_SIZE); | |
14103 | + } | |
73c609d5 | 14104 | + |
4e97e4e9 | 14105 | + low_pbe_page = ___toi_get_nonconflicting_page(0); |
1838f965 | 14106 | + if (!low_pbe_page) { |
14107 | + result = -ENOMEM; | |
14108 | + goto out; | |
14109 | + } | |
4e97e4e9 | 14110 | + this_low_pbe = (struct pbe *) page_address(low_pbe_page); |
73c609d5 | 14111 | + |
ad8f4a28 | 14112 | + /* |
4e97e4e9 | 14113 | + * Next, allocate all possible memory to find where we can |
14114 | + * load data directly into destination pages. I'd like to do | |
14115 | + * this in bigger chunks, but then we can't free pages | |
14116 | + * individually later. | |
14117 | + */ | |
73c609d5 | 14118 | + |
4e97e4e9 | 14119 | + do { |
ad8f4a28 | 14120 | + page = toi_alloc_page(30, flags); |
4e97e4e9 | 14121 | + if (page) |
14122 | + SetPagePageset1Copy(page); | |
14123 | + } while (page); | |
73c609d5 | 14124 | + |
ad8f4a28 | 14125 | + /* |
4e97e4e9 | 14126 | + * Find out how many high- and lowmem pages we allocated above, |
14127 | + * and how many pages we can reload directly to their original | |
14128 | + * location. | |
14129 | + */ | |
1838f965 | 14130 | + BITMAP_FOR_EACH_SET(pageset1_copy_map, pfn) { |
4e97e4e9 | 14131 | + int is_high; |
14132 | + page = pfn_to_page(pfn); | |
14133 | + is_high = PageHighMem(page); | |
14134 | + | |
14135 | + if (PagePageset1(page)) { | |
14136 | + if (test_action_state(TOI_NO_DIRECT_LOAD)) { | |
14137 | + ClearPagePageset1Copy(page); | |
ad8f4a28 | 14138 | + toi__free_page(30, page); |
4e97e4e9 | 14139 | + continue; |
14140 | + } else { | |
14141 | + if (is_high) | |
14142 | + high_direct++; | |
14143 | + else | |
14144 | + low_direct++; | |
14145 | + } | |
14146 | + } else { | |
14147 | + if (is_high) | |
14148 | + highallocd++; | |
14149 | + else | |
14150 | + lowallocd++; | |
73c609d5 | 14151 | + } |
4e97e4e9 | 14152 | + } |
73c609d5 | 14153 | + |
ad8f4a28 AM |
14154 | + high_needed -= high_direct; |
14155 | + low_needed -= low_direct; | |
4e97e4e9 | 14156 | + |
14157 | + /* | |
14158 | + * Do we need to use some lowmem pages for the copies of highmem | |
14159 | + * pages? | |
14160 | + */ | |
14161 | + if (high_needed > highallocd) { | |
14162 | + low_pages_for_highmem = high_needed - highallocd; | |
14163 | + high_needed -= low_pages_for_highmem; | |
14164 | + low_needed += low_pages_for_highmem; | |
73c609d5 | 14165 | + } |
ad8f4a28 | 14166 | + |
4e97e4e9 | 14167 | + high_to_free = highallocd - high_needed; |
14168 | + low_to_free = lowallocd - low_needed; | |
73c609d5 | 14169 | + |
4e97e4e9 | 14170 | + /* |
1838f965 | 14171 | + * Now generate our pbes (which will be used for the atomic restore), |
4e97e4e9 | 14172 | + * and free unneeded pages. |
14173 | + */ | |
1838f965 | 14174 | + BITMAP_FOR_EACH_SET(pageset1_copy_map, pfn) { |
4e97e4e9 | 14175 | + int is_high; |
14176 | + page = pfn_to_page(pfn); | |
14177 | + is_high = PageHighMem(page); | |
24613191 | 14178 | + |
4e97e4e9 | 14179 | + if (PagePageset1(page)) |
14180 | + continue; | |
24613191 | 14181 | + |
4e97e4e9 | 14182 | + /* Free the page? */ |
14183 | + if ((is_high && high_to_free) || | |
14184 | + (!is_high && low_to_free)) { | |
14185 | + ClearPagePageset1Copy(page); | |
ad8f4a28 | 14186 | + toi__free_page(30, page); |
4e97e4e9 | 14187 | + if (is_high) |
14188 | + high_to_free--; | |
14189 | + else | |
14190 | + low_to_free--; | |
14191 | + continue; | |
14192 | + } | |
24613191 | 14193 | + |
4e97e4e9 | 14194 | + /* Nope. We're going to use this page. Add a pbe. */ |
14195 | + if (is_high || low_pages_for_highmem) { | |
14196 | + struct page *orig_page; | |
14197 | + high_pbes_done++; | |
14198 | + if (!is_high) | |
14199 | + low_pages_for_highmem--; | |
14200 | + do { | |
1838f965 | 14201 | + orig_high_pfn = memory_bm_next_pfn(&dup_map1); |
14202 | + BUG_ON(orig_high_pfn == BM_END_OF_MAP); | |
4e97e4e9 | 14203 | + orig_page = pfn_to_page(orig_high_pfn); |
ad8f4a28 AM |
14204 | + } while (!PageHighMem(orig_page) || |
14205 | + load_direct(orig_page)); | |
24613191 | 14206 | + |
4e97e4e9 | 14207 | + this_high_pbe->orig_address = orig_page; |
14208 | + this_high_pbe->address = page; | |
14209 | + this_high_pbe->next = NULL; | |
14210 | + if (last_high_pbe_page != high_pbe_page) { | |
ad8f4a28 AM |
14211 | + *last_high_pbe_ptr = |
14212 | + (struct pbe *) high_pbe_page; | |
4e97e4e9 | 14213 | + if (!last_high_pbe_page) |
14214 | + last_high_pbe_page = high_pbe_page; | |
14215 | + } else | |
14216 | + *last_high_pbe_ptr = this_high_pbe; | |
14217 | + last_high_pbe_ptr = &this_high_pbe->next; | |
14218 | + if (last_high_pbe_page != high_pbe_page) { | |
14219 | + kunmap(last_high_pbe_page); | |
14220 | + last_high_pbe_page = high_pbe_page; | |
14221 | + } | |
ad8f4a28 AM |
14222 | + this_high_pbe = get_next_pbe(&high_pbe_page, |
14223 | + this_high_pbe, 1); | |
4e97e4e9 | 14224 | + if (IS_ERR(this_high_pbe)) { |
ad8f4a28 AM |
14225 | + printk(KERN_INFO |
14226 | + "This high pbe is an error.\n"); | |
4e97e4e9 | 14227 | + return -ENOMEM; |
14228 | + } | |
14229 | + } else { | |
14230 | + struct page *orig_page; | |
14231 | + low_pbes_done++; | |
14232 | + do { | |
1838f965 | 14233 | + orig_low_pfn = memory_bm_next_pfn(&dup_map2); |
14234 | + BUG_ON(orig_low_pfn == BM_END_OF_MAP); | |
4e97e4e9 | 14235 | + orig_page = pfn_to_page(orig_low_pfn); |
ad8f4a28 AM |
14236 | + } while (PageHighMem(orig_page) || |
14237 | + load_direct(orig_page)); | |
24613191 | 14238 | + |
4e97e4e9 | 14239 | + this_low_pbe->orig_address = page_address(orig_page); |
14240 | + this_low_pbe->address = page_address(page); | |
14241 | + this_low_pbe->next = NULL; | |
14242 | + *last_low_pbe_ptr = this_low_pbe; | |
14243 | + last_low_pbe_ptr = &this_low_pbe->next; | |
ad8f4a28 AM |
14244 | + this_low_pbe = get_next_pbe(&low_pbe_page, |
14245 | + this_low_pbe, 0); | |
4e97e4e9 | 14246 | + if (IS_ERR(this_low_pbe)) { |
ad8f4a28 | 14247 | + printk(KERN_INFO "this_low_pbe is an error.\n"); |
4e97e4e9 | 14248 | + return -ENOMEM; |
14249 | + } | |
14250 | + } | |
14251 | + } | |
24613191 | 14252 | + |
4e97e4e9 | 14253 | + if (high_pbe_page) |
14254 | + kunmap(high_pbe_page); | |
24613191 | 14255 | + |
4e97e4e9 | 14256 | + if (last_high_pbe_page != high_pbe_page) { |
14257 | + if (last_high_pbe_page) | |
14258 | + kunmap(last_high_pbe_page); | |
ad8f4a28 | 14259 | + toi__free_page(29, high_pbe_page); |
24613191 | 14260 | + } |
14261 | + | |
4e97e4e9 | 14262 | + free_conflicting_pages(); |
24613191 | 14263 | + |
1838f965 | 14264 | +out: |
14265 | + memory_bm_free(&dup_map1, 0); | |
14266 | + memory_bm_free(&dup_map2, 0); | |
14267 | + return result; | |
24613191 | 14268 | +} |
ad8f4a28 AM |
14269 | + |
14270 | +int add_boot_kernel_data_pbe(void) | |
14271 | +{ | |
14272 | + this_low_pbe->address = (char *) __toi_get_nonconflicting_page(); | |
14273 | + if (!this_low_pbe->address) { | |
14274 | + printk(KERN_INFO "Failed to get bkd atomic restore buffer."); | |
14275 | + return -ENOMEM; | |
14276 | + } | |
14277 | + | |
14278 | + toi_bkd.size = sizeof(toi_bkd); | |
14279 | + memcpy(this_low_pbe->address, &toi_bkd, sizeof(toi_bkd)); | |
14280 | + | |
14281 | + *last_low_pbe_ptr = this_low_pbe; | |
14282 | + this_low_pbe->orig_address = (char *) boot_kernel_data_buffer; | |
14283 | + this_low_pbe->next = NULL; | |
14284 | + return 0; | |
14285 | +} | |
4e97e4e9 | 14286 | diff --git a/kernel/power/tuxonice_pagedir.h b/kernel/power/tuxonice_pagedir.h |
14287 | new file mode 100644 | |
1838f965 | 14288 | index 0000000..9d0d929 |
4e97e4e9 | 14289 | --- /dev/null |
14290 | +++ b/kernel/power/tuxonice_pagedir.h | |
ad8f4a28 | 14291 | @@ -0,0 +1,50 @@ |
4e97e4e9 | 14292 | +/* |
14293 | + * kernel/power/tuxonice_pagedir.h | |
14294 | + * | |
1838f965 | 14295 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 14296 | + * |
14297 | + * This file is released under the GPLv2. | |
14298 | + * | |
14299 | + * Declarations for routines for handling pagesets. | |
14300 | + */ | |
24613191 | 14301 | + |
4e97e4e9 | 14302 | +#ifndef KERNEL_POWER_PAGEDIR_H |
14303 | +#define KERNEL_POWER_PAGEDIR_H | |
24613191 | 14304 | + |
4e97e4e9 | 14305 | +/* Pagedir |
14306 | + * | |
14307 | + * Contains the metadata for a set of pages saved in the image. | |
14308 | + */ | |
24613191 | 14309 | + |
4e97e4e9 | 14310 | +struct pagedir { |
14311 | + int id; | |
7f9d2ee0 | 14312 | + long size; |
4e97e4e9 | 14313 | +#ifdef CONFIG_HIGHMEM |
7f9d2ee0 | 14314 | + long size_high; |
4e97e4e9 | 14315 | +#endif |
14316 | +}; | |
24613191 | 14317 | + |
4e97e4e9 | 14318 | +#ifdef CONFIG_HIGHMEM |
14319 | +#define get_highmem_size(pagedir) (pagedir.size_high) | |
ad8f4a28 AM |
14320 | +#define set_highmem_size(pagedir, sz) do { pagedir.size_high = sz; } while (0) |
14321 | +#define inc_highmem_size(pagedir) do { pagedir.size_high++; } while (0) | |
4e97e4e9 | 14322 | +#define get_lowmem_size(pagedir) (pagedir.size - pagedir.size_high) |
14323 | +#else | |
14324 | +#define get_highmem_size(pagedir) (0) | |
ad8f4a28 AM |
14325 | +#define set_highmem_size(pagedir, sz) do { } while (0) |
14326 | +#define inc_highmem_size(pagedir) do { } while (0) | |
4e97e4e9 | 14327 | +#define get_lowmem_size(pagedir) (pagedir.size) |
14328 | +#endif | |
24613191 | 14329 | + |
4e97e4e9 | 14330 | +extern struct pagedir pagedir1, pagedir2; |
24613191 | 14331 | + |
4e97e4e9 | 14332 | +extern void toi_copy_pageset1(void); |
24613191 | 14333 | + |
4e97e4e9 | 14334 | +extern int toi_get_pageset1_load_addresses(void); |
24613191 | 14335 | + |
4e97e4e9 | 14336 | +extern unsigned long __toi_get_nonconflicting_page(void); |
ad8f4a28 | 14337 | +struct page *___toi_get_nonconflicting_page(int can_be_highmem); |
24613191 | 14338 | + |
4e97e4e9 | 14339 | +extern void toi_reset_alt_image_pageset2_pfn(void); |
ad8f4a28 | 14340 | +extern int add_boot_kernel_data_pbe(void); |
4e97e4e9 | 14341 | +#endif |
14342 | diff --git a/kernel/power/tuxonice_pageflags.c b/kernel/power/tuxonice_pageflags.c | |
14343 | new file mode 100644 | |
1838f965 | 14344 | index 0000000..23e1873 |
4e97e4e9 | 14345 | --- /dev/null |
14346 | +++ b/kernel/power/tuxonice_pageflags.c | |
1838f965 | 14347 | @@ -0,0 +1,46 @@ |
4e97e4e9 | 14348 | +/* |
14349 | + * kernel/power/tuxonice_pageflags.c | |
14350 | + * | |
1838f965 | 14351 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
ad8f4a28 | 14352 | + * |
4e97e4e9 | 14353 | + * This file is released under the GPLv2. |
14354 | + * | |
14355 | + * Routines for serialising and relocating pageflags in which we | |
14356 | + * store our image metadata. | |
14357 | + */ | |
24613191 | 14358 | + |
4e97e4e9 | 14359 | +#include <linux/kernel.h> |
14360 | +#include <linux/mm.h> | |
14361 | +#include <linux/module.h> | |
14362 | +#include <linux/bitops.h> | |
14363 | +#include <linux/list.h> | |
14364 | +#include <linux/suspend.h> | |
14365 | +#include "tuxonice_pageflags.h" | |
14366 | +#include "tuxonice_modules.h" | |
14367 | +#include "tuxonice_pagedir.h" | |
14368 | +#include "tuxonice.h" | |
24613191 | 14369 | + |
1838f965 | 14370 | +struct memory_bitmap pageset2_map; |
14371 | +struct memory_bitmap page_resave_map; | |
14372 | +struct memory_bitmap io_map; | |
14373 | +struct memory_bitmap nosave_map; | |
14374 | +struct memory_bitmap free_map; | |
24613191 | 14375 | + |
4e97e4e9 | 14376 | +int toi_pageflags_space_needed(void) |
24613191 | 14377 | +{ |
4e97e4e9 | 14378 | + int total = 0; |
1838f965 | 14379 | + struct zone_bitmap *zone_bm; |
14380 | + struct bm_block *bb; | |
24613191 | 14381 | + |
1838f965 | 14382 | + total = sizeof(unsigned int); |
4e97e4e9 | 14383 | + |
1838f965 | 14384 | + for (zone_bm = pageset1_map.zone_bm_list; zone_bm; |
14385 | + zone_bm = zone_bm->next) { | |
14386 | + total += 2 * sizeof(unsigned long) + sizeof(unsigned int); | |
4e97e4e9 | 14387 | + |
1838f965 | 14388 | + for (bb = zone_bm->bm_blocks; bb; bb = bb->next) |
14389 | + total += PAGE_SIZE; | |
4e97e4e9 | 14390 | + } |
24613191 | 14391 | + |
1838f965 | 14392 | + return total; |
24613191 | 14393 | +} |
4e97e4e9 | 14394 | diff --git a/kernel/power/tuxonice_pageflags.h b/kernel/power/tuxonice_pageflags.h |
14395 | new file mode 100644 | |
1838f965 | 14396 | index 0000000..84142d2 |
4e97e4e9 | 14397 | --- /dev/null |
14398 | +++ b/kernel/power/tuxonice_pageflags.h | |
1838f965 | 14399 | @@ -0,0 +1,62 @@ |
24613191 | 14400 | +/* |
4e97e4e9 | 14401 | + * kernel/power/tuxonice_pageflags.h |
24613191 | 14402 | + * |
1838f965 | 14403 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 14404 | + * |
14405 | + * This file is released under the GPLv2. | |
24613191 | 14406 | + */ |
14407 | + | |
1838f965 | 14408 | +#ifndef KERNEL_POWER_TUXONICE_PAGEFLAGS_H |
14409 | +#define KERNEL_POWER_TUXONICE_PAGEFLAGS_H | |
14410 | + | |
14411 | +#include "power.h" | |
24613191 | 14412 | + |
1838f965 | 14413 | +extern struct memory_bitmap pageset1_map; |
14414 | +extern struct memory_bitmap pageset1_copy_map; | |
14415 | +extern struct memory_bitmap pageset2_map; | |
14416 | +extern struct memory_bitmap page_resave_map; | |
14417 | +extern struct memory_bitmap io_map; | |
14418 | +extern struct memory_bitmap nosave_map; | |
14419 | +extern struct memory_bitmap free_map; | |
24613191 | 14420 | + |
1838f965 | 14421 | +#define PagePageset1(page) (memory_bm_test_bit(&pageset1_map, page_to_pfn(page))) |
14422 | +#define SetPagePageset1(page) (memory_bm_set_bit(&pageset1_map, page_to_pfn(page))) | |
14423 | +#define ClearPagePageset1(page) (memory_bm_clear_bit(&pageset1_map, page_to_pfn(page))) | |
24613191 | 14424 | + |
1838f965 | 14425 | +#define PagePageset1Copy(page) (memory_bm_test_bit(&pageset1_copy_map, page_to_pfn(page))) |
14426 | +#define SetPagePageset1Copy(page) (memory_bm_set_bit(&pageset1_copy_map, page_to_pfn(page))) | |
ad8f4a28 | 14427 | +#define ClearPagePageset1Copy(page) \ |
1838f965 | 14428 | + (memory_bm_clear_bit(&pageset1_copy_map, page_to_pfn(page))) |
24613191 | 14429 | + |
1838f965 | 14430 | +#define PagePageset2(page) (memory_bm_test_bit(&pageset2_map, page_to_pfn(page))) |
14431 | +#define SetPagePageset2(page) (memory_bm_set_bit(&pageset2_map, page_to_pfn(page))) | |
14432 | +#define ClearPagePageset2(page) (memory_bm_clear_bit(&pageset2_map, page_to_pfn(page))) | |
24613191 | 14433 | + |
1838f965 | 14434 | +#define PageWasRW(page) (memory_bm_test_bit(&pageset2_map, page_to_pfn(page))) |
14435 | +#define SetPageWasRW(page) (memory_bm_set_bit(&pageset2_map, page_to_pfn(page))) | |
14436 | +#define ClearPageWasRW(page) (memory_bm_clear_bit(&pageset2_map, page_to_pfn(page))) | |
24613191 | 14437 | + |
1838f965 | 14438 | +#define PageResave(page) (page_resave_map.zone_bm_list ? \ |
14439 | + memory_bm_test_bit(&page_resave_map, page_to_pfn(page)) : 0) | |
14440 | +#define SetPageResave(page) (memory_bm_set_bit(&page_resave_map, page_to_pfn(page))) | |
14441 | +#define ClearPageResave(page) (memory_bm_clear_bit(&page_resave_map, page_to_pfn(page))) | |
4e97e4e9 | 14442 | + |
1838f965 | 14443 | +#define PageNosave(page) (nosave_map.zone_bm_list ? \ |
14444 | + memory_bm_test_bit(&nosave_map, page_to_pfn(page)) : 0) | |
14445 | +#define SetPageNosave(page) (memory_bm_set_bit(&nosave_map, page_to_pfn(page))) | |
14446 | +#define ClearPageNosave(page) (memory_bm_clear_bit(&nosave_map, page_to_pfn(page))) | |
24613191 | 14447 | + |
1838f965 | 14448 | +#define PageNosaveFree(page) (free_map.zone_bm_list ? \ |
14449 | + memory_bm_test_bit(&free_map, page_to_pfn(page)) : 0) | |
14450 | +#define SetPageNosaveFree(page) (memory_bm_set_bit(&free_map, page_to_pfn(page))) | |
14451 | +#define ClearPageNosaveFree(page) (memory_bm_clear_bit(&free_map, page_to_pfn(page))) | |
4e97e4e9 | 14452 | + |
1838f965 | 14453 | +extern void save_pageflags(struct memory_bitmap *pagemap); |
14454 | +extern int load_pageflags(struct memory_bitmap *pagemap); | |
4e97e4e9 | 14455 | +extern int toi_pageflags_space_needed(void); |
1838f965 | 14456 | + |
14457 | +#define BITMAP_FOR_EACH_SET(map, pfn) \ | |
14458 | + memory_bm_position_reset(&map); \ | |
14459 | + for (pfn = memory_bm_next_pfn(&map); pfn != BM_END_OF_MAP; \ | |
14460 | + pfn = memory_bm_next_pfn(&map)) | |
14461 | +#endif | |
4e97e4e9 | 14462 | diff --git a/kernel/power/tuxonice_power_off.c b/kernel/power/tuxonice_power_off.c |
14463 | new file mode 100644 | |
1838f965 | 14464 | index 0000000..d1d5f07 |
4e97e4e9 | 14465 | --- /dev/null |
14466 | +++ b/kernel/power/tuxonice_power_off.c | |
1838f965 | 14467 | @@ -0,0 +1,281 @@ |
24613191 | 14468 | +/* |
4e97e4e9 | 14469 | + * kernel/power/tuxonice_power_off.c |
14470 | + * | |
1838f965 | 14471 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 14472 | + * |
4e97e4e9 | 14473 | + * This file is released under the GPLv2. |
24613191 | 14474 | + * |
4e97e4e9 | 14475 | + * Support for powering down. |
24613191 | 14476 | + */ |
14477 | + | |
4e97e4e9 | 14478 | +#include <linux/device.h> |
14479 | +#include <linux/suspend.h> | |
14480 | +#include <linux/mm.h> | |
14481 | +#include <linux/pm.h> | |
14482 | +#include <linux/reboot.h> | |
14483 | +#include <linux/cpu.h> | |
14484 | +#include <linux/console.h> | |
14485 | +#include <linux/fs.h> | |
14486 | +#include "tuxonice.h" | |
14487 | +#include "tuxonice_ui.h" | |
14488 | +#include "tuxonice_power_off.h" | |
14489 | +#include "tuxonice_sysfs.h" | |
14490 | +#include "tuxonice_modules.h" | |
1838f965 | 14491 | +#include "tuxonice_io.h" |
4e97e4e9 | 14492 | + |
ad8f4a28 AM |
14493 | +unsigned long toi_poweroff_method; /* 0 - Kernel power off */ |
14494 | +EXPORT_SYMBOL_GPL(toi_poweroff_method); | |
14495 | + | |
1838f965 | 14496 | +static int wake_delay; |
4e97e4e9 | 14497 | +static char lid_state_file[256], wake_alarm_dir[256]; |
14498 | +static struct file *lid_file, *alarm_file, *epoch_file; | |
1838f965 | 14499 | +static int post_wake_state = -1; |
24613191 | 14500 | + |
7f9d2ee0 | 14501 | +static int did_suspend_to_both; |
14502 | + | |
24613191 | 14503 | +/* |
4e97e4e9 | 14504 | + * __toi_power_down |
14505 | + * Functionality : Powers down or reboots the computer once the image | |
14506 | + * has been written to disk. | |
14507 | + * Key Assumptions : Able to reboot/power down via code called or that | |
14508 | + * the warning emitted if the calls fail will be visible | |
14509 | + * to the user (ie printk resumes devices). | |
24613191 | 14510 | + */ |
14511 | + | |
4e97e4e9 | 14512 | +static void __toi_power_down(int method) |
24613191 | 14513 | +{ |
4e97e4e9 | 14514 | + int error; |
24613191 | 14515 | + |
1838f965 | 14516 | + toi_cond_pause(1, test_action_state(TOI_REBOOT) ? "Ready to reboot." : |
14517 | + "Powering down."); | |
14518 | + | |
14519 | + if (test_result_state(TOI_ABORTED)) | |
14520 | + goto out; | |
4e97e4e9 | 14521 | + |
1838f965 | 14522 | + if (test_action_state(TOI_REBOOT)) |
14523 | + kernel_restart(NULL); | |
4e97e4e9 | 14524 | + |
14525 | + switch (method) { | |
ad8f4a28 AM |
14526 | + case 0: |
14527 | + break; | |
14528 | + case 3: | |
1838f965 | 14529 | + /* |
14530 | + * Re-read the overwritten part of pageset2 to make post-resume | |
14531 | + * faster. | |
14532 | + */ | |
14533 | + if (read_pageset2(1)) | |
14534 | + panic("Attempt to reload pagedir 2 failed. Try rebooting."); | |
14535 | + | |
ad8f4a28 | 14536 | + error = pm_notifier_call_chain(PM_SUSPEND_PREPARE); |
fea155ea | 14537 | + if (!error) { |
ad8f4a28 | 14538 | + error = suspend_devices_and_enter(PM_SUSPEND_MEM); |
fea155ea PS |
14539 | + if (!error) |
14540 | + did_suspend_to_both = 1; | |
14541 | + } | |
ad8f4a28 | 14542 | + pm_notifier_call_chain(PM_POST_SUSPEND); |
fea155ea PS |
14543 | + |
14544 | + /* Success - we're now post-resume-from-ram */ | |
14545 | + if (did_suspend_to_both) | |
ad8f4a28 | 14546 | + return; |
fea155ea PS |
14547 | + |
14548 | + /* Failed to suspend to ram - do normal power off */ | |
ad8f4a28 AM |
14549 | + break; |
14550 | + case 4: | |
1838f965 | 14551 | + /* |
f3e0dcc9 PS |
14552 | + * If succeeds, doesn't return. If fails, do a simple |
14553 | + * powerdown. | |
14554 | + */ | |
14555 | + hibernation_platform_enter(); | |
ad8f4a28 AM |
14556 | + break; |
14557 | + case 5: | |
14558 | + /* Historic entry only now */ | |
14559 | + break; | |
4e97e4e9 | 14560 | + } |
14561 | + | |
14562 | + if (method && method != 5) | |
7f9d2ee0 | 14563 | + toi_cond_pause(1, |
14564 | + "Falling back to alternate power off method."); | |
ad8f4a28 AM |
14565 | + |
14566 | + if (test_result_state(TOI_ABORTED)) | |
1838f965 | 14567 | + goto out; |
ad8f4a28 | 14568 | + |
4e97e4e9 | 14569 | + kernel_power_off(); |
14570 | + kernel_halt(); | |
7f9d2ee0 | 14571 | + toi_cond_pause(1, "Powerdown failed."); |
4e97e4e9 | 14572 | + while (1) |
14573 | + cpu_relax(); | |
1838f965 | 14574 | + |
14575 | +out: | |
14576 | + if (read_pageset2(1)) | |
14577 | + panic("Attempt to reload pagedir 2 failed. Try rebooting."); | |
14578 | + return; | |
4e97e4e9 | 14579 | +} |
24613191 | 14580 | + |
4e97e4e9 | 14581 | +#define CLOSE_FILE(file) \ |
ad8f4a28 AM |
14582 | + if (file) { \ |
14583 | + filp_close(file, NULL); file = NULL; \ | |
14584 | + } | |
24613191 | 14585 | + |
7f9d2ee0 | 14586 | +static void powerdown_cleanup(int toi_or_resume) |
4e97e4e9 | 14587 | +{ |
14588 | + if (!toi_or_resume) | |
14589 | + return; | |
24613191 | 14590 | + |
4e97e4e9 | 14591 | + CLOSE_FILE(lid_file); |
14592 | + CLOSE_FILE(alarm_file); | |
14593 | + CLOSE_FILE(epoch_file); | |
24613191 | 14594 | +} |
14595 | + | |
4e97e4e9 | 14596 | +static void open_file(char *format, char *arg, struct file **var, int mode, |
14597 | + char *desc) | |
24613191 | 14598 | +{ |
4e97e4e9 | 14599 | + char buf[256]; |
14600 | + | |
14601 | + if (strlen(arg)) { | |
14602 | + sprintf(buf, format, arg); | |
14603 | + *var = filp_open(buf, mode, 0); | |
14604 | + if (IS_ERR(*var) || !*var) { | |
ad8f4a28 | 14605 | + printk(KERN_INFO "Failed to open %s file '%s' (%p).\n", |
4e97e4e9 | 14606 | + desc, buf, *var); |
1838f965 | 14607 | + *var = NULL; |
24613191 | 14608 | + } |
14609 | + } | |
24613191 | 14610 | +} |
14611 | + | |
7f9d2ee0 | 14612 | +static int powerdown_init(int toi_or_resume) |
24613191 | 14613 | +{ |
4e97e4e9 | 14614 | + if (!toi_or_resume) |
14615 | + return 0; | |
14616 | + | |
7f9d2ee0 | 14617 | + did_suspend_to_both = 0; |
14618 | + | |
ad8f4a28 AM |
14619 | + open_file("/proc/acpi/button/%s/state", lid_state_file, &lid_file, |
14620 | + O_RDONLY, "lid"); | |
4e97e4e9 | 14621 | + |
14622 | + if (strlen(wake_alarm_dir)) { | |
14623 | + open_file("/sys/class/rtc/%s/wakealarm", wake_alarm_dir, | |
14624 | + &alarm_file, O_WRONLY, "alarm"); | |
14625 | + | |
14626 | + open_file("/sys/class/rtc/%s/since_epoch", wake_alarm_dir, | |
14627 | + &epoch_file, O_RDONLY, "epoch"); | |
14628 | + } | |
14629 | + | |
14630 | + return 0; | |
24613191 | 14631 | +} |
14632 | + | |
4e97e4e9 | 14633 | +static int lid_closed(void) |
24613191 | 14634 | +{ |
4e97e4e9 | 14635 | + char array[25]; |
14636 | + ssize_t size; | |
14637 | + loff_t pos = 0; | |
14638 | + | |
14639 | + if (!lid_file) | |
14640 | + return 0; | |
14641 | + | |
14642 | + size = vfs_read(lid_file, (char __user *) array, 25, &pos); | |
14643 | + if ((int) size < 1) { | |
ad8f4a28 AM |
14644 | + printk(KERN_INFO "Failed to read lid state file (%d).\n", |
14645 | + (int) size); | |
4e97e4e9 | 14646 | + return 0; |
14647 | + } | |
14648 | + | |
14649 | + if (!strcmp(array, "state: closed\n")) | |
14650 | + return 1; | |
14651 | + | |
14652 | + return 0; | |
24613191 | 14653 | +} |
14654 | + | |
4e97e4e9 | 14655 | +static void write_alarm_file(int value) |
24613191 | 14656 | +{ |
4e97e4e9 | 14657 | + ssize_t size; |
14658 | + char buf[40]; | |
14659 | + loff_t pos = 0; | |
14660 | + | |
14661 | + if (!alarm_file) | |
14662 | + return; | |
14663 | + | |
14664 | + sprintf(buf, "%d\n", value); | |
14665 | + | |
14666 | + size = vfs_write(alarm_file, (char __user *)buf, strlen(buf), &pos); | |
14667 | + | |
14668 | + if (size < 0) | |
ad8f4a28 AM |
14669 | + printk(KERN_INFO "Error %d writing alarm value %s.\n", |
14670 | + (int) size, buf); | |
24613191 | 14671 | +} |
14672 | + | |
4e97e4e9 | 14673 | +/** |
14674 | + * toi_check_resleep: See whether to powerdown again after waking. | |
14675 | + * | |
14676 | + * After waking, check whether we should powerdown again in a (usually | |
14677 | + * different) way. We only do this if the lid switch is still closed. | |
14678 | + */ | |
14679 | +void toi_check_resleep(void) | |
24613191 | 14680 | +{ |
4e97e4e9 | 14681 | + /* We only return if we suspended to ram and woke. */ |
14682 | + if (lid_closed() && post_wake_state >= 0) | |
14683 | + __toi_power_down(post_wake_state); | |
24613191 | 14684 | +} |
14685 | + | |
4e97e4e9 | 14686 | +void toi_power_down(void) |
24613191 | 14687 | +{ |
4e97e4e9 | 14688 | + if (alarm_file && wake_delay) { |
14689 | + char array[25]; | |
14690 | + loff_t pos = 0; | |
ad8f4a28 AM |
14691 | + size_t size = vfs_read(epoch_file, (char __user *) array, 25, |
14692 | + &pos); | |
e8d0ad9d | 14693 | + |
4e97e4e9 | 14694 | + if (((int) size) < 1) |
ad8f4a28 AM |
14695 | + printk(KERN_INFO "Failed to read epoch file (%d).\n", |
14696 | + (int) size); | |
4e97e4e9 | 14697 | + else { |
ad8f4a28 AM |
14698 | + unsigned long since_epoch = |
14699 | + simple_strtol(array, NULL, 0); | |
24613191 | 14700 | + |
4e97e4e9 | 14701 | + /* Clear any wakeup time. */ |
14702 | + write_alarm_file(0); | |
14703 | + | |
14704 | + /* Set new wakeup time. */ | |
14705 | + write_alarm_file(since_epoch + wake_delay); | |
14706 | + } | |
e8d0ad9d | 14707 | + } |
4e97e4e9 | 14708 | + |
14709 | + __toi_power_down(toi_poweroff_method); | |
14710 | + | |
14711 | + toi_check_resleep(); | |
e8d0ad9d | 14712 | +} |
ad8f4a28 | 14713 | +EXPORT_SYMBOL_GPL(toi_power_down); |
24613191 | 14714 | + |
4e97e4e9 | 14715 | +static struct toi_sysfs_data sysfs_params[] = { |
14716 | +#if defined(CONFIG_ACPI) | |
1838f965 | 14717 | + SYSFS_STRING("lid_file", SYSFS_RW, lid_state_file, 256, 0, NULL), |
14718 | + SYSFS_INT("wake_delay", SYSFS_RW, &wake_delay, 0, INT_MAX, 0, NULL), | |
14719 | + SYSFS_STRING("wake_alarm_dir", SYSFS_RW, wake_alarm_dir, 256, 0, NULL), | |
14720 | + SYSFS_INT("post_wake_state", SYSFS_RW, &post_wake_state, -1, 5, 0, | |
14721 | + NULL), | |
14722 | + SYSFS_UL("powerdown_method", SYSFS_RW, &toi_poweroff_method, 0, 5, 0), | |
14723 | + SYSFS_INT("did_suspend_to_both", SYSFS_READONLY, &did_suspend_to_both, | |
14724 | + 0, 0, 0, NULL) | |
4e97e4e9 | 14725 | +#endif |
14726 | +}; | |
14727 | + | |
14728 | +static struct toi_module_ops powerdown_ops = { | |
14729 | + .type = MISC_HIDDEN_MODULE, | |
14730 | + .name = "poweroff", | |
7f9d2ee0 | 14731 | + .initialise = powerdown_init, |
14732 | + .cleanup = powerdown_cleanup, | |
4e97e4e9 | 14733 | + .directory = "[ROOT]", |
14734 | + .module = THIS_MODULE, | |
14735 | + .sysfs_data = sysfs_params, | |
ad8f4a28 AM |
14736 | + .num_sysfs_entries = sizeof(sysfs_params) / |
14737 | + sizeof(struct toi_sysfs_data), | |
e8d0ad9d | 14738 | +}; |
24613191 | 14739 | + |
4e97e4e9 | 14740 | +int toi_poweroff_init(void) |
e8d0ad9d | 14741 | +{ |
4e97e4e9 | 14742 | + return toi_register_module(&powerdown_ops); |
e8d0ad9d | 14743 | +} |
14744 | + | |
4e97e4e9 | 14745 | +void toi_poweroff_exit(void) |
e8d0ad9d | 14746 | +{ |
4e97e4e9 | 14747 | + toi_unregister_module(&powerdown_ops); |
e8d0ad9d | 14748 | +} |
4e97e4e9 | 14749 | diff --git a/kernel/power/tuxonice_power_off.h b/kernel/power/tuxonice_power_off.h |
14750 | new file mode 100644 | |
1838f965 | 14751 | index 0000000..a85633a |
4e97e4e9 | 14752 | --- /dev/null |
14753 | +++ b/kernel/power/tuxonice_power_off.h | |
1838f965 | 14754 | @@ -0,0 +1,24 @@ |
24613191 | 14755 | +/* |
4e97e4e9 | 14756 | + * kernel/power/tuxonice_power_off.h |
24613191 | 14757 | + * |
1838f965 | 14758 | + * Copyright (C) 2006-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 14759 | + * |
14760 | + * This file is released under the GPLv2. | |
14761 | + * | |
4e97e4e9 | 14762 | + * Support for the powering down. |
14763 | + */ | |
14764 | + | |
14765 | +int toi_pm_state_finish(void); | |
14766 | +void toi_power_down(void); | |
14767 | +extern unsigned long toi_poweroff_method; | |
4e97e4e9 | 14768 | +int toi_poweroff_init(void); |
14769 | +void toi_poweroff_exit(void); | |
14770 | +void toi_check_resleep(void); | |
ad8f4a28 | 14771 | + |
7f9d2ee0 | 14772 | +extern int platform_begin(int platform_mode); |
ad8f4a28 | 14773 | +extern int platform_pre_snapshot(int platform_mode); |
1838f965 | 14774 | +extern void platform_leave(int platform_mode); |
14775 | +extern void platform_end(int platform_mode); | |
14776 | +extern void platform_finish(int platform_mode); | |
ad8f4a28 | 14777 | +extern int platform_pre_restore(int platform_mode); |
1838f965 | 14778 | +extern void platform_restore_cleanup(int platform_mode); |
4e97e4e9 | 14779 | diff --git a/kernel/power/tuxonice_prepare_image.c b/kernel/power/tuxonice_prepare_image.c |
14780 | new file mode 100644 | |
1838f965 | 14781 | index 0000000..a49adde |
4e97e4e9 | 14782 | --- /dev/null |
14783 | +++ b/kernel/power/tuxonice_prepare_image.c | |
1838f965 | 14784 | @@ -0,0 +1,1041 @@ |
4e97e4e9 | 14785 | +/* |
14786 | + * kernel/power/tuxonice_prepare_image.c | |
14787 | + * | |
1838f965 | 14788 | + * Copyright (C) 2003-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 14789 | + * |
14790 | + * This file is released under the GPLv2. | |
14791 | + * | |
14792 | + * We need to eat memory until we can: | |
14793 | + * 1. Perform the save without changing anything (RAM_NEEDED < #pages) | |
14794 | + * 2. Fit it all in available space (toiActiveAllocator->available_space() >= | |
14795 | + * main_storage_needed()) | |
14796 | + * 3. Reload the pagedir and pageset1 to places that don't collide with their | |
14797 | + * final destinations, not knowing to what extent the resumed kernel will | |
14798 | + * overlap with the one loaded at boot time. I think the resumed kernel | |
ad8f4a28 | 14799 | + * should overlap completely, but I don't want to rely on this as it is |
4e97e4e9 | 14800 | + * an unproven assumption. We therefore assume there will be no overlap at |
14801 | + * all (worse case). | |
14802 | + * 4. Meet the user's requested limit (if any) on the size of the image. | |
14803 | + * The limit is in MB, so pages/256 (assuming 4K pages). | |
14804 | + * | |
24613191 | 14805 | + */ |
14806 | + | |
14807 | +#include <linux/module.h> | |
24613191 | 14808 | +#include <linux/highmem.h> |
4e97e4e9 | 14809 | +#include <linux/freezer.h> |
14810 | +#include <linux/hardirq.h> | |
14811 | +#include <linux/mmzone.h> | |
14812 | +#include <linux/console.h> | |
24613191 | 14813 | + |
4e97e4e9 | 14814 | +#include "tuxonice_pageflags.h" |
14815 | +#include "tuxonice_modules.h" | |
14816 | +#include "tuxonice_io.h" | |
14817 | +#include "tuxonice_ui.h" | |
14818 | +#include "tuxonice_extent.h" | |
14819 | +#include "tuxonice_prepare_image.h" | |
14820 | +#include "tuxonice_block_io.h" | |
14821 | +#include "tuxonice.h" | |
14822 | +#include "tuxonice_checksum.h" | |
14823 | +#include "tuxonice_sysfs.h" | |
ad8f4a28 | 14824 | +#include "tuxonice_alloc.h" |
24613191 | 14825 | + |
7f9d2ee0 | 14826 | +static long num_nosave, header_space_allocated, main_storage_allocated, |
ad8f4a28 | 14827 | + storage_available; |
f3e0dcc9 | 14828 | +long extra_pd1_pages_allowance = CONFIG_TOI_DEFAULT_EXTRA_PAGES_ALLOWANCE; |
ad8f4a28 | 14829 | +int image_size_limit; |
1838f965 | 14830 | +static int no_ps2_needed; |
24613191 | 14831 | + |
4e97e4e9 | 14832 | +struct attention_list { |
14833 | + struct task_struct *task; | |
14834 | + struct attention_list *next; | |
14835 | +}; | |
24613191 | 14836 | + |
ad8f4a28 | 14837 | +static struct attention_list *attention_list; |
24613191 | 14838 | + |
4e97e4e9 | 14839 | +#define PAGESET1 0 |
14840 | +#define PAGESET2 1 | |
24613191 | 14841 | + |
4e97e4e9 | 14842 | +void free_attention_list(void) |
14843 | +{ | |
14844 | + struct attention_list *last = NULL; | |
24613191 | 14845 | + |
4e97e4e9 | 14846 | + while (attention_list) { |
14847 | + last = attention_list; | |
14848 | + attention_list = attention_list->next; | |
ad8f4a28 | 14849 | + toi_kfree(6, last); |
4e97e4e9 | 14850 | + } |
14851 | +} | |
24613191 | 14852 | + |
4e97e4e9 | 14853 | +static int build_attention_list(void) |
24613191 | 14854 | +{ |
4e97e4e9 | 14855 | + int i, task_count = 0; |
14856 | + struct task_struct *p; | |
14857 | + struct attention_list *next; | |
24613191 | 14858 | + |
ad8f4a28 | 14859 | + /* |
4e97e4e9 | 14860 | + * Count all userspace process (with task->mm) marked PF_NOFREEZE. |
14861 | + */ | |
14862 | + read_lock(&tasklist_lock); | |
14863 | + for_each_process(p) | |
14864 | + if ((p->flags & PF_NOFREEZE) || p == current) | |
14865 | + task_count++; | |
14866 | + read_unlock(&tasklist_lock); | |
24613191 | 14867 | + |
ad8f4a28 | 14868 | + /* |
4e97e4e9 | 14869 | + * Allocate attention list structs. |
14870 | + */ | |
14871 | + for (i = 0; i < task_count; i++) { | |
14872 | + struct attention_list *this = | |
ad8f4a28 | 14873 | + toi_kzalloc(6, sizeof(struct attention_list), |
4e97e4e9 | 14874 | + TOI_WAIT_GFP); |
14875 | + if (!this) { | |
ad8f4a28 AM |
14876 | + printk(KERN_INFO "Failed to allocate slab for " |
14877 | + "attention list.\n"); | |
4e97e4e9 | 14878 | + free_attention_list(); |
14879 | + return 1; | |
24613191 | 14880 | + } |
4e97e4e9 | 14881 | + this->next = NULL; |
14882 | + if (attention_list) | |
14883 | + this->next = attention_list; | |
14884 | + attention_list = this; | |
14885 | + } | |
24613191 | 14886 | + |
4e97e4e9 | 14887 | + next = attention_list; |
14888 | + read_lock(&tasklist_lock); | |
14889 | + for_each_process(p) | |
14890 | + if ((p->flags & PF_NOFREEZE) || p == current) { | |
14891 | + next->task = p; | |
14892 | + next = next->next; | |
14893 | + } | |
14894 | + read_unlock(&tasklist_lock); | |
14895 | + return 0; | |
14896 | +} | |
24613191 | 14897 | + |
4e97e4e9 | 14898 | +static void pageset2_full(void) |
14899 | +{ | |
14900 | + struct zone *zone; | |
14901 | + unsigned long flags; | |
14902 | + | |
14903 | + for_each_zone(zone) { | |
14904 | + spin_lock_irqsave(&zone->lru_lock, flags); | |
14905 | + if (zone_page_state(zone, NR_INACTIVE)) { | |
14906 | + struct page *page; | |
14907 | + list_for_each_entry(page, &zone->inactive_list, lru) | |
14908 | + SetPagePageset2(page); | |
14909 | + } | |
14910 | + if (zone_page_state(zone, NR_ACTIVE)) { | |
14911 | + struct page *page; | |
14912 | + list_for_each_entry(page, &zone->active_list, lru) | |
14913 | + SetPagePageset2(page); | |
14914 | + } | |
14915 | + spin_unlock_irqrestore(&zone->lru_lock, flags); | |
24613191 | 14916 | + } |
14917 | +} | |
14918 | + | |
4e97e4e9 | 14919 | +/* |
14920 | + * toi_mark_task_as_pageset | |
14921 | + * Functionality : Marks all the saveable pages belonging to a given process | |
14922 | + * as belonging to a particular pageset. | |
24613191 | 14923 | + */ |
4e97e4e9 | 14924 | + |
14925 | +static void toi_mark_task_as_pageset(struct task_struct *t, int pageset2) | |
24613191 | 14926 | +{ |
4e97e4e9 | 14927 | + struct vm_area_struct *vma; |
14928 | + struct mm_struct *mm; | |
24613191 | 14929 | + |
4e97e4e9 | 14930 | + mm = t->active_mm; |
24613191 | 14931 | + |
ad8f4a28 AM |
14932 | + if (!mm || !mm->mmap) |
14933 | + return; | |
24613191 | 14934 | + |
4e97e4e9 | 14935 | + if (!irqs_disabled()) |
14936 | + down_read(&mm->mmap_sem); | |
ad8f4a28 | 14937 | + |
4e97e4e9 | 14938 | + for (vma = mm->mmap; vma; vma = vma->vm_next) { |
14939 | + unsigned long posn; | |
14940 | + | |
14941 | + if (vma->vm_flags & (VM_PFNMAP | VM_IO | VM_RESERVED) || | |
14942 | + !vma->vm_start) | |
14943 | + continue; | |
14944 | + | |
14945 | + for (posn = vma->vm_start; posn < vma->vm_end; | |
14946 | + posn += PAGE_SIZE) { | |
14947 | + struct page *page = follow_page(vma, posn, 0); | |
14948 | + if (!page) | |
14949 | + continue; | |
14950 | + | |
14951 | + if (pageset2) | |
14952 | + SetPagePageset2(page); | |
14953 | + else { | |
14954 | + ClearPagePageset2(page); | |
14955 | + SetPagePageset1(page); | |
14956 | + } | |
24613191 | 14957 | + } |
14958 | + } | |
14959 | + | |
4e97e4e9 | 14960 | + if (!irqs_disabled()) |
14961 | + up_read(&mm->mmap_sem); | |
24613191 | 14962 | +} |
14963 | + | |
4e97e4e9 | 14964 | +/* mark_pages_for_pageset2 |
14965 | + * | |
14966 | + * Description: Mark unshared pages in processes not needed for hibernate as | |
14967 | + * being able to be written out in a separate pagedir. | |
14968 | + * HighMem pages are simply marked as pageset2. They won't be | |
14969 | + * needed during hibernate. | |
24613191 | 14970 | + */ |
14971 | + | |
4e97e4e9 | 14972 | +static void toi_mark_pages_for_pageset2(void) |
24613191 | 14973 | +{ |
4e97e4e9 | 14974 | + struct task_struct *p; |
14975 | + struct attention_list *this = attention_list; | |
73c609d5 | 14976 | + |
1838f965 | 14977 | + memory_bm_clear(&pageset2_map); |
24613191 | 14978 | + |
1838f965 | 14979 | + if (test_action_state(TOI_NO_PAGESET2) || no_ps2_needed) |
14980 | + return; | |
ad8f4a28 | 14981 | + |
4e97e4e9 | 14982 | + if (test_action_state(TOI_PAGESET2_FULL)) |
14983 | + pageset2_full(); | |
14984 | + else { | |
14985 | + read_lock(&tasklist_lock); | |
14986 | + for_each_process(p) { | |
fea155ea | 14987 | + if (!p->mm || (p->flags & PF_KTHREAD)) |
4e97e4e9 | 14988 | + continue; |
24613191 | 14989 | + |
4e97e4e9 | 14990 | + toi_mark_task_as_pageset(p, PAGESET2); |
14991 | + } | |
14992 | + read_unlock(&tasklist_lock); | |
24613191 | 14993 | + } |
14994 | + | |
ad8f4a28 | 14995 | + /* |
4e97e4e9 | 14996 | + * Because the tasks in attention_list are ones related to hibernating, |
14997 | + * we know that they won't go away under us. | |
14998 | + */ | |
24613191 | 14999 | + |
4e97e4e9 | 15000 | + while (this) { |
15001 | + if (!test_result_state(TOI_ABORTED)) | |
15002 | + toi_mark_task_as_pageset(this->task, PAGESET1); | |
15003 | + this = this->next; | |
15004 | + } | |
24613191 | 15005 | +} |
15006 | + | |
15007 | +/* | |
4e97e4e9 | 15008 | + * The atomic copy of pageset1 is stored in pageset2 pages. |
15009 | + * But if pageset1 is larger (normally only just after boot), | |
15010 | + * we need to allocate extra pages to store the atomic copy. | |
15011 | + * The following data struct and functions are used to handle | |
15012 | + * the allocation and freeing of that memory. | |
24613191 | 15013 | + */ |
15014 | + | |
7f9d2ee0 | 15015 | +static long extra_pages_allocated; |
24613191 | 15016 | + |
4e97e4e9 | 15017 | +struct extras { |
15018 | + struct page *page; | |
15019 | + int order; | |
15020 | + struct extras *next; | |
15021 | +}; | |
24613191 | 15022 | + |
4e97e4e9 | 15023 | +static struct extras *extras_list; |
15024 | + | |
15025 | +/* toi_free_extra_pagedir_memory | |
24613191 | 15026 | + * |
4e97e4e9 | 15027 | + * Description: Free previously allocated extra pagedir memory. |
24613191 | 15028 | + */ |
4e97e4e9 | 15029 | +void toi_free_extra_pagedir_memory(void) |
24613191 | 15030 | +{ |
4e97e4e9 | 15031 | + /* Free allocated pages */ |
15032 | + while (extras_list) { | |
15033 | + struct extras *this = extras_list; | |
15034 | + int i; | |
24613191 | 15035 | + |
4e97e4e9 | 15036 | + extras_list = this->next; |
24613191 | 15037 | + |
4e97e4e9 | 15038 | + for (i = 0; i < (1 << this->order); i++) |
15039 | + ClearPageNosave(this->page + i); | |
24613191 | 15040 | + |
ad8f4a28 AM |
15041 | + toi_free_pages(9, this->page, this->order); |
15042 | + toi_kfree(7, this); | |
24613191 | 15043 | + } |
24613191 | 15044 | + |
4e97e4e9 | 15045 | + extra_pages_allocated = 0; |
24613191 | 15046 | +} |
15047 | + | |
4e97e4e9 | 15048 | +/* toi_allocate_extra_pagedir_memory |
24613191 | 15049 | + * |
4e97e4e9 | 15050 | + * Description: Allocate memory for making the atomic copy of pagedir1 in the |
15051 | + * case where it is bigger than pagedir2. | |
15052 | + * Arguments: int num_to_alloc: Number of extra pages needed. | |
15053 | + * Result: int. Number of extra pages we now have allocated. | |
24613191 | 15054 | + */ |
4e97e4e9 | 15055 | +static int toi_allocate_extra_pagedir_memory(int extra_pages_needed) |
24613191 | 15056 | +{ |
4e97e4e9 | 15057 | + int j, order, num_to_alloc = extra_pages_needed - extra_pages_allocated; |
1838f965 | 15058 | + gfp_t flags = TOI_ATOMIC_GFP; |
24613191 | 15059 | + |
4e97e4e9 | 15060 | + if (num_to_alloc < 1) |
15061 | + return 0; | |
24613191 | 15062 | + |
4e97e4e9 | 15063 | + order = fls(num_to_alloc); |
15064 | + if (order >= MAX_ORDER) | |
15065 | + order = MAX_ORDER - 1; | |
24613191 | 15066 | + |
4e97e4e9 | 15067 | + while (num_to_alloc) { |
15068 | + struct page *newpage; | |
15069 | + unsigned long virt; | |
15070 | + struct extras *extras_entry; | |
ad8f4a28 | 15071 | + |
4e97e4e9 | 15072 | + while ((1 << order) > num_to_alloc) |
15073 | + order--; | |
24613191 | 15074 | + |
ad8f4a28 | 15075 | + extras_entry = (struct extras *) toi_kzalloc(7, |
4e97e4e9 | 15076 | + sizeof(struct extras), TOI_ATOMIC_GFP); |
24613191 | 15077 | + |
4e97e4e9 | 15078 | + if (!extras_entry) |
15079 | + return extra_pages_allocated; | |
24613191 | 15080 | + |
4e97e4e9 | 15081 | + virt = toi_get_free_pages(9, flags, order); |
15082 | + while (!virt && order) { | |
15083 | + order--; | |
15084 | + virt = toi_get_free_pages(9, flags, order); | |
15085 | + } | |
24613191 | 15086 | + |
4e97e4e9 | 15087 | + if (!virt) { |
ad8f4a28 | 15088 | + toi_kfree(7, extras_entry); |
4e97e4e9 | 15089 | + return extra_pages_allocated; |
15090 | + } | |
24613191 | 15091 | + |
4e97e4e9 | 15092 | + newpage = virt_to_page(virt); |
24613191 | 15093 | + |
4e97e4e9 | 15094 | + extras_entry->page = newpage; |
15095 | + extras_entry->order = order; | |
15096 | + extras_entry->next = NULL; | |
24613191 | 15097 | + |
4e97e4e9 | 15098 | + if (extras_list) |
15099 | + extras_entry->next = extras_list; | |
24613191 | 15100 | + |
4e97e4e9 | 15101 | + extras_list = extras_entry; |
24613191 | 15102 | + |
4e97e4e9 | 15103 | + for (j = 0; j < (1 << order); j++) { |
15104 | + SetPageNosave(newpage + j); | |
15105 | + SetPagePageset1Copy(newpage + j); | |
15106 | + } | |
24613191 | 15107 | + |
4e97e4e9 | 15108 | + extra_pages_allocated += (1 << order); |
15109 | + num_to_alloc -= (1 << order); | |
15110 | + } | |
15111 | + | |
15112 | + return extra_pages_allocated; | |
24613191 | 15113 | +} |
15114 | + | |
4e97e4e9 | 15115 | +/* |
15116 | + * real_nr_free_pages: Count pcp pages for a zone type or all zones | |
15117 | + * (-1 for all, otherwise zone_idx() result desired). | |
24613191 | 15118 | + */ |
7f9d2ee0 | 15119 | +long real_nr_free_pages(unsigned long zone_idx_mask) |
4e97e4e9 | 15120 | +{ |
15121 | + struct zone *zone; | |
7f9d2ee0 | 15122 | + int result = 0, cpu; |
24613191 | 15123 | + |
4e97e4e9 | 15124 | + /* PCP lists */ |
15125 | + for_each_zone(zone) { | |
15126 | + if (!populated_zone(zone)) | |
15127 | + continue; | |
ad8f4a28 | 15128 | + |
4e97e4e9 | 15129 | + if (!(zone_idx_mask & (1 << zone_idx(zone)))) |
15130 | + continue; | |
24613191 | 15131 | + |
4e97e4e9 | 15132 | + for_each_online_cpu(cpu) { |
15133 | + struct per_cpu_pageset *pset = zone_pcp(zone, cpu); | |
7f9d2ee0 | 15134 | + struct per_cpu_pages *pcp = &pset->pcp; |
15135 | + result += pcp->count; | |
4e97e4e9 | 15136 | + } |
15137 | + | |
15138 | + result += zone_page_state(zone, NR_FREE_PAGES); | |
24613191 | 15139 | + } |
4e97e4e9 | 15140 | + return result; |
15141 | +} | |
1838f965 | 15142 | +EXPORT_SYMBOL_GPL(real_nr_free_pages); |
24613191 | 15143 | + |
15144 | +/* | |
4e97e4e9 | 15145 | + * Discover how much extra memory will be required by the drivers |
15146 | + * when they're asked to hibernate. We can then ensure that amount | |
15147 | + * of memory is available when we really want it. | |
24613191 | 15148 | + */ |
4e97e4e9 | 15149 | +static void get_extra_pd1_allowance(void) |
15150 | +{ | |
7f9d2ee0 | 15151 | + long orig_num_free = real_nr_free_pages(all_zones_mask), final; |
ad8f4a28 | 15152 | + |
4e97e4e9 | 15153 | + toi_prepare_status(CLEAR_BAR, "Finding allowance for drivers."); |
24613191 | 15154 | + |
4e97e4e9 | 15155 | + suspend_console(); |
15156 | + device_suspend(PMSG_FREEZE); | |
fea155ea | 15157 | + device_pm_lock(); |
4e97e4e9 | 15158 | + local_irq_disable(); /* irqs might have been re-enabled on us */ |
15159 | + device_power_down(PMSG_FREEZE); | |
ad8f4a28 | 15160 | + |
4e97e4e9 | 15161 | + final = real_nr_free_pages(all_zones_mask); |
24613191 | 15162 | + |
fea155ea | 15163 | + device_power_up(PMSG_THAW); |
4e97e4e9 | 15164 | + local_irq_enable(); |
fea155ea PS |
15165 | + device_pm_unlock(); |
15166 | + device_resume(PMSG_THAW); | |
4e97e4e9 | 15167 | + resume_console(); |
24613191 | 15168 | + |
4e97e4e9 | 15169 | + extra_pd1_pages_allowance = max( |
f3e0dcc9 PS |
15170 | + orig_num_free - final + MIN_EXTRA_PAGES_ALLOWANCE, |
15171 | + (long) MIN_EXTRA_PAGES_ALLOWANCE); | |
4e97e4e9 | 15172 | +} |
24613191 | 15173 | + |
4e97e4e9 | 15174 | +/* |
15175 | + * Amount of storage needed, possibly taking into account the | |
15176 | + * expected compression ratio and possibly also ignoring our | |
15177 | + * allowance for extra pages. | |
15178 | + */ | |
7f9d2ee0 | 15179 | +static long main_storage_needed(int use_ecr, |
4e97e4e9 | 15180 | + int ignore_extra_pd1_allow) |
24613191 | 15181 | +{ |
f3e0dcc9 | 15182 | + return (pagedir1.size + pagedir2.size + |
4e97e4e9 | 15183 | + (ignore_extra_pd1_allow ? 0 : extra_pd1_pages_allowance)) * |
f3e0dcc9 | 15184 | + (use_ecr ? toi_expected_compression_ratio() : 100) / 100; |
24613191 | 15185 | +} |
15186 | + | |
4e97e4e9 | 15187 | +/* |
15188 | + * Storage needed for the image header, in bytes until the return. | |
15189 | + */ | |
7f9d2ee0 | 15190 | +static long header_storage_needed(void) |
24613191 | 15191 | +{ |
7f9d2ee0 | 15192 | + long bytes = (int) sizeof(struct toi_header) + |
4e97e4e9 | 15193 | + toi_header_storage_for_modules() + |
15194 | + toi_pageflags_space_needed(); | |
15195 | + | |
15196 | + return DIV_ROUND_UP(bytes, PAGE_SIZE); | |
24613191 | 15197 | +} |
15198 | + | |
24613191 | 15199 | +/* |
4e97e4e9 | 15200 | + * When freeing memory, pages from either pageset might be freed. |
24613191 | 15201 | + * |
ad8f4a28 AM |
15202 | + * When seeking to free memory to be able to hibernate, for every ps1 page |
15203 | + * freed, we need 2 less pages for the atomic copy because there is one less | |
15204 | + * page to copy and one more page into which data can be copied. | |
24613191 | 15205 | + * |
4e97e4e9 | 15206 | + * Freeing ps2 pages saves us nothing directly. No more memory is available |
15207 | + * for the atomic copy. Indirectly, a ps1 page might be freed (slab?), but | |
15208 | + * that's too much work to figure out. | |
24613191 | 15209 | + * |
4e97e4e9 | 15210 | + * => ps1_to_free functions |
24613191 | 15211 | + * |
4e97e4e9 | 15212 | + * Of course if we just want to reduce the image size, because of storage |
15213 | + * limitations or an image size limit either ps will do. | |
24613191 | 15214 | + * |
4e97e4e9 | 15215 | + * => any_to_free function |
24613191 | 15216 | + */ |
15217 | + | |
7f9d2ee0 | 15218 | +static long highpages_ps1_to_free(void) |
24613191 | 15219 | +{ |
7f9d2ee0 | 15220 | + return max_t(long, 0, DIV_ROUND_UP(get_highmem_size(pagedir1) - |
4e97e4e9 | 15221 | + get_highmem_size(pagedir2), 2) - real_nr_free_high_pages()); |
24613191 | 15222 | +} |
15223 | + | |
7f9d2ee0 | 15224 | +static long lowpages_ps1_to_free(void) |
24613191 | 15225 | +{ |
7f9d2ee0 | 15226 | + return max_t(long, 0, DIV_ROUND_UP(get_lowmem_size(pagedir1) + |
4e97e4e9 | 15227 | + extra_pd1_pages_allowance + MIN_FREE_RAM + |
ad8f4a28 | 15228 | + toi_memory_for_modules(0) - get_lowmem_size(pagedir2) - |
4e97e4e9 | 15229 | + real_nr_free_low_pages() - extra_pages_allocated, 2)); |
24613191 | 15230 | +} |
15231 | + | |
7f9d2ee0 | 15232 | +static long current_image_size(void) |
24613191 | 15233 | +{ |
4e97e4e9 | 15234 | + return pagedir1.size + pagedir2.size + header_space_allocated; |
15235 | +} | |
24613191 | 15236 | + |
7f9d2ee0 | 15237 | +static long storage_still_required(void) |
ad8f4a28 | 15238 | +{ |
7f9d2ee0 | 15239 | + return max_t(long, 0, main_storage_needed(1, 1) - storage_available); |
ad8f4a28 AM |
15240 | +} |
15241 | + | |
7f9d2ee0 | 15242 | +static long ram_still_required(void) |
ad8f4a28 | 15243 | +{ |
7f9d2ee0 | 15244 | + return max_t(long, 0, MIN_FREE_RAM + toi_memory_for_modules(0) - |
ad8f4a28 AM |
15245 | + real_nr_free_low_pages() + 2 * extra_pd1_pages_allowance); |
15246 | +} | |
15247 | + | |
7f9d2ee0 | 15248 | +static long any_to_free(int use_image_size_limit) |
4e97e4e9 | 15249 | +{ |
7f9d2ee0 | 15250 | + long user_limit = (use_image_size_limit && image_size_limit > 0) ? |
1838f965 | 15251 | + max_t(long, 0, current_image_size() - |
15252 | + (image_size_limit << 8)) : 0, | |
15253 | + storage_limit = storage_still_required(), | |
15254 | + ram_limit = ram_still_required(), | |
15255 | + first_max = max(user_limit, storage_limit); | |
24613191 | 15256 | + |
1838f965 | 15257 | + return max(first_max, ram_limit); |
15258 | +} | |
24613191 | 15259 | + |
1838f965 | 15260 | +static int need_pageset2(void) |
15261 | +{ | |
15262 | + return (real_nr_free_low_pages() + extra_pages_allocated - | |
15263 | + 2 * extra_pd1_pages_allowance - MIN_FREE_RAM - | |
15264 | + toi_memory_for_modules(0) - pagedir1.size) < pagedir2.size; | |
24613191 | 15265 | +} |
15266 | + | |
4e97e4e9 | 15267 | +/* amount_needed |
15268 | + * | |
15269 | + * Calculates the amount by which the image size needs to be reduced to meet | |
15270 | + * our constraints. | |
15271 | + */ | |
7f9d2ee0 | 15272 | +static long amount_needed(int use_image_size_limit) |
24613191 | 15273 | +{ |
4e97e4e9 | 15274 | + return max(highpages_ps1_to_free() + lowpages_ps1_to_free(), |
15275 | + any_to_free(use_image_size_limit)); | |
15276 | +} | |
24613191 | 15277 | + |
7f9d2ee0 | 15278 | +static long image_not_ready(int use_image_size_limit) |
4e97e4e9 | 15279 | +{ |
15280 | + toi_message(TOI_EAT_MEMORY, TOI_LOW, 1, | |
7f9d2ee0 | 15281 | + "Amount still needed (%ld) > 0:%d. Header: %ld < %ld: %d," |
15282 | + " Storage allocd: %ld < %ld: %d.\n", | |
4e97e4e9 | 15283 | + amount_needed(use_image_size_limit), |
15284 | + (amount_needed(use_image_size_limit) > 0), | |
15285 | + header_space_allocated, header_storage_needed(), | |
15286 | + header_space_allocated < header_storage_needed(), | |
ad8f4a28 | 15287 | + main_storage_allocated, |
4e97e4e9 | 15288 | + main_storage_needed(1, 1), |
15289 | + main_storage_allocated < main_storage_needed(1, 1)); | |
24613191 | 15290 | + |
4e97e4e9 | 15291 | + toi_cond_pause(0, NULL); |
24613191 | 15292 | + |
f3e0dcc9 | 15293 | + return (amount_needed(use_image_size_limit) > 0) || |
4e97e4e9 | 15294 | + header_space_allocated < header_storage_needed() || |
f3e0dcc9 | 15295 | + main_storage_allocated < main_storage_needed(1, 1); |
24613191 | 15296 | +} |
15297 | + | |
ad8f4a28 AM |
15298 | +static void display_failure_reason(int tries_exceeded) |
15299 | +{ | |
7f9d2ee0 | 15300 | + long storage_required = storage_still_required(), |
ad8f4a28 AM |
15301 | + ram_required = ram_still_required(), |
15302 | + high_ps1 = highpages_ps1_to_free(), | |
15303 | + low_ps1 = lowpages_ps1_to_free(); | |
15304 | + | |
15305 | + printk(KERN_INFO "Failed to prepare the image because...\n"); | |
15306 | + | |
15307 | + if (!storage_available) { | |
15308 | + printk(KERN_INFO "- You need some storage available to be " | |
15309 | + "able to hibernate.\n"); | |
15310 | + return; | |
15311 | + } | |
15312 | + | |
15313 | + if (tries_exceeded) | |
15314 | + printk(KERN_INFO "- The maximum number of iterations was " | |
15315 | + "reached without successfully preparing the " | |
15316 | + "image.\n"); | |
15317 | + | |
15318 | + if (header_space_allocated < header_storage_needed()) { | |
15319 | + printk(KERN_INFO "- Insufficient header storage allocated. " | |
f3e0dcc9 PS |
15320 | + "Need %ld, have %ld.\n", |
15321 | + header_storage_needed(), | |
ad8f4a28 AM |
15322 | + header_space_allocated); |
15323 | + set_abort_result(TOI_INSUFFICIENT_STORAGE); | |
15324 | + } | |
15325 | + | |
15326 | + if (storage_required) { | |
7f9d2ee0 | 15327 | + printk(KERN_INFO " - We need at least %ld pages of storage " |
15328 | + "(ignoring the header), but only have %ld.\n", | |
ad8f4a28 AM |
15329 | + main_storage_needed(1, 1), |
15330 | + main_storage_allocated); | |
15331 | + set_abort_result(TOI_INSUFFICIENT_STORAGE); | |
15332 | + } | |
15333 | + | |
15334 | + if (ram_required) { | |
7f9d2ee0 | 15335 | + printk(KERN_INFO " - We need %ld more free pages of low " |
ad8f4a28 AM |
15336 | + "memory.\n", ram_required); |
15337 | + printk(KERN_INFO " Minimum free : %8d\n", MIN_FREE_RAM); | |
7f9d2ee0 | 15338 | + printk(KERN_INFO " + Reqd. by modules : %8ld\n", |
ad8f4a28 | 15339 | + toi_memory_for_modules(0)); |
7f9d2ee0 | 15340 | + printk(KERN_INFO " - Currently free : %8ld\n", |
ad8f4a28 | 15341 | + real_nr_free_low_pages()); |
7f9d2ee0 | 15342 | + printk(KERN_INFO " + 2 * extra allow : %8ld\n", |
ad8f4a28 AM |
15343 | + 2 * extra_pd1_pages_allowance); |
15344 | + printk(KERN_INFO " : ========\n"); | |
f3e0dcc9 PS |
15345 | + printk(KERN_INFO " Still needed : %8ld\n", |
15346 | + ram_required); | |
ad8f4a28 AM |
15347 | + |
15348 | + /* Print breakdown of memory needed for modules */ | |
15349 | + toi_memory_for_modules(1); | |
15350 | + set_abort_result(TOI_UNABLE_TO_FREE_ENOUGH_MEMORY); | |
15351 | + } | |
15352 | + | |
15353 | + if (high_ps1) { | |
7f9d2ee0 | 15354 | + printk(KERN_INFO "- We need to free %ld highmem pageset 1 " |
ad8f4a28 AM |
15355 | + "pages.\n", high_ps1); |
15356 | + set_abort_result(TOI_UNABLE_TO_FREE_ENOUGH_MEMORY); | |
15357 | + } | |
15358 | + | |
15359 | + if (low_ps1) { | |
7f9d2ee0 | 15360 | + printk(KERN_INFO " - We need to free %ld lowmem pageset 1 " |
ad8f4a28 AM |
15361 | + "pages.\n", low_ps1); |
15362 | + set_abort_result(TOI_UNABLE_TO_FREE_ENOUGH_MEMORY); | |
15363 | + } | |
15364 | +} | |
15365 | + | |
4e97e4e9 | 15366 | +static void display_stats(int always, int sub_extra_pd1_allow) |
ad8f4a28 | 15367 | +{ |
4e97e4e9 | 15368 | + char buffer[255]; |
ad8f4a28 | 15369 | + snprintf(buffer, 254, |
7f9d2ee0 | 15370 | + "Free:%ld(%ld). Sets:%ld(%ld),%ld(%ld). Header:%ld/%ld. " |
15371 | + "Nosave:%ld-%ld=%ld. Storage:%lu/%lu(%lu=>%lu). " | |
1838f965 | 15372 | + "Needed:%ld,%ld,%ld(%d,%ld,%ld,%ld) (PS2:%s)\n", |
ad8f4a28 | 15373 | + |
4e97e4e9 | 15374 | + /* Free */ |
15375 | + real_nr_free_pages(all_zones_mask), | |
15376 | + real_nr_free_low_pages(), | |
ad8f4a28 | 15377 | + |
4e97e4e9 | 15378 | + /* Sets */ |
15379 | + pagedir1.size, pagedir1.size - get_highmem_size(pagedir1), | |
15380 | + pagedir2.size, pagedir2.size - get_highmem_size(pagedir2), | |
15381 | + | |
15382 | + /* Header */ | |
15383 | + header_space_allocated, header_storage_needed(), | |
e8d0ad9d | 15384 | + |
4e97e4e9 | 15385 | + /* Nosave */ |
15386 | + num_nosave, extra_pages_allocated, | |
15387 | + num_nosave - extra_pages_allocated, | |
24613191 | 15388 | + |
4e97e4e9 | 15389 | + /* Storage */ |
15390 | + main_storage_allocated, | |
15391 | + storage_available, | |
15392 | + main_storage_needed(1, sub_extra_pd1_allow), | |
15393 | + main_storage_needed(1, 1), | |
15394 | + | |
15395 | + /* Needed */ | |
15396 | + lowpages_ps1_to_free(), highpages_ps1_to_free(), | |
15397 | + any_to_free(1), | |
ad8f4a28 | 15398 | + MIN_FREE_RAM, toi_memory_for_modules(0), |
1838f965 | 15399 | + extra_pd1_pages_allowance, ((long) image_size_limit) << 8, |
15400 | + | |
15401 | + need_pageset2() ? "yes" : "no"); | |
24613191 | 15402 | + |
4e97e4e9 | 15403 | + if (always) |
1838f965 | 15404 | + printk("%s", buffer); |
4e97e4e9 | 15405 | + else |
15406 | + toi_message(TOI_EAT_MEMORY, TOI_MEDIUM, 1, buffer); | |
24613191 | 15407 | +} |
15408 | + | |
4e97e4e9 | 15409 | +/* generate_free_page_map |
15410 | + * | |
15411 | + * Description: This routine generates a bitmap of free pages from the | |
15412 | + * lists used by the memory manager. We then use the bitmap | |
15413 | + * to quickly calculate which pages to save and in which | |
15414 | + * pagesets. | |
15415 | + */ | |
ad8f4a28 | 15416 | +static void generate_free_page_map(void) |
24613191 | 15417 | +{ |
ad8f4a28 | 15418 | + int order, pfn, cpu, t; |
4e97e4e9 | 15419 | + unsigned long flags, i; |
15420 | + struct zone *zone; | |
ad8f4a28 | 15421 | + struct list_head *curr; |
24613191 | 15422 | + |
4e97e4e9 | 15423 | + for_each_zone(zone) { |
15424 | + if (!populated_zone(zone)) | |
e8d0ad9d | 15425 | + continue; |
ad8f4a28 | 15426 | + |
4e97e4e9 | 15427 | + spin_lock_irqsave(&zone->lock, flags); |
24613191 | 15428 | + |
ad8f4a28 | 15429 | + for (i = 0; i < zone->spanned_pages; i++) |
4e97e4e9 | 15430 | + ClearPageNosaveFree(pfn_to_page( |
1838f965 | 15431 | + ZONE_START(zone) + i)); |
24613191 | 15432 | + |
ad8f4a28 AM |
15433 | + for_each_migratetype_order(order, t) { |
15434 | + list_for_each(curr, | |
15435 | + &zone->free_area[order].free_list[t]) { | |
1838f965 | 15436 | + unsigned long j; |
ad8f4a28 AM |
15437 | + |
15438 | + pfn = page_to_pfn(list_entry(curr, struct page, | |
15439 | + lru)); | |
1838f965 | 15440 | + for (j = 0; j < (1UL << order); j++) |
15441 | + SetPageNosaveFree(pfn_to_page(pfn + j)); | |
ad8f4a28 AM |
15442 | + } |
15443 | + } | |
15444 | + | |
4e97e4e9 | 15445 | + for_each_online_cpu(cpu) { |
15446 | + struct per_cpu_pageset *pset = zone_pcp(zone, cpu); | |
7f9d2ee0 | 15447 | + struct per_cpu_pages *pcp = &pset->pcp; |
15448 | + struct page *page; | |
24613191 | 15449 | + |
7f9d2ee0 | 15450 | + list_for_each_entry(page, &pcp->list, lru) |
15451 | + SetPageNosaveFree(page); | |
24613191 | 15452 | + } |
ad8f4a28 | 15453 | + |
4e97e4e9 | 15454 | + spin_unlock_irqrestore(&zone->lock, flags); |
24613191 | 15455 | + } |
15456 | +} | |
15457 | + | |
4e97e4e9 | 15458 | +/* size_of_free_region |
ad8f4a28 AM |
15459 | + * |
15460 | + * Description: Return the number of pages that are free, beginning with and | |
4e97e4e9 | 15461 | + * including this one. |
15462 | + */ | |
15463 | +static int size_of_free_region(struct page *page) | |
24613191 | 15464 | +{ |
4e97e4e9 | 15465 | + struct zone *zone = page_zone(page); |
7f9d2ee0 | 15466 | + unsigned long this_pfn = page_to_pfn(page), |
15467 | + orig_pfn = this_pfn, | |
1838f965 | 15468 | + end_pfn = ZONE_START(zone) + zone->spanned_pages - 1; |
24613191 | 15469 | + |
7f9d2ee0 | 15470 | + while (this_pfn <= end_pfn && PageNosaveFree(pfn_to_page(this_pfn))) |
15471 | + this_pfn++; | |
15472 | + | |
f3e0dcc9 | 15473 | + return this_pfn - orig_pfn; |
24613191 | 15474 | +} |
15475 | + | |
4e97e4e9 | 15476 | +/* flag_image_pages |
24613191 | 15477 | + * |
4e97e4e9 | 15478 | + * This routine generates our lists of pages to be stored in each |
15479 | + * pageset. Since we store the data using extents, and adding new | |
15480 | + * extents might allocate a new extent page, this routine may well | |
15481 | + * be called more than once. | |
24613191 | 15482 | + */ |
4e97e4e9 | 15483 | +static void flag_image_pages(int atomic_copy) |
24613191 | 15484 | +{ |
4e97e4e9 | 15485 | + int num_free = 0; |
15486 | + unsigned long loop; | |
15487 | + struct zone *zone; | |
24613191 | 15488 | + |
4e97e4e9 | 15489 | + pagedir1.size = 0; |
15490 | + pagedir2.size = 0; | |
24613191 | 15491 | + |
4e97e4e9 | 15492 | + set_highmem_size(pagedir1, 0); |
15493 | + set_highmem_size(pagedir2, 0); | |
24613191 | 15494 | + |
4e97e4e9 | 15495 | + num_nosave = 0; |
24613191 | 15496 | + |
1838f965 | 15497 | + memory_bm_clear(&pageset1_map); |
24613191 | 15498 | + |
4e97e4e9 | 15499 | + generate_free_page_map(); |
24613191 | 15500 | + |
4e97e4e9 | 15501 | + /* |
ad8f4a28 AM |
15502 | + * Pages not to be saved are marked Nosave irrespective of being |
15503 | + * reserved. | |
4e97e4e9 | 15504 | + */ |
15505 | + for_each_zone(zone) { | |
15506 | + int highmem = is_highmem(zone); | |
15507 | + | |
15508 | + if (!populated_zone(zone)) | |
15509 | + continue; | |
15510 | + | |
15511 | + for (loop = 0; loop < zone->spanned_pages; loop++) { | |
1838f965 | 15512 | + unsigned long pfn = ZONE_START(zone) + loop; |
4e97e4e9 | 15513 | + struct page *page; |
15514 | + int chunk_size; | |
15515 | + | |
15516 | + if (!pfn_valid(pfn)) | |
15517 | + continue; | |
15518 | + | |
15519 | + page = pfn_to_page(pfn); | |
15520 | + | |
15521 | + chunk_size = size_of_free_region(page); | |
15522 | + if (chunk_size) { | |
15523 | + num_free += chunk_size; | |
15524 | + loop += chunk_size - 1; | |
15525 | + continue; | |
15526 | + } | |
15527 | + | |
15528 | + if (highmem) | |
15529 | + page = saveable_highmem_page(pfn); | |
e8d0ad9d | 15530 | + else |
4e97e4e9 | 15531 | + page = saveable_page(pfn); |
e8d0ad9d | 15532 | + |
4e97e4e9 | 15533 | + if (!page || PageNosave(page)) { |
15534 | + num_nosave++; | |
15535 | + continue; | |
15536 | + } | |
24613191 | 15537 | + |
4e97e4e9 | 15538 | + if (PagePageset2(page)) { |
15539 | + pagedir2.size++; | |
15540 | + if (PageHighMem(page)) | |
15541 | + inc_highmem_size(pagedir2); | |
15542 | + else | |
15543 | + SetPagePageset1Copy(page); | |
15544 | + if (PageResave(page)) { | |
15545 | + SetPagePageset1(page); | |
15546 | + ClearPagePageset1Copy(page); | |
15547 | + pagedir1.size++; | |
15548 | + if (PageHighMem(page)) | |
15549 | + inc_highmem_size(pagedir1); | |
15550 | + } | |
15551 | + } else { | |
15552 | + pagedir1.size++; | |
15553 | + SetPagePageset1(page); | |
15554 | + if (PageHighMem(page)) | |
15555 | + inc_highmem_size(pagedir1); | |
15556 | + } | |
15557 | + } | |
24613191 | 15558 | + } |
15559 | + | |
1838f965 | 15560 | + if (!atomic_copy) |
15561 | + toi_message(TOI_EAT_MEMORY, TOI_MEDIUM, 0, | |
15562 | + "Count data pages: Set1 (%d) + Set2 (%d) + Nosave (%ld)" | |
15563 | + " + NumFree (%d) = %d.\n", | |
15564 | + pagedir1.size, pagedir2.size, num_nosave, num_free, | |
15565 | + pagedir1.size + pagedir2.size + num_nosave + num_free); | |
4e97e4e9 | 15566 | +} |
24613191 | 15567 | + |
ad8f4a28 | 15568 | +void toi_recalculate_image_contents(int atomic_copy) |
4e97e4e9 | 15569 | +{ |
1838f965 | 15570 | + memory_bm_clear(&pageset1_map); |
4e97e4e9 | 15571 | + if (!atomic_copy) { |
1838f965 | 15572 | + unsigned long pfn; |
15573 | + BITMAP_FOR_EACH_SET(pageset2_map, pfn) | |
4e97e4e9 | 15574 | + ClearPagePageset1Copy(pfn_to_page(pfn)); |
15575 | + /* Need to call this before getting pageset1_size! */ | |
15576 | + toi_mark_pages_for_pageset2(); | |
15577 | + } | |
15578 | + flag_image_pages(atomic_copy); | |
24613191 | 15579 | + |
4e97e4e9 | 15580 | + if (!atomic_copy) { |
15581 | + storage_available = toiActiveAllocator->storage_available(); | |
15582 | + display_stats(0, 0); | |
24613191 | 15583 | + } |
24613191 | 15584 | +} |
15585 | + | |
4e97e4e9 | 15586 | +/* update_image |
15587 | + * | |
15588 | + * Allocate [more] memory and storage for the image. | |
15589 | + */ | |
1838f965 | 15590 | +static void update_image(int ps2_recalc) |
ad8f4a28 | 15591 | +{ |
7f9d2ee0 | 15592 | + int wanted, got; |
15593 | + long seek; | |
24613191 | 15594 | + |
4e97e4e9 | 15595 | + toi_recalculate_image_contents(0); |
24613191 | 15596 | + |
4e97e4e9 | 15597 | + /* Include allowance for growth in pagedir1 while writing pagedir 2 */ |
15598 | + wanted = pagedir1.size + extra_pd1_pages_allowance - | |
15599 | + get_lowmem_size(pagedir2); | |
15600 | + if (wanted > extra_pages_allocated) { | |
15601 | + got = toi_allocate_extra_pagedir_memory(wanted); | |
15602 | + if (wanted < got) { | |
15603 | + toi_message(TOI_EAT_MEMORY, TOI_LOW, 1, | |
15604 | + "Want %d extra pages for pageset1, got %d.\n", | |
15605 | + wanted, got); | |
15606 | + return; | |
15607 | + } | |
15608 | + } | |
24613191 | 15609 | + |
1838f965 | 15610 | + if (ps2_recalc) |
15611 | + goto recalc; | |
15612 | + | |
4e97e4e9 | 15613 | + thaw_kernel_threads(); |
24613191 | 15614 | + |
ad8f4a28 | 15615 | + /* |
4e97e4e9 | 15616 | + * Allocate remaining storage space, if possible, up to the |
15617 | + * maximum we know we'll need. It's okay to allocate the | |
15618 | + * maximum if the writer is the swapwriter, but | |
15619 | + * we don't want to grab all available space on an NFS share. | |
15620 | + * We therefore ignore the expected compression ratio here, | |
15621 | + * thereby trying to allocate the maximum image size we could | |
15622 | + * need (assuming compression doesn't expand the image), but | |
15623 | + * don't complain if we can't get the full amount we're after. | |
15624 | + */ | |
24613191 | 15625 | + |
7f9d2ee0 | 15626 | + storage_available = toiActiveAllocator->storage_available(); |
24613191 | 15627 | + |
7f9d2ee0 | 15628 | + header_space_allocated = header_storage_needed(); |
24613191 | 15629 | + |
7f9d2ee0 | 15630 | + toiActiveAllocator->reserve_header_space(header_space_allocated); |
24613191 | 15631 | + |
7f9d2ee0 | 15632 | + seek = min(storage_available, main_storage_needed(0, 0)); |
4e97e4e9 | 15633 | + |
7f9d2ee0 | 15634 | + toiActiveAllocator->allocate_storage(seek); |
15635 | + | |
15636 | + main_storage_allocated = toiActiveAllocator->storage_allocated(); | |
24613191 | 15637 | + |
4e97e4e9 | 15638 | + if (freeze_processes()) |
15639 | + set_abort_result(TOI_FREEZING_FAILED); | |
24613191 | 15640 | + |
1838f965 | 15641 | +recalc: |
4e97e4e9 | 15642 | + toi_recalculate_image_contents(0); |
24613191 | 15643 | +} |
15644 | + | |
4e97e4e9 | 15645 | +/* attempt_to_freeze |
ad8f4a28 | 15646 | + * |
4e97e4e9 | 15647 | + * Try to freeze processes. |
15648 | + */ | |
24613191 | 15649 | + |
4e97e4e9 | 15650 | +static int attempt_to_freeze(void) |
24613191 | 15651 | +{ |
4e97e4e9 | 15652 | + int result; |
ad8f4a28 | 15653 | + |
4e97e4e9 | 15654 | + /* Stop processes before checking again */ |
15655 | + thaw_processes(); | |
ad8f4a28 AM |
15656 | + toi_prepare_status(CLEAR_BAR, "Freezing processes & syncing " |
15657 | + "filesystems."); | |
4e97e4e9 | 15658 | + result = freeze_processes(); |
24613191 | 15659 | + |
4e97e4e9 | 15660 | + if (result) |
15661 | + set_abort_result(TOI_FREEZING_FAILED); | |
24613191 | 15662 | + |
4e97e4e9 | 15663 | + return result; |
15664 | +} | |
24613191 | 15665 | + |
4e97e4e9 | 15666 | +/* eat_memory |
15667 | + * | |
15668 | + * Try to free some memory, either to meet hard or soft constraints on the image | |
15669 | + * characteristics. | |
ad8f4a28 | 15670 | + * |
4e97e4e9 | 15671 | + * Hard constraints: |
15672 | + * - Pageset1 must be < half of memory; | |
15673 | + * - We must have enough memory free at resume time to have pageset1 | |
15674 | + * be able to be loaded in pages that don't conflict with where it has to | |
15675 | + * be restored. | |
15676 | + * Soft constraints | |
15677 | + * - User specificied image size limit. | |
15678 | + */ | |
15679 | +static void eat_memory(void) | |
15680 | +{ | |
7f9d2ee0 | 15681 | + long amount_wanted = 0; |
4e97e4e9 | 15682 | + int did_eat_memory = 0; |
ad8f4a28 | 15683 | + |
4e97e4e9 | 15684 | + /* |
15685 | + * Note that if we have enough storage space and enough free memory, we | |
15686 | + * may exit without eating anything. We give up when the last 10 | |
15687 | + * iterations ate no extra pages because we're not going to get much | |
15688 | + * more anyway, but the few pages we get will take a lot of time. | |
15689 | + * | |
15690 | + * We freeze processes before beginning, and then unfreeze them if we | |
15691 | + * need to eat memory until we think we have enough. If our attempts | |
15692 | + * to freeze fail, we give up and abort. | |
15693 | + */ | |
15694 | + | |
15695 | + toi_recalculate_image_contents(0); | |
15696 | + amount_wanted = amount_needed(1); | |
15697 | + | |
15698 | + switch (image_size_limit) { | |
ad8f4a28 AM |
15699 | + case -1: /* Don't eat any memory */ |
15700 | + if (amount_wanted > 0) { | |
15701 | + set_abort_result(TOI_WOULD_EAT_MEMORY); | |
15702 | + return; | |
15703 | + } | |
15704 | + break; | |
15705 | + case -2: /* Free caches only */ | |
15706 | + drop_pagecache(); | |
15707 | + toi_recalculate_image_contents(0); | |
15708 | + amount_wanted = amount_needed(1); | |
15709 | + did_eat_memory = 1; | |
15710 | + break; | |
15711 | + default: | |
15712 | + break; | |
24613191 | 15713 | + } |
15714 | + | |
4e97e4e9 | 15715 | + if (amount_wanted > 0 && !test_result_state(TOI_ABORTED) && |
15716 | + image_size_limit != -1) { | |
24613191 | 15717 | + |
ad8f4a28 | 15718 | + toi_prepare_status(CLEAR_BAR, |
7f9d2ee0 | 15719 | + "Seeking to free %ldMB of memory.", |
ad8f4a28 | 15720 | + MB(amount_wanted)); |
24613191 | 15721 | + |
4e97e4e9 | 15722 | + thaw_kernel_threads(); |
24613191 | 15723 | + |
1838f965 | 15724 | + shrink_all_memory(amount_wanted); |
24613191 | 15725 | + |
1838f965 | 15726 | + did_eat_memory = 1; |
24613191 | 15727 | + |
1838f965 | 15728 | + toi_recalculate_image_contents(0); |
24613191 | 15729 | + |
1838f965 | 15730 | + amount_wanted = amount_needed(1); |
24613191 | 15731 | + |
4e97e4e9 | 15732 | + toi_cond_pause(0, NULL); |
24613191 | 15733 | + |
4e97e4e9 | 15734 | + if (freeze_processes()) |
15735 | + set_abort_result(TOI_FREEZING_FAILED); | |
15736 | + } | |
ad8f4a28 | 15737 | + |
1838f965 | 15738 | + if (did_eat_memory) |
4e97e4e9 | 15739 | + toi_recalculate_image_contents(0); |
4e97e4e9 | 15740 | +} |
15741 | + | |
15742 | +/* toi_prepare_image | |
15743 | + * | |
15744 | + * Entry point to the whole image preparation section. | |
15745 | + * | |
15746 | + * We do four things: | |
15747 | + * - Freeze processes; | |
15748 | + * - Ensure image size constraints are met; | |
15749 | + * - Complete all the preparation for saving the image, | |
15750 | + * including allocation of storage. The only memory | |
15751 | + * that should be needed when we're finished is that | |
15752 | + * for actually storing the image (and we know how | |
15753 | + * much is needed for that because the modules tell | |
15754 | + * us). | |
15755 | + * - Make sure that all dirty buffers are written out. | |
15756 | + */ | |
15757 | +#define MAX_TRIES 2 | |
15758 | +int toi_prepare_image(void) | |
15759 | +{ | |
15760 | + int result = 1, tries = 1; | |
24613191 | 15761 | + |
4e97e4e9 | 15762 | + header_space_allocated = 0; |
15763 | + main_storage_allocated = 0; | |
1838f965 | 15764 | + no_ps2_needed = 0; |
24613191 | 15765 | + |
4e97e4e9 | 15766 | + if (attempt_to_freeze()) |
15767 | + return 1; | |
24613191 | 15768 | + |
4e97e4e9 | 15769 | + if (!extra_pd1_pages_allowance) |
15770 | + get_extra_pd1_allowance(); | |
24613191 | 15771 | + |
4e97e4e9 | 15772 | + storage_available = toiActiveAllocator->storage_available(); |
24613191 | 15773 | + |
4e97e4e9 | 15774 | + if (!storage_available) { |
7f9d2ee0 | 15775 | + printk(KERN_INFO "No storage available. Didn't try to prepare " |
15776 | + "an image.\n"); | |
ad8f4a28 | 15777 | + display_failure_reason(0); |
4e97e4e9 | 15778 | + set_abort_result(TOI_NOSTORAGE_AVAILABLE); |
15779 | + return 1; | |
15780 | + } | |
24613191 | 15781 | + |
4e97e4e9 | 15782 | + if (build_attention_list()) { |
15783 | + abort_hibernate(TOI_UNABLE_TO_PREPARE_IMAGE, | |
15784 | + "Unable to successfully prepare the image.\n"); | |
15785 | + return 1; | |
15786 | + } | |
24613191 | 15787 | + |
4e97e4e9 | 15788 | + do { |
ad8f4a28 AM |
15789 | + toi_prepare_status(CLEAR_BAR, |
15790 | + "Preparing Image. Try %d.", tries); | |
15791 | + | |
4e97e4e9 | 15792 | + eat_memory(); |
24613191 | 15793 | + |
4e97e4e9 | 15794 | + if (test_result_state(TOI_ABORTED)) |
15795 | + break; | |
24613191 | 15796 | + |
1838f965 | 15797 | + update_image(0); |
24613191 | 15798 | + |
4e97e4e9 | 15799 | + tries++; |
24613191 | 15800 | + |
4e97e4e9 | 15801 | + } while (image_not_ready(1) && tries <= MAX_TRIES && |
15802 | + !test_result_state(TOI_ABORTED)); | |
24613191 | 15803 | + |
4e97e4e9 | 15804 | + result = image_not_ready(0); |
24613191 | 15805 | + |
4e97e4e9 | 15806 | + if (!test_result_state(TOI_ABORTED)) { |
15807 | + if (result) { | |
15808 | + display_stats(1, 0); | |
ad8f4a28 | 15809 | + display_failure_reason(tries > MAX_TRIES); |
4e97e4e9 | 15810 | + abort_hibernate(TOI_UNABLE_TO_PREPARE_IMAGE, |
15811 | + "Unable to successfully prepare the image.\n"); | |
15812 | + } else { | |
1838f965 | 15813 | + /* Pageset 2 needed? */ |
15814 | + if (!need_pageset2() && | |
15815 | + test_action_state(TOI_NO_PS2_IF_UNNEEDED)) { | |
15816 | + no_ps2_needed = 1; | |
15817 | + update_image(1); | |
15818 | + } | |
15819 | + | |
4e97e4e9 | 15820 | + toi_cond_pause(1, "Image preparation complete."); |
15821 | + } | |
15822 | + } | |
24613191 | 15823 | + |
ad8f4a28 | 15824 | + return result ? result : allocate_checksum_pages(); |
24613191 | 15825 | +} |
4e97e4e9 | 15826 | diff --git a/kernel/power/tuxonice_prepare_image.h b/kernel/power/tuxonice_prepare_image.h |
15827 | new file mode 100644 | |
1838f965 | 15828 | index 0000000..46eda88 |
4e97e4e9 | 15829 | --- /dev/null |
15830 | +++ b/kernel/power/tuxonice_prepare_image.h | |
15831 | @@ -0,0 +1,35 @@ | |
15832 | +/* | |
15833 | + * kernel/power/tuxonice_prepare_image.h | |
15834 | + * | |
1838f965 | 15835 | + * Copyright (C) 2003-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 15836 | + * |
15837 | + * This file is released under the GPLv2. | |
15838 | + * | |
15839 | + */ | |
24613191 | 15840 | + |
4e97e4e9 | 15841 | +#include <asm/sections.h> |
24613191 | 15842 | + |
4e97e4e9 | 15843 | +extern int toi_prepare_image(void); |
15844 | +extern void toi_recalculate_image_contents(int storage_available); | |
7f9d2ee0 | 15845 | +extern long real_nr_free_pages(unsigned long zone_idx_mask); |
4e97e4e9 | 15846 | +extern int image_size_limit; |
15847 | +extern void toi_free_extra_pagedir_memory(void); | |
7f9d2ee0 | 15848 | +extern long extra_pd1_pages_allowance; |
4e97e4e9 | 15849 | +extern void free_attention_list(void); |
24613191 | 15850 | + |
4e97e4e9 | 15851 | +#define MIN_FREE_RAM 100 |
f3e0dcc9 | 15852 | +#define MIN_EXTRA_PAGES_ALLOWANCE 500 |
24613191 | 15853 | + |
4e97e4e9 | 15854 | +#define all_zones_mask ((unsigned long) ((1 << MAX_NR_ZONES) - 1)) |
15855 | +#ifdef CONFIG_HIGHMEM | |
15856 | +#define real_nr_free_high_pages() (real_nr_free_pages(1 << ZONE_HIGHMEM)) | |
15857 | +#define real_nr_free_low_pages() (real_nr_free_pages(all_zones_mask - \ | |
15858 | + (1 << ZONE_HIGHMEM))) | |
15859 | +#else | |
15860 | +#define real_nr_free_high_pages() (0) | |
15861 | +#define real_nr_free_low_pages() (real_nr_free_pages(all_zones_mask)) | |
24613191 | 15862 | + |
4e97e4e9 | 15863 | +/* For eat_memory function */ |
15864 | +#define ZONE_HIGHMEM (MAX_NR_ZONES + 1) | |
15865 | +#endif | |
24613191 | 15866 | + |
4e97e4e9 | 15867 | diff --git a/kernel/power/tuxonice_storage.c b/kernel/power/tuxonice_storage.c |
15868 | new file mode 100644 | |
1838f965 | 15869 | index 0000000..5dafc95 |
4e97e4e9 | 15870 | --- /dev/null |
15871 | +++ b/kernel/power/tuxonice_storage.c | |
1838f965 | 15872 | @@ -0,0 +1,282 @@ |
24613191 | 15873 | +/* |
4e97e4e9 | 15874 | + * kernel/power/tuxonice_storage.c |
24613191 | 15875 | + * |
1838f965 | 15876 | + * Copyright (C) 2005-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 15877 | + * |
15878 | + * This file is released under the GPLv2. | |
15879 | + * | |
15880 | + * Routines for talking to a userspace program that manages storage. | |
15881 | + * | |
15882 | + * The kernel side: | |
15883 | + * - starts the userspace program; | |
15884 | + * - sends messages telling it when to open and close the connection; | |
15885 | + * - tells it when to quit; | |
15886 | + * | |
15887 | + * The user space side: | |
15888 | + * - passes messages regarding status; | |
24613191 | 15889 | + * |
24613191 | 15890 | + */ |
15891 | + | |
4e97e4e9 | 15892 | +#include <linux/suspend.h> |
15893 | +#include <linux/freezer.h> | |
ad8f4a28 | 15894 | + |
4e97e4e9 | 15895 | +#include "tuxonice_sysfs.h" |
15896 | +#include "tuxonice_modules.h" | |
15897 | +#include "tuxonice_netlink.h" | |
15898 | +#include "tuxonice_storage.h" | |
15899 | +#include "tuxonice_ui.h" | |
15900 | + | |
15901 | +static struct user_helper_data usm_helper_data; | |
15902 | +static struct toi_module_ops usm_ops; | |
ad8f4a28 AM |
15903 | +static int message_received, usm_prepare_count; |
15904 | +static int storage_manager_last_action, storage_manager_action; | |
15905 | + | |
4e97e4e9 | 15906 | +static int usm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) |
24613191 | 15907 | +{ |
4e97e4e9 | 15908 | + int type; |
15909 | + int *data; | |
24613191 | 15910 | + |
4e97e4e9 | 15911 | + type = nlh->nlmsg_type; |
24613191 | 15912 | + |
4e97e4e9 | 15913 | + /* A control message: ignore them */ |
15914 | + if (type < NETLINK_MSG_BASE) | |
15915 | + return 0; | |
24613191 | 15916 | + |
4e97e4e9 | 15917 | + /* Unknown message: reply with EINVAL */ |
15918 | + if (type >= USM_MSG_MAX) | |
15919 | + return -EINVAL; | |
24613191 | 15920 | + |
4e97e4e9 | 15921 | + /* All operations require privileges, even GET */ |
15922 | + if (security_netlink_recv(skb, CAP_NET_ADMIN)) | |
15923 | + return -EPERM; | |
24613191 | 15924 | + |
4e97e4e9 | 15925 | + /* Only allow one task to receive NOFREEZE privileges */ |
15926 | + if (type == NETLINK_MSG_NOFREEZE_ME && usm_helper_data.pid != -1) | |
15927 | + return -EBUSY; | |
24613191 | 15928 | + |
ad8f4a28 | 15929 | + data = (int *) NLMSG_DATA(nlh); |
24613191 | 15930 | + |
4e97e4e9 | 15931 | + switch (type) { |
ad8f4a28 AM |
15932 | + case USM_MSG_SUCCESS: |
15933 | + case USM_MSG_FAILED: | |
15934 | + message_received = type; | |
15935 | + complete(&usm_helper_data.wait_for_process); | |
15936 | + break; | |
15937 | + default: | |
15938 | + printk(KERN_INFO "Storage manager doesn't recognise " | |
15939 | + "message %d.\n", type); | |
4e97e4e9 | 15940 | + } |
24613191 | 15941 | + |
4e97e4e9 | 15942 | + return 1; |
24613191 | 15943 | +} |
15944 | + | |
4e97e4e9 | 15945 | +#ifdef CONFIG_NET |
ad8f4a28 | 15946 | +static int activations; |
24613191 | 15947 | + |
4e97e4e9 | 15948 | +int toi_activate_storage(int force) |
24613191 | 15949 | +{ |
4e97e4e9 | 15950 | + int tries = 1; |
24613191 | 15951 | + |
4e97e4e9 | 15952 | + if (usm_helper_data.pid == -1 || !usm_ops.enabled) |
15953 | + return 0; | |
24613191 | 15954 | + |
4e97e4e9 | 15955 | + message_received = 0; |
15956 | + activations++; | |
24613191 | 15957 | + |
4e97e4e9 | 15958 | + if (activations > 1 && !force) |
15959 | + return 0; | |
24613191 | 15960 | + |
ad8f4a28 AM |
15961 | + while ((!message_received || message_received == USM_MSG_FAILED) && |
15962 | + tries < 2) { | |
15963 | + toi_prepare_status(DONT_CLEAR_BAR, "Activate storage attempt " | |
15964 | + "%d.\n", tries); | |
24613191 | 15965 | + |
4e97e4e9 | 15966 | + init_completion(&usm_helper_data.wait_for_process); |
24613191 | 15967 | + |
4e97e4e9 | 15968 | + toi_send_netlink_message(&usm_helper_data, |
15969 | + USM_MSG_CONNECT, | |
15970 | + NULL, 0); | |
24613191 | 15971 | + |
4e97e4e9 | 15972 | + /* Wait 2 seconds for the userspace process to make contact */ |
ad8f4a28 AM |
15973 | + wait_for_completion_timeout(&usm_helper_data.wait_for_process, |
15974 | + 2*HZ); | |
24613191 | 15975 | + |
4e97e4e9 | 15976 | + tries++; |
24613191 | 15977 | + } |
15978 | + | |
4e97e4e9 | 15979 | + return 0; |
24613191 | 15980 | +} |
15981 | + | |
4e97e4e9 | 15982 | +int toi_deactivate_storage(int force) |
24613191 | 15983 | +{ |
4e97e4e9 | 15984 | + if (usm_helper_data.pid == -1 || !usm_ops.enabled) |
15985 | + return 0; | |
ad8f4a28 | 15986 | + |
4e97e4e9 | 15987 | + message_received = 0; |
15988 | + activations--; | |
24613191 | 15989 | + |
4e97e4e9 | 15990 | + if (activations && !force) |
15991 | + return 0; | |
24613191 | 15992 | + |
4e97e4e9 | 15993 | + init_completion(&usm_helper_data.wait_for_process); |
24613191 | 15994 | + |
4e97e4e9 | 15995 | + toi_send_netlink_message(&usm_helper_data, |
15996 | + USM_MSG_DISCONNECT, | |
15997 | + NULL, 0); | |
24613191 | 15998 | + |
4e97e4e9 | 15999 | + wait_for_completion_timeout(&usm_helper_data.wait_for_process, 2*HZ); |
24613191 | 16000 | + |
4e97e4e9 | 16001 | + if (!message_received || message_received == USM_MSG_FAILED) { |
ad8f4a28 | 16002 | + printk(KERN_INFO "Returning failure disconnecting storage.\n"); |
4e97e4e9 | 16003 | + return 1; |
16004 | + } | |
24613191 | 16005 | + |
4e97e4e9 | 16006 | + return 0; |
24613191 | 16007 | +} |
4e97e4e9 | 16008 | +#endif |
24613191 | 16009 | + |
4e97e4e9 | 16010 | +static void storage_manager_simulate(void) |
24613191 | 16011 | +{ |
ad8f4a28 | 16012 | + printk(KERN_INFO "--- Storage manager simulate ---\n"); |
4e97e4e9 | 16013 | + toi_prepare_usm(); |
16014 | + schedule(); | |
ad8f4a28 | 16015 | + printk(KERN_INFO "--- Activate storage 1 ---\n"); |
4e97e4e9 | 16016 | + toi_activate_storage(1); |
16017 | + schedule(); | |
ad8f4a28 | 16018 | + printk(KERN_INFO "--- Deactivate storage 1 ---\n"); |
4e97e4e9 | 16019 | + toi_deactivate_storage(1); |
16020 | + schedule(); | |
ad8f4a28 | 16021 | + printk(KERN_INFO "--- Cleanup usm ---\n"); |
4e97e4e9 | 16022 | + toi_cleanup_usm(); |
16023 | + schedule(); | |
ad8f4a28 | 16024 | + printk(KERN_INFO "--- Storage manager simulate ends ---\n"); |
24613191 | 16025 | +} |
16026 | + | |
4e97e4e9 | 16027 | +static int usm_storage_needed(void) |
24613191 | 16028 | +{ |
4e97e4e9 | 16029 | + return strlen(usm_helper_data.program); |
24613191 | 16030 | +} |
16031 | + | |
4e97e4e9 | 16032 | +static int usm_save_config_info(char *buf) |
24613191 | 16033 | +{ |
4e97e4e9 | 16034 | + int len = strlen(usm_helper_data.program); |
16035 | + memcpy(buf, usm_helper_data.program, len); | |
16036 | + return len; | |
16037 | +} | |
24613191 | 16038 | + |
4e97e4e9 | 16039 | +static void usm_load_config_info(char *buf, int size) |
16040 | +{ | |
16041 | + /* Don't load the saved path if one has already been set */ | |
16042 | + if (usm_helper_data.program[0]) | |
16043 | + return; | |
24613191 | 16044 | + |
4e97e4e9 | 16045 | + memcpy(usm_helper_data.program, buf, size); |
24613191 | 16046 | +} |
16047 | + | |
4e97e4e9 | 16048 | +static int usm_memory_needed(void) |
24613191 | 16049 | +{ |
4e97e4e9 | 16050 | + /* ball park figure of 32 pages */ |
f3e0dcc9 | 16051 | + return 32 * PAGE_SIZE; |
24613191 | 16052 | +} |
16053 | + | |
4e97e4e9 | 16054 | +/* toi_prepare_usm |
24613191 | 16055 | + */ |
4e97e4e9 | 16056 | +int toi_prepare_usm(void) |
24613191 | 16057 | +{ |
4e97e4e9 | 16058 | + usm_prepare_count++; |
24613191 | 16059 | + |
4e97e4e9 | 16060 | + if (usm_prepare_count > 1 || !usm_ops.enabled) |
24613191 | 16061 | + return 0; |
ad8f4a28 | 16062 | + |
4e97e4e9 | 16063 | + usm_helper_data.pid = -1; |
24613191 | 16064 | + |
4e97e4e9 | 16065 | + if (!*usm_helper_data.program) |
16066 | + return 0; | |
24613191 | 16067 | + |
4e97e4e9 | 16068 | + toi_netlink_setup(&usm_helper_data); |
24613191 | 16069 | + |
4e97e4e9 | 16070 | + if (usm_helper_data.pid == -1) |
ad8f4a28 AM |
16071 | + printk(KERN_INFO "TuxOnIce Storage Manager wanted, but couldn't" |
16072 | + " start it.\n"); | |
24613191 | 16073 | + |
4e97e4e9 | 16074 | + toi_activate_storage(0); |
24613191 | 16075 | + |
f3e0dcc9 | 16076 | + return usm_helper_data.pid != -1; |
4e97e4e9 | 16077 | +} |
24613191 | 16078 | + |
4e97e4e9 | 16079 | +void toi_cleanup_usm(void) |
16080 | +{ | |
16081 | + usm_prepare_count--; | |
16082 | + | |
16083 | + if (usm_helper_data.pid > -1 && !usm_prepare_count) { | |
16084 | + toi_deactivate_storage(0); | |
16085 | + toi_netlink_close(&usm_helper_data); | |
24613191 | 16086 | + } |
4e97e4e9 | 16087 | +} |
24613191 | 16088 | + |
4e97e4e9 | 16089 | +static void storage_manager_activate(void) |
16090 | +{ | |
16091 | + if (storage_manager_action == storage_manager_last_action) | |
16092 | + return; | |
24613191 | 16093 | + |
4e97e4e9 | 16094 | + if (storage_manager_action) |
16095 | + toi_prepare_usm(); | |
16096 | + else | |
16097 | + toi_cleanup_usm(); | |
24613191 | 16098 | + |
4e97e4e9 | 16099 | + storage_manager_last_action = storage_manager_action; |
16100 | +} | |
24613191 | 16101 | + |
4e97e4e9 | 16102 | +/* |
16103 | + * User interface specific /sys/power/tuxonice entries. | |
16104 | + */ | |
24613191 | 16105 | + |
4e97e4e9 | 16106 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 16107 | + SYSFS_NONE("simulate_atomic_copy", storage_manager_simulate), |
16108 | + SYSFS_INT("enabled", SYSFS_RW, &usm_ops.enabled, 0, 1, 0, NULL), | |
16109 | + SYSFS_STRING("program", SYSFS_RW, usm_helper_data.program, 254, 0, | |
16110 | + NULL), | |
16111 | + SYSFS_INT("activate_storage", SYSFS_RW , &storage_manager_action, 0, 1, | |
16112 | + 0, storage_manager_activate) | |
4e97e4e9 | 16113 | +}; |
24613191 | 16114 | + |
4e97e4e9 | 16115 | +static struct toi_module_ops usm_ops = { |
16116 | + .type = MISC_MODULE, | |
16117 | + .name = "usm", | |
16118 | + .directory = "storage_manager", | |
16119 | + .module = THIS_MODULE, | |
16120 | + .storage_needed = usm_storage_needed, | |
16121 | + .save_config_info = usm_save_config_info, | |
16122 | + .load_config_info = usm_load_config_info, | |
16123 | + .memory_needed = usm_memory_needed, | |
24613191 | 16124 | + |
4e97e4e9 | 16125 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
16126 | + .num_sysfs_entries = sizeof(sysfs_params) / |
16127 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 16128 | +}; |
24613191 | 16129 | + |
4e97e4e9 | 16130 | +/* toi_usm_sysfs_init |
16131 | + * Description: Boot time initialisation for user interface. | |
24613191 | 16132 | + */ |
4e97e4e9 | 16133 | +int toi_usm_init(void) |
24613191 | 16134 | +{ |
4e97e4e9 | 16135 | + usm_helper_data.nl = NULL; |
16136 | + usm_helper_data.program[0] = '\0'; | |
16137 | + usm_helper_data.pid = -1; | |
16138 | + usm_helper_data.skb_size = 0; | |
16139 | + usm_helper_data.pool_limit = 6; | |
16140 | + usm_helper_data.netlink_id = NETLINK_TOI_USM; | |
16141 | + usm_helper_data.name = "userspace storage manager"; | |
16142 | + usm_helper_data.rcv_msg = usm_user_rcv_msg; | |
1838f965 | 16143 | + usm_helper_data.interface_version = 2; |
4e97e4e9 | 16144 | + usm_helper_data.must_init = 0; |
16145 | + init_completion(&usm_helper_data.wait_for_process); | |
16146 | + | |
16147 | + return toi_register_module(&usm_ops); | |
24613191 | 16148 | +} |
16149 | + | |
4e97e4e9 | 16150 | +void toi_usm_exit(void) |
24613191 | 16151 | +{ |
f3e0dcc9 | 16152 | + toi_netlink_close_complete(&usm_helper_data); |
4e97e4e9 | 16153 | + toi_unregister_module(&usm_ops); |
16154 | +} | |
16155 | diff --git a/kernel/power/tuxonice_storage.h b/kernel/power/tuxonice_storage.h | |
16156 | new file mode 100644 | |
1838f965 | 16157 | index 0000000..5477056 |
4e97e4e9 | 16158 | --- /dev/null |
16159 | +++ b/kernel/power/tuxonice_storage.h | |
16160 | @@ -0,0 +1,53 @@ | |
16161 | +/* | |
16162 | + * kernel/power/tuxonice_storage.h | |
16163 | + * | |
1838f965 | 16164 | + * Copyright (C) 2005-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 16165 | + * |
16166 | + * This file is released under the GPLv2. | |
16167 | + */ | |
24613191 | 16168 | + |
4e97e4e9 | 16169 | +#ifdef CONFIG_NET |
16170 | +int toi_prepare_usm(void); | |
16171 | +void toi_cleanup_usm(void); | |
24613191 | 16172 | + |
4e97e4e9 | 16173 | +int toi_activate_storage(int force); |
16174 | +int toi_deactivate_storage(int force); | |
16175 | +extern int toi_usm_init(void); | |
16176 | +extern void toi_usm_exit(void); | |
16177 | +#else | |
16178 | +static inline int toi_usm_init(void) { return 0; } | |
16179 | +static inline void toi_usm_exit(void) { } | |
24613191 | 16180 | + |
4e97e4e9 | 16181 | +static inline int toi_activate_storage(int force) |
16182 | +{ | |
e8d0ad9d | 16183 | + return 0; |
24613191 | 16184 | +} |
16185 | + | |
4e97e4e9 | 16186 | +static inline int toi_deactivate_storage(int force) |
16187 | +{ | |
16188 | + return 0; | |
16189 | +} | |
24613191 | 16190 | + |
4e97e4e9 | 16191 | +static inline int toi_prepare_usm(void) { return 0; } |
16192 | +static inline void toi_cleanup_usm(void) { } | |
16193 | +#endif | |
24613191 | 16194 | + |
4e97e4e9 | 16195 | +enum { |
16196 | + USM_MSG_BASE = 0x10, | |
24613191 | 16197 | + |
4e97e4e9 | 16198 | + /* Kernel -> Userspace */ |
16199 | + USM_MSG_CONNECT = 0x30, | |
16200 | + USM_MSG_DISCONNECT = 0x31, | |
16201 | + USM_MSG_SUCCESS = 0x40, | |
16202 | + USM_MSG_FAILED = 0x41, | |
24613191 | 16203 | + |
4e97e4e9 | 16204 | + USM_MSG_MAX, |
24613191 | 16205 | +}; |
16206 | + | |
4e97e4e9 | 16207 | +#ifdef CONFIG_NET |
16208 | +extern __init int toi_usm_init(void); | |
16209 | +extern __exit void toi_usm_cleanup(void); | |
24613191 | 16210 | +#else |
ad8f4a28 AM |
16211 | +#define toi_usm_init() do { } while (0) |
16212 | +#define toi_usm_cleanup() do { } while (0) | |
24613191 | 16213 | +#endif |
4e97e4e9 | 16214 | diff --git a/kernel/power/tuxonice_swap.c b/kernel/power/tuxonice_swap.c |
16215 | new file mode 100644 | |
1838f965 | 16216 | index 0000000..aa21de9 |
4e97e4e9 | 16217 | --- /dev/null |
16218 | +++ b/kernel/power/tuxonice_swap.c | |
1838f965 | 16219 | @@ -0,0 +1,1279 @@ |
24613191 | 16220 | +/* |
4e97e4e9 | 16221 | + * kernel/power/tuxonice_swap.c |
24613191 | 16222 | + * |
1838f965 | 16223 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 16224 | + * |
16225 | + * Distributed under GPLv2. | |
ad8f4a28 | 16226 | + * |
24613191 | 16227 | + * This file encapsulates functions for usage of swap space as a |
16228 | + * backing store. | |
16229 | + */ | |
16230 | + | |
16231 | +#include <linux/suspend.h> | |
16232 | +#include <linux/module.h> | |
16233 | +#include <linux/blkdev.h> | |
16234 | +#include <linux/swapops.h> | |
16235 | +#include <linux/swap.h> | |
16236 | +#include <linux/syscalls.h> | |
16237 | + | |
4e97e4e9 | 16238 | +#include "tuxonice.h" |
16239 | +#include "tuxonice_sysfs.h" | |
16240 | +#include "tuxonice_modules.h" | |
16241 | +#include "tuxonice_io.h" | |
16242 | +#include "tuxonice_ui.h" | |
16243 | +#include "tuxonice_extent.h" | |
16244 | +#include "tuxonice_block_io.h" | |
ad8f4a28 | 16245 | +#include "tuxonice_alloc.h" |
1838f965 | 16246 | +#include "tuxonice_builtin.h" |
24613191 | 16247 | + |
4e97e4e9 | 16248 | +static struct toi_module_ops toi_swapops; |
24613191 | 16249 | + |
24613191 | 16250 | +/* --- Struct of pages stored on disk */ |
16251 | + | |
f3e0dcc9 | 16252 | +struct sig_data { |
7f9d2ee0 | 16253 | + dev_t device; |
16254 | + unsigned long sector; | |
16255 | + int resume_attempted; | |
16256 | + int orig_sig_type; | |
16257 | +}; | |
16258 | + | |
24613191 | 16259 | +union diskpage { |
16260 | + union swap_header swh; /* swh.magic is the only member used */ | |
f3e0dcc9 | 16261 | + struct sig_data sig_data; |
24613191 | 16262 | +}; |
16263 | + | |
16264 | +union p_diskpage { | |
16265 | + union diskpage *pointer; | |
16266 | + char *ptr; | |
ad8f4a28 | 16267 | + unsigned long address; |
24613191 | 16268 | +}; |
16269 | + | |
7f9d2ee0 | 16270 | +enum { |
16271 | + IMAGE_SIGNATURE, | |
16272 | + NO_IMAGE_SIGNATURE, | |
16273 | + TRIED_RESUME, | |
16274 | + NO_TRIED_RESUME, | |
16275 | +}; | |
16276 | + | |
16277 | +/* | |
16278 | + * Both of these point to versions of the swap header page. original_sig points | |
16279 | + * to the data we read from disk at the start of hibernating or checking whether | |
16280 | + * to resume. no_image is the page stored in the image header, showing what the | |
16281 | + * swap header page looked like at the start of hibernating. | |
16282 | + */ | |
16283 | +static char *current_signature_page; | |
f3e0dcc9 | 16284 | +static char no_image_signature_contents[sizeof(struct sig_data)]; |
7f9d2ee0 | 16285 | + |
24613191 | 16286 | +/* Devices used for swap */ |
4e97e4e9 | 16287 | +static struct toi_bdev_info devinfo[MAX_SWAPFILES]; |
24613191 | 16288 | + |
16289 | +/* Extent chains for swap & blocks */ | |
1838f965 | 16290 | +static struct hibernate_extent_chain swapextents; |
16291 | +static struct hibernate_extent_chain block_chain[MAX_SWAPFILES]; | |
24613191 | 16292 | + |
16293 | +static dev_t header_dev_t; | |
16294 | +static struct block_device *header_block_device; | |
16295 | +static unsigned long headerblock; | |
16296 | + | |
16297 | +/* For swapfile automatically swapon/off'd. */ | |
16298 | +static char swapfilename[32] = ""; | |
4e97e4e9 | 16299 | +static int toi_swapon_status; |
24613191 | 16300 | + |
16301 | +/* Header Page Information */ | |
7f9d2ee0 | 16302 | +static long header_pages_reserved; |
24613191 | 16303 | + |
16304 | +/* Swap Pages */ | |
7f9d2ee0 | 16305 | +static long swap_pages_allocated; |
24613191 | 16306 | + |
16307 | +/* User Specified Parameters. */ | |
16308 | + | |
16309 | +static unsigned long resume_firstblock; | |
24613191 | 16310 | +static dev_t resume_swap_dev_t; |
16311 | +static struct block_device *resume_block_device; | |
16312 | + | |
1838f965 | 16313 | +static struct sysinfo swapinfo; |
24613191 | 16314 | + |
16315 | +/* Block devices open. */ | |
ad8f4a28 | 16316 | +struct bdev_opened { |
24613191 | 16317 | + dev_t device; |
16318 | + struct block_device *bdev; | |
24613191 | 16319 | +}; |
16320 | + | |
ad8f4a28 | 16321 | +/* |
24613191 | 16322 | + * Entry MAX_SWAPFILES is the resume block device, which may |
4e97e4e9 | 16323 | + * be a swap device not enabled when we hibernate. |
24613191 | 16324 | + * Entry MAX_SWAPFILES + 1 is the header block device, which |
16325 | + * is needed before we find out which slot it occupies. | |
4e97e4e9 | 16326 | + * |
16327 | + * We use a separate struct to devInfo so that we can track | |
16328 | + * the bdevs we open, because if we need to abort resuming | |
16329 | + * prior to the atomic restore, they need to be closed, but | |
16330 | + * closing them after sucessfully resuming would be wrong. | |
24613191 | 16331 | + */ |
4e97e4e9 | 16332 | +static struct bdev_opened *bdevs_opened[MAX_SWAPFILES + 2]; |
ad8f4a28 | 16333 | + |
4e97e4e9 | 16334 | +/** |
16335 | + * close_bdev: Close a swap bdev. | |
16336 | + * | |
16337 | + * int: The swap entry number to close. | |
16338 | + */ | |
24613191 | 16339 | +static void close_bdev(int i) |
16340 | +{ | |
4e97e4e9 | 16341 | + struct bdev_opened *this = bdevs_opened[i]; |
24613191 | 16342 | + |
4e97e4e9 | 16343 | + if (!this) |
16344 | + return; | |
24613191 | 16345 | + |
24613191 | 16346 | + blkdev_put(this->bdev); |
ad8f4a28 | 16347 | + toi_kfree(8, this); |
4e97e4e9 | 16348 | + bdevs_opened[i] = NULL; |
24613191 | 16349 | +} |
16350 | + | |
4e97e4e9 | 16351 | +/** |
16352 | + * close_bdevs: Close all bdevs we opened. | |
16353 | + * | |
16354 | + * Close all bdevs that we opened and reset the related vars. | |
16355 | + */ | |
24613191 | 16356 | +static void close_bdevs(void) |
16357 | +{ | |
16358 | + int i; | |
16359 | + | |
4e97e4e9 | 16360 | + for (i = 0; i < MAX_SWAPFILES + 2; i++) |
16361 | + close_bdev(i); | |
24613191 | 16362 | + |
16363 | + resume_block_device = header_block_device = NULL; | |
16364 | +} | |
16365 | + | |
4e97e4e9 | 16366 | +/** |
16367 | + * open_bdev: Open a bdev at resume time. | |
16368 | + * | |
16369 | + * index: The swap index. May be MAX_SWAPFILES for the resume_dev_t | |
16370 | + * (the user can have resume= pointing at a swap partition/file that isn't | |
16371 | + * swapon'd when they hibernate. MAX_SWAPFILES+1 for the first page of the | |
16372 | + * header. It will be from a swap partition that was enabled when we hibernated, | |
16373 | + * but we don't know it's real index until we read that first page. | |
16374 | + * dev_t: The device major/minor. | |
16375 | + * display_errs: Whether to try to do this quietly. | |
16376 | + * | |
16377 | + * We stored a dev_t in the image header. Open the matching device without | |
16378 | + * requiring /dev/<whatever> in most cases and record the details needed | |
16379 | + * to close it later and avoid duplicating work. | |
16380 | + */ | |
24613191 | 16381 | +static struct block_device *open_bdev(int index, dev_t device, int display_errs) |
16382 | +{ | |
16383 | + struct bdev_opened *this; | |
16384 | + struct block_device *bdev; | |
16385 | + | |
4e97e4e9 | 16386 | + if (bdevs_opened[index]) { |
16387 | + if (bdevs_opened[index]->device == device) | |
16388 | + return bdevs_opened[index]->bdev; | |
ad8f4a28 | 16389 | + |
24613191 | 16390 | + close_bdev(index); |
4e97e4e9 | 16391 | + } |
24613191 | 16392 | + |
ad8f4a28 | 16393 | + bdev = toi_open_by_devnum(device, FMODE_READ); |
24613191 | 16394 | + |
16395 | + if (IS_ERR(bdev) || !bdev) { | |
16396 | + if (display_errs) | |
ad8f4a28 | 16397 | + toi_early_boot_message(1, TOI_CONTINUE_REQ, |
24613191 | 16398 | + "Failed to get access to block device " |
16399 | + "\"%x\" (error %d).\n Maybe you need " | |
16400 | + "to run mknod and/or lvmsetup in an " | |
16401 | + "initrd/ramfs?", device, bdev); | |
16402 | + return ERR_PTR(-EINVAL); | |
16403 | + } | |
16404 | + | |
ad8f4a28 | 16405 | + this = toi_kzalloc(8, sizeof(struct bdev_opened), GFP_KERNEL); |
24613191 | 16406 | + if (!this) { |
4e97e4e9 | 16407 | + printk(KERN_WARNING "TuxOnIce: Failed to allocate memory for " |
24613191 | 16408 | + "opening a bdev."); |
ad8f4a28 | 16409 | + blkdev_put(bdev); |
24613191 | 16410 | + return ERR_PTR(-ENOMEM); |
16411 | + } | |
16412 | + | |
4e97e4e9 | 16413 | + bdevs_opened[index] = this; |
24613191 | 16414 | + this->device = device; |
16415 | + this->bdev = bdev; | |
16416 | + | |
24613191 | 16417 | + return bdev; |
16418 | +} | |
16419 | + | |
4e97e4e9 | 16420 | +/** |
16421 | + * enable_swapfile: Swapon the user specified swapfile prior to hibernating. | |
16422 | + * | |
16423 | + * Activate the given swapfile if it wasn't already enabled. Remember whether | |
16424 | + * we really did swapon it for swapoffing later. | |
24613191 | 16425 | + */ |
4e97e4e9 | 16426 | +static void enable_swapfile(void) |
24613191 | 16427 | +{ |
16428 | + int activateswapresult = -EINVAL; | |
16429 | + | |
24613191 | 16430 | + if (swapfilename[0]) { |
16431 | + /* Attempt to swap on with maximum priority */ | |
16432 | + activateswapresult = sys_swapon(swapfilename, 0xFFFF); | |
4e97e4e9 | 16433 | + if (activateswapresult && activateswapresult != -EBUSY) |
16434 | + printk("TuxOnIce: The swapfile/partition specified by " | |
16435 | + "/sys/power/tuxonice/swap/swapfile " | |
24613191 | 16436 | + "(%s) could not be turned on (error %d). " |
16437 | + "Attempting to continue.\n", | |
16438 | + swapfilename, activateswapresult); | |
16439 | + if (!activateswapresult) | |
4e97e4e9 | 16440 | + toi_swapon_status = 1; |
24613191 | 16441 | + } |
24613191 | 16442 | +} |
16443 | + | |
4e97e4e9 | 16444 | +/** |
16445 | + * disable_swapfile: Swapoff any file swaponed at the start of the cycle. | |
16446 | + * | |
16447 | + * If we did successfully swapon a file at the start of the cycle, swapoff | |
16448 | + * it now (finishing up). | |
16449 | + */ | |
16450 | +static void disable_swapfile(void) | |
24613191 | 16451 | +{ |
4e97e4e9 | 16452 | + if (!toi_swapon_status) |
16453 | + return; | |
24613191 | 16454 | + |
4e97e4e9 | 16455 | + sys_swapoff(swapfilename); |
16456 | + toi_swapon_status = 0; | |
24613191 | 16457 | +} |
16458 | + | |
4e97e4e9 | 16459 | +/** |
16460 | + * try_to_parse_resume_device: Try to parse resume= | |
16461 | + * | |
16462 | + * Any "swap:" has been stripped away and we just have the path to deal with. | |
16463 | + * We attempt to do name_to_dev_t, open and stat the file. Having opened the | |
16464 | + * file, get the struct block_device * to match. | |
16465 | + */ | |
24613191 | 16466 | +static int try_to_parse_resume_device(char *commandline, int quiet) |
16467 | +{ | |
16468 | + struct kstat stat; | |
16469 | + int error = 0; | |
16470 | + | |
16471 | + resume_swap_dev_t = name_to_dev_t(commandline); | |
16472 | + | |
16473 | + if (!resume_swap_dev_t) { | |
ad8f4a28 AM |
16474 | + struct file *file = filp_open(commandline, |
16475 | + O_RDONLY|O_LARGEFILE, 0); | |
24613191 | 16476 | + |
16477 | + if (!IS_ERR(file) && file) { | |
16478 | + vfs_getattr(file->f_vfsmnt, file->f_dentry, &stat); | |
16479 | + filp_close(file, NULL); | |
16480 | + } else | |
16481 | + error = vfs_stat(commandline, &stat); | |
16482 | + if (!error) | |
16483 | + resume_swap_dev_t = stat.rdev; | |
16484 | + } | |
16485 | + | |
16486 | + if (!resume_swap_dev_t) { | |
16487 | + if (quiet) | |
16488 | + return 1; | |
16489 | + | |
4e97e4e9 | 16490 | + if (test_toi_state(TOI_TRYING_TO_RESUME)) |
16491 | + toi_early_boot_message(1, TOI_CONTINUE_REQ, | |
24613191 | 16492 | + "Failed to translate \"%s\" into a device id.\n", |
16493 | + commandline); | |
16494 | + else | |
4e97e4e9 | 16495 | + printk("TuxOnIce: Can't translate \"%s\" into a device " |
24613191 | 16496 | + "id yet.\n", commandline); |
16497 | + return 1; | |
16498 | + } | |
16499 | + | |
16500 | + resume_block_device = open_bdev(MAX_SWAPFILES, resume_swap_dev_t, 0); | |
16501 | + if (IS_ERR(resume_block_device)) { | |
16502 | + if (!quiet) | |
4e97e4e9 | 16503 | + toi_early_boot_message(1, TOI_CONTINUE_REQ, |
24613191 | 16504 | + "Failed to get access to \"%s\", where" |
16505 | + " the swap header should be found.", | |
16506 | + commandline); | |
16507 | + return 1; | |
16508 | + } | |
ad8f4a28 | 16509 | + |
24613191 | 16510 | + return 0; |
16511 | +} | |
16512 | + | |
ad8f4a28 | 16513 | +/* |
24613191 | 16514 | + * If we have read part of the image, we might have filled memory with |
16515 | + * data that should be zeroed out. | |
16516 | + */ | |
4e97e4e9 | 16517 | +static void toi_swap_noresume_reset(void) |
24613191 | 16518 | +{ |
7f9d2ee0 | 16519 | + toi_bio_ops.rw_cleanup(READ); |
24613191 | 16520 | + memset((char *) &devinfo, 0, sizeof(devinfo)); |
24613191 | 16521 | +} |
16522 | + | |
7f9d2ee0 | 16523 | +static int get_current_signature(void) |
24613191 | 16524 | +{ |
7f9d2ee0 | 16525 | + int result; |
24613191 | 16526 | + |
7f9d2ee0 | 16527 | + if (current_signature_page) |
24613191 | 16528 | + return 0; |
24613191 | 16529 | + |
f3e0dcc9 PS |
16530 | + current_signature_page = (char *) toi_get_zeroed_page(38, |
16531 | + TOI_ATOMIC_GFP); | |
7f9d2ee0 | 16532 | + if (!current_signature_page) |
16533 | + return -ENOMEM; | |
ad8f4a28 | 16534 | + |
7f9d2ee0 | 16535 | + result = toi_bio_ops.bdev_page_io(READ, resume_block_device, |
16536 | + resume_firstblock, virt_to_page(current_signature_page)); | |
ad8f4a28 | 16537 | + |
7f9d2ee0 | 16538 | + return result; |
16539 | +} | |
24613191 | 16540 | + |
7f9d2ee0 | 16541 | +static int parse_signature(void) |
16542 | +{ | |
16543 | + union p_diskpage swap_header_page; | |
f3e0dcc9 | 16544 | + struct sig_data *sig; |
7f9d2ee0 | 16545 | + int type; |
16546 | + char *swap_header; | |
16547 | + const char *sigs[] = { | |
16548 | + "SWAP-SPACE", "SWAPSPACE2", "S1SUSP", "S2SUSP", "S1SUSPEND" | |
16549 | + }; | |
16550 | + | |
16551 | + if (!current_signature_page) { | |
16552 | + int result = get_current_signature(); | |
16553 | + | |
16554 | + if (result) | |
16555 | + return result; | |
24613191 | 16556 | + } |
16557 | + | |
7f9d2ee0 | 16558 | + swap_header_page = (union p_diskpage) current_signature_page; |
f3e0dcc9 | 16559 | + sig = (struct sig_data *) current_signature_page; |
7f9d2ee0 | 16560 | + swap_header = swap_header_page.pointer->swh.magic.magic; |
16561 | + | |
16562 | + for (type = 0; type < 5; type++) | |
16563 | + if (!memcmp(sigs[type], swap_header, strlen(sigs[type]))) | |
16564 | + return type; | |
16565 | + | |
f3e0dcc9 | 16566 | + if (memcmp(tuxonice_signature, swap_header, sizeof(tuxonice_signature))) |
7f9d2ee0 | 16567 | + return -1; |
16568 | + | |
16569 | + header_dev_t = sig->device; | |
16570 | + clear_toi_state(TOI_RESUMED_BEFORE); | |
16571 | + if (sig->resume_attempted) | |
16572 | + set_toi_state(TOI_RESUMED_BEFORE); | |
16573 | + headerblock = sig->sector; | |
16574 | + | |
16575 | + return 10; | |
16576 | +} | |
16577 | + | |
16578 | +static void forget_signatures(void) | |
16579 | +{ | |
16580 | + if (current_signature_page) { | |
16581 | + toi_free_page(38, (unsigned long) current_signature_page); | |
16582 | + current_signature_page = NULL; | |
16583 | + } | |
24613191 | 16584 | +} |
16585 | + | |
16586 | +/* | |
7f9d2ee0 | 16587 | + * write_modified_signature |
16588 | + * | |
16589 | + * Write a (potentially) modified signature page without forgetting the | |
16590 | + * original contents. | |
24613191 | 16591 | + */ |
7f9d2ee0 | 16592 | +static int write_modified_signature(int modification) |
24613191 | 16593 | +{ |
7f9d2ee0 | 16594 | + union p_diskpage swap_header_page; |
16595 | + struct swap_info_struct *si; | |
16596 | + int result; | |
16597 | + char *orig_sig; | |
24613191 | 16598 | + |
7f9d2ee0 | 16599 | + /* In case we haven't already */ |
16600 | + result = get_current_signature(); | |
16601 | + | |
16602 | + if (result) | |
16603 | + return result; | |
24613191 | 16604 | + |
7f9d2ee0 | 16605 | + swap_header_page.address = toi_get_zeroed_page(38, TOI_ATOMIC_GFP); |
24613191 | 16606 | + |
7f9d2ee0 | 16607 | + if (!swap_header_page.address) |
16608 | + return -ENOMEM; | |
16609 | + | |
16610 | + memcpy(swap_header_page.ptr, current_signature_page, PAGE_SIZE); | |
16611 | + | |
16612 | + switch (modification) { | |
16613 | + case IMAGE_SIGNATURE: | |
16614 | + | |
16615 | + memcpy(no_image_signature_contents, swap_header_page.ptr, | |
16616 | + sizeof(no_image_signature_contents)); | |
16617 | + | |
16618 | + /* Get the details of the header first page. */ | |
16619 | + toi_extent_state_goto_start(&toi_writer_posn); | |
16620 | + toi_bio_ops.forward_one_page(1); | |
16621 | + | |
16622 | + si = get_swap_info_struct(toi_writer_posn.current_chain); | |
16623 | + | |
16624 | + /* Prepare the signature */ | |
f3e0dcc9 PS |
16625 | + swap_header_page.pointer->sig_data.device = si->bdev->bd_dev; |
16626 | + swap_header_page.pointer->sig_data.sector = | |
7f9d2ee0 | 16627 | + toi_writer_posn.current_offset; |
f3e0dcc9 PS |
16628 | + swap_header_page.pointer->sig_data.resume_attempted = 0; |
16629 | + swap_header_page.pointer->sig_data.orig_sig_type = | |
7f9d2ee0 | 16630 | + parse_signature(); |
16631 | + | |
16632 | + memcpy(swap_header_page.pointer->swh.magic.magic, | |
16633 | + tuxonice_signature, sizeof(tuxonice_signature)); | |
16634 | + | |
16635 | + break; | |
16636 | + case NO_IMAGE_SIGNATURE: | |
f3e0dcc9 | 16637 | + if (!swap_header_page.pointer->sig_data.orig_sig_type) |
7f9d2ee0 | 16638 | + orig_sig = "SWAP-SPACE"; |
16639 | + else | |
16640 | + orig_sig = "SWAPSPACE2"; | |
16641 | + | |
16642 | + memcpy(swap_header_page.pointer->swh.magic.magic, orig_sig, 10); | |
16643 | + memcpy(swap_header_page.ptr, no_image_signature_contents, | |
16644 | + sizeof(no_image_signature_contents)); | |
16645 | + break; | |
16646 | + case TRIED_RESUME: | |
f3e0dcc9 | 16647 | + swap_header_page.pointer->sig_data.resume_attempted = 1; |
7f9d2ee0 | 16648 | + break; |
16649 | + case NO_TRIED_RESUME: | |
f3e0dcc9 | 16650 | + swap_header_page.pointer->sig_data.resume_attempted = 0; |
7f9d2ee0 | 16651 | + break; |
24613191 | 16652 | + } |
16653 | + | |
7f9d2ee0 | 16654 | + result = toi_bio_ops.bdev_page_io(WRITE, resume_block_device, |
16655 | + resume_firstblock, virt_to_page(swap_header_page.address)); | |
16656 | + | |
f3e0dcc9 PS |
16657 | + memcpy(current_signature_page, swap_header_page.ptr, PAGE_SIZE); |
16658 | + | |
7f9d2ee0 | 16659 | + toi_free_page(38, swap_header_page.address); |
24613191 | 16660 | + |
7f9d2ee0 | 16661 | + return result; |
16662 | +} | |
24613191 | 16663 | + |
f3e0dcc9 PS |
16664 | +/* |
16665 | + * apply_header_reservation | |
16666 | + * | |
16667 | + * Use 0 (READ) to forward_one_page so it doesn't complain if we haven't | |
16668 | + * allocated storage yet. | |
16669 | + */ | |
7f9d2ee0 | 16670 | +static int apply_header_reservation(void) |
24613191 | 16671 | +{ |
16672 | + int i; | |
16673 | + | |
4e97e4e9 | 16674 | + toi_extent_state_goto_start(&toi_writer_posn); |
f3e0dcc9 | 16675 | + toi_bio_ops.forward_one_page(0); /* To first page */ |
ad8f4a28 | 16676 | + |
f3e0dcc9 PS |
16677 | + for (i = 0; i < header_pages_reserved; i++) |
16678 | + if (toi_bio_ops.forward_one_page(0)) | |
24613191 | 16679 | + return -ENOSPC; |
24613191 | 16680 | + |
24613191 | 16681 | + /* The end of header pages will be the start of pageset 2; |
16682 | + * we are now sitting on the first pageset2 page. */ | |
7f9d2ee0 | 16683 | + toi_extent_state_save(&toi_writer_posn, &toi_writer_posn_save[2]); |
24613191 | 16684 | + return 0; |
16685 | +} | |
16686 | + | |
7f9d2ee0 | 16687 | +static void toi_swap_reserve_header_space(int request) |
16688 | +{ | |
16689 | + header_pages_reserved = (long) request; | |
16690 | + | |
16691 | + /* If we've already allocated storage (hence ignoring return value): */ | |
16692 | + apply_header_reservation(); | |
16693 | +} | |
16694 | + | |
4e97e4e9 | 16695 | +static void free_block_chains(void) |
24613191 | 16696 | +{ |
4e97e4e9 | 16697 | + int i; |
24613191 | 16698 | + |
16699 | + for (i = 0; i < MAX_SWAPFILES; i++) | |
16700 | + if (block_chain[i].first) | |
4e97e4e9 | 16701 | + toi_put_extent_chain(&block_chain[i]); |
16702 | +} | |
16703 | + | |
f3e0dcc9 | 16704 | +static int add_blocks_to_extent_chain(int chain, int start, int end) |
7f9d2ee0 | 16705 | +{ |
16706 | + if (test_action_state(TOI_TEST_BIO)) | |
16707 | + printk(KERN_INFO "Adding extent chain %d %d-%d.\n", chain, | |
f3e0dcc9 PS |
16708 | + start << devinfo[chain].bmap_shift, |
16709 | + end << devinfo[chain].bmap_shift); | |
7f9d2ee0 | 16710 | + |
f3e0dcc9 | 16711 | + if (toi_add_to_extent_chain(&block_chain[chain], start, end)) { |
7f9d2ee0 | 16712 | + free_block_chains(); |
16713 | + return -ENOMEM; | |
16714 | + } | |
16715 | + | |
16716 | + return 0; | |
16717 | +} | |
16718 | + | |
16719 | + | |
4e97e4e9 | 16720 | +static int get_main_pool_phys_params(void) |
16721 | +{ | |
f3e0dcc9 | 16722 | + struct hibernate_extent *extentpointer = NULL; |
4e97e4e9 | 16723 | + unsigned long address; |
16724 | + int extent_min = -1, extent_max = -1, last_chain = -1; | |
16725 | + | |
16726 | + free_block_chains(); | |
24613191 | 16727 | + |
4e97e4e9 | 16728 | + toi_extent_for_each(&swapextents, extentpointer, address) { |
f3e0dcc9 | 16729 | + swp_entry_t swap_address = (swp_entry_t) { address }; |
24613191 | 16730 | + pgoff_t offset = swp_offset(swap_address); |
16731 | + unsigned swapfilenum = swp_type(swap_address); | |
ad8f4a28 AM |
16732 | + struct swap_info_struct *sis = |
16733 | + get_swap_info_struct(swapfilenum); | |
24613191 | 16734 | + sector_t new_sector = map_swap_page(sis, offset); |
16735 | + | |
16736 | + if ((new_sector == extent_max + 1) && | |
ad8f4a28 | 16737 | + (last_chain == swapfilenum)) { |
24613191 | 16738 | + extent_max++; |
ad8f4a28 AM |
16739 | + continue; |
16740 | + } | |
16741 | + | |
7f9d2ee0 | 16742 | + if (extent_min > -1 && add_blocks_to_extent_chain(last_chain, |
16743 | + extent_min, extent_max)) | |
16744 | + return -ENOMEM; | |
16745 | + | |
ad8f4a28 AM |
16746 | + extent_min = extent_max = new_sector; |
16747 | + last_chain = swapfilenum; | |
24613191 | 16748 | + } |
16749 | + | |
7f9d2ee0 | 16750 | + if (extent_min > -1 && add_blocks_to_extent_chain(last_chain, |
16751 | + extent_min, extent_max)) | |
4e97e4e9 | 16752 | + return -ENOMEM; |
24613191 | 16753 | + |
7f9d2ee0 | 16754 | + return apply_header_reservation(); |
16755 | +} | |
16756 | + | |
16757 | +static long raw_to_real(long raw) | |
16758 | +{ | |
16759 | + long result; | |
16760 | + | |
16761 | + result = raw - (raw * (sizeof(unsigned long) + sizeof(int)) + | |
16762 | + (PAGE_SIZE + sizeof(unsigned long) + sizeof(int) + 1)) / | |
16763 | + (PAGE_SIZE + sizeof(unsigned long) + sizeof(int)); | |
16764 | + | |
16765 | + return result < 0 ? 0 : result; | |
24613191 | 16766 | +} |
16767 | + | |
4e97e4e9 | 16768 | +static int toi_swap_storage_allocated(void) |
24613191 | 16769 | +{ |
7f9d2ee0 | 16770 | + return (int) raw_to_real(swap_pages_allocated - header_pages_reserved); |
24613191 | 16771 | +} |
16772 | + | |
7f9d2ee0 | 16773 | +/* |
16774 | + * We can't just remember the value from allocation time, because other | |
16775 | + * processes might have allocated swap in the mean time. | |
16776 | + */ | |
4e97e4e9 | 16777 | +static int toi_swap_storage_available(void) |
24613191 | 16778 | +{ |
16779 | + si_swapinfo(&swapinfo); | |
7f9d2ee0 | 16780 | + return (int) raw_to_real((long) swapinfo.freeswap + |
16781 | + swap_pages_allocated - header_pages_reserved); | |
24613191 | 16782 | +} |
16783 | + | |
4e97e4e9 | 16784 | +static int toi_swap_initialise(int starting_cycle) |
24613191 | 16785 | +{ |
16786 | + if (!starting_cycle) | |
16787 | + return 0; | |
16788 | + | |
16789 | + enable_swapfile(); | |
16790 | + | |
16791 | + if (resume_swap_dev_t && !resume_block_device && | |
16792 | + IS_ERR(resume_block_device = | |
ad8f4a28 | 16793 | + open_bdev(MAX_SWAPFILES, resume_swap_dev_t, 1))) |
24613191 | 16794 | + return 1; |
16795 | + | |
16796 | + return 0; | |
16797 | +} | |
16798 | + | |
4e97e4e9 | 16799 | +static void toi_swap_cleanup(int ending_cycle) |
24613191 | 16800 | +{ |
16801 | + if (ending_cycle) | |
16802 | + disable_swapfile(); | |
ad8f4a28 | 16803 | + |
24613191 | 16804 | + close_bdevs(); |
7f9d2ee0 | 16805 | + |
16806 | + forget_signatures(); | |
24613191 | 16807 | +} |
16808 | + | |
4e97e4e9 | 16809 | +static int toi_swap_release_storage(void) |
24613191 | 16810 | +{ |
4e97e4e9 | 16811 | + if (test_action_state(TOI_KEEP_IMAGE) && |
16812 | + test_toi_state(TOI_NOW_RESUMING)) | |
24613191 | 16813 | + return 0; |
16814 | + | |
7f9d2ee0 | 16815 | + header_pages_reserved = 0; |
16816 | + swap_pages_allocated = 0; | |
24613191 | 16817 | + |
16818 | + if (swapextents.first) { | |
16819 | + /* Free swap entries */ | |
f3e0dcc9 | 16820 | + struct hibernate_extent *extentpointer; |
24613191 | 16821 | + unsigned long extentvalue; |
ad8f4a28 | 16822 | + toi_extent_for_each(&swapextents, extentpointer, |
e8d0ad9d | 16823 | + extentvalue) |
f3e0dcc9 | 16824 | + swap_free((swp_entry_t) { extentvalue }); |
24613191 | 16825 | + |
4e97e4e9 | 16826 | + toi_put_extent_chain(&swapextents); |
24613191 | 16827 | + |
4e97e4e9 | 16828 | + free_block_chains(); |
24613191 | 16829 | + } |
16830 | + | |
16831 | + return 0; | |
16832 | +} | |
16833 | + | |
e8d0ad9d | 16834 | +static void free_swap_range(unsigned long min, unsigned long max) |
16835 | +{ | |
16836 | + int j; | |
16837 | + | |
4e97e4e9 | 16838 | + for (j = min; j <= max; j++) |
f3e0dcc9 | 16839 | + swap_free((swp_entry_t) { j }); |
e8d0ad9d | 16840 | +} |
16841 | + | |
ad8f4a28 | 16842 | +/* |
24613191 | 16843 | + * Round robin allocation (where swap storage has the same priority). |
16844 | + * could make this very inefficient, so we track extents allocated on | |
7f9d2ee0 | 16845 | + * a per-swapfile basis. |
16846 | + * | |
16847 | + * We ignore here the fact that some space is for the header and doesn't | |
16848 | + * have the overhead. It will only rarely make a 1 page difference. | |
24613191 | 16849 | + */ |
7f9d2ee0 | 16850 | +static int toi_swap_allocate_storage(int request) |
24613191 | 16851 | +{ |
4e97e4e9 | 16852 | + int i, result = 0, to_add[MAX_SWAPFILES], pages_to_get, extra_pages, |
16853 | + gotten = 0; | |
24613191 | 16854 | + unsigned long extent_min[MAX_SWAPFILES], extent_max[MAX_SWAPFILES]; |
16855 | + | |
7f9d2ee0 | 16856 | + extra_pages = DIV_ROUND_UP(request * (sizeof(unsigned long) |
24613191 | 16857 | + + sizeof(int)), PAGE_SIZE); |
7f9d2ee0 | 16858 | + pages_to_get = request + extra_pages - swapextents.size; |
24613191 | 16859 | + |
16860 | + if (pages_to_get < 1) | |
16861 | + return 0; | |
16862 | + | |
ad8f4a28 | 16863 | + for (i = 0; i < MAX_SWAPFILES; i++) { |
24613191 | 16864 | + struct swap_info_struct *si = get_swap_info_struct(i); |
4e97e4e9 | 16865 | + to_add[i] = 0; |
16866 | + if (!si->bdev) | |
16867 | + continue; | |
16868 | + devinfo[i].bdev = si->bdev; | |
16869 | + devinfo[i].dev_t = si->bdev->bd_dev; | |
24613191 | 16870 | + devinfo[i].bmap_shift = 3; |
16871 | + devinfo[i].blocks_per_page = 1; | |
24613191 | 16872 | + } |
16873 | + | |
ad8f4a28 | 16874 | + for (i = 0; i < pages_to_get; i++) { |
24613191 | 16875 | + swp_entry_t entry; |
16876 | + unsigned long new_value; | |
16877 | + unsigned swapfilenum; | |
16878 | + | |
16879 | + entry = get_swap_page(); | |
e8d0ad9d | 16880 | + if (!entry.val) |
24613191 | 16881 | + break; |
24613191 | 16882 | + |
16883 | + swapfilenum = swp_type(entry); | |
f3e0dcc9 | 16884 | + new_value = entry.val; |
e8d0ad9d | 16885 | + |
4e97e4e9 | 16886 | + if (!to_add[swapfilenum]) { |
16887 | + to_add[swapfilenum] = 1; | |
e8d0ad9d | 16888 | + extent_min[swapfilenum] = new_value; |
16889 | + extent_max[swapfilenum] = new_value; | |
16890 | + gotten++; | |
16891 | + continue; | |
16892 | + } | |
16893 | + | |
16894 | + if (new_value == extent_max[swapfilenum] + 1) { | |
16895 | + extent_max[swapfilenum]++; | |
16896 | + gotten++; | |
16897 | + continue; | |
16898 | + } | |
16899 | + | |
4e97e4e9 | 16900 | + if (toi_add_to_extent_chain(&swapextents, |
24613191 | 16901 | + extent_min[swapfilenum], |
e8d0ad9d | 16902 | + extent_max[swapfilenum])) { |
ad8f4a28 AM |
16903 | + printk(KERN_INFO "Failed to allocate extent for " |
16904 | + "%lu-%lu.\n", extent_min[swapfilenum], | |
16905 | + extent_max[swapfilenum]); | |
e8d0ad9d | 16906 | + free_swap_range(extent_min[swapfilenum], |
24613191 | 16907 | + extent_max[swapfilenum]); |
e8d0ad9d | 16908 | + swap_free(entry); |
16909 | + gotten -= (extent_max[swapfilenum] - | |
4e97e4e9 | 16910 | + extent_min[swapfilenum] + 1); |
ad8f4a28 AM |
16911 | + /* Don't try to add again below */ |
16912 | + to_add[swapfilenum] = 0; | |
e8d0ad9d | 16913 | + break; |
16914 | + } else { | |
16915 | + extent_min[swapfilenum] = new_value; | |
16916 | + extent_max[swapfilenum] = new_value; | |
16917 | + gotten++; | |
24613191 | 16918 | + } |
16919 | + } | |
16920 | + | |
4e97e4e9 | 16921 | + for (i = 0; i < MAX_SWAPFILES; i++) { |
16922 | + if (!to_add[i] || !toi_add_to_extent_chain(&swapextents, | |
16923 | + extent_min[i], extent_max[i])) | |
16924 | + continue; | |
16925 | + | |
16926 | + free_swap_range(extent_min[i], extent_max[i]); | |
16927 | + gotten -= (extent_max[i] - extent_min[i] + 1); | |
16928 | + break; | |
16929 | + } | |
24613191 | 16930 | + |
e8d0ad9d | 16931 | + if (gotten < pages_to_get) |
16932 | + result = -ENOSPC; | |
16933 | + | |
7f9d2ee0 | 16934 | + swap_pages_allocated += (long) gotten; |
4e97e4e9 | 16935 | + |
16936 | + return result ? result : get_main_pool_phys_params(); | |
24613191 | 16937 | +} |
16938 | + | |
4e97e4e9 | 16939 | +static int toi_swap_write_header_init(void) |
24613191 | 16940 | +{ |
16941 | + int i, result; | |
16942 | + struct swap_info_struct *si; | |
16943 | + | |
7f9d2ee0 | 16944 | + toi_bio_ops.rw_init(WRITE, 0); |
4e97e4e9 | 16945 | + toi_writer_buffer_posn = 0; |
24613191 | 16946 | + |
16947 | + /* Info needed to bootstrap goes at the start of the header. | |
16948 | + * First we save the positions and devinfo, including the number | |
16949 | + * of header pages. Then we save the structs containing data needed | |
16950 | + * for reading the header pages back. | |
16951 | + * Note that even if header pages take more than one page, when we | |
16952 | + * read back the info, we will have restored the location of the | |
16953 | + * next header page by the time we go to use it. | |
16954 | + */ | |
16955 | + | |
7f9d2ee0 | 16956 | + result = toi_bio_ops.rw_header_chunk(WRITE, &toi_swapops, |
16957 | + (char *) &no_image_signature_contents, | |
f3e0dcc9 | 16958 | + sizeof(struct sig_data)); |
7f9d2ee0 | 16959 | + |
16960 | + if (result) | |
16961 | + return result; | |
16962 | + | |
24613191 | 16963 | + /* Forward one page will be done prior to the read */ |
16964 | + for (i = 0; i < MAX_SWAPFILES; i++) { | |
16965 | + si = get_swap_info_struct(i); | |
16966 | + if (si->swap_file) | |
16967 | + devinfo[i].dev_t = si->bdev->bd_dev; | |
16968 | + else | |
16969 | + devinfo[i].dev_t = (dev_t) 0; | |
16970 | + } | |
16971 | + | |
ad8f4a28 AM |
16972 | + result = toi_bio_ops.rw_header_chunk(WRITE, &toi_swapops, |
16973 | + (char *) &toi_writer_posn_save, | |
16974 | + sizeof(toi_writer_posn_save)); | |
16975 | + | |
16976 | + if (result) | |
24613191 | 16977 | + return result; |
16978 | + | |
ad8f4a28 AM |
16979 | + result = toi_bio_ops.rw_header_chunk(WRITE, &toi_swapops, |
16980 | + (char *) &devinfo, sizeof(devinfo)); | |
16981 | + | |
16982 | + if (result) | |
24613191 | 16983 | + return result; |
16984 | + | |
ad8f4a28 | 16985 | + for (i = 0; i < MAX_SWAPFILES; i++) |
4e97e4e9 | 16986 | + toi_serialise_extent_chain(&toi_swapops, &block_chain[i]); |
24613191 | 16987 | + |
16988 | + return 0; | |
16989 | +} | |
16990 | + | |
4e97e4e9 | 16991 | +static int toi_swap_write_header_cleanup(void) |
24613191 | 16992 | +{ |
24613191 | 16993 | + /* Write any unsaved data */ |
4e97e4e9 | 16994 | + if (toi_writer_buffer_posn) |
16995 | + toi_bio_ops.write_header_chunk_finish(); | |
24613191 | 16996 | + |
4e97e4e9 | 16997 | + toi_bio_ops.finish_all_io(); |
24613191 | 16998 | + |
7f9d2ee0 | 16999 | + /* Set signature to save we have an image */ |
17000 | + return write_modified_signature(IMAGE_SIGNATURE); | |
24613191 | 17001 | +} |
17002 | + | |
17003 | +/* ------------------------- HEADER READING ------------------------- */ | |
17004 | + | |
17005 | +/* | |
17006 | + * read_header_init() | |
ad8f4a28 | 17007 | + * |
24613191 | 17008 | + * Description: |
4e97e4e9 | 17009 | + * 1. Attempt to read the device specified with resume=. |
24613191 | 17010 | + * 2. Check the contents of the swap header for our signature. |
17011 | + * 3. Warn, ignore, reset and/or continue as appropriate. | |
4e97e4e9 | 17012 | + * 4. If continuing, read the toi_swap configuration section |
24613191 | 17013 | + * of the header and set up block device info so we can read |
17014 | + * the rest of the header & image. | |
17015 | + * | |
17016 | + * Returns: | |
17017 | + * May not return if user choose to reboot at a warning. | |
17018 | + * -EINVAL if cannot resume at this time. Booting should continue | |
17019 | + * normally. | |
17020 | + */ | |
17021 | + | |
4e97e4e9 | 17022 | +static int toi_swap_read_header_init(void) |
24613191 | 17023 | +{ |
17024 | + int i, result = 0; | |
7f9d2ee0 | 17025 | + toi_writer_buffer_posn = 0; |
24613191 | 17026 | + |
24613191 | 17027 | + if (!header_dev_t) { |
ad8f4a28 | 17028 | + printk(KERN_INFO "read_header_init called when we haven't " |
24613191 | 17029 | + "verified there is an image!\n"); |
17030 | + return -EINVAL; | |
17031 | + } | |
17032 | + | |
ad8f4a28 AM |
17033 | + /* |
17034 | + * If the header is not on the resume_swap_dev_t, get the resume device | |
17035 | + * first. | |
24613191 | 17036 | + */ |
17037 | + if (header_dev_t != resume_swap_dev_t) { | |
17038 | + header_block_device = open_bdev(MAX_SWAPFILES + 1, | |
17039 | + header_dev_t, 1); | |
17040 | + | |
17041 | + if (IS_ERR(header_block_device)) | |
17042 | + return PTR_ERR(header_block_device); | |
17043 | + } else | |
17044 | + header_block_device = resume_block_device; | |
17045 | + | |
7f9d2ee0 | 17046 | + toi_bio_ops.read_header_init(); |
17047 | + | |
ad8f4a28 | 17048 | + /* |
4e97e4e9 | 17049 | + * Read toi_swap configuration. |
24613191 | 17050 | + * Headerblock size taken into account already. |
17051 | + */ | |
7f9d2ee0 | 17052 | + result = toi_bio_ops.bdev_page_io(READ, header_block_device, |
24613191 | 17053 | + headerblock << 3, |
4e97e4e9 | 17054 | + virt_to_page((unsigned long) toi_writer_buffer)); |
7f9d2ee0 | 17055 | + if (result) |
17056 | + return result; | |
17057 | + | |
17058 | + memcpy(&no_image_signature_contents, toi_writer_buffer, | |
17059 | + sizeof(no_image_signature_contents)); | |
24613191 | 17060 | + |
7f9d2ee0 | 17061 | + toi_writer_buffer_posn = sizeof(no_image_signature_contents); |
24613191 | 17062 | + |
f3e0dcc9 PS |
17063 | + memcpy(&toi_writer_posn_save, toi_writer_buffer + |
17064 | + toi_writer_buffer_posn, sizeof(toi_writer_posn_save)); | |
7f9d2ee0 | 17065 | + |
17066 | + toi_writer_buffer_posn += sizeof(toi_writer_posn_save); | |
24613191 | 17067 | + |
ad8f4a28 AM |
17068 | + memcpy(&devinfo, toi_writer_buffer + toi_writer_buffer_posn, |
17069 | + sizeof(devinfo)); | |
24613191 | 17070 | + |
4e97e4e9 | 17071 | + toi_writer_buffer_posn += sizeof(devinfo); |
24613191 | 17072 | + |
17073 | + /* Restore device info */ | |
17074 | + for (i = 0; i < MAX_SWAPFILES; i++) { | |
17075 | + dev_t thisdevice = devinfo[i].dev_t; | |
1838f965 | 17076 | + struct block_device *bdev_result; |
24613191 | 17077 | + |
17078 | + devinfo[i].bdev = NULL; | |
17079 | + | |
17080 | + if (!thisdevice) | |
17081 | + continue; | |
17082 | + | |
17083 | + if (thisdevice == resume_swap_dev_t) { | |
17084 | + devinfo[i].bdev = resume_block_device; | |
24613191 | 17085 | + continue; |
17086 | + } | |
17087 | + | |
17088 | + if (thisdevice == header_dev_t) { | |
17089 | + devinfo[i].bdev = header_block_device; | |
24613191 | 17090 | + continue; |
17091 | + } | |
17092 | + | |
1838f965 | 17093 | + bdev_result = open_bdev(i, thisdevice, 1); |
17094 | + if (IS_ERR(bdev_result)) | |
17095 | + return PTR_ERR(bdev_result); | |
4e97e4e9 | 17096 | + devinfo[i].bdev = bdevs_opened[i]->bdev; |
24613191 | 17097 | + } |
17098 | + | |
4e97e4e9 | 17099 | + toi_extent_state_goto_start(&toi_writer_posn); |
17100 | + toi_bio_ops.set_extra_page_forward(); | |
24613191 | 17101 | + |
17102 | + for (i = 0; i < MAX_SWAPFILES && !result; i++) | |
4e97e4e9 | 17103 | + result = toi_load_extent_chain(&block_chain[i]); |
24613191 | 17104 | + |
17105 | + return result; | |
17106 | +} | |
17107 | + | |
4e97e4e9 | 17108 | +static int toi_swap_read_header_cleanup(void) |
24613191 | 17109 | +{ |
4e97e4e9 | 17110 | + toi_bio_ops.rw_cleanup(READ); |
24613191 | 17111 | + return 0; |
17112 | +} | |
17113 | + | |
24613191 | 17114 | +/* |
17115 | + * workspace_size | |
17116 | + * | |
17117 | + * Description: | |
17118 | + * Returns the number of bytes of RAM needed for this | |
17119 | + * code to do its work. (Used when calculating whether | |
4e97e4e9 | 17120 | + * we have enough memory to be able to hibernate & resume). |
24613191 | 17121 | + * |
17122 | + */ | |
4e97e4e9 | 17123 | +static int toi_swap_memory_needed(void) |
24613191 | 17124 | +{ |
17125 | + return 1; | |
17126 | +} | |
17127 | + | |
17128 | +/* | |
17129 | + * Print debug info | |
17130 | + * | |
17131 | + * Description: | |
17132 | + */ | |
4e97e4e9 | 17133 | +static int toi_swap_print_debug_stats(char *buffer, int size) |
24613191 | 17134 | +{ |
17135 | + int len = 0; | |
17136 | + struct sysinfo sysinfo; | |
ad8f4a28 | 17137 | + |
4e97e4e9 | 17138 | + if (toiActiveAllocator != &toi_swapops) { |
1838f965 | 17139 | + len = scnprintf(buffer, size, |
ad8f4a28 | 17140 | + "- SwapAllocator inactive.\n"); |
24613191 | 17141 | + return len; |
17142 | + } | |
17143 | + | |
1838f965 | 17144 | + len = scnprintf(buffer, size, "- SwapAllocator active.\n"); |
24613191 | 17145 | + if (swapfilename[0]) |
1838f965 | 17146 | + len += scnprintf(buffer+len, size-len, |
ad8f4a28 AM |
17147 | + " Attempting to automatically swapon: %s.\n", |
17148 | + swapfilename); | |
24613191 | 17149 | + |
17150 | + si_swapinfo(&sysinfo); | |
ad8f4a28 | 17151 | + |
1838f965 | 17152 | + len += scnprintf(buffer+len, size-len, |
17153 | + " Swap available for image: %d pages.\n", | |
4e97e4e9 | 17154 | + (int) sysinfo.freeswap + toi_swap_storage_allocated()); |
24613191 | 17155 | + |
17156 | + return len; | |
17157 | +} | |
17158 | + | |
17159 | +/* | |
17160 | + * Storage needed | |
17161 | + * | |
17162 | + * Returns amount of space in the swap header required | |
4e97e4e9 | 17163 | + * for the toi_swap's data. This ignores the links between |
24613191 | 17164 | + * pages, which we factor in when allocating the space. |
17165 | + * | |
17166 | + * We ensure the space is allocated, but actually save the | |
17167 | + * data from write_header_init and therefore don't also define a | |
17168 | + * save_config_info routine. | |
17169 | + */ | |
4e97e4e9 | 17170 | +static int toi_swap_storage_needed(void) |
24613191 | 17171 | +{ |
17172 | + int i, result; | |
4e97e4e9 | 17173 | + result = sizeof(toi_writer_posn_save) + sizeof(devinfo); |
24613191 | 17174 | + |
17175 | + for (i = 0; i < MAX_SWAPFILES; i++) { | |
17176 | + result += 3 * sizeof(int); | |
ad8f4a28 | 17177 | + result += (2 * sizeof(unsigned long) * |
24613191 | 17178 | + block_chain[i].num_extents); |
17179 | + } | |
17180 | + | |
17181 | + return result; | |
17182 | +} | |
17183 | + | |
17184 | +/* | |
17185 | + * Image_exists | |
7f9d2ee0 | 17186 | + * |
17187 | + * Returns -1 if don't know, otherwise 0 (no) or 1 (yes). | |
24613191 | 17188 | + */ |
7f9d2ee0 | 17189 | +static int toi_swap_image_exists(int quiet) |
24613191 | 17190 | +{ |
17191 | + int signature_found; | |
ad8f4a28 | 17192 | + |
24613191 | 17193 | + if (!resume_swap_dev_t) { |
7f9d2ee0 | 17194 | + if (!quiet) |
17195 | + printk(KERN_INFO "Not even trying to read header " | |
24613191 | 17196 | + "because resume_swap_dev_t is not set.\n"); |
7f9d2ee0 | 17197 | + return -1; |
24613191 | 17198 | + } |
ad8f4a28 | 17199 | + |
24613191 | 17200 | + if (!resume_block_device && |
17201 | + IS_ERR(resume_block_device = | |
17202 | + open_bdev(MAX_SWAPFILES, resume_swap_dev_t, 1))) { | |
7f9d2ee0 | 17203 | + if (!quiet) |
17204 | + printk(KERN_INFO "Failed to open resume dev_t (%x).\n", | |
ad8f4a28 | 17205 | + resume_swap_dev_t); |
7f9d2ee0 | 17206 | + return -1; |
24613191 | 17207 | + } |
17208 | + | |
7f9d2ee0 | 17209 | + signature_found = parse_signature(); |
24613191 | 17210 | + |
7f9d2ee0 | 17211 | + switch (signature_found) { |
17212 | + case -ENOMEM: | |
17213 | + return -1; | |
17214 | + case -1: | |
17215 | + if (!quiet) | |
17216 | + printk(KERN_ERR "TuxOnIce: Unable to find a signature." | |
17217 | + " Could you have moved a swap file?\n"); | |
17218 | + return -1; | |
17219 | + case 0: | |
17220 | + case 1: | |
17221 | + if (!quiet) | |
17222 | + printk(KERN_INFO "TuxOnIce: Normal swapspace found.\n"); | |
24613191 | 17223 | + return 0; |
7f9d2ee0 | 17224 | + case 2: |
17225 | + case 3: | |
17226 | + case 4: | |
17227 | + if (!quiet) | |
17228 | + printk(KERN_INFO "TuxOnIce: Detected another " | |
17229 | + "implementation's signature.\n"); | |
24613191 | 17230 | + return 0; |
7f9d2ee0 | 17231 | + case 10: |
17232 | + if (!quiet) | |
17233 | + printk(KERN_INFO "TuxOnIce: Detected TuxOnIce binary " | |
17234 | + "signature.\n"); | |
17235 | + return 1; | |
24613191 | 17236 | + } |
17237 | + | |
7f9d2ee0 | 17238 | + BUG(); |
17239 | + return 0; | |
17240 | +} | |
17241 | + | |
17242 | +/* toi_swap_remove_image | |
17243 | + * | |
17244 | + */ | |
17245 | +static int toi_swap_remove_image(void) | |
17246 | +{ | |
17247 | + /* | |
17248 | + * If nr_hibernates == 0, we must be booting, so no swap pages | |
17249 | + * will be recorded as used yet. | |
17250 | + */ | |
17251 | + | |
17252 | + if (nr_hibernates) | |
17253 | + toi_swap_release_storage(); | |
17254 | + | |
17255 | + /* | |
17256 | + * We don't do a sanity check here: we want to restore the swap | |
17257 | + * whatever version of kernel made the hibernate image. | |
17258 | + * | |
17259 | + * We need to write swap, but swap may not be enabled so | |
17260 | + * we write the device directly | |
17261 | + * | |
17262 | + * If we don't have an current_signature_page, we didn't | |
17263 | + * read an image header, so don't change anything. | |
17264 | + */ | |
17265 | + | |
17266 | + return toi_swap_image_exists(1) ? | |
17267 | + write_modified_signature(NO_IMAGE_SIGNATURE) : 0; | |
24613191 | 17268 | +} |
17269 | + | |
17270 | +/* | |
17271 | + * Mark resume attempted. | |
17272 | + * | |
7f9d2ee0 | 17273 | + * Record that we tried to resume from this image. We have already read the |
17274 | + * signature in. We just need to write the modified version. | |
24613191 | 17275 | + */ |
7f9d2ee0 | 17276 | +static int toi_swap_mark_resume_attempted(int mark) |
24613191 | 17277 | +{ |
24613191 | 17278 | + if (!resume_swap_dev_t) { |
ad8f4a28 | 17279 | + printk(KERN_INFO "Not even trying to record attempt at resuming" |
24613191 | 17280 | + " because resume_swap_dev_t is not set.\n"); |
7f9d2ee0 | 17281 | + return -ENODEV; |
24613191 | 17282 | + } |
ad8f4a28 | 17283 | + |
7f9d2ee0 | 17284 | + return write_modified_signature(mark ? TRIED_RESUME : NO_TRIED_RESUME); |
24613191 | 17285 | +} |
17286 | + | |
17287 | +/* | |
17288 | + * Parse Image Location | |
17289 | + * | |
4e97e4e9 | 17290 | + * Attempt to parse a resume= parameter. |
24613191 | 17291 | + * Swap Writer accepts: |
4e97e4e9 | 17292 | + * resume=swap:DEVNAME[:FIRSTBLOCK][@BLOCKSIZE] |
24613191 | 17293 | + * |
17294 | + * Where: | |
17295 | + * DEVNAME is convertable to a dev_t by name_to_dev_t | |
17296 | + * FIRSTBLOCK is the location of the first block in the swap file | |
17297 | + * (specifying for a swap partition is nonsensical but not prohibited). | |
17298 | + * Data is validated by attempting to read a swap header from the | |
4e97e4e9 | 17299 | + * location given. Failure will result in toi_swap refusing to |
24613191 | 17300 | + * save an image, and a reboot with correct parameters will be |
17301 | + * necessary. | |
17302 | + */ | |
4e97e4e9 | 17303 | +static int toi_swap_parse_sig_location(char *commandline, |
24613191 | 17304 | + int only_allocator, int quiet) |
17305 | +{ | |
4e97e4e9 | 17306 | + char *thischar, *devstart, *colon = NULL; |
24613191 | 17307 | + int signature_found, result = -EINVAL, temp_result; |
17308 | + | |
17309 | + if (strncmp(commandline, "swap:", 5)) { | |
ad8f4a28 | 17310 | + /* |
24613191 | 17311 | + * Failing swap:, we'll take a simple |
4e97e4e9 | 17312 | + * resume=/dev/hda2, but fall through to |
24613191 | 17313 | + * other allocators if /dev/ isn't matched. |
17314 | + */ | |
17315 | + if (strncmp(commandline, "/dev/", 5)) | |
17316 | + return 1; | |
17317 | + } else | |
17318 | + commandline += 5; | |
17319 | + | |
17320 | + devstart = thischar = commandline; | |
17321 | + while ((*thischar != ':') && (*thischar != '@') && | |
17322 | + ((thischar - commandline) < 250) && (*thischar)) | |
17323 | + thischar++; | |
17324 | + | |
17325 | + if (*thischar == ':') { | |
17326 | + colon = thischar; | |
17327 | + *colon = 0; | |
17328 | + thischar++; | |
17329 | + } | |
17330 | + | |
4e97e4e9 | 17331 | + while ((thischar - commandline) < 250 && *thischar) |
24613191 | 17332 | + thischar++; |
17333 | + | |
24613191 | 17334 | + if (colon) |
17335 | + resume_firstblock = (int) simple_strtoul(colon + 1, NULL, 0); | |
17336 | + else | |
17337 | + resume_firstblock = 0; | |
17338 | + | |
4e97e4e9 | 17339 | + clear_toi_state(TOI_CAN_HIBERNATE); |
17340 | + clear_toi_state(TOI_CAN_RESUME); | |
ad8f4a28 | 17341 | + |
24613191 | 17342 | + temp_result = try_to_parse_resume_device(devstart, quiet); |
17343 | + | |
17344 | + if (colon) | |
17345 | + *colon = ':'; | |
24613191 | 17346 | + |
17347 | + if (temp_result) | |
17348 | + return -EINVAL; | |
17349 | + | |
7f9d2ee0 | 17350 | + signature_found = toi_swap_image_exists(quiet); |
24613191 | 17351 | + |
17352 | + if (signature_found != -1) { | |
24613191 | 17353 | + result = 0; |
17354 | + | |
4e97e4e9 | 17355 | + toi_bio_ops.set_devinfo(devinfo); |
17356 | + toi_writer_posn.chains = &block_chain[0]; | |
17357 | + toi_writer_posn.num_chains = MAX_SWAPFILES; | |
17358 | + set_toi_state(TOI_CAN_HIBERNATE); | |
17359 | + set_toi_state(TOI_CAN_RESUME); | |
24613191 | 17360 | + } else |
17361 | + if (!quiet) | |
4e97e4e9 | 17362 | + printk(KERN_ERR "TuxOnIce: SwapAllocator: No swap " |
17363 | + "signature found at %s.\n", devstart); | |
24613191 | 17364 | + return result; |
24613191 | 17365 | +} |
17366 | + | |
17367 | +static int header_locations_read_sysfs(const char *page, int count) | |
17368 | +{ | |
17369 | + int i, printedpartitionsmessage = 0, len = 0, haveswap = 0; | |
1838f965 | 17370 | + struct inode *swapf = NULL; |
24613191 | 17371 | + int zone; |
4e97e4e9 | 17372 | + char *path_page = (char *) toi_get_free_page(10, GFP_KERNEL); |
24613191 | 17373 | + char *path, *output = (char *) page; |
17374 | + int path_len; | |
ad8f4a28 | 17375 | + |
24613191 | 17376 | + if (!page) |
17377 | + return 0; | |
17378 | + | |
17379 | + for (i = 0; i < MAX_SWAPFILES; i++) { | |
17380 | + struct swap_info_struct *si = get_swap_info_struct(i); | |
17381 | + | |
17382 | + if (!si->swap_file) | |
17383 | + continue; | |
ad8f4a28 | 17384 | + |
24613191 | 17385 | + if (S_ISBLK(si->swap_file->f_mapping->host->i_mode)) { |
17386 | + haveswap = 1; | |
17387 | + if (!printedpartitionsmessage) { | |
ad8f4a28 | 17388 | + len += sprintf(output + len, |
24613191 | 17389 | + "For swap partitions, simply use the " |
4e97e4e9 | 17390 | + "format: resume=swap:/dev/hda1.\n"); |
24613191 | 17391 | + printedpartitionsmessage = 1; |
17392 | + } | |
17393 | + } else { | |
17394 | + path_len = 0; | |
ad8f4a28 | 17395 | + |
7f9d2ee0 | 17396 | + path = d_path(&si->swap_file->f_path, path_page, |
17397 | + PAGE_SIZE); | |
24613191 | 17398 | + path_len = snprintf(path_page, 31, "%s", path); |
ad8f4a28 | 17399 | + |
24613191 | 17400 | + haveswap = 1; |
17401 | + swapf = si->swap_file->f_mapping->host; | |
ad8f4a28 AM |
17402 | + zone = bmap(swapf, 0); |
17403 | + if (!zone) { | |
17404 | + len += sprintf(output + len, | |
24613191 | 17405 | + "Swapfile %s has been corrupted. Reuse" |
17406 | + " mkswap on it and try again.\n", | |
17407 | + path_page); | |
17408 | + } else { | |
17409 | + char name_buffer[255]; | |
ad8f4a28 AM |
17410 | + len += sprintf(output + len, |
17411 | + "For swapfile `%s`," | |
4e97e4e9 | 17412 | + " use resume=swap:/dev/%s:0x%x.\n", |
24613191 | 17413 | + path_page, |
17414 | + bdevname(si->bdev, name_buffer), | |
17415 | + zone << (swapf->i_blkbits - 9)); | |
4e97e4e9 | 17416 | + } |
4e97e4e9 | 17417 | + } |
17418 | + } | |
ad8f4a28 | 17419 | + |
4e97e4e9 | 17420 | + if (!haveswap) |
17421 | + len = sprintf(output, "You need to turn on swap partitions " | |
17422 | + "before examining this file.\n"); | |
24613191 | 17423 | + |
ad8f4a28 | 17424 | + toi_free_page(10, (unsigned long) path_page); |
4e97e4e9 | 17425 | + return len; |
73c609d5 | 17426 | +} |
24613191 | 17427 | + |
4e97e4e9 | 17428 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 17429 | + SYSFS_STRING("swapfilename", SYSFS_RW, swapfilename, 255, 0, NULL), |
17430 | + SYSFS_CUSTOM("headerlocations", SYSFS_READONLY, | |
17431 | + header_locations_read_sysfs, NULL, 0, NULL), | |
17432 | + SYSFS_INT("enabled", SYSFS_RW, &toi_swapops.enabled, 0, 1, 0, | |
17433 | + attempt_to_parse_resume_device2), | |
4e97e4e9 | 17434 | +}; |
24613191 | 17435 | + |
4e97e4e9 | 17436 | +static struct toi_module_ops toi_swapops = { |
17437 | + .type = WRITER_MODULE, | |
17438 | + .name = "swap storage", | |
17439 | + .directory = "swap", | |
17440 | + .module = THIS_MODULE, | |
17441 | + .memory_needed = toi_swap_memory_needed, | |
17442 | + .print_debug_info = toi_swap_print_debug_stats, | |
17443 | + .storage_needed = toi_swap_storage_needed, | |
17444 | + .initialise = toi_swap_initialise, | |
17445 | + .cleanup = toi_swap_cleanup, | |
17446 | + | |
17447 | + .noresume_reset = toi_swap_noresume_reset, | |
17448 | + .storage_available = toi_swap_storage_available, | |
17449 | + .storage_allocated = toi_swap_storage_allocated, | |
17450 | + .release_storage = toi_swap_release_storage, | |
7f9d2ee0 | 17451 | + .reserve_header_space = toi_swap_reserve_header_space, |
4e97e4e9 | 17452 | + .allocate_storage = toi_swap_allocate_storage, |
17453 | + .image_exists = toi_swap_image_exists, | |
17454 | + .mark_resume_attempted = toi_swap_mark_resume_attempted, | |
17455 | + .write_header_init = toi_swap_write_header_init, | |
17456 | + .write_header_cleanup = toi_swap_write_header_cleanup, | |
17457 | + .read_header_init = toi_swap_read_header_init, | |
17458 | + .read_header_cleanup = toi_swap_read_header_cleanup, | |
17459 | + .remove_image = toi_swap_remove_image, | |
17460 | + .parse_sig_location = toi_swap_parse_sig_location, | |
24613191 | 17461 | + |
4e97e4e9 | 17462 | + .sysfs_data = sysfs_params, |
ad8f4a28 AM |
17463 | + .num_sysfs_entries = sizeof(sysfs_params) / |
17464 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 17465 | +}; |
24613191 | 17466 | + |
4e97e4e9 | 17467 | +/* ---- Registration ---- */ |
17468 | +static __init int toi_swap_load(void) | |
17469 | +{ | |
17470 | + toi_swapops.rw_init = toi_bio_ops.rw_init; | |
17471 | + toi_swapops.rw_cleanup = toi_bio_ops.rw_cleanup; | |
17472 | + toi_swapops.read_page = toi_bio_ops.read_page; | |
17473 | + toi_swapops.write_page = toi_bio_ops.write_page; | |
17474 | + toi_swapops.rw_header_chunk = toi_bio_ops.rw_header_chunk; | |
7f9d2ee0 | 17475 | + toi_swapops.rw_header_chunk_noreadahead = |
17476 | + toi_bio_ops.rw_header_chunk_noreadahead; | |
17477 | + toi_swapops.io_flusher = toi_bio_ops.io_flusher; | |
1838f965 | 17478 | + toi_swapops.update_throughput_throttle = toi_bio_ops.update_throughput_throttle; |
17479 | + toi_swapops.monitor_outstanding_io = toi_bio_ops.monitor_outstanding_io; | |
17480 | + toi_swapops.finish_all_io = toi_bio_ops.finish_all_io; | |
24613191 | 17481 | + |
4e97e4e9 | 17482 | + return toi_register_module(&toi_swapops); |
17483 | +} | |
24613191 | 17484 | + |
4e97e4e9 | 17485 | +#ifdef MODULE |
17486 | +static __exit void toi_swap_unload(void) | |
17487 | +{ | |
17488 | + toi_unregister_module(&toi_swapops); | |
73c609d5 | 17489 | +} |
24613191 | 17490 | + |
4e97e4e9 | 17491 | +module_init(toi_swap_load); |
17492 | +module_exit(toi_swap_unload); | |
17493 | +MODULE_LICENSE("GPL"); | |
17494 | +MODULE_AUTHOR("Nigel Cunningham"); | |
17495 | +MODULE_DESCRIPTION("TuxOnIce SwapAllocator"); | |
17496 | +#else | |
17497 | +late_initcall(toi_swap_load); | |
17498 | +#endif | |
17499 | diff --git a/kernel/power/tuxonice_sysfs.c b/kernel/power/tuxonice_sysfs.c | |
17500 | new file mode 100644 | |
1838f965 | 17501 | index 0000000..4f64dc7 |
4e97e4e9 | 17502 | --- /dev/null |
17503 | +++ b/kernel/power/tuxonice_sysfs.c | |
1838f965 | 17504 | @@ -0,0 +1,324 @@ |
4e97e4e9 | 17505 | +/* |
17506 | + * kernel/power/tuxonice_sysfs.c | |
17507 | + * | |
1838f965 | 17508 | + * Copyright (C) 2002-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 17509 | + * |
4e97e4e9 | 17510 | + * This file is released under the GPLv2. |
24613191 | 17511 | + * |
4e97e4e9 | 17512 | + * This file contains support for sysfs entries for tuning TuxOnIce. |
73c609d5 | 17513 | + * |
4e97e4e9 | 17514 | + * We have a generic handler that deals with the most common cases, and |
17515 | + * hooks for special handlers to use. | |
24613191 | 17516 | + */ |
24613191 | 17517 | + |
4e97e4e9 | 17518 | +#include <linux/suspend.h> |
17519 | +#include <linux/module.h> | |
24613191 | 17520 | + |
4e97e4e9 | 17521 | +#include "tuxonice_sysfs.h" |
17522 | +#include "tuxonice.h" | |
17523 | +#include "tuxonice_storage.h" | |
ad8f4a28 | 17524 | +#include "tuxonice_alloc.h" |
24613191 | 17525 | + |
ad8f4a28 | 17526 | +static int toi_sysfs_initialised; |
24613191 | 17527 | + |
4e97e4e9 | 17528 | +static void toi_initialise_sysfs(void); |
24613191 | 17529 | + |
4e97e4e9 | 17530 | +static struct toi_sysfs_data sysfs_params[]; |
24613191 | 17531 | + |
4e97e4e9 | 17532 | +#define to_sysfs_data(_attr) container_of(_attr, struct toi_sysfs_data, attr) |
24613191 | 17533 | + |
4e97e4e9 | 17534 | +static void toi_main_wrapper(void) |
24613191 | 17535 | +{ |
1838f965 | 17536 | + _toi_try_hibernate(); |
24613191 | 17537 | +} |
17538 | + | |
4e97e4e9 | 17539 | +static ssize_t toi_attr_show(struct kobject *kobj, struct attribute *attr, |
17540 | + char *page) | |
24613191 | 17541 | +{ |
4e97e4e9 | 17542 | + struct toi_sysfs_data *sysfs_data = to_sysfs_data(attr); |
17543 | + int len = 0; | |
1838f965 | 17544 | + int full_prep = sysfs_data->flags & SYSFS_NEEDS_SM_FOR_READ; |
24613191 | 17545 | + |
1838f965 | 17546 | + if (full_prep && toi_start_anything(0)) |
4e97e4e9 | 17547 | + return -EBUSY; |
17548 | + | |
17549 | + if (sysfs_data->flags & SYSFS_NEEDS_SM_FOR_READ) | |
17550 | + toi_prepare_usm(); | |
ad8f4a28 | 17551 | + |
4e97e4e9 | 17552 | + switch (sysfs_data->type) { |
ad8f4a28 AM |
17553 | + case TOI_SYSFS_DATA_CUSTOM: |
17554 | + len = (sysfs_data->data.special.read_sysfs) ? | |
17555 | + (sysfs_data->data.special.read_sysfs)(page, PAGE_SIZE) | |
17556 | + : 0; | |
17557 | + break; | |
17558 | + case TOI_SYSFS_DATA_BIT: | |
17559 | + len = sprintf(page, "%d\n", | |
17560 | + -test_bit(sysfs_data->data.bit.bit, | |
17561 | + sysfs_data->data.bit.bit_vector)); | |
17562 | + break; | |
17563 | + case TOI_SYSFS_DATA_INTEGER: | |
17564 | + len = sprintf(page, "%d\n", | |
17565 | + *(sysfs_data->data.integer.variable)); | |
17566 | + break; | |
17567 | + case TOI_SYSFS_DATA_LONG: | |
17568 | + len = sprintf(page, "%ld\n", | |
17569 | + *(sysfs_data->data.a_long.variable)); | |
17570 | + break; | |
17571 | + case TOI_SYSFS_DATA_UL: | |
17572 | + len = sprintf(page, "%lu\n", | |
17573 | + *(sysfs_data->data.ul.variable)); | |
17574 | + break; | |
17575 | + case TOI_SYSFS_DATA_STRING: | |
17576 | + len = sprintf(page, "%s\n", | |
17577 | + sysfs_data->data.string.variable); | |
17578 | + break; | |
73c609d5 | 17579 | + } |
24613191 | 17580 | + |
4e97e4e9 | 17581 | + if (sysfs_data->flags & SYSFS_NEEDS_SM_FOR_READ) |
17582 | + toi_cleanup_usm(); | |
24613191 | 17583 | + |
1838f965 | 17584 | + if (full_prep) |
17585 | + toi_finish_anything(0); | |
24613191 | 17586 | + |
4e97e4e9 | 17587 | + return len; |
17588 | +} | |
24613191 | 17589 | + |
1838f965 | 17590 | +#define BOUND(_variable, _type) do { \ |
4e97e4e9 | 17591 | + if (*_variable < sysfs_data->data._type.minimum) \ |
17592 | + *_variable = sysfs_data->data._type.minimum; \ | |
17593 | + else if (*_variable > sysfs_data->data._type.maximum) \ | |
ad8f4a28 | 17594 | + *_variable = sysfs_data->data._type.maximum; \ |
1838f965 | 17595 | +} while (0) |
24613191 | 17596 | + |
4e97e4e9 | 17597 | +static ssize_t toi_attr_store(struct kobject *kobj, struct attribute *attr, |
17598 | + const char *my_buf, size_t count) | |
17599 | +{ | |
17600 | + int assigned_temp_buffer = 0, result = count; | |
17601 | + struct toi_sysfs_data *sysfs_data = to_sysfs_data(attr); | |
17602 | + | |
17603 | + if (toi_start_anything((sysfs_data->flags & SYSFS_HIBERNATE_OR_RESUME))) | |
17604 | + return -EBUSY; | |
17605 | + | |
17606 | + ((char *) my_buf)[count] = 0; | |
17607 | + | |
17608 | + if (sysfs_data->flags & SYSFS_NEEDS_SM_FOR_WRITE) | |
17609 | + toi_prepare_usm(); | |
17610 | + | |
17611 | + switch (sysfs_data->type) { | |
ad8f4a28 AM |
17612 | + case TOI_SYSFS_DATA_CUSTOM: |
17613 | + if (sysfs_data->data.special.write_sysfs) | |
f3e0dcc9 PS |
17614 | + result = (sysfs_data->data.special.write_sysfs)(my_buf, |
17615 | + count); | |
ad8f4a28 AM |
17616 | + break; |
17617 | + case TOI_SYSFS_DATA_BIT: | |
17618 | + { | |
17619 | + int value = simple_strtoul(my_buf, NULL, 0); | |
17620 | + if (value) | |
17621 | + set_bit(sysfs_data->data.bit.bit, | |
17622 | + (sysfs_data->data.bit.bit_vector)); | |
17623 | + else | |
17624 | + clear_bit(sysfs_data->data.bit.bit, | |
17625 | + (sysfs_data->data.bit.bit_vector)); | |
17626 | + } | |
17627 | + break; | |
17628 | + case TOI_SYSFS_DATA_INTEGER: | |
17629 | + { | |
17630 | + int *variable = | |
17631 | + sysfs_data->data.integer.variable; | |
17632 | + *variable = simple_strtol(my_buf, NULL, 0); | |
17633 | + BOUND(variable, integer); | |
73c609d5 | 17634 | + break; |
ad8f4a28 AM |
17635 | + } |
17636 | + case TOI_SYSFS_DATA_LONG: | |
17637 | + { | |
17638 | + long *variable = | |
17639 | + sysfs_data->data.a_long.variable; | |
17640 | + *variable = simple_strtol(my_buf, NULL, 0); | |
17641 | + BOUND(variable, a_long); | |
4e97e4e9 | 17642 | + break; |
ad8f4a28 AM |
17643 | + } |
17644 | + case TOI_SYSFS_DATA_UL: | |
17645 | + { | |
17646 | + unsigned long *variable = | |
17647 | + sysfs_data->data.ul.variable; | |
17648 | + *variable = simple_strtoul(my_buf, NULL, 0); | |
17649 | + BOUND(variable, ul); | |
4e97e4e9 | 17650 | + break; |
ad8f4a28 AM |
17651 | + } |
17652 | + break; | |
17653 | + case TOI_SYSFS_DATA_STRING: | |
17654 | + { | |
17655 | + int copy_len = count; | |
17656 | + char *variable = | |
17657 | + sysfs_data->data.string.variable; | |
17658 | + | |
17659 | + if (sysfs_data->data.string.max_length && | |
17660 | + (copy_len > sysfs_data->data.string.max_length)) | |
17661 | + copy_len = sysfs_data->data.string.max_length; | |
17662 | + | |
17663 | + if (!variable) { | |
17664 | + variable = (char *) toi_get_zeroed_page(31, | |
17665 | + TOI_ATOMIC_GFP); | |
17666 | + sysfs_data->data.string.variable = variable; | |
17667 | + assigned_temp_buffer = 1; | |
4e97e4e9 | 17668 | + } |
ad8f4a28 | 17669 | + strncpy(variable, my_buf, copy_len); |
f3e0dcc9 | 17670 | + if (copy_len && my_buf[copy_len - 1] == '\n') |
ad8f4a28 AM |
17671 | + variable[count - 1] = 0; |
17672 | + variable[count] = 0; | |
17673 | + } | |
17674 | + break; | |
73c609d5 | 17675 | + } |
24613191 | 17676 | + |
4e97e4e9 | 17677 | + /* Side effect routine? */ |
17678 | + if (sysfs_data->write_side_effect) | |
17679 | + sysfs_data->write_side_effect(); | |
24613191 | 17680 | + |
4e97e4e9 | 17681 | + /* Free temporary buffers */ |
17682 | + if (assigned_temp_buffer) { | |
ad8f4a28 AM |
17683 | + toi_free_page(31, |
17684 | + (unsigned long) sysfs_data->data.string.variable); | |
4e97e4e9 | 17685 | + sysfs_data->data.string.variable = NULL; |
73c609d5 | 17686 | + } |
24613191 | 17687 | + |
4e97e4e9 | 17688 | + if (sysfs_data->flags & SYSFS_NEEDS_SM_FOR_WRITE) |
17689 | + toi_cleanup_usm(); | |
24613191 | 17690 | + |
4e97e4e9 | 17691 | + toi_finish_anything(sysfs_data->flags & SYSFS_HIBERNATE_OR_RESUME); |
24613191 | 17692 | + |
4e97e4e9 | 17693 | + return result; |
24613191 | 17694 | +} |
17695 | + | |
4e97e4e9 | 17696 | +static struct sysfs_ops toi_sysfs_ops = { |
17697 | + .show = &toi_attr_show, | |
17698 | + .store = &toi_attr_store, | |
17699 | +}; | |
17700 | + | |
17701 | +static struct kobj_type toi_ktype = { | |
17702 | + .sysfs_ops = &toi_sysfs_ops, | |
17703 | +}; | |
17704 | + | |
7f9d2ee0 | 17705 | +struct kobject *tuxonice_kobj; |
4e97e4e9 | 17706 | + |
17707 | +/* Non-module sysfs entries. | |
17708 | + * | |
17709 | + * This array contains entries that are automatically registered at | |
17710 | + * boot. Modules and the console code register their own entries separately. | |
73c609d5 | 17711 | + */ |
24613191 | 17712 | + |
4e97e4e9 | 17713 | +static struct toi_sysfs_data sysfs_params[] = { |
1838f965 | 17714 | + SYSFS_CUSTOM("do_hibernate", SYSFS_WRITEONLY, NULL, NULL, |
17715 | + SYSFS_HIBERNATING, toi_main_wrapper), | |
17716 | + SYSFS_CUSTOM("do_resume", SYSFS_WRITEONLY, NULL, NULL, | |
17717 | + SYSFS_RESUMING, __toi_try_resume) | |
4e97e4e9 | 17718 | +}; |
73c609d5 | 17719 | + |
4e97e4e9 | 17720 | +void remove_toi_sysdir(struct kobject *kobj) |
73c609d5 | 17721 | +{ |
4e97e4e9 | 17722 | + if (!kobj) |
73c609d5 | 17723 | + return; |
24613191 | 17724 | + |
7f9d2ee0 | 17725 | + kobject_put(kobj); |
73c609d5 | 17726 | +} |
24613191 | 17727 | + |
4e97e4e9 | 17728 | +struct kobject *make_toi_sysdir(char *name) |
73c609d5 | 17729 | +{ |
7f9d2ee0 | 17730 | + struct kobject *kobj = kobject_create_and_add(name, tuxonice_kobj); |
73c609d5 | 17731 | + |
ad8f4a28 AM |
17732 | + if (!kobj) { |
17733 | + printk(KERN_INFO "TuxOnIce: Can't allocate kobject for sysfs " | |
17734 | + "dir!\n"); | |
4e97e4e9 | 17735 | + return NULL; |
17736 | + } | |
73c609d5 | 17737 | + |
7f9d2ee0 | 17738 | + kobj->ktype = &toi_ktype; |
73c609d5 | 17739 | + |
7f9d2ee0 | 17740 | + return kobj; |
73c609d5 | 17741 | +} |
17742 | + | |
4e97e4e9 | 17743 | +/* toi_register_sysfs_file |
17744 | + * | |
17745 | + * Helper for registering a new /sysfs/tuxonice entry. | |
73c609d5 | 17746 | + */ |
17747 | + | |
4e97e4e9 | 17748 | +int toi_register_sysfs_file( |
17749 | + struct kobject *kobj, | |
17750 | + struct toi_sysfs_data *toi_sysfs_data) | |
73c609d5 | 17751 | +{ |
4e97e4e9 | 17752 | + int result; |
17753 | + | |
17754 | + if (!toi_sysfs_initialised) | |
17755 | + toi_initialise_sysfs(); | |
17756 | + | |
ad8f4a28 AM |
17757 | + result = sysfs_create_file(kobj, &toi_sysfs_data->attr); |
17758 | + if (result) | |
17759 | + printk(KERN_INFO "TuxOnIce: sysfs_create_file for %s " | |
17760 | + "returned %d.\n", | |
4e97e4e9 | 17761 | + toi_sysfs_data->attr.name, result); |
7f9d2ee0 | 17762 | + kobj->ktype = &toi_ktype; |
4e97e4e9 | 17763 | + |
17764 | + return result; | |
73c609d5 | 17765 | +} |
ad8f4a28 | 17766 | +EXPORT_SYMBOL_GPL(toi_register_sysfs_file); |
73c609d5 | 17767 | + |
4e97e4e9 | 17768 | +/* toi_unregister_sysfs_file |
17769 | + * | |
17770 | + * Helper for removing unwanted /sys/power/tuxonice entries. | |
73c609d5 | 17771 | + * |
73c609d5 | 17772 | + */ |
4e97e4e9 | 17773 | +void toi_unregister_sysfs_file(struct kobject *kobj, |
17774 | + struct toi_sysfs_data *toi_sysfs_data) | |
73c609d5 | 17775 | +{ |
4e97e4e9 | 17776 | + sysfs_remove_file(kobj, &toi_sysfs_data->attr); |
17777 | +} | |
ad8f4a28 | 17778 | +EXPORT_SYMBOL_GPL(toi_unregister_sysfs_file); |
24613191 | 17779 | + |
4e97e4e9 | 17780 | +void toi_cleanup_sysfs(void) |
17781 | +{ | |
17782 | + int i, | |
17783 | + numfiles = sizeof(sysfs_params) / sizeof(struct toi_sysfs_data); | |
24613191 | 17784 | + |
4e97e4e9 | 17785 | + if (!toi_sysfs_initialised) |
73c609d5 | 17786 | + return; |
24613191 | 17787 | + |
ad8f4a28 | 17788 | + for (i = 0; i < numfiles; i++) |
7f9d2ee0 | 17789 | + toi_unregister_sysfs_file(tuxonice_kobj, &sysfs_params[i]); |
24613191 | 17790 | + |
7f9d2ee0 | 17791 | + kobject_put(tuxonice_kobj); |
4e97e4e9 | 17792 | + toi_sysfs_initialised = 0; |
73c609d5 | 17793 | +} |
24613191 | 17794 | + |
4e97e4e9 | 17795 | +/* toi_initialise_sysfs |
73c609d5 | 17796 | + * |
4e97e4e9 | 17797 | + * Initialise the /sysfs/tuxonice directory. |
73c609d5 | 17798 | + */ |
24613191 | 17799 | + |
4e97e4e9 | 17800 | +static void toi_initialise_sysfs(void) |
73c609d5 | 17801 | +{ |
7f9d2ee0 | 17802 | + int i; |
4e97e4e9 | 17803 | + int numfiles = sizeof(sysfs_params) / sizeof(struct toi_sysfs_data); |
ad8f4a28 | 17804 | + |
4e97e4e9 | 17805 | + if (toi_sysfs_initialised) |
17806 | + return; | |
24613191 | 17807 | + |
4e97e4e9 | 17808 | + /* Make our TuxOnIce directory a child of /sys/power */ |
7f9d2ee0 | 17809 | + tuxonice_kobj = kobject_create_and_add("tuxonice", power_kobj); |
17810 | + if (!tuxonice_kobj) | |
4e97e4e9 | 17811 | + return; |
24613191 | 17812 | + |
4e97e4e9 | 17813 | + toi_sysfs_initialised = 1; |
24613191 | 17814 | + |
ad8f4a28 | 17815 | + for (i = 0; i < numfiles; i++) |
7f9d2ee0 | 17816 | + toi_register_sysfs_file(tuxonice_kobj, &sysfs_params[i]); |
4e97e4e9 | 17817 | +} |
24613191 | 17818 | + |
4e97e4e9 | 17819 | +int toi_sysfs_init(void) |
17820 | +{ | |
17821 | + toi_initialise_sysfs(); | |
17822 | + return 0; | |
17823 | +} | |
73c609d5 | 17824 | + |
4e97e4e9 | 17825 | +void toi_sysfs_exit(void) |
17826 | +{ | |
17827 | + toi_cleanup_sysfs(); | |
17828 | +} | |
17829 | diff --git a/kernel/power/tuxonice_sysfs.h b/kernel/power/tuxonice_sysfs.h | |
17830 | new file mode 100644 | |
1838f965 | 17831 | index 0000000..2fea1cc |
4e97e4e9 | 17832 | --- /dev/null |
17833 | +++ b/kernel/power/tuxonice_sysfs.h | |
1838f965 | 17834 | @@ -0,0 +1,138 @@ |
4e97e4e9 | 17835 | +/* |
17836 | + * kernel/power/tuxonice_sysfs.h | |
17837 | + * | |
1838f965 | 17838 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
4e97e4e9 | 17839 | + * |
17840 | + * This file is released under the GPLv2. | |
17841 | + */ | |
73c609d5 | 17842 | + |
4e97e4e9 | 17843 | +#include <linux/sysfs.h> |
17844 | +#include "power.h" | |
73c609d5 | 17845 | + |
4e97e4e9 | 17846 | +struct toi_sysfs_data { |
17847 | + struct attribute attr; | |
17848 | + int type; | |
17849 | + int flags; | |
17850 | + union { | |
17851 | + struct { | |
17852 | + unsigned long *bit_vector; | |
17853 | + int bit; | |
17854 | + } bit; | |
17855 | + struct { | |
17856 | + int *variable; | |
17857 | + int minimum; | |
17858 | + int maximum; | |
17859 | + } integer; | |
17860 | + struct { | |
17861 | + long *variable; | |
17862 | + long minimum; | |
17863 | + long maximum; | |
17864 | + } a_long; | |
17865 | + struct { | |
17866 | + unsigned long *variable; | |
17867 | + unsigned long minimum; | |
17868 | + unsigned long maximum; | |
17869 | + } ul; | |
17870 | + struct { | |
17871 | + char *variable; | |
17872 | + int max_length; | |
17873 | + } string; | |
17874 | + struct { | |
17875 | + int (*read_sysfs) (const char *buffer, int count); | |
17876 | + int (*write_sysfs) (const char *buffer, int count); | |
17877 | + void *data; | |
17878 | + } special; | |
17879 | + } data; | |
ad8f4a28 | 17880 | + |
1838f965 | 17881 | + /* Side effects routine. Used, eg, for reparsing the |
4e97e4e9 | 17882 | + * resume= entry when it changes */ |
ad8f4a28 | 17883 | + void (*write_side_effect) (void); |
4e97e4e9 | 17884 | + struct list_head sysfs_data_list; |
73c609d5 | 17885 | +}; |
17886 | + | |
4e97e4e9 | 17887 | +enum { |
17888 | + TOI_SYSFS_DATA_NONE = 1, | |
17889 | + TOI_SYSFS_DATA_CUSTOM, | |
17890 | + TOI_SYSFS_DATA_BIT, | |
17891 | + TOI_SYSFS_DATA_INTEGER, | |
17892 | + TOI_SYSFS_DATA_UL, | |
17893 | + TOI_SYSFS_DATA_LONG, | |
17894 | + TOI_SYSFS_DATA_STRING | |
17895 | +}; | |
73c609d5 | 17896 | + |
1838f965 | 17897 | +#define SYSFS_WRITEONLY 0200 |
17898 | +#define SYSFS_READONLY 0444 | |
17899 | +#define SYSFS_RW 0644 | |
73c609d5 | 17900 | + |
1838f965 | 17901 | +#define SYSFS_BIT(_name, _mode, _ul, _bit, _flags) { \ |
17902 | + .attr = {.name = _name , .mode = _mode }, \ | |
4e97e4e9 | 17903 | + .type = TOI_SYSFS_DATA_BIT, \ |
17904 | + .flags = _flags, \ | |
1838f965 | 17905 | + .data = { .bit = { .bit_vector = _ul, .bit = _bit } } } |
73c609d5 | 17906 | + |
1838f965 | 17907 | +#define SYSFS_INT(_name, _mode, _int, _min, _max, _flags, _wse) { \ |
17908 | + .attr = {.name = _name , .mode = _mode }, \ | |
4e97e4e9 | 17909 | + .type = TOI_SYSFS_DATA_INTEGER, \ |
17910 | + .flags = _flags, \ | |
17911 | + .data = { .integer = { .variable = _int, .minimum = _min, \ | |
1838f965 | 17912 | + .maximum = _max } }, \ |
17913 | + .write_side_effect = _wse } | |
73c609d5 | 17914 | + |
1838f965 | 17915 | +#define SYSFS_UL(_name, _mode, _ul, _min, _max, _flags) { \ |
17916 | + .attr = {.name = _name , .mode = _mode }, \ | |
4e97e4e9 | 17917 | + .type = TOI_SYSFS_DATA_UL, \ |
17918 | + .flags = _flags, \ | |
17919 | + .data = { .ul = { .variable = _ul, .minimum = _min, \ | |
1838f965 | 17920 | + .maximum = _max } } } |
73c609d5 | 17921 | + |
1838f965 | 17922 | +#define SYSFS_LONG(_name, _mode, _long, _min, _max, _flags) { \ |
17923 | + .attr = {.name = _name , .mode = _mode }, \ | |
4e97e4e9 | 17924 | + .type = TOI_SYSFS_DATA_LONG, \ |
17925 | + .flags = _flags, \ | |
17926 | + .data = { .a_long = { .variable = _long, .minimum = _min, \ | |
1838f965 | 17927 | + .maximum = _max } } } |
4e97e4e9 | 17928 | + |
1838f965 | 17929 | +#define SYSFS_STRING(_name, _mode, _string, _max_len, _flags, _wse) { \ |
17930 | + .attr = {.name = _name , .mode = _mode }, \ | |
4e97e4e9 | 17931 | + .type = TOI_SYSFS_DATA_STRING, \ |
17932 | + .flags = _flags, \ | |
1838f965 | 17933 | + .data = { .string = { .variable = _string, .max_length = _max_len } }, \ |
17934 | + .write_side_effect = _wse } | |
4e97e4e9 | 17935 | + |
1838f965 | 17936 | +#define SYSFS_CUSTOM(_name, _mode, _read, _write, _flags, _wse) { \ |
17937 | + .attr = {.name = _name , .mode = _mode }, \ | |
4e97e4e9 | 17938 | + .type = TOI_SYSFS_DATA_CUSTOM, \ |
17939 | + .flags = _flags, \ | |
1838f965 | 17940 | + .data = { .special = { .read_sysfs = _read, .write_sysfs = _write } }, \ |
17941 | + .write_side_effect = _wse } | |
4e97e4e9 | 17942 | + |
1838f965 | 17943 | +#define SYSFS_NONE(_name, _wse) { \ |
17944 | + .attr = {.name = _name , .mode = SYSFS_WRITEONLY }, \ | |
17945 | + .type = TOI_SYSFS_DATA_NONE, \ | |
17946 | + .write_side_effect = _wse, \ | |
17947 | +} | |
4e97e4e9 | 17948 | + |
17949 | +/* Flags */ | |
17950 | +#define SYSFS_NEEDS_SM_FOR_READ 1 | |
17951 | +#define SYSFS_NEEDS_SM_FOR_WRITE 2 | |
17952 | +#define SYSFS_HIBERNATE 4 | |
17953 | +#define SYSFS_RESUME 8 | |
17954 | +#define SYSFS_HIBERNATE_OR_RESUME (SYSFS_HIBERNATE | SYSFS_RESUME) | |
17955 | +#define SYSFS_HIBERNATING (SYSFS_HIBERNATE | SYSFS_NEEDS_SM_FOR_WRITE) | |
17956 | +#define SYSFS_RESUMING (SYSFS_RESUME | SYSFS_NEEDS_SM_FOR_WRITE) | |
17957 | +#define SYSFS_NEEDS_SM_FOR_BOTH \ | |
17958 | + (SYSFS_NEEDS_SM_FOR_READ | SYSFS_NEEDS_SM_FOR_WRITE) | |
17959 | + | |
17960 | +int toi_register_sysfs_file(struct kobject *kobj, | |
17961 | + struct toi_sysfs_data *toi_sysfs_data); | |
17962 | +void toi_unregister_sysfs_file(struct kobject *kobj, | |
17963 | + struct toi_sysfs_data *toi_sysfs_data); | |
17964 | + | |
7f9d2ee0 | 17965 | +extern struct kobject *tuxonice_kobj; |
4e97e4e9 | 17966 | + |
17967 | +struct kobject *make_toi_sysdir(char *name); | |
17968 | +void remove_toi_sysdir(struct kobject *obj); | |
17969 | +extern void toi_cleanup_sysfs(void); | |
17970 | + | |
17971 | +extern int toi_sysfs_init(void); | |
17972 | +extern void toi_sysfs_exit(void); | |
17973 | diff --git a/kernel/power/tuxonice_ui.c b/kernel/power/tuxonice_ui.c | |
17974 | new file mode 100644 | |
1838f965 | 17975 | index 0000000..4da4afd |
4e97e4e9 | 17976 | --- /dev/null |
17977 | +++ b/kernel/power/tuxonice_ui.c | |
1838f965 | 17978 | @@ -0,0 +1,250 @@ |
24613191 | 17979 | +/* |
4e97e4e9 | 17980 | + * kernel/power/tuxonice_ui.c |
24613191 | 17981 | + * |
4e97e4e9 | 17982 | + * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu> |
17983 | + * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz> | |
17984 | + * Copyright (C) 2002-2003 Florent Chabaud <fchabaud@free.fr> | |
1838f965 | 17985 | + * Copyright (C) 2002-2008 Nigel Cunningham (nigel at tuxonice net) |
24613191 | 17986 | + * |
17987 | + * This file is released under the GPLv2. | |
17988 | + * | |
4e97e4e9 | 17989 | + * Routines for TuxOnIce's user interface. |
17990 | + * | |
17991 | + * The user interface code talks to a userspace program via a | |
17992 | + * netlink socket. | |
17993 | + * | |
17994 | + * The kernel side: | |
17995 | + * - starts the userui program; | |
17996 | + * - sends text messages and progress bar status; | |
17997 | + * | |
17998 | + * The user space side: | |
17999 | + * - passes messages regarding user requests (abort, toggle reboot etc) | |
24613191 | 18000 | + * |
18001 | + */ | |
18002 | + | |
4e97e4e9 | 18003 | +#define __KERNEL_SYSCALLS__ |
18004 | + | |
4e97e4e9 | 18005 | +#include <linux/reboot.h> |
ad8f4a28 | 18006 | + |
4e97e4e9 | 18007 | +#include "tuxonice_sysfs.h" |
18008 | +#include "tuxonice_modules.h" | |
18009 | +#include "tuxonice.h" | |
18010 | +#include "tuxonice_ui.h" | |
18011 | +#include "tuxonice_netlink.h" | |
18012 | +#include "tuxonice_power_off.h" | |
7f9d2ee0 | 18013 | +#include "tuxonice_builtin.h" |
24613191 | 18014 | + |
4e97e4e9 | 18015 | +static char local_printf_buf[1024]; /* Same as printk - should be safe */ |
4e97e4e9 | 18016 | +struct ui_ops *toi_current_ui; |
1838f965 | 18017 | +EXPORT_SYMBOL_GPL(toi_current_ui); |
24613191 | 18018 | + |
4e97e4e9 | 18019 | +/** |
18020 | + * toi_wait_for_keypress - Wait for keypress via userui or /dev/console. | |
18021 | + * | |
18022 | + * @timeout: Maximum time to wait. | |
18023 | + * | |
18024 | + * Wait for a keypress, either from userui or /dev/console if userui isn't | |
18025 | + * available. The non-userui path is particularly for at boot-time, prior | |
18026 | + * to userui being started, when we have an important warning to give to | |
18027 | + * the user. | |
18028 | + */ | |
18029 | +static char toi_wait_for_keypress(int timeout) | |
24613191 | 18030 | +{ |
ad8f4a28 AM |
18031 | + if (toi_current_ui && toi_current_ui->wait_for_key(timeout)) |
18032 | + return ' '; | |
24613191 | 18033 | + |
ad8f4a28 | 18034 | + return toi_wait_for_keypress_dev_console(timeout); |
4e97e4e9 | 18035 | +} |
24613191 | 18036 | + |
4e97e4e9 | 18037 | +/* toi_early_boot_message() |
18038 | + * Description: Handle errors early in the process of booting. | |
18039 | + * The user may press C to continue booting, perhaps | |
ad8f4a28 AM |
18040 | + * invalidating the image, or space to reboot. |
18041 | + * This works from either the serial console or normally | |
4e97e4e9 | 18042 | + * attached keyboard. |
73c609d5 | 18043 | + * |
4e97e4e9 | 18044 | + * Note that we come in here from init, while the kernel is |
18045 | + * locked. If we want to get events from the serial console, | |
18046 | + * we need to temporarily unlock the kernel. | |
73c609d5 | 18047 | + * |
4e97e4e9 | 18048 | + * toi_early_boot_message may also be called post-boot. |
18049 | + * In this case, it simply printks the message and returns. | |
18050 | + * | |
18051 | + * Arguments: int Whether we are able to erase the image. | |
18052 | + * int default_answer. What to do when we timeout. This | |
18053 | + * will normally be continue, but the user might | |
18054 | + * provide command line options (__setup) to override | |
18055 | + * particular cases. | |
18056 | + * Char *. Pointer to a string explaining why we're moaning. | |
73c609d5 | 18057 | + */ |
24613191 | 18058 | + |
4e97e4e9 | 18059 | +#define say(message, a...) printk(KERN_EMERG message, ##a) |
24613191 | 18060 | + |
ad8f4a28 AM |
18061 | +void toi_early_boot_message(int message_detail, int default_answer, |
18062 | + char *warning_reason, ...) | |
24613191 | 18063 | +{ |
4e97e4e9 | 18064 | +#if defined(CONFIG_VT) || defined(CONFIG_SERIAL_CONSOLE) |
18065 | + unsigned long orig_state = get_toi_state(), continue_req = 0; | |
18066 | + unsigned long orig_loglevel = console_loglevel; | |
18067 | + int can_ask = 1; | |
18068 | +#else | |
18069 | + int can_ask = 0; | |
18070 | +#endif | |
24613191 | 18071 | + |
4e97e4e9 | 18072 | + va_list args; |
18073 | + int printed_len; | |
73c609d5 | 18074 | + |
4e97e4e9 | 18075 | + if (!toi_wait) { |
18076 | + set_toi_state(TOI_CONTINUE_REQ); | |
18077 | + can_ask = 0; | |
18078 | + } | |
73c609d5 | 18079 | + |
4e97e4e9 | 18080 | + if (warning_reason) { |
18081 | + va_start(args, warning_reason); | |
ad8f4a28 AM |
18082 | + printed_len = vsnprintf(local_printf_buf, |
18083 | + sizeof(local_printf_buf), | |
4e97e4e9 | 18084 | + warning_reason, |
18085 | + args); | |
18086 | + va_end(args); | |
24613191 | 18087 | + } |
18088 | + | |
4e97e4e9 | 18089 | + if (!test_toi_state(TOI_BOOT_TIME)) { |
18090 | + printk("TuxOnIce: %s\n", local_printf_buf); | |
18091 | + return; | |
18092 | + } | |
24613191 | 18093 | + |
4e97e4e9 | 18094 | + if (!can_ask) { |
18095 | + continue_req = !!default_answer; | |
18096 | + goto post_ask; | |
73c609d5 | 18097 | + } |
24613191 | 18098 | + |
4e97e4e9 | 18099 | +#if defined(CONFIG_VT) || defined(CONFIG_SERIAL_CONSOLE) |
18100 | + console_loglevel = 7; | |
24613191 | 18101 | + |
4e97e4e9 | 18102 | + say("=== TuxOnIce ===\n\n"); |
18103 | + if (warning_reason) { | |
18104 | + say("BIG FAT WARNING!! %s\n\n", local_printf_buf); | |
18105 | + switch (message_detail) { | |
ad8f4a28 AM |
18106 | + case 0: |
18107 | + say("If you continue booting, note that any image WILL" | |
18108 | + "NOT BE REMOVED.\nTuxOnIce is unable to do so " | |
18109 | + "because the appropriate modules aren't\n" | |
18110 | + "loaded. You should manually remove the image " | |
18111 | + "to avoid any\npossibility of corrupting your " | |
18112 | + "filesystem(s) later.\n"); | |
4e97e4e9 | 18113 | + break; |
ad8f4a28 AM |
18114 | + case 1: |
18115 | + say("If you want to use the current TuxOnIce image, " | |
18116 | + "reboot and try\nagain with the same kernel " | |
18117 | + "that you hibernated from. If you want\n" | |
18118 | + "to forget that image, continue and the image " | |
18119 | + "will be erased.\n"); | |
4e97e4e9 | 18120 | + break; |
18121 | + } | |
ad8f4a28 AM |
18122 | + say("Press SPACE to reboot or C to continue booting with " |
18123 | + "this kernel\n\n"); | |
4e97e4e9 | 18124 | + if (toi_wait > 0) |
ad8f4a28 AM |
18125 | + say("Default action if you don't select one in %d " |
18126 | + "seconds is: %s.\n", | |
4e97e4e9 | 18127 | + toi_wait, |
18128 | + default_answer == TOI_CONTINUE_REQ ? | |
18129 | + "continue booting" : "reboot"); | |
18130 | + } else { | |
ad8f4a28 AM |
18131 | + say("BIG FAT WARNING!!\n\n" |
18132 | + "You have tried to resume from this image before.\n" | |
18133 | + "If it failed once, it may well fail again.\n" | |
18134 | + "Would you like to remove the image and boot " | |
18135 | + "normally?\nThis will be equivalent to entering " | |
18136 | + "noresume on the\nkernel command line.\n\n" | |
18137 | + "Press SPACE to remove the image or C to continue " | |
18138 | + "resuming.\n\n"); | |
4e97e4e9 | 18139 | + if (toi_wait > 0) |
ad8f4a28 AM |
18140 | + say("Default action if you don't select one in %d " |
18141 | + "seconds is: %s.\n", toi_wait, | |
4e97e4e9 | 18142 | + !!default_answer ? |
18143 | + "continue resuming" : "remove the image"); | |
18144 | + } | |
18145 | + console_loglevel = orig_loglevel; | |
ad8f4a28 | 18146 | + |
4e97e4e9 | 18147 | + set_toi_state(TOI_SANITY_CHECK_PROMPT); |
18148 | + clear_toi_state(TOI_CONTINUE_REQ); | |
24613191 | 18149 | + |
4e97e4e9 | 18150 | + if (toi_wait_for_keypress(toi_wait) == 0) /* We timed out */ |
18151 | + continue_req = !!default_answer; | |
18152 | + else | |
18153 | + continue_req = test_toi_state(TOI_CONTINUE_REQ); | |
24613191 | 18154 | + |
4e97e4e9 | 18155 | +#endif /* CONFIG_VT or CONFIG_SERIAL_CONSOLE */ |
18156 | + | |
18157 | +post_ask: | |
18158 | + if ((warning_reason) && (!continue_req)) | |
18159 | + machine_restart(NULL); | |
ad8f4a28 | 18160 | + |
4e97e4e9 | 18161 | + restore_toi_state(orig_state); |
18162 | + if (continue_req) | |
18163 | + set_toi_state(TOI_CONTINUE_REQ); | |
24613191 | 18164 | +} |
1838f965 | 18165 | +EXPORT_SYMBOL_GPL(toi_early_boot_message); |
4e97e4e9 | 18166 | +#undef say |
24613191 | 18167 | + |
4e97e4e9 | 18168 | +/* |
18169 | + * User interface specific /sys/power/tuxonice entries. | |
24613191 | 18170 | + */ |
24613191 | 18171 | + |
4e97e4e9 | 18172 | +static struct toi_sysfs_data sysfs_params[] = { |
18173 | +#if defined(CONFIG_NET) && defined(CONFIG_SYSFS) | |
1838f965 | 18174 | + SYSFS_INT("default_console_level", SYSFS_RW, |
18175 | + &toi_bkd.toi_default_console_level, 0, 7, 0, NULL), | |
18176 | + SYSFS_UL("debug_sections", SYSFS_RW, &toi_bkd.toi_debug_state, 0, | |
18177 | + 1 << 30, 0), | |
18178 | + SYSFS_BIT("log_everything", SYSFS_RW, &toi_bkd.toi_action, TOI_LOGALL, | |
18179 | + 0) | |
4e97e4e9 | 18180 | +#endif |
4e97e4e9 | 18181 | +}; |
24613191 | 18182 | + |
4e97e4e9 | 18183 | +static struct toi_module_ops userui_ops = { |
18184 | + .type = MISC_HIDDEN_MODULE, | |
18185 | + .name = "printk ui", | |
18186 | + .directory = "user_interface", | |
18187 | + .module = THIS_MODULE, | |
18188 | + .sysfs_data = sysfs_params, | |
ad8f4a28 AM |
18189 | + .num_sysfs_entries = sizeof(sysfs_params) / |
18190 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 18191 | +}; |
24613191 | 18192 | + |
4e97e4e9 | 18193 | +int toi_register_ui_ops(struct ui_ops *this_ui) |
73c609d5 | 18194 | +{ |
4e97e4e9 | 18195 | + if (toi_current_ui) { |
ad8f4a28 AM |
18196 | + printk(KERN_INFO "Only one TuxOnIce user interface module can " |
18197 | + "be loaded at a time."); | |
4e97e4e9 | 18198 | + return -EBUSY; |
18199 | + } | |
18200 | + | |
18201 | + toi_current_ui = this_ui; | |
18202 | + | |
18203 | + return 0; | |
73c609d5 | 18204 | +} |
1838f965 | 18205 | +EXPORT_SYMBOL_GPL(toi_register_ui_ops); |
24613191 | 18206 | + |
4e97e4e9 | 18207 | +void toi_remove_ui_ops(struct ui_ops *this_ui) |
24613191 | 18208 | +{ |
4e97e4e9 | 18209 | + if (toi_current_ui != this_ui) |
73c609d5 | 18210 | + return; |
24613191 | 18211 | + |
4e97e4e9 | 18212 | + toi_current_ui = NULL; |
24613191 | 18213 | +} |
1838f965 | 18214 | +EXPORT_SYMBOL_GPL(toi_remove_ui_ops); |
24613191 | 18215 | + |
4e97e4e9 | 18216 | +/* toi_console_sysfs_init |
18217 | + * Description: Boot time initialisation for user interface. | |
24613191 | 18218 | + */ |
73c609d5 | 18219 | + |
4e97e4e9 | 18220 | +int toi_ui_init(void) |
24613191 | 18221 | +{ |
4e97e4e9 | 18222 | + return toi_register_module(&userui_ops); |
24613191 | 18223 | +} |
18224 | + | |
4e97e4e9 | 18225 | +void toi_ui_exit(void) |
24613191 | 18226 | +{ |
4e97e4e9 | 18227 | + toi_unregister_module(&userui_ops); |
73c609d5 | 18228 | +} |
4e97e4e9 | 18229 | diff --git a/kernel/power/tuxonice_ui.h b/kernel/power/tuxonice_ui.h |
18230 | new file mode 100644 | |
1838f965 | 18231 | index 0000000..884d0c5 |
4e97e4e9 | 18232 | --- /dev/null |
18233 | +++ b/kernel/power/tuxonice_ui.h | |
1838f965 | 18234 | @@ -0,0 +1,105 @@ |
73c609d5 | 18235 | +/* |
4e97e4e9 | 18236 | + * kernel/power/tuxonice_ui.h |
73c609d5 | 18237 | + * |
1838f965 | 18238 | + * Copyright (C) 2004-2008 Nigel Cunningham (nigel at tuxonice net) |
73c609d5 | 18239 | + */ |
24613191 | 18240 | + |
4e97e4e9 | 18241 | +enum { |
18242 | + DONT_CLEAR_BAR, | |
18243 | + CLEAR_BAR | |
73c609d5 | 18244 | +}; |
24613191 | 18245 | + |
73c609d5 | 18246 | +enum { |
4e97e4e9 | 18247 | + /* Userspace -> Kernel */ |
18248 | + USERUI_MSG_ABORT = 0x11, | |
18249 | + USERUI_MSG_SET_STATE = 0x12, | |
18250 | + USERUI_MSG_GET_STATE = 0x13, | |
18251 | + USERUI_MSG_GET_DEBUG_STATE = 0x14, | |
18252 | + USERUI_MSG_SET_DEBUG_STATE = 0x15, | |
18253 | + USERUI_MSG_SPACE = 0x18, | |
18254 | + USERUI_MSG_GET_POWERDOWN_METHOD = 0x1A, | |
18255 | + USERUI_MSG_SET_POWERDOWN_METHOD = 0x1B, | |
18256 | + USERUI_MSG_GET_LOGLEVEL = 0x1C, | |
18257 | + USERUI_MSG_SET_LOGLEVEL = 0x1D, | |
18258 | + USERUI_MSG_PRINTK = 0x1E, | |
18259 | + | |
18260 | + /* Kernel -> Userspace */ | |
18261 | + USERUI_MSG_MESSAGE = 0x21, | |
18262 | + USERUI_MSG_PROGRESS = 0x22, | |
18263 | + USERUI_MSG_POST_ATOMIC_RESTORE = 0x25, | |
18264 | + | |
18265 | + USERUI_MSG_MAX, | |
73c609d5 | 18266 | +}; |
24613191 | 18267 | + |
4e97e4e9 | 18268 | +struct userui_msg_params { |
1838f965 | 18269 | + u32 a, b, c, d; |
4e97e4e9 | 18270 | + char text[255]; |
18271 | +}; | |
24613191 | 18272 | + |
4e97e4e9 | 18273 | +struct ui_ops { |
18274 | + char (*wait_for_key) (int timeout); | |
1838f965 | 18275 | + u32 (*update_status) (u32 value, u32 maximum, const char *fmt, ...); |
4e97e4e9 | 18276 | + void (*prepare_status) (int clearbar, const char *fmt, ...); |
18277 | + void (*cond_pause) (int pause, char *message); | |
18278 | + void (*abort)(int result_code, const char *fmt, ...); | |
18279 | + void (*prepare)(void); | |
18280 | + void (*cleanup)(void); | |
18281 | + void (*post_atomic_restore)(void); | |
1838f965 | 18282 | + void (*message)(u32 section, u32 level, u32 normally_logged, |
18283 | + const char *fmt, ...); | |
4e97e4e9 | 18284 | +}; |
24613191 | 18285 | + |
4e97e4e9 | 18286 | +extern struct ui_ops *toi_current_ui; |
24613191 | 18287 | + |
4e97e4e9 | 18288 | +#define toi_update_status(val, max, fmt, args...) \ |
ad8f4a28 AM |
18289 | + (toi_current_ui ? (toi_current_ui->update_status) (val, max, fmt, ##args) : \ |
18290 | + max) | |
24613191 | 18291 | + |
4e97e4e9 | 18292 | +#define toi_ui_post_atomic_restore(void) \ |
18293 | + do { if (toi_current_ui) \ | |
18294 | + (toi_current_ui->post_atomic_restore)(); \ | |
ad8f4a28 | 18295 | + } while (0) |
24613191 | 18296 | + |
4e97e4e9 | 18297 | +#define toi_prepare_console(void) \ |
1838f965 | 18298 | + do { pm_prepare_console(); \ |
18299 | + if (toi_current_ui) \ | |
4e97e4e9 | 18300 | + (toi_current_ui->prepare)(); \ |
ad8f4a28 | 18301 | + } while (0) |
24613191 | 18302 | + |
4e97e4e9 | 18303 | +#define toi_cleanup_console(void) \ |
1838f965 | 18304 | + do { pm_restore_console(); \ |
18305 | + if (toi_current_ui) \ | |
4e97e4e9 | 18306 | + (toi_current_ui->cleanup)(); \ |
ad8f4a28 | 18307 | + } while (0) |
24613191 | 18308 | + |
4e97e4e9 | 18309 | +#define abort_hibernate(result, fmt, args...) \ |
18310 | + do { if (toi_current_ui) \ | |
18311 | + (toi_current_ui->abort)(result, fmt, ##args); \ | |
18312 | + else { \ | |
18313 | + set_abort_result(result); \ | |
18314 | + } \ | |
ad8f4a28 | 18315 | + } while (0) |
24613191 | 18316 | + |
4e97e4e9 | 18317 | +#define toi_cond_pause(pause, message) \ |
18318 | + do { if (toi_current_ui) \ | |
18319 | + (toi_current_ui->cond_pause)(pause, message); \ | |
ad8f4a28 | 18320 | + } while (0) |
24613191 | 18321 | + |
4e97e4e9 | 18322 | +#define toi_prepare_status(clear, fmt, args...) \ |
18323 | + do { if (toi_current_ui) \ | |
18324 | + (toi_current_ui->prepare_status)(clear, fmt, ##args); \ | |
18325 | + else \ | |
7f9d2ee0 | 18326 | + printk(KERN_ERR fmt "%s", ##args, "\n"); \ |
ad8f4a28 | 18327 | + } while (0) |
24613191 | 18328 | + |
4e97e4e9 | 18329 | +#define toi_message(sn, lev, log, fmt, a...) \ |
18330 | +do { \ | |
18331 | + if (toi_current_ui && (!sn || test_debug_state(sn))) \ | |
18332 | + toi_current_ui->message(sn, lev, log, fmt, ##a); \ | |
ad8f4a28 | 18333 | +} while (0) |
24613191 | 18334 | + |
4e97e4e9 | 18335 | +__exit void toi_ui_cleanup(void); |
18336 | +extern int toi_ui_init(void); | |
18337 | +extern void toi_ui_exit(void); | |
18338 | +extern int toi_register_ui_ops(struct ui_ops *this_ui); | |
18339 | +extern void toi_remove_ui_ops(struct ui_ops *this_ui); | |
18340 | diff --git a/kernel/power/tuxonice_userui.c b/kernel/power/tuxonice_userui.c | |
18341 | new file mode 100644 | |
1838f965 | 18342 | index 0000000..7cc5666 |
4e97e4e9 | 18343 | --- /dev/null |
18344 | +++ b/kernel/power/tuxonice_userui.c | |
1838f965 | 18345 | @@ -0,0 +1,663 @@ |
73c609d5 | 18346 | +/* |
4e97e4e9 | 18347 | + * kernel/power/user_ui.c |
73c609d5 | 18348 | + * |
4e97e4e9 | 18349 | + * Copyright (C) 2005-2007 Bernard Blackham |
1838f965 | 18350 | + * Copyright (C) 2002-2008 Nigel Cunningham (nigel at tuxonice net) |
73c609d5 | 18351 | + * |
18352 | + * This file is released under the GPLv2. | |
18353 | + * | |
4e97e4e9 | 18354 | + * Routines for TuxOnIce's user interface. |
73c609d5 | 18355 | + * |
18356 | + * The user interface code talks to a userspace program via a | |
18357 | + * netlink socket. | |
18358 | + * | |
18359 | + * The kernel side: | |
18360 | + * - starts the userui program; | |
18361 | + * - sends text messages and progress bar status; | |
18362 | + * | |
18363 | + * The user space side: | |
18364 | + * - passes messages regarding user requests (abort, toggle reboot etc) | |
24613191 | 18365 | + * |
24613191 | 18366 | + */ |
18367 | + | |
73c609d5 | 18368 | +#define __KERNEL_SYSCALLS__ |
24613191 | 18369 | + |
73c609d5 | 18370 | +#include <linux/suspend.h> |
18371 | +#include <linux/freezer.h> | |
18372 | +#include <linux/console.h> | |
18373 | +#include <linux/ctype.h> | |
18374 | +#include <linux/tty.h> | |
18375 | +#include <linux/vt_kern.h> | |
18376 | +#include <linux/module.h> | |
18377 | +#include <linux/reboot.h> | |
18378 | +#include <linux/kmod.h> | |
18379 | +#include <linux/security.h> | |
18380 | +#include <linux/syscalls.h> | |
ad8f4a28 | 18381 | + |
4e97e4e9 | 18382 | +#include "tuxonice_sysfs.h" |
18383 | +#include "tuxonice_modules.h" | |
18384 | +#include "tuxonice.h" | |
18385 | +#include "tuxonice_ui.h" | |
18386 | +#include "tuxonice_netlink.h" | |
18387 | +#include "tuxonice_power_off.h" | |
24613191 | 18388 | + |
73c609d5 | 18389 | +static char local_printf_buf[1024]; /* Same as printk - should be safe */ |
73c609d5 | 18390 | + |
4e97e4e9 | 18391 | +static struct user_helper_data ui_helper_data; |
18392 | +static struct toi_module_ops userui_ops; | |
18393 | +static int orig_kmsg; | |
24613191 | 18394 | + |
4e97e4e9 | 18395 | +static char lastheader[512]; |
18396 | +static int lastheader_message_len; | |
18397 | +static int ui_helper_changed; /* Used at resume-time so don't overwrite value | |
18398 | + set from initrd/ramfs. */ | |
18399 | + | |
18400 | +/* Number of distinct progress amounts that userspace can display */ | |
18401 | +static int progress_granularity = 30; | |
18402 | + | |
18403 | +static DECLARE_WAIT_QUEUE_HEAD(userui_wait_for_key); | |
18404 | + | |
18405 | +/** | |
18406 | + * ui_nl_set_state - Update toi_action based on a message from userui. | |
24613191 | 18407 | + * |
4e97e4e9 | 18408 | + * @n: The bit (1 << bit) to set. |
18409 | + */ | |
18410 | +static void ui_nl_set_state(int n) | |
18411 | +{ | |
18412 | + /* Only let them change certain settings */ | |
1838f965 | 18413 | + static const u32 toi_action_mask = |
4e97e4e9 | 18414 | + (1 << TOI_REBOOT) | (1 << TOI_PAUSE) | |
7f9d2ee0 | 18415 | + (1 << TOI_LOGALL) | |
4e97e4e9 | 18416 | + (1 << TOI_SINGLESTEP) | |
18417 | + (1 << TOI_PAUSE_NEAR_PAGESET_END); | |
18418 | + | |
ad8f4a28 | 18419 | + toi_bkd.toi_action = (toi_bkd.toi_action & (~toi_action_mask)) | |
4e97e4e9 | 18420 | + (n & toi_action_mask); |
18421 | + | |
18422 | + if (!test_action_state(TOI_PAUSE) && | |
18423 | + !test_action_state(TOI_SINGLESTEP)) | |
18424 | + wake_up_interruptible(&userui_wait_for_key); | |
18425 | +} | |
18426 | + | |
18427 | +/** | |
18428 | + * userui_post_atomic_restore - Tell userui that atomic restore just happened. | |
24613191 | 18429 | + * |
4e97e4e9 | 18430 | + * Tell userui that atomic restore just occured, so that it can do things like |
18431 | + * redrawing the screen, re-getting settings and so on. | |
18432 | + */ | |
18433 | +static void userui_post_atomic_restore(void) | |
18434 | +{ | |
18435 | + toi_send_netlink_message(&ui_helper_data, | |
18436 | + USERUI_MSG_POST_ATOMIC_RESTORE, NULL, 0); | |
18437 | +} | |
18438 | + | |
18439 | +/** | |
18440 | + * userui_storage_needed - Report how much memory in image header is needed. | |
18441 | + */ | |
18442 | +static int userui_storage_needed(void) | |
18443 | +{ | |
18444 | + return sizeof(ui_helper_data.program) + 1 + sizeof(int); | |
18445 | +} | |
18446 | + | |
18447 | +/** | |
18448 | + * userui_save_config_info - Fill buffer with config info for image header. | |
24613191 | 18449 | + * |
4e97e4e9 | 18450 | + * @buf: Buffer into which to put the config info we want to save. |
18451 | + */ | |
18452 | +static int userui_save_config_info(char *buf) | |
18453 | +{ | |
18454 | + *((int *) buf) = progress_granularity; | |
ad8f4a28 AM |
18455 | + memcpy(buf + sizeof(int), ui_helper_data.program, |
18456 | + sizeof(ui_helper_data.program)); | |
4e97e4e9 | 18457 | + return sizeof(ui_helper_data.program) + sizeof(int) + 1; |
18458 | +} | |
18459 | + | |
18460 | +/** | |
18461 | + * userui_load_config_info - Restore config info from buffer. | |
18462 | + * | |
18463 | + * @buf: Buffer containing header info loaded. | |
18464 | + * @size: Size of data loaded for this module. | |
18465 | + */ | |
18466 | +static void userui_load_config_info(char *buf, int size) | |
18467 | +{ | |
18468 | + progress_granularity = *((int *) buf); | |
18469 | + size -= sizeof(int); | |
18470 | + | |
18471 | + /* Don't load the saved path if one has already been set */ | |
18472 | + if (ui_helper_changed) | |
18473 | + return; | |
18474 | + | |
18475 | + if (size > sizeof(ui_helper_data.program)) | |
18476 | + size = sizeof(ui_helper_data.program); | |
18477 | + | |
18478 | + memcpy(ui_helper_data.program, buf + sizeof(int), size); | |
18479 | + ui_helper_data.program[sizeof(ui_helper_data.program)-1] = '\0'; | |
18480 | +} | |
18481 | + | |
18482 | +/** | |
18483 | + * set_ui_program_set: Record that userui program was changed. | |
18484 | + * | |
18485 | + * Side effect routine for when the userui program is set. In an initrd or | |
18486 | + * ramfs, the user may set a location for the userui program. If this happens, | |
18487 | + * we don't want to reload the value that was saved in the image header. This | |
18488 | + * routine allows us to flag that we shouldn't restore the program name from | |
18489 | + * the image header. | |
18490 | + */ | |
18491 | +static void set_ui_program_set(void) | |
18492 | +{ | |
18493 | + ui_helper_changed = 1; | |
18494 | +} | |
18495 | + | |
18496 | +/** | |
18497 | + * userui_memory_needed - Tell core how much memory to reserve for us. | |
18498 | + */ | |
18499 | +static int userui_memory_needed(void) | |
18500 | +{ | |
18501 | + /* ball park figure of 128 pages */ | |
1838f965 | 18502 | + return 128 * PAGE_SIZE; |
4e97e4e9 | 18503 | +} |
18504 | + | |
18505 | +/** | |
18506 | + * userui_update_status - Update the progress bar and (if on) in-bar message. | |
18507 | + * | |
18508 | + * @value: Current progress percentage numerator. | |
18509 | + * @maximum: Current progress percentage denominator. | |
18510 | + * @fmt: Message to be displayed in the middle of the progress bar. | |
18511 | + * | |
18512 | + * Note that a NULL message does not mean that any previous message is erased! | |
18513 | + * For that, you need toi_prepare_status with clearbar on. | |
18514 | + * | |
18515 | + * Returns an unsigned long, being the next numerator (as determined by the | |
18516 | + * maximum and progress granularity) where status needs to be updated. | |
18517 | + * This is to reduce unnecessary calls to update_status. | |
18518 | + */ | |
1838f965 | 18519 | +static u32 userui_update_status(u32 value, u32 maximum, const char *fmt, ...) |
4e97e4e9 | 18520 | +{ |
1838f965 | 18521 | + static u32 last_step = 9999; |
4e97e4e9 | 18522 | + struct userui_msg_params msg; |
1838f965 | 18523 | + u32 this_step, next_update; |
4e97e4e9 | 18524 | + int bitshift; |
4e97e4e9 | 18525 | + |
18526 | + if (ui_helper_data.pid == -1) | |
18527 | + return 0; | |
18528 | + | |
18529 | + if ((!maximum) || (!progress_granularity)) | |
18530 | + return maximum; | |
18531 | + | |
18532 | + if (value < 0) | |
18533 | + value = 0; | |
18534 | + | |
18535 | + if (value > maximum) | |
18536 | + value = maximum; | |
18537 | + | |
18538 | + /* Try to avoid math problems - we can't do 64 bit math here | |
18539 | + * (and shouldn't need it - anyone got screen resolution | |
18540 | + * of 65536 pixels or more?) */ | |
18541 | + bitshift = fls(maximum) - 16; | |
18542 | + if (bitshift > 0) { | |
1838f965 | 18543 | + u32 temp_maximum = maximum >> bitshift; |
18544 | + u32 temp_value = value >> bitshift; | |
18545 | + this_step = (u32) | |
4e97e4e9 | 18546 | + (temp_value * progress_granularity / temp_maximum); |
18547 | + next_update = (((this_step + 1) * temp_maximum / | |
18548 | + progress_granularity) + 1) << bitshift; | |
18549 | + } else { | |
1838f965 | 18550 | + this_step = (u32) (value * progress_granularity / maximum); |
4e97e4e9 | 18551 | + next_update = ((this_step + 1) * maximum / |
18552 | + progress_granularity) + 1; | |
18553 | + } | |
18554 | + | |
18555 | + if (this_step == last_step) | |
18556 | + return next_update; | |
18557 | + | |
18558 | + memset(&msg, 0, sizeof(msg)); | |
18559 | + | |
18560 | + msg.a = this_step; | |
18561 | + msg.b = progress_granularity; | |
18562 | + | |
18563 | + if (fmt) { | |
18564 | + va_list args; | |
18565 | + va_start(args, fmt); | |
18566 | + vsnprintf(msg.text, sizeof(msg.text), fmt, args); | |
18567 | + va_end(args); | |
18568 | + msg.text[sizeof(msg.text)-1] = '\0'; | |
18569 | + } | |
18570 | + | |
18571 | + toi_send_netlink_message(&ui_helper_data, USERUI_MSG_PROGRESS, | |
18572 | + &msg, sizeof(msg)); | |
18573 | + last_step = this_step; | |
18574 | + | |
18575 | + return next_update; | |
18576 | +} | |
18577 | + | |
18578 | +/** | |
18579 | + * userui_message - Display a message without necessarily logging it. | |
18580 | + * | |
18581 | + * @section: Type of message. Messages can be filtered by type. | |
18582 | + * @level: Degree of importance of the message. Lower values = higher priority. | |
18583 | + * @normally_logged: Whether logged even if log_everything is off. | |
18584 | + * @fmt: Message (and parameters). | |
18585 | + * | |
18586 | + * This function is intended to do the same job as printk, but without normally | |
18587 | + * logging what is printed. The point is to be able to get debugging info on | |
18588 | + * screen without filling the logs with "1/534. ^M 2/534^M. 3/534^M" | |
18589 | + * | |
18590 | + * It may be called from an interrupt context - can't sleep! | |
18591 | + */ | |
1838f965 | 18592 | +static void userui_message(u32 section, u32 level, u32 normally_logged, |
18593 | + const char *fmt, ...) | |
4e97e4e9 | 18594 | +{ |
18595 | + struct userui_msg_params msg; | |
18596 | + | |
18597 | + if ((level) && (level > console_loglevel)) | |
18598 | + return; | |
18599 | + | |
18600 | + memset(&msg, 0, sizeof(msg)); | |
18601 | + | |
18602 | + msg.a = section; | |
18603 | + msg.b = level; | |
18604 | + msg.c = normally_logged; | |
18605 | + | |
18606 | + if (fmt) { | |
18607 | + va_list args; | |
18608 | + va_start(args, fmt); | |
18609 | + vsnprintf(msg.text, sizeof(msg.text), fmt, args); | |
18610 | + va_end(args); | |
18611 | + msg.text[sizeof(msg.text)-1] = '\0'; | |
18612 | + } | |
18613 | + | |
18614 | + if (test_action_state(TOI_LOGALL)) | |
ad8f4a28 | 18615 | + printk(KERN_INFO "%s\n", msg.text); |
4e97e4e9 | 18616 | + |
18617 | + toi_send_netlink_message(&ui_helper_data, USERUI_MSG_MESSAGE, | |
18618 | + &msg, sizeof(msg)); | |
18619 | +} | |
18620 | + | |
18621 | +/** | |
18622 | + * wait_for_key_via_userui - Wait for userui to receive a keypress. | |
18623 | + */ | |
18624 | +static void wait_for_key_via_userui(void) | |
18625 | +{ | |
18626 | + DECLARE_WAITQUEUE(wait, current); | |
18627 | + | |
18628 | + add_wait_queue(&userui_wait_for_key, &wait); | |
18629 | + set_current_state(TASK_INTERRUPTIBLE); | |
18630 | + | |
18631 | + interruptible_sleep_on(&userui_wait_for_key); | |
18632 | + | |
18633 | + set_current_state(TASK_RUNNING); | |
18634 | + remove_wait_queue(&userui_wait_for_key, &wait); | |
18635 | +} | |
18636 | + | |
18637 | +/** | |
18638 | + * userui_prepare_status - Display high level messages. | |
18639 | + * | |
18640 | + * @clearbar: Whether to clear the progress bar. | |
18641 | + * @fmt...: New message for the title. | |
18642 | + * | |
18643 | + * Prepare the 'nice display', drawing the header and version, along with the | |
18644 | + * current action and perhaps also resetting the progress bar. | |
18645 | + */ | |
18646 | +static void userui_prepare_status(int clearbar, const char *fmt, ...) | |
18647 | +{ | |
18648 | + va_list args; | |
18649 | + | |
18650 | + if (fmt) { | |
18651 | + va_start(args, fmt); | |
18652 | + lastheader_message_len = vsnprintf(lastheader, 512, fmt, args); | |
18653 | + va_end(args); | |
18654 | + } | |
18655 | + | |
18656 | + if (clearbar) | |
18657 | + toi_update_status(0, 1, NULL); | |
18658 | + | |
18659 | + if (ui_helper_data.pid == -1) | |
18660 | + printk(KERN_EMERG "%s\n", lastheader); | |
18661 | + else | |
18662 | + toi_message(0, TOI_STATUS, 1, lastheader, NULL); | |
18663 | +} | |
18664 | + | |
18665 | +/** | |
18666 | + * toi_wait_for_keypress - Wait for keypress via userui. | |
18667 | + * | |
18668 | + * @timeout: Maximum time to wait. | |
18669 | + * | |
18670 | + * Wait for a keypress from userui. | |
18671 | + * | |
18672 | + * FIXME: Implement timeout? | |
24613191 | 18673 | + */ |
4e97e4e9 | 18674 | +static char userui_wait_for_keypress(int timeout) |
18675 | +{ | |
18676 | + char key = '\0'; | |
24613191 | 18677 | + |
4e97e4e9 | 18678 | + if (ui_helper_data.pid != -1) { |
18679 | + wait_for_key_via_userui(); | |
18680 | + key = ' '; | |
18681 | + } | |
ad8f4a28 | 18682 | + |
4e97e4e9 | 18683 | + return key; |
18684 | +} | |
24613191 | 18685 | + |
4e97e4e9 | 18686 | +/** |
18687 | + * userui_abort_hibernate - Abort a cycle & tell user if they didn't request it. | |
18688 | + * | |
18689 | + * @result_code: Reason why we're aborting (1 << bit). | |
18690 | + * @fmt: Message to display if telling the user what's going on. | |
18691 | + * | |
18692 | + * Abort a cycle. If this wasn't at the user's request (and we're displaying | |
18693 | + * output), tell the user why and wait for them to acknowledge the message. | |
18694 | + */ | |
18695 | +static void userui_abort_hibernate(int result_code, const char *fmt, ...) | |
24613191 | 18696 | +{ |
24613191 | 18697 | + va_list args; |
4e97e4e9 | 18698 | + int printed_len = 0; |
24613191 | 18699 | + |
4e97e4e9 | 18700 | + set_result_state(result_code); |
24613191 | 18701 | + |
4e97e4e9 | 18702 | + if (test_result_state(TOI_ABORTED)) |
18703 | + return; | |
24613191 | 18704 | + |
4e97e4e9 | 18705 | + set_result_state(TOI_ABORTED); |
24613191 | 18706 | + |
4e97e4e9 | 18707 | + if (test_result_state(TOI_ABORT_REQUESTED)) |
18708 | + return; | |
24613191 | 18709 | + |
4e97e4e9 | 18710 | + va_start(args, fmt); |
18711 | + printed_len = vsnprintf(local_printf_buf, sizeof(local_printf_buf), | |
18712 | + fmt, args); | |
18713 | + va_end(args); | |
18714 | + if (ui_helper_data.pid != -1) | |
18715 | + printed_len = sprintf(local_printf_buf + printed_len, | |
18716 | + " (Press SPACE to continue)"); | |
24613191 | 18717 | + |
7f9d2ee0 | 18718 | + toi_prepare_status(CLEAR_BAR, "%s", local_printf_buf); |
24613191 | 18719 | + |
4e97e4e9 | 18720 | + if (ui_helper_data.pid != -1) |
18721 | + userui_wait_for_keypress(0); | |
18722 | +} | |
24613191 | 18723 | + |
4e97e4e9 | 18724 | +/** |
18725 | + * request_abort_hibernate - Abort hibernating or resuming at user request. | |
18726 | + * | |
18727 | + * Handle the user requesting the cancellation of a hibernation or resume by | |
18728 | + * pressing escape. | |
18729 | + */ | |
18730 | +static void request_abort_hibernate(void) | |
18731 | +{ | |
18732 | + if (test_result_state(TOI_ABORT_REQUESTED)) | |
18733 | + return; | |
18734 | + | |
18735 | + if (test_toi_state(TOI_NOW_RESUMING)) { | |
18736 | + toi_prepare_status(CLEAR_BAR, "Escape pressed. " | |
18737 | + "Powering down again."); | |
18738 | + set_toi_state(TOI_STOP_RESUME); | |
18739 | + while (!test_toi_state(TOI_IO_STOPPED)) | |
18740 | + schedule(); | |
18741 | + if (toiActiveAllocator->mark_resume_attempted) | |
18742 | + toiActiveAllocator->mark_resume_attempted(0); | |
18743 | + toi_power_down(); | |
18744 | + } | |
18745 | + | |
18746 | + toi_prepare_status(CLEAR_BAR, "--- ESCAPE PRESSED :" | |
18747 | + " ABORTING HIBERNATION ---"); | |
18748 | + set_abort_result(TOI_ABORT_REQUESTED); | |
18749 | + wake_up_interruptible(&userui_wait_for_key); | |
24613191 | 18750 | +} |
24613191 | 18751 | + |
4e97e4e9 | 18752 | +/** |
18753 | + * userui_user_rcv_msg - Receive a netlink message from userui. | |
18754 | + * | |
18755 | + * @skb: skb received. | |
18756 | + * @nlh: Netlink header received. | |
24613191 | 18757 | + */ |
4e97e4e9 | 18758 | +static int userui_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) |
18759 | +{ | |
18760 | + int type; | |
18761 | + int *data; | |
24613191 | 18762 | + |
4e97e4e9 | 18763 | + type = nlh->nlmsg_type; |
24613191 | 18764 | + |
4e97e4e9 | 18765 | + /* A control message: ignore them */ |
18766 | + if (type < NETLINK_MSG_BASE) | |
18767 | + return 0; | |
24613191 | 18768 | + |
4e97e4e9 | 18769 | + /* Unknown message: reply with EINVAL */ |
18770 | + if (type >= USERUI_MSG_MAX) | |
18771 | + return -EINVAL; | |
24613191 | 18772 | + |
4e97e4e9 | 18773 | + /* All operations require privileges, even GET */ |
18774 | + if (security_netlink_recv(skb, CAP_NET_ADMIN)) | |
18775 | + return -EPERM; | |
24613191 | 18776 | + |
4e97e4e9 | 18777 | + /* Only allow one task to receive NOFREEZE privileges */ |
18778 | + if (type == NETLINK_MSG_NOFREEZE_ME && ui_helper_data.pid != -1) { | |
ad8f4a28 AM |
18779 | + printk(KERN_INFO "Got NOFREEZE_ME request when " |
18780 | + "ui_helper_data.pid is %d.\n", ui_helper_data.pid); | |
73c609d5 | 18781 | + return -EBUSY; |
18782 | + } | |
18783 | + | |
ad8f4a28 | 18784 | + data = (int *) NLMSG_DATA(nlh); |
73c609d5 | 18785 | + |
4e97e4e9 | 18786 | + switch (type) { |
ad8f4a28 AM |
18787 | + case USERUI_MSG_ABORT: |
18788 | + request_abort_hibernate(); | |
18789 | + return 0; | |
18790 | + case USERUI_MSG_GET_STATE: | |
18791 | + toi_send_netlink_message(&ui_helper_data, | |
18792 | + USERUI_MSG_GET_STATE, &toi_bkd.toi_action, | |
18793 | + sizeof(toi_bkd.toi_action)); | |
18794 | + return 0; | |
18795 | + case USERUI_MSG_GET_DEBUG_STATE: | |
18796 | + toi_send_netlink_message(&ui_helper_data, | |
18797 | + USERUI_MSG_GET_DEBUG_STATE, | |
18798 | + &toi_bkd.toi_debug_state, | |
18799 | + sizeof(toi_bkd.toi_debug_state)); | |
18800 | + return 0; | |
18801 | + case USERUI_MSG_SET_STATE: | |
18802 | + if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int))) | |
18803 | + return -EINVAL; | |
18804 | + ui_nl_set_state(*data); | |
18805 | + return 0; | |
18806 | + case USERUI_MSG_SET_DEBUG_STATE: | |
18807 | + if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int))) | |
18808 | + return -EINVAL; | |
18809 | + toi_bkd.toi_debug_state = (*data); | |
18810 | + return 0; | |
18811 | + case USERUI_MSG_SPACE: | |
18812 | + wake_up_interruptible(&userui_wait_for_key); | |
18813 | + return 0; | |
18814 | + case USERUI_MSG_GET_POWERDOWN_METHOD: | |
18815 | + toi_send_netlink_message(&ui_helper_data, | |
18816 | + USERUI_MSG_GET_POWERDOWN_METHOD, | |
18817 | + &toi_poweroff_method, | |
18818 | + sizeof(toi_poweroff_method)); | |
18819 | + return 0; | |
18820 | + case USERUI_MSG_SET_POWERDOWN_METHOD: | |
18821 | + if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int))) | |
18822 | + return -EINVAL; | |
18823 | + toi_poweroff_method = (*data); | |
18824 | + return 0; | |
18825 | + case USERUI_MSG_GET_LOGLEVEL: | |
18826 | + toi_send_netlink_message(&ui_helper_data, | |
18827 | + USERUI_MSG_GET_LOGLEVEL, | |
18828 | + &toi_bkd.toi_default_console_level, | |
18829 | + sizeof(toi_bkd.toi_default_console_level)); | |
18830 | + return 0; | |
18831 | + case USERUI_MSG_SET_LOGLEVEL: | |
18832 | + if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(int))) | |
18833 | + return -EINVAL; | |
18834 | + toi_bkd.toi_default_console_level = (*data); | |
18835 | + return 0; | |
18836 | + case USERUI_MSG_PRINTK: | |
1838f965 | 18837 | + printk("%s", (char *) data); |
ad8f4a28 | 18838 | + return 0; |
4e97e4e9 | 18839 | + } |
18840 | + | |
ad8f4a28 | 18841 | + /* Unhandled here */ |
4e97e4e9 | 18842 | + return 1; |
18843 | +} | |
18844 | + | |
18845 | +/** | |
18846 | + * userui_cond_pause - Possibly pause at user request. | |
18847 | + * | |
18848 | + * @pause: Whether to pause or just display the message. | |
18849 | + * @message: Message to display at the start of pausing. | |
ad8f4a28 | 18850 | + * |
4e97e4e9 | 18851 | + * Potentially pause and wait for the user to tell us to continue. We normally |
18852 | + * only pause when @pause is set. While paused, the user can do things like | |
18853 | + * changing the loglevel, toggling the display of debugging sections and such | |
18854 | + * like. | |
18855 | + */ | |
18856 | +static void userui_cond_pause(int pause, char *message) | |
18857 | +{ | |
18858 | + int displayed_message = 0, last_key = 0; | |
ad8f4a28 | 18859 | + |
4e97e4e9 | 18860 | + while (last_key != 32 && |
18861 | + ui_helper_data.pid != -1 && | |
ad8f4a28 | 18862 | + ((test_action_state(TOI_PAUSE) && pause) || |
4e97e4e9 | 18863 | + (test_action_state(TOI_SINGLESTEP)))) { |
18864 | + if (!displayed_message) { | |
ad8f4a28 | 18865 | + toi_prepare_status(DONT_CLEAR_BAR, |
4e97e4e9 | 18866 | + "%s Press SPACE to continue.%s", |
18867 | + message ? message : "", | |
ad8f4a28 | 18868 | + (test_action_state(TOI_SINGLESTEP)) ? |
4e97e4e9 | 18869 | + " Single step on." : ""); |
18870 | + displayed_message = 1; | |
18871 | + } | |
18872 | + last_key = userui_wait_for_keypress(0); | |
18873 | + } | |
18874 | + schedule(); | |
73c609d5 | 18875 | +} |
18876 | + | |
4e97e4e9 | 18877 | +/** |
18878 | + * userui_prepare_console - Prepare the console for use. | |
18879 | + * | |
18880 | + * Prepare a console for use, saving current kmsg settings and attempting to | |
18881 | + * start userui. Console loglevel changes are handled by userui. | |
18882 | + */ | |
18883 | +static void userui_prepare_console(void) | |
73c609d5 | 18884 | +{ |
4e97e4e9 | 18885 | + orig_kmsg = kmsg_redirect; |
18886 | + kmsg_redirect = fg_console + 1; | |
18887 | + | |
18888 | + ui_helper_data.pid = -1; | |
18889 | + | |
18890 | + if (!userui_ops.enabled) { | |
18891 | + printk("TuxOnIce: Userui disabled.\n"); | |
73c609d5 | 18892 | + return; |
4e97e4e9 | 18893 | + } |
73c609d5 | 18894 | + |
4e97e4e9 | 18895 | + if (*ui_helper_data.program) |
18896 | + toi_netlink_setup(&ui_helper_data); | |
18897 | + else | |
ad8f4a28 | 18898 | + printk(KERN_INFO "TuxOnIce: Userui program not configured.\n"); |
73c609d5 | 18899 | +} |
18900 | + | |
4e97e4e9 | 18901 | +/** |
18902 | + * userui_cleanup_console - Cleanup after a cycle. | |
18903 | + * | |
18904 | + * Tell userui to cleanup, and restore kmsg_redirect to its original value. | |
24613191 | 18905 | + */ |
18906 | + | |
4e97e4e9 | 18907 | +static void userui_cleanup_console(void) |
24613191 | 18908 | +{ |
4e97e4e9 | 18909 | + if (ui_helper_data.pid > -1) |
18910 | + toi_netlink_close(&ui_helper_data); | |
24613191 | 18911 | + |
4e97e4e9 | 18912 | + kmsg_redirect = orig_kmsg; |
24613191 | 18913 | +} |
18914 | + | |
24613191 | 18915 | +/* |
4e97e4e9 | 18916 | + * User interface specific /sys/power/tuxonice entries. |
24613191 | 18917 | + */ |
18918 | + | |
4e97e4e9 | 18919 | +static struct toi_sysfs_data sysfs_params[] = { |
18920 | +#if defined(CONFIG_NET) && defined(CONFIG_SYSFS) | |
1838f965 | 18921 | + SYSFS_BIT("enable_escape", SYSFS_RW, &toi_bkd.toi_action, |
18922 | + TOI_CAN_CANCEL, 0), | |
18923 | + SYSFS_BIT("pause_between_steps", SYSFS_RW, &toi_bkd.toi_action, | |
18924 | + TOI_PAUSE, 0), | |
18925 | + SYSFS_INT("enabled", SYSFS_RW, &userui_ops.enabled, 0, 1, 0, NULL), | |
18926 | + SYSFS_INT("progress_granularity", SYSFS_RW, &progress_granularity, 1, | |
18927 | + 2048, 0, NULL), | |
18928 | + SYSFS_STRING("program", SYSFS_RW, ui_helper_data.program, 255, 0, | |
18929 | + set_ui_program_set), | |
18930 | + SYSFS_INT("debug", SYSFS_RW, &ui_helper_data.debug, 0, 1, 0, NULL) | |
4e97e4e9 | 18931 | +#endif |
73c609d5 | 18932 | +}; |
18933 | + | |
4e97e4e9 | 18934 | +static struct toi_module_ops userui_ops = { |
18935 | + .type = MISC_MODULE, | |
18936 | + .name = "userui", | |
18937 | + .shared_directory = "user_interface", | |
18938 | + .module = THIS_MODULE, | |
18939 | + .storage_needed = userui_storage_needed, | |
18940 | + .save_config_info = userui_save_config_info, | |
18941 | + .load_config_info = userui_load_config_info, | |
18942 | + .memory_needed = userui_memory_needed, | |
18943 | + .sysfs_data = sysfs_params, | |
ad8f4a28 AM |
18944 | + .num_sysfs_entries = sizeof(sysfs_params) / |
18945 | + sizeof(struct toi_sysfs_data), | |
4e97e4e9 | 18946 | +}; |
73c609d5 | 18947 | + |
4e97e4e9 | 18948 | +static struct ui_ops my_ui_ops = { |
18949 | + .post_atomic_restore = userui_post_atomic_restore, | |
18950 | + .update_status = userui_update_status, | |
18951 | + .message = userui_message, | |
18952 | + .prepare_status = userui_prepare_status, | |
18953 | + .abort = userui_abort_hibernate, | |
18954 | + .cond_pause = userui_cond_pause, | |
18955 | + .prepare = userui_prepare_console, | |
18956 | + .cleanup = userui_cleanup_console, | |
18957 | + .wait_for_key = userui_wait_for_keypress, | |
18958 | +}; | |
73c609d5 | 18959 | + |
4e97e4e9 | 18960 | +/** |
18961 | + * toi_user_ui_init - Boot time initialisation for user interface. | |
18962 | + * | |
18963 | + * Invoked from the core init routine. | |
18964 | + */ | |
18965 | +static __init int toi_user_ui_init(void) | |
18966 | +{ | |
18967 | + int result; | |
73c609d5 | 18968 | + |
4e97e4e9 | 18969 | + ui_helper_data.nl = NULL; |
ad8f4a28 | 18970 | + strncpy(ui_helper_data.program, CONFIG_TOI_USERUI_DEFAULT_PATH, 255); |
4e97e4e9 | 18971 | + ui_helper_data.pid = -1; |
18972 | + ui_helper_data.skb_size = sizeof(struct userui_msg_params); | |
18973 | + ui_helper_data.pool_limit = 6; | |
18974 | + ui_helper_data.netlink_id = NETLINK_TOI_USERUI; | |
18975 | + ui_helper_data.name = "userspace ui"; | |
18976 | + ui_helper_data.rcv_msg = userui_user_rcv_msg; | |
1838f965 | 18977 | + ui_helper_data.interface_version = 8; |
4e97e4e9 | 18978 | + ui_helper_data.must_init = 0; |
18979 | + ui_helper_data.not_ready = userui_cleanup_console; | |
18980 | + init_completion(&ui_helper_data.wait_for_process); | |
18981 | + result = toi_register_module(&userui_ops); | |
18982 | + if (!result) | |
18983 | + result = toi_register_ui_ops(&my_ui_ops); | |
18984 | + if (result) | |
18985 | + toi_unregister_module(&userui_ops); | |
24613191 | 18986 | + |
4e97e4e9 | 18987 | + return result; |
18988 | +} | |
24613191 | 18989 | + |
4e97e4e9 | 18990 | +#ifdef MODULE |
18991 | +/** | |
18992 | + * toi_user_ui_ext - Cleanup code for if the core is unloaded. | |
18993 | + */ | |
18994 | +static __exit void toi_user_ui_exit(void) | |
18995 | +{ | |
f3e0dcc9 | 18996 | + toi_netlink_close_complete(&ui_helper_data); |
4e97e4e9 | 18997 | + toi_remove_ui_ops(&my_ui_ops); |
18998 | + toi_unregister_module(&userui_ops); | |
18999 | +} | |
24613191 | 19000 | + |
4e97e4e9 | 19001 | +module_init(toi_user_ui_init); |
19002 | +module_exit(toi_user_ui_exit); | |
19003 | +MODULE_AUTHOR("Nigel Cunningham"); | |
19004 | +MODULE_DESCRIPTION("TuxOnIce Userui Support"); | |
19005 | +MODULE_LICENSE("GPL"); | |
19006 | +#else | |
19007 | +late_initcall(toi_user_ui_init); | |
19008 | +#endif | |
1838f965 | 19009 | diff --git a/kernel/power/user.c b/kernel/power/user.c |
19010 | index a6332a3..66f4eb6 100644 | |
19011 | --- a/kernel/power/user.c | |
19012 | +++ b/kernel/power/user.c | |
19013 | @@ -64,6 +64,7 @@ static struct snapshot_data { | |
19014 | } snapshot_state; | |
19015 | ||
19016 | atomic_t snapshot_device_available = ATOMIC_INIT(1); | |
19017 | +EXPORT_SYMBOL_GPL(snapshot_device_available); | |
19018 | ||
19019 | static int snapshot_open(struct inode *inode, struct file *filp) | |
19020 | { | |
4e97e4e9 | 19021 | diff --git a/kernel/printk.c b/kernel/printk.c |
1838f965 | 19022 | index b51b156..bc78cb3 100644 |
4e97e4e9 | 19023 | --- a/kernel/printk.c |
19024 | +++ b/kernel/printk.c | |
1838f965 | 19025 | @@ -32,6 +32,7 @@ |
7f9d2ee0 | 19026 | #include <linux/security.h> |
24613191 | 19027 | #include <linux/bootmem.h> |
19028 | #include <linux/syscalls.h> | |
24613191 | 19029 | +#include <linux/suspend.h> |
19030 | ||
19031 | #include <asm/uaccess.h> | |
19032 | ||
1838f965 | 19033 | @@ -59,6 +60,7 @@ int console_printk[4] = { |
19034 | MINIMUM_CONSOLE_LOGLEVEL, /* minimum_console_loglevel */ | |
19035 | DEFAULT_CONSOLE_LOGLEVEL, /* default_console_loglevel */ | |
19036 | }; | |
19037 | +EXPORT_SYMBOL_GPL(console_printk); | |
24613191 | 19038 | |
19039 | /* | |
1838f965 | 19040 | * Low level drivers may need that to know if they can schedule in |
19041 | @@ -937,6 +939,7 @@ void suspend_console(void) | |
e8d0ad9d | 19042 | acquire_console_sem(); |
19043 | console_suspended = 1; | |
19044 | } | |
1838f965 | 19045 | +EXPORT_SYMBOL_GPL(suspend_console); |
e8d0ad9d | 19046 | |
19047 | void resume_console(void) | |
19048 | { | |
1838f965 | 19049 | @@ -945,6 +948,7 @@ void resume_console(void) |
e8d0ad9d | 19050 | console_suspended = 0; |
19051 | release_console_sem(); | |
19052 | } | |
1838f965 | 19053 | +EXPORT_SYMBOL_GPL(resume_console); |
e8d0ad9d | 19054 | |
19055 | /** | |
ad8f4a28 | 19056 | * acquire_console_sem - lock the console system for exclusive use. |
4e97e4e9 | 19057 | diff --git a/kernel/timer.c b/kernel/timer.c |
fea155ea | 19058 | index 03bc7f1..d70831d 100644 |
4e97e4e9 | 19059 | --- a/kernel/timer.c |
19060 | +++ b/kernel/timer.c | |
ad8f4a28 | 19061 | @@ -37,6 +37,8 @@ |
4e97e4e9 | 19062 | #include <linux/delay.h> |
19063 | #include <linux/tick.h> | |
19064 | #include <linux/kallsyms.h> | |
19065 | +#include <linux/notifier.h> | |
19066 | +#include <linux/suspend.h> | |
19067 | ||
19068 | #include <asm/uaccess.h> | |
19069 | #include <asm/unistd.h> | |
fea155ea | 19070 | @@ -1002,6 +1004,59 @@ unsigned long avenrun[3]; |
24613191 | 19071 | |
e8d0ad9d | 19072 | EXPORT_SYMBOL(avenrun); |
19073 | ||
4e97e4e9 | 19074 | +#ifdef CONFIG_PM |
e8d0ad9d | 19075 | +static unsigned long avenrun_save[3]; |
19076 | +/* | |
19077 | + * save_avenrun - Record the values prior to starting a hibernation cycle. | |
19078 | + * We do this to make the work done in hibernation invisible to userspace | |
19079 | + * post-suspend. Some programs, including some MTAs, watch the load average | |
19080 | + * and stop work until it lowers. Without this, they would stop working for | |
19081 | + * a while post-resume, unnecessarily. | |
19082 | + */ | |
19083 | + | |
4e97e4e9 | 19084 | +static void save_avenrun(void) |
e8d0ad9d | 19085 | +{ |
19086 | + avenrun_save[0] = avenrun[0]; | |
19087 | + avenrun_save[1] = avenrun[1]; | |
19088 | + avenrun_save[2] = avenrun[2]; | |
19089 | +} | |
19090 | + | |
4e97e4e9 | 19091 | +static void restore_avenrun(void) |
e8d0ad9d | 19092 | +{ |
19093 | + if (!avenrun_save[0]) | |
19094 | + return; | |
19095 | + | |
19096 | + avenrun[0] = avenrun_save[0]; | |
19097 | + avenrun[1] = avenrun_save[1]; | |
19098 | + avenrun[2] = avenrun_save[2]; | |
19099 | + | |
19100 | + avenrun_save[0] = 0; | |
19101 | +} | |
19102 | + | |
4e97e4e9 | 19103 | +static int avenrun_pm_callback(struct notifier_block *nfb, |
19104 | + unsigned long action, | |
19105 | + void *ignored) | |
19106 | +{ | |
19107 | + switch (action) { | |
19108 | + case PM_HIBERNATION_PREPARE: | |
19109 | + save_avenrun(); | |
19110 | + return NOTIFY_OK; | |
19111 | + case PM_POST_HIBERNATION: | |
19112 | + restore_avenrun(); | |
19113 | + return NOTIFY_OK; | |
19114 | + } | |
19115 | + | |
19116 | + return NOTIFY_DONE; | |
19117 | +} | |
19118 | + | |
19119 | +static void register_pm_notifier_callback(void) | |
19120 | +{ | |
19121 | + pm_notifier(avenrun_pm_callback, 0); | |
19122 | +} | |
19123 | +#else | |
19124 | +static inline void register_pm_notifier_callback(void) { } | |
19125 | +#endif | |
e8d0ad9d | 19126 | + |
19127 | /* | |
19128 | * calc_load - given tick count, update the avenrun load estimates. | |
19129 | * This is called while holding a write_lock on xtime_lock. | |
fea155ea | 19130 | @@ -1495,6 +1550,7 @@ void __init init_timers(void) |
4e97e4e9 | 19131 | BUG_ON(err == NOTIFY_BAD); |
19132 | register_cpu_notifier(&timers_nb); | |
fea155ea | 19133 | open_softirq(TIMER_SOFTIRQ, run_timer_softirq); |
4e97e4e9 | 19134 | + register_pm_notifier_callback(); |
19135 | } | |
24613191 | 19136 | |
4e97e4e9 | 19137 | /** |
1838f965 | 19138 | diff --git a/mm/bootmem.c b/mm/bootmem.c |
19139 | index ad8eec6..5d7d040 100644 | |
19140 | --- a/mm/bootmem.c | |
19141 | +++ b/mm/bootmem.c | |
19142 | @@ -22,6 +22,7 @@ | |
19143 | unsigned long max_low_pfn; | |
19144 | unsigned long min_low_pfn; | |
19145 | unsigned long max_pfn; | |
19146 | +EXPORT_SYMBOL_GPL(max_pfn); | |
19147 | ||
19148 | #ifdef CONFIG_CRASH_DUMP | |
19149 | /* | |
19150 | diff --git a/mm/highmem.c b/mm/highmem.c | |
19151 | index e16e152..cab4227 100644 | |
19152 | --- a/mm/highmem.c | |
19153 | +++ b/mm/highmem.c | |
19154 | @@ -58,6 +58,7 @@ unsigned int nr_free_highpages (void) | |
19155 | ||
19156 | return pages; | |
4e97e4e9 | 19157 | } |
1838f965 | 19158 | +EXPORT_SYMBOL_GPL(nr_free_highpages); |
4e97e4e9 | 19159 | |
1838f965 | 19160 | static int pkmap_count[LAST_PKMAP]; |
19161 | static unsigned int last_pkmap_nr; | |
19162 | diff --git a/mm/memory.c b/mm/memory.c | |
19163 | index 1002f47..034de70 100644 | |
19164 | --- a/mm/memory.c | |
19165 | +++ b/mm/memory.c | |
19166 | @@ -1110,6 +1110,7 @@ no_page_table: | |
19167 | } | |
19168 | return page; | |
19169 | } | |
19170 | +EXPORT_SYMBOL_GPL(follow_page); | |
24613191 | 19171 | |
1838f965 | 19172 | /* Can we do the FOLL_ANON optimization? */ |
19173 | static inline int use_zero_page(struct vm_area_struct *vma) | |
19174 | diff --git a/mm/mmzone.c b/mm/mmzone.c | |
19175 | index 16ce8b9..8dd207b 100644 | |
19176 | --- a/mm/mmzone.c | |
19177 | +++ b/mm/mmzone.c | |
19178 | @@ -13,6 +13,7 @@ struct pglist_data *first_online_pgdat(void) | |
19179 | { | |
19180 | return NODE_DATA(first_online_node); | |
19181 | } | |
19182 | +EXPORT_SYMBOL_GPL(first_online_pgdat); | |
19183 | ||
19184 | struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) | |
19185 | { | |
19186 | @@ -22,6 +23,7 @@ struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) | |
19187 | return NULL; | |
19188 | return NODE_DATA(nid); | |
4e97e4e9 | 19189 | } |
1838f965 | 19190 | +EXPORT_SYMBOL_GPL(next_online_pgdat); |
19191 | ||
19192 | /* | |
19193 | * next_zone - helper magic for for_each_zone() | |
19194 | @@ -41,6 +43,7 @@ struct zone *next_zone(struct zone *zone) | |
19195 | } | |
19196 | return zone; | |
19197 | } | |
19198 | +EXPORT_SYMBOL_GPL(next_zone); | |
19199 | ||
19200 | static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes) | |
19201 | { | |
19202 | diff --git a/mm/page-writeback.c b/mm/page-writeback.c | |
19203 | index 24de8b6..048fada 100644 | |
19204 | --- a/mm/page-writeback.c | |
19205 | +++ b/mm/page-writeback.c | |
19206 | @@ -93,6 +93,7 @@ int dirty_expire_interval = 30 * HZ; | |
19207 | * Flag that makes the machine dump writes/reads and block dirtyings. | |
19208 | */ | |
19209 | int block_dump; | |
19210 | +EXPORT_SYMBOL_GPL(block_dump); | |
4e97e4e9 | 19211 | |
1838f965 | 19212 | /* |
19213 | * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: | |
ad8f4a28 | 19214 | diff --git a/mm/page_alloc.c b/mm/page_alloc.c |
1838f965 | 19215 | index 51daae5..6c73ebd 100644 |
ad8f4a28 AM |
19216 | --- a/mm/page_alloc.c |
19217 | +++ b/mm/page_alloc.c | |
1838f965 | 19218 | @@ -1791,6 +1791,26 @@ static unsigned int nr_free_zone_pages(int offset) |
ad8f4a28 AM |
19219 | return sum; |
19220 | } | |
19221 | ||
19222 | +static unsigned int nr_unallocated_zone_pages(int offset) | |
19223 | +{ | |
f3e0dcc9 PS |
19224 | + struct zoneref *z; |
19225 | + struct zone *zone; | |
19226 | + | |
ad8f4a28 | 19227 | + /* Just pick one node, since fallback list is circular */ |
ad8f4a28 AM |
19228 | + unsigned int sum = 0; |
19229 | + | |
f3e0dcc9 | 19230 | + struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL); |
ad8f4a28 | 19231 | + |
f3e0dcc9 | 19232 | + for_each_zone_zonelist(zone, z, zonelist, offset) { |
ad8f4a28 AM |
19233 | + unsigned long high = zone->pages_high; |
19234 | + unsigned long left = zone_page_state(zone, NR_FREE_PAGES); | |
19235 | + if (left > high) | |
19236 | + sum += left - high; | |
19237 | + } | |
19238 | + | |
19239 | + return sum; | |
19240 | +} | |
19241 | + | |
19242 | /* | |
19243 | * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL | |
19244 | */ | |
1838f965 | 19245 | @@ -1801,6 +1821,15 @@ unsigned int nr_free_buffer_pages(void) |
ad8f4a28 AM |
19246 | EXPORT_SYMBOL_GPL(nr_free_buffer_pages); |
19247 | ||
19248 | /* | |
19249 | + * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL | |
19250 | + */ | |
19251 | +unsigned int nr_unallocated_buffer_pages(void) | |
19252 | +{ | |
19253 | + return nr_unallocated_zone_pages(gfp_zone(GFP_USER)); | |
19254 | +} | |
19255 | +EXPORT_SYMBOL_GPL(nr_unallocated_buffer_pages); | |
19256 | + | |
19257 | +/* | |
19258 | * Amount of free RAM allocatable within all zones | |
19259 | */ | |
19260 | unsigned int nr_free_pagecache_pages(void) | |
1838f965 | 19261 | diff --git a/mm/swapfile.c b/mm/swapfile.c |
19262 | index 1e330f2..dcead18 100644 | |
19263 | --- a/mm/swapfile.c | |
19264 | +++ b/mm/swapfile.c | |
19265 | @@ -213,6 +213,7 @@ noswap: | |
19266 | spin_unlock(&swap_lock); | |
19267 | return (swp_entry_t) {0}; | |
24613191 | 19268 | } |
1838f965 | 19269 | +EXPORT_SYMBOL_GPL(get_swap_page); |
24613191 | 19270 | |
1838f965 | 19271 | swp_entry_t get_swap_page_of_type(int type) |
19272 | { | |
19273 | @@ -305,6 +306,7 @@ void swap_free(swp_entry_t entry) | |
19274 | spin_unlock(&swap_lock); | |
19275 | } | |
24613191 | 19276 | } |
1838f965 | 19277 | +EXPORT_SYMBOL_GPL(swap_free); |
24613191 | 19278 | |
24613191 | 19279 | /* |
1838f965 | 19280 | * How many references to page are currently swapped out? |
19281 | @@ -982,6 +984,7 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) | |
19282 | BUG_ON(se == start_se); /* It *must* be present */ | |
19283 | } | |
19284 | } | |
19285 | +EXPORT_SYMBOL_GPL(map_swap_page); | |
19286 | ||
19287 | #ifdef CONFIG_HIBERNATION | |
19288 | /* | |
19289 | @@ -1342,6 +1345,7 @@ out_dput: | |
19290 | out: | |
19291 | return err; | |
19292 | } | |
19293 | +EXPORT_SYMBOL_GPL(sys_swapoff); | |
19294 | ||
19295 | #ifdef CONFIG_PROC_FS | |
19296 | /* iterator */ | |
19297 | @@ -1732,6 +1736,7 @@ out: | |
19298 | } | |
19299 | return error; | |
19300 | } | |
19301 | +EXPORT_SYMBOL_GPL(sys_swapon); | |
19302 | ||
19303 | void si_swapinfo(struct sysinfo *val) | |
19304 | { | |
19305 | @@ -1749,6 +1754,7 @@ void si_swapinfo(struct sysinfo *val) | |
19306 | val->totalswap = total_swap_pages + nr_to_be_unused; | |
19307 | spin_unlock(&swap_lock); | |
19308 | } | |
19309 | +EXPORT_SYMBOL_GPL(si_swapinfo); | |
19310 | ||
19311 | /* | |
19312 | * Verify that a swap entry is valid and increment its swap map count. | |
19313 | @@ -1797,6 +1803,7 @@ get_swap_info_struct(unsigned type) | |
19314 | { | |
19315 | return &swap_info[type]; | |
19316 | } | |
19317 | +EXPORT_SYMBOL_GPL(get_swap_info_struct); | |
19318 | ||
19319 | /* | |
19320 | * swap_lock prevents swap_map being freed. Don't grab an extra | |
19321 | diff --git a/mm/vmscan.c b/mm/vmscan.c | |
19322 | index 1ff1a58..6d718c1 100644 | |
19323 | --- a/mm/vmscan.c | |
19324 | +++ b/mm/vmscan.c | |
19325 | @@ -1749,6 +1749,9 @@ void wakeup_kswapd(struct zone *zone, int order) | |
e8d0ad9d | 19326 | if (!populated_zone(zone)) |
19327 | return; | |
19328 | ||
19329 | + if (freezer_is_on()) | |
19330 | + return; | |
19331 | + | |
19332 | pgdat = zone->zone_pgdat; | |
19333 | if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0)) | |
19334 | return; | |
1838f965 | 19335 | @@ -1910,6 +1913,7 @@ out: |
19336 | ||
19337 | return ret; | |
24613191 | 19338 | } |
1838f965 | 19339 | +EXPORT_SYMBOL_GPL(shrink_all_memory); |
19340 | #endif | |
24613191 | 19341 | |
1838f965 | 19342 | /* It's optimal to keep kswapds on the same CPUs as their memory, but |