Merge remote-tracking branch 'remotes/stsquad/tags/pull-testing-and-semihosting-280222-1' into staging

Testing and semihosting updates:

  - restore TESTS/IMAGES filtering to docker tests
  - add NOUSER to alpine image
  - bump lcitool version
  - move arm64/s390x cross build images to lcitool
  - add aarch32 runner CI scripts
  - expand testing to more vectors
  - update s390x jobs to focal for gitlab/travis
  - disable threadcount for all sh4
  - fix semihosting SYS_HEAPINFO and test

# gpg: Signature made Mon 28 Feb 2022 18:46:41 GMT
# gpg:                using RSA key 6685AE99E75167BCAFC8DF35FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>" [full]
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-testing-and-semihosting-280222-1:
  tests/tcg: port SYS_HEAPINFO to a system test
  semihosting/arm-compat: replace heuristic for softmmu SYS_HEAPINFO
  tests/tcg: completely disable threadcount for sh4
  gitlab: upgrade the job definition for s390x to 20.04
  travis.yml: Update the s390x jobs to Ubuntu Focal
  tests/tcg: add vectorised sha512 versions
  tests/tcg: add sha512 test
  tests/tcg: build sha1-vector with O3 and compare
  tests/tcg/ppc64: clean-up handling of byte-reverse
  gitlab: add a new aarch32 custom runner definition
  scripts/ci: allow for a secondary runner
  scripts/ci: add build env rules for aarch32 on aarch64
  tests/docker: introduce debian-riscv64-test-cross
  tests/docker: update debian-s390x-cross with lcitool
  tests/docker: update debian-arm64-cross with lcitool
  tests/lcitool: update to latest version
  tests/docker: add NOUSER for alpine image
  tests/docker: restore TESTS/IMAGES filtering

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

21 files changed, 1529 insertions, 94 deletions

diff --git a/tests/docker/Makefile.include b/tests/docker/Makefile.include
index f1a0c5db7a..e495b163a0 100644
--- a/tests/docker/Makefile.include
+++ b/tests/docker/Makefile.include
@@ -8,13 +8,19 @@ COMMA := ,
 
 HOST_ARCH = $(if $(ARCH),$(ARCH),$(shell uname -m))
 
+# These variables can be set by the user to limit the set of docker
+# images and tests to a more restricted subset
+TESTS ?= %
+IMAGES ?= %
+
 DOCKER_SUFFIX := .docker
 DOCKER_FILES_DIR := $(SRC_PATH)/tests/docker/dockerfiles
 # we don't run tests on intermediate images (used as base by another image)
 DOCKER_PARTIAL_IMAGES := debian10 debian11
 # we don't directly build virtual images (they are used to build other images)
 DOCKER_VIRTUAL_IMAGES := debian-bootstrap debian-toolchain empty
-DOCKER_IMAGES := $(sort $(filter-out $(DOCKER_VIRTUAL_IMAGES), $(notdir $(basename $(wildcard $(DOCKER_FILES_DIR)/*.docker)))))
+__IMAGES := $(sort $(filter-out $(DOCKER_VIRTUAL_IMAGES), $(notdir $(basename $(wildcard $(DOCKER_FILES_DIR)/*.docker)))))
+DOCKER_IMAGES := $(if $(IMAGES), $(filter $(IMAGES), $(__IMAGES)), $(__IMAGES))
 DOCKER_TARGETS := $(patsubst %,docker-image-%,$(DOCKER_IMAGES))
 # Use a global constant ccache directory to speed up repetitive builds
 DOCKER_CCACHE_DIR := $$HOME/.cache/qemu-docker-ccache
@@ -23,16 +29,14 @@ DOCKER_DEFAULT_REGISTRY := registry.gitlab.com/qemu-project/qemu
 endif
 DOCKER_REGISTRY := $(if $(REGISTRY),$(REGISTRY),$(DOCKER_DEFAULT_REGISTRY))
 
-DOCKER_TESTS := $(notdir $(shell \
-	find $(SRC_PATH)/tests/docker/ -name 'test-*' -type f))
+__TESTS := $(notdir $(shell \
+		find $(SRC_PATH)/tests/docker/ -name 'test-*' -type f))
+DOCKER_TESTS := $(if $(TESTS), $(filter $(TESTS), $(__TESTS)), $(__TESTS))
 
 ENGINE := auto
 
 DOCKER_SCRIPT=$(SRC_PATH)/tests/docker/docker.py --engine $(ENGINE)
 
-TESTS ?= %
-IMAGES ?= %
-
 CUR_TIME := $(shell date +%Y-%m-%d-%H.%M.%S.$$$$)
 DOCKER_SRC_COPY := $(BUILD_DIR)/docker-src.$(CUR_TIME)
 
@@ -133,7 +137,6 @@ DOCKER_PARTIAL_IMAGES += fedora
 endif
 
 docker-image-debian-alpha-cross: docker-image-debian10
-docker-image-debian-arm64-cross: docker-image-debian10
 docker-image-debian-armel-cross: docker-image-debian10
 docker-image-debian-armhf-cross: docker-image-debian10
 docker-image-debian-hppa-cross: docker-image-debian10
@@ -143,7 +146,6 @@ docker-image-debian-mips64-cross: docker-image-debian10
 docker-image-debian-mips64el-cross: docker-image-debian10
 docker-image-debian-mipsel-cross: docker-image-debian10
 docker-image-debian-ppc64el-cross: docker-image-debian10
-docker-image-debian-s390x-cross: docker-image-debian10
 docker-image-debian-sh4-cross: docker-image-debian10
 docker-image-debian-sparc64-cross: docker-image-debian10
 
@@ -154,6 +156,9 @@ docker-image-debian-native: DOCKER_REGISTRY=
 docker-image-debian10: NOUSER=1
 docker-image-debian11: NOUSER=1
 
+# alpine has no adduser
+docker-image-alpine: NOUSER=1
+
 #
 # The build rule for hexagon-cross is special in so far for most of
 # the time we don't want to build it. While dockers caching does avoid
@@ -206,19 +211,19 @@ docker-image-debian-nios2-cross: $(DOCKER_FILES_DIR)/debian-toolchain.docker \
 # Specialist build images, sometimes very limited tools
 docker-image-debian-tricore-cross: docker-image-debian10
 docker-image-debian-all-test-cross: docker-image-debian10
-docker-image-debian-arm64-test-cross: docker-image-debian11
 docker-image-debian-microblaze-cross: docker-image-debian10
 docker-image-debian-nios2-cross: docker-image-debian10
 docker-image-debian-powerpc-test-cross: docker-image-debian11
+docker-image-debian-riscv64-test-cross: docker-image-debian11
 
 # These images may be good enough for building tests but not for test builds
 DOCKER_PARTIAL_IMAGES += debian-alpha-cross
-DOCKER_PARTIAL_IMAGES += debian-arm64-test-cross
 DOCKER_PARTIAL_IMAGES += debian-powerpc-test-cross
 DOCKER_PARTIAL_IMAGES += debian-hppa-cross
 DOCKER_PARTIAL_IMAGES += debian-m68k-cross debian-mips64-cross
 DOCKER_PARTIAL_IMAGES += debian-microblaze-cross
 DOCKER_PARTIAL_IMAGES += debian-nios2-cross
+DOCKER_PARTIAL_IMAGES += debian-riscv64-test-cross
 DOCKER_PARTIAL_IMAGES += debian-sh4-cross debian-sparc64-cross
 DOCKER_PARTIAL_IMAGES += debian-tricore-cross
 DOCKER_PARTIAL_IMAGES += debian-xtensa-cross
@@ -274,8 +279,8 @@ endif
 	@echo '    TARGET_LIST=a,b,c    Override target list in builds.'
 	@echo '    EXTRA_CONFIGURE_OPTS="..."'
 	@echo '                         Extra configure options.'
-	@echo '    IMAGES="a b c ..":   Filters which images to build or run.'
-	@echo '    TESTS="x y z .."     Filters which tests to run (for docker-test).'
+	@echo '    IMAGES="a b c ..":   Restrict available images to subset.'
+	@echo '    TESTS="x y z .."     Restrict available tests to subset.'
 	@echo '    J=[0..9]*            Overrides the -jN parameter for make commands'
 	@echo '                         (default is 1)'
 	@echo '    DEBUG=1              Stop and drop to shell in the created container'
diff --git a/tests/docker/dockerfiles/debian-arm64-cross.docker b/tests/docker/dockerfiles/debian-arm64-cross.docker
index 166e24df13..589510a7be 100644
--- a/tests/docker/dockerfiles/debian-arm64-cross.docker
+++ b/tests/docker/dockerfiles/debian-arm64-cross.docker
@@ -1,32 +1,166 @@
+# THIS FILE WAS AUTO-GENERATED
 #
-# Docker arm64 cross-compiler target
+#  $ lcitool dockerfile --layers all --cross aarch64 debian-11 qemu
 #
-# This docker target builds on the debian Buster base image.
-#
-FROM qemu/debian10
+# https://gitlab.com/libvirt/libvirt-ci
 
-# Add the foreign architecture we want and install dependencies
-RUN dpkg --add-architecture arm64
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-    apt install -y --no-install-recommends \
-        crossbuild-essential-arm64
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-    apt build-dep -yy -a arm64 --arch-only qemu
+FROM docker.io/library/debian:11-slim
 
-# Specify the cross prefix for this image (see tests/docker/common.rc)
-ENV QEMU_CONFIGURE_OPTS --cross-prefix=aarch64-linux-gnu-
-ENV DEF_TARGET_LIST aarch64-softmmu,aarch64-linux-user
+RUN export DEBIAN_FRONTEND=noninteractive && \
+    apt-get update && \
+    apt-get install -y eatmydata && \
+    eatmydata apt-get dist-upgrade -y && \
+    eatmydata apt-get install --no-install-recommends -y \
+            bash \
+            bc \
+            bsdextrautils \
+            bzip2 \
+            ca-certificates \
+            ccache \
+            dbus \
+            debianutils \
+            diffutils \
+            exuberant-ctags \
+            findutils \
+            gcovr \
+            genisoimage \
+            gettext \
+            git \
+            hostname \
+            libpcre2-dev \
+            libspice-protocol-dev \
+            libtest-harness-perl \
+            llvm \
+            locales \
+            make \
+            meson \
+            ncat \
+            ninja-build \
+            openssh-client \
+            perl-base \
+            pkgconf \
+            python3 \
+            python3-numpy \
+            python3-opencv \
+            python3-pillow \
+            python3-pip \
+            python3-sphinx \
+            python3-sphinx-rtd-theme \
+            python3-venv \
+            python3-yaml \
+            rpm2cpio \
+            sed \
+            sparse \
+            tar \
+            tesseract-ocr \
+            tesseract-ocr-eng \
+            texinfo && \
+    eatmydata apt-get autoremove -y && \
+    eatmydata apt-get autoclean -y && \
+    sed -Ei 's,^# (en_US\.UTF-8 .*)$,\1,' /etc/locale.gen && \
+    dpkg-reconfigure locales
 
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-    apt install -y --no-install-recommends \
-        libbz2-dev:arm64 \
-        liblzo2-dev:arm64 \
-        librdmacm-dev:arm64 \
-        libsnappy-dev:arm64 \
-        libxen-dev:arm64
+ENV LANG "en_US.UTF-8"
+ENV MAKE "/usr/bin/make"
+ENV NINJA "/usr/bin/ninja"
+ENV PYTHON "/usr/bin/python3"
+ENV CCACHE_WRAPPERSDIR "/usr/libexec/ccache-wrappers"
 
-# nettle
-ENV QEMU_CONFIGURE_OPTS $QEMU_CONFIGURE_OPTS --enable-nettle
+RUN export DEBIAN_FRONTEND=noninteractive && \
+    dpkg --add-architecture arm64 && \
+    eatmydata apt-get update && \
+    eatmydata apt-get dist-upgrade -y && \
+    eatmydata apt-get install --no-install-recommends -y dpkg-dev && \
+    eatmydata apt-get install --no-install-recommends -y \
+            g++-aarch64-linux-gnu \
+            gcc-aarch64-linux-gnu \
+            libaio-dev:arm64 \
+            libasan5:arm64 \
+            libasound2-dev:arm64 \
+            libattr1-dev:arm64 \
+            libbpf-dev:arm64 \
+            libbrlapi-dev:arm64 \
+            libbz2-dev:arm64 \
+            libc6-dev:arm64 \
+            libcacard-dev:arm64 \
+            libcap-ng-dev:arm64 \
+            libcapstone-dev:arm64 \
+            libcurl4-gnutls-dev:arm64 \
+            libdaxctl-dev:arm64 \
+            libdrm-dev:arm64 \
+            libepoxy-dev:arm64 \
+            libfdt-dev:arm64 \
+            libffi-dev:arm64 \
+            libfuse3-dev:arm64 \
+            libgbm-dev:arm64 \
+            libgcrypt20-dev:arm64 \
+            libglib2.0-dev:arm64 \
+            libglusterfs-dev:arm64 \
+            libgnutls28-dev:arm64 \
+            libgtk-3-dev:arm64 \
+            libibumad-dev:arm64 \
+            libibverbs-dev:arm64 \
+            libiscsi-dev:arm64 \
+            libjemalloc-dev:arm64 \
+            libjpeg62-turbo-dev:arm64 \
+            liblttng-ust-dev:arm64 \
+            liblzo2-dev:arm64 \
+            libncursesw5-dev:arm64 \
+            libnfs-dev:arm64 \
+            libnuma-dev:arm64 \
+            libpam0g-dev:arm64 \
+            libpixman-1-dev:arm64 \
+            libpng-dev:arm64 \
+            libpulse-dev:arm64 \
+            librbd-dev:arm64 \
+            librdmacm-dev:arm64 \
+            libsasl2-dev:arm64 \
+            libsdl2-dev:arm64 \
+            libsdl2-image-dev:arm64 \
+            libseccomp-dev:arm64 \
+            libselinux1-dev:arm64 \
+            libslirp-dev:arm64 \
+            libsnappy-dev:arm64 \
+            libspice-server-dev:arm64 \
+            libssh-gcrypt-dev:arm64 \
+            libsystemd-dev:arm64 \
+            libtasn1-6-dev:arm64 \
+            libubsan1:arm64 \
+            libudev-dev:arm64 \
+            liburing-dev:arm64 \
+            libusb-1.0-0-dev:arm64 \
+            libusbredirhost-dev:arm64 \
+            libvdeplug-dev:arm64 \
+            libvirglrenderer-dev:arm64 \
+            libvte-2.91-dev:arm64 \
+            libxen-dev:arm64 \
+            libzstd-dev:arm64 \
+            nettle-dev:arm64 \
+            systemtap-sdt-dev:arm64 \
+            xfslibs-dev:arm64 \
+            zlib1g-dev:arm64 && \
+    eatmydata apt-get autoremove -y && \
+    eatmydata apt-get autoclean -y && \
+    mkdir -p /usr/local/share/meson/cross && \
+    echo "[binaries]\n\
+c = '/usr/bin/aarch64-linux-gnu-gcc'\n\
+ar = '/usr/bin/aarch64-linux-gnu-gcc-ar'\n\
+strip = '/usr/bin/aarch64-linux-gnu-strip'\n\
+pkgconfig = '/usr/bin/aarch64-linux-gnu-pkg-config'\n\
+\n\
+[host_machine]\n\
+system = 'linux'\n\
+cpu_family = 'aarch64'\n\
+cpu = 'aarch64'\n\
+endian = 'little'" > /usr/local/share/meson/cross/aarch64-linux-gnu && \
+    dpkg-query --showformat '${Package}_${Version}_${Architecture}\n' --show > /packages.txt && \
+    mkdir -p /usr/libexec/ccache-wrappers && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/aarch64-linux-gnu-c++ && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/aarch64-linux-gnu-cc && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/aarch64-linux-gnu-g++ && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/aarch64-linux-gnu-gcc
+
+ENV ABI "aarch64-linux-gnu"
+ENV MESON_OPTS "--cross-file=aarch64-linux-gnu"
+ENV QEMU_CONFIGURE_OPTS --cross-prefix=aarch64-linux-gnu-
+ENV DEF_TARGET_LIST aarch64-softmmu,aarch64-linux-user
diff --git a/tests/docker/dockerfiles/debian-arm64-test-cross.docker b/tests/docker/dockerfiles/debian-arm64-test-cross.docker
deleted file mode 100644
index 53a9012beb..0000000000
--- a/tests/docker/dockerfiles/debian-arm64-test-cross.docker
+++ /dev/null
@@ -1,13 +0,0 @@
-#
-# Docker arm64 cross-compiler target (tests only)
-#
-# This docker target builds on the debian Bullseye base image.
-#
-FROM qemu/debian11
-
-# Add the foreign architecture we want and install dependencies
-RUN dpkg --add-architecture arm64
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-        apt install -y --no-install-recommends \
-        crossbuild-essential-arm64 gcc-10-aarch64-linux-gnu
diff --git a/tests/docker/dockerfiles/debian-riscv64-test-cross.docker b/tests/docker/dockerfiles/debian-riscv64-test-cross.docker
new file mode 100644
index 0000000000..1d90901298
--- /dev/null
+++ b/tests/docker/dockerfiles/debian-riscv64-test-cross.docker
@@ -0,0 +1,12 @@
+#
+# Docker cross-compiler target
+#
+# This docker target builds on the Debian Bullseye base image.
+#
+FROM qemu/debian11
+
+RUN apt update && \
+    DEBIAN_FRONTEND=noninteractive eatmydata \
+    apt install -y --no-install-recommends \
+        gcc-riscv64-linux-gnu \
+        libc6-dev-riscv64-cross
diff --git a/tests/docker/dockerfiles/debian-s390x-cross.docker b/tests/docker/dockerfiles/debian-s390x-cross.docker
index 9f2ab51eb0..aa1bd6eb4c 100644
--- a/tests/docker/dockerfiles/debian-s390x-cross.docker
+++ b/tests/docker/dockerfiles/debian-s390x-cross.docker
@@ -1,33 +1,164 @@
+# THIS FILE WAS AUTO-GENERATED
 #
-# Docker s390 cross-compiler target
+#  $ lcitool dockerfile --layers all --cross s390x debian-11 qemu
 #
-# This docker target builds on the debian Stretch base image.
-#
-FROM qemu/debian10
+# https://gitlab.com/libvirt/libvirt-ci
+
+FROM docker.io/library/debian:11-slim
 
-# Add the s390x architecture
-RUN dpkg --add-architecture s390x
+RUN export DEBIAN_FRONTEND=noninteractive && \
+    apt-get update && \
+    apt-get install -y eatmydata && \
+    eatmydata apt-get dist-upgrade -y && \
+    eatmydata apt-get install --no-install-recommends -y \
+            bash \
+            bc \
+            bsdextrautils \
+            bzip2 \
+            ca-certificates \
+            ccache \
+            dbus \
+            debianutils \
+            diffutils \
+            exuberant-ctags \
+            findutils \
+            gcovr \
+            genisoimage \
+            gettext \
+            git \
+            hostname \
+            libpcre2-dev \
+            libspice-protocol-dev \
+            libtest-harness-perl \
+            llvm \
+            locales \
+            make \
+            meson \
+            ncat \
+            ninja-build \
+            openssh-client \
+            perl-base \
+            pkgconf \
+            python3 \
+            python3-numpy \
+            python3-opencv \
+            python3-pillow \
+            python3-pip \
+            python3-sphinx \
+            python3-sphinx-rtd-theme \
+            python3-venv \
+            python3-yaml \
+            rpm2cpio \
+            sed \
+            sparse \
+            tar \
+            tesseract-ocr \
+            tesseract-ocr-eng \
+            texinfo && \
+    eatmydata apt-get autoremove -y && \
+    eatmydata apt-get autoclean -y && \
+    sed -Ei 's,^# (en_US\.UTF-8 .*)$,\1,' /etc/locale.gen && \
+    dpkg-reconfigure locales
 
-# Grab the updated list of packages
-RUN apt update && apt dist-upgrade -yy
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-    apt install -y --no-install-recommends \
-        gcc-multilib-s390x-linux-gnu
+ENV LANG "en_US.UTF-8"
+ENV MAKE "/usr/bin/make"
+ENV NINJA "/usr/bin/ninja"
+ENV PYTHON "/usr/bin/python3"
+ENV CCACHE_WRAPPERSDIR "/usr/libexec/ccache-wrappers"
 
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-    apt build-dep -yy -a s390x --arch-only qemu
+RUN export DEBIAN_FRONTEND=noninteractive && \
+    dpkg --add-architecture s390x && \
+    eatmydata apt-get update && \
+    eatmydata apt-get dist-upgrade -y && \
+    eatmydata apt-get install --no-install-recommends -y dpkg-dev && \
+    eatmydata apt-get install --no-install-recommends -y \
+            g++-s390x-linux-gnu \
+            gcc-s390x-linux-gnu \
+            libaio-dev:s390x \
+            libasan5:s390x \
+            libasound2-dev:s390x \
+            libattr1-dev:s390x \
+            libbpf-dev:s390x \
+            libbrlapi-dev:s390x \
+            libbz2-dev:s390x \
+            libc6-dev:s390x \
+            libcacard-dev:s390x \
+            libcap-ng-dev:s390x \
+            libcapstone-dev:s390x \
+            libcurl4-gnutls-dev:s390x \
+            libdaxctl-dev:s390x \
+            libdrm-dev:s390x \
+            libepoxy-dev:s390x \
+            libfdt-dev:s390x \
+            libffi-dev:s390x \
+            libfuse3-dev:s390x \
+            libgbm-dev:s390x \
+            libgcrypt20-dev:s390x \
+            libglib2.0-dev:s390x \
+            libglusterfs-dev:s390x \
+            libgnutls28-dev:s390x \
+            libgtk-3-dev:s390x \
+            libibumad-dev:s390x \
+            libibverbs-dev:s390x \
+            libiscsi-dev:s390x \
+            libjemalloc-dev:s390x \
+            libjpeg62-turbo-dev:s390x \
+            liblttng-ust-dev:s390x \
+            liblzo2-dev:s390x \
+            libncursesw5-dev:s390x \
+            libnfs-dev:s390x \
+            libnuma-dev:s390x \
+            libpam0g-dev:s390x \
+            libpixman-1-dev:s390x \
+            libpng-dev:s390x \
+            libpulse-dev:s390x \
+            librbd-dev:s390x \
+            librdmacm-dev:s390x \
+            libsasl2-dev:s390x \
+            libsdl2-dev:s390x \
+            libsdl2-image-dev:s390x \
+            libseccomp-dev:s390x \
+            libselinux1-dev:s390x \
+            libslirp-dev:s390x \
+            libsnappy-dev:s390x \
+            libssh-gcrypt-dev:s390x \
+            libsystemd-dev:s390x \
+            libtasn1-6-dev:s390x \
+            libubsan1:s390x \
+            libudev-dev:s390x \
+            liburing-dev:s390x \
+            libusb-1.0-0-dev:s390x \
+            libusbredirhost-dev:s390x \
+            libvdeplug-dev:s390x \
+            libvirglrenderer-dev:s390x \
+            libvte-2.91-dev:s390x \
+            libzstd-dev:s390x \
+            nettle-dev:s390x \
+            systemtap-sdt-dev:s390x \
+            xfslibs-dev:s390x \
+            zlib1g-dev:s390x && \
+    eatmydata apt-get autoremove -y && \
+    eatmydata apt-get autoclean -y && \
+    mkdir -p /usr/local/share/meson/cross && \
+    echo "[binaries]\n\
+c = '/usr/bin/s390x-linux-gnu-gcc'\n\
+ar = '/usr/bin/s390x-linux-gnu-gcc-ar'\n\
+strip = '/usr/bin/s390x-linux-gnu-strip'\n\
+pkgconfig = '/usr/bin/s390x-linux-gnu-pkg-config'\n\
+\n\
+[host_machine]\n\
+system = 'linux'\n\
+cpu_family = 's390x'\n\
+cpu = 's390x'\n\
+endian = 'big'" > /usr/local/share/meson/cross/s390x-linux-gnu && \
+    dpkg-query --showformat '${Package}_${Version}_${Architecture}\n' --show > /packages.txt && \
+    mkdir -p /usr/libexec/ccache-wrappers && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/s390x-linux-gnu-c++ && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/s390x-linux-gnu-cc && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/s390x-linux-gnu-g++ && \
+    ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/s390x-linux-gnu-gcc
 
-# Specify the cross prefix for this image (see tests/docker/common.rc)
+ENV ABI "s390x-linux-gnu"
+ENV MESON_OPTS "--cross-file=s390x-linux-gnu"
 ENV QEMU_CONFIGURE_OPTS --cross-prefix=s390x-linux-gnu-
 ENV DEF_TARGET_LIST s390x-softmmu,s390x-linux-user
-
-# Install extra libraries to increase code coverage
-RUN apt update && \
-    DEBIAN_FRONTEND=noninteractive eatmydata \
-    apt install -y --no-install-recommends \
-        libbz2-dev:s390x \
-        liblzo2-dev:s390x \
-        librdmacm-dev:s390x \
-        libsnappy-dev:s390x
diff --git a/tests/docker/dockerfiles/opensuse-leap.docker b/tests/docker/dockerfiles/opensuse-leap.docker
index 1b78d8369a..e1ad9434a3 100644
--- a/tests/docker/dockerfiles/opensuse-leap.docker
+++ b/tests/docker/dockerfiles/opensuse-leap.docker
@@ -127,8 +127,7 @@ RUN zypper update -y && \
     ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/g++ && \
     ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/gcc
 
-RUN pip3 install \
-         meson==0.56.0
+RUN pip3 install meson==0.56.0
 
 ENV LANG "en_US.UTF-8"
 ENV MAKE "/usr/bin/make"
diff --git a/tests/docker/dockerfiles/ubuntu1804.docker b/tests/docker/dockerfiles/ubuntu1804.docker
index 699f2dfc6a..0a622b467c 100644
--- a/tests/docker/dockerfiles/ubuntu1804.docker
+++ b/tests/docker/dockerfiles/ubuntu1804.docker
@@ -134,8 +134,7 @@ RUN export DEBIAN_FRONTEND=noninteractive && \
     ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/g++ && \
     ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/gcc
 
-RUN pip3 install \
-         meson==0.56.0
+RUN pip3 install meson==0.56.0
 
 ENV LANG "en_US.UTF-8"
 ENV MAKE "/usr/bin/make"
diff --git a/tests/docker/dockerfiles/ubuntu2004.docker b/tests/docker/dockerfiles/ubuntu2004.docker
index 87513125b8..b9d06cb040 100644
--- a/tests/docker/dockerfiles/ubuntu2004.docker
+++ b/tests/docker/dockerfiles/ubuntu2004.docker
@@ -136,8 +136,7 @@ RUN export DEBIAN_FRONTEND=noninteractive && \
     ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/g++ && \
     ln -s /usr/bin/ccache /usr/libexec/ccache-wrappers/gcc
 
-RUN pip3 install \
-         meson==0.56.0
+RUN pip3 install meson==0.56.0
 
 ENV LANG "en_US.UTF-8"
 ENV MAKE "/usr/bin/make"
diff --git a/tests/lcitool/libvirt-ci b/tests/lcitool/libvirt-ci
-Subproject 6dd9b6fab1fe081b16bc975485d7a02c81ba5fb
+Subproject f83b916d5efa4bd33fbf4b7ea41bf6d535cc63f
diff --git a/tests/lcitool/refresh b/tests/lcitool/refresh
index 4ab90a310a..1f00281b44 100755
--- a/tests/lcitool/refresh
+++ b/tests/lcitool/refresh
@@ -76,6 +76,12 @@ ubuntu2004_tsanhack = [
    "RUN sed -i 's/^const/static const/g' /usr/lib/llvm-10/lib/clang/10.0.0/include/sanitizer/tsan_interface.h\n"
 ]
 
+def debian_cross_build(prefix, targets):
+   conf = "ENV QEMU_CONFIGURE_OPTS --cross-prefix=%s\n" % (prefix)
+   targets = "ENV DEF_TARGET_LIST %s\n" % (targets)
+   return "".join([conf, targets])
+
+
 try:
    generate_dockerfile("centos8", "centos-stream-8")
    generate_dockerfile("fedora", "fedora-35")
@@ -86,6 +92,16 @@ try:
    generate_dockerfile("opensuse-leap", "opensuse-leap-152")
    generate_dockerfile("alpine", "alpine-edge")
 
+   generate_dockerfile("debian-arm64-cross", "debian-11",
+                       cross="aarch64",
+                       trailer=debian_cross_build("aarch64-linux-gnu-",
+                                                  "aarch64-softmmu,aarch64-linux-user"))
+
+   generate_dockerfile("debian-s390x-cross", "debian-11",
+                       cross="s390x",
+                       trailer=debian_cross_build("s390x-linux-gnu-",
+                                                  "s390x-softmmu,s390x-linux-user"))
+
    generate_cirrus("freebsd-12")
    generate_cirrus("freebsd-13")
    generate_cirrus("macos-11")
diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target
index 1d967901bd..ac07acde66 100644
--- a/tests/tcg/aarch64/Makefile.target
+++ b/tests/tcg/aarch64/Makefile.target
@@ -50,6 +50,23 @@ sysregs: CFLAGS+=-march=armv8.1-a+sve
 AARCH64_TESTS += sve-ioctls
 sve-ioctls: CFLAGS+=-march=armv8.1-a+sve
 
+# Vector SHA1
+sha1-vector: CFLAGS=-O3
+sha1-vector: sha1.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+run-sha1-vector: sha1-vector run-sha1
+	$(call run-test, $<, $(QEMU) $(QEMU_OPTS) $<, "$< on $(TARGET_NAME)")
+	$(call diff-out, sha1-vector, sha1.out)
+
+TESTS += sha1-vector
+
+# Vector versions of sha512 (-O3 triggers vectorisation)
+sha512-vector: CFLAGS=-O3
+sha512-vector: sha512.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+TESTS += sha512-vector
+
 ifneq ($(HAVE_GDB_BIN),)
 GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
 
diff --git a/tests/tcg/aarch64/system/semiheap.c b/tests/tcg/aarch64/system/semiheap.c
new file mode 100644
index 0000000000..4ed258476d
--- /dev/null
+++ b/tests/tcg/aarch64/system/semiheap.c
@@ -0,0 +1,93 @@
+/*
+ * Semihosting System HEAPINFO Test
+ *
+ * Copyright (c) 2021 Linaro Ltd
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include <inttypes.h>
+#include <stddef.h>
+#include <minilib.h>
+
+#define SYS_HEAPINFO    0x16
+
+uintptr_t __semi_call(uintptr_t type, uintptr_t arg0)
+{
+    register uintptr_t t asm("x0") = type;
+    register uintptr_t a0 asm("x1") = arg0;
+    asm("hlt 0xf000"
+        : "=r" (t)
+        : "r" (t), "r" (a0)
+        : "memory" );
+
+    return t;
+}
+
+int main(int argc, char *argv[argc])
+{
+    struct {
+        void *heap_base;
+        void *heap_limit;
+        void *stack_base;
+        void *stack_limit;
+    } info = { };
+    void *ptr_to_info = (void *) &info;
+    uint32_t *ptr_to_heap;
+    int i;
+
+    ml_printf("Semihosting Heap Info Test\n");
+
+    __semi_call(SYS_HEAPINFO, (uintptr_t) &ptr_to_info);
+
+    if (info.heap_base == NULL || info.heap_limit == NULL) {
+        ml_printf("null heap: %p -> %p\n", info.heap_base, info.heap_limit);
+        return -1;
+    }
+
+    /* Error if heap base is above limit */
+    if ((uintptr_t) info.heap_base >= (uintptr_t) info.heap_limit) {
+        ml_printf("heap base %p >= heap_limit %p\n",
+               info.heap_base, info.heap_limit);
+        return -2;
+    }
+
+    if (info.stack_base == NULL) {
+        ml_printf("null stack: %p -> %p\n", info.stack_base, info.stack_limit);
+        return -3;
+    }
+
+    /*
+     * boot.S put our stack somewhere inside the data segment of the
+     * ELF file, and we know that SYS_HEAPINFO won't pick a range
+     * that overlaps with part of a loaded ELF file. So the info
+     * struct (on the stack) should not be inside the reported heap.
+     */
+    if (ptr_to_info > info.heap_base && ptr_to_info < info.heap_limit) {
+        ml_printf("info appears to be inside the heap: %p in %p:%p\n",
+               ptr_to_info, info.heap_base, info.heap_limit);
+        return -4;
+    }
+
+    ml_printf("heap: %p -> %p\n", info.heap_base, info.heap_limit);
+    ml_printf("stack: %p <- %p\n", info.stack_limit, info.stack_base);
+
+    /* finally can we read/write the heap */
+    ptr_to_heap = (uint32_t *) info.heap_base;
+    for (i = 0; i < 512; i++) {
+        *ptr_to_heap++ = i;
+    }
+    ptr_to_heap = (uint32_t *) info.heap_base;
+    for (i = 0; i < 512; i++) {
+        uint32_t tmp = *ptr_to_heap;
+        if (tmp != i) {
+            ml_printf("unexpected value in heap: %d @ %p", tmp, ptr_to_heap);
+            return -5;
+        }
+        ptr_to_heap++;
+    }
+    ml_printf("r/w to heap upto %p\n", ptr_to_heap);
+
+    ml_printf("Passed HeapInfo checks\n");
+    return 0;
+}
diff --git a/tests/tcg/arm/Makefile.target b/tests/tcg/arm/Makefile.target
index f509d823d4..2f815120a5 100644
--- a/tests/tcg/arm/Makefile.target
+++ b/tests/tcg/arm/Makefile.target
@@ -70,6 +70,23 @@ endif
 
 ARM_TESTS += commpage
 
+# Vector SHA1
+sha1-vector: CFLAGS=-O3
+sha1-vector: sha1.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+run-sha1-vector: sha1-vector run-sha1
+	$(call run-test, $<, $(QEMU) $(QEMU_OPTS) $<, "$< on $(TARGET_NAME)")
+	$(call diff-out, sha1-vector, sha1.out)
+
+ARM_TESTS += sha1-vector
+
+# Vector versions of sha512 (-O3 triggers vectorisation)
+sha512-vector: CFLAGS=-O3
+sha512-vector: sha512.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+ARM_TESTS += sha512-vector
+
 TESTS += $(ARM_TESTS)
 
 # On ARM Linux only supports 4k pages
diff --git a/tests/tcg/configure.sh b/tests/tcg/configure.sh
index 763e9b6ad8..0663bd19f4 100755
--- a/tests/tcg/configure.sh
+++ b/tests/tcg/configure.sh
@@ -97,7 +97,7 @@ for target in $target_list; do
     aarch64-*)
       # We don't have any bigendian build tools so we only use this for AArch64
       container_hosts="x86_64 aarch64"
-      container_image=debian-arm64-test-cross
+      container_image=debian-arm64-cross
       container_cross_cc=aarch64-linux-gnu-gcc-10
       ;;
     alpha-*)
@@ -180,7 +180,7 @@ for target in $target_list; do
       ;;
     riscv64-*)
       container_hosts=x86_64
-      container_image=debian-riscv64-cross
+      container_image=debian-riscv64-test-cross
       container_cross_cc=riscv64-linux-gnu-gcc
       ;;
     s390x-*)
diff --git a/tests/tcg/i386/Makefile.target b/tests/tcg/i386/Makefile.target
index 38c10379af..e1c0310be6 100644
--- a/tests/tcg/i386/Makefile.target
+++ b/tests/tcg/i386/Makefile.target
@@ -71,3 +71,12 @@ TESTS=$(MULTIARCH_TESTS) $(I386_TESTS)
 
 # On i386 and x86_64 Linux only supports 4k pages (large pages are a different hack)
 EXTRA_RUNS+=run-test-mmap-4096
+
+sha512-sse: CFLAGS=-msse4.1 -O3
+sha512-sse: sha512.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+run-sha512-sse: QEMU_OPTS+=-cpu max
+run-plugin-sha512-sse-with-%: QEMU_OPTS+=-cpu max
+
+TESTS+=sha512-sse
diff --git a/tests/tcg/multiarch/sha512.c b/tests/tcg/multiarch/sha512.c
new file mode 100644
index 0000000000..e1729828b9
--- /dev/null
+++ b/tests/tcg/multiarch/sha512.c
@@ -0,0 +1,990 @@
+/*
+ * sha512 test based on CCAN: https://ccodearchive.net/info/crypto/sha512.html
+ *
+ * src/crypto/sha512.cpp commit f914f1a746d7f91951c1da262a4a749dd3ebfa71
+ * Copyright (c) 2014 The Bitcoin Core developers
+ * Distributed under the MIT software license, see:
+ *  http://www.opensource.org/licenses/mit-license.php.
+ *
+ * SPDX-License-Identifier: MIT CC0-1.0
+ */
+#define _GNU_SOURCE         /* See feature_test_macros(7) */
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <stdarg.h>
+
+/* Required portions from endian.h */
+
+/**
+ * BSWAP_64 - reverse bytes in a constant uint64_t value.
+ * @val: constantvalue whose bytes to swap.
+ *
+ * Designed to be usable in constant-requiring initializers.
+ *
+ * Example:
+ *  struct mystruct {
+ *      char buf[BSWAP_64(0xff00000000000000ULL)];
+ *  };
+ */
+#define BSWAP_64(val)                       \
+    ((((uint64_t)(val) & 0x00000000000000ffULL) << 56)  \
+     | (((uint64_t)(val) & 0x000000000000ff00ULL) << 40)    \
+     | (((uint64_t)(val) & 0x0000000000ff0000ULL) << 24)    \
+     | (((uint64_t)(val) & 0x00000000ff000000ULL) << 8)     \
+     | (((uint64_t)(val) & 0x000000ff00000000ULL) >> 8)     \
+     | (((uint64_t)(val) & 0x0000ff0000000000ULL) >> 24)    \
+     | (((uint64_t)(val) & 0x00ff000000000000ULL) >> 40)    \
+     | (((uint64_t)(val) & 0xff00000000000000ULL) >> 56))
+
+
+typedef uint64_t beint64_t;
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+
+/**
+ * CPU_TO_BE64 - convert a constant uint64_t value to big-endian
+ * @native: constant to convert
+ */
+#define CPU_TO_BE64(native) ((beint64_t)(native))
+/**
+ * BE64_TO_CPU - convert a big-endian uint64_t constant
+ * @le_val: big-endian constant to convert
+ */
+#define BE64_TO_CPU(le_val) ((uint64_t)(le_val))
+
+#else /* ... HAVE_LITTLE_ENDIAN */
+#define CPU_TO_BE64(native) ((beint64_t)BSWAP_64(native))
+#define BE64_TO_CPU(le_val) BSWAP_64((uint64_t)le_val)
+#endif /* HAVE_LITTE_ENDIAN */
+
+/**
+ * cpu_to_be64 - convert a uint64_t value to big endian.
+ * @native: value to convert
+ */
+static inline beint64_t cpu_to_be64(uint64_t native)
+{
+    return CPU_TO_BE64(native);
+}
+
+/**
+ * be64_to_cpu - convert a big-endian uint64_t value
+ * @be_val: big-endian value to convert
+ */
+static inline uint64_t be64_to_cpu(beint64_t be_val)
+{
+    return BE64_TO_CPU(be_val);
+}
+
+/* From compiler.h */
+
+#ifndef UNUSED
+/**
+ * UNUSED - a parameter is unused
+ *
+ * Some compilers (eg. gcc with -W or -Wunused) warn about unused
+ * function parameters.  This suppresses such warnings and indicates
+ * to the reader that it's deliberate.
+ *
+ * Example:
+ *  // This is used as a callback, so needs to have this prototype.
+ *  static int some_callback(void *unused UNUSED)
+ *  {
+ *      return 0;
+ *  }
+ */
+#define UNUSED __attribute__((__unused__))
+#endif
+
+/* From sha512.h */
+
+/**
+ * struct sha512 - structure representing a completed SHA512.
+ * @u.u8: an unsigned char array.
+ * @u.u64: a 64-bit integer array.
+ *
+ * Other fields may be added to the union in future.
+ */
+struct sha512 {
+    union {
+        uint64_t u64[8];
+        unsigned char u8[64];
+    } u;
+};
+
+/**
+ * sha512 - return sha512 of an object.
+ * @sha512: the sha512 to fill in
+ * @p: pointer to memory,
+ * @size: the number of bytes pointed to by @p
+ *
+ * The bytes pointed to by @p is SHA512 hashed into @sha512.  This is
+ * equivalent to sha512_init(), sha512_update() then sha512_done().
+ */
+void sha512(struct sha512 *sha, const void *p, size_t size);
+
+/**
+ * struct sha512_ctx - structure to store running context for sha512
+ */
+struct sha512_ctx {
+    uint64_t s[8];
+    union {
+        uint64_t u64[16];
+        unsigned char u8[128];
+    } buf;
+    size_t bytes;
+};
+
+/**
+ * sha512_init - initialize an SHA512 context.
+ * @ctx: the sha512_ctx to initialize
+ *
+ * This must be called before sha512_update or sha512_done, or
+ * alternately you can assign SHA512_INIT.
+ *
+ * If it was already initialized, this forgets anything which was
+ * hashed before.
+ *
+ * Example:
+ * static void hash_all(const char **arr, struct sha512 *hash)
+ * {
+ *  size_t i;
+ *  struct sha512_ctx ctx;
+ *
+ *  sha512_init(&ctx);
+ *  for (i = 0; arr[i]; i++)
+ *      sha512_update(&ctx, arr[i], strlen(arr[i]));
+ *  sha512_done(&ctx, hash);
+ * }
+ */
+void sha512_init(struct sha512_ctx *ctx);
+
+/**
+ * SHA512_INIT - initializer for an SHA512 context.
+ *
+ * This can be used to statically initialize an SHA512 context (instead
+ * of sha512_init()).
+ *
+ * Example:
+ * static void hash_all(const char **arr, struct sha512 *hash)
+ * {
+ *  size_t i;
+ *  struct sha512_ctx ctx = SHA512_INIT;
+ *
+ *  for (i = 0; arr[i]; i++)
+ *      sha512_update(&ctx, arr[i], strlen(arr[i]));
+ *  sha512_done(&ctx, hash);
+ * }
+ */
+#define SHA512_INIT                                         \
+    { { 0x6a09e667f3bcc908ull, 0xbb67ae8584caa73bull,   \
+        0x3c6ef372fe94f82bull, 0xa54ff53a5f1d36f1ull,   \
+        0x510e527fade682d1ull, 0x9b05688c2b3e6c1full,   \
+        0x1f83d9abfb41bd6bull, 0x5be0cd19137e2179ull }, \
+      { { 0 } }, 0 }
+
+/**
+ * sha512_update - include some memory in the hash.
+ * @ctx: the sha512_ctx to use
+ * @p: pointer to memory,
+ * @size: the number of bytes pointed to by @p
+ *
+ * You can call this multiple times to hash more data, before calling
+ * sha512_done().
+ */
+void sha512_update(struct sha512_ctx *ctx, const void *p, size_t size);
+
+/**
+ * sha512_done - finish SHA512 and return the hash
+ * @ctx: the sha512_ctx to complete
+ * @res: the hash to return.
+ *
+ * Note that @ctx is *destroyed* by this, and must be reinitialized.
+ * To avoid that, pass a copy instead.
+ */
+void sha512_done(struct sha512_ctx *sha512, struct sha512 *res);
+
+/* From sha512.c */
+
+/*
+ * SHA512 core code translated from the Bitcoin project's C++:
+ *
+ * src/crypto/sha512.cpp commit f914f1a746d7f91951c1da262a4a749dd3ebfa71
+ * Copyright (c) 2014 The Bitcoin Core developers
+ * Distributed under the MIT software license, see the accompanying
+ * file COPYING or http://www.opensource.org/licenses/mit-license.php.
+ */
+/* #include <ccan/endian/endian.h> */
+/* #include <ccan/compiler/compiler.h> */
+#include <stdbool.h>
+#include <assert.h>
+#include <string.h>
+
+static void invalidate_sha512(struct sha512_ctx *ctx)
+{
+    ctx->bytes = (size_t)-1;
+}
+
+static void check_sha512(struct sha512_ctx *ctx UNUSED)
+{
+    assert(ctx->bytes != (size_t)-1);
+}
+
+static uint64_t Ch(uint64_t x, uint64_t y, uint64_t z)
+{
+    return z ^ (x & (y ^ z));
+}
+static uint64_t Maj(uint64_t x, uint64_t y, uint64_t z)
+{
+    return (x & y) | (z & (x | y));
+}
+static uint64_t Sigma0(uint64_t x)
+{
+    return (x >> 28 | x << 36) ^ (x >> 34 | x << 30) ^ (x >> 39 | x << 25);
+}
+static uint64_t Sigma1(uint64_t x)
+{
+    return (x >> 14 | x << 50) ^ (x >> 18 | x << 46) ^ (x >> 41 | x << 23);
+}
+static uint64_t sigma0(uint64_t x)
+{
+    return (x >> 1 | x << 63) ^ (x >> 8 | x << 56) ^ (x >> 7);
+}
+static uint64_t sigma1(uint64_t x)
+{
+    return (x >> 19 | x << 45) ^ (x >> 61 | x << 3) ^ (x >> 6);
+}
+
+/** One round of SHA-512. */
+static void Round(uint64_t a, uint64_t b, uint64_t c, uint64_t *d, uint64_t e, uint64_t f, uint64_t g, uint64_t *h, uint64_t k, uint64_t w)
+{
+    uint64_t t1 = *h + Sigma1(e) + Ch(e, f, g) + k + w;
+    uint64_t t2 = Sigma0(a) + Maj(a, b, c);
+    *d += t1;
+    *h = t1 + t2;
+}
+
+/** Perform one SHA-512 transformation, processing a 128-byte chunk. */
+static void Transform(uint64_t *s, const uint64_t *chunk)
+{
+    uint64_t a = s[0], b = s[1], c = s[2], d = s[3], e = s[4], f = s[5], g = s[6], h = s[7];
+    uint64_t w0, w1, w2, w3, w4, w5, w6, w7, w8, w9, w10, w11, w12, w13, w14, w15;
+
+    Round(a, b, c, &d, e, f, g, &h, 0x428a2f98d728ae22ull, w0 = be64_to_cpu(chunk[0]));
+    Round(h, a, b, &c, d, e, f, &g, 0x7137449123ef65cdull, w1 = be64_to_cpu(chunk[1]));
+    Round(g, h, a, &b, c, d, e, &f, 0xb5c0fbcfec4d3b2full, w2 = be64_to_cpu(chunk[2]));
+    Round(f, g, h, &a, b, c, d, &e, 0xe9b5dba58189dbbcull, w3 = be64_to_cpu(chunk[3]));
+    Round(e, f, g, &h, a, b, c, &d, 0x3956c25bf348b538ull, w4 = be64_to_cpu(chunk[4]));
+    Round(d, e, f, &g, h, a, b, &c, 0x59f111f1b605d019ull, w5 = be64_to_cpu(chunk[5]));
+    Round(c, d, e, &f, g, h, a, &b, 0x923f82a4af194f9bull, w6 = be64_to_cpu(chunk[6]));
+    Round(b, c, d, &e, f, g, h, &a, 0xab1c5ed5da6d8118ull, w7 = be64_to_cpu(chunk[7]));
+    Round(a, b, c, &d, e, f, g, &h, 0xd807aa98a3030242ull, w8 = be64_to_cpu(chunk[8]));
+    Round(h, a, b, &c, d, e, f, &g, 0x12835b0145706fbeull, w9 = be64_to_cpu(chunk[9]));
+    Round(g, h, a, &b, c, d, e, &f, 0x243185be4ee4b28cull, w10 = be64_to_cpu(chunk[10]));
+    Round(f, g, h, &a, b, c, d, &e, 0x550c7dc3d5ffb4e2ull, w11 = be64_to_cpu(chunk[11]));
+    Round(e, f, g, &h, a, b, c, &d, 0x72be5d74f27b896full, w12 = be64_to_cpu(chunk[12]));
+    Round(d, e, f, &g, h, a, b, &c, 0x80deb1fe3b1696b1ull, w13 = be64_to_cpu(chunk[13]));
+    Round(c, d, e, &f, g, h, a, &b, 0x9bdc06a725c71235ull, w14 = be64_to_cpu(chunk[14]));
+    Round(b, c, d, &e, f, g, h, &a, 0xc19bf174cf692694ull, w15 = be64_to_cpu(chunk[15]));
+
+    Round(a, b, c, &d, e, f, g, &h, 0xe49b69c19ef14ad2ull, w0 += sigma1(w14) + w9 + sigma0(w1));
+    Round(h, a, b, &c, d, e, f, &g, 0xefbe4786384f25e3ull, w1 += sigma1(w15) + w10 + sigma0(w2));
+    Round(g, h, a, &b, c, d, e, &f, 0x0fc19dc68b8cd5b5ull, w2 += sigma1(w0) + w11 + sigma0(w3));
+    Round(f, g, h, &a, b, c, d, &e, 0x240ca1cc77ac9c65ull, w3 += sigma1(w1) + w12 + sigma0(w4));
+    Round(e, f, g, &h, a, b, c, &d, 0x2de92c6f592b0275ull, w4 += sigma1(w2) + w13 + sigma0(w5));
+    Round(d, e, f, &g, h, a, b, &c, 0x4a7484aa6ea6e483ull, w5 += sigma1(w3) + w14 + sigma0(w6));
+    Round(c, d, e, &f, g, h, a, &b, 0x5cb0a9dcbd41fbd4ull, w6 += sigma1(w4) + w15 + sigma0(w7));
+    Round(b, c, d, &e, f, g, h, &a, 0x76f988da831153b5ull, w7 += sigma1(w5) + w0 + sigma0(w8));
+    Round(a, b, c, &d, e, f, g, &h, 0x983e5152ee66dfabull, w8 += sigma1(w6) + w1 + sigma0(w9));
+    Round(h, a, b, &c, d, e, f, &g, 0xa831c66d2db43210ull, w9 += sigma1(w7) + w2 + sigma0(w10));
+    Round(g, h, a, &b, c, d, e, &f, 0xb00327c898fb213full, w10 += sigma1(w8) + w3 + sigma0(w11));
+    Round(f, g, h, &a, b, c, d, &e, 0xbf597fc7beef0ee4ull, w11 += sigma1(w9) + w4 + sigma0(w12));
+    Round(e, f, g, &h, a, b, c, &d, 0xc6e00bf33da88fc2ull, w12 += sigma1(w10) + w5 + sigma0(w13));
+    Round(d, e, f, &g, h, a, b, &c, 0xd5a79147930aa725ull, w13 += sigma1(w11) + w6 + sigma0(w14));
+    Round(c, d, e, &f, g, h, a, &b, 0x06ca6351e003826full, w14 += sigma1(w12) + w7 + sigma0(w15));
+    Round(b, c, d, &e, f, g, h, &a, 0x142929670a0e6e70ull, w15 += sigma1(w13) + w8 + sigma0(w0));
+
+    Round(a, b, c, &d, e, f, g, &h, 0x27b70a8546d22ffcull, w0 += sigma1(w14) + w9 + sigma0(w1));
+    Round(h, a, b, &c, d, e, f, &g, 0x2e1b21385c26c926ull, w1 += sigma1(w15) + w10 + sigma0(w2));
+    Round(g, h, a, &b, c, d, e, &f, 0x4d2c6dfc5ac42aedull, w2 += sigma1(w0) + w11 + sigma0(w3));
+    Round(f, g, h, &a, b, c, d, &e, 0x53380d139d95b3dfull, w3 += sigma1(w1) + w12 + sigma0(w4));
+    Round(e, f, g, &h, a, b, c, &d, 0x650a73548baf63deull, w4 += sigma1(w2) + w13 + sigma0(w5));
+    Round(d, e, f, &g, h, a, b, &c, 0x766a0abb3c77b2a8ull, w5 += sigma1(w3) + w14 + sigma0(w6));
+    Round(c, d, e, &f, g, h, a, &b, 0x81c2c92e47edaee6ull, w6 += sigma1(w4) + w15 + sigma0(w7));
+    Round(b, c, d, &e, f, g, h, &a, 0x92722c851482353bull, w7 += sigma1(w5) + w0 + sigma0(w8));
+    Round(a, b, c, &d, e, f, g, &h, 0xa2bfe8a14cf10364ull, w8 += sigma1(w6) + w1 + sigma0(w9));
+    Round(h, a, b, &c, d, e, f, &g, 0xa81a664bbc423001ull, w9 += sigma1(w7) + w2 + sigma0(w10));
+    Round(g, h, a, &b, c, d, e, &f, 0xc24b8b70d0f89791ull, w10 += sigma1(w8) + w3 + sigma0(w11));
+    Round(f, g, h, &a, b, c, d, &e, 0xc76c51a30654be30ull, w11 += sigma1(w9) + w4 + sigma0(w12));
+    Round(e, f, g, &h, a, b, c, &d, 0xd192e819d6ef5218ull, w12 += sigma1(w10) + w5 + sigma0(w13));
+    Round(d, e, f, &g, h, a, b, &c, 0xd69906245565a910ull, w13 += sigma1(w11) + w6 + sigma0(w14));
+    Round(c, d, e, &f, g, h, a, &b, 0xf40e35855771202aull, w14 += sigma1(w12) + w7 + sigma0(w15));
+    Round(b, c, d, &e, f, g, h, &a, 0x106aa07032bbd1b8ull, w15 += sigma1(w13) + w8 + sigma0(w0));
+
+    Round(a, b, c, &d, e, f, g, &h, 0x19a4c116b8d2d0c8ull, w0 += sigma1(w14) + w9 + sigma0(w1));
+    Round(h, a, b, &c, d, e, f, &g, 0x1e376c085141ab53ull, w1 += sigma1(w15) + w10 + sigma0(w2));
+    Round(g, h, a, &b, c, d, e, &f, 0x2748774cdf8eeb99ull, w2 += sigma1(w0) + w11 + sigma0(w3));
+    Round(f, g, h, &a, b, c, d, &e, 0x34b0bcb5e19b48a8ull, w3 += sigma1(w1) + w12 + sigma0(w4));
+    Round(e, f, g, &h, a, b, c, &d, 0x391c0cb3c5c95a63ull, w4 += sigma1(w2) + w13 + sigma0(w5));
+    Round(d, e, f, &g, h, a, b, &c, 0x4ed8aa4ae3418acbull, w5 += sigma1(w3) + w14 + sigma0(w6));
+    Round(c, d, e, &f, g, h, a, &b, 0x5b9cca4f7763e373ull, w6 += sigma1(w4) + w15 + sigma0(w7));
+    Round(b, c, d, &e, f, g, h, &a, 0x682e6ff3d6b2b8a3ull, w7 += sigma1(w5) + w0 + sigma0(w8));
+    Round(a, b, c, &d, e, f, g, &h, 0x748f82ee5defb2fcull, w8 += sigma1(w6) + w1 + sigma0(w9));
+    Round(h, a, b, &c, d, e, f, &g, 0x78a5636f43172f60ull, w9 += sigma1(w7) + w2 + sigma0(w10));
+    Round(g, h, a, &b, c, d, e, &f, 0x84c87814a1f0ab72ull, w10 += sigma1(w8) + w3 + sigma0(w11));
+    Round(f, g, h, &a, b, c, d, &e, 0x8cc702081a6439ecull, w11 += sigma1(w9) + w4 + sigma0(w12));
+    Round(e, f, g, &h, a, b, c, &d, 0x90befffa23631e28ull, w12 += sigma1(w10) + w5 + sigma0(w13));
+    Round(d, e, f, &g, h, a, b, &c, 0xa4506cebde82bde9ull, w13 += sigma1(w11) + w6 + sigma0(w14));
+    Round(c, d, e, &f, g, h, a, &b, 0xbef9a3f7b2c67915ull, w14 += sigma1(w12) + w7 + sigma0(w15));
+    Round(b, c, d, &e, f, g, h, &a, 0xc67178f2e372532bull, w15 += sigma1(w13) + w8 + sigma0(w0));
+
+    Round(a, b, c, &d, e, f, g, &h, 0xca273eceea26619cull, w0 += sigma1(w14) + w9 + sigma0(w1));
+    Round(h, a, b, &c, d, e, f, &g, 0xd186b8c721c0c207ull, w1 += sigma1(w15) + w10 + sigma0(w2));
+    Round(g, h, a, &b, c, d, e, &f, 0xeada7dd6cde0eb1eull, w2 += sigma1(w0) + w11 + sigma0(w3));
+    Round(f, g, h, &a, b, c, d, &e, 0xf57d4f7fee6ed178ull, w3 += sigma1(w1) + w12 + sigma0(w4));
+    Round(e, f, g, &h, a, b, c, &d, 0x06f067aa72176fbaull, w4 += sigma1(w2) + w13 + sigma0(w5));
+    Round(d, e, f, &g, h, a, b, &c, 0x0a637dc5a2c898a6ull, w5 += sigma1(w3) + w14 + sigma0(w6));
+    Round(c, d, e, &f, g, h, a, &b, 0x113f9804bef90daeull, w6 += sigma1(w4) + w15 + sigma0(w7));
+    Round(b, c, d, &e, f, g, h, &a, 0x1b710b35131c471bull, w7 += sigma1(w5) + w0 + sigma0(w8));
+    Round(a, b, c, &d, e, f, g, &h, 0x28db77f523047d84ull, w8 += sigma1(w6) + w1 + sigma0(w9));
+    Round(h, a, b, &c, d, e, f, &g, 0x32caab7b40c72493ull, w9 += sigma1(w7) + w2 + sigma0(w10));
+    Round(g, h, a, &b, c, d, e, &f, 0x3c9ebe0a15c9bebcull, w10 += sigma1(w8) + w3 + sigma0(w11));
+    Round(f, g, h, &a, b, c, d, &e, 0x431d67c49c100d4cull, w11 += sigma1(w9) + w4 + sigma0(w12));
+    Round(e, f, g, &h, a, b, c, &d, 0x4cc5d4becb3e42b6ull, w12 += sigma1(w10) + w5 + sigma0(w13));
+    Round(d, e, f, &g, h, a, b, &c, 0x597f299cfc657e2aull, w13 += sigma1(w11) + w6 + sigma0(w14));
+    Round(c, d, e, &f, g, h, a, &b, 0x5fcb6fab3ad6faecull, w14 + sigma1(w12) + w7 + sigma0(w15));
+    Round(b, c, d, &e, f, g, h, &a, 0x6c44198c4a475817ull, w15 + sigma1(w13) + w8 + sigma0(w0));
+
+    s[0] += a;
+    s[1] += b;
+    s[2] += c;
+    s[3] += d;
+    s[4] += e;
+    s[5] += f;
+    s[6] += g;
+    s[7] += h;
+}
+
+static bool alignment_ok(const void *p UNUSED, size_t n UNUSED)
+{
+#if HAVE_UNALIGNED_ACCESS
+    return true;
+#else
+    return ((size_t)p % n == 0);
+#endif
+}
+
+static void add(struct sha512_ctx *ctx, const void *p, size_t len)
+{
+    const unsigned char *data = p;
+    size_t bufsize = ctx->bytes % 128;
+
+    if (bufsize + len >= 128) {
+        /* Fill the buffer, and process it. */
+        memcpy(ctx->buf.u8 + bufsize, data, 128 - bufsize);
+        ctx->bytes += 128 - bufsize;
+        data += 128 - bufsize;
+        len -= 128 - bufsize;
+        Transform(ctx->s, ctx->buf.u64);
+        bufsize = 0;
+    }
+
+    while (len >= 128) {
+        /* Process full chunks directly from the source. */
+        if (alignment_ok(data, sizeof(uint64_t)))
+            Transform(ctx->s, (const uint64_t *)data);
+        else {
+            memcpy(ctx->buf.u8, data, sizeof(ctx->buf));
+            Transform(ctx->s, ctx->buf.u64);
+        }
+        ctx->bytes += 128;
+        data += 128;
+        len -= 128;
+    }
+
+    if (len) {
+        /* Fill the buffer with what remains. */
+        memcpy(ctx->buf.u8 + bufsize, data, len);
+        ctx->bytes += len;
+    }
+}
+
+void sha512_init(struct sha512_ctx *ctx)
+{
+    struct sha512_ctx init = SHA512_INIT;
+    *ctx = init;
+}
+
+void sha512_update(struct sha512_ctx *ctx, const void *p, size_t size)
+{
+    check_sha512(ctx);
+    add(ctx, p, size);
+}
+
+void sha512_done(struct sha512_ctx *ctx, struct sha512 *res)
+{
+    static const unsigned char pad[128] = { 0x80 };
+    uint64_t sizedesc[2] = { 0, 0 };
+    size_t i;
+
+    sizedesc[1] = cpu_to_be64((uint64_t)ctx->bytes << 3);
+
+    /* Add '1' bit to terminate, then all 0 bits, up to next block - 16. */
+    add(ctx, pad, 1 + ((256 - 16 - (ctx->bytes % 128) - 1) % 128));
+    /* Add number of bits of data (big endian) */
+    add(ctx, sizedesc, sizeof(sizedesc));
+    for (i = 0; i < sizeof(ctx->s) / sizeof(ctx->s[0]); i++)
+        res->u.u64[i] = cpu_to_be64(ctx->s[i]);
+    invalidate_sha512(ctx);
+}
+
+void sha512(struct sha512 *sha, const void *p, size_t size)
+{
+    struct sha512_ctx ctx;
+
+    sha512_init(&ctx);
+    sha512_update(&ctx, p, size);
+    sha512_done(&ctx, sha);
+}
+
+/* From hex.h */
+/**
+ * hex_decode - Unpack a hex string.
+ * @str: the hexidecimal string
+ * @slen: the length of @str
+ * @buf: the buffer to write the data into
+ * @bufsize: the length of @buf
+ *
+ * Returns false if there are any characters which aren't 0-9, a-f or A-F,
+ * of the string wasn't the right length for @bufsize.
+ *
+ * Example:
+ *  unsigned char data[20];
+ *
+ *  if (!hex_decode(argv[1], strlen(argv[1]), data, 20))
+ *      printf("String is malformed!\n");
+ */
+bool hex_decode(const char *str, size_t slen, void *buf, size_t bufsize);
+
+/**
+ * hex_encode - Create a nul-terminated hex string
+ * @buf: the buffer to read the data from
+ * @bufsize: the length of @buf
+ * @dest: the string to fill
+ * @destsize: the max size of the string
+ *
+ * Returns true if the string, including terminator, fit in @destsize;
+ *
+ * Example:
+ *  unsigned char buf[] = { 0x1F, 0x2F };
+ *  char str[5];
+ *
+ *  if (!hex_encode(buf, sizeof(buf), str, sizeof(str)))
+ *      abort();
+ */
+bool hex_encode(const void *buf, size_t bufsize, char *dest, size_t destsize);
+
+/**
+ * hex_str_size - Calculate how big a nul-terminated hex string is
+ * @bytes: bytes of data to represent
+ *
+ * Example:
+ *  unsigned char buf[] = { 0x1F, 0x2F };
+ *  char str[hex_str_size(sizeof(buf))];
+ *
+ *  hex_encode(buf, sizeof(buf), str, sizeof(str));
+ */
+static inline size_t hex_str_size(size_t bytes)
+{
+    return 2 * bytes + 1;
+}
+
+/* From hex.c */
+static bool char_to_hex(unsigned char *val, char c)
+{
+    if (c >= '0' && c <= '9') {
+        *val = c - '0';
+        return true;
+    }
+    if (c >= 'a' && c <= 'f') {
+        *val = c - 'a' + 10;
+        return true;
+    }
+    if (c >= 'A' && c <= 'F') {
+        *val = c - 'A' + 10;
+        return true;
+    }
+    return false;
+}
+
+bool hex_decode(const char *str, size_t slen, void *buf, size_t bufsize)
+{
+    unsigned char v1, v2;
+    unsigned char *p = buf;
+
+    while (slen > 1) {
+        if (!char_to_hex(&v1, str[0]) || !char_to_hex(&v2, str[1]))
+            return false;
+        if (!bufsize)
+            return false;
+        *(p++) = (v1 << 4) | v2;
+        str += 2;
+        slen -= 2;
+        bufsize--;
+    }
+    return slen == 0 && bufsize == 0;
+}
+
+static char hexchar(unsigned int val)
+{
+    if (val < 10)
+        return '0' + val;
+    if (val < 16)
+        return 'a' + val - 10;
+    abort();
+}
+
+bool hex_encode(const void *buf, size_t bufsize, char *dest, size_t destsize)
+{
+    size_t i;
+
+    if (destsize < hex_str_size(bufsize))
+        return false;
+
+    for (i = 0; i < bufsize; i++) {
+        unsigned int c = ((const unsigned char *)buf)[i];
+        *(dest++) = hexchar(c >> 4);
+        *(dest++) = hexchar(c & 0xF);
+    }
+    *dest = '\0';
+
+    return true;
+}
+
+/* From tap.h */
+/**
+ * plan_tests - announce the number of tests you plan to run
+ * @tests: the number of tests
+ *
+ * This should be the first call in your test program: it allows tracing
+ * of failures which mean that not all tests are run.
+ *
+ * If you don't know how many tests will actually be run, assume all of them
+ * and use skip() if you don't actually run some tests.
+ *
+ * Example:
+ *  plan_tests(13);
+ */
+void plan_tests(unsigned int tests);
+
+/**
+ * ok1 - Simple conditional test
+ * @e: the expression which we expect to be true.
+ *
+ * This is the simplest kind of test: if the expression is true, the
+ * test passes.  The name of the test which is printed will simply be
+ * file name, line number, and the expression itself.
+ *
+ * Example:
+ *  ok1(somefunc() == 1);
+ */
+# define ok1(e) ((e) ?                          \
+         _gen_result(1, __func__, __FILE__, __LINE__, "%s", #e) : \
+         _gen_result(0, __func__, __FILE__, __LINE__, "%s", #e))
+
+/**
+ * exit_status - the value that main should return.
+ *
+ * For maximum compatibility your test program should return a particular exit
+ * code (ie. 0 if all tests were run, and every test which was expected to
+ * succeed succeeded).
+ *
+ * Example:
+ *  exit(exit_status());
+ */
+int exit_status(void);
+
+/**
+ * tap_fail_callback - function to call when we fail
+ *
+ * This can be used to ease debugging, or exit on the first failure.
+ */
+void (*tap_fail_callback)(void);
+
+/* From tap.c */
+
+static int no_plan = 0;
+static int skip_all = 0;
+static int have_plan = 0;
+static unsigned int test_count = 0; /* Number of tests that have been run */
+static unsigned int e_tests = 0; /* Expected number of tests to run */
+static unsigned int failures = 0; /* Number of tests that failed */
+static char *todo_msg = NULL;
+static const char *todo_msg_fixed = "libtap malloc issue";
+static int todo = 0;
+static int test_died = 0;
+static int test_pid;
+
+static void
+_expected_tests(unsigned int tests)
+{
+    printf("1..%d\n", tests);
+    e_tests = tests;
+}
+
+static void
+diagv(const char *fmt, va_list ap)
+{
+    fputs("# ", stdout);
+    vfprintf(stdout, fmt, ap);
+    fputs("\n", stdout);
+}
+
+static void
+_diag(const char *fmt, ...)
+{
+    va_list ap;
+    va_start(ap, fmt);
+    diagv(fmt, ap);
+    va_end(ap);
+}
+
+/*
+ * Generate a test result.
+ *
+ * ok -- boolean, indicates whether or not the test passed.
+ * test_name -- the name of the test, may be NULL
+ * test_comment -- a comment to print afterwards, may be NULL
+ */
+unsigned int
+_gen_result(int ok, const char *func, const char *file, unsigned int line,
+        const char *test_name, ...)
+{
+    va_list ap;
+    char *local_test_name = NULL;
+    char *c;
+    int name_is_digits;
+
+    test_count++;
+
+    /* Start by taking the test name and performing any printf()
+       expansions on it */
+    if(test_name != NULL) {
+        va_start(ap, test_name);
+        if (vasprintf(&local_test_name, test_name, ap) < 0)
+            local_test_name = NULL;
+        va_end(ap);
+
+        /* Make sure the test name contains more than digits
+           and spaces.  Emit an error message and exit if it
+           does */
+        if(local_test_name) {
+            name_is_digits = 1;
+            for(c = local_test_name; *c != '\0'; c++) {
+                if(!isdigit((unsigned char)*c)
+                   && !isspace((unsigned char)*c)) {
+                    name_is_digits = 0;
+                    break;
+                }
+            }
+
+            if(name_is_digits) {
+                _diag("    You named your test '%s'.  You shouldn't use numbers for your test names.", local_test_name);
+                _diag("    Very confusing.");
+            }
+        }
+    }
+
+    if(!ok) {
+        printf("not ");
+        failures++;
+    }
+
+    printf("ok %d", test_count);
+
+    if(test_name != NULL) {
+        printf(" - ");
+
+        /* Print the test name, escaping any '#' characters it
+           might contain */
+        if(local_test_name != NULL) {
+            flockfile(stdout);
+            for(c = local_test_name; *c != '\0'; c++) {
+                if(*c == '#')
+                    fputc('\\', stdout);
+                fputc((int)*c, stdout);
+            }
+            funlockfile(stdout);
+        } else {    /* vasprintf() failed, use a fixed message */
+            printf("%s", todo_msg_fixed);
+        }
+    }
+
+    /* If we're in a todo_start() block then flag the test as being
+       TODO.  todo_msg should contain the message to print at this
+       point.  If it's NULL then asprintf() failed, and we should
+       use the fixed message.
+
+       This is not counted as a failure, so decrement the counter if
+       the test failed. */
+    if(todo) {
+        printf(" # TODO %s", todo_msg ? todo_msg : todo_msg_fixed);
+        if(!ok)
+            failures--;
+    }
+
+    printf("\n");
+
+    if(!ok)
+        _diag("    Failed %stest (%s:%s() at line %d)",
+              todo ? "(TODO) " : "", file, func, line);
+
+    free(local_test_name);
+
+    if (!ok && tap_fail_callback)
+        tap_fail_callback();
+
+    /* We only care (when testing) that ok is positive, but here we
+       specifically only want to return 1 or 0 */
+    return ok ? 1 : 0;
+}
+
+/*
+ * Cleanup at the end of the run, produce any final output that might be
+ * required.
+ */
+static void
+_cleanup(void)
+{
+    /* If we forked, don't do cleanup in child! */
+    if (getpid() != test_pid)
+        return;
+
+    /* If plan_no_plan() wasn't called, and we don't have a plan,
+       and we're not skipping everything, then something happened
+       before we could produce any output */
+    if(!no_plan && !have_plan && !skip_all) {
+        _diag("Looks like your test died before it could output anything.");
+        return;
+    }
+
+    if(test_died) {
+        _diag("Looks like your test died just after %d.", test_count);
+        return;
+    }
+
+
+    /* No plan provided, but now we know how many tests were run, and can
+       print the header at the end */
+    if(!skip_all && (no_plan || !have_plan)) {
+        printf("1..%d\n", test_count);
+    }
+
+    if((have_plan && !no_plan) && e_tests < test_count) {
+        _diag("Looks like you planned %d tests but ran %d extra.",
+              e_tests, test_count - e_tests);
+        return;
+    }
+
+    if((have_plan || !no_plan) && e_tests > test_count) {
+        _diag("Looks like you planned %d tests but only ran %d.",
+              e_tests, test_count);
+        if(failures) {
+            _diag("Looks like you failed %d tests of %d run.",
+                  failures, test_count);
+        }
+        return;
+    }
+
+    if(failures)
+        _diag("Looks like you failed %d tests of %d.",
+              failures, test_count);
+
+}
+
+/*
+ * Initialise the TAP library.  Will only do so once, however many times it's
+ * called.
+ */
+static void
+_tap_init(void)
+{
+    static int run_once = 0;
+
+    if(!run_once) {
+        test_pid = getpid();
+        atexit(_cleanup);
+
+        /* stdout needs to be unbuffered so that the output appears
+           in the same place relative to stderr output as it does
+           with Test::Harness */
+//      setbuf(stdout, 0);
+        run_once = 1;
+    }
+}
+
+/*
+ * Note the number of tests that will be run.
+ */
+void
+plan_tests(unsigned int tests)
+{
+
+    _tap_init();
+
+    if(have_plan != 0) {
+        fprintf(stderr, "You tried to plan twice!\n");
+        test_died = 1;
+        exit(255);
+    }
+
+    if(tests == 0) {
+        fprintf(stderr, "You said to run 0 tests!  You've got to run something.\n");
+        test_died = 1;
+        exit(255);
+    }
+
+    have_plan = 1;
+
+    _expected_tests(tests);
+}
+
+static int
+exit_status_(void)
+{
+    int r;
+
+    /* If there's no plan, just return the number of failures */
+    if(no_plan || !have_plan) {
+        return failures;
+    }
+
+    /* Ran too many tests?  Return the number of tests that were run
+       that shouldn't have been */
+    if(e_tests < test_count) {
+        r = test_count - e_tests;
+        return r;
+    }
+
+    /* Return the number of tests that failed + the number of tests
+       that weren't run */
+    r = failures + e_tests - test_count;
+
+    return r;
+}
+
+int
+exit_status(void)
+{
+    int r = exit_status_();
+    if (r > 255)
+        r = 255;
+    return r;
+}
+
+/* From run-test-vectors.c */
+
+/* Test vectors. */
+struct test {
+    const char *vector;
+    size_t repetitions;
+    const char *expected;
+};
+
+static const char ZEROES[] =
+    "0000000000000000000000000000000000000000000000000000000000000000"
+    "0000000000000000000000000000000000000000000000000000000000000000";
+
+static struct test tests[] = {
+    /* http://csrc.nist.gov/groups/STM/cavp/secure-hashing.html ShortMsg */
+    { "21", 1,
+      "3831a6a6155e509dee59a7f451eb35324d8f8f2df6e3708894740f98fdee2388"
+      "9f4de5adb0c5010dfb555cda77c8ab5dc902094c52de3278f35a75ebc25f093a" },
+    { "9083", 1,
+      "55586ebba48768aeb323655ab6f4298fc9f670964fc2e5f2731e34dfa4b0c09e"
+      "6e1e12e3d7286b3145c61c2047fb1a2a1297f36da64160b31fa4c8c2cddd2fb4" },
+    { "0a55db", 1,
+      "7952585e5330cb247d72bae696fc8a6b0f7d0804577e347d99bc1b11e52f3849"
+      "85a428449382306a89261ae143c2f3fb613804ab20b42dc097e5bf4a96ef919b" },
+    { "23be86d5", 1,
+      "76d42c8eadea35a69990c63a762f330614a4699977f058adb988f406fb0be8f2"
+      "ea3dce3a2bbd1d827b70b9b299ae6f9e5058ee97b50bd4922d6d37ddc761f8eb" },
+    { "eb0ca946c1", 1,
+      "d39ecedfe6e705a821aee4f58bfc489c3d9433eb4ac1b03a97e321a2586b40dd"
+      "0522f40fa5aef36afff591a78c916bfc6d1ca515c4983dd8695b1ec7951d723e" },
+    { "38667f39277b", 1,
+      "85708b8ff05d974d6af0801c152b95f5fa5c06af9a35230c5bea2752f031f9bd"
+      "84bd844717b3add308a70dc777f90813c20b47b16385664eefc88449f04f2131" },
+    { "b39f71aaa8a108", 1,
+      "258b8efa05b4a06b1e63c7a3f925c5ef11fa03e3d47d631bf4d474983783d8c0"
+      "b09449009e842fc9fa15de586c67cf8955a17d790b20f41dadf67ee8cdcdfce6" },
+    { "dc28484ebfd293d62ac759d5754bdf502423e4d419fa79020805134b2ce3dff7"
+      "38c7556c91d810adbad8dd210f041296b73c2185d4646c97fc0a5b69ed49ac8c"
+      "7ced0bd1cfd7e3c3cca47374d189247da6811a40b0ab097067ed4ad40ade2e47"
+      "91e39204e398b3204971445822a1be0dd93af8", 1,
+      "615115d2e8b62e345adaa4bdb95395a3b4fe27d71c4a111b86c1841463c5f03d"
+      "6b20d164a39948ab08ae060720d05c10f6022e5c8caf2fa3bca2e04d9c539ded" },
+    { "fd2203e467574e834ab07c9097ae164532f24be1eb5d88f1af7748ceff0d2c67"
+      "a21f4e4097f9d3bb4e9fbf97186e0db6db0100230a52b453d421f8ab9c9a6043"
+      "aa3295ea20d2f06a2f37470d8a99075f1b8a8336f6228cf08b5942fc1fb4299c"
+      "7d2480e8e82bce175540bdfad7752bc95b577f229515394f3ae5cec870a4b2f8",
+      1,
+      "a21b1077d52b27ac545af63b32746c6e3c51cb0cb9f281eb9f3580a6d4996d5c"
+      "9917d2a6e484627a9d5a06fa1b25327a9d710e027387fc3e07d7c4d14c6086cc" },
+    /* http://www.di-mgt.com.au/sha_testvectors.html */
+    { ZEROES, 1,
+      "7be9fda48f4179e611c698a73cff09faf72869431efee6eaad14de0cb44bbf66"
+      "503f752b7a8eb17083355f3ce6eb7d2806f236b25af96a24e22b887405c20081" }
+};
+
+static void *xmalloc(size_t size)
+{
+    char * ret;
+    ret = malloc(size);
+    if (ret == NULL) {
+        perror("malloc");
+        abort();
+    }
+    return ret;
+}
+
+static bool do_test(const struct test *t)
+{
+    struct sha512 h;
+    char got[128 + 1];
+    bool passed;
+    size_t i, vector_len = strlen(t->vector) / 2;
+    void *vector = xmalloc(vector_len);
+
+    hex_decode(t->vector, vector_len * 2, vector, vector_len);
+
+    for (i = 0; i < t->repetitions; i++) {
+        sha512(&h, vector, vector_len);
+        if (t->repetitions > 1)
+            memcpy(vector, &h, sizeof(h));
+    }
+
+    hex_encode(&h, sizeof(h), got, sizeof(got));
+
+    passed = strcmp(t->expected, got) == 0;
+    free(vector);
+    return passed;
+}
+
+int main(void)
+{
+    const size_t num_tests = sizeof(tests) / sizeof(tests[0]);
+    size_t i;
+
+    /* This is how many tests you plan to run */
+    plan_tests(num_tests);
+
+    for (i = 0; i < num_tests; i++)
+        ok1(do_test(&tests[i]));
+
+    /* This exits depending on whether all tests passed */
+    return exit_status();
+}
diff --git a/tests/tcg/ppc64/Makefile.target b/tests/tcg/ppc64/Makefile.target
index 0368007028..c9498053df 100644
--- a/tests/tcg/ppc64/Makefile.target
+++ b/tests/tcg/ppc64/Makefile.target
@@ -10,19 +10,21 @@ PPC64_TESTS=bcdsub non_signalling_xscv
 endif
 $(PPC64_TESTS): CFLAGS += -mpower8-vector
 
-PPC64_TESTS += byte_reverse
 PPC64_TESTS += mtfsf
+
 ifneq ($(DOCKER_IMAGE)$(CROSS_CC_HAS_POWER10),)
+PPC64_TESTS += byte_reverse sha512-vector
+endif
+byte_reverse: CFLAGS += -mcpu=power10
 run-byte_reverse: QEMU_OPTS+=-cpu POWER10
 run-plugin-byte_reverse-with-%: QEMU_OPTS+=-cpu POWER10
-else
-byte_reverse:
-	$(call skip-test, "BUILD of $@", "missing compiler support")
-run-byte_reverse:
-	$(call skip-test, "RUN of byte_reverse", "not built")
-run-plugin-byte_reverse-with-%:
-	$(call skip-test, "RUN of byte_reverse ($*)", "not built")
-endif
+
+sha512-vector: CFLAGS +=-mcpu=power10 -O3
+sha512-vector: sha512.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+run-sha512-vector: QEMU_OPTS+=-cpu POWER10
+run-plugin-sha512-vector-with-%: QEMU_OPTS+=-cpu POWER10
 
 PPC64_TESTS += signal_save_restore_xer
 
diff --git a/tests/tcg/ppc64le/Makefile.target b/tests/tcg/ppc64le/Makefile.target
index 480ff0898d..12d85e946b 100644
--- a/tests/tcg/ppc64le/Makefile.target
+++ b/tests/tcg/ppc64le/Makefile.target
@@ -10,12 +10,19 @@ endif
 $(PPC64LE_TESTS): CFLAGS += -mpower8-vector
 
 ifneq ($(DOCKER_IMAGE)$(CROSS_CC_HAS_POWER10),)
-PPC64LE_TESTS += byte_reverse
+PPC64LE_TESTS += byte_reverse sha512-vector
 endif
 byte_reverse: CFLAGS += -mcpu=power10
 run-byte_reverse: QEMU_OPTS+=-cpu POWER10
 run-plugin-byte_reverse-with-%: QEMU_OPTS+=-cpu POWER10
 
+sha512-vector: CFLAGS +=-mcpu=power10 -O3
+sha512-vector: sha512.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+run-sha512-vector: QEMU_OPTS+=-cpu POWER10
+run-plugin-sha512-vector-with-%: QEMU_OPTS+=-cpu POWER10
+
 PPC64LE_TESTS += mtfsf
 PPC64LE_TESTS += signal_save_restore_xer
 
diff --git a/tests/tcg/s390x/Makefile.target b/tests/tcg/s390x/Makefile.target
index 8c9b6a13ce..257c568c58 100644
--- a/tests/tcg/s390x/Makefile.target
+++ b/tests/tcg/s390x/Makefile.target
@@ -28,3 +28,12 @@ run-gdbstub-signals-s390x: signals-s390x
 
 EXTRA_RUNS += run-gdbstub-signals-s390x
 endif
+
+# MVX versions of sha512
+sha512-mvx: CFLAGS=-march=z13 -mvx -O3
+sha512-mvx: sha512.c
+	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+run-sha512-mvx: QEMU_OPTS+=-cpu max
+
+TESTS+=sha512-mvx
diff --git a/tests/tcg/sh4/Makefile.target b/tests/tcg/sh4/Makefile.target
index 620ccc23c1..35ebe6b4e3 100644
--- a/tests/tcg/sh4/Makefile.target
+++ b/tests/tcg/sh4/Makefile.target
@@ -20,5 +20,7 @@ run-plugin-linux-test-with-%:
 	$(call skip-test, $<, "BROKEN")
 
 # This test is currently unreliable: https://gitlab.com/qemu-project/qemu/-/issues/856
+run-threadcount:
+	$(call skip-test, $<, "BROKEN")
 run-plugin-threadcount-with-%:
 	$(call skip-test, $<, "BROKEN")
diff --git a/tests/tcg/x86_64/Makefile.target b/tests/tcg/x86_64/Makefile.target
index 4a8a464c57..17cf168f0a 100644
--- a/tests/tcg/x86_64/Makefile.target
+++ b/tests/tcg/x86_64/Makefile.target
@@ -22,3 +22,10 @@ test-x86_64: test-i386.c test-i386.h test-i386-shift.h test-i386-muldiv.h
 
 vsyscall: $(SRC_PATH)/tests/tcg/x86_64/vsyscall.c
 	$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
+
+# TCG does not yet support all SSE (SIGILL on pshufb)
+# sha512-sse: CFLAGS=-march=core2 -O3
+# sha512-sse: sha512.c
+# 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+TESTS+=sha512-sse