[PATCH v2 07/10] commit-graph: refactor `parse_commit_graph()` to take a repository
- From
Patrick Steinhardt <ps@pks.im>
- Date
- Aug 6, 2025, 12:00 UTC
- Message-ID
- <20250806-b4-pks-commit-graph-wo-the-repository-v2-7-911bae638e61@pks.im>
- In-Reply-To
- <20250806-b4-pks-commit-graph-wo-the-repository-v2-0-911bae638e61@pks.im>
Refactor `parse_commit_graph()` so that it takes a repository instead of taking repository settings. On the one hand this allows us to get rid of instances where we access `the_hash_algo` by using the repository's hash algorithm instead. On the other hand it also allows us to move the call of `prepare_repo_settings()` into the function itself.
Note that there's one small catch, as the commit-graph fuzzer calls this function directly without having a fully functional repository at hand. And while the fuzzer already initializes `the_repository` with relevant info, the call to `prepare_repo_settings()` would fail because we don't have a fully-initialized repository.
Work around the issue by also settings `settings.initialized` to pretend that we've already read the settings.
While at it, remove the redundant `parse_commit_graph()` declaration in the fuzzer. It was added together with aa658574bf (commit-graph, fuzz: add fuzzer for commit-graph, 2019-01-15), but as we also declared the same function in "commit-graph.h" it wasn't ever needed.
Signed-off-by: Patrick Steinhardt <ps@pks.im> --- commit-graph.c | 23 ++++++++++++----------- commit-graph.h | 2 +- oss-fuzz/fuzz-commit-graph.c | 6 ++---- 3 files changed, 15 insertions(+), 16 deletions(-)
diff --git a/commit-graph.c b/commit-graph.c index 590a6972d2a..50391cc0f32 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -270,9 +270,8 @@ struct commit_graph *load_commit_graph_one_fd_st(struct repository *r, } graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); - prepare_repo_settings(r); - ret = parse_commit_graph(&r->settings, graph_map, graph_size); + ret = parse_commit_graph(r, graph_map, graph_size); if (ret) ret->odb_source = source; else @@ -372,7 +371,7 @@ static int graph_read_bloom_data(const unsigned char *chunk_start, return 0; } -struct commit_graph *parse_commit_graph(struct repo_settings *s, +struct commit_graph *parse_commit_graph(struct repository *r, void *graph_map, size_t graph_size) { const unsigned char *data; @@ -384,7 +383,7 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, if (!graph_map) return NULL; - if (graph_size < graph_min_size(the_hash_algo)) + if (graph_size < graph_min_size(r->hash_algo)) return NULL; data = (const unsigned char *)graph_map; @@ -404,22 +403,22 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, } hash_version = *(unsigned char*)(data + 5); - if (hash_version != oid_version(the_hash_algo)) { + if (hash_version != oid_version(r->hash_algo)) { error(_("commit-graph hash version %X does not match version %X"), - hash_version, oid_version(the_hash_algo)); + hash_version, oid_version(r->hash_algo)); return NULL; } graph = alloc_commit_graph(); - graph->hash_algo = the_hash_algo; + graph->hash_algo = r->hash_algo; graph->num_chunks = *(unsigned char*)(data + 6); graph->data = graph_map; graph->data_len = graph_size; if (graph_size < GRAPH_HEADER_SIZE + (graph->num_chunks + 1) * CHUNK_TOC_ENTRY_SIZE + - GRAPH_FANOUT_SIZE + the_hash_algo->rawsz) { + GRAPH_FANOUT_SIZE + r->hash_algo->rawsz) { error(_("commit-graph file is too small to hold %u chunks"), graph->num_chunks); free(graph); @@ -450,7 +449,9 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, pair_chunk(cf, GRAPH_CHUNKID_BASE, &graph->chunk_base_graphs, &graph->chunk_base_graphs_size); - if (s->commit_graph_generation_version >= 2) { + prepare_repo_settings(r); + + if (r->settings.commit_graph_generation_version >= 2) { read_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA, graph_read_generation_data, graph); pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW, @@ -461,7 +462,7 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, graph->read_generation_data = 1; } - if (s->commit_graph_changed_paths_version) { + if (r->settings.commit_graph_changed_paths_version) { read_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES, graph_read_bloom_index, graph); read_chunk(cf, GRAPH_CHUNKID_BLOOMDATA, @@ -478,7 +479,7 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s, } oidread(&graph->oid, graph->data + graph->data_len - graph->hash_algo->rawsz, - the_repository->hash_algo); + r->hash_algo); free_chunkfile(cf); return graph; diff --git a/commit-graph.h b/commit-graph.h index f20d28ff3a0..5a5c876af0b 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -128,7 +128,7 @@ struct repo_settings; * Callers should initialize the repo_settings with prepare_repo_settings() * prior to calling parse_commit_graph(). */ -struct commit_graph *parse_commit_graph(struct repo_settings *s, +struct commit_graph *parse_commit_graph(struct repository *r, void *graph_map, size_t graph_size); /* diff --git a/oss-fuzz/fuzz-commit-graph.c b/oss-fuzz/fuzz-commit-graph.c index fbb77fec197..fb8b8787a46 100644 --- a/oss-fuzz/fuzz-commit-graph.c +++ b/oss-fuzz/fuzz-commit-graph.c @@ -4,9 +4,6 @@ #include "commit-graph.h" #include "repository.h" -struct commit_graph *parse_commit_graph(struct repo_settings *s, - void *graph_map, size_t graph_size); - int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size); int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) @@ -22,9 +19,10 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) * possible. */ repo_set_hash_algo(the_repository, GIT_HASH_SHA1); + the_repository->settings.initialized = 1; the_repository->settings.commit_graph_generation_version = 2; the_repository->settings.commit_graph_changed_paths_version = 1; - g = parse_commit_graph(&the_repository->settings, (void *)data, size); + g = parse_commit_graph(the_repository, (void *)data, size); repo_clear(the_repository); free_commit_graph(g);
-- 2.51.0.rc0.215.g125493bb4a.dirty