Merge branch 'tb/commit-graph-genv2-upgrade-fix' into maint

There was a bug in the codepath to upgrade generation information
in commit-graph from v1 to v2 format, which has been corrected.
source: <cover.1657667404.git.me@ttaylorr.com>

* tb/commit-graph-genv2-upgrade-fix:
  commit-graph: fix corrupt upgrade from generation v1 to v2
  commit-graph: introduce `repo_find_commit_pos_in_graph()`
  t5318: demonstrate commit-graph generation v2 corruption

bloom.c

@@ -30,10 +30,9 @@ static inline unsigned char get_bitmask(uint32_t pos)
 
 static int load_bloom_filter_from_graph(struct commit_graph *g,
 					struct bloom_filter *filter,
-					struct commit *c)
+					uint32_t graph_pos)
 {
 	uint32_t lex_pos, start_index, end_index;
-	uint32_t graph_pos = commit_graph_position(c);
 
 	while (graph_pos < g->num_commits_in_base)
 		g = g->base_graph;
@@ -203,9 +202,10 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 	filter = bloom_filter_slab_at(&bloom_filters, c);
 
 	if (!filter->data) {
-		load_commit_graph_info(r, c);
+		uint32_t graph_pos;
-		if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH)
+		if (repo_find_commit_pos_in_graph(r, c, &graph_pos))
-			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
+			load_bloom_filter_from_graph(r->objects->commit_graph,
+						     filter, graph_pos);
 	}
 
 	if (filter->data && filter->len)

commit-graph.c

@@ -889,6 +889,14 @@ static int find_commit_pos_in_graph(struct commit *item, struct commit_graph *g,
 	}
 }
 
+int repo_find_commit_pos_in_graph(struct repository *r, struct commit *c,
+				  uint32_t *pos)
+{
+	if (!prepare_commit_graph(r))
+		return 0;
+	return find_commit_pos_in_graph(c, r->objects->commit_graph, pos);
+}
+
 struct commit *lookup_commit_in_graph(struct repository *repo, const struct object_id *id)
 {
 	struct commit *commit;
@@ -946,9 +954,7 @@ int parse_commit_in_graph(struct repository *r, struct commit *item)
 void load_commit_graph_info(struct repository *r, struct commit *item)
 {
 	uint32_t pos;
-	if (!prepare_commit_graph(r))
+	if (repo_find_commit_pos_in_graph(r, item, &pos))
-		return;
-	if (find_commit_pos_in_graph(item, r->objects->commit_graph, &pos))
 		fill_commit_graph_info(item, r->objects->commit_graph, pos);
 }
 

commit-graph.h

@@ -40,6 +40,21 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st);
  */
 int parse_commit_in_graph(struct repository *r, struct commit *item);
 
+/*
+ * Fills `*pos` with the graph position of `c`, and returns 1 if `c` is
+ * found in the commit-graph belonging to `r`, or 0 otherwise.
+ * Initializes the commit-graph belonging to `r` if it hasn't been
+ * already.
+ *
+ * Note: this is a low-level helper that does not alter any slab data
+ * associated with `c`. Useful in circumstances where the slab data is
+ * already being modified (e.g., writing the commit-graph itself).
+ *
+ * In most cases, callers should use `parse_commit_in_graph()` instead.
+ */
+int repo_find_commit_pos_in_graph(struct repository *r, struct commit *c,
+				  uint32_t *pos);
+
 /*
  * Look up the given commit ID in the commit-graph. This will only return a
  * commit if the ID exists both in the graph and in the object database such

t/t5318-commit-graph.sh

@@ -811,4 +811,31 @@ test_expect_success 'set up and verify repo with generation data overflow chunk'
 
 graph_git_behavior 'generation data overflow chunk repo' repo left right
 
+test_expect_success 'overflow during generation version upgrade' '
+	git init overflow-v2-upgrade &&
+	(
+		cd overflow-v2-upgrade &&
+
+		# This commit will have a date at two seconds past the Epoch,
+		# and a (v1) generation number of 1, since it is a root commit.
+		#
+		# The offset will then be computed as 1-2, which will underflow
+		# to 2^31, which is greater than the v2 offset small limit of
+		# 2^31-1.
+		#
+		# This is sufficient to need a large offset table for the v2
+		# generation numbers.
+		test_commit --date "@2 +0000" base &&
+		git repack -d &&
+
+		# Test that upgrading from generation v1 to v2 correctly
+		# produces the overflow table.
+		git -c commitGraph.generationVersion=1 commit-graph write &&
+		git -c commitGraph.generationVersion=2 commit-graph write \
+			--changed-paths &&
+
+		git rev-list --all
+	)
+'
+
 test_done