-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxfs_buf.c
1876 lines (1623 loc) · 41.8 KB
/
xfs_buf.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
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include <linux/stddef.h>
#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/vmalloc.h>
#include <linux/bio.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/workqueue.h>
#include <linux/percpu.h>
#include <linux/blkdev.h>
#include <linux/hash.h>
#include <linux/kthread.h>
#include <linux/migrate.h>
#include <linux/backing-dev.h>
#include <linux/freezer.h>
#include "xfs_sb.h"
#include "xfs_inum.h"
#include "xfs_log.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_trace.h"
static kmem_zone_t *xfs_buf_zone;
STATIC int xfsbufd(void *);
STATIC void xfs_buf_delwri_queue(xfs_buf_t *, int);
static struct workqueue_struct *xfslogd_workqueue;
struct workqueue_struct *xfsdatad_workqueue;
struct workqueue_struct *xfsconvertd_workqueue;
#ifdef XFS_BUF_LOCK_TRACKING
# define XB_SET_OWNER(bp) ((bp)->b_last_holder = current->pid)
# define XB_CLEAR_OWNER(bp) ((bp)->b_last_holder = -1)
# define XB_GET_OWNER(bp) ((bp)->b_last_holder)
#else
# define XB_SET_OWNER(bp) do { } while (0)
# define XB_CLEAR_OWNER(bp) do { } while (0)
# define XB_GET_OWNER(bp) do { } while (0)
#endif
#define xb_to_gfp(flags) \
((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : \
((flags) & XBF_DONT_BLOCK) ? GFP_NOFS : GFP_KERNEL) | __GFP_NOWARN)
#define xb_to_km(flags) \
(((flags) & XBF_DONT_BLOCK) ? KM_NOFS : KM_SLEEP)
#define xfs_buf_allocate(flags) \
kmem_zone_alloc(xfs_buf_zone, xb_to_km(flags))
#define xfs_buf_deallocate(bp) \
kmem_zone_free(xfs_buf_zone, (bp));
static inline int
xfs_buf_is_vmapped(
struct xfs_buf *bp)
{
/*
* Return true if the buffer is vmapped.
*
* The XBF_MAPPED flag is set if the buffer should be mapped, but the
* code is clever enough to know it doesn't have to map a single page,
* so the check has to be both for XBF_MAPPED and bp->b_page_count > 1.
*/
return (bp->b_flags & XBF_MAPPED) && bp->b_page_count > 1;
}
static inline int
xfs_buf_vmap_len(
struct xfs_buf *bp)
{
return (bp->b_page_count * PAGE_SIZE) - bp->b_offset;
}
/*
* xfs_buf_lru_add - add a buffer to the LRU.
*
* The LRU takes a new reference to the buffer so that it will only be freed
* once the shrinker takes the buffer off the LRU.
*/
STATIC void
xfs_buf_lru_add(
struct xfs_buf *bp)
{
struct xfs_buftarg *btp = bp->b_target;
spin_lock(&btp->bt_lru_lock);
if (list_empty(&bp->b_lru)) {
atomic_inc(&bp->b_hold);
list_add_tail(&bp->b_lru, &btp->bt_lru);
btp->bt_lru_nr++;
}
spin_unlock(&btp->bt_lru_lock);
}
/*
* xfs_buf_lru_del - remove a buffer from the LRU
*
* The unlocked check is safe here because it only occurs when there are not
* b_lru_ref counts left on the inode under the pag->pag_buf_lock. it is there
* to optimise the shrinker removing the buffer from the LRU and calling
* xfs_buf_free(). i.e. it removes an unnecessary round trip on the
* bt_lru_lock.
*/
STATIC void
xfs_buf_lru_del(
struct xfs_buf *bp)
{
struct xfs_buftarg *btp = bp->b_target;
if (list_empty(&bp->b_lru))
return;
spin_lock(&btp->bt_lru_lock);
if (!list_empty(&bp->b_lru)) {
list_del_init(&bp->b_lru);
btp->bt_lru_nr--;
}
spin_unlock(&btp->bt_lru_lock);
}
/*
* When we mark a buffer stale, we remove the buffer from the LRU and clear the
* b_lru_ref count so that the buffer is freed immediately when the buffer
* reference count falls to zero. If the buffer is already on the LRU, we need
* to remove the reference that LRU holds on the buffer.
*
* This prevents build-up of stale buffers on the LRU.
*/
void
xfs_buf_stale(
struct xfs_buf *bp)
{
bp->b_flags |= XBF_STALE;
atomic_set(&(bp)->b_lru_ref, 0);
if (!list_empty(&bp->b_lru)) {
struct xfs_buftarg *btp = bp->b_target;
spin_lock(&btp->bt_lru_lock);
if (!list_empty(&bp->b_lru)) {
list_del_init(&bp->b_lru);
btp->bt_lru_nr--;
atomic_dec(&bp->b_hold);
}
spin_unlock(&btp->bt_lru_lock);
}
ASSERT(atomic_read(&bp->b_hold) >= 1);
}
STATIC void
_xfs_buf_initialize(
xfs_buf_t *bp,
xfs_buftarg_t *target,
xfs_off_t range_base,
size_t range_length,
xfs_buf_flags_t flags)
{
/*
* We don't want certain flags to appear in b_flags.
*/
flags &= ~(XBF_LOCK|XBF_MAPPED|XBF_DONT_BLOCK|XBF_READ_AHEAD);
memset(bp, 0, sizeof(xfs_buf_t));
atomic_set(&bp->b_hold, 1);
atomic_set(&bp->b_lru_ref, 1);
init_completion(&bp->b_iowait);
INIT_LIST_HEAD(&bp->b_lru);
INIT_LIST_HEAD(&bp->b_list);
RB_CLEAR_NODE(&bp->b_rbnode);
sema_init(&bp->b_sema, 0); /* held, no waiters */
XB_SET_OWNER(bp);
bp->b_target = target;
bp->b_file_offset = range_base;
/*
* Set buffer_length and count_desired to the same value initially.
* I/O routines should use count_desired, which will be the same in
* most cases but may be reset (e.g. XFS recovery).
*/
bp->b_buffer_length = bp->b_count_desired = range_length;
bp->b_flags = flags;
bp->b_bn = XFS_BUF_DADDR_NULL;
atomic_set(&bp->b_pin_count, 0);
init_waitqueue_head(&bp->b_waiters);
XFS_STATS_INC(xb_create);
trace_xfs_buf_init(bp, _RET_IP_);
}
/*
* Allocate a page array capable of holding a specified number
* of pages, and point the page buf at it.
*/
STATIC int
_xfs_buf_get_pages(
xfs_buf_t *bp,
int page_count,
xfs_buf_flags_t flags)
{
/* Make sure that we have a page list */
if (bp->b_pages == NULL) {
bp->b_offset = xfs_buf_poff(bp->b_file_offset);
bp->b_page_count = page_count;
if (page_count <= XB_PAGES) {
bp->b_pages = bp->b_page_array;
} else {
bp->b_pages = kmem_alloc(sizeof(struct page *) *
page_count, xb_to_km(flags));
if (bp->b_pages == NULL)
return -ENOMEM;
}
memset(bp->b_pages, 0, sizeof(struct page *) * page_count);
}
return 0;
}
/*
* Frees b_pages if it was allocated.
*/
STATIC void
_xfs_buf_free_pages(
xfs_buf_t *bp)
{
if (bp->b_pages != bp->b_page_array) {
kmem_free(bp->b_pages);
bp->b_pages = NULL;
}
}
/*
* Releases the specified buffer.
*
* The modification state of any associated pages is left unchanged.
* The buffer most not be on any hash - use xfs_buf_rele instead for
* hashed and refcounted buffers
*/
void
xfs_buf_free(
xfs_buf_t *bp)
{
trace_xfs_buf_free(bp, _RET_IP_);
ASSERT(list_empty(&bp->b_lru));
if (bp->b_flags & _XBF_PAGES) {
uint i;
if (xfs_buf_is_vmapped(bp))
vm_unmap_ram(bp->b_addr - bp->b_offset,
bp->b_page_count);
for (i = 0; i < bp->b_page_count; i++) {
struct page *page = bp->b_pages[i];
__free_page(page);
}
} else if (bp->b_flags & _XBF_KMEM)
kmem_free(bp->b_addr);
_xfs_buf_free_pages(bp);
xfs_buf_deallocate(bp);
}
/*
* Allocates all the pages for buffer in question and builds it's page list.
*/
STATIC int
xfs_buf_allocate_memory(
xfs_buf_t *bp,
uint flags)
{
size_t size = bp->b_count_desired;
size_t nbytes, offset;
gfp_t gfp_mask = xb_to_gfp(flags);
unsigned short page_count, i;
xfs_off_t end;
int error;
/*
* for buffers that are contained within a single page, just allocate
* the memory from the heap - there's no need for the complexity of
* page arrays to keep allocation down to order 0.
*/
if (bp->b_buffer_length < PAGE_SIZE) {
bp->b_addr = kmem_alloc(bp->b_buffer_length, xb_to_km(flags));
if (!bp->b_addr) {
/* low memory - use alloc_page loop instead */
goto use_alloc_page;
}
if (((unsigned long)(bp->b_addr + bp->b_buffer_length - 1) &
PAGE_MASK) !=
((unsigned long)bp->b_addr & PAGE_MASK)) {
/* b_addr spans two pages - use alloc_page instead */
kmem_free(bp->b_addr);
bp->b_addr = NULL;
goto use_alloc_page;
}
bp->b_offset = offset_in_page(bp->b_addr);
bp->b_pages = bp->b_page_array;
bp->b_pages[0] = virt_to_page(bp->b_addr);
bp->b_page_count = 1;
bp->b_flags |= XBF_MAPPED | _XBF_KMEM;
return 0;
}
use_alloc_page:
end = bp->b_file_offset + bp->b_buffer_length;
page_count = xfs_buf_btoc(end) - xfs_buf_btoct(bp->b_file_offset);
error = _xfs_buf_get_pages(bp, page_count, flags);
if (unlikely(error))
return error;
offset = bp->b_offset;
bp->b_flags |= _XBF_PAGES;
for (i = 0; i < bp->b_page_count; i++) {
struct page *page;
uint retries = 0;
retry:
page = alloc_page(gfp_mask);
if (unlikely(page == NULL)) {
if (flags & XBF_READ_AHEAD) {
bp->b_page_count = i;
error = ENOMEM;
goto out_free_pages;
}
/*
* This could deadlock.
*
* But until all the XFS lowlevel code is revamped to
* handle buffer allocation failures we can't do much.
*/
if (!(++retries % 100))
xfs_err(NULL,
"possible memory allocation deadlock in %s (mode:0x%x)",
__func__, gfp_mask);
XFS_STATS_INC(xb_page_retries);
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
XFS_STATS_INC(xb_page_found);
nbytes = min_t(size_t, size, PAGE_SIZE - offset);
size -= nbytes;
bp->b_pages[i] = page;
offset = 0;
}
return 0;
out_free_pages:
for (i = 0; i < bp->b_page_count; i++)
__free_page(bp->b_pages[i]);
return error;
}
/*
* Map buffer into kernel address-space if necessary.
*/
STATIC int
_xfs_buf_map_pages(
xfs_buf_t *bp,
uint flags)
{
ASSERT(bp->b_flags & _XBF_PAGES);
if (bp->b_page_count == 1) {
/* A single page buffer is always mappable */
bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset;
bp->b_flags |= XBF_MAPPED;
} else if (flags & XBF_MAPPED) {
int retried = 0;
do {
bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-1, PAGE_KERNEL);
if (bp->b_addr)
break;
vm_unmap_aliases();
} while (retried++ <= 1);
if (!bp->b_addr)
return -ENOMEM;
bp->b_addr += bp->b_offset;
bp->b_flags |= XBF_MAPPED;
}
return 0;
}
/*
* Finding and Reading Buffers
*/
/*
* Look up, and creates if absent, a lockable buffer for
* a given range of an inode. The buffer is returned
* locked. If other overlapping buffers exist, they are
* released before the new buffer is created and locked,
* which may imply that this call will block until those buffers
* are unlocked. No I/O is implied by this call.
*/
xfs_buf_t *
_xfs_buf_find(
xfs_buftarg_t *btp, /* block device target */
xfs_off_t ioff, /* starting offset of range */
size_t isize, /* length of range */
xfs_buf_flags_t flags,
xfs_buf_t *new_bp)
{
xfs_off_t range_base;
size_t range_length;
struct xfs_perag *pag;
struct rb_node **rbp;
struct rb_node *parent;
xfs_buf_t *bp;
range_base = (ioff << BBSHIFT);
range_length = (isize << BBSHIFT);
/* Check for IOs smaller than the sector size / not sector aligned */
ASSERT(!(range_length < (1 << btp->bt_sshift)));
ASSERT(!(range_base & (xfs_off_t)btp->bt_smask));
/* get tree root */
pag = xfs_perag_get(btp->bt_mount,
xfs_daddr_to_agno(btp->bt_mount, ioff));
/* walk tree */
spin_lock(&pag->pag_buf_lock);
rbp = &pag->pag_buf_tree.rb_node;
parent = NULL;
bp = NULL;
while (*rbp) {
parent = *rbp;
bp = rb_entry(parent, struct xfs_buf, b_rbnode);
if (range_base < bp->b_file_offset)
rbp = &(*rbp)->rb_left;
else if (range_base > bp->b_file_offset)
rbp = &(*rbp)->rb_right;
else {
/*
* found a block offset match. If the range doesn't
* match, the only way this is allowed is if the buffer
* in the cache is stale and the transaction that made
* it stale has not yet committed. i.e. we are
* reallocating a busy extent. Skip this buffer and
* continue searching to the right for an exact match.
*/
if (bp->b_buffer_length != range_length) {
ASSERT(bp->b_flags & XBF_STALE);
rbp = &(*rbp)->rb_right;
continue;
}
atomic_inc(&bp->b_hold);
goto found;
}
}
/* No match found */
if (new_bp) {
_xfs_buf_initialize(new_bp, btp, range_base,
range_length, flags);
rb_link_node(&new_bp->b_rbnode, parent, rbp);
rb_insert_color(&new_bp->b_rbnode, &pag->pag_buf_tree);
/* the buffer keeps the perag reference until it is freed */
new_bp->b_pag = pag;
spin_unlock(&pag->pag_buf_lock);
} else {
XFS_STATS_INC(xb_miss_locked);
spin_unlock(&pag->pag_buf_lock);
xfs_perag_put(pag);
}
return new_bp;
found:
spin_unlock(&pag->pag_buf_lock);
xfs_perag_put(pag);
if (!xfs_buf_trylock(bp)) {
if (flags & XBF_TRYLOCK) {
xfs_buf_rele(bp);
XFS_STATS_INC(xb_busy_locked);
return NULL;
}
xfs_buf_lock(bp);
XFS_STATS_INC(xb_get_locked_waited);
}
/*
* if the buffer is stale, clear all the external state associated with
* it. We need to keep flags such as how we allocated the buffer memory
* intact here.
*/
if (bp->b_flags & XBF_STALE) {
ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
bp->b_flags &= XBF_MAPPED | _XBF_KMEM | _XBF_PAGES;
}
trace_xfs_buf_find(bp, flags, _RET_IP_);
XFS_STATS_INC(xb_get_locked);
return bp;
}
/*
* Assembles a buffer covering the specified range.
* Storage in memory for all portions of the buffer will be allocated,
* although backing storage may not be.
*/
xfs_buf_t *
xfs_buf_get(
xfs_buftarg_t *target,/* target for buffer */
xfs_off_t ioff, /* starting offset of range */
size_t isize, /* length of range */
xfs_buf_flags_t flags)
{
xfs_buf_t *bp, *new_bp;
int error = 0;
new_bp = xfs_buf_allocate(flags);
if (unlikely(!new_bp))
return NULL;
bp = _xfs_buf_find(target, ioff, isize, flags, new_bp);
if (bp == new_bp) {
error = xfs_buf_allocate_memory(bp, flags);
if (error)
goto no_buffer;
} else {
xfs_buf_deallocate(new_bp);
if (unlikely(bp == NULL))
return NULL;
}
if (!(bp->b_flags & XBF_MAPPED)) {
error = _xfs_buf_map_pages(bp, flags);
if (unlikely(error)) {
xfs_warn(target->bt_mount,
"%s: failed to map pages\n", __func__);
goto no_buffer;
}
}
XFS_STATS_INC(xb_get);
/*
* Always fill in the block number now, the mapped cases can do
* their own overlay of this later.
*/
bp->b_bn = ioff;
bp->b_count_desired = bp->b_buffer_length;
trace_xfs_buf_get(bp, flags, _RET_IP_);
return bp;
no_buffer:
if (flags & (XBF_LOCK | XBF_TRYLOCK))
xfs_buf_unlock(bp);
xfs_buf_rele(bp);
return NULL;
}
STATIC int
_xfs_buf_read(
xfs_buf_t *bp,
xfs_buf_flags_t flags)
{
int status;
ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE)));
ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD);
bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
status = xfs_buf_iorequest(bp);
if (status || bp->b_error || (flags & XBF_ASYNC))
return status;
return xfs_buf_iowait(bp);
}
xfs_buf_t *
xfs_buf_read(
xfs_buftarg_t *target,
xfs_off_t ioff,
size_t isize,
xfs_buf_flags_t flags)
{
xfs_buf_t *bp;
flags |= XBF_READ;
bp = xfs_buf_get(target, ioff, isize, flags);
if (bp) {
trace_xfs_buf_read(bp, flags, _RET_IP_);
if (!XFS_BUF_ISDONE(bp)) {
XFS_STATS_INC(xb_get_read);
_xfs_buf_read(bp, flags);
} else if (flags & XBF_ASYNC) {
/*
* Read ahead call which is already satisfied,
* drop the buffer
*/
goto no_buffer;
} else {
/* We do not want read in the flags */
bp->b_flags &= ~XBF_READ;
}
}
return bp;
no_buffer:
if (flags & (XBF_LOCK | XBF_TRYLOCK))
xfs_buf_unlock(bp);
xfs_buf_rele(bp);
return NULL;
}
/*
* If we are not low on memory then do the readahead in a deadlock
* safe manner.
*/
void
xfs_buf_readahead(
xfs_buftarg_t *target,
xfs_off_t ioff,
size_t isize)
{
if (bdi_read_congested(target->bt_bdi))
return;
xfs_buf_read(target, ioff, isize,
XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD|XBF_DONT_BLOCK);
}
/*
* Read an uncached buffer from disk. Allocates and returns a locked
* buffer containing the disk contents or nothing.
*/
struct xfs_buf *
xfs_buf_read_uncached(
struct xfs_mount *mp,
struct xfs_buftarg *target,
xfs_daddr_t daddr,
size_t length,
int flags)
{
xfs_buf_t *bp;
int error;
bp = xfs_buf_get_uncached(target, length, flags);
if (!bp)
return NULL;
/* set up the buffer for a read IO */
XFS_BUF_SET_ADDR(bp, daddr);
XFS_BUF_READ(bp);
xfsbdstrat(mp, bp);
error = xfs_buf_iowait(bp);
if (error || bp->b_error) {
xfs_buf_relse(bp);
return NULL;
}
return bp;
}
xfs_buf_t *
xfs_buf_get_empty(
size_t len,
xfs_buftarg_t *target)
{
xfs_buf_t *bp;
bp = xfs_buf_allocate(0);
if (bp)
_xfs_buf_initialize(bp, target, 0, len, 0);
return bp;
}
/*
* Return a buffer allocated as an empty buffer and associated to external
* memory via xfs_buf_associate_memory() back to it's empty state.
*/
void
xfs_buf_set_empty(
struct xfs_buf *bp,
size_t len)
{
if (bp->b_pages)
_xfs_buf_free_pages(bp);
bp->b_pages = NULL;
bp->b_page_count = 0;
bp->b_addr = NULL;
bp->b_file_offset = 0;
bp->b_buffer_length = bp->b_count_desired = len;
bp->b_bn = XFS_BUF_DADDR_NULL;
bp->b_flags &= ~XBF_MAPPED;
}
static inline struct page *
mem_to_page(
void *addr)
{
if ((!is_vmalloc_addr(addr))) {
return virt_to_page(addr);
} else {
return vmalloc_to_page(addr);
}
}
int
xfs_buf_associate_memory(
xfs_buf_t *bp,
void *mem,
size_t len)
{
int rval;
int i = 0;
unsigned long pageaddr;
unsigned long offset;
size_t buflen;
int page_count;
pageaddr = (unsigned long)mem & PAGE_MASK;
offset = (unsigned long)mem - pageaddr;
buflen = PAGE_ALIGN(len + offset);
page_count = buflen >> PAGE_SHIFT;
/* Free any previous set of page pointers */
if (bp->b_pages)
_xfs_buf_free_pages(bp);
bp->b_pages = NULL;
bp->b_addr = mem;
rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK);
if (rval)
return rval;
bp->b_offset = offset;
for (i = 0; i < bp->b_page_count; i++) {
bp->b_pages[i] = mem_to_page((void *)pageaddr);
pageaddr += PAGE_SIZE;
}
bp->b_count_desired = len;
bp->b_buffer_length = buflen;
bp->b_flags |= XBF_MAPPED;
return 0;
}
xfs_buf_t *
xfs_buf_get_uncached(
struct xfs_buftarg *target,
size_t len,
int flags)
{
unsigned long page_count = PAGE_ALIGN(len) >> PAGE_SHIFT;
int error, i;
xfs_buf_t *bp;
bp = xfs_buf_allocate(0);
if (unlikely(bp == NULL))
goto fail;
_xfs_buf_initialize(bp, target, 0, len, 0);
error = _xfs_buf_get_pages(bp, page_count, 0);
if (error)
goto fail_free_buf;
for (i = 0; i < page_count; i++) {
bp->b_pages[i] = alloc_page(xb_to_gfp(flags));
if (!bp->b_pages[i])
goto fail_free_mem;
}
bp->b_flags |= _XBF_PAGES;
error = _xfs_buf_map_pages(bp, XBF_MAPPED);
if (unlikely(error)) {
xfs_warn(target->bt_mount,
"%s: failed to map pages\n", __func__);
goto fail_free_mem;
}
trace_xfs_buf_get_uncached(bp, _RET_IP_);
return bp;
fail_free_mem:
while (--i >= 0)
__free_page(bp->b_pages[i]);
_xfs_buf_free_pages(bp);
fail_free_buf:
xfs_buf_deallocate(bp);
fail:
return NULL;
}
/*
* Increment reference count on buffer, to hold the buffer concurrently
* with another thread which may release (free) the buffer asynchronously.
* Must hold the buffer already to call this function.
*/
void
xfs_buf_hold(
xfs_buf_t *bp)
{
trace_xfs_buf_hold(bp, _RET_IP_);
atomic_inc(&bp->b_hold);
}
/*
* Releases a hold on the specified buffer. If the
* the hold count is 1, calls xfs_buf_free.
*/
void
xfs_buf_rele(
xfs_buf_t *bp)
{
struct xfs_perag *pag = bp->b_pag;
trace_xfs_buf_rele(bp, _RET_IP_);
if (!pag) {
ASSERT(list_empty(&bp->b_lru));
ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
if (atomic_dec_and_test(&bp->b_hold))
xfs_buf_free(bp);
return;
}
ASSERT(!RB_EMPTY_NODE(&bp->b_rbnode));
ASSERT(atomic_read(&bp->b_hold) > 0);
if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
if (!(bp->b_flags & XBF_STALE) &&
atomic_read(&bp->b_lru_ref)) {
xfs_buf_lru_add(bp);
spin_unlock(&pag->pag_buf_lock);
} else {
xfs_buf_lru_del(bp);
ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)));
rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
spin_unlock(&pag->pag_buf_lock);
xfs_perag_put(pag);
xfs_buf_free(bp);
}
}
}
/*
* Lock a buffer object, if it is not already locked.
*
* If we come across a stale, pinned, locked buffer, we know that we are
* being asked to lock a buffer that has been reallocated. Because it is
* pinned, we know that the log has not been pushed to disk and hence it
* will still be locked. Rather than continuing to have trylock attempts
* fail until someone else pushes the log, push it ourselves before
* returning. This means that the xfsaild will not get stuck trying
* to push on stale inode buffers.
*/
int
xfs_buf_trylock(
struct xfs_buf *bp)
{
int locked;
locked = down_trylock(&bp->b_sema) == 0;
if (locked)
XB_SET_OWNER(bp);
else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
xfs_log_force(bp->b_target->bt_mount, 0);
trace_xfs_buf_trylock(bp, _RET_IP_);
return locked;
}
/*
* Lock a buffer object.
*
* If we come across a stale, pinned, locked buffer, we know that we
* are being asked to lock a buffer that has been reallocated. Because
* it is pinned, we know that the log has not been pushed to disk and
* hence it will still be locked. Rather than sleeping until someone
* else pushes the log, push it ourselves before trying to get the lock.
*/
void
xfs_buf_lock(
struct xfs_buf *bp)
{
trace_xfs_buf_lock(bp, _RET_IP_);
if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
xfs_log_force(bp->b_target->bt_mount, 0);
down(&bp->b_sema);
XB_SET_OWNER(bp);
trace_xfs_buf_lock_done(bp, _RET_IP_);
}
/*
* Releases the lock on the buffer object.
* If the buffer is marked delwri but is not queued, do so before we
* unlock the buffer as we need to set flags correctly. We also need to
* take a reference for the delwri queue because the unlocker is going to
* drop their's and they don't know we just queued it.
*/
void
xfs_buf_unlock(
struct xfs_buf *bp)
{
if ((bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)) == XBF_DELWRI) {
atomic_inc(&bp->b_hold);
bp->b_flags |= XBF_ASYNC;
xfs_buf_delwri_queue(bp, 0);
}
XB_CLEAR_OWNER(bp);
up(&bp->b_sema);
trace_xfs_buf_unlock(bp, _RET_IP_);
}
STATIC void
xfs_buf_wait_unpin(
xfs_buf_t *bp)
{
DECLARE_WAITQUEUE (wait, current);
if (atomic_read(&bp->b_pin_count) == 0)
return;
add_wait_queue(&bp->b_waiters, &wait);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (atomic_read(&bp->b_pin_count) == 0)
break;
io_schedule();
}
remove_wait_queue(&bp->b_waiters, &wait);
set_current_state(TASK_RUNNING);
}
/*
* Buffer Utility Routines
*/
STATIC void
xfs_buf_iodone_work(
struct work_struct *work)
{
xfs_buf_t *bp =
container_of(work, xfs_buf_t, b_iodone_work);
if (bp->b_iodone)
(*(bp->b_iodone))(bp);
else if (bp->b_flags & XBF_ASYNC)
xfs_buf_relse(bp);
}
void
xfs_buf_ioend(
xfs_buf_t *bp,
int schedule)
{
trace_xfs_buf_iodone(bp, _RET_IP_);
bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
if (bp->b_error == 0)
bp->b_flags |= XBF_DONE;
if ((bp->b_iodone) || (bp->b_flags & XBF_ASYNC)) {