Merge branch 'jt/connectivity-check-after-unshallow'

"git fetch" failed to correctly validate the set of objects it
received when making a shallow history deeper, which has been
corrected.

* jt/connectivity-check-after-unshallow:
  fetch-pack: write shallow, then check connectivity
  fetch-pack: implement ref-in-want
  fetch-pack: put shallow info in output parameter
  fetch: refactor to make function args narrower
  fetch: refactor fetch_refs into two functions
  fetch: refactor the population of peer ref OIDs
  upload-pack: test negotiation with changing repository
  upload-pack: implement ref-in-want
  test-pkt-line: add unpack-sideband subcommand

6 files changed, 484 insertions, 0 deletions

diff --git a/t/helper/test-pkt-line.c b/t/helper/test-pkt-line.c
index 0f19e53c75..30775f986f 100644
--- a/t/helper/test-pkt-line.c
+++ b/t/helper/test-pkt-line.c
@@ -1,3 +1,4 @@
+#include "cache.h"
 #include "pkt-line.h"
 
 static void pack_line(const char *line)
@@ -48,6 +49,36 @@ static void unpack(void)
 	}
 }
 
+static void unpack_sideband(void)
+{
+	struct packet_reader reader;
+	packet_reader_init(&reader, 0, NULL, 0,
+			   PACKET_READ_GENTLE_ON_EOF |
+			   PACKET_READ_CHOMP_NEWLINE);
+
+	while (packet_reader_read(&reader) != PACKET_READ_EOF) {
+		int band;
+		int fd;
+
+		switch (reader.status) {
+		case PACKET_READ_EOF:
+			break;
+		case PACKET_READ_NORMAL:
+			band = reader.line[0] & 0xff;
+			if (band < 1 || band > 2)
+				die("unexpected side band %d", band);
+			fd = band;
+
+			write_or_die(fd, reader.line + 1, reader.pktlen - 1);
+			break;
+		case PACKET_READ_FLUSH:
+			return;
+		case PACKET_READ_DELIM:
+			break;
+		}
+	}
+}
+
 int cmd_main(int argc, const char **argv)
 {
 	if (argc < 2)
@@ -57,6 +88,8 @@ int cmd_main(int argc, const char **argv)
 		pack(argc - 2, argv + 2);
 	else if (!strcmp(argv[1], "unpack"))
 		unpack();
+	else if (!strcmp(argv[1], "unpack-sideband"))
+		unpack_sideband();
 	else
 		die("invalid argument '%s'", argv[1]);
 
diff --git a/t/lib-httpd.sh b/t/lib-httpd.sh
index 435a37465a..ed41b155af 100644
--- a/t/lib-httpd.sh
+++ b/t/lib-httpd.sh
@@ -132,6 +132,7 @@ prepare_httpd() {
 	cp "$TEST_PATH"/passwd "$HTTPD_ROOT_PATH"
 	install_script broken-smart-http.sh
 	install_script error.sh
+	install_script apply-one-time-sed.sh
 
 	ln -s "$LIB_HTTPD_MODULE_PATH" "$HTTPD_ROOT_PATH/modules"
 
diff --git a/t/lib-httpd/apache.conf b/t/lib-httpd/apache.conf
index 724d9ae462..581c010d8f 100644
--- a/t/lib-httpd/apache.conf
+++ b/t/lib-httpd/apache.conf
@@ -111,9 +111,14 @@ Alias /auth/dumb/ www/auth/dumb/
 	SetEnv GIT_EXEC_PATH ${GIT_EXEC_PATH}
 	SetEnv GIT_HTTP_EXPORT_ALL
 </LocationMatch>
+<LocationMatch /one_time_sed/>
+	SetEnv GIT_EXEC_PATH ${GIT_EXEC_PATH}
+	SetEnv GIT_HTTP_EXPORT_ALL
+</LocationMatch>
 ScriptAliasMatch /smart_*[^/]*/(.*) ${GIT_EXEC_PATH}/git-http-backend/$1
 ScriptAlias /broken_smart/ broken-smart-http.sh/
 ScriptAlias /error/ error.sh/
+ScriptAliasMatch /one_time_sed/(.*) apply-one-time-sed.sh/$1
 <Directory ${GIT_EXEC_PATH}>
 	Options FollowSymlinks
 </Directory>
@@ -123,6 +128,9 @@ ScriptAlias /error/ error.sh/
 <Files error.sh>
   Options ExecCGI
 </Files>
+<Files apply-one-time-sed.sh>
+	Options ExecCGI
+</Files>
 <Files ${GIT_EXEC_PATH}/git-http-backend>
 	Options ExecCGI
 </Files>
diff --git a/t/lib-httpd/apply-one-time-sed.sh b/t/lib-httpd/apply-one-time-sed.sh
new file mode 100644
index 0000000000..fcef728925
--- /dev/null
+++ b/t/lib-httpd/apply-one-time-sed.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+
+# If "one-time-sed" exists in $HTTPD_ROOT_PATH, run sed on the HTTP response,
+# using the contents of "one-time-sed" as the sed command to be run. If the
+# response was modified as a result, delete "one-time-sed" so that subsequent
+# HTTP responses are no longer modified.
+#
+# This can be used to simulate the effects of the repository changing in
+# between HTTP request-response pairs.
+if [ -e one-time-sed ]; then
+	"$GIT_EXEC_PATH/git-http-backend" >out
+	sed "$(cat one-time-sed)" <out >out_modified
+
+	if diff out out_modified >/dev/null; then
+		cat out
+	else
+		cat out_modified
+		rm one-time-sed
+	fi
+else
+	"$GIT_EXEC_PATH/git-http-backend"
+fi
diff --git a/t/t5537-fetch-shallow.sh b/t/t5537-fetch-shallow.sh
index 943231af96..7045685e2d 100755
--- a/t/t5537-fetch-shallow.sh
+++ b/t/t5537-fetch-shallow.sh
@@ -186,4 +186,47 @@ EOF
 	test_cmp expect actual
 '
 
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+REPO="$HTTPD_DOCUMENT_ROOT_PATH/repo"
+
+test_expect_success 'shallow fetches check connectivity before writing shallow file' '
+	rm -rf "$REPO" client &&
+
+	git init "$REPO" &&
+	test_commit -C "$REPO" one &&
+	test_commit -C "$REPO" two &&
+	test_commit -C "$REPO" three &&
+
+	git init client &&
+
+	# Use protocol v2 to ensure that shallow information is sent exactly
+	# once by the server, since we are planning to manipulate it.
+	git -C "$REPO" config protocol.version 2 &&
+	git -C client config protocol.version 2 &&
+
+	git -C client fetch --depth=2 "$HTTPD_URL/one_time_sed/repo" master:a_branch &&
+
+	# Craft a situation in which the server sends back an unshallow request
+	# with an empty packfile. This is done by refetching with a shorter
+	# depth (to ensure that the packfile is empty), and overwriting the
+	# shallow line in the response with the unshallow line we want.
+	printf "s/0034shallow %s/0036unshallow %s/" \
+	       "$(git -C "$REPO" rev-parse HEAD)" \
+	       "$(git -C "$REPO" rev-parse HEAD^)" \
+	       >"$HTTPD_ROOT_PATH/one-time-sed" &&
+	test_must_fail git -C client fetch --depth=1 "$HTTPD_URL/one_time_sed/repo" \
+		master:a_branch &&
+
+	# Ensure that the one-time-sed script was used.
+	! test -e "$HTTPD_ROOT_PATH/one-time-sed" &&
+
+	# Ensure that the resulting repo is consistent, despite our failure to
+	# fetch.
+	git -C client fsck
+'
+
+stop_httpd
+
 test_done
diff --git a/t/t5703-upload-pack-ref-in-want.sh b/t/t5703-upload-pack-ref-in-want.sh
new file mode 100755
index 0000000000..a73c55a47e
--- /dev/null
+++ b/t/t5703-upload-pack-ref-in-want.sh
@@ -0,0 +1,377 @@
+#!/bin/sh
+
+test_description='upload-pack ref-in-want'
+
+. ./test-lib.sh
+
+get_actual_refs () {
+	sed -n -e '/wanted-refs/,/0001/{
+		/wanted-refs/d
+		/0001/d
+		p
+		}' <out | test-pkt-line unpack >actual_refs
+}
+
+get_actual_commits () {
+	sed -n -e '/packfile/,/0000/{
+		/packfile/d
+		p
+		}' <out | test-pkt-line unpack-sideband >o.pack &&
+	git index-pack o.pack &&
+	git verify-pack -v o.idx | grep commit | cut -c-40 | sort >actual_commits
+}
+
+check_output () {
+	get_actual_refs &&
+	test_cmp expected_refs actual_refs &&
+	get_actual_commits &&
+	test_cmp expected_commits actual_commits
+}
+
+# c(o/foo) d(o/bar)
+#        \ /
+#         b   e(baz)  f(master)
+#          \__  |  __/
+#             \ | /
+#               a
+test_expect_success 'setup repository' '
+	test_commit a &&
+	git checkout -b o/foo &&
+	test_commit b &&
+	test_commit c &&
+	git checkout -b o/bar b &&
+	test_commit d &&
+	git checkout -b baz a &&
+	test_commit e &&
+	git checkout master &&
+	test_commit f
+'
+
+test_expect_success 'config controls ref-in-want advertisement' '
+	git serve --advertise-capabilities >out &&
+	! grep -a ref-in-want out &&
+
+	git config uploadpack.allowRefInWant false &&
+	git serve --advertise-capabilities >out &&
+	! grep -a ref-in-want out &&
+
+	git config uploadpack.allowRefInWant true &&
+	git serve --advertise-capabilities >out &&
+	grep -a ref-in-want out
+'
+
+test_expect_success 'invalid want-ref line' '
+	test-pkt-line pack >in <<-EOF &&
+	command=fetch
+	0001
+	no-progress
+	want-ref refs/heads/non-existent
+	done
+	0000
+	EOF
+
+	test_must_fail git serve --stateless-rpc 2>out <in &&
+	grep "unknown ref" out
+'
+
+test_expect_success 'basic want-ref' '
+	cat >expected_refs <<-EOF &&
+	$(git rev-parse f) refs/heads/master
+	EOF
+	git rev-parse f | sort >expected_commits &&
+
+	test-pkt-line pack >in <<-EOF &&
+	command=fetch
+	0001
+	no-progress
+	want-ref refs/heads/master
+	have $(git rev-parse a)
+	done
+	0000
+	EOF
+
+	git serve --stateless-rpc >out <in &&
+	check_output
+'
+
+test_expect_success 'multiple want-ref lines' '
+	cat >expected_refs <<-EOF &&
+	$(git rev-parse c) refs/heads/o/foo
+	$(git rev-parse d) refs/heads/o/bar
+	EOF
+	git rev-parse c d | sort >expected_commits &&
+
+	test-pkt-line pack >in <<-EOF &&
+	command=fetch
+	0001
+	no-progress
+	want-ref refs/heads/o/foo
+	want-ref refs/heads/o/bar
+	have $(git rev-parse b)
+	done
+	0000
+	EOF
+
+	git serve --stateless-rpc >out <in &&
+	check_output
+'
+
+test_expect_success 'mix want and want-ref' '
+	cat >expected_refs <<-EOF &&
+	$(git rev-parse f) refs/heads/master
+	EOF
+	git rev-parse e f | sort >expected_commits &&
+
+	test-pkt-line pack >in <<-EOF &&
+	command=fetch
+	0001
+	no-progress
+	want-ref refs/heads/master
+	want $(git rev-parse e)
+	have $(git rev-parse a)
+	done
+	0000
+	EOF
+
+	git serve --stateless-rpc >out <in &&
+	check_output
+'
+
+test_expect_success 'want-ref with ref we already have commit for' '
+	cat >expected_refs <<-EOF &&
+	$(git rev-parse c) refs/heads/o/foo
+	EOF
+	>expected_commits &&
+
+	test-pkt-line pack >in <<-EOF &&
+	command=fetch
+	0001
+	no-progress
+	want-ref refs/heads/o/foo
+	have $(git rev-parse c)
+	done
+	0000
+	EOF
+
+	git serve --stateless-rpc >out <in &&
+	check_output
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+REPO="$HTTPD_DOCUMENT_ROOT_PATH/repo"
+LOCAL_PRISTINE="$(pwd)/local_pristine"
+
+test_expect_success 'setup repos for change-while-negotiating test' '
+	(
+		git init "$REPO" &&
+		cd "$REPO" &&
+		>.git/git-daemon-export-ok &&
+		test_commit m1 &&
+		git tag -d m1 &&
+
+		# Local repo with many commits (so that negotiation will take
+		# more than 1 request/response pair)
+		git clone "http://127.0.0.1:$LIB_HTTPD_PORT/smart/repo" "$LOCAL_PRISTINE" &&
+		cd "$LOCAL_PRISTINE" &&
+		git checkout -b side &&
+		for i in $(seq 1 33); do test_commit s$i; done &&
+
+		# Add novel commits to upstream
+		git checkout master &&
+		cd "$REPO" &&
+		test_commit m2 &&
+		test_commit m3 &&
+		git tag -d m2 m3
+	) &&
+	git -C "$LOCAL_PRISTINE" remote set-url origin "http://127.0.0.1:$LIB_HTTPD_PORT/one_time_sed/repo" &&
+	git -C "$LOCAL_PRISTINE" config protocol.version 2
+'
+
+inconsistency () {
+	# Simulate that the server initially reports $2 as the ref
+	# corresponding to $1, and after that, $1 as the ref corresponding to
+	# $1. This corresponds to the real-life situation where the server's
+	# repository appears to change during negotiation, for example, when
+	# different servers in a load-balancing arrangement serve (stateless)
+	# RPCs during a single negotiation.
+	printf "s/%s/%s/" \
+	       $(git -C "$REPO" rev-parse $1 | tr -d "\n") \
+	       $(git -C "$REPO" rev-parse $2 | tr -d "\n") \
+	       >"$HTTPD_ROOT_PATH/one-time-sed"
+}
+
+test_expect_success 'server is initially ahead - no ref in want' '
+	git -C "$REPO" config uploadpack.allowRefInWant false &&
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	inconsistency master 1234567890123456789012345678901234567890 &&
+	test_must_fail git -C local fetch 2>err &&
+	grep "ERR upload-pack: not our ref" err
+'
+
+test_expect_success 'server is initially ahead - ref in want' '
+	git -C "$REPO" config uploadpack.allowRefInWant true &&
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	inconsistency master 1234567890123456789012345678901234567890 &&
+	git -C local fetch &&
+
+	git -C "$REPO" rev-parse --verify master >expected &&
+	git -C local rev-parse --verify refs/remotes/origin/master >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'server is initially behind - no ref in want' '
+	git -C "$REPO" config uploadpack.allowRefInWant false &&
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	inconsistency master "master^" &&
+	git -C local fetch &&
+
+	git -C "$REPO" rev-parse --verify "master^" >expected &&
+	git -C local rev-parse --verify refs/remotes/origin/master >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'server is initially behind - ref in want' '
+	git -C "$REPO" config uploadpack.allowRefInWant true &&
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	inconsistency master "master^" &&
+	git -C local fetch &&
+
+	git -C "$REPO" rev-parse --verify "master" >expected &&
+	git -C local rev-parse --verify refs/remotes/origin/master >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'server loses a ref - ref in want' '
+	git -C "$REPO" config uploadpack.allowRefInWant true &&
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	echo "s/master/raster/" >"$HTTPD_ROOT_PATH/one-time-sed" &&
+	test_must_fail git -C local fetch 2>err &&
+
+	grep "ERR unknown ref refs/heads/raster" err
+'
+
+stop_httpd
+
+REPO="$(pwd)/repo"
+LOCAL_PRISTINE="$(pwd)/local_pristine"
+
+# $REPO
+# c(o/foo) d(o/bar)
+#        \ /
+#         b   e(baz)  f(master)
+#          \__  |  __/
+#             \ | /
+#               a
+#
+# $LOCAL_PRISTINE
+#		s32(side)
+#		|
+#		.
+#		.
+#		|
+#		a(master)
+test_expect_success 'setup repos for fetching with ref-in-want tests' '
+	(
+		git init "$REPO" &&
+		cd "$REPO" &&
+		test_commit a &&
+
+		# Local repo with many commits (so that negotiation will take
+		# more than 1 request/response pair)
+		rm -rf "$LOCAL_PRISTINE" &&
+		git clone "file://$REPO" "$LOCAL_PRISTINE" &&
+		cd "$LOCAL_PRISTINE" &&
+		git checkout -b side &&
+		for i in $(seq 1 33); do test_commit s$i; done &&
+
+		# Add novel commits to upstream
+		git checkout master &&
+		cd "$REPO" &&
+		git checkout -b o/foo &&
+		test_commit b &&
+		test_commit c &&
+		git checkout -b o/bar b &&
+		test_commit d &&
+		git checkout -b baz a &&
+		test_commit e &&
+		git checkout master &&
+		test_commit f
+	) &&
+	git -C "$REPO" config uploadpack.allowRefInWant true &&
+	git -C "$LOCAL_PRISTINE" config protocol.version 2
+'
+
+test_expect_success 'fetching with exact OID' '
+	test_when_finished "rm -f log" &&
+
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	GIT_TRACE_PACKET="$(pwd)/log" git -C local fetch origin \
+		$(git -C "$REPO" rev-parse d):refs/heads/actual &&
+
+	git -C "$REPO" rev-parse "d" >expected &&
+	git -C local rev-parse refs/heads/actual >actual &&
+	test_cmp expected actual &&
+	grep "want $(git -C "$REPO" rev-parse d)" log
+'
+
+test_expect_success 'fetching multiple refs' '
+	test_when_finished "rm -f log" &&
+
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	GIT_TRACE_PACKET="$(pwd)/log" git -C local fetch origin master baz &&
+
+	git -C "$REPO" rev-parse "master" "baz" >expected &&
+	git -C local rev-parse refs/remotes/origin/master refs/remotes/origin/baz >actual &&
+	test_cmp expected actual &&
+	grep "want-ref refs/heads/master" log &&
+	grep "want-ref refs/heads/baz" log
+'
+
+test_expect_success 'fetching ref and exact OID' '
+	test_when_finished "rm -f log" &&
+
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	GIT_TRACE_PACKET="$(pwd)/log" git -C local fetch origin \
+		master $(git -C "$REPO" rev-parse b):refs/heads/actual &&
+
+	git -C "$REPO" rev-parse "master" "b" >expected &&
+	git -C local rev-parse refs/remotes/origin/master refs/heads/actual >actual &&
+	test_cmp expected actual &&
+	grep "want $(git -C "$REPO" rev-parse b)" log &&
+	grep "want-ref refs/heads/master" log
+'
+
+test_expect_success 'fetching with wildcard that does not match any refs' '
+	test_when_finished "rm -f log" &&
+
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	git -C local fetch origin refs/heads/none*:refs/heads/* >out &&
+	test_must_be_empty out
+'
+
+test_expect_success 'fetching with wildcard that matches multiple refs' '
+	test_when_finished "rm -f log" &&
+
+	rm -rf local &&
+	cp -r "$LOCAL_PRISTINE" local &&
+	GIT_TRACE_PACKET="$(pwd)/log" git -C local fetch origin refs/heads/o*:refs/heads/o* &&
+
+	git -C "$REPO" rev-parse "o/foo" "o/bar" >expected &&
+	git -C local rev-parse "o/foo" "o/bar" >actual &&
+	test_cmp expected actual &&
+	grep "want-ref refs/heads/o/foo" log &&
+	grep "want-ref refs/heads/o/bar" log
+'
+
+test_done