Merge branch 'sg/archive-restrict-remote'

Allow loosening remote "git archive" invocation security check that
refuses to serve tree-ish not at the tip of any ref.

* sg/archive-restrict-remote:
  add uploadarchive.allowUnreachable option
  docs: clarify remote restrictions for git-upload-archive

Author: gitster

Documentation/config.txt

@@ -2336,6 +2336,13 @@ transfer.unpackLimit::
 	not set, the value of this variable is used instead.
 	The default value is 100.
 
+uploadarchive.allowUnreachable::
+	If true, allow clients to use `git archive --remote` to request
+	any tree, whether reachable from the ref tips or not. See the
+	discussion in the `SECURITY` section of
+	linkgit:git-upload-archive[1] for more details. Defaults to
+	`false`.
+
 uploadpack.hiderefs::
 	String(s) `upload-pack` uses to decide which refs to omit
 	from its initial advertisement.  Use more than one

Documentation/git-archive.txt

@@ -65,7 +65,10 @@ OPTIONS
 
 --remote=<repo>::
 	Instead of making a tar archive from the local repository,
-	retrieve a tar archive from a remote repository.
+	retrieve a tar archive from a remote repository. Note that the
+	remote repository may place restrictions on which sha1
+	expressions may be allowed in `<tree-ish>`. See
+	linkgit:git-upload-archive[1] for details.
 
 --exec=<git-upload-archive>::
 	Used with --remote to specify the path to the

Documentation/git-upload-archive.txt

@@ -20,6 +20,38 @@ This command is usually not invoked directly by the end user.  The UI
 for the protocol is on the 'git archive' side, and the program pair
 is meant to be used to get an archive from a remote repository.
 
+SECURITY
+--------
+
+In order to protect the privacy of objects that have been removed from
+history but may not yet have been pruned, `git-upload-archive` avoids
+serving archives for commits and trees that are not reachable from the
+repository's refs.  However, because calculating object reachability is
+computationally expensive, `git-upload-archive` implements a stricter
+but easier-to-check set of rules:
+
+  1. Clients may request a commit or tree that is pointed to directly by
+     a ref. E.g., `git archive --remote=origin v1.0`.
+
+  2. Clients may request a sub-tree within a commit or tree using the
+     `ref:path` syntax. E.g., `git archive --remote=origin v1.0:Documentation`.
+
+  3. Clients may _not_ use other sha1 expressions, even if the end
+     result is reachable. E.g., neither a relative commit like `master^`
+     nor a literal sha1 like `abcd1234` is allowed, even if the result
+     is reachable from the refs.
+
+Note that rule 3 disallows many cases that do not have any privacy
+implications. These rules are subject to change in future versions of
+git, and the server accessed by `git archive --remote` may or may not
+follow these exact rules.
+
+If the config option `uploadArchive.allowUnreachable` is true, these
+rules are ignored, and clients may use arbitrary sha1 expressions.
+This is useful if you do not care about the privacy of unreachable
+objects, or if your object database is already publicly available for
+access via non-smart-http.
+
 OPTIONS
 -------
 <directory>::

archive.c

@@ -17,6 +17,7 @@ static char const * const archive_usage[] = {
 static const struct archiver **archivers;
 static int nr_archivers;
 static int alloc_archivers;
+static int remote_allow_unreachable;
 
 void register_archiver(struct archiver *ar)
 {
@@ -257,7 +258,7 @@ static void parse_treeish_arg(const char **argv,
 	unsigned char sha1[20];
 
 	/* Remotes are only allowed to fetch actual refs */
-	if (remote) {
+	if (remote && !remote_allow_unreachable) {
 		char *ref = NULL;
 		const char *colon = strchr(name, ':');
 		int refnamelen = colon ? colon - name : strlen(name);
@@ -401,6 +402,14 @@ static int parse_archive_args(int argc, const char **argv,
 	return argc;
 }
 
+static int git_default_archive_config(const char *var, const char *value,
+				      void *cb)
+{
+	if (!strcmp(var, "uploadarchive.allowunreachable"))
+		remote_allow_unreachable = git_config_bool(var, value);
+	return git_default_config(var, value, cb);
+}
+
 int write_archive(int argc, const char **argv, const char *prefix,
 		  int setup_prefix, const char *name_hint, int remote)
 {
@@ -411,7 +420,7 @@ int write_archive(int argc, const char **argv, const char *prefix,
 	if (setup_prefix && prefix == NULL)
 		prefix = setup_git_directory_gently(&nongit);
 
-	git_config(git_default_config, NULL);
+	git_config(git_default_archive_config, NULL);
 	init_tar_archiver();
 	init_zip_archiver();
 

t/t5000-tar-tree.sh

@@ -213,6 +213,15 @@ test_expect_success 'clients cannot access unreachable commits' '
 	test_must_fail git archive --remote=. $sha1 >remote.tar
 '
 
+test_expect_success 'upload-archive can allow unreachable commits' '
+	test_commit unreachable1 &&
+	sha1=`git rev-parse HEAD` &&
+	git reset --hard HEAD^ &&
+	git archive $sha1 >remote.tar &&
+	test_config uploadarchive.allowUnreachable true &&
+	git archive --remote=. $sha1 >remote.tar
+'
+
 test_expect_success 'setup tar filters' '
 	git config tar.tar.foo.command "tr ab ba" &&
 	git config tar.bar.command "tr ab ba" &&