Make on-disk index representation separate from in-core one

This converts the index explicitly on read and write to its on-disk
format, allowing the in-core format to contain more flags, and be
simpler.

In particular, the in-core format is now host-endian (as opposed to the
on-disk one that is network endian in order to be able to be shared
across machines) and as a result we can dispense with all the
htonl/ntohl on accesses to the cache_entry fields.

This will make it easier to make use of various temporary flags that do
not exist in the on-disk format.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

builtin-apply.c

@@ -1946,7 +1946,7 @@ static int read_file_or_gitlink(struct cache_entry *ce, struct strbuf *buf)
 	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 {
@@ -2023,7 +2023,7 @@ static int check_to_create_blob(const char *new_name, int ok_if_exists)
 
 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;
@@ -2082,12 +2082,12 @@ static int check_patch(struct patch *patch, struct patch *prev_patch)
 				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;
 

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;

builtin-commit.c

@@ -156,7 +156,7 @@ static int list_paths(struct path_list *list, const char *with_tree,
 
 	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;

builtin-fsck.c

@@ -765,7 +765,7 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 			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);

builtin-grep.c

@@ -331,7 +331,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		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;
@@ -387,7 +387,7 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 
 	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;

builtin-ls-files.c

@@ -189,7 +189,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 		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]))
@@ -210,7 +210,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	} 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));
@@ -242,7 +242,7 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 				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);
 		}
@@ -350,7 +350,7 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix)
 		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) {
@@ -379,7 +379,7 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix)
 			 */
 			if (last_stage0 &&
 			    !strcmp(last_stage0->name, ce->name))
-				ce->ce_flags |= htons(CE_UPDATE);
+				ce->ce_flags |= CE_UPDATE;
 		}
 	}
 }

builtin-read-tree.c

@@ -45,8 +45,7 @@ static int read_cache_unmerged(void)
 				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;
 	}

builtin-rerere.c

@@ -149,8 +149,8 @@ static int find_conflict(struct path_list *conflict)
 		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 */
 		}

builtin-update-index.c

@@ -47,10 +47,10 @@ static int mark_valid(const char *path)
 	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);
@@ -95,7 +95,7 @@ static int add_one_path(struct cache_entry *old, const char *path, int len, stru
 	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);
 
@@ -139,7 +139,7 @@ static int process_directory(const char *path, int len, struct stat *st)
 	/* 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)
@@ -183,7 +183,7 @@ static int process_file(const char *path, int len, struct stat *st)
 	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);
@@ -226,7 +226,7 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 	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))
@@ -246,14 +246,14 @@ static void chmod_path(int flip, const char *path)
 	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;
 	}

cache-tree.c

@@ -320,13 +320,13 @@ static int update_one(struct cache_tree *it,
 		}
 		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);

cache.h

@@ -94,48 +94,66 @@ struct cache_time {
  * 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;
+	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 create_ce_flags(len, stage) ((len) | ((stage) << CE_STAGESHIFT))
+#define ce_namelen(ce) (CE_NAMEMASK & (ce)->ce_flags)
 #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_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 +164,14 @@ 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;
 };
 
 extern struct index_state the_index;

diff-lib.c

@@ -37,7 +37,7 @@ static int get_mode(const char *path, int *mode)
 	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
@@ -384,7 +384,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 					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];
@@ -398,10 +398,10 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 				 */
 				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;
 				}
@@ -442,15 +442,15 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
 			}
 			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);
@@ -471,7 +471,7 @@ static void diff_index_show_file(struct rev_info *revs,
 				 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);
 }
 
@@ -550,14 +550,14 @@ static int show_modified(struct rev_info *revs,
 		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);
@@ -569,9 +569,6 @@ static int show_modified(struct rev_info *revs,
 	    !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;
@@ -628,7 +625,7 @@ static int diff_cache(struct rev_info *revs,
 					   cached, match_missing))
 				break;
 			diff_unmerge(&revs->diffopt, ce->name,
-				     ntohl(ce->ce_mode), ce->sha1);
+				     ce->ce_mode, ce->sha1);
 			break;
 		case 3:
 			diff_unmerge(&revs->diffopt, ce->name,
@@ -664,7 +661,7 @@ static void mark_merge_entries(void)
 		struct cache_entry *ce = active_cache[i];
 		if (!ce_stage(ce))
 			continue;
-		ce->ce_flags |= htons(CE_STAGEMASK);
+		ce->ce_flags |= CE_STAGEMASK;
 	}
 }
 
@@ -722,8 +719,7 @@ int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt)
 			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;
 	}

dir.c

@@ -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;

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);

merge-index.c

@@ -48,7 +48,7 @@ static int merge_entry(int pos, const char *path)
 			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);

merge-recursive.c

@@ -333,7 +333,7 @@ static struct path_list *get_unmerged(void)
 			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);
 	}
 

reachable.c

@@ -176,7 +176,7 @@ static void add_cache_refs(struct rev_info *revs)
 		 * 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);

read-cache.c

@@ -30,20 +30,16 @@ struct index_state the_index;
  */
 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;
 }
 
 static int ce_compare_data(struct cache_entry *ce, struct stat *st)
@@ -116,7 +112,7 @@ static int ce_modified_check_fs(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;
@@ -128,14 +124,17 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 {
 	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:
@@ -149,32 +148,18 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 		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))
-		changed |= MTIME_CHANGED;
-	if (ce->ce_ctime.sec != htonl(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))
+	if (ce->ce_mtime != (unsigned int) st->st_mtime)
 		changed |= MTIME_CHANGED;
-	if (ce->ce_ctime.nsec != htonl(st->st_ctim.tv_nsec))
+	if (ce->ce_ctime != (unsigned int) st->st_ctime)
 		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
@@ -183,11 +168,11 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 	 * 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;
@@ -205,7 +190,7 @@ int ie_match_stat(struct index_state *istate,
 	 * 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);
@@ -228,7 +213,7 @@ int ie_match_stat(struct index_state *istate,
 	 */
 	if (!changed &&
 	    istate->timestamp &&
-	    istate->timestamp <= ntohl(ce->ce_mtime.sec)) {
+	    istate->timestamp <= ce->ce_mtime) {
 		if (assume_racy_is_modified)
 			changed |= DATA_CHANGED;
 		else
@@ -257,7 +242,7 @@ int ie_modified(struct index_state *istate,
 	 * 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);
@@ -320,7 +305,7 @@ int index_name_pos(struct index_state *istate, const char *name, int namelen)
 	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) {
@@ -405,7 +390,7 @@ 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)
@@ -583,7 +568,7 @@ static int has_file_name(struct index_state *istate,
 			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)
@@ -616,7 +601,7 @@ static int has_dir_name(struct index_state *istate,
 		}
 		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
@@ -679,7 +664,7 @@ static int check_file_directory_conflict(struct index_state *istate,
 	/*
 	 * 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;
 
 	/*
@@ -704,7 +689,7 @@ 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) {
@@ -736,7 +721,7 @@ 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;
@@ -810,7 +795,7 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate,
 		 * 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
 			return ce;
@@ -826,7 +811,6 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate,
 	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
@@ -834,8 +818,8 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate,
 	 * 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 +864,7 @@ 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)
@@ -942,16 +926,34 @@ int read_index(struct index_state *istate)
 	return read_index_from(istate, get_index_file());
 }
 
+static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
+{
+	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);
+	memcpy(ce->name, ondisk->name, ce_namelen(ce)+1);
+}
+
 /* 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;
@@ -967,31 +969,47 @@ int read_index_from(struct index_state *istate, const char *path)
 		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(mmap_size);
+
+	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);
+		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);
 		istate->cache[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
@@ -999,40 +1017,36 @@ int read_index_from(struct index_state *istate, const char *path)
 		 * 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;
 	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
@@ -1144,10 +1158,32 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
 		 * 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;
@@ -1157,7 +1193,7 @@ int write_index(struct index_state *istate, int newfd)
 	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);
@@ -1170,12 +1206,12 @@ int write_index(struct index_state *istate, int newfd)
 
 	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))
+		    istate->timestamp <= ce->ce_mtime)
 			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;
 	}
 

sha1_name.c

@@ -695,7 +695,7 @@ int get_sha1_with_mode(const char *name, unsigned char *sha1, unsigned *mode)
 				break;
 			if (ce_stage(ce) == stage) {
 				hashcpy(sha1, ce->sha1);
-				*mode = ntohl(ce->ce_mode);
+				*mode = ce->ce_mode;
 				return 0;
 			}
 			pos++;

tree.c

@@ -142,8 +142,8 @@ static int cmp_cache_name_compare(const void *a_, const void *b_)
 
 	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)

unpack-trees.c

@@ -289,7 +289,6 @@ static struct checkout state;
 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];
@@ -297,7 +296,7 @@ static void check_updates(struct cache_entry **src, int nr,
 	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++;
 		}
 
@@ -310,15 +309,15 @@ static void check_updates(struct cache_entry **src, int nr,
 	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';
@@ -408,7 +407,7 @@ static void verify_uptodate(struct cache_entry *ce,
 		 * 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++;
 	}
@@ -568,7 +567,7 @@ static void verify_absent(struct cache_entry *ce, const char *action,
 		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;
 		}
 
@@ -580,7 +579,7 @@ static void verify_absent(struct cache_entry *ce, const char *action,
 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?
@@ -601,7 +600,7 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old,
 		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;
 }
@@ -613,7 +612,7 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old,
 		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;
@@ -634,7 +633,7 @@ static void show_stage_entry(FILE *o,
 	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);
@@ -920,7 +919,7 @@ int oneway_merge(struct cache_entry **src,
 			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);
 	}