/
ffs_alloc.c
1570 lines (1441 loc) · 43.2 KB
/
ffs_alloc.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
/* $OpenBSD: ffs_alloc.c,v 1.110 2020/02/21 11:13:55 otto Exp $ */
/* $NetBSD: ffs_alloc.c,v 1.11 1996/05/11 18:27:09 mycroft Exp $ */
/*
* Copyright (c) 2002 Networks Associates Technology, Inc.
* All rights reserved.
*
* This software was developed for the FreeBSD Project by Marshall
* Kirk McKusick and Network Associates Laboratories, the Security
* Research Division of Network Associates, Inc. under DARPA/SPAWAR
* contract N66001-01-C-8035 ("CBOSS"), as part of the DARPA CHATS
* research program.
*
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)ffs_alloc.c 8.11 (Berkeley) 10/27/94
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/buf.h>
#include <sys/vnode.h>
#include <sys/mount.h>
#include <sys/syslog.h>
#include <sys/stdint.h>
#include <sys/time.h>
#include <ufs/ufs/quota.h>
#include <ufs/ufs/inode.h>
#include <ufs/ufs/ufsmount.h>
#include <ufs/ufs/ufs_extern.h>
#include <ufs/ffs/fs.h>
#include <ufs/ffs/ffs_extern.h>
#define ffs_fserr(fs, uid, cp) do { \
log(LOG_ERR, "uid %u on %s: %s\n", (uid), \
(fs)->fs_fsmnt, (cp)); \
} while (0)
daddr_t ffs_alloccg(struct inode *, int, daddr_t, int);
struct buf * ffs_cgread(struct fs *, struct inode *, int);
daddr_t ffs_alloccgblk(struct inode *, struct buf *, daddr_t);
ufsino_t ffs_dirpref(struct inode *);
daddr_t ffs_fragextend(struct inode *, int, daddr_t, int, int);
daddr_t ffs_hashalloc(struct inode *, int, daddr_t, int,
daddr_t (*)(struct inode *, int, daddr_t, int));
daddr_t ffs_nodealloccg(struct inode *, int, daddr_t, int);
daddr_t ffs_mapsearch(struct fs *, struct cg *, daddr_t, int);
static const struct timeval fserr_interval = { 2, 0 };
/*
* Allocate a block in the file system.
*
* The size of the requested block is given, which must be some
* multiple of fs_fsize and <= fs_bsize.
* A preference may be optionally specified. If a preference is given
* the following hierarchy is used to allocate a block:
* 1) allocate the requested block.
* 2) allocate a rotationally optimal block in the same cylinder.
* 3) allocate a block in the same cylinder group.
* 4) quadratically rehash into other cylinder groups, until an
* available block is located.
* If no block preference is given the following hierarchy is used
* to allocate a block:
* 1) allocate a block in the cylinder group that contains the
* inode for the file.
* 2) quadratically rehash into other cylinder groups, until an
* available block is located.
*/
int
ffs_alloc(struct inode *ip, daddr_t lbn, daddr_t bpref, int size,
struct ucred *cred, daddr_t *bnp)
{
static struct timeval fsfull_last;
struct fs *fs;
daddr_t bno;
int cg;
int error;
*bnp = 0;
fs = ip->i_fs;
#ifdef DIAGNOSTIC
if ((u_int)size > fs->fs_bsize || fragoff(fs, size) != 0) {
printf("dev = 0x%x, bsize = %d, size = %d, fs = %s\n",
ip->i_dev, fs->fs_bsize, size, fs->fs_fsmnt);
panic("ffs_alloc: bad size");
}
if (cred == NOCRED)
panic("ffs_alloc: missing credential");
#endif /* DIAGNOSTIC */
if (size == fs->fs_bsize && fs->fs_cstotal.cs_nbfree == 0)
goto nospace;
if (cred->cr_uid != 0 && freespace(fs, fs->fs_minfree) <= 0)
goto nospace;
if ((error = ufs_quota_alloc_blocks(ip, btodb(size), cred)) != 0)
return (error);
/*
* Start allocation in the preferred block's cylinder group or
* the file's inode's cylinder group if no preferred block was
* specified.
*/
if (bpref >= fs->fs_size)
bpref = 0;
if (bpref == 0)
cg = ino_to_cg(fs, ip->i_number);
else
cg = dtog(fs, bpref);
/* Try allocating a block. */
bno = ffs_hashalloc(ip, cg, bpref, size, ffs_alloccg);
if (bno > 0) {
/* allocation successful, update inode data */
DIP_ADD(ip, blocks, btodb(size));
ip->i_flag |= IN_CHANGE | IN_UPDATE;
*bnp = bno;
return (0);
}
/* Restore user's disk quota because allocation failed. */
(void) ufs_quota_free_blocks(ip, btodb(size), cred);
nospace:
if (ratecheck(&fsfull_last, &fserr_interval)) {
ffs_fserr(fs, cred->cr_uid, "file system full");
uprintf("\n%s: write failed, file system is full\n",
fs->fs_fsmnt);
}
return (ENOSPC);
}
/*
* Reallocate a fragment to a bigger size
*
* The number and size of the old block is given, and a preference
* and new size is also specified. The allocator attempts to extend
* the original block. Failing that, the regular block allocator is
* invoked to get an appropriate block.
*/
int
ffs_realloccg(struct inode *ip, daddr_t lbprev, daddr_t bpref, int osize,
int nsize, struct ucred *cred, struct buf **bpp, daddr_t *blknop)
{
static struct timeval fsfull_last;
struct fs *fs;
struct buf *bp = NULL;
daddr_t quota_updated = 0;
int cg, request, error;
daddr_t bprev, bno;
if (bpp != NULL)
*bpp = NULL;
fs = ip->i_fs;
#ifdef DIAGNOSTIC
if ((u_int)osize > fs->fs_bsize || fragoff(fs, osize) != 0 ||
(u_int)nsize > fs->fs_bsize || fragoff(fs, nsize) != 0) {
printf(
"dev = 0x%x, bsize = %d, osize = %d, nsize = %d, fs = %s\n",
ip->i_dev, fs->fs_bsize, osize, nsize, fs->fs_fsmnt);
panic("ffs_realloccg: bad size");
}
if (cred == NOCRED)
panic("ffs_realloccg: missing credential");
#endif /* DIAGNOSTIC */
if (cred->cr_uid != 0 && freespace(fs, fs->fs_minfree) <= 0)
goto nospace;
bprev = DIP(ip, db[lbprev]);
if (bprev == 0) {
printf("dev = 0x%x, bsize = %d, bprev = %lld, fs = %s\n",
ip->i_dev, fs->fs_bsize, (long long)bprev, fs->fs_fsmnt);
panic("ffs_realloccg: bad bprev");
}
/*
* Allocate the extra space in the buffer.
*/
if (bpp != NULL) {
if ((error = bread(ITOV(ip), lbprev, fs->fs_bsize, &bp)) != 0)
goto error;
buf_adjcnt(bp, osize);
}
if ((error = ufs_quota_alloc_blocks(ip, btodb(nsize - osize), cred))
!= 0)
goto error;
quota_updated = btodb(nsize - osize);
/*
* Check for extension in the existing location.
*/
cg = dtog(fs, bprev);
if ((bno = ffs_fragextend(ip, cg, bprev, osize, nsize)) != 0) {
DIP_ADD(ip, blocks, btodb(nsize - osize));
ip->i_flag |= IN_CHANGE | IN_UPDATE;
if (bpp != NULL) {
if (bp->b_blkno != fsbtodb(fs, bno))
panic("ffs_realloccg: bad blockno");
#ifdef DIAGNOSTIC
if (nsize > bp->b_bufsize)
panic("ffs_realloccg: small buf");
#endif
buf_adjcnt(bp, nsize);
bp->b_flags |= B_DONE;
memset(bp->b_data + osize, 0, nsize - osize);
*bpp = bp;
}
if (blknop != NULL) {
*blknop = bno;
}
return (0);
}
/*
* Allocate a new disk location.
*/
if (bpref >= fs->fs_size)
bpref = 0;
switch (fs->fs_optim) {
case FS_OPTSPACE:
/*
* Allocate an exact sized fragment. Although this makes
* best use of space, we will waste time relocating it if
* the file continues to grow. If the fragmentation is
* less than half of the minimum free reserve, we choose
* to begin optimizing for time.
*/
request = nsize;
if (fs->fs_minfree < 5 ||
fs->fs_cstotal.cs_nffree >
fs->fs_dsize * fs->fs_minfree / (2 * 100))
break;
fs->fs_optim = FS_OPTTIME;
break;
case FS_OPTTIME:
/*
* At this point we have discovered a file that is trying to
* grow a small fragment to a larger fragment. To save time,
* we allocate a full sized block, then free the unused portion.
* If the file continues to grow, the `ffs_fragextend' call
* above will be able to grow it in place without further
* copying. If aberrant programs cause disk fragmentation to
* grow within 2% of the free reserve, we choose to begin
* optimizing for space.
*/
request = fs->fs_bsize;
if (fs->fs_cstotal.cs_nffree <
fs->fs_dsize * (fs->fs_minfree - 2) / 100)
break;
fs->fs_optim = FS_OPTSPACE;
break;
default:
printf("dev = 0x%x, optim = %d, fs = %s\n",
ip->i_dev, fs->fs_optim, fs->fs_fsmnt);
panic("ffs_realloccg: bad optim");
/* NOTREACHED */
}
bno = ffs_hashalloc(ip, cg, bpref, request, ffs_alloccg);
if (bno <= 0)
goto nospace;
(void) uvm_vnp_uncache(ITOV(ip));
if (!DOINGSOFTDEP(ITOV(ip)))
ffs_blkfree(ip, bprev, (long)osize);
if (nsize < request)
ffs_blkfree(ip, bno + numfrags(fs, nsize),
(long)(request - nsize));
DIP_ADD(ip, blocks, btodb(nsize - osize));
ip->i_flag |= IN_CHANGE | IN_UPDATE;
if (bpp != NULL) {
bp->b_blkno = fsbtodb(fs, bno);
#ifdef DIAGNOSTIC
if (nsize > bp->b_bufsize)
panic("ffs_realloccg: small buf 2");
#endif
buf_adjcnt(bp, nsize);
bp->b_flags |= B_DONE;
memset(bp->b_data + osize, 0, nsize - osize);
*bpp = bp;
}
if (blknop != NULL) {
*blknop = bno;
}
return (0);
nospace:
if (ratecheck(&fsfull_last, &fserr_interval)) {
ffs_fserr(fs, cred->cr_uid, "file system full");
uprintf("\n%s: write failed, file system is full\n",
fs->fs_fsmnt);
}
error = ENOSPC;
error:
if (bp != NULL) {
brelse(bp);
bp = NULL;
}
/*
* Restore user's disk quota because allocation failed.
*/
if (quota_updated != 0)
(void)ufs_quota_free_blocks(ip, quota_updated, cred);
return error;
}
/*
* Allocate an inode in the file system.
*
* If allocating a directory, use ffs_dirpref to select the inode.
* If allocating in a directory, the following hierarchy is followed:
* 1) allocate the preferred inode.
* 2) allocate an inode in the same cylinder group.
* 3) quadratically rehash into other cylinder groups, until an
* available inode is located.
* If no inode preference is given the following hierarchy is used
* to allocate an inode:
* 1) allocate an inode in cylinder group 0.
* 2) quadratically rehash into other cylinder groups, until an
* available inode is located.
*/
int
ffs_inode_alloc(struct inode *pip, mode_t mode, struct ucred *cred,
struct vnode **vpp)
{
static struct timeval fsnoinodes_last;
struct vnode *pvp = ITOV(pip);
struct fs *fs;
struct inode *ip;
ufsino_t ino, ipref;
int cg, error;
*vpp = NULL;
fs = pip->i_fs;
if (fs->fs_cstotal.cs_nifree == 0)
goto noinodes;
if ((mode & IFMT) == IFDIR)
ipref = ffs_dirpref(pip);
else
ipref = pip->i_number;
if (ipref >= fs->fs_ncg * fs->fs_ipg)
ipref = 0;
cg = ino_to_cg(fs, ipref);
/*
* Track number of dirs created one after another
* in a same cg without intervening by files.
*/
if ((mode & IFMT) == IFDIR) {
if (fs->fs_contigdirs[cg] < 255)
fs->fs_contigdirs[cg]++;
} else {
if (fs->fs_contigdirs[cg] > 0)
fs->fs_contigdirs[cg]--;
}
ino = (ufsino_t)ffs_hashalloc(pip, cg, ipref, mode, ffs_nodealloccg);
if (ino == 0)
goto noinodes;
error = VFS_VGET(pvp->v_mount, ino, vpp);
if (error) {
ffs_inode_free(pip, ino, mode);
return (error);
}
ip = VTOI(*vpp);
if (DIP(ip, mode)) {
printf("mode = 0%o, inum = %u, fs = %s\n",
DIP(ip, mode), ip->i_number, fs->fs_fsmnt);
panic("ffs_valloc: dup alloc");
}
if (DIP(ip, blocks)) {
printf("free inode %s/%d had %lld blocks\n",
fs->fs_fsmnt, ino, (long long)DIP(ip, blocks));
DIP_ASSIGN(ip, blocks, 0);
}
DIP_ASSIGN(ip, flags, 0);
/*
* Set up a new generation number for this inode.
* XXX - just increment for now, this is wrong! (millert)
* Need a way to preserve randomization.
*/
if (DIP(ip, gen) != 0)
DIP_ADD(ip, gen, 1);
if (DIP(ip, gen) == 0)
DIP_ASSIGN(ip, gen, arc4random() & INT_MAX);
if (DIP(ip, gen) == 0 || DIP(ip, gen) == -1)
DIP_ASSIGN(ip, gen, 1); /* Shouldn't happen */
return (0);
noinodes:
if (ratecheck(&fsnoinodes_last, &fserr_interval)) {
ffs_fserr(fs, cred->cr_uid, "out of inodes");
uprintf("\n%s: create/symlink failed, no inodes free\n",
fs->fs_fsmnt);
}
return (ENOSPC);
}
/*
* Find a cylinder group to place a directory.
*
* The policy implemented by this algorithm is to allocate a
* directory inode in the same cylinder group as its parent
* directory, but also to reserve space for its files inodes
* and data. Restrict the number of directories which may be
* allocated one after another in the same cylinder group
* without intervening allocation of files.
*
* If we allocate a first level directory then force allocation
* in another cylinder group.
*/
ufsino_t
ffs_dirpref(struct inode *pip)
{
struct fs *fs;
int cg, prefcg, dirsize, cgsize;
int avgifree, avgbfree, avgndir, curdirsize;
int minifree, minbfree, maxndir;
int mincg, minndir;
int maxcontigdirs;
fs = pip->i_fs;
avgifree = fs->fs_cstotal.cs_nifree / fs->fs_ncg;
avgbfree = fs->fs_cstotal.cs_nbfree / fs->fs_ncg;
avgndir = fs->fs_cstotal.cs_ndir / fs->fs_ncg;
/*
* Force allocation in another cg if creating a first level dir.
*/
if (ITOV(pip)->v_flag & VROOT) {
prefcg = arc4random_uniform(fs->fs_ncg);
mincg = prefcg;
minndir = fs->fs_ipg;
for (cg = prefcg; cg < fs->fs_ncg; cg++)
if (fs->fs_cs(fs, cg).cs_ndir < minndir &&
fs->fs_cs(fs, cg).cs_nifree >= avgifree &&
fs->fs_cs(fs, cg).cs_nbfree >= avgbfree) {
mincg = cg;
minndir = fs->fs_cs(fs, cg).cs_ndir;
}
for (cg = 0; cg < prefcg; cg++)
if (fs->fs_cs(fs, cg).cs_ndir < minndir &&
fs->fs_cs(fs, cg).cs_nifree >= avgifree &&
fs->fs_cs(fs, cg).cs_nbfree >= avgbfree) {
mincg = cg;
minndir = fs->fs_cs(fs, cg).cs_ndir;
}
cg = mincg;
goto end;
} else
prefcg = ino_to_cg(fs, pip->i_number);
/*
* Count various limits which used for
* optimal allocation of a directory inode.
*/
maxndir = min(avgndir + fs->fs_ipg / 16, fs->fs_ipg);
minifree = avgifree - (avgifree / 4);
if (minifree < 1)
minifree = 1;
minbfree = avgbfree - (avgbfree / 4);
if (minbfree < 1)
minbfree = 1;
cgsize = fs->fs_fsize * fs->fs_fpg;
dirsize = fs->fs_avgfilesize * fs->fs_avgfpdir;
curdirsize = avgndir ? (cgsize - avgbfree * fs->fs_bsize) / avgndir : 0;
if (dirsize < curdirsize)
dirsize = curdirsize;
if (dirsize <= 0)
maxcontigdirs = 0; /* dirsize overflowed */
else
maxcontigdirs = min(avgbfree * fs->fs_bsize / dirsize, 255);
if (fs->fs_avgfpdir > 0)
maxcontigdirs = min(maxcontigdirs,
fs->fs_ipg / fs->fs_avgfpdir);
if (maxcontigdirs == 0)
maxcontigdirs = 1;
/*
* Limit number of dirs in one cg and reserve space for
* regular files, but only if we have no deficit in
* inodes or space.
*
* We are trying to find a suitable cylinder group nearby
* our preferred cylinder group to place a new directory.
* We scan from our preferred cylinder group forward looking
* for a cylinder group that meets our criterion. If we get
* to the final cylinder group and do not find anything,
* we start scanning backwards from our preferred cylinder
* group. The ideal would be to alternate looking forward
* and backward, but tha tis just too complex to code for
* the gain it would get. The most likely place where the
* backward scan would take effect is when we start near
* the end of the filesystem and do not find anything from
* where we are to the end. In that case, scanning backward
* will likely find us a suitable cylinder group much closer
* to our desired location than if we were to start scanning
* forward from the beginning for the filesystem.
*/
for (cg = prefcg; cg < fs->fs_ncg; cg++)
if (fs->fs_cs(fs, cg).cs_ndir < maxndir &&
fs->fs_cs(fs, cg).cs_nifree >= minifree &&
fs->fs_cs(fs, cg).cs_nbfree >= minbfree) {
if (fs->fs_contigdirs[cg] < maxcontigdirs)
goto end;
}
for (cg = prefcg - 1; cg >= 0; cg--)
if (fs->fs_cs(fs, cg).cs_ndir < maxndir &&
fs->fs_cs(fs, cg).cs_nifree >= minifree &&
fs->fs_cs(fs, cg).cs_nbfree >= minbfree) {
if (fs->fs_contigdirs[cg] < maxcontigdirs)
goto end;
}
/*
* This is a backstop when we have deficit in space.
*/
for (cg = prefcg; cg < fs->fs_ncg; cg++)
if (fs->fs_cs(fs, cg).cs_nifree >= avgifree)
goto end;
for (cg = prefcg - 1; cg >= 0; cg--)
if (fs->fs_cs(fs, cg).cs_nifree >= avgifree)
goto end;
end:
return ((ufsino_t)(fs->fs_ipg * cg));
}
/*
* Select the desired position for the next block in a file. The file is
* logically divided into sections. The first section is composed of the
* direct blocks. Each additional section contains fs_maxbpg blocks.
*
* If no blocks have been allocated in the first section, the policy is to
* request a block in the same cylinder group as the inode that describes
* the file. The first indirect is allocated immediately following the last
* direct block and the data blocks for the first indirect immediately
* follow it.
*
* If no blocks have been allocated in any other section, the indirect
* block(s) are allocated in the same cylinder group as its inode in an
* area reserved immediately following the inode blocks. The policy for
* the data blocks is to place them in a cylinder group with a greater than
* average number of free blocks. An appropriate cylinder group is found
* by using a rotor that sweeps the cylinder groups. When a new group of
* blocks is needed, the sweep begins in the cylinder group following the
* cylinder group from which the previous allocation was made. The sweep
* continues until a cylinder group with greater than the average number
* of free blocks is found. If the allocation is for the first block in an
* indirect block, the information on the previous allocation is unavailable;
* here a best guess is made based upon the logical block number being
* allocated.
*/
int32_t
ffs1_blkpref(struct inode *ip, daddr_t lbn, int indx, int32_t *bap)
{
struct fs *fs;
int cg, inocg, avgbfree, startcg;
uint32_t pref;
KASSERT(indx <= 0 || bap != NULL);
fs = ip->i_fs;
/*
* Allocation of indirect blocks is indicated by passing negative
* values in indx: -1 for single indirect, -2 for double indirect,
* -3 for triple indirect. As noted below, we attempt to allocate
* the first indirect inline with the file data. For all later
* indirect blocks, the data is often allocated in other cylinder
* groups. However to speed random file access and to speed up
* fsck, the filesystem reserves the first fs_metaspace blocks
* (typically half of fs_minfree) of the data area of each cylinder
* group to hold these later indirect blocks.
*/
inocg = ino_to_cg(fs, ip->i_number);
if (indx < 0) {
/*
* Our preference for indirect blocks is the zone at the
* beginning of the inode's cylinder group data area that
* we try to reserve for indirect blocks.
*/
pref = cgmeta(fs, inocg);
/*
* If we are allocating the first indirect block, try to
* place it immediately following the last direct block.
*/
if (indx == -1 && lbn < NDADDR + NINDIR(fs) &&
ip->i_din1->di_db[NDADDR - 1] != 0)
pref = ip->i_din1->di_db[NDADDR - 1] + fs->fs_frag;
return (pref);
}
/*
* If we are allocating the first data block in the first indirect
* block and the indirect has been allocated in the data block area,
* try to place it immediately following the indirect block.
*/
if (lbn == NDADDR) {
pref = ip->i_din1->di_ib[0];
if (pref != 0 && pref >= cgdata(fs, inocg) &&
pref < cgbase(fs, inocg + 1))
return (pref + fs->fs_frag);
}
/*
* If we are the beginning of a file, or we have already allocated
* the maximum number of blocks per cylinder group, or we do not
* have a block allocated immediately preceding us, then we need
* to decide where to start allocating new blocks.
*/
if (indx % fs->fs_maxbpg == 0 || bap[indx - 1] == 0) {
/*
* If we are allocating a directory data block, we want
* to place it in the metadata area.
*/
if ((DIP(ip, mode) & IFMT) == IFDIR)
return (cgmeta(fs, inocg));
/*
* Until we fill all the direct and all the first indirect's
* blocks, we try to allocate in the data area of the inode's
* cylinder group.
*/
if (lbn < NDADDR + NINDIR(fs))
return (cgdata(fs, inocg));
/*
* Find a cylinder with greater than average number of
* unused data blocks.
*/
if (indx == 0 || bap[indx - 1] == 0)
startcg = inocg + lbn / fs->fs_maxbpg;
else
startcg = dtog(fs, bap[indx - 1]) + 1;
startcg %= fs->fs_ncg;
avgbfree = fs->fs_cstotal.cs_nbfree / fs->fs_ncg;
for (cg = startcg; cg < fs->fs_ncg; cg++)
if (fs->fs_cs(fs, cg).cs_nbfree >= avgbfree) {
fs->fs_cgrotor = cg;
return (cgdata(fs, cg));
}
for (cg = 0; cg <= startcg; cg++)
if (fs->fs_cs(fs, cg).cs_nbfree >= avgbfree) {
fs->fs_cgrotor = cg;
return (cgdata(fs, cg));
}
return (0);
}
/*
* Otherwise, we just always try to lay things out contiguously.
*/
return (bap[indx - 1] + fs->fs_frag);
}
/*
* Same as above, for UFS2.
*/
#ifdef FFS2
int64_t
ffs2_blkpref(struct inode *ip, daddr_t lbn, int indx, int64_t *bap)
{
struct fs *fs;
int cg, inocg, avgbfree, startcg;
uint64_t pref;
KASSERT(indx <= 0 || bap != NULL);
fs = ip->i_fs;
/*
* Allocation of indirect blocks is indicated by passing negative
* values in indx: -1 for single indirect, -2 for double indirect,
* -3 for triple indirect. As noted below, we attempt to allocate
* the first indirect inline with the file data. For all later
* indirect blocks, the data is often allocated in other cylinder
* groups. However to speed random file access and to speed up
* fsck, the filesystem reserves the first fs_metaspace blocks
* (typically half of fs_minfree) of the data area of each cylinder
* group to hold these later indirect blocks.
*/
inocg = ino_to_cg(fs, ip->i_number);
if (indx < 0) {
/*
* Our preference for indirect blocks is the zone at the
* beginning of the inode's cylinder group data area that
* we try to reserve for indirect blocks.
*/
pref = cgmeta(fs, inocg);
/*
* If we are allocating the first indirect block, try to
* place it immediately following the last direct block.
*/
if (indx == -1 && lbn < NDADDR + NINDIR(fs) &&
ip->i_din2->di_db[NDADDR - 1] != 0)
pref = ip->i_din2->di_db[NDADDR - 1] + fs->fs_frag;
return (pref);
}
/*
* If we are allocating the first data block in the first indirect
* block and the indirect has been allocated in the data block area,
* try to place it immediately following the indirect block.
*/
if (lbn == NDADDR) {
pref = ip->i_din2->di_ib[0];
if (pref != 0 && pref >= cgdata(fs, inocg) &&
pref < cgbase(fs, inocg + 1))
return (pref + fs->fs_frag);
}
/*
* If we are the beginning of a file, or we have already allocated
* the maximum number of blocks per cylinder group, or we do not
* have a block allocated immediately preceding us, then we need
* to decide where to start allocating new blocks.
*/
if (indx % fs->fs_maxbpg == 0 || bap[indx - 1] == 0) {
/*
* If we are allocating a directory data block, we want
* to place it in the metadata area.
*/
if ((DIP(ip, mode) & IFMT) == IFDIR)
return (cgmeta(fs, inocg));
/*
* Until we fill all the direct and all the first indirect's
* blocks, we try to allocate in the data area of the inode's
* cylinder group.
*/
if (lbn < NDADDR + NINDIR(fs))
return (cgdata(fs, inocg));
/*
* Find a cylinder with greater than average number of
* unused data blocks.
*/
if (indx == 0 || bap[indx - 1] == 0)
startcg = inocg + lbn / fs->fs_maxbpg;
else
startcg = dtog(fs, bap[indx - 1] + 1);
startcg %= fs->fs_ncg;
avgbfree = fs->fs_cstotal.cs_nbfree / fs->fs_ncg;
for (cg = startcg; cg < fs->fs_ncg; cg++)
if (fs->fs_cs(fs, cg).cs_nbfree >= avgbfree)
return (cgbase(fs, cg) + fs->fs_frag);
for (cg = 0; cg < startcg; cg++)
if (fs->fs_cs(fs, cg).cs_nbfree >= avgbfree)
return (cgbase(fs, cg) + fs->fs_frag);
return (0);
}
/*
* Otherwise, we just always try to lay things out contiguously.
*/
return (bap[indx - 1] + fs->fs_frag);
}
#endif /* FFS2 */
/*
* Implement the cylinder overflow algorithm.
*
* The policy implemented by this algorithm is:
* 1) allocate the block in its requested cylinder group.
* 2) quadratically rehash on the cylinder group number.
* 3) brute force search for a free block.
*/
daddr_t
ffs_hashalloc(struct inode *ip, int cg, daddr_t pref, int size,
daddr_t (*allocator)(struct inode *, int, daddr_t, int))
{
struct fs *fs;
daddr_t result;
int i, icg = cg;
fs = ip->i_fs;
/*
* 1: preferred cylinder group
*/
result = (*allocator)(ip, cg, pref, size);
if (result)
return (result);
/*
* 2: quadratic rehash
*/
for (i = 1; i < fs->fs_ncg; i *= 2) {
cg += i;
if (cg >= fs->fs_ncg)
cg -= fs->fs_ncg;
result = (*allocator)(ip, cg, 0, size);
if (result)
return (result);
}
/*
* 3: brute force search
* Note that we start at i == 2, since 0 was checked initially,
* and 1 is always checked in the quadratic rehash.
*/
cg = (icg + 2) % fs->fs_ncg;
for (i = 2; i < fs->fs_ncg; i++) {
result = (*allocator)(ip, cg, 0, size);
if (result)
return (result);
cg++;
if (cg == fs->fs_ncg)
cg = 0;
}
return (0);
}
struct buf *
ffs_cgread(struct fs *fs, struct inode *ip, int cg)
{
struct buf *bp;
if (bread(ip->i_devvp, fsbtodb(fs, cgtod(fs, cg)),
(int)fs->fs_cgsize, &bp)) {
brelse(bp);
return (NULL);
}
if (!cg_chkmagic((struct cg *)bp->b_data)) {
brelse(bp);
return (NULL);
}
return bp;
}
/*
* Determine whether a fragment can be extended.
*
* Check to see if the necessary fragments are available, and
* if they are, allocate them.
*/
daddr_t
ffs_fragextend(struct inode *ip, int cg, daddr_t bprev, int osize, int nsize)
{
struct fs *fs;
struct cg *cgp;
struct buf *bp;
struct timespec now;
daddr_t bno;
int i, frags, bbase;
fs = ip->i_fs;
if (fs->fs_cs(fs, cg).cs_nffree < numfrags(fs, nsize - osize))
return (0);
frags = numfrags(fs, nsize);
bbase = fragnum(fs, bprev);
if (bbase > fragnum(fs, (bprev + frags - 1))) {
/* cannot extend across a block boundary */
return (0);
}
if (!(bp = ffs_cgread(fs, ip, cg)))
return (0);
cgp = (struct cg *)bp->b_data;
nanotime(&now);
cgp->cg_ffs2_time = now.tv_sec;
cgp->cg_time = now.tv_sec;
bno = dtogd(fs, bprev);
for (i = numfrags(fs, osize); i < frags; i++)
if (isclr(cg_blksfree(cgp), bno + i)) {
brelse(bp);
return (0);
}
/*
* the current fragment can be extended
* deduct the count on fragment being extended into
* increase the count on the remaining fragment (if any)
* allocate the extended piece
*/
for (i = frags; i < fs->fs_frag - bbase; i++)
if (isclr(cg_blksfree(cgp), bno + i))
break;
cgp->cg_frsum[i - numfrags(fs, osize)]--;
if (i != frags)
cgp->cg_frsum[i - frags]++;
for (i = numfrags(fs, osize); i < frags; i++) {
clrbit(cg_blksfree(cgp), bno + i);
cgp->cg_cs.cs_nffree--;
fs->fs_cstotal.cs_nffree--;
fs->fs_cs(fs, cg).cs_nffree--;
}
fs->fs_fmod = 1;
if (DOINGSOFTDEP(ITOV(ip)))
softdep_setup_blkmapdep(bp, fs, bprev);
bdwrite(bp);
return (bprev);
}
/*
* Determine whether a block can be allocated.
*
* Check to see if a block of the appropriate size is available,
* and if it is, allocate it.
*/
daddr_t
ffs_alloccg(struct inode *ip, int cg, daddr_t bpref, int size)
{
struct fs *fs;
struct cg *cgp;
struct buf *bp;
struct timespec now;
daddr_t bno, blkno;
int i, frags, allocsiz;
fs = ip->i_fs;
if (fs->fs_cs(fs, cg).cs_nbfree == 0 && size == fs->fs_bsize)
return (0);
if (!(bp = ffs_cgread(fs, ip, cg)))
return (0);
cgp = (struct cg *)bp->b_data;
if (cgp->cg_cs.cs_nbfree == 0 && size == fs->fs_bsize) {
brelse(bp);
return (0);
}
nanotime(&now);
cgp->cg_ffs2_time = now.tv_sec;
cgp->cg_time = now.tv_sec;
if (size == fs->fs_bsize) {
/* allocate and return a complete data block */
bno = ffs_alloccgblk(ip, bp, bpref);
bdwrite(bp);
return (bno);
}
/*
* check to see if any fragments are already available
* allocsiz is the size which will be allocated, hacking
* it down to a smaller size if necessary
*/
frags = numfrags(fs, size);
for (allocsiz = frags; allocsiz < fs->fs_frag; allocsiz++)
if (cgp->cg_frsum[allocsiz] != 0)
break;
if (allocsiz == fs->fs_frag) {
/*
* no fragments were available, so a block will be
* allocated, and hacked up
*/
if (cgp->cg_cs.cs_nbfree == 0) {
brelse(bp);
return (0);
}
bno = ffs_alloccgblk(ip, bp, bpref);
bpref = dtogd(fs, bno);
for (i = frags; i < fs->fs_frag; i++)
setbit(cg_blksfree(cgp), bpref + i);
i = fs->fs_frag - frags;
cgp->cg_cs.cs_nffree += i;
fs->fs_cstotal.cs_nffree += i;
fs->fs_cs(fs, cg).cs_nffree += i;
fs->fs_fmod = 1;
cgp->cg_frsum[i]++;
bdwrite(bp);
return (bno);
}
bno = ffs_mapsearch(fs, cgp, bpref, allocsiz);
if (bno < 0) {
brelse(bp);