Merge branch 'ds/reachable-topo-order'

The revision walker machinery learned to take advantage of the
commit generation numbers stored in the commit-graph file.

* ds/reachable-topo-order:
  t6012: make rev-list tests more interesting
  revision.c: generation-based topo-order algorithm
  commit/revisions: bookkeeping before refactoring
  revision.c: begin refactoring --topo-order logic
  test-reach: add rev-list tests
  test-reach: add run_three_modes method
  prio-queue: add 'peek' operation

1 files changed, 232 insertions, 11 deletions

diff --git a/revision.c b/revision.c
index bdd3e7c9f1..13e0519c02 100644
--- a/revision.c
+++ b/revision.c
@@ -25,6 +25,8 @@
 #include "worktree.h"
 #include "argv-array.h"
 #include "commit-reach.h"
+#include "commit-graph.h"
+#include "prio-queue.h"
 
 volatile show_early_output_fn_t show_early_output;
 
@@ -767,8 +769,8 @@ static void commit_list_insert_by_date_cached(struct commit *p, struct commit_li
 		*cache = new_entry;
 }
 
-static int add_parents_to_list(struct rev_info *revs, struct commit *commit,
-		    struct commit_list **list, struct commit_list **cache_ptr)
+static int process_parents(struct rev_info *revs, struct commit *commit,
+			   struct commit_list **list, struct commit_list **cache_ptr)
 {
 	struct commit_list *parent = commit->parents;
 	unsigned left_flag;
@@ -807,7 +809,8 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit,
 			if (p->object.flags & SEEN)
 				continue;
 			p->object.flags |= SEEN;
-			commit_list_insert_by_date_cached(p, list, cached_base, cache_ptr);
+			if (list)
+				commit_list_insert_by_date_cached(p, list, cached_base, cache_ptr);
 		}
 		return 0;
 	}
@@ -846,7 +849,8 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit,
 		p->object.flags |= left_flag;
 		if (!(p->object.flags & SEEN)) {
 			p->object.flags |= SEEN;
-			commit_list_insert_by_date_cached(p, list, cached_base, cache_ptr);
+			if (list)
+				commit_list_insert_by_date_cached(p, list, cached_base, cache_ptr);
 		}
 		if (revs->first_parent_only)
 			break;
@@ -1090,7 +1094,7 @@ static int limit_list(struct rev_info *revs)
 
 		if (revs->max_age != -1 && (commit->date < revs->max_age))
 			obj->flags |= UNINTERESTING;
-		if (add_parents_to_list(revs, commit, &list, NULL) < 0)
+		if (process_parents(revs, commit, &list, NULL) < 0)
 			return -1;
 		if (obj->flags & UNINTERESTING) {
 			mark_parents_uninteresting(commit);
@@ -2468,7 +2472,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 	if (revs->diffopt.objfind)
 		revs->simplify_history = 0;
 
-	if (revs->topo_order)
+	if (revs->topo_order && !generation_numbers_enabled(the_repository))
 		revs->limited = 1;
 
 	if (revs->prune_data.nr) {
@@ -2907,6 +2911,217 @@ static int mark_uninteresting(const struct object_id *oid,
 	return 0;
 }
 
+define_commit_slab(indegree_slab, int);
+define_commit_slab(author_date_slab, timestamp_t);
+
+struct topo_walk_info {
+	uint32_t min_generation;
+	struct prio_queue explore_queue;
+	struct prio_queue indegree_queue;
+	struct prio_queue topo_queue;
+	struct indegree_slab indegree;
+	struct author_date_slab author_date;
+};
+
+static inline void test_flag_and_insert(struct prio_queue *q, struct commit *c, int flag)
+{
+	if (c->object.flags & flag)
+		return;
+
+	c->object.flags |= flag;
+	prio_queue_put(q, c);
+}
+
+static void explore_walk_step(struct rev_info *revs)
+{
+	struct topo_walk_info *info = revs->topo_walk_info;
+	struct commit_list *p;
+	struct commit *c = prio_queue_get(&info->explore_queue);
+
+	if (!c)
+		return;
+
+	if (parse_commit_gently(c, 1) < 0)
+		return;
+
+	if (revs->sort_order == REV_SORT_BY_AUTHOR_DATE)
+		record_author_date(&info->author_date, c);
+
+	if (revs->max_age != -1 && (c->date < revs->max_age))
+		c->object.flags |= UNINTERESTING;
+
+	if (process_parents(revs, c, NULL, NULL) < 0)
+		return;
+
+	if (c->object.flags & UNINTERESTING)
+		mark_parents_uninteresting(c);
+
+	for (p = c->parents; p; p = p->next)
+		test_flag_and_insert(&info->explore_queue, p->item, TOPO_WALK_EXPLORED);
+}
+
+static void explore_to_depth(struct rev_info *revs,
+			     uint32_t gen_cutoff)
+{
+	struct topo_walk_info *info = revs->topo_walk_info;
+	struct commit *c;
+	while ((c = prio_queue_peek(&info->explore_queue)) &&
+	       c->generation >= gen_cutoff)
+		explore_walk_step(revs);
+}
+
+static void indegree_walk_step(struct rev_info *revs)
+{
+	struct commit_list *p;
+	struct topo_walk_info *info = revs->topo_walk_info;
+	struct commit *c = prio_queue_get(&info->indegree_queue);
+
+	if (!c)
+		return;
+
+	if (parse_commit_gently(c, 1) < 0)
+		return;
+
+	explore_to_depth(revs, c->generation);
+
+	for (p = c->parents; p; p = p->next) {
+		struct commit *parent = p->item;
+		int *pi = indegree_slab_at(&info->indegree, parent);
+
+		if (*pi)
+			(*pi)++;
+		else
+			*pi = 2;
+
+		test_flag_and_insert(&info->indegree_queue, parent, TOPO_WALK_INDEGREE);
+
+		if (revs->first_parent_only)
+			return;
+	}
+}
+
+static void compute_indegrees_to_depth(struct rev_info *revs,
+				       uint32_t gen_cutoff)
+{
+	struct topo_walk_info *info = revs->topo_walk_info;
+	struct commit *c;
+	while ((c = prio_queue_peek(&info->indegree_queue)) &&
+	       c->generation >= gen_cutoff)
+		indegree_walk_step(revs);
+}
+
+static void init_topo_walk(struct rev_info *revs)
+{
+	struct topo_walk_info *info;
+	struct commit_list *list;
+	revs->topo_walk_info = xmalloc(sizeof(struct topo_walk_info));
+	info = revs->topo_walk_info;
+	memset(info, 0, sizeof(struct topo_walk_info));
+
+	init_indegree_slab(&info->indegree);
+	memset(&info->explore_queue, 0, sizeof(info->explore_queue));
+	memset(&info->indegree_queue, 0, sizeof(info->indegree_queue));
+	memset(&info->topo_queue, 0, sizeof(info->topo_queue));
+
+	switch (revs->sort_order) {
+	default: /* REV_SORT_IN_GRAPH_ORDER */
+		info->topo_queue.compare = NULL;
+		break;
+	case REV_SORT_BY_COMMIT_DATE:
+		info->topo_queue.compare = compare_commits_by_commit_date;
+		break;
+	case REV_SORT_BY_AUTHOR_DATE:
+		init_author_date_slab(&info->author_date);
+		info->topo_queue.compare = compare_commits_by_author_date;
+		info->topo_queue.cb_data = &info->author_date;
+		break;
+	}
+
+	info->explore_queue.compare = compare_commits_by_gen_then_commit_date;
+	info->indegree_queue.compare = compare_commits_by_gen_then_commit_date;
+
+	info->min_generation = GENERATION_NUMBER_INFINITY;
+	for (list = revs->commits; list; list = list->next) {
+		struct commit *c = list->item;
+
+		if (parse_commit_gently(c, 1))
+			continue;
+
+		test_flag_and_insert(&info->explore_queue, c, TOPO_WALK_EXPLORED);
+		test_flag_and_insert(&info->indegree_queue, c, TOPO_WALK_INDEGREE);
+
+		if (c->generation < info->min_generation)
+			info->min_generation = c->generation;
+
+		*(indegree_slab_at(&info->indegree, c)) = 1;
+
+		if (revs->sort_order == REV_SORT_BY_AUTHOR_DATE)
+			record_author_date(&info->author_date, c);
+	}
+	compute_indegrees_to_depth(revs, info->min_generation);
+
+	for (list = revs->commits; list; list = list->next) {
+		struct commit *c = list->item;
+
+		if (*(indegree_slab_at(&info->indegree, c)) == 1)
+			prio_queue_put(&info->topo_queue, c);
+	}
+
+	/*
+	 * This is unfortunate; the initial tips need to be shown
+	 * in the order given from the revision traversal machinery.
+	 */
+	if (revs->sort_order == REV_SORT_IN_GRAPH_ORDER)
+		prio_queue_reverse(&info->topo_queue);
+}
+
+static struct commit *next_topo_commit(struct rev_info *revs)
+{
+	struct commit *c;
+	struct topo_walk_info *info = revs->topo_walk_info;
+
+	/* pop next off of topo_queue */
+	c = prio_queue_get(&info->topo_queue);
+
+	if (c)
+		*(indegree_slab_at(&info->indegree, c)) = 0;
+
+	return c;
+}
+
+static void expand_topo_walk(struct rev_info *revs, struct commit *commit)
+{
+	struct commit_list *p;
+	struct topo_walk_info *info = revs->topo_walk_info;
+	if (process_parents(revs, commit, NULL, NULL) < 0) {
+		if (!revs->ignore_missing_links)
+			die("Failed to traverse parents of commit %s",
+			    oid_to_hex(&commit->object.oid));
+	}
+
+	for (p = commit->parents; p; p = p->next) {
+		struct commit *parent = p->item;
+		int *pi;
+
+		if (parse_commit_gently(parent, 1) < 0)
+			continue;
+
+		if (parent->generation < info->min_generation) {
+			info->min_generation = parent->generation;
+			compute_indegrees_to_depth(revs, info->min_generation);
+		}
+
+		pi = indegree_slab_at(&info->indegree, parent);
+
+		(*pi)--;
+		if (*pi == 1)
+			prio_queue_put(&info->topo_queue, parent);
+
+		if (revs->first_parent_only)
+			return;
+	}
+}
+
 int prepare_revision_walk(struct rev_info *revs)
 {
 	int i;
@@ -2943,11 +3158,13 @@ int prepare_revision_walk(struct rev_info *revs)
 		commit_list_sort_by_date(&revs->commits);
 	if (revs->no_walk)
 		return 0;
-	if (revs->limited)
+	if (revs->limited) {
 		if (limit_list(revs) < 0)
 			return -1;
-	if (revs->topo_order)
-		sort_in_topological_order(&revs->commits, revs->sort_order);
+		if (revs->topo_order)
+			sort_in_topological_order(&revs->commits, revs->sort_order);
+	} else if (revs->topo_order)
+		init_topo_walk(revs);
 	if (revs->line_level_traverse)
 		line_log_filter(revs);
 	if (revs->simplify_merges)
@@ -2964,7 +3181,7 @@ static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp
 	for (;;) {
 		struct commit *p = *pp;
 		if (!revs->limited)
-			if (add_parents_to_list(revs, p, &revs->commits, &cache) < 0)
+			if (process_parents(revs, p, &revs->commits, &cache) < 0)
 				return rewrite_one_error;
 		if (p->object.flags & UNINTERESTING)
 			return rewrite_one_ok;
@@ -3272,6 +3489,8 @@ static struct commit *get_revision_1(struct rev_info *revs)
 
 		if (revs->reflog_info)
 			commit = next_reflog_entry(revs->reflog_info);
+		else if (revs->topo_walk_info)
+			commit = next_topo_commit(revs);
 		else
 			commit = pop_commit(&revs->commits);
 
@@ -3293,7 +3512,9 @@ static struct commit *get_revision_1(struct rev_info *revs)
 
 			if (revs->reflog_info)
 				try_to_simplify_commit(revs, commit);
-			else if (add_parents_to_list(revs, commit, &revs->commits, NULL) < 0) {
+			else if (revs->topo_walk_info)
+				expand_topo_walk(revs, commit);
+			else if (process_parents(revs, commit, &revs->commits, NULL) < 0) {
 				if (!revs->ignore_missing_links)
 					die("Failed to traverse parents of commit %s",
 						oid_to_hex(&commit->object.oid));