git/revision.c

#include "cache.h"
#include "object-store.h"
#include "tag.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "diff.h"
#include "diff-merges.h"
#include "refs.h"
#include "revision.h"
#include "repository.h"
#include "graph.h"
#include "grep.h"
#include "reflog-walk.h"
#include "patch-ids.h"
#include "decorate.h"
#include "log-tree.h"
#include "string-list.h"
#include "line-log.h"
#include "mailmap.h"
#include "commit-slab.h"
#include "dir.h"
#include "cache-tree.h"
#include "bisect.h"
#include "packfile.h"
#include "worktree.h"
#include "strvec.h"
#include "commit-reach.h"
#include "commit-graph.h"
#include "prio-queue.h"
#include "hashmap.h"
#include "utf8.h"
#include "bloom.h"
#include "json-writer.h"
#include "list-objects-filter-options.h"
#include "resolve-undo.h"

volatile show_early_output_fn_t show_early_output;

static const char *term_bad;
static const char *term_good;

implement_shared_commit_slab(revision_sources, char *);

static inline int want_ancestry(const struct rev_info *revs);

void show_object_with_name(FILE *out, struct object *obj, const char *name)
{
	fprintf(out, "%s ", oid_to_hex(&obj->oid));
	/*
	 * This "for (const char *p = ..." is made as a first step towards
	 * making use of such declarations elsewhere in our codebase.  If
	 * it causes compilation problems on your platform, please report
	 * it to the Git mailing list at git@vger.kernel.org. In the meantime,
	 * adding -std=gnu99 to CFLAGS may help if you are with older GCC.
	 */
	for (const char *p = name; *p && *p != '\n'; p++)
		fputc(*p, out);
	fputc('\n', out);
}

static void mark_blob_uninteresting(struct blob *blob)
{
	if (!blob)
		return;
	if (blob->object.flags & UNINTERESTING)
		return;
	blob->object.flags |= UNINTERESTING;
}

static void mark_tree_contents_uninteresting(struct repository *r,
					     struct tree *tree)
{
	struct tree_desc desc;
	struct name_entry entry;

	if (parse_tree_gently(tree, 1) < 0)
		return;

	init_tree_desc(&desc, tree->buffer, tree->size);
	while (tree_entry(&desc, &entry)) {
		switch (object_type(entry.mode)) {
		case OBJ_TREE:
			mark_tree_uninteresting(r, lookup_tree(r, &entry.oid));
			break;
		case OBJ_BLOB:
			mark_blob_uninteresting(lookup_blob(r, &entry.oid));
			break;
		default:
			/* Subproject commit - not in this repository */
			break;
		}
	}

	/*
	 * We don't care about the tree any more
	 * after it has been marked uninteresting.
	 */
	free_tree_buffer(tree);
}

void mark_tree_uninteresting(struct repository *r, struct tree *tree)
{
	struct object *obj;

	if (!tree)
		return;

	obj = &tree->object;
	if (obj->flags & UNINTERESTING)
		return;
	obj->flags |= UNINTERESTING;
	mark_tree_contents_uninteresting(r, tree);
}

struct path_and_oids_entry {
	struct hashmap_entry ent;
	char *path;
	struct oidset trees;
};

static int path_and_oids_cmp(const void *hashmap_cmp_fn_data,
			     const struct hashmap_entry *eptr,
			     const struct hashmap_entry *entry_or_key,
			     const void *keydata)
{
	const struct path_and_oids_entry *e1, *e2;

	e1 = container_of(eptr, const struct path_and_oids_entry, ent);
	e2 = container_of(entry_or_key, const struct path_and_oids_entry, ent);

	return strcmp(e1->path, e2->path);
}

static void paths_and_oids_clear(struct hashmap *map)
{
	struct hashmap_iter iter;
	struct path_and_oids_entry *entry;

	hashmap_for_each_entry(map, &iter, entry, ent /* member name */) {
		oidset_clear(&entry->trees);
		free(entry->path);
	}

	hashmap_clear_and_free(map, struct path_and_oids_entry, ent);
}

static void paths_and_oids_insert(struct hashmap *map,
				  const char *path,
				  const struct object_id *oid)
{
	int hash = strhash(path);
	struct path_and_oids_entry key;
	struct path_and_oids_entry *entry;

	hashmap_entry_init(&key.ent, hash);

	/* use a shallow copy for the lookup */
	key.path = (char *)path;
	oidset_init(&key.trees, 0);

	entry = hashmap_get_entry(map, &key, ent, NULL);
	if (!entry) {
		CALLOC_ARRAY(entry, 1);
		hashmap_entry_init(&entry->ent, hash);
		entry->path = xstrdup(key.path);
		oidset_init(&entry->trees, 16);
		hashmap_put(map, &entry->ent);
	}

	oidset_insert(&entry->trees, oid);
}

static void add_children_by_path(struct repository *r,
				 struct tree *tree,
				 struct hashmap *map)
{
	struct tree_desc desc;
	struct name_entry entry;

	if (!tree)
		return;

	if (parse_tree_gently(tree, 1) < 0)
		return;

	init_tree_desc(&desc, tree->buffer, tree->size);
	while (tree_entry(&desc, &entry)) {
		switch (object_type(entry.mode)) {
		case OBJ_TREE:
			paths_and_oids_insert(map, entry.path, &entry.oid);

			if (tree->object.flags & UNINTERESTING) {
				struct tree *child = lookup_tree(r, &entry.oid);
				if (child)
					child->object.flags |= UNINTERESTING;
			}
			break;
		case OBJ_BLOB:
			if (tree->object.flags & UNINTERESTING) {
				struct blob *child = lookup_blob(r, &entry.oid);
				if (child)
					child->object.flags |= UNINTERESTING;
			}
			break;
		default:
			/* Subproject commit - not in this repository */
			break;
		}
	}

	free_tree_buffer(tree);
}

void mark_trees_uninteresting_sparse(struct repository *r,
				     struct oidset *trees)
{
	unsigned has_interesting = 0, has_uninteresting = 0;
	struct hashmap map = HASHMAP_INIT(path_and_oids_cmp, NULL);
	struct hashmap_iter map_iter;
	struct path_and_oids_entry *entry;
	struct object_id *oid;
	struct oidset_iter iter;

	oidset_iter_init(trees, &iter);
	while ((!has_interesting || !has_uninteresting) &&
	       (oid = oidset_iter_next(&iter))) {
		struct tree *tree = lookup_tree(r, oid);

		if (!tree)
			continue;

		if (tree->object.flags & UNINTERESTING)
			has_uninteresting = 1;
		else
			has_interesting = 1;
	}

	/* Do not walk unless we have both types of trees. */
	if (!has_uninteresting || !has_interesting)
		return;

	oidset_iter_init(trees, &iter);
	while ((oid = oidset_iter_next(&iter))) {
		struct tree *tree = lookup_tree(r, oid);
		add_children_by_path(r, tree, &map);
	}

	hashmap_for_each_entry(&map, &map_iter, entry, ent /* member name */)
		mark_trees_uninteresting_sparse(r, &entry->trees);

	paths_and_oids_clear(&map);
}

struct commit_stack {
	struct commit **items;
	size_t nr, alloc;
};
#define COMMIT_STACK_INIT { 0 }

static void commit_stack_push(struct commit_stack *stack, struct commit *commit)
{
	ALLOC_GROW(stack->items, stack->nr + 1, stack->alloc);
	stack->items[stack->nr++] = commit;
}

static struct commit *commit_stack_pop(struct commit_stack *stack)
{
	return stack->nr ? stack->items[--stack->nr] : NULL;
}

static void commit_stack_clear(struct commit_stack *stack)
{
	FREE_AND_NULL(stack->items);
	stack->nr = stack->alloc = 0;
}

static void mark_one_parent_uninteresting(struct rev_info *revs, struct commit *commit,
					  struct commit_stack *pending)
{
	struct commit_list *l;

	if (commit->object.flags & UNINTERESTING)
		return;
	commit->object.flags |= UNINTERESTING;

	/*
	 * Normally we haven't parsed the parent
	 * yet, so we won't have a parent of a parent
	 * here. However, it may turn out that we've
	 * reached this commit some other way (where it
	 * wasn't uninteresting), in which case we need
	 * to mark its parents recursively too..
	 */
	for (l = commit->parents; l; l = l->next) {
		commit_stack_push(pending, l->item);
		if (revs && revs->exclude_first_parent_only)
			break;
	}
}

void mark_parents_uninteresting(struct rev_info *revs, struct commit *commit)
{
	struct commit_stack pending = COMMIT_STACK_INIT;
	struct commit_list *l;

	for (l = commit->parents; l; l = l->next) {
		mark_one_parent_uninteresting(revs, l->item, &pending);
		if (revs && revs->exclude_first_parent_only)
			break;
	}

	while (pending.nr > 0)
		mark_one_parent_uninteresting(revs, commit_stack_pop(&pending),
					      &pending);

	commit_stack_clear(&pending);
}

static void add_pending_object_with_path(struct rev_info *revs,
					 struct object *obj,
					 const char *name, unsigned mode,
					 const char *path)
{
	struct interpret_branch_name_options options = { 0 };
	if (!obj)
		return;
	if (revs->no_walk && (obj->flags & UNINTERESTING))
		revs->no_walk = 0;
	if (revs->reflog_info && obj->type == OBJ_COMMIT) {
		struct strbuf buf = STRBUF_INIT;
		size_t namelen = strlen(name);
		int len = interpret_branch_name(name, namelen, &buf, &options);

		if (0 < len && len < namelen && buf.len)
			strbuf_addstr(&buf, name + len);
		add_reflog_for_walk(revs->reflog_info,
				    (struct commit *)obj,
				    buf.buf[0] ? buf.buf: name);
		strbuf_release(&buf);
		return; /* do not add the commit itself */
	}
	add_object_array_with_path(obj, name, &revs->pending, mode, path);
}

static void add_pending_object_with_mode(struct rev_info *revs,
					 struct object *obj,
					 const char *name, unsigned mode)
{
	add_pending_object_with_path(revs, obj, name, mode, NULL);
}

void add_pending_object(struct rev_info *revs,
			struct object *obj, const char *name)
{
	add_pending_object_with_mode(revs, obj, name, S_IFINVALID);
}

void add_head_to_pending(struct rev_info *revs)
{
	struct object_id oid;
	struct object *obj;
	if (get_oid("HEAD", &oid))
		return;
	obj = parse_object(revs->repo, &oid);
	if (!obj)
		return;
	add_pending_object(revs, obj, "HEAD");
}

static struct object *get_reference(struct rev_info *revs, const char *name,
				    const struct object_id *oid,
				    unsigned int flags)
{
	struct object *object;
	struct commit *commit;

	/*
	 * If the repository has commit graphs, we try to opportunistically
	 * look up the object ID in those graphs. Like this, we can avoid
	 * parsing commit data from disk.
	 */
	commit = lookup_commit_in_graph(revs->repo, oid);
	if (commit)
		object = &commit->object;
	else
		object = parse_object(revs->repo, oid);

	if (!object) {
		if (revs->ignore_missing)
			return object;
		if (revs->exclude_promisor_objects && is_promisor_object(oid))
			return NULL;
		die("bad object %s", name);
	}
	object->flags |= flags;
	return object;
}

void add_pending_oid(struct rev_info *revs, const char *name,
		      const struct object_id *oid, unsigned int flags)
{
	struct object *object = get_reference(revs, name, oid, flags);
	add_pending_object(revs, object, name);
}

static struct commit *handle_commit(struct rev_info *revs,
				    struct object_array_entry *entry)
{
	struct object *object = entry->item;
	const char *name = entry->name;
	const char *path = entry->path;
	unsigned int mode = entry->mode;
	unsigned long flags = object->flags;

	/*
	 * Tag object? Look what it points to..
	 */
	while (object->type == OBJ_TAG) {
		struct tag *tag = (struct tag *) object;
		if (revs->tag_objects && !(flags & UNINTERESTING))
			add_pending_object(revs, object, tag->tag);
		object = parse_object(revs->repo, get_tagged_oid(tag));
		if (!object) {
			if (revs->ignore_missing_links || (flags & UNINTERESTING))
				return NULL;
			if (revs->exclude_promisor_objects &&
			    is_promisor_object(&tag->tagged->oid))
				return NULL;
			die("bad object %s", oid_to_hex(&tag->tagged->oid));
		}
		object->flags |= flags;
		/*
		 * We'll handle the tagged object by looping or dropping
		 * through to the non-tag handlers below. Do not
		 * propagate path data from the tag's pending entry.
		 */
		path = NULL;
		mode = 0;
	}

	/*
	 * Commit object? Just return it, we'll do all the complex
	 * reachability crud.
	 */
	if (object->type == OBJ_COMMIT) {
		struct commit *commit = (struct commit *)object;

		if (repo_parse_commit(revs->repo, commit) < 0)
			die("unable to parse commit %s", name);
		if (flags & UNINTERESTING) {
			mark_parents_uninteresting(revs, commit);

			if (!revs->topo_order || !generation_numbers_enabled(the_repository))
				revs->limited = 1;
		}
		if (revs->sources) {
			char **slot = revision_sources_at(revs->sources, commit);

			if (!*slot)
				*slot = xstrdup(name);
		}
		return commit;
	}

	/*
	 * Tree object? Either mark it uninteresting, or add it
	 * to the list of objects to look at later..
	 */
	if (object->type == OBJ_TREE) {
		struct tree *tree = (struct tree *)object;
		if (!revs->tree_objects)
			return NULL;
		if (flags & UNINTERESTING) {
			mark_tree_contents_uninteresting(revs->repo, tree);
			return NULL;
		}
		add_pending_object_with_path(revs, object, name, mode, path);
		return NULL;
	}

	/*
	 * Blob object? You know the drill by now..
	 */
	if (object->type == OBJ_BLOB) {
		if (!revs->blob_objects)
			return NULL;
		if (flags & UNINTERESTING)
			return NULL;
		add_pending_object_with_path(revs, object, name, mode, path);
		return NULL;
	}
	die("%s is unknown object", name);
}

static int everybody_uninteresting(struct commit_list *orig,
				   struct commit **interesting_cache)
{
	struct commit_list *list = orig;

	if (*interesting_cache) {
		struct commit *commit = *interesting_cache;
		if (!(commit->object.flags & UNINTERESTING))
			return 0;
	}

	while (list) {
		struct commit *commit = list->item;
		list = list->next;
		if (commit->object.flags & UNINTERESTING)
			continue;

		*interesting_cache = commit;
		return 0;
	}
	return 1;
}

/*
 * A definition of "relevant" commit that we can use to simplify limited graphs
 * by eliminating side branches.
 *
 * A "relevant" commit is one that is !UNINTERESTING (ie we are including it
 * in our list), or that is a specified BOTTOM commit. Then after computing
 * a limited list, during processing we can generally ignore boundary merges
 * coming from outside the graph, (ie from irrelevant parents), and treat
 * those merges as if they were single-parent. TREESAME is defined to consider
 * only relevant parents, if any. If we are TREESAME to our on-graph parents,
 * we don't care if we were !TREESAME to non-graph parents.
 *
 * Treating bottom commits as relevant ensures that a limited graph's
 * connection to the actual bottom commit is not viewed as a side branch, but
 * treated as part of the graph. For example:
 *
 *   ....Z...A---X---o---o---B
 *        .     /
 *         W---Y
 *
 * When computing "A..B", the A-X connection is at least as important as
 * Y-X, despite A being flagged UNINTERESTING.
 *
 * And when computing --ancestry-path "A..B", the A-X connection is more
 * important than Y-X, despite both A and Y being flagged UNINTERESTING.
 */
static inline int relevant_commit(struct commit *commit)
{
	return (commit->object.flags & (UNINTERESTING | BOTTOM)) != UNINTERESTING;
}

/*
 * Return a single relevant commit from a parent list. If we are a TREESAME
 * commit, and this selects one of our parents, then we can safely simplify to
 * that parent.
 */
static struct commit *one_relevant_parent(const struct rev_info *revs,
					  struct commit_list *orig)
{
	struct commit_list *list = orig;
	struct commit *relevant = NULL;

	if (!orig)
		return NULL;

	/*
	 * For 1-parent commits, or if first-parent-only, then return that
	 * first parent (even if not "relevant" by the above definition).
	 * TREESAME will have been set purely on that parent.
	 */
	if (revs->first_parent_only || !orig->next)
		return orig->item;

	/*
	 * For multi-parent commits, identify a sole relevant parent, if any.
	 * If we have only one relevant parent, then TREESAME will be set purely
	 * with regard to that parent, and we can simplify accordingly.
	 *
	 * If we have more than one relevant parent, or no relevant parents
	 * (and multiple irrelevant ones), then we can't select a parent here
	 * and return NULL.
	 */
	while (list) {
		struct commit *commit = list->item;
		list = list->next;
		if (relevant_commit(commit)) {
			if (relevant)
				return NULL;
			relevant = commit;
		}
	}
	return relevant;
}

/*
 * The goal is to get REV_TREE_NEW as the result only if the
 * diff consists of all '+' (and no other changes), REV_TREE_OLD
 * if the whole diff is removal of old data, and otherwise
 * REV_TREE_DIFFERENT (of course if the trees are the same we
 * want REV_TREE_SAME).
 *
 * The only time we care about the distinction is when
 * remove_empty_trees is in effect, in which case we care only about
 * whether the whole change is REV_TREE_NEW, or if there's another type
 * of change. Which means we can stop the diff early in either of these
 * cases:
 *
 *   1. We're not using remove_empty_trees at all.
 *
 *   2. We saw anything except REV_TREE_NEW.
 */
#define REV_TREE_SAME		0
#define REV_TREE_NEW		1	/* Only new files */
#define REV_TREE_OLD		2	/* Only files removed */
#define REV_TREE_DIFFERENT	3	/* Mixed changes */
static int tree_difference = REV_TREE_SAME;

static void file_add_remove(struct diff_options *options,
		    int addremove, unsigned mode,
		    const struct object_id *oid,
		    int oid_valid,
		    const char *fullpath, unsigned dirty_submodule)
{
	int diff = addremove == '+' ? REV_TREE_NEW : REV_TREE_OLD;
	struct rev_info *revs = options->change_fn_data;

	tree_difference |= diff;
	if (!revs->remove_empty_trees || tree_difference != REV_TREE_NEW)
		options->flags.has_changes = 1;
}

static void file_change(struct diff_options *options,
		 unsigned old_mode, unsigned new_mode,
		 const struct object_id *old_oid,
		 const struct object_id *new_oid,
		 int old_oid_valid, int new_oid_valid,
		 const char *fullpath,
		 unsigned old_dirty_submodule, unsigned new_dirty_submodule)
{
	tree_difference = REV_TREE_DIFFERENT;
	options->flags.has_changes = 1;
}

static int bloom_filter_atexit_registered;
static unsigned int count_bloom_filter_maybe;
static unsigned int count_bloom_filter_definitely_not;
static unsigned int count_bloom_filter_false_positive;
static unsigned int count_bloom_filter_not_present;

static void trace2_bloom_filter_statistics_atexit(void)
{
	struct json_writer jw = JSON_WRITER_INIT;

	jw_object_begin(&jw, 0);
	jw_object_intmax(&jw, "filter_not_present", count_bloom_filter_not_present);
	jw_object_intmax(&jw, "maybe", count_bloom_filter_maybe);
	jw_object_intmax(&jw, "definitely_not", count_bloom_filter_definitely_not);
	jw_object_intmax(&jw, "false_positive", count_bloom_filter_false_positive);
	jw_end(&jw);

	trace2_data_json("bloom", the_repository, "statistics", &jw);

	jw_release(&jw);
}

static int forbid_bloom_filters(struct pathspec *spec)
{
	if (spec->has_wildcard)
		return 1;
	if (spec->nr > 1)
		return 1;
	if (spec->magic & ~PATHSPEC_LITERAL)
		return 1;
	if (spec->nr && (spec->items[0].magic & ~PATHSPEC_LITERAL))
		return 1;

	return 0;
}

static void prepare_to_use_bloom_filter(struct rev_info *revs)
{
	struct pathspec_item *pi;
	char *path_alloc = NULL;
	const char *path, *p;
	size_t len;
	int path_component_nr = 1;

	if (!revs->commits)
		return;

	if (forbid_bloom_filters(&revs->prune_data))
		return;

	repo_parse_commit(revs->repo, revs->commits->item);

	revs->bloom_filter_settings = get_bloom_filter_settings(revs->repo);
	if (!revs->bloom_filter_settings)
		return;

	if (!revs->pruning.pathspec.nr)
		return;

	pi = &revs->pruning.pathspec.items[0];

	/* remove single trailing slash from path, if needed */
	if (pi->len > 0 && pi->match[pi->len - 1] == '/') {
		path_alloc = xmemdupz(pi->match, pi->len - 1);
		path = path_alloc;
	} else
		path = pi->match;

	len = strlen(path);
	if (!len) {
		revs->bloom_filter_settings = NULL;
		free(path_alloc);
		return;
	}

	p = path;
	while (*p) {
		/*
		 * At this point, the path is normalized to use Unix-style
		 * path separators. This is required due to how the
		 * changed-path Bloom filters store the paths.
		 */
		if (*p == '/')
			path_component_nr++;
		p++;
	}

	revs->bloom_keys_nr = path_component_nr;
	ALLOC_ARRAY(revs->bloom_keys, revs->bloom_keys_nr);

	fill_bloom_key(path, len, &revs->bloom_keys[0],
		       revs->bloom_filter_settings);
	path_component_nr = 1;

	p = path + len - 1;
	while (p > path) {
		if (*p == '/')
			fill_bloom_key(path, p - path,
				       &revs->bloom_keys[path_component_nr++],
				       revs->bloom_filter_settings);
		p--;
	}

	if (trace2_is_enabled() && !bloom_filter_atexit_registered) {
		atexit(trace2_bloom_filter_statistics_atexit);
		bloom_filter_atexit_registered = 1;
	}

	free(path_alloc);
}

static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
						 struct commit *commit)
{
	struct bloom_filter *filter;
	int result = 1, j;

	if (!revs->repo->objects->commit_graph)
		return -1;

	if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
		return -1;

	filter = get_bloom_filter(revs->repo, commit);

	if (!filter) {
		count_bloom_filter_not_present++;
		return -1;
	}

	for (j = 0; result && j < revs->bloom_keys_nr; j++) {
		result = bloom_filter_contains(filter,
					       &revs->bloom_keys[j],
					       revs->bloom_filter_settings);
	}

	if (result)
		count_bloom_filter_maybe++;
	else
		count_bloom_filter_definitely_not++;

	return result;
}

static int rev_compare_tree(struct rev_info *revs,
			    struct commit *parent, struct commit *commit, int nth_parent)
{
	struct tree *t1 = get_commit_tree(parent);
	struct tree *t2 = get_commit_tree(commit);
	int bloom_ret = 1;

	if (!t1)
		return REV_TREE_NEW;
	if (!t2)
		return REV_TREE_OLD;

	if (revs->simplify_by_decoration) {
		/*
		 * If we are simplifying by decoration, then the commit
		 * is worth showing if it has a tag pointing at it.
		 */
		if (get_name_decoration(&commit->object))
			return REV_TREE_DIFFERENT;
		/*
		 * A commit that is not pointed by a tag is uninteresting
		 * if we are not limited by path.  This means that you will
		 * see the usual "commits that touch the paths" plus any
		 * tagged commit by specifying both --simplify-by-decoration
		 * and pathspec.
		 */
		if (!revs->prune_data.nr)
			return REV_TREE_SAME;
	}

	if (revs->bloom_keys_nr && !nth_parent) {
		bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);

		if (bloom_ret == 0)
			return REV_TREE_SAME;
	}

	tree_difference = REV_TREE_SAME;
	revs->pruning.flags.has_changes = 0;
	diff_tree_oid(&t1->object.oid, &t2->object.oid, "", &revs->pruning);

	if (!nth_parent)
		if (bloom_ret == 1 && tree_difference == REV_TREE_SAME)
			count_bloom_filter_false_positive++;

	return tree_difference;
}

static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit)
{
	struct tree *t1 = get_commit_tree(commit);

	if (!t1)
		return 0;

	tree_difference = REV_TREE_SAME;
	revs->pruning.flags.has_changes = 0;
	diff_tree_oid(NULL, &t1->object.oid, "", &revs->pruning);

	return tree_difference == REV_TREE_SAME;
}

struct treesame_state {
	unsigned int nparents;
	unsigned char treesame[FLEX_ARRAY];
};

static struct treesame_state *initialise_treesame(struct rev_info *revs, struct commit *commit)
{
	unsigned n = commit_list_count(commit->parents);
	struct treesame_state *st = xcalloc(1, st_add(sizeof(*st), n));
	st->nparents = n;
	add_decoration(&revs->treesame, &commit->object, st);
	return st;
}

/*
 * Must be called immediately after removing the nth_parent from a commit's
 * parent list, if we are maintaining the per-parent treesame[] decoration.
 * This does not recalculate the master TREESAME flag - update_treesame()
 * should be called to update it after a sequence of treesame[] modifications
 * that may have affected it.
 */
static int compact_treesame(struct rev_info *revs, struct commit *commit, unsigned nth_parent)
{
	struct treesame_state *st;
	int old_same;

	if (!commit->parents) {
		/*
		 * Have just removed the only parent from a non-merge.
		 * Different handling, as we lack decoration.
		 */
		if (nth_parent != 0)
			die("compact_treesame %u", nth_parent);
		old_same = !!(commit->object.flags & TREESAME);
		if (rev_same_tree_as_empty(revs, commit))
			commit->object.flags |= TREESAME;
		else
			commit->object.flags &= ~TREESAME;
		return old_same;
	}

	st = lookup_decoration(&revs->treesame, &commit->object);
	if (!st || nth_parent >= st->nparents)
		die("compact_treesame %u", nth_parent);

	old_same = st->treesame[nth_parent];
	memmove(st->treesame + nth_parent,
		st->treesame + nth_parent + 1,
		st->nparents - nth_parent - 1);

	/*
	 * If we've just become a non-merge commit, update TREESAME
	 * immediately, and remove the no-longer-needed decoration.
	 * If still a merge, defer update until update_treesame().
	 */
	if (--st->nparents == 1) {
		if (commit->parents->next)
			die("compact_treesame parents mismatch");
		if (st->treesame[0] && revs->dense)
			commit->object.flags |= TREESAME;
		else
			commit->object.flags &= ~TREESAME;
		free(add_decoration(&revs->treesame, &commit->object, NULL));
	}

	return old_same;
}

static unsigned update_treesame(struct rev_info *revs, struct commit *commit)
{
	if (commit->parents && commit->parents->next) {
		unsigned n;
		struct treesame_state *st;
		struct commit_list *p;
		unsigned relevant_parents;
		unsigned relevant_change, irrelevant_change;

		st = lookup_decoration(&revs->treesame, &commit->object);
		if (!st)
			die("update_treesame %s", oid_to_hex(&commit->object.oid));
		relevant_parents = 0;
		relevant_change = irrelevant_change = 0;
		for (p = commit->parents, n = 0; p; n++, p = p->next) {
			if (relevant_commit(p->item)) {
				relevant_change |= !st->treesame[n];
				relevant_parents++;
			} else
				irrelevant_change |= !st->treesame[n];
		}
		if (relevant_parents ? relevant_change : irrelevant_change)
			commit->object.flags &= ~TREESAME;
		else
			commit->object.flags |= TREESAME;
	}

	return commit->object.flags & TREESAME;
}

static inline int limiting_can_increase_treesame(const struct rev_info *revs)
{
	/*
	 * TREESAME is irrelevant unless prune && dense;
	 * if simplify_history is set, we can't have a mixture of TREESAME and
	 *    !TREESAME INTERESTING parents (and we don't have treesame[]
	 *    decoration anyway);
	 * if first_parent_only is set, then the TREESAME flag is locked
	 *    against the first parent (and again we lack treesame[] decoration).
	 */
	return revs->prune && revs->dense &&
	       !revs->simplify_history &&
	       !revs->first_parent_only;
}

static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
{
	struct commit_list **pp, *parent;
	struct treesame_state *ts = NULL;
	int relevant_change = 0, irrelevant_change = 0;
	int relevant_parents, nth_parent;

	/*
	 * If we don't do pruning, everything is interesting
	 */
	if (!revs->prune)
		return;

	if (!get_commit_tree(commit))
		return;

	if (!commit->parents) {
		if (rev_same_tree_as_empty(revs, commit))
			commit->object.flags |= TREESAME;
		return;
	}

	/*
	 * Normal non-merge commit? If we don't want to make the
	 * history dense, we consider it always to be a change..
	 */
	if (!revs->dense && !commit->parents->next)
		return;

	for (pp = &commit->parents, nth_parent = 0, relevant_parents = 0;
	     (parent = *pp) != NULL;
	     pp = &parent->next, nth_parent++) {
		struct commit *p = parent->item;
		if (relevant_commit(p))
			relevant_parents++;

		if (nth_parent == 1) {
			/*
			 * This our second loop iteration - so we now know
			 * we're dealing with a merge.
			 *
			 * Do not compare with later parents when we care only about
			 * the first parent chain, in order to avoid derailing the
			 * traversal to follow a side branch that brought everything
			 * in the path we are limited to by the pathspec.
			 */
			if (revs->first_parent_only)
				break;
			/*
			 * If this will remain a potentially-simplifiable
			 * merge, remember per-parent treesame if needed.
			 * Initialise the array with the comparison from our
			 * first iteration.
			 */
			if (revs->treesame.name &&
			    !revs->simplify_history &&
			    !(commit->object.flags & UNINTERESTING)) {
				ts = initialise_treesame(revs, commit);
				if (!(irrelevant_change || relevant_change))
					ts->treesame[0] = 1;
			}
		}
		if (repo_parse_commit(revs->repo, p) < 0)
			die("cannot simplify commit %s (because of %s)",
			    oid_to_hex(&commit->object.oid),
			    oid_to_hex(&p->object.oid));
		switch (rev_compare_tree(revs, p, commit, nth_parent)) {
		case REV_TREE_SAME:
			if (!revs->simplify_history || !relevant_commit(p)) {
				/* Even if a merge with an uninteresting
				 * side branch brought the entire change
				 * we are interested in, we do not want
				 * to lose the other branches of this
				 * merge, so we just keep going.
				 */
				if (ts)
					ts->treesame[nth_parent] = 1;
				continue;
			}
			parent->next = NULL;
			commit->parents = parent;

			/*
			 * A merge commit is a "diversion" if it is not
			 * TREESAME to its first parent but is TREESAME
			 * to a later parent. In the simplified history,
			 * we "divert" the history walk to the later
			 * parent. These commits are shown when "show_pulls"
			 * is enabled, so do not mark the object as
			 * TREESAME here.
			 */
			if (!revs->show_pulls || !nth_parent)
				commit->object.flags |= TREESAME;

			return;

		case REV_TREE_NEW:
			if (revs->remove_empty_trees &&
			    rev_same_tree_as_empty(revs, p)) {
				/* We are adding all the specified
				 * paths from this parent, so the
				 * history beyond this parent is not
				 * interesting.  Remove its parents
				 * (they are grandparents for us).
				 * IOW, we pretend this parent is a
				 * "root" commit.
				 */
				if (repo_parse_commit(revs->repo, p) < 0)
					die("cannot simplify commit %s (invalid %s)",
					    oid_to_hex(&commit->object.oid),
					    oid_to_hex(&p->object.oid));
				p->parents = NULL;
			}
		/* fallthrough */
		case REV_TREE_OLD:
		case REV_TREE_DIFFERENT:
			if (relevant_commit(p))
				relevant_change = 1;
			else
				irrelevant_change = 1;

			if (!nth_parent)
				commit->object.flags |= PULL_MERGE;

			continue;
		}
		die("bad tree compare for commit %s", oid_to_hex(&commit->object.oid));
	}

	/*
	 * TREESAME is straightforward for single-parent commits. For merge
	 * commits, it is most useful to define it so that "irrelevant"
	 * parents cannot make us !TREESAME - if we have any relevant
	 * parents, then we only consider TREESAMEness with respect to them,
	 * allowing irrelevant merges from uninteresting branches to be
	 * simplified away. Only if we have only irrelevant parents do we
	 * base TREESAME on them. Note that this logic is replicated in
	 * update_treesame, which should be kept in sync.
	 */
	if (relevant_parents ? !relevant_change : !irrelevant_change)
		commit->object.flags |= TREESAME;
}

static int process_parents(struct rev_info *revs, struct commit *commit,
			   struct commit_list **list, struct prio_queue *queue)
{
	struct commit_list *parent = commit->parents;
	unsigned left_flag;

	if (commit->object.flags & ADDED)
		return 0;
	commit->object.flags |= ADDED;

	if (revs->include_check &&
	    !revs->include_check(commit, revs->include_check_data))
		return 0;

	/*
	 * If the commit is uninteresting, don't try to
	 * prune parents - we want the maximal uninteresting
	 * set.
	 *
	 * Normally we haven't parsed the parent
	 * yet, so we won't have a parent of a parent
	 * here. However, it may turn out that we've
	 * reached this commit some other way (where it
	 * wasn't uninteresting), in which case we need
	 * to mark its parents recursively too..
	 */
	if (commit->object.flags & UNINTERESTING) {
		while (parent) {
			struct commit *p = parent->item;
			parent = parent->next;
			if (p)
				p->object.flags |= UNINTERESTING;
			if (repo_parse_commit_gently(revs->repo, p, 1) < 0)
				continue;
			if (p->parents)
				mark_parents_uninteresting(revs, p);
			if (p->object.flags & SEEN)
				continue;
			p->object.flags |= (SEEN | NOT_USER_GIVEN);
			if (list)
				commit_list_insert_by_date(p, list);
			if (queue)
				prio_queue_put(queue, p);
			if (revs->exclude_first_parent_only)
				break;
		}
		return 0;
	}

	/*
	 * Ok, the commit wasn't uninteresting. Try to
	 * simplify the commit history and find the parent
	 * that has no differences in the path set if one exists.
	 */
	try_to_simplify_commit(revs, commit);

	if (revs->no_walk)
		return 0;

	left_flag = (commit->object.flags & SYMMETRIC_LEFT);

	for (parent = commit->parents; parent; parent = parent->next) {
		struct commit *p = parent->item;
		int gently = revs->ignore_missing_links ||
			     revs->exclude_promisor_objects;
		if (repo_parse_commit_gently(revs->repo, p, gently) < 0) {
			if (revs->exclude_promisor_objects &&
			    is_promisor_object(&p->object.oid)) {
				if (revs->first_parent_only)
					break;
				continue;
			}
			return -1;
		}
		if (revs->sources) {
			char **slot = revision_sources_at(revs->sources, p);

			if (!*slot)
				*slot = *revision_sources_at(revs->sources, commit);
		}
		p->object.flags |= left_flag;
		if (!(p->object.flags & SEEN)) {
			p->object.flags |= (SEEN | NOT_USER_GIVEN);
			if (list)
				commit_list_insert_by_date(p, list);
			if (queue)
				prio_queue_put(queue, p);
		}
		if (revs->first_parent_only)
			break;
	}
	return 0;
}

static void cherry_pick_list(struct commit_list *list, struct rev_info *revs)
{
	struct commit_list *p;
	int left_count = 0, right_count = 0;
	int left_first;
	struct patch_ids ids;
	unsigned cherry_flag;

	/* First count the commits on the left and on the right */
	for (p = list; p; p = p->next) {
		struct commit *commit = p->item;
		unsigned flags = commit->object.flags;
		if (flags & BOUNDARY)
			;
		else if (flags & SYMMETRIC_LEFT)
			left_count++;
		else
			right_count++;
	}

	if (!left_count || !right_count)
		return;

	left_first = left_count < right_count;
	init_patch_ids(revs->repo, &ids);
	ids.diffopts.pathspec = revs->diffopt.pathspec;

	/* Compute patch-ids for one side */
	for (p = list; p; p = p->next) {
		struct commit *commit = p->item;
		unsigned flags = commit->object.flags;

		if (flags & BOUNDARY)
			continue;
		/*
		 * If we have fewer left, left_first is set and we omit
		 * commits on the right branch in this loop.  If we have
		 * fewer right, we skip the left ones.
		 */
		if (left_first != !!(flags & SYMMETRIC_LEFT))
			continue;
		add_commit_patch_id(commit, &ids);
	}

	/* either cherry_mark or cherry_pick are true */
	cherry_flag = revs->cherry_mark ? PATCHSAME : SHOWN;

	/* Check the other side */
	for (p = list; p; p = p->next) {
		struct commit *commit = p->item;
		struct patch_id *id;
		unsigned flags = commit->object.flags;

		if (flags & BOUNDARY)
			continue;
		/*
		 * If we have fewer left, left_first is set and we omit
		 * commits on the left branch in this loop.
		 */
		if (left_first == !!(flags & SYMMETRIC_LEFT))
			continue;

		/*
		 * Have we seen the same patch id?
		 */
		id = patch_id_iter_first(commit, &ids);
		if (!id)
			continue;

		commit->object.flags |= cherry_flag;
		do {
			id->commit->object.flags |= cherry_flag;
		} while ((id = patch_id_iter_next(id, &ids)));
	}

	free_patch_ids(&ids);
}

/* How many extra uninteresting commits we want to see.. */
#define SLOP 5

static int still_interesting(struct commit_list *src, timestamp_t date, int slop,
			     struct commit **interesting_cache)
{
	/*
	 * No source list at all? We're definitely done..
	 */
	if (!src)
		return 0;

	/*
	 * Does the destination list contain entries with a date
	 * before the source list? Definitely _not_ done.
	 */
	if (date <= src->item->date)
		return SLOP;

	/*
	 * Does the source list still have interesting commits in
	 * it? Definitely not done..
	 */
	if (!everybody_uninteresting(src, interesting_cache))
		return SLOP;

	/* Ok, we're closing in.. */
	return slop-1;
}

/*
 * "rev-list --ancestry-path A..B" computes commits that are ancestors
 * of B but not ancestors of A but further limits the result to those
 * that are descendants of A.  This takes the list of bottom commits and
 * the result of "A..B" without --ancestry-path, and limits the latter
 * further to the ones that can reach one of the commits in "bottom".
 */
static void limit_to_ancestry(struct commit_list *bottom, struct commit_list *list)
{
	struct commit_list *p;
	struct commit_list *rlist = NULL;
	int made_progress;

	/*
	 * Reverse the list so that it will be likely that we would
	 * process parents before children.
	 */
	for (p = list; p; p = p->next)
		commit_list_insert(p->item, &rlist);

	for (p = bottom; p; p = p->next)
		p->item->object.flags |= TMP_MARK;

	/*
	 * Mark the ones that can reach bottom commits in "list",
	 * in a bottom-up fashion.
	 */
	do {
		made_progress = 0;
		for (p = rlist; p; p = p->next) {
			struct commit *c = p->item;
			struct commit_list *parents;
			if (c->object.flags & (TMP_MARK | UNINTERESTING))
				continue;
			for (parents = c->parents;
			     parents;
			     parents = parents->next) {
				if (!(parents->item->object.flags & TMP_MARK))
					continue;
				c->object.flags |= TMP_MARK;
				made_progress = 1;
				break;
			}
		}
	} while (made_progress);

	/*
	 * NEEDSWORK: decide if we want to remove parents that are
	 * not marked with TMP_MARK from commit->parents for commits
	 * in the resulting list.  We may not want to do that, though.
	 */

	/*
	 * The ones that are not marked with TMP_MARK are uninteresting
	 */
	for (p = list; p; p = p->next) {
		struct commit *c = p->item;
		if (c->object.flags & TMP_MARK)
			continue;
		c->object.flags |= UNINTERESTING;
	}

	/* We are done with the TMP_MARK */
	for (p = list; p; p = p->next)
		p->item->object.flags &= ~TMP_MARK;
	for (p = bottom; p; p = p->next)
		p->item->object.flags &= ~TMP_MARK;
	free_commit_list(rlist);
}

/*
 * Before walking the history, keep the set of "negative" refs the
 * caller has asked to exclude.
 *
 * This is used to compute "rev-list --ancestry-path A..B", as we need
 * to filter the result of "A..B" further to the ones that can actually
 * reach A.
 */
static struct commit_list *collect_bottom_commits(struct commit_list *list)
{
	struct commit_list *elem, *bottom = NULL;
	for (elem = list; elem; elem = elem->next)
		if (elem->item->object.flags & BOTTOM)
			commit_list_insert(elem->item, &bottom);
	return bottom;
}

/* Assumes either left_only or right_only is set */
static void limit_left_right(struct commit_list *list, struct rev_info *revs)
{
	struct commit_list *p;

	for (p = list; p; p = p->next) {
		struct commit *commit = p->item;

		if (revs->right_only) {
			if (commit->object.flags & SYMMETRIC_LEFT)
				commit->object.flags |= SHOWN;
		} else	/* revs->left_only is set */
			if (!(commit->object.flags & SYMMETRIC_LEFT))
				commit->object.flags |= SHOWN;
	}
}

static int limit_list(struct rev_info *revs)
{
	int slop = SLOP;
	timestamp_t date = TIME_MAX;
	struct commit_list *original_list = revs->commits;
	struct commit_list *newlist = NULL;
	struct commit_list **p = &newlist;
	struct commit_list *bottom = NULL;
	struct commit *interesting_cache = NULL;

	if (revs->ancestry_path) {
		bottom = collect_bottom_commits(original_list);
		if (!bottom)
			die("--ancestry-path given but there are no bottom commits");
	}

	while (original_list) {
		struct commit *commit = pop_commit(&original_list);
		struct object *obj = &commit->object;
		show_early_output_fn_t show;

		if (commit == interesting_cache)
			interesting_cache = NULL;

		if (revs->max_age != -1 && (commit->date < revs->max_age))
			obj->flags |= UNINTERESTING;
		if (process_parents(revs, commit, &original_list, NULL) < 0)
			return -1;
		if (obj->flags & UNINTERESTING) {
			mark_parents_uninteresting(revs, commit);
			slop = still_interesting(original_list, date, slop, &interesting_cache);
			if (slop)
				continue;
			break;
		}
		if (revs->min_age != -1 && (commit->date > revs->min_age) &&
		    !revs->line_level_traverse)
			continue;
		if (revs->max_age_as_filter != -1 &&
			(commit->date < revs->max_age_as_filter) && !revs->line_level_traverse)
			continue;
		date = commit->date;
		p = &commit_list_insert(commit, p)->next;

		show = show_early_output;
		if (!show)
			continue;

		show(revs, newlist);
		show_early_output = NULL;
	}
	if (revs->cherry_pick || revs->cherry_mark)
		cherry_pick_list(newlist, revs);

	if (revs->left_only || revs->right_only)
		limit_left_right(newlist, revs);

	if (bottom)
		limit_to_ancestry(bottom, newlist);
	free_commit_list(bottom);

	/*
	 * Check if any commits have become TREESAME by some of their parents
	 * becoming UNINTERESTING.
	 */
	if (limiting_can_increase_treesame(revs)) {
		struct commit_list *list = NULL;
		for (list = newlist; list; list = list->next) {
			struct commit *c = list->item;
			if (c->object.flags & (UNINTERESTING | TREESAME))
				continue;
			update_treesame(revs, c);
		}
	}

	free_commit_list(original_list);
	revs->commits = newlist;
	return 0;
}

/*
 * Add an entry to refs->cmdline with the specified information.
 * *name is copied.
 */
static void add_rev_cmdline(struct rev_info *revs,
			    struct object *item,
			    const char *name,
			    int whence,
			    unsigned flags)
{
	struct rev_cmdline_info *info = &revs->cmdline;
	unsigned int nr = info->nr;

	ALLOC_GROW(info->rev, nr + 1, info->alloc);
	info->rev[nr].item = item;
	info->rev[nr].name = xstrdup(name);
	info->rev[nr].whence = whence;
	info->rev[nr].flags = flags;
	info->nr++;
}

static void add_rev_cmdline_list(struct rev_info *revs,
				 struct commit_list *commit_list,
				 int whence,
				 unsigned flags)
{
	while (commit_list) {
		struct object *object = &commit_list->item->object;
		add_rev_cmdline(revs, object, oid_to_hex(&object->oid),
				whence, flags);
		commit_list = commit_list->next;
	}
}

struct all_refs_cb {
	int all_flags;
	int warned_bad_reflog;
	struct rev_info *all_revs;
	const char *name_for_errormsg;
	struct worktree *wt;
};

int ref_excluded(struct string_list *ref_excludes, const char *path)
{
	struct string_list_item *item;

	if (!ref_excludes)
		return 0;
	for_each_string_list_item(item, ref_excludes) {
		if (!wildmatch(item->string, path, 0))
			return 1;
	}
	return 0;
}

static int handle_one_ref(const char *path, const struct object_id *oid,
			  int flag, void *cb_data)
{
	struct all_refs_cb *cb = cb_data;
	struct object *object;

	if (ref_excluded(cb->all_revs->ref_excludes, path))
	    return 0;

	object = get_reference(cb->all_revs, path, oid, cb->all_flags);
	add_rev_cmdline(cb->all_revs, object, path, REV_CMD_REF, cb->all_flags);
	add_pending_object(cb->all_revs, object, path);
	return 0;
}

static void init_all_refs_cb(struct all_refs_cb *cb, struct rev_info *revs,
	unsigned flags)
{
	cb->all_revs = revs;
	cb->all_flags = flags;
	revs->rev_input_given = 1;
	cb->wt = NULL;
}

void clear_ref_exclusion(struct string_list **ref_excludes_p)
{
	if (*ref_excludes_p) {
		string_list_clear(*ref_excludes_p, 0);
		free(*ref_excludes_p);
	}
	*ref_excludes_p = NULL;
}

void add_ref_exclusion(struct string_list **ref_excludes_p, const char *exclude)
{
	if (!*ref_excludes_p) {
		CALLOC_ARRAY(*ref_excludes_p, 1);
		(*ref_excludes_p)->strdup_strings = 1;
	}
	string_list_append(*ref_excludes_p, exclude);
}

static void handle_refs(struct ref_store *refs,
			struct rev_info *revs, unsigned flags,
			int (*for_each)(struct ref_store *, each_ref_fn, void *))
{
	struct all_refs_cb cb;

	if (!refs) {
		/* this could happen with uninitialized submodules */
		return;
	}

	init_all_refs_cb(&cb, revs, flags);
	for_each(refs, handle_one_ref, &cb);
}

static void handle_one_reflog_commit(struct object_id *oid, void *cb_data)
{
	struct all_refs_cb *cb = cb_data;
	if (!is_null_oid(oid)) {
		struct object *o = parse_object(cb->all_revs->repo, oid);
		if (o) {
			o->flags |= cb->all_flags;
			/* ??? CMDLINEFLAGS ??? */
			add_pending_object(cb->all_revs, o, "");
		}
		else if (!cb->warned_bad_reflog) {
			warning("reflog of '%s' references pruned commits",
				cb->name_for_errormsg);
			cb->warned_bad_reflog = 1;
		}
	}
}

static int handle_one_reflog_ent(struct object_id *ooid, struct object_id *noid,
		const char *email, timestamp_t timestamp, int tz,
		const char *message, void *cb_data)
{
	handle_one_reflog_commit(ooid, cb_data);
	handle_one_reflog_commit(noid, cb_data);
	return 0;
}

static int handle_one_reflog(const char *refname_in_wt,
			     const struct object_id *oid,
			     int flag, void *cb_data)
{
	struct all_refs_cb *cb = cb_data;
	struct strbuf refname = STRBUF_INIT;

	cb->warned_bad_reflog = 0;
	strbuf_worktree_ref(cb->wt, &refname, refname_in_wt);
	cb->name_for_errormsg = refname.buf;
	refs_for_each_reflog_ent(get_main_ref_store(the_repository),
				 refname.buf,
				 handle_one_reflog_ent, cb_data);
	strbuf_release(&refname);
	return 0;
}

static void add_other_reflogs_to_pending(struct all_refs_cb *cb)
{
	struct worktree **worktrees, **p;

	worktrees = get_worktrees();
	for (p = worktrees; *p; p++) {
		struct worktree *wt = *p;

		if (wt->is_current)
			continue;

		cb->wt = wt;
		refs_for_each_reflog(get_worktree_ref_store(wt),
				     handle_one_reflog,
				     cb);
	}
	free_worktrees(worktrees);
}

void add_reflogs_to_pending(struct rev_info *revs, unsigned flags)
{
	struct all_refs_cb cb;

	cb.all_revs = revs;
	cb.all_flags = flags;
	cb.wt = NULL;
	for_each_reflog(handle_one_reflog, &cb);

	if (!revs->single_worktree)
		add_other_reflogs_to_pending(&cb);
}

static void add_cache_tree(struct cache_tree *it, struct rev_info *revs,
			   struct strbuf *path, unsigned int flags)
{
	size_t baselen = path->len;
	int i;

	if (it->entry_count >= 0) {
		struct tree *tree = lookup_tree(revs->repo, &it->oid);
		tree->object.flags |= flags;
		add_pending_object_with_path(revs, &tree->object, "",
					     040000, path->buf);
	}

	for (i = 0; i < it->subtree_nr; i++) {
		struct cache_tree_sub *sub = it->down[i];
		strbuf_addf(path, "%s%s", baselen ? "/" : "", sub->name);
		add_cache_tree(sub->cache_tree, revs, path, flags);
		strbuf_setlen(path, baselen);
	}

}

static void add_resolve_undo_to_pending(struct index_state *istate, struct rev_info *revs)
{
	struct string_list_item *item;
	struct string_list *resolve_undo = istate->resolve_undo;

	if (!resolve_undo)
		return;

	for_each_string_list_item(item, resolve_undo) {
		const char *path = item->string;
		struct resolve_undo_info *ru = item->util;
		int i;

		if (!ru)
			continue;
		for (i = 0; i < 3; i++) {
			struct blob *blob;

			if (!ru->mode[i] || !S_ISREG(ru->mode[i]))
				continue;

			blob = lookup_blob(revs->repo, &ru->oid[i]);
			if (!blob) {
				warning(_("resolve-undo records `%s` which is missing"),
					oid_to_hex(&ru->oid[i]));
				continue;
			}
			add_pending_object_with_path(revs, &blob->object, "",
						     ru->mode[i], path);
		}
	}
}

static void do_add_index_objects_to_pending(struct rev_info *revs,
					    struct index_state *istate,
					    unsigned int flags)
{
	int i;

	/* TODO: audit for interaction with sparse-index. */
	ensure_full_index(istate);
	for (i = 0; i < istate->cache_nr; i++) {
		struct cache_entry *ce = istate->cache[i];
		struct blob *blob;

		if (S_ISGITLINK(ce->ce_mode))
			continue;

		blob = lookup_blob(revs->repo, &ce->oid);
		if (!blob)
			die("unable to add index blob to traversal");
		blob->object.flags |= flags;
		add_pending_object_with_path(revs, &blob->object, "",
					     ce->ce_mode, ce->name);
	}

	if (istate->cache_tree) {
		struct strbuf path = STRBUF_INIT;
		add_cache_tree(istate->cache_tree, revs, &path, flags);
		strbuf_release(&path);
	}

	add_resolve_undo_to_pending(istate, revs);
}

void add_index_objects_to_pending(struct rev_info *revs, unsigned int flags)
{
	struct worktree **worktrees, **p;

	repo_read_index(revs->repo);
	do_add_index_objects_to_pending(revs, revs->repo->index, flags);

	if (revs->single_worktree)
		return;

	worktrees = get_worktrees();
	for (p = worktrees; *p; p++) {
		struct worktree *wt = *p;
		struct index_state istate = { NULL };

		if (wt->is_current)
			continue; /* current index already taken care of */

		if (read_index_from(&istate,
				    worktree_git_path(wt, "index"),
				    get_worktree_git_dir(wt)) > 0)
			do_add_index_objects_to_pending(revs, &istate, flags);
		discard_index(&istate);
	}
	free_worktrees(worktrees);
}

struct add_alternate_refs_data {
	struct rev_info *revs;
	unsigned int flags;
};

static void add_one_alternate_ref(const struct object_id *oid,
				  void *vdata)
{
	const char *name = ".alternate";
	struct add_alternate_refs_data *data = vdata;
	struct object *obj;

	obj = get_reference(data->revs, name, oid, data->flags);
	add_rev_cmdline(data->revs, obj, name, REV_CMD_REV, data->flags);
	add_pending_object(data->revs, obj, name);
}

static void add_alternate_refs_to_pending(struct rev_info *revs,
					  unsigned int flags)
{
	struct add_alternate_refs_data data;
	data.revs = revs;
	data.flags = flags;
	for_each_alternate_ref(add_one_alternate_ref, &data);
}

static int add_parents_only(struct rev_info *revs, const char *arg_, int flags,
			    int exclude_parent)
{
	struct object_id oid;
	struct object *it;
	struct commit *commit;
	struct commit_list *parents;
	int parent_number;
	const char *arg = arg_;

	if (*arg == '^') {
		flags ^= UNINTERESTING | BOTTOM;
		arg++;
	}
	if (get_oid_committish(arg, &oid))
		return 0;
	while (1) {
		it = get_reference(revs, arg, &oid, 0);
		if (!it && revs->ignore_missing)
			return 0;
		if (it->type != OBJ_TAG)
			break;
		if (!((struct tag*)it)->tagged)
			return 0;
		oidcpy(&oid, &((struct tag*)it)->tagged->oid);
	}
	if (it->type != OBJ_COMMIT)
		return 0;
	commit = (struct commit *)it;
	if (exclude_parent &&
	    exclude_parent > commit_list_count(commit->parents))
		return 0;
	for (parents = commit->parents, parent_number = 1;
	     parents;
	     parents = parents->next, parent_number++) {
		if (exclude_parent && parent_number != exclude_parent)
			continue;

		it = &parents->item->object;
		it->flags |= flags;
		add_rev_cmdline(revs, it, arg_, REV_CMD_PARENTS_ONLY, flags);
		add_pending_object(revs, it, arg);
	}
	return 1;
}

void repo_init_revisions(struct repository *r,
			 struct rev_info *revs,
			 const char *prefix)
{
	memset(revs, 0, sizeof(*revs));

	revs->repo = r;
	revs->abbrev = DEFAULT_ABBREV;
	revs->simplify_history = 1;
	revs->pruning.repo = r;
	revs->pruning.flags.recursive = 1;
	revs->pruning.flags.quick = 1;
	revs->pruning.add_remove = file_add_remove;
	revs->pruning.change = file_change;
	revs->pruning.change_fn_data = revs;
	revs->sort_order = REV_SORT_IN_GRAPH_ORDER;
	revs->dense = 1;
	revs->prefix = prefix;
	revs->max_age = -1;
	revs->max_age_as_filter = -1;
	revs->min_age = -1;
	revs->skip_count = -1;
	revs->max_count = -1;
	revs->max_parents = -1;
	revs->expand_tabs_in_log = -1;

	revs->commit_format = CMIT_FMT_DEFAULT;
	revs->expand_tabs_in_log_default = 8;

	grep_init(&revs->grep_filter, revs->repo);
	revs->grep_filter.status_only = 1;

	repo_diff_setup(revs->repo, &revs->diffopt);
	if (prefix && !revs->diffopt.prefix) {
		revs->diffopt.prefix = prefix;
		revs->diffopt.prefix_length = strlen(prefix);
	}

	init_display_notes(&revs->notes_opt);
}

static void add_pending_commit_list(struct rev_info *revs,
				    struct commit_list *commit_list,
				    unsigned int flags)
{
	while (commit_list) {
		struct object *object = &commit_list->item->object;
		object->flags |= flags;
		add_pending_object(revs, object, oid_to_hex(&object->oid));
		commit_list = commit_list->next;
	}
}

static void prepare_show_merge(struct rev_info *revs)
{
	struct commit_list *bases;
	struct commit *head, *other;
	struct object_id oid;
	const char **prune = NULL;
	int i, prune_num = 1; /* counting terminating NULL */
	struct index_state *istate = revs->repo->index;

	if (get_oid("HEAD", &oid))
		die("--merge without HEAD?");
	head = lookup_commit_or_die(&oid, "HEAD");
	if (get_oid("MERGE_HEAD", &oid))
		die("--merge without MERGE_HEAD?");
	other = lookup_commit_or_die(&oid, "MERGE_HEAD");
	add_pending_object(revs, &head->object, "HEAD");
	add_pending_object(revs, &other->object, "MERGE_HEAD");
	bases = get_merge_bases(head, other);
	add_rev_cmdline_list(revs, bases, REV_CMD_MERGE_BASE, UNINTERESTING | BOTTOM);
	add_pending_commit_list(revs, bases, UNINTERESTING | BOTTOM);
	free_commit_list(bases);
	head->object.flags |= SYMMETRIC_LEFT;

	if (!istate->cache_nr)
		repo_read_index(revs->repo);
	for (i = 0; i < istate->cache_nr; i++) {
		const struct cache_entry *ce = istate->cache[i];
		if (!ce_stage(ce))
			continue;
		if (ce_path_match(istate, ce, &revs->prune_data, NULL)) {
			prune_num++;
			REALLOC_ARRAY(prune, prune_num);
			prune[prune_num-2] = ce->name;
			prune[prune_num-1] = NULL;
		}
		while ((i+1 < istate->cache_nr) &&
		       ce_same_name(ce, istate->cache[i+1]))
			i++;
	}
	clear_pathspec(&revs->prune_data);
	parse_pathspec(&revs->prune_data, PATHSPEC_ALL_MAGIC & ~PATHSPEC_LITERAL,
		       PATHSPEC_PREFER_FULL | PATHSPEC_LITERAL_PATH, "", prune);
	revs->limited = 1;
}

static int dotdot_missing(const char *arg, char *dotdot,
			  struct rev_info *revs, int symmetric)
{
	if (revs->ignore_missing)
		return 0;
	/* de-munge so we report the full argument */
	*dotdot = '.';
	die(symmetric
	    ? "Invalid symmetric difference expression %s"
	    : "Invalid revision range %s", arg);
}

static int handle_dotdot_1(const char *arg, char *dotdot,
			   struct rev_info *revs, int flags,
			   int cant_be_filename,
			   struct object_context *a_oc,
			   struct object_context *b_oc)
{
	const char *a_name, *b_name;
	struct object_id a_oid, b_oid;
	struct object *a_obj, *b_obj;
	unsigned int a_flags, b_flags;
	int symmetric = 0;
	unsigned int flags_exclude = flags ^ (UNINTERESTING | BOTTOM);
	unsigned int oc_flags = GET_OID_COMMITTISH | GET_OID_RECORD_PATH;

	a_name = arg;
	if (!*a_name)
		a_name = "HEAD";

	b_name = dotdot + 2;
	if (*b_name == '.') {
		symmetric = 1;
		b_name++;
	}
	if (!*b_name)
		b_name = "HEAD";

	if (get_oid_with_context(revs->repo, a_name, oc_flags, &a_oid, a_oc) ||
	    get_oid_with_context(revs->repo, b_name, oc_flags, &b_oid, b_oc))
		return -1;

	if (!cant_be_filename) {
		*dotdot = '.';
		verify_non_filename(revs->prefix, arg);
		*dotdot = '\0';
	}

	a_obj = parse_object(revs->repo, &a_oid);
	b_obj = parse_object(revs->repo, &b_oid);
	if (!a_obj || !b_obj)
		return dotdot_missing(arg, dotdot, revs, symmetric);

	if (!symmetric) {
		/* just A..B */
		b_flags = flags;
		a_flags = flags_exclude;
	} else {
		/* A...B -- find merge bases between the two */
		struct commit *a, *b;
		struct commit_list *exclude;

		a = lookup_commit_reference(revs->repo, &a_obj->oid);
		b = lookup_commit_reference(revs->repo, &b_obj->oid);
		if (!a || !b)
			return dotdot_missing(arg, dotdot, revs, symmetric);

		exclude = get_merge_bases(a, b);
		add_rev_cmdline_list(revs, exclude, REV_CMD_MERGE_BASE,
				     flags_exclude);
		add_pending_commit_list(revs, exclude, flags_exclude);
		free_commit_list(exclude);

		b_flags = flags;
		a_flags = flags | SYMMETRIC_LEFT;
	}

	a_obj->flags |= a_flags;
	b_obj->flags |= b_flags;
	add_rev_cmdline(revs, a_obj, a_name, REV_CMD_LEFT, a_flags);
	add_rev_cmdline(revs, b_obj, b_name, REV_CMD_RIGHT, b_flags);
	add_pending_object_with_path(revs, a_obj, a_name, a_oc->mode, a_oc->path);
	add_pending_object_with_path(revs, b_obj, b_name, b_oc->mode, b_oc->path);
	return 0;
}

static int handle_dotdot(const char *arg,
			 struct rev_info *revs, int flags,
			 int cant_be_filename)
{
	struct object_context a_oc, b_oc;
	char *dotdot = strstr(arg, "..");
	int ret;

	if (!dotdot)
		return -1;

	memset(&a_oc, 0, sizeof(a_oc));
	memset(&b_oc, 0, sizeof(b_oc));

	*dotdot = '\0';
	ret = handle_dotdot_1(arg, dotdot, revs, flags, cant_be_filename,
			      &a_oc, &b_oc);
	*dotdot = '.';

	free(a_oc.path);
	free(b_oc.path);

	return ret;
}

static int handle_revision_arg_1(const char *arg_, struct rev_info *revs, int flags, unsigned revarg_opt)
{
	struct object_context oc;
	char *mark;
	struct object *object;
	struct object_id oid;
	int local_flags;
	const char *arg = arg_;
	int cant_be_filename = revarg_opt & REVARG_CANNOT_BE_FILENAME;
	unsigned get_sha1_flags = GET_OID_RECORD_PATH;

	flags = flags & UNINTERESTING ? flags | BOTTOM : flags & ~BOTTOM;

	if (!cant_be_filename && !strcmp(arg, "..")) {
		/*
		 * Just ".."?  That is not a range but the
		 * pathspec for the parent directory.
		 */
		return -1;
	}

	if (!handle_dotdot(arg, revs, flags, revarg_opt))
		return 0;

	mark = strstr(arg, "^@");
	if (mark && !mark[2]) {
		*mark = 0;
		if (add_parents_only(revs, arg, flags, 0))
			return 0;
		*mark = '^';
	}
	mark = strstr(arg, "^!");
	if (mark && !mark[2]) {
		*mark = 0;
		if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), 0))
			*mark = '^';
	}
	mark = strstr(arg, "^-");
	if (mark) {
		int exclude_parent = 1;

		if (mark[2]) {
			char *end;
			exclude_parent = strtoul(mark + 2, &end, 10);
			if (*end != '\0' || !exclude_parent)
				return -1;
		}

		*mark = 0;
		if (!add_parents_only(revs, arg, flags ^ (UNINTERESTING | BOTTOM), exclude_parent))
			*mark = '^';
	}

	local_flags = 0;
	if (*arg == '^') {
		local_flags = UNINTERESTING | BOTTOM;
		arg++;
	}

	if (revarg_opt & REVARG_COMMITTISH)
		get_sha1_flags |= GET_OID_COMMITTISH;

	if (get_oid_with_context(revs->repo, arg, get_sha1_flags, &oid, &oc))
		return revs->ignore_missing ? 0 : -1;
	if (!cant_be_filename)
		verify_non_filename(revs->prefix, arg);
	object = get_reference(revs, arg, &oid, flags ^ local_flags);
	if (!object)
		return revs->ignore_missing ? 0 : -1;
	add_rev_cmdline(revs, object, arg_, REV_CMD_REV, flags ^ local_flags);
	add_pending_object_with_path(revs, object, arg, oc.mode, oc.path);
	free(oc.path);
	return 0;
}

int handle_revision_arg(const char *arg, struct rev_info *revs, int flags, unsigned revarg_opt)
{
	int ret = handle_revision_arg_1(arg, revs, flags, revarg_opt);
	if (!ret)
		revs->rev_input_given = 1;
	return ret;
}

static void read_pathspec_from_stdin(struct strbuf *sb,
				     struct strvec *prune)
{
	while (strbuf_getline(sb, stdin) != EOF)
		strvec_push(prune, sb->buf);
}

static void read_revisions_from_stdin(struct rev_info *revs,
				      struct strvec *prune)
{
	struct strbuf sb;
	int seen_dashdash = 0;
	int save_warning;

	save_warning = warn_on_object_refname_ambiguity;
	warn_on_object_refname_ambiguity = 0;

	strbuf_init(&sb, 1000);
	while (strbuf_getline(&sb, stdin) != EOF) {
		int len = sb.len;
		if (!len)
			break;
		if (sb.buf[0] == '-') {
			if (len == 2 && sb.buf[1] == '-') {
				seen_dashdash = 1;
				break;
			}
			die("options not supported in --stdin mode");
		}
		if (handle_revision_arg(sb.buf, revs, 0,
					REVARG_CANNOT_BE_FILENAME))
			die("bad revision '%s'", sb.buf);
	}
	if (seen_dashdash)
		read_pathspec_from_stdin(&sb, prune);

	strbuf_release(&sb);
	warn_on_object_refname_ambiguity = save_warning;
}

static void add_grep(struct rev_info *revs, const char *ptn, enum grep_pat_token what)
{
	append_grep_pattern(&revs->grep_filter, ptn, "command line", 0, what);
}

static void add_header_grep(struct rev_info *revs, enum grep_header_field field, const char *pattern)
{
	append_header_grep_pattern(&revs->grep_filter, field, pattern);
}

static void add_message_grep(struct rev_info *revs, const char *pattern)
{
	add_grep(revs, pattern, GREP_PATTERN_BODY);
}

static int handle_revision_opt(struct rev_info *revs, int argc, const char **argv,
			       int *unkc, const char **unkv,
			       const struct setup_revision_opt* opt)
{
	const char *arg = argv[0];
	const char *optarg;
	int argcount;
	const unsigned hexsz = the_hash_algo->hexsz;

	/* pseudo revision arguments */
	if (!strcmp(arg, "--all")