-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathread-cache.c
2360 lines (2089 loc) · 62.5 KB
/
read-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
/*
* GIT - The information manager from hell
*
* Copyright (C) Linus Torvalds, 2005
*/
#define NO_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
#include "tempfile.h"
#include "lockfile.h"
#include "cache-tree.h"
#include "refs.h"
#include "dir.h"
#include "tree.h"
#include "commit.h"
#include "blob.h"
#include "resolve-undo.h"
#include "strbuf.h"
#include "varint.h"
#include "split-index.h"
#include "utf8.h"
/* Mask for the name length in ce_flags in the on-disk index */
#define CE_NAMEMASK (0x0fff)
/* Index extensions.
*
* The first letter should be 'A'..'Z' for extensions that are not
* necessary for a correct operation (i.e. optimization data).
* When new extensions are added that _needs_ to be understood in
* order to correctly interpret the index file, pick character that
* is outside the range, to cause the reader to abort.
*/
#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
#define CACHE_EXT_TREE 0x54524545 /* "TREE" */
#define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
#define CACHE_EXT_LINK 0x6c696e6b /* "link" */
#define CACHE_EXT_UNTRACKED 0x554E5452 /* "UNTR" */
/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED)
struct index_state the_index;
static const char *alternate_index_output;
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
istate->cache[nr] = ce;
add_name_hash(istate, ce);
}
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
struct cache_entry *old = istate->cache[nr];
replace_index_entry_in_base(istate, old, ce);
remove_name_hash(istate, old);
free(old);
set_index_entry(istate, nr, ce);
ce->ce_flags |= CE_UPDATE_IN_BASE;
istate->cache_changed |= CE_ENTRY_CHANGED;
}
void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
{
struct cache_entry *old = istate->cache[nr], *new;
int namelen = strlen(new_name);
new = xmalloc(cache_entry_size(namelen));
copy_cache_entry(new, old);
new->ce_flags &= ~CE_HASHED;
new->ce_namelen = namelen;
new->index = 0;
memcpy(new->name, new_name, namelen + 1);
cache_tree_invalidate_path(istate, old->name);
untracked_cache_remove_from_index(istate, old->name);
remove_index_entry_at(istate, nr);
add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}
void fill_stat_data(struct stat_data *sd, struct stat *st)
{
sd->sd_ctime.sec = (unsigned int)st->st_ctime;
sd->sd_mtime.sec = (unsigned int)st->st_mtime;
sd->sd_ctime.nsec = ST_CTIME_NSEC(*st);
sd->sd_mtime.nsec = ST_MTIME_NSEC(*st);
sd->sd_dev = st->st_dev;
sd->sd_ino = st->st_ino;
sd->sd_uid = st->st_uid;
sd->sd_gid = st->st_gid;
sd->sd_size = st->st_size;
}
int match_stat_data(const struct stat_data *sd, struct stat *st)
{
int changed = 0;
if (sd->sd_mtime.sec != (unsigned int)st->st_mtime)
changed |= MTIME_CHANGED;
if (trust_ctime && check_stat &&
sd->sd_ctime.sec != (unsigned int)st->st_ctime)
changed |= CTIME_CHANGED;
#ifdef USE_NSEC
if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st))
changed |= MTIME_CHANGED;
if (trust_ctime && check_stat &&
sd->sd_ctime.nsec != ST_CTIME_NSEC(*st))
changed |= CTIME_CHANGED;
#endif
if (check_stat) {
if (sd->sd_uid != (unsigned int) st->st_uid ||
sd->sd_gid != (unsigned int) st->st_gid)
changed |= OWNER_CHANGED;
if (sd->sd_ino != (unsigned int) st->st_ino)
changed |= INODE_CHANGED;
}
#ifdef USE_STDEV
/*
* st_dev breaks on network filesystems where different
* clients will have different views of what "device"
* the filesystem is on
*/
if (check_stat && sd->sd_dev != (unsigned int) st->st_dev)
changed |= INODE_CHANGED;
#endif
if (sd->sd_size != (unsigned int) st->st_size)
changed |= DATA_CHANGED;
return changed;
}
/*
* This only updates the "non-critical" parts of the directory
* cache, ie the parts that aren't tracked by GIT, and only used
* to validate the cache.
*/
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
fill_stat_data(&ce->ce_stat_data, st);
if (assume_unchanged)
ce->ce_flags |= CE_VALID;
if (S_ISREG(st->st_mode))
ce_mark_uptodate(ce);
}
static int ce_compare_data(const struct cache_entry *ce, struct stat *st)
{
int match = -1;
static int cloexec = O_CLOEXEC;
int fd = open(ce->name, O_RDONLY | cloexec);
if ((cloexec & O_CLOEXEC) && fd < 0 && errno == EINVAL) {
/* Try again w/o O_CLOEXEC: the kernel might not support it */
cloexec &= ~O_CLOEXEC;
fd = open(ce->name, O_RDONLY | cloexec);
}
if (fd >= 0) {
unsigned char sha1[20];
if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0))
match = hashcmp(sha1, ce->oid.hash);
/* index_fd() closed the file descriptor already */
}
return match;
}
static int ce_compare_link(const struct cache_entry *ce, size_t expected_size)
{
int match = -1;
void *buffer;
unsigned long size;
enum object_type type;
struct strbuf sb = STRBUF_INIT;
if (strbuf_readlink(&sb, ce->name, expected_size))
return -1;
buffer = read_sha1_file(ce->oid.hash, &type, &size);
if (buffer) {
if (size == sb.len)
match = memcmp(buffer, sb.buf, size);
free(buffer);
}
strbuf_release(&sb);
return match;
}
static int ce_compare_gitlink(const struct cache_entry *ce)
{
unsigned char sha1[20];
/*
* We don't actually require that the .git directory
* under GITLINK directory be a valid git directory. It
* might even be missing (in case nobody populated that
* sub-project).
*
* If so, we consider it always to match.
*/
if (resolve_gitlink_ref(ce->name, "HEAD", sha1) < 0)
return 0;
return hashcmp(sha1, ce->oid.hash);
}
static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st)
{
switch (st->st_mode & S_IFMT) {
case S_IFREG:
if (ce_compare_data(ce, st))
return DATA_CHANGED;
break;
case S_IFLNK:
if (ce_compare_link(ce, xsize_t(st->st_size)))
return DATA_CHANGED;
break;
case S_IFDIR:
if (S_ISGITLINK(ce->ce_mode))
return ce_compare_gitlink(ce) ? DATA_CHANGED : 0;
default:
return TYPE_CHANGED;
}
return 0;
}
static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st)
{
unsigned int changed = 0;
if (ce->ce_flags & CE_REMOVE)
return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;
switch (ce->ce_mode & S_IFMT) {
case S_IFREG:
changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
/* We consider only the owner x bit to be relevant for
* "mode changes"
*/
if (trust_executable_bit &&
(0100 & (ce->ce_mode ^ st->st_mode)))
changed |= MODE_CHANGED;
break;
case S_IFLNK:
if (!S_ISLNK(st->st_mode) &&
(has_symlinks || !S_ISREG(st->st_mode)))
changed |= TYPE_CHANGED;
break;
case S_IFGITLINK:
/* We ignore most of the st_xxx fields for gitlinks */
if (!S_ISDIR(st->st_mode))
changed |= TYPE_CHANGED;
else if (ce_compare_gitlink(ce))
changed |= DATA_CHANGED;
return changed;
default:
die("internal error: ce_mode is %o", ce->ce_mode);
}
changed |= match_stat_data(&ce->ce_stat_data, st);
/* Racily smudged entry? */
if (!ce->ce_stat_data.sd_size) {
if (!is_empty_blob_sha1(ce->oid.hash))
changed |= DATA_CHANGED;
}
return changed;
}
static int is_racy_stat(const struct index_state *istate,
const struct stat_data *sd)
{
return (istate->timestamp.sec &&
#ifdef USE_NSEC
/* nanosecond timestamped files can also be racy! */
(istate->timestamp.sec < sd->sd_mtime.sec ||
(istate->timestamp.sec == sd->sd_mtime.sec &&
istate->timestamp.nsec <= sd->sd_mtime.nsec))
#else
istate->timestamp.sec <= sd->sd_mtime.sec
#endif
);
}
static int is_racy_timestamp(const struct index_state *istate,
const struct cache_entry *ce)
{
return (!S_ISGITLINK(ce->ce_mode) &&
is_racy_stat(istate, &ce->ce_stat_data));
}
int match_stat_data_racy(const struct index_state *istate,
const struct stat_data *sd, struct stat *st)
{
if (is_racy_stat(istate, sd))
return MTIME_CHANGED;
return match_stat_data(sd, st);
}
int ie_match_stat(const struct index_state *istate,
const struct cache_entry *ce, struct stat *st,
unsigned int options)
{
unsigned int changed;
int ignore_valid = options & CE_MATCH_IGNORE_VALID;
int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;
/*
* If it's marked as always valid in the index, it's
* valid whatever the checked-out copy says.
*
* skip-worktree has the same effect with higher precedence
*/
if (!ignore_skip_worktree && ce_skip_worktree(ce))
return 0;
if (!ignore_valid && (ce->ce_flags & CE_VALID))
return 0;
/*
* Intent-to-add entries have not been added, so the index entry
* by definition never matches what is in the work tree until it
* actually gets added.
*/
if (ce_intent_to_add(ce))
return DATA_CHANGED | TYPE_CHANGED | MODE_CHANGED;
changed = ce_match_stat_basic(ce, st);
/*
* Within 1 second of this sequence:
* echo xyzzy >file && git-update-index --add file
* running this command:
* echo frotz >file
* would give a falsely clean cache entry. The mtime and
* length match the cache, and other stat fields do not change.
*
* We could detect this at update-index time (the cache entry
* being registered/updated records the same time as "now")
* and delay the return from git-update-index, but that would
* effectively mean we can make at most one commit per second,
* which is not acceptable. Instead, we check cache entries
* whose mtime are the same as the index file timestamp more
* carefully than others.
*/
if (!changed && is_racy_timestamp(istate, ce)) {
if (assume_racy_is_modified)
changed |= DATA_CHANGED;
else
changed |= ce_modified_check_fs(ce, st);
}
return changed;
}
int ie_modified(const struct index_state *istate,
const struct cache_entry *ce,
struct stat *st, unsigned int options)
{
int changed, changed_fs;
changed = ie_match_stat(istate, ce, st, options);
if (!changed)
return 0;
/*
* If the mode or type has changed, there's no point in trying
* to refresh the entry - it's not going to match
*/
if (changed & (MODE_CHANGED | TYPE_CHANGED))
return changed;
/*
* Immediately after read-tree or update-index --cacheinfo,
* the length field is zero, as we have never even read the
* lstat(2) information once, and we cannot trust DATA_CHANGED
* returned by ie_match_stat() which in turn was returned by
* ce_match_stat_basic() to signal that the filesize of the
* blob changed. We have to actually go to the filesystem to
* see if the contents match, and if so, should answer "unchanged".
*
* The logic does not apply to gitlinks, as ce_match_stat_basic()
* already has checked the actual HEAD from the filesystem in the
* subproject. If ie_match_stat() already said it is different,
* then we know it is.
*/
if ((changed & DATA_CHANGED) &&
(S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
return changed;
changed_fs = ce_modified_check_fs(ce, st);
if (changed_fs)
return changed | changed_fs;
return 0;
}
int base_name_compare(const char *name1, int len1, int mode1,
const char *name2, int len2, int mode2)
{
unsigned char c1, c2;
int len = len1 < len2 ? len1 : len2;
int cmp;
cmp = memcmp(name1, name2, len);
if (cmp)
return cmp;
c1 = name1[len];
c2 = name2[len];
if (!c1 && S_ISDIR(mode1))
c1 = '/';
if (!c2 && S_ISDIR(mode2))
c2 = '/';
return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}
/*
* df_name_compare() is identical to base_name_compare(), except it
* compares conflicting directory/file entries as equal. Note that
* while a directory name compares as equal to a regular file, they
* then individually compare _differently_ to a filename that has
* a dot after the basename (because '\0' < '.' < '/').
*
* This is used by routines that want to traverse the git namespace
* but then handle conflicting entries together when possible.
*/
int df_name_compare(const char *name1, int len1, int mode1,
const char *name2, int len2, int mode2)
{
int len = len1 < len2 ? len1 : len2, cmp;
unsigned char c1, c2;
cmp = memcmp(name1, name2, len);
if (cmp)
return cmp;
/* Directories and files compare equal (same length, same name) */
if (len1 == len2)
return 0;
c1 = name1[len];
if (!c1 && S_ISDIR(mode1))
c1 = '/';
c2 = name2[len];
if (!c2 && S_ISDIR(mode2))
c2 = '/';
if (c1 == '/' && !c2)
return 0;
if (c2 == '/' && !c1)
return 0;
return c1 - c2;
}
int name_compare(const char *name1, size_t len1, const char *name2, size_t len2)
{
size_t min_len = (len1 < len2) ? len1 : len2;
int cmp = memcmp(name1, name2, min_len);
if (cmp)
return cmp;
if (len1 < len2)
return -1;
if (len1 > len2)
return 1;
return 0;
}
int cache_name_stage_compare(const char *name1, int len1, int stage1, const char *name2, int len2, int stage2)
{
int cmp;
cmp = name_compare(name1, len1, name2, len2);
if (cmp)
return cmp;
if (stage1 < stage2)
return -1;
if (stage1 > stage2)
return 1;
return 0;
}
static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage)
{
int first, last;
first = 0;
last = istate->cache_nr;
while (last > first) {
int next = (last + first) >> 1;
struct cache_entry *ce = istate->cache[next];
int cmp = cache_name_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce));
if (!cmp)
return next;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
return -first-1;
}
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
{
return index_name_stage_pos(istate, name, namelen, 0);
}
/* Remove entry, return true if there are more entries to go.. */
int remove_index_entry_at(struct index_state *istate, int pos)
{
struct cache_entry *ce = istate->cache[pos];
record_resolve_undo(istate, ce);
remove_name_hash(istate, ce);
save_or_free_index_entry(istate, ce);
istate->cache_changed |= CE_ENTRY_REMOVED;
istate->cache_nr--;
if (pos >= istate->cache_nr)
return 0;
memmove(istate->cache + pos,
istate->cache + pos + 1,
(istate->cache_nr - pos) * sizeof(struct cache_entry *));
return 1;
}
/*
* Remove all cache entries marked for removal, that is where
* CE_REMOVE is set in ce_flags. This is much more effective than
* calling remove_index_entry_at() for each entry to be removed.
*/
void remove_marked_cache_entries(struct index_state *istate)
{
struct cache_entry **ce_array = istate->cache;
unsigned int i, j;
for (i = j = 0; i < istate->cache_nr; i++) {
if (ce_array[i]->ce_flags & CE_REMOVE) {
remove_name_hash(istate, ce_array[i]);
save_or_free_index_entry(istate, ce_array[i]);
}
else
ce_array[j++] = ce_array[i];
}
if (j == istate->cache_nr)
return;
istate->cache_changed |= CE_ENTRY_REMOVED;
istate->cache_nr = j;
}
int remove_file_from_index(struct index_state *istate, const char *path)
{
int pos = index_name_pos(istate, path, strlen(path));
if (pos < 0)
pos = -pos-1;
cache_tree_invalidate_path(istate, path);
untracked_cache_remove_from_index(istate, path);
while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
remove_index_entry_at(istate, pos);
return 0;
}
static int compare_name(struct cache_entry *ce, const char *path, int namelen)
{
return namelen != ce_namelen(ce) || memcmp(path, ce->name, namelen);
}
static int index_name_pos_also_unmerged(struct index_state *istate,
const char *path, int namelen)
{
int pos = index_name_pos(istate, path, namelen);
struct cache_entry *ce;
if (pos >= 0)
return pos;
/* maybe unmerged? */
pos = -1 - pos;
if (pos >= istate->cache_nr ||
compare_name((ce = istate->cache[pos]), path, namelen))
return -1;
/* order of preference: stage 2, 1, 3 */
if (ce_stage(ce) == 1 && pos + 1 < istate->cache_nr &&
ce_stage((ce = istate->cache[pos + 1])) == 2 &&
!compare_name(ce, path, namelen))
pos++;
return pos;
}
static int different_name(struct cache_entry *ce, struct cache_entry *alias)
{
int len = ce_namelen(ce);
return ce_namelen(alias) != len || memcmp(ce->name, alias->name, len);
}
/*
* If we add a filename that aliases in the cache, we will use the
* name that we already have - but we don't want to update the same
* alias twice, because that implies that there were actually two
* different files with aliasing names!
*
* So we use the CE_ADDED flag to verify that the alias was an old
* one before we accept it as
*/
static struct cache_entry *create_alias_ce(struct index_state *istate,
struct cache_entry *ce,
struct cache_entry *alias)
{
int len;
struct cache_entry *new;
if (alias->ce_flags & CE_ADDED)
die("Will not add file alias '%s' ('%s' already exists in index)", ce->name, alias->name);
/* Ok, create the new entry using the name of the existing alias */
len = ce_namelen(alias);
new = xcalloc(1, cache_entry_size(len));
memcpy(new->name, alias->name, len);
copy_cache_entry(new, ce);
save_or_free_index_entry(istate, ce);
return new;
}
void set_object_name_for_intent_to_add_entry(struct cache_entry *ce)
{
unsigned char sha1[20];
if (write_sha1_file("", 0, blob_type, sha1))
die("cannot create an empty blob in the object database");
hashcpy(ce->oid.hash, sha1);
}
int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
{
int size, namelen, was_same;
mode_t st_mode = st->st_mode;
struct cache_entry *ce, *alias;
unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY;
int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
int pretend = flags & ADD_CACHE_PRETEND;
int intent_only = flags & ADD_CACHE_INTENT;
int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
(intent_only ? ADD_CACHE_NEW_ONLY : 0));
if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
return error("%s: can only add regular files, symbolic links or git-directories", path);
namelen = strlen(path);
if (S_ISDIR(st_mode)) {
while (namelen && path[namelen-1] == '/')
namelen--;
}
size = cache_entry_size(namelen);
ce = xcalloc(1, size);
memcpy(ce->name, path, namelen);
ce->ce_namelen = namelen;
if (!intent_only)
fill_stat_cache_info(ce, st);
else
ce->ce_flags |= CE_INTENT_TO_ADD;
if (trust_executable_bit && has_symlinks) {
ce->ce_mode = create_ce_mode(st_mode);
} else {
/* If there is an existing entry, pick the mode bits and type
* from it, otherwise assume unexecutable regular file.
*/
struct cache_entry *ent;
int pos = index_name_pos_also_unmerged(istate, path, namelen);
ent = (0 <= pos) ? istate->cache[pos] : NULL;
ce->ce_mode = ce_mode_from_stat(ent, st_mode);
}
/* When core.ignorecase=true, determine if a directory of the same name but differing
* case already exists within the Git repository. If it does, ensure the directory
* case of the file being added to the repository matches (is folded into) the existing
* entry's directory case.
*/
if (ignore_case) {
adjust_dirname_case(istate, ce->name);
}
alias = index_file_exists(istate, ce->name, ce_namelen(ce), ignore_case);
if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
/* Nothing changed, really */
if (!S_ISGITLINK(alias->ce_mode))
ce_mark_uptodate(alias);
alias->ce_flags |= CE_ADDED;
free(ce);
return 0;
}
if (!intent_only) {
if (index_path(ce->oid.hash, path, st, HASH_WRITE_OBJECT)) {
free(ce);
return error("unable to index file %s", path);
}
} else
set_object_name_for_intent_to_add_entry(ce);
if (ignore_case && alias && different_name(ce, alias))
ce = create_alias_ce(istate, ce, alias);
ce->ce_flags |= CE_ADDED;
/* It was suspected to be racily clean, but it turns out to be Ok */
was_same = (alias &&
!ce_stage(alias) &&
!oidcmp(&alias->oid, &ce->oid) &&
ce->ce_mode == alias->ce_mode);
if (pretend)
free(ce);
else if (add_index_entry(istate, ce, add_option)) {
free(ce);
return error("unable to add %s to index", path);
}
if (verbose && !was_same)
printf("add '%s'\n", path);
return 0;
}
int add_file_to_index(struct index_state *istate, const char *path, int flags)
{
struct stat st;
if (lstat(path, &st))
die_errno("unable to stat '%s'", path);
return add_to_index(istate, path, &st, flags);
}
struct cache_entry *make_cache_entry(unsigned int mode,
const unsigned char *sha1, const char *path, int stage,
unsigned int refresh_options)
{
int size, len;
struct cache_entry *ce, *ret;
if (!verify_path(path)) {
error("Invalid path '%s'", path);
return NULL;
}
len = strlen(path);
size = cache_entry_size(len);
ce = xcalloc(1, size);
hashcpy(ce->oid.hash, sha1);
memcpy(ce->name, path, len);
ce->ce_flags = create_ce_flags(stage);
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
ret = refresh_cache_entry(ce, refresh_options);
if (ret != ce)
free(ce);
return ret;
}
/*
* Chmod an index entry with either +x or -x.
*
* Returns -1 if the chmod for the particular cache entry failed (if it's
* not a regular file), -2 if an invalid flip argument is passed in, 0
* otherwise.
*/
int chmod_index_entry(struct index_state *istate, struct cache_entry *ce,
char flip)
{
if (!S_ISREG(ce->ce_mode))
return -1;
switch (flip) {
case '+':
ce->ce_mode |= 0111;
break;
case '-':
ce->ce_mode &= ~0111;
break;
default:
return -2;
}
cache_tree_invalidate_path(istate, ce->name);
ce->ce_flags |= CE_UPDATE_IN_BASE;
istate->cache_changed |= CE_ENTRY_CHANGED;
return 0;
}
int ce_same_name(const struct cache_entry *a, const struct cache_entry *b)
{
int len = ce_namelen(a);
return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}
/*
* We fundamentally don't like some paths: we don't want
* dot or dot-dot anywhere, and for obvious reasons don't
* want to recurse into ".git" either.
*
* Also, we don't want double slashes or slashes at the
* end that can make pathnames ambiguous.
*/
static int verify_dotfile(const char *rest)
{
/*
* The first character was '.', but that
* has already been discarded, we now test
* the rest.
*/
/* "." is not allowed */
if (*rest == '\0' || is_dir_sep(*rest))
return 0;
switch (*rest) {
/*
* ".git" followed by NUL or slash is bad. This
* shares the path end test with the ".." case.
*/
case 'g':
case 'G':
if (rest[1] != 'i' && rest[1] != 'I')
break;
if (rest[2] != 't' && rest[2] != 'T')
break;
rest += 2;
/* fallthrough */
case '.':
if (rest[1] == '\0' || is_dir_sep(rest[1]))
return 0;
}
return 1;
}
int verify_path(const char *path)
{
char c;
if (has_dos_drive_prefix(path))
return 0;
goto inside;
for (;;) {
if (!c)
return 1;
if (is_dir_sep(c)) {
inside:
if (protect_hfs && is_hfs_dotgit(path))
return 0;
if (protect_ntfs && is_ntfs_dotgit(path))
return 0;
c = *path++;
if ((c == '.' && !verify_dotfile(path)) ||
is_dir_sep(c) || c == '\0')
return 0;
}
c = *path++;
}
}
/*
* Do we have another file that has the beginning components being a
* proper superset of the name we're trying to add?
*/
static int has_file_name(struct index_state *istate,
const struct cache_entry *ce, int pos, int ok_to_replace)
{
int retval = 0;
int len = ce_namelen(ce);
int stage = ce_stage(ce);
const char *name = ce->name;
while (pos < istate->cache_nr) {
struct cache_entry *p = istate->cache[pos++];
if (len >= ce_namelen(p))
break;
if (memcmp(name, p->name, len))
break;
if (ce_stage(p) != stage)
continue;
if (p->name[len] != '/')
continue;
if (p->ce_flags & CE_REMOVE)
continue;
retval = -1;
if (!ok_to_replace)
break;
remove_index_entry_at(istate, --pos);
}
return retval;
}
/*
* Do we have another file with a pathname that is a proper
* subset of the name we're trying to add?
*/
static int has_dir_name(struct index_state *istate,
const struct cache_entry *ce, int pos, int ok_to_replace)
{
int retval = 0;
int stage = ce_stage(ce);
const char *name = ce->name;
const char *slash = name + ce_namelen(ce);
for (;;) {
int len;
for (;;) {
if (*--slash == '/')
break;
if (slash <= ce->name)
return retval;
}
len = slash - name;
pos = index_name_stage_pos(istate, name, len, stage);
if (pos >= 0) {
/*
* Found one, but not so fast. This could
* be a marker that says "I was here, but
* I am being removed". Such an entry is
* not a part of the resulting tree, and
* it is Ok to have a directory at the same
* path.
*/
if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
retval = -1;
if (!ok_to_replace)
break;
remove_index_entry_at(istate, pos);
continue;
}
}
else
pos = -pos-1;
/*
* Trivial optimization: if we find an entry that
* already matches the sub-directory, then we know
* we're ok, and we can exit.
*/
while (pos < istate->cache_nr) {
struct cache_entry *p = istate->cache[pos];
if ((ce_namelen(p) <= len) ||
(p->name[len] != '/') ||
memcmp(p->name, name, len))
break; /* not our subdirectory */
if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
/*
* p is at the same stage as our entry, and
* is a subdirectory of what we are looking
* at, so we cannot have conflicts at our
* level or anything shorter.
*/
return retval;
pos++;
}
}
return retval;
}
/* We may be in a situation where we already have path/file and path
* is being added, or we already have path and path/file is being
* added. Either one would result in a nonsense tree that has path
* twice when git-write-tree tries to write it out. Prevent it.
*
* If ok-to-replace is specified, we remove the conflicting entries
* from the cache so the caller should recompute the insert position.
* When this happens, we return non-zero.
*/
static int check_file_directory_conflict(struct index_state *istate,
const struct cache_entry *ce,
int pos, int ok_to_replace)
{
int retval;
/*
* When ce is an "I am going away" entry, we allow it to be added
*/
if (ce->ce_flags & CE_REMOVE)
return 0;
/*
* We check if the path is a sub-path of a subsequent pathname
* first, since removing those will not change the position
* in the array.
*/
retval = has_file_name(istate, ce, pos, ok_to_replace);
/*
* Then check if the path might have a clashing sub-directory
* before it.
*/
return retval + has_dir_name(istate, ce, pos, ok_to_replace);
}