Merge branch 'lt/unpack-trees'

* lt/unpack-trees:
  unpack_trees(): fix diff-index regression.
  traverse_trees_recursive(): propagate merge errors up
  unpack_trees(): minor memory leak fix in unused destination index
  Make 'unpack_trees()' have a separate source and destination index
  Make 'unpack_trees()' take the index to work on as an argument
  Add 'const' where appropriate to index handling functions
  Fix tree-walking compare_entry() in the presense of --prefix
  Move 'unpack_trees()' over to 'traverse_trees()' interface
  Make 'traverse_trees()' traverse conflicting DF entries in parallel
  Add return value to 'traverse_tree()' callback
  Make 'traverse_tree()' use linked structure rather than 'const char *base'
  Add 'df_name_compare()' helper function

15 files changed, 503 insertions, 452 deletions

diff --git a/builtin-checkout.c b/builtin-checkout.c
index 6b08016228..7deb504837 100644
--- a/builtin-checkout.c
+++ b/builtin-checkout.c
@@ -152,6 +152,7 @@ static int reset_to_new(struct tree *tree, int quiet)
 {
 	struct unpack_trees_options opts;
 	struct tree_desc tree_desc;
+
 	memset(&opts, 0, sizeof(opts));
 	opts.head_idx = -1;
 	opts.update = 1;
@@ -159,6 +160,8 @@ static int reset_to_new(struct tree *tree, int quiet)
 	opts.merge = 1;
 	opts.fn = oneway_merge;
 	opts.verbose_update = !quiet;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
 	parse_tree(tree);
 	init_tree_desc(&tree_desc, tree->buffer, tree->size);
 	if (unpack_trees(1, &tree_desc, &opts))
@@ -170,6 +173,7 @@ static void reset_clean_to_new(struct tree *tree, int quiet)
 {
 	struct unpack_trees_options opts;
 	struct tree_desc tree_desc;
+
 	memset(&opts, 0, sizeof(opts));
 	opts.head_idx = -1;
 	opts.skip_unmerged = 1;
@@ -177,6 +181,8 @@ static void reset_clean_to_new(struct tree *tree, int quiet)
 	opts.merge = 1;
 	opts.fn = oneway_merge;
 	opts.verbose_update = !quiet;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
 	parse_tree(tree);
 	init_tree_desc(&tree_desc, tree->buffer, tree->size);
 	if (unpack_trees(1, &tree_desc, &opts))
@@ -224,8 +230,11 @@ static int merge_working_tree(struct checkout_opts *opts,
 		struct tree_desc trees[2];
 		struct tree *tree;
 		struct unpack_trees_options topts;
+
 		memset(&topts, 0, sizeof(topts));
 		topts.head_idx = -1;
+		topts.src_index = &the_index;
+		topts.dst_index = &the_index;
 
 		refresh_cache(REFRESH_QUIET);
 
diff --git a/builtin-commit.c b/builtin-commit.c
index f49c22e642..660a3458f7 100644
--- a/builtin-commit.c
+++ b/builtin-commit.c
@@ -198,6 +198,8 @@ static void create_base_index(void)
 	opts.head_idx = 1;
 	opts.index_only = 1;
 	opts.merge = 1;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
 
 	opts.fn = oneway_merge;
 	tree = parse_tree_indirect(head_sha1);
diff --git a/builtin-merge-recursive.c b/builtin-merge-recursive.c
index 5a0a7b5297..5c7fbb2599 100644
--- a/builtin-merge-recursive.c
+++ b/builtin-merge-recursive.c
@@ -213,6 +213,8 @@ static int git_merge_trees(int index_only,
 	opts.merge = 1;
 	opts.head_idx = 2;
 	opts.fn = threeway_merge;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
 
 	init_tree_desc_from_tree(t+0, common);
 	init_tree_desc_from_tree(t+1, head);
diff --git a/builtin-read-tree.c b/builtin-read-tree.c
index 0138f5a917..160456dad1 100644
--- a/builtin-read-tree.c
+++ b/builtin-read-tree.c
@@ -102,6 +102,8 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix)
 
 	memset(&opts, 0, sizeof(opts));
 	opts.head_idx = -1;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
 
 	git_config(git_default_config);
 
@@ -220,27 +222,6 @@ int cmd_read_tree(int argc, const char **argv, const char *unused_prefix)
 	if ((opts.dir && !opts.update))
 		die("--exclude-per-directory is meaningless unless -u");
 
-	if (opts.prefix) {
-		int pfxlen = strlen(opts.prefix);
-		int pos;
-		if (opts.prefix[pfxlen-1] != '/')
-			die("prefix must end with /");
-		if (stage != 2)
-			die("binding merge takes only one tree");
-		pos = cache_name_pos(opts.prefix, pfxlen);
-		if (0 <= pos)
-			die("corrupt index file");
-		pos = -pos-1;
-		if (pos < active_nr &&
-		    !strncmp(active_cache[pos]->name, opts.prefix, pfxlen))
-			die("subdirectory '%s' already exists.", opts.prefix);
-		pos = cache_name_pos(opts.prefix, pfxlen-1);
-		if (0 <= pos)
-			die("file '%.*s' already exists.",
-					pfxlen-1, opts.prefix);
-		opts.pos = -1 - pos;
-	}
-
 	if (opts.merge) {
 		if (stage < 2)
 			die("just how do you expect me to merge %d trees?", stage-1);
diff --git a/cache.h b/cache.h
index bdefcc9188..2a1e7ec6b2 100644
--- a/cache.h
+++ b/cache.h
@@ -346,12 +346,12 @@ extern void verify_non_filename(const char *prefix, const char *name);
 /* Initialize and use the cache information */
 extern int read_index(struct index_state *);
 extern int read_index_from(struct index_state *, const char *path);
-extern int write_index(struct index_state *, int newfd);
+extern int write_index(const struct index_state *, int newfd);
 extern int discard_index(struct index_state *);
-extern int unmerged_index(struct index_state *);
+extern int unmerged_index(const 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);
+extern int index_name_pos(const 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 */
 #define ADD_CACHE_SKIP_DFCHECK 4	/* Ok to skip DF conflict checks */
@@ -368,8 +368,8 @@ extern int ce_same_name(struct cache_entry *a, struct cache_entry *b);
 #define CE_MATCH_IGNORE_VALID		01
 /* do not check the contents but report dirty on racily-clean entries */
 #define CE_MATCH_RACY_IS_DIRTY	02
-extern int ie_match_stat(struct index_state *, struct cache_entry *, struct stat *, unsigned int);
-extern int ie_modified(struct index_state *, struct cache_entry *, struct stat *, unsigned int);
+extern int ie_match_stat(const struct index_state *, struct cache_entry *, struct stat *, unsigned int);
+extern int ie_modified(const struct index_state *, struct cache_entry *, struct stat *, unsigned int);
 
 extern int ce_path_match(const struct cache_entry *ce, const char **pathspec);
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path);
@@ -536,6 +536,7 @@ extern int create_symref(const char *ref, const char *refs_heads_master, const c
 extern int validate_headref(const char *ref);
 
 extern int base_name_compare(const char *name1, int len1, int mode1, const char *name2, int len2, int mode2);
+extern int df_name_compare(const char *name1, int len1, int mode1, const char *name2, int len2, int mode2);
 extern int cache_name_compare(const char *name1, int len1, const char *name2, int len2);
 
 extern void *read_object_with_reference(const unsigned char *sha1,
diff --git a/diff-lib.c b/diff-lib.c
index 4581b594d0..52dbac34a4 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -600,8 +600,7 @@ static void mark_merge_entries(void)
  */
 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 cache_entry *tree)
 {
 	struct rev_info *revs = o->unpack_data;
 	int match_missing, cached;
@@ -642,32 +641,19 @@ static void do_oneway_diff(struct unpack_trees_options *o,
 	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)
+static inline void skip_same_name(struct cache_entry *ce, struct unpack_trees_options *o)
 {
-	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;
-			ce = *++p;
-			if (ce_namelen(ce) != namelen)
-				break;
-			if (memcmp(ce->name, src->name, namelen))
-				break;
-			skip++;
-		}
+	int len = ce_namelen(ce);
+	const struct index_state *index = o->src_index;
+
+	while (o->pos < index->cache_nr) {
+		struct cache_entry *next = index->cache[o->pos];
+		if (len != ce_namelen(next))
+			break;
+		if (memcmp(ce->name, next->name, len))
+			break;
+		o->pos++;
 	}
-	return skip;
 }
 
 /*
@@ -685,17 +671,14 @@ static inline int count_skip(const struct cache_entry *src, int pos)
  * the fairly complex unpack_trees() semantic requirements, including
  * the skipping, the path matching, the type conflict cases etc.
  */
-static int oneway_diff(struct cache_entry **src,
-	struct unpack_trees_options *o,
-	int index_pos)
+static int oneway_diff(struct cache_entry **src, struct unpack_trees_options *o)
 {
-	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);
+	if (idx && ce_stage(idx))
+		skip_same_name(idx, o);
 
 	/*
 	 * Unpack-trees generates a DF/conflict entry if
@@ -707,9 +690,9 @@ static int oneway_diff(struct cache_entry **src,
 		tree = NULL;
 
 	if (ce_path_match(idx ? idx : tree, revs->prune_data))
-		do_oneway_diff(o, idx, tree, index_pos, skip);
+		do_oneway_diff(o, idx, tree);
 
-	return skip;
+	return 0;
 }
 
 int run_diff_index(struct rev_info *revs, int cached)
@@ -734,6 +717,8 @@ int run_diff_index(struct rev_info *revs, int cached)
 	opts.merge = 1;
 	opts.fn = oneway_diff;
 	opts.unpack_data = revs;
+	opts.src_index = &the_index;
+	opts.dst_index = NULL;
 
 	init_tree_desc(&t, tree->buffer, tree->size);
 	if (unpack_trees(1, &t, &opts))
@@ -787,6 +772,8 @@ int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt)
 	opts.merge = 1;
 	opts.fn = oneway_diff;
 	opts.unpack_data = &revs;
+	opts.src_index = &the_index;
+	opts.dst_index = &the_index;
 
 	init_tree_desc(&t, tree->buffer, tree->size);
 	if (unpack_trees(1, &t, &opts))
diff --git a/hash.c b/hash.c
index d9ec82fa66..1cd4c9d5c0 100644
--- a/hash.c
+++ b/hash.c
@@ -9,7 +9,7 @@
  * the existing entry, or the empty slot if none existed. The caller
  * can then look at the (*ptr) to see whether it existed or not.
  */
-static struct hash_table_entry *lookup_hash_entry(unsigned int hash, struct hash_table *table)
+static struct hash_table_entry *lookup_hash_entry(unsigned int hash, const struct hash_table *table)
 {
 	unsigned int size = table->size, nr = hash % size;
 	struct hash_table_entry *array = table->array;
@@ -66,7 +66,7 @@ static void grow_hash_table(struct hash_table *table)
 	free(old_array);
 }
 
-void *lookup_hash(unsigned int hash, struct hash_table *table)
+void *lookup_hash(unsigned int hash, const struct hash_table *table)
 {
 	if (!table->array)
 		return NULL;
@@ -81,7 +81,7 @@ void **insert_hash(unsigned int hash, void *ptr, struct hash_table *table)
 	return insert_hash_entry(hash, ptr, table);
 }
 
-int for_each_hash(struct hash_table *table, int (*fn)(void *))
+int for_each_hash(const struct hash_table *table, int (*fn)(void *))
 {
 	int sum = 0;
 	unsigned int i;
diff --git a/hash.h b/hash.h
index a8b0fbb5b5..69e33a47b9 100644
--- a/hash.h
+++ b/hash.h
@@ -28,9 +28,9 @@ struct hash_table {
 	struct hash_table_entry *array;
 };
 
-extern void *lookup_hash(unsigned int hash, struct hash_table *table);
+extern void *lookup_hash(unsigned int hash, const struct hash_table *table);
 extern void **insert_hash(unsigned int hash, void *ptr, struct hash_table *table);
-extern int for_each_hash(struct hash_table *table, int (*fn)(void *));
+extern int for_each_hash(const struct hash_table *table, int (*fn)(void *));
 extern void free_hash(struct hash_table *table);
 
 static inline void init_hash(struct hash_table *table)
diff --git a/merge-tree.c b/merge-tree.c
index e08324686c..02fc10f7e6 100644
--- a/merge-tree.c
+++ b/merge-tree.c
@@ -168,7 +168,13 @@ static struct merge_list *create_entry(unsigned stage, unsigned mode, const unsi
 	return res;
 }
 
-static void resolve(const char *base, struct name_entry *branch1, struct name_entry *result)
+static char *traverse_path(const struct traverse_info *info, const struct name_entry *n)
+{
+	char *path = xmalloc(traverse_path_len(info, n) + 1);
+	return make_traverse_path(path, info, n);
+}
+
+static void resolve(const struct traverse_info *info, struct name_entry *branch1, struct name_entry *result)
 {
 	struct merge_list *orig, *final;
 	const char *path;
@@ -177,7 +183,7 @@ static void resolve(const char *base, struct name_entry *branch1, struct name_en
 	if (!branch1)
 		return;
 
-	path = xstrdup(mkpath("%s%s", base, result->path));
+	path = traverse_path(info, result);
 	orig = create_entry(2, branch1->mode, branch1->sha1, path);
 	final = create_entry(0, result->mode, result->sha1, path);
 
@@ -186,9 +192,8 @@ static void resolve(const char *base, struct name_entry *branch1, struct name_en
 	add_merge_entry(final);
 }
 
-static int unresolved_directory(const char *base, struct name_entry n[3])
+static int unresolved_directory(const struct traverse_info *info, struct name_entry n[3])
 {
-	int baselen, pathlen;
 	char *newbase;
 	struct name_entry *p;
 	struct tree_desc t[3];
@@ -204,13 +209,7 @@ static int unresolved_directory(const char *base, struct name_entry n[3])
 	}
 	if (!S_ISDIR(p->mode))
 		return 0;
-	baselen = strlen(base);
-	pathlen = tree_entry_len(p->path, p->sha1);
-	newbase = xmalloc(baselen + pathlen + 2);
-	memcpy(newbase, base, baselen);
-	memcpy(newbase + baselen, p->path, pathlen);
-	memcpy(newbase + baselen + pathlen, "/", 2);
-
+	newbase = traverse_path(info, p);
 	buf0 = fill_tree_descriptor(t+0, n[0].sha1);
 	buf1 = fill_tree_descriptor(t+1, n[1].sha1);
 	buf2 = fill_tree_descriptor(t+2, n[2].sha1);
@@ -224,7 +223,7 @@ static int unresolved_directory(const char *base, struct name_entry n[3])
 }
 
 
-static struct merge_list *link_entry(unsigned stage, const char *base, struct name_entry *n, struct merge_list *entry)
+static struct merge_list *link_entry(unsigned stage, const struct traverse_info *info, struct name_entry *n, struct merge_list *entry)
 {
 	const char *path;
 	struct merge_list *link;
@@ -234,17 +233,17 @@ static struct merge_list *link_entry(unsigned stage, const char *base, struct na
 	if (entry)
 		path = entry->path;
 	else
-		path = xstrdup(mkpath("%s%s", base, n->path));
+		path = traverse_path(info, n);
 	link = create_entry(stage, n->mode, n->sha1, path);
 	link->link = entry;
 	return link;
 }
 
-static void unresolved(const char *base, struct name_entry n[3])
+static void unresolved(const struct traverse_info *info, struct name_entry n[3])
 {
 	struct merge_list *entry = NULL;
 
-	if (unresolved_directory(base, n))
+	if (unresolved_directory(info, n))
 		return;
 
 	/*
@@ -252,9 +251,9 @@ static void unresolved(const char *base, struct name_entry n[3])
 	 * list has the stages in order - link_entry adds new
 	 * links at the front.
 	 */
-	entry = link_entry(3, base, n + 2, entry);
-	entry = link_entry(2, base, n + 1, entry);
-	entry = link_entry(1, base, n + 0, entry);
+	entry = link_entry(3, info, n + 2, entry);
+	entry = link_entry(2, info, n + 1, entry);
+	entry = link_entry(1, info, n + 0, entry);
 
 	add_merge_entry(entry);
 }
@@ -288,36 +287,41 @@ static void unresolved(const char *base, struct name_entry n[3])
  * The successful merge rules are the same as for the three-way merge
  * in git-read-tree.
  */
-static void threeway_callback(int n, unsigned long mask, struct name_entry *entry, const char *base)
+static int threeway_callback(int n, unsigned long mask, unsigned long dirmask, struct name_entry *entry, struct traverse_info *info)
 {
 	/* Same in both? */
 	if (same_entry(entry+1, entry+2)) {
 		if (entry[0].sha1) {
-			resolve(base, NULL, entry+1);
-			return;
+			resolve(info, NULL, entry+1);
+			return mask;
 		}
 	}
 
 	if (same_entry(entry+0, entry+1)) {
 		if (entry[2].sha1 && !S_ISDIR(entry[2].mode)) {
-			resolve(base, entry+1, entry+2);
-			return;
+			resolve(info, entry+1, entry+2);
+			return mask;
 		}
 	}
 
 	if (same_entry(entry+0, entry+2)) {
 		if (entry[1].sha1 && !S_ISDIR(entry[1].mode)) {
-			resolve(base, NULL, entry+1);
-			return;
+			resolve(info, NULL, entry+1);
+			return mask;
 		}
 	}
 
-	unresolved(base, entry);
+	unresolved(info, entry);
+	return mask;
 }
 
 static void merge_trees(struct tree_desc t[3], const char *base)
 {
-	traverse_trees(3, t, base, threeway_callback);
+	struct traverse_info info;
+
+	setup_traverse_info(&info, base);
+	info.fn = threeway_callback;
+	traverse_trees(3, t, &info);
 }
 
 static void *get_tree_descriptor(struct tree_desc *desc, const char *rev)
diff --git a/read-cache.c b/read-cache.c
index 657f0c5894..a92b25b59b 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -255,13 +255,13 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 	return changed;
 }
 
-static int is_racy_timestamp(struct index_state *istate, struct cache_entry *ce)
+static int is_racy_timestamp(const 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,
+int ie_match_stat(const struct index_state *istate,
 		  struct cache_entry *ce, struct stat *st,
 		  unsigned int options)
 {
@@ -304,7 +304,7 @@ int ie_match_stat(struct index_state *istate,
 	return changed;
 }
 
-int ie_modified(struct index_state *istate,
+int ie_modified(const struct index_state *istate,
 		struct cache_entry *ce, struct stat *st, unsigned int options)
 {
 	int changed, changed_fs;
@@ -351,6 +351,41 @@ int base_name_compare(const char *name1, int len1, int mode1,
 	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 cache_name_compare(const char *name1, int flags1, const char *name2, int flags2)
 {
 	int len1 = flags1 & CE_NAMEMASK;
@@ -377,7 +412,7 @@ int cache_name_compare(const char *name1, int flags1, const char *name2, int fla
 	return 0;
 }
 
-int index_name_pos(struct index_state *istate, const char *name, int namelen)
+int index_name_pos(const struct index_state *istate, const char *name, int namelen)
 {
 	int first, last;
 
@@ -1166,7 +1201,7 @@ int discard_index(struct index_state *istate)
 	return 0;
 }
 
-int unmerged_index(struct index_state *istate)
+int unmerged_index(const struct index_state *istate)
 {
 	int i;
 	for (i = 0; i < istate->cache_nr; i++) {
@@ -1311,7 +1346,7 @@ static int ce_write_entry(SHA_CTX *c, int fd, struct cache_entry *ce)
 	return ce_write(c, fd, ondisk, size);
 }
 
-int write_index(struct index_state *istate, int newfd)
+int write_index(const struct index_state *istate, int newfd)
 {
 	SHA_CTX c;
 	struct cache_header hdr;
diff --git a/t/t1005-read-tree-reset.sh b/t/t1005-read-tree-reset.sh
index f1b12167b8..8c4556408e 100755
--- a/t/t1005-read-tree-reset.sh
+++ b/t/t1005-read-tree-reset.sh
@@ -21,7 +21,7 @@ test_expect_success 'setup' '
   git commit -m two
 '
 
-test_expect_failure 'reset should work' '
+test_expect_success 'reset should work' '
   git read-tree -u --reset HEAD^ &&
   git ls-files >actual &&
   diff -u expect actual
diff --git a/tree-walk.c b/tree-walk.c
index 142205ddc3..02e2aed773 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -62,7 +62,7 @@ void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1)
 
 static int entry_compare(struct name_entry *a, struct name_entry *b)
 {
-	return base_name_compare(
+	return df_name_compare(
 			a->path, tree_entry_len(a->path, a->sha1), a->mode,
 			b->path, tree_entry_len(b->path, b->sha1), b->mode);
 }
@@ -104,12 +104,48 @@ int tree_entry(struct tree_desc *desc, struct name_entry *entry)
 	return 1;
 }
 
-void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback)
+void setup_traverse_info(struct traverse_info *info, const char *base)
 {
+	int pathlen = strlen(base);
+	static struct traverse_info dummy;
+
+	memset(info, 0, sizeof(*info));
+	if (pathlen && base[pathlen-1] == '/')
+		pathlen--;
+	info->pathlen = pathlen ? pathlen + 1 : 0;
+	info->name.path = base;
+	info->name.sha1 = (void *)(base + pathlen + 1);
+	if (pathlen)
+		info->prev = &dummy;
+}
+
+char *make_traverse_path(char *path, const struct traverse_info *info, const struct name_entry *n)
+{
+	int len = tree_entry_len(n->path, n->sha1);
+	int pathlen = info->pathlen;
+
+	path[pathlen + len] = 0;
+	for (;;) {
+		memcpy(path + pathlen, n->path, len);
+		if (!pathlen)
+			break;
+		path[--pathlen] = '/';
+		n = &info->name;
+		len = tree_entry_len(n->path, n->sha1);
+		info = info->prev;
+		pathlen -= len;
+	}
+	return path;
+}
+
+int traverse_trees(int n, struct tree_desc *t, struct traverse_info *info)
+{
+	int ret = 0;
 	struct name_entry *entry = xmalloc(n*sizeof(*entry));
 
 	for (;;) {
 		unsigned long mask = 0;
+		unsigned long dirmask = 0;
 		int i, last;
 
 		last = -1;
@@ -134,25 +170,35 @@ void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callb
 					mask = 0;
 			}
 			mask |= 1ul << i;
+			if (S_ISDIR(entry[i].mode))
+				dirmask |= 1ul << i;
 			last = i;
 		}
 		if (!mask)
 			break;
+		dirmask &= mask;
 
 		/*
-		 * Update the tree entries we've walked, and clear
-		 * all the unused name-entries.
+		 * Clear all the unused name-entries.
 		 */
 		for (i = 0; i < n; i++) {
-			if (mask & (1ul << i)) {
-				update_tree_entry(t+i);
+			if (mask & (1ul << i))
 				continue;
-			}
 			entry_clear(entry + i);
 		}
-		callback(n, mask, entry, base);
+		ret = info->fn(n, mask, dirmask, entry, info);
+		if (ret < 0)
+			break;
+		if (ret)
+			mask &= ret;
+		ret = 0;
+		for (i = 0; i < n; i++) {
+			if (mask & (1ul << i))
+				update_tree_entry(t + i);
+		}
 	}
 	free(entry);
+	return ret;
 }
 
 static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char *result, unsigned *mode)
diff --git a/tree-walk.h b/tree-walk.h
index db0fbdc701..42110a465f 100644
--- a/tree-walk.h
+++ b/tree-walk.h
@@ -33,10 +33,27 @@ int tree_entry(struct tree_desc *, struct name_entry *);
 
 void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1);
 
-typedef void (*traverse_callback_t)(int n, unsigned long mask, struct name_entry *entry, const char *base);
-
-void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback);
+struct traverse_info;
+typedef int (*traverse_callback_t)(int n, unsigned long mask, unsigned long dirmask, struct name_entry *entry, struct traverse_info *);
+int traverse_trees(int n, struct tree_desc *t, struct traverse_info *info);
+
+struct traverse_info {
+	struct traverse_info *prev;
+	struct name_entry name;
+	int pathlen;
+
+	unsigned long conflicts;
+	traverse_callback_t fn;
+	void *data;
+};
 
 int get_tree_entry(const unsigned char *, const char *, unsigned char *, unsigned *);
+extern char *make_traverse_path(char *path, const struct traverse_info *info, const struct name_entry *n);
+extern void setup_traverse_info(struct traverse_info *info, const char *base);
+
+static inline int traverse_path_len(const struct traverse_info *info, const struct name_entry *n)
+{
+	return info->pathlen + tree_entry_len(n->path, n->sha1);
+}
 
 #endif
diff --git a/unpack-trees.c b/unpack-trees.c
index 3e448d8974..be89d52e8c 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1,3 +1,4 @@
+#define NO_THE_INDEX_COMPATIBILITY_MACROS
 #include "cache.h"
 #include "dir.h"
 #include "tree.h"
@@ -7,268 +8,18 @@
 #include "progress.h"
 #include "refs.h"
 
-#define DBRT_DEBUG 1
-
-struct tree_entry_list {
-	struct tree_entry_list *next;
-	unsigned int mode;
-	const char *name;
-	const unsigned char *sha1;
-};
-
-static struct tree_entry_list *create_tree_entry_list(struct tree_desc *desc)
-{
-	struct name_entry one;
-	struct tree_entry_list *ret = NULL;
-	struct tree_entry_list **list_p = &ret;
-
-	while (tree_entry(desc, &one)) {
-		struct tree_entry_list *entry;
-
-		entry = xmalloc(sizeof(struct tree_entry_list));
-		entry->name = one.path;
-		entry->sha1 = one.sha1;
-		entry->mode = one.mode;
-		entry->next = NULL;
-
-		*list_p = entry;
-		list_p = &entry->next;
-	}
-	return ret;
-}
-
-static int entcmp(const char *name1, int dir1, const char *name2, int dir2)
+static void add_entry(struct unpack_trees_options *o, struct cache_entry *ce,
+	unsigned int set, unsigned int clear)
 {
-	int len1 = strlen(name1);
-	int len2 = strlen(name2);
-	int len = len1 < len2 ? len1 : len2;
-	int ret = memcmp(name1, name2, len);
-	unsigned char c1, c2;
-	if (ret)
-		return ret;
-	c1 = name1[len];
-	c2 = name2[len];
-	if (!c1 && dir1)
-		c1 = '/';
-	if (!c2 && dir2)
-		c2 = '/';
-	ret = (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
-	if (c1 && c2 && !ret)
-		ret = len1 - len2;
-	return ret;
-}
-
-static inline void remove_entry(int remove)
-{
-	if (remove >= 0)
-		remove_cache_entry_at(remove);
-}
-
-static int unpack_trees_rec(struct tree_entry_list **posns, int len,
-			    const char *base, struct unpack_trees_options *o,
-			    struct tree_entry_list *df_conflict_list)
-{
-	int remove;
-	int baselen = strlen(base);
-	int src_size = len + 1;
-	int retval = 0;
-
-	do {
-		int i;
-		const char *first;
-		int firstdir = 0;
-		int pathlen;
-		unsigned ce_size;
-		struct tree_entry_list **subposns;
-		struct cache_entry **src;
-		int any_files = 0;
-		int any_dirs = 0;
-		char *cache_name;
-		int ce_stage;
-		int skip_entry = 0;
-
-		/* Find the first name in the input. */
-
-		first = NULL;
-		cache_name = NULL;
-
-		/* Check the cache */
-		if (o->merge && o->pos < active_nr) {
-			/* This is a bit tricky: */
-			/* If the index has a subdirectory (with
-			 * contents) as the first name, it'll get a
-			 * filename like "foo/bar". But that's after
-			 * "foo", so the entry in trees will get
-			 * handled first, at which point we'll go into
-			 * "foo", and deal with "bar" from the index,
-			 * because the base will be "foo/". The only
-			 * way we can actually have "foo/bar" first of
-			 * all the things is if the trees don't
-			 * contain "foo" at all, in which case we'll
-			 * handle "foo/bar" without going into the
-			 * directory, but that's fine (and will return
-			 * an error anyway, with the added unknown
-			 * file case.
-			 */
-
-			cache_name = active_cache[o->pos]->name;
-			if (strlen(cache_name) > baselen &&
-			    !memcmp(cache_name, base, baselen)) {
-				cache_name += baselen;
-				first = cache_name;
-			} else {
-				cache_name = NULL;
-			}
-		}
-
-#if DBRT_DEBUG > 1
-		if (first)
-			fprintf(stderr, "index %s\n", first);
-#endif
-		for (i = 0; i < len; i++) {
-			if (!posns[i] || posns[i] == df_conflict_list)
-				continue;
-#if DBRT_DEBUG > 1
-			fprintf(stderr, "%d %s\n", i + 1, posns[i]->name);
-#endif
-			if (!first || entcmp(first, firstdir,
-					     posns[i]->name,
-					     S_ISDIR(posns[i]->mode)) > 0) {
-				first = posns[i]->name;
-				firstdir = S_ISDIR(posns[i]->mode);
-			}
-		}
-		/* No name means we're done */
-		if (!first)
-			goto leave_directory;
-
-		pathlen = strlen(first);
-		ce_size = cache_entry_size(baselen + pathlen);
-
-		src = xcalloc(src_size, sizeof(struct cache_entry *));
-
-		subposns = xcalloc(len, sizeof(struct tree_list_entry *));
-
-		remove = -1;
-		if (cache_name && !strcmp(cache_name, first)) {
-			any_files = 1;
-			src[0] = active_cache[o->pos];
-			remove = o->pos;
-			if (o->skip_unmerged && ce_stage(src[0]))
-				skip_entry = 1;
-		}
-
-		for (i = 0; i < len; i++) {
-			struct cache_entry *ce;
-
-			if (!posns[i] ||
-			    (posns[i] != df_conflict_list &&
-			     strcmp(first, posns[i]->name))) {
-				continue;
-			}
-
-			if (posns[i] == df_conflict_list) {
-				src[i + o->merge] = o->df_conflict_entry;
-				continue;
-			}
+	unsigned int size = ce_size(ce);
+	struct cache_entry *new = xmalloc(size);
 
-			if (S_ISDIR(posns[i]->mode)) {
-				struct tree *tree = lookup_tree(posns[i]->sha1);
-				struct tree_desc t;
-				any_dirs = 1;
-				parse_tree(tree);
-				init_tree_desc(&t, tree->buffer, tree->size);
-				subposns[i] = create_tree_entry_list(&t);
-				posns[i] = posns[i]->next;
-				src[i + o->merge] = o->df_conflict_entry;
-				continue;
-			}
-
-			if (skip_entry) {
-				subposns[i] = df_conflict_list;
-				posns[i] = posns[i]->next;
-				continue;
-			}
-
-			if (!o->merge)
-				ce_stage = 0;
-			else if (i + 1 < o->head_idx)
-				ce_stage = 1;
-			else if (i + 1 > o->head_idx)
-				ce_stage = 3;
-			else
-				ce_stage = 2;
-
-			ce = xcalloc(1, ce_size);
-			ce->ce_mode = create_ce_mode(posns[i]->mode);
-			ce->ce_flags = create_ce_flags(baselen + pathlen,
-						       ce_stage);
-			memcpy(ce->name, base, baselen);
-			memcpy(ce->name + baselen, first, pathlen + 1);
-
-			any_files = 1;
-
-			hashcpy(ce->sha1, posns[i]->sha1);
-			src[i + o->merge] = ce;
-			subposns[i] = df_conflict_list;