buildgcc: Implement simple tarball hash verification

This patch implements a relatively simple hash-based verification scheme
for downloaded files (tarballs):

After buildgcc downloads a file or notices that it has already been
downloaded, it hashes the file, and compares the hash against the known
hash stored in util/crossgcc/sum/$filename.cksum. Two errors can occur:

1. The hash file is missing. In this case, crossgcc asks the user to
   verify the authenticity of the downloaded file. It also calculates
   its hash and stores it in util/crossgcc/sum/$filename.cksum.calc.
   If the file is authentic, the user may rename the calculated hash
   file to $filename.cksum, so that it can be found the next time
   buildgcc is started.

2. The known hash and the calculated hash differ. This is the case that
   this patch seeks to protect against, because it may imply that the
   downloaded file was unexpectedly changed, either in transit
   (Man-in-the-Middle attack) or on the file server that it was
   downloaded from. If buildgcc detects such a hash mismatch, it asks
   the user to delete the downloaded file and retry, because it can also
   be caused by a benign network error. If, however, the error persists,
   buildgcc can't continue without risking that the user runs malicious
   code, and it stops.

Note: The hash algorithm may be changed in the future, but for now I
left it at SHA-1, to avoid bloating this patch.

Change-Id: I0d5d67b34684d02011a845d00f6f5b6769f43b4f
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Reviewed-on: https://review.coreboot.org/21592
Tested-by: build bot (Jenkins) <no-reply@coreboot.org>
Reviewed-by: Paul Menzel <paulepanter@users.sourceforge.net>
Reviewed-by: Patrick Georgi <pgeorgi@google.com>

util/crossgcc/buildgcc

@@ -18,8 +18,8 @@
 
 cd $(dirname $0)
 
-CROSSGCC_DATE="August 16th, 2017"
+CROSSGCC_DATE="September 19th, 2017"
-CROSSGCC_VERSION="1.47"
+CROSSGCC_VERSION="1.48"
 CROSSGCC_COMMIT=$( git describe )
 
 # default settings
@@ -304,18 +304,6 @@ ada_requested() {
 	echo "${LANGUAGES}" | grep -q '\<ada\>'
 }
 
-check_sum() {
-	test -z "$CHECKSUM" || \
-	test "$(cat sum/$1.cksum 2>/dev/null | sed -e 's@.*\([0-9a-f]\{40,\}\).*@\1@')" = \
-	"$($CHECKSUM tarballs/$1 2>/dev/null | sed -e 's@.*\([0-9a-f]\{40,\}\).*@\1@')"
-}
-
-compute_sum() {
-	test ! -f sum/$1.cksum && test -f tarballs/$1 && \
-	(test -z "$CHECKSUM" || $CHECKSUM tarballs/$1 > sum/$1.cksum ) && \
-	printf "(checksum created. ${RED}Note. Please upload sum/$1.cksum if the corresponding archive is upgraded.)${NC}"
-}
-
 download() {
 	package=$1
 	archive="$(eval echo \$$package"_ARCHIVE")"
@@ -323,15 +311,14 @@ download() {
 	FILE=$(basename $archive)
 	printf " * $FILE "
 
-	if test -f tarballs/$FILE && check_sum $FILE ; then
+	if test -f tarballs/$FILE; then
-		echo "(cached)"
+		printf "(cached)... "
 	else
 		printf "(downloading from $archive)"
 		rm -f tarballs/$FILE
 		cd tarballs
 		download_showing_percentage $archive
 		cd ..
-		compute_sum $FILE
 	fi
 
 	if [ ! -f tarballs/$FILE ]; then
@@ -340,6 +327,91 @@ download() {
 	fi
 }
 
+# Compute the hash of the package given in $1, and print it raw (just the
+# hexadecimal hash).
+compute_hash() {
+	package=$1
+	archive="$(eval echo \$$package"_ARCHIVE")"
+	file="$(basename "$archive")"
+
+	if test -z "$CHECKSUM"; then
+		echo "${RED}\$CHECKSUM program missing. This is bad.${NC}" 1>&2
+		exit 1
+	fi
+
+	$CHECKSUM "tarballs/$file" 2>/dev/null | sed -e 's@.*\([0-9a-f]\{40,\}\).*@\1@'
+}
+
+error_hash_missing() {
+	package="$1"
+	archive="$(eval echo \$$package"_ARCHIVE")"
+	file="$(basename "$archive")"
+
+	fullhashfile="util/crossgcc/sum/$file.cksum"
+	printf "${RED}hash file missing:${NC}\n\n" 1>&2
+	printf "Please verify util/crossgcc/tarball/$file carefully\n" 1>&2
+	printf "(using PGP if possible), and then rename\n" 1>&2
+	printf "        ${CYAN}${fullhashfile}.calc${NC}\n" 1>&2
+	printf "     to ${CYAN}${fullhashfile}${NC}\n\n" 1>&2
+
+	exit 1
+}
+
+# Read the known hash file of the package given in $1, and print it raw.
+get_known_hash() {
+	package=$1
+	archive="$(eval echo \$$package"_ARCHIVE")"
+	file="$(basename "$archive")"
+	hashfile="sum/$file.cksum"
+
+	if [ ! -f "$hashfile" ]; then
+		calc_hash="$(compute_hash "$package")" || exit 1
+		echo "$calc_hash  tarballs/$file" > "${hashfile}.calc"
+
+		error_hash_missing "$package"
+		exit 1
+	fi
+
+	cat "$hashfile" | sed -e 's@.*\([0-9a-f]\{40,\}\).*@\1@'
+}
+
+error_hash_mismatch() {
+	package=$1
+	known_hash="$2"
+	computed_hash="$3"
+	archive="$(eval echo \$$package"_ARCHIVE")"
+	file="$(basename "$archive")"
+
+	printf "${RED}hash mismatch:${NC}\n\n"
+	printf "             expected (known) hash: $known_hash\n"
+	printf "calculated hash of downloaded file: $computed_hash\n\n"
+
+	printf "If you think this is due to a network error, please delete\n"
+	printf "  ${CYAN}util/crossgcc/tarballs/$file${NC}\n"
+	printf "and try again. If the problem persists, it may be due to an\n"
+	printf "administration error on the file server, or you might be\n"
+	printf "subject to a Man-in-the-Middle attack\n\n"
+
+	exit 1
+}
+
+# verify_hash - Check that the hash of the file given in $1 matches the known
+# hash; Bail out on mismatch or missing hash file.
+verify_hash() {
+	package=$1
+	archive="$(eval echo \$$package"_ARCHIVE")"
+
+	known_hash="$(get_known_hash "$package")" || exit "$?"
+	computed_hash="$(compute_hash "$package")" || exit "$?"
+
+	if [ "$known_hash" != "$computed_hash" ]; then
+		error_hash_mismatch "$package" "$known_hash" "$computed_hash"
+		exit 1
+	fi
+
+	printf "${GREEN}hash verified ("$known_hash")${NC}\n"
+}
+
 unpack_and_patch() {
 	package=$1
 	archive="$(eval echo \$$package"_ARCHIVE")"
@@ -965,7 +1037,7 @@ if searchtool wget "GNU" nofail > /dev/null; then
 		wget $url 2>&1 | while read line; do
 			echo $line | grep -o "[0-9]\+%" | awk '{printf("\b\b\b\b%4s", $1)}'
 		done
-		printf "${NC}\n"
+		printf "${NC}... "
 	}
 elif searchtool curl "^curl " > /dev/null; then
 	download_showing_percentage() {
@@ -1129,10 +1201,11 @@ export PATH=$DESTDIR$TARGETDIR/bin:$PATH
 
 # Download, unpack, patch and build all packages
 
-printf "Downloading tarballs ... \n"
+printf "Downloading and verifing tarballs ... \n"
 mkdir -p tarballs
 for P in $PACKAGES; do
-	download $P
+	download "$P" || exit "$?"
+	verify_hash "$P" || exit "$?"
 done
 printf "Downloaded tarballs ... ${green}ok${NC}\n"