clear parsed flag when we free tree buffers

Many code paths will free a tree object's buffer and set it
to NULL after finishing with it in order to keep memory
usage down during a traversal. However, out of 8 sites that
do this, only one actually unsets the "parsed" flag back.
Those sites that don't are setting a trap for later users of
the tree object; even after calling parse_tree, the buffer
will remain NULL, causing potential segfaults.

It is not known whether this is triggerable in the current
code. Most commands do not do an in-memory traversal
followed by actually using the objects again. However, it
does not hurt to be safe for future callers.

In most cases, we can abstract this out to a
"free_tree_buffer" helper. However, there are two
exceptions:

  1. The fsck code relies on the parsed flag to know that we
     were able to parse the object at one point. We can
     switch this to using a flag in the "flags" field.

  2. The index-pack code sets the buffer to NULL but does
     not free it (it is freed by a caller). We should still
     unset the parsed flag here, but we cannot use our
     helper, as we do not want to free the buffer.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/fsck.c

@@ -16,6 +16,7 @@
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
+#define HAS_OBJ   0x0004
 
 static int show_root;
 static int show_tags;
@@ -101,7 +102,7 @@ static int mark_object(struct object *obj, int type, void *data)
 	if (obj->flags & REACHABLE)
 		return 0;
 	obj->flags |= REACHABLE;
-	if (!obj->parsed) {
+	if (!(obj->flags & HAS_OBJ)) {
 		if (parent && !has_sha1_file(obj->sha1)) {
 			printf("broken link from %7s %s\n",
 				 typename(parent->type), sha1_to_hex(parent->sha1));
@@ -127,16 +128,13 @@ static int traverse_one_object(struct object *obj)
 	struct tree *tree = NULL;
 
 	if (obj->type == OBJ_TREE) {
-		obj->parsed = 0;
 		tree = (struct tree *)obj;
 		if (parse_tree(tree) < 0)
 			return 1; /* error already displayed */
 	}
 	result = fsck_walk(obj, mark_object, obj);
-	if (tree) {
+	if (tree)
-		free(tree->buffer);
+		free_tree_buffer(tree);
-		tree->buffer = NULL;
-	}
 	return result;
 }
 
@@ -178,7 +176,7 @@ static void check_reachable_object(struct object *obj)
 	 * except if it was in a pack-file and we didn't
 	 * do a full fsck
 	 */
-	if (!obj->parsed) {
+	if (!(obj->flags & HAS_OBJ)) {
 		if (has_sha1_pack(obj->sha1))
 			return; /* it is in pack - forget about it */
 		printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
@@ -306,8 +304,7 @@ static int fsck_obj(struct object *obj)
 	if (obj->type == OBJ_TREE) {
 		struct tree *item = (struct tree *) obj;
 
-		free(item->buffer);
+		free_tree_buffer(item);
-		item->buffer = NULL;
 	}
 
 	if (obj->type == OBJ_COMMIT) {
@@ -340,6 +337,7 @@ static int fsck_sha1(const unsigned char *sha1)
 		return error("%s: object corrupt or missing",
 			     sha1_to_hex(sha1));
 	}
+	obj->flags |= HAS_OBJ;
 	return fsck_obj(obj);
 }
 
@@ -352,6 +350,7 @@ static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
 		errors_found |= ERROR_OBJECT;
 		return error("%s: object corrupt or missing", sha1_to_hex(sha1));
 	}
+	obj->flags = HAS_OBJ;
 	return fsck_obj(obj);
 }
 

builtin/index-pack.c

@@ -765,6 +765,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			if (obj->type == OBJ_TREE) {
 				struct tree *item = (struct tree *) obj;
 				item->buffer = NULL;
+				obj->parsed = 0;
 			}
 			if (obj->type == OBJ_COMMIT) {
 				struct commit *commit = (struct commit *) obj;

builtin/reflog.c

@@ -94,8 +94,7 @@ static int tree_is_complete(const unsigned char *sha1)
 			complete = 0;
 		}
 	}
-	free(tree->buffer);
+	free_tree_buffer(tree);
-	tree->buffer = NULL;
 
 	if (complete)
 		tree->object.flags |= SEEN;

http-push.c

@@ -1330,8 +1330,7 @@ static struct object_list **process_tree(struct tree *tree,
 			break;
 		}
 
-	free(tree->buffer);
+	free_tree_buffer(tree);
-	tree->buffer = NULL;
 	return p;
 }
 

list-objects.c

@@ -123,8 +123,7 @@ static void process_tree(struct rev_info *revs,
 				     cb_data);
 	}
 	strbuf_setlen(base, baselen);
-	free(tree->buffer);
+	free_tree_buffer(tree);
-	tree->buffer = NULL;
 }
 
 static void mark_edge_parents_uninteresting(struct commit *commit,

reachable.c

@@ -80,8 +80,7 @@ static void process_tree(struct tree *tree,
 		else
 			process_blob(lookup_blob(entry.sha1), p, &me, entry.path, cp);
 	}
-	free(tree->buffer);
+	free_tree_buffer(tree);
-	tree->buffer = NULL;
 }
 
 static void process_tag(struct tag *tag, struct object_array *p,

revision.c

@@ -134,8 +134,7 @@ void mark_tree_uninteresting(struct tree *tree)
 	 * We don't care about the tree any more
 	 * after it has been marked uninteresting.
 	 */
-	free(tree->buffer);
+	free_tree_buffer(tree);
-	tree->buffer = NULL;
 }
 
 void mark_parents_uninteresting(struct commit *commit)

tree.c

@@ -225,6 +225,14 @@ int parse_tree(struct tree *item)
 	return parse_tree_buffer(item, buffer, size);
 }
 
+void free_tree_buffer(struct tree *tree)
+{
+	free(tree->buffer);
+	tree->buffer = NULL;
+	tree->size = 0;
+	tree->object.parsed = 0;
+}
+
 struct tree *parse_tree_indirect(const unsigned char *sha1)
 {
 	struct object *obj = parse_object(sha1);

tree.h

@@ -16,6 +16,7 @@ struct tree *lookup_tree(const unsigned char *sha1);
 int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size);
 
 int parse_tree(struct tree *tree);
+void free_tree_buffer(struct tree *tree);
 
 /* Parses and returns the tree in the given ent, chasing tags and commits. */
 struct tree *parse_tree_indirect(const unsigned char *sha1);

walker.c

@@ -56,10 +56,7 @@ static int process_tree(struct walker *walker, struct tree *tree)
 		if (!obj || process(walker, obj))
 			return -1;
 	}
-	free(tree->buffer);
+	free_tree_buffer(tree);
-	tree->buffer = NULL;
-	tree->size = 0;
-	tree->object.parsed = 0;
 	return 0;
 }