blob: f8a674d7f092441fb5fb3ba2a35d3da3f9175e1a [file] [log] [blame]
David Chinner2a82b8b2007-07-11 11:09:12 +10001/*
2 * Copyright (c) 2006-2007 Silicon Graphics, Inc.
3 * All Rights Reserved.
4 *
5 * This program is free software; you can redistribute it and/or
6 * modify it under the terms of the GNU General Public License as
7 * published by the Free Software Foundation.
8 *
9 * This program is distributed in the hope that it would be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
13 *
14 * You should have received a copy of the GNU General Public License
15 * along with this program; if not, write the Free Software Foundation,
16 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
17 */
18#include "xfs.h"
19#include "xfs_mru_cache.h"
20
21/*
22 * The MRU Cache data structure consists of a data store, an array of lists and
23 * a lock to protect its internal state. At initialisation time, the client
24 * supplies an element lifetime in milliseconds and a group count, as well as a
25 * function pointer to call when deleting elements. A data structure for
26 * queueing up work in the form of timed callbacks is also included.
27 *
28 * The group count controls how many lists are created, and thereby how finely
29 * the elements are grouped in time. When reaping occurs, all the elements in
30 * all the lists whose time has expired are deleted.
31 *
32 * To give an example of how this works in practice, consider a client that
33 * initialises an MRU Cache with a lifetime of ten seconds and a group count of
34 * five. Five internal lists will be created, each representing a two second
35 * period in time. When the first element is added, time zero for the data
36 * structure is initialised to the current time.
37 *
38 * All the elements added in the first two seconds are appended to the first
39 * list. Elements added in the third second go into the second list, and so on.
40 * If an element is accessed at any point, it is removed from its list and
41 * inserted at the head of the current most-recently-used list.
42 *
43 * The reaper function will have nothing to do until at least twelve seconds
44 * have elapsed since the first element was added. The reason for this is that
45 * if it were called at t=11s, there could be elements in the first list that
46 * have only been inactive for nine seconds, so it still does nothing. If it is
47 * called anywhere between t=12 and t=14 seconds, it will delete all the
48 * elements that remain in the first list. It's therefore possible for elements
49 * to remain in the data store even after they've been inactive for up to
50 * (t + t/g) seconds, where t is the inactive element lifetime and g is the
51 * number of groups.
52 *
53 * The above example assumes that the reaper function gets called at least once
54 * every (t/g) seconds. If it is called less frequently, unused elements will
55 * accumulate in the reap list until the reaper function is eventually called.
56 * The current implementation uses work queue callbacks to carefully time the
57 * reaper function calls, so this should happen rarely, if at all.
58 *
59 * From a design perspective, the primary reason for the choice of a list array
60 * representing discrete time intervals is that it's only practical to reap
61 * expired elements in groups of some appreciable size. This automatically
62 * introduces a granularity to element lifetimes, so there's no point storing an
63 * individual timeout with each element that specifies a more precise reap time.
64 * The bonus is a saving of sizeof(long) bytes of memory per element stored.
65 *
66 * The elements could have been stored in just one list, but an array of
67 * counters or pointers would need to be maintained to allow them to be divided
68 * up into discrete time groups. More critically, the process of touching or
69 * removing an element would involve walking large portions of the entire list,
70 * which would have a detrimental effect on performance. The additional memory
71 * requirement for the array of list heads is minimal.
72 *
73 * When an element is touched or deleted, it needs to be removed from its
74 * current list. Doubly linked lists are used to make the list maintenance
75 * portion of these operations O(1). Since reaper timing can be imprecise,
76 * inserts and lookups can occur when there are no free lists available. When
77 * this happens, all the elements on the LRU list need to be migrated to the end
78 * of the reap list. To keep the list maintenance portion of these operations
79 * O(1) also, list tails need to be accessible without walking the entire list.
80 * This is the reason why doubly linked list heads are used.
81 */
82
83/*
84 * An MRU Cache is a dynamic data structure that stores its elements in a way
85 * that allows efficient lookups, but also groups them into discrete time
86 * intervals based on insertion time. This allows elements to be efficiently
87 * and automatically reaped after a fixed period of inactivity.
88 *
89 * When a client data pointer is stored in the MRU Cache it needs to be added to
90 * both the data store and to one of the lists. It must also be possible to
91 * access each of these entries via the other, i.e. to:
92 *
93 * a) Walk a list, removing the corresponding data store entry for each item.
94 * b) Look up a data store entry, then access its list entry directly.
95 *
96 * To achieve both of these goals, each entry must contain both a list entry and
97 * a key, in addition to the user's data pointer. Note that it's not a good
98 * idea to have the client embed one of these structures at the top of their own
99 * data structure, because inserting the same item more than once would most
100 * likely result in a loop in one of the lists. That's a sure-fire recipe for
101 * an infinite loop in the code.
102 */
Christoph Hellwig22328d72014-04-23 07:11:51 +1000103struct xfs_mru_cache {
104 struct radix_tree_root store; /* Core storage data structure. */
105 struct list_head *lists; /* Array of lists, one per grp. */
106 struct list_head reap_list; /* Elements overdue for reaping. */
107 spinlock_t lock; /* Lock to protect this struct. */
108 unsigned int grp_count; /* Number of discrete groups. */
109 unsigned int grp_time; /* Time period spanned by grps. */
110 unsigned int lru_grp; /* Group containing time zero. */
111 unsigned long time_zero; /* Time first element was added. */
112 xfs_mru_cache_free_func_t free_func; /* Function pointer for freeing. */
113 struct delayed_work work; /* Workqueue data for reaping. */
114 unsigned int queued; /* work has been queued */
115};
David Chinner2a82b8b2007-07-11 11:09:12 +1000116
David Chinner2a82b8b2007-07-11 11:09:12 +1000117static struct workqueue_struct *xfs_mru_reap_wq;
118
119/*
120 * When inserting, destroying or reaping, it's first necessary to update the
121 * lists relative to a particular time. In the case of destroying, that time
122 * will be well in the future to ensure that all items are moved to the reap
123 * list. In all other cases though, the time will be the current time.
124 *
125 * This function enters a loop, moving the contents of the LRU list to the reap
126 * list again and again until either a) the lists are all empty, or b) time zero
127 * has been advanced sufficiently to be within the immediate element lifetime.
128 *
129 * Case a) above is detected by counting how many groups are migrated and
130 * stopping when they've all been moved. Case b) is detected by monitoring the
131 * time_zero field, which is updated as each group is migrated.
132 *
133 * The return value is the earliest time that more migration could be needed, or
134 * zero if there's no need to schedule more work because the lists are empty.
135 */
136STATIC unsigned long
137_xfs_mru_cache_migrate(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000138 struct xfs_mru_cache *mru,
139 unsigned long now)
David Chinner2a82b8b2007-07-11 11:09:12 +1000140{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000141 unsigned int grp;
142 unsigned int migrated = 0;
143 struct list_head *lru_list;
David Chinner2a82b8b2007-07-11 11:09:12 +1000144
145 /* Nothing to do if the data store is empty. */
146 if (!mru->time_zero)
147 return 0;
148
149 /* While time zero is older than the time spanned by all the lists. */
150 while (mru->time_zero <= now - mru->grp_count * mru->grp_time) {
151
152 /*
153 * If the LRU list isn't empty, migrate its elements to the tail
154 * of the reap list.
155 */
156 lru_list = mru->lists + mru->lru_grp;
157 if (!list_empty(lru_list))
158 list_splice_init(lru_list, mru->reap_list.prev);
159
160 /*
161 * Advance the LRU group number, freeing the old LRU list to
162 * become the new MRU list; advance time zero accordingly.
163 */
164 mru->lru_grp = (mru->lru_grp + 1) % mru->grp_count;
165 mru->time_zero += mru->grp_time;
166
167 /*
168 * If reaping is so far behind that all the elements on all the
169 * lists have been migrated to the reap list, it's now empty.
170 */
171 if (++migrated == mru->grp_count) {
172 mru->lru_grp = 0;
173 mru->time_zero = 0;
174 return 0;
175 }
176 }
177
178 /* Find the first non-empty list from the LRU end. */
179 for (grp = 0; grp < mru->grp_count; grp++) {
180
181 /* Check the grp'th list from the LRU end. */
182 lru_list = mru->lists + ((mru->lru_grp + grp) % mru->grp_count);
183 if (!list_empty(lru_list))
184 return mru->time_zero +
185 (mru->grp_count + grp) * mru->grp_time;
186 }
187
188 /* All the lists must be empty. */
189 mru->lru_grp = 0;
190 mru->time_zero = 0;
191 return 0;
192}
193
194/*
195 * When inserting or doing a lookup, an element needs to be inserted into the
196 * MRU list. The lists must be migrated first to ensure that they're
197 * up-to-date, otherwise the new element could be given a shorter lifetime in
198 * the cache than it should.
199 */
200STATIC void
201_xfs_mru_cache_list_insert(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000202 struct xfs_mru_cache *mru,
203 struct xfs_mru_cache_elem *elem)
David Chinner2a82b8b2007-07-11 11:09:12 +1000204{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000205 unsigned int grp = 0;
206 unsigned long now = jiffies;
David Chinner2a82b8b2007-07-11 11:09:12 +1000207
208 /*
209 * If the data store is empty, initialise time zero, leave grp set to
210 * zero and start the work queue timer if necessary. Otherwise, set grp
211 * to the number of group times that have elapsed since time zero.
212 */
213 if (!_xfs_mru_cache_migrate(mru, now)) {
214 mru->time_zero = now;
David Chinner65de5562007-08-16 15:21:11 +1000215 if (!mru->queued) {
216 mru->queued = 1;
217 queue_delayed_work(xfs_mru_reap_wq, &mru->work,
218 mru->grp_count * mru->grp_time);
219 }
David Chinner2a82b8b2007-07-11 11:09:12 +1000220 } else {
221 grp = (now - mru->time_zero) / mru->grp_time;
222 grp = (mru->lru_grp + grp) % mru->grp_count;
223 }
224
225 /* Insert the element at the tail of the corresponding list. */
226 list_add_tail(&elem->list_node, mru->lists + grp);
227}
228
229/*
230 * When destroying or reaping, all the elements that were migrated to the reap
231 * list need to be deleted. For each element this involves removing it from the
232 * data store, removing it from the reap list, calling the client's free
233 * function and deleting the element from the element zone.
David Chinnera8272ce2007-11-23 16:28:09 +1100234 *
235 * We get called holding the mru->lock, which we drop and then reacquire.
236 * Sparse need special help with this to tell it we know what we are doing.
David Chinner2a82b8b2007-07-11 11:09:12 +1000237 */
238STATIC void
239_xfs_mru_cache_clear_reap_list(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000240 struct xfs_mru_cache *mru)
241 __releases(mru->lock) __acquires(mru->lock)
David Chinner2a82b8b2007-07-11 11:09:12 +1000242{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000243 struct xfs_mru_cache_elem *elem, *next;
David Chinner2a82b8b2007-07-11 11:09:12 +1000244 struct list_head tmp;
245
246 INIT_LIST_HEAD(&tmp);
247 list_for_each_entry_safe(elem, next, &mru->reap_list, list_node) {
248
249 /* Remove the element from the data store. */
250 radix_tree_delete(&mru->store, elem->key);
251
252 /*
253 * remove to temp list so it can be freed without
254 * needing to hold the lock
255 */
256 list_move(&elem->list_node, &tmp);
257 }
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000258 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000259
260 list_for_each_entry_safe(elem, next, &tmp, list_node) {
David Chinner2a82b8b2007-07-11 11:09:12 +1000261 list_del_init(&elem->list_node);
Christoph Hellwig22328d72014-04-23 07:11:51 +1000262 mru->free_func(elem);
David Chinner2a82b8b2007-07-11 11:09:12 +1000263 }
264
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000265 spin_lock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000266}
267
268/*
269 * We fire the reap timer every group expiry interval so
270 * we always have a reaper ready to run. This makes shutdown
271 * and flushing of the reaper easy to do. Hence we need to
272 * keep when the next reap must occur so we can determine
273 * at each interval whether there is anything we need to do.
274 */
275STATIC void
276_xfs_mru_cache_reap(
277 struct work_struct *work)
278{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000279 struct xfs_mru_cache *mru =
280 container_of(work, struct xfs_mru_cache, work.work);
David Chinner65de5562007-08-16 15:21:11 +1000281 unsigned long now, next;
David Chinner2a82b8b2007-07-11 11:09:12 +1000282
283 ASSERT(mru && mru->lists);
284 if (!mru || !mru->lists)
285 return;
286
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000287 spin_lock(&mru->lock);
David Chinner65de5562007-08-16 15:21:11 +1000288 next = _xfs_mru_cache_migrate(mru, jiffies);
289 _xfs_mru_cache_clear_reap_list(mru);
290
291 mru->queued = next;
292 if ((mru->queued > 0)) {
293 now = jiffies;
294 if (next <= now)
295 next = 0;
296 else
297 next -= now;
298 queue_delayed_work(xfs_mru_reap_wq, &mru->work, next);
David Chinner2a82b8b2007-07-11 11:09:12 +1000299 }
300
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000301 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000302}
303
304int
305xfs_mru_cache_init(void)
306{
Brian Foster8018ec02014-09-09 11:44:46 +1000307 xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache",
308 WQ_MEM_RECLAIM|WQ_FREEZABLE, 1);
Christoph Hellwig9f8868f2008-07-18 17:11:46 +1000309 if (!xfs_mru_reap_wq)
Christoph Hellwig22328d72014-04-23 07:11:51 +1000310 return -ENOMEM;
David Chinner2a82b8b2007-07-11 11:09:12 +1000311 return 0;
312}
313
314void
315xfs_mru_cache_uninit(void)
316{
317 destroy_workqueue(xfs_mru_reap_wq);
David Chinner2a82b8b2007-07-11 11:09:12 +1000318}
319
320/*
321 * To initialise a struct xfs_mru_cache pointer, call xfs_mru_cache_create()
322 * with the address of the pointer, a lifetime value in milliseconds, a group
323 * count and a free function to use when deleting elements. This function
324 * returns 0 if the initialisation was successful.
325 */
326int
327xfs_mru_cache_create(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000328 struct xfs_mru_cache **mrup,
David Chinner2a82b8b2007-07-11 11:09:12 +1000329 unsigned int lifetime_ms,
330 unsigned int grp_count,
331 xfs_mru_cache_free_func_t free_func)
332{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000333 struct xfs_mru_cache *mru = NULL;
334 int err = 0, grp;
335 unsigned int grp_time;
David Chinner2a82b8b2007-07-11 11:09:12 +1000336
337 if (mrup)
338 *mrup = NULL;
339
340 if (!mrup || !grp_count || !lifetime_ms || !free_func)
Dave Chinner24513372014-06-25 14:58:08 +1000341 return -EINVAL;
David Chinner2a82b8b2007-07-11 11:09:12 +1000342
343 if (!(grp_time = msecs_to_jiffies(lifetime_ms) / grp_count))
Dave Chinner24513372014-06-25 14:58:08 +1000344 return -EINVAL;
David Chinner2a82b8b2007-07-11 11:09:12 +1000345
346 if (!(mru = kmem_zalloc(sizeof(*mru), KM_SLEEP)))
Dave Chinner24513372014-06-25 14:58:08 +1000347 return -ENOMEM;
David Chinner2a82b8b2007-07-11 11:09:12 +1000348
349 /* An extra list is needed to avoid reaping up to a grp_time early. */
350 mru->grp_count = grp_count + 1;
David Chinner65de5562007-08-16 15:21:11 +1000351 mru->lists = kmem_zalloc(mru->grp_count * sizeof(*mru->lists), KM_SLEEP);
David Chinner2a82b8b2007-07-11 11:09:12 +1000352
353 if (!mru->lists) {
Dave Chinner24513372014-06-25 14:58:08 +1000354 err = -ENOMEM;
David Chinner2a82b8b2007-07-11 11:09:12 +1000355 goto exit;
356 }
357
358 for (grp = 0; grp < mru->grp_count; grp++)
359 INIT_LIST_HEAD(mru->lists + grp);
360
361 /*
362 * We use GFP_KERNEL radix tree preload and do inserts under a
363 * spinlock so GFP_ATOMIC is appropriate for the radix tree itself.
364 */
365 INIT_RADIX_TREE(&mru->store, GFP_ATOMIC);
366 INIT_LIST_HEAD(&mru->reap_list);
Eric Sandeen007c61c2007-10-11 17:43:56 +1000367 spin_lock_init(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000368 INIT_DELAYED_WORK(&mru->work, _xfs_mru_cache_reap);
369
370 mru->grp_time = grp_time;
371 mru->free_func = free_func;
372
David Chinner2a82b8b2007-07-11 11:09:12 +1000373 *mrup = mru;
374
375exit:
376 if (err && mru && mru->lists)
Denys Vlasenkof0e2d932008-05-19 16:31:57 +1000377 kmem_free(mru->lists);
David Chinner2a82b8b2007-07-11 11:09:12 +1000378 if (err && mru)
Denys Vlasenkof0e2d932008-05-19 16:31:57 +1000379 kmem_free(mru);
David Chinner2a82b8b2007-07-11 11:09:12 +1000380
381 return err;
382}
383
384/*
385 * Call xfs_mru_cache_flush() to flush out all cached entries, calling their
386 * free functions as they're deleted. When this function returns, the caller is
387 * guaranteed that all the free functions for all the elements have finished
David Chinner65de5562007-08-16 15:21:11 +1000388 * executing and the reaper is not running.
David Chinner2a82b8b2007-07-11 11:09:12 +1000389 */
Dave Chinnerb657fc82010-01-11 11:47:47 +0000390static void
David Chinner2a82b8b2007-07-11 11:09:12 +1000391xfs_mru_cache_flush(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000392 struct xfs_mru_cache *mru)
David Chinner2a82b8b2007-07-11 11:09:12 +1000393{
394 if (!mru || !mru->lists)
395 return;
396
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000397 spin_lock(&mru->lock);
David Chinner65de5562007-08-16 15:21:11 +1000398 if (mru->queued) {
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000399 spin_unlock(&mru->lock);
Tejun Heoafe2c512010-12-14 16:21:17 +0100400 cancel_delayed_work_sync(&mru->work);
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000401 spin_lock(&mru->lock);
David Chinner65de5562007-08-16 15:21:11 +1000402 }
David Chinner2a82b8b2007-07-11 11:09:12 +1000403
David Chinner65de5562007-08-16 15:21:11 +1000404 _xfs_mru_cache_migrate(mru, jiffies + mru->grp_count * mru->grp_time);
405 _xfs_mru_cache_clear_reap_list(mru);
David Chinner2a82b8b2007-07-11 11:09:12 +1000406
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000407 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000408}
409
410void
411xfs_mru_cache_destroy(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000412 struct xfs_mru_cache *mru)
David Chinner2a82b8b2007-07-11 11:09:12 +1000413{
414 if (!mru || !mru->lists)
415 return;
416
David Chinner65de5562007-08-16 15:21:11 +1000417 xfs_mru_cache_flush(mru);
David Chinner2a82b8b2007-07-11 11:09:12 +1000418
Denys Vlasenkof0e2d932008-05-19 16:31:57 +1000419 kmem_free(mru->lists);
420 kmem_free(mru);
David Chinner2a82b8b2007-07-11 11:09:12 +1000421}
422
423/*
424 * To insert an element, call xfs_mru_cache_insert() with the data store, the
425 * element's key and the client data pointer. This function returns 0 on
426 * success or ENOMEM if memory for the data element couldn't be allocated.
427 */
428int
429xfs_mru_cache_insert(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000430 struct xfs_mru_cache *mru,
431 unsigned long key,
432 struct xfs_mru_cache_elem *elem)
David Chinner2a82b8b2007-07-11 11:09:12 +1000433{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000434 int error;
David Chinner2a82b8b2007-07-11 11:09:12 +1000435
436 ASSERT(mru && mru->lists);
437 if (!mru || !mru->lists)
Dave Chinner24513372014-06-25 14:58:08 +1000438 return -EINVAL;
David Chinner2a82b8b2007-07-11 11:09:12 +1000439
Byoungyoung Lee20dafee2015-03-25 14:57:53 +1100440 if (radix_tree_preload(GFP_NOFS))
Dave Chinner24513372014-06-25 14:58:08 +1000441 return -ENOMEM;
David Chinner2a82b8b2007-07-11 11:09:12 +1000442
David Chinner2a82b8b2007-07-11 11:09:12 +1000443 INIT_LIST_HEAD(&elem->list_node);
444 elem->key = key;
David Chinner2a82b8b2007-07-11 11:09:12 +1000445
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000446 spin_lock(&mru->lock);
Dave Chinner24513372014-06-25 14:58:08 +1000447 error = radix_tree_insert(&mru->store, key, elem);
David Chinner2a82b8b2007-07-11 11:09:12 +1000448 radix_tree_preload_end();
Christoph Hellwig22328d72014-04-23 07:11:51 +1000449 if (!error)
450 _xfs_mru_cache_list_insert(mru, elem);
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000451 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000452
Christoph Hellwigce695c62014-04-23 07:11:50 +1000453 return error;
David Chinner2a82b8b2007-07-11 11:09:12 +1000454}
455
456/*
457 * To remove an element without calling the free function, call
458 * xfs_mru_cache_remove() with the data store and the element's key. On success
459 * the client data pointer for the removed element is returned, otherwise this
460 * function will return a NULL pointer.
461 */
Christoph Hellwig22328d72014-04-23 07:11:51 +1000462struct xfs_mru_cache_elem *
David Chinner2a82b8b2007-07-11 11:09:12 +1000463xfs_mru_cache_remove(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000464 struct xfs_mru_cache *mru,
465 unsigned long key)
David Chinner2a82b8b2007-07-11 11:09:12 +1000466{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000467 struct xfs_mru_cache_elem *elem;
David Chinner2a82b8b2007-07-11 11:09:12 +1000468
469 ASSERT(mru && mru->lists);
470 if (!mru || !mru->lists)
471 return NULL;
472
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000473 spin_lock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000474 elem = radix_tree_delete(&mru->store, key);
Christoph Hellwig22328d72014-04-23 07:11:51 +1000475 if (elem)
David Chinner2a82b8b2007-07-11 11:09:12 +1000476 list_del(&elem->list_node);
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000477 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000478
Christoph Hellwig22328d72014-04-23 07:11:51 +1000479 return elem;
David Chinner2a82b8b2007-07-11 11:09:12 +1000480}
481
482/*
483 * To remove and element and call the free function, call xfs_mru_cache_delete()
484 * with the data store and the element's key.
485 */
486void
487xfs_mru_cache_delete(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000488 struct xfs_mru_cache *mru,
489 unsigned long key)
David Chinner2a82b8b2007-07-11 11:09:12 +1000490{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000491 struct xfs_mru_cache_elem *elem;
David Chinner2a82b8b2007-07-11 11:09:12 +1000492
Christoph Hellwig22328d72014-04-23 07:11:51 +1000493 elem = xfs_mru_cache_remove(mru, key);
494 if (elem)
495 mru->free_func(elem);
David Chinner2a82b8b2007-07-11 11:09:12 +1000496}
497
498/*
499 * To look up an element using its key, call xfs_mru_cache_lookup() with the
500 * data store and the element's key. If found, the element will be moved to the
501 * head of the MRU list to indicate that it's been touched.
502 *
503 * The internal data structures are protected by a spinlock that is STILL HELD
504 * when this function returns. Call xfs_mru_cache_done() to release it. Note
505 * that it is not safe to call any function that might sleep in the interim.
506 *
507 * The implementation could have used reference counting to avoid this
508 * restriction, but since most clients simply want to get, set or test a member
509 * of the returned data structure, the extra per-element memory isn't warranted.
510 *
511 * If the element isn't found, this function returns NULL and the spinlock is
512 * released. xfs_mru_cache_done() should NOT be called when this occurs.
David Chinnera8272ce2007-11-23 16:28:09 +1100513 *
514 * Because sparse isn't smart enough to know about conditional lock return
515 * status, we need to help it get it right by annotating the path that does
516 * not release the lock.
David Chinner2a82b8b2007-07-11 11:09:12 +1000517 */
Christoph Hellwig22328d72014-04-23 07:11:51 +1000518struct xfs_mru_cache_elem *
David Chinner2a82b8b2007-07-11 11:09:12 +1000519xfs_mru_cache_lookup(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000520 struct xfs_mru_cache *mru,
521 unsigned long key)
David Chinner2a82b8b2007-07-11 11:09:12 +1000522{
Christoph Hellwig22328d72014-04-23 07:11:51 +1000523 struct xfs_mru_cache_elem *elem;
David Chinner2a82b8b2007-07-11 11:09:12 +1000524
525 ASSERT(mru && mru->lists);
526 if (!mru || !mru->lists)
527 return NULL;
528
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000529 spin_lock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000530 elem = radix_tree_lookup(&mru->store, key);
531 if (elem) {
532 list_del(&elem->list_node);
533 _xfs_mru_cache_list_insert(mru, elem);
David Chinnera8272ce2007-11-23 16:28:09 +1100534 __release(mru_lock); /* help sparse not be stupid */
535 } else
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000536 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000537
Christoph Hellwig22328d72014-04-23 07:11:51 +1000538 return elem;
David Chinner2a82b8b2007-07-11 11:09:12 +1000539}
540
541/*
David Chinner2a82b8b2007-07-11 11:09:12 +1000542 * To release the internal data structure spinlock after having performed an
543 * xfs_mru_cache_lookup() or an xfs_mru_cache_peek(), call xfs_mru_cache_done()
544 * with the data store pointer.
545 */
546void
547xfs_mru_cache_done(
Christoph Hellwig22328d72014-04-23 07:11:51 +1000548 struct xfs_mru_cache *mru)
549 __releases(mru->lock)
David Chinner2a82b8b2007-07-11 11:09:12 +1000550{
Eric Sandeenba74d0c2007-10-11 17:42:10 +1000551 spin_unlock(&mru->lock);
David Chinner2a82b8b2007-07-11 11:09:12 +1000552}