-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathglock.c
2545 lines (2230 loc) · 65.1 KB
/
glock.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
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/buffer_head.h>
#include <linux/delay.h>
#include <linux/sort.h>
#include <linux/hash.h>
#include <linux/jhash.h>
#include <linux/kallsyms.h>
#include <linux/gfs2_ondisk.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
#include <linux/rcupdate.h>
#include <linux/rculist_bl.h>
#include <linux/bit_spinlock.h>
#include <linux/percpu.h>
#include <linux/list_sort.h>
#include <linux/lockref.h>
#include <linux/rhashtable.h>
#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "lops.h"
#include "meta_io.h"
#include "quota.h"
#include "super.h"
#include "util.h"
#include "bmap.h"
#define CREATE_TRACE_POINTS
#include "trace_gfs2.h"
struct gfs2_glock_iter {
struct gfs2_sbd *sdp; /* incore superblock */
struct rhashtable_iter hti; /* rhashtable iterator */
struct gfs2_glock *gl; /* current glock struct */
loff_t last_pos; /* last position */
};
typedef void (*glock_examiner) (struct gfs2_glock * gl);
static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
static struct dentry *gfs2_root;
static struct workqueue_struct *glock_workqueue;
struct workqueue_struct *gfs2_delete_workqueue;
static LIST_HEAD(lru_list);
static atomic_t lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(lru_lock);
#define GFS2_GL_HASH_SHIFT 15
#define GFS2_GL_HASH_SIZE BIT(GFS2_GL_HASH_SHIFT)
static const struct rhashtable_params ht_parms = {
.nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4,
.key_len = offsetofend(struct lm_lockname, ln_type),
.key_offset = offsetof(struct gfs2_glock, gl_name),
.head_offset = offsetof(struct gfs2_glock, gl_node),
};
static struct rhashtable gl_hash_table;
#define GLOCK_WAIT_TABLE_BITS 12
#define GLOCK_WAIT_TABLE_SIZE (1 << GLOCK_WAIT_TABLE_BITS)
static wait_queue_head_t glock_wait_table[GLOCK_WAIT_TABLE_SIZE] __cacheline_aligned;
struct wait_glock_queue {
struct lm_lockname *name;
wait_queue_entry_t wait;
};
static int glock_wake_function(wait_queue_entry_t *wait, unsigned int mode,
int sync, void *key)
{
struct wait_glock_queue *wait_glock =
container_of(wait, struct wait_glock_queue, wait);
struct lm_lockname *wait_name = wait_glock->name;
struct lm_lockname *wake_name = key;
if (wake_name->ln_sbd != wait_name->ln_sbd ||
wake_name->ln_number != wait_name->ln_number ||
wake_name->ln_type != wait_name->ln_type)
return 0;
return autoremove_wake_function(wait, mode, sync, key);
}
static wait_queue_head_t *glock_waitqueue(struct lm_lockname *name)
{
u32 hash = jhash2((u32 *)name, ht_parms.key_len / 4, 0);
return glock_wait_table + hash_32(hash, GLOCK_WAIT_TABLE_BITS);
}
/**
* wake_up_glock - Wake up waiters on a glock
* @gl: the glock
*/
static void wake_up_glock(struct gfs2_glock *gl)
{
wait_queue_head_t *wq = glock_waitqueue(&gl->gl_name);
if (waitqueue_active(wq))
__wake_up(wq, TASK_NORMAL, 1, &gl->gl_name);
}
static void gfs2_glock_dealloc(struct rcu_head *rcu)
{
struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
kfree(gl->gl_lksb.sb_lvbptr);
if (gl->gl_ops->go_flags & GLOF_ASPACE)
kmem_cache_free(gfs2_glock_aspace_cachep, gl);
else
kmem_cache_free(gfs2_glock_cachep, gl);
}
/**
* glock_blocked_by_withdraw - determine if we can still use a glock
* @gl: the glock
*
* We need to allow some glocks to be enqueued, dequeued, promoted, and demoted
* when we're withdrawn. For example, to maintain metadata integrity, we should
* disallow the use of inode and rgrp glocks when withdrawn. Other glocks, like
* iopen or the transaction glocks may be safely used because none of their
* metadata goes through the journal. So in general, we should disallow all
* glocks that are journaled, and allow all the others. One exception is:
* we need to allow our active journal to be promoted and demoted so others
* may recover it and we can reacquire it when they're done.
*/
static bool glock_blocked_by_withdraw(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
if (likely(!gfs2_withdrawn(sdp)))
return false;
if (gl->gl_ops->go_flags & GLOF_NONDISK)
return false;
if (!sdp->sd_jdesc ||
gl->gl_name.ln_number == sdp->sd_jdesc->jd_no_addr)
return false;
return true;
}
void gfs2_glock_free(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
gfs2_glock_assert_withdraw(gl, atomic_read(&gl->gl_revokes) == 0);
rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms);
smp_mb();
wake_up_glock(gl);
call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
if (atomic_dec_and_test(&sdp->sd_glock_disposal))
wake_up(&sdp->sd_glock_wait);
}
/**
* gfs2_glock_hold() - increment reference count on glock
* @gl: The glock to hold
*
*/
void gfs2_glock_hold(struct gfs2_glock *gl)
{
GLOCK_BUG_ON(gl, __lockref_is_dead(&gl->gl_lockref));
lockref_get(&gl->gl_lockref);
}
/**
* demote_ok - Check to see if it's ok to unlock a glock
* @gl: the glock
*
* Returns: 1 if it's ok
*/
static int demote_ok(const struct gfs2_glock *gl)
{
const struct gfs2_glock_operations *glops = gl->gl_ops;
if (gl->gl_state == LM_ST_UNLOCKED)
return 0;
if (!list_empty(&gl->gl_holders))
return 0;
if (glops->go_demote_ok)
return glops->go_demote_ok(gl);
return 1;
}
void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
{
if (!(gl->gl_ops->go_flags & GLOF_LRU))
return;
spin_lock(&lru_lock);
list_del(&gl->gl_lru);
list_add_tail(&gl->gl_lru, &lru_list);
if (!test_bit(GLF_LRU, &gl->gl_flags)) {
set_bit(GLF_LRU, &gl->gl_flags);
atomic_inc(&lru_count);
}
spin_unlock(&lru_lock);
}
static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
{
if (!(gl->gl_ops->go_flags & GLOF_LRU))
return;
spin_lock(&lru_lock);
if (test_bit(GLF_LRU, &gl->gl_flags)) {
list_del_init(&gl->gl_lru);
atomic_dec(&lru_count);
clear_bit(GLF_LRU, &gl->gl_flags);
}
spin_unlock(&lru_lock);
}
/*
* Enqueue the glock on the work queue. Passes one glock reference on to the
* work queue.
*/
static void __gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) {
if (!queue_delayed_work(glock_workqueue, &gl->gl_work, delay)) {
/*
* We are holding the lockref spinlock, and the work was still
* queued above. The queued work (glock_work_func) takes that
* spinlock before dropping its glock reference(s), so it
* cannot have dropped them in the meantime.
*/
GLOCK_BUG_ON(gl, gl->gl_lockref.count < 2);
gl->gl_lockref.count--;
}
}
static void gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) {
spin_lock(&gl->gl_lockref.lock);
__gfs2_glock_queue_work(gl, delay);
spin_unlock(&gl->gl_lockref.lock);
}
static void __gfs2_glock_put(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct address_space *mapping = gfs2_glock2aspace(gl);
lockref_mark_dead(&gl->gl_lockref);
gfs2_glock_remove_from_lru(gl);
spin_unlock(&gl->gl_lockref.lock);
GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
if (mapping) {
truncate_inode_pages_final(mapping);
if (!gfs2_withdrawn(sdp))
GLOCK_BUG_ON(gl, mapping->nrpages ||
mapping->nrexceptional);
}
trace_gfs2_glock_put(gl);
sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
}
/*
* Cause the glock to be put in work queue context.
*/
void gfs2_glock_queue_put(struct gfs2_glock *gl)
{
gfs2_glock_queue_work(gl, 0);
}
/**
* gfs2_glock_put() - Decrement reference count on glock
* @gl: The glock to put
*
*/
void gfs2_glock_put(struct gfs2_glock *gl)
{
if (lockref_put_or_lock(&gl->gl_lockref))
return;
__gfs2_glock_put(gl);
}
/**
* may_grant - check if its ok to grant a new lock
* @gl: The glock
* @gh: The lock request which we wish to grant
*
* Returns: true if its ok to grant the lock
*/
static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
{
const struct gfs2_holder *gh_head = list_first_entry(&gl->gl_holders, const struct gfs2_holder, gh_list);
if ((gh->gh_state == LM_ST_EXCLUSIVE ||
gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
return 0;
if (gl->gl_state == gh->gh_state)
return 1;
if (gh->gh_flags & GL_EXACT)
return 0;
if (gl->gl_state == LM_ST_EXCLUSIVE) {
if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
return 1;
if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
return 1;
}
if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
return 1;
return 0;
}
static void gfs2_holder_wake(struct gfs2_holder *gh)
{
clear_bit(HIF_WAIT, &gh->gh_iflags);
smp_mb__after_atomic();
wake_up_bit(&gh->gh_iflags, HIF_WAIT);
if (gh->gh_flags & GL_ASYNC) {
struct gfs2_sbd *sdp = gh->gh_gl->gl_name.ln_sbd;
wake_up(&sdp->sd_async_glock_wait);
}
}
/**
* do_error - Something unexpected has happened during a lock request
*
*/
static void do_error(struct gfs2_glock *gl, const int ret)
{
struct gfs2_holder *gh, *tmp;
list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
if (test_bit(HIF_HOLDER, &gh->gh_iflags))
continue;
if (ret & LM_OUT_ERROR)
gh->gh_error = -EIO;
else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
gh->gh_error = GLR_TRYFAILED;
else
continue;
list_del_init(&gh->gh_list);
trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
}
}
/**
* do_promote - promote as many requests as possible on the current queue
* @gl: The glock
*
* Returns: 1 if there is a blocked holder at the head of the list, or 2
* if a type specific operation is underway.
*/
static int do_promote(struct gfs2_glock *gl)
__releases(&gl->gl_lockref.lock)
__acquires(&gl->gl_lockref.lock)
{
const struct gfs2_glock_operations *glops = gl->gl_ops;
struct gfs2_holder *gh, *tmp;
int ret;
restart:
list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
if (test_bit(HIF_HOLDER, &gh->gh_iflags))
continue;
if (may_grant(gl, gh)) {
if (gh->gh_list.prev == &gl->gl_holders &&
glops->go_lock) {
spin_unlock(&gl->gl_lockref.lock);
/* FIXME: eliminate this eventually */
ret = glops->go_lock(gh);
spin_lock(&gl->gl_lockref.lock);
if (ret) {
if (ret == 1)
return 2;
gh->gh_error = ret;
list_del_init(&gh->gh_list);
trace_gfs2_glock_queue(gh, 0);
gfs2_holder_wake(gh);
goto restart;
}
set_bit(HIF_HOLDER, &gh->gh_iflags);
trace_gfs2_promote(gh, 1);
gfs2_holder_wake(gh);
goto restart;
}
set_bit(HIF_HOLDER, &gh->gh_iflags);
trace_gfs2_promote(gh, 0);
gfs2_holder_wake(gh);
continue;
}
if (gh->gh_list.prev == &gl->gl_holders)
return 1;
do_error(gl, 0);
break;
}
return 0;
}
/**
* find_first_waiter - find the first gh that's waiting for the glock
* @gl: the glock
*/
static inline struct gfs2_holder *find_first_waiter(const struct gfs2_glock *gl)
{
struct gfs2_holder *gh;
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
return gh;
}
return NULL;
}
/**
* state_change - record that the glock is now in a different state
* @gl: the glock
* @new_state the new state
*
*/
static void state_change(struct gfs2_glock *gl, unsigned int new_state)
{
int held1, held2;
held1 = (gl->gl_state != LM_ST_UNLOCKED);
held2 = (new_state != LM_ST_UNLOCKED);
if (held1 != held2) {
GLOCK_BUG_ON(gl, __lockref_is_dead(&gl->gl_lockref));
if (held2)
gl->gl_lockref.count++;
else
gl->gl_lockref.count--;
}
if (new_state != gl->gl_target)
/* shorten our minimum hold time */
gl->gl_hold_time = max(gl->gl_hold_time - GL_GLOCK_HOLD_DECR,
GL_GLOCK_MIN_HOLD);
gl->gl_state = new_state;
gl->gl_tchange = jiffies;
}
static void gfs2_set_demote(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
set_bit(GLF_DEMOTE, &gl->gl_flags);
smp_mb();
wake_up(&sdp->sd_async_glock_wait);
}
static void gfs2_demote_wake(struct gfs2_glock *gl)
{
gl->gl_demote_state = LM_ST_EXCLUSIVE;
clear_bit(GLF_DEMOTE, &gl->gl_flags);
smp_mb__after_atomic();
wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
}
/**
* finish_xmote - The DLM has replied to one of our lock requests
* @gl: The glock
* @ret: The status from the DLM
*
*/
static void finish_xmote(struct gfs2_glock *gl, unsigned int ret)
{
const struct gfs2_glock_operations *glops = gl->gl_ops;
struct gfs2_holder *gh;
unsigned state = ret & LM_OUT_ST_MASK;
int rv;
spin_lock(&gl->gl_lockref.lock);
trace_gfs2_glock_state_change(gl, state);
state_change(gl, state);
gh = find_first_waiter(gl);
/* Demote to UN request arrived during demote to SH or DF */
if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
state != LM_ST_UNLOCKED && gl->gl_demote_state == LM_ST_UNLOCKED)
gl->gl_target = LM_ST_UNLOCKED;
/* Check for state != intended state */
if (unlikely(state != gl->gl_target)) {
if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) {
/* move to back of queue and try next entry */
if (ret & LM_OUT_CANCELED) {
if ((gh->gh_flags & LM_FLAG_PRIORITY) == 0)
list_move_tail(&gh->gh_list, &gl->gl_holders);
gh = find_first_waiter(gl);
gl->gl_target = gh->gh_state;
goto retry;
}
/* Some error or failed "try lock" - report it */
if ((ret & LM_OUT_ERROR) ||
(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
gl->gl_target = gl->gl_state;
do_error(gl, ret);
goto out;
}
}
switch(state) {
/* Unlocked due to conversion deadlock, try again */
case LM_ST_UNLOCKED:
retry:
do_xmote(gl, gh, gl->gl_target);
break;
/* Conversion fails, unlock and try again */
case LM_ST_SHARED:
case LM_ST_DEFERRED:
do_xmote(gl, gh, LM_ST_UNLOCKED);
break;
default: /* Everything else */
fs_err(gl->gl_name.ln_sbd, "wanted %u got %u\n",
gl->gl_target, state);
GLOCK_BUG_ON(gl, 1);
}
spin_unlock(&gl->gl_lockref.lock);
return;
}
/* Fast path - we got what we asked for */
if (test_and_clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags))
gfs2_demote_wake(gl);
if (state != LM_ST_UNLOCKED) {
if (glops->go_xmote_bh) {
spin_unlock(&gl->gl_lockref.lock);
rv = glops->go_xmote_bh(gl, gh);
spin_lock(&gl->gl_lockref.lock);
if (rv) {
do_error(gl, rv);
goto out;
}
}
rv = do_promote(gl);
if (rv == 2)
goto out_locked;
}
out:
clear_bit(GLF_LOCK, &gl->gl_flags);
out_locked:
spin_unlock(&gl->gl_lockref.lock);
}
static bool is_system_glock(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
if (gl == m_ip->i_gl)
return true;
return false;
}
/**
* do_xmote - Calls the DLM to change the state of a lock
* @gl: The lock state
* @gh: The holder (only for promotes)
* @target: The target lock state
*
*/
static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target)
__releases(&gl->gl_lockref.lock)
__acquires(&gl->gl_lockref.lock)
{
const struct gfs2_glock_operations *glops = gl->gl_ops;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
int ret;
if (target != LM_ST_UNLOCKED && glock_blocked_by_withdraw(gl) &&
gh && !(gh->gh_flags & LM_FLAG_NOEXP))
return;
lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
LM_FLAG_PRIORITY);
GLOCK_BUG_ON(gl, gl->gl_state == target);
GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
glops->go_inval) {
/*
* If another process is already doing the invalidate, let that
* finish first. The glock state machine will get back to this
* holder again later.
*/
if (test_and_set_bit(GLF_INVALIDATE_IN_PROGRESS,
&gl->gl_flags))
return;
do_error(gl, 0); /* Fail queued try locks */
}
gl->gl_req = target;
set_bit(GLF_BLOCKING, &gl->gl_flags);
if ((gl->gl_req == LM_ST_UNLOCKED) ||
(gl->gl_state == LM_ST_EXCLUSIVE) ||
(lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB)))
clear_bit(GLF_BLOCKING, &gl->gl_flags);
spin_unlock(&gl->gl_lockref.lock);
if (glops->go_sync) {
ret = glops->go_sync(gl);
/* If we had a problem syncing (due to io errors or whatever,
* we should not invalidate the metadata or tell dlm to
* release the glock to other nodes.
*/
if (ret) {
if (cmpxchg(&sdp->sd_log_error, 0, ret)) {
fs_err(sdp, "Error %d syncing glock \n", ret);
gfs2_dump_glock(NULL, gl, true);
}
goto skip_inval;
}
}
if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) {
/*
* The call to go_sync should have cleared out the ail list.
* If there are still items, we have a problem. We ought to
* withdraw, but we can't because the withdraw code also uses
* glocks. Warn about the error, dump the glock, then fall
* through and wait for logd to do the withdraw for us.
*/
if ((atomic_read(&gl->gl_ail_count) != 0) &&
(!cmpxchg(&sdp->sd_log_error, 0, -EIO))) {
gfs2_glock_assert_warn(gl,
!atomic_read(&gl->gl_ail_count));
gfs2_dump_glock(NULL, gl, true);
}
glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
}
skip_inval:
gfs2_glock_hold(gl);
/*
* Check for an error encountered since we called go_sync and go_inval.
* If so, we can't withdraw from the glock code because the withdraw
* code itself uses glocks (see function signal_our_withdraw) to
* change the mount to read-only. Most importantly, we must not call
* dlm to unlock the glock until the journal is in a known good state
* (after journal replay) otherwise other nodes may use the object
* (rgrp or dinode) and then later, journal replay will corrupt the
* file system. The best we can do here is wait for the logd daemon
* to see sd_log_error and withdraw, and in the meantime, requeue the
* work for later.
*
* We make a special exception for some system glocks, such as the
* system statfs inode glock, which needs to be granted before the
* gfs2_quotad daemon can exit, and that exit needs to finish before
* we can unmount the withdrawn file system.
*
* However, if we're just unlocking the lock (say, for unmount, when
* gfs2_gl_hash_clear calls clear_glock) and recovery is complete
* then it's okay to tell dlm to unlock it.
*/
if (unlikely(sdp->sd_log_error && !gfs2_withdrawn(sdp)))
gfs2_withdraw_delayed(sdp);
if (glock_blocked_by_withdraw(gl) &&
(target != LM_ST_UNLOCKED ||
test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags))) {
if (!is_system_glock(gl)) {
gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD);
goto out;
} else {
clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
}
}
if (sdp->sd_lockstruct.ls_ops->lm_lock) {
/* lock_dlm */
ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
if (ret == -EINVAL && gl->gl_target == LM_ST_UNLOCKED &&
target == LM_ST_UNLOCKED &&
test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) {
finish_xmote(gl, target);
gfs2_glock_queue_work(gl, 0);
} else if (ret) {
fs_err(sdp, "lm_lock ret %d\n", ret);
GLOCK_BUG_ON(gl, !gfs2_withdrawn(sdp));
}
} else { /* lock_nolock */
finish_xmote(gl, target);
gfs2_glock_queue_work(gl, 0);
}
out:
spin_lock(&gl->gl_lockref.lock);
}
/**
* find_first_holder - find the first "holder" gh
* @gl: the glock
*/
static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
{
struct gfs2_holder *gh;
if (!list_empty(&gl->gl_holders)) {
gh = list_first_entry(&gl->gl_holders, struct gfs2_holder, gh_list);
if (test_bit(HIF_HOLDER, &gh->gh_iflags))
return gh;
}
return NULL;
}
/**
* run_queue - do all outstanding tasks related to a glock
* @gl: The glock in question
* @nonblock: True if we must not block in run_queue
*
*/
static void run_queue(struct gfs2_glock *gl, const int nonblock)
__releases(&gl->gl_lockref.lock)
__acquires(&gl->gl_lockref.lock)
{
struct gfs2_holder *gh = NULL;
int ret;
if (test_and_set_bit(GLF_LOCK, &gl->gl_flags))
return;
GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags));
if (test_bit(GLF_DEMOTE, &gl->gl_flags) &&
gl->gl_demote_state != gl->gl_state) {
if (find_first_holder(gl))
goto out_unlock;
if (nonblock)
goto out_sched;
set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
gl->gl_target = gl->gl_demote_state;
} else {
if (test_bit(GLF_DEMOTE, &gl->gl_flags))
gfs2_demote_wake(gl);
ret = do_promote(gl);
if (ret == 0)
goto out_unlock;
if (ret == 2)
goto out;
gh = find_first_waiter(gl);
gl->gl_target = gh->gh_state;
if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
do_error(gl, 0); /* Fail queued try locks */
}
do_xmote(gl, gh, gl->gl_target);
out:
return;
out_sched:
clear_bit(GLF_LOCK, &gl->gl_flags);
smp_mb__after_atomic();
gl->gl_lockref.count++;
__gfs2_glock_queue_work(gl, 0);
return;
out_unlock:
clear_bit(GLF_LOCK, &gl->gl_flags);
smp_mb__after_atomic();
return;
}
void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation)
{
struct gfs2_inode_lvb *ri = (void *)gl->gl_lksb.sb_lvbptr;
if (ri->ri_magic == 0)
ri->ri_magic = cpu_to_be32(GFS2_MAGIC);
if (ri->ri_magic == cpu_to_be32(GFS2_MAGIC))
ri->ri_generation_deleted = cpu_to_be64(generation);
}
bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation)
{
struct gfs2_inode_lvb *ri = (void *)gl->gl_lksb.sb_lvbptr;
if (ri->ri_magic != cpu_to_be32(GFS2_MAGIC))
return false;
return generation <= be64_to_cpu(ri->ri_generation_deleted);
}
static void gfs2_glock_poke(struct gfs2_glock *gl)
{
int flags = LM_FLAG_TRY_1CB | LM_FLAG_ANY | GL_SKIP;
struct gfs2_holder gh;
int error;
gfs2_holder_init(gl, LM_ST_SHARED, flags, &gh);
error = gfs2_glock_nq(&gh);
if (!error)
gfs2_glock_dq(&gh);
gfs2_holder_uninit(&gh);
}
static bool gfs2_try_evict(struct gfs2_glock *gl)
{
struct gfs2_inode *ip;
bool evicted = false;
/*
* If there is contention on the iopen glock and we have an inode, try
* to grab and release the inode so that it can be evicted. This will
* allow the remote node to go ahead and delete the inode without us
* having to do it, which will avoid rgrp glock thrashing.
*
* The remote node is likely still holding the corresponding inode
* glock, so it will run before we get to verify that the delete has
* happened below.
*/
spin_lock(&gl->gl_lockref.lock);
ip = gl->gl_object;
if (ip && !igrab(&ip->i_inode))
ip = NULL;
spin_unlock(&gl->gl_lockref.lock);
if (ip) {
struct gfs2_glock *inode_gl = NULL;
gl->gl_no_formal_ino = ip->i_no_formal_ino;
set_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
d_prune_aliases(&ip->i_inode);
iput(&ip->i_inode);
/* If the inode was evicted, gl->gl_object will now be NULL. */
spin_lock(&gl->gl_lockref.lock);
ip = gl->gl_object;
if (ip) {
inode_gl = ip->i_gl;
lockref_get(&inode_gl->gl_lockref);
clear_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
}
spin_unlock(&gl->gl_lockref.lock);
if (inode_gl) {
gfs2_glock_poke(inode_gl);
gfs2_glock_put(inode_gl);
}
evicted = !ip;
}
return evicted;
}
static void delete_work_func(struct work_struct *work)
{
struct delayed_work *dwork = to_delayed_work(work);
struct gfs2_glock *gl = container_of(dwork, struct gfs2_glock, gl_delete);
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct inode *inode;
u64 no_addr = gl->gl_name.ln_number;
spin_lock(&gl->gl_lockref.lock);
clear_bit(GLF_PENDING_DELETE, &gl->gl_flags);
spin_unlock(&gl->gl_lockref.lock);
/* If someone's using this glock to create a new dinode, the block must
have been freed by another node, then re-used, in which case our
iopen callback is too late after the fact. Ignore it. */
if (test_bit(GLF_INODE_CREATING, &gl->gl_flags))
goto out;
if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
/*
* If we can evict the inode, give the remote node trying to
* delete the inode some time before verifying that the delete
* has happened. Otherwise, if we cause contention on the inode glock
* immediately, the remote node will think that we still have
* the inode in use, and so it will give up waiting.
*
* If we can't evict the inode, signal to the remote node that
* the inode is still in use. We'll later try to delete the
* inode locally in gfs2_evict_inode.
*
* FIXME: We only need to verify that the remote node has
* deleted the inode because nodes before this remote delete
* rework won't cooperate. At a later time, when we no longer
* care about compatibility with such nodes, we can skip this
* step entirely.
*/
if (gfs2_try_evict(gl)) {
if (gfs2_queue_delete_work(gl, 5 * HZ))
return;
}
goto out;
}
inode = gfs2_lookup_by_inum(sdp, no_addr, gl->gl_no_formal_ino,
GFS2_BLKST_UNLINKED);
if (!IS_ERR_OR_NULL(inode)) {
d_prune_aliases(inode);
iput(inode);
}
out:
gfs2_glock_put(gl);
}
static void glock_work_func(struct work_struct *work)
{
unsigned long delay = 0;
struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
unsigned int drop_refs = 1;
if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) {
finish_xmote(gl, gl->gl_reply);
drop_refs++;
}
spin_lock(&gl->gl_lockref.lock);
if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
gl->gl_state != LM_ST_UNLOCKED &&
gl->gl_demote_state != LM_ST_EXCLUSIVE) {
unsigned long holdtime, now = jiffies;
holdtime = gl->gl_tchange + gl->gl_hold_time;
if (time_before(now, holdtime))
delay = holdtime - now;
if (!delay) {
clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
gfs2_set_demote(gl);
}
}
run_queue(gl, 0);
if (delay) {
/* Keep one glock reference for the work we requeue. */
drop_refs--;
if (gl->gl_name.ln_type != LM_TYPE_INODE)
delay = 0;
__gfs2_glock_queue_work(gl, delay);
}
/*
* Drop the remaining glock references manually here. (Mind that
* __gfs2_glock_queue_work depends on the lockref spinlock begin held
* here as well.)
*/
gl->gl_lockref.count -= drop_refs;
if (!gl->gl_lockref.count) {
__gfs2_glock_put(gl);
return;
}
spin_unlock(&gl->gl_lockref.lock);
}
static struct gfs2_glock *find_insert_glock(struct lm_lockname *name,
struct gfs2_glock *new)
{
struct wait_glock_queue wait;
wait_queue_head_t *wq = glock_waitqueue(name);
struct gfs2_glock *gl;
wait.name = name;
init_wait(&wait.wait);
wait.wait.func = glock_wake_function;
again:
prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
rcu_read_lock();
if (new) {
gl = rhashtable_lookup_get_insert_fast(&gl_hash_table,
&new->gl_node, ht_parms);
if (IS_ERR(gl))
goto out;
} else {
gl = rhashtable_lookup_fast(&gl_hash_table,
name, ht_parms);
}
if (gl && !lockref_get_not_dead(&gl->gl_lockref)) {
rcu_read_unlock();
schedule();
goto again;
}
out:
rcu_read_unlock();
finish_wait(wq, &wait.wait);
return gl;
}
/**