[PATCH v2 05/11] commit-graph: add base graphs chunk

["Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>]

From: Derrick Stolee <dstolee@microsoft.com>

To quickly verify a commit-graph chain is valid on load, we will
read from the new "Base Graphs Chunk" of each file in the chain.
This will prevent accidentally loading incorrect data from manually
editing the commit-graph-chain file or renaming graph-{hash}.graph
files.

The commit_graph struct already had an object_id struct "oid", but
it was never initialized or used. Add a line to read the hash from
the end of the commit-graph file and into the oid member.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 .../technical/commit-graph-format.txt         | 11 ++++++++--
 commit-graph.c                                | 22 +++++++++++++++++++
 commit-graph.h                                |  1 +
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
index 16452a0504..a4f17441ae 100644
--- a/Documentation/technical/commit-graph-format.txt
+++ b/Documentation/technical/commit-graph-format.txt
@@ -44,8 +44,9 @@ HEADER:
 
   1-byte number (C) of "chunks"
 
-  1-byte (reserved for later use)
-     Current clients should ignore this value.
+  1-byte number (B) of base commit-graphs
+      We infer the length (H*B) of the Base Graphs chunk
+      from this value.
 
 CHUNK LOOKUP:
 
@@ -92,6 +93,12 @@ CHUNK DATA:
       positions for the parents until reaching a value with the most-significant
       bit on. The other bits correspond to the position of the last parent.
 
+  Base Graphs List (ID: {'B', 'A', 'S', 'E'}) [Optional]
+      This list of H-byte hashes describe a set of B commit-graph files that
+      form a commit-graph chain. The graph position for the ith commit in this
+      file's OID Lookup chunk is equal to i plus the number of commits in all
+      base graphs.  If B is non-zero, this chunk must exist.
+
 TRAILER:
 
 	H-byte HASH-checksum of all of the above.
diff --git a/commit-graph.c b/commit-graph.c
index 70e44393b8..060897fff0 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -22,6 +22,7 @@
 #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
+#define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -262,6 +263,12 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 			else
 				graph->chunk_extra_edges = data + chunk_offset;
 			break;
+
+		case GRAPH_CHUNKID_BASE:
+			if (graph->chunk_base_graphs)
+				chunk_repeated = 1;
+			else
+				graph->chunk_base_graphs = data + chunk_offset;
 		}
 
 		if (chunk_repeated) {
@@ -280,6 +287,8 @@ struct commit_graph *parse_commit_graph(void *graph_map, int fd,
 		last_chunk_offset = chunk_offset;
 	}
 
+	hashcpy(graph->oid.hash, graph->data + graph->data_len - graph->hash_len);
+
 	if (verify_commit_graph_lite(graph))
 		return NULL;
 
@@ -315,8 +324,21 @@ static int add_graph_to_chain(struct commit_graph *g,
 {
 	struct commit_graph *cur_g = chain;
 
+	if (n && !g->chunk_base_graphs) {
+		warning(_("commit-graph has no base graphs chunk"));
+		return 0;
+	}
+
 	while (n) {
 		n--;
+
+		if (!oideq(&oids[n], &cur_g->oid) ||
+		    !hasheq(oids[n].hash, g->chunk_base_graphs + g->hash_len * n)) {
+			warning(_("commit-graph chain does not match"));
+			return 0;
+		}
+
+
 		cur_g = cur_g->base_graph;
 	}
 
diff --git a/commit-graph.h b/commit-graph.h
index f9fe32ebe3..80f4917ddb 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -55,6 +55,7 @@ struct commit_graph {
 	const unsigned char *chunk_oid_lookup;
 	const unsigned char *chunk_commit_data;
 	const unsigned char *chunk_extra_edges;
+	const unsigned char *chunk_base_graphs;
 };
 
 struct commit_graph *load_commit_graph_one_fd_st(int fd, struct stat *st);
-- 
gitgitgadget