Merge branch 'jk/http-walker-limit-redirect' into maint

Update the error messages from the dumb-http client when it fails
to obtain loose objects; we used to give sensible error message
only upon 404 but we now forbid unexpected redirects that needs to
be reported with something sensible.

* jk/http-walker-limit-redirect:
  http-walker: complain about non-404 loose object errors
  http: treat http-alternates like redirects
  http: make redirects more obvious
  remote-curl: rename shadowed options variable
  http: always update the base URL for redirects
  http: simplify update_url_from_redirect

4 files changed, 80 insertions, 0 deletions

diff --git a/t/lib-httpd/apache.conf b/t/lib-httpd/apache.conf
index c3e6313..69174c6 100644
--- a/t/lib-httpd/apache.conf
+++ b/t/lib-httpd/apache.conf
@@ -123,6 +123,7 @@ ScriptAlias /error/ error.sh/
 </Files>
 
 RewriteEngine on
+RewriteRule ^/dumb-redir/(.*)$ /dumb/$1 [R=301]
 RewriteRule ^/smart-redir-perm/(.*)$ /smart/$1 [R=301]
 RewriteRule ^/smart-redir-temp/(.*)$ /smart/$1 [R=302]
 RewriteRule ^/smart-redir-auth/(.*)$ /auth/smart/$1 [R=301]
@@ -132,6 +133,19 @@ RewriteRule ^/ftp-redir/(.*)$ ftp://localhost:1000/$1 [R=302]
 RewriteRule ^/loop-redir/x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-(.*) /$1 [R=302]
 RewriteRule ^/loop-redir/(.*)$ /loop-redir/x-$1 [R=302]
 
+# The first rule issues a client-side redirect to something
+# that _doesn't_ look like a git repo. The second rule is a
+# server-side rewrite, so that it turns out the odd-looking
+# thing _is_ a git repo. The "[PT]" tells Apache to match
+# the usual ScriptAlias rules for /smart.
+RewriteRule ^/insane-redir/(.*)$ /intern-redir/$1/foo [R=301]
+RewriteRule ^/intern-redir/(.*)/foo$ /smart/$1 [PT]
+
+# Serve info/refs internally without redirecting, but
+# issue a redirect for any object requests.
+RewriteRule ^/redir-objects/(.*/info/refs)$ /dumb/$1 [PT]
+RewriteRule ^/redir-objects/(.*/objects/.*)$ /dumb/$1 [R=301]
+
 # Apache 2.2 does not understand <RequireAll>, so we use RewriteCond.
 # And as RewriteCond does not allow testing for non-matches, we match
 # the desired case first (one has abra, two has cadabra), and let it
diff --git a/t/t5550-http-fetch-dumb.sh b/t/t5550-http-fetch-dumb.sh
index 7641417..264a1ab 100755
--- a/t/t5550-http-fetch-dumb.sh
+++ b/t/t5550-http-fetch-dumb.sh
@@ -307,5 +307,66 @@ test_expect_success 'remote-http complains cleanly about malformed urls' '
 	test_must_fail git remote-http http::/example.com/repo.git
 '
 
+test_expect_success 'redirects can be forbidden/allowed' '
+	test_must_fail git -c http.followRedirects=false \
+		clone $HTTPD_URL/dumb-redir/repo.git dumb-redir &&
+	git -c http.followRedirects=true \
+		clone $HTTPD_URL/dumb-redir/repo.git dumb-redir 2>stderr
+'
+
+test_expect_success 'redirects are reported to stderr' '
+	# just look for a snippet of the redirected-to URL
+	test_i18ngrep /dumb/ stderr
+'
+
+test_expect_success 'non-initial redirects can be forbidden' '
+	test_must_fail git -c http.followRedirects=initial \
+		clone $HTTPD_URL/redir-objects/repo.git redir-objects &&
+	git -c http.followRedirects=true \
+		clone $HTTPD_URL/redir-objects/repo.git redir-objects
+'
+
+test_expect_success 'http.followRedirects defaults to "initial"' '
+	test_must_fail git clone $HTTPD_URL/redir-objects/repo.git default
+'
+
+# The goal is for a clone of the "evil" repository, which has no objects
+# itself, to cause the client to fetch objects from the "victim" repository.
+test_expect_success 'set up evil alternates scheme' '
+	victim=$HTTPD_DOCUMENT_ROOT_PATH/victim.git &&
+	git init --bare "$victim" &&
+	git -C "$victim" --work-tree=. commit --allow-empty -m secret &&
+	git -C "$victim" repack -ad &&
+	git -C "$victim" update-server-info &&
+	sha1=$(git -C "$victim" rev-parse HEAD) &&
+
+	evil=$HTTPD_DOCUMENT_ROOT_PATH/evil.git &&
+	git init --bare "$evil" &&
+	# do this by hand to avoid object existence check
+	printf "%s\\t%s\\n" $sha1 refs/heads/master >"$evil/info/refs"
+'
+
+# Here we'll just redirect via HTTP. In a real-world attack these would be on
+# different servers, but we should reject it either way.
+test_expect_success 'http-alternates is a non-initial redirect' '
+	echo "$HTTPD_URL/dumb/victim.git/objects" \
+		>"$evil/objects/info/http-alternates" &&
+	test_must_fail git -c http.followRedirects=initial \
+		clone $HTTPD_URL/dumb/evil.git evil-initial &&
+	git -c http.followRedirects=true \
+		clone $HTTPD_URL/dumb/evil.git evil-initial
+'
+
+# Curl supports a lot of protocols that we'd prefer not to allow
+# http-alternates to use, but it's hard to test whether curl has
+# accessed, say, the SMTP protocol, because we are not running an SMTP server.
+# But we can check that it does not allow access to file://, which would
+# otherwise allow this clone to complete.
+test_expect_success 'http-alternates cannot point at funny protocols' '
+	echo "file://$victim/objects" >"$evil/objects/info/http-alternates" &&
+	test_must_fail git -c http.followRedirects=true \
+		clone "$HTTPD_URL/dumb/evil.git" evil-file
+'
+
 stop_httpd
 test_done
diff --git a/t/t5551-http-fetch-smart.sh b/t/t5551-http-fetch-smart.sh
index 1ec5b27..6e5b9e4 100755
--- a/t/t5551-http-fetch-smart.sh
+++ b/t/t5551-http-fetch-smart.sh
@@ -119,6 +119,10 @@ test_expect_success 'redirects re-root further requests' '
 	git clone $HTTPD_URL/smart-redir-limited/repo.git repo-redir-limited
 '
 
+test_expect_success 're-rooting dies on insane schemes' '
+	test_must_fail git clone $HTTPD_URL/insane-redir/repo.git insane
+'
+
 test_expect_success 'clone from password-protected repository' '
 	echo two >expect &&
 	set_askpass user@host pass@host &&
diff --git a/t/t5812-proto-disable-http.sh b/t/t5812-proto-disable-http.sh
index 0d105d5..044cc15 100755
--- a/t/t5812-proto-disable-http.sh
+++ b/t/t5812-proto-disable-http.sh
@@ -18,6 +18,7 @@ test_proto "smart http" http "$HTTPD_URL/smart/repo.git"
 
 test_expect_success 'curl redirects respect whitelist' '
 	test_must_fail env GIT_ALLOW_PROTOCOL=http:https \
+			   GIT_SMART_HTTP=0 \
 		git clone "$HTTPD_URL/ftp-redir/repo.git" 2>stderr &&
 	{
 		test_i18ngrep "ftp.*disabled" stderr ||