![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
| author | Junio C Hamano <gitster@pobox.com> | |
| Tue, 12 Feb 2008 00:46:20 +0000 (16:46 -0800) | ||
| committer | Junio C Hamano <gitster@pobox.com> | |
| Tue, 12 Feb 2008 00:46:20 +0000 (16:46 -0800) |
* lt/in-core-index:
lazy index hashing
Create pathname-based hash-table lookup into index
read-cache.c: introduce is_racy_timestamp() helper
read-cache.c: fix a couple more CE_REMOVE conversion
Also use unpack_trees() in do_diff_cache()
Make run_diff_index() use unpack_trees(), not read_tree()
Avoid running lstat(2) on the same cache entry.
index: be careful when handling long names
Make on-disk index representation separate from in-core one
lazy index hashing
Create pathname-based hash-table lookup into index
read-cache.c: introduce is_racy_timestamp() helper
read-cache.c: fix a couple more CE_REMOVE conversion
Also use unpack_trees() in do_diff_cache()
Make run_diff_index() use unpack_trees(), not read_tree()
Avoid running lstat(2) on the same cache entry.
index: be careful when handling long names
Make on-disk index representation separate from in-core one
25 files changed:
| builtin-apply.c | patch | blob | history | |
| builtin-blame.c | patch | blob | history | |
| builtin-commit.c | patch | blob | history | |
| builtin-fsck.c | patch | blob | history | |
| builtin-grep.c | patch | blob | history | |
| builtin-ls-files.c | patch | blob | history | |
| builtin-read-tree.c | patch | blob | history | |
| builtin-rerere.c | patch | blob | history | |
| builtin-update-index.c | patch | blob | history | |
| cache-tree.c | patch | blob | history | |
| cache.h | patch | blob | history | |
| diff-lib.c | patch | blob | history | |
| diff.c | patch | blob | history | |
| dir.c | patch | blob | history | |
| entry.c | patch | blob | history | |
| merge-index.c | patch | blob | history | |
| merge-recursive.c | patch | blob | history | |
| reachable.c | patch | blob | history | |
| read-cache.c | patch | blob | history | |
| sha1_name.c | patch | blob | history | |
| t/t0000-basic.sh | patch | blob | history | |
| tree.c | patch | blob | history | |
| unpack-trees.c | patch | blob | history | |
| unpack-trees.h | patch | blob | history | |
| wt-status.c | patch | blob | history |
diff --git a/builtin-apply.c b/builtin-apply.c
index a11b1bbeee9568adbf8a3e32f77d14b132985061..46dad5b2a1ce6d70d540df8a40da94702dde68c7 100644 (file)
--- a/builtin-apply.c
+++ b/builtin-apply.c
if (!ce)
return 0;
- if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+ if (S_ISGITLINK(ce->ce_mode)) {
strbuf_grow(buf, 100);
strbuf_addf(buf, "Subproject commit %s\n", sha1_to_hex(ce->sha1));
} else {
static int verify_index_match(struct cache_entry *ce, struct stat *st)
{
- if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+ if (S_ISGITLINK(ce->ce_mode)) {
if (!S_ISDIR(st->st_mode))
return -1;
return 0;
return error("%s: does not match index",
old_name);
if (cached)
- st_mode = ntohl(ce->ce_mode);
+ st_mode = ce->ce_mode;
} else if (stat_ret < 0)
return error("%s: %s", old_name, strerror(errno));
if (!cached)
- st_mode = ntohl(ce_mode_from_stat(ce, st.st_mode));
+ st_mode = ce_mode_from_stat(ce, st.st_mode);
if (patch->is_new < 0)
patch->is_new = 0;
@@ -2388,7 +2388,7 @@ static void add_index_file(const char *path, unsigned mode, void *buf, unsigned
ce = xcalloc(1, ce_size);
memcpy(ce->name, path, namelen);
ce->ce_mode = create_ce_mode(mode);
- ce->ce_flags = htons(namelen);
+ ce->ce_flags = namelen;
if (S_ISGITLINK(mode)) {
const char *s = buf;
diff --git a/builtin-blame.c b/builtin-blame.c
index 9b4c02e87f7ef4a20d269ab9315b6977cf7fb3fb..c7e68874e7f02ac150343ab6d7a0aa95601f2ba3 100644 (file)
--- a/builtin-blame.c
+++ b/builtin-blame.c
@@ -2092,7 +2092,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
if (!mode) {
int pos = cache_name_pos(path, len);
if (0 <= pos)
- mode = ntohl(active_cache[pos]->ce_mode);
+ mode = active_cache[pos]->ce_mode;
else
/* Let's not bother reading from HEAD tree */
mode = S_IFREG | 0644;
diff --git a/builtin-commit.c b/builtin-commit.c
index a43f2019959a950639f013ff534610e228d8c149..717eb18da0e0cbe901dd8a660649388ccc0a24e1 100644 (file)
--- a/builtin-commit.c
+++ b/builtin-commit.c
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
- if (ce->ce_flags & htons(CE_UPDATE))
+ if (ce->ce_flags & CE_UPDATE)
continue;
if (!pathspec_match(pattern, m, ce->name, 0))
continue;
diff --git a/builtin-fsck.c b/builtin-fsck.c
index 8c564345f411baeb1fb91e68ebc2f3be42c2f8af..cc7524be80f51bca45ef8a205900cf50135bfc5d 100644 (file)
--- a/builtin-fsck.c
+++ b/builtin-fsck.c
struct blob *blob;
struct object *obj;
- mode = ntohl(active_cache[i]->ce_mode);
+ mode = active_cache[i]->ce_mode;
if (S_ISGITLINK(mode))
continue;
blob = lookup_blob(active_cache[i]->sha1);
diff --git a/builtin-grep.c b/builtin-grep.c
index 0d6cc7361f6e1a70e4d3d9e24913d60e8ceb9e58..9180b39e3f22e5d3805649c655c61aafc7861968 100644 (file)
--- a/builtin-grep.c
+++ b/builtin-grep.c
struct cache_entry *ce = active_cache[i];
char *name;
int kept;
- if (!S_ISREG(ntohl(ce->ce_mode)))
+ if (!S_ISREG(ce->ce_mode))
continue;
if (!pathspec_matches(paths, ce->name))
continue;
for (nr = 0; nr < active_nr; nr++) {
struct cache_entry *ce = active_cache[nr];
- if (!S_ISREG(ntohl(ce->ce_mode)))
+ if (!S_ISREG(ce->ce_mode))
continue;
if (!pathspec_matches(paths, ce->name))
continue;
diff --git a/builtin-ls-files.c b/builtin-ls-files.c
index 0f0ab2da167c57402efad9dc09e58964759c23cd..d56e33e251036274dbe48e300fcebd8289624cbe 100644 (file)
--- a/builtin-ls-files.c
+++ b/builtin-ls-files.c
return;
if (tag && *tag && show_valid_bit &&
- (ce->ce_flags & htons(CE_VALID))) {
+ (ce->ce_flags & CE_VALID)) {
static char alttag[4];
memcpy(alttag, tag, 3);
if (isalpha(tag[0]))
} else {
printf("%s%06o %s %d\t",
tag,
- ntohl(ce->ce_mode),
+ ce->ce_mode,
abbrev ? find_unique_abbrev(ce->sha1,abbrev)
: sha1_to_hex(ce->sha1),
ce_stage(ce));
continue;
if (show_unmerged && !ce_stage(ce))
continue;
- if (ce->ce_flags & htons(CE_UPDATE))
+ if (ce->ce_flags & CE_UPDATE)
continue;
show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce);
}
struct cache_entry *ce = active_cache[i];
if (!ce_stage(ce))
continue;
- ce->ce_flags |= htons(CE_STAGEMASK);
+ ce->ce_flags |= CE_STAGEMASK;
}
if (prefix) {
*/
if (last_stage0 &&
!strcmp(last_stage0->name, ce->name))
- ce->ce_flags |= htons(CE_UPDATE);
+ ce->ce_flags |= CE_UPDATE;
}
}
}
diff --git a/builtin-read-tree.c b/builtin-read-tree.c
index c0ea0342b755c6749391803d19f852182c0c512e..57854017535a36fc1fcd7bb997f198956391199d 100644 (file)
--- a/builtin-read-tree.c
+++ b/builtin-read-tree.c
continue;
cache_tree_invalidate_path(active_cache_tree, ce->name);
last = ce;
- ce->ce_mode = 0;
- ce->ce_flags &= ~htons(CE_STAGEMASK);
+ ce->ce_flags |= CE_REMOVE;
}
*dst++ = ce;
}
diff --git a/builtin-rerere.c b/builtin-rerere.c
index a9e3ebc13725cbe8658478797d6e1d8e097e5292..b0c17bde879d42c16fe5c7f0756763cd638f8bac 100644 (file)
--- a/builtin-rerere.c
+++ b/builtin-rerere.c
if (ce_stage(e2) == 2 &&
ce_stage(e3) == 3 &&
ce_same_name(e2, e3) &&
- S_ISREG(ntohl(e2->ce_mode)) &&
- S_ISREG(ntohl(e3->ce_mode))) {
+ S_ISREG(e2->ce_mode) &&
+ S_ISREG(e3->ce_mode)) {
path_list_insert((const char *)e2->name, conflict);
i++; /* skip over both #2 and #3 */
}
diff --git a/builtin-update-index.c b/builtin-update-index.c
index c3a14c74ed00db592db55a018db37657148a9900..a8795d3d5fea9f340dfe21a71190f120c63856cd 100644 (file)
--- a/builtin-update-index.c
+++ b/builtin-update-index.c
if (0 <= pos) {
switch (mark_valid_only) {
case MARK_VALID:
- active_cache[pos]->ce_flags |= htons(CE_VALID);
+ active_cache[pos]->ce_flags |= CE_VALID;
break;
case UNMARK_VALID:
- active_cache[pos]->ce_flags &= ~htons(CE_VALID);
+ active_cache[pos]->ce_flags &= ~CE_VALID;
break;
}
cache_tree_invalidate_path(active_cache_tree, path);
size = cache_entry_size(len);
ce = xcalloc(1, size);
memcpy(ce->name, path, len);
- ce->ce_flags = htons(len);
+ ce->ce_flags = len;
fill_stat_cache_info(ce, st);
ce->ce_mode = ce_mode_from_stat(old, st->st_mode);
/* Exact match: file or existing gitlink */
if (pos >= 0) {
struct cache_entry *ce = active_cache[pos];
- if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+ if (S_ISGITLINK(ce->ce_mode)) {
/* Do nothing to the index if there is no HEAD! */
if (resolve_gitlink_ref(path, "HEAD", sha1) < 0)
int pos = cache_name_pos(path, len);
struct cache_entry *ce = pos < 0 ? NULL : active_cache[pos];
- if (ce && S_ISGITLINK(ntohl(ce->ce_mode)))
+ if (ce && S_ISGITLINK(ce->ce_mode))
return error("%s is already a gitlink, not replacing", path);
return add_one_path(ce, path, len, st);
ce->ce_flags = create_ce_flags(len, stage);
ce->ce_mode = create_ce_mode(mode);
if (assume_unchanged)
- ce->ce_flags |= htons(CE_VALID);
+ ce->ce_flags |= CE_VALID;
option = allow_add ? ADD_CACHE_OK_TO_ADD : 0;
option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0;
if (add_cache_entry(ce, option))
if (pos < 0)
goto fail;
ce = active_cache[pos];
- mode = ntohl(ce->ce_mode);
+ mode = ce->ce_mode;
if (!S_ISREG(mode))
goto fail;
switch (flip) {
case '+':
- ce->ce_mode |= htonl(0111); break;
+ ce->ce_mode |= 0111; break;
case '-':
- ce->ce_mode &= htonl(~0111); break;
+ ce->ce_mode &= ~0111; break;
default:
goto fail;
}
diff --git a/cache-tree.c b/cache-tree.c
index 50b35264fd0405a299700ef8bf4a61f416f30e46..bfc95d2dc9600083b73b61c06d2b32c983db8511 100644 (file)
--- a/cache-tree.c
+++ b/cache-tree.c
}
else {
sha1 = ce->sha1;
- mode = ntohl(ce->ce_mode);
+ mode = ce->ce_mode;
entlen = pathlen - baselen;
}
if (mode != S_IFGITLINK && !missing_ok && !has_sha1_file(sha1))
return error("invalid object %s", sha1_to_hex(sha1));
- if (!ce->ce_mode)
+ if (ce->ce_flags & CE_REMOVE)
continue; /* entry being removed */
strbuf_grow(&buffer, entlen + 100);
index 6abcee437238ccc2b46e7d7d74f79db3a4b682a1..3867ba7ff5c3946e0449c78b26880a71107730a0 100644 (file)
--- a/cache.h
+++ b/cache.h
#include "git-compat-util.h"
#include "strbuf.h"
+#include "hash.h"
#include SHA1_HEADER
#include <zlib.h>
* We save the fields in big-endian order to allow using the
* index file over NFS transparently.
*/
+struct ondisk_cache_entry {
+ struct cache_time ctime;
+ struct cache_time mtime;
+ unsigned int dev;
+ unsigned int ino;
+ unsigned int mode;
+ unsigned int uid;
+ unsigned int gid;
+ unsigned int size;
+ unsigned char sha1[20];
+ unsigned short flags;
+ char name[FLEX_ARRAY]; /* more */
+};
+
struct cache_entry {
- struct cache_time ce_ctime;
- struct cache_time ce_mtime;
+ struct cache_entry *next;
+ unsigned int ce_ctime;
+ unsigned int ce_mtime;
unsigned int ce_dev;
unsigned int ce_ino;
unsigned int ce_mode;
unsigned int ce_uid;
unsigned int ce_gid;
unsigned int ce_size;
+ unsigned int ce_flags;
unsigned char sha1[20];
- unsigned short ce_flags;
char name[FLEX_ARRAY]; /* more */
};
#define CE_NAMEMASK (0x0fff)
#define CE_STAGEMASK (0x3000)
-#define CE_UPDATE (0x4000)
#define CE_VALID (0x8000)
#define CE_STAGESHIFT 12
-#define create_ce_flags(len, stage) htons((len) | ((stage) << CE_STAGESHIFT))
-#define ce_namelen(ce) (CE_NAMEMASK & ntohs((ce)->ce_flags))
+/* In-memory only */
+#define CE_UPDATE (0x10000)
+#define CE_REMOVE (0x20000)
+#define CE_UPTODATE (0x40000)
+#define CE_UNHASHED (0x80000)
+
+static inline unsigned create_ce_flags(size_t len, unsigned stage)
+{
+ if (len >= CE_NAMEMASK)
+ len = CE_NAMEMASK;
+ return (len | (stage << CE_STAGESHIFT));
+}
+
+static inline size_t ce_namelen(const struct cache_entry *ce)
+{
+ size_t len = ce->ce_flags & CE_NAMEMASK;
+ if (len < CE_NAMEMASK)
+ return len;
+ return strlen(ce->name + CE_NAMEMASK) + CE_NAMEMASK;
+}
+
#define ce_size(ce) cache_entry_size(ce_namelen(ce))
-#define ce_stage(ce) ((CE_STAGEMASK & ntohs((ce)->ce_flags)) >> CE_STAGESHIFT)
+#define ondisk_ce_size(ce) ondisk_cache_entry_size(ce_namelen(ce))
+#define ce_stage(ce) ((CE_STAGEMASK & (ce)->ce_flags) >> CE_STAGESHIFT)
+#define ce_uptodate(ce) ((ce)->ce_flags & CE_UPTODATE)
+#define ce_mark_uptodate(ce) ((ce)->ce_flags |= CE_UPTODATE)
#define ce_permissions(mode) (((mode) & 0100) ? 0755 : 0644)
static inline unsigned int create_ce_mode(unsigned int mode)
{
if (S_ISLNK(mode))
- return htonl(S_IFLNK);
+ return S_IFLNK;
if (S_ISDIR(mode) || S_ISGITLINK(mode))
- return htonl(S_IFGITLINK);
- return htonl(S_IFREG | ce_permissions(mode));
+ return S_IFGITLINK;
+ return S_IFREG | ce_permissions(mode);
}
static inline unsigned int ce_mode_from_stat(struct cache_entry *ce, unsigned int mode)
{
extern int trust_executable_bit, has_symlinks;
if (!has_symlinks && S_ISREG(mode) &&
- ce && S_ISLNK(ntohl(ce->ce_mode)))
+ ce && S_ISLNK(ce->ce_mode))
return ce->ce_mode;
if (!trust_executable_bit && S_ISREG(mode)) {
- if (ce && S_ISREG(ntohl(ce->ce_mode)))
+ if (ce && S_ISREG(ce->ce_mode))
return ce->ce_mode;
return create_ce_mode(0666);
}
@@ -146,14 +183,16 @@ static inline unsigned int ce_mode_from_stat(struct cache_entry *ce, unsigned in
S_ISLNK(mode) ? S_IFLNK : S_ISDIR(mode) ? S_IFDIR : S_IFGITLINK)
#define cache_entry_size(len) ((offsetof(struct cache_entry,name) + (len) + 8) & ~7)
+#define ondisk_cache_entry_size(len) ((offsetof(struct ondisk_cache_entry,name) + (len) + 8) & ~7)
struct index_state {
struct cache_entry **cache;
unsigned int cache_nr, cache_alloc, cache_changed;
struct cache_tree *cache_tree;
time_t timestamp;
- void *mmap;
- size_t mmap_size;
+ void *alloc;
+ unsigned name_hash_initialized : 1;
+ struct hash_table name_hash;
};
extern struct index_state the_index;
#define refresh_cache(flags) refresh_index(&the_index, (flags), NULL, NULL)
#define ce_match_stat(ce, st, options) ie_match_stat(&the_index, (ce), (st), (options))
#define ce_modified(ce, st, options) ie_modified(&the_index, (ce), (st), (options))
+#define cache_name_exists(name, namelen) index_name_exists(&the_index, (name), (namelen))
#endif
enum object_type {
extern int write_index(struct index_state *, int newfd);
extern int discard_index(struct index_state *);
extern int verify_path(const char *path);
+extern int index_name_exists(struct index_state *istate, const char *name, int namelen);
extern int index_name_pos(struct index_state *, const char *name, int namelen);
#define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */
#define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */
diff --git a/diff-lib.c b/diff-lib.c
index d85d8f34ba055ad7e02bf5d61ae4a675ce0be1d3..03eaa7cef35dfaec0a8f61b2b96892e5604ed731 100644 (file)
--- a/diff-lib.c
+++ b/diff-lib.c
#include "revision.h"
#include "cache-tree.h"
#include "path-list.h"
+#include "unpack-trees.h"
/*
* diff-files
if (!path || !strcmp(path, "/dev/null"))
*mode = 0;
else if (!strcmp(path, "-"))
- *mode = ntohl(create_ce_mode(0666));
+ *mode = create_ce_mode(0666);
else if (stat(path, &st))
return error("Could not access '%s'", path);
else
continue;
}
else
- dpath->mode = ntohl(ce_mode_from_stat(ce, st.st_mode));
+ dpath->mode = ce_mode_from_stat(ce, st.st_mode);
while (i < entries) {
struct cache_entry *nce = active_cache[i];
*/
stage = ce_stage(nce);
if (2 <= stage) {
- int mode = ntohl(nce->ce_mode);
+ int mode = nce->ce_mode;
num_compare_stages++;
hashcpy(dpath->parent[stage-2].sha1, nce->sha1);
- dpath->parent[stage-2].mode = ntohl(ce_mode_from_stat(nce, mode));
+ dpath->parent[stage-2].mode = ce_mode_from_stat(nce, mode);
dpath->parent[stage-2].status =
DIFF_STATUS_MODIFIED;
}
continue;
}
+ if (ce_uptodate(ce))
+ continue;
if (lstat(ce->name, &st) < 0) {
if (errno != ENOENT && errno != ENOTDIR) {
perror(ce->name);
}
if (silent_on_removed)
continue;
- diff_addremove(&revs->diffopt, '-', ntohl(ce->ce_mode),
+ diff_addremove(&revs->diffopt, '-', ce->ce_mode,
ce->sha1, ce->name, NULL);
continue;
}
changed = ce_match_stat(ce, &st, ce_option);
if (!changed && !DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
continue;
- oldmode = ntohl(ce->ce_mode);
- newmode = ntohl(ce_mode_from_stat(ce, st.st_mode));
+ oldmode = ce->ce_mode;
+ newmode = ce_mode_from_stat(ce, st.st_mode);
diff_change(&revs->diffopt, oldmode, newmode,
ce->sha1, (changed ? null_sha1 : ce->sha1),
ce->name, NULL);
struct cache_entry *ce,
unsigned char *sha1, unsigned int mode)
{
- diff_addremove(&revs->diffopt, prefix[0], ntohl(mode),
+ diff_addremove(&revs->diffopt, prefix[0], mode,
sha1, ce->name, NULL);
}
p->len = pathlen;
memcpy(p->path, new->name, pathlen);
p->path[pathlen] = 0;
- p->mode = ntohl(mode);
+ p->mode = mode;
hashclr(p->sha1);
memset(p->parent, 0, 2 * sizeof(struct combine_diff_parent));
p->parent[0].status = DIFF_STATUS_MODIFIED;
- p->parent[0].mode = ntohl(new->ce_mode);
+ p->parent[0].mode = new->ce_mode;
hashcpy(p->parent[0].sha1, new->sha1);
p->parent[1].status = DIFF_STATUS_MODIFIED;
- p->parent[1].mode = ntohl(old->ce_mode);
+ p->parent[1].mode = old->ce_mode;
hashcpy(p->parent[1].sha1, old->sha1);
show_combined_diff(p, 2, revs->dense_combined_merges, revs);
free(p);
!DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER))
return 0;
- mode = ntohl(mode);
- oldmode = ntohl(oldmode);
-
diff_change(&revs->diffopt, oldmode, mode,
old->sha1, sha1, old->name, NULL);
return 0;
}
-static int diff_cache(struct rev_info *revs,
- struct cache_entry **ac, int entries,
- const char **pathspec,
- int cached, int match_missing)
+/*
+ * This turns all merge entries into "stage 3". That guarantees that
+ * when we read in the new tree (into "stage 1"), we won't lose sight
+ * of the fact that we had unmerged entries.
+ */
+static void mark_merge_entries(void)
{
- while (entries) {
- struct cache_entry *ce = *ac;
- int same = (entries > 1) && ce_same_name(ce, ac[1]);
+ int i;
+ for (i = 0; i < active_nr; i++) {
+ struct cache_entry *ce = active_cache[i];
+ if (!ce_stage(ce))
+ continue;
+ ce->ce_flags |= CE_STAGEMASK;
+ }
+}
- if (DIFF_OPT_TST(&revs->diffopt, QUIET) &&
- DIFF_OPT_TST(&revs->diffopt, HAS_CHANGES))
- break;
+/*
+ * This gets a mix of an existing index and a tree, one pathname entry
+ * at a time. The index entry may be a single stage-0 one, but it could
+ * also be multiple unmerged entries (in which case idx_pos/idx_nr will
+ * give you the position and number of entries in the index).
+ */
+static void do_oneway_diff(struct unpack_trees_options *o,
+ struct cache_entry *idx,
+ struct cache_entry *tree,
+ int idx_pos, int idx_nr)
+{
+ struct rev_info *revs = o->unpack_data;
+ int match_missing, cached;
- if (!ce_path_match(ce, pathspec))
- goto skip_entry;
+ /*
+ * Backward compatibility wart - "diff-index -m" does
+ * not mean "do not ignore merges", but "match_missing".
+ *
+ * But with the revision flag parsing, that's found in
+ * "!revs->ignore_merges".
+ */
+ cached = o->index_only;
+ match_missing = !revs->ignore_merges;
+
+ if (cached && idx && ce_stage(idx)) {
+ if (tree)
+ diff_unmerge(&revs->diffopt, idx->name, idx->ce_mode, idx->sha1);
+ return;
+ }
+
+ /*
+ * Something added to the tree?
+ */
+ if (!tree) {
+ show_new_file(revs, idx, cached, match_missing);
+ return;
+ }
- switch (ce_stage(ce)) {
- case 0:
- /* No stage 1 entry? That means it's a new file */
- if (!same) {
- show_new_file(revs, ce, cached, match_missing);
+ /*
+ * Something removed from the tree?
+ */
+ if (!idx) {
+ diff_index_show_file(revs, "-", tree, tree->sha1, tree->ce_mode);
+ return;
+ }
+
+ /* Show difference between old and new */
+ show_modified(revs, tree, idx, 1, cached, match_missing);
+}
+
+/*
+ * Count how many index entries go with the first one
+ */
+static inline int count_skip(const struct cache_entry *src, int pos)
+{
+ int skip = 1;
+
+ /* We can only have multiple entries if the first one is not stage-0 */
+ if (ce_stage(src)) {
+ struct cache_entry **p = active_cache + pos;
+ int namelen = ce_namelen(src);
+
+ for (;;) {
+ const struct cache_entry *ce;
+ pos++;
+ if (pos >= active_nr)
break;
- }
- /* Show difference between old and new */
- show_modified(revs, ac[1], ce, 1,
- cached, match_missing);
- break;
- case 1:
- /* No stage 3 (merge) entry?
- * That means it's been deleted.
- */
- if (!same) {
- diff_index_show_file(revs, "-", ce,
- ce->sha1, ce->ce_mode);
+ ce = *++p;
+ if (ce_namelen(ce) != namelen)
break;
- }
- /* We come here with ce pointing at stage 1
- * (original tree) and ac[1] pointing at stage
- * 3 (unmerged). show-modified with
- * report-missing set to false does not say the
- * file is deleted but reports true if work
- * tree does not have it, in which case we
- * fall through to report the unmerged state.
- * Otherwise, we show the differences between
- * the original tree and the work tree.
- */
- if (!cached &&
- !show_modified(revs, ce, ac[1], 0,
- cached, match_missing))
+ if (memcmp(ce->name, src->name, namelen))
break;
- diff_unmerge(&revs->diffopt, ce->name,
- ntohl(ce->ce_mode), ce->sha1);
- break;
- case 3:
- diff_unmerge(&revs->diffopt, ce->name,
- 0, null_sha1);
- break;
-
- default:
- die("impossible cache entry stage");
+ skip++;
}
-
-skip_entry:
- /*
- * Ignore all the different stages for this file,
- * we've handled the relevant cases now.
- */
- do {
- ac++;
- entries--;
- } while (entries && ce_same_name(ce, ac[0]));
}
- return 0;
+ return skip;
}
/*
- * This turns all merge entries into "stage 3". That guarantees that
- * when we read in the new tree (into "stage 1"), we won't lose sight
- * of the fact that we had unmerged entries.
+ * The unpack_trees() interface is designed for merging, so
+ * the different source entries are designed primarily for
+ * the source trees, with the old index being really mainly
+ * used for being replaced by the result.
+ *
+ * For diffing, the index is more important, and we only have a
+ * single tree.
+ *
+ * We're supposed to return how many index entries we want to skip.
+ *
+ * This wrapper makes it all more readable, and takes care of all
+ * the fairly complex unpack_trees() semantic requirements, including
+ * the skipping, the path matching, the type conflict cases etc.
*/
-static void mark_merge_entries(void)
+static int oneway_diff(struct cache_entry **src,
+ struct unpack_trees_options *o,
+ int index_pos)
{
- int i;
- for (i = 0; i < active_nr; i++) {
- struct cache_entry *ce = active_cache[i];
- if (!ce_stage(ce))
- continue;
- ce->ce_flags |= htons(CE_STAGEMASK);
- }
+ int skip = 0;
+ struct cache_entry *idx = src[0];
+ struct cache_entry *tree = src[1];
+ struct rev_info *revs = o->unpack_data;
+
+ if (index_pos >= 0)
+ skip = count_skip(idx, index_pos);
+
+ /*
+ * Unpack-trees generates a DF/conflict entry if
+ * there was a directory in the index and a tree
+ * in the tree. From a diff standpoint, that's a
+ * delete of the tree and a create of the file.
+ */
+ if (tree == o->df_conflict_entry)
+ tree = NULL;
+
+ if (ce_path_match(idx ? idx : tree, revs->prune_data))
+ do_oneway_diff(o, idx, tree, index_pos, skip);
+
+ return skip;
}
int run_diff_index(struct rev_info *revs, int cached)
{
- int ret;
struct object *ent;
struct tree *tree;
const char *tree_name;
- int match_missing = 0;
-
- /*
- * Backward compatibility wart - "diff-index -m" does
- * not mean "do not ignore merges", but totally different.
- */
- if (!revs->ignore_merges)
- match_missing = 1;
+ struct unpack_trees_options opts;
+ struct tree_desc t;
mark_merge_entries();
tree = parse_tree_indirect(ent->sha1);
if (!tree)
return error("bad tree object %s", tree_name);
- if (read_tree(tree, 1, revs->prune_data))
- return error("unable to read tree object %s", tree_name);
- ret = diff_cache(revs, active_cache, active_nr, revs->prune_data,
- cached, match_missing);
+
+ memset(&opts, 0, sizeof(opts));
+ opts.head_idx = 1;
+ opts.index_only = cached;
+ opts.merge = 1;
+ opts.fn = oneway_diff;
+ opts.unpack_data = revs;
+
+ init_tree_desc(&t, tree->buffer, tree->size);
+ unpack_trees(1, &t, &opts);
+
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
- return ret;
+ return 0;
}
int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt)
int i;
struct cache_entry **dst;
struct cache_entry *last = NULL;
+ struct unpack_trees_options opts;
+ struct tree_desc t;
/*
* This is used by git-blame to run diff-cache internally;
cache_tree_invalidate_path(active_cache_tree,
ce->name);
last = ce;
- ce->ce_mode = 0;
- ce->ce_flags &= ~htons(CE_STAGEMASK);
+ ce->ce_flags |= CE_REMOVE;
}
*dst++ = ce;
}
tree = parse_tree_indirect(tree_sha1);
if (!tree)
die("bad tree object %s", sha1_to_hex(tree_sha1));
- if (read_tree(tree, 1, opt->paths))
- return error("unable to read tree %s", sha1_to_hex(tree_sha1));
- return diff_cache(&revs, active_cache, active_nr, revs.prune_data,
- 1, 0);
+
+ memset(&opts, 0, sizeof(opts));
+ opts.head_idx = 1;
+ opts.index_only = 1;
+ opts.merge = 1;
+ opts.fn = oneway_diff;
+ opts.unpack_data = &revs;
+
+ init_tree_desc(&t, tree->buffer, tree->size);
+ unpack_trees(1, &t, &opts);
+ return 0;
}
index 4d2e23ae1b7dd4bd43d5c03871ce8ab519272115..cd8bc4dcc32757dfed9374fa8769599a6a7857ad 100644 (file)
--- a/diff.c
+++ b/diff.c
@@ -1520,17 +1520,22 @@ static int reuse_worktree_file(const char *name, const unsigned char *sha1, int
if (pos < 0)
return 0;
ce = active_cache[pos];
- if ((lstat(name, &st) < 0) ||
- !S_ISREG(st.st_mode) || /* careful! */
- ce_match_stat(ce, &st, 0) ||
- hashcmp(sha1, ce->sha1))
+
+ /*
+ * This is not the sha1 we are looking for, or
+ * unreusable because it is not a regular file.
+ */
+ if (hashcmp(sha1, ce->sha1) || !S_ISREG(ce->ce_mode))
return 0;
- /* we return 1 only when we can stat, it is a regular file,
- * stat information matches, and sha1 recorded in the cache
- * matches. I.e. we know the file in the work tree really is
- * the same as the <name, sha1> pair.
+
+ /*
+ * If ce matches the file in the work tree, we can reuse it.
*/
- return 1;
+ if (ce_uptodate(ce) ||
+ (!lstat(name, &st) && !ce_match_stat(ce, &st, 0)))
+ return 1;
+
+ return 0;
}
static int populate_from_stdin(struct diff_filespec *s)
index 3e345c2fc508eb82e66f4ffe2c825670f0bddd99..6543105b9622212430a9e5ed131a81074e019d9a 100644 (file)
--- a/dir.c
+++ b/dir.c
struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
{
- if (cache_name_pos(pathname, len) >= 0)
+ if (cache_name_exists(pathname, len))
return NULL;
ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
@@ -391,7 +391,7 @@ static enum exist_status directory_exists_in_index(const char *dirname, int len)
break;
if (endchar == '/')
return index_directory;
- if (!endchar && S_ISGITLINK(ntohl(ce->ce_mode)))
+ if (!endchar && S_ISGITLINK(ce->ce_mode))
return index_gitdir;
}
return index_nonexistent;
index 257ab46e943f1f8b7445f01c10d949224c17112f..44f4b897d4ff7afff7dbab92ce8754645ad8da6a 100644 (file)
--- a/entry.c
+++ b/entry.c
@@ -103,7 +103,7 @@ static int write_entry(struct cache_entry *ce, char *path, const struct checkout
int fd;
long wrote;
- switch (ntohl(ce->ce_mode) & S_IFMT) {
+ switch (ce->ce_mode & S_IFMT) {
char *new;
struct strbuf buf;
unsigned long size;
@@ -129,7 +129,7 @@ static int write_entry(struct cache_entry *ce, char *path, const struct checkout
strcpy(path, ".merge_file_XXXXXX");
fd = mkstemp(path);
} else
- fd = create_file(path, ntohl(ce->ce_mode));
+ fd = create_file(path, ce->ce_mode);
if (fd < 0) {
free(new);
return error("git-checkout-index: unable to create file %s (%s)",
@@ -221,7 +221,7 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *t
unlink(path);
if (S_ISDIR(st.st_mode)) {
/* If it is a gitlink, leave it alone! */
- if (S_ISGITLINK(ntohl(ce->ce_mode)))
+ if (S_ISGITLINK(ce->ce_mode))
return 0;
if (!state->force)
return error("%s is a directory", path);
diff --git a/merge-index.c b/merge-index.c
index fa719cb0b1bd227423587c9e41eed77c755465a4..bbb700b54eab2a14f60e090231a196874ff3a9e0 100644 (file)
--- a/merge-index.c
+++ b/merge-index.c
break;
found++;
strcpy(hexbuf[stage], sha1_to_hex(ce->sha1));
- sprintf(ownbuf[stage], "%o", ntohl(ce->ce_mode));
+ sprintf(ownbuf[stage], "%o", ce->ce_mode);
arguments[stage] = hexbuf[stage];
arguments[stage + 4] = ownbuf[stage];
} while (++pos < active_nr);
diff --git a/merge-recursive.c b/merge-recursive.c
index 34e3167cafc3d09e1a2b32bc9a5c64b4de1e442d..dd52342539cd05e59bb13e956d51251417f21e3c 100644 (file)
--- a/merge-recursive.c
+++ b/merge-recursive.c
item->util = xcalloc(1, sizeof(struct stage_data));
}
e = item->util;
- e->stages[ce_stage(ce)].mode = ntohl(ce->ce_mode);
+ e->stages[ce_stage(ce)].mode = ce->ce_mode;
hashcpy(e->stages[ce_stage(ce)].sha, ce->sha1);
}
diff --git a/reachable.c b/reachable.c
index 6383401e2dd6bef3251a105ac136312dfdcdeb3c..00f289f2f470c0f4b95e0fcac043aa2e054d1ce6 100644 (file)
--- a/reachable.c
+++ b/reachable.c
* lookup_blob() on them, to avoid populating the hash table
* with invalid information
*/
- if (S_ISGITLINK(ntohl(active_cache[i]->ce_mode)))
+ if (S_ISGITLINK(active_cache[i]->ce_mode))
continue;
lookup_blob(active_cache[i]->sha1);
diff --git a/read-cache.c b/read-cache.c
index 7db55883d65fd28c2eaa291b5688273532988d88..e45f4b3d61c2982ca20c910a7fc11c5bd89204be 100644 (file)
--- a/read-cache.c
+++ b/read-cache.c
struct index_state the_index;
+static unsigned int hash_name(const char *name, int namelen)
+{
+ unsigned int hash = 0x123;
+
+ do {
+ unsigned char c = *name++;
+ hash = hash*101 + c;
+ } while (--namelen);
+ return hash;
+}
+
+static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
+{
+ void **pos;
+ unsigned int hash = hash_name(ce->name, ce_namelen(ce));
+
+ pos = insert_hash(hash, ce, &istate->name_hash);
+ if (pos) {
+ ce->next = *pos;
+ *pos = ce;
+ }
+}
+
+static void lazy_init_name_hash(struct index_state *istate)
+{
+ int nr;
+
+ if (istate->name_hash_initialized)
+ return;
+ for (nr = 0; nr < istate->cache_nr; nr++)
+ hash_index_entry(istate, istate->cache[nr]);
+ istate->name_hash_initialized = 1;
+}
+
+static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
+{
+ istate->cache[nr] = ce;
+ if (istate->name_hash_initialized)
+ hash_index_entry(istate, ce);
+}
+
+/*
+ * We don't actually *remove* it, we can just mark it invalid so that
+ * we won't find it in lookups.
+ *
+ * Not only would we have to search the lists (simple enough), but
+ * we'd also have to rehash other hash buckets in case this makes the
+ * hash bucket empty (common). So it's much better to just mark
+ * it.
+ */
+static void remove_hash_entry(struct index_state *istate, struct cache_entry *ce)
+{
+ ce->ce_flags |= CE_UNHASHED;
+}
+
+static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
+{
+ struct cache_entry *old = istate->cache[nr];
+
+ if (ce != old) {
+ remove_hash_entry(istate, old);
+ set_index_entry(istate, nr, ce);
+ }
+ istate->cache_changed = 1;
+}
+
+int index_name_exists(struct index_state *istate, const char *name, int namelen)
+{
+ unsigned int hash = hash_name(name, namelen);
+ struct cache_entry *ce;
+
+ lazy_init_name_hash(istate);
+ ce = lookup_hash(hash, &istate->name_hash);
+
+ while (ce) {
+ if (!(ce->ce_flags & CE_UNHASHED)) {
+ if (!cache_name_compare(name, namelen, ce->name, ce->ce_flags))
+ return 1;
+ }
+ ce = ce->next;
+ }
+ return 0;
+}
+
/*
* This only updates the "non-critical" parts of the directory
* cache, ie the parts that aren't tracked by GIT, and only used
*/
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
- ce->ce_ctime.sec = htonl(st->st_ctime);
- ce->ce_mtime.sec = htonl(st->st_mtime);
-#ifdef USE_NSEC
- ce->ce_ctime.nsec = htonl(st->st_ctim.tv_nsec);
- ce->ce_mtime.nsec = htonl(st->st_mtim.tv_nsec);
-#endif
- ce->ce_dev = htonl(st->st_dev);
- ce->ce_ino = htonl(st->st_ino);
- ce->ce_uid = htonl(st->st_uid);
- ce->ce_gid = htonl(st->st_gid);
- ce->ce_size = htonl(st->st_size);
+ ce->ce_ctime = st->st_ctime;
+ ce->ce_mtime = st->st_mtime;
+ ce->ce_dev = st->st_dev;
+ ce->ce_ino = st->st_ino;
+ ce->ce_uid = st->st_uid;
+ ce->ce_gid = st->st_gid;
+ ce->ce_size = st->st_size;
if (assume_unchanged)
- ce->ce_flags |= htons(CE_VALID);
+ ce->ce_flags |= CE_VALID;
+
+ if (S_ISREG(st->st_mode))
+ ce_mark_uptodate(ce);
}
static int ce_compare_data(struct cache_entry *ce, struct stat *st)
return DATA_CHANGED;
break;
case S_IFDIR:
- if (S_ISGITLINK(ntohl(ce->ce_mode)))
+ if (S_ISGITLINK(ce->ce_mode))
return 0;
default:
return TYPE_CHANGED;
{
unsigned int changed = 0;
- switch (ntohl(ce->ce_mode) & S_IFMT) {
+ 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 & (ntohl(ce->ce_mode) ^ st->st_mode)))
+ (0100 & (ce->ce_mode ^ st->st_mode)))
changed |= MODE_CHANGED;
break;
case S_IFLNK:
else if (ce_compare_gitlink(ce))
changed |= DATA_CHANGED;
return changed;
- case 0: /* Special case: unmerged file in index */
- return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;
default:
- die("internal error: ce_mode is %o", ntohl(ce->ce_mode));
+ die("internal error: ce_mode is %o", ce->ce_mode);
}
- if (ce->ce_mtime.sec != htonl(st->st_mtime))
+ if (ce->ce_mtime != (unsigned int) st->st_mtime)
changed |= MTIME_CHANGED;
- if (ce->ce_ctime.sec != htonl(st->st_ctime))
+ if (ce->ce_ctime != (unsigned int) st->st_ctime)
changed |= CTIME_CHANGED;
-#ifdef USE_NSEC
- /*
- * nsec seems unreliable - not all filesystems support it, so
- * as long as it is in the inode cache you get right nsec
- * but after it gets flushed, you get zero nsec.
- */
- if (ce->ce_mtime.nsec != htonl(st->st_mtim.tv_nsec))
- changed |= MTIME_CHANGED;
- if (ce->ce_ctime.nsec != htonl(st->st_ctim.tv_nsec))
- changed |= CTIME_CHANGED;
-#endif
-
- if (ce->ce_uid != htonl(st->st_uid) ||
- ce->ce_gid != htonl(st->st_gid))
+ if (ce->ce_uid != (unsigned int) st->st_uid ||
+ ce->ce_gid != (unsigned int) st->st_gid)
changed |= OWNER_CHANGED;
- if (ce->ce_ino != htonl(st->st_ino))
+ if (ce->ce_ino != (unsigned int) st->st_ino)
changed |= INODE_CHANGED;
#ifdef USE_STDEV
* clients will have different views of what "device"
* the filesystem is on
*/
- if (ce->ce_dev != htonl(st->st_dev))
+ if (ce->ce_dev != (unsigned int) st->st_dev)
changed |= INODE_CHANGED;
#endif
- if (ce->ce_size != htonl(st->st_size))
+ if (ce->ce_size != (unsigned int) st->st_size)
changed |= DATA_CHANGED;
return changed;
}
+static int is_racy_timestamp(struct index_state *istate, struct cache_entry *ce)
+{
+ return (istate->timestamp &&
+ ((unsigned int)istate->timestamp) <= ce->ce_mtime);
+}
+
int ie_match_stat(struct index_state *istate,
struct cache_entry *ce, struct stat *st,
unsigned int options)
* If it's marked as always valid in the index, it's
* valid whatever the checked-out copy says.
*/
- if (!ignore_valid && (ce->ce_flags & htons(CE_VALID)))
+ if (!ignore_valid && (ce->ce_flags & CE_VALID))
return 0;
changed = ce_match_stat_basic(ce, st);
* whose mtime are the same as the index file timestamp more
* carefully than others.
*/
- if (!changed &&
- istate->timestamp &&
- istate->timestamp <= ntohl(ce->ce_mtime.sec)) {
+ if (!changed && is_racy_timestamp(istate, ce)) {
if (assume_racy_is_modified)
changed |= DATA_CHANGED;
else
* the length field is zero. For other cases the ce_size
* should match the SHA1 recorded in the index entry.
*/
- if ((changed & DATA_CHANGED) && ce->ce_size != htonl(0))
+ if ((changed & DATA_CHANGED) && ce->ce_size != 0)
return changed;
changed_fs = ce_modified_check_fs(ce, st);
while (last > first) {
int next = (last + first) >> 1;
struct cache_entry *ce = istate->cache[next];
- int cmp = cache_name_compare(name, namelen, ce->name, ntohs(ce->ce_flags));
+ int cmp = cache_name_compare(name, namelen, ce->name, ce->ce_flags);
if (!cmp)
return next;
if (cmp < 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];
+
+ remove_hash_entry(istate, ce);
istate->cache_changed = 1;
istate->cache_nr--;
if (pos >= istate->cache_nr)
@@ -405,7 +484,7 @@ int add_file_to_index(struct index_state *istate, const char *path, int verbose)
size = cache_entry_size(namelen);
ce = xcalloc(1, size);
memcpy(ce->name, path, namelen);
- ce->ce_flags = htons(namelen);
+ ce->ce_flags = namelen;
fill_stat_cache_info(ce, &st);
if (trust_executable_bit && has_symlinks)
@@ -427,6 +506,7 @@ int add_file_to_index(struct index_state *istate, const char *path, int verbose)
!ie_match_stat(istate, istate->cache[pos], &st, ce_option)) {
/* Nothing changed, really */
free(ce);
+ ce_mark_uptodate(istate->cache[pos]);
return 0;
}
continue;
if (p->name[len] != '/')
continue;
- if (!ce_stage(p) && !p->ce_mode)
+ if (p->ce_flags & CE_REMOVE)
continue;
retval = -1;
if (!ok_to_replace)
}
len = slash - name;
- pos = index_name_pos(istate, name, ntohs(create_ce_flags(len, stage)));
+ pos = index_name_pos(istate, name, create_ce_flags(len, stage));
if (pos >= 0) {
/*
* Found one, but not so fast. This could
* it is Ok to have a directory at the same
* path.
*/
- if (stage || istate->cache[pos]->ce_mode) {
+ if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
retval = -1;
if (!ok_to_replace)
break;
(p->name[len] != '/') ||
memcmp(p->name, name, len))
break; /* not our subdirectory */
- if (ce_stage(p) == stage && (stage || p->ce_mode))
- /* p is at the same stage as our entry, and
+ 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.
/*
* When ce is an "I am going away" entry, we allow it to be added
*/
- if (!ce_stage(ce) && !ce->ce_mode)
+ if (ce->ce_flags & CE_REMOVE)
return 0;
/*
@@ -704,12 +785,11 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
cache_tree_invalidate_path(istate->cache_tree, ce->name);
- pos = index_name_pos(istate, ce->name, ntohs(ce->ce_flags));
+ pos = index_name_pos(istate, ce->name, ce->ce_flags);
/* existing match? Just replace it. */
if (pos >= 0) {
- istate->cache_changed = 1;
- istate->cache[pos] = ce;
+ replace_index_entry(istate, pos, ce);
return 0;
}
pos = -pos-1;
@@ -736,7 +816,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
if (!ok_to_replace)
return error("'%s' appears as both a file and as a directory",
ce->name);
- pos = index_name_pos(istate, ce->name, ntohs(ce->ce_flags));
+ pos = index_name_pos(istate, ce->name, ce->ce_flags);
pos = -pos-1;
}
return pos + 1;
@@ -769,7 +849,7 @@ int add_index_entry(struct index_state *istate, struct cache_entry *ce, int opti
memmove(istate->cache + pos + 1,
istate->cache + pos,
(istate->cache_nr - pos - 1) * sizeof(ce));
- istate->cache[pos] = ce;
+ set_index_entry(istate, pos, ce);
istate->cache_changed = 1;
return 0;
}
int changed, size;
int ignore_valid = options & CE_MATCH_IGNORE_VALID;
+ if (ce_uptodate(ce))
+ return ce;
+
if (lstat(ce->name, &st) < 0) {
if (err)
*err = errno;
* valid again, under "assume unchanged" mode.
*/
if (ignore_valid && assume_unchanged &&
- !(ce->ce_flags & htons(CE_VALID)))
+ !(ce->ce_flags & CE_VALID))
; /* mark this one VALID again */
- else
+ else {
+ /*
+ * We do not mark the index itself "modified"
+ * because CE_UPTODATE flag is in-core only;
+ * we are not going to write this change out.
+ */
+ ce_mark_uptodate(ce);
return ce;
+ }
}
if (ie_modified(istate, ce, &st, options)) {
updated = xmalloc(size);
memcpy(updated, ce, size);
fill_stat_cache_info(updated, &st);
-
/*
* If ignore_valid is not set, we should leave CE_VALID bit
* alone. Otherwise, paths marked with --no-assume-unchanged
* automatically, which is not really what we want.
*/
if (!ignore_valid && assume_unchanged &&
- !(ce->ce_flags & htons(CE_VALID)))
- updated->ce_flags &= ~htons(CE_VALID);
+ !(ce->ce_flags & CE_VALID))
+ updated->ce_flags &= ~CE_VALID;
return updated;
}
@@ -880,7 +969,7 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p
/* If we are doing --really-refresh that
* means the index is not valid anymore.
*/
- ce->ce_flags &= ~htons(CE_VALID);
+ ce->ce_flags &= ~CE_VALID;
istate->cache_changed = 1;
}
if (quiet)
@@ -889,11 +978,8 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p
has_errors = 1;
continue;
}
- istate->cache_changed = 1;
- /* You can NOT just free istate->cache[i] here, since it
- * might not be necessarily malloc()ed but can also come
- * from mmap(). */
- istate->cache[i] = new;
+
+ replace_index_entry(istate, i, new);
}
return has_errors;
}
return read_index_from(istate, get_index_file());
}
+static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
+{
+ size_t len;
+
+ ce->ce_ctime = ntohl(ondisk->ctime.sec);
+ ce->ce_mtime = ntohl(ondisk->mtime.sec);
+ ce->ce_dev = ntohl(ondisk->dev);
+ ce->ce_ino = ntohl(ondisk->ino);
+ ce->ce_mode = ntohl(ondisk->mode);
+ ce->ce_uid = ntohl(ondisk->uid);
+ ce->ce_gid = ntohl(ondisk->gid);
+ ce->ce_size = ntohl(ondisk->size);
+ /* On-disk flags are just 16 bits */
+ ce->ce_flags = ntohs(ondisk->flags);
+ hashcpy(ce->sha1, ondisk->sha1);
+
+ len = ce->ce_flags & CE_NAMEMASK;
+ if (len == CE_NAMEMASK)
+ len = strlen(ondisk->name);
+ /*
+ * NEEDSWORK: If the original index is crafted, this copy could
+ * go unchecked.
+ */
+ memcpy(ce->name, ondisk->name, len + 1);
+}
+
+static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
+{
+ long per_entry;
+
+ per_entry = sizeof(struct cache_entry) - sizeof(struct ondisk_cache_entry);
+
+ /*
+ * Alignment can cause differences. This should be "alignof", but
+ * since that's a gcc'ism, just use the size of a pointer.
+ */
+ per_entry += sizeof(void *);
+ return ondisk_size + entries*per_entry;
+}
+
/* remember to discard_cache() before reading a different cache! */
int read_index_from(struct index_state *istate, const char *path)
{
int fd, i;
struct stat st;
- unsigned long offset;
+ unsigned long src_offset, dst_offset;
struct cache_header *hdr;
+ void *mmap;
+ size_t mmap_size;
errno = EBUSY;
- if (istate->mmap)
+ if (istate->alloc)
return istate->cache_nr;
errno = ENOENT;
die("cannot stat the open index (%s)", strerror(errno));
errno = EINVAL;
- istate->mmap_size = xsize_t(st.st_size);
- if (istate->mmap_size < sizeof(struct cache_header) + 20)
+ mmap_size = xsize_t(st.st_size);
+ if (mmap_size < sizeof(struct cache_header) + 20)
die("index file smaller than expected");
- istate->mmap = xmmap(NULL, istate->mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+ mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
close(fd);
+ if (mmap == MAP_FAILED)
+ die("unable to map index file");
- hdr = istate->mmap;
- if (verify_hdr(hdr, istate->mmap_size) < 0)
+ hdr = mmap;
+ if (verify_hdr(hdr, mmap_size) < 0)
goto unmap;
istate->cache_nr = ntohl(hdr->hdr_entries);
istate->cache_alloc = alloc_nr(istate->cache_nr);
istate->cache = xcalloc(istate->cache_alloc, sizeof(struct cache_entry *));
- offset = sizeof(*hdr);
+ /*
+ * The disk format is actually larger than the in-memory format,
+ * due to space for nsec etc, so even though the in-memory one
+ * has room for a few more flags, we can allocate using the same
+ * index size
+ */
+ istate->alloc = xmalloc(estimate_cache_size(mmap_size, istate->cache_nr));
+
+ src_offset = sizeof(*hdr);
+ dst_offset = 0;
for (i = 0; i < istate->cache_nr; i++) {
+ struct ondisk_cache_entry *disk_ce;
struct cache_entry *ce;
- ce = (struct cache_entry *)((char *)(istate->mmap) + offset);
- offset = offset + ce_size(ce);
- istate->cache[i] = ce;
+ disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
+ ce = (struct cache_entry *)((char *)istate->alloc + dst_offset);
+ convert_from_disk(disk_ce, ce);
+ set_index_entry(istate, i, ce);
+
+ src_offset += ondisk_ce_size(ce);
+ dst_offset += ce_size(ce);
}
istate->timestamp = st.st_mtime;
- while (offset <= istate->mmap_size - 20 - 8) {
+ while (src_offset <= mmap_size - 20 - 8) {
/* After an array of active_nr index entries,
* there can be arbitrary number of extended
* sections, each of which is prefixed with
* in 4-byte network byte order.
*/
unsigned long extsize;
- memcpy(&extsize, (char *)(istate->mmap) + offset + 4, 4);
+ memcpy(&extsize, (char *)mmap + src_offset + 4, 4);
extsize = ntohl(extsize);
if (read_index_extension(istate,
- ((const char *) (istate->mmap)) + offset,
- (char *) (istate->mmap) + offset + 8,
+ (const char *) mmap + src_offset,
+ (char *) mmap + src_offset + 8,
extsize) < 0)
goto unmap;
- offset += 8;
- offset += extsize;
+ src_offset += 8;
+ src_offset += extsize;
}
+ munmap(mmap, mmap_size);
return istate->cache_nr;
unmap:
- munmap(istate->mmap, istate->mmap_size);
+ munmap(mmap, mmap_size);
errno = EINVAL;
die("index file corrupt");
}
int discard_index(struct index_state *istate)
{
- int ret;
-
istate->cache_nr = 0;
istate->cache_changed = 0;
istate->timestamp = 0;
+ free_hash(&istate->name_hash);
cache_tree_free(&(istate->cache_tree));
- if (istate->mmap == NULL)
- return 0;
- ret = munmap(istate->mmap, istate->mmap_size);
- istate->mmap = NULL;
- istate->mmap_size = 0;
+ free(istate->alloc);
+ istate->alloc = NULL;
/* no need to throw away allocated active_cache */
- return ret;
+ return 0;
}
#define WRITE_BUFFER_SIZE 8192
* file, and never calls us, so the cached size information
* for "frotz" stays 6 which does not match the filesystem.
*/
- ce->ce_size = htonl(0);
+ ce->ce_size = 0;
}
}
+static int ce_write_entry(SHA_CTX *c, int fd, struct cache_entry *ce)
+{
+ int size = ondisk_ce_size(ce);
+ struct ondisk_cache_entry *ondisk = xcalloc(1, size);
+
+ ondisk->ctime.sec = htonl(ce->ce_ctime);
+ ondisk->ctime.nsec = 0;
+ ondisk->mtime.sec = htonl(ce->ce_mtime);
+ ondisk->mtime.nsec = 0;
+ ondisk->dev = htonl(ce->ce_dev);
+ ondisk->ino = htonl(ce->ce_ino);
+ ondisk->mode = htonl(ce->ce_mode);
+ ondisk->uid = htonl(ce->ce_uid);
+ ondisk->gid = htonl(ce->ce_gid);
+ ondisk->size = htonl(ce->ce_size);
+ hashcpy(ondisk->sha1, ce->sha1);
+ ondisk->flags = htons(ce->ce_flags);
+ memcpy(ondisk->name, ce->name, ce_namelen(ce));
+
+ return ce_write(c, fd, ondisk, size);
+}
+
int write_index(struct index_state *istate, int newfd)
{
SHA_CTX c;
int entries = istate->cache_nr;
for (i = removed = 0; i < entries; i++)
- if (!cache[i]->ce_mode)
+ if (cache[i]->ce_flags & CE_REMOVE)
removed++;
hdr.hdr_signature = htonl(CACHE_SIGNATURE);
for (i = 0; i < entries; i++) {
struct cache_entry *ce = cache[i];
- if (!ce->ce_mode)
+ if (ce->ce_flags & CE_REMOVE)
continue;
- if (istate->timestamp &&
- istate->timestamp <= ntohl(ce->ce_mtime.sec))
+ if (is_racy_timestamp(istate, ce))
ce_smudge_racily_clean_entry(ce);
- if (ce_write(&c, newfd, ce, ce_size(ce)) < 0)
+ if (ce_write_entry(&c, newfd, ce) < 0)
return -1;
}
diff --git a/sha1_name.c b/sha1_name.c
index 13e11645e1fd6b61812cc3e88d2ad6cd42cad9ce..be8489e4e5fc98c6e38036a40fb5ca8c0db77ebc 100644 (file)
--- a/sha1_name.c
+++ b/sha1_name.c
break;
if (ce_stage(ce) == stage) {
hashcpy(sha1, ce->sha1);
- *mode = ntohl(ce->ce_mode);
+ *mode = ce->ce_mode;
return 0;
}
pos++;
diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh
index cd0de506d208f3d741aa2223e8cc639850326ae7..92de08822702f780c6895a5d2c070ee009ecfef7 100755 (executable)
--- a/t/t0000-basic.sh
+++ b/t/t0000-basic.sh
test "$sym" = "$(test-absolute-path $dir2/syml)"
'
+test_expect_success 'very long name in the index handled sanely' '
+
+ a=a && # 1
+ a=$a$a$a$a$a$a$a$a$a$a$a$a$a$a$a$a && # 16
+ a=$a$a$a$a$a$a$a$a$a$a$a$a$a$a$a$a && # 256
+ a=$a$a$a$a$a$a$a$a$a$a$a$a$a$a$a$a && # 4096
+ a=${a}q &&
+
+ >path4 &&
+ git update-index --add path4 &&
+ (
+ git ls-files -s path4 |
+ sed -e "s/ .*/ /" |
+ tr -d "\012"
+ echo "$a"
+ ) | git update-index --index-info &&
+ len=$(git ls-files "a*" | wc -c) &&
+ test $len = 4098
+'
+
test_done
index 8c0819fa721771f6dc2e727860345376edb3ea60..87708ef420aaa328c9a8dfcefbcf4aa7ba6d4b72 100644 (file)
--- a/tree.c
+++ b/tree.c
ce1 = *((const struct cache_entry **)a_);
ce2 = *((const struct cache_entry **)b_);
- return cache_name_compare(ce1->name, ntohs(ce1->ce_flags),
- ce2->name, ntohs(ce2->ce_flags));
+ return cache_name_compare(ce1->name, ce1->ce_flags,
+ ce2->name, ce2->ce_flags);
}
int read_tree(struct tree *tree, int stage, const char **match)
diff --git a/unpack-trees.c b/unpack-trees.c
index aa2513ed798969c02fc5e14097666eb4c4c02bae..ff46fd62fdceeefc2ebd98ae1c9483964cb37bd5 100644 (file)
--- a/unpack-trees.c
+++ b/unpack-trees.c
static void check_updates(struct cache_entry **src, int nr,
struct unpack_trees_options *o)
{
- unsigned short mask = htons(CE_UPDATE);
unsigned cnt = 0, total = 0;
struct progress *progress = NULL;
char last_symlink[PATH_MAX];
if (o->update && o->verbose_update) {
for (total = cnt = 0; cnt < nr; cnt++) {
struct cache_entry *ce = src[cnt];
- if (!ce->ce_mode || ce->ce_flags & mask)
+ if (ce->ce_flags & (CE_UPDATE | CE_REMOVE))
total++;
}
while (nr--) {
struct cache_entry *ce = *src++;
- if (!ce->ce_mode || ce->ce_flags & mask)
+ if (ce->ce_flags & (CE_UPDATE | CE_REMOVE))
display_progress(progress, ++cnt);
- if (!ce->ce_mode) {
+ if (ce->ce_flags & CE_REMOVE) {
if (o->update)
unlink_entry(ce->name, last_symlink);
continue;
}
- if (ce->ce_flags & mask) {
- ce->ce_flags &= ~mask;
+ if (ce->ce_flags & CE_UPDATE) {
+ ce->ce_flags &= ~CE_UPDATE;
if (o->update) {
checkout_entry(ce, &state, NULL);
*last_symlink = '\0';
* submodules that are marked to be automatically
* checked out.
*/
- if (S_ISGITLINK(ntohl(ce->ce_mode)))
+ if (S_ISGITLINK(ce->ce_mode))
return;
errno = 0;
}
@@ -450,7 +449,7 @@ static int verify_clean_subdirectory(struct cache_entry *ce, const char *action,
int cnt = 0;
unsigned char sha1[20];
- if (S_ISGITLINK(ntohl(ce->ce_mode)) &&
+ if (S_ISGITLINK(ce->ce_mode) &&
resolve_gitlink_ref(ce->name, "HEAD", sha1) == 0) {
/* If we are not going to update the submodule, then
* we don't care.
@@ -481,7 +480,7 @@ static int verify_clean_subdirectory(struct cache_entry *ce, const char *action,
*/
if (!ce_stage(ce)) {
verify_uptodate(ce, o);
- ce->ce_mode = 0;
+ ce->ce_flags |= CE_REMOVE;
}
cnt++;
}
cnt = cache_name_pos(ce->name, strlen(ce->name));
if (0 <= cnt) {
struct cache_entry *ce = active_cache[cnt];
- if (!ce_stage(ce) && !ce->ce_mode)
+ if (ce->ce_flags & CE_REMOVE)
return;
}
static int merged_entry(struct cache_entry *merge, struct cache_entry *old,
struct unpack_trees_options *o)
{
- merge->ce_flags |= htons(CE_UPDATE);
+ merge->ce_flags |= CE_UPDATE;
if (old) {
/*
* See if we can re-use the old CE directly?
invalidate_ce_path(merge);
}
- merge->ce_flags &= ~htons(CE_STAGEMASK);
+ merge->ce_flags &= ~CE_STAGEMASK;
add_cache_entry(merge, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
return 1;
}
verify_uptodate(old, o);
else
verify_absent(ce, "removed", o);
- ce->ce_mode = 0;
+ ce->ce_flags |= CE_REMOVE;
add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
invalidate_ce_path(ce);
return 1;
else
fprintf(o, "%s%06o %s %d\t%s\n",
label,
- ntohl(ce->ce_mode),
+ ce->ce_mode,
sha1_to_hex(ce->sha1),
ce_stage(ce),
ce->name);
struct stat st;
if (lstat(old->name, &st) ||
ce_match_stat(old, &st, CE_MATCH_IGNORE_VALID))
- old->ce_flags |= htons(CE_UPDATE);
+ old->ce_flags |= CE_UPDATE;
}
return keep_entry(old, o);
}
diff --git a/unpack-trees.h b/unpack-trees.h
index 5517faafad6ca3f327c81ab6e8e5f2701ff0ad14..197a0044aa71fc9ca310b36b279b8382487a40a7 100644 (file)
--- a/unpack-trees.h
+++ b/unpack-trees.h
int merge_size;
struct cache_entry *df_conflict_entry;
+ void *unpack_data;
};
extern int unpack_trees(unsigned n, struct tree_desc *t,
diff --git a/wt-status.c b/wt-status.c
index bfd1b0fcc612a827adc7416626895b89e8504d90..f14022f2a9b8ce740067f7c6bf03bd51203cf2ca 100644 (file)
--- a/wt-status.c
+++ b/wt-status.c
wt_status_print_trailer(s);
}
-static void wt_read_cache(struct wt_status *s)
-{
- discard_cache();
- read_cache_from(s->index_file);
-}
-
static void wt_status_print_initial(struct wt_status *s)
{
int i;
struct strbuf buf;
strbuf_init(&buf, 0);
- wt_read_cache(s);
if (active_nr) {
s->commitable = 1;
wt_status_print_cached_header(s);
rev.diffopt.detect_rename = 1;
rev.diffopt.rename_limit = 100;
rev.diffopt.break_opt = 0;
- wt_read_cache(s);
run_diff_index(&rev, 1);
}
rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK;
rev.diffopt.format_callback = wt_status_print_changed_cb;
rev.diffopt.format_callback_data = s;
- wt_read_cache(s);
run_diff_files(&rev, 0);
}
setup_revisions(0, NULL, &rev, s->reference);
rev.diffopt.output_format |= DIFF_FORMAT_PATCH;
rev.diffopt.detect_rename = 1;
- wt_read_cache(s);
run_diff_index(&rev, 1);
fflush(stdout);