forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 127
/
Copy pathcache.c
1775 lines (1530 loc) · 41.9 KB
/
cache.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* net/sunrpc/cache.c
*
* Generic code for various authentication-related caches
* used by sunrpc clients and servers.
*
* Copyright (C) 2002 Neil Brown <neilb@cse.unsw.edu.au>
*
* Released under terms in GPL version 2. See COPYING.
*
*/
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <asm/uaccess.h>
#include <linux/poll.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/net.h>
#include <linux/workqueue.h>
#include <linux/mutex.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <asm/ioctls.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
#define RPCDBG_FACILITY RPCDBG_CACHE
static int cache_defer_req(struct cache_req *req, struct cache_head *item);
static void cache_revisit_request(struct cache_head *item);
static void cache_init(struct cache_head *h)
{
time_t now = seconds_since_boot();
h->next = NULL;
h->flags = 0;
kref_init(&h->ref);
h->expiry_time = now + CACHE_NEW_EXPIRY;
h->last_refresh = now;
}
static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h)
{
return (h->expiry_time < seconds_since_boot()) ||
(detail->flush_time > h->last_refresh);
}
struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
struct cache_head *key, int hash)
{
struct cache_head **head, **hp;
struct cache_head *new = NULL, *freeme = NULL;
head = &detail->hash_table[hash];
read_lock(&detail->hash_lock);
for (hp=head; *hp != NULL ; hp = &(*hp)->next) {
struct cache_head *tmp = *hp;
if (detail->match(tmp, key)) {
if (cache_is_expired(detail, tmp))
/* This entry is expired, we will discard it. */
break;
cache_get(tmp);
read_unlock(&detail->hash_lock);
return tmp;
}
}
read_unlock(&detail->hash_lock);
/* Didn't find anything, insert an empty entry */
new = detail->alloc();
if (!new)
return NULL;
/* must fully initialise 'new', else
* we might get lose if we need to
* cache_put it soon.
*/
cache_init(new);
detail->init(new, key);
write_lock(&detail->hash_lock);
/* check if entry appeared while we slept */
for (hp=head; *hp != NULL ; hp = &(*hp)->next) {
struct cache_head *tmp = *hp;
if (detail->match(tmp, key)) {
if (cache_is_expired(detail, tmp)) {
*hp = tmp->next;
tmp->next = NULL;
detail->entries --;
freeme = tmp;
break;
}
cache_get(tmp);
write_unlock(&detail->hash_lock);
cache_put(new, detail);
return tmp;
}
}
new->next = *head;
*head = new;
detail->entries++;
cache_get(new);
write_unlock(&detail->hash_lock);
if (freeme)
cache_put(freeme, detail);
return new;
}
EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
static void cache_fresh_locked(struct cache_head *head, time_t expiry)
{
head->expiry_time = expiry;
head->last_refresh = seconds_since_boot();
set_bit(CACHE_VALID, &head->flags);
}
static void cache_fresh_unlocked(struct cache_head *head,
struct cache_detail *detail)
{
if (test_and_clear_bit(CACHE_PENDING, &head->flags)) {
cache_revisit_request(head);
cache_dequeue(detail, head);
}
}
struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
struct cache_head *new, struct cache_head *old, int hash)
{
/* The 'old' entry is to be replaced by 'new'.
* If 'old' is not VALID, we update it directly,
* otherwise we need to replace it
*/
struct cache_head **head;
struct cache_head *tmp;
if (!test_bit(CACHE_VALID, &old->flags)) {
write_lock(&detail->hash_lock);
if (!test_bit(CACHE_VALID, &old->flags)) {
if (test_bit(CACHE_NEGATIVE, &new->flags))
set_bit(CACHE_NEGATIVE, &old->flags);
else
detail->update(old, new);
cache_fresh_locked(old, new->expiry_time);
write_unlock(&detail->hash_lock);
cache_fresh_unlocked(old, detail);
return old;
}
write_unlock(&detail->hash_lock);
}
/* We need to insert a new entry */
tmp = detail->alloc();
if (!tmp) {
cache_put(old, detail);
return NULL;
}
cache_init(tmp);
detail->init(tmp, old);
head = &detail->hash_table[hash];
write_lock(&detail->hash_lock);
if (test_bit(CACHE_NEGATIVE, &new->flags))
set_bit(CACHE_NEGATIVE, &tmp->flags);
else
detail->update(tmp, new);
tmp->next = *head;
*head = tmp;
detail->entries++;
cache_get(tmp);
cache_fresh_locked(tmp, new->expiry_time);
cache_fresh_locked(old, 0);
write_unlock(&detail->hash_lock);
cache_fresh_unlocked(tmp, detail);
cache_fresh_unlocked(old, detail);
cache_put(old, detail);
return tmp;
}
EXPORT_SYMBOL_GPL(sunrpc_cache_update);
static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
{
if (!cd->cache_upcall)
return -EINVAL;
return cd->cache_upcall(cd, h);
}
static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h)
{
if (!test_bit(CACHE_VALID, &h->flags))
return -EAGAIN;
else {
/* entry is valid */
if (test_bit(CACHE_NEGATIVE, &h->flags))
return -ENOENT;
else
return 0;
}
}
/*
* This is the generic cache management routine for all
* the authentication caches.
* It checks the currency of a cache item and will (later)
* initiate an upcall to fill it if needed.
*
*
* Returns 0 if the cache_head can be used, or cache_puts it and returns
* -EAGAIN if upcall is pending and request has been queued
* -ETIMEDOUT if upcall failed or request could not be queue or
* upcall completed but item is still invalid (implying that
* the cache item has been replaced with a newer one).
* -ENOENT if cache entry was negative
*/
int cache_check(struct cache_detail *detail,
struct cache_head *h, struct cache_req *rqstp)
{
int rv;
long refresh_age, age;
/* First decide return status as best we can */
rv = cache_is_valid(detail, h);
/* now see if we want to start an upcall */
refresh_age = (h->expiry_time - h->last_refresh);
age = seconds_since_boot() - h->last_refresh;
if (rqstp == NULL) {
if (rv == -EAGAIN)
rv = -ENOENT;
} else if (rv == -EAGAIN || age > refresh_age/2) {
dprintk("RPC: Want update, refage=%ld, age=%ld\n",
refresh_age, age);
if (!test_and_set_bit(CACHE_PENDING, &h->flags)) {
switch (cache_make_upcall(detail, h)) {
case -EINVAL:
clear_bit(CACHE_PENDING, &h->flags);
cache_revisit_request(h);
if (rv == -EAGAIN) {
set_bit(CACHE_NEGATIVE, &h->flags);
cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY);
cache_fresh_unlocked(h, detail);
rv = -ENOENT;
}
break;
case -EAGAIN:
clear_bit(CACHE_PENDING, &h->flags);
cache_revisit_request(h);
break;
}
}
}
if (rv == -EAGAIN) {
if (cache_defer_req(rqstp, h) < 0) {
/* Request is not deferred */
rv = cache_is_valid(detail, h);
if (rv == -EAGAIN)
rv = -ETIMEDOUT;
}
}
if (rv)
cache_put(h, detail);
return rv;
}
EXPORT_SYMBOL_GPL(cache_check);
/*
* caches need to be periodically cleaned.
* For this we maintain a list of cache_detail and
* a current pointer into that list and into the table
* for that entry.
*
* Each time clean_cache is called it finds the next non-empty entry
* in the current table and walks the list in that entry
* looking for entries that can be removed.
*
* An entry gets removed if:
* - The expiry is before current time
* - The last_refresh time is before the flush_time for that cache
*
* later we might drop old entries with non-NEVER expiry if that table
* is getting 'full' for some definition of 'full'
*
* The question of "how often to scan a table" is an interesting one
* and is answered in part by the use of the "nextcheck" field in the
* cache_detail.
* When a scan of a table begins, the nextcheck field is set to a time
* that is well into the future.
* While scanning, if an expiry time is found that is earlier than the
* current nextcheck time, nextcheck is set to that expiry time.
* If the flush_time is ever set to a time earlier than the nextcheck
* time, the nextcheck time is then set to that flush_time.
*
* A table is then only scanned if the current time is at least
* the nextcheck time.
*
*/
static LIST_HEAD(cache_list);
static DEFINE_SPINLOCK(cache_list_lock);
static struct cache_detail *current_detail;
static int current_index;
static void do_cache_clean(struct work_struct *work);
static struct delayed_work cache_cleaner;
static void sunrpc_init_cache_detail(struct cache_detail *cd)
{
rwlock_init(&cd->hash_lock);
INIT_LIST_HEAD(&cd->queue);
spin_lock(&cache_list_lock);
cd->nextcheck = 0;
cd->entries = 0;
atomic_set(&cd->readers, 0);
cd->last_close = 0;
cd->last_warn = -1;
list_add(&cd->others, &cache_list);
spin_unlock(&cache_list_lock);
/* start the cleaning process */
schedule_delayed_work(&cache_cleaner, 0);
}
static void sunrpc_destroy_cache_detail(struct cache_detail *cd)
{
cache_purge(cd);
spin_lock(&cache_list_lock);
write_lock(&cd->hash_lock);
if (cd->entries || atomic_read(&cd->inuse)) {
write_unlock(&cd->hash_lock);
spin_unlock(&cache_list_lock);
goto out;
}
if (current_detail == cd)
current_detail = NULL;
list_del_init(&cd->others);
write_unlock(&cd->hash_lock);
spin_unlock(&cache_list_lock);
if (list_empty(&cache_list)) {
/* module must be being unloaded so its safe to kill the worker */
cancel_delayed_work_sync(&cache_cleaner);
}
return;
out:
printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
}
/* clean cache tries to find something to clean
* and cleans it.
* It returns 1 if it cleaned something,
* 0 if it didn't find anything this time
* -1 if it fell off the end of the list.
*/
static int cache_clean(void)
{
int rv = 0;
struct list_head *next;
spin_lock(&cache_list_lock);
/* find a suitable table if we don't already have one */
while (current_detail == NULL ||
current_index >= current_detail->hash_size) {
if (current_detail)
next = current_detail->others.next;
else
next = cache_list.next;
if (next == &cache_list) {
current_detail = NULL;
spin_unlock(&cache_list_lock);
return -1;
}
current_detail = list_entry(next, struct cache_detail, others);
if (current_detail->nextcheck > seconds_since_boot())
current_index = current_detail->hash_size;
else {
current_index = 0;
current_detail->nextcheck = seconds_since_boot()+30*60;
}
}
/* find a non-empty bucket in the table */
while (current_detail &&
current_index < current_detail->hash_size &&
current_detail->hash_table[current_index] == NULL)
current_index++;
/* find a cleanable entry in the bucket and clean it, or set to next bucket */
if (current_detail && current_index < current_detail->hash_size) {
struct cache_head *ch, **cp;
struct cache_detail *d;
write_lock(¤t_detail->hash_lock);
/* Ok, now to clean this strand */
cp = & current_detail->hash_table[current_index];
for (ch = *cp ; ch ; cp = & ch->next, ch = *cp) {
if (current_detail->nextcheck > ch->expiry_time)
current_detail->nextcheck = ch->expiry_time+1;
if (!cache_is_expired(current_detail, ch))
continue;
*cp = ch->next;
ch->next = NULL;
current_detail->entries--;
rv = 1;
break;
}
write_unlock(¤t_detail->hash_lock);
d = current_detail;
if (!ch)
current_index ++;
spin_unlock(&cache_list_lock);
if (ch) {
if (test_and_clear_bit(CACHE_PENDING, &ch->flags))
cache_dequeue(current_detail, ch);
cache_revisit_request(ch);
cache_put(ch, d);
}
} else
spin_unlock(&cache_list_lock);
return rv;
}
/*
* We want to regularly clean the cache, so we need to schedule some work ...
*/
static void do_cache_clean(struct work_struct *work)
{
int delay = 5;
if (cache_clean() == -1)
delay = round_jiffies_relative(30*HZ);
if (list_empty(&cache_list))
delay = 0;
if (delay)
schedule_delayed_work(&cache_cleaner, delay);
}
/*
* Clean all caches promptly. This just calls cache_clean
* repeatedly until we are sure that every cache has had a chance to
* be fully cleaned
*/
void cache_flush(void)
{
while (cache_clean() != -1)
cond_resched();
while (cache_clean() != -1)
cond_resched();
}
EXPORT_SYMBOL_GPL(cache_flush);
void cache_purge(struct cache_detail *detail)
{
detail->flush_time = LONG_MAX;
detail->nextcheck = seconds_since_boot();
cache_flush();
detail->flush_time = 1;
}
EXPORT_SYMBOL_GPL(cache_purge);
/*
* Deferral and Revisiting of Requests.
*
* If a cache lookup finds a pending entry, we
* need to defer the request and revisit it later.
* All deferred requests are stored in a hash table,
* indexed by "struct cache_head *".
* As it may be wasteful to store a whole request
* structure, we allow the request to provide a
* deferred form, which must contain a
* 'struct cache_deferred_req'
* This cache_deferred_req contains a method to allow
* it to be revisited when cache info is available
*/
#define DFR_HASHSIZE (PAGE_SIZE/sizeof(struct list_head))
#define DFR_HASH(item) ((((long)item)>>4 ^ (((long)item)>>13)) % DFR_HASHSIZE)
#define DFR_MAX 300 /* ??? */
static DEFINE_SPINLOCK(cache_defer_lock);
static LIST_HEAD(cache_defer_list);
static struct hlist_head cache_defer_hash[DFR_HASHSIZE];
static int cache_defer_cnt;
static void __unhash_deferred_req(struct cache_deferred_req *dreq)
{
list_del_init(&dreq->recent);
hlist_del_init(&dreq->hash);
cache_defer_cnt--;
}
static void __hash_deferred_req(struct cache_deferred_req *dreq, struct cache_head *item)
{
int hash = DFR_HASH(item);
list_add(&dreq->recent, &cache_defer_list);
hlist_add_head(&dreq->hash, &cache_defer_hash[hash]);
}
static int setup_deferral(struct cache_deferred_req *dreq, struct cache_head *item)
{
struct cache_deferred_req *discard;
dreq->item = item;
spin_lock(&cache_defer_lock);
__hash_deferred_req(dreq, item);
/* it is in, now maybe clean up */
discard = NULL;
if (++cache_defer_cnt > DFR_MAX) {
discard = list_entry(cache_defer_list.prev,
struct cache_deferred_req, recent);
__unhash_deferred_req(discard);
}
spin_unlock(&cache_defer_lock);
if (discard)
/* there was one too many */
discard->revisit(discard, 1);
if (!test_bit(CACHE_PENDING, &item->flags)) {
/* must have just been validated... */
cache_revisit_request(item);
return -EAGAIN;
}
return 0;
}
struct thread_deferred_req {
struct cache_deferred_req handle;
struct completion completion;
};
static void cache_restart_thread(struct cache_deferred_req *dreq, int too_many)
{
struct thread_deferred_req *dr =
container_of(dreq, struct thread_deferred_req, handle);
complete(&dr->completion);
}
static int cache_wait_req(struct cache_req *req, struct cache_head *item)
{
struct thread_deferred_req sleeper;
struct cache_deferred_req *dreq = &sleeper.handle;
int ret;
sleeper.completion = COMPLETION_INITIALIZER_ONSTACK(sleeper.completion);
dreq->revisit = cache_restart_thread;
ret = setup_deferral(dreq, item);
if (ret)
return ret;
if (wait_for_completion_interruptible_timeout(
&sleeper.completion, req->thread_wait) <= 0) {
/* The completion wasn't completed, so we need
* to clean up
*/
spin_lock(&cache_defer_lock);
if (!hlist_unhashed(&sleeper.handle.hash)) {
__unhash_deferred_req(&sleeper.handle);
spin_unlock(&cache_defer_lock);
} else {
/* cache_revisit_request already removed
* this from the hash table, but hasn't
* called ->revisit yet. It will very soon
* and we need to wait for it.
*/
spin_unlock(&cache_defer_lock);
wait_for_completion(&sleeper.completion);
}
}
if (test_bit(CACHE_PENDING, &item->flags)) {
/* item is still pending, try request
* deferral
*/
return -ETIMEDOUT;
}
/* only return success if we actually deferred the
* request. In this case we waited until it was
* answered so no deferral has happened - rather
* an answer already exists.
*/
return -EEXIST;
}
static int cache_defer_req(struct cache_req *req, struct cache_head *item)
{
struct cache_deferred_req *dreq;
int ret;
if (cache_defer_cnt >= DFR_MAX) {
/* too much in the cache, randomly drop this one,
* or continue and drop the oldest
*/
if (net_random()&1)
return -ENOMEM;
}
if (req->thread_wait) {
ret = cache_wait_req(req, item);
if (ret != -ETIMEDOUT)
return ret;
}
dreq = req->defer(req);
if (dreq == NULL)
return -ENOMEM;
return setup_deferral(dreq, item);
}
static void cache_revisit_request(struct cache_head *item)
{
struct cache_deferred_req *dreq;
struct list_head pending;
struct hlist_node *lp, *tmp;
int hash = DFR_HASH(item);
INIT_LIST_HEAD(&pending);
spin_lock(&cache_defer_lock);
hlist_for_each_entry_safe(dreq, lp, tmp, &cache_defer_hash[hash], hash)
if (dreq->item == item) {
__unhash_deferred_req(dreq);
list_add(&dreq->recent, &pending);
}
spin_unlock(&cache_defer_lock);
while (!list_empty(&pending)) {
dreq = list_entry(pending.next, struct cache_deferred_req, recent);
list_del_init(&dreq->recent);
dreq->revisit(dreq, 0);
}
}
void cache_clean_deferred(void *owner)
{
struct cache_deferred_req *dreq, *tmp;
struct list_head pending;
INIT_LIST_HEAD(&pending);
spin_lock(&cache_defer_lock);
list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) {
if (dreq->owner == owner) {
__unhash_deferred_req(dreq);
list_add(&dreq->recent, &pending);
}
}
spin_unlock(&cache_defer_lock);
while (!list_empty(&pending)) {
dreq = list_entry(pending.next, struct cache_deferred_req, recent);
list_del_init(&dreq->recent);
dreq->revisit(dreq, 1);
}
}
/*
* communicate with user-space
*
* We have a magic /proc file - /proc/sunrpc/<cachename>/channel.
* On read, you get a full request, or block.
* On write, an update request is processed.
* Poll works if anything to read, and always allows write.
*
* Implemented by linked list of requests. Each open file has
* a ->private that also exists in this list. New requests are added
* to the end and may wakeup and preceding readers.
* New readers are added to the head. If, on read, an item is found with
* CACHE_UPCALLING clear, we free it from the list.
*
*/
static DEFINE_SPINLOCK(queue_lock);
static DEFINE_MUTEX(queue_io_mutex);
struct cache_queue {
struct list_head list;
int reader; /* if 0, then request */
};
struct cache_request {
struct cache_queue q;
struct cache_head *item;
char * buf;
int len;
int readers;
};
struct cache_reader {
struct cache_queue q;
int offset; /* if non-0, we have a refcnt on next request */
};
static ssize_t cache_read(struct file *filp, char __user *buf, size_t count,
loff_t *ppos, struct cache_detail *cd)
{
struct cache_reader *rp = filp->private_data;
struct cache_request *rq;
struct inode *inode = filp->f_path.dentry->d_inode;
int err;
if (count == 0)
return 0;
mutex_lock(&inode->i_mutex); /* protect against multiple concurrent
* readers on this file */
again:
spin_lock(&queue_lock);
/* need to find next request */
while (rp->q.list.next != &cd->queue &&
list_entry(rp->q.list.next, struct cache_queue, list)
->reader) {
struct list_head *next = rp->q.list.next;
list_move(&rp->q.list, next);
}
if (rp->q.list.next == &cd->queue) {
spin_unlock(&queue_lock);
mutex_unlock(&inode->i_mutex);
BUG_ON(rp->offset);
return 0;
}
rq = container_of(rp->q.list.next, struct cache_request, q.list);
BUG_ON(rq->q.reader);
if (rp->offset == 0)
rq->readers++;
spin_unlock(&queue_lock);
if (rp->offset == 0 && !test_bit(CACHE_PENDING, &rq->item->flags)) {
err = -EAGAIN;
spin_lock(&queue_lock);
list_move(&rp->q.list, &rq->q.list);
spin_unlock(&queue_lock);
} else {
if (rp->offset + count > rq->len)
count = rq->len - rp->offset;
err = -EFAULT;
if (copy_to_user(buf, rq->buf + rp->offset, count))
goto out;
rp->offset += count;
if (rp->offset >= rq->len) {
rp->offset = 0;
spin_lock(&queue_lock);
list_move(&rp->q.list, &rq->q.list);
spin_unlock(&queue_lock);
}
err = 0;
}
out:
if (rp->offset == 0) {
/* need to release rq */
spin_lock(&queue_lock);
rq->readers--;
if (rq->readers == 0 &&
!test_bit(CACHE_PENDING, &rq->item->flags)) {
list_del(&rq->q.list);
spin_unlock(&queue_lock);
cache_put(rq->item, cd);
kfree(rq->buf);
kfree(rq);
} else
spin_unlock(&queue_lock);
}
if (err == -EAGAIN)
goto again;
mutex_unlock(&inode->i_mutex);
return err ? err : count;
}
static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
size_t count, struct cache_detail *cd)
{
ssize_t ret;
if (copy_from_user(kaddr, buf, count))
return -EFAULT;
kaddr[count] = '\0';
ret = cd->cache_parse(cd, kaddr, count);
if (!ret)
ret = count;
return ret;
}
static ssize_t cache_slow_downcall(const char __user *buf,
size_t count, struct cache_detail *cd)
{
static char write_buf[8192]; /* protected by queue_io_mutex */
ssize_t ret = -EINVAL;
if (count >= sizeof(write_buf))
goto out;
mutex_lock(&queue_io_mutex);
ret = cache_do_downcall(write_buf, buf, count, cd);
mutex_unlock(&queue_io_mutex);
out:
return ret;
}
static ssize_t cache_downcall(struct address_space *mapping,
const char __user *buf,
size_t count, struct cache_detail *cd)
{
struct page *page;
char *kaddr;
ssize_t ret = -ENOMEM;
if (count >= PAGE_CACHE_SIZE)
goto out_slow;
page = find_or_create_page(mapping, 0, GFP_KERNEL);
if (!page)
goto out_slow;
kaddr = kmap(page);
ret = cache_do_downcall(kaddr, buf, count, cd);
kunmap(page);
unlock_page(page);
page_cache_release(page);
return ret;
out_slow:
return cache_slow_downcall(buf, count, cd);
}
static ssize_t cache_write(struct file *filp, const char __user *buf,
size_t count, loff_t *ppos,
struct cache_detail *cd)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = filp->f_path.dentry->d_inode;
ssize_t ret = -EINVAL;
if (!cd->cache_parse)
goto out;
mutex_lock(&inode->i_mutex);
ret = cache_downcall(mapping, buf, count, cd);
mutex_unlock(&inode->i_mutex);
out:
return ret;
}
static DECLARE_WAIT_QUEUE_HEAD(queue_wait);
static unsigned int cache_poll(struct file *filp, poll_table *wait,
struct cache_detail *cd)
{
unsigned int mask;
struct cache_reader *rp = filp->private_data;
struct cache_queue *cq;
poll_wait(filp, &queue_wait, wait);
/* alway allow write */
mask = POLL_OUT | POLLWRNORM;
if (!rp)
return mask;
spin_lock(&queue_lock);
for (cq= &rp->q; &cq->list != &cd->queue;
cq = list_entry(cq->list.next, struct cache_queue, list))
if (!cq->reader) {
mask |= POLLIN | POLLRDNORM;
break;
}
spin_unlock(&queue_lock);
return mask;
}
static int cache_ioctl(struct inode *ino, struct file *filp,
unsigned int cmd, unsigned long arg,
struct cache_detail *cd)
{
int len = 0;
struct cache_reader *rp = filp->private_data;
struct cache_queue *cq;
if (cmd != FIONREAD || !rp)
return -EINVAL;
spin_lock(&queue_lock);
/* only find the length remaining in current request,
* or the length of the next request
*/
for (cq= &rp->q; &cq->list != &cd->queue;
cq = list_entry(cq->list.next, struct cache_queue, list))
if (!cq->reader) {
struct cache_request *cr =
container_of(cq, struct cache_request, q);
len = cr->len - rp->offset;
break;
}
spin_unlock(&queue_lock);
return put_user(len, (int __user *)arg);
}
static int cache_open(struct inode *inode, struct file *filp,
struct cache_detail *cd)
{
struct cache_reader *rp = NULL;
if (!cd || !try_module_get(cd->owner))
return -EACCES;
nonseekable_open(inode, filp);
if (filp->f_mode & FMODE_READ) {
rp = kmalloc(sizeof(*rp), GFP_KERNEL);
if (!rp)
return -ENOMEM;
rp->offset = 0;
rp->q.reader = 1;
atomic_inc(&cd->readers);
spin_lock(&queue_lock);
list_add(&rp->q.list, &cd->queue);
spin_unlock(&queue_lock);
}
filp->private_data = rp;
return 0;
}
static int cache_release(struct inode *inode, struct file *filp,
struct cache_detail *cd)
{
struct cache_reader *rp = filp->private_data;
if (rp) {
spin_lock(&queue_lock);
if (rp->offset) {
struct cache_queue *cq;
for (cq= &rp->q; &cq->list != &cd->queue;
cq = list_entry(cq->list.next, struct cache_queue, list))
if (!cq->reader) {
container_of(cq, struct cache_request, q)
->readers--;
break;
}
rp->offset = 0;
}
list_del(&rp->q.list);
spin_unlock(&queue_lock);
filp->private_data = NULL;
kfree(rp);
cd->last_close = seconds_since_boot();
atomic_dec(&cd->readers);
}
module_put(cd->owner);
return 0;
}
static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch)
{
struct cache_queue *cq;
spin_lock(&queue_lock);
list_for_each_entry(cq, &detail->queue, list)
if (!cq->reader) {
struct cache_request *cr = container_of(cq, struct cache_request, q);
if (cr->item != ch)
continue;
if (cr->readers != 0)
continue;
list_del(&cr->q.list);
spin_unlock(&queue_lock);
cache_put(cr->item, detail);
kfree(cr->buf);
kfree(cr);
return;