diff options
412 files changed, 11053 insertions, 9559 deletions
diff --git a/.gitlab-ci.d/buildtest-template.yml b/.gitlab-ci.d/buildtest-template.yml new file mode 100644 index 0000000000..3e3e19d96b --- /dev/null +++ b/.gitlab-ci.d/buildtest-template.yml @@ -0,0 +1,81 @@ +.native_build_job_template: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + before_script: + - JOBS=$(expr $(nproc) + 1) + script: + - if test -n "$LD_JOBS"; + then + scripts/git-submodule.sh update meson ; + fi + - mkdir build + - cd build + - if test -n "$TARGETS"; + then + ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=git} $CONFIGURE_ARGS --target-list="$TARGETS" ; + else + ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=git} $CONFIGURE_ARGS ; + fi || { cat config.log meson-logs/meson-log.txt && exit 1; } + - if test -n "$LD_JOBS"; + then + ../meson/meson.py configure . -Dbackend_max_links="$LD_JOBS" ; + fi || exit 1; + - make -j"$JOBS" + - if test -n "$MAKE_CHECK_ARGS"; + then + make -j"$JOBS" $MAKE_CHECK_ARGS ; + fi + +.native_test_job_template: + stage: test + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + script: + - scripts/git-submodule.sh update + $(sed -n '/GIT_SUBMODULES=/ s/.*=// p' build/config-host.mak) + - cd build + - find . -type f -exec touch {} + + # Avoid recompiling by hiding ninja with NINJA=":" + - make NINJA=":" $MAKE_CHECK_ARGS + +.acceptance_test_job_template: + extends: .native_test_job_template + cache: + key: "${CI_JOB_NAME}-cache" + paths: + - ${CI_PROJECT_DIR}/avocado-cache + policy: pull-push + artifacts: + name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG" + when: on_failure + expire_in: 7 days + paths: + - build/tests/results/latest/results.xml + - build/tests/results/latest/test-results + reports: + junit: build/tests/results/latest/results.xml + before_script: + - mkdir -p ~/.config/avocado + - echo "[datadir.paths]" > ~/.config/avocado/avocado.conf + - echo "cache_dirs = ['${CI_PROJECT_DIR}/avocado-cache']" + >> ~/.config/avocado/avocado.conf + - echo -e '[job.output.testlogs]\nstatuses = ["FAIL", "INTERRUPT"]' + >> ~/.config/avocado/avocado.conf + - if [ -d ${CI_PROJECT_DIR}/avocado-cache ]; then + du -chs ${CI_PROJECT_DIR}/avocado-cache ; + fi + - export AVOCADO_ALLOW_UNTRUSTED_CODE=1 + after_script: + - cd build + - du -chs ${CI_PROJECT_DIR}/avocado-cache + rules: + # Only run these jobs if running on the mainstream namespace, + # or if the user set the QEMU_CI_AVOCADO_TESTING variable (either + # in its namespace setting or via git-push option, see documentation + # in /.gitlab-ci.yml of this repository). + - if: '$CI_PROJECT_NAMESPACE == "qemu-project"' + when: always + - if: '$QEMU_CI_AVOCADO_TESTING' + when: always + # Otherwise, set to manual (the jobs are created but not run). + - when: manual + allow_failure: true diff --git a/.gitlab-ci.d/buildtest.yml b/.gitlab-ci.d/buildtest.yml new file mode 100644 index 0000000000..b72c57e4df --- /dev/null +++ b/.gitlab-ci.d/buildtest.yml @@ -0,0 +1,695 @@ +include: + - local: '/.gitlab-ci.d/buildtest-template.yml' + +build-system-alpine: + extends: .native_build_job_template + needs: + - job: amd64-alpine-container + variables: + IMAGE: alpine + TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu + microblazeel-softmmu mips64el-softmmu + MAKE_CHECK_ARGS: check-build + CONFIGURE_ARGS: --enable-docs --enable-trace-backends=log,simple,syslog + artifacts: + expire_in: 2 days + paths: + - .git-submodule-status + - build + +check-system-alpine: + extends: .native_test_job_template + needs: + - job: build-system-alpine + artifacts: true + variables: + IMAGE: alpine + MAKE_CHECK_ARGS: check + +acceptance-system-alpine: + extends: .acceptance_test_job_template + needs: + - job: build-system-alpine + artifacts: true + variables: + IMAGE: alpine + MAKE_CHECK_ARGS: check-acceptance + +build-system-ubuntu: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-slirp=system + TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu + microblazeel-softmmu mips64el-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-ubuntu: + extends: .native_test_job_template + needs: + - job: build-system-ubuntu + artifacts: true + variables: + IMAGE: ubuntu2004 + MAKE_CHECK_ARGS: check + +acceptance-system-ubuntu: + extends: .acceptance_test_job_template + needs: + - job: build-system-ubuntu + artifacts: true + variables: + IMAGE: ubuntu2004 + MAKE_CHECK_ARGS: check-acceptance + +build-system-debian: + extends: .native_build_job_template + needs: + job: amd64-debian-container + variables: + IMAGE: debian-amd64 + CONFIGURE_ARGS: --enable-fdt=system + TARGETS: arm-softmmu avr-softmmu i386-softmmu mipsel-softmmu + riscv64-softmmu sh4eb-softmmu sparc-softmmu xtensaeb-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-debian: + extends: .native_test_job_template + needs: + - job: build-system-debian + artifacts: true + variables: + IMAGE: debian-amd64 + MAKE_CHECK_ARGS: check + +acceptance-system-debian: + extends: .acceptance_test_job_template + needs: + - job: build-system-debian + artifacts: true + variables: + IMAGE: debian-amd64 + MAKE_CHECK_ARGS: check-acceptance + +build-system-fedora: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs + --enable-fdt=system --enable-slirp=system --enable-capstone=system + TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu + xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-fedora: + extends: .native_test_job_template + needs: + - job: build-system-fedora + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-system-fedora: + extends: .acceptance_test_job_template + needs: + - job: build-system-fedora + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +build-system-centos: + extends: .native_build_job_template + needs: + job: amd64-centos8-container + variables: + IMAGE: centos8 + CONFIGURE_ARGS: --disable-nettle --enable-gcrypt --enable-fdt=system + --enable-modules --enable-trace-backends=dtrace + TARGETS: ppc64-softmmu or1k-softmmu s390x-softmmu + x86_64-softmmu rx-softmmu sh4-softmmu nios2-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-centos: + extends: .native_test_job_template + needs: + - job: build-system-centos + artifacts: true + variables: + IMAGE: centos8 + MAKE_CHECK_ARGS: check + +acceptance-system-centos: + extends: .acceptance_test_job_template + needs: + - job: build-system-centos + artifacts: true + variables: + IMAGE: centos8 + MAKE_CHECK_ARGS: check-acceptance + +build-system-opensuse: + extends: .native_build_job_template + needs: + job: amd64-opensuse-leap-container + variables: + IMAGE: opensuse-leap + CONFIGURE_ARGS: --enable-fdt=system + TARGETS: s390x-softmmu x86_64-softmmu aarch64-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-opensuse: + extends: .native_test_job_template + needs: + - job: build-system-opensuse + artifacts: true + variables: + IMAGE: opensuse-leap + MAKE_CHECK_ARGS: check + +acceptance-system-opensuse: + extends: .acceptance_test_job_template + needs: + - job: build-system-opensuse + artifacts: true + variables: + IMAGE: opensuse-leap + MAKE_CHECK_ARGS: check-acceptance + + +build-disabled: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + CONFIGURE_ARGS: + --disable-attr + --disable-auth-pam + --disable-avx2 + --disable-bochs + --disable-brlapi + --disable-bzip2 + --disable-cap-ng + --disable-capstone + --disable-cloop + --disable-coroutine-pool + --disable-curl + --disable-curses + --disable-dmg + --disable-docs + --disable-gcrypt + --disable-glusterfs + --disable-gnutls + --disable-gtk + --disable-guest-agent + --disable-iconv + --disable-keyring + --disable-kvm + --disable-libiscsi + --disable-libpmem + --disable-libssh + --disable-libudev + --disable-libusb + --disable-libxml2 + --disable-linux-aio + --disable-live-block-migration + --disable-lzo + --disable-malloc-trim + --disable-mpath + --disable-nettle + --disable-numa + --disable-opengl + --disable-parallels + --disable-pie + --disable-qcow1 + --disable-qed + --disable-qom-cast-debug + --disable-rbd + --disable-rdma + --disable-replication + --disable-sdl + --disable-seccomp + --disable-slirp + --disable-smartcard + --disable-snappy + --disable-sparse + --disable-spice + --disable-strip + --disable-tpm + --disable-usb-redir + --disable-vdi + --disable-vhost-crypto + --disable-vhost-net + --disable-vhost-scsi + --disable-vhost-kernel + --disable-vhost-user + --disable-vhost-vdpa + --disable-vhost-vsock + --disable-virglrenderer + --disable-vnc + --disable-vte + --disable-vvfat + --disable-xen + --disable-zstd + TARGETS: arm-softmmu i386-softmmu ppc64-softmmu mips64-softmmu + s390x-softmmu i386-linux-user + MAKE_CHECK_ARGS: check-qtest SPEED=slow + +# This jobs explicitly disable TCG (--disable-tcg), KVM is detected by +# the configure script. The container doesn't contain Xen headers so +# Xen accelerator is not detected / selected. As result it build the +# i386-softmmu and x86_64-softmmu with KVM being the single accelerator +# available. +# Also use a different coroutine implementation (which is only really of +# interest to KVM users, i.e. with TCG disabled) +build-tcg-disabled: + extends: .native_build_job_template + needs: + job: amd64-centos8-container + variables: + IMAGE: centos8 + script: + - mkdir build + - cd build + - ../configure --disable-tcg --audio-drv-list="" --with-coroutine=ucontext + || { cat config.log meson-logs/meson-log.txt && exit 1; } + - make -j"$JOBS" + - make check-unit + - make check-qapi-schema + - cd tests/qemu-iotests/ + - ./check -raw 001 002 003 004 005 008 009 010 011 012 021 025 032 033 048 + 052 063 077 086 101 104 106 113 148 150 151 152 157 159 160 163 + 170 171 183 184 192 194 197 208 215 221 222 226 227 236 253 277 + - ./check -qcow2 028 051 056 057 058 065 068 082 085 091 095 096 102 122 + 124 132 139 142 144 145 151 152 155 157 165 194 196 197 200 202 + 208 209 215 216 218 222 227 234 246 247 248 250 254 255 257 258 + 260 261 262 263 264 270 272 273 277 279 + +build-user: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-system + MAKE_CHECK_ARGS: check-tcg + +build-user-static: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-system --static + MAKE_CHECK_ARGS: check-tcg + +# Because the hexagon cross-compiler takes so long to build we don't rely +# on the CI system to build it and hence this job has an optional dependency +# declared. The image is manually uploaded. +build-user-hexagon: + extends: .native_build_job_template + needs: + job: hexagon-cross-container + optional: true + variables: + IMAGE: debian-hexagon-cross + TARGETS: hexagon-linux-user + CONFIGURE_ARGS: --disable-tools --disable-docs --enable-debug-tcg + MAKE_CHECK_ARGS: check-tcg + +# Only build the softmmu targets we have check-tcg tests for +build-some-softmmu: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --enable-debug + TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu + MAKE_CHECK_ARGS: check-tcg + +# Run check-tcg against linux-user (with plugins) +# we skip sparc64-linux-user until it has been fixed somewhat +# we skip cris-linux-user as it doesn't use the common run loop +build-user-plugins: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-system --enable-plugins --enable-debug-tcg --target-list-exclude=sparc64-linux-user,cris-linux-user + MAKE_CHECK_ARGS: check-tcg + timeout: 1h 30m + +build-some-softmmu-plugins: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-user --enable-plugins --enable-debug-tcg + TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu + MAKE_CHECK_ARGS: check-tcg + +clang-system: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ + --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined + TARGETS: alpha-softmmu arm-softmmu m68k-softmmu mips64-softmmu + ppc-softmmu s390x-softmmu + MAKE_CHECK_ARGS: check-qtest check-tcg + +clang-user: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --disable-system + --target-list-exclude=microblazeel-linux-user,aarch64_be-linux-user,i386-linux-user,m68k-linux-user,mipsn32el-linux-user,xtensaeb-linux-user + --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined + MAKE_CHECK_ARGS: check-unit check-tcg + +# Set LD_JOBS=1 because this requires LTO and ld consumes a large amount of memory. +# On gitlab runners, default value sometimes end up calling 2 lds concurrently and +# triggers an Out-Of-Memory error +# +# Since slirp callbacks are used in QEMU Timers, slirp needs to be compiled together +# with QEMU and linked as a static library to avoid false positives in CFI checks. +# This can be accomplished by using -enable-slirp=git, which avoids the use of +# a system-wide version of the library +# +# Split in three sets of build/check/acceptance to limit the execution time of each +# job +build-cfi-aarch64: + extends: .native_build_job_template + needs: + - job: amd64-fedora-container + variables: + LD_JOBS: 1 + AR: llvm-ar + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug + --enable-safe-stack --enable-slirp=git + TARGETS: aarch64-softmmu + MAKE_CHECK_ARGS: check-build + timeout: 70m + artifacts: + expire_in: 2 days + paths: + - build + +check-cfi-aarch64: + extends: .native_test_job_template + needs: + - job: build-cfi-aarch64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-cfi-aarch64: + extends: .acceptance_test_job_template + needs: + - job: build-cfi-aarch64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +build-cfi-ppc64-s390x: + extends: .native_build_job_template + needs: + - job: amd64-fedora-container + variables: + LD_JOBS: 1 + AR: llvm-ar + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug + --enable-safe-stack --enable-slirp=git + TARGETS: ppc64-softmmu s390x-softmmu + MAKE_CHECK_ARGS: check-build + timeout: 70m + artifacts: + expire_in: 2 days + paths: + - build + +check-cfi-ppc64-s390x: + extends: .native_test_job_template + needs: + - job: build-cfi-ppc64-s390x + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-cfi-ppc64-s390x: + extends: .acceptance_test_job_template + needs: + - job: build-cfi-ppc64-s390x + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +build-cfi-x86_64: + extends: .native_build_job_template + needs: + - job: amd64-fedora-container + variables: + LD_JOBS: 1 + AR: llvm-ar + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug + --enable-safe-stack --enable-slirp=git + TARGETS: x86_64-softmmu + MAKE_CHECK_ARGS: check-build + timeout: 70m + artifacts: + expire_in: 2 days + paths: + - build + +check-cfi-x86_64: + extends: .native_test_job_template + needs: + - job: build-cfi-x86_64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-cfi-x86_64: + extends: .acceptance_test_job_template + needs: + - job: build-cfi-x86_64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +tsan-build: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-tsan --cc=clang-10 --cxx=clang++-10 + --enable-trace-backends=ust --enable-fdt=system --enable-slirp=system + TARGETS: x86_64-softmmu ppc64-softmmu riscv64-softmmu x86_64-linux-user + MAKE_CHECK_ARGS: bench V=1 + +# These targets are on the way out +build-deprecated: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools + MAKE_CHECK_ARGS: build-tcg + TARGETS: ppc64abi32-linux-user + artifacts: + expire_in: 2 days + paths: + - build + +# We split the check-tcg step as test failures are expected but we still +# want to catch the build breaking. +check-deprecated: + extends: .native_test_job_template + needs: + - job: build-deprecated + artifacts: true + variables: + IMAGE: debian-all-test-cross + MAKE_CHECK_ARGS: check-tcg + allow_failure: true + +# gprof/gcov are GCC features +gprof-gcov: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-gprof --enable-gcov + MAKE_CHECK_ARGS: check + TARGETS: aarch64-softmmu ppc64-softmmu s390x-softmmu x86_64-softmmu + timeout: 70m + after_script: + - ${CI_PROJECT_DIR}/scripts/ci/coverage-summary.sh + +build-oss-fuzz: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + script: + - mkdir build-oss-fuzz + - CC="clang" CXX="clang++" CFLAGS="-fsanitize=address" + ./scripts/oss-fuzz/build.sh + - export ASAN_OPTIONS="fast_unwind_on_malloc=0" + - for fuzzer in $(find ./build-oss-fuzz/DEST_DIR/ -executable -type f + | grep -v slirp); do + grep "LLVMFuzzerTestOneInput" ${fuzzer} > /dev/null 2>&1 || continue ; + echo Testing ${fuzzer} ... ; + "${fuzzer}" -runs=1 -seed=1 || exit 1 ; + done + # Unrelated to fuzzer: run some tests with -fsanitize=address + - cd build-oss-fuzz && make check-qtest-i386 check-unit + +build-tci: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + script: + - TARGETS="aarch64 alpha arm hppa m68k microblaze ppc64 s390x x86_64" + - mkdir build + - cd build + - ../configure --enable-tcg-interpreter + --target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)" || { cat config.log meson-logs/meson-log.txt && exit 1; } + - make -j"$JOBS" + - make tests/qtest/boot-serial-test tests/qtest/cdrom-test tests/qtest/pxe-test + - for tg in $TARGETS ; do + export QTEST_QEMU_BINARY="./qemu-system-${tg}" ; + ./tests/qtest/boot-serial-test || exit 1 ; + ./tests/qtest/cdrom-test || exit 1 ; + done + - QTEST_QEMU_BINARY="./qemu-system-x86_64" ./tests/qtest/pxe-test + - QTEST_QEMU_BINARY="./qemu-system-s390x" ./tests/qtest/pxe-test -m slow + - make check-tcg + +# Alternate coroutines implementations are only really of interest to KVM users +# However we can't test against KVM on Gitlab-CI so we can only run unit tests +build-coroutine-sigaltstack: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --with-coroutine=sigaltstack --disable-tcg + --enable-trace-backends=ftrace + MAKE_CHECK_ARGS: check-unit + +# Check our reduced build configurations +build-without-default-devices: + extends: .native_build_job_template + needs: + job: amd64-centos8-container + variables: + IMAGE: centos8 + CONFIGURE_ARGS: --without-default-devices --disable-user + +build-without-default-features: + extends: .native_build_job_template + needs: + job: amd64-debian-container + variables: + IMAGE: debian-amd64 + CONFIGURE_ARGS: --without-default-features --disable-user + --target-list-exclude=arm-softmmu,i386-softmmu,mipsel-softmmu,mips64-softmmu,ppc-softmmu + MAKE_CHECK_ARGS: check-unit + +build-libvhost-user: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/fedora:latest + needs: + job: amd64-fedora-container + before_script: + - dnf install -y meson ninja-build + script: + - mkdir subprojects/libvhost-user/build + - cd subprojects/libvhost-user/build + - meson + - ninja + +# No targets are built here, just tools, docs, and unit tests. This +# also feeds into the eventual documentation deployment steps later +build-tools-and-docs-debian: + extends: .native_build_job_template + needs: + job: amd64-debian-container + variables: + IMAGE: debian-amd64 + MAKE_CHECK_ARGS: check-unit check-softfloat ctags TAGS cscope + CONFIGURE_ARGS: --disable-system --disable-user --enable-docs --enable-tools + artifacts: + expire_in: 2 days + paths: + - build + +# Prepare for GitLab pages deployment. Anything copied into the +# "public" directory will be deployed to $USER.gitlab.io/$PROJECT +pages: + image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:latest + stage: test + needs: + - job: build-tools-and-docs-debian + script: + - mkdir -p public + # HTML-ised source tree + - make gtags + - htags -anT --tree-view=filetree -m qemu_init + -t "Welcome to the QEMU sourcecode" + - mv HTML public/src + # Project documentation + - make -C build install DESTDIR=$(pwd)/temp-install + - mv temp-install/usr/local/share/doc/qemu/* public/ + artifacts: + paths: + - public diff --git a/.gitlab-ci.d/container-core.yml b/.gitlab-ci.d/container-core.yml new file mode 100644 index 0000000000..e8dd1f476a --- /dev/null +++ b/.gitlab-ci.d/container-core.yml @@ -0,0 +1,17 @@ +include: + - local: '/.gitlab-ci.d/container-template.yml' + +amd64-centos8-container: + extends: .container_job_template + variables: + NAME: centos8 + +amd64-fedora-container: + extends: .container_job_template + variables: + NAME: fedora + +amd64-debian10-container: + extends: .container_job_template + variables: + NAME: debian10 diff --git a/.gitlab-ci.d/container-cross.yml b/.gitlab-ci.d/container-cross.yml new file mode 100644 index 0000000000..0fcebe363a --- /dev/null +++ b/.gitlab-ci.d/container-cross.yml @@ -0,0 +1,192 @@ +alpha-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-alpha-cross + +amd64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-amd64-cross + +amd64-debian-user-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-all-test-cross + +arm64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-arm64-cross + +arm64-test-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian11-container'] + variables: + NAME: debian-arm64-test-cross + +armel-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-armel-cross + +armhf-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-armhf-cross + +# We never want to build hexagon in the CI system and by default we +# always want to refer to the master registry where it lives. +hexagon-cross-container: + image: docker:stable + stage: containers + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project"' + when: never + - when: always + variables: + NAME: debian-hexagon-cross + GIT_DEPTH: 1 + services: + - docker:dind + before_script: + - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" + - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/qemu/$NAME:latest" + - docker info + - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" + script: + - echo "TAG:$TAG" + - echo "COMMON_TAG:$COMMON_TAG" + - docker pull $COMMON_TAG + - docker tag $COMMON_TAG $TAG + - docker push "$TAG" + after_script: + - docker logout + +hppa-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-hppa-cross + +m68k-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-m68k-cross + +mips64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mips64-cross + +mips64el-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mips64el-cross + +mips-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mips-cross + +mipsel-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mipsel-cross + +powerpc-test-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian11-container'] + variables: + NAME: debian-powerpc-test-cross + +ppc64el-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-ppc64el-cross + +riscv64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-riscv64-cross + +s390x-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-s390x-cross + +sh4-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-sh4-cross + +sparc64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-sparc64-cross + +tricore-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-tricore-cross + +xtensa-debian-cross-container: + extends: .container_job_template + variables: + NAME: debian-xtensa-cross + +cris-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-cris-cross + +i386-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-i386-cross + +win32-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-win32-cross + +win64-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-win64-cross diff --git a/.gitlab-ci.d/container-template.yml b/.gitlab-ci.d/container-template.yml new file mode 100644 index 0000000000..1baecd9460 --- /dev/null +++ b/.gitlab-ci.d/container-template.yml @@ -0,0 +1,21 @@ +.container_job_template: + image: docker:stable + stage: containers + services: + - docker:dind + before_script: + - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" + - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/$NAME:latest" + - apk add python3 + - docker info + - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" + script: + - echo "TAG:$TAG" + - echo "COMMON_TAG:$COMMON_TAG" + - ./tests/docker/docker.py --engine docker build + -t "qemu/$NAME" -f "tests/docker/dockerfiles/$NAME.docker" + -r $CI_REGISTRY/qemu-project/qemu + - docker tag "qemu/$NAME" "$TAG" + - docker push "$TAG" + after_script: + - docker logout diff --git a/.gitlab-ci.d/containers.yml b/.gitlab-ci.d/containers.yml index 765408ae27..cd06d3f5f4 100644 --- a/.gitlab-ci.d/containers.yml +++ b/.gitlab-ci.d/containers.yml @@ -1,72 +1,17 @@ -.container_job_template: - image: docker:stable - stage: containers - services: - - docker:dind - before_script: - - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" - - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/$NAME:latest" - - apk add python3 - - docker info - - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" - script: - - echo "TAG:$TAG" - - echo "COMMON_TAG:$COMMON_TAG" - - docker pull "$TAG" || docker pull "$COMMON_TAG" || true - - ./tests/docker/docker.py --engine docker build - -t "qemu/$NAME" -f "tests/docker/dockerfiles/$NAME.docker" - -r $CI_REGISTRY_IMAGE - - docker tag "qemu/$NAME" "$TAG" - - docker push "$TAG" - after_script: - - docker logout +include: + - local: '/.gitlab-ci.d/container-core.yml' + - local: '/.gitlab-ci.d/container-cross.yml' amd64-alpine-container: extends: .container_job_template variables: NAME: alpine -amd64-centos7-container: - extends: .container_job_template - variables: - NAME: centos7 - -amd64-centos8-container: - extends: .container_job_template - variables: - NAME: centos8 - -amd64-debian10-container: - extends: .container_job_template - variables: - NAME: debian10 - amd64-debian11-container: extends: .container_job_template variables: NAME: debian11 -alpha-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-alpha-cross - -amd64-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-amd64-cross - -amd64-debian-user-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-all-test-cross - amd64-debian-container: extends: .container_job_template stage: containers-layer2 @@ -74,155 +19,6 @@ amd64-debian-container: variables: NAME: debian-amd64 -arm64-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-arm64-cross - -arm64-test-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian11-container'] - variables: - NAME: debian-arm64-test-cross - -armel-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-armel-cross - -armhf-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-armhf-cross - -hppa-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-hppa-cross - -m68k-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-m68k-cross - -mips64-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mips64-cross - -mips64el-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mips64el-cross - -mips-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mips-cross - -mipsel-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mipsel-cross - -powerpc-test-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian11-container'] - variables: - NAME: debian-powerpc-test-cross - -ppc64el-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-ppc64el-cross - -riscv64-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-riscv64-cross - -s390x-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-s390x-cross - -sh4-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-sh4-cross - -sparc64-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-sparc64-cross - -tricore-debian-cross-container: - extends: .container_job_template - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-tricore-cross - -xtensa-debian-cross-container: - extends: .container_job_template - variables: - NAME: debian-xtensa-cross - -cris-fedora-cross-container: - extends: .container_job_template - variables: - NAME: fedora-cris-cross - -amd64-fedora-container: - extends: .container_job_template - variables: - NAME: fedora - -i386-fedora-cross-container: - extends: .container_job_template - variables: - NAME: fedora-i386-cross - -win32-fedora-cross-container: - extends: .container_job_template - variables: - NAME: fedora-win32-cross - -win64-fedora-cross-container: - extends: .container_job_template - variables: - NAME: fedora-win64-cross - amd64-ubuntu1804-container: extends: .container_job_template variables: @@ -242,3 +38,8 @@ amd64-opensuse-leap-container: extends: .container_job_template variables: NAME: opensuse-leap + +python-container: + extends: .container_job_template + variables: + NAME: python diff --git a/.gitlab-ci.d/crossbuild-template.yml b/.gitlab-ci.d/crossbuild-template.yml new file mode 100644 index 0000000000..1be541174c --- /dev/null +++ b/.gitlab-ci.d/crossbuild-template.yml @@ -0,0 +1,41 @@ +.cross_system_build_job: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + timeout: 80m + script: + - mkdir build + - cd build + - PKG_CONFIG_PATH=$PKG_CONFIG_PATH + ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS + --disable-user --target-list-exclude="arm-softmmu cris-softmmu + i386-softmmu microblaze-softmmu mips-softmmu mipsel-softmmu + mips64-softmmu ppc-softmmu sh4-softmmu xtensa-softmmu" + - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS + +# Job to cross-build specific accelerators. +# +# Set the $ACCEL variable to select the specific accelerator (default to +# KVM), and set extra options (such disabling other accelerators) via the +# $EXTRA_CONFIGURE_OPTS variable. +.cross_accel_build_job: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + timeout: 30m + script: + - mkdir build + - cd build + - PKG_CONFIG_PATH=$PKG_CONFIG_PATH + ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS + --disable-tools --enable-${ACCEL:-kvm} $EXTRA_CONFIGURE_OPTS + - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS + +.cross_user_build_job: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + script: + - mkdir build + - cd build + - PKG_CONFIG_PATH=$PKG_CONFIG_PATH + ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS + --disable-system + - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS diff --git a/.gitlab-ci.d/crossbuilds.yml b/.gitlab-ci.d/crossbuilds.yml index e44e4b49a2..6b3865c9e8 100644 --- a/.gitlab-ci.d/crossbuilds.yml +++ b/.gitlab-ci.d/crossbuilds.yml @@ -1,44 +1,5 @@ -.cross_system_build_job: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - timeout: 80m - script: - - mkdir build - - cd build - - PKG_CONFIG_PATH=$PKG_CONFIG_PATH - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS - --disable-user --target-list-exclude="arm-softmmu cris-softmmu - i386-softmmu microblaze-softmmu mips-softmmu mipsel-softmmu - mips64-softmmu ppc-softmmu sh4-softmmu xtensa-softmmu" - - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS - -# Job to cross-build specific accelerators. -# -# Set the $ACCEL variable to select the specific accelerator (default to -# KVM), and set extra options (such disabling other accelerators) via the -# $ACCEL_CONFIGURE_OPTS variable. -.cross_accel_build_job: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - timeout: 30m - script: - - mkdir build - - cd build - - PKG_CONFIG_PATH=$PKG_CONFIG_PATH - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS - --disable-tools --enable-${ACCEL:-kvm} $ACCEL_CONFIGURE_OPTS - - make -j$(expr $(nproc) + 1) all check-build - -.cross_user_build_job: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - script: - - mkdir build - - cd build - - PKG_CONFIG_PATH=$PKG_CONFIG_PATH - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS - --disable-system - - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS +include: + - local: '/.gitlab-ci.d/crossbuild-template.yml' cross-armel-system: extends: .cross_system_build_job @@ -98,6 +59,15 @@ cross-i386-user: IMAGE: fedora-i386-cross MAKE_CHECK_ARGS: check +cross-i386-tci: + extends: .cross_accel_build_job + timeout: 60m + variables: + IMAGE: fedora-i386-cross + ACCEL: tcg-interpreter + EXTRA_CONFIGURE_OPTS: --target-list=i386-softmmu,i386-linux-user,aarch64-softmmu,aarch64-linux-user,ppc-softmmu,ppc-linux-user + MAKE_CHECK_ARGS: check check-tcg + cross-mips-system: extends: .cross_system_build_job needs: @@ -174,7 +144,7 @@ cross-s390x-kvm-only: job: s390x-debian-cross-container variables: IMAGE: debian-s390x-cross - ACCEL_CONFIGURE_OPTS: --disable-tcg + EXTRA_CONFIGURE_OPTS: --disable-tcg cross-mips64el-kvm-only: extends: .cross_accel_build_job @@ -182,7 +152,7 @@ cross-mips64el-kvm-only: job: mips64el-debian-cross-container variables: IMAGE: debian-mips64el-cross - ACCEL_CONFIGURE_OPTS: --disable-tcg --target-list=mips64el-softmmu + EXTRA_CONFIGURE_OPTS: --disable-tcg --target-list=mips64el-softmmu cross-win32-system: extends: .cross_system_build_job @@ -205,7 +175,7 @@ cross-amd64-xen-only: variables: IMAGE: debian-amd64-cross ACCEL: xen - ACCEL_CONFIGURE_OPTS: --disable-tcg --disable-kvm + EXTRA_CONFIGURE_OPTS: --disable-tcg --disable-kvm cross-arm64-xen-only: extends: .cross_accel_build_job @@ -214,4 +184,4 @@ cross-arm64-xen-only: variables: IMAGE: debian-arm64-cross ACCEL: xen - ACCEL_CONFIGURE_OPTS: --disable-tcg --disable-kvm + EXTRA_CONFIGURE_OPTS: --disable-tcg --disable-kvm diff --git a/.gitlab-ci.d/qemu-project.yml b/.gitlab-ci.d/qemu-project.yml new file mode 100644 index 0000000000..64cb2ba1da --- /dev/null +++ b/.gitlab-ci.d/qemu-project.yml @@ -0,0 +1,11 @@ +# This file contains the set of jobs run by the QEMU project: +# https://gitlab.com/qemu-project/qemu/-/pipelines + +include: + - local: '/.gitlab-ci.d/stages.yml' + - local: '/.gitlab-ci.d/edk2.yml' + - local: '/.gitlab-ci.d/opensbi.yml' + - local: '/.gitlab-ci.d/containers.yml' + - local: '/.gitlab-ci.d/crossbuilds.yml' + - local: '/.gitlab-ci.d/buildtest.yml' + - local: '/.gitlab-ci.d/static_checks.yml' diff --git a/.gitlab-ci.d/stages.yml b/.gitlab-ci.d/stages.yml new file mode 100644 index 0000000000..f50826018d --- /dev/null +++ b/.gitlab-ci.d/stages.yml @@ -0,0 +1,8 @@ +# Currently we have two build stages after our containers are built: +# - build (for traditional build and test or first stage build) +# - test (for test stages, using build artefacts from a build stage) +stages: + - containers + - containers-layer2 + - build + - test diff --git a/.gitlab-ci.d/static_checks.yml b/.gitlab-ci.d/static_checks.yml new file mode 100644 index 0000000000..8e30872164 --- /dev/null +++ b/.gitlab-ci.d/static_checks.yml @@ -0,0 +1,47 @@ +check-patch: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/centos8:latest + needs: + job: amd64-centos8-container + script: .gitlab-ci.d/check-patch.py + variables: + GIT_DEPTH: 1000 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH' + when: never + - when: on_success + allow_failure: true + +check-dco: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/centos8:latest + needs: + job: amd64-centos8-container + script: .gitlab-ci.d/check-dco.py + variables: + GIT_DEPTH: 1000 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH' + when: never + - when: on_success + +check-python-pipenv: + stage: test + image: $CI_REGISTRY_IMAGE/qemu/python:latest + script: + - make -C python venv-check + variables: + GIT_DEPTH: 1 + needs: + job: python-container + +check-python-tox: + stage: test + image: $CI_REGISTRY_IMAGE/qemu/python:latest + script: + - make -C python check-tox + variables: + GIT_DEPTH: 1 + needs: + job: python-container + allow_failure: true diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index f718b61fa7..6dc5385e69 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -1,851 +1,39 @@ -# Currently we have two build stages after our containers are built: -# - build (for traditional build and test or first stage build) -# - test (for test stages, using build artefacts from a build stage) -stages: - - containers - - containers-layer2 - - build - - test - -include: - - local: '/.gitlab-ci.d/edk2.yml' - - local: '/.gitlab-ci.d/opensbi.yml' - - local: '/.gitlab-ci.d/containers.yml' - - local: '/.gitlab-ci.d/crossbuilds.yml' - -.native_build_job_template: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - before_script: - - JOBS=$(expr $(nproc) + 1) - script: - - if test -n "$LD_JOBS"; - then - scripts/git-submodule.sh update meson ; - fi - - mkdir build - - cd build - - if test -n "$TARGETS"; - then - ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=internal} $CONFIGURE_ARGS --target-list="$TARGETS" ; - else - ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=internal} $CONFIGURE_ARGS ; - fi || { cat config.log meson-logs/meson-log.txt && exit 1; } - - if test -n "$LD_JOBS"; - then - ../meson/meson.py configure . -Dbackend_max_links="$LD_JOBS" ; - fi || exit 1; - - make -j"$JOBS" - - if test -n "$MAKE_CHECK_ARGS"; - then - make -j"$JOBS" $MAKE_CHECK_ARGS ; - fi - -.native_test_job_template: - stage: test - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - script: - - scripts/git-submodule.sh update - $(sed -n '/GIT_SUBMODULES=/ s/.*=// p' build/config-host.mak) - - cd build - - find . -type f -exec touch {} + - # Avoid recompiling by hiding ninja with NINJA=":" - - make NINJA=":" $MAKE_CHECK_ARGS - -.acceptance_template: &acceptance_definition - cache: - key: "${CI_JOB_NAME}-cache" - paths: - - ${CI_PROJECT_DIR}/avocado-cache - policy: pull-push - artifacts: - name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG" - when: always - expire_in: 2 days - paths: - - build/tests/results/latest/results.xml - - build/tests/results/latest/test-results - reports: - junit: build/tests/results/latest/results.xml - before_script: - - mkdir -p ~/.config/avocado - - echo "[datadir.paths]" > ~/.config/avocado/avocado.conf - - echo "cache_dirs = ['${CI_PROJECT_DIR}/avocado-cache']" - >> ~/.config/avocado/avocado.conf - - echo -e '[job.output.testlogs]\nstatuses = ["FAIL", "INTERRUPT"]' - >> ~/.config/avocado/avocado.conf - - if [ -d ${CI_PROJECT_DIR}/avocado-cache ]; then - du -chs ${CI_PROJECT_DIR}/avocado-cache ; - fi - - export AVOCADO_ALLOW_UNTRUSTED_CODE=1 - after_script: - - cd build - - du -chs ${CI_PROJECT_DIR}/avocado-cache - -build-system-alpine: - extends: .native_build_job_template - needs: - - job: amd64-alpine-container - variables: - IMAGE: alpine - TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu - microblazeel-softmmu mips64el-softmmu - MAKE_CHECK_ARGS: check-build - CONFIGURE_ARGS: --enable-docs --enable-trace-backends=log,simple,syslog - artifacts: - expire_in: 2 days - paths: - - .git-submodule-status - - build - -check-system-alpine: - extends: .native_test_job_template - needs: - - job: build-system-alpine - artifacts: true - variables: - IMAGE: alpine - MAKE_CHECK_ARGS: check - -acceptance-system-alpine: - extends: .native_test_job_template - needs: - - job: build-system-alpine - artifacts: true - variables: - IMAGE: alpine - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-ubuntu: - extends: .native_build_job_template - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-slirp=system - TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu - microblazeel-softmmu mips64el-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-ubuntu: - extends: .native_test_job_template - needs: - - job: build-system-ubuntu - artifacts: true - variables: - IMAGE: ubuntu2004 - MAKE_CHECK_ARGS: check - -acceptance-system-ubuntu: - extends: .native_test_job_template - needs: - - job: build-system-ubuntu - artifacts: true - variables: - IMAGE: ubuntu2004 - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-debian: - extends: .native_build_job_template - needs: - job: amd64-debian-container - variables: - IMAGE: debian-amd64 - CONFIGURE_ARGS: --enable-fdt=system - TARGETS: arm-softmmu avr-softmmu i386-softmmu mipsel-softmmu - riscv64-softmmu sh4eb-softmmu sparc-softmmu xtensaeb-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-debian: - extends: .native_test_job_template - needs: - - job: build-system-debian - artifacts: true - variables: - IMAGE: debian-amd64 - MAKE_CHECK_ARGS: check - -acceptance-system-debian: - extends: .native_test_job_template - needs: - - job: build-system-debian - artifacts: true - variables: - IMAGE: debian-amd64 - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-fedora: - extends: .native_build_job_template - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs - --enable-fdt=system --enable-slirp=system --enable-capstone=system - TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu - xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-fedora: - extends: .native_test_job_template - needs: - - job: build-system-fedora - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-system-fedora: - extends: .native_test_job_template - needs: - - job: build-system-fedora - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-centos: - extends: .native_build_job_template - needs: - job: amd64-centos8-container - variables: - IMAGE: centos8 - CONFIGURE_ARGS: --disable-nettle --enable-gcrypt --enable-fdt=system - --enable-modules --enable-trace-backends=dtrace - TARGETS: ppc64-softmmu or1k-softmmu s390x-softmmu - x86_64-softmmu rx-softmmu sh4-softmmu nios2-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-centos: - extends: .native_test_job_template - needs: - - job: build-system-centos - artifacts: true - variables: - IMAGE: centos8 - MAKE_CHECK_ARGS: check - -acceptance-system-centos: - extends: .native_test_job_template - needs: - - job: build-system-centos - artifacts: true - variables: - IMAGE: centos8 - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-opensuse: - extends: .native_build_job_template - needs: - job: amd64-opensuse-leap-container - variables: - IMAGE: opensuse-leap - CONFIGURE_ARGS: --enable-fdt=system - TARGETS: s390x-softmmu x86_64-softmmu aarch64-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-opensuse: - extends: .native_test_job_template - needs: - - job: build-system-opensuse - artifacts: true - variables: - IMAGE: opensuse-leap - MAKE_CHECK_ARGS: check - -acceptance-system-opensuse: - extends: .native_test_job_template - needs: - - job: build-system-opensuse - artifacts: true - variables: - IMAGE: opensuse-leap - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - - -build-disabled: - extends: .native_build_job_template - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - CONFIGURE_ARGS: - --disable-attr - --disable-auth-pam - --disable-avx2 - --disable-bochs - --disable-brlapi - --disable-bzip2 - --disable-cap-ng - --disable-capstone - --disable-cloop - --disable-coroutine-pool - --disable-curl - --disable-curses - --disable-dmg - --disable-docs - --disable-gcrypt - --disable-glusterfs - --disable-gnutls - --disable-gtk - --disable-guest-agent - --disable-iconv - --disable-keyring - --disable-kvm - --disable-libiscsi - --disable-libpmem - --disable-libssh - --disable-libudev - --disable-libusb - --disable-libxml2 - --disable-linux-aio - --disable-live-block-migration - --disable-lzo - --disable-malloc-trim - --disable-mpath - --disable-nettle - --disable-numa - --disable-opengl - --disable-parallels - --disable-pie - --disable-qcow1 - --disable-qed - --disable-qom-cast-debug - --disable-rbd - --disable-rdma - --disable-replication - --disable-sdl - --disable-seccomp - --disable-slirp - --disable-smartcard - --disable-snappy - --disable-sparse - --disable-spice - --disable-strip - --disable-tpm - --disable-usb-redir - --disable-vdi - --disable-vhost-crypto - --disable-vhost-net - --disable-vhost-scsi - --disable-vhost-kernel - --disable-vhost-user - --disable-vhost-vdpa - --disable-vhost-vsock - --disable-virglrenderer - --disable-vnc - --disable-vte - --disable-vvfat - --disable-xen - --disable-zstd - TARGETS: arm-softmmu i386-softmmu ppc64-softmmu mips64-softmmu - s390x-softmmu i386-linux-user - MAKE_CHECK_ARGS: check-qtest SPEED=slow - -# This jobs explicitly disable TCG (--disable-tcg), KVM is detected by -# the configure script. The container doesn't contain Xen headers so -# Xen accelerator is not detected / selected. As result it build the -# i386-softmmu and x86_64-softmmu with KVM being the single accelerator -# available. -# Also use a different coroutine implementation (which is only really of -# interest to KVM users, i.e. with TCG disabled) -build-tcg-disabled: - extends: .native_build_job_template - needs: - job: amd64-centos8-container - variables: - IMAGE: centos8 - script: - - mkdir build - - cd build - - ../configure --disable-tcg --audio-drv-list="" --with-coroutine=ucontext - || { cat config.log meson-logs/meson-log.txt && exit 1; } - - make -j"$JOBS" - - make check-unit - - make check-qapi-schema - - cd tests/qemu-iotests/ - - ./check -raw 001 002 003 004 005 008 009 010 011 012 021 025 032 033 048 - 052 063 077 086 101 104 106 113 148 150 151 152 157 159 160 163 - 170 171 183 184 192 194 197 208 215 221 222 226 227 236 253 277 - - ./check -qcow2 028 051 056 057 058 065 068 082 085 091 095 096 102 122 - 124 132 139 142 144 145 151 152 155 157 165 194 196 197 200 202 - 208 209 215 216 218 222 227 234 246 247 248 250 254 255 257 258 - 260 261 262 263 264 270 272 273 277 279 - -build-user: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-system - MAKE_CHECK_ARGS: check-tcg - -build-user-static: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-system --static - MAKE_CHECK_ARGS: check-tcg - -# Because the hexagon cross-compiler takes so long to build we don't rely -# on the CI system to build it and hence this job has no dependency -# declared. The image is manually uploaded. -build-user-hexagon: - extends: .native_build_job_template - variables: - IMAGE: debian-hexagon-cross - TARGETS: hexagon-linux-user - CONFIGURE_ARGS: --disable-tools --disable-docs --enable-debug-tcg - MAKE_CHECK_ARGS: check-tcg - -# Only build the softmmu targets we have check-tcg tests for -build-some-softmmu: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --enable-debug - TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu - MAKE_CHECK_ARGS: check-tcg - -# Run check-tcg against linux-user (with plugins) -# we skip sparc64-linux-user until it has been fixed somewhat -# we skip cris-linux-user as it doesn't use the common run loop -build-user-plugins: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-system --enable-plugins --enable-debug-tcg --target-list-exclude=sparc64-linux-user,cris-linux-user - MAKE_CHECK_ARGS: check-tcg - timeout: 1h 30m - -build-user-centos7: - extends: .native_build_job_template - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - CONFIGURE_ARGS: --disable-system --disable-tools --disable-docs - MAKE_CHECK_ARGS: check-tcg - -build-some-softmmu-plugins: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-user --enable-plugins --enable-debug-tcg - TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu - MAKE_CHECK_ARGS: check-tcg - -clang-system: - extends: .native_build_job_template - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ - --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined - TARGETS: alpha-softmmu arm-softmmu m68k-softmmu mips64-softmmu - ppc-softmmu s390x-softmmu - MAKE_CHECK_ARGS: check-qtest check-tcg - -clang-user: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --disable-system - --target-list-exclude=microblazeel-linux-user,aarch64_be-linux-user,i386-linux-user,m68k-linux-user,mipsn32el-linux-user,xtensaeb-linux-user - --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined - MAKE_CHECK_ARGS: check-unit check-tcg - -# Set LD_JOBS=1 because this requires LTO and ld consumes a large amount of memory. -# On gitlab runners, default value sometimes end up calling 2 lds concurrently and -# triggers an Out-Of-Memory error # -# Since slirp callbacks are used in QEMU Timers, slirp needs to be compiled together -# with QEMU and linked as a static library to avoid false positives in CFI checks. -# This can be accomplished by using -enable-slirp=git, which avoids the use of -# a system-wide version of the library +# This is the GitLab CI configuration file for the mainstream QEMU +# project: https://gitlab.com/qemu-project/qemu/-/pipelines # -# Split in three sets of build/check/acceptance to limit the execution time of each -# job -build-cfi-aarch64: - extends: .native_build_job_template - needs: - - job: amd64-fedora-container - variables: - LD_JOBS: 1 - AR: llvm-ar - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git - TARGETS: aarch64-softmmu - MAKE_CHECK_ARGS: check-build - timeout: 70m - artifacts: - expire_in: 2 days - paths: - - build - -check-cfi-aarch64: - extends: .native_test_job_template - needs: - - job: build-cfi-aarch64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-cfi-aarch64: - extends: .native_test_job_template - needs: - - job: build-cfi-aarch64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-cfi-ppc64-s390x: - extends: .native_build_job_template - needs: - - job: amd64-fedora-container - variables: - LD_JOBS: 1 - AR: llvm-ar - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git - TARGETS: ppc64-softmmu s390x-softmmu - MAKE_CHECK_ARGS: check-build - timeout: 70m - artifacts: - expire_in: 2 days - paths: - - build - -check-cfi-ppc64-s390x: - extends: .native_test_job_template - needs: - - job: build-cfi-ppc64-s390x - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-cfi-ppc64-s390x: - extends: .native_test_job_template - needs: - - job: build-cfi-ppc64-s390x - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-cfi-x86_64: - extends: .native_build_job_template - needs: - - job: amd64-fedora-container - variables: - LD_JOBS: 1 - AR: llvm-ar - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git - TARGETS: x86_64-softmmu - MAKE_CHECK_ARGS: check-build - timeout: 70m - artifacts: - expire_in: 2 days - paths: - - build - -check-cfi-x86_64: - extends: .native_test_job_template - needs: - - job: build-cfi-x86_64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-cfi-x86_64: - extends: .native_test_job_template - needs: - - job: build-cfi-x86_64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -tsan-build: - extends: .native_build_job_template - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-tsan --cc=clang-10 --cxx=clang++-10 - --enable-trace-backends=ust --enable-fdt=system --enable-slirp=system - TARGETS: x86_64-softmmu ppc64-softmmu riscv64-softmmu x86_64-linux-user - MAKE_CHECK_ARGS: bench V=1 - -# These targets are on the way out -build-deprecated: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools - MAKE_CHECK_ARGS: build-tcg - TARGETS: ppc64abi32-linux-user - artifacts: - expire_in: 2 days - paths: - - build - -# We split the check-tcg step as test failures are expected but we still -# want to catch the build breaking. -check-deprecated: - extends: .native_test_job_template - needs: - - job: build-deprecated - artifacts: true - variables: - IMAGE: debian-all-test-cross - MAKE_CHECK_ARGS: check-tcg - allow_failure: true - -# gprof/gcov are GCC features -gprof-gcov: - extends: .native_build_job_template - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-gprof --enable-gcov - MAKE_CHECK_ARGS: check - TARGETS: aarch64-softmmu ppc64-softmmu s390x-softmmu x86_64-softmmu - timeout: 70m - after_script: - - ${CI_PROJECT_DIR}/scripts/ci/coverage-summary.sh - -build-oss-fuzz: - extends: .native_build_job_template - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - script: - - mkdir build-oss-fuzz - - CC="clang" CXX="clang++" CFLAGS="-fsanitize=address" - ./scripts/oss-fuzz/build.sh - - export ASAN_OPTIONS="fast_unwind_on_malloc=0" - - for fuzzer in $(find ./build-oss-fuzz/DEST_DIR/ -executable -type f - | grep -v slirp); do - grep "LLVMFuzzerTestOneInput" ${fuzzer} > /dev/null 2>&1 || continue ; - echo Testing ${fuzzer} ... ; - "${fuzzer}" -runs=1 -seed=1 || exit 1 ; - done - # Unrelated to fuzzer: run some tests with -fsanitize=address - - cd build-oss-fuzz && make check-qtest-i386 check-unit - -build-tci: - extends: .native_build_job_template - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - script: - - TARGETS="aarch64 alpha arm hppa m68k microblaze ppc64 s390x x86_64" - - mkdir build - - cd build - - ../configure --enable-tcg-interpreter - --target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)" || { cat config.log meson-logs/meson-log.txt && exit 1; } - - make -j"$JOBS" - - make tests/qtest/boot-serial-test tests/qtest/cdrom-test tests/qtest/pxe-test - - for tg in $TARGETS ; do - export QTEST_QEMU_BINARY="./qemu-system-${tg}" ; - ./tests/qtest/boot-serial-test || exit 1 ; - ./tests/qtest/cdrom-test || exit 1 ; - done - - QTEST_QEMU_BINARY="./qemu-system-x86_64" ./tests/qtest/pxe-test - - QTEST_QEMU_BINARY="./qemu-system-s390x" ./tests/qtest/pxe-test -m slow - - make check-tcg - -# Alternate coroutines implementations are only really of interest to KVM users -# However we can't test against KVM on Gitlab-CI so we can only run unit tests -build-coroutine-sigaltstack: - extends: .native_build_job_template - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --with-coroutine=sigaltstack --disable-tcg - --enable-trace-backends=ftrace - MAKE_CHECK_ARGS: check-unit - -# Most jobs test latest gcrypt or nettle builds +# !!! DO NOT ADD ANY NEW CONFIGURATION TO THIS FILE !!! # -# These jobs test old gcrypt and nettle from RHEL7 -# which had some API differences. -crypto-old-nettle: - extends: .native_build_job_template - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - TARGETS: x86_64-softmmu x86_64-linux-user - CONFIGURE_ARGS: --disable-gcrypt --enable-nettle - MAKE_CHECK_ARGS: check - -crypto-old-gcrypt: - extends: .native_build_job_template - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - TARGETS: x86_64-softmmu x86_64-linux-user - CONFIGURE_ARGS: --disable-nettle --enable-gcrypt - MAKE_CHECK_ARGS: check - -crypto-only-gnutls: - extends: .native_build_job_template - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - TARGETS: x86_64-softmmu x86_64-linux-user - CONFIGURE_ARGS: --disable-nettle --disable-gcrypt --enable-gnutls - MAKE_CHECK_ARGS: check - - -# Check our reduced build configurations -build-without-default-devices: - extends: .native_build_job_template - needs: - job: amd64-centos8-container - variables: - IMAGE: centos8 - CONFIGURE_ARGS: --without-default-devices --disable-user - -build-without-default-features: - extends: .native_build_job_template - needs: - job: amd64-debian-container - variables: - IMAGE: debian-amd64 - CONFIGURE_ARGS: --without-default-features --disable-user - --target-list-exclude=arm-softmmu,i386-softmmu,mipsel-softmmu,mips64-softmmu,ppc-softmmu - MAKE_CHECK_ARGS: check-unit - -check-patch: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/centos8:latest - needs: - job: amd64-centos8-container - script: .gitlab-ci.d/check-patch.py - except: - variables: - - $CI_PROJECT_NAMESPACE == 'qemu-project' && $CI_COMMIT_BRANCH == 'master' - variables: - GIT_DEPTH: 1000 - allow_failure: true - -check-dco: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/centos8:latest - needs: - job: amd64-centos8-container - script: .gitlab-ci.d/check-dco.py - except: - variables: - - $CI_PROJECT_NAMESPACE == 'qemu-project' && $CI_COMMIT_BRANCH == 'master' - variables: - GIT_DEPTH: 1000 - -build-libvhost-user: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/fedora:latest - needs: - job: amd64-fedora-container - before_script: - - dnf install -y meson ninja-build - script: - - mkdir subprojects/libvhost-user/build - - cd subprojects/libvhost-user/build - - meson - - ninja - -# No targets are built here, just tools, docs, and unit tests. This -# also feeds into the eventual documentation deployment steps later -build-tools-and-docs-debian: - extends: .native_build_job_template - needs: - job: amd64-debian-container - variables: - IMAGE: debian-amd64 - MAKE_CHECK_ARGS: check-unit check-softfloat ctags TAGS cscope - CONFIGURE_ARGS: --disable-system --disable-user --enable-docs --enable-tools - artifacts: - expire_in: 2 days - paths: - - build +# Only documentation or comments is accepted. +# +# To use a different set of jobs than the mainstream QEMU project, +# you need to set the location of your custom yml file at "custom CI/CD +# configuration path", on your GitLab CI namespace: +# https://docs.gitlab.com/ee/ci/pipelines/settings.html#custom-cicd-configuration-path +# +# ---------------------------------------------------------------------- +# +# QEMU CI jobs are based on templates. Some templates provide +# user-configurable options, modifiable via configuration variables. +# +# These variables can be set globally in the user's CI namespace +# setting: +# https://docs.gitlab.com/ee/ci/variables/#create-a-custom-variable-in-the-ui +# or set manually each time a branch/tag is pushed, as a git-push +# command line argument: +# https://docs.gitlab.com/ee/user/project/push_options.html#push-options-for-gitlab-cicd +# +# Example setting the QEMU_CI_EXAMPLE_VAR variable: +# +# git push -o ci.variable="QEMU_CI_EXAMPLE_VAR=value" myrepo mybranch +# +# ---------------------------------------------------------------------- +# +# List of environment variables that can be use to modify the set +# of jobs selected: +# +# - QEMU_CI_AVOCADO_TESTING +# If set, tests using the Avocado framework will be run -# Prepare for GitLab pages deployment. Anything copied into the -# "public" directory will be deployed to $USER.gitlab.io/$PROJECT -pages: - image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:latest - stage: test - needs: - - job: build-tools-and-docs-debian - script: - - mkdir -p public - # HTML-ised source tree - - make gtags - - htags -anT --tree-view=filetree -m qemu_init - -t "Welcome to the QEMU sourcecode" - - mv HTML public/src - # Project documentation - - make -C build install DESTDIR=$(pwd)/temp-install - - mv temp-install/usr/local/share/doc/qemu/* public/ - artifacts: - paths: - - public +include: + - local: '/.gitlab-ci.d/qemu-project.yml' diff --git a/.patchew.yml b/.patchew.yml index 988c29261f..2638b7f564 100644 --- a/.patchew.yml +++ b/.patchew.yml @@ -88,7 +88,7 @@ email: more information: {{ logtext }} - {% elif test == "docker-mingw@fedora" or test == "docker-quick@centos7" or test == "asan" %} + {% elif test == "docker-mingw@fedora" or test == "docker-quick@centos8" or test == "asan" %} Hi, This series failed the {{ test }} build test. Please find the testing commands and @@ -124,13 +124,13 @@ testing: script: | #!/bin/bash time make docker-test-debug@fedora TARGET_LIST=x86_64-softmmu J=14 NETWORK=1 - docker-quick@centos7: + docker-quick@centos8: enabled: false requirements: docker,x86_64 timeout: 3600 script: | #!/bin/bash - time make docker-test-quick@centos7 SHOW_ENV=1 J=14 NETWORK=1 + time make docker-test-quick@centos8 SHOW_ENV=1 J=14 NETWORK=1 checkpatch: enabled: true requirements: '' diff --git a/MAINTAINERS b/MAINTAINERS index 99fe76b463..7d9cd29042 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -128,7 +128,6 @@ F: docs/devel/decodetree.rst F: include/exec/cpu*.h F: include/exec/exec-all.h F: include/exec/helper*.h -F: include/exec/tb-hash.h F: include/sysemu/cpus.h F: include/sysemu/tcg.h F: include/hw/core/tcg-cpu-ops.h @@ -437,7 +436,15 @@ M: Roman Bolshakov <r.bolshakov@yadro.com> W: https://wiki.qemu.org/Features/HVF S: Maintained F: target/i386/hvf/ + +HVF +M: Cameron Esfahani <dirty@apple.com> +M: Roman Bolshakov <r.bolshakov@yadro.com> +W: https://wiki.qemu.org/Features/HVF +S: Maintained +F: accel/hvf/ F: include/sysemu/hvf.h +F: include/sysemu/hvf_int.h WHPX CPUs M: Sunil Muthuswamy <sunilmut@microsoft.com> @@ -2693,7 +2700,7 @@ F: scripts/tracetool.py F: scripts/tracetool/ F: scripts/qemu-trace-stap* F: docs/tools/qemu-trace-stap.rst -F: docs/devel/tracing.txt +F: docs/devel/tracing.rst T: git https://github.com/stefanha/qemu.git tracing TPM @@ -3370,7 +3377,7 @@ Documentation Build system architecture M: Daniel P. Berrange <berrange@redhat.com> S: Odd Fixes -F: docs/devel/build-system.txt +F: docs/devel/build-system.rst GIT Data Mining Config M: Alex Bennée <alex.bennee@linaro.org> @@ -48,9 +48,11 @@ Makefile: .git-submodule-status .PHONY: git-submodule-update git-submodule-update: +ifneq ($(GIT_SUBMODULES_ACTION),ignore) $(call quiet-command, \ (GIT="$(GIT)" "$(SRC_PATH)/scripts/git-submodule.sh" $(GIT_SUBMODULES_ACTION) $(GIT_SUBMODULES)), \ "GIT","$(GIT_SUBMODULES)") +endif # 0. ensure the build tree is okay diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c new file mode 100644 index 0000000000..d1691be989 --- /dev/null +++ b/accel/hvf/hvf-accel-ops.c @@ -0,0 +1,471 @@ +/* + * Copyright 2008 IBM Corporation + * 2008 Red Hat, Inc. + * Copyright 2011 Intel Corporation + * Copyright 2016 Veertu, Inc. + * Copyright 2017 The Android Open Source Project + * + * QEMU Hypervisor.framework support + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + * + * This file contain code under public domain from the hvdos project: + * https://github.com/mist64/hvdos + * + * Parts Copyright (c) 2011 NetApp, Inc. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL NETAPP, INC OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "exec/address-spaces.h" +#include "exec/exec-all.h" +#include "sysemu/cpus.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/runstate.h" +#include "qemu/guest-random.h" + +HVFState *hvf_state; + +/* Memory slots */ + +hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) +{ + hvf_slot *slot; + int x; + for (x = 0; x < hvf_state->num_slots; ++x) { + slot = &hvf_state->slots[x]; + if (slot->size && start < (slot->start + slot->size) && + (start + size) > slot->start) { + return slot; + } + } + return NULL; +} + +struct mac_slot { + int present; + uint64_t size; + uint64_t gpa_start; + uint64_t gva; +}; + +struct mac_slot mac_slots[32]; + +static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) +{ + struct mac_slot *macslot; + hv_return_t ret; + + macslot = &mac_slots[slot->slot_id]; + + if (macslot->present) { + if (macslot->size != slot->size) { + macslot->present = 0; + ret = hv_vm_unmap(macslot->gpa_start, macslot->size); + assert_hvf_ok(ret); + } + } + + if (!slot->size) { + return 0; + } + + macslot->present = 1; + macslot->gpa_start = slot->start; + macslot->size = slot->size; + ret = hv_vm_map(slot->mem, slot->start, slot->size, flags); + assert_hvf_ok(ret); + return 0; +} + +static void hvf_set_phys_mem(MemoryRegionSection *section, bool add) +{ + hvf_slot *mem; + MemoryRegion *area = section->mr; + bool writeable = !area->readonly && !area->rom_device; + hv_memory_flags_t flags; + + if (!memory_region_is_ram(area)) { + if (writeable) { + return; + } else if (!memory_region_is_romd(area)) { + /* + * If the memory device is not in romd_mode, then we actually want + * to remove the hvf memory slot so all accesses will trap. + */ + add = false; + } + } + + mem = hvf_find_overlap_slot( + section->offset_within_address_space, + int128_get64(section->size)); + + if (mem && add) { + if (mem->size == int128_get64(section->size) && + mem->start == section->offset_within_address_space && + mem->mem == (memory_region_get_ram_ptr(area) + + section->offset_within_region)) { + return; /* Same region was attempted to register, go away. */ + } + } + + /* Region needs to be reset. set the size to 0 and remap it. */ + if (mem) { + mem->size = 0; + if (do_hvf_set_memory(mem, 0)) { + error_report("Failed to reset overlapping slot"); + abort(); + } + } + + if (!add) { + return; + } + + if (area->readonly || + (!memory_region_is_ram(area) && memory_region_is_romd(area))) { + flags = HV_MEMORY_READ | HV_MEMORY_EXEC; + } else { + flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; + } + + /* Now make a new slot. */ + int x; + + for (x = 0; x < hvf_state->num_slots; ++x) { + mem = &hvf_state->slots[x]; + if (!mem->size) { + break; + } + } + + if (x == hvf_state->num_slots) { + error_report("No free slots"); + abort(); + } + + mem->size = int128_get64(section->size); + mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region; + mem->start = section->offset_within_address_space; + mem->region = area; + + if (do_hvf_set_memory(mem, flags)) { + error_report("Error registering new memory slot"); + abort(); + } +} + +static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) +{ + if (!cpu->vcpu_dirty) { + hvf_get_registers(cpu); + cpu->vcpu_dirty = true; + } +} + +static void hvf_cpu_synchronize_state(CPUState *cpu) +{ + if (!cpu->vcpu_dirty) { + run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); + } +} + +static void do_hvf_cpu_synchronize_set_dirty(CPUState *cpu, + run_on_cpu_data arg) +{ + /* QEMU state is the reference, push it to HVF now and on next entry */ + cpu->vcpu_dirty = true; +} + +static void hvf_cpu_synchronize_post_reset(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL); +} + +static void hvf_cpu_synchronize_post_init(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL); +} + +static void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL); +} + +static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) +{ + hvf_slot *slot; + + slot = hvf_find_overlap_slot( + section->offset_within_address_space, + int128_get64(section->size)); + + /* protect region against writes; begin tracking it */ + if (on) { + slot->flags |= HVF_SLOT_LOG; + hv_vm_protect((uintptr_t)slot->start, (size_t)slot->size, + HV_MEMORY_READ); + /* stop tracking region*/ + } else { + slot->flags &= ~HVF_SLOT_LOG; + hv_vm_protect((uintptr_t)slot->start, (size_t)slot->size, + HV_MEMORY_READ | HV_MEMORY_WRITE); + } +} + +static void hvf_log_start(MemoryListener *listener, + MemoryRegionSection *section, int old, int new) +{ + if (old != 0) { + return; + } + + hvf_set_dirty_tracking(section, 1); +} + +static void hvf_log_stop(MemoryListener *listener, + MemoryRegionSection *section, int old, int new) +{ + if (new != 0) { + return; + } + + hvf_set_dirty_tracking(section, 0); +} + +static void hvf_log_sync(MemoryListener *listener, + MemoryRegionSection *section) +{ + /* + * sync of dirty pages is handled elsewhere; just make sure we keep + * tracking the region. + */ + hvf_set_dirty_tracking(section, 1); +} + +static void hvf_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + hvf_set_phys_mem(section, true); +} + +static void hvf_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + hvf_set_phys_mem(section, false); +} + +static MemoryListener hvf_memory_listener = { + .priority = 10, + .region_add = hvf_region_add, + .region_del = hvf_region_del, + .log_start = hvf_log_start, + .log_stop = hvf_log_stop, + .log_sync = hvf_log_sync, +}; + +static void dummy_signal(int sig) +{ +} + +bool hvf_allowed; + +static int hvf_accel_init(MachineState *ms) +{ + int x; + hv_return_t ret; + HVFState *s; + + ret = hv_vm_create(HV_VM_DEFAULT); + assert_hvf_ok(ret); + + s = g_new0(HVFState, 1); + + s->num_slots = 32; + for (x = 0; x < s->num_slots; ++x) { + s->slots[x].size = 0; + s->slots[x].slot_id = x; + } + + hvf_state = s; + memory_listener_register(&hvf_memory_listener, &address_space_memory); + return 0; +} + +static void hvf_accel_class_init(ObjectClass *oc, void *data) +{ + AccelClass *ac = ACCEL_CLASS(oc); + ac->name = "HVF"; + ac->init_machine = hvf_accel_init; + ac->allowed = &hvf_allowed; +} + +static const TypeInfo hvf_accel_type = { + .name = TYPE_HVF_ACCEL, + .parent = TYPE_ACCEL, + .class_init = hvf_accel_class_init, +}; + +static void hvf_type_init(void) +{ + type_register_static(&hvf_accel_type); +} + +type_init(hvf_type_init); + +static void hvf_vcpu_destroy(CPUState *cpu) +{ + hv_return_t ret = hv_vcpu_destroy(cpu->hvf->fd); + assert_hvf_ok(ret); + + hvf_arch_vcpu_destroy(cpu); + g_free(cpu->hvf); + cpu->hvf = NULL; +} + +static int hvf_init_vcpu(CPUState *cpu) +{ + int r; + + cpu->hvf = g_malloc0(sizeof(*cpu->hvf)); + + /* init cpu signals */ + sigset_t set; + struct sigaction sigact; + + memset(&sigact, 0, sizeof(sigact)); + sigact.sa_handler = dummy_signal; + sigaction(SIG_IPI, &sigact, NULL); + + pthread_sigmask(SIG_BLOCK, NULL, &set); + sigdelset(&set, SIG_IPI); + + r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf->fd, HV_VCPU_DEFAULT); + cpu->vcpu_dirty = 1; + assert_hvf_ok(r); + + return hvf_arch_init_vcpu(cpu); +} + +/* + * The HVF-specific vCPU thread function. This one should only run when the host + * CPU supports the VMX "unrestricted guest" feature. + */ +static void *hvf_cpu_thread_fn(void *arg) +{ + CPUState *cpu = arg; + + int r; + + assert(hvf_enabled()); + + rcu_register_thread(); + + qemu_mutex_lock_iothread(); + qemu_thread_get_self(cpu->thread); + + cpu->thread_id = qemu_get_thread_id(); + cpu->can_do_io = 1; + current_cpu = cpu; + + hvf_init_vcpu(cpu); + + /* signal CPU creation */ + cpu_thread_signal_created(cpu); + qemu_guest_random_seed_thread_part2(cpu->random_seed); + + do { + if (cpu_can_run(cpu)) { + r = hvf_vcpu_exec(cpu); + if (r == EXCP_DEBUG) { + cpu_handle_guest_debug(cpu); + } + } + qemu_wait_io_event(cpu); + } while (!cpu->unplug || cpu_can_run(cpu)); + + hvf_vcpu_destroy(cpu); + cpu_thread_signal_destroyed(cpu); + qemu_mutex_unlock_iothread(); + rcu_unregister_thread(); + return NULL; +} + +static void hvf_start_vcpu_thread(CPUState *cpu) +{ + char thread_name[VCPU_THREAD_NAME_SIZE]; + + /* + * HVF currently does not support TCG, and only runs in + * unrestricted-guest mode. + */ + assert(hvf_enabled()); + + cpu->thread = g_malloc0(sizeof(QemuThread)); + cpu->halt_cond = g_malloc0(sizeof(QemuCond)); + qemu_cond_init(cpu->halt_cond); + + snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HVF", + cpu->cpu_index); + qemu_thread_create(cpu->thread, thread_name, hvf_cpu_thread_fn, + cpu, QEMU_THREAD_JOINABLE); +} + +static void hvf_accel_ops_class_init(ObjectClass *oc, void *data) +{ + AccelOpsClass *ops = ACCEL_OPS_CLASS(oc); + + ops->create_vcpu_thread = hvf_start_vcpu_thread; + + ops->synchronize_post_reset = hvf_cpu_synchronize_post_reset; + ops->synchronize_post_init = hvf_cpu_synchronize_post_init; + ops->synchronize_state = hvf_cpu_synchronize_state; + ops->synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm; +}; +static const TypeInfo hvf_accel_ops_type = { + .name = ACCEL_OPS_NAME("hvf"), + + .parent = TYPE_ACCEL_OPS, + .class_init = hvf_accel_ops_class_init, + .abstract = true, +}; +static void hvf_accel_ops_register_types(void) +{ + type_register_static(&hvf_accel_ops_type); +} +type_init(hvf_accel_ops_register_types); diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c new file mode 100644 index 0000000000..f185b0830a --- /dev/null +++ b/accel/hvf/hvf-all.c @@ -0,0 +1,47 @@ +/* + * QEMU Hypervisor.framework support + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" + +void assert_hvf_ok(hv_return_t ret) +{ + if (ret == HV_SUCCESS) { + return; + } + + switch (ret) { + case HV_ERROR: + error_report("Error: HV_ERROR"); + break; + case HV_BUSY: + error_report("Error: HV_BUSY"); + break; + case HV_BAD_ARGUMENT: + error_report("Error: HV_BAD_ARGUMENT"); + break; + case HV_NO_RESOURCES: + error_report("Error: HV_NO_RESOURCES"); + break; + case HV_NO_DEVICE: + error_report("Error: HV_NO_DEVICE"); + break; + case HV_UNSUPPORTED: + error_report("Error: HV_UNSUPPORTED"); + break; + default: + error_report("Unknown Error"); + } + + abort(); +} diff --git a/accel/hvf/meson.build b/accel/hvf/meson.build new file mode 100644 index 0000000000..fc52cb7843 --- /dev/null +++ b/accel/hvf/meson.build @@ -0,0 +1,7 @@ +hvf_ss = ss.source_set() +hvf_ss.add(files( + 'hvf-all.c', + 'hvf-accel-ops.c', +)) + +specific_ss.add_all(when: 'CONFIG_HVF', if_true: hvf_ss) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 4e0168e88b..c7ec538850 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -15,6 +15,7 @@ #include "qemu/osdep.h" #include <sys/ioctl.h> +#include <poll.h> #include <linux/kvm.h> @@ -78,6 +79,25 @@ struct KVMParkedVcpu { QLIST_ENTRY(KVMParkedVcpu) node; }; +enum KVMDirtyRingReaperState { + KVM_DIRTY_RING_REAPER_NONE = 0, + /* The reaper is sleeping */ + KVM_DIRTY_RING_REAPER_WAIT, + /* The reaper is reaping for dirty pages */ + KVM_DIRTY_RING_REAPER_REAPING, +}; + +/* + * KVM reaper instance, responsible for collecting the KVM dirty bits + * via the dirty ring. + */ +struct KVMDirtyRingReaper { + /* The reaper thread */ + QemuThread reaper_thr; + volatile uint64_t reaper_iteration; /* iteration number of reaper thr */ + volatile enum KVMDirtyRingReaperState reaper_state; /* reap thr state */ +}; + struct KVMState { AccelState parent_obj; @@ -126,6 +146,9 @@ struct KVMState KVMMemoryListener *ml; AddressSpace *as; } *as; + uint64_t kvm_dirty_ring_bytes; /* Size of the per-vcpu dirty ring */ + uint32_t kvm_dirty_ring_size; /* Number of dirty GFNs per ring */ + struct KVMDirtyRingReaper reaper; }; KVMState *kvm_state; @@ -172,8 +195,12 @@ typedef struct KVMResampleFd KVMResampleFd; static QLIST_HEAD(, KVMResampleFd) kvm_resample_fd_list = QLIST_HEAD_INITIALIZER(kvm_resample_fd_list); -#define kvm_slots_lock(kml) qemu_mutex_lock(&(kml)->slots_lock) -#define kvm_slots_unlock(kml) qemu_mutex_unlock(&(kml)->slots_lock) +static QemuMutex kml_slots_lock; + +#define kvm_slots_lock() qemu_mutex_lock(&kml_slots_lock) +#define kvm_slots_unlock() qemu_mutex_unlock(&kml_slots_lock) + +static void kvm_slot_init_dirty_bitmap(KVMSlot *mem); static inline void kvm_resample_fd_remove(int gsi) { @@ -239,9 +266,9 @@ bool kvm_has_free_slot(MachineState *ms) bool result; KVMMemoryListener *kml = &s->memory_listener; - kvm_slots_lock(kml); + kvm_slots_lock(); result = !!kvm_get_free_slot(kml); - kvm_slots_unlock(kml); + kvm_slots_unlock(); return result; } @@ -307,7 +334,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, KVMMemoryListener *kml = &s->memory_listener; int i, ret = 0; - kvm_slots_lock(kml); + kvm_slots_lock(); for (i = 0; i < s->nr_slots; i++) { KVMSlot *mem = &kml->slots[i]; @@ -317,7 +344,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, break; } } - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -383,6 +410,13 @@ static int do_kvm_destroy_vcpu(CPUState *cpu) goto err; } + if (cpu->kvm_dirty_gfns) { + ret = munmap(cpu->kvm_dirty_gfns, s->kvm_dirty_ring_size); + if (ret < 0) { + goto err; + } + } + vcpu = g_malloc0(sizeof(*vcpu)); vcpu->vcpu_id = kvm_arch_vcpu_id(cpu); vcpu->kvm_fd = cpu->kvm_fd; @@ -459,6 +493,19 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp) (void *)cpu->kvm_run + s->coalesced_mmio * PAGE_SIZE; } + if (s->kvm_dirty_ring_size) { + /* Use MAP_SHARED to share pages with the kernel */ + cpu->kvm_dirty_gfns = mmap(NULL, s->kvm_dirty_ring_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu->kvm_fd, + PAGE_SIZE * KVM_DIRTY_LOG_PAGE_OFFSET); + if (cpu->kvm_dirty_gfns == MAP_FAILED) { + ret = -errno; + DPRINTF("mmap'ing vcpu dirty gfns failed: %d\n", ret); + goto err; + } + } + ret = kvm_arch_init_vcpu(cpu); if (ret < 0) { error_setg_errno(errp, -ret, @@ -498,6 +545,7 @@ static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem, return 0; } + kvm_slot_init_dirty_bitmap(mem); return kvm_set_user_memory_region(kml, mem, false); } @@ -513,7 +561,7 @@ static int kvm_section_update_flags(KVMMemoryListener *kml, return 0; } - kvm_slots_lock(kml); + kvm_slots_lock(); while (size && !ret) { slot_size = MIN(kvm_max_slot_size, size); @@ -529,7 +577,7 @@ static int kvm_section_update_flags(KVMMemoryListener *kml, } out: - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -568,22 +616,28 @@ static void kvm_log_stop(MemoryListener *listener, } /* get kvm's dirty pages bitmap and update qemu's */ -static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section, - unsigned long *bitmap) +static void kvm_slot_sync_dirty_pages(KVMSlot *slot) { - ram_addr_t start = section->offset_within_region + - memory_region_get_ram_addr(section->mr); - ram_addr_t pages = int128_get64(section->size) / qemu_real_host_page_size; + ram_addr_t start = slot->ram_start_offset; + ram_addr_t pages = slot->memory_size / qemu_real_host_page_size; - cpu_physical_memory_set_dirty_lebitmap(bitmap, start, pages); - return 0; + cpu_physical_memory_set_dirty_lebitmap(slot->dirty_bmap, start, pages); +} + +static void kvm_slot_reset_dirty_pages(KVMSlot *slot) +{ + memset(slot->dirty_bmap, 0, slot->dirty_bmap_size); } #define ALIGN(x, y) (((x)+(y)-1) & ~((y)-1)) /* Allocate the dirty bitmap for a slot */ -static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) +static void kvm_slot_init_dirty_bitmap(KVMSlot *mem) { + if (!(mem->flags & KVM_MEM_LOG_DIRTY_PAGES) || mem->dirty_bmap) { + return; + } + /* * XXX bad kernel interface alert * For dirty bitmap, kernel allocates array of size aligned to @@ -604,6 +658,196 @@ static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) hwaddr bitmap_size = ALIGN(mem->memory_size / qemu_real_host_page_size, /*HOST_LONG_BITS*/ 64) / 8; mem->dirty_bmap = g_malloc0(bitmap_size); + mem->dirty_bmap_size = bitmap_size; +} + +/* + * Sync dirty bitmap from kernel to KVMSlot.dirty_bmap, return true if + * succeeded, false otherwise + */ +static bool kvm_slot_get_dirty_log(KVMState *s, KVMSlot *slot) +{ + struct kvm_dirty_log d = {}; + int ret; + + d.dirty_bitmap = slot->dirty_bmap; + d.slot = slot->slot | (slot->as_id << 16); + ret = kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d); + + if (ret == -ENOENT) { + /* kernel does not have dirty bitmap in this slot */ + ret = 0; + } + if (ret) { + error_report_once("%s: KVM_GET_DIRTY_LOG failed with %d", + __func__, ret); + } + return ret == 0; +} + +/* Should be with all slots_lock held for the address spaces. */ +static void kvm_dirty_ring_mark_page(KVMState *s, uint32_t as_id, + uint32_t slot_id, uint64_t offset) +{ + KVMMemoryListener *kml; + KVMSlot *mem; + + if (as_id >= s->nr_as) { + return; + } + + kml = s->as[as_id].ml; + mem = &kml->slots[slot_id]; + + if (!mem->memory_size || offset >= + (mem->memory_size / qemu_real_host_page_size)) { + return; + } + + set_bit(offset, mem->dirty_bmap); +} + +static bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags == KVM_DIRTY_GFN_F_DIRTY; +} + +static void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_RESET; +} + +/* + * Should be with all slots_lock held for the address spaces. It returns the + * dirty page we've collected on this dirty ring. + */ +static uint32_t kvm_dirty_ring_reap_one(KVMState *s, CPUState *cpu) +{ + struct kvm_dirty_gfn *dirty_gfns = cpu->kvm_dirty_gfns, *cur; + uint32_t ring_size = s->kvm_dirty_ring_size; + uint32_t count = 0, fetch = cpu->kvm_fetch_index; + + assert(dirty_gfns && ring_size); + trace_kvm_dirty_ring_reap_vcpu(cpu->cpu_index); + + while (true) { + cur = &dirty_gfns[fetch % ring_size]; + if (!dirty_gfn_is_dirtied(cur)) { + break; + } + kvm_dirty_ring_mark_page(s, cur->slot >> 16, cur->slot & 0xffff, + cur->offset); + dirty_gfn_set_collected(cur); + trace_kvm_dirty_ring_page(cpu->cpu_index, fetch, cur->offset); + fetch++; + count++; + } + cpu->kvm_fetch_index = fetch; + + return count; +} + +/* Must be with slots_lock held */ +static uint64_t kvm_dirty_ring_reap_locked(KVMState *s) +{ + int ret; + CPUState *cpu; + uint64_t total = 0; + int64_t stamp; + + stamp = get_clock(); + + CPU_FOREACH(cpu) { + total += kvm_dirty_ring_reap_one(s, cpu); + } + + if (total) { + ret = kvm_vm_ioctl(s, KVM_RESET_DIRTY_RINGS); + assert(ret == total); + } + + stamp = get_clock() - stamp; + + if (total) { + trace_kvm_dirty_ring_reap(total, stamp / 1000); + } + + return total; +} + +/* + * Currently for simplicity, we must hold BQL before calling this. We can + * consider to drop the BQL if we're clear with all the race conditions. + */ +static uint64_t kvm_dirty_ring_reap(KVMState *s) +{ + uint64_t total; + + /* + * We need to lock all kvm slots for all address spaces here, + * because: + * + * (1) We need to mark dirty for dirty bitmaps in multiple slots + * and for tons of pages, so it's better to take the lock here + * once rather than once per page. And more importantly, + * + * (2) We must _NOT_ publish dirty bits to the other threads + * (e.g., the migration thread) via the kvm memory slot dirty + * bitmaps before correctly re-protect those dirtied pages. + * Otherwise we can have potential risk of data corruption if + * the page data is read in the other thread before we do + * reset below. + */ + kvm_slots_lock(); + total = kvm_dirty_ring_reap_locked(s); + kvm_slots_unlock(); + + return total; +} + +static void do_kvm_cpu_synchronize_kick(CPUState *cpu, run_on_cpu_data arg) +{ + /* No need to do anything */ +} + +/* + * Kick all vcpus out in a synchronized way. When returned, we + * guarantee that every vcpu has been kicked and at least returned to + * userspace once. + */ +static void kvm_cpu_synchronize_kick_all(void) +{ + CPUState *cpu; + + CPU_FOREACH(cpu) { + run_on_cpu(cpu, do_kvm_cpu_synchronize_kick, RUN_ON_CPU_NULL); + } +} + +/* + * Flush all the existing dirty pages to the KVM slot buffers. When + * this call returns, we guarantee that all the touched dirty pages + * before calling this function have been put into the per-kvmslot + * dirty bitmap. + * + * This function must be called with BQL held. + */ +static void kvm_dirty_ring_flush(void) +{ + trace_kvm_dirty_ring_flush(0); + /* + * The function needs to be serialized. Since this function + * should always be with BQL held, serialization is guaranteed. + * However, let's be sure of it. + */ + assert(qemu_mutex_iothread_locked()); + /* + * First make sure to flush the hardware buffers by kicking all + * vcpus out in a synchronous way. + */ + kvm_cpu_synchronize_kick_all(); + kvm_dirty_ring_reap(kvm_state); + trace_kvm_dirty_ring_flush(1); } /** @@ -617,53 +861,28 @@ static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) * @kml: the KVM memory listener object * @section: the memory section to sync the dirty bitmap with */ -static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml, - MemoryRegionSection *section) +static void kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml, + MemoryRegionSection *section) { KVMState *s = kvm_state; - struct kvm_dirty_log d = {}; KVMSlot *mem; hwaddr start_addr, size; - hwaddr slot_size, slot_offset = 0; - int ret = 0; + hwaddr slot_size; size = kvm_align_section(section, &start_addr); while (size) { - MemoryRegionSection subsection = *section; - slot_size = MIN(kvm_max_slot_size, size); mem = kvm_lookup_matching_slot(kml, start_addr, slot_size); if (!mem) { /* We don't have a slot if we want to trap every access. */ - goto out; - } - - if (!mem->dirty_bmap) { - /* Allocate on the first log_sync, once and for all */ - kvm_memslot_init_dirty_bitmap(mem); + return; } - - d.dirty_bitmap = mem->dirty_bmap; - d.slot = mem->slot | (kml->as_id << 16); - ret = kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d); - if (ret == -ENOENT) { - /* kernel does not have dirty bitmap in this slot */ - ret = 0; - } else if (ret < 0) { - error_report("ioctl KVM_GET_DIRTY_LOG failed: %d", errno); - goto out; - } else { - subsection.offset_within_region += slot_offset; - subsection.size = int128_make64(slot_size); - kvm_get_dirty_pages_log_range(&subsection, d.dirty_bitmap); + if (kvm_slot_get_dirty_log(s, mem)) { + kvm_slot_sync_dirty_pages(mem); } - - slot_offset += slot_size; start_addr += slot_size; size -= slot_size; } -out: - return ret; } /* Alignment requirement for KVM_CLEAR_DIRTY_LOG - 64 pages */ @@ -810,7 +1029,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml, return ret; } - kvm_slots_lock(kml); + kvm_slots_lock(); for (i = 0; i < s->nr_slots; i++) { mem = &kml->slots[i]; @@ -836,7 +1055,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml, } } - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -1119,7 +1338,8 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, int err; MemoryRegion *mr = section->mr; bool writeable = !mr->readonly && !mr->rom_device; - hwaddr start_addr, size, slot_size; + hwaddr start_addr, size, slot_size, mr_offset; + ram_addr_t ram_start_offset; void *ram; if (!memory_region_is_ram(mr)) { @@ -1137,11 +1357,15 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, return; } - /* use aligned delta to align the ram address */ - ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + - (start_addr - section->offset_within_address_space); + /* The offset of the kvmslot within the memory region */ + mr_offset = section->offset_within_region + start_addr - + section->offset_within_address_space; - kvm_slots_lock(kml); + /* use aligned delta to align the ram address and offset */ + ram = memory_region_get_ram_ptr(mr) + mr_offset; + ram_start_offset = memory_region_get_ram_addr(mr) + mr_offset; + + kvm_slots_lock(); if (!add) { do { @@ -1151,7 +1375,25 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, goto out; } if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { - kvm_physical_sync_dirty_bitmap(kml, section); + /* + * NOTE: We should be aware of the fact that here we're only + * doing a best effort to sync dirty bits. No matter whether + * we're using dirty log or dirty ring, we ignored two facts: + * + * (1) dirty bits can reside in hardware buffers (PML) + * + * (2) after we collected dirty bits here, pages can be dirtied + * again before we do the final KVM_SET_USER_MEMORY_REGION to + * remove the slot. + * + * Not easy. Let's cross the fingers until it's fixed. + */ + if (kvm_state->kvm_dirty_ring_size) { + kvm_dirty_ring_reap_locked(kvm_state); + } else { + kvm_slot_get_dirty_log(kvm_state, mem); + } + kvm_slot_sync_dirty_pages(mem); } /* unregister the slot */ @@ -1175,18 +1417,13 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, do { slot_size = MIN(kvm_max_slot_size, size); mem = kvm_alloc_slot(kml); + mem->as_id = kml->as_id; mem->memory_size = slot_size; mem->start_addr = start_addr; + mem->ram_start_offset = ram_start_offset; mem->ram = ram; mem->flags = kvm_mem_flags(mr); - - if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { - /* - * Reallocate the bmap; it means it doesn't disappear in - * middle of a migrate. - */ - kvm_memslot_init_dirty_bitmap(mem); - } + kvm_slot_init_dirty_bitmap(mem); err = kvm_set_user_memory_region(kml, mem, true); if (err) { fprintf(stderr, "%s: error registering slot: %s\n", __func__, @@ -1194,12 +1431,58 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, abort(); } start_addr += slot_size; + ram_start_offset += slot_size; ram += slot_size; size -= slot_size; } while (size); out: - kvm_slots_unlock(kml); + kvm_slots_unlock(); +} + +static void *kvm_dirty_ring_reaper_thread(void *data) +{ + KVMState *s = data; + struct KVMDirtyRingReaper *r = &s->reaper; + + rcu_register_thread(); + + trace_kvm_dirty_ring_reaper("init"); + + while (true) { + r->reaper_state = KVM_DIRTY_RING_REAPER_WAIT; + trace_kvm_dirty_ring_reaper("wait"); + /* + * TODO: provide a smarter timeout rather than a constant? + */ + sleep(1); + + trace_kvm_dirty_ring_reaper("wakeup"); + r->reaper_state = KVM_DIRTY_RING_REAPER_REAPING; + + qemu_mutex_lock_iothread(); + kvm_dirty_ring_reap(s); + qemu_mutex_unlock_iothread(); + + r->reaper_iteration++; + } + + trace_kvm_dirty_ring_reaper("exit"); + + rcu_unregister_thread(); + + return NULL; +} + +static int kvm_dirty_ring_reaper_init(KVMState *s) +{ + struct KVMDirtyRingReaper *r = &s->reaper; + + qemu_thread_create(&r->reaper_thr, "kvm-reaper", + kvm_dirty_ring_reaper_thread, + s, QEMU_THREAD_JOINABLE); + + return 0; } static void kvm_region_add(MemoryListener *listener, @@ -1224,14 +1507,40 @@ static void kvm_log_sync(MemoryListener *listener, MemoryRegionSection *section) { KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener); - int r; - kvm_slots_lock(kml); - r = kvm_physical_sync_dirty_bitmap(kml, section); - kvm_slots_unlock(kml); - if (r < 0) { - abort(); + kvm_slots_lock(); + kvm_physical_sync_dirty_bitmap(kml, section); + kvm_slots_unlock(); +} + +static void kvm_log_sync_global(MemoryListener *l) +{ + KVMMemoryListener *kml = container_of(l, KVMMemoryListener, listener); + KVMState *s = kvm_state; + KVMSlot *mem; + int i; + + /* Flush all kernel dirty addresses into KVMSlot dirty bitmap */ + kvm_dirty_ring_flush(); + + /* + * TODO: make this faster when nr_slots is big while there are + * only a few used slots (small VMs). + */ + kvm_slots_lock(); + for (i = 0; i < s->nr_slots; i++) { + mem = &kml->slots[i]; + if (mem->memory_size && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + kvm_slot_sync_dirty_pages(mem); + /* + * This is not needed by KVM_GET_DIRTY_LOG because the + * ioctl will unconditionally overwrite the whole region. + * However kvm dirty ring has no such side effect. + */ + kvm_slot_reset_dirty_pages(mem); + } } + kvm_slots_unlock(); } static void kvm_log_clear(MemoryListener *listener, @@ -1328,7 +1637,6 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, { int i; - qemu_mutex_init(&kml->slots_lock); kml->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot)); kml->as_id = as_id; @@ -1340,10 +1648,15 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, kml->listener.region_del = kvm_region_del; kml->listener.log_start = kvm_log_start; kml->listener.log_stop = kvm_log_stop; - kml->listener.log_sync = kvm_log_sync; - kml->listener.log_clear = kvm_log_clear; kml->listener.priority = 10; + if (s->kvm_dirty_ring_size) { + kml->listener.log_sync_global = kvm_log_sync_global; + } else { + kml->listener.log_sync = kvm_log_sync; + kml->listener.log_clear = kvm_log_clear; + } + memory_listener_register(&kml->listener, as); for (i = 0; i < s->nr_as; ++i) { @@ -2001,6 +2314,8 @@ static int kvm_init(MachineState *ms) int type = 0; uint64_t dirty_log_manual_caps; + qemu_mutex_init(&kml_slots_lock); + s = KVM_STATE(ms->accelerator); /* @@ -2017,7 +2332,6 @@ static int kvm_init(MachineState *ms) QTAILQ_INIT(&s->kvm_sw_breakpoints); #endif QLIST_INIT(&s->kvm_parked_vcpus); - s->vmfd = -1; s->fd = qemu_open_old("/dev/kvm", O_RDWR); if (s->fd == -1) { fprintf(stderr, "Could not access KVM kernel module: %m\n"); @@ -2125,20 +2439,70 @@ static int kvm_init(MachineState *ms) s->coalesced_pio = s->coalesced_mmio && kvm_check_extension(s, KVM_CAP_COALESCED_PIO); - dirty_log_manual_caps = - kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); - s->manual_dirty_log_protect = dirty_log_manual_caps; - if (dirty_log_manual_caps) { - ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, - dirty_log_manual_caps); - if (ret) { - warn_report("Trying to enable capability %"PRIu64" of " - "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " - "Falling back to the legacy mode. ", - dirty_log_manual_caps); - s->manual_dirty_log_protect = 0; + /* + * Enable KVM dirty ring if supported, otherwise fall back to + * dirty logging mode + */ + if (s->kvm_dirty_ring_size > 0) { + uint64_t ring_bytes; + + ring_bytes = s->kvm_dirty_ring_size * sizeof(struct kvm_dirty_gfn); + + /* Read the max supported pages */ + ret = kvm_vm_check_extension(s, KVM_CAP_DIRTY_LOG_RING); + if (ret > 0) { + if (ring_bytes > ret) { + error_report("KVM dirty ring size %" PRIu32 " too big " + "(maximum is %ld). Please use a smaller value.", + s->kvm_dirty_ring_size, + (long)ret / sizeof(struct kvm_dirty_gfn)); + ret = -EINVAL; + goto err; + } + + ret = kvm_vm_enable_cap(s, KVM_CAP_DIRTY_LOG_RING, 0, ring_bytes); + if (ret) { + error_report("Enabling of KVM dirty ring failed: %s. " + "Suggested mininum value is 1024.", strerror(-ret)); + goto err; + } + + s->kvm_dirty_ring_bytes = ring_bytes; + } else { + warn_report("KVM dirty ring not available, using bitmap method"); + s->kvm_dirty_ring_size = 0; + } + } + + /* + * KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is not needed when dirty ring is + * enabled. More importantly, KVM_DIRTY_LOG_INITIALLY_SET will assume no + * page is wr-protected initially, which is against how kvm dirty ring is + * usage - kvm dirty ring requires all pages are wr-protected at the very + * beginning. Enabling this feature for dirty ring causes data corruption. + * + * TODO: Without KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 and kvm clear dirty log, + * we may expect a higher stall time when starting the migration. In the + * future we can enable KVM_CLEAR_DIRTY_LOG to work with dirty ring too: + * instead of clearing dirty bit, it can be a way to explicitly wr-protect + * guest pages. + */ + if (!s->kvm_dirty_ring_size) { + dirty_log_manual_caps = + kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + s->manual_dirty_log_protect = dirty_log_manual_caps; + if (dirty_log_manual_caps) { + ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, + dirty_log_manual_caps); + if (ret) { + warn_report("Trying to enable capability %"PRIu64" of " + "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " + "Falling back to the legacy mode. ", + dirty_log_manual_caps); + s->manual_dirty_log_protect = 0; + } } } @@ -2224,6 +2588,14 @@ static int kvm_init(MachineState *ms) ret = ram_block_discard_disable(true); assert(!ret); } + + if (s->kvm_dirty_ring_size) { + ret = kvm_dirty_ring_reaper_init(s); + if (ret) { + goto err; + } + } + return 0; err: @@ -2536,6 +2908,17 @@ int kvm_cpu_exec(CPUState *cpu) case KVM_EXIT_INTERNAL_ERROR: ret = kvm_handle_internal_error(cpu, run); break; + case KVM_EXIT_DIRTY_RING_FULL: + /* + * We shouldn't continue if the dirty ring of this vcpu is + * still full. Got kicked by KVM_RESET_DIRTY_RINGS. + */ + trace_kvm_dirty_ring_full(cpu->cpu_index); + qemu_mutex_lock_iothread(); + kvm_dirty_ring_reap(kvm_state); + qemu_mutex_unlock_iothread(); + ret = 0; + break; case KVM_EXIT_SYSTEM_EVENT: switch (run->system_event.type) { case KVM_SYSTEM_EVENT_SHUTDOWN: @@ -3112,6 +3495,11 @@ static void kvm_set_kvm_shadow_mem(Object *obj, Visitor *v, KVMState *s = KVM_STATE(obj); int64_t value; + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + if (!visit_type_int(v, name, &value, errp)) { return; } @@ -3126,6 +3514,11 @@ static void kvm_set_kernel_irqchip(Object *obj, Visitor *v, KVMState *s = KVM_STATE(obj); OnOffSplit mode; + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + if (!visit_type_OnOffSplit(v, name, &mode, errp)) { return; } @@ -3168,13 +3561,53 @@ bool kvm_kernel_irqchip_split(void) return kvm_state->kernel_irqchip_split == ON_OFF_AUTO_ON; } +static void kvm_get_dirty_ring_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + uint32_t value = s->kvm_dirty_ring_size; + + visit_type_uint32(v, name, &value, errp); +} + +static void kvm_set_dirty_ring_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + Error *error = NULL; + uint32_t value; + + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + + visit_type_uint32(v, name, &value, &error); + if (error) { + error_propagate(errp, error); + return; + } + if (value & (value - 1)) { + error_setg(errp, "dirty-ring-size must be a power of two."); + return; + } + + s->kvm_dirty_ring_size = value; +} + static void kvm_accel_instance_init(Object *obj) { KVMState *s = KVM_STATE(obj); + s->fd = -1; + s->vmfd = -1; s->kvm_shadow_mem = -1; s->kernel_irqchip_allowed = true; s->kernel_irqchip_split = ON_OFF_AUTO_AUTO; + /* KVM dirty ring is by default off */ + s->kvm_dirty_ring_size = 0; } static void kvm_accel_class_init(ObjectClass *oc, void *data) @@ -3196,6 +3629,12 @@ static void kvm_accel_class_init(ObjectClass *oc, void *data) NULL, NULL); object_class_property_set_description(oc, "kvm-shadow-mem", "KVM shadow MMU size"); + + object_class_property_add(oc, "dirty-ring-size", "uint32", + kvm_get_dirty_ring_size, kvm_set_dirty_ring_size, + NULL, NULL); + object_class_property_set_description(oc, "dirty-ring-size", + "Size of KVM dirty page ring buffer (default: 0, i.e. use bitmap)"); } static const TypeInfo kvm_accel_type = { diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events index e15ae8980d..399aaeb0ec 100644 --- a/accel/kvm/trace-events +++ b/accel/kvm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # kvm-all.c kvm_ioctl(int type, void *arg) "type 0x%x, arg %p" @@ -18,4 +18,11 @@ kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t kvm_set_user_memory(uint32_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, int ret) "Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " ret=%d" kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32 kvm_resample_fd_notify(int gsi) "gsi %d" +kvm_dirty_ring_full(int id) "vcpu %d" +kvm_dirty_ring_reap_vcpu(int id) "vcpu %d" +kvm_dirty_ring_page(int vcpu, uint32_t slot, uint64_t offset) "vcpu %d fetch %"PRIu32" offset 0x%"PRIx64 +kvm_dirty_ring_reaper(const char *s) "%s" +kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)" +kvm_dirty_ring_reaper_kick(const char *reason) "%s" +kvm_dirty_ring_flush(int finished) "%d" diff --git a/accel/meson.build b/accel/meson.build index b44ba30c86..dfd808d2c8 100644 --- a/accel/meson.build +++ b/accel/meson.build @@ -2,6 +2,7 @@ specific_ss.add(files('accel-common.c')) softmmu_ss.add(files('accel-softmmu.c')) user_ss.add(files('accel-user.c')) +subdir('hvf') subdir('qtest') subdir('kvm') subdir('tcg') diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index 0dc5271715..ad1279d2ed 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -29,8 +29,6 @@ #include "qemu/compiler.h" #include "qemu/timer.h" #include "qemu/rcu.h" -#include "exec/tb-hash.h" -#include "exec/tb-lookup.h" #include "exec/log.h" #include "qemu/main-loop.h" #if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY) @@ -40,6 +38,9 @@ #include "exec/cpu-all.h" #include "sysemu/cpu-timers.h" #include "sysemu/replay.h" +#include "tb-hash.h" +#include "tb-lookup.h" +#include "tb-context.h" #include "internal.h" /* -icount align implementation. */ diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 2f7088614a..f24348e979 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -24,7 +24,6 @@ #include "exec/memory.h" #include "exec/cpu_ldst.h" #include "exec/cputlb.h" -#include "exec/tb-hash.h" #include "exec/memory-internal.h" #include "exec/ram_addr.h" #include "tcg/tcg.h" @@ -36,6 +35,7 @@ #include "exec/translate-all.h" #include "trace/trace-root.h" #include "trace/mem.h" +#include "tb-hash.h" #include "internal.h" #ifdef CONFIG_PLUGIN #include "qemu/plugin-memory.h" diff --git a/include/exec/tb-context.h b/accel/tcg/tb-context.h index cc33979113..cc33979113 100644 --- a/include/exec/tb-context.h +++ b/accel/tcg/tb-context.h diff --git a/include/exec/tb-hash.h b/accel/tcg/tb-hash.h index 0a273d9605..0a273d9605 100644 --- a/include/exec/tb-hash.h +++ b/accel/tcg/tb-hash.h diff --git a/include/exec/tb-lookup.h b/accel/tcg/tb-lookup.h index 29d61ceb34..9c9e0079da 100644 --- a/include/exec/tb-lookup.h +++ b/accel/tcg/tb-lookup.h @@ -14,7 +14,7 @@ #endif #include "exec/exec-all.h" -#include "exec/tb-hash.h" +#include "tb-hash.h" /* Might cause an exception, so have a longjmp destination ready */ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, diff --git a/accel/tcg/tcg-runtime.c b/accel/tcg/tcg-runtime.c index 49f5de37e8..66ac830e2f 100644 --- a/accel/tcg/tcg-runtime.c +++ b/accel/tcg/tcg-runtime.c @@ -30,7 +30,7 @@ #include "disas/disas.h" #include "exec/log.h" #include "tcg/tcg.h" -#include "exec/tb-lookup.h" +#include "tb-lookup.h" /* 32-bit helpers */ diff --git a/accel/tcg/trace-events b/accel/tcg/trace-events index 6eefb37f5d..59eab96f26 100644 --- a/accel/tcg/trace-events +++ b/accel/tcg/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # TCG related tracing # cpu-exec.c diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 640ff6e3e7..1eefe6ea8d 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -47,7 +47,6 @@ #endif #include "exec/cputlb.h" -#include "exec/tb-hash.h" #include "exec/translate-all.h" #include "qemu/bitmap.h" #include "qemu/error-report.h" @@ -60,6 +59,8 @@ #include "sysemu/tcg.h" #include "qapi/error.h" #include "hw/core/tcg-cpu-ops.h" +#include "tb-hash.h" +#include "tb-context.h" #include "internal.h" /* #define DEBUG_TB_INVALIDATE */ diff --git a/audio/trace-events b/audio/trace-events index 6aec535763..957c92337b 100644 --- a/audio/trace-events +++ b/audio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # alsaaudio.c alsa_revents(int revents) "revents = %d" diff --git a/authz/trace-events b/authz/trace-events index e62ebb36b7..9c255dafb6 100644 --- a/authz/trace-events +++ b/authz/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # base.c qauthz_is_allowed(void *authz, const char *identity, bool allowed) "AuthZ %p check identity=%s allowed=%d" diff --git a/backends/tpm/trace-events b/backends/tpm/trace-events index 0a2591fb2d..3298766dd7 100644 --- a/backends/tpm/trace-events +++ b/backends/tpm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # tpm_passthrough.c tpm_passthrough_handle_request(void *cmd) "processing command %p" diff --git a/backends/trace-events b/backends/trace-events index 59058f7630..652eb76a57 100644 --- a/backends/trace-events +++ b/backends/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # dbus-vmstate.c dbus_vmstate_pre_save(void) @@ -84,14 +84,6 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs); -static int bdrv_attach_child_noperm(BlockDriverState *parent_bs, - BlockDriverState *child_bs, - const char *child_name, - const BdrvChildClass *child_class, - BdrvChildRole child_role, - BdrvChild **child, - Transaction *tran, - Error **errp); static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs, Transaction *tran); @@ -265,7 +257,7 @@ void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix, * image is inactivated. */ bool bdrv_is_read_only(BlockDriverState *bs) { - return bs->read_only; + return !(bs->open_flags & BDRV_O_RDWR); } int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, @@ -317,7 +309,6 @@ int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, goto fail; } - bs->read_only = true; bs->open_flags &= ~BDRV_O_RDWR; return 0; @@ -1158,7 +1149,7 @@ int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough) static char *bdrv_child_get_parent_desc(BdrvChild *c) { BlockDriverState *parent = c->opaque; - return g_strdup(bdrv_get_device_or_node_name(parent)); + return g_strdup_printf("node '%s'", bdrv_get_node_name(parent)); } static void bdrv_child_cb_drained_begin(BdrvChild *child) @@ -1412,7 +1403,7 @@ static int bdrv_child_cb_update_filename(BdrvChild *c, BlockDriverState *base, return 0; } -static AioContext *bdrv_child_cb_get_parent_aio_context(BdrvChild *c) +AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c) { BlockDriverState *bs = c->opaque; @@ -1432,7 +1423,7 @@ const BdrvChildClass child_of_bds = { .can_set_aio_ctx = bdrv_child_cb_can_set_aio_ctx, .set_aio_ctx = bdrv_child_cb_set_aio_ctx, .update_filename = bdrv_child_cb_update_filename, - .get_parent_aio_context = bdrv_child_cb_get_parent_aio_context, + .get_parent_aio_context = child_of_bds_get_parent_aio_context, }; AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c) @@ -1549,7 +1540,6 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, } bs->drv = drv; - bs->read_only = !(bs->open_flags & BDRV_O_RDWR); bs->opaque = g_malloc0(drv->instance_size); if (drv->bdrv_file_open) { @@ -1720,6 +1710,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, QemuOpts *opts; BlockDriver *drv; Error *local_err = NULL; + bool ro; assert(bs->file == NULL); assert(options != NULL && bs->options != options); @@ -1770,17 +1761,17 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, trace_bdrv_open_common(bs, filename ?: "", bs->open_flags, drv->format_name); - bs->read_only = !(bs->open_flags & BDRV_O_RDWR); + ro = bdrv_is_read_only(bs); - if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) { - if (!bs->read_only && bdrv_is_whitelisted(drv, true)) { + if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, ro)) { + if (!ro && bdrv_is_whitelisted(drv, true)) { ret = bdrv_apply_auto_read_only(bs, NULL, NULL); } else { ret = -ENOTSUP; } if (ret < 0) { error_setg(errp, - !bs->read_only && bdrv_is_whitelisted(drv, true) + !ro && bdrv_is_whitelisted(drv, true) ? "Driver '%s' can only be used for read-only devices" : "Driver '%s' is not whitelisted", drv->format_name); @@ -1792,7 +1783,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, assert(qatomic_read(&bs->copy_on_read) == 0); if (bs->open_flags & BDRV_O_COPY_ON_READ) { - if (!bs->read_only) { + if (!ro) { bdrv_enable_copy_on_read(bs); } else { error_setg(errp, "Can't use copy-on-read on read-only device"); @@ -2035,27 +2026,38 @@ bool bdrv_is_writable(BlockDriverState *bs) static char *bdrv_child_user_desc(BdrvChild *c) { - if (c->klass->get_parent_desc) { - return c->klass->get_parent_desc(c); - } - - return g_strdup("another user"); + return c->klass->get_parent_desc(c); } +/* + * Check that @a allows everything that @b needs. @a and @b must reference same + * child node. + */ static bool bdrv_a_allow_b(BdrvChild *a, BdrvChild *b, Error **errp) { - g_autofree char *user = NULL; - g_autofree char *perm_names = NULL; + const char *child_bs_name; + g_autofree char *a_user = NULL; + g_autofree char *b_user = NULL; + g_autofree char *perms = NULL; + + assert(a->bs); + assert(a->bs == b->bs); if ((b->perm & a->shared_perm) == b->perm) { return true; } - perm_names = bdrv_perm_names(b->perm & ~a->shared_perm); - user = bdrv_child_user_desc(a); - error_setg(errp, "Conflicts with use by %s as '%s', which does not " - "allow '%s' on %s", - user, a->name, perm_names, bdrv_get_node_name(b->bs)); + child_bs_name = bdrv_get_node_name(b->bs); + a_user = bdrv_child_user_desc(a); + b_user = bdrv_child_user_desc(b); + perms = bdrv_perm_names(b->perm & ~a->shared_perm); + + error_setg(errp, "Permission conflict on node '%s': permissions '%s' are " + "both required by %s (uses node '%s' as '%s' child) and " + "unshared by %s (uses node '%s' as '%s' child).", + child_bs_name, perms, + b_user, child_bs_name, b->name, + a_user, child_bs_name, a->name); return false; } @@ -2760,6 +2762,12 @@ static TransactionActionDrv bdrv_attach_child_common_drv = { /* * Common part of attaching bdrv child to bs or to blk or to job + * + * Resulting new child is returned through @child. + * At start *@child must be NULL. + * @child is saved to a new entry of @tran, so that *@child could be reverted to + * NULL on abort(). So referenced variable must live at least until transaction + * end. */ static int bdrv_attach_child_common(BlockDriverState *child_bs, const char *child_name, @@ -2775,6 +2783,7 @@ static int bdrv_attach_child_common(BlockDriverState *child_bs, assert(child); assert(*child == NULL); + assert(child_class->get_parent_desc); new_child = g_new(BdrvChild, 1); *new_child = (BdrvChild) { @@ -2834,6 +2843,10 @@ static int bdrv_attach_child_common(BlockDriverState *child_bs, return 0; } +/* + * Variable referenced by @child must live at least until transaction end. + * (see bdrv_attach_child_common() doc for details) + */ static int bdrv_attach_child_noperm(BlockDriverState *parent_bs, BlockDriverState *child_bs, const char *child_name, @@ -2916,7 +2929,6 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, child_role, perm, shared_perm, opaque, &child, tran, errp); if (ret < 0) { - assert(child == NULL); goto out; } @@ -2924,6 +2936,9 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, out: tran_finalize(tran, ret); + /* child is unset on failure by bdrv_attach_child_common_abort() */ + assert((ret < 0) == !child); + bdrv_unref(child_bs); return child; } @@ -2963,6 +2978,8 @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, out: tran_finalize(tran, ret); + /* child is unset on failure by bdrv_attach_child_common_abort() */ + assert((ret < 0) == !child); bdrv_unref(child_bs); @@ -4545,7 +4562,6 @@ static void bdrv_reopen_commit(BDRVReopenState *reopen_state) bs->explicit_options = reopen_state->explicit_options; bs->options = reopen_state->options; bs->open_flags = reopen_state->flags; - bs->read_only = !(reopen_state->flags & BDRV_O_RDWR); bs->detect_zeroes = reopen_state->detect_zeroes; if (reopen_state->replace_backing_bs) { diff --git a/block/block-backend.c b/block/block-backend.c index de5496af66..15f1ea4288 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -141,19 +141,18 @@ static void blk_root_set_aio_ctx(BdrvChild *child, AioContext *ctx, static char *blk_root_get_parent_desc(BdrvChild *child) { BlockBackend *blk = child->opaque; - char *dev_id; + g_autofree char *dev_id = NULL; if (blk->name) { - return g_strdup(blk->name); + return g_strdup_printf("block device '%s'", blk->name); } dev_id = blk_get_attached_dev_id(blk); if (*dev_id) { - return dev_id; + return g_strdup_printf("block device '%s'", dev_id); } else { /* TODO Callback into the BB owner for something more detailed */ - g_free(dev_id); - return g_strdup("a block device"); + return g_strdup("an unnamed block device"); } } @@ -1852,7 +1851,7 @@ bool blk_supports_write_perm(BlockBackend *blk) if (bs) { return !bdrv_is_read_only(bs); } else { - return !blk->root_state.read_only; + return blk->root_state.open_flags & BDRV_O_RDWR; } } @@ -2269,7 +2268,6 @@ void blk_update_root_state(BlockBackend *blk) assert(blk->root); blk->root_state.open_flags = blk->root->bs->open_flags; - blk->root_state.read_only = blk->root->bs->read_only; blk->root_state.detect_zeroes = blk->root->bs->detect_zeroes; } @@ -2288,12 +2286,7 @@ bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk) */ int blk_get_open_flags_from_root_state(BlockBackend *blk) { - int bs_flags; - - bs_flags = blk->root_state.read_only ? 0 : BDRV_O_RDWR; - bs_flags |= blk->root_state.open_flags & ~BDRV_O_RDWR; - - return bs_flags; + return blk->root_state.open_flags; } BlockBackendRootState *blk_get_root_state(BlockBackend *blk) @@ -2393,8 +2386,13 @@ static void blk_root_drained_begin(BdrvChild *child) static bool blk_root_drained_poll(BdrvChild *child) { BlockBackend *blk = child->opaque; + bool busy = false; assert(blk->quiesce_counter); - return !!blk->in_flight; + + if (blk->dev_ops && blk->dev_ops->drained_poll) { + busy = blk->dev_ops->drained_poll(blk->dev_opaque); + } + return busy || !!blk->in_flight; } static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter) diff --git a/block/block-copy.c b/block/block-copy.c index c2e5090412..5808cfe657 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -65,6 +65,7 @@ typedef struct BlockCopyTask { int64_t offset; int64_t bytes; bool zeroes; + bool copy_range; QLIST_ENTRY(BlockCopyTask) list; CoQueue wait_queue; /* coroutines blocked on this task */ } BlockCopyTask; @@ -183,6 +184,7 @@ static BlockCopyTask *block_copy_task_create(BlockCopyState *s, .call_state = call_state, .offset = offset, .bytes = bytes, + .copy_range = s->use_copy_range, }; qemu_co_queue_init(&task->wait_queue); QLIST_INSERT_HEAD(&s->tasks, task, list); @@ -342,11 +344,18 @@ static coroutine_fn int block_copy_task_run(AioTaskPool *pool, * * No sync here: nor bitmap neighter intersecting requests handling, only copy. * + * @copy_range is an in-out argument: if *copy_range is false, copy_range is not + * done. If *copy_range is true, copy_range is attempted. If the copy_range + * attempt fails, the function falls back to the usual read+write and + * *copy_range is set to false. *copy_range and zeroes must not be true + * simultaneously. + * * Returns 0 on success. */ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, int64_t offset, int64_t bytes, - bool zeroes, bool *error_is_read) + bool zeroes, bool *copy_range, + bool *error_is_read) { int ret; int64_t nbytes = MIN(offset + bytes, s->len) - offset; @@ -359,6 +368,7 @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, assert(offset + bytes <= s->len || offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size)); assert(nbytes < INT_MAX); + assert(!(*copy_range && zeroes)); if (zeroes) { ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags & @@ -370,32 +380,15 @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, return ret; } - if (s->use_copy_range) { + if (*copy_range) { ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes, 0, s->write_flags); if (ret < 0) { trace_block_copy_copy_range_fail(s, offset, ret); - s->use_copy_range = false; - s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); + *copy_range = false; /* Fallback to read+write with allocated buffer */ } else { - if (s->use_copy_range) { - /* - * Successful copy-range. Now increase copy_size. copy_range - * does not respect max_transfer (it's a TODO), so we factor - * that in here. - * - * Note: we double-check s->use_copy_range for the case when - * parallel block-copy request unsets it during previous - * bdrv_co_copy_range call. - */ - s->copy_size = - MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE), - QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source, - s->target), - s->cluster_size)); - } - goto out; + return 0; } } @@ -431,17 +424,49 @@ out: return ret; } +static void block_copy_handle_copy_range_result(BlockCopyState *s, + bool is_success) +{ + if (!s->use_copy_range) { + /* already disabled */ + return; + } + + if (is_success) { + /* + * Successful copy-range. Now increase copy_size. copy_range + * does not respect max_transfer (it's a TODO), so we factor + * that in here. + */ + s->copy_size = + MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE), + QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source, + s->target), + s->cluster_size)); + } else { + /* Copy-range failed, disable it. */ + s->use_copy_range = false; + s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); + } +} + static coroutine_fn int block_copy_task_entry(AioTask *task) { BlockCopyTask *t = container_of(task, BlockCopyTask, task); bool error_is_read = false; + bool copy_range = t->copy_range; int ret; ret = block_copy_do_copy(t->s, t->offset, t->bytes, t->zeroes, - &error_is_read); - if (ret < 0 && !t->call_state->ret) { - t->call_state->ret = ret; - t->call_state->error_is_read = error_is_read; + ©_range, &error_is_read); + if (t->copy_range) { + block_copy_handle_copy_range_result(t->s, copy_range); + } + if (ret < 0) { + if (!t->call_state->ret) { + t->call_state->ret = ret; + t->call_state->error_is_read = error_is_read; + } } else { progress_work_done(t->s->progress, t->bytes); } @@ -617,7 +642,10 @@ block_copy_dirty_clusters(BlockCopyCallState *call_state) g_free(task); continue; } - task->zeroes = ret & BDRV_BLOCK_ZERO; + if (ret & BDRV_BLOCK_ZERO) { + task->zeroes = true; + task->copy_range = false; + } if (s->speed) { if (!call_state->ignore_ratelimit) { diff --git a/block/commit.c b/block/commit.c index b89bb20b75..b7f0c7c061 100644 --- a/block/commit.c +++ b/block/commit.c @@ -453,7 +453,7 @@ int bdrv_commit(BlockDriverState *bs) return -EBUSY; } - ro = backing_file_bs->read_only; + ro = bdrv_is_read_only(backing_file_bs); if (ro) { if (bdrv_reopen_set_read_only(backing_file_bs, false, NULL)) { diff --git a/block/file-posix.c b/block/file-posix.c index 10b71d9a13..f37dfc10b3 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1625,17 +1625,17 @@ static int handle_aiocb_write_zeroes(void *opaque) if (s->has_write_zeroes) { int ret = do_fallocate(s->fd, FALLOC_FL_ZERO_RANGE, aiocb->aio_offset, aiocb->aio_nbytes); - if (ret == -EINVAL) { - /* - * Allow falling back to pwrite for file systems that - * do not support fallocate() for an unaligned byte range. - */ - return -ENOTSUP; - } - if (ret == 0 || ret != -ENOTSUP) { + if (ret == -ENOTSUP) { + s->has_write_zeroes = false; + } else if (ret == 0 || ret != -EINVAL) { return ret; } - s->has_write_zeroes = false; + /* + * Note: Some file systems do not like unaligned byte ranges, and + * return EINVAL in such a case, though they should not do it according + * to the man-page of fallocate(). Thus we simply ignore this return + * value and try the other fallbacks instead. + */ } #endif @@ -1650,6 +1650,17 @@ static int handle_aiocb_write_zeroes(void *opaque) return ret; } s->has_fallocate = false; + } else if (ret == -EINVAL) { + /* + * Some file systems like older versions of GPFS do not like un- + * aligned byte ranges, and return EINVAL in such a case, though + * they should not do it according to the man-page of fallocate(). + * Warn about the bad filesystem and try the final fallback instead. + */ + warn_report_once("Your file system is misbehaving: " + "fallocate(FALLOC_FL_PUNCH_HOLE) returned EINVAL. " + "Please report this bug to your file sytem " + "vendor."); } else if (ret != -ENOTSUP) { return ret; } else { diff --git a/block/io.c b/block/io.c index 1e826ba9e8..323854d063 100644 --- a/block/io.c +++ b/block/io.c @@ -1973,7 +1973,7 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, int64_t bytes, bdrv_check_request(offset, bytes, &error_abort); - if (bs->read_only) { + if (bdrv_is_read_only(bs)) { return -EPERM; } @@ -3406,7 +3406,7 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, if (new_bytes) { bdrv_make_request_serialising(&req, 1); } - if (bs->read_only) { + if (bdrv_is_read_only(bs)) { error_setg(errp, "Image is read-only"); ret = -EACCES; goto out; diff --git a/block/qapi.c b/block/qapi.c index 943e7b15ad..dc69341bfe 100644 --- a/block/qapi.c +++ b/block/qapi.c @@ -59,7 +59,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk, info = g_malloc0(sizeof(*info)); info->file = g_strdup(bs->filename); - info->ro = bs->read_only; + info->ro = bdrv_is_read_only(bs); info->drv = g_strdup(bs->drv->format_name); info->encrypted = bs->encrypted; diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index 2e98c7f4b6..71ddb08c21 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -1026,7 +1026,7 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, int new_l1_bytes; int ret; - assert(bs->read_only); + assert(bdrv_is_read_only(bs)); /* Search the snapshot */ snapshot_index = find_snapshot_by_id_and_name(bs, snapshot_id, name); diff --git a/block/qcow2.c b/block/qcow2.c index 39b91ef940..ee4530cdbd 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -1723,8 +1723,7 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, /* Clear unknown autoclear feature bits */ update_header |= s->autoclear_features & ~QCOW2_AUTOCLEAR_MASK; - update_header = - update_header && !bs->read_only && !(flags & BDRV_O_INACTIVE); + update_header = update_header && bdrv_is_writable(bs); if (update_header) { s->autoclear_features &= QCOW2_AUTOCLEAR_MASK; } @@ -1811,7 +1810,7 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; /* Repair image if dirty */ - if (!(flags & (BDRV_O_CHECK | BDRV_O_INACTIVE)) && !bs->read_only && + if (!(flags & BDRV_O_CHECK) && bdrv_is_writable(bs) && (s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) { BdrvCheckResult result = {0}; diff --git a/block/quorum.c b/block/quorum.c index cfc1436abb..f2c0805000 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -1279,7 +1279,7 @@ static BlockDriver bdrv_quorum = { .bdrv_dirname = quorum_dirname, .bdrv_co_block_status = quorum_co_block_status, - .bdrv_co_flush_to_disk = quorum_co_flush, + .bdrv_co_flush = quorum_co_flush, .bdrv_getlength = quorum_getlength, diff --git a/block/replication.c b/block/replication.c index 97be7ef4de..52163f2d1f 100644 --- a/block/replication.c +++ b/block/replication.c @@ -22,7 +22,7 @@ #include "sysemu/block-backend.h" #include "qapi/error.h" #include "qapi/qmp/qdict.h" -#include "replication.h" +#include "block/replication.h" typedef enum { BLOCK_REPLICATION_NONE, /* block replication is not started */ diff --git a/block/snapshot.c b/block/snapshot.c index e8ae9a28c1..6702c75e42 100644 --- a/block/snapshot.c +++ b/block/snapshot.c @@ -415,7 +415,7 @@ int bdrv_snapshot_load_tmp(BlockDriverState *bs, error_setg(errp, "snapshot_id and name are both NULL"); return -EINVAL; } - if (!bs->read_only) { + if (!bdrv_is_read_only(bs)) { error_setg(errp, "Device is not readonly"); return -EINVAL; } diff --git a/block/ssh.c b/block/ssh.c index ebe3d8b631..b51a031620 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -277,7 +277,6 @@ static void ssh_parse_filename(const char *filename, QDict *options, static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp) { int ret; -#ifdef HAVE_LIBSSH_0_8 enum ssh_known_hosts_e state; int r; ssh_key pubkey; @@ -343,46 +342,6 @@ static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp) error_setg(errp, "error while checking for known server (%d)", state); goto out; } -#else /* !HAVE_LIBSSH_0_8 */ - int state; - - state = ssh_is_server_known(s->session); - trace_ssh_server_status(state); - - switch (state) { - case SSH_SERVER_KNOWN_OK: - /* OK */ - trace_ssh_check_host_key_knownhosts(); - break; - case SSH_SERVER_KNOWN_CHANGED: - ret = -EINVAL; - error_setg(errp, - "host key does not match the one in known_hosts; this " - "may be a possible attack"); - goto out; - case SSH_SERVER_FOUND_OTHER: - ret = -EINVAL; - error_setg(errp, - "host key for this server not found, another type exists"); - goto out; - case SSH_SERVER_FILE_NOT_FOUND: - ret = -ENOENT; - error_setg(errp, "known_hosts file not found"); - goto out; - case SSH_SERVER_NOT_KNOWN: - ret = -EINVAL; - error_setg(errp, "no host key was found in known_hosts"); - goto out; - case SSH_SERVER_ERROR: - ret = -EINVAL; - error_setg(errp, "server error"); - goto out; - default: - ret = -EINVAL; - error_setg(errp, "error while checking for known server (%d)", state); - goto out; - } -#endif /* !HAVE_LIBSSH_0_8 */ /* known_hosts checking successful. */ ret = 0; @@ -438,11 +397,7 @@ check_host_key_hash(BDRVSSHState *s, const char *hash, unsigned char *server_hash; size_t server_hash_len; -#ifdef HAVE_LIBSSH_0_8 r = ssh_get_server_publickey(s->session, &pubkey); -#else - r = ssh_get_publickey(s->session, &pubkey); -#endif if (r != SSH_OK) { session_error_setg(errp, s, "failed to read remote host key"); return -EINVAL; @@ -1233,8 +1188,6 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what) } } -#ifdef HAVE_LIBSSH_0_8 - static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs) { int r; @@ -1271,18 +1224,6 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs) return ret; } -#else /* !HAVE_LIBSSH_0_8 */ - -static coroutine_fn int ssh_co_flush(BlockDriverState *bs) -{ - BDRVSSHState *s = bs->opaque; - - unsafe_flush_warning(s, "libssh >= 0.8.0"); - return 0; -} - -#endif /* !HAVE_LIBSSH_0_8 */ - static int64_t ssh_getlength(BlockDriverState *bs) { BDRVSSHState *s = bs->opaque; diff --git a/block/trace-events b/block/trace-events index 31062ed437..574760ba9a 100644 --- a/block/trace-events +++ b/block/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # ../block.c bdrv_open_common(void *bs, const char *filename, int flags, const char *format_name) "bs %p filename \"%s\" flags 0x%x format_name \"%s\"" diff --git a/block/vhdx-log.c b/block/vhdx-log.c index 404fb5f3cb..7672161d95 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -801,7 +801,7 @@ int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed, } if (logs.valid) { - if (bs->read_only) { + if (bdrv_is_read_only(bs)) { bdrv_refresh_filename(bs); ret = -EPERM; error_setg(errp, diff --git a/block/vvfat.c b/block/vvfat.c index 54807f82ca..ae9d387da7 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -3127,10 +3127,7 @@ static void vvfat_qcow_options(BdrvChildRole role, bool parent_is_format, qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on"); } -static const BdrvChildClass child_vvfat_qcow = { - .parent_is_bds = true, - .inherit_options = vvfat_qcow_options, -}; +static BdrvChildClass child_vvfat_qcow; static int enable_write_target(BlockDriverState *bs, Error **errp) { @@ -3208,15 +3205,12 @@ static void vvfat_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - BDRVVVFATState *s = bs->opaque; - - assert(c == s->qcow || (role & BDRV_CHILD_COW)); - - if (c == s->qcow) { + if (role & BDRV_CHILD_DATA) { /* This is a private node, nobody should try to attach to it */ *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE; *nshared = BLK_PERM_WRITE_UNCHANGED; } else { + assert(role & BDRV_CHILD_COW); /* The backing file is there so 'commit' can use it. vvfat doesn't * access it in any way. */ *nperm = 0; @@ -3270,6 +3264,8 @@ static BlockDriver bdrv_vvfat = { static void bdrv_vvfat_init(void) { + child_vvfat_qcow = child_of_bds; + child_vvfat_qcow.inherit_options = vvfat_qcow_options; bdrv_register(&bdrv_vvfat); } diff --git a/blockdev.c b/blockdev.c index 834c2304a1..f08192deda 100644 --- a/blockdev.c +++ b/blockdev.c @@ -583,8 +583,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts, blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL); blk_rs = blk_get_root_state(blk); - blk_rs->open_flags = bdrv_flags; - blk_rs->read_only = read_only; + blk_rs->open_flags = bdrv_flags | (read_only ? 0 : BDRV_O_RDWR); blk_rs->detect_zeroes = detect_zeroes; qobject_unref(bs_opts); diff --git a/chardev/trace-events b/chardev/trace-events index 5ea4408207..027107b0c1 100644 --- a/chardev/trace-events +++ b/chardev/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # wctablet.c wct_init(void) "" @@ -256,31 +256,11 @@ gdb_bin=$(command -v "gdb-multiarch" || command -v "gdb") if test -e "$source_path/.git" then git_submodules_action="update" - git_submodules="ui/keycodemapdb" - git_submodules="$git_submodules tests/fp/berkeley-testfloat-3" - git_submodules="$git_submodules tests/fp/berkeley-softfloat-3" else git_submodules_action="ignore" - git_submodules="" - - if ! test -f "$source_path/ui/keycodemapdb/README" - then - echo - echo "ERROR: missing file $source_path/ui/keycodemapdb/README" - echo - echo "This is not a GIT checkout but module content appears to" - echo "be missing. Do not use 'git archive' or GitHub download links" - echo "to acquire QEMU source archives. Non-GIT builds are only" - echo "supported with source archives linked from:" - echo - echo " https://www.qemu.org/download/#source" - echo - echo "Developers working with GIT can use scripts/archive-source.sh" - echo "if they need to create valid source archives." - echo - exit 1 - fi fi + +git_submodules="ui/keycodemapdb" git="git" # Don't accept a target_list environment variable. @@ -428,7 +408,6 @@ gnutls="$default_feature" nettle="$default_feature" nettle_xts="no" gcrypt="$default_feature" -gcrypt_hmac="no" gcrypt_xts="no" qemu_private_xts="yes" auth_pam="$default_feature" @@ -1598,6 +1577,28 @@ case $git_submodules_action in fi ;; ignore) + if ! test -f "$source_path/ui/keycodemapdb/README" + then + echo + echo "ERROR: missing GIT submodules" + echo + if test -e "$source_path/.git"; then + echo "--with-git-submodules=ignore specified but submodules were not" + echo "checked out. Please initialize and update submodules." + else + echo "This is not a GIT checkout but module content appears to" + echo "be missing. Do not use 'git archive' or GitHub download links" + echo "to acquire QEMU source archives. Non-GIT builds are only" + echo "supported with source archives linked from:" + echo + echo " https://www.qemu.org/download/#source" + echo + echo "Developers working with GIT can use scripts/archive-source.sh" + echo "if they need to create valid source archives." + fi + echo + exit 1 + fi ;; *) echo "ERROR: invalid --with-git-submodules= value '$git_submodules_action'" @@ -2061,17 +2062,17 @@ fi cat > $TMPC << EOF #if defined(__clang_major__) && defined(__clang_minor__) # ifdef __apple_build_version__ -# if __clang_major__ < 5 || (__clang_major__ == 5 && __clang_minor__ < 1) -# error You need at least XCode Clang v5.1 to compile QEMU +# if __clang_major__ < 10 || (__clang_major__ == 10 && __clang_minor__ < 0) +# error You need at least XCode Clang v10.0 to compile QEMU # endif # else -# if __clang_major__ < 3 || (__clang_major__ == 3 && __clang_minor__ < 4) -# error You need at least Clang v3.4 to compile QEMU +# if __clang_major__ < 6 || (__clang_major__ == 6 && __clang_minor__ < 0) +# error You need at least Clang v6.0 to compile QEMU # endif # endif #elif defined(__GNUC__) && defined(__GNUC_MINOR__) -# if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 8) -# error You need at least GCC v4.8 to compile QEMU +# if __GNUC__ < 7 || (__GNUC__ == 7 && __GNUC_MINOR__ < 5) +# error You need at least GCC v7.5.0 to compile QEMU # endif #else # error You either need GCC or Clang to compiler QEMU @@ -2079,7 +2080,7 @@ cat > $TMPC << EOF int main (void) { return 0; } EOF if ! compile_prog "" "" ; then - error_exit "You need at least GCC v4.8 or Clang v3.4 (or XCode Clang v5.1)" + error_exit "You need at least GCC v7.5 or Clang v6.0 (or XCode Clang v10.0)" fi # Accumulate -Wfoo and -Wno-bar separately. @@ -2287,6 +2288,11 @@ if test "$solaris" = "yes" ; then fi fi +if test "$tcg" = "enabled"; then + git_submodules="$git_submodules tests/fp/berkeley-testfloat-3" + git_submodules="$git_submodules tests/fp/berkeley-softfloat-3" +fi + if test -z "${target_list+xxx}" ; then default_targets=yes for target in $default_target_list; do @@ -2801,7 +2807,7 @@ fi if test "$gnutls" != "no"; then pass="no" - if $pkg_config --exists "gnutls >= 3.1.18"; then + if $pkg_config --exists "gnutls >= 3.5.18"; then gnutls_cflags=$($pkg_config --cflags gnutls) gnutls_libs=$($pkg_config --libs gnutls) # Packaging for the static libraries is not always correct. @@ -2859,7 +2865,7 @@ has_libgcrypt() { maj=`libgcrypt-config --version | awk -F . '{print $1}'` min=`libgcrypt-config --version | awk -F . '{print $2}'` - if test $maj != 1 || test $min -lt 5 + if test $maj != 1 || test $min -lt 8 then return 1 fi @@ -2870,10 +2876,9 @@ has_libgcrypt() { if test "$nettle" != "no"; then pass="no" - if $pkg_config --exists "nettle >= 2.7.1"; then + if $pkg_config --exists "nettle >= 3.4"; then nettle_cflags=$($pkg_config --cflags nettle) nettle_libs=$($pkg_config --libs nettle) - nettle_version=$($pkg_config --modversion nettle) # Link test to make sure the given libraries work (e.g for static). write_c_skeleton if compile_prog "" "$nettle_libs" ; then @@ -2927,18 +2932,6 @@ if test "$gcrypt" != "no"; then cat > $TMPC << EOF #include <gcrypt.h> int main(void) { - gcry_mac_hd_t handle; - gcry_mac_open(&handle, GCRY_MAC_HMAC_MD5, - GCRY_MAC_FLAG_SECURE, NULL); - return 0; -} -EOF - if compile_prog "$gcrypt_cflags" "$gcrypt_libs" ; then - gcrypt_hmac=yes - fi - cat > $TMPC << EOF -#include <gcrypt.h> -int main(void) { gcry_cipher_hd_t handle; gcry_cipher_open(&handle, GCRY_CIPHER_AES, GCRY_CIPHER_MODE_XTS, 0); return 0; @@ -3320,7 +3313,7 @@ done ########################################## # glib support probe -glib_req_ver=2.48 +glib_req_ver=2.56 glib_modules=gthread-2.0 if test "$modules" = yes; then glib_modules="$glib_modules gmodule-export-2.0" @@ -3528,7 +3521,7 @@ fi ########################################## # libssh probe if test "$libssh" != "no" ; then - if $pkg_config --exists libssh; then + if $pkg_config --exists "libssh >= 0.8.7"; then libssh_cflags=$($pkg_config libssh --cflags) libssh_libs=$($pkg_config libssh --libs) libssh=yes @@ -3541,23 +3534,6 @@ if test "$libssh" != "no" ; then fi ########################################## -# Check for libssh 0.8 -# This is done like this instead of using the LIBSSH_VERSION_* and -# SSH_VERSION_* macros because some distributions in the past shipped -# snapshots of the future 0.8 from Git, and those snapshots did not -# have updated version numbers (still referring to 0.7.0). - -if test "$libssh" = "yes"; then - cat > $TMPC <<EOF -#include <libssh/libssh.h> -int main(void) { return ssh_get_server_publickey(NULL, NULL); } -EOF - if compile_prog "$libssh_cflags" "$libssh_libs"; then - libssh_cflags="-DHAVE_LIBSSH_0_8 $libssh_cflags" - fi -fi - -########################################## # linux-aio probe if test "$linux_aio" != "no" ; then @@ -3626,9 +3602,7 @@ fi case "$fdt" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} dtc" - fi + git_submodules="${git_submodules} dtc" ;; esac @@ -4350,9 +4324,7 @@ fi case "$capstone" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} capstone" - fi + git_submodules="${git_submodules} capstone" ;; esac @@ -5282,9 +5254,7 @@ fi case "$slirp" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} slirp" - fi + git_submodules="${git_submodules} slirp" ;; esac @@ -5476,9 +5446,7 @@ if test "$cpu" = "s390x" ; then roms="$roms s390-ccw" # SLOF is required for building the s390-ccw firmware on s390x, # since it is using the libnet code from SLOF for network booting. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} roms/SLOF" - fi + git_submodules="${git_submodules} roms/SLOF" fi fi @@ -5746,15 +5714,11 @@ if test "$gnutls" = "yes" ; then fi if test "$gcrypt" = "yes" ; then echo "CONFIG_GCRYPT=y" >> $config_host_mak - if test "$gcrypt_hmac" = "yes" ; then - echo "CONFIG_GCRYPT_HMAC=y" >> $config_host_mak - fi echo "GCRYPT_CFLAGS=$gcrypt_cflags" >> $config_host_mak echo "GCRYPT_LIBS=$gcrypt_libs" >> $config_host_mak fi if test "$nettle" = "yes" ; then echo "CONFIG_NETTLE=y" >> $config_host_mak - echo "CONFIG_NETTLE_VERSION_MAJOR=${nettle_version%%.*}" >> $config_host_mak echo "NETTLE_CFLAGS=$nettle_cflags" >> $config_host_mak echo "NETTLE_LIBS=$nettle_libs" >> $config_host_mak fi @@ -6510,10 +6474,14 @@ fi # Create list of config switches that should be poisoned in common code... # but filter out CONFIG_TCG and CONFIG_USER_ONLY which are special. -sed -n -e '/CONFIG_TCG/d' -e '/CONFIG_USER_ONLY/d' \ - -e '/^#define / { s///; s/ .*//; s/^/#pragma GCC poison /p; }' \ - *-config-devices.h *-config-target.h | \ - sort -u > config-poison.h +target_configs_h=$(ls *-config-devices.h *-config-target.h 2>/dev/null) +if test -n "$target_configs_h" ; then + sed -n -e '/CONFIG_TCG/d' -e '/CONFIG_USER_ONLY/d' \ + -e '/^#define / { s///; s/ .*//; s/^/#pragma GCC poison /p; }' \ + $target_configs_h | sort -u > config-poison.h +else + :> config-poison.h +fi # Save the configure command line for later reuse. cat <<EOD >config.status diff --git a/contrib/vhost-user-gpu/vhost-user-gpu.c b/contrib/vhost-user-gpu/vhost-user-gpu.c index f73f292c9f..6dc6a44f4e 100644 --- a/contrib/vhost-user-gpu/vhost-user-gpu.c +++ b/contrib/vhost-user-gpu/vhost-user-gpu.c @@ -49,6 +49,8 @@ static char *opt_render_node; static gboolean opt_virgl; static void vg_handle_ctrl(VuDev *dev, int qidx); +static void vg_cleanup_mapping(VuGpu *g, + struct virtio_gpu_simple_resource *res); static const char * vg_cmd_to_string(int cmd) @@ -349,6 +351,7 @@ vg_resource_create_2d(VuGpu *g, g_critical("%s: resource creation failed %d %d %d", __func__, c2d.resource_id, c2d.width, c2d.height); g_free(res); + vugbm_buffer_destroy(&res->buffer); cmd->error = VIRTIO_GPU_RESP_ERR_OUT_OF_MEMORY; return; } @@ -399,6 +402,7 @@ vg_resource_destroy(VuGpu *g, } vugbm_buffer_destroy(&res->buffer); + vg_cleanup_mapping(g, res); pixman_image_unref(res->image); QTAILQ_REMOVE(&g->reslist, res, next); g_free(res); @@ -488,6 +492,11 @@ vg_resource_attach_backing(VuGpu *g, return; } + if (res->iov) { + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + ret = vg_create_mapping_iov(g, &ab, cmd, &res->iov); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; @@ -497,6 +506,22 @@ vg_resource_attach_backing(VuGpu *g, res->iov_cnt = ab.nr_entries; } +/* Though currently only free iov, maybe later will do more work. */ +void vg_cleanup_mapping_iov(VuGpu *g, + struct iovec *iov, uint32_t count) +{ + g_free(iov); +} + +static void +vg_cleanup_mapping(VuGpu *g, + struct virtio_gpu_simple_resource *res) +{ + vg_cleanup_mapping_iov(g, res->iov, res->iov_cnt); + res->iov = NULL; + res->iov_cnt = 0; +} + static void vg_resource_detach_backing(VuGpu *g, struct virtio_gpu_ctrl_command *cmd) @@ -515,9 +540,7 @@ vg_resource_detach_backing(VuGpu *g, return; } - g_free(res->iov); - res->iov = NULL; - res->iov_cnt = 0; + vg_cleanup_mapping(g, res); } static void diff --git a/contrib/vhost-user-gpu/virgl.c b/contrib/vhost-user-gpu/virgl.c index 9e6660c7ab..3e45e1bd33 100644 --- a/contrib/vhost-user-gpu/virgl.c +++ b/contrib/vhost-user-gpu/virgl.c @@ -108,9 +108,17 @@ virgl_cmd_resource_unref(VuGpu *g, struct virtio_gpu_ctrl_command *cmd) { struct virtio_gpu_resource_unref unref; + struct iovec *res_iovs = NULL; + int num_iovs = 0; VUGPU_FILL_CMD(unref); + virgl_renderer_resource_detach_iov(unref.resource_id, + &res_iovs, + &num_iovs); + if (res_iovs != NULL && num_iovs != 0) { + vg_cleanup_mapping_iov(g, res_iovs, num_iovs); + } virgl_renderer_resource_unref(unref.resource_id); } @@ -128,6 +136,7 @@ virgl_cmd_get_capset_info(VuGpu *g, VUGPU_FILL_CMD(info); + memset(&resp, 0, sizeof(resp)); if (info.capset_index == 0) { resp.capset_id = VIRTIO_GPU_CAPSET_VIRGL; virgl_renderer_get_cap_set(resp.capset_id, @@ -169,6 +178,10 @@ virgl_cmd_get_capset(VuGpu *g, virgl_renderer_get_cap_set(gc.capset_id, &max_ver, &max_size); + if (!max_size) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; + } resp = g_malloc0(sizeof(*resp) + max_size); resp->hdr.type = VIRTIO_GPU_RESP_OK_CAPSET; @@ -279,8 +292,11 @@ virgl_resource_attach_backing(VuGpu *g, return; } - virgl_renderer_resource_attach_iov(att_rb.resource_id, + ret = virgl_renderer_resource_attach_iov(att_rb.resource_id, res_iovs, att_rb.nr_entries); + if (ret != 0) { + vg_cleanup_mapping_iov(g, res_iovs, att_rb.nr_entries); + } } static void @@ -299,7 +315,7 @@ virgl_resource_detach_backing(VuGpu *g, if (res_iovs == NULL || num_iovs == 0) { return; } - g_free(res_iovs); + vg_cleanup_mapping_iov(g, res_iovs, num_iovs); } static void diff --git a/contrib/vhost-user-gpu/vugpu.h b/contrib/vhost-user-gpu/vugpu.h index 04d5615812..e2864bba68 100644 --- a/contrib/vhost-user-gpu/vugpu.h +++ b/contrib/vhost-user-gpu/vugpu.h @@ -169,7 +169,7 @@ int vg_create_mapping_iov(VuGpu *g, struct virtio_gpu_resource_attach_backing *ab, struct virtio_gpu_ctrl_command *cmd, struct iovec **iov); - +void vg_cleanup_mapping_iov(VuGpu *g, struct iovec *iov, uint32_t count); void vg_get_display_info(VuGpu *vg, struct virtio_gpu_ctrl_command *cmd); void vg_wait_ok(VuGpu *g); @@ -29,6 +29,7 @@ #ifdef CONFIG_USER_ONLY #include "qemu.h" #else +#include "hw/core/sysemu-cpu-ops.h" #include "exec/address-spaces.h" #endif #include "sysemu/tcg.h" @@ -127,7 +128,9 @@ const VMStateDescription vmstate_cpu_common = { void cpu_exec_realizefn(CPUState *cpu, Error **errp) { +#ifndef CONFIG_USER_ONLY CPUClass *cc = CPU_GET_CLASS(cpu); +#endif cpu_list_add(cpu); if (!accel_cpu_realizefn(cpu, errp)) { @@ -141,26 +144,25 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) #endif /* CONFIG_TCG */ #ifdef CONFIG_USER_ONLY - assert(cc->vmsd == NULL); + assert(qdev_get_vmsd(DEVICE(cpu)) == NULL || + qdev_get_vmsd(DEVICE(cpu))->unmigratable); #else if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_register(NULL, cpu->cpu_index, &vmstate_cpu_common, cpu); } - if (cc->vmsd != NULL) { - vmstate_register(NULL, cpu->cpu_index, cc->vmsd, cpu); + if (cc->sysemu_ops->legacy_vmsd != NULL) { + vmstate_register(NULL, cpu->cpu_index, cc->sysemu_ops->legacy_vmsd, cpu); } #endif /* CONFIG_USER_ONLY */ } void cpu_exec_unrealizefn(CPUState *cpu) { +#ifndef CONFIG_USER_ONLY CPUClass *cc = CPU_GET_CLASS(cpu); -#ifdef CONFIG_USER_ONLY - assert(cc->vmsd == NULL); -#else - if (cc->vmsd != NULL) { - vmstate_unregister(NULL, cc->vmsd, cpu); + if (cc->sysemu_ops->legacy_vmsd != NULL) { + vmstate_unregister(NULL, cc->sysemu_ops->legacy_vmsd, cpu); } if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_unregister(NULL, &vmstate_cpu_common, cpu); diff --git a/crypto/cipher-nettle.c.inc b/crypto/cipher-nettle.c.inc index cac771e4ff..fc6f40c026 100644 --- a/crypto/cipher-nettle.c.inc +++ b/crypto/cipher-nettle.c.inc @@ -34,47 +34,6 @@ #include <nettle/xts.h> #endif -typedef void (*QCryptoCipherNettleFuncWrapper)(const void *ctx, - size_t length, - uint8_t *dst, - const uint8_t *src); - -#if CONFIG_NETTLE_VERSION_MAJOR < 3 -typedef nettle_crypt_func * QCryptoCipherNettleFuncNative; -typedef void * cipher_ctx_t; -typedef unsigned cipher_length_t; -#define CONST_CTX - -#define cast5_set_key cast128_set_key - -#define aes128_ctx aes_ctx -#define aes192_ctx aes_ctx -#define aes256_ctx aes_ctx -#define aes128_set_encrypt_key(c, k) \ - aes_set_encrypt_key(c, 16, k) -#define aes192_set_encrypt_key(c, k) \ - aes_set_encrypt_key(c, 24, k) -#define aes256_set_encrypt_key(c, k) \ - aes_set_encrypt_key(c, 32, k) -#define aes128_set_decrypt_key(c, k) \ - aes_set_decrypt_key(c, 16, k) -#define aes192_set_decrypt_key(c, k) \ - aes_set_decrypt_key(c, 24, k) -#define aes256_set_decrypt_key(c, k) \ - aes_set_decrypt_key(c, 32, k) -#define aes128_encrypt aes_encrypt -#define aes192_encrypt aes_encrypt -#define aes256_encrypt aes_encrypt -#define aes128_decrypt aes_decrypt -#define aes192_decrypt aes_decrypt -#define aes256_decrypt aes_decrypt -#else -typedef nettle_cipher_func * QCryptoCipherNettleFuncNative; -typedef const void * cipher_ctx_t; -typedef size_t cipher_length_t; -#define CONST_CTX const -#endif - static inline bool qcrypto_length_check(size_t len, size_t blocksize, Error **errp) { @@ -197,12 +156,12 @@ static const struct QCryptoCipherDriver NAME##_driver_ctr = { \ static void NAME##_xts_wrape(const void *ctx, size_t length, \ uint8_t *dst, const uint8_t *src) \ { \ - ENCRYPT((cipher_ctx_t)ctx, length, dst, src); \ + ENCRYPT((const void *)ctx, length, dst, src); \ } \ static void NAME##_xts_wrapd(const void *ctx, size_t length, \ uint8_t *dst, const uint8_t *src) \ { \ - DECRYPT((cipher_ctx_t)ctx, length, dst, src); \ + DECRYPT((const void *)ctx, length, dst, src); \ } \ static int NAME##_encrypt_xts(QCryptoCipher *cipher, const void *in, \ void *out, size_t len, Error **errp) \ @@ -282,13 +241,13 @@ typedef struct QCryptoNettleDESRFB { uint8_t iv[DES_BLOCK_SIZE]; } QCryptoNettleDESRFB; -static void des_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des_encrypt(ctx, length, dst, src); } -static void des_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des_decrypt(ctx, length, dst, src); @@ -304,13 +263,13 @@ typedef struct QCryptoNettleDES3 { uint8_t iv[DES3_BLOCK_SIZE]; } QCryptoNettleDES3; -static void des3_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des3_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des3_encrypt(ctx, length, dst, src); } -static void des3_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des3_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des3_decrypt(ctx, length, dst, src); @@ -327,17 +286,17 @@ typedef struct QCryptoNettleAES128 { struct aes128_ctx key[2], key_xts[2]; } QCryptoNettleAES128; -static void aes128_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes128_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes128_ctx *keys = ctx; + const struct aes128_ctx *keys = ctx; aes128_encrypt(&keys[0], length, dst, src); } -static void aes128_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes128_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes128_ctx *keys = ctx; + const struct aes128_ctx *keys = ctx; aes128_decrypt(&keys[1], length, dst, src); } @@ -353,17 +312,17 @@ typedef struct QCryptoNettleAES192 { struct aes192_ctx key[2], key_xts[2]; } QCryptoNettleAES192; -static void aes192_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes192_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes192_ctx *keys = ctx; + const struct aes192_ctx *keys = ctx; aes192_encrypt(&keys[0], length, dst, src); } -static void aes192_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes192_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes192_ctx *keys = ctx; + const struct aes192_ctx *keys = ctx; aes192_decrypt(&keys[1], length, dst, src); } @@ -379,17 +338,17 @@ typedef struct QCryptoNettleAES256 { struct aes256_ctx key[2], key_xts[2]; } QCryptoNettleAES256; -static void aes256_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes256_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes256_ctx *keys = ctx; + const struct aes256_ctx *keys = ctx; aes256_encrypt(&keys[0], length, dst, src); } -static void aes256_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, - uint8_t *dst, const uint8_t *src) +static void aes256_decrypt_native(const void *ctx, size_t length, + uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes256_ctx *keys = ctx; + const struct aes256_ctx *keys = ctx; aes256_decrypt(&keys[1], length, dst, src); } @@ -404,13 +363,13 @@ typedef struct QCryptoNettleCAST128 { struct cast128_ctx key, key_xts; } QCryptoNettleCAST128; -static void cast128_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void cast128_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { cast128_encrypt(ctx, length, dst, src); } -static void cast128_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void cast128_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { cast128_decrypt(ctx, length, dst, src); @@ -428,13 +387,13 @@ typedef struct QCryptoNettleSerpent { } QCryptoNettleSerpent; -static void serpent_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void serpent_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { serpent_encrypt(ctx, length, dst, src); } -static void serpent_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void serpent_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { serpent_decrypt(ctx, length, dst, src); @@ -451,13 +410,13 @@ typedef struct QCryptoNettleTwofish { struct twofish_ctx key, key_xts; } QCryptoNettleTwofish; -static void twofish_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void twofish_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { twofish_encrypt(ctx, length, dst, src); } -static void twofish_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void twofish_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { twofish_decrypt(ctx, length, dst, src); diff --git a/crypto/hash-nettle.c b/crypto/hash-nettle.c index 2a6ee7c7d5..1ca1a41062 100644 --- a/crypto/hash-nettle.c +++ b/crypto/hash-nettle.c @@ -26,18 +26,12 @@ #include <nettle/sha.h> #include <nettle/ripemd160.h> -#if CONFIG_NETTLE_VERSION_MAJOR < 3 -typedef unsigned int hash_length_t; -#else -typedef size_t hash_length_t; -#endif - typedef void (*qcrypto_nettle_init)(void *ctx); typedef void (*qcrypto_nettle_write)(void *ctx, - hash_length_t len, + size_t len, const uint8_t *buf); typedef void (*qcrypto_nettle_result)(void *ctx, - hash_length_t len, + size_t len, uint8_t *buf); union qcrypto_hash_ctx { diff --git a/crypto/hmac-nettle.c b/crypto/hmac-nettle.c index 1152b741fd..1ad6c4f253 100644 --- a/crypto/hmac-nettle.c +++ b/crypto/hmac-nettle.c @@ -18,22 +18,16 @@ #include "hmacpriv.h" #include <nettle/hmac.h> -#if CONFIG_NETTLE_VERSION_MAJOR < 3 -typedef unsigned int hmac_length_t; -#else -typedef size_t hmac_length_t; -#endif - typedef void (*qcrypto_nettle_hmac_setkey)(void *ctx, - hmac_length_t key_length, + size_t key_length, const uint8_t *key); typedef void (*qcrypto_nettle_hmac_update)(void *ctx, - hmac_length_t length, + size_t length, const uint8_t *data); typedef void (*qcrypto_nettle_hmac_digest)(void *ctx, - hmac_length_t length, + size_t length, uint8_t *digest); typedef struct QCryptoHmacNettle QCryptoHmacNettle; diff --git a/crypto/meson.build b/crypto/meson.build index 7f37b5d335..af7e80c6f6 100644 --- a/crypto/meson.build +++ b/crypto/meson.build @@ -26,11 +26,7 @@ if 'CONFIG_NETTLE' in config_host crypto_ss.add(files('hash-nettle.c', 'hmac-nettle.c', 'pbkdf-nettle.c')) elif 'CONFIG_GCRYPT' in config_host crypto_ss.add(files('hash-gcrypt.c', 'pbkdf-gcrypt.c')) - if 'CONFIG_GCRYPT_HMAC' in config_host - crypto_ss.add(files('hmac-gcrypt.c')) - else - crypto_ss.add(files('hmac-glib.c')) - endif + crypto_ss.add(files('hmac-gcrypt.c')) else crypto_ss.add(files('hash-glib.c', 'hmac-glib.c', 'pbkdf-stub.c')) endif diff --git a/crypto/tlscredsx509.c b/crypto/tlscredsx509.c index bc503bab55..d9d6f4421e 100644 --- a/crypto/tlscredsx509.c +++ b/crypto/tlscredsx509.c @@ -354,11 +354,9 @@ qcrypto_tls_creds_check_cert_pair(gnutls_x509_crt_t cert, reason = "The certificate has been revoked"; } -#ifndef GNUTLS_1_0_COMPAT if (status & GNUTLS_CERT_INSECURE_ALGORITHM) { reason = "The certificate uses an insecure algorithm"; } -#endif error_setg(errp, "Our own certificate %s failed validation against %s: %s", diff --git a/crypto/trace-events b/crypto/trace-events index 798b6067ab..bccd0bbf29 100644 --- a/crypto/trace-events +++ b/crypto/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # tlscreds.c qcrypto_tls_creds_load_dh(void *creds, const char *filename) "TLS creds load DH creds=%p filename=%s" diff --git a/default-configs/devices/ppc64-softmmu.mak b/default-configs/devices/ppc64-softmmu.mak index ae0841fa3a..cca52665d9 100644 --- a/default-configs/devices/ppc64-softmmu.mak +++ b/default-configs/devices/ppc64-softmmu.mak @@ -8,4 +8,3 @@ CONFIG_POWERNV=y # For pSeries CONFIG_PSERIES=y -CONFIG_NVDIMM=y diff --git a/docs/conf.py b/docs/conf.py index 00cf66ab54..42729e22bb 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -279,6 +279,7 @@ man_pages = [ ['Stefan Hajnoczi <stefanha@redhat.com>', 'Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>'], 1), ] +man_make_section_directory = False # -- Options for Texinfo output ------------------------------------------- diff --git a/docs/devel/lockcnt.txt b/docs/devel/lockcnt.txt index 2d85462fe3..a3fb3bc5d8 100644 --- a/docs/devel/lockcnt.txt +++ b/docs/devel/lockcnt.txt @@ -145,7 +145,7 @@ can also be more efficient in two ways: - on some platforms, one can implement QemuLockCnt to hold the lock and the mutex in a single word, making the fast path no more expensive than simply managing a counter using atomic operations (see - docs/devel/atomics.txt). This can be very helpful if concurrent access to + docs/devel/atomics.rst). This can be very helpful if concurrent access to the data structure is expected to be rare. diff --git a/docs/devel/secure-coding-practices.rst b/docs/devel/secure-coding-practices.rst index cbfc8af67e..0454cc527e 100644 --- a/docs/devel/secure-coding-practices.rst +++ b/docs/devel/secure-coding-practices.rst @@ -104,3 +104,12 @@ structures and only process the local copy. This prevents time-of-check-to-time-of-use (TOCTOU) race conditions that could cause QEMU to crash when a vCPU thread modifies guest RAM while device emulation is processing it. + +Use of null-co block drivers +---------------------------- + +The ``null-co`` block driver is designed for performance: its read accesses are +not initialized by default. In case this driver has to be used for security +research, it must be used with the ``read-zeroes=on`` option which fills read +buffers with zeroes. Security issues reported with the default +(``read-zeroes=off``) will be discarded. diff --git a/docs/devel/testing.rst b/docs/devel/testing.rst index 1da4c4e4c4..4e42392810 100644 --- a/docs/devel/testing.rst +++ b/docs/devel/testing.rst @@ -810,6 +810,32 @@ and hypothetical example follows: At test "tear down", ``avocado_qemu.Test`` handles all the QEMUMachines shutdown. +The ``avocado_qemu.LinuxTest`` base test class +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The ``avocado_qemu.LinuxTest`` is further specialization of the +``avocado_qemu.Test`` class, so it contains all the characteristics of +the later plus some extra features. + +First of all, this base class is intended for tests that need to +interact with a fully booted and operational Linux guest. At this +time, it uses a Fedora 31 guest image. The most basic example looks +like this: + +.. code:: + + from avocado_qemu import LinuxTest + + + class SomeTest(LinuxTest): + + def test(self): + self.launch_and_wait() + self.ssh_command('some_command_to_be_run_in_the_guest') + +Please refer to tests that use ``avocado_qemu.LinuxTest`` under +``tests/acceptance`` for more examples. + QEMUMachine ~~~~~~~~~~~ diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst index a1911f9403..57ee2bd94f 100644 --- a/docs/system/arm/aspeed.rst +++ b/docs/system/arm/aspeed.rst @@ -5,7 +5,7 @@ The QEMU Aspeed machines model BMCs of various OpenPOWER systems and Aspeed evaluation boards. They are based on different releases of the Aspeed SoC : the AST2400 integrating an ARM926EJ-S CPU (400MHz), the AST2500 with an ARM1176JZS CPU (800MHz) and more recently the AST2600 -with dual cores ARM Cortex A7 CPUs (1.2GHz). +with dual cores ARM Cortex-A7 CPUs (1.2GHz). The SoC comes with RAM, Gigabit ethernet, USB, SD/MMC, USB, SPI, I2C, etc. @@ -24,7 +24,7 @@ AST2500 SoC based machines : AST2600 SoC based machines : -- ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex A7) +- ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex-A7) - ``tacoma-bmc`` OpenPOWER Witherspoon POWER9 AST2600 BMC Supported devices diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index d3cf2d9cd7..ca011bd479 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -3,19 +3,19 @@ Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are designed to be used as Baseboard Management Controllers (BMCs) in various -servers. They all feature one or two ARM Cortex A9 CPU cores, as well as an +servers. They all feature one or two ARM Cortex-A9 CPU cores, as well as an assortment of peripherals targeted for either Enterprise or Data Center / Hyperscale applications. The former is a superset of the latter, so NPCM750 has all the peripherals of NPCM730 and more. .. _Nuvoton iBMC: https://www.nuvoton.com/products/cloud-computing/ibmc/ -The NPCM750 SoC has two Cortex A9 cores and is targeted for the Enterprise +The NPCM750 SoC has two Cortex-A9 cores and is targeted for the Enterprise segment. The following machines are based on this chip : - ``npcm750-evb`` Nuvoton NPCM750 Evaluation board -The NPCM730 SoC has two Cortex A9 cores and is targeted for Data Center and +The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and Hyperscale applications. The following machines are based on this chip : - ``quanta-gsj`` Quanta GSJ server BMC diff --git a/docs/system/arm/sabrelite.rst b/docs/system/arm/sabrelite.rst index 71713310e3..4ccb0560af 100644 --- a/docs/system/arm/sabrelite.rst +++ b/docs/system/arm/sabrelite.rst @@ -10,7 +10,7 @@ Supported devices The SABRE Lite machine supports the following devices: - * Up to 4 Cortex A9 cores + * Up to 4 Cortex-A9 cores * Generic Interrupt Controller * 1 Clock Controller Module * 1 System Reset Controller diff --git a/docs/system/removed-features.rst b/docs/system/removed-features.rst index 5a462ac568..1d22195b1d 100644 --- a/docs/system/removed-features.rst +++ b/docs/system/removed-features.rst @@ -249,6 +249,11 @@ Use ``migrate-set-parameters`` and ``info migrate-parameters`` instead. Use ``migrate-set-parameters`` instead. +``info cpustats`` (removed in 6.1) +'''''''''''''''''''''''''''''''''' + +This command didn't produce any output already. Removed with no replacement. + Guest Emulator ISAs ------------------- diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index a897a5a743..dddee92d6e 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -140,49 +140,30 @@ static void partsN(canonicalize)(FloatPartsN *p, float_status *status, * fraction; these bits will be removed. The exponent will be biased * by EXP_BIAS and must be bounded by [EXP_MAX-1, 0]. */ -static void partsN(uncanon)(FloatPartsN *p, float_status *s, - const FloatFmt *fmt) +static void partsN(uncanon_normal)(FloatPartsN *p, float_status *s, + const FloatFmt *fmt) { const int exp_max = fmt->exp_max; const int frac_shift = fmt->frac_shift; - const uint64_t frac_lsb = fmt->frac_lsb; - const uint64_t frac_lsbm1 = fmt->frac_lsbm1; const uint64_t round_mask = fmt->round_mask; - const uint64_t roundeven_mask = fmt->roundeven_mask; + const uint64_t frac_lsb = round_mask + 1; + const uint64_t frac_lsbm1 = round_mask ^ (round_mask >> 1); + const uint64_t roundeven_mask = round_mask | frac_lsb; uint64_t inc; - bool overflow_norm; + bool overflow_norm = false; int exp, flags = 0; - if (unlikely(p->cls != float_class_normal)) { - switch (p->cls) { - case float_class_zero: - p->exp = 0; - frac_clear(p); - return; - case float_class_inf: - g_assert(!fmt->arm_althp); - p->exp = fmt->exp_max; - frac_clear(p); - return; - case float_class_qnan: - case float_class_snan: - g_assert(!fmt->arm_althp); - p->exp = fmt->exp_max; - frac_shr(p, fmt->frac_shift); - return; - default: - break; - } - g_assert_not_reached(); - } - switch (s->float_rounding_mode) { case float_round_nearest_even: - overflow_norm = false; - inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 ? frac_lsbm1 : 0); + if (N > 64 && frac_lsb == 0) { + inc = ((p->frac_hi & 1) || (p->frac_lo & round_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } else { + inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } break; case float_round_ties_away: - overflow_norm = false; inc = frac_lsbm1; break; case float_round_to_zero: @@ -199,7 +180,13 @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s, break; case float_round_to_odd: overflow_norm = true; - inc = p->frac_lo & frac_lsb ? 0 : round_mask; + /* fall through */ + case float_round_to_odd_inf: + if (N > 64 && frac_lsb == 0) { + inc = p->frac_hi & 1 ? 0 : round_mask; + } else { + inc = p->frac_lo & frac_lsb ? 0 : round_mask; + } break; default: g_assert_not_reached(); @@ -214,8 +201,8 @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s, p->frac_hi |= DECOMPOSED_IMPLICIT_BIT; exp++; } + p->frac_lo &= ~round_mask; } - frac_shr(p, frac_shift); if (fmt->arm_althp) { /* ARM Alt HP eschews Inf and NaN for a wider exponent. */ @@ -224,18 +211,21 @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s, flags = float_flag_invalid; exp = exp_max; frac_allones(p); + p->frac_lo &= ~round_mask; } } else if (unlikely(exp >= exp_max)) { flags |= float_flag_overflow | float_flag_inexact; if (overflow_norm) { exp = exp_max - 1; frac_allones(p); + p->frac_lo &= ~round_mask; } else { p->cls = float_class_inf; exp = exp_max; frac_clear(p); } } + frac_shr(p, frac_shift); } else if (s->flush_to_zero) { flags |= float_flag_output_denormal; p->cls = float_class_zero; @@ -255,17 +245,29 @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s, /* Need to recompute round-to-even/round-to-odd. */ switch (s->float_rounding_mode) { case float_round_nearest_even: - inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 - ? frac_lsbm1 : 0); + if (N > 64 && frac_lsb == 0) { + inc = ((p->frac_hi & 1) || + (p->frac_lo & round_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } else { + inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } break; case float_round_to_odd: - inc = p->frac_lo & frac_lsb ? 0 : round_mask; + case float_round_to_odd_inf: + if (N > 64 && frac_lsb == 0) { + inc = p->frac_hi & 1 ? 0 : round_mask; + } else { + inc = p->frac_lo & frac_lsb ? 0 : round_mask; + } break; default: break; } flags |= float_flag_inexact; frac_addi(p, p, inc); + p->frac_lo &= ~round_mask; } exp = (p->frac_hi & DECOMPOSED_IMPLICIT_BIT) != 0; @@ -282,6 +284,35 @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s, float_raise(flags, s); } +static void partsN(uncanon)(FloatPartsN *p, float_status *s, + const FloatFmt *fmt) +{ + if (likely(p->cls == float_class_normal)) { + parts_uncanon_normal(p, s, fmt); + } else { + switch (p->cls) { + case float_class_zero: + p->exp = 0; + frac_clear(p); + return; + case float_class_inf: + g_assert(!fmt->arm_althp); + p->exp = fmt->exp_max; + frac_clear(p); + return; + case float_class_qnan: + case float_class_snan: + g_assert(!fmt->arm_althp); + p->exp = fmt->exp_max; + frac_shr(p, fmt->frac_shift); + return; + default: + break; + } + g_assert_not_reached(); + } +} + /* * Returns the result of adding or subtracting the values of the * floating-point values `a' and `b'. The operation is performed @@ -596,6 +627,246 @@ static FloatPartsN *partsN(div)(FloatPartsN *a, FloatPartsN *b, } /* + * Floating point remainder, per IEC/IEEE, or modulus. + */ +static FloatPartsN *partsN(modrem)(FloatPartsN *a, FloatPartsN *b, + uint64_t *mod_quot, float_status *s) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + + if (likely(ab_mask == float_cmask_normal)) { + frac_modrem(a, b, mod_quot); + return a; + } + + if (mod_quot) { + *mod_quot = 0; + } + + /* All the NaN cases */ + if (unlikely(ab_mask & float_cmask_anynan)) { + return parts_pick_nan(a, b, s); + } + + /* Inf % N; N % 0 */ + if (a->cls == float_class_inf || b->cls == float_class_zero) { + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); + return a; + } + + /* N % Inf; 0 % N */ + g_assert(b->cls == float_class_inf || a->cls == float_class_zero); + return a; +} + +/* + * Square Root + * + * The base algorithm is lifted from + * https://git.musl-libc.org/cgit/musl/tree/src/math/sqrtf.c + * https://git.musl-libc.org/cgit/musl/tree/src/math/sqrt.c + * https://git.musl-libc.org/cgit/musl/tree/src/math/sqrtl.c + * and is thus MIT licenced. + */ +static void partsN(sqrt)(FloatPartsN *a, float_status *status, + const FloatFmt *fmt) +{ + const uint32_t three32 = 3u << 30; + const uint64_t three64 = 3ull << 62; + uint32_t d32, m32, r32, s32, u32; /* 32-bit computation */ + uint64_t d64, m64, r64, s64, u64; /* 64-bit computation */ + uint64_t dh, dl, rh, rl, sh, sl, uh, ul; /* 128-bit computation */ + uint64_t d0h, d0l, d1h, d1l, d2h, d2l; + uint64_t discard; + bool exp_odd; + size_t index; + + if (unlikely(a->cls != float_class_normal)) { + switch (a->cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(a, status); + return; + case float_class_zero: + return; + case float_class_inf: + if (unlikely(a->sign)) { + goto d_nan; + } + return; + default: + g_assert_not_reached(); + } + } + + if (unlikely(a->sign)) { + goto d_nan; + } + + /* + * Argument reduction. + * x = 4^e frac; with integer e, and frac in [1, 4) + * m = frac fixed point at bit 62, since we're in base 4. + * If base-2 exponent is odd, exchange that for multiply by 2, + * which results in no shift. + */ + exp_odd = a->exp & 1; + index = extract64(a->frac_hi, 57, 6) | (!exp_odd << 6); + if (!exp_odd) { + frac_shr(a, 1); + } + + /* + * Approximate r ~= 1/sqrt(m) and s ~= sqrt(m) when m in [1, 4). + * + * Initial estimate: + * 7-bit lookup table (1-bit exponent and 6-bit significand). + * + * The relative error (e = r0*sqrt(m)-1) of a linear estimate + * (r0 = a*m + b) is |e| < 0.085955 ~ 0x1.6p-4 at best; + * a table lookup is faster and needs one less iteration. + * The 7-bit table gives |e| < 0x1.fdp-9. + * + * A Newton-Raphson iteration for r is + * s = m*r + * d = s*r + * u = 3 - d + * r = r*u/2 + * + * Fixed point representations: + * m, s, d, u, three are all 2.30; r is 0.32 + */ + m64 = a->frac_hi; + m32 = m64 >> 32; + + r32 = rsqrt_tab[index] << 16; + /* |r*sqrt(m) - 1| < 0x1.FDp-9 */ + + s32 = ((uint64_t)m32 * r32) >> 32; + d32 = ((uint64_t)s32 * r32) >> 32; + u32 = three32 - d32; + + if (N == 64) { + /* float64 or smaller */ + + r32 = ((uint64_t)r32 * u32) >> 31; + /* |r*sqrt(m) - 1| < 0x1.7Bp-16 */ + + s32 = ((uint64_t)m32 * r32) >> 32; + d32 = ((uint64_t)s32 * r32) >> 32; + u32 = three32 - d32; + + if (fmt->frac_size <= 23) { + /* float32 or smaller */ + + s32 = ((uint64_t)s32 * u32) >> 32; /* 3.29 */ + s32 = (s32 - 1) >> 6; /* 9.23 */ + /* s < sqrt(m) < s + 0x1.08p-23 */ + + /* compute nearest rounded result to 2.23 bits */ + uint32_t d0 = (m32 << 16) - s32 * s32; + uint32_t d1 = s32 - d0; + uint32_t d2 = d1 + s32 + 1; + s32 += d1 >> 31; + a->frac_hi = (uint64_t)s32 << (64 - 25); + + /* increment or decrement for inexact */ + if (d2 != 0) { + a->frac_hi += ((int32_t)(d1 ^ d2) < 0 ? -1 : 1); + } + goto done; + } + + /* float64 */ + + r64 = (uint64_t)r32 * u32 * 2; + /* |r*sqrt(m) - 1| < 0x1.37-p29; convert to 64-bit arithmetic */ + mul64To128(m64, r64, &s64, &discard); + mul64To128(s64, r64, &d64, &discard); + u64 = three64 - d64; + + mul64To128(s64, u64, &s64, &discard); /* 3.61 */ + s64 = (s64 - 2) >> 9; /* 12.52 */ + + /* Compute nearest rounded result */ + uint64_t d0 = (m64 << 42) - s64 * s64; + uint64_t d1 = s64 - d0; + uint64_t d2 = d1 + s64 + 1; + s64 += d1 >> 63; + a->frac_hi = s64 << (64 - 54); + + /* increment or decrement for inexact */ + if (d2 != 0) { + a->frac_hi += ((int64_t)(d1 ^ d2) < 0 ? -1 : 1); + } + goto done; + } + + r64 = (uint64_t)r32 * u32 * 2; + /* |r*sqrt(m) - 1| < 0x1.7Bp-16; convert to 64-bit arithmetic */ + + mul64To128(m64, r64, &s64, &discard); + mul64To128(s64, r64, &d64, &discard); + u64 = three64 - d64; + mul64To128(u64, r64, &r64, &discard); + r64 <<= 1; + /* |r*sqrt(m) - 1| < 0x1.a5p-31 */ + + mul64To128(m64, r64, &s64, &discard); + mul64To128(s64, r64, &d64, &discard); + u64 = three64 - d64; + mul64To128(u64, r64, &rh, &rl); + add128(rh, rl, rh, rl, &rh, &rl); + /* |r*sqrt(m) - 1| < 0x1.c001p-59; change to 128-bit arithmetic */ + + mul128To256(a->frac_hi, a->frac_lo, rh, rl, &sh, &sl, &discard, &discard); + mul128To256(sh, sl, rh, rl, &dh, &dl, &discard, &discard); + sub128(three64, 0, dh, dl, &uh, &ul); + mul128To256(uh, ul, sh, sl, &sh, &sl, &discard, &discard); /* 3.125 */ + /* -0x1p-116 < s - sqrt(m) < 0x3.8001p-125 */ + + sub128(sh, sl, 0, 4, &sh, &sl); + shift128Right(sh, sl, 13, &sh, &sl); /* 16.112 */ + /* s < sqrt(m) < s + 1ulp */ + + /* Compute nearest rounded result */ + mul64To128(sl, sl, &d0h, &d0l); + d0h += 2 * sh * sl; + sub128(a->frac_lo << 34, 0, d0h, d0l, &d0h, &d0l); + sub128(sh, sl, d0h, d0l, &d1h, &d1l); + add128(sh, sl, 0, 1, &d2h, &d2l); + add128(d2h, d2l, d1h, d1l, &d2h, &d2l); + add128(sh, sl, 0, d1h >> 63, &sh, &sl); + shift128Left(sh, sl, 128 - 114, &sh, &sl); + + /* increment or decrement for inexact */ + if (d2h | d2l) { + if ((int64_t)(d1h ^ d2h) < 0) { + sub128(sh, sl, 0, 1, &sh, &sl); + } else { + add128(sh, sl, 0, 1, &sh, &sl); + } + } + a->frac_lo = sl; + a->frac_hi = sh; + + done: + /* Convert back from base 4 to base 2. */ + a->exp >>= 1; + if (!(a->frac_hi & DECOMPOSED_IMPLICIT_BIT)) { + frac_add(a, a, a); + } else { + a->exp += 1; + } + return; + + d_nan: + float_raise(float_flag_invalid, status); + parts_default_nan(a, status); +} + +/* * Rounds the floating-point value `a' to an integer, and returns the * result as a floating-point value. The operation is performed * according to the IEC/IEEE Standard for Binary Floating-Point @@ -761,7 +1032,7 @@ static void partsN(round_to_int)(FloatPartsN *a, FloatRoundMode rmode, * the largest positive integer is returned. Otherwise, if the * conversion overflows, the largest integer with the same sign as `a' * is returned. -*/ + */ static int64_t partsN(float_to_sint)(FloatPartsN *p, FloatRoundMode rmode, int scale, int64_t min, int64_t max, float_status *s) @@ -815,3 +1086,407 @@ static int64_t partsN(float_to_sint)(FloatPartsN *p, FloatRoundMode rmode, float_raise(flags, s); return r; } + +/* + * Returns the result of converting the floating-point value `a' to + * the unsigned integer format. The conversion is performed according + * to the IEC/IEEE Standard for Binary Floating-Point + * Arithmetic---which means in particular that the conversion is + * rounded according to the current rounding mode. If `a' is a NaN, + * the largest unsigned integer is returned. Otherwise, if the + * conversion overflows, the largest unsigned integer is returned. If + * the 'a' is negative, the result is rounded and zero is returned; + * values that do not round to zero will raise the inexact exception + * flag. + */ +static uint64_t partsN(float_to_uint)(FloatPartsN *p, FloatRoundMode rmode, + int scale, uint64_t max, float_status *s) +{ + int flags = 0; + uint64_t r; + + switch (p->cls) { + case float_class_snan: + case float_class_qnan: + flags = float_flag_invalid; + r = max; + break; + + case float_class_inf: + flags = float_flag_invalid; + r = p->sign ? 0 : max; + break; + + case float_class_zero: + return 0; + + case float_class_normal: + /* TODO: N - 2 is frac_size for rounding; could use input fmt. */ + if (parts_round_to_int_normal(p, rmode, scale, N - 2)) { + flags = float_flag_inexact; + if (p->cls == float_class_zero) { + r = 0; + break; + } + } + + if (p->sign) { + flags = float_flag_invalid; + r = 0; + } else if (p->exp > DECOMPOSED_BINARY_POINT) { + flags = float_flag_invalid; + r = max; + } else { + r = p->frac_hi >> (DECOMPOSED_BINARY_POINT - p->exp); + if (r > max) { + flags = float_flag_invalid; + r = max; + } + } + break; + + default: + g_assert_not_reached(); + } + + float_raise(flags, s); + return r; +} + +/* + * Integer to float conversions + * + * Returns the result of converting the two's complement integer `a' + * to the floating-point format. The conversion is performed according + * to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ +static void partsN(sint_to_float)(FloatPartsN *p, int64_t a, + int scale, float_status *s) +{ + uint64_t f = a; + int shift; + + memset(p, 0, sizeof(*p)); + + if (a == 0) { + p->cls = float_class_zero; + return; + } + + p->cls = float_class_normal; + if (a < 0) { + f = -f; + p->sign = true; + } + shift = clz64(f); + scale = MIN(MAX(scale, -0x10000), 0x10000); + + p->exp = DECOMPOSED_BINARY_POINT - shift + scale; + p->frac_hi = f << shift; +} + +/* + * Unsigned Integer to float conversions + * + * Returns the result of converting the unsigned integer `a' to the + * floating-point format. The conversion is performed according to the + * IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ +static void partsN(uint_to_float)(FloatPartsN *p, uint64_t a, + int scale, float_status *status) +{ + memset(p, 0, sizeof(*p)); + + if (a == 0) { + p->cls = float_class_zero; + } else { + int shift = clz64(a); + scale = MIN(MAX(scale, -0x10000), 0x10000); + p->cls = float_class_normal; + p->exp = DECOMPOSED_BINARY_POINT - shift + scale; + p->frac_hi = a << shift; + } +} + +/* + * Float min/max. + */ +static FloatPartsN *partsN(minmax)(FloatPartsN *a, FloatPartsN *b, + float_status *s, int flags) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + int a_exp, b_exp, cmp; + + if (unlikely(ab_mask & float_cmask_anynan)) { + /* + * For minnum/maxnum, if one operand is a QNaN, and the other + * operand is numerical, then return numerical argument. + */ + if ((flags & minmax_isnum) + && !(ab_mask & float_cmask_snan) + && (ab_mask & ~float_cmask_qnan)) { + return is_nan(a->cls) ? b : a; + } + return parts_pick_nan(a, b, s); + } + + a_exp = a->exp; + b_exp = b->exp; + + if (unlikely(ab_mask != float_cmask_normal)) { + switch (a->cls) { + case float_class_normal: + break; + case float_class_inf: + a_exp = INT16_MAX; + break; + case float_class_zero: + a_exp = INT16_MIN; + break; + default: + g_assert_not_reached(); + break; + } + switch (b->cls) { + case float_class_normal: + break; + case float_class_inf: + b_exp = INT16_MAX; + break; + case float_class_zero: + b_exp = INT16_MIN; + break; + default: + g_assert_not_reached(); + break; + } + } + + /* Compare magnitudes. */ + cmp = a_exp - b_exp; + if (cmp == 0) { + cmp = frac_cmp(a, b); + } + + /* + * Take the sign into account. + * For ismag, only do this if the magnitudes are equal. + */ + if (!(flags & minmax_ismag) || cmp == 0) { + if (a->sign != b->sign) { + /* For differing signs, the negative operand is less. */ + cmp = a->sign ? -1 : 1; + } else if (a->sign) { + /* For two negative operands, invert the magnitude comparison. */ + cmp = -cmp; + } + } + + if (flags & minmax_ismin) { + cmp = -cmp; + } + return cmp < 0 ? b : a; +} + +/* + * Floating point compare + */ +static FloatRelation partsN(compare)(FloatPartsN *a, FloatPartsN *b, + float_status *s, bool is_quiet) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + int cmp; + + if (likely(ab_mask == float_cmask_normal)) { + if (a->sign != b->sign) { + goto a_sign; + } + if (a->exp != b->exp) { + cmp = a->exp < b->exp ? -1 : 1; + } else { + cmp = frac_cmp(a, b); + } + if (a->sign) { + cmp = -cmp; + } + return cmp; + } + + if (unlikely(ab_mask & float_cmask_anynan)) { + if (!is_quiet || (ab_mask & float_cmask_snan)) { + float_raise(float_flag_invalid, s); + } + return float_relation_unordered; + } + + if (ab_mask & float_cmask_zero) { + if (ab_mask == float_cmask_zero) { + return float_relation_equal; + } else if (a->cls == float_class_zero) { + goto b_sign; + } else { + goto a_sign; + } + } + + if (ab_mask == float_cmask_inf) { + if (a->sign == b->sign) { + return float_relation_equal; + } + } else if (b->cls == float_class_inf) { + goto b_sign; + } else { + g_assert(a->cls == float_class_inf); + } + + a_sign: + return a->sign ? float_relation_less : float_relation_greater; + b_sign: + return b->sign ? float_relation_greater : float_relation_less; +} + +/* + * Multiply A by 2 raised to the power N. + */ +static void partsN(scalbn)(FloatPartsN *a, int n, float_status *s) +{ + switch (a->cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(a, s); + break; + case float_class_zero: + case float_class_inf: + break; + case float_class_normal: + a->exp += MIN(MAX(n, -0x10000), 0x10000); + break; + default: + g_assert_not_reached(); + } +} + +/* + * Return log2(A) + */ +static void partsN(log2)(FloatPartsN *a, float_status *s, const FloatFmt *fmt) +{ + uint64_t a0, a1, r, t, ign; + FloatPartsN f; + int i, n, a_exp, f_exp; + + if (unlikely(a->cls != float_class_normal)) { + switch (a->cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(a, s); + return; + case float_class_zero: + /* log2(0) = -inf */ + a->cls = float_class_inf; + a->sign = 1; + return; + case float_class_inf: + if (unlikely(a->sign)) { + goto d_nan; + } + return; + default: + break; + } + g_assert_not_reached(); + } + if (unlikely(a->sign)) { + goto d_nan; + } + + /* TODO: This algorithm looses bits too quickly for float128. */ + g_assert(N == 64); + + a_exp = a->exp; + f_exp = -1; + + r = 0; + t = DECOMPOSED_IMPLICIT_BIT; + a0 = a->frac_hi; + a1 = 0; + + n = fmt->frac_size + 2; + if (unlikely(a_exp == -1)) { + /* + * When a_exp == -1, we're computing the log2 of a value [0.5,1.0). + * When the value is very close to 1.0, there are lots of 1's in + * the msb parts of the fraction. At the end, when we subtract + * this value from -1.0, we can see a catastrophic loss of precision, + * as 0x800..000 - 0x7ff..ffx becomes 0x000..00y, leaving only the + * bits of y in the final result. To minimize this, compute as many + * digits as we can. + * ??? This case needs another algorithm to avoid this. + */ + n = fmt->frac_size * 2 + 2; + /* Don't compute a value overlapping the sticky bit */ + n = MIN(n, 62); + } + + for (i = 0; i < n; i++) { + if (a1) { + mul128To256(a0, a1, a0, a1, &a0, &a1, &ign, &ign); + } else if (a0 & 0xffffffffull) { + mul64To128(a0, a0, &a0, &a1); + } else if (a0 & ~DECOMPOSED_IMPLICIT_BIT) { + a0 >>= 32; + a0 *= a0; + } else { + goto exact; + } + + if (a0 & DECOMPOSED_IMPLICIT_BIT) { + if (unlikely(a_exp == 0 && r == 0)) { + /* + * When a_exp == 0, we're computing the log2 of a value + * [1.0,2.0). When the value is very close to 1.0, there + * are lots of 0's in the msb parts of the fraction. + * We need to compute more digits to produce a correct + * result -- restart at the top of the fraction. + * ??? This is likely to lose precision quickly, as for + * float128; we may need another method. + */ + f_exp -= i; + t = r = DECOMPOSED_IMPLICIT_BIT; + i = 0; + } else { + r |= t; + } + } else { + add128(a0, a1, a0, a1, &a0, &a1); + } + t >>= 1; + } + + /* Set sticky for inexact. */ + r |= (a1 || a0 & ~DECOMPOSED_IMPLICIT_BIT); + + exact: + parts_sint_to_float(a, a_exp, 0, s); + if (r == 0) { + return; + } + + memset(&f, 0, sizeof(f)); + f.cls = float_class_normal; + f.frac_hi = r; + f.exp = f_exp - frac_normalize(&f); + + if (a_exp < 0) { + parts_sub_normal(a, &f); + } else if (a_exp > 0) { + parts_add_normal(a, &f); + } else { + *a = f; + } + return; + + d_nan: + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); +} diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index c895733e79..12467bb9bb 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -257,14 +257,6 @@ const floatx80 floatx80_infinity = make_floatx80_init(floatx80_infinity_high, floatx80_infinity_low); /*---------------------------------------------------------------------------- -| Internal canonical NaN format. -*----------------------------------------------------------------------------*/ -typedef struct { - bool sign; - uint64_t high, low; -} commonNaNT; - -/*---------------------------------------------------------------------------- | Returns 1 if the half-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. *----------------------------------------------------------------------------*/ @@ -380,46 +372,6 @@ bool float32_is_signaling_nan(float32 a_, float_status *status) } /*---------------------------------------------------------------------------- -| Returns the result of converting the single-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float32ToCommonNaN(float32 a, float_status *status) -{ - commonNaNT z; - - if (float32_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = float32_val(a) >> 31; - z.low = 0; - z.high = ((uint64_t)float32_val(a)) << 41; - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the single- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float32 commonNaNToFloat32(commonNaNT a, float_status *status) -{ - uint32_t mantissa = a.high >> 41; - - if (status->default_nan_mode) { - return float32_default_nan(status); - } - - if (mantissa) { - return make_float32( - (((uint32_t)a.sign) << 31) | 0x7F800000 | (a.high >> 41)); - } else { - return float32_default_nan(status); - } -} - -/*---------------------------------------------------------------------------- | Select which NaN to propagate for a two-input operation. | IEEE754 doesn't specify all the details of this, so the | algorithm is target-specific. @@ -690,62 +642,6 @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } /*---------------------------------------------------------------------------- -| Takes two single-precision floating-point values `a' and `b', one of which -| is a NaN, and returns the appropriate NaN result. If either `a' or `b' is a -| signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static float32 propagateFloat32NaN(float32 a, float32 b, float_status *status) -{ - bool aIsLargerSignificand; - uint32_t av, bv; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!float32_is_any_nan(a) - ? float_class_normal - : float32_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!float32_is_any_nan(b) - ? float_class_normal - : float32_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - av = float32_val(a); - bv = float32_val(b); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return float32_default_nan(status); - } - - if ((uint32_t)(av << 1) < (uint32_t)(bv << 1)) { - aIsLargerSignificand = 0; - } else if ((uint32_t)(bv << 1) < (uint32_t)(av << 1)) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (av < bv) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return float32_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return float32_silence_nan(a, status); - } - return a; - } -} - -/*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. *----------------------------------------------------------------------------*/ @@ -786,104 +682,6 @@ bool float64_is_signaling_nan(float64 a_, float_status *status) } /*---------------------------------------------------------------------------- -| Returns the result of converting the double-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float64ToCommonNaN(float64 a, float_status *status) -{ - commonNaNT z; - - if (float64_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = float64_val(a) >> 63; - z.low = 0; - z.high = float64_val(a) << 12; - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the double- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float64 commonNaNToFloat64(commonNaNT a, float_status *status) -{ - uint64_t mantissa = a.high >> 12; - - if (status->default_nan_mode) { - return float64_default_nan(status); - } - - if (mantissa) { - return make_float64( - (((uint64_t) a.sign) << 63) - | UINT64_C(0x7FF0000000000000) - | (a.high >> 12)); - } else { - return float64_default_nan(status); - } -} - -/*---------------------------------------------------------------------------- -| Takes two double-precision floating-point values `a' and `b', one of which -| is a NaN, and returns the appropriate NaN result. If either `a' or `b' is a -| signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static float64 propagateFloat64NaN(float64 a, float64 b, float_status *status) -{ - bool aIsLargerSignificand; - uint64_t av, bv; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!float64_is_any_nan(a) - ? float_class_normal - : float64_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!float64_is_any_nan(b) - ? float_class_normal - : float64_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - av = float64_val(a); - bv = float64_val(b); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return float64_default_nan(status); - } - - if ((uint64_t)(av << 1) < (uint64_t)(bv << 1)) { - aIsLargerSignificand = 0; - } else if ((uint64_t)(bv << 1) < (uint64_t)(av << 1)) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (av < bv) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return float64_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return float64_silence_nan(a, status); - } - return a; - } -} - -/*---------------------------------------------------------------------------- | Returns 1 if the extended double-precision floating-point value `a' is a | quiet NaN; otherwise returns 0. This slightly differs from the same | function for other types as floatx80 has an explicit bit. @@ -947,55 +745,6 @@ floatx80 floatx80_silence_nan(floatx80 a, float_status *status) } /*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point NaN `a' to the canonical NaN format. If `a' is a signaling NaN, the -| invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT floatx80ToCommonNaN(floatx80 a, float_status *status) -{ - floatx80 dflt; - commonNaNT z; - - if (floatx80_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - if (a.low >> 63) { - z.sign = a.high >> 15; - z.low = 0; - z.high = a.low << 1; - } else { - dflt = floatx80_default_nan(status); - z.sign = dflt.high >> 15; - z.low = 0; - z.high = dflt.low << 1; - } - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the extended -| double-precision floating-point format. -*----------------------------------------------------------------------------*/ - -static floatx80 commonNaNToFloatx80(commonNaNT a, float_status *status) -{ - floatx80 z; - - if (status->default_nan_mode) { - return floatx80_default_nan(status); - } - - if (a.high >> 1) { - z.low = UINT64_C(0x8000000000000000) | a.high >> 1; - z.high = (((uint16_t)a.sign) << 15) | 0x7FFF; - } else { - z = floatx80_default_nan(status); - } - return z; -} - -/*---------------------------------------------------------------------------- | Takes two extended double-precision floating-point values `a' and `b', one | of which is a NaN, and returns the appropriate NaN result. If either `a' or | `b' is a signaling NaN, the invalid exception is raised. @@ -1086,92 +835,3 @@ bool float128_is_signaling_nan(float128 a, float_status *status) } } } - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float128ToCommonNaN(float128 a, float_status *status) -{ - commonNaNT z; - - if (float128_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = a.high >> 63; - shortShift128Left(a.high, a.low, 16, &z.high, &z.low); - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the quadruple- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float128 commonNaNToFloat128(commonNaNT a, float_status *status) -{ - float128 z; - - if (status->default_nan_mode) { - return float128_default_nan(status); - } - - shift128Right(a.high, a.low, 16, &z.high, &z.low); - z.high |= (((uint64_t)a.sign) << 63) | UINT64_C(0x7FFF000000000000); - return z; -} - -/*---------------------------------------------------------------------------- -| Takes two quadruple-precision floating-point values `a' and `b', one of -| which is a NaN, and returns the appropriate NaN result. If either `a' or -| `b' is a signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static float128 propagateFloat128NaN(float128 a, float128 b, - float_status *status) -{ - bool aIsLargerSignificand; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!float128_is_any_nan(a) - ? float_class_normal - : float128_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!float128_is_any_nan(b) - ? float_class_normal - : float128_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return float128_default_nan(status); - } - - if (lt128(a.high << 1, a.low, b.high << 1, b.low)) { - aIsLargerSignificand = 0; - } else if (lt128(b.high << 1, b.low, a.high << 1, a.low)) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (a.high < b.high) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return float128_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return float128_silence_nan(a, status); - } - return a; - } -} diff --git a/fpu/softfloat.c b/fpu/softfloat.c index 0dc2203477..1cb162882b 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -401,60 +401,6 @@ float64_gen2(float64 xa, float64 xb, float_status *s, return soft(ua.s, ub.s, s); } -/*---------------------------------------------------------------------------- -| Returns the fraction bits of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint32_t extractFloat32Frac(float32 a) -{ - return float32_val(a) & 0x007FFFFF; -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline int extractFloat32Exp(float32 a) -{ - return (float32_val(a) >> 23) & 0xFF; -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline bool extractFloat32Sign(float32 a) -{ - return float32_val(a) >> 31; -} - -/*---------------------------------------------------------------------------- -| Returns the fraction bits of the double-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloat64Frac(float64 a) -{ - return float64_val(a) & UINT64_C(0x000FFFFFFFFFFFFF); -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the double-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline int extractFloat64Exp(float64 a) -{ - return (float64_val(a) >> 52) & 0x7FF; -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the double-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline bool extractFloat64Sign(float64 a) -{ - return float64_val(a) >> 63; -} - /* * Classify a floating point number. Everything above float_class_qnan * is a NaN so cls >= float_class_qnan is any NaN. @@ -482,6 +428,15 @@ enum { float_cmask_anynan = float_cmask_qnan | float_cmask_snan, }; +/* Flags for parts_minmax. */ +enum { + /* Set for minimum; clear for maximum. */ + minmax_ismin = 1, + /* Set for the IEEE 754-2008 minNum() and maxNum() operations. */ + minmax_isnum = 2, + /* Set for the IEEE 754-2008 minNumMag() and minNumMag() operations. */ + minmax_ismag = 4, +}; /* Simple helpers for checking if, or what kind of, NaN we have */ static inline __attribute__((unused)) bool is_nan(FloatClass c) @@ -554,9 +509,7 @@ typedef struct { * frac_size: the size of the fraction field * frac_shift: shift to normalise the fraction with DECOMPOSED_BINARY_POINT * The following are computed based the size of fraction - * frac_lsb: least significant bit of fraction - * frac_lsbm1: the bit below the least significant bit (for rounding) - * round_mask/roundeven_mask: masks used for rounding + * round_mask: bits below lsb which must be rounded * The following optional modifiers are available: * arm_althp: handle ARM Alternative Half Precision */ @@ -566,24 +519,21 @@ typedef struct { int exp_max; int frac_size; int frac_shift; - uint64_t frac_lsb; - uint64_t frac_lsbm1; - uint64_t round_mask; - uint64_t roundeven_mask; bool arm_althp; + uint64_t round_mask; } FloatFmt; /* Expand fields based on the size of exponent and fraction */ -#define FLOAT_PARAMS(E, F) \ - .exp_size = E, \ - .exp_bias = ((1 << E) - 1) >> 1, \ - .exp_max = (1 << E) - 1, \ - .frac_size = F, \ - .frac_shift = (-F - 1) & 63, \ - .frac_lsb = 1ull << ((-F - 1) & 63), \ - .frac_lsbm1 = 1ull << ((-F - 2) & 63), \ - .round_mask = (1ull << ((-F - 1) & 63)) - 1, \ - .roundeven_mask = (2ull << ((-F - 1) & 63)) - 1 +#define FLOAT_PARAMS_(E) \ + .exp_size = E, \ + .exp_bias = ((1 << E) - 1) >> 1, \ + .exp_max = (1 << E) - 1 + +#define FLOAT_PARAMS(E, F) \ + FLOAT_PARAMS_(E), \ + .frac_size = F, \ + .frac_shift = (-F - 1) & 63, \ + .round_mask = (1ull << ((-F - 1) & 63)) - 1 static const FloatFmt float16_params = { FLOAT_PARAMS(5, 10) @@ -610,6 +560,18 @@ static const FloatFmt float128_params = { FLOAT_PARAMS(15, 112) }; +#define FLOATX80_PARAMS(R) \ + FLOAT_PARAMS_(15), \ + .frac_size = R == 64 ? 63 : R, \ + .frac_shift = 0, \ + .round_mask = R == 64 ? -1 : (1ull << ((-R - 1) & 63)) - 1 + +static const FloatFmt floatx80_params[3] = { + [floatx80_precision_s] = { FLOATX80_PARAMS(23) }, + [floatx80_precision_d] = { FLOATX80_PARAMS(52) }, + [floatx80_precision_x] = { FLOATX80_PARAMS(64) }, +}; + /* Unpack a float to parts, but do not canonicalize. */ static void unpack_raw64(FloatParts64 *r, const FloatFmt *fmt, uint64_t raw) { @@ -644,6 +606,16 @@ static inline void float64_unpack_raw(FloatParts64 *p, float64 f) unpack_raw64(p, &float64_params, f); } +static void floatx80_unpack_raw(FloatParts128 *p, floatx80 f) +{ + *p = (FloatParts128) { + .cls = float_class_unclassified, + .sign = extract32(f.high, 15, 1), + .exp = extract32(f.high, 0, 15), + .frac_hi = f.low + }; +} + static void float128_unpack_raw(FloatParts128 *p, float128 f) { const int f_size = float128_params.frac_size - 64; @@ -755,6 +727,14 @@ static void parts128_canonicalize(FloatParts128 *p, float_status *status, #define parts_canonicalize(A, S, F) \ PARTS_GENERIC_64_128(canonicalize, A)(A, S, F) +static void parts64_uncanon_normal(FloatParts64 *p, float_status *status, + const FloatFmt *fmt); +static void parts128_uncanon_normal(FloatParts128 *p, float_status *status, + const FloatFmt *fmt); + +#define parts_uncanon_normal(A, S, F) \ + PARTS_GENERIC_64_128(uncanon_normal, A)(A, S, F) + static void parts64_uncanon(FloatParts64 *p, float_status *status, const FloatFmt *fmt); static void parts128_uncanon(FloatParts128 *p, float_status *status, @@ -811,6 +791,20 @@ static FloatParts128 *parts128_div(FloatParts128 *a, FloatParts128 *b, #define parts_div(A, B, S) \ PARTS_GENERIC_64_128(div, A)(A, B, S) +static FloatParts64 *parts64_modrem(FloatParts64 *a, FloatParts64 *b, + uint64_t *mod_quot, float_status *s); +static FloatParts128 *parts128_modrem(FloatParts128 *a, FloatParts128 *b, + uint64_t *mod_quot, float_status *s); + +#define parts_modrem(A, B, Q, S) \ + PARTS_GENERIC_64_128(modrem, A)(A, B, Q, S) + +static void parts64_sqrt(FloatParts64 *a, float_status *s, const FloatFmt *f); +static void parts128_sqrt(FloatParts128 *a, float_status *s, const FloatFmt *f); + +#define parts_sqrt(A, S, F) \ + PARTS_GENERIC_64_128(sqrt, A)(A, S, F) + static bool parts64_round_to_int_normal(FloatParts64 *a, FloatRoundMode rm, int scale, int frac_size); static bool parts128_round_to_int_normal(FloatParts128 *a, FloatRoundMode r, @@ -839,6 +833,60 @@ static int64_t parts128_float_to_sint(FloatParts128 *p, FloatRoundMode rmode, #define parts_float_to_sint(P, R, Z, MN, MX, S) \ PARTS_GENERIC_64_128(float_to_sint, P)(P, R, Z, MN, MX, S) +static uint64_t parts64_float_to_uint(FloatParts64 *p, FloatRoundMode rmode, + int scale, uint64_t max, + float_status *s); +static uint64_t parts128_float_to_uint(FloatParts128 *p, FloatRoundMode rmode, + int scale, uint64_t max, + float_status *s); + +#define parts_float_to_uint(P, R, Z, M, S) \ + PARTS_GENERIC_64_128(float_to_uint, P)(P, R, Z, M, S) + +static void parts64_sint_to_float(FloatParts64 *p, int64_t a, + int scale, float_status *s); +static void parts128_sint_to_float(FloatParts128 *p, int64_t a, + int scale, float_status *s); + +#define parts_sint_to_float(P, I, Z, S) \ + PARTS_GENERIC_64_128(sint_to_float, P)(P, I, Z, S) + +static void parts64_uint_to_float(FloatParts64 *p, uint64_t a, + int scale, float_status *s); +static void parts128_uint_to_float(FloatParts128 *p, uint64_t a, + int scale, float_status *s); + +#define parts_uint_to_float(P, I, Z, S) \ + PARTS_GENERIC_64_128(uint_to_float, P)(P, I, Z, S) + +static FloatParts64 *parts64_minmax(FloatParts64 *a, FloatParts64 *b, + float_status *s, int flags); +static FloatParts128 *parts128_minmax(FloatParts128 *a, FloatParts128 *b, + float_status *s, int flags); + +#define parts_minmax(A, B, S, F) \ + PARTS_GENERIC_64_128(minmax, A)(A, B, S, F) + +static int parts64_compare(FloatParts64 *a, FloatParts64 *b, + float_status *s, bool q); +static int parts128_compare(FloatParts128 *a, FloatParts128 *b, + float_status *s, bool q); + +#define parts_compare(A, B, S, Q) \ + PARTS_GENERIC_64_128(compare, A)(A, B, S, Q) + +static void parts64_scalbn(FloatParts64 *a, int n, float_status *s); +static void parts128_scalbn(FloatParts128 *a, int n, float_status *s); + +#define parts_scalbn(A, N, S) \ + PARTS_GENERIC_64_128(scalbn, A)(A, N, S) + +static void parts64_log2(FloatParts64 *a, float_status *s, const FloatFmt *f); +static void parts128_log2(FloatParts128 *a, float_status *s, const FloatFmt *f); + +#define parts_log2(A, S, F) \ + PARTS_GENERIC_64_128(log2, A)(A, S, F) + /* * Helper functions for softfloat-parts.c.inc, per-size operations. */ @@ -1135,6 +1183,186 @@ static int frac256_normalize(FloatParts256 *a) #define frac_normalize(A) FRAC_GENERIC_64_128_256(normalize, A)(A) +static void frac64_modrem(FloatParts64 *a, FloatParts64 *b, uint64_t *mod_quot) +{ + uint64_t a0, a1, b0, t0, t1, q, quot; + int exp_diff = a->exp - b->exp; + int shift; + + a0 = a->frac; + a1 = 0; + + if (exp_diff < -1) { + if (mod_quot) { + *mod_quot = 0; + } + return; + } + if (exp_diff == -1) { + a0 >>= 1; + exp_diff = 0; + } + + b0 = b->frac; + quot = q = b0 <= a0; + if (q) { + a0 -= b0; + } + + exp_diff -= 64; + while (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 2 ? q - 2 : 0; + mul64To128(b0, q, &t0, &t1); + sub128(a0, a1, t0, t1, &a0, &a1); + shortShift128Left(a0, a1, 62, &a0, &a1); + exp_diff -= 62; + quot = (quot << 62) + q; + } + + exp_diff += 64; + if (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 2 ? (q - 2) >> (64 - exp_diff) : 0; + mul64To128(b0, q << (64 - exp_diff), &t0, &t1); + sub128(a0, a1, t0, t1, &a0, &a1); + shortShift128Left(0, b0, 64 - exp_diff, &t0, &t1); + while (le128(t0, t1, a0, a1)) { + ++q; + sub128(a0, a1, t0, t1, &a0, &a1); + } + quot = (exp_diff < 64 ? quot << exp_diff : 0) + q; + } else { + t0 = b0; + t1 = 0; + } + + if (mod_quot) { + *mod_quot = quot; + } else { + sub128(t0, t1, a0, a1, &t0, &t1); + if (lt128(t0, t1, a0, a1) || + (eq128(t0, t1, a0, a1) && (q & 1))) { + a0 = t0; + a1 = t1; + a->sign = !a->sign; + } + } + + if (likely(a0)) { + shift = clz64(a0); + shortShift128Left(a0, a1, shift, &a0, &a1); + } else if (likely(a1)) { + shift = clz64(a1); + a0 = a1 << shift; + a1 = 0; + shift += 64; + } else { + a->cls = float_class_zero; + return; + } + + a->exp = b->exp + exp_diff - shift; + a->frac = a0 | (a1 != 0); +} + +static void frac128_modrem(FloatParts128 *a, FloatParts128 *b, + uint64_t *mod_quot) +{ + uint64_t a0, a1, a2, b0, b1, t0, t1, t2, q, quot; + int exp_diff = a->exp - b->exp; + int shift; + + a0 = a->frac_hi; + a1 = a->frac_lo; + a2 = 0; + + if (exp_diff < -1) { + if (mod_quot) { + *mod_quot = 0; + } + return; + } + if (exp_diff == -1) { + shift128Right(a0, a1, 1, &a0, &a1); + exp_diff = 0; + } + + b0 = b->frac_hi; + b1 = b->frac_lo; + + quot = q = le128(b0, b1, a0, a1); + if (q) { + sub128(a0, a1, b0, b1, &a0, &a1); + } + + exp_diff -= 64; + while (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 4 ? q - 4 : 0; + mul128By64To192(b0, b1, q, &t0, &t1, &t2); + sub192(a0, a1, a2, t0, t1, t2, &a0, &a1, &a2); + shortShift192Left(a0, a1, a2, 61, &a0, &a1, &a2); + exp_diff -= 61; + quot = (quot << 61) + q; + } + + exp_diff += 64; + if (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 4 ? (q - 4) >> (64 - exp_diff) : 0; + mul128By64To192(b0, b1, q << (64 - exp_diff), &t0, &t1, &t2); + sub192(a0, a1, a2, t0, t1, t2, &a0, &a1, &a2); + shortShift192Left(0, b0, b1, 64 - exp_diff, &t0, &t1, &t2); + while (le192(t0, t1, t2, a0, a1, a2)) { + ++q; + sub192(a0, a1, a2, t0, t1, t2, &a0, &a1, &a2); + } + quot = (exp_diff < 64 ? quot << exp_diff : 0) + q; + } else { + t0 = b0; + t1 = b1; + t2 = 0; + } + + if (mod_quot) { + *mod_quot = quot; + } else { + sub192(t0, t1, t2, a0, a1, a2, &t0, &t1, &t2); + if (lt192(t0, t1, t2, a0, a1, a2) || + (eq192(t0, t1, t2, a0, a1, a2) && (q & 1))) { + a0 = t0; + a1 = t1; + a2 = t2; + a->sign = !a->sign; + } + } + + if (likely(a0)) { + shift = clz64(a0); + shortShift192Left(a0, a1, a2, shift, &a0, &a1, &a2); + } else if (likely(a1)) { + shift = clz64(a1); + shortShift128Left(a1, a2, shift, &a0, &a1); + a2 = 0; + shift += 64; + } else if (likely(a2)) { + shift = clz64(a2); + a0 = a2 << shift; + a1 = a2 = 0; + shift += 128; + } else { + a->cls = float_class_zero; + return; + } + + a->exp = b->exp + exp_diff - shift; + a->frac_hi = a0; + a->frac_lo = a1 | (a2 != 0); +} + +#define frac_modrem(A, B, Q) FRAC_GENERIC_64_128(modrem, A)(A, B, Q) + static void frac64_shl(FloatParts64 *a, int c) { a->frac <<= c; @@ -1329,6 +1557,30 @@ static void frac128_widen(FloatParts256 *r, FloatParts128 *a) #define frac_widen(A, B) FRAC_GENERIC_64_128(widen, B)(A, B) +/* + * Reciprocal sqrt table. 1 bit of exponent, 6-bits of mantessa. + * From https://git.musl-libc.org/cgit/musl/tree/src/math/sqrt_data.c + * and thus MIT licenced. + */ +static const uint16_t rsqrt_tab[128] = { + 0xb451, 0xb2f0, 0xb196, 0xb044, 0xaef9, 0xadb6, 0xac79, 0xab43, + 0xaa14, 0xa8eb, 0xa7c8, 0xa6aa, 0xa592, 0xa480, 0xa373, 0xa26b, + 0xa168, 0xa06a, 0x9f70, 0x9e7b, 0x9d8a, 0x9c9d, 0x9bb5, 0x9ad1, + 0x99f0, 0x9913, 0x983a, 0x9765, 0x9693, 0x95c4, 0x94f8, 0x9430, + 0x936b, 0x92a9, 0x91ea, 0x912e, 0x9075, 0x8fbe, 0x8f0a, 0x8e59, + 0x8daa, 0x8cfe, 0x8c54, 0x8bac, 0x8b07, 0x8a64, 0x89c4, 0x8925, + 0x8889, 0x87ee, 0x8756, 0x86c0, 0x862b, 0x8599, 0x8508, 0x8479, + 0x83ec, 0x8361, 0x82d8, 0x8250, 0x81c9, 0x8145, 0x80c2, 0x8040, + 0xff02, 0xfd0e, 0xfb25, 0xf947, 0xf773, 0xf5aa, 0xf3ea, 0xf234, + 0xf087, 0xeee3, 0xed47, 0xebb3, 0xea27, 0xe8a3, 0xe727, 0xe5b2, + 0xe443, 0xe2dc, 0xe17a, 0xe020, 0xdecb, 0xdd7d, 0xdc34, 0xdaf1, + 0xd9b3, 0xd87b, 0xd748, 0xd61a, 0xd4f1, 0xd3cd, 0xd2ad, 0xd192, + 0xd07b, 0xcf69, 0xce5b, 0xcd51, 0xcc4a, 0xcb48, 0xca4a, 0xc94f, + 0xc858, 0xc764, 0xc674, 0xc587, 0xc49d, 0xc3b7, 0xc2d4, 0xc1f4, + 0xc116, 0xc03c, 0xbf65, 0xbe90, 0xbdbe, 0xbcef, 0xbc23, 0xbb59, + 0xba91, 0xb9cc, 0xb90a, 0xb84a, 0xb78c, 0xb6d0, 0xb617, 0xb560, +}; + #define partsN(NAME) glue(glue(glue(parts,N),_),NAME) #define FloatPartsN glue(FloatParts,N) #define FloatPartsW glue(FloatParts,W) @@ -1446,6 +1698,92 @@ static float128 float128_round_pack_canonical(FloatParts128 *p, return float128_pack_raw(p); } +/* Returns false if the encoding is invalid. */ +static bool floatx80_unpack_canonical(FloatParts128 *p, floatx80 f, + float_status *s) +{ + /* Ensure rounding precision is set before beginning. */ + switch (s->floatx80_rounding_precision) { + case floatx80_precision_x: + case floatx80_precision_d: + case floatx80_precision_s: + break; + default: + g_assert_not_reached(); + } + + if (unlikely(floatx80_invalid_encoding(f))) { + float_raise(float_flag_invalid, s); + return false; + } + + floatx80_unpack_raw(p, f); + + if (likely(p->exp != floatx80_params[floatx80_precision_x].exp_max)) { + parts_canonicalize(p, s, &floatx80_params[floatx80_precision_x]); + } else { + /* The explicit integer bit is ignored, after invalid checks. */ + p->frac_hi &= MAKE_64BIT_MASK(0, 63); + p->cls = (p->frac_hi == 0 ? float_class_inf + : parts_is_snan_frac(p->frac_hi, s) + ? float_class_snan : float_class_qnan); + } + return true; +} + +static floatx80 floatx80_round_pack_canonical(FloatParts128 *p, + float_status *s) +{ + const FloatFmt *fmt = &floatx80_params[s->floatx80_rounding_precision]; + uint64_t frac; + int exp; + + switch (p->cls) { + case float_class_normal: + if (s->floatx80_rounding_precision == floatx80_precision_x) { + parts_uncanon_normal(p, s, fmt); + frac = p->frac_hi; + exp = p->exp; + } else { + FloatParts64 p64; + + p64.sign = p->sign; + p64.exp = p->exp; + frac_truncjam(&p64, p); + parts_uncanon_normal(&p64, s, fmt); + frac = p64.frac; + exp = p64.exp; + } + if (exp != fmt->exp_max) { + break; + } + /* rounded to inf -- fall through to set frac correctly */ + + case float_class_inf: + /* x86 and m68k differ in the setting of the integer bit. */ + frac = floatx80_infinity_low; + exp = fmt->exp_max; + break; + + case float_class_zero: + frac = 0; + exp = 0; + break; + + case float_class_snan: + case float_class_qnan: + /* NaNs have the integer bit set. */ + frac = p->frac_hi | (1ull << 63); + exp = fmt->exp_max; + break; + + default: + g_assert_not_reached(); + } + + return packFloatx80(p->sign, exp, frac); +} + /* * Addition and subtraction */ @@ -1635,6 +1973,30 @@ float128 float128_sub(float128 a, float128 b, float_status *status) return float128_addsub(a, b, status, true); } +static floatx80 QEMU_FLATTEN +floatx80_addsub(floatx80 a, floatx80 b, float_status *status, bool subtract) +{ + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_addsub(&pa, &pb, status, subtract); + return floatx80_round_pack_canonical(pr, status); +} + +floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status) +{ + return floatx80_addsub(a, b, status, false); +} + +floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status) +{ + return floatx80_addsub(a, b, status, true); +} + /* * Multiplication */ @@ -1722,6 +2084,20 @@ float128_mul(float128 a, float128 b, float_status *status) return float128_round_pack_canonical(pr, status); } +floatx80 QEMU_FLATTEN +floatx80_mul(floatx80 a, floatx80 b, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_mul(&pa, &pb, status); + return floatx80_round_pack_canonical(pr, status); +} + /* * Fused multiply-add */ @@ -2058,6 +2434,92 @@ float128_div(float128 a, float128 b, float_status *status) return float128_round_pack_canonical(pr, status); } +floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_div(&pa, &pb, status); + return floatx80_round_pack_canonical(pr, status); +} + +/* + * Remainder + */ + +float32 float32_rem(float32 a, float32 b, float_status *status) +{ + FloatParts64 pa, pb, *pr; + + float32_unpack_canonical(&pa, a, status); + float32_unpack_canonical(&pb, b, status); + pr = parts_modrem(&pa, &pb, NULL, status); + + return float32_round_pack_canonical(pr, status); +} + +float64 float64_rem(float64 a, float64 b, float_status *status) +{ + FloatParts64 pa, pb, *pr; + + float64_unpack_canonical(&pa, a, status); + float64_unpack_canonical(&pb, b, status); + pr = parts_modrem(&pa, &pb, NULL, status); + + return float64_round_pack_canonical(pr, status); +} + +float128 float128_rem(float128 a, float128 b, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + float128_unpack_canonical(&pa, a, status); + float128_unpack_canonical(&pb, b, status); + pr = parts_modrem(&pa, &pb, NULL, status); + + return float128_round_pack_canonical(pr, status); +} + +/* + * Returns the remainder of the extended double-precision floating-point value + * `a' with respect to the corresponding value `b'. + * If 'mod' is false, the operation is performed according to the IEC/IEEE + * Standard for Binary Floating-Point Arithmetic. If 'mod' is true, return + * the remainder based on truncating the quotient toward zero instead and + * *quotient is set to the low 64 bits of the absolute value of the integer + * quotient. + */ +floatx80 floatx80_modrem(floatx80 a, floatx80 b, bool mod, + uint64_t *quotient, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + *quotient = 0; + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + pr = parts_modrem(&pa, &pb, mod ? quotient : NULL, status); + + return floatx80_round_pack_canonical(pr, status); +} + +floatx80 floatx80_rem(floatx80 a, floatx80 b, float_status *status) +{ + uint64_t quotient; + return floatx80_modrem(a, b, false, "ient, status); +} + +floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status) +{ + uint64_t quotient; + return floatx80_modrem(a, b, true, "ient, status); +} + /* * Float to Float conversions * @@ -2312,6 +2774,73 @@ float128 float64_to_float128(float64 a, float_status *s) return float128_round_pack_canonical(&p128, s); } +float32 floatx80_to_float32(floatx80 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + if (floatx80_unpack_canonical(&p128, a, s)) { + parts_float_to_float_narrow(&p64, &p128, s); + } else { + parts_default_nan(&p64, s); + } + return float32_round_pack_canonical(&p64, s); +} + +float64 floatx80_to_float64(floatx80 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + if (floatx80_unpack_canonical(&p128, a, s)) { + parts_float_to_float_narrow(&p64, &p128, s); + } else { + parts_default_nan(&p64, s); + } + return float64_round_pack_canonical(&p64, s); +} + +float128 floatx80_to_float128(floatx80 a, float_status *s) +{ + FloatParts128 p; + + if (floatx80_unpack_canonical(&p, a, s)) { + parts_float_to_float(&p, s); + } else { + parts_default_nan(&p, s); + } + return float128_round_pack_canonical(&p, s); +} + +floatx80 float32_to_floatx80(float32 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float32_unpack_canonical(&p64, a, s); + parts_float_to_float_widen(&p128, &p64, s); + return floatx80_round_pack_canonical(&p128, s); +} + +floatx80 float64_to_floatx80(float64 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float64_unpack_canonical(&p64, a, s); + parts_float_to_float_widen(&p128, &p64, s); + return floatx80_round_pack_canonical(&p128, s); +} + +floatx80 float128_to_floatx80(float128 a, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return floatx80_round_pack_canonical(&p, s); +} + /* * Round to integral value */ @@ -2361,6 +2890,19 @@ float128 float128_round_to_int(float128 a, float_status *s) return float128_round_pack_canonical(&p, s); } +floatx80 floatx80_round_to_int(floatx80 a, float_status *status) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, status)) { + return floatx80_default_nan(status); + } + + parts_round_to_int(&p, status->float_rounding_mode, 0, status, + &floatx80_params[status->floatx80_rounding_precision]); + return floatx80_round_pack_canonical(&p, status); +} + /* * Floating-point to signed integer conversions */ @@ -2500,6 +3042,28 @@ static int64_t float128_to_int64_scalbn(float128 a, FloatRoundMode rmode, return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); } +static int32_t floatx80_to_int32_scalbn(floatx80 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + parts_default_nan(&p, s); + } + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); +} + +static int64_t floatx80_to_int64_scalbn(floatx80 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + parts_default_nan(&p, s); + } + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); +} + int8_t float16_to_int8(float16 a, float_status *s) { return float16_to_int8_scalbn(a, s->float_rounding_mode, 0, s); @@ -2560,6 +3124,16 @@ int64_t float128_to_int64(float128 a, float_status *s) return float128_to_int64_scalbn(a, s->float_rounding_mode, 0, s); } +int32_t floatx80_to_int32(floatx80 a, float_status *s) +{ + return floatx80_to_int32_scalbn(a, s->float_rounding_mode, 0, s); +} + +int64_t floatx80_to_int64(floatx80 a, float_status *s) +{ + return floatx80_to_int64_scalbn(a, s->float_rounding_mode, 0, s); +} + int16_t float16_to_int16_round_to_zero(float16 a, float_status *s) { return float16_to_int16_scalbn(a, float_round_to_zero, 0, s); @@ -2615,6 +3189,16 @@ int64_t float128_to_int64_round_to_zero(float128 a, float_status *s) return float128_to_int64_scalbn(a, float_round_to_zero, 0, s); } +int32_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *s) +{ + return floatx80_to_int32_scalbn(a, float_round_to_zero, 0, s); +} + +int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *s) +{ + return floatx80_to_int64_scalbn(a, float_round_to_zero, 0, s); +} + int16_t bfloat16_to_int16(bfloat16 a, float_status *s) { return bfloat16_to_int16_scalbn(a, s->float_rounding_mode, 0, s); @@ -2646,80 +3230,16 @@ int64_t bfloat16_to_int64_round_to_zero(bfloat16 a, float_status *s) } /* - * Returns the result of converting the floating-point value `a' to - * the unsigned integer format. The conversion is performed according - * to the IEC/IEEE Standard for Binary Floating-Point - * Arithmetic---which means in particular that the conversion is - * rounded according to the current rounding mode. If `a' is a NaN, - * the largest unsigned integer is returned. Otherwise, if the - * conversion overflows, the largest unsigned integer is returned. If - * the 'a' is negative, the result is rounded and zero is returned; - * values that do not round to zero will raise the inexact exception - * flag. + * Floating-point to unsigned integer conversions */ -static uint64_t round_to_uint_and_pack(FloatParts64 p, FloatRoundMode rmode, - int scale, uint64_t max, - float_status *s) -{ - int flags = 0; - uint64_t r; - - switch (p.cls) { - case float_class_snan: - case float_class_qnan: - flags = float_flag_invalid; - r = max; - break; - - case float_class_inf: - flags = float_flag_invalid; - r = p.sign ? 0 : max; - break; - - case float_class_zero: - return 0; - - case float_class_normal: - /* TODO: 62 = N - 2, frac_size for rounding */ - if (parts_round_to_int_normal(&p, rmode, scale, 62)) { - flags = float_flag_inexact; - if (p.cls == float_class_zero) { - r = 0; - break; - } - } - - if (p.sign) { - flags = float_flag_invalid; - r = 0; - } else if (p.exp > DECOMPOSED_BINARY_POINT) { - flags = float_flag_invalid; - r = max; - } else { - r = p.frac >> (DECOMPOSED_BINARY_POINT - p.exp); - if (r > max) { - flags = float_flag_invalid; - r = max; - } - } - break; - - default: - g_assert_not_reached(); - } - - float_raise(flags, s); - return r; -} - uint8_t float16_to_uint8_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { FloatParts64 p; float16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT8_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT8_MAX, s); } uint16_t float16_to_uint16_scalbn(float16 a, FloatRoundMode rmode, int scale, @@ -2728,7 +3248,7 @@ uint16_t float16_to_uint16_scalbn(float16 a, FloatRoundMode rmode, int scale, FloatParts64 p; float16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); } uint32_t float16_to_uint32_scalbn(float16 a, FloatRoundMode rmode, int scale, @@ -2737,7 +3257,7 @@ uint32_t float16_to_uint32_scalbn(float16 a, FloatRoundMode rmode, int scale, FloatParts64 p; float16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); } uint64_t float16_to_uint64_scalbn(float16 a, FloatRoundMode rmode, int scale, @@ -2746,7 +3266,7 @@ uint64_t float16_to_uint64_scalbn(float16 a, FloatRoundMode rmode, int scale, FloatParts64 p; float16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); } uint16_t float32_to_uint16_scalbn(float32 a, FloatRoundMode rmode, int scale, @@ -2755,7 +3275,7 @@ uint16_t float32_to_uint16_scalbn(float32 a, FloatRoundMode rmode, int scale, FloatParts64 p; float32_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); } uint32_t float32_to_uint32_scalbn(float32 a, FloatRoundMode rmode, int scale, @@ -2764,7 +3284,7 @@ uint32_t float32_to_uint32_scalbn(float32 a, FloatRoundMode rmode, int scale, FloatParts64 p; float32_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); } uint64_t float32_to_uint64_scalbn(float32 a, FloatRoundMode rmode, int scale, @@ -2773,7 +3293,7 @@ uint64_t float32_to_uint64_scalbn(float32 a, FloatRoundMode rmode, int scale, FloatParts64 p; float32_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); } uint16_t float64_to_uint16_scalbn(float64 a, FloatRoundMode rmode, int scale, @@ -2782,7 +3302,7 @@ uint16_t float64_to_uint16_scalbn(float64 a, FloatRoundMode rmode, int scale, FloatParts64 p; float64_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); } uint32_t float64_to_uint32_scalbn(float64 a, FloatRoundMode rmode, int scale, @@ -2791,7 +3311,7 @@ uint32_t float64_to_uint32_scalbn(float64 a, FloatRoundMode rmode, int scale, FloatParts64 p; float64_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); } uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale, @@ -2800,7 +3320,52 @@ uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale, FloatParts64 p; float64_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); +} + +uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); +} + +uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); +} + +uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); +} + +static uint32_t float128_to_uint32_scalbn(float128 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); +} + +static uint64_t float128_to_uint64_scalbn(float128 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); } uint8_t float16_to_uint8(float16 a, float_status *s) @@ -2853,6 +3418,16 @@ uint64_t float64_to_uint64(float64 a, float_status *s) return float64_to_uint64_scalbn(a, s->float_rounding_mode, 0, s); } +uint32_t float128_to_uint32(float128 a, float_status *s) +{ + return float128_to_uint32_scalbn(a, s->float_rounding_mode, 0, s); +} + +uint64_t float128_to_uint64(float128 a, float_status *s) +{ + return float128_to_uint64_scalbn(a, s->float_rounding_mode, 0, s); +} + uint16_t float16_to_uint16_round_to_zero(float16 a, float_status *s) { return float16_to_uint16_scalbn(a, float_round_to_zero, 0, s); @@ -2898,36 +3473,14 @@ uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *s) return float64_to_uint64_scalbn(a, float_round_to_zero, 0, s); } -/* - * Returns the result of converting the bfloat16 value `a' to - * the unsigned integer format. - */ - -uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode, - int scale, float_status *s) -{ - FloatParts64 p; - - bfloat16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT16_MAX, s); -} - -uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode, - int scale, float_status *s) +uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *s) { - FloatParts64 p; - - bfloat16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT32_MAX, s); + return float128_to_uint32_scalbn(a, float_round_to_zero, 0, s); } -uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode, - int scale, float_status *s) +uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *s) { - FloatParts64 p; - - bfloat16_unpack_canonical(&p, a, s); - return round_to_uint_and_pack(p, rmode, scale, UINT64_MAX, s); + return float128_to_uint64_scalbn(a, float_round_to_zero, 0, s); } uint16_t bfloat16_to_uint16(bfloat16 a, float_status *s) @@ -2961,42 +3514,15 @@ uint64_t bfloat16_to_uint64_round_to_zero(bfloat16 a, float_status *s) } /* - * Integer to float conversions - * - * Returns the result of converting the two's complement integer `a' - * to the floating-point format. The conversion is performed according - * to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. + * Signed integer to floating-point conversions */ -static FloatParts64 int_to_float(int64_t a, int scale, float_status *status) -{ - FloatParts64 r = { .sign = false }; - - if (a == 0) { - r.cls = float_class_zero; - } else { - uint64_t f = a; - int shift; - - r.cls = float_class_normal; - if (a < 0) { - f = -f; - r.sign = true; - } - shift = clz64(f); - scale = MIN(MAX(scale, -0x10000), 0x10000); - - r.exp = DECOMPOSED_BINARY_POINT - shift + scale; - r.frac = f << shift; - } - - return r; -} - float16 int64_to_float16_scalbn(int64_t a, int scale, float_status *status) { - FloatParts64 pa = int_to_float(a, scale, status); - return float16_round_pack_canonical(&pa, status); + FloatParts64 p; + + parts_sint_to_float(&p, a, scale, status); + return float16_round_pack_canonical(&p, status); } float16 int32_to_float16_scalbn(int32_t a, int scale, float_status *status) @@ -3031,8 +3557,17 @@ float16 int8_to_float16(int8_t a, float_status *status) float32 int64_to_float32_scalbn(int64_t a, int scale, float_status *status) { - FloatParts64 pa = int_to_float(a, scale, status); - return float32_round_pack_canonical(&pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float32 ur; + ur.h = a; + return ur.s; + } + + parts64_sint_to_float(&p, a, scale, status); + return float32_round_pack_canonical(&p, status); } float32 int32_to_float32_scalbn(int32_t a, int scale, float_status *status) @@ -3062,8 +3597,17 @@ float32 int16_to_float32(int16_t a, float_status *status) float64 int64_to_float64_scalbn(int64_t a, int scale, float_status *status) { - FloatParts64 pa = int_to_float(a, scale, status); - return float64_round_pack_canonical(&pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float64 ur; + ur.h = a; + return ur.s; + } + + parts_sint_to_float(&p, a, scale, status); + return float64_round_pack_canonical(&p, status); } float64 int32_to_float64_scalbn(int32_t a, int scale, float_status *status) @@ -3091,15 +3635,12 @@ float64 int16_to_float64(int16_t a, float_status *status) return int64_to_float64_scalbn(a, 0, status); } -/* - * Returns the result of converting the two's complement integer `a' - * to the bfloat16 format. - */ - bfloat16 int64_to_bfloat16_scalbn(int64_t a, int scale, float_status *status) { - FloatParts64 pa = int_to_float(a, scale, status); - return bfloat16_round_pack_canonical(&pa, status); + FloatParts64 p; + + parts_sint_to_float(&p, a, scale, status); + return bfloat16_round_pack_canonical(&p, status); } bfloat16 int32_to_bfloat16_scalbn(int32_t a, int scale, float_status *status) @@ -3127,36 +3668,42 @@ bfloat16 int16_to_bfloat16(int16_t a, float_status *status) return int64_to_bfloat16_scalbn(a, 0, status); } -/* - * Unsigned Integer to float conversions - * - * Returns the result of converting the unsigned integer `a' to the - * floating-point format. The conversion is performed according to the - * IEC/IEEE Standard for Binary Floating-Point Arithmetic. - */ +float128 int64_to_float128(int64_t a, float_status *status) +{ + FloatParts128 p; -static FloatParts64 uint_to_float(uint64_t a, int scale, float_status *status) + parts_sint_to_float(&p, a, 0, status); + return float128_round_pack_canonical(&p, status); +} + +float128 int32_to_float128(int32_t a, float_status *status) { - FloatParts64 r = { .sign = false }; - int shift; + return int64_to_float128(a, status); +} - if (a == 0) { - r.cls = float_class_zero; - } else { - scale = MIN(MAX(scale, -0x10000), 0x10000); - shift = clz64(a); - r.cls = float_class_normal; - r.exp = DECOMPOSED_BINARY_POINT - shift + scale; - r.frac = a << shift; - } +floatx80 int64_to_floatx80(int64_t a, float_status *status) +{ + FloatParts128 p; - return r; + parts_sint_to_float(&p, a, 0, status); + return floatx80_round_pack_canonical(&p, status); +} + +floatx80 int32_to_floatx80(int32_t a, float_status *status) +{ + return int64_to_floatx80(a, status); } +/* + * Unsigned Integer to floating-point conversions + */ + float16 uint64_to_float16_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts64 pa = uint_to_float(a, scale, status); - return float16_round_pack_canonical(&pa, status); + FloatParts64 p; + + parts_uint_to_float(&p, a, scale, status); + return float16_round_pack_canonical(&p, status); } float16 uint32_to_float16_scalbn(uint32_t a, int scale, float_status *status) @@ -3191,8 +3738,17 @@ float16 uint8_to_float16(uint8_t a, float_status *status) float32 uint64_to_float32_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts64 pa = uint_to_float(a, scale, status); - return float32_round_pack_canonical(&pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float32 ur; + ur.h = a; + return ur.s; + } + + parts_uint_to_float(&p, a, scale, status); + return float32_round_pack_canonical(&p, status); } float32 uint32_to_float32_scalbn(uint32_t a, int scale, float_status *status) @@ -3222,8 +3778,17 @@ float32 uint16_to_float32(uint16_t a, float_status *status) float64 uint64_to_float64_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts64 pa = uint_to_float(a, scale, status); - return float64_round_pack_canonical(&pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float64 ur; + ur.h = a; + return ur.s; + } + + parts_uint_to_float(&p, a, scale, status); + return float64_round_pack_canonical(&p, status); } float64 uint32_to_float64_scalbn(uint32_t a, int scale, float_status *status) @@ -3251,15 +3816,12 @@ float64 uint16_to_float64(uint16_t a, float_status *status) return uint64_to_float64_scalbn(a, 0, status); } -/* - * Returns the result of converting the unsigned integer `a' to the - * bfloat16 format. - */ - bfloat16 uint64_to_bfloat16_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts64 pa = uint_to_float(a, scale, status); - return bfloat16_round_pack_canonical(&pa, status); + FloatParts64 p; + + parts_uint_to_float(&p, a, scale, status); + return bfloat16_round_pack_canonical(&p, status); } bfloat16 uint32_to_bfloat16_scalbn(uint32_t a, int scale, float_status *status) @@ -3287,232 +3849,132 @@ bfloat16 uint16_to_bfloat16(uint16_t a, float_status *status) return uint64_to_bfloat16_scalbn(a, 0, status); } -/* Float Min/Max */ -/* min() and max() functions. These can't be implemented as - * 'compare and pick one input' because that would mishandle - * NaNs and +0 vs -0. - * - * minnum() and maxnum() functions. These are similar to the min() - * and max() functions but if one of the arguments is a QNaN and - * the other is numerical then the numerical argument is returned. - * SNaNs will get quietened before being returned. - * minnum() and maxnum correspond to the IEEE 754-2008 minNum() - * and maxNum() operations. min() and max() are the typical min/max - * semantics provided by many CPUs which predate that specification. - * - * minnummag() and maxnummag() functions correspond to minNumMag() - * and minNumMag() from the IEEE-754 2008. +float128 uint64_to_float128(uint64_t a, float_status *status) +{ + FloatParts128 p; + + parts_uint_to_float(&p, a, 0, status); + return float128_round_pack_canonical(&p, status); +} + +/* + * Minimum and maximum */ -static FloatParts64 minmax_floats(FloatParts64 a, FloatParts64 b, bool ismin, - bool ieee, bool ismag, float_status *s) -{ - if (unlikely(is_nan(a.cls) || is_nan(b.cls))) { - if (ieee) { - /* Takes two floating-point values `a' and `b', one of - * which is a NaN, and returns the appropriate NaN - * result. If either `a' or `b' is a signaling NaN, - * the invalid exception is raised. - */ - if (is_snan(a.cls) || is_snan(b.cls)) { - return *parts_pick_nan(&a, &b, s); - } else if (is_nan(a.cls) && !is_nan(b.cls)) { - return b; - } else if (is_nan(b.cls) && !is_nan(a.cls)) { - return a; - } - } - return *parts_pick_nan(&a, &b, s); - } else { - int a_exp, b_exp; - switch (a.cls) { - case float_class_normal: - a_exp = a.exp; - break; - case float_class_inf: - a_exp = INT_MAX; - break; - case float_class_zero: - a_exp = INT_MIN; - break; - default: - g_assert_not_reached(); - break; - } - switch (b.cls) { - case float_class_normal: - b_exp = b.exp; - break; - case float_class_inf: - b_exp = INT_MAX; - break; - case float_class_zero: - b_exp = INT_MIN; - break; - default: - g_assert_not_reached(); - break; - } +static float16 float16_minmax(float16 a, float16 b, float_status *s, int flags) +{ + FloatParts64 pa, pb, *pr; - if (ismag && (a_exp != b_exp || a.frac != b.frac)) { - bool a_less = a_exp < b_exp; - if (a_exp == b_exp) { - a_less = a.frac < b.frac; - } - return a_less ^ ismin ? b : a; - } + float16_unpack_canonical(&pa, a, s); + float16_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); - if (a.sign == b.sign) { - bool a_less = a_exp < b_exp; - if (a_exp == b_exp) { - a_less = a.frac < b.frac; - } - return a.sign ^ a_less ^ ismin ? b : a; - } else { - return a.sign ^ ismin ? b : a; - } - } + return float16_round_pack_canonical(pr, s); } -#define MINMAX(sz, name, ismin, isiee, ismag) \ -float ## sz float ## sz ## _ ## name(float ## sz a, float ## sz b, \ - float_status *s) \ -{ \ - FloatParts64 pa, pb, pr; \ - float ## sz ## _unpack_canonical(&pa, a, s); \ - float ## sz ## _unpack_canonical(&pb, b, s); \ - pr = minmax_floats(pa, pb, ismin, isiee, ismag, s); \ - return float ## sz ## _round_pack_canonical(&pr, s); \ -} - -MINMAX(16, min, true, false, false) -MINMAX(16, minnum, true, true, false) -MINMAX(16, minnummag, true, true, true) -MINMAX(16, max, false, false, false) -MINMAX(16, maxnum, false, true, false) -MINMAX(16, maxnummag, false, true, true) - -MINMAX(32, min, true, false, false) -MINMAX(32, minnum, true, true, false) -MINMAX(32, minnummag, true, true, true) -MINMAX(32, max, false, false, false) -MINMAX(32, maxnum, false, true, false) -MINMAX(32, maxnummag, false, true, true) - -MINMAX(64, min, true, false, false) -MINMAX(64, minnum, true, true, false) -MINMAX(64, minnummag, true, true, true) -MINMAX(64, max, false, false, false) -MINMAX(64, maxnum, false, true, false) -MINMAX(64, maxnummag, false, true, true) - -#undef MINMAX - -#define BF16_MINMAX(name, ismin, isiee, ismag) \ -bfloat16 bfloat16_ ## name(bfloat16 a, bfloat16 b, float_status *s) \ -{ \ - FloatParts64 pa, pb, pr; \ - bfloat16_unpack_canonical(&pa, a, s); \ - bfloat16_unpack_canonical(&pb, b, s); \ - pr = minmax_floats(pa, pb, ismin, isiee, ismag, s); \ - return bfloat16_round_pack_canonical(&pr, s); \ -} - -BF16_MINMAX(min, true, false, false) -BF16_MINMAX(minnum, true, true, false) -BF16_MINMAX(minnummag, true, true, true) -BF16_MINMAX(max, false, false, false) -BF16_MINMAX(maxnum, false, true, false) -BF16_MINMAX(maxnummag, false, true, true) - -#undef BF16_MINMAX - -/* Floating point compare */ -static FloatRelation compare_floats(FloatParts64 a, FloatParts64 b, bool is_quiet, - float_status *s) -{ - if (is_nan(a.cls) || is_nan(b.cls)) { - if (!is_quiet || - a.cls == float_class_snan || - b.cls == float_class_snan) { - float_raise(float_flag_invalid, s); - } - return float_relation_unordered; - } +static bfloat16 bfloat16_minmax(bfloat16 a, bfloat16 b, + float_status *s, int flags) +{ + FloatParts64 pa, pb, *pr; - if (a.cls == float_class_zero) { - if (b.cls == float_class_zero) { - return float_relation_equal; - } - return b.sign ? float_relation_greater : float_relation_less; - } else if (b.cls == float_class_zero) { - return a.sign ? float_relation_less : float_relation_greater; - } + bfloat16_unpack_canonical(&pa, a, s); + bfloat16_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); - /* The only really important thing about infinity is its sign. If - * both are infinities the sign marks the smallest of the two. - */ - if (a.cls == float_class_inf) { - if ((b.cls == float_class_inf) && (a.sign == b.sign)) { - return float_relation_equal; - } - return a.sign ? float_relation_less : float_relation_greater; - } else if (b.cls == float_class_inf) { - return b.sign ? float_relation_greater : float_relation_less; - } + return bfloat16_round_pack_canonical(pr, s); +} - if (a.sign != b.sign) { - return a.sign ? float_relation_less : float_relation_greater; - } +static float32 float32_minmax(float32 a, float32 b, float_status *s, int flags) +{ + FloatParts64 pa, pb, *pr; - if (a.exp == b.exp) { - if (a.frac == b.frac) { - return float_relation_equal; - } - if (a.sign) { - return a.frac > b.frac ? - float_relation_less : float_relation_greater; - } else { - return a.frac > b.frac ? - float_relation_greater : float_relation_less; - } - } else { - if (a.sign) { - return a.exp > b.exp ? float_relation_less : float_relation_greater; - } else { - return a.exp > b.exp ? float_relation_greater : float_relation_less; - } - } + float32_unpack_canonical(&pa, a, s); + float32_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); + + return float32_round_pack_canonical(pr, s); } -#define COMPARE(name, attr, sz) \ -static int attr \ -name(float ## sz a, float ## sz b, bool is_quiet, float_status *s) \ -{ \ - FloatParts64 pa, pb; \ - float ## sz ## _unpack_canonical(&pa, a, s); \ - float ## sz ## _unpack_canonical(&pb, b, s); \ - return compare_floats(pa, pb, is_quiet, s); \ +static float64 float64_minmax(float64 a, float64 b, float_status *s, int flags) +{ + FloatParts64 pa, pb, *pr; + + float64_unpack_canonical(&pa, a, s); + float64_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); + + return float64_round_pack_canonical(pr, s); } -COMPARE(soft_f16_compare, QEMU_FLATTEN, 16) -COMPARE(soft_f32_compare, QEMU_SOFTFLOAT_ATTR, 32) -COMPARE(soft_f64_compare, QEMU_SOFTFLOAT_ATTR, 64) +static float128 float128_minmax(float128 a, float128 b, + float_status *s, int flags) +{ + FloatParts128 pa, pb, *pr; + + float128_unpack_canonical(&pa, a, s); + float128_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); + + return float128_round_pack_canonical(pr, s); +} -#undef COMPARE +#define MINMAX_1(type, name, flags) \ + type type##_##name(type a, type b, float_status *s) \ + { return type##_minmax(a, b, s, flags); } + +#define MINMAX_2(type) \ + MINMAX_1(type, max, 0) \ + MINMAX_1(type, maxnum, minmax_isnum) \ + MINMAX_1(type, maxnummag, minmax_isnum | minmax_ismag) \ + MINMAX_1(type, min, minmax_ismin) \ + MINMAX_1(type, minnum, minmax_ismin | minmax_isnum) \ + MINMAX_1(type, minnummag, minmax_ismin | minmax_isnum | minmax_ismag) + +MINMAX_2(float16) +MINMAX_2(bfloat16) +MINMAX_2(float32) +MINMAX_2(float64) +MINMAX_2(float128) + +#undef MINMAX_1 +#undef MINMAX_2 + +/* + * Floating point compare + */ + +static FloatRelation QEMU_FLATTEN +float16_do_compare(float16 a, float16 b, float_status *s, bool is_quiet) +{ + FloatParts64 pa, pb; + + float16_unpack_canonical(&pa, a, s); + float16_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); +} FloatRelation float16_compare(float16 a, float16 b, float_status *s) { - return soft_f16_compare(a, b, false, s); + return float16_do_compare(a, b, s, false); } FloatRelation float16_compare_quiet(float16 a, float16 b, float_status *s) { - return soft_f16_compare(a, b, true, s); + return float16_do_compare(a, b, s, true); +} + +static FloatRelation QEMU_SOFTFLOAT_ATTR +float32_do_compare(float32 a, float32 b, float_status *s, bool is_quiet) +{ + FloatParts64 pa, pb; + + float32_unpack_canonical(&pa, a, s); + float32_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } static FloatRelation QEMU_FLATTEN -f32_compare(float32 xa, float32 xb, bool is_quiet, float_status *s) +float32_hs_compare(float32 xa, float32 xb, float_status *s, bool is_quiet) { union_float32 ua, ub; @@ -3533,25 +3995,36 @@ f32_compare(float32 xa, float32 xb, bool is_quiet, float_status *s) if (likely(isless(ua.h, ub.h))) { return float_relation_less; } - /* The only condition remaining is unordered. + /* + * The only condition remaining is unordered. * Fall through to set flags. */ soft: - return soft_f32_compare(ua.s, ub.s, is_quiet, s); + return float32_do_compare(ua.s, ub.s, s, is_quiet); } FloatRelation float32_compare(float32 a, float32 b, float_status *s) { - return f32_compare(a, b, false, s); + return float32_hs_compare(a, b, s, false); } FloatRelation float32_compare_quiet(float32 a, float32 b, float_status *s) { - return f32_compare(a, b, true, s); + return float32_hs_compare(a, b, s, true); +} + +static FloatRelation QEMU_SOFTFLOAT_ATTR +float64_do_compare(float64 a, float64 b, float_status *s, bool is_quiet) +{ + FloatParts64 pa, pb; + + float64_unpack_canonical(&pa, a, s); + float64_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } static FloatRelation QEMU_FLATTEN -f64_compare(float64 xa, float64 xb, bool is_quiet, float_status *s) +float64_hs_compare(float64 xa, float64 xb, float_status *s, bool is_quiet) { union_float64 ua, ub; @@ -3572,196 +4045,177 @@ f64_compare(float64 xa, float64 xb, bool is_quiet, float_status *s) if (likely(isless(ua.h, ub.h))) { return float_relation_less; } - /* The only condition remaining is unordered. + /* + * The only condition remaining is unordered. * Fall through to set flags. */ soft: - return soft_f64_compare(ua.s, ub.s, is_quiet, s); + return float64_do_compare(ua.s, ub.s, s, is_quiet); } FloatRelation float64_compare(float64 a, float64 b, float_status *s) { - return f64_compare(a, b, false, s); + return float64_hs_compare(a, b, s, false); } FloatRelation float64_compare_quiet(float64 a, float64 b, float_status *s) { - return f64_compare(a, b, true, s); + return float64_hs_compare(a, b, s, true); } static FloatRelation QEMU_FLATTEN -soft_bf16_compare(bfloat16 a, bfloat16 b, bool is_quiet, float_status *s) +bfloat16_do_compare(bfloat16 a, bfloat16 b, float_status *s, bool is_quiet) { FloatParts64 pa, pb; bfloat16_unpack_canonical(&pa, a, s); bfloat16_unpack_canonical(&pb, b, s); - return compare_floats(pa, pb, is_quiet, s); + return parts_compare(&pa, &pb, s, is_quiet); } FloatRelation bfloat16_compare(bfloat16 a, bfloat16 b, float_status *s) { - return soft_bf16_compare(a, b, false, s); + return bfloat16_do_compare(a, b, s, false); } FloatRelation bfloat16_compare_quiet(bfloat16 a, bfloat16 b, float_status *s) { - return soft_bf16_compare(a, b, true, s); + return bfloat16_do_compare(a, b, s, true); } -/* Multiply A by 2 raised to the power N. */ -static FloatParts64 scalbn_decomposed(FloatParts64 a, int n, float_status *s) +static FloatRelation QEMU_FLATTEN +float128_do_compare(float128 a, float128 b, float_status *s, bool is_quiet) { - if (unlikely(is_nan(a.cls))) { - parts_return_nan(&a, s); - } - if (a.cls == float_class_normal) { - /* The largest float type (even though not supported by FloatParts64) - * is float128, which has a 15 bit exponent. Bounding N to 16 bits - * still allows rounding to infinity, without allowing overflow - * within the int32_t that backs FloatParts64.exp. - */ - n = MIN(MAX(n, -0x10000), 0x10000); - a.exp += n; - } - return a; + FloatParts128 pa, pb; + + float128_unpack_canonical(&pa, a, s); + float128_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } -float16 float16_scalbn(float16 a, int n, float_status *status) +FloatRelation float128_compare(float128 a, float128 b, float_status *s) { - FloatParts64 pa, pr; - - float16_unpack_canonical(&pa, a, status); - pr = scalbn_decomposed(pa, n, status); - return float16_round_pack_canonical(&pr, status); + return float128_do_compare(a, b, s, false); } -float32 float32_scalbn(float32 a, int n, float_status *status) +FloatRelation float128_compare_quiet(float128 a, float128 b, float_status *s) { - FloatParts64 pa, pr; - - float32_unpack_canonical(&pa, a, status); - pr = scalbn_decomposed(pa, n, status); - return float32_round_pack_canonical(&pr, status); + return float128_do_compare(a, b, s, true); } -float64 float64_scalbn(float64 a, int n, float_status *status) +static FloatRelation QEMU_FLATTEN +floatx80_do_compare(floatx80 a, floatx80 b, float_status *s, bool is_quiet) { - FloatParts64 pa, pr; + FloatParts128 pa, pb; - float64_unpack_canonical(&pa, a, status); - pr = scalbn_decomposed(pa, n, status); - return float64_round_pack_canonical(&pr, status); + if (!floatx80_unpack_canonical(&pa, a, s) || + !floatx80_unpack_canonical(&pb, b, s)) { + return float_relation_unordered; + } + return parts_compare(&pa, &pb, s, is_quiet); } -bfloat16 bfloat16_scalbn(bfloat16 a, int n, float_status *status) +FloatRelation floatx80_compare(floatx80 a, floatx80 b, float_status *s) { - FloatParts64 pa, pr; + return floatx80_do_compare(a, b, s, false); +} - bfloat16_unpack_canonical(&pa, a, status); - pr = scalbn_decomposed(pa, n, status); - return bfloat16_round_pack_canonical(&pr, status); +FloatRelation floatx80_compare_quiet(floatx80 a, floatx80 b, float_status *s) +{ + return floatx80_do_compare(a, b, s, true); } /* - * Square Root - * - * The old softfloat code did an approximation step before zeroing in - * on the final result. However for simpleness we just compute the - * square root by iterating down from the implicit bit to enough extra - * bits to ensure we get a correctly rounded result. - * - * This does mean however the calculation is slower than before, - * especially for 64 bit floats. + * Scale by 2**N */ -static FloatParts64 sqrt_float(FloatParts64 a, float_status *s, const FloatFmt *p) +float16 float16_scalbn(float16 a, int n, float_status *status) { - uint64_t a_frac, r_frac, s_frac; - int bit, last_bit; + FloatParts64 p; - if (is_nan(a.cls)) { - parts_return_nan(&a, s); - return a; - } - if (a.cls == float_class_zero) { - return a; /* sqrt(+-0) = +-0 */ - } - if (a.sign) { - float_raise(float_flag_invalid, s); - parts_default_nan(&a, s); - return a; - } - if (a.cls == float_class_inf) { - return a; /* sqrt(+inf) = +inf */ - } + float16_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float16_round_pack_canonical(&p, status); +} - assert(a.cls == float_class_normal); +float32 float32_scalbn(float32 a, int n, float_status *status) +{ + FloatParts64 p; - /* We need two overflow bits at the top. Adding room for that is a - * right shift. If the exponent is odd, we can discard the low bit - * by multiplying the fraction by 2; that's a left shift. Combine - * those and we shift right by 1 if the exponent is odd, otherwise 2. - */ - a_frac = a.frac >> (2 - (a.exp & 1)); - a.exp >>= 1; + float32_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float32_round_pack_canonical(&p, status); +} - /* Bit-by-bit computation of sqrt. */ - r_frac = 0; - s_frac = 0; +float64 float64_scalbn(float64 a, int n, float_status *status) +{ + FloatParts64 p; - /* Iterate from implicit bit down to the 3 extra bits to compute a - * properly rounded result. Remember we've inserted two more bits - * at the top, so these positions are two less. - */ - bit = DECOMPOSED_BINARY_POINT - 2; - last_bit = MAX(p->frac_shift - 4, 0); - do { - uint64_t q = 1ULL << bit; - uint64_t t_frac = s_frac + q; - if (t_frac <= a_frac) { - s_frac = t_frac + q; - a_frac -= t_frac; - r_frac += q; - } - a_frac <<= 1; - } while (--bit >= last_bit); + float64_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float64_round_pack_canonical(&p, status); +} - /* Undo the right shift done above. If there is any remaining - * fraction, the result is inexact. Set the sticky bit. - */ - a.frac = (r_frac << 2) + (a_frac != 0); +bfloat16 bfloat16_scalbn(bfloat16 a, int n, float_status *status) +{ + FloatParts64 p; - return a; + bfloat16_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return bfloat16_round_pack_canonical(&p, status); +} + +float128 float128_scalbn(float128 a, int n, float_status *status) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float128_round_pack_canonical(&p, status); +} + +floatx80 floatx80_scalbn(floatx80 a, int n, float_status *status) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, status)) { + return floatx80_default_nan(status); + } + parts_scalbn(&p, n, status); + return floatx80_round_pack_canonical(&p, status); } +/* + * Square Root + */ + float16 QEMU_FLATTEN float16_sqrt(float16 a, float_status *status) { - FloatParts64 pa, pr; + FloatParts64 p; - float16_unpack_canonical(&pa, a, status); - pr = sqrt_float(pa, status, &float16_params); - return float16_round_pack_canonical(&pr, status); + float16_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float16_params); + return float16_round_pack_canonical(&p, status); } static float32 QEMU_SOFTFLOAT_ATTR soft_f32_sqrt(float32 a, float_status *status) { - FloatParts64 pa, pr; + FloatParts64 p; - float32_unpack_canonical(&pa, a, status); - pr = sqrt_float(pa, status, &float32_params); - return float32_round_pack_canonical(&pr, status); + float32_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float32_params); + return float32_round_pack_canonical(&p, status); } static float64 QEMU_SOFTFLOAT_ATTR soft_f64_sqrt(float64 a, float_status *status) { - FloatParts64 pa, pr; + FloatParts64 p; - float64_unpack_canonical(&pa, a, status); - pr = sqrt_float(pa, status, &float64_params); - return float64_round_pack_canonical(&pr, status); + float64_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float64_params); + return float64_round_pack_canonical(&p, status); } float32 QEMU_FLATTEN float32_sqrt(float32 xa, float_status *s) @@ -3820,11 +4274,52 @@ float64 QEMU_FLATTEN float64_sqrt(float64 xa, float_status *s) bfloat16 QEMU_FLATTEN bfloat16_sqrt(bfloat16 a, float_status *status) { - FloatParts64 pa, pr; + FloatParts64 p; - bfloat16_unpack_canonical(&pa, a, status); - pr = sqrt_float(pa, status, &bfloat16_params); - return bfloat16_round_pack_canonical(&pr, status); + bfloat16_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &bfloat16_params); + return bfloat16_round_pack_canonical(&p, status); +} + +float128 QEMU_FLATTEN float128_sqrt(float128 a, float_status *status) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float128_params); + return float128_round_pack_canonical(&p, status); +} + +floatx80 floatx80_sqrt(floatx80 a, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + return floatx80_default_nan(s); + } + parts_sqrt(&p, s, &floatx80_params[s->floatx80_rounding_precision]); + return floatx80_round_pack_canonical(&p, s); +} + +/* + * log2 + */ +float32 float32_log2(float32 a, float_status *status) +{ + FloatParts64 p; + + float32_unpack_canonical(&p, a, status); + parts_log2(&p, status, &float32_params); + return float32_round_pack_canonical(&p, status); +} + +float64 float64_log2(float64 a, float_status *status) +{ + FloatParts64 p; + + float64_unpack_canonical(&p, a, status); + parts_log2(&p, status, &float64_params); + return float64_round_pack_canonical(&p, status); } /*---------------------------------------------------------------------------- @@ -4003,481 +4498,6 @@ bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status) } /*---------------------------------------------------------------------------- -| Takes a 64-bit fixed-point value `absZ' with binary point between bits 6 -| and 7, and returns the properly rounded 32-bit integer corresponding to the -| input. If `zSign' is 1, the input is negated before being converted to an -| integer. Bit 63 of `absZ' must be zero. Ordinarily, the fixed-point input -| is simply rounded to an integer, with the inexact exception raised if the -| input cannot be represented exactly as an integer. However, if the fixed- -| point input is too large, the invalid exception is raised and the largest -| positive or negative integer is returned. -*----------------------------------------------------------------------------*/ - -static int32_t roundAndPackInt32(bool zSign, uint64_t absZ, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven; - int8_t roundIncrement, roundBits; - int32_t z; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x40; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x7f; - break; - case float_round_down: - roundIncrement = zSign ? 0x7f : 0; - break; - case float_round_to_odd: - roundIncrement = absZ & 0x80 ? 0 : 0x7f; - break; - default: - abort(); - } - roundBits = absZ & 0x7F; - absZ = ( absZ + roundIncrement )>>7; - if (!(roundBits ^ 0x40) && roundNearestEven) { - absZ &= ~1; - } - z = absZ; - if ( zSign ) z = - z; - if ( ( absZ>>32 ) || ( z && ( ( z < 0 ) ^ zSign ) ) ) { - float_raise(float_flag_invalid, status); - return zSign ? INT32_MIN : INT32_MAX; - } - if (roundBits) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and -| `absZ1', with binary point between bits 63 and 64 (between the input words), -| and returns the properly rounded 64-bit integer corresponding to the input. -| If `zSign' is 1, the input is negated before being converted to an integer. -| Ordinarily, the fixed-point input is simply rounded to an integer, with -| the inexact exception raised if the input cannot be represented exactly as -| an integer. However, if the fixed-point input is too large, the invalid -| exception is raised and the largest positive or negative integer is -| returned. -*----------------------------------------------------------------------------*/ - -static int64_t roundAndPackInt64(bool zSign, uint64_t absZ0, uint64_t absZ1, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven, increment; - int64_t z; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t) absZ1 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && absZ1; - break; - case float_round_down: - increment = zSign && absZ1; - break; - case float_round_to_odd: - increment = !(absZ0 & 1) && absZ1; - break; - default: - abort(); - } - if ( increment ) { - ++absZ0; - if ( absZ0 == 0 ) goto overflow; - if (!(absZ1 << 1) && roundNearestEven) { - absZ0 &= ~1; - } - } - z = absZ0; - if ( zSign ) z = - z; - if ( z && ( ( z < 0 ) ^ zSign ) ) { - overflow: - float_raise(float_flag_invalid, status); - return zSign ? INT64_MIN : INT64_MAX; - } - if (absZ1) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and -| `absZ1', with binary point between bits 63 and 64 (between the input words), -| and returns the properly rounded 64-bit unsigned integer corresponding to the -| input. Ordinarily, the fixed-point input is simply rounded to an integer, -| with the inexact exception raised if the input cannot be represented exactly -| as an integer. However, if the fixed-point input is too large, the invalid -| exception is raised and the largest unsigned integer is returned. -*----------------------------------------------------------------------------*/ - -static int64_t roundAndPackUint64(bool zSign, uint64_t absZ0, - uint64_t absZ1, float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven, increment; - - roundingMode = status->float_rounding_mode; - roundNearestEven = (roundingMode == float_round_nearest_even); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t)absZ1 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && absZ1; - break; - case float_round_down: - increment = zSign && absZ1; - break; - case float_round_to_odd: - increment = !(absZ0 & 1) && absZ1; - break; - default: - abort(); - } - if (increment) { - ++absZ0; - if (absZ0 == 0) { - float_raise(float_flag_invalid, status); - return UINT64_MAX; - } - if (!(absZ1 << 1) && roundNearestEven) { - absZ0 &= ~1; - } - } - - if (zSign && absZ0) { - float_raise(float_flag_invalid, status); - return 0; - } - - if (absZ1) { - float_raise(float_flag_inexact, status); - } - return absZ0; -} - -/*---------------------------------------------------------------------------- -| Normalizes the subnormal single-precision floating-point value represented -| by the denormalized significand `aSig'. The normalized exponent and -| significand are stored at the locations pointed to by `zExpPtr' and -| `zSigPtr', respectively. -*----------------------------------------------------------------------------*/ - -static void - normalizeFloat32Subnormal(uint32_t aSig, int *zExpPtr, uint32_t *zSigPtr) -{ - int8_t shiftCount; - - shiftCount = clz32(aSig) - 8; - *zSigPtr = aSig<<shiftCount; - *zExpPtr = 1 - shiftCount; - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper single-precision floating- -| point value corresponding to the abstract input. Ordinarily, the abstract -| value is simply rounded and packed into the single-precision format, with -| the inexact exception raised if the abstract input cannot be represented -| exactly. However, if the abstract value is too large, the overflow and -| inexact exceptions are raised and an infinity or maximal finite value is -| returned. If the abstract value is too small, the input value is rounded to -| a subnormal number, and the underflow and inexact exceptions are raised if -| the abstract input cannot be represented exactly as a subnormal single- -| precision floating-point number. -| The input significand `zSig' has its binary point between bits 30 -| and 29, which is 7 bits to the left of the usual location. This shifted -| significand must be normalized or smaller. If `zSig' is not normalized, -| `zExp' must be 0; in that case, the result returned is a subnormal number, -| and it must not require rounding. In the usual case that `zSig' is -| normalized, `zExp' must be 1 less than the ``true'' floating-point exponent. -| The handling of underflow and overflow follows the IEC/IEEE Standard for -| Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float32 roundAndPackFloat32(bool zSign, int zExp, uint32_t zSig, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven; - int8_t roundIncrement, roundBits; - bool isTiny; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x40; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x7f; - break; - case float_round_down: - roundIncrement = zSign ? 0x7f : 0; - break; - case float_round_to_odd: - roundIncrement = zSig & 0x80 ? 0 : 0x7f; - break; - default: - abort(); - break; - } - roundBits = zSig & 0x7F; - if ( 0xFD <= (uint16_t) zExp ) { - if ( ( 0xFD < zExp ) - || ( ( zExp == 0xFD ) - && ( (int32_t) ( zSig + roundIncrement ) < 0 ) ) - ) { - bool overflow_to_inf = roundingMode != float_round_to_odd && - roundIncrement != 0; - float_raise(float_flag_overflow | float_flag_inexact, status); - return packFloat32(zSign, 0xFF, -!overflow_to_inf); - } - if ( zExp < 0 ) { - if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); - return packFloat32(zSign, 0, 0); - } - isTiny = status->tininess_before_rounding - || (zExp < -1) - || (zSig + roundIncrement < 0x80000000); - shift32RightJamming( zSig, - zExp, &zSig ); - zExp = 0; - roundBits = zSig & 0x7F; - if (isTiny && roundBits) { - float_raise(float_flag_underflow, status); - } - if (roundingMode == float_round_to_odd) { - /* - * For round-to-odd case, the roundIncrement depends on - * zSig which just changed. - */ - roundIncrement = zSig & 0x80 ? 0 : 0x7f; - } - } - } - if (roundBits) { - float_raise(float_flag_inexact, status); - } - zSig = ( zSig + roundIncrement )>>7; - if (!(roundBits ^ 0x40) && roundNearestEven) { - zSig &= ~1; - } - if ( zSig == 0 ) zExp = 0; - return packFloat32( zSign, zExp, zSig ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper single-precision floating- -| point value corresponding to the abstract input. This routine is just like -| `roundAndPackFloat32' except that `zSig' does not have to be normalized. -| Bit 31 of `zSig' must be zero, and `zExp' must be 1 less than the ``true'' -| floating-point exponent. -*----------------------------------------------------------------------------*/ - -static float32 - normalizeRoundAndPackFloat32(bool zSign, int zExp, uint32_t zSig, - float_status *status) -{ - int8_t shiftCount; - - shiftCount = clz32(zSig) - 1; - return roundAndPackFloat32(zSign, zExp - shiftCount, zSig<<shiftCount, - status); - -} - -/*---------------------------------------------------------------------------- -| Normalizes the subnormal double-precision floating-point value represented -| by the denormalized significand `aSig'. The normalized exponent and -| significand are stored at the locations pointed to by `zExpPtr' and -| `zSigPtr', respectively. -*----------------------------------------------------------------------------*/ - -static void - normalizeFloat64Subnormal(uint64_t aSig, int *zExpPtr, uint64_t *zSigPtr) -{ - int8_t shiftCount; - - shiftCount = clz64(aSig) - 11; - *zSigPtr = aSig<<shiftCount; - *zExpPtr = 1 - shiftCount; - -} - -/*---------------------------------------------------------------------------- -| Packs the sign `zSign', exponent `zExp', and significand `zSig' into a -| double-precision floating-point value, returning the result. After being -| shifted into the proper positions, the three fields are simply added -| together to form the result. This means that any integer portion of `zSig' -| will be added into the exponent. Since a properly normalized significand -| will have an integer portion equal to 1, the `zExp' input should be 1 less -| than the desired result exponent whenever `zSig' is a complete, normalized -| significand. -*----------------------------------------------------------------------------*/ - -static inline float64 packFloat64(bool zSign, int zExp, uint64_t zSig) -{ - - return make_float64( - ( ( (uint64_t) zSign )<<63 ) + ( ( (uint64_t) zExp )<<52 ) + zSig); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper double-precision floating- -| point value corresponding to the abstract input. Ordinarily, the abstract -| value is simply rounded and packed into the double-precision format, with -| the inexact exception raised if the abstract input cannot be represented -| exactly. However, if the abstract value is too large, the overflow and -| inexact exceptions are raised and an infinity or maximal finite value is -| returned. If the abstract value is too small, the input value is rounded to -| a subnormal number, and the underflow and inexact exceptions are raised if -| the abstract input cannot be represented exactly as a subnormal double- -| precision floating-point number. -| The input significand `zSig' has its binary point between bits 62 -| and 61, which is 10 bits to the left of the usual location. This shifted -| significand must be normalized or smaller. If `zSig' is not normalized, -| `zExp' must be 0; in that case, the result returned is a subnormal number, -| and it must not require rounding. In the usual case that `zSig' is -| normalized, `zExp' must be 1 less than the ``true'' floating-point exponent. -| The handling of underflow and overflow follows the IEC/IEEE Standard for -| Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float64 roundAndPackFloat64(bool zSign, int zExp, uint64_t zSig, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven; - int roundIncrement, roundBits; - bool isTiny; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x200; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x3ff; - break; - case float_round_down: - roundIncrement = zSign ? 0x3ff : 0; - break; - case float_round_to_odd: - roundIncrement = (zSig & 0x400) ? 0 : 0x3ff; - break; - default: - abort(); - } - roundBits = zSig & 0x3FF; - if ( 0x7FD <= (uint16_t) zExp ) { - if ( ( 0x7FD < zExp ) - || ( ( zExp == 0x7FD ) - && ( (int64_t) ( zSig + roundIncrement ) < 0 ) ) - ) { - bool overflow_to_inf = roundingMode != float_round_to_odd && - roundIncrement != 0; - float_raise(float_flag_overflow | float_flag_inexact, status); - return packFloat64(zSign, 0x7FF, -(!overflow_to_inf)); - } - if ( zExp < 0 ) { - if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); - return packFloat64(zSign, 0, 0); - } - isTiny = status->tininess_before_rounding - || (zExp < -1) - || (zSig + roundIncrement < UINT64_C(0x8000000000000000)); - shift64RightJamming( zSig, - zExp, &zSig ); - zExp = 0; - roundBits = zSig & 0x3FF; - if (isTiny && roundBits) { - float_raise(float_flag_underflow, status); - } - if (roundingMode == float_round_to_odd) { - /* - * For round-to-odd case, the roundIncrement depends on - * zSig which just changed. - */ - roundIncrement = (zSig & 0x400) ? 0 : 0x3ff; - } - } - } - if (roundBits) { - float_raise(float_flag_inexact, status); - } - zSig = ( zSig + roundIncrement )>>10; - if (!(roundBits ^ 0x200) && roundNearestEven) { - zSig &= ~1; - } - if ( zSig == 0 ) zExp = 0; - return packFloat64( zSign, zExp, zSig ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper double-precision floating- -| point value corresponding to the abstract input. This routine is just like -| `roundAndPackFloat64' except that `zSig' does not have to be normalized. -| Bit 63 of `zSig' must be zero, and `zExp' must be 1 less than the ``true'' -| floating-point exponent. -*----------------------------------------------------------------------------*/ - -static float64 - normalizeRoundAndPackFloat64(bool zSign, int zExp, uint64_t zSig, - float_status *status) -{ - int8_t shiftCount; - - shiftCount = clz64(zSig) - 1; - return roundAndPackFloat64(zSign, zExp - shiftCount, zSig<<shiftCount, - status); - -} - -/*---------------------------------------------------------------------------- | Normalizes the subnormal extended double-precision floating-point value | represented by the denormalized significand `aSig'. The normalized exponent | and significand are stored at the locations pointed to by `zExpPtr' and @@ -4507,10 +4527,10 @@ void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, | a subnormal number, and the underflow and inexact exceptions are raised if | the abstract input cannot be represented exactly as a subnormal extended | double-precision floating-point number. -| If `roundingPrecision' is 32 or 64, the result is rounded to the same -| number of bits as single or double precision, respectively. Otherwise, the -| result is rounded to the full precision of the extended double-precision -| format. +| If `roundingPrecision' is floatx80_precision_s or floatx80_precision_d, +| the result is rounded to the same number of bits as single or double +| precision, respectively. Otherwise, the result is rounded to the full +| precision of the extended double-precision format. | The input significand must be normalized or smaller. If the input | significand is not normalized, `zExp' must be 0; in that case, the result | returned is a subnormal number, and it must not require rounding. The @@ -4518,27 +4538,29 @@ void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, | Floating-Point Arithmetic. *----------------------------------------------------------------------------*/ -floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, +floatx80 roundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status) { - int8_t roundingMode; + FloatRoundMode roundingMode; bool roundNearestEven, increment, isTiny; int64_t roundIncrement, roundMask, roundBits; roundingMode = status->float_rounding_mode; roundNearestEven = ( roundingMode == float_round_nearest_even ); - if ( roundingPrecision == 80 ) goto precision80; - if ( roundingPrecision == 64 ) { + switch (roundingPrecision) { + case floatx80_precision_x: + goto precision80; + case floatx80_precision_d: roundIncrement = UINT64_C(0x0000000000000400); roundMask = UINT64_C(0x00000000000007FF); - } - else if ( roundingPrecision == 32 ) { + break; + case floatx80_precision_s: roundIncrement = UINT64_C(0x0000008000000000); roundMask = UINT64_C(0x000000FFFFFFFFFF); - } - else { - goto precision80; + break; + default: + g_assert_not_reached(); } zSig0 |= ( zSig1 != 0 ); switch (roundingMode) { @@ -4715,7 +4737,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, | normalized. *----------------------------------------------------------------------------*/ -floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, +floatx80 normalizeRoundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status) @@ -4736,538 +4758,6 @@ floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, } /*---------------------------------------------------------------------------- -| Returns the least-significant 64 fraction bits of the quadruple-precision -| floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloat128Frac1( float128 a ) -{ - - return a.low; - -} - -/*---------------------------------------------------------------------------- -| Returns the most-significant 48 fraction bits of the quadruple-precision -| floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloat128Frac0( float128 a ) -{ - - return a.high & UINT64_C(0x0000FFFFFFFFFFFF); - -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the quadruple-precision floating-point value -| `a'. -*----------------------------------------------------------------------------*/ - -static inline int32_t extractFloat128Exp( float128 a ) -{ - - return ( a.high>>48 ) & 0x7FFF; - -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the quadruple-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline bool extractFloat128Sign(float128 a) -{ - return a.high >> 63; -} - -/*---------------------------------------------------------------------------- -| Normalizes the subnormal quadruple-precision floating-point value -| represented by the denormalized significand formed by the concatenation of -| `aSig0' and `aSig1'. The normalized exponent is stored at the location -| pointed to by `zExpPtr'. The most significant 49 bits of the normalized -| significand are stored at the location pointed to by `zSig0Ptr', and the -| least significant 64 bits of the normalized significand are stored at the -| location pointed to by `zSig1Ptr'. -*----------------------------------------------------------------------------*/ - -static void - normalizeFloat128Subnormal( - uint64_t aSig0, - uint64_t aSig1, - int32_t *zExpPtr, - uint64_t *zSig0Ptr, - uint64_t *zSig1Ptr - ) -{ - int8_t shiftCount; - - if ( aSig0 == 0 ) { - shiftCount = clz64(aSig1) - 15; - if ( shiftCount < 0 ) { - *zSig0Ptr = aSig1>>( - shiftCount ); - *zSig1Ptr = aSig1<<( shiftCount & 63 ); - } - else { - *zSig0Ptr = aSig1<<shiftCount; - *zSig1Ptr = 0; - } - *zExpPtr = - shiftCount - 63; - } - else { - shiftCount = clz64(aSig0) - 15; - shortShift128Left( aSig0, aSig1, shiftCount, zSig0Ptr, zSig1Ptr ); - *zExpPtr = 1 - shiftCount; - } - -} - -/*---------------------------------------------------------------------------- -| Packs the sign `zSign', the exponent `zExp', and the significand formed -| by the concatenation of `zSig0' and `zSig1' into a quadruple-precision -| floating-point value, returning the result. After being shifted into the -| proper positions, the three fields `zSign', `zExp', and `zSig0' are simply -| added together to form the most significant 32 bits of the result. This -| means that any integer portion of `zSig0' will be added into the exponent. -| Since a properly normalized significand will have an integer portion equal -| to 1, the `zExp' input should be 1 less than the desired result exponent -| whenever `zSig0' and `zSig1' concatenated form a complete, normalized -| significand. -*----------------------------------------------------------------------------*/ - -static inline float128 -packFloat128(bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1) -{ - float128 z; - - z.low = zSig1; - z.high = ((uint64_t)zSign << 63) + ((uint64_t)zExp << 48) + zSig0; - return z; -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and extended significand formed by the concatenation of `zSig0', `zSig1', -| and `zSig2', and returns the proper quadruple-precision floating-point value -| corresponding to the abstract input. Ordinarily, the abstract value is -| simply rounded and packed into the quadruple-precision format, with the -| inexact exception raised if the abstract input cannot be represented -| exactly. However, if the abstract value is too large, the overflow and -| inexact exceptions are raised and an infinity or maximal finite value is -| returned. If the abstract value is too small, the input value is rounded to -| a subnormal number, and the underflow and inexact exceptions are raised if -| the abstract input cannot be represented exactly as a subnormal quadruple- -| precision floating-point number. -| The input significand must be normalized or smaller. If the input -| significand is not normalized, `zExp' must be 0; in that case, the result -| returned is a subnormal number, and it must not require rounding. In the -| usual case that the input significand is normalized, `zExp' must be 1 less -| than the ``true'' floating-point exponent. The handling of underflow and -| overflow follows the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float128 roundAndPackFloat128(bool zSign, int32_t zExp, - uint64_t zSig0, uint64_t zSig1, - uint64_t zSig2, float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven, increment, isTiny; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t)zSig2 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && zSig2; - break; - case float_round_down: - increment = zSign && zSig2; - break; - case float_round_to_odd: - increment = !(zSig1 & 0x1) && zSig2; - break; - default: - abort(); - } - if ( 0x7FFD <= (uint32_t) zExp ) { - if ( ( 0x7FFD < zExp ) - || ( ( zExp == 0x7FFD ) - && eq128( - UINT64_C(0x0001FFFFFFFFFFFF), - UINT64_C(0xFFFFFFFFFFFFFFFF), - zSig0, - zSig1 - ) - && increment - ) - ) { - float_raise(float_flag_overflow | float_flag_inexact, status); - if ( ( roundingMode == float_round_to_zero ) - || ( zSign && ( roundingMode == float_round_up ) ) - || ( ! zSign && ( roundingMode == float_round_down ) ) - || (roundingMode == float_round_to_odd) - ) { - return - packFloat128( - zSign, - 0x7FFE, - UINT64_C(0x0000FFFFFFFFFFFF), - UINT64_C(0xFFFFFFFFFFFFFFFF) - ); - } - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( zExp < 0 ) { - if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); - return packFloat128(zSign, 0, 0, 0); - } - isTiny = status->tininess_before_rounding - || (zExp < -1) - || !increment - || lt128(zSig0, zSig1, - UINT64_C(0x0001FFFFFFFFFFFF), - UINT64_C(0xFFFFFFFFFFFFFFFF)); - shift128ExtraRightJamming( - zSig0, zSig1, zSig2, - zExp, &zSig0, &zSig1, &zSig2 ); - zExp = 0; - if (isTiny && zSig2) { - float_raise(float_flag_underflow, status); - } - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t)zSig2 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && zSig2; - break; - case float_round_down: - increment = zSign && zSig2; - break; - case float_round_to_odd: - increment = !(zSig1 & 0x1) && zSig2; - break; - default: - abort(); - } - } - } - if (zSig2) { - float_raise(float_flag_inexact, status); - } - if ( increment ) { - add128( zSig0, zSig1, 0, 1, &zSig0, &zSig1 ); - if ((zSig2 + zSig2 == 0) && roundNearestEven) { - zSig1 &= ~1; - } - } - else { - if ( ( zSig0 | zSig1 ) == 0 ) zExp = 0; - } - return packFloat128( zSign, zExp, zSig0, zSig1 ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand formed by the concatenation of `zSig0' and `zSig1', and -| returns the proper quadruple-precision floating-point value corresponding -| to the abstract input. This routine is just like `roundAndPackFloat128' -| except that the input significand has fewer bits and does not have to be -| normalized. In all cases, `zExp' must be 1 less than the ``true'' floating- -| point exponent. -*----------------------------------------------------------------------------*/ - -static float128 normalizeRoundAndPackFloat128(bool zSign, int32_t zExp, - uint64_t zSig0, uint64_t zSig1, - float_status *status) -{ - int8_t shiftCount; - uint64_t zSig2; - - if ( zSig0 == 0 ) { - zSig0 = zSig1; - zSig1 = 0; - zExp -= 64; - } - shiftCount = clz64(zSig0) - 15; - if ( 0 <= shiftCount ) { - zSig2 = 0; - shortShift128Left( zSig0, zSig1, shiftCount, &zSig0, &zSig1 ); - } - else { - shift128ExtraRightJamming( - zSig0, zSig1, 0, - shiftCount, &zSig0, &zSig1, &zSig2 ); - } - zExp -= shiftCount; - return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status); - -} - - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 32-bit two's complement integer `a' -| to the extended double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 int32_to_floatx80(int32_t a, float_status *status) -{ - bool zSign; - uint32_t absA; - int8_t shiftCount; - uint64_t zSig; - - if ( a == 0 ) return packFloatx80( 0, 0, 0 ); - zSign = ( a < 0 ); - absA = zSign ? - a : a; - shiftCount = clz32(absA) + 32; - zSig = absA; - return packFloatx80( zSign, 0x403E - shiftCount, zSig<<shiftCount ); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 32-bit two's complement integer `a' to -| the quadruple-precision floating-point format. The conversion is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 int32_to_float128(int32_t a, float_status *status) -{ - bool zSign; - uint32_t absA; - int8_t shiftCount; - uint64_t zSig0; - - if ( a == 0 ) return packFloat128( 0, 0, 0, 0 ); - zSign = ( a < 0 ); - absA = zSign ? - a : a; - shiftCount = clz32(absA) + 17; - zSig0 = absA; - return packFloat128( zSign, 0x402E - shiftCount, zSig0<<shiftCount, 0 ); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 64-bit two's complement integer `a' -| to the extended double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 int64_to_floatx80(int64_t a, float_status *status) -{ - bool zSign; - uint64_t absA; - int8_t shiftCount; - - if ( a == 0 ) return packFloatx80( 0, 0, 0 ); - zSign = ( a < 0 ); - absA = zSign ? - a : a; - shiftCount = clz64(absA); - return packFloatx80( zSign, 0x403E - shiftCount, absA<<shiftCount ); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 64-bit two's complement integer `a' to -| the quadruple-precision floating-point format. The conversion is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 int64_to_float128(int64_t a, float_status *status) -{ - bool zSign; - uint64_t absA; - int8_t shiftCount; - int32_t zExp; - uint64_t zSig0, zSig1; - - if ( a == 0 ) return packFloat128( 0, 0, 0, 0 ); - zSign = ( a < 0 ); - absA = zSign ? - a : a; - shiftCount = clz64(absA) + 49; - zExp = 0x406E - shiftCount; - if ( 64 <= shiftCount ) { - zSig1 = 0; - zSig0 = absA; - shiftCount -= 64; - } - else { - zSig1 = absA; - zSig0 = 0; - } - shortShift128Left( zSig0, zSig1, shiftCount, &zSig0, &zSig1 ); - return packFloat128( zSign, zExp, zSig0, zSig1 ); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 64-bit unsigned integer `a' -| to the quadruple-precision floating-point format. The conversion is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 uint64_to_float128(uint64_t a, float_status *status) -{ - if (a == 0) { - return float128_zero; - } - return normalizeRoundAndPackFloat128(0, 0x406E, 0, a, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the single-precision floating-point value -| `a' to the extended double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 float32_to_floatx80(float32 a, float_status *status) -{ - bool aSign; - int aExp; - uint32_t aSig; - - a = float32_squash_input_denormal(a, status); - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - if ( aExp == 0xFF ) { - if (aSig) { - floatx80 res = commonNaNToFloatx80(float32ToCommonNaN(a, status), - status); - return floatx80_silence_nan(res, status); - } - return packFloatx80(aSign, - floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( aSign, 0, 0 ); - normalizeFloat32Subnormal( aSig, &aExp, &aSig ); - } - aSig |= 0x00800000; - return packFloatx80( aSign, aExp + 0x3F80, ( (uint64_t) aSig )<<40 ); - -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the single-precision floating-point value `a' -| with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float32 float32_rem(float32 a, float32 b, float_status *status) -{ - bool aSign, zSign; - int aExp, bExp, expDiff; - uint32_t aSig, bSig; - uint32_t q; - uint64_t aSig64, bSig64, q64; - uint32_t alternateASig; - int32_t sigMean; - a = float32_squash_input_denormal(a, status); - b = float32_squash_input_denormal(b, status); - - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - bSig = extractFloat32Frac( b ); - bExp = extractFloat32Exp( b ); - if ( aExp == 0xFF ) { - if ( aSig || ( ( bExp == 0xFF ) && bSig ) ) { - return propagateFloat32NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - if ( bExp == 0xFF ) { - if (bSig) { - return propagateFloat32NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - normalizeFloat32Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return a; - normalizeFloat32Subnormal( aSig, &aExp, &aSig ); - } - expDiff = aExp - bExp; - aSig |= 0x00800000; - bSig |= 0x00800000; - if ( expDiff < 32 ) { - aSig <<= 8; - bSig <<= 8; - if ( expDiff < 0 ) { - if ( expDiff < -1 ) return a; - aSig >>= 1; - } - q = ( bSig <= aSig ); - if ( q ) aSig -= bSig; - if ( 0 < expDiff ) { - q = ( ( (uint64_t) aSig )<<32 ) / bSig; - q >>= 32 - expDiff; - bSig >>= 2; - aSig = ( ( aSig>>1 )<<( expDiff - 1 ) ) - bSig * q; - } - else { - aSig >>= 2; - bSig >>= 2; - } - } - else { - if ( bSig <= aSig ) aSig -= bSig; - aSig64 = ( (uint64_t) aSig )<<40; - bSig64 = ( (uint64_t) bSig )<<40; - expDiff -= 64; - while ( 0 < expDiff ) { - q64 = estimateDiv128To64( aSig64, 0, bSig64 ); - q64 = ( 2 < q64 ) ? q64 - 2 : 0; - aSig64 = - ( ( bSig * q64 )<<38 ); - expDiff -= 62; - } - expDiff += 64; - q64 = estimateDiv128To64( aSig64, 0, bSig64 ); - q64 = ( 2 < q64 ) ? q64 - 2 : 0; - q = q64>>( 64 - expDiff ); - bSig <<= 6; - aSig = ( ( aSig64>>33 )<<( expDiff - 1 ) ) - bSig * q; - } - do { - alternateASig = aSig; - ++q; - aSig -= bSig; - } while ( 0 <= (int32_t) aSig ); - sigMean = aSig + alternateASig; - if ( ( sigMean < 0 ) || ( ( sigMean == 0 ) && ( q & 1 ) ) ) { - aSig = alternateASig; - } - zSign = ( (int32_t) aSig < 0 ); - if ( zSign ) aSig = - aSig; - return normalizeRoundAndPackFloat32(aSign ^ zSign, bExp, aSig, status); -} - - - -/*---------------------------------------------------------------------------- | Returns the binary exponential of the single-precision floating-point value | `a'. The operation is performed according to the IEC/IEEE Standard for | Binary Floating-Point Arithmetic. @@ -5306,542 +4796,40 @@ static const float64 float32_exp2_coefficients[15] = float32 float32_exp2(float32 a, float_status *status) { - bool aSign; - int aExp; - uint32_t aSig; - float64 r, x, xn; + FloatParts64 xp, xnp, tp, rp; int i; - a = float32_squash_input_denormal(a, status); - - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - if ( aExp == 0xFF) { - if (aSig) { - return propagateFloat32NaN(a, float32_zero, status); + float32_unpack_canonical(&xp, a, status); + if (unlikely(xp.cls != float_class_normal)) { + switch (xp.cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(&xp, status); + return float32_round_pack_canonical(&xp, status); + case float_class_inf: + return xp.sign ? float32_zero : a; + case float_class_zero: + return float32_one; + default: + break; } - return (aSign) ? float32_zero : a; - } - if (aExp == 0) { - if (aSig == 0) return float32_one; + g_assert_not_reached(); } float_raise(float_flag_inexact, status); - /* ******************************* */ - /* using float64 for approximation */ - /* ******************************* */ - x = float32_to_float64(a, status); - x = float64_mul(x, float64_ln2, status); + float64_unpack_canonical(&xnp, float64_ln2, status); + xp = *parts_mul(&xp, &tp, status); + xnp = xp; - xn = x; - r = float64_one; + float64_unpack_canonical(&rp, float64_one, status); for (i = 0 ; i < 15 ; i++) { - float64 f; - - f = float64_mul(xn, float32_exp2_coefficients[i], status); - r = float64_add(r, f, status); - - xn = float64_mul(xn, x, status); - } - - return float64_to_float32(r, status); -} - -/*---------------------------------------------------------------------------- -| Returns the binary log of the single-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ -float32 float32_log2(float32 a, float_status *status) -{ - bool aSign, zSign; - int aExp; - uint32_t aSig, zSig, i; - - a = float32_squash_input_denormal(a, status); - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloat32( 1, 0xFF, 0 ); - normalizeFloat32Subnormal( aSig, &aExp, &aSig ); - } - if ( aSign ) { - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - if ( aExp == 0xFF ) { - if (aSig) { - return propagateFloat32NaN(a, float32_zero, status); - } - return a; - } - - aExp -= 0x7F; - aSig |= 0x00800000; - zSign = aExp < 0; - zSig = aExp << 23; - - for (i = 1 << 22; i > 0; i >>= 1) { - aSig = ( (uint64_t)aSig * aSig ) >> 23; - if ( aSig & 0x01000000 ) { - aSig >>= 1; - zSig |= i; - } - } - - if ( zSign ) - zSig = -zSig; - - return normalizeRoundAndPackFloat32(zSign, 0x85, zSig, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the double-precision floating-point value -| `a' to the extended double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 float64_to_floatx80(float64 a, float_status *status) -{ - bool aSign; - int aExp; - uint64_t aSig; - - a = float64_squash_input_denormal(a, status); - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - if ( aExp == 0x7FF ) { - if (aSig) { - floatx80 res = commonNaNToFloatx80(float64ToCommonNaN(a, status), - status); - return floatx80_silence_nan(res, status); - } - return packFloatx80(aSign, - floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( aSign, 0, 0 ); - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - return - packFloatx80( - aSign, aExp + 0x3C00, (aSig | UINT64_C(0x0010000000000000)) << 11); - -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the double-precision floating-point value `a' -| with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 float64_rem(float64 a, float64 b, float_status *status) -{ - bool aSign, zSign; - int aExp, bExp, expDiff; - uint64_t aSig, bSig; - uint64_t q, alternateASig; - int64_t sigMean; - - a = float64_squash_input_denormal(a, status); - b = float64_squash_input_denormal(b, status); - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - bSig = extractFloat64Frac( b ); - bExp = extractFloat64Exp( b ); - if ( aExp == 0x7FF ) { - if ( aSig || ( ( bExp == 0x7FF ) && bSig ) ) { - return propagateFloat64NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - if ( bExp == 0x7FF ) { - if (bSig) { - return propagateFloat64NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - normalizeFloat64Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return a; - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - expDiff = aExp - bExp; - aSig = (aSig | UINT64_C(0x0010000000000000)) << 11; - bSig = (bSig | UINT64_C(0x0010000000000000)) << 11; - if ( expDiff < 0 ) { - if ( expDiff < -1 ) return a; - aSig >>= 1; - } - q = ( bSig <= aSig ); - if ( q ) aSig -= bSig; - expDiff -= 64; - while ( 0 < expDiff ) { - q = estimateDiv128To64( aSig, 0, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - aSig = - ( ( bSig>>2 ) * q ); - expDiff -= 62; - } - expDiff += 64; - if ( 0 < expDiff ) { - q = estimateDiv128To64( aSig, 0, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - q >>= 64 - expDiff; - bSig >>= 2; - aSig = ( ( aSig>>1 )<<( expDiff - 1 ) ) - bSig * q; - } - else { - aSig >>= 2; - bSig >>= 2; - } - do { - alternateASig = aSig; - ++q; - aSig -= bSig; - } while ( 0 <= (int64_t) aSig ); - sigMean = aSig + alternateASig; - if ( ( sigMean < 0 ) || ( ( sigMean == 0 ) && ( q & 1 ) ) ) { - aSig = alternateASig; - } - zSign = ( (int64_t) aSig < 0 ); - if ( zSign ) aSig = - aSig; - return normalizeRoundAndPackFloat64(aSign ^ zSign, bExp, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the binary log of the double-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ -float64 float64_log2(float64 a, float_status *status) -{ - bool aSign, zSign; - int aExp; - uint64_t aSig, aSig0, aSig1, zSig, i; - a = float64_squash_input_denormal(a, status); - - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloat64( 1, 0x7FF, 0 ); - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - if ( aSign ) { - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - if ( aExp == 0x7FF ) { - if (aSig) { - return propagateFloat64NaN(a, float64_zero, status); - } - return a; - } - - aExp -= 0x3FF; - aSig |= UINT64_C(0x0010000000000000); - zSign = aExp < 0; - zSig = (uint64_t)aExp << 52; - for (i = 1LL << 51; i > 0; i >>= 1) { - mul64To128( aSig, aSig, &aSig0, &aSig1 ); - aSig = ( aSig0 << 12 ) | ( aSig1 >> 52 ); - if ( aSig & UINT64_C(0x0020000000000000) ) { - aSig >>= 1; - zSig |= i; - } - } - - if ( zSign ) - zSig = -zSig; - return normalizeRoundAndPackFloat64(zSign, 0x408, zSig, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 32-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic---which means in particular that the conversion -| is rounded according to the current rounding mode. If `a' is a NaN, the -| largest positive integer is returned. Otherwise, if the conversion -| overflows, the largest integer with the same sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int32_t floatx80_to_int32(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1 << 31; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) aSign = 0; - shiftCount = 0x4037 - aExp; - if ( shiftCount <= 0 ) shiftCount = 1; - shift64RightJamming( aSig, shiftCount, &aSig ); - return roundAndPackInt32(aSign, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 32-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic, except that the conversion is always rounded -| toward zero. If `a' is a NaN, the largest positive integer is returned. -| Otherwise, if the conversion overflows, the largest integer with the same -| sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int32_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig, savedASig; - int32_t z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1 << 31; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( 0x401E < aExp ) { - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) aSign = 0; - goto invalid; - } - else if ( aExp < 0x3FFF ) { - if (aExp || aSig) { - float_raise(float_flag_inexact, status); - } - return 0; - } - shiftCount = 0x403E - aExp; - savedASig = aSig; - aSig >>= shiftCount; - z = aSig; - if ( aSign ) z = - z; - if ( ( z < 0 ) ^ aSign ) { - invalid: - float_raise(float_flag_invalid, status); - return aSign ? (int32_t) 0x80000000 : 0x7FFFFFFF; - } - if ( ( aSig<<shiftCount ) != savedASig ) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 64-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic---which means in particular that the conversion -| is rounded according to the current rounding mode. If `a' is a NaN, -| the largest positive integer is returned. Otherwise, if the conversion -| overflows, the largest integer with the same sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int64_t floatx80_to_int64(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig, aSigExtra; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1ULL << 63; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - shiftCount = 0x403E - aExp; - if ( shiftCount <= 0 ) { - if ( shiftCount ) { - float_raise(float_flag_invalid, status); - if (!aSign || floatx80_is_any_nan(a)) { - return INT64_MAX; - } - return INT64_MIN; - } - aSigExtra = 0; - } - else { - shift64ExtraRightJamming( aSig, 0, shiftCount, &aSig, &aSigExtra ); - } - return roundAndPackInt64(aSign, aSig, aSigExtra, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 64-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic, except that the conversion is always rounded -| toward zero. If `a' is a NaN, the largest positive integer is returned. -| Otherwise, if the conversion overflows, the largest integer with the same -| sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig; - int64_t z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1ULL << 63; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - shiftCount = aExp - 0x403E; - if ( 0 <= shiftCount ) { - aSig &= UINT64_C(0x7FFFFFFFFFFFFFFF); - if ( ( a.high != 0xC03E ) || aSig ) { - float_raise(float_flag_invalid, status); - if ( ! aSign || ( ( aExp == 0x7FFF ) && aSig ) ) { - return INT64_MAX; - } - } - return INT64_MIN; - } - else if ( aExp < 0x3FFF ) { - if (aExp | aSig) { - float_raise(float_flag_inexact, status); - } - return 0; + float64_unpack_canonical(&tp, float32_exp2_coefficients[i], status); + rp = *parts_muladd(&tp, &xp, &rp, 0, status); + xnp = *parts_mul(&xnp, &xp, status); } - z = aSig>>( - shiftCount ); - if ( (uint64_t) ( aSig<<( shiftCount & 63 ) ) ) { - float_raise(float_flag_inexact, status); - } - if ( aSign ) z = - z; - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the single-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float32 floatx80_to_float32(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig<<1 ) ) { - float32 res = commonNaNToFloat32(floatx80ToCommonNaN(a, status), - status); - return float32_silence_nan(res, status); - } - return packFloat32( aSign, 0xFF, 0 ); - } - shift64RightJamming( aSig, 33, &aSig ); - if ( aExp || aSig ) aExp -= 0x3F81; - return roundAndPackFloat32(aSign, aExp, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the double-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 floatx80_to_float64(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig, zSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig<<1 ) ) { - float64 res = commonNaNToFloat64(floatx80ToCommonNaN(a, status), - status); - return float64_silence_nan(res, status); - } - return packFloat64( aSign, 0x7FF, 0 ); - } - shift64RightJamming( aSig, 1, &zSig ); - if ( aExp || aSig ) aExp -= 0x3C01; - return roundAndPackFloat64(aSign, aExp, zSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the quadruple-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 floatx80_to_float128(floatx80 a, float_status *status) -{ - bool aSign; - int aExp; - uint64_t aSig, zSig0, zSig1; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) { - float128 res = commonNaNToFloat128(floatx80ToCommonNaN(a, status), - status); - return float128_silence_nan(res, status); - } - shift128Right( aSig<<1, 0, 16, &zSig0, &zSig1 ); - return packFloat128( aSign, aExp, zSig0, zSig1 ); + return float32_round_pack_canonical(&rp, status); } /*---------------------------------------------------------------------------- @@ -5854,1195 +4842,12 @@ float128 floatx80_to_float128(floatx80 a, float_status *status) floatx80 floatx80_round(floatx80 a, float_status *status) { - return roundAndPackFloatx80(status->floatx80_rounding_precision, - extractFloatx80Sign(a), - extractFloatx80Exp(a), - extractFloatx80Frac(a), 0, status); -} - -/*---------------------------------------------------------------------------- -| Rounds the extended double-precision floating-point value `a' to an integer, -| and returns the result as an extended quadruple-precision floating-point -| value. The operation is performed according to the IEC/IEEE Standard for -| Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_round_to_int(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t lastBitMask, roundBitsMask; - floatx80 z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aExp = extractFloatx80Exp( a ); - if ( 0x403E <= aExp ) { - if ( ( aExp == 0x7FFF ) && (uint64_t) ( extractFloatx80Frac( a )<<1 ) ) { - return propagateFloatx80NaN(a, a, status); - } - return a; - } - if ( aExp < 0x3FFF ) { - if ( ( aExp == 0 ) - && ( (uint64_t) ( extractFloatx80Frac( a ) ) == 0 ) ) { - return a; - } - float_raise(float_flag_inexact, status); - aSign = extractFloatx80Sign( a ); - switch (status->float_rounding_mode) { - case float_round_nearest_even: - if ( ( aExp == 0x3FFE ) && (uint64_t) ( extractFloatx80Frac( a )<<1 ) - ) { - return - packFloatx80( aSign, 0x3FFF, UINT64_C(0x8000000000000000)); - } - break; - case float_round_ties_away: - if (aExp == 0x3FFE) { - return packFloatx80(aSign, 0x3FFF, UINT64_C(0x8000000000000000)); - } - break; - case float_round_down: - return - aSign ? - packFloatx80( 1, 0x3FFF, UINT64_C(0x8000000000000000)) - : packFloatx80( 0, 0, 0 ); - case float_round_up: - return - aSign ? packFloatx80( 1, 0, 0 ) - : packFloatx80( 0, 0x3FFF, UINT64_C(0x8000000000000000)); - - case float_round_to_zero: - break; - default: - g_assert_not_reached(); - } - return packFloatx80( aSign, 0, 0 ); - } - lastBitMask = 1; - lastBitMask <<= 0x403E - aExp; - roundBitsMask = lastBitMask - 1; - z = a; - switch (status->float_rounding_mode) { - case float_round_nearest_even: - z.low += lastBitMask>>1; - if ((z.low & roundBitsMask) == 0) { - z.low &= ~lastBitMask; - } - break; - case float_round_ties_away: - z.low += lastBitMask >> 1; - break; - case float_round_to_zero: - break; - case float_round_up: - if (!extractFloatx80Sign(z)) { - z.low += roundBitsMask; - } - break; - case float_round_down: - if (extractFloatx80Sign(z)) { - z.low += roundBitsMask; - } - break; - default: - abort(); - } - z.low &= ~ roundBitsMask; - if ( z.low == 0 ) { - ++z.high; - z.low = UINT64_C(0x8000000000000000); - } - if (z.low != a.low) { - float_raise(float_flag_inexact, status); - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the absolute values of the extended double- -| precision floating-point values `a' and `b'. If `zSign' is 1, the sum is -| negated before being returned. `zSign' is ignored if the result is a NaN. -| The addition is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static floatx80 addFloatx80Sigs(floatx80 a, floatx80 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - int32_t expDiff; - - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) { - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) --expDiff; - shift64ExtraRightJamming( bSig, 0, expDiff, &bSig, &zSig1 ); - zExp = aExp; - } - else if ( expDiff < 0 ) { - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80(zSign, - floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) ++expDiff; - shift64ExtraRightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); - zExp = bExp; - } - else { - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - zSig1 = 0; - zSig0 = aSig + bSig; - if ( aExp == 0 ) { - if ((aSig | bSig) & UINT64_C(0x8000000000000000) && zSig0 < aSig) { - /* At least one of the values is a pseudo-denormal, - * and there is a carry out of the result. */ - zExp = 1; - goto shiftRight1; - } - if (zSig0 == 0) { - return packFloatx80(zSign, 0, 0); - } - normalizeFloatx80Subnormal( zSig0, &zExp, &zSig0 ); - goto roundAndPack; - } - zExp = aExp; - goto shiftRight1; - } - zSig0 = aSig + bSig; - if ( (int64_t) zSig0 < 0 ) goto roundAndPack; - shiftRight1: - shift64ExtraRightJamming( zSig0, zSig1, 1, &zSig0, &zSig1 ); - zSig0 |= UINT64_C(0x8000000000000000); - ++zExp; - roundAndPack: - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the absolute values of the extended -| double-precision floating-point values `a' and `b'. If `zSign' is 1, the -| difference is negated before being returned. `zSign' is ignored if the -| result is a NaN. The subtraction is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static floatx80 subFloatx80Sigs(floatx80 a, floatx80 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - int32_t expDiff; - - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) goto aExpBigger; - if ( expDiff < 0 ) goto bExpBigger; - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) { - return propagateFloatx80NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - if ( aExp == 0 ) { - aExp = 1; - bExp = 1; - } - zSig1 = 0; - if ( bSig < aSig ) goto aBigger; - if ( aSig < bSig ) goto bBigger; - return packFloatx80(status->float_rounding_mode == float_round_down, 0, 0); - bExpBigger: - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80(zSign ^ 1, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) ++expDiff; - shift128RightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); - bBigger: - sub128( bSig, 0, aSig, zSig1, &zSig0, &zSig1 ); - zExp = bExp; - zSign ^= 1; - goto normalizeRoundAndPack; - aExpBigger: - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) --expDiff; - shift128RightJamming( bSig, 0, expDiff, &bSig, &zSig1 ); - aBigger: - sub128( aSig, 0, bSig, zSig1, &zSig0, &zSig1 ); - zExp = aExp; - normalizeRoundAndPack: - return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the extended double-precision floating-point -| values `a' and `b'. The operation is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign == bSign ) { - return addFloatx80Sigs(a, b, aSign, status); - } - else { - return subFloatx80Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the extended double-precision floating- -| point values `a' and `b'. The operation is performed according to the -| IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign == bSign ) { - return subFloatx80Sigs(a, b, aSign, status); - } - else { - return addFloatx80Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of multiplying the extended double-precision floating- -| point values `a' and `b'. The operation is performed according to the -| IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_mul(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign, zSign; - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - bSign = extractFloatx80Sign( b ); - zSign = aSign ^ bSign; - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig<<1 ) - || ( ( bExp == 0x7FFF ) && (uint64_t) ( bSig<<1 ) ) ) { - return propagateFloatx80NaN(a, b, status); - } - if ( ( bExp | bSig ) == 0 ) goto invalid; - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - if ( ( aExp | aSig ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( zSign, 0, 0 ); - normalizeFloatx80Subnormal( aSig, &aExp, &aSig ); - } - if ( bExp == 0 ) { - if ( bSig == 0 ) return packFloatx80( zSign, 0, 0 ); - normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); - } - zExp = aExp + bExp - 0x3FFE; - mul64To128( aSig, bSig, &zSig0, &zSig1 ); - if ( 0 < (int64_t) zSig0 ) { - shortShift128Left( zSig0, zSig1, 1, &zSig0, &zSig1 ); - --zExp; - } - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of dividing the extended double-precision floating-point -| value `a' by the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign, zSign; - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - uint64_t rem0, rem1, rem2, term0, term1, term2; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - bSign = extractFloatx80Sign( b ); - zSign = aSign ^ bSign; - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - goto invalid; - } - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80( zSign, 0, 0 ); - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - if ( ( aExp | aSig ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - float_raise(float_flag_divbyzero, status); - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( zSign, 0, 0 ); - normalizeFloatx80Subnormal( aSig, &aExp, &aSig ); - } - zExp = aExp - bExp + 0x3FFE; - rem1 = 0; - if ( bSig <= aSig ) { - shift128Right( aSig, 0, 1, &aSig, &rem1 ); - ++zExp; - } - zSig0 = estimateDiv128To64( aSig, rem1, bSig ); - mul64To128( bSig, zSig0, &term0, &term1 ); - sub128( aSig, rem1, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - add128( rem0, rem1, 0, bSig, &rem0, &rem1 ); - } - zSig1 = estimateDiv128To64( rem1, 0, bSig ); - if ( (uint64_t) ( zSig1<<1 ) <= 8 ) { - mul64To128( bSig, zSig1, &term1, &term2 ); - sub128( rem1, 0, term1, term2, &rem1, &rem2 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - add128( rem1, rem2, 0, bSig, &rem1, &rem2 ); - } - zSig1 |= ( ( rem1 | rem2 ) != 0 ); - } - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the extended double-precision floating-point value -| `a' with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic, -| if 'mod' is false; if 'mod' is true, return the remainder based on truncating -| the quotient toward zero instead. '*quotient' is set to the low 64 bits of -| the absolute value of the integer quotient. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_modrem(floatx80 a, floatx80 b, bool mod, uint64_t *quotient, - float_status *status) -{ - bool aSign, zSign; - int32_t aExp, bExp, expDiff, aExpOrig; - uint64_t aSig0, aSig1, bSig; - uint64_t q, term0, term1, alternateASig0, alternateASig1; - - *quotient = 0; - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig0 = extractFloatx80Frac( a ); - aExpOrig = aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig0<<1 ) - || ( ( bExp == 0x7FFF ) && (uint64_t) ( bSig<<1 ) ) ) { - return propagateFloatx80NaN(a, b, status); - } - goto invalid; - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - if (aExp == 0 && aSig0 >> 63) { - /* - * Pseudo-denormal argument must be returned in normalized - * form. - */ - return packFloatx80(aSign, 1, aSig0); - } - return a; - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig0 == 0 ) return a; - normalizeFloatx80Subnormal( aSig0, &aExp, &aSig0 ); - } - zSign = aSign; - expDiff = aExp - bExp; - aSig1 = 0; - if ( expDiff < 0 ) { - if ( mod || expDiff < -1 ) { - if (aExp == 1 && aExpOrig == 0) { - /* - * Pseudo-denormal argument must be returned in - * normalized form. - */ - return packFloatx80(aSign, aExp, aSig0); - } - return a; - } - shift128Right( aSig0, 0, 1, &aSig0, &aSig1 ); - expDiff = 0; - } - *quotient = q = ( bSig <= aSig0 ); - if ( q ) aSig0 -= bSig; - expDiff -= 64; - while ( 0 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - mul64To128( bSig, q, &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &aSig0, &aSig1 ); - shortShift128Left( aSig0, aSig1, 62, &aSig0, &aSig1 ); - expDiff -= 62; - *quotient <<= 62; - *quotient += q; - } - expDiff += 64; - if ( 0 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - q >>= 64 - expDiff; - mul64To128( bSig, q<<( 64 - expDiff ), &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &aSig0, &aSig1 ); - shortShift128Left( 0, bSig, 64 - expDiff, &term0, &term1 ); - while ( le128( term0, term1, aSig0, aSig1 ) ) { - ++q; - sub128( aSig0, aSig1, term0, term1, &aSig0, &aSig1 ); - } - if (expDiff < 64) { - *quotient <<= expDiff; - } else { - *quotient = 0; - } - *quotient += q; - } - else { - term1 = 0; - term0 = bSig; - } - if (!mod) { - sub128( term0, term1, aSig0, aSig1, &alternateASig0, &alternateASig1 ); - if ( lt128( alternateASig0, alternateASig1, aSig0, aSig1 ) - || ( eq128( alternateASig0, alternateASig1, aSig0, aSig1 ) - && ( q & 1 ) ) - ) { - aSig0 = alternateASig0; - aSig1 = alternateASig1; - zSign = ! zSign; - ++*quotient; - } - } - return - normalizeRoundAndPackFloatx80( - 80, zSign, bExp + expDiff, aSig0, aSig1, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the extended double-precision floating-point value -| `a' with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_rem(floatx80 a, floatx80 b, float_status *status) -{ - uint64_t quotient; - return floatx80_modrem(a, b, false, "ient, status); -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the extended double-precision floating-point value -| `a' with respect to the corresponding value `b', with the quotient truncated -| toward zero. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status) -{ - uint64_t quotient; - return floatx80_modrem(a, b, true, "ient, status); -} - -/*---------------------------------------------------------------------------- -| Returns the square root of the extended double-precision floating-point -| value `a'. The operation is performed according to the IEC/IEEE Standard -| for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_sqrt(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, zExp; - uint64_t aSig0, aSig1, zSig0, zSig1, doubleZSig0; - uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig0 = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig0 << 1)) { - return propagateFloatx80NaN(a, a, status); - } - if ( ! aSign ) return a; - goto invalid; - } - if ( aSign ) { - if ( ( aExp | aSig0 ) == 0 ) return a; - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - if ( aExp == 0 ) { - if ( aSig0 == 0 ) return packFloatx80( 0, 0, 0 ); - normalizeFloatx80Subnormal( aSig0, &aExp, &aSig0 ); - } - zExp = ( ( aExp - 0x3FFF )>>1 ) + 0x3FFF; - zSig0 = estimateSqrt32( aExp, aSig0>>32 ); - shift128Right( aSig0, 0, 2 + ( aExp & 1 ), &aSig0, &aSig1 ); - zSig0 = estimateDiv128To64( aSig0, aSig1, zSig0<<32 ) + ( zSig0<<30 ); - doubleZSig0 = zSig0<<1; - mul64To128( zSig0, zSig0, &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - doubleZSig0 -= 2; - add128( rem0, rem1, zSig0>>63, doubleZSig0 | 1, &rem0, &rem1 ); - } - zSig1 = estimateDiv128To64( rem1, 0, doubleZSig0 ); - if ( ( zSig1 & UINT64_C(0x3FFFFFFFFFFFFFFF) ) <= 5 ) { - if ( zSig1 == 0 ) zSig1 = 1; - mul64To128( doubleZSig0, zSig1, &term1, &term2 ); - sub128( rem1, 0, term1, term2, &rem1, &rem2 ); - mul64To128( zSig1, zSig1, &term2, &term3 ); - sub192( rem1, rem2, 0, 0, term2, term3, &rem1, &rem2, &rem3 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - shortShift128Left( 0, zSig1, 1, &term2, &term3 ); - term3 |= 1; - term2 |= doubleZSig0; - add192( rem1, rem2, rem3, 0, term2, term3, &rem1, &rem2, &rem3 ); - } - zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 ); - } - shortShift128Left( 0, zSig1, 1, &zSig0, &zSig1 ); - zSig0 |= doubleZSig0; - return roundAndPackFloatx80(status->floatx80_rounding_precision, - 0, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point value -| `a' to the 64-bit unsigned integer format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic---which means in particular that the conversion is rounded -| according to the current rounding mode. If `a' is a NaN, the largest -| positive integer is returned. If the conversion overflows, the -| largest unsigned integer is returned. If 'a' is negative, the value is -| rounded and zero is returned; negative values that do not round to zero -| will raise the inexact exception. -*----------------------------------------------------------------------------*/ - -uint64_t float128_to_uint64(float128 a, float_status *status) -{ - bool aSign; - int aExp; - int shiftCount; - uint64_t aSig0, aSig1; - - aSig0 = extractFloat128Frac0(a); - aSig1 = extractFloat128Frac1(a); - aExp = extractFloat128Exp(a); - aSign = extractFloat128Sign(a); - if (aSign && (aExp > 0x3FFE)) { - float_raise(float_flag_invalid, status); - if (float128_is_any_nan(a)) { - return UINT64_MAX; - } else { - return 0; - } - } - if (aExp) { - aSig0 |= UINT64_C(0x0001000000000000); - } - shiftCount = 0x402F - aExp; - if (shiftCount <= 0) { - if (0x403E < aExp) { - float_raise(float_flag_invalid, status); - return UINT64_MAX; - } - shortShift128Left(aSig0, aSig1, -shiftCount, &aSig0, &aSig1); - } else { - shift64ExtraRightJamming(aSig0, aSig1, shiftCount, &aSig0, &aSig1); - } - return roundAndPackUint64(aSign, aSig0, aSig1, status); -} - -uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *status) -{ - uint64_t v; - signed char current_rounding_mode = status->float_rounding_mode; - - set_float_rounding_mode(float_round_to_zero, status); - v = float128_to_uint64(a, status); - set_float_rounding_mode(current_rounding_mode, status); - - return v; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the 32-bit unsigned integer format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic except that the conversion is always rounded toward zero. -| If `a' is a NaN, the largest positive integer is returned. Otherwise, -| if the conversion overflows, the largest unsigned integer is returned. -| If 'a' is negative, the value is rounded and zero is returned; negative -| values that do not round to zero will raise the inexact exception. -*----------------------------------------------------------------------------*/ - -uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *status) -{ - uint64_t v; - uint32_t res; - int old_exc_flags = get_float_exception_flags(status); - - v = float128_to_uint64_round_to_zero(a, status); - if (v > 0xffffffff) { - res = 0xffffffff; - } else { - return v; - } - set_float_exception_flags(old_exc_flags, status); - float_raise(float_flag_invalid, status); - return res; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point value -| `a' to the 32-bit unsigned integer format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic---which means in particular that the conversion is rounded -| according to the current rounding mode. If `a' is a NaN, the largest -| positive integer is returned. If the conversion overflows, the -| largest unsigned integer is returned. If 'a' is negative, the value is -| rounded and zero is returned; negative values that do not round to zero -| will raise the inexact exception. -*----------------------------------------------------------------------------*/ - -uint32_t float128_to_uint32(float128 a, float_status *status) -{ - uint64_t v; - uint32_t res; - int old_exc_flags = get_float_exception_flags(status); - - v = float128_to_uint64(a, status); - if (v > 0xffffffff) { - res = 0xffffffff; - } else { - return v; - } - set_float_exception_flags(old_exc_flags, status); - float_raise(float_flag_invalid, status); - return res; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the extended double-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 float128_to_floatx80(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 ) { - floatx80 res = commonNaNToFloatx80(float128ToCommonNaN(a, status), - status); - return floatx80_silence_nan(res, status); - } - return packFloatx80(aSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return packFloatx80( aSign, 0, 0 ); - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - else { - aSig0 |= UINT64_C(0x0001000000000000); - } - shortShift128Left( aSig0, aSig1, 15, &aSig0, &aSig1 ); - return roundAndPackFloatx80(80, aSign, aExp, aSig0, aSig1, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the quadruple-precision floating-point value `a' -| with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_rem(float128 a, float128 b, float_status *status) -{ - bool aSign, zSign; - int32_t aExp, bExp, expDiff; - uint64_t aSig0, aSig1, bSig0, bSig1, q, term0, term1, term2; - uint64_t allZero, alternateASig0, alternateASig1, sigMean1; - int64_t sigMean0; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - bSig1 = extractFloat128Frac1( b ); - bSig0 = extractFloat128Frac0( b ); - bExp = extractFloat128Exp( b ); - if ( aExp == 0x7FFF ) { - if ( ( aSig0 | aSig1 ) - || ( ( bExp == 0x7FFF ) && ( bSig0 | bSig1 ) ) ) { - return propagateFloat128NaN(a, b, status); - } - goto invalid; - } - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - if ( ( bSig0 | bSig1 ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - normalizeFloat128Subnormal( bSig0, bSig1, &bExp, &bSig0, &bSig1 ); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return a; - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - expDiff = aExp - bExp; - if ( expDiff < -1 ) return a; - shortShift128Left( - aSig0 | UINT64_C(0x0001000000000000), - aSig1, - 15 - ( expDiff < 0 ), - &aSig0, - &aSig1 - ); - shortShift128Left( - bSig0 | UINT64_C(0x0001000000000000), bSig1, 15, &bSig0, &bSig1 ); - q = le128( bSig0, bSig1, aSig0, aSig1 ); - if ( q ) sub128( aSig0, aSig1, bSig0, bSig1, &aSig0, &aSig1 ); - expDiff -= 64; - while ( 0 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig0 ); - q = ( 4 < q ) ? q - 4 : 0; - mul128By64To192( bSig0, bSig1, q, &term0, &term1, &term2 ); - shortShift192Left( term0, term1, term2, 61, &term1, &term2, &allZero ); - shortShift128Left( aSig0, aSig1, 61, &aSig0, &allZero ); - sub128( aSig0, 0, term1, term2, &aSig0, &aSig1 ); - expDiff -= 61; - } - if ( -64 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig0 ); - q = ( 4 < q ) ? q - 4 : 0; - q >>= - expDiff; - shift128Right( bSig0, bSig1, 12, &bSig0, &bSig1 ); - expDiff += 52; - if ( expDiff < 0 ) { - shift128Right( aSig0, aSig1, - expDiff, &aSig0, &aSig1 ); - } - else { - shortShift128Left( aSig0, aSig1, expDiff, &aSig0, &aSig1 ); - } - mul128By64To192( bSig0, bSig1, q, &term0, &term1, &term2 ); - sub128( aSig0, aSig1, term1, term2, &aSig0, &aSig1 ); - } - else { - shift128Right( aSig0, aSig1, 12, &aSig0, &aSig1 ); - shift128Right( bSig0, bSig1, 12, &bSig0, &bSig1 ); - } - do { - alternateASig0 = aSig0; - alternateASig1 = aSig1; - ++q; - sub128( aSig0, aSig1, bSig0, bSig1, &aSig0, &aSig1 ); - } while ( 0 <= (int64_t) aSig0 ); - add128( - aSig0, aSig1, alternateASig0, alternateASig1, (uint64_t *)&sigMean0, &sigMean1 ); - if ( ( sigMean0 < 0 ) - || ( ( ( sigMean0 | sigMean1 ) == 0 ) && ( q & 1 ) ) ) { - aSig0 = alternateASig0; - aSig1 = alternateASig1; - } - zSign = ( (int64_t) aSig0 < 0 ); - if ( zSign ) sub128( 0, 0, aSig0, aSig1, &aSig0, &aSig1 ); - return normalizeRoundAndPackFloat128(aSign ^ zSign, bExp - 4, aSig0, aSig1, - status); -} - -/*---------------------------------------------------------------------------- -| Returns the square root of the quadruple-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_sqrt(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp, zExp; - uint64_t aSig0, aSig1, zSig0, zSig1, zSig2, doubleZSig0; - uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if (aSig0 | aSig1) { - return propagateFloat128NaN(a, a, status); - } - if ( ! aSign ) return a; - goto invalid; - } - if ( aSign ) { - if ( ( aExp | aSig0 | aSig1 ) == 0 ) return a; - invalid: - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return packFloat128( 0, 0, 0, 0 ); - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - zExp = ( ( aExp - 0x3FFF )>>1 ) + 0x3FFE; - aSig0 |= UINT64_C(0x0001000000000000); - zSig0 = estimateSqrt32( aExp, aSig0>>17 ); - shortShift128Left( aSig0, aSig1, 13 - ( aExp & 1 ), &aSig0, &aSig1 ); - zSig0 = estimateDiv128To64( aSig0, aSig1, zSig0<<32 ) + ( zSig0<<30 ); - doubleZSig0 = zSig0<<1; - mul64To128( zSig0, zSig0, &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - doubleZSig0 -= 2; - add128( rem0, rem1, zSig0>>63, doubleZSig0 | 1, &rem0, &rem1 ); - } - zSig1 = estimateDiv128To64( rem1, 0, doubleZSig0 ); - if ( ( zSig1 & 0x1FFF ) <= 5 ) { - if ( zSig1 == 0 ) zSig1 = 1; - mul64To128( doubleZSig0, zSig1, &term1, &term2 ); - sub128( rem1, 0, term1, term2, &rem1, &rem2 ); - mul64To128( zSig1, zSig1, &term2, &term3 ); - sub192( rem1, rem2, 0, 0, term2, term3, &rem1, &rem2, &rem3 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - shortShift128Left( 0, zSig1, 1, &term2, &term3 ); - term3 |= 1; - term2 |= doubleZSig0; - add192( rem1, rem2, rem3, 0, term2, term3, &rem1, &rem2, &rem3 ); - } - zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 ); - } - shift128ExtraRightJamming( zSig0, zSig1, 0, 14, &zSig0, &zSig1, &zSig2 ); - return roundAndPackFloat128(0, zExp, zSig0, zSig1, zSig2, status); - -} - -static inline FloatRelation -floatx80_compare_internal(floatx80 a, floatx80 b, bool is_quiet, - float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return float_relation_unordered; - } - if (( ( extractFloatx80Exp( a ) == 0x7fff ) && - ( extractFloatx80Frac( a )<<1 ) ) || - ( ( extractFloatx80Exp( b ) == 0x7fff ) && - ( extractFloatx80Frac( b )<<1 ) )) { - if (!is_quiet || - floatx80_is_signaling_nan(a, status) || - floatx80_is_signaling_nan(b, status)) { - float_raise(float_flag_invalid, status); - } - return float_relation_unordered; - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign != bSign ) { - - if ( ( ( (uint16_t) ( ( a.high | b.high ) << 1 ) ) == 0) && - ( ( a.low | b.low ) == 0 ) ) { - /* zero case */ - return float_relation_equal; - } else { - return 1 - (2 * aSign); - } - } else { - /* Normalize pseudo-denormals before comparison. */ - if ((a.high & 0x7fff) == 0 && a.low & UINT64_C(0x8000000000000000)) { - ++a.high; - } - if ((b.high & 0x7fff) == 0 && b.low & UINT64_C(0x8000000000000000)) { - ++b.high; - } - if (a.low == b.low && a.high == b.high) { - return float_relation_equal; - } else { - return 1 - 2 * (aSign ^ ( lt128( a.high, a.low, b.high, b.low ) )); - } - } -} - -FloatRelation floatx80_compare(floatx80 a, floatx80 b, float_status *status) -{ - return floatx80_compare_internal(a, b, 0, status); -} - -FloatRelation floatx80_compare_quiet(floatx80 a, floatx80 b, - float_status *status) -{ - return floatx80_compare_internal(a, b, 1, status); -} - -static inline FloatRelation -float128_compare_internal(float128 a, float128 b, bool is_quiet, - float_status *status) -{ - bool aSign, bSign; - - if (( ( extractFloat128Exp( a ) == 0x7fff ) && - ( extractFloat128Frac0( a ) | extractFloat128Frac1( a ) ) ) || - ( ( extractFloat128Exp( b ) == 0x7fff ) && - ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )) { - if (!is_quiet || - float128_is_signaling_nan(a, status) || - float128_is_signaling_nan(b, status)) { - float_raise(float_flag_invalid, status); - } - return float_relation_unordered; - } - aSign = extractFloat128Sign( a ); - bSign = extractFloat128Sign( b ); - if ( aSign != bSign ) { - if ( ( ( ( a.high | b.high )<<1 ) | a.low | b.low ) == 0 ) { - /* zero case */ - return float_relation_equal; - } else { - return 1 - (2 * aSign); - } - } else { - if (a.low == b.low && a.high == b.high) { - return float_relation_equal; - } else { - return 1 - 2 * (aSign ^ ( lt128( a.high, a.low, b.high, b.low ) )); - } - } -} - -FloatRelation float128_compare(float128 a, float128 b, float_status *status) -{ - return float128_compare_internal(a, b, 0, status); -} - -FloatRelation float128_compare_quiet(float128 a, float128 b, - float_status *status) -{ - return float128_compare_internal(a, b, 1, status); -} - -floatx80 floatx80_scalbn(floatx80 a, int n, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig; + FloatParts128 p; - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); + if (!floatx80_unpack_canonical(&p, a, status)) { return floatx80_default_nan(status); } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - - if ( aExp == 0x7FFF ) { - if ( aSig<<1 ) { - return propagateFloatx80NaN(a, a, status); - } - return a; - } - - if (aExp == 0) { - if (aSig == 0) { - return a; - } - aExp++; - } - - if (n > 0x10000) { - n = 0x10000; - } else if (n < -0x10000) { - n = -0x10000; - } - - aExp += n; - return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision, - aSign, aExp, aSig, 0, status); -} - -float128 float128_scalbn(float128 a, int n, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 ) { - return propagateFloat128NaN(a, a, status); - } - return a; - } - if (aExp != 0) { - aSig0 |= UINT64_C(0x0001000000000000); - } else if (aSig0 == 0 && aSig1 == 0) { - return a; - } else { - aExp++; - } - - if (n > 0x10000) { - n = 0x10000; - } else if (n < -0x10000) { - n = -0x10000; - } - - aExp += n - 1; - return normalizeRoundAndPackFloat128( aSign, aExp, aSig0, aSig1 - , status); - + return floatx80_round_pack_canonical(&p, status); } static void __attribute__((constructor)) softfloat_init(void) @@ -465,6 +465,15 @@ int use_gdb_syscalls(void) return gdb_syscall_mode == GDB_SYS_ENABLED; } +static bool stub_can_reverse(void) +{ +#ifdef CONFIG_USER_ONLY + return false; +#else + return replay_mode == REPLAY_MODE_PLAY; +#endif +} + /* Resume execution. */ static inline void gdb_continue(void) { @@ -1338,6 +1347,8 @@ typedef union GdbCmdVariant { } thread_id; } GdbCmdVariant; +#define get_param(p, i) (&g_array_index(p, GdbCmdVariant, i)) + static const char *cmd_next_param(const char *param, const char delimiter) { static const char all_delimiters[] = ",;:="; @@ -1363,55 +1374,52 @@ static const char *cmd_next_param(const char *param, const char delimiter) } static int cmd_parse_params(const char *data, const char *schema, - GdbCmdVariant *params, int *num_params) + GArray *params) { - int curr_param; const char *curr_schema, *curr_data; - *num_params = 0; - - if (!schema) { - return 0; - } + g_assert(schema); + g_assert(params->len == 0); curr_schema = schema; - curr_param = 0; curr_data = data; while (curr_schema[0] && curr_schema[1] && *curr_data) { + GdbCmdVariant this_param; + switch (curr_schema[0]) { case 'l': if (qemu_strtoul(curr_data, &curr_data, 16, - ¶ms[curr_param].val_ul)) { + &this_param.val_ul)) { return -EINVAL; } - curr_param++; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 'L': if (qemu_strtou64(curr_data, &curr_data, 16, - (uint64_t *)¶ms[curr_param].val_ull)) { + (uint64_t *)&this_param.val_ull)) { return -EINVAL; } - curr_param++; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 's': - params[curr_param].data = curr_data; - curr_param++; + this_param.data = curr_data; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 'o': - params[curr_param].opcode = *(uint8_t *)curr_data; - curr_param++; + this_param.opcode = *(uint8_t *)curr_data; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 't': - params[curr_param].thread_id.kind = + this_param.thread_id.kind = read_thread_id(curr_data, &curr_data, - ¶ms[curr_param].thread_id.pid, - ¶ms[curr_param].thread_id.tid); - curr_param++; + &this_param.thread_id.pid, + &this_param.thread_id.tid); curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case '?': curr_data = cmd_next_param(curr_data, curr_schema[1]); @@ -1422,16 +1430,10 @@ static int cmd_parse_params(const char *data, const char *schema, curr_schema += 2; } - *num_params = curr_param; return 0; } -typedef struct GdbCmdContext { - GdbCmdVariant *params; - int num_params; -} GdbCmdContext; - -typedef void (*GdbCmdHandler)(GdbCmdContext *gdb_ctx, void *user_ctx); +typedef void (*GdbCmdHandler)(GArray *params, void *user_ctx); /* * cmd_startswith -> cmd is compared using startswith @@ -1471,8 +1473,8 @@ static inline int startswith(const char *string, const char *pattern) static int process_string_cmd(void *user_ctx, const char *data, const GdbCmdParseEntry *cmds, int num_cmds) { - int i, schema_len, max_num_params = 0; - GdbCmdContext gdb_ctx; + int i; + g_autoptr(GArray) params = g_array_new(false, true, sizeof(GdbCmdVariant)); if (!cmds) { return -1; @@ -1488,24 +1490,13 @@ static int process_string_cmd(void *user_ctx, const char *data, } if (cmd->schema) { - schema_len = strlen(cmd->schema); - if (schema_len % 2) { - return -2; + if (cmd_parse_params(&data[strlen(cmd->cmd)], + cmd->schema, params)) { + return -1; } - - max_num_params = schema_len / 2; - } - - gdb_ctx.params = - (GdbCmdVariant *)alloca(sizeof(*gdb_ctx.params) * max_num_params); - memset(gdb_ctx.params, 0, sizeof(*gdb_ctx.params) * max_num_params); - - if (cmd_parse_params(&data[strlen(cmd->cmd)], cmd->schema, - gdb_ctx.params, &gdb_ctx.num_params)) { - return -1; } - cmd->handler(&gdb_ctx, user_ctx); + cmd->handler(params, user_ctx); return 0; } @@ -1528,18 +1519,18 @@ static void run_cmd_parser(const char *data, const GdbCmdParseEntry *cmd) } } -static void handle_detach(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_detach(GArray *params, void *user_ctx) { GDBProcess *process; uint32_t pid = 1; if (gdbserver_state.multiprocess) { - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - pid = gdb_ctx->params[0].val_ul; + pid = get_param(params, 0)->val_ul; } process = gdb_get_process(pid); @@ -1562,22 +1553,22 @@ static void handle_detach(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_thread_alive(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_thread_alive(GArray *params, void *user_ctx) { CPUState *cpu; - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - if (gdb_ctx->params[0].thread_id.kind == GDB_READ_THREAD_ERR) { + if (get_param(params, 0)->thread_id.kind == GDB_READ_THREAD_ERR) { put_packet("E22"); return; } - cpu = gdb_get_cpu(gdb_ctx->params[0].thread_id.pid, - gdb_ctx->params[0].thread_id.tid); + cpu = gdb_get_cpu(get_param(params, 0)->thread_id.pid, + get_param(params, 0)->thread_id.tid); if (!cpu) { put_packet("E22"); return; @@ -1586,17 +1577,17 @@ static void handle_thread_alive(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_continue(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_continue(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params) { - gdb_set_cpu_pc(gdb_ctx->params[0].val_ull); + if (params->len) { + gdb_set_cpu_pc(get_param(params, 0)->val_ull); } gdbserver_state.signal = 0; gdb_continue(); } -static void handle_cont_with_sig(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_cont_with_sig(GArray *params, void *user_ctx) { unsigned long signal = 0; @@ -1604,8 +1595,8 @@ static void handle_cont_with_sig(GdbCmdContext *gdb_ctx, void *user_ctx) * Note: C sig;[addr] is currently unsupported and we simply * omit the addr parameter */ - if (gdb_ctx->num_params) { - signal = gdb_ctx->params[0].val_ul; + if (params->len) { + signal = get_param(params, 0)->val_ul; } gdbserver_state.signal = gdb_signal_to_target(signal); @@ -1615,27 +1606,27 @@ static void handle_cont_with_sig(GdbCmdContext *gdb_ctx, void *user_ctx) gdb_continue(); } -static void handle_set_thread(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_thread(GArray *params, void *user_ctx) { CPUState *cpu; - if (gdb_ctx->num_params != 2) { + if (params->len != 2) { put_packet("E22"); return; } - if (gdb_ctx->params[1].thread_id.kind == GDB_READ_THREAD_ERR) { + if (get_param(params, 1)->thread_id.kind == GDB_READ_THREAD_ERR) { put_packet("E22"); return; } - if (gdb_ctx->params[1].thread_id.kind != GDB_ONE_THREAD) { + if (get_param(params, 1)->thread_id.kind != GDB_ONE_THREAD) { put_packet("OK"); return; } - cpu = gdb_get_cpu(gdb_ctx->params[1].thread_id.pid, - gdb_ctx->params[1].thread_id.tid); + cpu = gdb_get_cpu(get_param(params, 1)->thread_id.pid, + get_param(params, 1)->thread_id.tid); if (!cpu) { put_packet("E22"); return; @@ -1645,7 +1636,7 @@ static void handle_set_thread(GdbCmdContext *gdb_ctx, void *user_ctx) * Note: This command is deprecated and modern gdb's will be using the * vCont command instead. */ - switch (gdb_ctx->params[0].opcode) { + switch (get_param(params, 0)->opcode) { case 'c': gdbserver_state.c_cpu = cpu; put_packet("OK"); @@ -1660,18 +1651,18 @@ static void handle_set_thread(GdbCmdContext *gdb_ctx, void *user_ctx) } } -static void handle_insert_bp(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_insert_bp(GArray *params, void *user_ctx) { int res; - if (gdb_ctx->num_params != 3) { + if (params->len != 3) { put_packet("E22"); return; } - res = gdb_breakpoint_insert(gdb_ctx->params[0].val_ul, - gdb_ctx->params[1].val_ull, - gdb_ctx->params[2].val_ull); + res = gdb_breakpoint_insert(get_param(params, 0)->val_ul, + get_param(params, 1)->val_ull, + get_param(params, 2)->val_ull); if (res >= 0) { put_packet("OK"); return; @@ -1683,18 +1674,18 @@ static void handle_insert_bp(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("E22"); } -static void handle_remove_bp(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_remove_bp(GArray *params, void *user_ctx) { int res; - if (gdb_ctx->num_params != 3) { + if (params->len != 3) { put_packet("E22"); return; } - res = gdb_breakpoint_remove(gdb_ctx->params[0].val_ul, - gdb_ctx->params[1].val_ull, - gdb_ctx->params[2].val_ull); + res = gdb_breakpoint_remove(get_param(params, 0)->val_ul, + get_param(params, 1)->val_ull, + get_param(params, 2)->val_ull); if (res >= 0) { put_packet("OK"); return; @@ -1717,7 +1708,7 @@ static void handle_remove_bp(GdbCmdContext *gdb_ctx, void *user_ctx) * the remote gdb to fallback to older methods. */ -static void handle_set_reg(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_reg(GArray *params, void *user_ctx) { int reg_size; @@ -1726,19 +1717,19 @@ static void handle_set_reg(GdbCmdContext *gdb_ctx, void *user_ctx) return; } - if (gdb_ctx->num_params != 2) { + if (params->len != 2) { put_packet("E22"); return; } - reg_size = strlen(gdb_ctx->params[1].data) / 2; - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[1].data, reg_size); + reg_size = strlen(get_param(params, 1)->data) / 2; + hextomem(gdbserver_state.mem_buf, get_param(params, 1)->data, reg_size); gdb_write_register(gdbserver_state.g_cpu, gdbserver_state.mem_buf->data, - gdb_ctx->params[0].val_ull); + get_param(params, 0)->val_ull); put_packet("OK"); } -static void handle_get_reg(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_get_reg(GArray *params, void *user_ctx) { int reg_size; @@ -1747,14 +1738,14 @@ static void handle_get_reg(GdbCmdContext *gdb_ctx, void *user_ctx) return; } - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E14"); return; } reg_size = gdb_read_register(gdbserver_state.g_cpu, gdbserver_state.mem_buf, - gdb_ctx->params[0].val_ull); + get_param(params, 0)->val_ull); if (!reg_size) { put_packet("E14"); return; @@ -1766,22 +1757,24 @@ static void handle_get_reg(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_write_mem(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_write_mem(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params != 3) { + if (params->len != 3) { put_packet("E22"); return; } /* hextomem() reads 2*len bytes */ - if (gdb_ctx->params[1].val_ull > strlen(gdb_ctx->params[2].data) / 2) { + if (get_param(params, 1)->val_ull > + strlen(get_param(params, 2)->data) / 2) { put_packet("E22"); return; } - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[2].data, - gdb_ctx->params[1].val_ull); - if (target_memory_rw_debug(gdbserver_state.g_cpu, gdb_ctx->params[0].val_ull, + hextomem(gdbserver_state.mem_buf, get_param(params, 2)->data, + get_param(params, 1)->val_ull); + if (target_memory_rw_debug(gdbserver_state.g_cpu, + get_param(params, 0)->val_ull, gdbserver_state.mem_buf->data, gdbserver_state.mem_buf->len, true)) { put_packet("E14"); @@ -1791,22 +1784,24 @@ static void handle_write_mem(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_read_mem(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_read_mem(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params != 2) { + if (params->len != 2) { put_packet("E22"); return; } /* memtohex() doubles the required space */ - if (gdb_ctx->params[1].val_ull > MAX_PACKET_LENGTH / 2) { + if (get_param(params, 1)->val_ull > MAX_PACKET_LENGTH / 2) { put_packet("E22"); return; } - g_byte_array_set_size(gdbserver_state.mem_buf, gdb_ctx->params[1].val_ull); + g_byte_array_set_size(gdbserver_state.mem_buf, + get_param(params, 1)->val_ull); - if (target_memory_rw_debug(gdbserver_state.g_cpu, gdb_ctx->params[0].val_ull, + if (target_memory_rw_debug(gdbserver_state.g_cpu, + get_param(params, 0)->val_ull, gdbserver_state.mem_buf->data, gdbserver_state.mem_buf->len, false)) { put_packet("E14"); @@ -1818,19 +1813,19 @@ static void handle_read_mem(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_write_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_write_all_regs(GArray *params, void *user_ctx) { target_ulong addr, len; uint8_t *registers; int reg_size; - if (!gdb_ctx->num_params) { + if (!params->len) { return; } cpu_synchronize_state(gdbserver_state.g_cpu); - len = strlen(gdb_ctx->params[0].data) / 2; - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[0].data, len); + len = strlen(get_param(params, 0)->data) / 2; + hextomem(gdbserver_state.mem_buf, get_param(params, 0)->data, len); registers = gdbserver_state.mem_buf->data; for (addr = 0; addr < gdbserver_state.g_cpu->gdb_num_g_regs && len > 0; addr++) { @@ -1841,7 +1836,7 @@ static void handle_write_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_read_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_read_all_regs(GArray *params, void *user_ctx) { target_ulong addr, len; @@ -1859,14 +1854,14 @@ static void handle_read_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_file_io(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_file_io(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params >= 1 && gdbserver_state.current_syscall_cb) { + if (params->len >= 1 && gdbserver_state.current_syscall_cb) { target_ulong ret, err; - ret = (target_ulong)gdb_ctx->params[0].val_ull; - if (gdb_ctx->num_params >= 2) { - err = (target_ulong)gdb_ctx->params[1].val_ull; + ret = (target_ulong)get_param(params, 0)->val_ull; + if (params->len >= 2) { + err = (target_ulong)get_param(params, 1)->val_ull; } else { err = 0; } @@ -1874,7 +1869,7 @@ static void handle_file_io(GdbCmdContext *gdb_ctx, void *user_ctx) gdbserver_state.current_syscall_cb = NULL; } - if (gdb_ctx->num_params >= 3 && gdb_ctx->params[2].opcode == (uint8_t)'C') { + if (params->len >= 3 && get_param(params, 2)->opcode == (uint8_t)'C') { put_packet("T02"); return; } @@ -1882,23 +1877,23 @@ static void handle_file_io(GdbCmdContext *gdb_ctx, void *user_ctx) gdb_continue(); } -static void handle_step(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_step(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params) { - gdb_set_cpu_pc((target_ulong)gdb_ctx->params[0].val_ull); + if (params->len) { + gdb_set_cpu_pc((target_ulong)get_param(params, 0)->val_ull); } cpu_single_step(gdbserver_state.c_cpu, get_sstep_flags()); gdb_continue(); } -static void handle_backward(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_backward(GArray *params, void *user_ctx) { - if (replay_mode != REPLAY_MODE_PLAY) { + if (!stub_can_reverse()) { put_packet("E22"); } - if (gdb_ctx->num_params == 1) { - switch (gdb_ctx->params[0].opcode) { + if (params->len == 1) { + switch (get_param(params, 0)->opcode) { case 's': if (replay_reverse_step()) { gdb_continue(); @@ -1920,20 +1915,20 @@ static void handle_backward(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet(""); } -static void handle_v_cont_query(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_cont_query(GArray *params, void *user_ctx) { put_packet("vCont;c;C;s;S"); } -static void handle_v_cont(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_cont(GArray *params, void *user_ctx) { int res; - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - res = gdb_handle_vcont(gdb_ctx->params[0].data); + res = gdb_handle_vcont(get_param(params, 0)->data); if ((res == -EINVAL) || (res == -ERANGE)) { put_packet("E22"); } else if (res) { @@ -1941,17 +1936,17 @@ static void handle_v_cont(GdbCmdContext *gdb_ctx, void *user_ctx) } } -static void handle_v_attach(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_attach(GArray *params, void *user_ctx) { GDBProcess *process; CPUState *cpu; g_string_assign(gdbserver_state.str_buf, "E22"); - if (!gdb_ctx->num_params) { + if (!params->len) { goto cleanup; } - process = gdb_get_process(gdb_ctx->params[0].val_ul); + process = gdb_get_process(get_param(params, 0)->val_ul); if (!process) { goto cleanup; } @@ -1972,7 +1967,7 @@ cleanup: put_strbuf(); } -static void handle_v_kill(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_kill(GArray *params, void *user_ctx) { /* Kill the target */ put_packet("OK"); @@ -1981,7 +1976,7 @@ static void handle_v_kill(GdbCmdContext *gdb_ctx, void *user_ctx) exit(0); } -static GdbCmdParseEntry gdb_v_commands_table[] = { +static const GdbCmdParseEntry gdb_v_commands_table[] = { /* Order is important if has same prefix */ { .handler = handle_v_cont_query, @@ -2007,43 +2002,43 @@ static GdbCmdParseEntry gdb_v_commands_table[] = { }, }; -static void handle_v_commands(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_commands(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - if (process_string_cmd(NULL, gdb_ctx->params[0].data, + if (process_string_cmd(NULL, get_param(params, 0)->data, gdb_v_commands_table, ARRAY_SIZE(gdb_v_commands_table))) { put_packet(""); } } -static void handle_query_qemu_sstepbits(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_qemu_sstepbits(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "ENABLE=%x,NOIRQ=%x,NOTIMER=%x", SSTEP_ENABLE, SSTEP_NOIRQ, SSTEP_NOTIMER); put_strbuf(); } -static void handle_set_qemu_sstep(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_qemu_sstep(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - sstep_flags = gdb_ctx->params[0].val_ul; + sstep_flags = get_param(params, 0)->val_ul; put_packet("OK"); } -static void handle_query_qemu_sstep(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_qemu_sstep(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "0x%x", sstep_flags); put_strbuf(); } -static void handle_query_curr_tid(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_curr_tid(GArray *params, void *user_ctx) { CPUState *cpu; GDBProcess *process; @@ -2060,7 +2055,7 @@ static void handle_query_curr_tid(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_query_threads(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_threads(GArray *params, void *user_ctx) { if (!gdbserver_state.query_cpu) { put_packet("l"); @@ -2073,25 +2068,25 @@ static void handle_query_threads(GdbCmdContext *gdb_ctx, void *user_ctx) gdbserver_state.query_cpu = gdb_next_attached_cpu(gdbserver_state.query_cpu); } -static void handle_query_first_threads(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_first_threads(GArray *params, void *user_ctx) { gdbserver_state.query_cpu = gdb_first_attached_cpu(); - handle_query_threads(gdb_ctx, user_ctx); + handle_query_threads(params, user_ctx); } -static void handle_query_thread_extra(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_thread_extra(GArray *params, void *user_ctx) { g_autoptr(GString) rs = g_string_new(NULL); CPUState *cpu; - if (!gdb_ctx->num_params || - gdb_ctx->params[0].thread_id.kind == GDB_READ_THREAD_ERR) { + if (!params->len || + get_param(params, 0)->thread_id.kind == GDB_READ_THREAD_ERR) { put_packet("E22"); return; } - cpu = gdb_get_cpu(gdb_ctx->params[0].thread_id.pid, - gdb_ctx->params[0].thread_id.tid); + cpu = gdb_get_cpu(get_param(params, 0)->thread_id.pid, + get_param(params, 0)->thread_id.tid); if (!cpu) { return; } @@ -2116,7 +2111,7 @@ static void handle_query_thread_extra(GdbCmdContext *gdb_ctx, void *user_ctx) } #ifdef CONFIG_USER_ONLY -static void handle_query_offsets(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_offsets(GArray *params, void *user_ctx) { TaskState *ts; @@ -2131,17 +2126,17 @@ static void handle_query_offsets(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } #else -static void handle_query_rcmd(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_rcmd(GArray *params, void *user_ctx) { const guint8 zero = 0; int len; - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - len = strlen(gdb_ctx->params[0].data); + len = strlen(get_param(params, 0)->data); if (len % 2) { put_packet("E01"); return; @@ -2149,7 +2144,7 @@ static void handle_query_rcmd(GdbCmdContext *gdb_ctx, void *user_ctx) g_assert(gdbserver_state.mem_buf->len == 0); len = len / 2; - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[0].data, len); + hextomem(gdbserver_state.mem_buf, get_param(params, 0)->data, len); g_byte_array_append(gdbserver_state.mem_buf, &zero, 1); qemu_chr_be_write(gdbserver_state.mon_chr, gdbserver_state.mem_buf->data, gdbserver_state.mem_buf->len); @@ -2157,7 +2152,7 @@ static void handle_query_rcmd(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif -static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_supported(GArray *params, void *user_ctx) { CPUClass *cc; @@ -2167,7 +2162,7 @@ static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) g_string_append(gdbserver_state.str_buf, ";qXfer:features:read+"); } - if (replay_mode == REPLAY_MODE_PLAY) { + if (stub_can_reverse()) { g_string_append(gdbserver_state.str_buf, ";ReverseStep+;ReverseContinue+"); } @@ -2178,8 +2173,8 @@ static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif - if (gdb_ctx->num_params && - strstr(gdb_ctx->params[0].data, "multiprocess+")) { + if (params->len && + strstr(get_param(params, 0)->data, "multiprocess+")) { gdbserver_state.multiprocess = true; } @@ -2187,7 +2182,7 @@ static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_xfer_features(GArray *params, void *user_ctx) { GDBProcess *process; CPUClass *cc; @@ -2195,7 +2190,7 @@ static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) const char *xml; const char *p; - if (gdb_ctx->num_params < 3) { + if (params->len < 3) { put_packet("E22"); return; } @@ -2208,15 +2203,15 @@ static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) } gdb_has_xml = true; - p = gdb_ctx->params[0].data; + p = get_param(params, 0)->data; xml = get_feature_xml(p, &p, process); if (!xml) { put_packet("E00"); return; } - addr = gdb_ctx->params[1].val_ul; - len = gdb_ctx->params[2].val_ul; + addr = get_param(params, 1)->val_ul; + len = get_param(params, 2)->val_ul; total_len = strlen(xml); if (addr > total_len) { put_packet("E00"); @@ -2240,18 +2235,18 @@ static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) } #if defined(CONFIG_USER_ONLY) && defined(CONFIG_LINUX_USER) -static void handle_query_xfer_auxv(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_xfer_auxv(GArray *params, void *user_ctx) { TaskState *ts; unsigned long offset, len, saved_auxv, auxv_len; - if (gdb_ctx->num_params < 2) { + if (params->len < 2) { put_packet("E22"); return; } - offset = gdb_ctx->params[0].val_ul; - len = gdb_ctx->params[1].val_ul; + offset = get_param(params, 0)->val_ul; + len = get_param(params, 1)->val_ul; ts = gdbserver_state.c_cpu->opaque; saved_auxv = ts->info->saved_auxv; auxv_len = ts->info->auxv_len; @@ -2286,12 +2281,12 @@ static void handle_query_xfer_auxv(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif -static void handle_query_attached(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_attached(GArray *params, void *user_ctx) { put_packet(GDB_ATTACHED); } -static void handle_query_qemu_supported(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_qemu_supported(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "sstepbits;sstep"); #ifndef CONFIG_USER_ONLY @@ -2301,21 +2296,21 @@ static void handle_query_qemu_supported(GdbCmdContext *gdb_ctx, void *user_ctx) } #ifndef CONFIG_USER_ONLY -static void handle_query_qemu_phy_mem_mode(GdbCmdContext *gdb_ctx, +static void handle_query_qemu_phy_mem_mode(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "%d", phy_memory_mode); put_strbuf(); } -static void handle_set_qemu_phy_mem_mode(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_qemu_phy_mem_mode(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - if (!gdb_ctx->params[0].val_ul) { + if (!get_param(params, 0)->val_ul) { phy_memory_mode = 0; } else { phy_memory_mode = 1; @@ -2324,7 +2319,7 @@ static void handle_set_qemu_phy_mem_mode(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif -static GdbCmdParseEntry gdb_gen_query_set_common_table[] = { +static const GdbCmdParseEntry gdb_gen_query_set_common_table[] = { /* Order is important if has same prefix */ { .handler = handle_query_qemu_sstepbits, @@ -2342,7 +2337,7 @@ static GdbCmdParseEntry gdb_gen_query_set_common_table[] = { }, }; -static GdbCmdParseEntry gdb_gen_query_table[] = { +static const GdbCmdParseEntry gdb_gen_query_table[] = { { .handler = handle_query_curr_tid, .cmd = "C", @@ -2420,7 +2415,7 @@ static GdbCmdParseEntry gdb_gen_query_table[] = { #endif }; -static GdbCmdParseEntry gdb_gen_set_table[] = { +static const GdbCmdParseEntry gdb_gen_set_table[] = { /* Order is important if has same prefix */ { .handler = handle_set_qemu_sstep, @@ -2438,45 +2433,45 @@ static GdbCmdParseEntry gdb_gen_set_table[] = { #endif }; -static void handle_gen_query(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_gen_query(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - if (!process_string_cmd(NULL, gdb_ctx->params[0].data, + if (!process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_query_set_common_table, ARRAY_SIZE(gdb_gen_query_set_common_table))) { return; } - if (process_string_cmd(NULL, gdb_ctx->params[0].data, + if (process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_query_table, ARRAY_SIZE(gdb_gen_query_table))) { put_packet(""); } } -static void handle_gen_set(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_gen_set(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - if (!process_string_cmd(NULL, gdb_ctx->params[0].data, + if (!process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_query_set_common_table, ARRAY_SIZE(gdb_gen_query_set_common_table))) { return; } - if (process_string_cmd(NULL, gdb_ctx->params[0].data, + if (process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_set_table, ARRAY_SIZE(gdb_gen_set_table))) { put_packet(""); } } -static void handle_target_halt(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_target_halt(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "T%02xthread:", GDB_SIGNAL_TRAP); gdb_append_thread_id(gdbserver_state.c_cpu, gdbserver_state.str_buf); diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx index ab0c7aa5ee..b2347a6aea 100644 --- a/hmp-commands-info.hx +++ b/hmp-commands-info.hx @@ -500,19 +500,6 @@ SRST Show the current VM UUID. ERST - { - .name = "cpustats", - .args_type = "", - .params = "", - .help = "show CPU statistics", - .cmd = hmp_info_cpustats, - }, - -SRST - ``info cpustats`` - Show CPU statistics. -ERST - #if defined(CONFIG_SLIRP) { .name = "usernet", diff --git a/hmp-commands.hx b/hmp-commands.hx index 435c591a1c..2d21fe5ad4 100644 --- a/hmp-commands.hx +++ b/hmp-commands.hx @@ -1297,6 +1297,7 @@ ERST .help = "create QOM object", .cmd = hmp_object_add, .command_completion = object_add_completion, + .flags = "p", }, SRST @@ -1311,6 +1312,7 @@ ERST .help = "destroy QOM object", .cmd = hmp_object_del, .command_completion = object_del_completion, + .flags = "p", }, SRST @@ -1667,7 +1669,7 @@ ERST { .name = "replay_break", - .args_type = "icount:i", + .args_type = "icount:l", .params = "icount", .help = "set breakpoint at the specified instruction count", .cmd = hmp_replay_break, @@ -1699,7 +1701,7 @@ ERST { .name = "replay_seek", - .args_type = "icount:i", + .args_type = "icount:l", .params = "icount", .help = "replay execution to the specified instruction count", .cmd = hmp_replay_seek, diff --git a/hw/9pfs/trace-events b/hw/9pfs/trace-events index 10188daf7f..6c77966c0b 100644 --- a/hw/9pfs/trace-events +++ b/hw/9pfs/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # 9p.c v9fs_rcancel(uint16_t tag, uint8_t id) "tag %d id %d" diff --git a/hw/acpi/tpm.c b/hw/acpi/tpm.c index b96459e45b..cdc0227536 100644 --- a/hw/acpi/tpm.c +++ b/hw/acpi/tpm.c @@ -57,7 +57,7 @@ void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev) aml_operation_region( "TPP3", AML_SYSTEM_MEMORY, aml_int(TPM_PPI_ADDR_BASE + - 0x15a /* movv, docs/specs/tpm.txt */), + 0x15a /* movv, docs/specs/tpm.rst */), 0x1)); field = aml_field("TPP3", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); aml_append(field, aml_named_field("MOVV", 8)); diff --git a/hw/acpi/trace-events b/hw/acpi/trace-events index dcc1438f3a..974d770e8b 100644 --- a/hw/acpi/trace-events +++ b/hw/acpi/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # memory_hotplug.c mhp_acpi_invalid_slot_selected(uint32_t slot) "0x%"PRIx32 diff --git a/hw/adc/trace-events b/hw/adc/trace-events index 4c3279ece2..456f21c8f4 100644 --- a/hw/adc/trace-events +++ b/hw/adc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # npcm7xx_adc.c npcm7xx_adc_read(const char *id, uint64_t offset, uint32_t value) " %s offset: 0x%04" PRIx64 " value 0x%04" PRIx32 diff --git a/hw/alpha/trace-events b/hw/alpha/trace-events index 5b8315f27f..952a816407 100644 --- a/hw/alpha/trace-events +++ b/hw/alpha/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c alpha_pci_iack_write(void) "" diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index b887f6a5b1..67723d9ea6 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -6,6 +6,7 @@ config ARM_VIRT imply VFIO_PLATFORM imply VFIO_XGMAC imply TPM_TIS_SYSBUS + imply NVDIMM select ARM_GIC select ACPI select ARM_SMMUV3 diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index af0d935bf7..9ce5c30cd5 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -176,6 +176,12 @@ static void armv7m_realize(DeviceState *dev, Error **errp) return; } } + if (object_property_find(OBJECT(s->cpu), "init-nsvtor")) { + if (!object_property_set_uint(OBJECT(s->cpu), "init-nsvtor", + s->init_nsvtor, errp)) { + return; + } + } if (object_property_find(OBJECT(s->cpu), "start-powered-off")) { if (!object_property_set_bool(OBJECT(s->cpu), "start-powered-off", s->start_powered_off, errp)) { @@ -254,6 +260,7 @@ static Property armv7m_properties[] = { MemoryRegion *), DEFINE_PROP_LINK("idau", ARMv7MState, idau, TYPE_IDAU_INTERFACE, Object *), DEFINE_PROP_UINT32("init-svtor", ARMv7MState, init_svtor, 0), + DEFINE_PROP_UINT32("init-nsvtor", ARMv7MState, init_nsvtor, 0), DEFINE_PROP_BOOL("enable-bitband", ARMv7MState, enable_bitband, false), DEFINE_PROP_BOOL("start-powered-off", ARMv7MState, start_powered_off, false), diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index 3fe6c55744..0eafc79154 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -947,7 +947,7 @@ static void aspeed_machine_ast2600_evb_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); - mc->desc = "Aspeed AST2600 EVB (Cortex A7)"; + mc->desc = "Aspeed AST2600 EVB (Cortex-A7)"; amc->soc_name = "ast2600-a1"; amc->hw_strap1 = AST2600_EVB_HW_STRAP1; amc->hw_strap2 = AST2600_EVB_HW_STRAP2; @@ -966,7 +966,7 @@ static void aspeed_machine_tacoma_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); - mc->desc = "OpenPOWER Tacoma BMC (Cortex A7)"; + mc->desc = "OpenPOWER Tacoma BMC (Cortex-A7)"; amc->soc_name = "ast2600-a1"; amc->hw_strap1 = TACOMA_BMC_HW_STRAP1; amc->hw_strap2 = TACOMA_BMC_HW_STRAP2; @@ -1003,7 +1003,7 @@ static void aspeed_machine_rainier_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); - mc->desc = "IBM Rainier BMC (Cortex A7)"; + mc->desc = "IBM Rainier BMC (Cortex-A7)"; amc->soc_name = "ast2600-a1"; amc->hw_strap1 = RAINIER_BMC_HW_STRAP1; amc->hw_strap2 = RAINIER_BMC_HW_STRAP2; diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c index ce16b6b317..77fae874b1 100644 --- a/hw/arm/mcimx6ul-evk.c +++ b/hw/arm/mcimx6ul-evk.c @@ -67,7 +67,7 @@ static void mcimx6ul_evk_init(MachineState *machine) static void mcimx6ul_evk_machine_init(MachineClass *mc) { - mc->desc = "Freescale i.MX6UL Evaluation Kit (Cortex A7)"; + mc->desc = "Freescale i.MX6UL Evaluation Kit (Cortex-A7)"; mc->init = mcimx6ul_evk_init; mc->max_cpus = FSL_IMX6UL_NUM_CPUS; mc->default_ram_id = "mcimx6ul-evk.ram"; diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c index e896222c34..935d4b0f1c 100644 --- a/hw/arm/mcimx7d-sabre.c +++ b/hw/arm/mcimx7d-sabre.c @@ -67,7 +67,7 @@ static void mcimx7d_sabre_init(MachineState *machine) static void mcimx7d_sabre_machine_init(MachineClass *mc) { - mc->desc = "Freescale i.MX7 DUAL SABRE (Cortex A7)"; + mc->desc = "Freescale i.MX7 DUAL SABRE (Cortex-A7)"; mc->init = mcimx7d_sabre_init; mc->max_cpus = FSL_IMX7_NUM_CPUS; mc->default_ram_id = "mcimx7d-sabre.ram"; diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index d4553e3786..698be46d30 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -299,7 +299,7 @@ static void npcm750_evb_machine_class_init(ObjectClass *oc, void *data) npcm7xx_set_soc_type(nmc, TYPE_NPCM750); - mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex A9)"; + mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex-A9)"; mc->init = npcm750_evb_init; mc->default_ram_size = 512 * MiB; }; @@ -311,7 +311,7 @@ static void gsj_machine_class_init(ObjectClass *oc, void *data) npcm7xx_set_soc_type(nmc, TYPE_NPCM730); - mc->desc = "Quanta GSJ (Cortex A9)"; + mc->desc = "Quanta GSJ (Cortex-A9)"; mc->init = quanta_gsj_init; mc->default_ram_size = 512 * MiB; }; diff --git a/hw/arm/sabrelite.c b/hw/arm/sabrelite.c index 42348e5cb1..29fc777b61 100644 --- a/hw/arm/sabrelite.c +++ b/hw/arm/sabrelite.c @@ -105,7 +105,7 @@ static void sabrelite_init(MachineState *machine) static void sabrelite_machine_init(MachineClass *mc) { - mc->desc = "Freescale i.MX6 Quad SABRE Lite Board (Cortex A9)"; + mc->desc = "Freescale i.MX6 Quad SABRE Lite Board (Cortex-A9)"; mc->init = sabrelite_init; mc->max_cpus = FSL_IMX6_NUM_CPUS; mc->ignore_memory_transaction_failures = true; diff --git a/hw/arm/trace-events b/hw/arm/trace-events index b79a91af5f..2dee296c8f 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # virt-acpi-build.c virt_acpi_setup(void) "No fw cfg or ACPI disabled. Bailing out." diff --git a/hw/audio/trace-events b/hw/audio/trace-events index 432e10712f..e0e71cd9b1 100644 --- a/hw/audio/trace-events +++ b/hw/audio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # cs4231.c cs4231_mem_readl_dreg(uint32_t reg, uint32_t ret) "read dreg %d: 0x%02x" diff --git a/hw/block/dataplane/trace-events b/hw/block/dataplane/trace-events index 843cc4e7b1..38fc3e7507 100644 --- a/hw/block/dataplane/trace-events +++ b/hw/block/dataplane/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # virtio-blk.c virtio_blk_data_plane_start(void *s) "dataplane %p" diff --git a/hw/block/trace-events b/hw/block/trace-events index 646917d045..70bed9ddb7 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # fdc.c fdc_ioport_read(uint8_t reg, uint8_t value) "read reg 0x%02x val 0x%02x" diff --git a/hw/char/trace-events b/hw/char/trace-events index 2e6e6b119a..1436fb462d 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # parallel.c parallel_ioport_read(const char *desc, uint16_t addr, uint8_t value) "read [%s] addr 0x%02x val 0x%02x" diff --git a/hw/core/cpu.c b/hw/core/cpu-common.c index 00330ba07d..e2f5a64604 100644 --- a/hw/core/cpu.c +++ b/hw/core/cpu-common.c @@ -34,7 +34,6 @@ #include "hw/qdev-properties.h" #include "trace/trace-root.h" #include "qemu/plugin.h" -#include "sysemu/hw_accel.h" CPUState *cpu_by_arch_id(int64_t id) { @@ -67,33 +66,6 @@ CPUState *cpu_create(const char *typename) return cpu; } -bool cpu_paging_enabled(const CPUState *cpu) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return cc->get_paging_enabled(cpu); -} - -static bool cpu_common_get_paging_enabled(const CPUState *cpu) -{ - return false; -} - -void cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, - Error **errp) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - cc->get_memory_mapping(cpu, list, errp); -} - -static void cpu_common_get_memory_mapping(CPUState *cpu, - MemoryMappingList *list, - Error **errp) -{ - error_setg(errp, "Obtaining memory mappings is unsupported on this CPU."); -} - /* Resetting the IRQ comes from across the code base so we take the * BQL here if we need to. cpu_interrupt assumes it is held.*/ void cpu_reset_interrupt(CPUState *cpu, int mask) @@ -117,65 +89,6 @@ void cpu_exit(CPUState *cpu) qatomic_set(&cpu->icount_decr_ptr->u16.high, -1); } -int cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf32_qemunote)(f, cpu, opaque); -} - -static int cpu_common_write_elf32_qemunote(WriteCoreDumpFunction f, - CPUState *cpu, void *opaque) -{ - return 0; -} - -int cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf32_note)(f, cpu, cpuid, opaque); -} - -static int cpu_common_write_elf32_note(WriteCoreDumpFunction f, - CPUState *cpu, int cpuid, - void *opaque) -{ - return -1; -} - -int cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf64_qemunote)(f, cpu, opaque); -} - -static int cpu_common_write_elf64_qemunote(WriteCoreDumpFunction f, - CPUState *cpu, void *opaque) -{ - return 0; -} - -int cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf64_note)(f, cpu, cpuid, opaque); -} - -static int cpu_common_write_elf64_note(WriteCoreDumpFunction f, - CPUState *cpu, int cpuid, - void *opaque) -{ - return -1; -} - - static int cpu_common_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg) { return 0; @@ -186,28 +99,6 @@ static int cpu_common_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg) return 0; } -static bool cpu_common_virtio_is_big_endian(CPUState *cpu) -{ - return target_words_bigendian(); -} - -/* - * XXX the following #if is always true because this is a common_ss - * module, so target CONFIG_* is never defined. - */ -#if !defined(CONFIG_USER_ONLY) -GuestPanicInformation *cpu_get_crash_info(CPUState *cpu) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - GuestPanicInformation *res = NULL; - - if (cc->get_crash_info) { - res = cc->get_crash_info(cpu); - } - return res; -} -#endif - void cpu_dump_state(CPUState *cpu, FILE *f, int flags) { CPUClass *cc = CPU_GET_CLASS(cpu); @@ -218,15 +109,6 @@ void cpu_dump_state(CPUState *cpu, FILE *f, int flags) } } -void cpu_dump_statistics(CPUState *cpu, int flags) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - if (cc->dump_statistics) { - cc->dump_statistics(cpu, flags); - } -} - void cpu_reset(CPUState *cpu) { device_cold_reset(DEVICE(cpu)); @@ -398,15 +280,8 @@ static void cpu_class_init(ObjectClass *klass, void *data) k->parse_features = cpu_common_parse_features; k->get_arch_id = cpu_common_get_arch_id; k->has_work = cpu_common_has_work; - k->get_paging_enabled = cpu_common_get_paging_enabled; - k->get_memory_mapping = cpu_common_get_memory_mapping; - k->write_elf32_qemunote = cpu_common_write_elf32_qemunote; - k->write_elf32_note = cpu_common_write_elf32_note; - k->write_elf64_qemunote = cpu_common_write_elf64_qemunote; - k->write_elf64_note = cpu_common_write_elf64_note; k->gdb_read_register = cpu_common_gdb_read_register; k->gdb_write_register = cpu_common_gdb_write_register; - k->virtio_is_big_endian = cpu_common_virtio_is_big_endian; set_bit(DEVICE_CATEGORY_CPU, dc->categories); dc->realize = cpu_common_realizefn; dc->unrealize = cpu_common_unrealizefn; diff --git a/hw/core/cpu-sysemu.c b/hw/core/cpu-sysemu.c new file mode 100644 index 0000000000..00253f8929 --- /dev/null +++ b/hw/core/cpu-sysemu.c @@ -0,0 +1,145 @@ +/* + * QEMU CPU model (system emulation specific) + * + * Copyright (c) 2012-2014 SUSE LINUX Products GmbH + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see + * <http://www.gnu.org/licenses/gpl-2.0.html> + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/core/cpu.h" +#include "hw/core/sysemu-cpu-ops.h" + +bool cpu_paging_enabled(const CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->get_paging_enabled) { + return cc->sysemu_ops->get_paging_enabled(cpu); + } + + return false; +} + +void cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, + Error **errp) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->get_memory_mapping) { + cc->sysemu_ops->get_memory_mapping(cpu, list, errp); + return; + } + + error_setg(errp, "Obtaining memory mappings is unsupported on this CPU."); +} + +hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, + MemTxAttrs *attrs) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->get_phys_page_attrs_debug) { + return cc->sysemu_ops->get_phys_page_attrs_debug(cpu, addr, attrs); + } + /* Fallback for CPUs which don't implement the _attrs_ hook */ + *attrs = MEMTXATTRS_UNSPECIFIED; + return cc->sysemu_ops->get_phys_page_debug(cpu, addr); +} + +hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) +{ + MemTxAttrs attrs = {}; + + return cpu_get_phys_page_attrs_debug(cpu, addr, &attrs); +} + +int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + int ret = 0; + + if (cc->sysemu_ops->asidx_from_attrs) { + ret = cc->sysemu_ops->asidx_from_attrs(cpu, attrs); + assert(ret < cpu->num_ases && ret >= 0); + } + return ret; +} + +int cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf32_qemunote) { + return 0; + } + return (*cc->sysemu_ops->write_elf32_qemunote)(f, cpu, opaque); +} + +int cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf32_note) { + return -1; + } + return (*cc->sysemu_ops->write_elf32_note)(f, cpu, cpuid, opaque); +} + +int cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf64_qemunote) { + return 0; + } + return (*cc->sysemu_ops->write_elf64_qemunote)(f, cpu, opaque); +} + +int cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf64_note) { + return -1; + } + return (*cc->sysemu_ops->write_elf64_note)(f, cpu, cpuid, opaque); +} + +bool cpu_virtio_is_big_endian(CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->virtio_is_big_endian) { + return cc->sysemu_ops->virtio_is_big_endian(cpu); + } + return target_words_bigendian(); +} + +GuestPanicInformation *cpu_get_crash_info(CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + GuestPanicInformation *res = NULL; + + if (cc->sysemu_ops->get_crash_info) { + res = cc->sysemu_ops->get_crash_info(cpu); + } + return res; +} diff --git a/hw/core/machine.c b/hw/core/machine.c index 1bf0e687b9..55b9bc7817 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -38,6 +38,7 @@ GlobalProperty hw_compat_6_0[] = { { "gpex-pcihost", "allow-unmapped-accesses", "false" }, + { "i8042", "extended-state", "false"}, }; const size_t hw_compat_6_0_len = G_N_ELEMENTS(hw_compat_6_0); diff --git a/hw/core/meson.build b/hw/core/meson.build index 59f1605bb0..18f44fb7c2 100644 --- a/hw/core/meson.build +++ b/hw/core/meson.build @@ -13,7 +13,7 @@ hwcore_files = files( 'qdev-clock.c', ) -common_ss.add(files('cpu.c')) +common_ss.add(files('cpu-common.c')) common_ss.add(when: 'CONFIG_FITLOADER', if_true: files('loader-fit.c')) common_ss.add(when: 'CONFIG_GENERIC_LOADER', if_true: files('generic-loader.c')) common_ss.add(when: ['CONFIG_GUEST_LOADER', fdt], if_true: files('guest-loader.c')) @@ -25,6 +25,7 @@ common_ss.add(when: 'CONFIG_SPLIT_IRQ', if_true: files('split-irq.c')) common_ss.add(when: 'CONFIG_XILINX_AXI', if_true: files('stream.c')) softmmu_ss.add(files( + 'cpu-sysemu.c', 'fw-path-provider.c', 'loader.c', 'machine-hmp-cmds.c', diff --git a/hw/display/meson.build b/hw/display/meson.build index aaf797c5e9..e1f473c1df 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -56,6 +56,7 @@ if config_all_devices.has_key('CONFIG_VIRTIO_GPU') virtio_gpu_ss = ss.source_set() virtio_gpu_ss.add(when: 'CONFIG_VIRTIO_GPU', if_true: [files('virtio-gpu-base.c', 'virtio-gpu.c'), pixman]) + virtio_gpu_ss.add(when: 'CONFIG_LINUX', if_true: files('virtio-gpu-udmabuf.c')) virtio_gpu_ss.add(when: 'CONFIG_VHOST_USER_GPU', if_true: files('vhost-user-gpu.c')) hw_display_modules += {'virtio-gpu': virtio_gpu_ss} diff --git a/hw/display/qxl.c b/hw/display/qxl.c index 2ba75637ec..6e1f8ff1b2 100644 --- a/hw/display/qxl.c +++ b/hw/display/qxl.c @@ -321,7 +321,7 @@ static ram_addr_t qxl_rom_size(void) #define QXL_ROM_SZ 8192 QEMU_BUILD_BUG_ON(QXL_REQUIRED_SZ > QXL_ROM_SZ); - return QXL_ROM_SZ; + return QEMU_ALIGN_UP(QXL_REQUIRED_SZ, qemu_real_host_page_size); } static void init_qxl_rom(PCIQXLDevice *d) diff --git a/hw/display/trace-events b/hw/display/trace-events index 9fccca18a1..f03f6655bc 100644 --- a/hw/display/trace-events +++ b/hw/display/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # jazz_led.c jazz_led_read(uint64_t addr, uint8_t val) "read addr=0x%"PRIx64": 0x%x" @@ -30,8 +30,10 @@ virtio_gpu_features(bool virgl) "virgl %d" virtio_gpu_cmd_get_display_info(void) "" virtio_gpu_cmd_get_edid(uint32_t scanout) "scanout %d" virtio_gpu_cmd_set_scanout(uint32_t id, uint32_t res, uint32_t w, uint32_t h, uint32_t x, uint32_t y) "id %d, res 0x%x, w %d, h %d, x %d, y %d" +virtio_gpu_cmd_set_scanout_blob(uint32_t id, uint32_t res, uint32_t w, uint32_t h, uint32_t x, uint32_t y) "id %d, res 0x%x, w %d, h %d, x %d, y %d" virtio_gpu_cmd_res_create_2d(uint32_t res, uint32_t fmt, uint32_t w, uint32_t h) "res 0x%x, fmt 0x%x, w %d, h %d" virtio_gpu_cmd_res_create_3d(uint32_t res, uint32_t fmt, uint32_t w, uint32_t h, uint32_t d) "res 0x%x, fmt 0x%x, w %d, h %d, d %d" +virtio_gpu_cmd_res_create_blob(uint32_t res, uint64_t size) "res 0x%x, size %" PRId64 virtio_gpu_cmd_res_unref(uint32_t res) "res 0x%x" virtio_gpu_cmd_res_back_attach(uint32_t res) "res 0x%x" virtio_gpu_cmd_res_back_detach(uint32_t res) "res 0x%x" diff --git a/hw/display/virtio-gpu-base.c b/hw/display/virtio-gpu-base.c index afb3ee7d9a..dd294276cb 100644 --- a/hw/display/virtio-gpu-base.c +++ b/hw/display/virtio-gpu-base.c @@ -208,6 +208,9 @@ virtio_gpu_base_get_features(VirtIODevice *vdev, uint64_t features, if (virtio_gpu_edid_enabled(g->conf)) { features |= (1 << VIRTIO_GPU_F_EDID); } + if (virtio_gpu_blob_enabled(g->conf)) { + features |= (1 << VIRTIO_GPU_F_RESOURCE_BLOB); + } return features; } diff --git a/hw/display/virtio-gpu-udmabuf.c b/hw/display/virtio-gpu-udmabuf.c new file mode 100644 index 0000000000..3c01a415e7 --- /dev/null +++ b/hw/display/virtio-gpu-udmabuf.c @@ -0,0 +1,223 @@ +/* + * Virtio GPU Device + * + * Copyright Red Hat, Inc. 2013-2014 + * + * Authors: + * Dave Airlie <airlied@redhat.com> + * Gerd Hoffmann <kraxel@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "ui/console.h" +#include "hw/virtio/virtio-gpu.h" +#include "hw/virtio/virtio-gpu-pixman.h" +#include "trace.h" +#include "exec/ramblock.h" +#include "sysemu/hostmem.h" +#include <sys/ioctl.h> +#include <fcntl.h> +#include <linux/memfd.h> +#include "qemu/memfd.h" +#include "standard-headers/linux/udmabuf.h" + +static void virtio_gpu_create_udmabuf(struct virtio_gpu_simple_resource *res) +{ + struct udmabuf_create_list *list; + RAMBlock *rb; + ram_addr_t offset; + int udmabuf, i; + + udmabuf = udmabuf_fd(); + if (udmabuf < 0) { + return; + } + + list = g_malloc0(sizeof(struct udmabuf_create_list) + + sizeof(struct udmabuf_create_item) * res->iov_cnt); + + for (i = 0; i < res->iov_cnt; i++) { + rcu_read_lock(); + rb = qemu_ram_block_from_host(res->iov[i].iov_base, false, &offset); + rcu_read_unlock(); + + if (!rb || rb->fd < 0) { + g_free(list); + return; + } + + list->list[i].memfd = rb->fd; + list->list[i].offset = offset; + list->list[i].size = res->iov[i].iov_len; + } + + list->count = res->iov_cnt; + list->flags = UDMABUF_FLAGS_CLOEXEC; + + res->dmabuf_fd = ioctl(udmabuf, UDMABUF_CREATE_LIST, list); + if (res->dmabuf_fd < 0) { + warn_report("%s: UDMABUF_CREATE_LIST: %s", __func__, + strerror(errno)); + } + g_free(list); +} + +static void virtio_gpu_remap_udmabuf(struct virtio_gpu_simple_resource *res) +{ + res->remapped = mmap(NULL, res->blob_size, PROT_READ, + MAP_SHARED, res->dmabuf_fd, 0); + if (res->remapped == MAP_FAILED) { + warn_report("%s: dmabuf mmap failed: %s", __func__, + strerror(errno)); + res->remapped = NULL; + } +} + +static void virtio_gpu_destroy_udmabuf(struct virtio_gpu_simple_resource *res) +{ + if (res->remapped) { + munmap(res->remapped, res->blob_size); + res->remapped = NULL; + } + if (res->dmabuf_fd >= 0) { + close(res->dmabuf_fd); + res->dmabuf_fd = -1; + } +} + +static int find_memory_backend_type(Object *obj, void *opaque) +{ + bool *memfd_backend = opaque; + int ret; + + if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) { + HostMemoryBackend *backend = MEMORY_BACKEND(obj); + RAMBlock *rb = backend->mr.ram_block; + + if (rb && rb->fd > 0) { + ret = fcntl(rb->fd, F_GET_SEALS); + if (ret > 0) { + *memfd_backend = true; + } + } + } + + return 0; +} + +bool virtio_gpu_have_udmabuf(void) +{ + Object *memdev_root; + int udmabuf; + bool memfd_backend = false; + + udmabuf = udmabuf_fd(); + if (udmabuf < 0) { + return false; + } + + memdev_root = object_resolve_path("/objects", NULL); + object_child_foreach(memdev_root, find_memory_backend_type, &memfd_backend); + + return memfd_backend; +} + +void virtio_gpu_init_udmabuf(struct virtio_gpu_simple_resource *res) +{ + void *pdata = NULL; + + res->dmabuf_fd = -1; + if (res->iov_cnt == 1) { + pdata = res->iov[0].iov_base; + } else { + virtio_gpu_create_udmabuf(res); + if (res->dmabuf_fd < 0) { + return; + } + virtio_gpu_remap_udmabuf(res); + if (!res->remapped) { + return; + } + pdata = res->remapped; + } + + res->blob = pdata; +} + +void virtio_gpu_fini_udmabuf(struct virtio_gpu_simple_resource *res) +{ + if (res->remapped) { + virtio_gpu_destroy_udmabuf(res); + } +} + +static void virtio_gpu_free_dmabuf(VirtIOGPU *g, VGPUDMABuf *dmabuf) +{ + struct virtio_gpu_scanout *scanout; + + scanout = &g->parent_obj.scanout[dmabuf->scanout_id]; + dpy_gl_release_dmabuf(scanout->con, &dmabuf->buf); + QTAILQ_REMOVE(&g->dmabuf.bufs, dmabuf, next); + g_free(dmabuf); +} + +static VGPUDMABuf +*virtio_gpu_create_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb) +{ + VGPUDMABuf *dmabuf; + + if (res->dmabuf_fd < 0) { + return NULL; + } + + dmabuf = g_new0(VGPUDMABuf, 1); + dmabuf->buf.width = fb->width; + dmabuf->buf.height = fb->height; + dmabuf->buf.stride = fb->stride; + dmabuf->buf.fourcc = qemu_pixman_to_drm_format(fb->format); + dmabuf->buf.fd = res->dmabuf_fd; + + dmabuf->scanout_id = scanout_id; + QTAILQ_INSERT_HEAD(&g->dmabuf.bufs, dmabuf, next); + + return dmabuf; +} + +int virtio_gpu_update_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb) +{ + struct virtio_gpu_scanout *scanout = &g->parent_obj.scanout[scanout_id]; + VGPUDMABuf *new_primary, *old_primary = NULL; + + new_primary = virtio_gpu_create_dmabuf(g, scanout_id, res, fb); + if (!new_primary) { + return -EINVAL; + } + + if (g->dmabuf.primary) { + old_primary = g->dmabuf.primary; + } + + g->dmabuf.primary = new_primary; + qemu_console_resize(scanout->con, + new_primary->buf.width, + new_primary->buf.height); + dpy_gl_scanout_dmabuf(scanout->con, &new_primary->buf); + + if (old_primary) { + virtio_gpu_free_dmabuf(g, old_primary); + } + + return 0; +} diff --git a/hw/display/virtio-gpu-virgl.c b/hw/display/virtio-gpu-virgl.c index 72c14d9132..092c6dc380 100644 --- a/hw/display/virtio-gpu-virgl.c +++ b/hw/display/virtio-gpu-virgl.c @@ -289,7 +289,8 @@ static void virgl_resource_attach_backing(VirtIOGPU *g, VIRTIO_GPU_FILL_CMD(att_rb); trace_virtio_gpu_cmd_res_back_attach(att_rb.resource_id); - ret = virtio_gpu_create_mapping_iov(g, &att_rb, cmd, NULL, &res_iovs, &res_niov); + ret = virtio_gpu_create_mapping_iov(g, att_rb.nr_entries, sizeof(att_rb), + cmd, NULL, &res_iovs, &res_niov); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; return; diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c index db56f0454a..4d549377cb 100644 --- a/hw/display/virtio-gpu.c +++ b/hw/display/virtio-gpu.c @@ -35,6 +35,10 @@ static struct virtio_gpu_simple_resource* virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id); +static struct virtio_gpu_simple_resource * +virtio_gpu_find_check_resource(VirtIOGPU *g, uint32_t resource_id, + bool require_backing, + const char *caller, uint32_t *error); static void virtio_gpu_cleanup_mapping(VirtIOGPU *g, struct virtio_gpu_simple_resource *res); @@ -45,20 +49,30 @@ void virtio_gpu_update_cursor_data(VirtIOGPU *g, { struct virtio_gpu_simple_resource *res; uint32_t pixels; + void *data; - res = virtio_gpu_find_resource(g, resource_id); + res = virtio_gpu_find_check_resource(g, resource_id, false, + __func__, NULL); if (!res) { return; } - if (pixman_image_get_width(res->image) != s->current_cursor->width || - pixman_image_get_height(res->image) != s->current_cursor->height) { - return; + if (res->blob_size) { + if (res->blob_size < (s->current_cursor->width * + s->current_cursor->height * 4)) { + return; + } + data = res->blob; + } else { + if (pixman_image_get_width(res->image) != s->current_cursor->width || + pixman_image_get_height(res->image) != s->current_cursor->height) { + return; + } + data = pixman_image_get_data(res->image); } pixels = s->current_cursor->width * s->current_cursor->height; - memcpy(s->current_cursor->data, - pixman_image_get_data(res->image), + memcpy(s->current_cursor->data, data, pixels * sizeof(uint32_t)); } @@ -114,6 +128,37 @@ virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id) return NULL; } +static struct virtio_gpu_simple_resource * +virtio_gpu_find_check_resource(VirtIOGPU *g, uint32_t resource_id, + bool require_backing, + const char *caller, uint32_t *error) +{ + struct virtio_gpu_simple_resource *res; + + res = virtio_gpu_find_resource(g, resource_id); + if (!res) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid resource specified %d\n", + caller, resource_id); + if (error) { + *error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + } + return NULL; + } + + if (require_backing) { + if (!res->iov || (!res->image && !res->blob)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no backing storage %d\n", + caller, resource_id); + if (error) { + *error = VIRTIO_GPU_RESP_ERR_UNSPEC; + } + return NULL; + } + } + + return res; +} + void virtio_gpu_ctrl_response(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd, struct virtio_gpu_ctrl_hdr *resp, @@ -277,6 +322,62 @@ static void virtio_gpu_resource_create_2d(VirtIOGPU *g, g->hostmem += res->hostmem; } +static void virtio_gpu_resource_create_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_create_blob cblob; + int ret; + + VIRTIO_GPU_FILL_CMD(cblob); + virtio_gpu_create_blob_bswap(&cblob); + trace_virtio_gpu_cmd_res_create_blob(cblob.resource_id, cblob.size); + + if (cblob.resource_id == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: resource id 0 is not allowed\n", + __func__); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + return; + } + + res = virtio_gpu_find_resource(g, cblob.resource_id); + if (res) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: resource already exists %d\n", + __func__, cblob.resource_id); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + return; + } + + res = g_new0(struct virtio_gpu_simple_resource, 1); + res->resource_id = cblob.resource_id; + res->blob_size = cblob.size; + + if (cblob.blob_mem != VIRTIO_GPU_BLOB_MEM_GUEST && + cblob.blob_flags != VIRTIO_GPU_BLOB_FLAG_USE_SHAREABLE) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid memory type\n", + __func__); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + g_free(res); + return; + } + + if (res->iov) { + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + + ret = virtio_gpu_create_mapping_iov(g, cblob.nr_entries, sizeof(cblob), + cmd, &res->addrs, &res->iov, + &res->iov_cnt); + if (ret != 0) { + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + + virtio_gpu_init_udmabuf(res); + QTAILQ_INSERT_HEAD(&g->reslist, res, next); +} + static void virtio_gpu_disable_scanout(VirtIOGPU *g, int scanout_id) { struct virtio_gpu_scanout *scanout = &g->parent_obj.scanout[scanout_id]; @@ -311,7 +412,7 @@ static void virtio_gpu_resource_destroy(VirtIOGPU *g, } } - pixman_image_unref(res->image); + qemu_pixman_image_unref(res->image); virtio_gpu_cleanup_mapping(g, res); QTAILQ_REMOVE(&g->reslist, res, next); g->hostmem -= res->hostmem; @@ -352,11 +453,9 @@ static void virtio_gpu_transfer_to_host_2d(VirtIOGPU *g, virtio_gpu_t2d_bswap(&t2d); trace_virtio_gpu_cmd_res_xfer_toh_2d(t2d.resource_id); - res = virtio_gpu_find_resource(g, t2d.resource_id); - if (!res || !res->iov) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, t2d.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + res = virtio_gpu_find_check_resource(g, t2d.resource_id, true, + __func__, &cmd->error); + if (!res || res->blob) { return; } @@ -402,6 +501,7 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g, { struct virtio_gpu_simple_resource *res; struct virtio_gpu_resource_flush rf; + struct virtio_gpu_scanout *scanout; pixman_region16_t flush_region; int i; @@ -410,20 +510,31 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g, trace_virtio_gpu_cmd_res_flush(rf.resource_id, rf.r.width, rf.r.height, rf.r.x, rf.r.y); - res = virtio_gpu_find_resource(g, rf.resource_id); + res = virtio_gpu_find_check_resource(g, rf.resource_id, false, + __func__, &cmd->error); if (!res) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, rf.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; return; } - if (rf.r.x > res->width || + if (res->blob) { + for (i = 0; i < g->parent_obj.conf.max_outputs; i++) { + scanout = &g->parent_obj.scanout[i]; + if (scanout->resource_id == res->resource_id && + console_has_gl(scanout->con)) { + dpy_gl_update(scanout->con, 0, 0, scanout->width, + scanout->height); + return; + } + } + } + + if (!res->blob && + (rf.r.x > res->width || rf.r.y > res->height || rf.r.width > res->width || rf.r.height > res->height || rf.r.x + rf.r.width > res->width || - rf.r.y + rf.r.height > res->height) { + rf.r.y + rf.r.height > res->height)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: flush bounds outside resource" " bounds for resource %d: %d %d %d %d vs %d %d\n", __func__, rf.resource_id, rf.r.x, rf.r.y, @@ -435,7 +546,6 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g, pixman_region_init_rect(&flush_region, rf.r.x, rf.r.y, rf.r.width, rf.r.height); for (i = 0; i < g->parent_obj.conf.max_outputs; i++) { - struct virtio_gpu_scanout *scanout; pixman_region16_t region, finalregion; pixman_box16_t *extents; @@ -468,14 +578,115 @@ static void virtio_unref_resource(pixman_image_t *image, void *data) pixman_image_unref(data); } +static void virtio_gpu_update_scanout(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_rect *r) +{ + struct virtio_gpu_simple_resource *ores; + struct virtio_gpu_scanout *scanout; + + scanout = &g->parent_obj.scanout[scanout_id]; + ores = virtio_gpu_find_resource(g, scanout->resource_id); + if (ores) { + ores->scanout_bitmask &= ~(1 << scanout_id); + } + + res->scanout_bitmask |= (1 << scanout_id); + scanout->resource_id = res->resource_id; + scanout->x = r->x; + scanout->y = r->y; + scanout->width = r->width; + scanout->height = r->height; +} + +static void virtio_gpu_do_set_scanout(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_framebuffer *fb, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_rect *r, + uint32_t *error) +{ + struct virtio_gpu_scanout *scanout; + uint8_t *data; + + if (scanout_id >= g->parent_obj.conf.max_outputs) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout id specified %d", + __func__, scanout_id); + *error = VIRTIO_GPU_RESP_ERR_INVALID_SCANOUT_ID; + return; + } + scanout = &g->parent_obj.scanout[scanout_id]; + + if (r->x > fb->width || + r->y > fb->height || + r->width < 16 || + r->height < 16 || + r->width > fb->width || + r->height > fb->height || + r->x + r->width > fb->width || + r->y + r->height > fb->height) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout %d bounds for" + " resource %d, rect (%d,%d)+%d,%d, fb %d %d\n", + __func__, scanout_id, res->resource_id, + r->x, r->y, r->width, r->height, + fb->width, fb->height); + *error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; + } + + g->parent_obj.enable = 1; + + if (res->blob) { + if (console_has_gl(scanout->con)) { + if (!virtio_gpu_update_dmabuf(g, scanout_id, res, fb)) { + virtio_gpu_update_scanout(g, scanout_id, res, r); + return; + } + } + + data = res->blob; + } else { + data = (uint8_t *)pixman_image_get_data(res->image); + } + + /* create a surface for this scanout */ + if ((res->blob && !console_has_gl(scanout->con)) || + !scanout->ds || + surface_data(scanout->ds) != data + fb->offset || + scanout->width != r->width || + scanout->height != r->height) { + pixman_image_t *rect; + void *ptr = data + fb->offset; + rect = pixman_image_create_bits(fb->format, r->width, r->height, + ptr, fb->stride); + + if (res->image) { + pixman_image_ref(res->image); + pixman_image_set_destroy_function(rect, virtio_unref_resource, + res->image); + } + + /* realloc the surface ptr */ + scanout->ds = qemu_create_displaysurface_pixman(rect); + if (!scanout->ds) { + *error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + + pixman_image_unref(rect); + dpy_gfx_replace_surface(g->parent_obj.scanout[scanout_id].con, + scanout->ds); + } + + virtio_gpu_update_scanout(g, scanout_id, res, r); +} + static void virtio_gpu_set_scanout(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) { - struct virtio_gpu_simple_resource *res, *ores; - struct virtio_gpu_scanout *scanout; - pixman_format_code_t format; - uint32_t offset; - int bpp; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_framebuffer fb = { 0 }; struct virtio_gpu_set_scanout ss; VIRTIO_GPU_FILL_CMD(ss); @@ -483,86 +694,85 @@ static void virtio_gpu_set_scanout(VirtIOGPU *g, trace_virtio_gpu_cmd_set_scanout(ss.scanout_id, ss.resource_id, ss.r.width, ss.r.height, ss.r.x, ss.r.y); - if (ss.scanout_id >= g->parent_obj.conf.max_outputs) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout id specified %d", - __func__, ss.scanout_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_SCANOUT_ID; + if (ss.resource_id == 0) { + virtio_gpu_disable_scanout(g, ss.scanout_id); return; } - g->parent_obj.enable = 1; + res = virtio_gpu_find_check_resource(g, ss.resource_id, true, + __func__, &cmd->error); + if (!res) { + return; + } + + fb.format = pixman_image_get_format(res->image); + fb.bytes_pp = DIV_ROUND_UP(PIXMAN_FORMAT_BPP(fb.format), 8); + fb.width = pixman_image_get_width(res->image); + fb.height = pixman_image_get_height(res->image); + fb.stride = pixman_image_get_stride(res->image); + fb.offset = ss.r.x * fb.bytes_pp + ss.r.y * fb.stride; + + virtio_gpu_do_set_scanout(g, ss.scanout_id, + &fb, res, &ss.r, &cmd->error); +} + +static void virtio_gpu_set_scanout_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_framebuffer fb = { 0 }; + struct virtio_gpu_set_scanout_blob ss; + uint64_t fbend; + + VIRTIO_GPU_FILL_CMD(ss); + virtio_gpu_scanout_blob_bswap(&ss); + trace_virtio_gpu_cmd_set_scanout_blob(ss.scanout_id, ss.resource_id, + ss.r.width, ss.r.height, ss.r.x, + ss.r.y); + if (ss.resource_id == 0) { virtio_gpu_disable_scanout(g, ss.scanout_id); return; } - /* create a surface for this scanout */ - res = virtio_gpu_find_resource(g, ss.resource_id); + res = virtio_gpu_find_check_resource(g, ss.resource_id, true, + __func__, &cmd->error); if (!res) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, ss.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; return; } - if (ss.r.x > res->width || - ss.r.y > res->height || - ss.r.width < 16 || - ss.r.height < 16 || - ss.r.width > res->width || - ss.r.height > res->height || - ss.r.x + ss.r.width > res->width || - ss.r.y + ss.r.height > res->height) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout %d bounds for" - " resource %d, (%d,%d)+%d,%d vs %d %d\n", - __func__, ss.scanout_id, ss.resource_id, ss.r.x, ss.r.y, - ss.r.width, ss.r.height, res->width, res->height); + fb.format = virtio_gpu_get_pixman_format(ss.format); + if (!fb.format) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: host couldn't handle guest format %d\n", + __func__, ss.format); cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; return; } - scanout = &g->parent_obj.scanout[ss.scanout_id]; - - format = pixman_image_get_format(res->image); - bpp = DIV_ROUND_UP(PIXMAN_FORMAT_BPP(format), 8); - offset = (ss.r.x * bpp) + ss.r.y * pixman_image_get_stride(res->image); - if (!scanout->ds || surface_data(scanout->ds) - != ((uint8_t *)pixman_image_get_data(res->image) + offset) || - scanout->width != ss.r.width || - scanout->height != ss.r.height) { - pixman_image_t *rect; - void *ptr = (uint8_t *)pixman_image_get_data(res->image) + offset; - rect = pixman_image_create_bits(format, ss.r.width, ss.r.height, ptr, - pixman_image_get_stride(res->image)); - pixman_image_ref(res->image); - pixman_image_set_destroy_function(rect, virtio_unref_resource, - res->image); - /* realloc the surface ptr */ - scanout->ds = qemu_create_displaysurface_pixman(rect); - if (!scanout->ds) { - cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; - return; - } - pixman_image_unref(rect); - dpy_gfx_replace_surface(g->parent_obj.scanout[ss.scanout_id].con, - scanout->ds); - } + fb.bytes_pp = DIV_ROUND_UP(PIXMAN_FORMAT_BPP(fb.format), 8); + fb.width = ss.width; + fb.height = ss.height; + fb.stride = ss.strides[0]; + fb.offset = ss.offsets[0] + ss.r.x * fb.bytes_pp + ss.r.y * fb.stride; - ores = virtio_gpu_find_resource(g, scanout->resource_id); - if (ores) { - ores->scanout_bitmask &= ~(1 << ss.scanout_id); + fbend = fb.offset; + fbend += fb.stride * (ss.r.height - 1); + fbend += fb.bytes_pp * ss.r.width; + if (fbend > res->blob_size) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: fb end out of range\n", + __func__); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; } - res->scanout_bitmask |= (1 << ss.scanout_id); - scanout->resource_id = ss.resource_id; - scanout->x = ss.r.x; - scanout->y = ss.r.y; - scanout->width = ss.r.width; - scanout->height = ss.r.height; + virtio_gpu_do_set_scanout(g, ss.scanout_id, + &fb, res, &ss.r, &cmd->error); } int virtio_gpu_create_mapping_iov(VirtIOGPU *g, - struct virtio_gpu_resource_attach_backing *ab, + uint32_t nr_entries, uint32_t offset, struct virtio_gpu_ctrl_command *cmd, uint64_t **addr, struct iovec **iov, uint32_t *niov) @@ -571,17 +781,17 @@ int virtio_gpu_create_mapping_iov(VirtIOGPU *g, size_t esize, s; int e, v; - if (ab->nr_entries > 16384) { + if (nr_entries > 16384) { qemu_log_mask(LOG_GUEST_ERROR, "%s: nr_entries is too big (%d > 16384)\n", - __func__, ab->nr_entries); + __func__, nr_entries); return -1; } - esize = sizeof(*ents) * ab->nr_entries; + esize = sizeof(*ents) * nr_entries; ents = g_malloc(esize); s = iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, - sizeof(*ab), ents, esize); + offset, ents, esize); if (s != esize) { qemu_log_mask(LOG_GUEST_ERROR, "%s: command data size incorrect %zu vs %zu\n", @@ -594,7 +804,7 @@ int virtio_gpu_create_mapping_iov(VirtIOGPU *g, if (addr) { *addr = NULL; } - for (e = 0, v = 0; e < ab->nr_entries; e++) { + for (e = 0, v = 0; e < nr_entries; e++) { uint64_t a = le64_to_cpu(ents[e].addr); uint32_t l = le32_to_cpu(ents[e].length); hwaddr len; @@ -606,8 +816,7 @@ int virtio_gpu_create_mapping_iov(VirtIOGPU *g, a, &len, DMA_DIRECTION_TO_DEVICE); if (!map) { qemu_log_mask(LOG_GUEST_ERROR, "%s: failed to map MMIO memory for" - " resource %d element %d\n", - __func__, ab->resource_id, e); + " element %d\n", __func__, e); virtio_gpu_cleanup_mapping_iov(g, *iov, v); g_free(ents); *iov = NULL; @@ -663,6 +872,10 @@ static void virtio_gpu_cleanup_mapping(VirtIOGPU *g, res->iov_cnt = 0; g_free(res->addrs); res->addrs = NULL; + + if (res->blob) { + virtio_gpu_fini_udmabuf(res); + } } static void @@ -690,8 +903,8 @@ virtio_gpu_resource_attach_backing(VirtIOGPU *g, return; } - ret = virtio_gpu_create_mapping_iov(g, &ab, cmd, &res->addrs, - &res->iov, &res->iov_cnt); + ret = virtio_gpu_create_mapping_iov(g, ab.nr_entries, sizeof(ab), cmd, + &res->addrs, &res->iov, &res->iov_cnt); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; return; @@ -709,11 +922,9 @@ virtio_gpu_resource_detach_backing(VirtIOGPU *g, virtio_gpu_bswap_32(&detach, sizeof(detach)); trace_virtio_gpu_cmd_res_back_detach(detach.resource_id); - res = virtio_gpu_find_resource(g, detach.resource_id); - if (!res || !res->iov) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, detach.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + res = virtio_gpu_find_check_resource(g, detach.resource_id, true, + __func__, &cmd->error); + if (!res) { return; } virtio_gpu_cleanup_mapping(g, res); @@ -735,6 +946,13 @@ void virtio_gpu_simple_process_cmd(VirtIOGPU *g, case VIRTIO_GPU_CMD_RESOURCE_CREATE_2D: virtio_gpu_resource_create_2d(g, cmd); break; + case VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB: + if (!virtio_gpu_blob_enabled(g->parent_obj.conf)) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + break; + } + virtio_gpu_resource_create_blob(g, cmd); + break; case VIRTIO_GPU_CMD_RESOURCE_UNREF: virtio_gpu_resource_unref(g, cmd); break; @@ -747,6 +965,13 @@ void virtio_gpu_simple_process_cmd(VirtIOGPU *g, case VIRTIO_GPU_CMD_SET_SCANOUT: virtio_gpu_set_scanout(g, cmd); break; + case VIRTIO_GPU_CMD_SET_SCANOUT_BLOB: + if (!virtio_gpu_blob_enabled(g->parent_obj.conf)) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + break; + } + virtio_gpu_set_scanout_blob(g, cmd); + break; case VIRTIO_GPU_CMD_RESOURCE_ATTACH_BACKING: virtio_gpu_resource_attach_backing(g, cmd); break; @@ -1058,6 +1283,18 @@ void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(qdev); VirtIOGPU *g = VIRTIO_GPU(qdev); + if (virtio_gpu_blob_enabled(g->parent_obj.conf)) { + if (!virtio_gpu_have_udmabuf()) { + error_setg(errp, "cannot enable blob resources without udmabuf"); + return; + } + + if (virtio_gpu_virgl_enabled(g->parent_obj.conf)) { + error_setg(errp, "blobs and virgl are not compatible (yet)"); + return; + } + } + if (!virtio_gpu_base_device_realize(qdev, virtio_gpu_handle_ctrl_cb, virtio_gpu_handle_cursor_cb, @@ -1151,6 +1388,8 @@ static Property virtio_gpu_properties[] = { VIRTIO_GPU_BASE_PROPERTIES(VirtIOGPU, parent_obj.conf), DEFINE_PROP_SIZE("max_hostmem", VirtIOGPU, conf_max_hostmem, 256 * MiB), + DEFINE_PROP_BIT("blob", VirtIOGPU, parent_obj.conf.flags, + VIRTIO_GPU_FLAG_BLOB_ENABLED, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/dma/trace-events b/hw/dma/trace-events index 44893995f6..3c47df54e4 100644 --- a/hw/dma/trace-events +++ b/hw/dma/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # rc4030.c jazzio_read(uint64_t addr, uint32_t ret) "read reg[0x%"PRIx64"] = 0x%x" diff --git a/hw/gpio/trace-events b/hw/gpio/trace-events index 46ab9323bd..f0b664158e 100644 --- a/hw/gpio/trace-events +++ b/hw/gpio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # npcm7xx_gpio.c npcm7xx_gpio_read(const char *id, uint64_t offset, uint64_t value) " %s offset: 0x%04" PRIx64 " value 0x%08" PRIx64 diff --git a/hw/hppa/trace-events b/hw/hppa/trace-events index 3ff620319a..3f42be9056 100644 --- a/hw/hppa/trace-events +++ b/hw/hppa/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c hppa_pci_iack_write(void) "" diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events index 82f19e6a2d..7d8907c1ee 100644 --- a/hw/i2c/trace-events +++ b/hw/i2c/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # core.c diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index 7f91f30877..66838fa397 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -23,6 +23,7 @@ config PC imply TPM_TIS_ISA imply VGA_PCI imply VIRTIO_VGA + imply NVDIMM select FDC select I8259 select I8254 diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 8cfaf216e7..c6d8d0d84d 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -94,7 +94,11 @@ #include "trace.h" #include CONFIG_DEVICES -GlobalProperty pc_compat_6_0[] = {}; +GlobalProperty pc_compat_6_0[] = { + { "qemu64" "-" TYPE_X86_CPU, "family", "6" }, + { "qemu64" "-" TYPE_X86_CPU, "model", "6" }, + { "qemu64" "-" TYPE_X86_CPU, "stepping", "3" }, +}; const size_t pc_compat_6_0_len = G_N_ELEMENTS(pc_compat_6_0); GlobalProperty pc_compat_5_2[] = { diff --git a/hw/i386/trace-events b/hw/i386/trace-events index e48bef2b0d..5bf7e52bf5 100644 --- a/hw/i386/trace-events +++ b/hw/i386/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # x86-iommu.c x86_iommu_iec_notify(bool global, uint32_t index, uint32_t mask) "Notify IEC invalidation: global=%d index=%" PRIu32 " mask=%" PRIu32 diff --git a/hw/i386/xen/trace-events b/hw/i386/xen/trace-events index ca3a4948ba..5d6be61090 100644 --- a/hw/i386/xen/trace-events +++ b/hw/i386/xen/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # xen_platform.c xen_platform_log(char *s) "xen platform: %s" diff --git a/hw/ide/trace-events b/hw/ide/trace-events index 6e357685f9..15d7921f15 100644 --- a/hw/ide/trace-events +++ b/hw/ide/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # core.c # portio diff --git a/hw/input/hid.c b/hw/input/hid.c index e1d2e46083..8aab0521f4 100644 --- a/hw/input/hid.c +++ b/hw/input/hid.c @@ -51,8 +51,8 @@ static const uint8_t hid_usage_keys[0x100] = { 0x45, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0xe8, 0xe9, 0x71, 0x72, 0x73, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, 0x00, 0xe3, 0xe7, 0x65, + 0x88, 0x00, 0x00, 0x87, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x8a, 0x00, 0x8b, 0x00, 0x89, 0xe7, 0x65, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c index dde85ba6c6..baba62f357 100644 --- a/hw/input/pckbd.c +++ b/hw/input/pckbd.c @@ -23,13 +23,16 @@ */ #include "qemu/osdep.h" +#include "qemu/error-report.h" #include "qemu/log.h" +#include "qemu/timer.h" #include "hw/isa/isa.h" #include "migration/vmstate.h" #include "hw/acpi/aml-build.h" #include "hw/input/ps2.h" #include "hw/irq.h" #include "hw/input/i8042.h" +#include "hw/qdev-properties.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" @@ -59,21 +62,6 @@ #define KBD_CCMD_RESET 0xFE /* Pulse bit 0 of the output port P2 = CPU reset. */ #define KBD_CCMD_NO_OP 0xFF /* Pulse no bits of the output port P2. */ -/* Keyboard Commands */ -#define KBD_CMD_SET_LEDS 0xED /* Set keyboard leds */ -#define KBD_CMD_ECHO 0xEE -#define KBD_CMD_GET_ID 0xF2 /* get keyboard ID */ -#define KBD_CMD_SET_RATE 0xF3 /* Set typematic rate */ -#define KBD_CMD_ENABLE 0xF4 /* Enable scanning */ -#define KBD_CMD_RESET_DISABLE 0xF5 /* reset and disable scanning */ -#define KBD_CMD_RESET_ENABLE 0xF6 /* reset and enable scanning */ -#define KBD_CMD_RESET 0xFF /* Reset */ - -/* Keyboard Replies */ -#define KBD_REPLY_POR 0xAA /* Power on reset */ -#define KBD_REPLY_ACK 0xFA /* Command ACK */ -#define KBD_REPLY_RESEND 0xFE /* Command NACK, send the cmd again */ - /* Status Register Bits */ #define KBD_STAT_OBF 0x01 /* Keyboard output buffer full */ #define KBD_STAT_IBF 0x02 /* Keyboard input buffer full */ @@ -106,41 +94,37 @@ */ #define KBD_OUT_ONES 0xcc -/* Mouse Commands */ -#define AUX_SET_SCALE11 0xE6 /* Set 1:1 scaling */ -#define AUX_SET_SCALE21 0xE7 /* Set 2:1 scaling */ -#define AUX_SET_RES 0xE8 /* Set resolution */ -#define AUX_GET_SCALE 0xE9 /* Get scaling factor */ -#define AUX_SET_STREAM 0xEA /* Set stream mode */ -#define AUX_POLL 0xEB /* Poll */ -#define AUX_RESET_WRAP 0xEC /* Reset wrap mode */ -#define AUX_SET_WRAP 0xEE /* Set wrap mode */ -#define AUX_SET_REMOTE 0xF0 /* Set remote mode */ -#define AUX_GET_TYPE 0xF2 /* Get type */ -#define AUX_SET_SAMPLE 0xF3 /* Set sample rate */ -#define AUX_ENABLE_DEV 0xF4 /* Enable aux device */ -#define AUX_DISABLE_DEV 0xF5 /* Disable aux device */ -#define AUX_SET_DEFAULT 0xF6 -#define AUX_RESET 0xFF /* Reset aux device */ -#define AUX_ACK 0xFA /* Command byte ACK. */ - -#define MOUSE_STATUS_REMOTE 0x40 -#define MOUSE_STATUS_ENABLED 0x20 -#define MOUSE_STATUS_SCALE21 0x10 - -#define KBD_PENDING_KBD 1 -#define KBD_PENDING_AUX 2 +#define KBD_PENDING_KBD_COMPAT 0x01 +#define KBD_PENDING_AUX_COMPAT 0x02 +#define KBD_PENDING_CTRL_KBD 0x04 +#define KBD_PENDING_CTRL_AUX 0x08 +#define KBD_PENDING_KBD KBD_MODE_DISABLE_KBD /* 0x10 */ +#define KBD_PENDING_AUX KBD_MODE_DISABLE_MOUSE /* 0x20 */ + +#define KBD_MIGR_TIMER_PENDING 0x1 + +#define KBD_OBSRC_KBD 0x01 +#define KBD_OBSRC_MOUSE 0x02 +#define KBD_OBSRC_CTRL 0x04 typedef struct KBDState { uint8_t write_cmd; /* if non zero, write data to port 60 is expected */ uint8_t status; uint8_t mode; uint8_t outport; + uint32_t migration_flags; + uint32_t obsrc; bool outport_present; + bool extended_state; + bool extended_state_loaded; /* Bitmask of devices with data available. */ uint8_t pending; + uint8_t obdata; + uint8_t cbdata; + uint8_t pending_tmp; void *kbd; void *mouse; + QEMUTimer *throttle_timer; qemu_irq irq_kbd; qemu_irq irq_mouse; @@ -148,56 +132,123 @@ typedef struct KBDState { hwaddr mask; } KBDState; -/* update irq and KBD_STAT_[MOUSE_]OBF */ /* XXX: not generating the irqs if KBD_MODE_DISABLE_KBD is set may be incorrect, but it avoids having to simulate exact delays */ -static void kbd_update_irq(KBDState *s) +static void kbd_update_irq_lines(KBDState *s) { int irq_kbd_level, irq_mouse_level; irq_kbd_level = 0; irq_mouse_level = 0; + + if (s->status & KBD_STAT_OBF) { + if (s->status & KBD_STAT_MOUSE_OBF) { + if (s->mode & KBD_MODE_MOUSE_INT) { + irq_mouse_level = 1; + } + } else { + if ((s->mode & KBD_MODE_KBD_INT) && + !(s->mode & KBD_MODE_DISABLE_KBD)) { + irq_kbd_level = 1; + } + } + } + qemu_set_irq(s->irq_kbd, irq_kbd_level); + qemu_set_irq(s->irq_mouse, irq_mouse_level); +} + +static void kbd_deassert_irq(KBDState *s) +{ + s->status &= ~(KBD_STAT_OBF | KBD_STAT_MOUSE_OBF); + s->outport &= ~(KBD_OUT_OBF | KBD_OUT_MOUSE_OBF); + kbd_update_irq_lines(s); +} + +static uint8_t kbd_pending(KBDState *s) +{ + if (s->extended_state) { + return s->pending & (~s->mode | ~(KBD_PENDING_KBD | KBD_PENDING_AUX)); + } else { + return s->pending; + } +} + +/* update irq and KBD_STAT_[MOUSE_]OBF */ +static void kbd_update_irq(KBDState *s) +{ + uint8_t pending = kbd_pending(s); + s->status &= ~(KBD_STAT_OBF | KBD_STAT_MOUSE_OBF); s->outport &= ~(KBD_OUT_OBF | KBD_OUT_MOUSE_OBF); - if (s->pending) { + if (pending) { s->status |= KBD_STAT_OBF; s->outport |= KBD_OUT_OBF; - /* kbd data takes priority over aux data. */ - if (s->pending == KBD_PENDING_AUX) { + if (pending & KBD_PENDING_CTRL_KBD) { + s->obsrc = KBD_OBSRC_CTRL; + } else if (pending & KBD_PENDING_CTRL_AUX) { s->status |= KBD_STAT_MOUSE_OBF; s->outport |= KBD_OUT_MOUSE_OBF; - if (s->mode & KBD_MODE_MOUSE_INT) - irq_mouse_level = 1; + s->obsrc = KBD_OBSRC_CTRL; + } else if (pending & KBD_PENDING_KBD) { + s->obsrc = KBD_OBSRC_KBD; } else { - if ((s->mode & KBD_MODE_KBD_INT) && - !(s->mode & KBD_MODE_DISABLE_KBD)) - irq_kbd_level = 1; + s->status |= KBD_STAT_MOUSE_OBF; + s->outport |= KBD_OUT_MOUSE_OBF; + s->obsrc = KBD_OBSRC_MOUSE; } } - qemu_set_irq(s->irq_kbd, irq_kbd_level); - qemu_set_irq(s->irq_mouse, irq_mouse_level); + kbd_update_irq_lines(s); +} + +static void kbd_safe_update_irq(KBDState *s) +{ + /* + * with KBD_STAT_OBF set, a call to kbd_read_data() will eventually call + * kbd_update_irq() + */ + if (s->status & KBD_STAT_OBF) { + return; + } + /* the throttle timer is pending and will call kbd_update_irq() */ + if (s->throttle_timer && timer_pending(s->throttle_timer)) { + return; + } + if (kbd_pending(s)) { + kbd_update_irq(s); + } } static void kbd_update_kbd_irq(void *opaque, int level) { - KBDState *s = (KBDState *)opaque; + KBDState *s = opaque; - if (level) + if (level) { s->pending |= KBD_PENDING_KBD; - else + } else { s->pending &= ~KBD_PENDING_KBD; - kbd_update_irq(s); + } + kbd_safe_update_irq(s); } static void kbd_update_aux_irq(void *opaque, int level) { - KBDState *s = (KBDState *)opaque; + KBDState *s = opaque; - if (level) + if (level) { s->pending |= KBD_PENDING_AUX; - else + } else { s->pending &= ~KBD_PENDING_AUX; - kbd_update_irq(s); + } + kbd_safe_update_irq(s); +} + +static void kbd_throttle_timeout(void *opaque) +{ + KBDState *s = opaque; + + if (kbd_pending(s)) { + kbd_update_irq(s); + } } static uint64_t kbd_read_status(void *opaque, hwaddr addr, @@ -212,10 +263,25 @@ static uint64_t kbd_read_status(void *opaque, hwaddr addr, static void kbd_queue(KBDState *s, int b, int aux) { - if (aux) - ps2_queue(s->mouse, b); - else - ps2_queue(s->kbd, b); + if (s->extended_state) { + s->cbdata = b; + s->pending &= ~KBD_PENDING_CTRL_KBD & ~KBD_PENDING_CTRL_AUX; + s->pending |= aux ? KBD_PENDING_CTRL_AUX : KBD_PENDING_CTRL_KBD; + kbd_safe_update_irq(s); + } else { + ps2_queue(aux ? s->mouse : s->kbd, b); + } +} + +static uint8_t kbd_dequeue(KBDState *s) +{ + uint8_t b = s->cbdata; + + s->pending &= ~KBD_PENDING_CTRL_KBD & ~KBD_PENDING_CTRL_AUX; + if (kbd_pending(s)) { + kbd_update_irq(s); + } + return b; } static void outport_write(KBDState *s, uint32_t val) @@ -265,6 +331,7 @@ static void kbd_write_command(void *opaque, hwaddr addr, break; case KBD_CCMD_MOUSE_ENABLE: s->mode &= ~KBD_MODE_DISABLE_MOUSE; + kbd_safe_update_irq(s); break; case KBD_CCMD_TEST_MOUSE: kbd_queue(s, 0x00, 0); @@ -278,11 +345,10 @@ static void kbd_write_command(void *opaque, hwaddr addr, break; case KBD_CCMD_KBD_DISABLE: s->mode |= KBD_MODE_DISABLE_KBD; - kbd_update_irq(s); break; case KBD_CCMD_KBD_ENABLE: s->mode &= ~KBD_MODE_DISABLE_KBD; - kbd_update_irq(s); + kbd_safe_update_irq(s); break; case KBD_CCMD_READ_INPORT: kbd_queue(s, 0x80, 0); @@ -315,15 +381,24 @@ static uint64_t kbd_read_data(void *opaque, hwaddr addr, unsigned size) { KBDState *s = opaque; - uint32_t val; - if (s->pending == KBD_PENDING_AUX) - val = ps2_read_data(s->mouse); - else - val = ps2_read_data(s->kbd); + if (s->status & KBD_STAT_OBF) { + kbd_deassert_irq(s); + if (s->obsrc & KBD_OBSRC_KBD) { + if (s->throttle_timer) { + timer_mod(s->throttle_timer, + qemu_clock_get_us(QEMU_CLOCK_VIRTUAL) + 1000); + } + s->obdata = ps2_read_data(s->kbd); + } else if (s->obsrc & KBD_OBSRC_MOUSE) { + s->obdata = ps2_read_data(s->mouse); + } else if (s->obsrc & KBD_OBSRC_CTRL) { + s->obdata = kbd_dequeue(s); + } + } - trace_pckbd_kbd_read_data(val); - return val; + trace_pckbd_kbd_read_data(s->obdata); + return s->obdata; } static void kbd_write_data(void *opaque, hwaddr addr, @@ -336,12 +411,23 @@ static void kbd_write_data(void *opaque, hwaddr addr, switch(s->write_cmd) { case 0: ps2_write_keyboard(s->kbd, val); + /* sending data to the keyboard reenables PS/2 communication */ + s->mode &= ~KBD_MODE_DISABLE_KBD; + kbd_safe_update_irq(s); break; case KBD_CCMD_WRITE_MODE: s->mode = val; ps2_keyboard_set_translation(s->kbd, (s->mode & KBD_MODE_KCC) != 0); - /* ??? */ - kbd_update_irq(s); + /* + * a write to the mode byte interrupt enable flags directly updates + * the irq lines + */ + kbd_update_irq_lines(s); + /* + * a write to the mode byte disable interface flags may raise + * an irq if there is pending data in the PS/2 queues. + */ + kbd_safe_update_irq(s); break; case KBD_CCMD_WRITE_OBUF: kbd_queue(s, val, 0); @@ -354,6 +440,9 @@ static void kbd_write_data(void *opaque, hwaddr addr, break; case KBD_CCMD_WRITE_MOUSE: ps2_write_mouse(s->mouse, val); + /* sending data to the mouse reenables PS/2 communication */ + s->mode &= ~KBD_MODE_DISABLE_MOUSE; + kbd_safe_update_irq(s); break; default: break; @@ -368,7 +457,11 @@ static void kbd_reset(void *opaque) s->mode = KBD_MODE_KBD_INT | KBD_MODE_MOUSE_INT; s->status = KBD_STAT_CMD | KBD_STAT_UNLOCKED; s->outport = KBD_OUT_RESET | KBD_OUT_A20 | KBD_OUT_ONES; - s->outport_present = false; + s->pending = 0; + kbd_deassert_irq(s); + if (s->throttle_timer) { + timer_del(s->throttle_timer); + } } static uint8_t kbd_outport_default(KBDState *s) @@ -403,13 +496,99 @@ static const VMStateDescription vmstate_kbd_outport = { } }; +static int kbd_extended_state_pre_save(void *opaque) +{ + KBDState *s = opaque; + + s->migration_flags = 0; + if (s->throttle_timer && timer_pending(s->throttle_timer)) { + s->migration_flags |= KBD_MIGR_TIMER_PENDING; + } + + return 0; +} + +static int kbd_extended_state_post_load(void *opaque, int version_id) +{ + KBDState *s = opaque; + + if (s->migration_flags & KBD_MIGR_TIMER_PENDING) { + kbd_throttle_timeout(s); + } + s->extended_state_loaded = true; + + return 0; +} + +static bool kbd_extended_state_needed(void *opaque) +{ + KBDState *s = opaque; + + return s->extended_state; +} + +static const VMStateDescription vmstate_kbd_extended_state = { + .name = "pckbd/extended_state", + .post_load = kbd_extended_state_post_load, + .pre_save = kbd_extended_state_pre_save, + .needed = kbd_extended_state_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(migration_flags, KBDState), + VMSTATE_UINT32(obsrc, KBDState), + VMSTATE_UINT8(obdata, KBDState), + VMSTATE_UINT8(cbdata, KBDState), + VMSTATE_END_OF_LIST() + } +}; + +static int kbd_pre_save(void *opaque) +{ + KBDState *s = opaque; + + if (s->extended_state) { + s->pending_tmp = s->pending; + } else { + s->pending_tmp = 0; + if (s->pending & KBD_PENDING_KBD) { + s->pending_tmp |= KBD_PENDING_KBD_COMPAT; + } + if (s->pending & KBD_PENDING_AUX) { + s->pending_tmp |= KBD_PENDING_AUX_COMPAT; + } + } + return 0; +} + +static int kbd_pre_load(void *opaque) +{ + KBDState *s = opaque; + + s->outport_present = false; + s->extended_state_loaded = false; + return 0; +} + static int kbd_post_load(void *opaque, int version_id) { KBDState *s = opaque; if (!s->outport_present) { s->outport = kbd_outport_default(s); } - s->outport_present = false; + s->pending = s->pending_tmp; + if (!s->extended_state_loaded) { + s->obsrc = s->status & KBD_STAT_OBF ? + (s->status & KBD_STAT_MOUSE_OBF ? KBD_OBSRC_MOUSE : KBD_OBSRC_KBD) : + 0; + if (s->pending & KBD_PENDING_KBD_COMPAT) { + s->pending |= KBD_PENDING_KBD; + } + if (s->pending & KBD_PENDING_AUX_COMPAT) { + s->pending |= KBD_PENDING_AUX; + } + } + /* clear all unused flags */ + s->pending &= KBD_PENDING_CTRL_KBD | KBD_PENDING_CTRL_AUX | + KBD_PENDING_KBD | KBD_PENDING_AUX; return 0; } @@ -417,16 +596,19 @@ static const VMStateDescription vmstate_kbd = { .name = "pckbd", .version_id = 3, .minimum_version_id = 3, + .pre_load = kbd_pre_load, .post_load = kbd_post_load, + .pre_save = kbd_pre_save, .fields = (VMStateField[]) { VMSTATE_UINT8(write_cmd, KBDState), VMSTATE_UINT8(status, KBDState), VMSTATE_UINT8(mode, KBDState), - VMSTATE_UINT8(pending, KBDState), + VMSTATE_UINT8(pending_tmp, KBDState), VMSTATE_END_OF_LIST() }, .subsections = (const VMStateDescription*[]) { &vmstate_kbd_outport, + &vmstate_kbd_extended_state, NULL } }; @@ -472,6 +654,8 @@ void i8042_mm_init(qemu_irq kbd_irq, qemu_irq mouse_irq, s->irq_mouse = mouse_irq; s->mask = mask; + s->extended_state = true; + vmstate_register(NULL, 0, &vmstate_kbd, s); memory_region_init_io(region, NULL, &i8042_mmio_ops, s, "i8042", size); @@ -485,6 +669,7 @@ struct ISAKBDState { ISADevice parent_obj; KBDState kbd; + bool kbd_throttle; MemoryRegion io[2]; }; @@ -557,6 +742,13 @@ static void i8042_realizefn(DeviceState *dev, Error **errp) s->kbd = ps2_kbd_init(kbd_update_kbd_irq, s); s->mouse = ps2_mouse_init(kbd_update_aux_irq, s); + if (isa_s->kbd_throttle && !isa_s->kbd.extended_state) { + warn_report(TYPE_I8042 ": can't enable kbd-throttle without" + " extended-state, disabling kbd-throttle"); + } else if (isa_s->kbd_throttle) { + s->throttle_timer = timer_new_us(QEMU_CLOCK_VIRTUAL, + kbd_throttle_timeout, s); + } qemu_register_reset(kbd_reset, s); } @@ -588,11 +780,18 @@ static void i8042_build_aml(ISADevice *isadev, Aml *scope) aml_append(scope, mou); } +static Property i8042_properties[] = { + DEFINE_PROP_BOOL("extended-state", ISAKBDState, kbd.extended_state, true), + DEFINE_PROP_BOOL("kbd-throttle", ISAKBDState, kbd_throttle, false), + DEFINE_PROP_END_OF_LIST(), +}; + static void i8042_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); + device_class_set_props(dc, i8042_properties); dc->realize = i8042_realizefn; dc->vmsd = &vmstate_kbd_isa; isa->build_aml = i8042_build_aml; diff --git a/hw/input/ps2.c b/hw/input/ps2.c index 72cdb80ae1..8dd482c1f6 100644 --- a/hw/input/ps2.c +++ b/hw/input/ps2.c @@ -212,8 +212,12 @@ void ps2_raise_irq(PS2State *s) void ps2_queue(PS2State *s, int b) { + if (PS2_QUEUE_SIZE - s->queue.count < 1) { + return; + } + ps2_queue_noirq(s, b); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } void ps2_queue_2(PS2State *s, int b1, int b2) @@ -224,7 +228,7 @@ void ps2_queue_2(PS2State *s, int b1, int b2) ps2_queue_noirq(s, b1); ps2_queue_noirq(s, b2); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } void ps2_queue_3(PS2State *s, int b1, int b2, int b3) @@ -236,7 +240,7 @@ void ps2_queue_3(PS2State *s, int b1, int b2, int b3) ps2_queue_noirq(s, b1); ps2_queue_noirq(s, b2); ps2_queue_noirq(s, b3); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } void ps2_queue_4(PS2State *s, int b1, int b2, int b3, int b4) @@ -249,7 +253,7 @@ void ps2_queue_4(PS2State *s, int b1, int b2, int b3, int b4) ps2_queue_noirq(s, b2); ps2_queue_noirq(s, b3); ps2_queue_noirq(s, b4); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } /* keycode is the untranslated scancode in the current scancode set. */ @@ -293,7 +297,8 @@ static void ps2_keyboard_event(DeviceState *dev, QemuConsole *src, qcode = qemu_input_key_value_to_qcode(key->key); mod = ps2_modifier_bit(qcode); - trace_ps2_keyboard_event(s, qcode, key->down, mod, s->modifiers); + trace_ps2_keyboard_event(s, qcode, key->down, mod, + s->modifiers, s->scancode_set, s->translate); if (key->down) { s->modifiers |= mod; } else { @@ -515,7 +520,9 @@ uint32_t ps2_read_data(PS2State *s) /* reading deasserts IRQ */ s->update_irq(s->update_arg, 0); /* reassert IRQs if data left */ - s->update_irq(s->update_arg, q->count != 0); + if (q->count) { + s->update_irq(s->update_arg, 1); + } } return val; } @@ -645,7 +652,8 @@ void ps2_keyboard_set_translation(void *opaque, int mode) static int ps2_mouse_send_packet(PS2MouseState *s) { - const int needed = 3 + (s->mouse_type - 2); + /* IMPS/2 and IMEX send 4 bytes, PS2 sends 3 bytes */ + const int needed = s->mouse_type ? 4 : 3; unsigned int b; int dx1, dy1, dz1; diff --git a/hw/input/trace-events b/hw/input/trace-events index 33741e74f5..e0bfe7f3ee 100644 --- a/hw/input/trace-events +++ b/hw/input/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # adb-kbd.c adb_device_kbd_no_key(void) "Ignoring NO_KEY" @@ -30,7 +30,7 @@ pckbd_kbd_write_data(uint64_t val) "0x%02"PRIx64 # ps2.c ps2_put_keycode(void *opaque, int keycode) "%p keycode 0x%02x" -ps2_keyboard_event(void *opaque, int qcode, int down, unsigned int modifier, unsigned int modifiers) "%p qcode %d down %d modifier 0x%x modifiers 0x%x" +ps2_keyboard_event(void *opaque, int qcode, int down, unsigned int modifier, unsigned int modifiers, int set, int xlate) "%p qcode %d down %d modifier 0x%x modifiers 0x%x set %d xlate %d" ps2_read_data(void *opaque) "%p" ps2_set_ledstate(void *s, int ledstate) "%p ledstate %d" ps2_reset_keyboard(void *s) "%p" diff --git a/hw/intc/trace-events b/hw/intc/trace-events index 626bb554b2..e56e7dd3b6 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # i8259.c pic_update_irq(bool master, uint8_t imr, uint8_t irr, uint8_t padd) "master %d imr %"PRIu8" irr %"PRIu8" padd %"PRIu8 diff --git a/hw/isa/trace-events b/hw/isa/trace-events index 641d69eedf..b8f877e1ed 100644 --- a/hw/isa/trace-events +++ b/hw/isa/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # isa-superio.c superio_create_parallel(int id, uint16_t base, unsigned int irq) "id=%d, base 0x%03x, irq %u" diff --git a/hw/mem/Kconfig b/hw/mem/Kconfig index a0ef2cf648..8b19fdc49f 100644 --- a/hw/mem/Kconfig +++ b/hw/mem/Kconfig @@ -7,6 +7,4 @@ config MEM_DEVICE config NVDIMM bool - default y - depends on (PC || PSERIES || ARM_VIRT) select MEM_DEVICE diff --git a/hw/mem/trace-events b/hw/mem/trace-events index 9f6b52acd7..8b6b02b5bf 100644 --- a/hw/mem/trace-events +++ b/hw/mem/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pc-dimm.c mhp_pc_dimm_assigned_slot(int slot) "%d" diff --git a/hw/mips/jazz.c b/hw/mips/jazz.c index dba2088ed1..1e1cf8154e 100644 --- a/hw/mips/jazz.c +++ b/hw/mips/jazz.c @@ -119,30 +119,6 @@ static const MemoryRegionOps dma_dummy_ops = { #define MAGNUM_BIOS_SIZE \ (BIOS_SIZE < MAGNUM_BIOS_SIZE_MAX ? BIOS_SIZE : MAGNUM_BIOS_SIZE_MAX) -#if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) -static void (*real_do_transaction_failed)(CPUState *cpu, hwaddr physaddr, - vaddr addr, unsigned size, - MMUAccessType access_type, - int mmu_idx, MemTxAttrs attrs, - MemTxResult response, - uintptr_t retaddr); - -static void mips_jazz_do_transaction_failed(CPUState *cs, hwaddr physaddr, - vaddr addr, unsigned size, - MMUAccessType access_type, - int mmu_idx, MemTxAttrs attrs, - MemTxResult response, - uintptr_t retaddr) -{ - if (access_type != MMU_INST_FETCH) { - /* ignore invalid access (ie do not raise exception) */ - return; - } - (*real_do_transaction_failed)(cs, physaddr, addr, size, access_type, - mmu_idx, attrs, response, retaddr); -} -#endif /* CONFIG_TCG && !CONFIG_USER_ONLY */ - static void mips_jazz_init(MachineState *machine, enum jazz_model_e jazz_model) { @@ -151,7 +127,7 @@ static void mips_jazz_init(MachineState *machine, int bios_size, n; Clock *cpuclk; MIPSCPU *cpu; - CPUClass *cc; + MIPSCPUClass *mcc; CPUMIPSState *env; qemu_irq *i8259; rc4030_dma *dmas; @@ -198,8 +174,6 @@ static void mips_jazz_init(MachineState *machine, * However, we can't simply add a global memory region to catch * everything, as this would make all accesses including instruction * accesses be ignored and not raise exceptions. - * So instead we hijack the do_transaction_failed method on the CPU, and - * do not raise exceptions for data access. * * NOTE: this behaviour of raising exceptions for bad instruction * fetches but not bad data accesses was added in commit 54e755588cf1e9 @@ -209,11 +183,8 @@ static void mips_jazz_init(MachineState *machine, * we could replace this hijacking of CPU methods with a simple global * memory region that catches all memory accesses, as we do on Malta. */ - cc = CPU_GET_CLASS(cpu); -#if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) - real_do_transaction_failed = cc->tcg_ops->do_transaction_failed; - cc->tcg_ops->do_transaction_failed = mips_jazz_do_transaction_failed; -#endif /* CONFIG_TCG && !CONFIG_USER_ONLY */ + mcc = MIPS_CPU_GET_CLASS(cpu); + mcc->no_data_aborts = true; /* allocate RAM */ memory_region_add_subregion(address_space, 0, machine->ram); diff --git a/hw/misc/macio/trace-events b/hw/misc/macio/trace-events index e4a1cc0d24..ad4b9d1c08 100644 --- a/hw/misc/macio/trace-events +++ b/hw/misc/macio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # cuda.c cuda_delay_set_sr_int(void) "" diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c index a1ee67dc9a..0b61070c52 100644 --- a/hw/misc/npcm7xx_clk.c +++ b/hw/misc/npcm7xx_clk.c @@ -35,7 +35,7 @@ #define NPCM7XX_CLOCK_REF_HZ (25000000) /* Register Field Definitions */ -#define NPCM7XX_CLK_WDRCR_CA9C BIT(0) /* Cortex A9 Cores */ +#define NPCM7XX_CLK_WDRCR_CA9C BIT(0) /* Cortex-A9 Cores */ #define PLLCON_LOKI BIT(31) #define PLLCON_LOKS BIT(30) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index 0752217636..ede413965b 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-cpucfg.c allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_addr 0x%" PRIu32 diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index f03450c028..9c7035bc94 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -283,9 +283,8 @@ static uint32_t imx_phy_read(IMXFECState *s, int reg) uint32_t phy = reg / 32; if (phy != s->phy_num) { - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad phy num %u\n", - TYPE_IMX_FEC, __func__, phy); - return 0; + trace_imx_phy_read_num(phy, s->phy_num); + return 0xffff; } reg %= 32; @@ -345,8 +344,7 @@ static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) uint32_t phy = reg / 32; if (phy != s->phy_num) { - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad phy num %u\n", - TYPE_IMX_FEC, __func__, phy); + trace_imx_phy_write_num(phy, s->phy_num); return; } diff --git a/hw/net/trace-events b/hw/net/trace-events index 314e21fa99..c28b91ee1a 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-sun8i-emac.c allwinner_sun8i_emac_mii_write_reg(uint32_t reg, uint32_t value) "MII write: reg=0x%" PRIx32 " value=0x%" PRIx32 @@ -402,7 +402,9 @@ i82596_channel_attention(void *s) "%p: Received CHANNEL ATTENTION" # imx_fec.c imx_phy_read(uint32_t val, int phy, int reg) "0x%04"PRIx32" <= phy[%d].reg[%d]" +imx_phy_read_num(int phy, int configured) "read request from unconfigured phy %d (configured %d)" imx_phy_write(uint32_t val, int phy, int reg) "0x%04"PRIx32" => phy[%d].reg[%d]" +imx_phy_write_num(int phy, int configured) "write request to unconfigured phy %d (configured %d)" imx_phy_update_link(const char *s) "%s" imx_phy_reset(void) "" imx_fec_read_bd(uint64_t addr, int flags, int len, int data) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x" diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 613be072c3..bd7958b9f0 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -3481,6 +3481,7 @@ static void virtio_net_device_unrealize(DeviceState *dev) if (n->failover) { device_listener_unregister(&n->primary_listener); + remove_migration_state_change_notifier(&n->migration_state); } max_queues = n->multiqueue ? n->max_queues : 1; diff --git a/hw/nvram/trace-events b/hw/nvram/trace-events index e023193295..5e33b24d47 100644 --- a/hw/nvram/trace-events +++ b/hw/nvram/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # ds1225y.c nvram_read(uint32_t addr, uint32_t ret) "read addr %d: 0x%02x" diff --git a/hw/pci-host/trace-events b/hw/pci-host/trace-events index dac86ad3f0..f4b3a50cb0 100644 --- a/hw/pci-host/trace-events +++ b/hw/pci-host/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # grackle.c grackle_set_irq(int irq_num, int level) "set_irq num %d level %d" diff --git a/hw/pci/trace-events b/hw/pci/trace-events index def4b3926d..fc777d0b5e 100644 --- a/hw/pci/trace-events +++ b/hw/pci/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c pci_update_mappings_del(void *d, uint32_t bus, uint32_t slot, uint32_t func, int bar, uint64_t addr, uint64_t size) "d=%p %02x:%02x.%x %d,0x%"PRIx64"+0x%"PRIx64 diff --git a/hw/ppc/Kconfig b/hw/ppc/Kconfig index e51e0e5e5a..66e0b15d9e 100644 --- a/hw/ppc/Kconfig +++ b/hw/ppc/Kconfig @@ -3,6 +3,7 @@ config PSERIES imply PCI_DEVICES imply TEST_DEVICES imply VIRTIO_VGA + imply NVDIMM select DIMM select PCI select SPAPR_VSCSI diff --git a/hw/ppc/pef.c b/hw/ppc/pef.c index 573be3ed79..cc44d5e339 100644 --- a/hw/ppc/pef.c +++ b/hw/ppc/pef.c @@ -41,7 +41,7 @@ struct PefGuest { ConfidentialGuestSupport parent_obj; }; -static int kvmppc_svm_init(Error **errp) +static int kvmppc_svm_init(ConfidentialGuestSupport *cgs, Error **errp) { #ifdef CONFIG_KVM static Error *pef_mig_blocker; @@ -65,6 +65,8 @@ static int kvmppc_svm_init(Error **errp) /* NB: This can fail if --only-migratable is used */ migrate_add_blocker(pef_mig_blocker, &error_fatal); + cgs->ready = true; + return 0; #else g_assert_not_reached(); @@ -102,7 +104,7 @@ int pef_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) return -1; } - return kvmppc_svm_init(errp); + return kvmppc_svm_init(cgs, errp); } int pef_kvm_reset(ConfidentialGuestSupport *cgs, Error **errp) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index c23bcc4490..4dd90b75cc 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -1005,7 +1005,7 @@ static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt, bool reset) _FDT(chosen = fdt_add_subnode(fdt, 0, "chosen")); if (reset) { - const char *boot_device = machine->boot_order; + const char *boot_device = spapr->boot_device; char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus); size_t cb = 0; char *bootlist = get_boot_devices_list(&cb); @@ -2376,8 +2376,10 @@ static SaveVMHandlers savevm_htab_handlers = { static void spapr_boot_set(void *opaque, const char *boot_device, Error **errp) { - MachineState *machine = MACHINE(opaque); - machine->boot_order = g_strdup(boot_device); + SpaprMachineState *spapr = SPAPR_MACHINE(opaque); + + g_free(spapr->boot_device); + spapr->boot_device = g_strdup(boot_device); } static void spapr_create_lmb_dr_connectors(SpaprMachineState *spapr) diff --git a/hw/ppc/spapr_nvdimm.c b/hw/ppc/spapr_nvdimm.c index 252204e25f..91de1052f2 100644 --- a/hw/ppc/spapr_nvdimm.c +++ b/hw/ppc/spapr_nvdimm.c @@ -35,6 +35,18 @@ /* SCM device is unable to persist memory contents */ #define PAPR_PMEM_UNARMED PPC_BIT(0) +/* + * The nvdimm size should be aligned to SCM block size. + * The SCM block size should be aligned to SPAPR_MEMORY_BLOCK_SIZE + * in order to have SCM regions not to overlap with dimm memory regions. + * The SCM devices can have variable block sizes. For now, fixing the + * block size to the minimum value. + */ +#define SPAPR_MINIMUM_SCM_BLOCK_SIZE SPAPR_MEMORY_BLOCK_SIZE + +/* Have an explicit check for alignment */ +QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE); + bool spapr_nvdimm_validate(HotplugHandler *hotplug_dev, NVDIMMDevice *nvdimm, uint64_t size, Error **errp) { @@ -163,11 +175,11 @@ int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, void spapr_dt_persistent_memory(SpaprMachineState *spapr, void *fdt) { - int offset = fdt_subnode_offset(fdt, 0, "persistent-memory"); + int offset = fdt_subnode_offset(fdt, 0, "ibm,persistent-memory"); GSList *iter, *nvdimms = nvdimm_get_device_list(); if (offset < 0) { - offset = fdt_add_subnode(fdt, 0, "persistent-memory"); + offset = fdt_add_subnode(fdt, 0, "ibm,persistent-memory"); _FDT(offset); _FDT((fdt_setprop_cell(fdt, offset, "#address-cells", 0x1))); _FDT((fdt_setprop_cell(fdt, offset, "#size-cells", 0x0))); diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c index 7817cf72ee..f3b37df8ea 100644 --- a/hw/ppc/spapr_pci_vfio.c +++ b/hw/ppc/spapr_pci_vfio.c @@ -46,6 +46,16 @@ void spapr_phb_vfio_reset(DeviceState *qdev) spapr_phb_vfio_eeh_reenable(SPAPR_PCI_HOST_BRIDGE(qdev)); } +static void spapr_eeh_pci_find_device(PCIBus *bus, PCIDevice *pdev, + void *opaque) +{ + bool *found = opaque; + + if (object_dynamic_cast(OBJECT(pdev), "vfio-pci")) { + *found = true; + } +} + int spapr_phb_vfio_eeh_set_option(SpaprPhbState *sphb, unsigned int addr, int option) { @@ -58,17 +68,33 @@ int spapr_phb_vfio_eeh_set_option(SpaprPhbState *sphb, break; case RTAS_EEH_ENABLE: { PCIHostState *phb; - PCIDevice *pdev; + bool found = false; /* - * The EEH functionality is enabled on basis of PCI device, - * instead of PE. We need check the validity of the PCI - * device address. + * The EEH functionality is enabled per sphb level instead of + * per PCI device. We have already identified this specific sphb + * based on buid passed as argument to ibm,set-eeh-option rtas + * call. Now we just need to check the validity of the PCI + * pass-through devices (vfio-pci) under this sphb bus. + * We have already validated that all the devices under this sphb + * are from same iommu group (within same PE) before comming here. + * + * Prior to linux commit 98ba956f6a389 ("powerpc/pseries/eeh: + * Rework device EEH PE determination") kernel would call + * eeh-set-option for each device in the PE using the device's + * config_address as the argument rather than the PE address. + * Hence if we check validity of supplied config_addr whether + * it matches to this PHB will cause issues with older kernel + * versions v5.9 and older. If we return an error from + * eeh-set-option when the argument isn't a valid PE address + * then older kernels (v5.9 and older) will interpret that as + * EEH not being supported. */ phb = PCI_HOST_BRIDGE(sphb); - pdev = pci_find_device(phb->bus, - (addr >> 16) & 0xFF, (addr >> 8) & 0xFF); - if (!pdev || !object_dynamic_cast(OBJECT(pdev), "vfio-pci")) { + pci_for_each_device(phb->bus, (addr >> 16) & 0xFF, + spapr_eeh_pci_find_device, &found); + + if (!found) { return RTAS_OUT_PARAM_ERROR; } diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index 03355b4c0a..b476382ae6 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -132,8 +132,8 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr, target_ulong id, start, r3; PowerPCCPU *newcpu; CPUPPCState *env; - PowerPCCPUClass *pcc; target_ulong lpcr; + target_ulong caller_lpcr; if (nargs != 3 || nret != 1) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); @@ -152,7 +152,6 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr, } env = &newcpu->env; - pcc = POWERPC_CPU_GET_CLASS(newcpu); if (!CPU(newcpu)->halted) { rtas_st(rets, 0, RTAS_OUT_HW_ERROR); @@ -164,11 +163,15 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr, env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME); hreg_compute_hflags(env); - /* Enable Power-saving mode Exit Cause exceptions for the new CPU */ + caller_lpcr = callcpu->env.spr[SPR_LPCR]; lpcr = env->spr[SPR_LPCR]; - if (!pcc->interrupts_big_endian(callcpu)) { - lpcr |= LPCR_ILE; - } + + /* Set ILE the same way */ + lpcr = (lpcr & ~LPCR_ILE) | (caller_lpcr & LPCR_ILE); + + /* Set AIL the same way */ + lpcr = (lpcr & ~LPCR_AIL) | (caller_lpcr & LPCR_AIL); + if (env->mmu_model == POWERPC_MMU_3_00) { /* * New cpus are expected to start in the same radix/hash mode diff --git a/hw/ppc/trace-events b/hw/ppc/trace-events index b4bbfbb013..0ba3e40353 100644 --- a/hw/ppc/trace-events +++ b/hw/ppc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # spapr_pci.c spapr_pci_msi(const char *msg, uint32_t ca) "%s (cfg=0x%x)" diff --git a/hw/rdma/trace-events b/hw/rdma/trace-events index 2022a820cb..9accb14973 100644 --- a/hw/rdma/trace-events +++ b/hw/rdma/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # rdma_backend.c rdma_check_dev_attr(const char *name, int max_bk, int max_fe) "%s: be=%d, fe=%d" diff --git a/hw/rdma/vmw/trace-events b/hw/rdma/vmw/trace-events index 323fca8456..a6c77e1e10 100644 --- a/hw/rdma/vmw/trace-events +++ b/hw/rdma/vmw/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pvrdma_main.c pvrdma_regs_read(uint64_t addr, uint64_t val) "pvrdma.regs[0x%"PRIx64"]=0x%"PRIx64 diff --git a/hw/rtc/trace-events b/hw/rtc/trace-events index 8bdcf74264..ebb311a5b0 100644 --- a/hw/rtc/trace-events +++ b/hw/rtc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-rtc.c allwinner_rtc_read(uint64_t addr, uint64_t value) "addr 0x%" PRIx64 " value 0x%" PRIx64 diff --git a/hw/s390x/trace-events b/hw/s390x/trace-events index 8156693749..8b9213eab9 100644 --- a/hw/s390x/trace-events +++ b/hw/s390x/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # css.c css_enable_facility(const char *facility) "CSS: enable %s" diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index 3580e7ee61..e8a547dbb7 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -1582,6 +1582,7 @@ invalid_field: scsi_check_condition(r, SENSE_CODE(INVALID_FIELD)); } +/* sector_num and nb_sectors expected to be in qdev blocksize */ static inline bool check_lba_range(SCSIDiskState *s, uint64_t sector_num, uint32_t nb_sectors) { @@ -1614,11 +1615,12 @@ static void scsi_unmap_complete_noio(UnmapCBData *data, int ret) assert(r->req.aiocb == NULL); if (data->count > 0) { - r->sector = ldq_be_p(&data->inbuf[0]) - * (s->qdev.blocksize / BDRV_SECTOR_SIZE); - r->sector_count = (ldl_be_p(&data->inbuf[8]) & 0xffffffffULL) - * (s->qdev.blocksize / BDRV_SECTOR_SIZE); - if (!check_lba_range(s, r->sector, r->sector_count)) { + uint64_t sector_num = ldq_be_p(&data->inbuf[0]); + uint32_t nb_sectors = ldl_be_p(&data->inbuf[8]) & 0xffffffffULL; + r->sector = sector_num * (s->qdev.blocksize / BDRV_SECTOR_SIZE); + r->sector_count = nb_sectors * (s->qdev.blocksize / BDRV_SECTOR_SIZE); + + if (!check_lba_range(s, sector_num, nb_sectors)) { block_acct_invalid(blk_get_stats(s->qdev.conf.blk), BLOCK_ACCT_UNMAP); scsi_check_condition(r, SENSE_CODE(LBA_OUT_OF_RANGE)); diff --git a/hw/scsi/trace-events b/hw/scsi/trace-events index 1c331fb189..1a27e141ae 100644 --- a/hw/scsi/trace-events +++ b/hw/scsi/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # scsi-bus.c scsi_req_alloc(int target, int lun, int tag) "target %d lun %d tag %d" diff --git a/hw/sd/trace-events b/hw/sd/trace-events index e185d07a1d..3cc2ef89ba 100644 --- a/hw/sd/trace-events +++ b/hw/sd/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-sdhost.c allwinner_sdhost_set_inserted(bool inserted) "inserted %u" diff --git a/hw/sparc/trace-events b/hw/sparc/trace-events index d3a30a816a..00b0212c3b 100644 --- a/hw/sparc/trace-events +++ b/hw/sparc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # sun4m.c sun4m_cpu_set_irq_raise(int level) "Raise CPU IRQ %d" diff --git a/hw/sparc64/trace-events b/hw/sparc64/trace-events index b85d14c30c..3eb4bacf79 100644 --- a/hw/sparc64/trace-events +++ b/hw/sparc64/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # sun4u.c ebus_isa_irq_handler(int n, int level) "Set ISA IRQ %d level %d" diff --git a/hw/timer/trace-events b/hw/timer/trace-events index 029fb56280..5234c0ea9e 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # slavio_timer.c slavio_timer_get_out(uint64_t limit, uint32_t counthigh, uint32_t count) "limit 0x%"PRIx64" count 0x%x0x%08x" diff --git a/hw/tpm/tpm_ppi.c b/hw/tpm/tpm_ppi.c index 72d7a3d926..362edcc5c9 100644 --- a/hw/tpm/tpm_ppi.c +++ b/hw/tpm/tpm_ppi.c @@ -23,7 +23,7 @@ void tpm_ppi_reset(TPMPPI *tpmppi) { - if (tpmppi->buf[0x15a /* movv, docs/specs/tpm.txt */] & 0x1) { + if (tpmppi->buf[0x15a /* movv, docs/specs/tpm.rst */] & 0x1) { GuestPhysBlockList guest_phys_blocks; GuestPhysBlock *block; diff --git a/hw/tpm/trace-events b/hw/tpm/trace-events index 6005ecb5da..f17110458e 100644 --- a/hw/tpm/trace-events +++ b/hw/tpm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # tpm_crb.c tpm_crb_mmio_read(uint64_t addr, unsigned size, uint32_t val) "CRB read 0x%016" PRIx64 " len:%u val: 0x%" PRIx32 diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c index 9421734d0f..e934b1a5b1 100644 --- a/hw/usb/hcd-xhci-pci.c +++ b/hw/usb/hcd-xhci-pci.c @@ -57,7 +57,7 @@ static void xhci_pci_intr_update(XHCIState *xhci, int n, bool enable) } } -static void xhci_pci_intr_raise(XHCIState *xhci, int n, bool level) +static bool xhci_pci_intr_raise(XHCIState *xhci, int n, bool level) { XHCIPciState *s = container_of(xhci, XHCIPciState, xhci); PCIDevice *pci_dev = PCI_DEVICE(s); @@ -67,15 +67,18 @@ static void xhci_pci_intr_raise(XHCIState *xhci, int n, bool level) msi_enabled(pci_dev))) { pci_set_irq(pci_dev, level); } - if (msix_enabled(pci_dev)) { + + if (msix_enabled(pci_dev) && level) { msix_notify(pci_dev, n); - return; + return true; } - if (msi_enabled(pci_dev)) { + if (msi_enabled(pci_dev) && level) { msi_notify(pci_dev, n); - return; + return true; } + + return false; } static void xhci_pci_reset(DeviceState *dev) diff --git a/hw/usb/hcd-xhci-sysbus.c b/hw/usb/hcd-xhci-sysbus.c index 42e2574c82..a14e438196 100644 --- a/hw/usb/hcd-xhci-sysbus.c +++ b/hw/usb/hcd-xhci-sysbus.c @@ -16,11 +16,13 @@ #include "hw/acpi/aml-build.h" #include "hw/irq.h" -static void xhci_sysbus_intr_raise(XHCIState *xhci, int n, bool level) +static bool xhci_sysbus_intr_raise(XHCIState *xhci, int n, bool level) { XHCISysbusState *s = container_of(xhci, XHCISysbusState, xhci); qemu_set_irq(s->irq[n], level); + + return false; } void xhci_sysbus_reset(DeviceState *dev) diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c index 46212b1e69..e01700039b 100644 --- a/hw/usb/hcd-xhci.c +++ b/hw/usb/hcd-xhci.c @@ -551,7 +551,9 @@ static void xhci_intr_update(XHCIState *xhci, int v) level = 1; } if (xhci->intr_raise) { - xhci->intr_raise(xhci, 0, level); + if (xhci->intr_raise(xhci, 0, level)) { + xhci->intr[0].iman &= ~IMAN_IP; + } } } if (xhci->intr_update) { @@ -579,7 +581,9 @@ static void xhci_intr_raise(XHCIState *xhci, int v) return; } if (xhci->intr_raise) { - xhci->intr_raise(xhci, v, true); + if (xhci->intr_raise(xhci, v, true)) { + xhci->intr[v].iman &= ~IMAN_IP; + } } } diff --git a/hw/usb/hcd-xhci.h b/hw/usb/hcd-xhci.h index 7bba361f3b..98f598382a 100644 --- a/hw/usb/hcd-xhci.h +++ b/hw/usb/hcd-xhci.h @@ -194,7 +194,7 @@ typedef struct XHCIState { uint32_t flags; uint32_t max_pstreams_mask; void (*intr_update)(XHCIState *s, int n, bool enable); - void (*intr_raise)(XHCIState *s, int n, bool level); + bool (*intr_raise)(XHCIState *s, int n, bool level); DeviceState *hostOpaque; /* Operational Registers */ diff --git a/hw/usb/trace-events b/hw/usb/trace-events index 38e05fc7f4..b8287b63f1 100644 --- a/hw/usb/trace-events +++ b/hw/usb/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # core.c usb_packet_state_change(int bus, const char *port, int ep, void *p, const char *o, const char *n) "bus %d, port %s, ep %d, packet %p, state %s -> %s" diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 079f53acf2..0ef1b5f4a6 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c vfio_intx_interrupt(const char *name, char line) " (%s) Pin %c" diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index c62727f879..8ed19e9d0c 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # vhost.c vhost_commit(bool started, bool changed) "Started: %d Changed: %d" diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index e02544b2df..ab516ac614 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -1972,9 +1972,7 @@ static enum virtio_device_endian virtio_default_endian(void) static enum virtio_device_endian virtio_current_cpu_endian(void) { - CPUClass *cc = CPU_GET_CLASS(current_cpu); - - if (cc->virtio_is_big_endian(current_cpu)) { + if (cpu_virtio_is_big_endian(current_cpu)) { return VIRTIO_DEVICE_ENDIAN_BIG; } else { return VIRTIO_DEVICE_ENDIAN_LITTLE; diff --git a/hw/watchdog/trace-events b/hw/watchdog/trace-events index 3124ca1f1b..c3bafbffa9 100644 --- a/hw/watchdog/trace-events +++ b/hw/watchdog/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # cmsdk-apb-watchdog.c cmsdk_apb_watchdog_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB watchdog read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" diff --git a/hw/xen/trace-events b/hw/xen/trace-events index e6885bc751..3da3fd8348 100644 --- a/hw/xen/trace-events +++ b/hw/xen/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # ../../include/hw/xen/xen_common.h xen_default_ioreq_server(void) "" diff --git a/include/block/block.h b/include/block/block.h index 82185965ff..8e707a83b7 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -701,6 +701,7 @@ bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, GSList **ignore, Error **errp); AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); +AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c); int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz); int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo); diff --git a/include/block/block_int.h b/include/block/block_int.h index b2c8b09d0f..057d88b1fc 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -843,7 +843,6 @@ struct BlockDriverState { * locking needed during I/O... */ int open_flags; /* flags used to open the file, re-used for re-open */ - bool read_only; /* if true, the media is read only */ bool encrypted; /* if true, the media is encrypted */ bool sg; /* if true, the device is a /dev/sg* */ bool probed; /* if true, format was probed rather than specified */ @@ -1008,7 +1007,6 @@ struct BlockDriverState { struct BlockBackendRootState { int open_flags; - bool read_only; BlockdevDetectZeroesOptions detect_zeroes; }; diff --git a/replication.h b/include/block/replication.h index d49fc22cb9..21931b4f0c 100644 --- a/replication.h +++ b/include/block/replication.h @@ -23,7 +23,7 @@ typedef struct ReplicationOps ReplicationOps; typedef struct ReplicationState ReplicationState; /** - * SECTION:replication.h + * SECTION:block/replication.h * @title:Base Replication System * @short_description: interfaces for handling replication * @@ -32,7 +32,7 @@ typedef struct ReplicationState ReplicationState; * <example> * <title>How to use replication interfaces</title> * <programlisting> - * #include "replication.h" + * #include "block/replication.h" * * typedef struct BDRVReplicationState { * ReplicationState *rs; diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 8021adf38f..754f4130c9 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -21,7 +21,6 @@ #define EXEC_ALL_H #include "cpu.h" -#include "exec/tb-context.h" #ifdef CONFIG_TCG #include "exec/cpu_ldst.h" #endif diff --git a/include/exec/memory.h b/include/exec/memory.h index c8b9088924..c158fd7084 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -617,6 +617,18 @@ struct MemoryListener { void (*log_sync)(MemoryListener *listener, MemoryRegionSection *section); /** + * @log_sync_global: + * + * This is the global version of @log_sync when the listener does + * not have a way to synchronize the log with finer granularity. + * When the listener registers with @log_sync_global defined, then + * its @log_sync must be NULL. Vice versa. + * + * @listener: The #MemoryListener. + */ + void (*log_sync_global)(MemoryListener *listener); + + /** * @log_clear: * * Called before reading the dirty memory bitmap for a @@ -2305,7 +2317,7 @@ static inline uint8_t address_space_ldub_cached(MemoryRegionCache *cache, } static inline void address_space_stb_cached(MemoryRegionCache *cache, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) + hwaddr addr, uint8_t val, MemTxAttrs attrs, MemTxResult *result) { assert(addr < cache->len); if (likely(cache->ptr)) { diff --git a/include/exec/memory_ldst.h.inc b/include/exec/memory_ldst.h.inc index 46e6c220d3..7c3a641f7e 100644 --- a/include/exec/memory_ldst.h.inc +++ b/include/exec/memory_ldst.h.inc @@ -20,7 +20,7 @@ */ #ifdef TARGET_ENDIANNESS -extern uint32_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, +extern uint16_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); extern uint32_t glue(address_space_ldl, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); @@ -29,17 +29,17 @@ extern uint64_t glue(address_space_ldq, SUFFIX)(ARG1_DECL, extern void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stw, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stl, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stq, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val, MemTxAttrs attrs, MemTxResult *result); #else -extern uint32_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, +extern uint8_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); -extern uint32_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, +extern uint16_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); -extern uint32_t glue(address_space_lduw_be, SUFFIX)(ARG1_DECL, +extern uint16_t glue(address_space_lduw_be, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); extern uint32_t glue(address_space_ldl_le, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); @@ -50,11 +50,11 @@ extern uint64_t glue(address_space_ldq_le, SUFFIX)(ARG1_DECL, extern uint64_t glue(address_space_ldq_be, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stb, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint8_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stw_le, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stw_be, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stl_le, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stl_be, SUFFIX)(ARG1_DECL, diff --git a/include/exec/memory_ldst_cached.h.inc b/include/exec/memory_ldst_cached.h.inc index 7bc8790d34..d7834f852c 100644 --- a/include/exec/memory_ldst_cached.h.inc +++ b/include/exec/memory_ldst_cached.h.inc @@ -24,6 +24,18 @@ #define LD_P(size) \ glue(glue(ld, size), glue(ENDIANNESS, _p)) +static inline uint16_t ADDRESS_SPACE_LD_CACHED(uw)(MemoryRegionCache *cache, + hwaddr addr, MemTxAttrs attrs, MemTxResult *result) +{ + assert(addr < cache->len && 2 <= cache->len - addr); + fuzz_dma_read_cb(cache->xlat + addr, 2, cache->mrs.mr); + if (likely(cache->ptr)) { + return LD_P(uw)(cache->ptr + addr); + } else { + return ADDRESS_SPACE_LD_CACHED_SLOW(uw)(cache, addr, attrs, result); + } +} + static inline uint32_t ADDRESS_SPACE_LD_CACHED(l)(MemoryRegionCache *cache, hwaddr addr, MemTxAttrs attrs, MemTxResult *result) { @@ -48,18 +60,6 @@ static inline uint64_t ADDRESS_SPACE_LD_CACHED(q)(MemoryRegionCache *cache, } } -static inline uint32_t ADDRESS_SPACE_LD_CACHED(uw)(MemoryRegionCache *cache, - hwaddr addr, MemTxAttrs attrs, MemTxResult *result) -{ - assert(addr < cache->len && 2 <= cache->len - addr); - fuzz_dma_read_cb(cache->xlat + addr, 2, cache->mrs.mr); - if (likely(cache->ptr)) { - return LD_P(uw)(cache->ptr + addr); - } else { - return ADDRESS_SPACE_LD_CACHED_SLOW(uw)(cache, addr, attrs, result); - } -} - #undef ADDRESS_SPACE_LD_CACHED #undef ADDRESS_SPACE_LD_CACHED_SLOW #undef LD_P @@ -71,25 +71,25 @@ static inline uint32_t ADDRESS_SPACE_LD_CACHED(uw)(MemoryRegionCache *cache, #define ST_P(size) \ glue(glue(st, size), glue(ENDIANNESS, _p)) -static inline void ADDRESS_SPACE_ST_CACHED(l)(MemoryRegionCache *cache, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) +static inline void ADDRESS_SPACE_ST_CACHED(w)(MemoryRegionCache *cache, + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result) { - assert(addr < cache->len && 4 <= cache->len - addr); + assert(addr < cache->len && 2 <= cache->len - addr); if (likely(cache->ptr)) { - ST_P(l)(cache->ptr + addr, val); + ST_P(w)(cache->ptr + addr, val); } else { - ADDRESS_SPACE_ST_CACHED_SLOW(l)(cache, addr, val, attrs, result); + ADDRESS_SPACE_ST_CACHED_SLOW(w)(cache, addr, val, attrs, result); } } -static inline void ADDRESS_SPACE_ST_CACHED(w)(MemoryRegionCache *cache, +static inline void ADDRESS_SPACE_ST_CACHED(l)(MemoryRegionCache *cache, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) { - assert(addr < cache->len && 2 <= cache->len - addr); + assert(addr < cache->len && 4 <= cache->len - addr); if (likely(cache->ptr)) { - ST_P(w)(cache->ptr + addr, val); + ST_P(l)(cache->ptr + addr, val); } else { - ADDRESS_SPACE_ST_CACHED_SLOW(w)(cache, addr, val, attrs, result); + ADDRESS_SPACE_ST_CACHED_SLOW(l)(cache, addr, val, attrs, result); } } diff --git a/include/exec/memory_ldst_phys.h.inc b/include/exec/memory_ldst_phys.h.inc index b9dd53c389..ecd678610d 100644 --- a/include/exec/memory_ldst_phys.h.inc +++ b/include/exec/memory_ldst_phys.h.inc @@ -20,6 +20,12 @@ */ #ifdef TARGET_ENDIANNESS +static inline uint16_t glue(lduw_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_lduw, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + static inline uint32_t glue(ldl_phys, SUFFIX)(ARG1_DECL, hwaddr addr) { return glue(address_space_ldl, SUFFIX)(ARG1, addr, @@ -32,10 +38,10 @@ static inline uint64_t glue(ldq_phys, SUFFIX)(ARG1_DECL, hwaddr addr) MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(lduw_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stw_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint16_t val) { - return glue(address_space_lduw, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stw, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } static inline void glue(stl_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) @@ -44,18 +50,30 @@ static inline void glue(stl_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) MEMTXATTRS_UNSPECIFIED, NULL); } -static inline void glue(stw_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stw, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - static inline void glue(stq_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val) { glue(address_space_stq, SUFFIX)(ARG1, addr, val, MEMTXATTRS_UNSPECIFIED, NULL); } #else +static inline uint8_t glue(ldub_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_ldub, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + +static inline uint16_t glue(lduw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_lduw_le, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + +static inline uint16_t glue(lduw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_lduw_be, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + static inline uint32_t glue(ldl_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr) { return glue(address_space_ldl_le, SUFFIX)(ARG1, addr, @@ -80,22 +98,22 @@ static inline uint64_t glue(ldq_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr) MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(ldub_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stb_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint8_t val) { - return glue(address_space_ldub, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stb, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(lduw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint16_t val) { - return glue(address_space_lduw_le, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stw_le, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(lduw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint16_t val) { - return glue(address_space_lduw_be, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stw_be, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } static inline void glue(stl_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) @@ -110,24 +128,6 @@ static inline void glue(stl_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t va MEMTXATTRS_UNSPECIFIED, NULL); } -static inline void glue(stb_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stb, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - -static inline void glue(stw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stw_le, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - -static inline void glue(stw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stw_be, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - static inline void glue(stq_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val) { glue(address_space_stq_le, SUFFIX)(ARG1, addr, val, diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index 2f0674fbdd..34f4cf92ae 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -69,7 +69,7 @@ static inline void set_float_exception_flags(int val, float_status *status) status->float_exception_flags = val; } -static inline void set_floatx80_rounding_precision(int val, +static inline void set_floatx80_rounding_precision(FloatX80RoundPrec val, float_status *status) { status->floatx80_rounding_precision = val; @@ -120,7 +120,8 @@ static inline int get_float_exception_flags(float_status *status) return status->float_exception_flags; } -static inline int get_floatx80_rounding_precision(float_status *status) +static inline FloatX80RoundPrec +get_floatx80_rounding_precision(float_status *status) { return status->floatx80_rounding_precision; } diff --git a/include/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h index ec4e27a595..81c3fe8256 100644 --- a/include/fpu/softfloat-macros.h +++ b/include/fpu/softfloat-macros.h @@ -745,4 +745,38 @@ static inline bool ne128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1) return a0 != b0 || a1 != b1; } +/* + * Similarly, comparisons of 192-bit values. + */ + +static inline bool eq192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2) +{ + return ((a0 ^ b0) | (a1 ^ b1) | (a2 ^ b2)) == 0; +} + +static inline bool le192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2) +{ + if (a0 != b0) { + return a0 < b0; + } + if (a1 != b1) { + return a1 < b1; + } + return a2 <= b2; +} + +static inline bool lt192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2) +{ + if (a0 != b0) { + return a0 < b0; + } + if (a1 != b1) { + return a1 < b1; + } + return a2 < b2; +} + #endif diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index 8a3f20fae9..5bcbd041f7 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -134,8 +134,10 @@ typedef enum __attribute__((__packed__)) { float_round_up = 2, float_round_to_zero = 3, float_round_ties_away = 4, - /* Not an IEEE rounding mode: round to the closest odd mantissa value */ + /* Not an IEEE rounding mode: round to closest odd, overflow to max */ float_round_to_odd = 5, + /* Not an IEEE rounding mode: round to closest odd, overflow to inf */ + float_round_to_odd_inf = 6, } FloatRoundMode; /* @@ -152,6 +154,14 @@ enum { float_flag_output_denormal = 128 }; +/* + * Rounding precision for floatx80. + */ +typedef enum __attribute__((__packed__)) { + floatx80_precision_x, + floatx80_precision_d, + floatx80_precision_s, +} FloatX80RoundPrec; /* * Floating Point Status. Individual architectures may maintain @@ -163,7 +173,7 @@ enum { typedef struct float_status { FloatRoundMode float_rounding_mode; uint8_t float_exception_flags; - signed char floatx80_rounding_precision; + FloatX80RoundPrec floatx80_rounding_precision; bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ bool flush_to_zero; diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index 53f2c2ea3c..ec7dca0960 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -1152,7 +1152,7 @@ floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status); | Floating-Point Arithmetic. *----------------------------------------------------------------------------*/ -floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, +floatx80 roundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status); @@ -1165,7 +1165,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, | normalized. *----------------------------------------------------------------------------*/ -floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, +floatx80 normalizeRoundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status); @@ -1204,6 +1204,12 @@ float128 float128_rem(float128, float128, float_status *status); float128 float128_sqrt(float128, float_status *status); FloatRelation float128_compare(float128, float128, float_status *status); FloatRelation float128_compare_quiet(float128, float128, float_status *status); +float128 float128_min(float128, float128, float_status *status); +float128 float128_max(float128, float128, float_status *status); +float128 float128_minnum(float128, float128, float_status *status); +float128 float128_maxnum(float128, float128, float_status *status); +float128 float128_minnummag(float128, float128, float_status *status); +float128 float128_maxnummag(float128, float128, float_status *status); bool float128_is_quiet_nan(float128, float_status *status); bool float128_is_signaling_nan(float128, float_status *status); float128 float128_silence_nan(float128, float_status *status); diff --git a/include/glib-compat.h b/include/glib-compat.h index 4542e920d5..9e95c888f5 100644 --- a/include/glib-compat.h +++ b/include/glib-compat.h @@ -19,12 +19,12 @@ /* Ask for warnings for anything that was marked deprecated in * the defined version, or before. It is a candidate for rewrite. */ -#define GLIB_VERSION_MIN_REQUIRED GLIB_VERSION_2_48 +#define GLIB_VERSION_MIN_REQUIRED GLIB_VERSION_2_56 /* Ask for warnings if code tries to use function that did not * exist in the defined version. These risk breaking builds */ -#define GLIB_VERSION_MAX_ALLOWED GLIB_VERSION_2_48 +#define GLIB_VERSION_MAX_ALLOWED GLIB_VERSION_2_56 #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wdeprecated-declarations" @@ -68,15 +68,6 @@ * without generating warnings. */ -#if defined(_WIN32) && !GLIB_CHECK_VERSION(2, 50, 0) -/* - * g_poll has a problem on Windows when using - * timeouts < 10ms, so use wrapper. - */ -#define g_poll(fds, nfds, timeout) g_poll_fixed(fds, nfds, timeout) -gint g_poll_fixed(GPollFD *fds, guint nfds, gint timeout); -#endif - #if defined(G_OS_UNIX) /* * Note: The fallback implementation is not MT-safe, and it returns a copy of diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index cc308a5d2c..63025fb27c 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -18,7 +18,7 @@ */ /* - * The Allwinner H3 is a System on Chip containing four ARM Cortex A7 + * The Allwinner H3 is a System on Chip containing four ARM Cortex-A7 * processor cores. Features and specifications include DDR2/DDR3 memory, * SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and * various I/O modules. diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index 189b23a8ce..bc6733c518 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -46,6 +46,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MState, ARMV7M) * devices will be automatically layered on top of this view.) * + Property "idau": IDAU interface (forwarded to CPU object) * + Property "init-svtor": secure VTOR reset value (forwarded to CPU object) + * + Property "init-nsvtor": non-secure VTOR reset value (forwarded to CPU object) * + Property "vfp": enable VFP (forwarded to CPU object) * + Property "dsp": enable DSP (forwarded to CPU object) * + Property "enable-bitband": expose bitbanded IO @@ -69,6 +70,7 @@ struct ARMv7MState { MemoryRegion *board_memory; Object *idau; uint32_t init_svtor; + uint32_t init_nsvtor; bool enable_bitband; bool start_powered_off; bool vfp; diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index d45f78290e..4e0ea68efc 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -80,6 +80,9 @@ struct TCGCPUOps; /* see accel-cpu.h */ struct AccelCPUClass; +/* see sysemu-cpu-ops.h */ +struct SysemuCPUOps; + /** * CPUClass: * @class_by_name: Callback to map -cpu command line model name to an @@ -87,16 +90,9 @@ struct AccelCPUClass; * @parse_features: Callback to parse command line arguments. * @reset_dump_flags: #CPUDumpFlags to use for reset logging. * @has_work: Callback for checking if there is work to do. - * @virtio_is_big_endian: Callback to return %true if a CPU which supports - * runtime configurable endianness is currently big-endian. Non-configurable - * CPUs can use the default implementation of this method. This method should - * not be used by any callers other than the pre-1.0 virtio devices. * @memory_rw_debug: Callback for GDB memory access. * @dump_state: Callback for dumping state. - * @dump_statistics: Callback for dumping statistics. * @get_arch_id: Callback for getting architecture-dependent CPU ID. - * @get_paging_enabled: Callback for inquiring whether paging is enabled. - * @get_memory_mapping: Callback for obtaining the memory mappings. * @set_pc: Callback for setting the Program Counter register. This * should have the semantics used by the target architecture when * setting the PC from a source such as an ELF file entry point; @@ -105,24 +101,8 @@ struct AccelCPUClass; * If the target behaviour here is anything other than "set * the PC register to the value passed in" then the target must * also implement the synchronize_from_tb hook. - * @get_phys_page_debug: Callback for obtaining a physical address. - * @get_phys_page_attrs_debug: Callback for obtaining a physical address and the - * associated memory transaction attributes to use for the access. - * CPUs which use memory transaction attributes should implement this - * instead of get_phys_page_debug. - * @asidx_from_attrs: Callback to return the CPU AddressSpace to use for - * a memory access with the specified memory transaction attributes. * @gdb_read_register: Callback for letting GDB read a register. * @gdb_write_register: Callback for letting GDB write a register. - * @write_elf64_note: Callback for writing a CPU-specific ELF note to a - * 64-bit VM coredump. - * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF - * note to a 32-bit VM coredump. - * @write_elf32_note: Callback for writing a CPU-specific ELF note to a - * 32-bit VM coredump. - * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF - * note to a 32-bit VM coredump. - * @vmsd: State description for migration. * @gdb_num_core_regs: Number of core registers accessible to GDB. * @gdb_core_xml_file: File name for core registers GDB XML description. * @gdb_stop_before_watchpoint: Indicates whether GDB expects the CPU to stop @@ -150,34 +130,14 @@ struct CPUClass { int reset_dump_flags; bool (*has_work)(CPUState *cpu); - bool (*virtio_is_big_endian)(CPUState *cpu); int (*memory_rw_debug)(CPUState *cpu, vaddr addr, uint8_t *buf, int len, bool is_write); void (*dump_state)(CPUState *cpu, FILE *, int flags); - GuestPanicInformation* (*get_crash_info)(CPUState *cpu); - void (*dump_statistics)(CPUState *cpu, int flags); int64_t (*get_arch_id)(CPUState *cpu); - bool (*get_paging_enabled)(const CPUState *cpu); - void (*get_memory_mapping)(CPUState *cpu, MemoryMappingList *list, - Error **errp); void (*set_pc)(CPUState *cpu, vaddr value); - hwaddr (*get_phys_page_debug)(CPUState *cpu, vaddr addr); - hwaddr (*get_phys_page_attrs_debug)(CPUState *cpu, vaddr addr, - MemTxAttrs *attrs); - int (*asidx_from_attrs)(CPUState *cpu, MemTxAttrs attrs); int (*gdb_read_register)(CPUState *cpu, GByteArray *buf, int reg); int (*gdb_write_register)(CPUState *cpu, uint8_t *buf, int reg); - int (*write_elf64_note)(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque); - int (*write_elf64_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque); - int (*write_elf32_note)(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque); - int (*write_elf32_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque); - - const VMStateDescription *vmsd; const char *gdb_core_xml_file; gchar * (*gdb_arch_name)(CPUState *cpu); const char * (*gdb_get_dynamic_xml)(CPUState *cpu, const char *xmlname); @@ -190,8 +150,11 @@ struct CPUClass { bool gdb_stop_before_watchpoint; struct AccelCPUClass *accel_cpu; + /* when system emulation is not available, this pointer is NULL */ + const struct SysemuCPUOps *sysemu_ops; + /* when TCG is not available, this pointer is NULL */ - struct TCGCPUOps *tcg_ops; + const struct TCGCPUOps *tcg_ops; /* * if not NULL, this is called in order for the CPUClass to initialize @@ -251,6 +214,7 @@ struct KVMState; struct kvm_run; struct hax_vcpu_state; +struct hvf_vcpu_state; #define TB_JMP_CACHE_BITS 12 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) @@ -329,6 +293,10 @@ struct qemu_work_item; * @ignore_memory_transaction_failures: Cached copy of the MachineState * flag of the same name: allows the board to suppress calling of the * CPU do_transaction_failed hook function. + * @kvm_dirty_gfns: Points to the KVM dirty ring for this CPU when KVM dirty + * ring is enabled. + * @kvm_fetch_index: Keeps the index that we last fetched from the per-vCPU + * dirty ring structure. * * State of one CPU core or thread. */ @@ -400,9 +368,12 @@ struct CPUState { */ uintptr_t mem_io_pc; + /* Only used in KVM */ int kvm_fd; struct KVMState *kvm_state; struct kvm_run *kvm_run; + struct kvm_dirty_gfn *kvm_dirty_gfns; + uint32_t kvm_fetch_index; /* Used for events with 'vcpu' and *without* the 'disabled' properties */ DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS); @@ -436,7 +407,7 @@ struct CPUState { struct hax_vcpu_state *hax_vcpu; - int hvf_fd; + struct hvf_vcpu_state *hvf; /* track IOMMUs whose translations we've cached in the TCG TLB */ GArray *iommu_notifiers; @@ -562,16 +533,6 @@ enum CPUDumpFlags { */ void cpu_dump_state(CPUState *cpu, FILE *f, int flags); -/** - * cpu_dump_statistics: - * @cpu: The CPU whose state is to be dumped. - * @flags: Flags what to dump. - * - * Dump CPU statistics to the current monitor if we have one, else to - * stdout. - */ -void cpu_dump_statistics(CPUState *cpu, int flags); - #ifndef CONFIG_USER_ONLY /** * cpu_get_phys_page_attrs_debug: @@ -586,18 +547,8 @@ void cpu_dump_statistics(CPUState *cpu, int flags); * * Returns: Corresponding physical page address or -1 if no page found. */ -static inline hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, - MemTxAttrs *attrs) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - if (cc->get_phys_page_attrs_debug) { - return cc->get_phys_page_attrs_debug(cpu, addr, attrs); - } - /* Fallback for CPUs which don't implement the _attrs_ hook */ - *attrs = MEMTXATTRS_UNSPECIFIED; - return cc->get_phys_page_debug(cpu, addr); -} +hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, + MemTxAttrs *attrs); /** * cpu_get_phys_page_debug: @@ -609,12 +560,7 @@ static inline hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, * * Returns: Corresponding physical page address or -1 if no page found. */ -static inline hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) -{ - MemTxAttrs attrs = {}; - - return cpu_get_phys_page_attrs_debug(cpu, addr, &attrs); -} +hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); /** cpu_asidx_from_attrs: * @cpu: CPU @@ -623,17 +569,16 @@ static inline hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) * Returns the address space index specifying the CPU AddressSpace * to use for a memory access with the given transaction attributes. */ -static inline int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - int ret = 0; +int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs); - if (cc->asidx_from_attrs) { - ret = cc->asidx_from_attrs(cpu, attrs); - assert(ret < cpu->num_ases && ret >= 0); - } - return ret; -} +/** + * cpu_virtio_is_big_endian: + * @cpu: CPU + + * Returns %true if a CPU which supports runtime configurable endianness + * is currently big-endian. + */ +bool cpu_virtio_is_big_endian(CPUState *cpu); #endif /* CONFIG_USER_ONLY */ @@ -1074,10 +1019,8 @@ bool target_words_bigendian(void); #ifdef NEED_CPU_H #ifdef CONFIG_SOFTMMU + extern const VMStateDescription vmstate_cpu_common; -#else -#define vmstate_cpu_common vmstate_dummy -#endif #define VMSTATE_CPU() { \ .name = "parent_obj", \ @@ -1086,6 +1029,7 @@ extern const VMStateDescription vmstate_cpu_common; .flags = VMS_STRUCT, \ .offset = 0, \ } +#endif /* CONFIG_SOFTMMU */ #endif /* NEED_CPU_H */ diff --git a/include/hw/core/sysemu-cpu-ops.h b/include/hw/core/sysemu-cpu-ops.h new file mode 100644 index 0000000000..a9ba39e5f2 --- /dev/null +++ b/include/hw/core/sysemu-cpu-ops.h @@ -0,0 +1,92 @@ +/* + * CPU operations specific to system emulation + * + * Copyright (c) 2012 SUSE LINUX Products GmbH + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef SYSEMU_CPU_OPS_H +#define SYSEMU_CPU_OPS_H + +#include "hw/core/cpu.h" + +/* + * struct SysemuCPUOps: System operations specific to a CPU class + */ +typedef struct SysemuCPUOps { + /** + * @get_memory_mapping: Callback for obtaining the memory mappings. + */ + void (*get_memory_mapping)(CPUState *cpu, MemoryMappingList *list, + Error **errp); + /** + * @get_paging_enabled: Callback for inquiring whether paging is enabled. + */ + bool (*get_paging_enabled)(const CPUState *cpu); + /** + * @get_phys_page_debug: Callback for obtaining a physical address. + */ + hwaddr (*get_phys_page_debug)(CPUState *cpu, vaddr addr); + /** + * @get_phys_page_attrs_debug: Callback for obtaining a physical address + * and the associated memory transaction attributes to use for the + * access. + * CPUs which use memory transaction attributes should implement this + * instead of get_phys_page_debug. + */ + hwaddr (*get_phys_page_attrs_debug)(CPUState *cpu, vaddr addr, + MemTxAttrs *attrs); + /** + * @asidx_from_attrs: Callback to return the CPU AddressSpace to use for + * a memory access with the specified memory transaction attributes. + */ + int (*asidx_from_attrs)(CPUState *cpu, MemTxAttrs attrs); + /** + * @get_crash_info: Callback for reporting guest crash information in + * GUEST_PANICKED events. + */ + GuestPanicInformation* (*get_crash_info)(CPUState *cpu); + /** + * @write_elf32_note: Callback for writing a CPU-specific ELF note to a + * 32-bit VM coredump. + */ + int (*write_elf32_note)(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque); + /** + * @write_elf64_note: Callback for writing a CPU-specific ELF note to a + * 64-bit VM coredump. + */ + int (*write_elf64_note)(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque); + /** + * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF + * note to a 32-bit VM coredump. + */ + int (*write_elf32_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque); + /** + * @write_elf64_qemunote: Callback for writing a CPU- and QEMU-specific ELF + * note to a 64-bit VM coredump. + */ + int (*write_elf64_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque); + /** + * @virtio_is_big_endian: Callback to return %true if a CPU which supports + * runtime configurable endianness is currently big-endian. + * Non-configurable CPUs can use the default implementation of this method. + * This method should not be used by any callers other than the pre-1.0 + * virtio devices. + */ + bool (*virtio_is_big_endian)(CPUState *cpu); + + /** + * @legacy_vmsd: Legacy state for migration. + * Do not use in new targets, use #DeviceClass::vmsd instead. + */ + const VMStateDescription *legacy_vmsd; + +} SysemuCPUOps; + +#endif /* SYSEMU_CPU_OPS_H */ diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index bbf817af46..f05219f75e 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -223,6 +223,9 @@ struct SpaprMachineState { int fwnmi_machine_check_interlock; QemuCond fwnmi_machine_check_interlock_cond; + /* Set by -boot */ + char *boot_device; + /*< public >*/ char *kvm_type; char *host_model; diff --git a/include/hw/ppc/spapr_nvdimm.h b/include/hw/ppc/spapr_nvdimm.h index 73be250e2a..764f999f54 100644 --- a/include/hw/ppc/spapr_nvdimm.h +++ b/include/hw/ppc/spapr_nvdimm.h @@ -11,19 +11,9 @@ #define HW_SPAPR_NVDIMM_H #include "hw/mem/nvdimm.h" -#include "hw/ppc/spapr.h" -/* - * The nvdimm size should be aligned to SCM block size. - * The SCM block size should be aligned to SPAPR_MEMORY_BLOCK_SIZE - * inorder to have SCM regions not to overlap with dimm memory regions. - * The SCM devices can have variable block sizes. For now, fixing the - * block size to the minimum value. - */ -#define SPAPR_MINIMUM_SCM_BLOCK_SIZE SPAPR_MEMORY_BLOCK_SIZE - -/* Have an explicit check for alignment */ -QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE); +typedef struct SpaprDrc SpaprDrc; +typedef struct SpaprMachineState SpaprMachineState; int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, void *fdt, int *fdt_start_offset, Error **errp); diff --git a/include/hw/virtio/virtio-gpu-bswap.h b/include/hw/virtio/virtio-gpu-bswap.h index 203f9e1718..e2bee8f595 100644 --- a/include/hw/virtio/virtio-gpu-bswap.h +++ b/include/hw/virtio/virtio-gpu-bswap.h @@ -59,4 +59,20 @@ virtio_gpu_t2d_bswap(struct virtio_gpu_transfer_to_host_2d *t2d) le32_to_cpus(&t2d->padding); } +static inline void +virtio_gpu_create_blob_bswap(struct virtio_gpu_resource_create_blob *cblob) +{ + virtio_gpu_ctrl_hdr_bswap(&cblob->hdr); + le32_to_cpus(&cblob->resource_id); + le32_to_cpus(&cblob->blob_flags); + le64_to_cpus(&cblob->size); +} + +static inline void +virtio_gpu_scanout_blob_bswap(struct virtio_gpu_set_scanout_blob *ssb) +{ + virtio_gpu_bswap_32(ssb, sizeof(*ssb) - sizeof(ssb->offsets[3])); + le32_to_cpus(&ssb->offsets[3]); +} + #endif diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h index 8ca2c55d9a..bcf54d970f 100644 --- a/include/hw/virtio/virtio-gpu.h +++ b/include/hw/virtio/virtio-gpu.h @@ -50,9 +50,23 @@ struct virtio_gpu_simple_resource { uint32_t scanout_bitmask; pixman_image_t *image; uint64_t hostmem; + + uint64_t blob_size; + void *blob; + int dmabuf_fd; + uint8_t *remapped; + QTAILQ_ENTRY(virtio_gpu_simple_resource) next; }; +struct virtio_gpu_framebuffer { + pixman_format_code_t format; + uint32_t bytes_pp; + uint32_t width, height; + uint32_t stride; + uint32_t offset; +}; + struct virtio_gpu_scanout { QemuConsole *con; DisplaySurface *ds; @@ -75,6 +89,7 @@ enum virtio_gpu_base_conf_flags { VIRTIO_GPU_FLAG_STATS_ENABLED, VIRTIO_GPU_FLAG_EDID_ENABLED, VIRTIO_GPU_FLAG_DMABUF_ENABLED, + VIRTIO_GPU_FLAG_BLOB_ENABLED, }; #define virtio_gpu_virgl_enabled(_cfg) \ @@ -85,6 +100,8 @@ enum virtio_gpu_base_conf_flags { (_cfg.flags & (1 << VIRTIO_GPU_FLAG_EDID_ENABLED)) #define virtio_gpu_dmabuf_enabled(_cfg) \ (_cfg.flags & (1 << VIRTIO_GPU_FLAG_DMABUF_ENABLED)) +#define virtio_gpu_blob_enabled(_cfg) \ + (_cfg.flags & (1 << VIRTIO_GPU_FLAG_BLOB_ENABLED)) struct virtio_gpu_base_conf { uint32_t max_outputs; @@ -133,6 +150,12 @@ struct VirtIOGPUBaseClass { DEFINE_PROP_UINT32("xres", _state, _conf.xres, 1024), \ DEFINE_PROP_UINT32("yres", _state, _conf.yres, 768) +typedef struct VGPUDMABuf { + QemuDmaBuf buf; + uint32_t scanout_id; + QTAILQ_ENTRY(VGPUDMABuf) next; +} VGPUDMABuf; + struct VirtIOGPU { VirtIOGPUBase parent_obj; @@ -161,6 +184,11 @@ struct VirtIOGPU { uint32_t req_3d; uint32_t bytes_3d; } stats; + + struct { + QTAILQ_HEAD(, VGPUDMABuf) bufs; + VGPUDMABuf *primary; + } dmabuf; }; struct VirtIOGPUClass { @@ -224,7 +252,7 @@ void virtio_gpu_get_display_info(VirtIOGPU *g, void virtio_gpu_get_edid(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd); int virtio_gpu_create_mapping_iov(VirtIOGPU *g, - struct virtio_gpu_resource_attach_backing *ab, + uint32_t nr_entries, uint32_t offset, struct virtio_gpu_ctrl_command *cmd, uint64_t **addr, struct iovec **iov, uint32_t *niov); @@ -238,6 +266,15 @@ void virtio_gpu_update_cursor_data(VirtIOGPU *g, struct virtio_gpu_scanout *s, uint32_t resource_id); +/* virtio-gpu-udmabuf.c */ +bool virtio_gpu_have_udmabuf(void); +void virtio_gpu_init_udmabuf(struct virtio_gpu_simple_resource *res); +void virtio_gpu_fini_udmabuf(struct virtio_gpu_simple_resource *res); +int virtio_gpu_update_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb); + /* virtio-gpu-3d.c */ void virtio_gpu_virgl_process_cmd(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd); diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 075ee80096..8df7b69f38 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -194,8 +194,6 @@ struct VMStateDescription { const VMStateDescription **subsections; }; -extern const VMStateDescription vmstate_dummy; - extern const VMStateInfo vmstate_info_bool; extern const VMStateInfo vmstate_info_int8; diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h index 8f4b3a80fb..3ccf84fd46 100644 --- a/include/qemu/atomic.h +++ b/include/qemu/atomic.h @@ -8,7 +8,7 @@ * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. * - * See docs/devel/atomics.txt for discussion about the guarantees each + * See docs/devel/atomics.rst for discussion about the guarantees each * atomic primitive is meant to provide. */ @@ -432,7 +432,7 @@ * sequentially consistent operations. * * As long as they are used as paired operations they are safe to - * use. See docs/devel/atomics.txt for more discussion. + * use. See docs/devel/atomics.rst for more discussion. */ #ifndef qatomic_mb_read diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h index ad2bcf45b4..adb9a1a260 100644 --- a/include/qemu/atomic128.h +++ b/include/qemu/atomic128.h @@ -6,7 +6,7 @@ * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. * - * See docs/devel/atomics.txt for discussion about the guarantees each + * See docs/devel/atomics.rst for discussion about the guarantees each * atomic primitive is meant to provide. */ diff --git a/include/qemu/config-file.h b/include/qemu/config-file.h index 8d3e53ae4d..0500b3668d 100644 --- a/include/qemu/config-file.h +++ b/include/qemu/config-file.h @@ -1,7 +1,7 @@ #ifndef QEMU_CONFIG_FILE_H #define QEMU_CONFIG_FILE_H - +void qemu_load_module_for_opts(const char *group); QemuOptsList *qemu_find_opts(const char *group); QemuOptsList *qemu_find_opts_err(const char *group, Error **errp); QemuOpts *qemu_find_opts_singleton(const char *group); diff --git a/qemu-options.h b/include/qemu/qemu-options.h index b4ee63cd60..4a62c83c45 100644 --- a/qemu-options.h +++ b/include/qemu/qemu-options.h @@ -29,8 +29,13 @@ #define QEMU_OPTIONS_H enum { -#define QEMU_OPTIONS_GENERATE_ENUM -#include "qemu-options-wrapper.h" + +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + opt_enum, +#define DEFHEADING(text) +#define ARCHHEADING(text, arch_mask) + +#include "qemu-options.def" }; #endif diff --git a/include/standard-headers/linux/udmabuf.h b/include/standard-headers/linux/udmabuf.h new file mode 100644 index 0000000000..e19eb5b5ce --- /dev/null +++ b/include/standard-headers/linux/udmabuf.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_UDMABUF_H +#define _LINUX_UDMABUF_H + +#include "standard-headers/linux/types.h" + +#define UDMABUF_FLAGS_CLOEXEC 0x01 + +struct udmabuf_create { + uint32_t memfd; + uint32_t flags; + uint64_t offset; + uint64_t size; +}; + +struct udmabuf_create_item { + uint32_t memfd; + uint32_t __pad; + uint64_t offset; + uint64_t size; +}; + +struct udmabuf_create_list { + uint32_t flags; + uint32_t count; + struct udmabuf_create_item list[]; +}; + +#define UDMABUF_CREATE _IOW('u', 0x42, struct udmabuf_create) +#define UDMABUF_CREATE_LIST _IOW('u', 0x43, struct udmabuf_create_list) + +#endif /* _LINUX_UDMABUF_H */ diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index 880e903293..5423e3d9c6 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -66,6 +66,10 @@ typedef struct BlockDevOps { * Runs when the backend's last drain request ends. */ void (*drained_end)(void *opaque); + /* + * Is the device still busy? + */ + bool (*drained_poll)(void *opaque); } BlockDevOps; /* This struct is embedded in (the private) BlockBackend struct and contains diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h new file mode 100644 index 0000000000..8b66a4e7d0 --- /dev/null +++ b/include/sysemu/hvf_int.h @@ -0,0 +1,58 @@ +/* + * QEMU Hypervisor.framework (HVF) support + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +/* header to be included in HVF-specific code */ + +#ifndef HVF_INT_H +#define HVF_INT_H + +#include <Hypervisor/hv.h> + +/* hvf_slot flags */ +#define HVF_SLOT_LOG (1 << 0) + +typedef struct hvf_slot { + uint64_t start; + uint64_t size; + uint8_t *mem; + int slot_id; + uint32_t flags; + MemoryRegion *region; +} hvf_slot; + +typedef struct hvf_vcpu_caps { + uint64_t vmx_cap_pinbased; + uint64_t vmx_cap_procbased; + uint64_t vmx_cap_procbased2; + uint64_t vmx_cap_entry; + uint64_t vmx_cap_exit; + uint64_t vmx_cap_preemption_timer; +} hvf_vcpu_caps; + +struct HVFState { + AccelState parent; + hvf_slot slots[32]; + int num_slots; + + hvf_vcpu_caps *hvf_caps; +}; +extern HVFState *hvf_state; + +struct hvf_vcpu_state { + int fd; +}; + +void assert_hvf_ok(hv_return_t ret); +int hvf_arch_init_vcpu(CPUState *cpu); +void hvf_arch_vcpu_destroy(CPUState *cpu); +int hvf_vcpu_exec(CPUState *); +hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); +int hvf_put_registers(CPUState *); +int hvf_get_registers(CPUState *); + +#endif diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index ccb8869f01..c788452cd9 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -23,12 +23,15 @@ typedef struct KVMSlot int old_flags; /* Dirty bitmap cache for the slot */ unsigned long *dirty_bmap; + unsigned long dirty_bmap_size; + /* Cache of the address space ID */ + int as_id; + /* Cache of the offset in ram address space */ + ram_addr_t ram_start_offset; } KVMSlot; typedef struct KVMMemoryListener { MemoryListener listener; - /* Protects the slots and all inside them */ - QemuMutex slots_lock; KVMSlot *slots; int as_id; } KVMMemoryListener; diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index 0f0695e90d..74cb345308 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -27,7 +27,6 @@ #include "cpu.h" #include "exec/memop.h" -#include "exec/tb-context.h" #include "qemu/bitops.h" #include "qemu/plugin.h" #include "qemu/queue.h" diff --git a/include/ui/console.h b/include/ui/console.h index ca3c7af6a6..b30b63976a 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -471,4 +471,7 @@ bool vnc_display_reload_certs(const char *id, Error **errp); /* input.c */ int index_from_key(const char *key, size_t key_length); +/* udmabuf.c */ +int udmabuf_fd(void); + #endif diff --git a/include/ui/qemu-pixman.h b/include/ui/qemu-pixman.h index 87737a6f16..806ddcd7cd 100644 --- a/include/ui/qemu-pixman.h +++ b/include/ui/qemu-pixman.h @@ -62,6 +62,7 @@ typedef struct PixelFormat { PixelFormat qemu_pixelformat_from_pixman(pixman_format_code_t format); pixman_format_code_t qemu_default_pixman_format(int bpp, bool native_endian); pixman_format_code_t qemu_drm_format_to_pixman(uint32_t drm_format); +uint32_t qemu_pixman_to_drm_format(pixman_format_code_t pixman); int qemu_pixman_get_type(int rshift, int gshift, int bshift); pixman_format_code_t qemu_pixman_get_format(PixelFormat *pf); bool qemu_pixman_check_format(DisplayChangeListener *dcl, diff --git a/io/trace-events b/io/trace-events index d7bc70b966..c5e814eb44 100644 --- a/io/trace-events +++ b/io/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # task.c qio_task_new(void *task, void *source, void *func, void *opaque) "Task new task=%p source=%p func=%p opaque=%p" diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 020b62a619..897f831374 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -1591,6 +1591,8 @@ enum sev_cmd_id { KVM_SEV_DBG_ENCRYPT, /* Guest certificates commands */ KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, KVM_SEV_NR_MAX, }; @@ -1643,6 +1645,12 @@ struct kvm_sev_dbg { __u32 len; }; +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) diff --git a/linux-user/arm/nwfpe/fpa11.c b/linux-user/arm/nwfpe/fpa11.c index f6f8163eab..9a93610d24 100644 --- a/linux-user/arm/nwfpe/fpa11.c +++ b/linux-user/arm/nwfpe/fpa11.c @@ -97,37 +97,38 @@ void SetRoundingMode(const unsigned int opcode) void SetRoundingPrecision(const unsigned int opcode) { - int rounding_precision; - FPA11 *fpa11 = GET_FPA11(); + FloatX80RoundPrec rounding_precision; + FPA11 *fpa11 = GET_FPA11(); #ifdef MAINTAIN_FPCR - fpa11->fpcr &= ~MASK_ROUNDING_PRECISION; + fpa11->fpcr &= ~MASK_ROUNDING_PRECISION; #endif - switch (opcode & MASK_ROUNDING_PRECISION) - { - case ROUND_SINGLE: - rounding_precision = 32; + switch (opcode & MASK_ROUNDING_PRECISION) { + case ROUND_SINGLE: + rounding_precision = floatx80_precision_s; #ifdef MAINTAIN_FPCR - fpa11->fpcr |= ROUND_SINGLE; + fpa11->fpcr |= ROUND_SINGLE; #endif - break; + break; - case ROUND_DOUBLE: - rounding_precision = 64; + case ROUND_DOUBLE: + rounding_precision = floatx80_precision_d; #ifdef MAINTAIN_FPCR - fpa11->fpcr |= ROUND_DOUBLE; + fpa11->fpcr |= ROUND_DOUBLE; #endif - break; + break; - case ROUND_EXTENDED: - rounding_precision = 80; + case ROUND_EXTENDED: + rounding_precision = floatx80_precision_x; #ifdef MAINTAIN_FPCR - fpa11->fpcr |= ROUND_EXTENDED; + fpa11->fpcr |= ROUND_EXTENDED; #endif - break; + break; - default: rounding_precision = 80; - } - set_floatx80_rounding_precision(rounding_precision, &fpa11->fp_status); + default: + rounding_precision = floatx80_precision_x; + break; + } + set_floatx80_rounding_precision(rounding_precision, &fpa11->fp_status); } /* Emulate the instruction in the opcode. */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index 1ab97e38e0..17ab06f612 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -659,7 +659,9 @@ static uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_sve_i8mm, ARM_HWCAP2_A64_SVEI8MM); GET_FEATURE_ID(aa64_sve_f32mm, ARM_HWCAP2_A64_SVEF32MM); GET_FEATURE_ID(aa64_sve_f64mm, ARM_HWCAP2_A64_SVEF64MM); + GET_FEATURE_ID(aa64_sve_bf16, ARM_HWCAP2_A64_SVEBF16); GET_FEATURE_ID(aa64_i8mm, ARM_HWCAP2_A64_I8MM); + GET_FEATURE_ID(aa64_bf16, ARM_HWCAP2_A64_BF16); GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); diff --git a/linux-user/trace-events b/linux-user/trace-events index 0296133dae..1ec0d11ee3 100644 --- a/linux-user/trace-events +++ b/linux-user/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # signal.c signal_table_init(int i) "number of unavailable signals: %d" diff --git a/memory_ldst.c.inc b/memory_ldst.c.inc index b56e961967..84b868f294 100644 --- a/memory_ldst.c.inc +++ b/memory_ldst.c.inc @@ -157,7 +157,7 @@ uint64_t glue(address_space_ldq_be, SUFFIX)(ARG1_DECL, DEVICE_BIG_ENDIAN); } -uint32_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, +uint8_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result) { uint8_t *ptr; @@ -193,7 +193,7 @@ uint32_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, } /* warning: addr must be aligned */ -static inline uint32_t glue(address_space_lduw_internal, SUFFIX)(ARG1_DECL, +static inline uint16_t glue(address_space_lduw_internal, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result, enum device_endian endian) { @@ -240,21 +240,21 @@ static inline uint32_t glue(address_space_lduw_internal, SUFFIX)(ARG1_DECL, return val; } -uint32_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, +uint16_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result) { return glue(address_space_lduw_internal, SUFFIX)(ARG1, addr, attrs, result, DEVICE_NATIVE_ENDIAN); } -uint32_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, +uint16_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result) { return glue(address_space_lduw_internal, SUFFIX)(ARG1, addr, attrs, result, DEVICE_LITTLE_ENDIAN); } -uint32_t glue(address_space_lduw_be, SUFFIX)(ARG1_DECL, +uint16_t glue(address_space_lduw_be, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result) { return glue(address_space_lduw_internal, SUFFIX)(ARG1, addr, attrs, result, @@ -366,7 +366,7 @@ void glue(address_space_stl_be, SUFFIX)(ARG1_DECL, } void glue(address_space_stb, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) + hwaddr addr, uint8_t val, MemTxAttrs attrs, MemTxResult *result) { uint8_t *ptr; MemoryRegion *mr; @@ -398,7 +398,7 @@ void glue(address_space_stb, SUFFIX)(ARG1_DECL, /* warning: addr must be aligned */ static inline void glue(address_space_stw_internal, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result, enum device_endian endian) { uint8_t *ptr; @@ -441,21 +441,21 @@ static inline void glue(address_space_stw_internal, SUFFIX)(ARG1_DECL, } void glue(address_space_stw, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result) { glue(address_space_stw_internal, SUFFIX)(ARG1, addr, val, attrs, result, DEVICE_NATIVE_ENDIAN); } void glue(address_space_stw_le, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result) { glue(address_space_stw_internal, SUFFIX)(ARG1, addr, val, attrs, result, DEVICE_LITTLE_ENDIAN); } void glue(address_space_stw_be, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result) { glue(address_space_stw_internal, SUFFIX)(ARG1, addr, val, attrs, result, DEVICE_BIG_ENDIAN); diff --git a/meson.build b/meson.build index bcbce8e164..e63dcf7bd4 100644 --- a/meson.build +++ b/meson.build @@ -1918,7 +1918,7 @@ util_ss.add_all(trace_ss) util_ss = util_ss.apply(config_all, strict: false) libqemuutil = static_library('qemuutil', sources: util_ss.sources() + stub_ss.sources() + genh, - dependencies: [util_ss.dependencies(), m, glib, socket, malloc]) + dependencies: [util_ss.dependencies(), m, glib, socket, malloc, pixman]) qemuutil = declare_dependency(link_with: libqemuutil, sources: genh + version_res) @@ -2167,6 +2167,7 @@ common_all = common_ss.apply(config_all, strict: false) common_all = static_library('common', build_by_default: false, sources: common_all.sources() + genh, + implicit_include_directories: false, dependencies: common_all.dependencies(), name_suffix: 'fa') diff --git a/migration/colo.c b/migration/colo.c index de27662cab..e498fdb125 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -28,7 +28,7 @@ #include "migration/failover.h" #include "migration/ram.h" #ifdef CONFIG_REPLICATION -#include "replication.h" +#include "block/replication.h" #endif #include "net/colo-compare.h" #include "net/colo.h" diff --git a/migration/rdma.c b/migration/rdma.c index 00eac34232..1cdb4561f3 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -36,6 +36,7 @@ #include <rdma/rdma_cma.h> #include "trace.h" #include "qom/object.h" +#include <poll.h> /* * Print and error on both the Monitor and the Log file. @@ -316,6 +317,7 @@ typedef struct RDMALocalBlocks { typedef struct RDMAContext { char *host; int port; + char *host_port; RDMAWorkRequestData wr_data[RDMA_WRID_MAX]; @@ -987,10 +989,12 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) } } + rdma_freeaddrinfo(res); ERROR(errp, "could not resolve address %s", rdma->host); goto err_resolve_get_addr; route: + rdma_freeaddrinfo(res); qemu_rdma_dump_gid("source_resolve_addr", rdma->cm_id); ret = rdma_get_cm_event(rdma->channel, &cm_event); @@ -2390,7 +2394,9 @@ static void qemu_rdma_cleanup(RDMAContext *rdma) rdma->channel = NULL; } g_free(rdma->host); + g_free(rdma->host_port); rdma->host = NULL; + rdma->host_port = NULL; } @@ -2455,7 +2461,36 @@ err_rdma_source_init: return -1; } -static int qemu_rdma_connect(RDMAContext *rdma, Error **errp) +static int qemu_get_cm_event_timeout(RDMAContext *rdma, + struct rdma_cm_event **cm_event, + long msec, Error **errp) +{ + int ret; + struct pollfd poll_fd = { + .fd = rdma->channel->fd, + .events = POLLIN, + .revents = 0 + }; + + do { + ret = poll(&poll_fd, 1, msec); + } while (ret < 0 && errno == EINTR); + + if (ret == 0) { + ERROR(errp, "poll cm event timeout"); + return -1; + } else if (ret < 0) { + ERROR(errp, "failed to poll cm event, errno=%i", errno); + return -1; + } else if (poll_fd.revents & POLLIN) { + return rdma_get_cm_event(rdma->channel, cm_event); + } else { + ERROR(errp, "no POLLIN event, revent=%x", poll_fd.revents); + return -1; + } +} + +static int qemu_rdma_connect(RDMAContext *rdma, Error **errp, bool return_path) { RDMACapabilities cap = { .version = RDMA_CONTROL_VERSION_CURRENT, @@ -2493,11 +2528,14 @@ static int qemu_rdma_connect(RDMAContext *rdma, Error **errp) goto err_rdma_source_connect; } - ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (return_path) { + ret = qemu_get_cm_event_timeout(rdma, &cm_event, 5000, errp); + } else { + ret = rdma_get_cm_event(rdma->channel, &cm_event); + } if (ret) { perror("rdma_get_cm_event after rdma_connect"); ERROR(errp, "connecting to destination!"); - rdma_ack_cm_event(cm_event); goto err_rdma_source_connect; } @@ -2594,6 +2632,7 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) break; } + rdma_freeaddrinfo(res); if (!e) { ERROR(errp, "Error: could not rdma_bind_addr!"); goto err_dest_init_bind_addr; @@ -2646,6 +2685,7 @@ static void *qemu_rdma_data_init(const char *host_port, Error **errp) if (!inet_parse(addr, host_port, NULL)) { rdma->port = atoi(addr->port); rdma->host = g_strdup(addr->host); + rdma->host_port = g_strdup(host_port); } else { ERROR(errp, "bad RDMA migration address '%s'", host_port); g_free(rdma); @@ -3274,6 +3314,7 @@ static int qemu_rdma_accept(RDMAContext *rdma) .private_data = &cap, .private_data_len = sizeof(cap), }; + RDMAContext *rdma_return_path = NULL; struct rdma_cm_event *cm_event; struct ibv_context *verbs; int ret = -EINVAL; @@ -3289,6 +3330,20 @@ static int qemu_rdma_accept(RDMAContext *rdma) goto err_rdma_dest_wait; } + /* + * initialize the RDMAContext for return path for postcopy after first + * connection request reached. + */ + if (migrate_postcopy() && !rdma->is_return_path) { + rdma_return_path = qemu_rdma_data_init(rdma->host_port, NULL); + if (rdma_return_path == NULL) { + rdma_ack_cm_event(cm_event); + goto err_rdma_dest_wait; + } + + qemu_rdma_return_path_dest_init(rdma_return_path, rdma); + } + memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap)); network_to_caps(&cap); @@ -3404,6 +3459,7 @@ static int qemu_rdma_accept(RDMAContext *rdma) err_rdma_dest_wait: rdma->error_state = ret; qemu_rdma_cleanup(rdma); + g_free(rdma_return_path); return ret; } @@ -4041,29 +4097,22 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp) if (ret) { ERROR(errp, "listening on socket!"); - goto err; + goto cleanup_rdma; } trace_rdma_start_incoming_migration_after_rdma_listen(); - /* initialize the RDMAContext for return path */ - if (migrate_postcopy()) { - rdma_return_path = qemu_rdma_data_init(host_port, &local_err); - - if (rdma_return_path == NULL) { - goto err; - } - - qemu_rdma_return_path_dest_init(rdma_return_path, rdma); - } - qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, NULL, (void *)(intptr_t)rdma); return; + +cleanup_rdma: + qemu_rdma_cleanup(rdma); err: error_propagate(errp, local_err); if (rdma) { g_free(rdma->host); + g_free(rdma->host_port); } g_free(rdma); g_free(rdma_return_path); @@ -4096,7 +4145,7 @@ void rdma_start_outgoing_migration(void *opaque, } trace_rdma_start_outgoing_migration_after_rdma_source_init(); - ret = qemu_rdma_connect(rdma, errp); + ret = qemu_rdma_connect(rdma, errp, false); if (ret) { goto err; @@ -4117,7 +4166,7 @@ void rdma_start_outgoing_migration(void *opaque, goto return_path_err; } - ret = qemu_rdma_connect(rdma_return_path, errp); + ret = qemu_rdma_connect(rdma_return_path, errp, true); if (ret) { goto return_path_err; diff --git a/migration/trace-events b/migration/trace-events index 668c562fed..860c4f4025 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # savevm.c qemu_loadvm_state_section(unsigned int section_type) "%d" diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index d9bef63373..d10ee14110 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -1133,7 +1133,7 @@ void hmp_loadvm(Monitor *mon, const QDict *qdict) vm_stop(RUN_STATE_RESTORE_VM); - if (!load_snapshot(name, NULL, false, NULL, &err) && saved_vm_running) { + if (load_snapshot(name, NULL, false, NULL, &err) && saved_vm_running) { vm_start(); } hmp_handle_error(mon, err); diff --git a/monitor/misc.c b/monitor/misc.c index f3a393ea59..1539e18557 100644 --- a/monitor/misc.c +++ b/monitor/misc.c @@ -369,17 +369,6 @@ static void hmp_info_history(Monitor *mon, const QDict *qdict) } } -static void hmp_info_cpustats(Monitor *mon, const QDict *qdict) -{ - CPUState *cs = mon_get_cpu(mon); - - if (!cs) { - monitor_printf(mon, "No CPU available\n"); - return; - } - cpu_dump_statistics(cs, 0); -} - static void hmp_info_trace_events(Monitor *mon, const QDict *qdict) { const char *name = qdict_get_try_str(qdict, "name"); diff --git a/monitor/trace-events b/monitor/trace-events index 348dcfca9b..032d1220e1 100644 --- a/monitor/trace-events +++ b/monitor/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # hmp.c handle_hmp_command(void *mon, const char *cmdline) "mon %p cmdline: %s" diff --git a/nbd/server.c b/nbd/server.c index 86a44a9b41..b60ebc3ab6 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -1513,6 +1513,11 @@ static void nbd_request_put(NBDRequestData *req) g_free(req); client->nb_requests--; + + if (client->quiescing && client->nb_requests == 0) { + aio_wait_kick(); + } + nbd_client_receive_next_request(client); nbd_client_put(client); @@ -1530,49 +1535,68 @@ static void blk_aio_attached(AioContext *ctx, void *opaque) QTAILQ_FOREACH(client, &exp->clients, next) { qio_channel_attach_aio_context(client->ioc, ctx); + assert(client->nb_requests == 0); assert(client->recv_coroutine == NULL); assert(client->send_coroutine == NULL); - - if (client->quiescing) { - client->quiescing = false; - nbd_client_receive_next_request(client); - } } } -static void nbd_aio_detach_bh(void *opaque) +static void blk_aio_detach(void *opaque) { NBDExport *exp = opaque; NBDClient *client; + trace_nbd_blk_aio_detach(exp->name, exp->common.ctx); + QTAILQ_FOREACH(client, &exp->clients, next) { qio_channel_detach_aio_context(client->ioc); + } + + exp->common.ctx = NULL; +} + +static void nbd_drained_begin(void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; + + QTAILQ_FOREACH(client, &exp->clients, next) { client->quiescing = true; + } +} - if (client->recv_coroutine) { - if (client->read_yielding) { - qemu_aio_coroutine_enter(exp->common.ctx, - client->recv_coroutine); - } else { - AIO_WAIT_WHILE(exp->common.ctx, client->recv_coroutine != NULL); - } - } +static void nbd_drained_end(void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; - if (client->send_coroutine) { - AIO_WAIT_WHILE(exp->common.ctx, client->send_coroutine != NULL); - } + QTAILQ_FOREACH(client, &exp->clients, next) { + client->quiescing = false; + nbd_client_receive_next_request(client); } } -static void blk_aio_detach(void *opaque) +static bool nbd_drained_poll(void *opaque) { NBDExport *exp = opaque; + NBDClient *client; - trace_nbd_blk_aio_detach(exp->name, exp->common.ctx); + QTAILQ_FOREACH(client, &exp->clients, next) { + if (client->nb_requests != 0) { + /* + * If there's a coroutine waiting for a request on nbd_read_eof() + * enter it here so we don't depend on the client to wake it up. + */ + if (client->recv_coroutine != NULL && client->read_yielding) { + qemu_aio_coroutine_enter(exp->common.ctx, + client->recv_coroutine); + } - aio_wait_bh_oneshot(exp->common.ctx, nbd_aio_detach_bh, exp); + return true; + } + } - exp->common.ctx = NULL; + return false; } static void nbd_eject_notifier(Notifier *n, void *data) @@ -1594,6 +1618,12 @@ void nbd_export_set_on_eject_blk(BlockExport *exp, BlockBackend *blk) blk_add_remove_bs_notifier(blk, &nbd_exp->eject_notifier); } +static const BlockDevOps nbd_block_ops = { + .drained_begin = nbd_drained_begin, + .drained_end = nbd_drained_end, + .drained_poll = nbd_drained_poll, +}; + static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, Error **errp) { @@ -1715,8 +1745,17 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, exp->allocation_depth = arg->allocation_depth; + /* + * We need to inhibit request queuing in the block layer to ensure we can + * be properly quiesced when entering a drained section, as our coroutines + * servicing pending requests might enter blk_pread(). + */ + blk_set_disable_request_queuing(blk, true); + blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp); + blk_set_dev_ops(blk, &nbd_block_ops, exp); + QTAILQ_INSERT_TAIL(&exports, exp, next); return 0; @@ -1788,6 +1827,7 @@ static void nbd_export_delete(BlockExport *blk_exp) } blk_remove_aio_context_notifier(exp->common.blk, blk_aio_attached, blk_aio_detach, exp); + blk_set_disable_request_queuing(exp->common.blk, false); } for (i = 0; i < exp->nr_export_bitmaps; i++) { diff --git a/nbd/trace-events b/nbd/trace-events index a955918e97..c4919a2dd5 100644 --- a/nbd/trace-events +++ b/nbd/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # client.c nbd_send_option_request(uint32_t opt, const char *name, uint32_t len) "Sending option request %" PRIu32" (%s), len %" PRIu32 diff --git a/net/tap-bsd.c b/net/tap-bsd.c index 4f64f31e98..e45a6d124e 100644 --- a/net/tap-bsd.c +++ b/net/tap-bsd.c @@ -35,10 +35,6 @@ #include <net/if_tap.h> #endif -#if defined(__OpenBSD__) -#include <sys/param.h> -#endif - #ifndef __FreeBSD__ int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required, int mq_required, Error **errp) @@ -59,11 +55,7 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr, if (*ifname) { snprintf(dname, sizeof dname, "/dev/%s", ifname); } else { -#if defined(__OpenBSD__) && OpenBSD < 201605 - snprintf(dname, sizeof dname, "/dev/tun%d", i); -#else snprintf(dname, sizeof dname, "/dev/tap%d", i); -#endif } TFR(fd = open(dname, O_RDWR)); if (fd >= 0) { diff --git a/net/trace-events b/net/trace-events index bfaff7891d..d7a17256cc 100644 --- a/net/trace-events +++ b/net/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # announce.c qemu_announce_self_iter(const char *id, const char *name, const char *mac, int skip) "%s:%s:%s skip: %d" diff --git a/os-posix.c b/os-posix.c index a6846f51c1..ae6c9f2a5e 100644 --- a/os-posix.c +++ b/os-posix.c @@ -32,7 +32,7 @@ #include "qemu-common.h" /* Needed early for CONFIG_BSD etc. */ #include "net/slirp.h" -#include "qemu-options.h" +#include "qemu/qemu-options.h" #include "qemu/error-report.h" #include "qemu/log.h" #include "sysemu/runstate.h" diff --git a/os-win32.c b/os-win32.c index fd1137bab1..e31c921983 100644 --- a/os-win32.c +++ b/os-win32.c @@ -27,7 +27,6 @@ #include <windows.h> #include <mmsystem.h> #include "qemu-common.h" -#include "qemu-options.h" #include "sysemu/runstate.h" static BOOL WINAPI qemu_ctrl_handler(DWORD type) diff --git a/pc-bios/s390-ccw/dasd-ipl.c b/pc-bios/s390-ccw/dasd-ipl.c index 71cbae2f16..254bb1a15e 100644 --- a/pc-bios/s390-ccw/dasd-ipl.c +++ b/pc-bios/s390-ccw/dasd-ipl.c @@ -205,7 +205,7 @@ static void run_ipl2(SubChannelId schid, uint16_t cutype, uint32_t addr) /* * Limitations in vfio-ccw support complicate the IPL process. Details can - * be found in docs/devel/s390-dasd-ipl.txt + * be found in docs/devel/s390-dasd-ipl.rst */ void dasd_ipl(SubChannelId schid, uint16_t cutype) { diff --git a/plugins/plugin.h b/plugins/plugin.h index 1aa29dcadd..55017e3581 100644 --- a/plugins/plugin.h +++ b/plugins/plugin.h @@ -13,6 +13,7 @@ #define _PLUGIN_INTERNAL_H_ #include <gmodule.h> +#include "qemu/qht.h" #define QEMU_PLUGIN_MIN_VERSION 0 diff --git a/python/.gitignore b/python/.gitignore new file mode 100644 index 0000000000..272ed223a8 --- /dev/null +++ b/python/.gitignore @@ -0,0 +1,16 @@ +# linter/tooling cache +.mypy_cache/ +.cache/ + +# python packaging +build/ +dist/ +qemu.egg-info/ + +# editor config +.idea/ +.vscode/ + +# virtual environments (pipenv et al) +.venv/ +.tox/ diff --git a/python/MANIFEST.in b/python/MANIFEST.in new file mode 100644 index 0000000000..7059ad2822 --- /dev/null +++ b/python/MANIFEST.in @@ -0,0 +1,3 @@ +include VERSION +include PACKAGE.rst +exclude README.rst diff --git a/python/Makefile b/python/Makefile new file mode 100644 index 0000000000..b5621b0d54 --- /dev/null +++ b/python/Makefile @@ -0,0 +1,48 @@ +.PHONY: help venv venv-check check clean distclean develop + +help: + @echo "python packaging help:" + @echo "" + @echo "make venv: Create pipenv's virtual environment." + @echo " NOTE: Requires Python 3.6 and pipenv." + @echo " Will download packages from PyPI." + @echo " Hint: (On Fedora): 'sudo dnf install python36 pipenv'" + @echo "" + @echo "make venv-check: run linters using pipenv's virtual environment." + @echo " Hint: If you don't know which test to run, run this one!" + @echo "" + @echo "make develop: Install deps for 'make check', and" + @echo " the qemu libs in editable/development mode." + @echo "" + @echo "make check: run linters using the current environment." + @echo "" + @echo "make check-tox: run linters using multiple python versions." + @echo "" + @echo "make clean: remove package build output." + @echo "" + @echo "make distclean: remove venv files, qemu package forwarder," + @echo " built distribution files, and everything" + @echo " from 'make clean'." + +venv: .venv +.venv: Pipfile.lock + @PIPENV_VENV_IN_PROJECT=1 pipenv sync --dev --keep-outdated + @touch .venv + +venv-check: venv + @pipenv run make check + +develop: + pip3 install -e .[devel] + +check: + @avocado --config avocado.cfg run tests/ + +check-tox: + @tox + +clean: + python3 setup.py clean --all + +distclean: clean + rm -rf qemu.egg-info/ .venv/ .tox/ dist/ diff --git a/python/PACKAGE.rst b/python/PACKAGE.rst new file mode 100644 index 0000000000..b0b86cc4c3 --- /dev/null +++ b/python/PACKAGE.rst @@ -0,0 +1,43 @@ +QEMU Python Tooling +=================== + +This package provides QEMU tooling used by the QEMU project to build, +configure, and test QEMU. It is not a fully-fledged SDK and it is subject +to change at any time. + +Usage +----- + +The ``qemu.qmp`` subpackage provides a library for communicating with +QMP servers. The ``qemu.machine`` subpackage offers rudimentary +facilities for launching and managing QEMU processes. Refer to each +package's documentation +(``>>> help(qemu.qmp)``, ``>>> help(qemu.machine)``) +for more information. + +Contributing +------------ + +This package is maintained by John Snow <jsnow@redhat.com> as part of +the QEMU source tree. Contributions are welcome and follow the `QEMU +patch submission process +<https://wiki.qemu.org/Contribute/SubmitAPatch>`_, which involves +sending patches to the QEMU development mailing list. + +John maintains a `GitLab staging branch +<https://gitlab.com/jsnow/qemu/-/tree/python>`_, and there is an +official `GitLab mirror <https://gitlab.com/qemu-project/qemu>`_. + +Please report bugs on the `QEMU issue tracker +<https://gitlab.com/qemu-project/qemu/-/issues>`_ and tag ``@jsnow`` in +the report. + +Optional packages necessary for running code quality analysis for this +package can be installed with the optional dependency group "devel": +``pip install qemu[devel]``. + +``make develop`` can be used to install this package in editable mode +(to the current environment) *and* bring in testing dependencies in one +command. + +``make check`` can be used to run the available tests. diff --git a/python/Pipfile b/python/Pipfile new file mode 100644 index 0000000000..e7acb8cefa --- /dev/null +++ b/python/Pipfile @@ -0,0 +1,13 @@ +[[source]] +name = "pypi" +url = "https://pypi.org/simple" +verify_ssl = true + +[dev-packages] +qemu = {editable = true, extras = ["devel"], path = "."} + +[packages] +qemu = {editable = true,path = "."} + +[requires] +python_version = "3.6" diff --git a/python/Pipfile.lock b/python/Pipfile.lock new file mode 100644 index 0000000000..6e344f5fad --- /dev/null +++ b/python/Pipfile.lock @@ -0,0 +1,231 @@ +{ + "_meta": { + "hash": { + "sha256": "eff562a688ebc6f3ffe67494dbb804b883e2159ad81c4d55d96da9f7aec13e91" + }, + "pipfile-spec": 6, + "requires": { + "python_version": "3.6" + }, + "sources": [ + { + "name": "pypi", + "url": "https://pypi.org/simple", + "verify_ssl": true + } + ] + }, + "default": { + "qemu": { + "editable": true, + "path": "." + } + }, + "develop": { + "astroid": { + "hashes": [ + "sha256:4db03ab5fc3340cf619dbc25e42c2cc3755154ce6009469766d7143d1fc2ee4e", + "sha256:8a398dfce302c13f14bab13e2b14fe385d32b73f4e4853b9bdfb64598baa1975" + ], + "markers": "python_version ~= '3.6'", + "version": "==2.5.6" + }, + "avocado-framework": { + "hashes": [ + "sha256:42aa7962df98d6b78d4efd9afa2177226dc630f3d83a2a7d5baf7a0a7da7fa1b", + "sha256:d96ae343abf890e1ef3b3a6af5ce49e35f6bded0715770c4acb325bca555c515" + ], + "markers": "python_version >= '3.6'", + "version": "==88.1" + }, + "flake8": { + "hashes": [ + "sha256:07528381786f2a6237b061f6e96610a4167b226cb926e2aa2b6b1d78057c576b", + "sha256:bf8fd333346d844f616e8d47905ef3a3384edae6b4e9beb0c5101e25e3110907" + ], + "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'", + "version": "==3.9.2" + }, + "importlib-metadata": { + "hashes": [ + "sha256:8c501196e49fb9df5df43833bdb1e4328f64847763ec8a50703148b73784d581", + "sha256:d7eb1dea6d6a6086f8be21784cc9e3bcfa55872b52309bc5fad53a8ea444465d" + ], + "markers": "python_version < '3.8'", + "version": "==4.0.1" + }, + "isort": { + "hashes": [ + "sha256:0a943902919f65c5684ac4e0154b1ad4fac6dcaa5d9f3426b732f1c8b5419be6", + "sha256:2bb1680aad211e3c9944dbce1d4ba09a989f04e238296c87fe2139faa26d655d" + ], + "markers": "python_version >= '3.6' and python_version < '4.0'", + "version": "==5.8.0" + }, + "lazy-object-proxy": { + "hashes": [ + "sha256:17e0967ba374fc24141738c69736da90e94419338fd4c7c7bef01ee26b339653", + "sha256:1fee665d2638491f4d6e55bd483e15ef21f6c8c2095f235fef72601021e64f61", + "sha256:22ddd618cefe54305df49e4c069fa65715be4ad0e78e8d252a33debf00f6ede2", + "sha256:24a5045889cc2729033b3e604d496c2b6f588c754f7a62027ad4437a7ecc4837", + "sha256:410283732af311b51b837894fa2f24f2c0039aa7f220135192b38fcc42bd43d3", + "sha256:4732c765372bd78a2d6b2150a6e99d00a78ec963375f236979c0626b97ed8e43", + "sha256:489000d368377571c6f982fba6497f2aa13c6d1facc40660963da62f5c379726", + "sha256:4f60460e9f1eb632584c9685bccea152f4ac2130e299784dbaf9fae9f49891b3", + "sha256:5743a5ab42ae40caa8421b320ebf3a998f89c85cdc8376d6b2e00bd12bd1b587", + "sha256:85fb7608121fd5621cc4377a8961d0b32ccf84a7285b4f1d21988b2eae2868e8", + "sha256:9698110e36e2df951c7c36b6729e96429c9c32b3331989ef19976592c5f3c77a", + "sha256:9d397bf41caad3f489e10774667310d73cb9c4258e9aed94b9ec734b34b495fd", + "sha256:b579f8acbf2bdd9ea200b1d5dea36abd93cabf56cf626ab9c744a432e15c815f", + "sha256:b865b01a2e7f96db0c5d12cfea590f98d8c5ba64ad222300d93ce6ff9138bcad", + "sha256:bf34e368e8dd976423396555078def5cfc3039ebc6fc06d1ae2c5a65eebbcde4", + "sha256:c6938967f8528b3668622a9ed3b31d145fab161a32f5891ea7b84f6b790be05b", + "sha256:d1c2676e3d840852a2de7c7d5d76407c772927addff8d742b9808fe0afccebdf", + "sha256:d7124f52f3bd259f510651450e18e0fd081ed82f3c08541dffc7b94b883aa981", + "sha256:d900d949b707778696fdf01036f58c9876a0d8bfe116e8d220cfd4b15f14e741", + "sha256:ebfd274dcd5133e0afae738e6d9da4323c3eb021b3e13052d8cbd0e457b1256e", + "sha256:ed361bb83436f117f9917d282a456f9e5009ea12fd6de8742d1a4752c3017e93", + "sha256:f5144c75445ae3ca2057faac03fda5a902eff196702b0a24daf1d6ce0650514b" + ], + "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'", + "version": "==1.6.0" + }, + "mccabe": { + "hashes": [ + "sha256:ab8a6258860da4b6677da4bd2fe5dc2c659cff31b3ee4f7f5d64e79735b80d42", + "sha256:dd8d182285a0fe56bace7f45b5e7d1a6ebcbf524e8f3bd87eb0f125271b8831f" + ], + "version": "==0.6.1" + }, + "mypy": { + "hashes": [ + "sha256:0d0a87c0e7e3a9becdfbe936c981d32e5ee0ccda3e0f07e1ef2c3d1a817cf73e", + "sha256:25adde9b862f8f9aac9d2d11971f226bd4c8fbaa89fb76bdadb267ef22d10064", + "sha256:28fb5479c494b1bab244620685e2eb3c3f988d71fd5d64cc753195e8ed53df7c", + "sha256:2f9b3407c58347a452fc0736861593e105139b905cca7d097e413453a1d650b4", + "sha256:33f159443db0829d16f0a8d83d94df3109bb6dd801975fe86bacb9bf71628e97", + "sha256:3f2aca7f68580dc2508289c729bd49ee929a436208d2b2b6aab15745a70a57df", + "sha256:499c798053cdebcaa916eef8cd733e5584b5909f789de856b482cd7d069bdad8", + "sha256:4eec37370483331d13514c3f55f446fc5248d6373e7029a29ecb7b7494851e7a", + "sha256:552a815579aa1e995f39fd05dde6cd378e191b063f031f2acfe73ce9fb7f9e56", + "sha256:5873888fff1c7cf5b71efbe80e0e73153fe9212fafdf8e44adfe4c20ec9f82d7", + "sha256:61a3d5b97955422964be6b3baf05ff2ce7f26f52c85dd88db11d5e03e146a3a6", + "sha256:674e822aa665b9fd75130c6c5f5ed9564a38c6cea6a6432ce47eafb68ee578c5", + "sha256:7ce3175801d0ae5fdfa79b4f0cfed08807af4d075b402b7e294e6aa72af9aa2a", + "sha256:9743c91088d396c1a5a3c9978354b61b0382b4e3c440ce83cf77994a43e8c521", + "sha256:9f94aac67a2045ec719ffe6111df543bac7874cee01f41928f6969756e030564", + "sha256:a26f8ec704e5a7423c8824d425086705e381b4f1dfdef6e3a1edab7ba174ec49", + "sha256:abf7e0c3cf117c44d9285cc6128856106183938c68fd4944763003decdcfeb66", + "sha256:b09669bcda124e83708f34a94606e01b614fa71931d356c1f1a5297ba11f110a", + "sha256:cd07039aa5df222037005b08fbbfd69b3ab0b0bd7a07d7906de75ae52c4e3119", + "sha256:d23e0ea196702d918b60c8288561e722bf437d82cb7ef2edcd98cfa38905d506", + "sha256:d65cc1df038ef55a99e617431f0553cd77763869eebdf9042403e16089fe746c", + "sha256:d7da2e1d5f558c37d6e8c1246f1aec1e7349e4913d8fb3cb289a35de573fe2eb" + ], + "markers": "python_version >= '3.5'", + "version": "==0.812" + }, + "mypy-extensions": { + "hashes": [ + "sha256:090fedd75945a69ae91ce1303b5824f428daf5a028d2f6ab8a299250a846f15d", + "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8" + ], + "version": "==0.4.3" + }, + "pycodestyle": { + "hashes": [ + "sha256:514f76d918fcc0b55c6680472f0a37970994e07bbb80725808c17089be302068", + "sha256:c389c1d06bf7904078ca03399a4816f974a1d590090fecea0c63ec26ebaf1cef" + ], + "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'", + "version": "==2.7.0" + }, + "pyflakes": { + "hashes": [ + "sha256:7893783d01b8a89811dd72d7dfd4d84ff098e5eed95cfa8905b22bbffe52efc3", + "sha256:f5bc8ecabc05bb9d291eb5203d6810b49040f6ff446a756326104746cc00c1db" + ], + "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'", + "version": "==2.3.1" + }, + "pylint": { + "hashes": [ + "sha256:586d8fa9b1891f4b725f587ef267abe2a1bad89d6b184520c7f07a253dd6e217", + "sha256:f7e2072654a6b6afdf5e2fb38147d3e2d2d43c89f648637baab63e026481279b" + ], + "markers": "python_version ~= '3.6'", + "version": "==2.8.2" + }, + "qemu": { + "editable": true, + "path": "." + }, + "toml": { + "hashes": [ + "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b", + "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f" + ], + "markers": "python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2'", + "version": "==0.10.2" + }, + "typed-ast": { + "hashes": [ + "sha256:01ae5f73431d21eead5015997ab41afa53aa1fbe252f9da060be5dad2c730ace", + "sha256:067a74454df670dcaa4e59349a2e5c81e567d8d65458d480a5b3dfecec08c5ff", + "sha256:0fb71b8c643187d7492c1f8352f2c15b4c4af3f6338f21681d3681b3dc31a266", + "sha256:1b3ead4a96c9101bef08f9f7d1217c096f31667617b58de957f690c92378b528", + "sha256:2068531575a125b87a41802130fa7e29f26c09a2833fea68d9a40cf33902eba6", + "sha256:209596a4ec71d990d71d5e0d312ac935d86930e6eecff6ccc7007fe54d703808", + "sha256:2c726c276d09fc5c414693a2de063f521052d9ea7c240ce553316f70656c84d4", + "sha256:398e44cd480f4d2b7ee8d98385ca104e35c81525dd98c519acff1b79bdaac363", + "sha256:52b1eb8c83f178ab787f3a4283f68258525f8d70f778a2f6dd54d3b5e5fb4341", + "sha256:5feca99c17af94057417d744607b82dd0a664fd5e4ca98061480fd8b14b18d04", + "sha256:7538e495704e2ccda9b234b82423a4038f324f3a10c43bc088a1636180f11a41", + "sha256:760ad187b1041a154f0e4d0f6aae3e40fdb51d6de16e5c99aedadd9246450e9e", + "sha256:777a26c84bea6cd934422ac2e3b78863a37017618b6e5c08f92ef69853e765d3", + "sha256:95431a26309a21874005845c21118c83991c63ea800dd44843e42a916aec5899", + "sha256:9ad2c92ec681e02baf81fdfa056fe0d818645efa9af1f1cd5fd6f1bd2bdfd805", + "sha256:9c6d1a54552b5330bc657b7ef0eae25d00ba7ffe85d9ea8ae6540d2197a3788c", + "sha256:aee0c1256be6c07bd3e1263ff920c325b59849dc95392a05f258bb9b259cf39c", + "sha256:af3d4a73793725138d6b334d9d247ce7e5f084d96284ed23f22ee626a7b88e39", + "sha256:b36b4f3920103a25e1d5d024d155c504080959582b928e91cb608a65c3a49e1a", + "sha256:b9574c6f03f685070d859e75c7f9eeca02d6933273b5e69572e5ff9d5e3931c3", + "sha256:bff6ad71c81b3bba8fa35f0f1921fb24ff4476235a6e94a26ada2e54370e6da7", + "sha256:c190f0899e9f9f8b6b7863debfb739abcb21a5c054f911ca3596d12b8a4c4c7f", + "sha256:c907f561b1e83e93fad565bac5ba9c22d96a54e7ea0267c708bffe863cbe4075", + "sha256:cae53c389825d3b46fb37538441f75d6aecc4174f615d048321b716df2757fb0", + "sha256:dd4a21253f42b8d2b48410cb31fe501d32f8b9fbeb1f55063ad102fe9c425e40", + "sha256:dde816ca9dac1d9c01dd504ea5967821606f02e510438120091b84e852367428", + "sha256:f2362f3cb0f3172c42938946dbc5b7843c2a28aec307c49100c8b38764eb6927", + "sha256:f328adcfebed9f11301eaedfa48e15bdece9b519fb27e6a8c01aa52a17ec31b3", + "sha256:f8afcf15cc511ada719a88e013cec87c11aff7b91f019295eb4530f96fe5ef2f", + "sha256:fb1bbeac803adea29cedd70781399c99138358c26d05fcbd23c13016b7f5ec65" + ], + "markers": "implementation_name == 'cpython' and python_version < '3.8'", + "version": "==1.4.3" + }, + "typing-extensions": { + "hashes": [ + "sha256:0ac0f89795dd19de6b97debb0c6af1c70987fd80a2d62d1958f7e56fcc31b497", + "sha256:50b6f157849174217d0656f99dc82fe932884fb250826c18350e159ec6cdf342", + "sha256:779383f6086d90c99ae41cf0ff39aac8a7937a9283ce0a414e5dd782f4c94a84" + ], + "markers": "python_version < '3.8'", + "version": "==3.10.0.0" + }, + "wrapt": { + "hashes": [ + "sha256:b62ffa81fb85f4332a4f609cab4ac40709470da05643a082ec1eb88e6d9b97d7" + ], + "version": "==1.12.1" + }, + "zipp": { + "hashes": [ + "sha256:3607921face881ba3e026887d8150cca609d517579abe052ac81fc5aeffdbd76", + "sha256:51cb66cc54621609dd593d1787f286ee42a5c0adbb4b29abea5a63edc3e03098" + ], + "markers": "python_version >= '3.6'", + "version": "==3.4.1" + } + } +} diff --git a/python/README.rst b/python/README.rst new file mode 100644 index 0000000000..dcf993819d --- /dev/null +++ b/python/README.rst @@ -0,0 +1,58 @@ +QEMU Python Tooling +=================== + +This directory houses Python tooling used by the QEMU project to build, +configure, and test QEMU. It is organized by namespace (``qemu``), and +then by package (e.g. ``qemu/machine``, ``qemu/qmp``, etc). + +``setup.py`` is used by ``pip`` to install this tooling to the current +environment. ``setup.cfg`` provides the packaging configuration used by +``setup.py`` in a setuptools specific format. You will generally invoke +it by doing one of the following: + +1. ``pip3 install .`` will install these packages to your current + environment. If you are inside a virtual environment, they will + install there. If you are not, it will attempt to install to the + global environment, which is **not recommended**. + +2. ``pip3 install --user .`` will install these packages to your user's + local python packages. If you are inside of a virtual environment, + this will fail; you likely want the first invocation above. + +If you append the ``-e`` argument, pip will install in "editable" mode; +which installs a version of the package that installs a forwarder +pointing to these files, such that the package always reflects the +latest version in your git tree. + +Installing ".[devel]" instead of "." will additionally pull in required +packages for testing this package. They are not runtime requirements, +and are not needed to simply use these libraries. + +Running ``make develop`` will pull in all testing dependencies and +install QEMU in editable mode to the current environment. + +See `Installing packages using pip and virtual environments +<https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/>`_ +for more information. + + +Files in this directory +----------------------- + +- ``qemu/`` Python package source directory. +- ``tests/`` Python package tests directory. +- ``avocado.cfg`` Configuration for the Avocado test-runner. + Used by ``make check`` et al. +- ``Makefile`` provides some common testing/installation invocations. + Try ``make help`` to see available targets. +- ``MANIFEST.in`` is read by python setuptools, it specifies additional files + that should be included by a source distribution. +- ``PACKAGE.rst`` is used as the README file that is visible on PyPI.org. +- ``Pipfile`` is used by Pipenv to generate ``Pipfile.lock``. +- ``Pipfile.lock`` is a set of pinned package dependencies that this package + is tested under in our CI suite. It is used by ``make venv-check``. +- ``README.rst`` you are here! +- ``VERSION`` contains the PEP-440 compliant version used to describe + this package; it is referenced by ``setup.cfg``. +- ``setup.cfg`` houses setuptools package configuration. +- ``setup.py`` is the setuptools installer used by pip; See above. diff --git a/python/VERSION b/python/VERSION new file mode 100644 index 0000000000..c19f3b832b --- /dev/null +++ b/python/VERSION @@ -0,0 +1 @@ +0.6.1.0a1 diff --git a/python/avocado.cfg b/python/avocado.cfg new file mode 100644 index 0000000000..10dc6fb605 --- /dev/null +++ b/python/avocado.cfg @@ -0,0 +1,10 @@ +[simpletests] +# Don't show stdout/stderr in the test *summary* +status.failure_fields = ['status'] + +[job] +# Don't show the full debug.log output; only select stdout/stderr. +output.testlogs.logfiles = ['stdout', 'stderr'] + +# Show full stdout/stderr only on tests that FAIL +output.testlogs.statuses = ['FAIL'] diff --git a/python/mypy.ini b/python/mypy.ini deleted file mode 100644 index 1a581c5f1e..0000000000 --- a/python/mypy.ini +++ /dev/null @@ -1,4 +0,0 @@ -[mypy] -strict = True -python_version = 3.6 -warn_unused_configs = True diff --git a/python/qemu/.flake8 b/python/qemu/.flake8 deleted file mode 100644 index 45d8146f3f..0000000000 --- a/python/qemu/.flake8 +++ /dev/null @@ -1,2 +0,0 @@ -[flake8] -extend-ignore = E722 # Pylint handles this, but smarter.
\ No newline at end of file diff --git a/python/qemu/.isort.cfg b/python/qemu/.isort.cfg deleted file mode 100644 index 6d0fd6cc0d..0000000000 --- a/python/qemu/.isort.cfg +++ /dev/null @@ -1,7 +0,0 @@ -[settings] -force_grid_wrap=4 -force_sort_within_sections=True -include_trailing_comma=True -line_length=72 -lines_after_imports=2 -multi_line_output=3
\ No newline at end of file diff --git a/python/qemu/README.rst b/python/qemu/README.rst new file mode 100644 index 0000000000..d04943f526 --- /dev/null +++ b/python/qemu/README.rst @@ -0,0 +1,8 @@ +QEMU Python Namespace +===================== + +This directory serves as the root of a `Python PEP 420 implicit +namespace package <https://www.python.org/dev/peps/pep-0420/>`_. + +Each directory below is assumed to be an installable Python package that +is available under the ``qemu.<package>`` namespace. diff --git a/python/qemu/__init__.py b/python/qemu/__init__.py deleted file mode 100644 index 4ca06c34a4..0000000000 --- a/python/qemu/__init__.py +++ /dev/null @@ -1,11 +0,0 @@ -# QEMU library -# -# Copyright (C) 2015-2016 Red Hat Inc. -# Copyright (C) 2012 IBM Corp. -# -# Authors: -# Fam Zheng <famz@redhat.com> -# -# This work is licensed under the terms of the GNU GPL, version 2. See -# the COPYING file in the top-level directory. -# diff --git a/python/qemu/machine/README.rst b/python/qemu/machine/README.rst new file mode 100644 index 0000000000..ac2b4fffb4 --- /dev/null +++ b/python/qemu/machine/README.rst @@ -0,0 +1,9 @@ +qemu.machine package +==================== + +This package provides core utilities used for testing and debugging +QEMU. It is used by the iotests, vm tests, acceptance tests, and several +other utilities in the ./scripts directory. It is not a fully-fledged +SDK and it is subject to change at any time. + +See the documentation in ``__init__.py`` for more information. diff --git a/python/qemu/machine/__init__.py b/python/qemu/machine/__init__.py new file mode 100644 index 0000000000..728f27adbe --- /dev/null +++ b/python/qemu/machine/__init__.py @@ -0,0 +1,36 @@ +""" +QEMU development and testing library. + +This library provides a few high-level classes for driving QEMU from a +test suite, not intended for production use. + +- QEMUMachine: Configure and Boot a QEMU VM + - QEMUQtestMachine: VM class, with a qtest socket. + +- QEMUQtestProtocol: Connect to, send/receive qtest messages. +""" + +# Copyright (C) 2020-2021 John Snow for Red Hat Inc. +# Copyright (C) 2015-2016 Red Hat Inc. +# Copyright (C) 2012 IBM Corp. +# +# Authors: +# John Snow <jsnow@redhat.com> +# Fam Zheng <fam@euphon.net> +# +# This work is licensed under the terms of the GNU GPL, version 2. See +# the COPYING file in the top-level directory. +# + +# pylint: disable=import-error +# see: https://github.com/PyCQA/pylint/issues/3624 +# see: https://github.com/PyCQA/pylint/issues/3651 +from .machine import QEMUMachine +from .qtest import QEMUQtestMachine, QEMUQtestProtocol + + +__all__ = ( + 'QEMUMachine', + 'QEMUQtestProtocol', + 'QEMUQtestMachine', +) diff --git a/python/qemu/console_socket.py b/python/qemu/machine/console_socket.py index ac21130e44..8c4ff598ad 100644 --- a/python/qemu/console_socket.py +++ b/python/qemu/machine/console_socket.py @@ -39,6 +39,7 @@ class ConsoleSocket(socket.socket): self.connect(address) self._logfile = None if file: + # pylint: disable=consider-using-with self._logfile = open(file, "bw") self._open = True self._drain_thread = None @@ -46,11 +47,11 @@ class ConsoleSocket(socket.socket): self._drain_thread = self._thread_start() def __repr__(self) -> str: - s = super().__repr__() - s = s.rstrip(">") - s = "%s, logfile=%s, drain_thread=%s>" % (s, self._logfile, - self._drain_thread) - return s + tmp = super().__repr__() + tmp = tmp.rstrip(">") + tmp = "%s, logfile=%s, drain_thread=%s>" % (tmp, self._logfile, + self._drain_thread) + return tmp def _drain_fn(self) -> None: """Drains the socket and runs while the socket is open.""" diff --git a/python/qemu/machine.py b/python/qemu/machine/machine.py index 6e44bda337..b62435528e 100644 --- a/python/qemu/machine.py +++ b/python/qemu/machine/machine.py @@ -38,8 +38,14 @@ from typing import ( Type, ) -from . import console_socket, qmp -from .qmp import QMPMessage, QMPReturnValue, SocketAddrT +from qemu.qmp import ( # pylint: disable=import-error + QEMUMonitorProtocol, + QMPMessage, + QMPReturnValue, + SocketAddrT, +) + +from . import console_socket LOG = logging.getLogger(__name__) @@ -84,7 +90,7 @@ class QEMUMachine: args: Sequence[str] = (), wrapper: Sequence[str] = (), name: Optional[str] = None, - test_dir: str = "/var/tmp", + base_temp_dir: str = "/var/tmp", monitor_address: Optional[SocketAddrT] = None, socket_scm_helper: Optional[str] = None, sock_dir: Optional[str] = None, @@ -97,10 +103,10 @@ class QEMUMachine: @param args: list of extra arguments @param wrapper: list of arguments used as prefix to qemu binary @param name: prefix for socket and log file names (default: qemu-PID) - @param test_dir: where to create socket and log file + @param base_temp_dir: default location where temp files are created @param monitor_address: address for QMP monitor @param socket_scm_helper: helper program, required for send_fd_scm() - @param sock_dir: where to create socket (overrides test_dir for sock) + @param sock_dir: where to create socket (defaults to base_temp_dir) @param drain_console: (optional) True to drain console socket to buffer @param console_log: (optional) path to console log file @note: Qemu process is not started until launch() is used. @@ -112,8 +118,8 @@ class QEMUMachine: self._wrapper = wrapper self._name = name or "qemu-%d" % os.getpid() - self._test_dir = test_dir - self._sock_dir = sock_dir or self._test_dir + self._base_temp_dir = base_temp_dir + self._sock_dir = sock_dir or self._base_temp_dir self._socket_scm_helper = socket_scm_helper if monitor_address is not None: @@ -139,7 +145,7 @@ class QEMUMachine: self._events: List[QMPMessage] = [] self._iolog: Optional[str] = None self._qmp_set = True # Enable QMP monitor by default. - self._qmp_connection: Optional[qmp.QEMUMonitorProtocol] = None + self._qmp_connection: Optional[QEMUMonitorProtocol] = None self._qemu_full_args: Tuple[str, ...] = () self._temp_dir: Optional[str] = None self._launched = False @@ -223,14 +229,16 @@ class QEMUMachine: assert fd is not None fd_param.append(str(fd)) - devnull = open(os.path.devnull, 'rb') - proc = subprocess.Popen( - fd_param, stdin=devnull, stdout=subprocess.PIPE, - stderr=subprocess.STDOUT, close_fds=False + proc = subprocess.run( + fd_param, + stdin=subprocess.DEVNULL, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + check=False, + close_fds=False, ) - output = proc.communicate()[0] - if output: - LOG.debug(output) + if proc.stdout: + LOG.debug(proc.stdout) return proc.returncode @@ -303,10 +311,7 @@ class QEMUMachine: return args def _pre_launch(self) -> None: - self._temp_dir = tempfile.mkdtemp(prefix="qemu-machine-", - dir=self._test_dir) - self._qemu_log_path = os.path.join(self._temp_dir, self._name + ".log") - self._qemu_log_file = open(self._qemu_log_path, 'wb') + self._qemu_log_path = os.path.join(self.temp_dir, self._name + ".log") if self._console_set: self._remove_files.append(self._console_address) @@ -315,12 +320,17 @@ class QEMUMachine: if self._remove_monitor_sockfile: assert isinstance(self._monitor_address, str) self._remove_files.append(self._monitor_address) - self._qmp_connection = qmp.QEMUMonitorProtocol( + self._qmp_connection = QEMUMonitorProtocol( self._monitor_address, server=True, nickname=self._name ) + # NOTE: Make sure any opened resources are *definitely* freed in + # _post_shutdown()! + # pylint: disable=consider-using-with + self._qemu_log_file = open(self._qemu_log_path, 'wb') + def _post_launch(self) -> None: if self._qmp_connection: self._qmp.accept() @@ -393,7 +403,6 @@ class QEMUMachine: """ Launch the VM and establish a QMP connection """ - devnull = open(os.path.devnull, 'rb') self._pre_launch() self._qemu_full_args = tuple( chain(self._wrapper, @@ -402,8 +411,11 @@ class QEMUMachine: self._args) ) LOG.debug('VM launch command: %r', ' '.join(self._qemu_full_args)) + + # Cleaning up of this subprocess is guaranteed by _do_shutdown. + # pylint: disable=consider-using-with self._popen = subprocess.Popen(self._qemu_full_args, - stdin=devnull, + stdin=subprocess.DEVNULL, stdout=self._qemu_log_file, stderr=subprocess.STDOUT, shell=False, @@ -535,7 +547,7 @@ class QEMUMachine: self._qmp_set = enabled @property - def _qmp(self) -> qmp.QEMUMonitorProtocol: + def _qmp(self) -> QEMUMonitorProtocol: if self._qmp_connection is None: raise QEMUMachineError("Attempt to access QMP with no connection") return self._qmp_connection @@ -744,3 +756,13 @@ class QEMUMachine: file=self._console_log_path, drain=self._drain_console) return self._console_socket + + @property + def temp_dir(self) -> str: + """ + Returns a temporary directory to be used for this machine + """ + if self._temp_dir is None: + self._temp_dir = tempfile.mkdtemp(prefix="qemu-machine-", + dir=self._base_temp_dir) + return self._temp_dir diff --git a/python/qemu/qtest.py b/python/qemu/machine/qtest.py index 39a0cf62fe..93700684d1 100644 --- a/python/qemu/qtest.py +++ b/python/qemu/machine/qtest.py @@ -26,8 +26,9 @@ from typing import ( TextIO, ) +from qemu.qmp import SocketAddrT # pylint: disable=import-error + from .machine import QEMUMachine -from .qmp import SocketAddrT class QEMUQtestProtocol: @@ -112,14 +113,14 @@ class QEMUQtestMachine(QEMUMachine): binary: str, args: Sequence[str] = (), name: Optional[str] = None, - test_dir: str = "/var/tmp", + base_temp_dir: str = "/var/tmp", socket_scm_helper: Optional[str] = None, sock_dir: Optional[str] = None): if name is None: name = "qemu-%d" % os.getpid() if sock_dir is None: - sock_dir = test_dir - super().__init__(binary, args, name=name, test_dir=test_dir, + sock_dir = base_temp_dir + super().__init__(binary, args, name=name, base_temp_dir=base_temp_dir, socket_scm_helper=socket_scm_helper, sock_dir=sock_dir) self._qtest: Optional[QEMUQtestProtocol] = None diff --git a/python/qemu/pylintrc b/python/qemu/pylintrc deleted file mode 100644 index 3f69205000..0000000000 --- a/python/qemu/pylintrc +++ /dev/null @@ -1,58 +0,0 @@ -[MASTER] - -[MESSAGES CONTROL] - -# Disable the message, report, category or checker with the given id(s). You -# can either give multiple identifiers separated by comma (,) or put this -# option multiple times (only on the command line, not in the configuration -# file where it should appear only once). You can also use "--disable=all" to -# disable everything first and then reenable specific checks. For example, if -# you want to run only the similarities checker, you can use "--disable=all -# --enable=similarities". If you want to run only the classes checker, but have -# no Warning level messages displayed, use "--disable=all --enable=classes -# --disable=W". -disable=too-many-arguments, - too-many-instance-attributes, - too-many-public-methods, - -[REPORTS] - -[REFACTORING] - -[MISCELLANEOUS] - -[LOGGING] - -[BASIC] - -# Good variable names which should always be accepted, separated by a comma. -good-names=i, - j, - k, - ex, - Run, - _, - fd, - c, -[VARIABLES] - -[STRING] - -[SPELLING] - -[FORMAT] - -[SIMILARITIES] - -# Ignore imports when computing similarities. -ignore-imports=yes - -[TYPECHECK] - -[CLASSES] - -[IMPORTS] - -[DESIGN] - -[EXCEPTIONS] diff --git a/python/qemu/qmp/README.rst b/python/qemu/qmp/README.rst new file mode 100644 index 0000000000..c21951491c --- /dev/null +++ b/python/qemu/qmp/README.rst @@ -0,0 +1,9 @@ +qemu.qmp package +================ + +This package provides a library used for connecting to and communicating +with QMP servers. It is used extensively by iotests, vm tests, +acceptance tests, and other utilities in the ./scripts directory. It is +not a fully-fledged SDK and is subject to change at any time. + +See the documentation in ``__init__.py`` for more information. diff --git a/python/qemu/qmp.py b/python/qemu/qmp/__init__.py index 2cd4d43036..9606248a3d 100644 --- a/python/qemu/qmp.py +++ b/python/qemu/qmp/__init__.py @@ -1,4 +1,14 @@ -""" QEMU Monitor Protocol Python class """ +""" +QEMU Monitor Protocol (QMP) development library & tooling. + +This package provides a fairly low-level class for communicating to QMP +protocol servers, as implemented by QEMU, the QEMU Guest Agent, and the +QEMU Storage Daemon. This library is not intended for production use. + +`QEMUMonitorProtocol` is the primary class of interest, and all errors +raised derive from `QMPError`. +""" + # Copyright (C) 2009, 2010 Red Hat Inc. # # Authors: diff --git a/python/qemu/utils/README.rst b/python/qemu/utils/README.rst new file mode 100644 index 0000000000..975fbf4d7d --- /dev/null +++ b/python/qemu/utils/README.rst @@ -0,0 +1,7 @@ +qemu.utils package +================== + +This package provides miscellaneous utilities used for testing and +debugging QEMU. It is used primarily by the vm and acceptance tests. + +See the documentation in ``__init__.py`` for more information. diff --git a/python/qemu/utils/__init__.py b/python/qemu/utils/__init__.py new file mode 100644 index 0000000000..7f1a5138c4 --- /dev/null +++ b/python/qemu/utils/__init__.py @@ -0,0 +1,45 @@ +""" +QEMU development and testing utilities + +This package provides a small handful of utilities for performing +various tasks not directly related to the launching of a VM. +""" + +# Copyright (C) 2021 Red Hat Inc. +# +# Authors: +# John Snow <jsnow@redhat.com> +# Cleber Rosa <crosa@redhat.com> +# +# This work is licensed under the terms of the GNU GPL, version 2. See +# the COPYING file in the top-level directory. +# + +import re +from typing import Optional + +# pylint: disable=import-error +from .accel import kvm_available, list_accel, tcg_available + + +__all__ = ( + 'get_info_usernet_hostfwd_port', + 'kvm_available', + 'list_accel', + 'tcg_available', +) + + +def get_info_usernet_hostfwd_port(info_usernet_output: str) -> Optional[int]: + """ + Returns the port given to the hostfwd parameter via info usernet + + :param info_usernet_output: output generated by hmp command "info usernet" + :return: the port number allocated by the hostfwd option + """ + for line in info_usernet_output.split('\r\n'): + regex = r'TCP.HOST_FORWARD.*127\.0\.0\.1\s+(\d+)\s+10\.' + match = re.search(regex, line) + if match is not None: + return int(match[1]) + return None diff --git a/python/qemu/accel.py b/python/qemu/utils/accel.py index 297933df2a..297933df2a 100644 --- a/python/qemu/accel.py +++ b/python/qemu/utils/accel.py diff --git a/python/setup.cfg b/python/setup.cfg new file mode 100644 index 0000000000..0fcdec6f32 --- /dev/null +++ b/python/setup.cfg @@ -0,0 +1,102 @@ +[metadata] +name = qemu +version = file:VERSION +maintainer = QEMU Developer Team +maintainer_email = qemu-devel@nongnu.org +url = https://www.qemu.org/ +download_url = https://www.qemu.org/download/ +description = QEMU Python Build, Debug and SDK tooling. +long_description = file:PACKAGE.rst +long_description_content_type = text/x-rst +classifiers = + Development Status :: 3 - Alpha + License :: OSI Approved :: GNU General Public License v2 (GPLv2) + Natural Language :: English + Operating System :: OS Independent + Programming Language :: Python :: 3 :: Only + Programming Language :: Python :: 3.6 + Programming Language :: Python :: 3.7 + Programming Language :: Python :: 3.8 + Programming Language :: Python :: 3.9 + Programming Language :: Python :: 3.10 + +[options] +python_requires = >= 3.6 +packages = + qemu.qmp + qemu.machine + qemu.utils + +[options.extras_require] +# Run `pipenv lock --dev` when changing these requirements. +devel = + avocado-framework >= 87.0 + flake8 >= 3.6.0 + isort >= 5.1.2 + mypy >= 0.770 + pylint >= 2.8.0 + tox >= 3.18.0 + +[flake8] +extend-ignore = E722 # Prefer pylint's bare-except checks to flake8's +exclude = __pycache__, + .venv, + .tox, + +[mypy] +strict = True +python_version = 3.6 +warn_unused_configs = True +namespace_packages = True + +[pylint.messages control] +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once). You can also use "--disable=all" to +# disable everything first and then reenable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use "--disable=all --enable=classes +# --disable=W". +disable=too-many-arguments, + too-many-instance-attributes, + too-many-public-methods, + +[pylint.basic] +# Good variable names which should always be accepted, separated by a comma. +good-names=i, + j, + k, + ex, + Run, + _, + fd, + c, + +[pylint.similarities] +# Ignore imports when computing similarities. +ignore-imports=yes + +[isort] +force_grid_wrap=4 +force_sort_within_sections=True +include_trailing_comma=True +line_length=72 +lines_after_imports=2 +multi_line_output=3 + +# tox (https://tox.readthedocs.io/) is a tool for running tests in +# multiple virtualenvs. This configuration file will run the test suite +# on all supported python versions. To use it, "pip install tox" and +# then run "tox" from this directory. You will need all of these versions +# of python available on your system to run this test. + +[tox:tox] +envlist = py36, py37, py38, py39, py310 + +[testenv] +allowlist_externals = make +deps = .[devel] +commands = + make check diff --git a/python/setup.py b/python/setup.py new file mode 100755 index 0000000000..2014f81b75 --- /dev/null +++ b/python/setup.py @@ -0,0 +1,23 @@ +#!/usr/bin/env python3 +""" +QEMU tooling installer script +Copyright (c) 2020-2021 John Snow for Red Hat, Inc. +""" + +import setuptools +import pkg_resources + + +def main(): + """ + QEMU tooling installer + """ + + # https://medium.com/@daveshawley/safely-using-setup-cfg-for-metadata-1babbe54c108 + pkg_resources.require('setuptools>=39.2') + + setuptools.setup() + + +if __name__ == '__main__': + main() diff --git a/python/tests/flake8.sh b/python/tests/flake8.sh new file mode 100755 index 0000000000..51e0788462 --- /dev/null +++ b/python/tests/flake8.sh @@ -0,0 +1,2 @@ +#!/bin/sh -e +python3 -m flake8 diff --git a/python/tests/isort.sh b/python/tests/isort.sh new file mode 100755 index 0000000000..4480405bfb --- /dev/null +++ b/python/tests/isort.sh @@ -0,0 +1,2 @@ +#!/bin/sh -e +python3 -m isort -c qemu/ diff --git a/python/tests/mypy.sh b/python/tests/mypy.sh new file mode 100755 index 0000000000..5f980f563b --- /dev/null +++ b/python/tests/mypy.sh @@ -0,0 +1,2 @@ +#!/bin/sh -e +python3 -m mypy -p qemu diff --git a/python/tests/pylint.sh b/python/tests/pylint.sh new file mode 100755 index 0000000000..4b10b34db7 --- /dev/null +++ b/python/tests/pylint.sh @@ -0,0 +1,2 @@ +#!/bin/sh -e +python3 -m pylint qemu/ diff --git a/qapi/misc-target.json b/qapi/misc-target.json index 6200c671be..5573dcf8f0 100644 --- a/qapi/misc-target.json +++ b/qapi/misc-target.json @@ -285,3 +285,41 @@ ## { 'command': 'query-gic-capabilities', 'returns': ['GICCapability'], 'if': 'defined(TARGET_ARM)' } + + +## +# @SevAttestationReport: +# +# The struct describes attestation report for a Secure Encrypted Virtualization +# feature. +# +# @data: guest attestation report (base64 encoded) +# +# +# Since: 6.1 +## +{ 'struct': 'SevAttestationReport', + 'data': { 'data': 'str'}, + 'if': 'defined(TARGET_I386)' } + +## +# @query-sev-attestation-report: +# +# This command is used to get the SEV attestation report, and is supported on AMD +# X86 platforms only. +# +# @mnonce: a random 16 bytes value encoded in base64 (it will be included in report) +# +# Returns: SevAttestationReport objects. +# +# Since: 6.1 +# +# Example: +# +# -> { "execute" : "query-sev-attestation-report", "arguments": { "mnonce": "aaaaaaa" } } +# <- { "return" : { "data": "aaaaaaaabbbddddd"} } +# +## +{ 'command': 'query-sev-attestation-report', 'data': { 'mnonce': 'str' }, + 'returns': 'SevAttestationReport', + 'if': 'defined(TARGET_I386)' } diff --git a/qapi/qom.json b/qapi/qom.json index 40d70c434a..f7ef30f940 100644 --- a/qapi/qom.json +++ b/qapi/qom.json @@ -645,6 +645,21 @@ 'data': { 'path': 'str' } } ## +# @QtestProperties: +# +# Properties for qtest objects. +# +# @chardev: the chardev to be used to receive qtest commands on. +# +# @log: the path to a log file +# +# Since: 6.0 +## +{ 'struct': 'QtestProperties', + 'data': { 'chardev': 'str', + '*log': 'str' } } + +## # @RemoteObjectProperties: # # Properties for x-remote-object objects. @@ -769,6 +784,7 @@ 'memory-backend-ram', 'pef-guest', 'pr-manager-helper', + 'qtest', 'rng-builtin', 'rng-egd', 'rng-random', @@ -825,6 +841,7 @@ 'if': 'defined(CONFIG_LINUX)' }, 'memory-backend-ram': 'MemoryBackendProperties', 'pr-manager-helper': 'PrManagerHelperProperties', + 'qtest': 'QtestProperties', 'rng-builtin': 'RngProperties', 'rng-egd': 'RngEgdProperties', 'rng-random': 'RngRandomProperties', @@ -857,7 +874,8 @@ # <- { "return": {} } # ## -{ 'command': 'object-add', 'data': 'ObjectOptions', 'boxed': true } +{ 'command': 'object-add', 'data': 'ObjectOptions', 'boxed': true, + 'allow-preconfig': true } ## # @object-del: @@ -877,4 +895,5 @@ # <- { "return": {} } # ## -{ 'command': 'object-del', 'data': {'id': 'str'} } +{ 'command': 'object-del', 'data': {'id': 'str'}, + 'allow-preconfig': true } diff --git a/qapi/trace-events b/qapi/trace-events index 3cabe912ae..cccafc07e5 100644 --- a/qapi/trace-events +++ b/qapi/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # qapi-visit-core.c visit_free(void *v) "v=%p" diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index 998b67186d..e8d862a426 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -92,9 +92,19 @@ static int command(BlockBackend *blk, const cmdinfo_t *ct, int argc, return -EINVAL; } - /* Request additional permissions if necessary for this command. The caller + /* + * Request additional permissions if necessary for this command. The caller * is responsible for restoring the original permissions afterwards if this - * is what it wants. */ + * is what it wants. + * + * Coverity thinks that blk may be NULL in the following if condition. It's + * not so: in init_check_command() we fail if blk is NULL for command with + * both CMD_FLAG_GLOBAL and CMD_NOFILE_OK flags unset. And in + * qemuio_add_command() we assert that command with non-zero .perm field + * doesn't set this flags. So, the following assertion is to silence + * Coverity: + */ + assert(blk || !ct->perm); if (ct->perm && blk_is_available(blk)) { uint64_t orig_perm, orig_shared_perm; blk_get_perm(blk, &orig_perm, &orig_shared_perm); diff --git a/qemu-options-wrapper.h b/qemu-options-wrapper.h deleted file mode 100644 index 6f548e3922..0000000000 --- a/qemu-options-wrapper.h +++ /dev/null @@ -1,40 +0,0 @@ - -#if defined(QEMU_OPTIONS_GENERATE_ENUM) - -#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ - opt_enum, -#define DEFHEADING(text) -#define ARCHHEADING(text, arch_mask) - -#elif defined(QEMU_OPTIONS_GENERATE_HELP) - -#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ - if ((arch_mask) & arch_type) \ - fputs(opt_help, stdout); - -#define ARCHHEADING(text, arch_mask) \ - if ((arch_mask) & arch_type) \ - puts(stringify(text)); - -#define DEFHEADING(text) ARCHHEADING(text, QEMU_ARCH_ALL) - -#elif defined(QEMU_OPTIONS_GENERATE_OPTIONS) - -#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ - { option, opt_arg, opt_enum, arch_mask }, -#define DEFHEADING(text) -#define ARCHHEADING(text, arch_mask) - -#else -#error "qemu-options-wrapper.h included with no option defined" -#endif - -#include "qemu-options.def" - -#undef DEF -#undef DEFHEADING -#undef ARCHHEADING - -#undef QEMU_OPTIONS_GENERATE_ENUM -#undef QEMU_OPTIONS_GENERATE_HELP -#undef QEMU_OPTIONS_GENERATE_OPTIONS diff --git a/qemu-options.hx b/qemu-options.hx index e22fb94d99..14258784b3 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -141,6 +141,7 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel, " kvm-shadow-mem=size of KVM shadow MMU in bytes\n" " split-wx=on|off (enable TCG split w^x mapping)\n" " tb-size=n (TCG translation block cache size)\n" + " dirty-ring-size=n (KVM dirty ring GFN count, default 0)\n" " thread=single|multi (enable multi-threaded TCG)\n", QEMU_ARCH_ALL) SRST ``-accel name[,prop=value[,...]]`` @@ -181,6 +182,17 @@ SRST where both the back-end and front-ends support it and no incompatible TCG features have been enabled (e.g. icount/replay). + + ``dirty-ring-size=n`` + When the KVM accelerator is used, it controls the size of the per-vCPU + dirty page ring buffer (number of entries for each vCPU). It should + be a value that is power of two, and it should be 1024 or bigger (but + still less than the maximum value that the kernel supports). 4096 + could be a good initial value if you have no idea which is the best. + Set this value to 0 to disable the feature. By default, this feature + is disabled (dirty-ring-size=0). When enabled, KVM will instead + record dirty pages in a bitmap. + ERST DEF("smp", HAS_ARG, QEMU_OPTION_smp, @@ -3787,8 +3799,11 @@ DEF("mon", HAS_ARG, QEMU_OPTION_mon, \ "-mon [chardev=]name[,mode=readline|control][,pretty[=on|off]]\n", QEMU_ARCH_ALL) SRST ``-mon [chardev=]name[,mode=readline|control][,pretty[=on|off]]`` - Setup monitor on chardev name. ``pretty`` is only valid when - ``mode=control``, turning on JSON pretty printing to ease + Setup monitor on chardev name. ``mode=control`` configures + a QMP monitor (a JSON RPC-style protocol) and it is not the + same as HMP, the human monitor that has a "(qemu)" prompt. + ``pretty`` is only valid when ``mode=control``, + turning on JSON pretty printing to ease human reading and debugging. ERST @@ -5264,3 +5279,7 @@ ERST HXCOMM This is the last statement. Insert new options before this line! + +#undef DEF +#undef DEFHEADING +#undef ARCHHEADING diff --git a/qom/trace-events b/qom/trace-events index 945205bd10..b2e9f4a712 100644 --- a/qom/trace-events +++ b/qom/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # object.c object_dynamic_cast_assert(const char *type, const char *target, const char *file, int line, const char *func) "%s->%s (%s:%d:%s)" diff --git a/replication.c b/replication.c index be3a42f9c9..4acd3f8004 100644 --- a/replication.c +++ b/replication.c @@ -14,7 +14,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "replication.h" +#include "block/replication.h" static QLIST_HEAD(, ReplicationState) replication_states; diff --git a/scripts/simpletrace.py b/scripts/simpletrace.py index d61fb0bd87..1f6d1ae1f3 100755 --- a/scripts/simpletrace.py +++ b/scripts/simpletrace.py @@ -7,7 +7,7 @@ # This work is licensed under the terms of the GNU GPL, version 2. See # the COPYING file in the top-level directory. # -# For help see docs/devel/tracing.txt +# For help see docs/devel/tracing.rst import struct import inspect diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index 1050e36169..fea4d6eb65 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -34,6 +34,7 @@ cp_portable() { if grep '#include' "$f" | grep -v -e 'linux/virtio' \ -e 'linux/types' \ + -e 'linux/ioctl' \ -e 'stdint' \ -e 'linux/if_ether' \ -e 'input-event-codes' \ @@ -66,6 +67,7 @@ cp_portable() { -e 's/__BITS_PER_LONG/HOST_LONG_BITS/' \ -e '/\"drm.h\"/d' \ -e '/sys\/ioctl.h/d' \ + -e '/linux\/ioctl.h/d' \ -e 's/SW_MAX/SW_MAX_/' \ -e 's/atomic_t/int/' \ -e 's/__kernel_long_t/long/' \ @@ -190,6 +192,7 @@ for i in "$tmpdir"/include/linux/*virtio*.h \ "$tmpdir/include/linux/fuse.h" \ "$tmpdir/include/linux/input.h" \ "$tmpdir/include/linux/input-event-codes.h" \ + "$tmpdir/include/linux/udmabuf.h" \ "$tmpdir/include/linux/pci_regs.h" \ "$tmpdir/include/linux/ethtool.h" \ "$tmpdir/include/linux/const.h" \ diff --git a/scsi/trace-events b/scsi/trace-events index 6dbfeae790..baf924fa89 100644 --- a/scsi/trace-events +++ b/scsi/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pr-manager.c pr_manager_execute(int fd, int cmd, int sa) "fd=%d cmd=0x%02x service action=0x%02x" diff --git a/softmmu/memory.c b/softmmu/memory.c index 3bb533c0bc..c19b0be6b1 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -2055,6 +2055,10 @@ void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr, memory_region_get_dirty_log_mask(mr)); } +/* + * If memory region `mr' is NULL, do global sync. Otherwise, sync + * dirty bitmap for the specified memory region. + */ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr) { MemoryListener *listener; @@ -2068,18 +2072,24 @@ static void memory_region_sync_dirty_bitmap(MemoryRegion *mr) * address space once. */ QTAILQ_FOREACH(listener, &memory_listeners, link) { - if (!listener->log_sync) { - continue; - } - as = listener->address_space; - view = address_space_get_flatview(as); - FOR_EACH_FLAT_RANGE(fr, view) { - if (fr->dirty_log_mask && (!mr || fr->mr == mr)) { - MemoryRegionSection mrs = section_from_flat_range(fr, view); - listener->log_sync(listener, &mrs); + if (listener->log_sync) { + as = listener->address_space; + view = address_space_get_flatview(as); + FOR_EACH_FLAT_RANGE(fr, view) { + if (fr->dirty_log_mask && (!mr || fr->mr == mr)) { + MemoryRegionSection mrs = section_from_flat_range(fr, view); + listener->log_sync(listener, &mrs); + } } + flatview_unref(view); + } else if (listener->log_sync_global) { + /* + * No matter whether MR is specified, what we can do here + * is to do a global sync, because we are not capable to + * sync in a finer granularity. + */ + listener->log_sync_global(listener); } - flatview_unref(view); } } @@ -2767,6 +2777,9 @@ void memory_listener_register(MemoryListener *listener, AddressSpace *as) { MemoryListener *other = NULL; + /* Only one of them can be defined for a listener */ + assert(!(listener->log_sync && listener->log_sync_global)); + listener->address_space = as; if (QTAILQ_EMPTY(&memory_listeners) || listener->priority >= QTAILQ_LAST(&memory_listeners)->priority) { diff --git a/softmmu/physmem.c b/softmmu/physmem.c index e1da81ed2f..1c8717684a 100644 --- a/softmmu/physmem.c +++ b/softmmu/physmem.c @@ -905,6 +905,16 @@ void cpu_check_watchpoint(CPUState *cpu, vaddr addr, vaddr len, && (wp->flags & flags)) { if (replay_running_debug()) { /* + * replay_breakpoint reads icount. + * Force recompile to succeed, because icount may + * be read only at the end of the block. + */ + if (!cpu->can_do_io) { + /* Force execution of one insn next time. */ + cpu->cflags_next_tb = 1 | CF_LAST_IO | curr_cflags(cpu); + cpu_loop_exit_restore(cpu, ra); + } + /* * Don't process the watchpoints when we are * in a reverse debugging operation. */ diff --git a/softmmu/qtest.c b/softmmu/qtest.c index 130c366615..72751e1fd8 100644 --- a/softmmu/qtest.c +++ b/softmmu/qtest.c @@ -27,6 +27,8 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qemu/cutils.h" +#include "qapi/qmp/qerror.h" +#include "qom/object_interfaces.h" #include CONFIG_DEVICES #ifdef CONFIG_PSERIES #include "hw/ppc/spapr_rtas.h" @@ -34,11 +36,25 @@ #define MAX_IRQ 256 +#define TYPE_QTEST "qtest" + +OBJECT_DECLARE_SIMPLE_TYPE(QTest, QTEST) + +struct QTest { + Object parent; + + bool has_machine_link; + char *chr_name; + Chardev *chr; + CharBackend qtest_chr; + char *log; +}; + bool qtest_allowed; static DeviceState *irq_intercept_dev; static FILE *qtest_log_fp; -static CharBackend qtest_chr; +static QTest *qtest; static GString *inbuf; static int irq_levels[MAX_IRQ]; static qemu_timeval start_time; @@ -320,7 +336,7 @@ static void qtest_irq_handler(void *opaque, int n, int level) qemu_set_irq(old_irq, level); if (irq_levels[n] != level) { - CharBackend *chr = &qtest_chr; + CharBackend *chr = &qtest->qtest_chr; irq_levels[n] = level; qtest_send_prefix(chr); qtest_sendf(chr, "IRQ %s %d\n", @@ -849,18 +865,39 @@ static void qtest_event(void *opaque, QEMUChrEvent event) break; } } + void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error **errp) { + ERRP_GUARD(); Chardev *chr; + Object *qtest; chr = qemu_chr_new("qtest", qtest_chrdev, NULL); - if (chr == NULL) { error_setg(errp, "Failed to initialize device for qtest: \"%s\"", qtest_chrdev); return; } + qtest = object_new(TYPE_QTEST); + object_property_set_str(qtest, "chardev", "qtest", &error_abort); + if (qtest_log) { + object_property_set_str(qtest, "log", qtest_log, &error_abort); + } + object_property_add_child(qdev_get_machine(), "qtest", qtest); + user_creatable_complete(USER_CREATABLE(qtest), errp); + if (*errp) { + object_unparent(qtest); + } + object_unref(OBJECT(chr)); + object_unref(qtest); +} + +static bool qtest_server_start(QTest *q, Error **errp) +{ + Chardev *chr = q->chr; + const char *qtest_log = q->log; + if (qtest_log) { if (strcmp(qtest_log, "none") != 0) { qtest_log_fp = fopen(qtest_log, "w+"); @@ -869,16 +906,20 @@ void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error ** qtest_log_fp = stderr; } - qemu_chr_fe_init(&qtest_chr, chr, errp); - qemu_chr_fe_set_handlers(&qtest_chr, qtest_can_read, qtest_read, - qtest_event, NULL, &qtest_chr, NULL, true); - qemu_chr_fe_set_echo(&qtest_chr, true); + if (!qemu_chr_fe_init(&q->qtest_chr, chr, errp)) { + return false; + } + qemu_chr_fe_set_handlers(&q->qtest_chr, qtest_can_read, qtest_read, + qtest_event, NULL, &q->qtest_chr, NULL, true); + qemu_chr_fe_set_echo(&q->qtest_chr, true); inbuf = g_string_new(""); if (!qtest_server_send) { - qtest_server_set_send_handler(qtest_server_char_be_send, &qtest_chr); + qtest_server_set_send_handler(qtest_server_char_be_send, &q->qtest_chr); } + qtest = q; + return true; } void qtest_server_set_send_handler(void (*send)(void*, const char*), @@ -890,7 +931,7 @@ void qtest_server_set_send_handler(void (*send)(void*, const char*), bool qtest_driver(void) { - return qtest_chr.chr != NULL; + return qtest && qtest->qtest_chr.chr != NULL; } void qtest_server_inproc_recv(void *dummy, const char *buf) @@ -905,3 +946,129 @@ void qtest_server_inproc_recv(void *dummy, const char *buf) g_string_truncate(gstr, 0); } } + +static void qtest_complete(UserCreatable *uc, Error **errp) +{ + QTest *q = QTEST(uc); + if (qtest) { + error_setg(errp, "Only one instance of qtest can be created"); + return; + } + if (!q->chr_name) { + error_setg(errp, "No backend specified"); + return; + } + + if (OBJECT(uc)->parent != qdev_get_machine()) { + q->has_machine_link = true; + object_property_add_const_link(qdev_get_machine(), "qtest", OBJECT(uc)); + } else { + /* -qtest was used. */ + } + + qtest_server_start(q, errp); +} + +static void qtest_unparent(Object *obj) +{ + QTest *q = QTEST(obj); + + if (qtest == q) { + qemu_chr_fe_disconnect(&q->qtest_chr); + assert(!qtest_opened); + qemu_chr_fe_deinit(&q->qtest_chr, false); + if (qtest_log_fp) { + fclose(qtest_log_fp); + qtest_log_fp = NULL; + } + qtest = NULL; + } + + if (q->has_machine_link) { + object_property_del(qdev_get_machine(), "qtest"); + q->has_machine_link = false; + } +} + +static void qtest_set_log(Object *obj, const char *value, Error **errp) +{ + QTest *q = QTEST(obj); + + if (qtest == q) { + error_setg(errp, QERR_PERMISSION_DENIED); + } else { + g_free(q->log); + q->log = g_strdup(value); + } +} + +static char *qtest_get_log(Object *obj, Error **errp) +{ + QTest *q = QTEST(obj); + + return g_strdup(q->log); +} + +static void qtest_set_chardev(Object *obj, const char *value, Error **errp) +{ + QTest *q = QTEST(obj); + Chardev *chr; + + if (qtest == q) { + error_setg(errp, QERR_PERMISSION_DENIED); + return; + } + + chr = qemu_chr_find(value); + if (!chr) { + error_setg(errp, "Cannot find character device '%s'", value); + return; + } + + g_free(q->chr_name); + q->chr_name = g_strdup(value); + + if (q->chr) { + object_unref(q->chr); + } + q->chr = chr; + object_ref(chr); +} + +static char *qtest_get_chardev(Object *obj, Error **errp) +{ + QTest *q = QTEST(obj); + + return g_strdup(q->chr_name); +} + +static void qtest_class_init(ObjectClass *oc, void *data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc); + + oc->unparent = qtest_unparent; + ucc->complete = qtest_complete; + + object_class_property_add_str(oc, "chardev", + qtest_get_chardev, qtest_set_chardev); + object_class_property_add_str(oc, "log", + qtest_get_log, qtest_set_log); +} + +static const TypeInfo qtest_info = { + .name = TYPE_QTEST, + .parent = TYPE_OBJECT, + .class_init = qtest_class_init, + .instance_size = sizeof(QTest), + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void register_types(void) +{ + type_register_static(&qtest_info); +} + +type_init(register_types); diff --git a/softmmu/trace-events b/softmmu/trace-events index b80ca042e1..5262828b8d 100644 --- a/softmmu/trace-events +++ b/softmmu/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # balloon.c # Since requests are raised via monitor, not many tracepoints are needed. diff --git a/softmmu/vl.c b/softmmu/vl.c index 93e78469bc..6054f6f0b9 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -88,7 +88,7 @@ #include "qapi/qobject-input-visitor.h" #include "qemu/option.h" #include "qemu/config-file.h" -#include "qemu-options.h" +#include "qemu/qemu-options.h" #include "qemu/main-loop.h" #ifdef CONFIG_VIRTFS #include "fsdev/qemu-fsdev.h" @@ -854,8 +854,17 @@ static void help(int exitcode) "'disk_image' is a raw hard disk image for IDE hard disk 0\n\n", error_get_progname()); -#define QEMU_OPTIONS_GENERATE_HELP -#include "qemu-options-wrapper.h" +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + if ((arch_mask) & arch_type) \ + fputs(opt_help, stdout); + +#define ARCHHEADING(text, arch_mask) \ + if ((arch_mask) & arch_type) \ + puts(stringify(text)); + +#define DEFHEADING(text) ARCHHEADING(text, QEMU_ARCH_ALL) + +#include "qemu-options.def" printf("\nDuring emulation, the following keys are useful:\n" "ctrl-alt-f toggle full screen\n" @@ -880,8 +889,13 @@ typedef struct QEMUOption { static const QEMUOption qemu_options[] = { { "h", 0, QEMU_OPTION_h, QEMU_ARCH_ALL }, -#define QEMU_OPTIONS_GENERATE_OPTIONS -#include "qemu-options-wrapper.h" + +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + { option, opt_arg, opt_enum, arch_mask }, +#define DEFHEADING(text) +#define ARCHHEADING(text, arch_mask) + +#include "qemu-options.def" { NULL }, }; @@ -1758,8 +1772,9 @@ static bool object_create_early(const char *type) * add one, state the reason in a comment! */ - /* Reason: rng-egd property "chardev" */ - if (g_str_equal(type, "rng-egd")) { + /* Reason: property "chardev" */ + if (g_str_equal(type, "rng-egd") || + g_str_equal(type, "qtest")) { return false; } @@ -2024,8 +2039,6 @@ static void set_memory_options(MachineClass *mc) exit(EXIT_FAILURE); } - /* store value for the future use */ - qemu_opt_set_number(opts, "size", ram_size, &error_abort); maxram_size = ram_size; if (qemu_opt_get(opts, "maxmem")) { @@ -2614,6 +2627,23 @@ void qmp_x_exit_preconfig(Error **errp) } } +#ifdef CONFIG_MODULES +void qemu_load_module_for_opts(const char *group) +{ + static bool spice_tried; + if (g_str_equal(group, "spice") && !spice_tried) { + ui_module_load_one("spice-core"); + spice_tried = true; + } + + static bool iscsi_tried; + if (g_str_equal(group, "iscsi") && !iscsi_tried) { + block_module_load_one("iscsi"); + iscsi_tried = true; + } +} +#endif + void qemu_init(int argc, char **argv, char **envp) { QemuOpts *opts; @@ -3374,10 +3404,6 @@ void qemu_init(int argc, char **argv, char **envp) case QEMU_OPTION_spice: olist = qemu_find_opts_err("spice", NULL); if (!olist) { - ui_module_load_one("spice-core"); - olist = qemu_find_opts("spice"); - } - if (!olist) { error_report("spice support is disabled"); exit(1); } diff --git a/stubs/meson.build b/stubs/meson.build index 3faef16892..65c22c0568 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -22,6 +22,7 @@ stub_ss.add(files('isa-bus.c')) stub_ss.add(files('is-daemonized.c')) stub_ss.add(when: 'CONFIG_LINUX_AIO', if_true: files('linux-aio.c')) stub_ss.add(files('migr-blocker.c')) +stub_ss.add(files('module-opts.c')) stub_ss.add(files('monitor.c')) stub_ss.add(files('monitor-core.c')) stub_ss.add(files('pci-bus.c')) @@ -52,6 +53,7 @@ if have_system stub_ss.add(files('semihost.c')) stub_ss.add(files('usb-dev-stub.c')) stub_ss.add(files('xen-hw-stub.c')) + stub_ss.add(files('virtio-gpu-udmabuf.c')) else stub_ss.add(files('qdev.c')) endif diff --git a/stubs/module-opts.c b/stubs/module-opts.c new file mode 100644 index 0000000000..a7d0e4ad6e --- /dev/null +++ b/stubs/module-opts.c @@ -0,0 +1,6 @@ +#include "qemu/osdep.h" +#include "qemu/config-file.h" + +void qemu_load_module_for_opts(const char *group) +{ +} diff --git a/stubs/virtio-gpu-udmabuf.c b/stubs/virtio-gpu-udmabuf.c new file mode 100644 index 0000000000..81f661441a --- /dev/null +++ b/stubs/virtio-gpu-udmabuf.c @@ -0,0 +1,27 @@ +#include "qemu/osdep.h" +#include "hw/virtio/virtio-gpu.h" + +bool virtio_gpu_have_udmabuf(void) +{ + /* nothing (stub) */ + return false; +} + +void virtio_gpu_init_udmabuf(struct virtio_gpu_simple_resource *res) +{ + /* nothing (stub) */ +} + +void virtio_gpu_fini_udmabuf(struct virtio_gpu_simple_resource *res) +{ + /* nothing (stub) */ +} + +int virtio_gpu_update_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb) +{ + /* nothing (stub) */ + return 0; +} diff --git a/stubs/vmstate.c b/stubs/vmstate.c index cc4fe41dfc..8513d9204e 100644 --- a/stubs/vmstate.c +++ b/stubs/vmstate.c @@ -1,8 +1,6 @@ #include "qemu/osdep.h" #include "migration/vmstate.h" -const VMStateDescription vmstate_dummy = {}; - int vmstate_register_with_alias_id(VMStateIf *obj, uint32_t instance_id, const VMStateDescription *vmsd, diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c index 27192b62e2..4871ad0c0a 100644 --- a/target/alpha/cpu.c +++ b/target/alpha/cpu.c @@ -206,9 +206,17 @@ static void alpha_cpu_initfn(Object *obj) #endif } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps alpha_sysemu_ops = { + .get_phys_page_debug = alpha_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps alpha_tcg_ops = { +static const struct TCGCPUOps alpha_tcg_ops = { .initialize = alpha_translate_init, .cpu_exec_interrupt = alpha_cpu_exec_interrupt, .tlb_fill = alpha_cpu_tlb_fill, @@ -236,8 +244,8 @@ static void alpha_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = alpha_cpu_gdb_read_register; cc->gdb_write_register = alpha_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = alpha_cpu_get_phys_page_debug; dc->vmsd = &vmstate_alpha_cpu; + cc->sysemu_ops = &alpha_sysemu_ops; #endif cc->disas_set_info = alpha_cpu_disas_set_info; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 7aeb4b1381..9cddfd6a44 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -327,6 +327,7 @@ static void arm_cpu_reset(DeviceState *dev) env->regs[14] = 0xffffffff; env->v7m.vecbase[M_REG_S] = cpu->init_svtor & 0xffffff80; + env->v7m.vecbase[M_REG_NS] = cpu->init_nsvtor & 0xffffff80; /* Load the initial SP and PC from offset 0 and 4 in the vector table */ vecbase = env->v7m.vecbase[env->v7m.secure]; @@ -1272,6 +1273,15 @@ void arm_cpu_post_init(Object *obj) &cpu->init_svtor, OBJ_PROP_FLAG_READWRITE); } + if (arm_feature(&cpu->env, ARM_FEATURE_M)) { + /* + * Initial value of the NS VTOR (for cores without the Security + * extension, this is the only VTOR) + */ + object_property_add_uint32_ptr(obj, "init-nsvtor", + &cpu->init_nsvtor, + OBJ_PROP_FLAG_READWRITE); + } qdev_property_add_static(DEVICE(obj), &arm_cpu_cfgend_property); @@ -1463,6 +1473,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) u = cpu->isar.id_isar6; u = FIELD_DP32(u, ID_ISAR6, JSCVT, 0); + u = FIELD_DP32(u, ID_ISAR6, BF16, 0); cpu->isar.id_isar6 = u; u = cpu->isar.mvfr0; @@ -1503,6 +1514,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 0); + t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 0); t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 0); cpu->isar.id_aa64isar1 = t; @@ -1518,6 +1530,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) u = cpu->isar.id_isar6; u = FIELD_DP32(u, ID_ISAR6, DP, 0); u = FIELD_DP32(u, ID_ISAR6, FHM, 0); + u = FIELD_DP32(u, ID_ISAR6, BF16, 0); u = FIELD_DP32(u, ID_ISAR6, I8MM, 0); cpu->isar.id_isar6 = u; @@ -1944,8 +1957,21 @@ static gchar *arm_gdb_arch_name(CPUState *cs) return g_strdup("arm"); } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps arm_sysemu_ops = { + .get_phys_page_attrs_debug = arm_cpu_get_phys_page_attrs_debug, + .asidx_from_attrs = arm_asidx_from_attrs, + .write_elf32_note = arm_cpu_write_elf32_note, + .write_elf64_note = arm_cpu_write_elf64_note, + .virtio_is_big_endian = arm_cpu_virtio_is_big_endian, + .legacy_vmsd = &vmstate_arm_cpu, +}; +#endif + #ifdef CONFIG_TCG -static struct TCGCPUOps arm_tcg_ops = { +static const struct TCGCPUOps arm_tcg_ops = { .initialize = arm_translate_init, .synchronize_from_tb = arm_cpu_synchronize_from_tb, .cpu_exec_interrupt = arm_cpu_exec_interrupt, @@ -1981,12 +2007,7 @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = arm_cpu_gdb_read_register; cc->gdb_write_register = arm_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_attrs_debug = arm_cpu_get_phys_page_attrs_debug; - cc->asidx_from_attrs = arm_asidx_from_attrs; - cc->vmsd = &vmstate_arm_cpu; - cc->virtio_is_big_endian = arm_cpu_virtio_is_big_endian; - cc->write_elf64_note = arm_cpu_write_elf64_note; - cc->write_elf32_note = arm_cpu_write_elf32_note; + cc->sysemu_ops = &arm_sysemu_ops; #endif cc->gdb_num_core_regs = 26; cc->gdb_core_xml_file = "arm-core.xml"; diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 04f8be35bf..be9a4dceae 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -563,7 +563,8 @@ typedef struct CPUARMState { uint32_t fpdscr[M_REG_NUM_BANKS]; uint32_t cpacr[M_REG_NUM_BANKS]; uint32_t nsacr; - int ltpsize; + uint32_t ltpsize; + uint32_t vpr; } v7m; /* Information associated with an exception about to be taken: @@ -868,6 +869,8 @@ struct ARMCPU { /* For v8M, initial value of the Secure VTOR */ uint32_t init_svtor; + /* For v8M, initial value of the Non-secure VTOR */ + uint32_t init_nsvtor; /* [QEMU_]KVM_ARM_TARGET_* constant for this CPU, or * QEMU_KVM_ARM_TARGET_NONE if the kernel doesn't support this CPU type. @@ -1561,6 +1564,7 @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPCR_LTPSIZE_SHIFT 16 /* LTPSIZE, M-profile only */ #define FPCR_LTPSIZE_MASK (7 << FPCR_LTPSIZE_SHIFT) +#define FPCR_LTPSIZE_LENGTH 3 #define FPCR_NZCV_MASK (FPCR_N | FPCR_Z | FPCR_C | FPCR_V) #define FPCR_NZCVQC_MASK (FPCR_NZCV_MASK | FPCR_QC) @@ -1761,6 +1765,11 @@ FIELD(V7M_FPCCR, ASPEN, 31, 1) R_V7M_FPCCR_UFRDY_MASK | \ R_V7M_FPCCR_ASPEN_MASK) +/* v7M VPR bits */ +FIELD(V7M_VPR, P0, 0, 16) +FIELD(V7M_VPR, MASK01, 16, 4) +FIELD(V7M_VPR, MASK23, 20, 4) + /* * System register ID fields. */ @@ -3783,6 +3792,11 @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; } +static inline bool isar_feature_aa32_bf16(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, BF16) != 0; +} + static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0; @@ -3817,6 +3831,28 @@ static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) } } +static inline bool isar_feature_aa32_mve(const ARMISARegisters *id) +{ + /* + * Return true if MVE is supported (either integer or floating point). + * We must check for M-profile as the MVFR1 field means something + * else for A-profile. + */ + return isar_feature_aa32_mprofile(id) && + FIELD_EX32(id->mvfr1, MVFR1, MVE) > 0; +} + +static inline bool isar_feature_aa32_mve_fp(const ARMISARegisters *id) +{ + /* + * Return true if MVE is supported (either integer or floating point). + * We must check for M-profile as the MVFR1 field means something + * else for A-profile. + */ + return isar_feature_aa32_mprofile(id) && + FIELD_EX32(id->mvfr1, MVFR1, MVE) >= 2; +} + static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) { /* @@ -4122,6 +4158,11 @@ static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2; } +static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; +} + static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically. */ @@ -4266,6 +4307,11 @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; } +static inline bool isar_feature_aa64_sve_bf16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BFLOAT16) != 0; +} + static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index d561dc7acc..1c23187d1a 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -661,6 +661,7 @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 1); t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* ARMv8.4-RCPC */ t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); @@ -708,6 +709,7 @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* PMULL */ t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 1); t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); @@ -731,6 +733,7 @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_ISAR6, FHM, 1); u = FIELD_DP32(u, ID_ISAR6, SB, 1); u = FIELD_DP32(u, ID_ISAR6, SPECRES, 1); + u = FIELD_DP32(u, ID_ISAR6, BF16, 1); u = FIELD_DP32(u, ID_ISAR6, I8MM, 1); cpu->isar.id_isar6 = u; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index d3458335ed..d2d97115ea 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -898,7 +898,7 @@ static void pxa270c5_initfn(Object *obj) } #ifdef CONFIG_TCG -static struct TCGCPUOps arm_v7m_tcg_ops = { +static const struct TCGCPUOps arm_v7m_tcg_ops = { .initialize = arm_translate_init, .synchronize_from_tb = arm_cpu_synchronize_from_tb, .cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt, @@ -968,6 +968,7 @@ static void arm_max_initfn(Object *obj) t = FIELD_DP32(t, ID_ISAR6, FHM, 1); t = FIELD_DP32(t, ID_ISAR6, SB, 1); t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); + t = FIELD_DP32(t, ID_ISAR6, BF16, 1); t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); cpu->isar.id_isar6 = t; diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 29a14a21f5..dc629f851a 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -1197,6 +1197,8 @@ DEF_HELPER_FLAGS_5(sve_fcvt_hd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_fcvt_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_bfcvt, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -2752,6 +2754,8 @@ DEF_HELPER_FLAGS_5(sve2_fcvtnt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_fcvtnt_ds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_bfcvtnt, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_fcvtlt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/helper.h b/target/arm/helper.h index 23ccb0f72f..dc6eb96d43 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -143,6 +143,8 @@ DEF_HELPER_3(vfp_cmped, void, f64, f64, env) DEF_HELPER_2(vfp_fcvtds, f64, f32, env) DEF_HELPER_2(vfp_fcvtsd, f32, f64, env) +DEF_HELPER_FLAGS_2(bfcvt, TCG_CALL_NO_RWG, i32, f32, ptr) +DEF_HELPER_FLAGS_2(bfcvt_pair, TCG_CALL_NO_RWG, i32, i64, ptr) DEF_HELPER_2(vfp_uitoh, f16, i32, ptr) DEF_HELPER_2(vfp_uitos, f32, i32, ptr) @@ -1000,6 +1002,19 @@ DEF_HELPER_FLAGS_5(gvec_ummla_b, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_usmmla_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_bfdot, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_bfdot_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_bfmmla, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index eda74e5545..074c543455 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -2601,10 +2601,7 @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) limit = is_psp ? env->v7m.psplim[false] : env->v7m.msplim[false]; if (val < limit) { - CPUState *cs = env_cpu(env); - - cpu_restore_state(cs, GETPC(), true); - raise_exception(env, EXCP_STKOF, 0, 1); + raise_exception_ra(env, EXCP_STKOF, 0, 1, GETPC()); } if (is_psp) { diff --git a/target/arm/machine.c b/target/arm/machine.c index 6ad1d306b1..81e30de824 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -318,6 +318,25 @@ static const VMStateDescription vmstate_m_fp = { } }; +static bool mve_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + + return cpu_isar_feature(aa32_mve, cpu); +} + +static const VMStateDescription vmstate_m_mve = { + .name = "cpu/m/mve", + .version_id = 1, + .minimum_version_id = 1, + .needed = mve_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(env.v7m.vpr, ARMCPU), + VMSTATE_UINT32(env.v7m.ltpsize, ARMCPU), + VMSTATE_END_OF_LIST() + }, +}; + static const VMStateDescription vmstate_m = { .name = "cpu/m", .version_id = 4, @@ -344,6 +363,7 @@ static const VMStateDescription vmstate_m = { &vmstate_m_other_sp, &vmstate_m_v8m, &vmstate_m_fp, + &vmstate_m_mve, NULL } }; diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index a6fccc6e69..166b9d260f 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -563,20 +563,14 @@ static void mte_check_fail(CPUARMState *env, uint32_t desc, switch (tcf) { case 1: - /* - * Tag check fail causes a synchronous exception. - * - * In restore_state_to_opc, we set the exception syndrome - * for the load or store operation. Unwind first so we - * may overwrite that with the syndrome for the tag check. - */ - cpu_restore_state(env_cpu(env), ra, true); + /* Tag check fail causes a synchronous exception. */ env->exception.vaddress = dirty_ptr; is_write = FIELD_EX32(desc, MTEDESC, WRITE); syn = syn_data_abort_no_iss(arm_current_el(env) != 0, 0, 0, 0, 0, is_write, 0x11); - raise_exception(env, EXCP_DATA_ABORT, syn, exception_target_el(env)); + raise_exception_ra(env, EXCP_DATA_ABORT, syn, + exception_target_el(env), ra); /* noreturn, but fall through to the assert anyway */ case 0: diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index ec83f10ab3..fd3a01bfa0 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -521,6 +521,7 @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VRINTZ 1111 001 11 . 11 .. 10 .... 0 1011 . . 0 .... @2misc VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0 + VCVT_B16_F32 1111 001 11 . 11 .. 10 .... 0 1100 1 . 0 .... @2misc_q0 VRINTM 1111 001 11 . 11 .. 10 .... 0 1101 . . 0 .... @2misc diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index cc9f4cdd85..df80e6ebf6 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -52,6 +52,8 @@ VUDOT 1111 110 00 . 10 .... .... 1101 . q:1 . 1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp VUSDOT 1111 110 01 . 10 .... .... 1101 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp +VDOT_b16 1111 110 00 . 00 .... .... 1101 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp # VFM[AS]L VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \ @@ -65,6 +67,11 @@ VUMMLA 1111 1100 0.10 .... .... 1100 .1.1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp VUSMMLA 1111 1100 1.10 .... .... 1100 .1.0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp +VMMLA_b16 1111 1100 0.00 .... .... 1100 .1.0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp + +VFMA_b16 1111 110 0 0.11 .... .... 1000 . q:1 . 1 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ vn=%vn_dp vd=%vd_dp size=1 @@ -79,6 +86,8 @@ VUSDOT_scalar 1111 1110 1 . 00 .... .... 1101 . q:1 index:1 0 vm:4 \ vn=%vn_dp vd=%vd_dp VSUDOT_scalar 1111 1110 1 . 00 .... .... 1101 . q:1 index:1 1 vm:4 \ vn=%vn_dp vd=%vd_dp +VDOT_b16_scal 1111 1110 0 . 00 .... .... 1101 . q:1 index:1 0 vm:4 \ + vn=%vn_dp vd=%vd_dp %vfml_scalar_q0_rm 0:3 5:1 %vfml_scalar_q1_index 5:1 3:1 @@ -86,3 +95,5 @@ VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 0 . 1 index:1 ... \ rm=%vfml_scalar_q0_rm vn=%vn_sp vd=%vd_dp q=0 VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 1 . 1 . rm:3 \ index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp q=1 +VFMA_b16_scal 1111 1110 0.11 .... .... 1000 . q:1 . 1 . vm:3 \ + index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index efcb600992..e98fd86305 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -27,8 +27,8 @@ #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) -static CPUState *do_raise_exception(CPUARMState *env, uint32_t excp, - uint32_t syndrome, uint32_t target_el) +void raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) { CPUState *cs = env_cpu(env); @@ -49,22 +49,21 @@ static CPUState *do_raise_exception(CPUARMState *env, uint32_t excp, cs->exception_index = excp; env->exception.syndrome = syndrome; env->exception.target_el = target_el; - - return cs; -} - -void raise_exception(CPUARMState *env, uint32_t excp, - uint32_t syndrome, uint32_t target_el) -{ - CPUState *cs = do_raise_exception(env, excp, syndrome, target_el); cpu_loop_exit(cs); } void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome, uint32_t target_el, uintptr_t ra) { - CPUState *cs = do_raise_exception(env, excp, syndrome, target_el); - cpu_loop_exit_restore(cs, ra); + CPUState *cs = env_cpu(env); + + /* + * restore_state_to_opc() will set env->exception.syndrome, so + * we must restore CPU state here before setting the syndrome + * the caller passed us, and cannot use cpu_loop_exit_restore(). + */ + cpu_restore_state(cs, ra, true); + raise_exception(env, excp, syndrome, target_el); } uint64_t HELPER(neon_tbl)(CPUARMState *env, uint32_t desc, @@ -96,15 +95,12 @@ void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue) * raising an exception if the limit is breached. */ if (newvalue < v7m_sp_limit(env)) { - CPUState *cs = env_cpu(env); - /* * Stack limit exceptions are a rare case, so rather than syncing - * PC/condbits before the call, we use cpu_restore_state() to - * get them right before raising the exception. + * PC/condbits before the call, we use raise_exception_ra() so + * that cpu_restore_state() will sort them out. */ - cpu_restore_state(cs, GETPC(), true); - raise_exception(env, EXCP_STKOF, 0, 1); + raise_exception_ra(env, EXCP_STKOF, 0, 1, GETPC()); } } diff --git a/target/arm/sve.decode b/target/arm/sve.decode index cb077bfde9..a62c169f1a 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -1036,6 +1036,7 @@ FNMLS_zpzzz 01100101 .. 1 ..... 111 ... ..... ..... @rdn_pg_rm_ra # SVE floating-point convert precision FCVT_sh 01100101 10 0010 00 101 ... ..... ..... @rd_pg_rn_e0 FCVT_hs 01100101 10 0010 01 101 ... ..... ..... @rd_pg_rn_e0 +BFCVT 01100101 10 0010 10 101 ... ..... ..... @rd_pg_rn_e0 FCVT_dh 01100101 11 0010 00 101 ... ..... ..... @rd_pg_rn_e0 FCVT_hd 01100101 11 0010 01 101 ... ..... ..... @rd_pg_rn_e0 FCVT_ds 01100101 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0 @@ -1567,8 +1568,10 @@ SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm ### SVE2 floating point matrix multiply accumulate - -FMMLA 01100100 .. 1 ..... 111001 ..... ..... @rda_rn_rm +{ + BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 + FMMLA 01100100 .. 1 ..... 111 001 ..... ..... @rda_rn_rm +} ### SVE2 Memory Gather Load Group @@ -1610,6 +1613,7 @@ RAX1 01000101 00 1 ..... 11110 1 ..... ..... @rd_rn_rm_e0 FCVTXNT_ds 01100100 00 0010 10 101 ... ..... ..... @rd_pg_rn_e0 FCVTX_ds 01100101 00 0010 10 101 ... ..... ..... @rd_pg_rn_e0 FCVTNT_sh 01100100 10 0010 00 101 ... ..... ..... @rd_pg_rn_e0 +BFCVTNT 01100100 10 0010 10 101 ... ..... ..... @rd_pg_rn_e0 FCVTLT_hs 01100100 10 0010 01 101 ... ..... ..... @rd_pg_rn_e0 FCVTNT_ds 01100100 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0 FCVTLT_sd 01100100 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0 @@ -1623,8 +1627,19 @@ FMLALT_zzzw 01100100 10 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 FMLSLB_zzzw 01100100 10 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_e0 FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_e0 +BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 +BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 + +### SVE2 floating-point bfloat16 dot-product +BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 + ### SVE2 floating-point multiply-add long (indexed) FMLALB_zzxw 01100100 10 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 FMLALT_zzxw 01100100 10 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 FMLSLB_zzxw 01100100 10 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2 FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 +BFMLALB_zzxw 01100100 11 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 +BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 + +### SVE2 floating-point bfloat16 dot-product (indexed) +BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index 40af3024df..46a957b6fb 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -4708,6 +4708,7 @@ static inline uint64_t vfp_float64_to_uint64_rtz(float64 f, float_status *s) DO_ZPZ_FP(sve_fcvt_sh, uint32_t, H1_4, sve_f32_to_f16) DO_ZPZ_FP(sve_fcvt_hs, uint32_t, H1_4, sve_f16_to_f32) +DO_ZPZ_FP(sve_bfcvt, uint32_t, H1_4, float32_to_bfloat16) DO_ZPZ_FP(sve_fcvt_dh, uint64_t, , sve_f64_to_f16) DO_ZPZ_FP(sve_fcvt_hd, uint64_t, , sve_f16_to_f64) DO_ZPZ_FP(sve_fcvt_ds, uint64_t, , float64_to_float32) @@ -7740,6 +7741,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ } while (i != 0); \ } +DO_FCVTNT(sve_bfcvtnt, uint32_t, uint16_t, H1_4, H1_2, float32_to_bfloat16) DO_FCVTNT(sve2_fcvtnt_sh, uint32_t, uint16_t, H1_4, H1_2, sve_f32_to_f16) DO_FCVTNT(sve2_fcvtnt_ds, uint64_t, uint32_t, , H1_4, float64_to_float32) diff --git a/target/arm/trace-events b/target/arm/trace-events index 41c63d7570..2a0ba7bffc 100644 --- a/target/arm/trace-events +++ b/target/arm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # helper.c arm_gt_recalc(int timer, int irqstate, uint64_t nexttick) "gt recalc: timer %d irqstate %d next tick 0x%" PRIx64 diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index ceac0ee2bd..8713dfec17 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -3355,8 +3355,9 @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, int o3_opc = extract32(insn, 12, 4); bool r = extract32(insn, 22, 1); bool a = extract32(insn, 23, 1); - TCGv_i64 tcg_rs, clean_addr; + TCGv_i64 tcg_rs, tcg_rt, clean_addr; AtomicThreeOpFn *fn = NULL; + MemOp mop = s->be_data | size | MO_ALIGN; if (is_vector || !dc_isar_feature(aa64_atomics, s)) { unallocated_encoding(s); @@ -3377,9 +3378,11 @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, break; case 004: /* LDSMAX */ fn = tcg_gen_atomic_fetch_smax_i64; + mop |= MO_SIGN; break; case 005: /* LDSMIN */ fn = tcg_gen_atomic_fetch_smin_i64; + mop |= MO_SIGN; break; case 006: /* LDUMAX */ fn = tcg_gen_atomic_fetch_umax_i64; @@ -3422,6 +3425,7 @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, } tcg_rs = read_cpu_reg(s, rs, true); + tcg_rt = cpu_reg(s, rt); if (o3_opc == 1) { /* LDCLR */ tcg_gen_not_i64(tcg_rs, tcg_rs); @@ -3430,8 +3434,11 @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, /* The tcg atomic primitives are all full barriers. Therefore we * can ignore the Acquire and Release bits of this instruction. */ - fn(cpu_reg(s, rt), clean_addr, tcg_rs, get_mem_index(s), - s->be_data | size | MO_ALIGN); + fn(tcg_rt, clean_addr, tcg_rs, get_mem_index(s), mop); + + if ((mop & MO_SIGN) && size != MO_64) { + tcg_gen_ext32u_i64(tcg_rt, tcg_rt); + } } /* @@ -6273,6 +6280,9 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) case 0x3: /* FSQRT */ gen_helper_vfp_sqrts(tcg_res, tcg_op, cpu_env); goto done; + case 0x6: /* BFCVT */ + gen_fpst = gen_helper_bfcvt; + break; case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ case 0xa: /* FRINTM */ @@ -6494,8 +6504,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) int rd = extract32(insn, 0, 5); if (mos) { - unallocated_encoding(s); - return; + goto do_unallocated; } switch (opcode) { @@ -6504,8 +6513,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) /* FCVT between half, single and double precision */ int dtype = extract32(opcode, 0, 2); if (type == 2 || dtype == type) { - unallocated_encoding(s); - return; + goto do_unallocated; } if (!fp_access_check(s)) { return; @@ -6517,8 +6525,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) case 0x10 ... 0x13: /* FRINT{32,64}{X,Z} */ if (type > 1 || !dc_isar_feature(aa64_frint, s)) { - unallocated_encoding(s); - return; + goto do_unallocated; } /* fall through */ case 0x0 ... 0x3: @@ -6540,8 +6547,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) break; case 3: if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; + goto do_unallocated; } if (!fp_access_check(s)) { @@ -6550,11 +6556,28 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) handle_fp_1src_half(s, opcode, rd, rn); break; default: - unallocated_encoding(s); + goto do_unallocated; + } + break; + + case 0x6: + switch (type) { + case 1: /* BFCVT */ + if (!dc_isar_feature(aa64_bf16, s)) { + goto do_unallocated; + } + if (!fp_access_check(s)) { + return; + } + handle_fp_1src_single(s, opcode, rd, rn); + break; + default: + goto do_unallocated; } break; default: + do_unallocated: unallocated_encoding(s); break; } @@ -10330,6 +10353,13 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, tcg_temp_free_i32(ahp); } break; + case 0x36: /* BFCVTN, BFCVTN2 */ + { + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + gen_helper_bfcvt_pair(tcg_res[pass], tcg_op, fpst); + tcg_temp_free_ptr(fpst); + } + break; case 0x56: /* FCVTXN, FCVTXN2 */ /* 64 bit to 32 bit float conversion * with von Neumann rounding (round to odd) @@ -12205,6 +12235,24 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } feature = dc_isar_feature(aa64_fcma, s); break; + case 0x1d: /* BFMMLA */ + if (size != MO_16 || !is_q) { + unallocated_encoding(s); + return; + } + feature = dc_isar_feature(aa64_bf16, s); + break; + case 0x1f: + switch (size) { + case 1: /* BFDOT */ + case 3: /* BFMLAL{B,T} */ + feature = dc_isar_feature(aa64_bf16, s); + break; + default: + unallocated_encoding(s); + return; + } + break; default: unallocated_encoding(s); return; @@ -12288,6 +12336,23 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } return; + case 0xd: /* BFMMLA */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfmmla); + return; + case 0xf: + switch (size) { + case 1: /* BFDOT */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfdot); + break; + case 3: /* BFMLAL{B,T} */ + gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, false, is_q, + gen_helper_gvec_bfmlal); + break; + default: + g_assert_not_reached(); + } + return; + default: g_assert_not_reached(); } @@ -12730,6 +12795,16 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd); return; + case 0x36: /* BFCVTN, BFCVTN2 */ + if (!dc_isar_feature(aa64_bf16, s) || size != 2) { + unallocated_encoding(s); + return; + } + if (!fp_access_check(s)) { + return; + } + handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd); + return; case 0x17: /* FCVTL, FCVTL2 */ if (!fp_access_check(s)) { return; @@ -13389,12 +13464,35 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) return; } break; - case 0x0f: /* SUDOT, USDOT */ - if (is_scalar || (size & 1) || !dc_isar_feature(aa64_i8mm, s)) { + case 0x0f: + switch (size) { + case 0: /* SUDOT */ + case 2: /* USDOT */ + if (is_scalar || !dc_isar_feature(aa64_i8mm, s)) { + unallocated_encoding(s); + return; + } + size = MO_32; + break; + case 1: /* BFDOT */ + if (is_scalar || !dc_isar_feature(aa64_bf16, s)) { + unallocated_encoding(s); + return; + } + size = MO_32; + break; + case 3: /* BFMLAL{B,T} */ + if (is_scalar || !dc_isar_feature(aa64_bf16, s)) { + unallocated_encoding(s); + return; + } + /* can't set is_fp without other incorrect size checks */ + size = MO_16; + break; + default: unallocated_encoding(s); return; } - size = MO_32; break; case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ @@ -13510,13 +13608,26 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b); return; - case 0x0f: /* SUDOT, USDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, - extract32(insn, 23, 1) - ? gen_helper_gvec_usdot_idx_b - : gen_helper_gvec_sudot_idx_b); - return; - + case 0x0f: + switch (extract32(insn, 22, 2)) { + case 0: /* SUDOT */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, + gen_helper_gvec_sudot_idx_b); + return; + case 1: /* BFDOT */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, + gen_helper_gvec_bfdot_idx); + return; + case 2: /* USDOT */ + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, + gen_helper_gvec_usdot_idx_b); + return; + case 3: /* BFMLAL{B,T} */ + gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, 0, (index << 1) | is_q, + gen_helper_gvec_bfmlal_idx); + return; + } + g_assert_not_reached(); case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index 9e990b41ed..633fef3bf7 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -296,6 +296,15 @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a) gen_helper_gvec_usdot_b); } +static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a) +{ + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_bfdot); +} + static bool trans_VFML(DisasContext *s, arg_VFML *a) { int opr_sz; @@ -381,6 +390,15 @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a) gen_helper_gvec_sudot_idx_b); } +static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a) +{ + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, + gen_helper_gvec_bfdot_idx); +} + static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a) { int opr_sz; @@ -3422,6 +3440,51 @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) return true; } +static bool trans_VCVT_B16_F32(DisasContext *s, arg_2misc *a) +{ + TCGv_ptr fpst; + TCGv_i64 tmp; + TCGv_i32 dst0, dst1; + + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm & 1) || (a->size != 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = fpstatus_ptr(FPST_STD); + tmp = tcg_temp_new_i64(); + dst0 = tcg_temp_new_i32(); + dst1 = tcg_temp_new_i32(); + + read_neon_element64(tmp, a->vm, 0, MO_64); + gen_helper_bfcvt_pair(dst0, tmp, fpst); + + read_neon_element64(tmp, a->vm, 1, MO_64); + gen_helper_bfcvt_pair(dst1, tmp, fpst); + + write_neon_element32(dst0, a->vd, 0, MO_32); + write_neon_element32(dst1, a->vd, 1, MO_32); + + tcg_temp_free_i64(tmp); + tcg_temp_free_i32(dst0); + tcg_temp_free_i32(dst1); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a) { TCGv_ptr fpst; @@ -4063,3 +4126,31 @@ static bool trans_VUSMMLA(DisasContext *s, arg_VUSMMLA *a) return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0, gen_helper_gvec_usmmla_b); } + +static bool trans_VMMLA_b16(DisasContext *s, arg_VMMLA_b16 *a) +{ + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0, + gen_helper_gvec_bfmmla); +} + +static bool trans_VFMA_b16(DisasContext *s, arg_VFMA_b16 *a) +{ + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + return do_neon_ddda_fpst(s, 7, a->vd, a->vn, a->vm, a->q, FPST_STD, + gen_helper_gvec_bfmlal); +} + +static bool trans_VFMA_b16_scal(DisasContext *s, arg_VFMA_b16_scal *a) +{ + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + return do_neon_ddda_fpst(s, 6, a->vd, a->vn, a->vm, + (a->index << 1) | a->q, FPST_STD, + gen_helper_gvec_bfmlal_idx); +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 9574efe957..46210eb696 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -4777,6 +4777,14 @@ static bool trans_FCVT_hs(DisasContext *s, arg_rpr_esz *a) return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_hs); } +static bool trans_BFCVT(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_bfcvt); +} + static bool trans_FCVT_dh(DisasContext *s, arg_rpr_esz *a) { return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_dh); @@ -8472,6 +8480,14 @@ static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a) return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_sh); } +static bool trans_BFCVTNT(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_bfcvtnt); +} + static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz *a) { if (!dc_isar_feature(aa64_sve2, s)) { @@ -8637,3 +8653,99 @@ static bool trans_UMMLA(DisasContext *s, arg_rrrr_esz *a) { return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_ummla_b, 0); } + +static bool trans_BFDOT_zzzz(DisasContext *s, arg_rrrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot, + a->rd, a->rn, a->rm, a->ra, 0); + } + return true; +} + +static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot_idx, + a->rd, a->rn, a->rm, a->ra, a->index); + } + return true; +} + +static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, gen_helper_gvec_bfmmla, + a->rd, a->rn, a->rm, a->ra, 0); + } + return true; +} + +static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + if (sve_access_check(s)) { + TCGv_ptr status = fpstatus_ptr(FPST_FPCR); + unsigned vsz = vec_full_reg_size(s); + + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + status, vsz, vsz, sel, + gen_helper_gvec_bfmlal); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool trans_BFMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_BFMLAL_zzzw(s, a, false); +} + +static bool trans_BFMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_BFMLAL_zzzw(s, a, true); +} + +static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) +{ + if (!dc_isar_feature(aa64_sve_bf16, s)) { + return false; + } + if (sve_access_check(s)) { + TCGv_ptr status = fpstatus_ptr(FPST_FPCR); + unsigned vsz = vec_full_reg_size(s); + + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + status, vsz, vsz, (a->index << 1) | sel, + gen_helper_gvec_bfmlal_idx); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool trans_BFMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a) +{ + return do_BFMLAL_zzxw(s, a, false); +} + +static bool trans_BFMLALT_zzxw(DisasContext *s, arg_rrxr_esz *a) +{ + return do_BFMLAL_zzxw(s, a, true); +} diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index 3da84f30a0..d01e465821 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -543,11 +543,16 @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) /* VMOV scalar to general purpose register */ TCGv_i32 tmp; - /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ - if (a->size == MO_32 - ? !dc_isar_feature(aa32_fpsp_v2, s) - : !arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; + /* + * SIZE == MO_32 is a VFP instruction; otherwise NEON. MVE has + * all sizes, whether the CPU has fp or not. + */ + if (!dc_isar_feature(aa32_mve, s)) { + if (a->size == MO_32 + ? !dc_isar_feature(aa32_fpsp_v2, s) + : !arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } } /* UNDEF accesses to D16-D31 if they don't exist */ @@ -571,11 +576,16 @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) /* VMOV general purpose register to scalar */ TCGv_i32 tmp; - /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ - if (a->size == MO_32 - ? !dc_isar_feature(aa32_fpsp_v2, s) - : !arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; + /* + * SIZE == MO_32 is a VFP instruction; otherwise NEON. MVE has + * all sizes, whether the CPU has fp or not. + */ + if (!dc_isar_feature(aa32_mve, s)) { + if (a->size == MO_32 + ? !dc_isar_feature(aa32_fpsp_v2, s) + : !arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } } /* UNDEF accesses to D16-D31 if they don't exist */ @@ -671,7 +681,7 @@ typedef enum FPSysRegCheckResult { static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) { - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return FPSysRegCheckFailed; } @@ -681,16 +691,22 @@ static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) break; case ARM_VFP_FPSCR_NZCVQC: if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { - return false; + return FPSysRegCheckFailed; } break; case ARM_VFP_FPCXT_S: case ARM_VFP_FPCXT_NS: if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { - return false; + return FPSysRegCheckFailed; } if (!s->v8m_secure) { - return false; + return FPSysRegCheckFailed; + } + break; + case ARM_VFP_VPR: + case ARM_VFP_P0: + if (!dc_isar_feature(aa32_mve, s)) { + return FPSysRegCheckFailed; } break; default: @@ -807,6 +823,25 @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, tcg_temp_free_i32(sfpa); break; } + case ARM_VFP_VPR: + /* Behaves as NOP if not privileged */ + if (IS_USER(s)) { + break; + } + tmp = loadfn(s, opaque); + store_cpu_field(tmp, v7m.vpr); + break; + case ARM_VFP_P0: + { + TCGv_i32 vpr; + tmp = loadfn(s, opaque); + vpr = load_cpu_field(v7m.vpr); + tcg_gen_deposit_i32(vpr, vpr, tmp, + R_V7M_VPR_P0_SHIFT, R_V7M_VPR_P0_LENGTH); + store_cpu_field(vpr, v7m.vpr); + tcg_temp_free_i32(tmp); + break; + } default: g_assert_not_reached(); } @@ -925,6 +960,19 @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, tcg_temp_free_i32(fpscr); break; } + case ARM_VFP_VPR: + /* Behaves as NOP if not privileged */ + if (IS_USER(s)) { + break; + } + tmp = load_cpu_field(v7m.vpr); + storefn(s, opaque, tmp); + break; + case ARM_VFP_P0: + tmp = load_cpu_field(v7m.vpr); + tcg_gen_extract_i32(tmp, tmp, R_V7M_VPR_P0_SHIFT, R_V7M_VPR_P0_LENGTH); + storefn(s, opaque, tmp); + break; default: g_assert_not_reached(); } @@ -1254,7 +1302,7 @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) { TCGv_i32 tmp; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1287,7 +1335,7 @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a) { TCGv_i32 tmp; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1329,7 +1377,7 @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) * floating point register. Note that this does not require support * for double precision arithmetic. */ - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1368,7 +1416,7 @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) uint32_t offset; TCGv_i32 addr, tmp; - if (!dc_isar_feature(aa32_fp16_arith, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1403,7 +1451,7 @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) uint32_t offset; TCGv_i32 addr, tmp; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1439,7 +1487,7 @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) TCGv_i64 tmp; /* Note that this does not require support for double arithmetic. */ - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1479,7 +1527,7 @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) TCGv_i32 addr, tmp; int i, n; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1557,7 +1605,7 @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) int i, n; /* Note that this does not require support for double arithmetic. */ - if (!dc_isar_feature(aa32_fpsp_v2, s)) { + if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) { return false; } @@ -1915,9 +1963,7 @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) int veclen = s->vec_len; TCGv_i32 f0, fd; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { - return false; - } + /* Note that the caller must check the aa32_fpsp_v2 feature. */ if (!dc_isar_feature(aa32_fpshvec, s) && (veclen != 0 || s->vec_stride != 0)) { @@ -1992,6 +2038,8 @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) */ TCGv_i32 f0; + /* Note that the caller must check the aa32_fp16_arith feature */ + if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -2020,9 +2068,7 @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) int veclen = s->vec_len; TCGv_i64 f0, fd; - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } + /* Note that the caller must check the aa32_fpdp_v2 feature. */ /* UNDEF accesses to D16-D31 if they don't exist */ if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vm) & 0x10)) { @@ -2800,23 +2846,37 @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) return true; } -#define DO_VFP_2OP(INSN, PREC, FN) \ +#define DO_VFP_2OP(INSN, PREC, FN, CHECK) \ static bool trans_##INSN##_##PREC(DisasContext *s, \ arg_##INSN##_##PREC *a) \ { \ + if (!dc_isar_feature(CHECK, s)) { \ + return false; \ + } \ return do_vfp_2op_##PREC(s, FN, a->vd, a->vm); \ } -DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32) -DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64) +#define DO_VFP_VMOV(INSN, PREC, FN) \ + static bool trans_##INSN##_##PREC(DisasContext *s, \ + arg_##INSN##_##PREC *a) \ + { \ + if (!dc_isar_feature(aa32_fp##PREC##_v2, s) && \ + !dc_isar_feature(aa32_mve, s)) { \ + return false; \ + } \ + return do_vfp_2op_##PREC(s, FN, a->vd, a->vm); \ + } -DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh) -DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss) -DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd) +DO_VFP_VMOV(VMOV_reg, sp, tcg_gen_mov_i32) +DO_VFP_VMOV(VMOV_reg, dp, tcg_gen_mov_i64) -DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh) -DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs) -DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd) +DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh, aa32_fp16_arith) +DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss, aa32_fpsp_v2) +DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd, aa32_fpdp_v2) + +DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh, aa32_fp16_arith) +DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs, aa32_fpsp_v2) +DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd, aa32_fpdp_v2) static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) { @@ -2833,9 +2893,9 @@ static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) gen_helper_vfp_sqrtd(vd, vm, cpu_env); } -DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp) -DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) -DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) +DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp, aa32_fp16_arith) +DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp, aa32_fpsp_v2) +DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp, aa32_fpdp_v2) static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) { @@ -3025,6 +3085,30 @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) return true; } +static bool trans_VCVT_b16_f32(DisasContext *s, arg_VCVT_b16_f32 *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_bf16, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = fpstatus_ptr(FPST_FPCR); + tmp = tcg_temp_new_i32(); + + vfp_load_reg32(tmp, a->vm); + gen_helper_bfcvt(tmp, tmp, fpst); + tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a) { TCGv_ptr fpst; diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index e84b438340..5862f187cd 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -2385,7 +2385,7 @@ static void do_mmla_b(void *vd, void *vn, void *vm, void *va, uint32_t desc, * Process the entire segment at once, writing back the * results only after we've consumed all of the inputs. * - * Key to indicies by column: + * Key to indices by column: * i j i j */ sum0 = a[H4(0 + 0)]; @@ -2412,3 +2412,141 @@ static void do_mmla_b(void *vd, void *vn, void *vm, void *va, uint32_t desc, DO_MMLA_B(gvec_smmla_b, do_smmla_b) DO_MMLA_B(gvec_ummla_b, do_ummla_b) DO_MMLA_B(gvec_usmmla_b, do_usmmla_b) + +/* + * BFloat16 Dot Product + */ + +static float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2) +{ + /* FPCR is ignored for BFDOT and BFMMLA. */ + float_status bf_status = { + .tininess_before_rounding = float_tininess_before_rounding, + .float_rounding_mode = float_round_to_odd_inf, + .flush_to_zero = true, + .flush_inputs_to_zero = true, + .default_nan_mode = true, + }; + float32 t1, t2; + + /* + * Extract each BFloat16 from the element pair, and shift + * them such that they become float32. + */ + t1 = float32_mul(e1 << 16, e2 << 16, &bf_status); + t2 = float32_mul(e1 & 0xffff0000u, e2 & 0xffff0000u, &bf_status); + t1 = float32_add(t1, t2, &bf_status); + t1 = float32_add(sum, t1, &bf_status); + + return t1; +} + +void HELPER(gvec_bfdot)(void *vd, void *vn, void *vm, void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = bfdotadd(a[i], n[i], m[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + intptr_t index = simd_data(desc); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = vm; + + for (i = 0; i < elements; i += eltspersegment) { + uint32_t m_idx = m[i + H4(index)]; + + for (j = i; j < i + eltspersegment; j++) { + d[j] = bfdotadd(a[j], n[j], m_idx); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, uint32_t desc) +{ + intptr_t s, opr_sz = simd_oprsz(desc); + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = vm; + + for (s = 0; s < opr_sz / 4; s += 4) { + float32 sum00, sum01, sum10, sum11; + + /* + * Process the entire segment at once, writing back the + * results only after we've consumed all of the inputs. + * + * Key to indicies by column: + * i j i k j k + */ + sum00 = a[s + H4(0 + 0)]; + sum00 = bfdotadd(sum00, n[s + H4(0 + 0)], m[s + H4(0 + 0)]); + sum00 = bfdotadd(sum00, n[s + H4(0 + 1)], m[s + H4(0 + 1)]); + + sum01 = a[s + H4(0 + 1)]; + sum01 = bfdotadd(sum01, n[s + H4(0 + 0)], m[s + H4(2 + 0)]); + sum01 = bfdotadd(sum01, n[s + H4(0 + 1)], m[s + H4(2 + 1)]); + + sum10 = a[s + H4(2 + 0)]; + sum10 = bfdotadd(sum10, n[s + H4(2 + 0)], m[s + H4(0 + 0)]); + sum10 = bfdotadd(sum10, n[s + H4(2 + 1)], m[s + H4(0 + 1)]); + + sum11 = a[s + H4(2 + 1)]; + sum11 = bfdotadd(sum11, n[s + H4(2 + 0)], m[s + H4(2 + 0)]); + sum11 = bfdotadd(sum11, n[s + H4(2 + 1)], m[s + H4(2 + 1)]); + + d[s + H4(0 + 0)] = sum00; + d[s + H4(0 + 1)] = sum01; + d[s + H4(2 + 0)] = sum10; + d[s + H4(2 + 1)] = sum11; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, + void *stat, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + intptr_t sel = simd_data(desc); + float32 *d = vd, *a = va; + bfloat16 *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + float32 nn = n[H2(i * 2 + sel)] << 16; + float32 mm = m[H2(i * 2 + sel)] << 16; + d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, + void *va, void *stat, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1); + intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 1, 3); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); + float32 *d = vd, *a = va; + bfloat16 *n = vn, *m = vm; + + for (i = 0; i < elements; i += eltspersegment) { + float32 m_idx = m[H2(2 * i + index)] << 16; + + for (j = i; j < i + eltspersegment; j++) { + float32 n_j = n[H2(2 * j + sel)] << 16; + d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], 0, stat); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index 6f7f28f9a4..52535d9b0b 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -205,6 +205,8 @@ VCVT_f64_f16 ---- 1110 1.11 0010 .... 1011 t:1 1.0 .... \ # VCVTB and VCVTT to f16: Vd format is always vd_sp; # Vm format depends on size bit +VCVT_b16_f32 ---- 1110 1.11 0011 .... 1001 t:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCVT_f16_f32 ---- 1110 1.11 0011 .... 1010 t:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \ diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index 01b9d8557f..496f003477 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -195,8 +195,10 @@ uint32_t vfp_get_fpscr(CPUARMState *env) void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) { + ARMCPU *cpu = env_archcpu(env); + /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ - if (!cpu_isar_feature(any_fp16, env_archcpu(env))) { + if (!cpu_isar_feature(any_fp16, cpu)) { val &= ~FPCR_FZ16; } @@ -210,11 +212,12 @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) * because in v7A no-short-vector-support cores still had to * allow Stride/Len to be written with the only effect that * some insns are required to UNDEF if the guest sets them. - * - * TODO: if M-profile MVE implemented, set LTPSIZE. */ env->vfp.vec_len = extract32(val, 16, 3); env->vfp.vec_stride = extract32(val, 20, 2); + } else if (cpu_isar_feature(aa32_mve, cpu)) { + env->v7m.ltpsize = extract32(val, FPCR_LTPSIZE_SHIFT, + FPCR_LTPSIZE_LENGTH); } if (arm_feature(env, ARM_FEATURE_NEON)) { @@ -408,6 +411,18 @@ float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) return float64_to_float32(x, &env->vfp.fp_status); } +uint32_t HELPER(bfcvt)(float32 x, void *status) +{ + return float32_to_bfloat16(x, status); +} + +uint32_t HELPER(bfcvt_pair)(uint64_t pair, void *status) +{ + bfloat16 lo = float32_to_bfloat16(extract64(pair, 0, 32), status); + bfloat16 hi = float32_to_bfloat16(extract64(pair, 32, 32), status); + return deposit32(lo, 16, 16, hi); +} + /* * VFP3 fixed point conversion. The AArch32 versions of fix-to-float * must always round-to-nearest; the AArch64 ones honour the FPSCR diff --git a/target/avr/cpu.c b/target/avr/cpu.c index 0f4596932b..57e3fab4a0 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -184,9 +184,15 @@ static void avr_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, "\n"); } +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps avr_sysemu_ops = { + .get_phys_page_debug = avr_cpu_get_phys_page_debug, +}; + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps avr_tcg_ops = { +static const struct TCGCPUOps avr_tcg_ops = { .initialize = avr_cpu_tcg_init, .synchronize_from_tb = avr_cpu_synchronize_from_tb, .cpu_exec_interrupt = avr_cpu_exec_interrupt, @@ -212,8 +218,8 @@ static void avr_cpu_class_init(ObjectClass *oc, void *data) cc->dump_state = avr_cpu_dump_state; cc->set_pc = avr_cpu_set_pc; cc->memory_rw_debug = avr_cpu_memory_rw_debug; - cc->get_phys_page_debug = avr_cpu_get_phys_page_debug; - cc->vmsd = &vms_avr_cpu; + dc->vmsd = &vms_avr_cpu; + cc->sysemu_ops = &avr_sysemu_ops; cc->disas_set_info = avr_cpu_disas_set_info; cc->gdb_read_register = avr_cpu_gdb_read_register; cc->gdb_write_register = avr_cpu_gdb_write_register; diff --git a/target/avr/machine.c b/target/avr/machine.c index de264f57c3..16f7a3e031 100644 --- a/target/avr/machine.c +++ b/target/avr/machine.c @@ -98,8 +98,8 @@ static const VMStateInfo vms_eind = { const VMStateDescription vms_avr_cpu = { .name = "cpu", - .version_id = 0, - .minimum_version_id = 0, + .version_id = 1, + .minimum_version_id = 1, .fields = (VMStateField[]) { VMSTATE_UINT32(env.pc_w, AVRCPU), VMSTATE_UINT32(env.sp, AVRCPU), diff --git a/target/cris/cpu.c b/target/cris/cpu.c index ed983380fc..70932b1f8c 100644 --- a/target/cris/cpu.c +++ b/target/cris/cpu.c @@ -193,9 +193,17 @@ static void cris_cpu_initfn(Object *obj) #endif } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps cris_sysemu_ops = { + .get_phys_page_debug = cris_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps crisv10_tcg_ops = { +static const struct TCGCPUOps crisv10_tcg_ops = { .initialize = cris_initialize_crisv10_tcg, .cpu_exec_interrupt = cris_cpu_exec_interrupt, .tlb_fill = cris_cpu_tlb_fill, @@ -205,7 +213,7 @@ static struct TCGCPUOps crisv10_tcg_ops = { #endif /* !CONFIG_USER_ONLY */ }; -static struct TCGCPUOps crisv32_tcg_ops = { +static const struct TCGCPUOps crisv32_tcg_ops = { .initialize = cris_initialize_tcg, .cpu_exec_interrupt = cris_cpu_exec_interrupt, .tlb_fill = cris_cpu_tlb_fill, @@ -292,8 +300,8 @@ static void cris_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = cris_cpu_gdb_read_register; cc->gdb_write_register = cris_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = cris_cpu_get_phys_page_debug; dc->vmsd = &vmstate_cris_cpu; + cc->sysemu_ops = &cris_sysemu_ops; #endif cc->gdb_num_core_regs = 49; diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index ebe60a6e15..3338365c16 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -269,7 +269,7 @@ static bool hexagon_tlb_fill(CPUState *cs, vaddr address, int size, #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps hexagon_tcg_ops = { +static const struct TCGCPUOps hexagon_tcg_ops = { .initialize = hexagon_translate_init, .synchronize_from_tb = hexagon_cpu_synchronize_from_tb, .tlb_fill = hexagon_tlb_fill, diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index d8fad52d1f..2eace4ee12 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -131,9 +131,17 @@ static ObjectClass *hppa_cpu_class_by_name(const char *cpu_model) return object_class_by_name(TYPE_HPPA_CPU); } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps hppa_sysemu_ops = { + .get_phys_page_debug = hppa_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps hppa_tcg_ops = { +static const struct TCGCPUOps hppa_tcg_ops = { .initialize = hppa_translate_init, .synchronize_from_tb = hppa_cpu_synchronize_from_tb, .cpu_exec_interrupt = hppa_cpu_exec_interrupt, @@ -161,8 +169,8 @@ static void hppa_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = hppa_cpu_gdb_read_register; cc->gdb_write_register = hppa_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = hppa_cpu_get_phys_page_debug; dc->vmsd = &vmstate_hppa_cpu; + cc->sysemu_ops = &hppa_sysemu_ops; #endif cc->disas_set_info = hppa_cpu_disas_set_info; cc->gdb_num_core_regs = 128; diff --git a/target/hppa/trace-events b/target/hppa/trace-events index 0731ce7ce1..8931517890 100644 --- a/target/hppa/trace-events +++ b/target/hppa/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # mem_helper.c disable hppa_tlb_flush_ent(void *env, void *ent, uint64_t va_b, uint64_t va_e, uint64_t pa) "env=%p ent=%p va_b=0x%lx va_e=0x%lx pa=0x%lx" diff --git a/target/i386/cpu-dump.c b/target/i386/cpu-dump.c index aac21f1f60..02b635a52c 100644 --- a/target/i386/cpu-dump.c +++ b/target/i386/cpu-dump.c @@ -478,6 +478,11 @@ void x86_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, "EFER=%016" PRIx64 "\n", env->efer); if (flags & CPU_DUMP_FPU) { int fptag; + const uint64_t avx512_mask = XSTATE_OPMASK_MASK | \ + XSTATE_ZMM_Hi256_MASK | \ + XSTATE_Hi16_ZMM_MASK | \ + XSTATE_YMM_MASK | XSTATE_SSE_MASK, + avx_mask = XSTATE_YMM_MASK | XSTATE_SSE_MASK; fptag = 0; for(i = 0; i < 8; i++) { fptag |= ((!env->fptags[i]) << i); @@ -499,21 +504,49 @@ void x86_cpu_dump_state(CPUState *cs, FILE *f, int flags) else qemu_fprintf(f, " "); } - if (env->hflags & HF_CS64_MASK) - nb = 16; - else - nb = 8; - for(i=0;i<nb;i++) { - qemu_fprintf(f, "XMM%02d=%08x%08x%08x%08x", - i, - env->xmm_regs[i].ZMM_L(3), - env->xmm_regs[i].ZMM_L(2), - env->xmm_regs[i].ZMM_L(1), - env->xmm_regs[i].ZMM_L(0)); - if ((i & 1) == 1) - qemu_fprintf(f, "\n"); - else - qemu_fprintf(f, " "); + + if ((env->xcr0 & avx512_mask) == avx512_mask) { + /* XSAVE enabled AVX512 */ + for (i = 0; i < NB_OPMASK_REGS; i++) { + qemu_fprintf(f, "Opmask%02d=%016"PRIx64"%s", i, + env->opmask_regs[i], ((i & 3) == 3) ? "\n" : " "); + } + + nb = (env->hflags & HF_CS64_MASK) ? 32 : 8; + for (i = 0; i < nb; i++) { + qemu_fprintf(f, "ZMM%02d=%016"PRIx64" %016"PRIx64" %016"PRIx64 + " %016"PRIx64" %016"PRIx64" %016"PRIx64 + " %016"PRIx64" %016"PRIx64"\n", + i, + env->xmm_regs[i].ZMM_Q(7), + env->xmm_regs[i].ZMM_Q(6), + env->xmm_regs[i].ZMM_Q(5), + env->xmm_regs[i].ZMM_Q(4), + env->xmm_regs[i].ZMM_Q(3), + env->xmm_regs[i].ZMM_Q(2), + env->xmm_regs[i].ZMM_Q(1), + env->xmm_regs[i].ZMM_Q(0)); + } + } else if ((env->xcr0 & avx_mask) == avx_mask) { + /* XSAVE enabled AVX */ + nb = env->hflags & HF_CS64_MASK ? 16 : 8; + for (i = 0; i < nb; i++) { + qemu_fprintf(f, "YMM%02d=%016"PRIx64" %016"PRIx64" %016"PRIx64 + " %016"PRIx64"\n", i, + env->xmm_regs[i].ZMM_Q(3), + env->xmm_regs[i].ZMM_Q(2), + env->xmm_regs[i].ZMM_Q(1), + env->xmm_regs[i].ZMM_Q(0)); + } + } else { /* SSE and below cases */ + nb = env->hflags & HF_CS64_MASK ? 16 : 8; + for (i = 0; i < nb; i++) { + qemu_fprintf(f, "XMM%02d=%016"PRIx64" %016"PRIx64"%s", + i, + env->xmm_regs[i].ZMM_Q(1), + env->xmm_regs[i].ZMM_Q(0), + (i & 1) ? "\n" : " "); + } } } if (flags & CPU_DUMP_CODE) { diff --git a/target/i386/cpu-sysemu.c b/target/i386/cpu-sysemu.c index 6477584313..1078e3d157 100644 --- a/target/i386/cpu-sysemu.c +++ b/target/i386/cpu-sysemu.c @@ -312,7 +312,7 @@ GuestPanicInformation *x86_cpu_get_crash_info(CPUState *cs) CPUX86State *env = &cpu->env; GuestPanicInformation *panic_info = NULL; - if (env->features[FEAT_HYPERV_EDX] & HV_GUEST_CRASH_MSR_AVAILABLE) { + if (hyperv_feat_enabled(cpu, HYPERV_FEAT_CRASH)) { panic_info = g_malloc0(sizeof(GuestPanicInformation)); panic_info->type = GUEST_PANIC_INFORMATION_TYPE_HYPER_V; diff --git a/target/i386/cpu.c b/target/i386/cpu.c index c496bfa1c2..e0ba36cc23 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -776,94 +776,6 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { */ .no_autoenable_flags = ~0U, }, - /* - * .feat_names are commented out for Hyper-V enlightenments because we - * don't want to have two different ways for enabling them on QEMU command - * line. Some features (e.g. "hyperv_time", "hyperv_vapic", ...) require - * enabling several feature bits simultaneously, exposing these bits - * individually may just confuse guests. - */ - [FEAT_HYPERV_EAX] = { - .type = CPUID_FEATURE_WORD, - .feat_names = { - NULL /* hv_msr_vp_runtime_access */, NULL /* hv_msr_time_refcount_access */, - NULL /* hv_msr_synic_access */, NULL /* hv_msr_stimer_access */, - NULL /* hv_msr_apic_access */, NULL /* hv_msr_hypercall_access */, - NULL /* hv_vpindex_access */, NULL /* hv_msr_reset_access */, - NULL /* hv_msr_stats_access */, NULL /* hv_reftsc_access */, - NULL /* hv_msr_idle_access */, NULL /* hv_msr_frequency_access */, - NULL /* hv_msr_debug_access */, NULL /* hv_msr_reenlightenment_access */, - NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - }, - .cpuid = { .eax = 0x40000003, .reg = R_EAX, }, - }, - [FEAT_HYPERV_EBX] = { - .type = CPUID_FEATURE_WORD, - .feat_names = { - NULL /* hv_create_partitions */, NULL /* hv_access_partition_id */, - NULL /* hv_access_memory_pool */, NULL /* hv_adjust_message_buffers */, - NULL /* hv_post_messages */, NULL /* hv_signal_events */, - NULL /* hv_create_port */, NULL /* hv_connect_port */, - NULL /* hv_access_stats */, NULL, NULL, NULL /* hv_debugging */, - NULL /* hv_cpu_power_management */, NULL /* hv_configure_profiler */, - NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - }, - .cpuid = { .eax = 0x40000003, .reg = R_EBX, }, - }, - [FEAT_HYPERV_EDX] = { - .type = CPUID_FEATURE_WORD, - .feat_names = { - NULL /* hv_mwait */, NULL /* hv_guest_debugging */, - NULL /* hv_perf_monitor */, NULL /* hv_cpu_dynamic_part */, - NULL /* hv_hypercall_params_xmm */, NULL /* hv_guest_idle_state */, - NULL, NULL, - NULL, NULL, NULL /* hv_guest_crash_msr */, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - }, - .cpuid = { .eax = 0x40000003, .reg = R_EDX, }, - }, - [FEAT_HV_RECOMM_EAX] = { - .type = CPUID_FEATURE_WORD, - .feat_names = { - NULL /* hv_recommend_pv_as_switch */, - NULL /* hv_recommend_pv_tlbflush_local */, - NULL /* hv_recommend_pv_tlbflush_remote */, - NULL /* hv_recommend_msr_apic_access */, - NULL /* hv_recommend_msr_reset */, - NULL /* hv_recommend_relaxed_timing */, - NULL /* hv_recommend_dma_remapping */, - NULL /* hv_recommend_int_remapping */, - NULL /* hv_recommend_x2apic_msrs */, - NULL /* hv_recommend_autoeoi_deprecation */, - NULL /* hv_recommend_pv_ipi */, - NULL /* hv_recommend_ex_hypercalls */, - NULL /* hv_hypervisor_is_nested */, - NULL /* hv_recommend_int_mbec */, - NULL /* hv_recommend_evmcs */, - NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, - }, - .cpuid = { .eax = 0x40000004, .reg = R_EAX, }, - }, - [FEAT_HV_NESTED_EAX] = { - .type = CPUID_FEATURE_WORD, - .cpuid = { .eax = 0x4000000A, .reg = R_EAX, }, - }, [FEAT_SVM] = { .type = CPUID_FEATURE_WORD, .feat_names = { @@ -940,7 +852,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .type = CPUID_FEATURE_WORD, .feat_names = { NULL, NULL, NULL, NULL, - NULL, "avx512-bf16", NULL, NULL, + "avx-vnni", "avx512-bf16", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -1576,7 +1488,7 @@ typedef struct X86CPUDefinition { int stepping; FeatureWordArray features; const char *model_id; - CPUCaches *cache_info; + const CPUCaches *const cache_info; /* * Definitions for alternative versions of CPU model. * List is terminated by item with version == 0. @@ -1589,7 +1501,7 @@ typedef struct X86CPUDefinition { /* Reference to a specific CPU model version */ struct X86CPUModel { /* Base CPU definition */ - X86CPUDefinition *cpudef; + const X86CPUDefinition *cpudef; /* CPU model version */ X86CPUVersion version; const char *note; @@ -1601,14 +1513,15 @@ struct X86CPUModel { }; /* Get full model name for CPU version */ -static char *x86_cpu_versioned_model_name(X86CPUDefinition *cpudef, +static char *x86_cpu_versioned_model_name(const X86CPUDefinition *cpudef, X86CPUVersion version) { assert(version > 0); return g_strdup_printf("%s-v%d", cpudef->name, (int)version); } -static const X86CPUVersionDefinition *x86_cpu_def_get_versions(X86CPUDefinition *def) +static const X86CPUVersionDefinition * +x86_cpu_def_get_versions(const X86CPUDefinition *def) { /* When X86CPUDefinition::versions is NULL, we register only v1 */ static const X86CPUVersionDefinition default_version_list[] = { @@ -1619,7 +1532,7 @@ static const X86CPUVersionDefinition *x86_cpu_def_get_versions(X86CPUDefinition return def->versions ?: default_version_list; } -static CPUCaches epyc_cache_info = { +static const CPUCaches epyc_cache_info = { .l1d_cache = &(CPUCacheInfo) { .type = DATA_CACHE, .level = 1, @@ -1669,7 +1582,7 @@ static CPUCaches epyc_cache_info = { }, }; -static CPUCaches epyc_rome_cache_info = { +static const CPUCaches epyc_rome_cache_info = { .l1d_cache = &(CPUCacheInfo) { .type = DATA_CACHE, .level = 1, @@ -1719,7 +1632,7 @@ static CPUCaches epyc_rome_cache_info = { }, }; -static CPUCaches epyc_milan_cache_info = { +static const CPUCaches epyc_milan_cache_info = { .l1d_cache = &(CPUCacheInfo) { .type = DATA_CACHE, .level = 1, @@ -1797,14 +1710,14 @@ static CPUCaches epyc_milan_cache_info = { * PT in VMX operation */ -static X86CPUDefinition builtin_x86_defs[] = { +static const X86CPUDefinition builtin_x86_defs[] = { { .name = "qemu64", .level = 0xd, .vendor = CPUID_VENDOR_AMD, - .family = 6, - .model = 6, - .stepping = 3, + .family = 15, + .model = 107, + .stepping = 1, .features[FEAT_1_EDX] = PPRO_FEATURES | CPUID_MTRR | CPUID_CLFLUSH | CPUID_MCA | @@ -2802,12 +2715,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_ERMS | CPUID_7_0_EBX_INVPCID | CPUID_7_0_EBX_RTM | CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX | CPUID_7_0_EBX_SMAP, - /* Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is added in version 4 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -2883,6 +2791,15 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ } } }, + { + .version = 4, + .note = "IBRS, XSAVES, no TSX", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ } + } + }, { /* end of list */ } } }, @@ -2922,12 +2839,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_EBX_AVX512VL | CPUID_7_0_EBX_CLFLUSHOPT, .features[FEAT_7_0_ECX] = CPUID_7_0_ECX_PKU, - /* Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is added in version 5 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -3015,6 +2927,15 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ } } }, + { + .version = 5, + .note = "IBRS, XSAVES, EPT switching, no TSX", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ } + } + }, { /* end of list */ } } }, @@ -3057,12 +2978,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_ECX_AVX512VNNI, .features[FEAT_7_0_EDX] = CPUID_7_0_EDX_SPEC_CTRL | CPUID_7_0_EDX_SPEC_CTRL_SSBD, - /* Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is added in version 5 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -3146,6 +3062,14 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ } }, }, + { .version = 5, + .note = "ARCH_CAPABILITIES, EPT switching, XSAVES, no TSX", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ } + }, + }, { /* end of list */ } } }, @@ -3194,14 +3118,8 @@ static X86CPUDefinition builtin_x86_defs[] = { MSR_ARCH_CAP_SKIP_L1DFL_VMENTRY | MSR_ARCH_CAP_MDS_NO | MSR_ARCH_CAP_PSCHANGE_MC_NO | MSR_ARCH_CAP_TAA_NO, .features[FEAT_7_1_EAX] = - CPUID_7_1_EAX_AVX512_BF16, - /* - * Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + CPUID_7_1_EAX_AVX_VNNI | CPUID_7_1_EAX_AVX512_BF16, + /* XSAVES is added in version 2 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -3257,6 +3175,18 @@ static X86CPUDefinition builtin_x86_defs[] = { .features[FEAT_VMX_VMFUNC] = MSR_VMX_VMFUNC_EPT_SWITCHING, .xlevel = 0x80000008, .model_id = "Intel Xeon Processor (Cooperlake)", + .versions = (X86CPUVersionDefinition[]) { + { .version = 1 }, + { .version = 2, + .note = "XSAVES", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ } + }, + }, + { /* end of list */ } + } }, { .name = "Icelake-Client", @@ -3299,12 +3229,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_ECX_AVX512_VPOPCNTDQ, .features[FEAT_7_0_EDX] = CPUID_7_0_EDX_SPEC_CTRL | CPUID_7_0_EDX_SPEC_CTRL_SSBD, - /* Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is added in version 3 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -3372,6 +3297,15 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ } }, }, + { + .version = 3, + .note = "no TSX, XSAVES, deprecated", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ } + }, + }, { /* end of list */ } }, .deprecation_note = "use Icelake-Server instead" @@ -3420,12 +3354,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_ECX_AVX512_VPOPCNTDQ | CPUID_7_0_ECX_LA57, .features[FEAT_7_0_EDX] = CPUID_7_0_EDX_SPEC_CTRL | CPUID_7_0_EDX_SPEC_CTRL_SSBD, - /* Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is added in version 5 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -3518,6 +3447,15 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ } }, }, + { + .version = 5, + .note = "XSAVES", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ } + }, + }, { /* end of list */ } } }, @@ -3552,13 +3490,7 @@ static X86CPUDefinition builtin_x86_defs[] = { .features[FEAT_7_0_EDX] = CPUID_7_0_EDX_SPEC_CTRL | CPUID_7_0_EDX_ARCH_CAPABILITIES | CPUID_7_0_EDX_SPEC_CTRL_SSBD, - /* - * Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is added in version 3 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, .features[FEAT_6_EAX] = @@ -3625,6 +3557,15 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ }, }, }, + { + .version = 3, + .note = "XSAVES, no MPX, no MONITOR", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ }, + }, + }, { /* end of list */ }, }, }, @@ -3683,13 +3624,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_EDX_CORE_CAPABILITY, .features[FEAT_CORE_CAPABILITY] = MSR_CORE_CAP_SPLIT_LOCK_DETECT, - /* - * Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component, - * and the only one defined in Skylake (processor tracing) - * probably will block migration anyway. - */ + /* XSAVES is is added in version 3 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -3754,6 +3689,15 @@ static X86CPUDefinition builtin_x86_defs[] = { { /* end of list */ }, }, }, + { + .version = 3, + .note = "XSAVES, no MPX", + .props = (PropValue[]) { + { "xsaves", "on" }, + { "vmx-xsaves", "on" }, + { /* end of list */ }, + }, + }, { /* end of list */ }, }, }, @@ -4035,11 +3979,7 @@ static X86CPUDefinition builtin_x86_defs[] = { CPUID_7_0_EBX_FSGSBASE | CPUID_7_0_EBX_BMI1 | CPUID_7_0_EBX_AVX2 | CPUID_7_0_EBX_SMEP | CPUID_7_0_EBX_BMI2 | CPUID_7_0_EBX_RDSEED | CPUID_7_0_EBX_ADX | CPUID_7_0_EBX_SMAP | CPUID_7_0_EBX_CLFLUSHOPT, - /* - * Missing: XSAVES (not supported by some Linux versions, - * including v4.1 to v4.12). - * KVM doesn't yet expose any XSAVES state save component. - */ + /* XSAVES is added in version 2 */ .features[FEAT_XSAVE] = CPUID_XSAVE_XSAVEOPT | CPUID_XSAVE_XSAVEC | CPUID_XSAVE_XGETBV1, @@ -4050,6 +3990,17 @@ static X86CPUDefinition builtin_x86_defs[] = { .xlevel = 0x8000001E, .model_id = "Hygon Dhyana Processor", .cache_info = &epyc_cache_info, + .versions = (X86CPUVersionDefinition[]) { + { .version = 1 }, + { .version = 2, + .note = "XSAVES", + .props = (PropValue[]) { + { "xsaves", "on" }, + { /* end of list */ } + }, + }, + { /* end of list */ } + } }, { .name = "EPYC-Rome", @@ -4246,9 +4197,15 @@ static void max_x86_cpu_initfn(Object *obj) */ object_property_set_str(OBJECT(cpu), "vendor", CPUID_VENDOR_AMD, &error_abort); +#ifdef TARGET_X86_64 + object_property_set_int(OBJECT(cpu), "family", 15, &error_abort); + object_property_set_int(OBJECT(cpu), "model", 107, &error_abort); + object_property_set_int(OBJECT(cpu), "stepping", 1, &error_abort); +#else object_property_set_int(OBJECT(cpu), "family", 6, &error_abort); object_property_set_int(OBJECT(cpu), "model", 6, &error_abort); object_property_set_int(OBJECT(cpu), "stepping", 3, &error_abort); +#endif object_property_set_str(OBJECT(cpu), "model-id", "QEMU TCG CPU version " QEMU_HW_VERSION, &error_abort); @@ -5023,7 +4980,7 @@ static void x86_cpu_apply_version_props(X86CPU *cpu, X86CPUModel *model) */ static void x86_cpu_load_model(X86CPU *cpu, X86CPUModel *model) { - X86CPUDefinition *def = model->cpudef; + const X86CPUDefinition *def = model->cpudef; CPUX86State *env = &cpu->env; FeatureWord w; @@ -5110,7 +5067,7 @@ static void x86_register_cpu_model_type(const char *name, X86CPUModel *model) type_register(&ti); } -static void x86_register_cpudef_types(X86CPUDefinition *def) +static void x86_register_cpudef_types(const X86CPUDefinition *def) { X86CPUModel *m; const X86CPUVersionDefinition *vdef; @@ -6096,17 +6053,16 @@ static void x86_cpu_hyperv_realize(X86CPU *cpu) /* Hyper-V vendor id */ if (!cpu->hyperv_vendor) { - memcpy(cpu->hyperv_vendor_id, "Microsoft Hv", 12); - } else { - len = strlen(cpu->hyperv_vendor); - - if (len > 12) { - warn_report("hv-vendor-id truncated to 12 characters"); - len = 12; - } - memset(cpu->hyperv_vendor_id, 0, 12); - memcpy(cpu->hyperv_vendor_id, cpu->hyperv_vendor, len); + object_property_set_str(OBJECT(cpu), "hv-vendor-id", "Microsoft Hv", + &error_abort); + } + len = strlen(cpu->hyperv_vendor); + if (len > 12) { + warn_report("hv-vendor-id truncated to 12 characters"); + len = 12; } + memset(cpu->hyperv_vendor_id, 0, 12); + memcpy(cpu->hyperv_vendor_id, cpu->hyperv_vendor, len); /* 'Hv#1' interface identification*/ cpu->hyperv_interface_id[0] = 0x31237648; @@ -6485,12 +6441,14 @@ static int64_t x86_cpu_get_arch_id(CPUState *cs) return cpu->apic_id; } +#if !defined(CONFIG_USER_ONLY) static bool x86_cpu_get_paging_enabled(const CPUState *cs) { X86CPU *cpu = X86_CPU(cs); return cpu->env.cr[0] & CR0_PG_MASK; } +#endif /* !CONFIG_USER_ONLY */ static void x86_cpu_set_pc(CPUState *cs, vaddr value) { @@ -6714,6 +6672,23 @@ static Property x86_cpu_properties[] = { DEFINE_PROP_END_OF_LIST() }; +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps i386_sysemu_ops = { + .get_memory_mapping = x86_cpu_get_memory_mapping, + .get_paging_enabled = x86_cpu_get_paging_enabled, + .get_phys_page_attrs_debug = x86_cpu_get_phys_page_attrs_debug, + .asidx_from_attrs = x86_asidx_from_attrs, + .get_crash_info = x86_cpu_get_crash_info, + .write_elf32_note = x86_cpu_write_elf32_note, + .write_elf64_note = x86_cpu_write_elf64_note, + .write_elf32_qemunote = x86_cpu_write_elf32_qemunote, + .write_elf64_qemunote = x86_cpu_write_elf64_qemunote, + .legacy_vmsd = &vmstate_x86_cpu, +}; +#endif + static void x86_cpu_common_class_init(ObjectClass *oc, void *data) { X86CPUClass *xcc = X86_CPU_CLASS(oc); @@ -6738,18 +6713,9 @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = x86_cpu_gdb_read_register; cc->gdb_write_register = x86_cpu_gdb_write_register; cc->get_arch_id = x86_cpu_get_arch_id; - cc->get_paging_enabled = x86_cpu_get_paging_enabled; #ifndef CONFIG_USER_ONLY - cc->asidx_from_attrs = x86_asidx_from_attrs; - cc->get_memory_mapping = x86_cpu_get_memory_mapping; - cc->get_phys_page_attrs_debug = x86_cpu_get_phys_page_attrs_debug; - cc->get_crash_info = x86_cpu_get_crash_info; - cc->write_elf64_note = x86_cpu_write_elf64_note; - cc->write_elf64_qemunote = x86_cpu_write_elf64_qemunote; - cc->write_elf32_note = x86_cpu_write_elf32_note; - cc->write_elf32_qemunote = x86_cpu_write_elf32_qemunote; - cc->vmsd = &vmstate_x86_cpu; + cc->sysemu_ops = &i386_sysemu_ops; #endif /* !CONFIG_USER_ONLY */ cc->gdb_arch_name = x86_gdb_arch_name; diff --git a/target/i386/cpu.h b/target/i386/cpu.h index e6836393f7..ac3abea97c 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -531,11 +531,6 @@ typedef enum FeatureWord { FEAT_C000_0001_EDX, /* CPUID[C000_0001].EDX */ FEAT_KVM, /* CPUID[4000_0001].EAX (KVM_CPUID_FEATURES) */ FEAT_KVM_HINTS, /* CPUID[4000_0001].EDX */ - FEAT_HYPERV_EAX, /* CPUID[4000_0003].EAX */ - FEAT_HYPERV_EBX, /* CPUID[4000_0003].EBX */ - FEAT_HYPERV_EDX, /* CPUID[4000_0003].EDX */ - FEAT_HV_RECOMM_EAX, /* CPUID[4000_0004].EAX */ - FEAT_HV_NESTED_EAX, /* CPUID[4000_000A].EAX */ FEAT_SVM, /* CPUID[8000_000A].EDX */ FEAT_XSAVE, /* CPUID[EAX=0xd,ECX=1].EAX */ FEAT_6_EAX, /* CPUID[6].EAX */ @@ -817,6 +812,8 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS]; /* Speculative Store Bypass Disable */ #define CPUID_7_0_EDX_SPEC_CTRL_SSBD (1U << 31) +/* AVX VNNI Instruction */ +#define CPUID_7_1_EAX_AVX_VNNI (1U << 4) /* AVX512 BFloat16 Instruction */ #define CPUID_7_1_EAX_AVX512_BF16 (1U << 5) @@ -1697,6 +1694,7 @@ struct X86CPU { uint32_t hyperv_interface_id[4]; uint32_t hyperv_version_id[4]; uint32_t hyperv_limits[3]; + uint32_t hyperv_nested[4]; bool check_cpuid; bool enforce_cpuid; diff --git a/target/i386/hvf/hvf-accel-ops.c b/target/i386/hvf/hvf-accel-ops.c deleted file mode 100644 index cbaad238e0..0000000000 --- a/target/i386/hvf/hvf-accel-ops.c +++ /dev/null @@ -1,146 +0,0 @@ -/* - * Copyright 2008 IBM Corporation - * 2008 Red Hat, Inc. - * Copyright 2011 Intel Corporation - * Copyright 2016 Veertu, Inc. - * Copyright 2017 The Android Open Source Project - * - * QEMU Hypervisor.framework support - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - * - * This file contain code under public domain from the hvdos project: - * https://github.com/mist64/hvdos - * - * Parts Copyright (c) 2011 NetApp, Inc. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * - * THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``AS IS'' AND - * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL NETAPP, INC OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL - * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS - * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - */ - -#include "qemu/osdep.h" -#include "qemu/error-report.h" -#include "qemu/main-loop.h" -#include "sysemu/hvf.h" -#include "sysemu/runstate.h" -#include "target/i386/cpu.h" -#include "qemu/guest-random.h" - -#include "hvf-accel-ops.h" - -/* - * The HVF-specific vCPU thread function. This one should only run when the host - * CPU supports the VMX "unrestricted guest" feature. - */ -static void *hvf_cpu_thread_fn(void *arg) -{ - CPUState *cpu = arg; - - int r; - - assert(hvf_enabled()); - - rcu_register_thread(); - - qemu_mutex_lock_iothread(); - qemu_thread_get_self(cpu->thread); - - cpu->thread_id = qemu_get_thread_id(); - cpu->can_do_io = 1; - current_cpu = cpu; - - hvf_init_vcpu(cpu); - - /* signal CPU creation */ - cpu_thread_signal_created(cpu); - qemu_guest_random_seed_thread_part2(cpu->random_seed); - - do { - if (cpu_can_run(cpu)) { - r = hvf_vcpu_exec(cpu); - if (r == EXCP_DEBUG) { - cpu_handle_guest_debug(cpu); - } - } - qemu_wait_io_event(cpu); - } while (!cpu->unplug || cpu_can_run(cpu)); - - hvf_vcpu_destroy(cpu); - cpu_thread_signal_destroyed(cpu); - qemu_mutex_unlock_iothread(); - rcu_unregister_thread(); - return NULL; -} - -static void hvf_start_vcpu_thread(CPUState *cpu) -{ - char thread_name[VCPU_THREAD_NAME_SIZE]; - - /* - * HVF currently does not support TCG, and only runs in - * unrestricted-guest mode. - */ - assert(hvf_enabled()); - - cpu->thread = g_malloc0(sizeof(QemuThread)); - cpu->halt_cond = g_malloc0(sizeof(QemuCond)); - qemu_cond_init(cpu->halt_cond); - - snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HVF", - cpu->cpu_index); - qemu_thread_create(cpu->thread, thread_name, hvf_cpu_thread_fn, - cpu, QEMU_THREAD_JOINABLE); -} - -static void hvf_accel_ops_class_init(ObjectClass *oc, void *data) -{ - AccelOpsClass *ops = ACCEL_OPS_CLASS(oc); - - ops->create_vcpu_thread = hvf_start_vcpu_thread; - - ops->synchronize_post_reset = hvf_cpu_synchronize_post_reset; - ops->synchronize_post_init = hvf_cpu_synchronize_post_init; - ops->synchronize_state = hvf_cpu_synchronize_state; - ops->synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm; -}; -static const TypeInfo hvf_accel_ops_type = { - .name = ACCEL_OPS_NAME("hvf"), - - .parent = TYPE_ACCEL_OPS, - .class_init = hvf_accel_ops_class_init, - .abstract = true, -}; -static void hvf_accel_ops_register_types(void) -{ - type_register_static(&hvf_accel_ops_type); -} -type_init(hvf_accel_ops_register_types); diff --git a/target/i386/hvf/hvf-accel-ops.h b/target/i386/hvf/hvf-accel-ops.h deleted file mode 100644 index 8f992da168..0000000000 --- a/target/i386/hvf/hvf-accel-ops.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * Accelerator CPUS Interface - * - * Copyright 2020 SUSE LLC - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ - -#ifndef HVF_CPUS_H -#define HVF_CPUS_H - -#include "sysemu/cpus.h" - -int hvf_init_vcpu(CPUState *); -int hvf_vcpu_exec(CPUState *); -void hvf_cpu_synchronize_state(CPUState *); -void hvf_cpu_synchronize_post_reset(CPUState *); -void hvf_cpu_synchronize_post_init(CPUState *); -void hvf_cpu_synchronize_pre_loadvm(CPUState *); -void hvf_vcpu_destroy(CPUState *); - -#endif /* HVF_CPUS_H */ diff --git a/target/i386/hvf/hvf-i386.h b/target/i386/hvf/hvf-i386.h index 59cfca8875..76e9235524 100644 --- a/target/i386/hvf/hvf-i386.h +++ b/target/i386/hvf/hvf-i386.h @@ -18,42 +18,11 @@ #include "qemu/accel.h" #include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "cpu.h" #include "x86.h" -/* hvf_slot flags */ -#define HVF_SLOT_LOG (1 << 0) - -typedef struct hvf_slot { - uint64_t start; - uint64_t size; - uint8_t *mem; - int slot_id; - uint32_t flags; - MemoryRegion *region; -} hvf_slot; - -typedef struct hvf_vcpu_caps { - uint64_t vmx_cap_pinbased; - uint64_t vmx_cap_procbased; - uint64_t vmx_cap_procbased2; - uint64_t vmx_cap_entry; - uint64_t vmx_cap_exit; - uint64_t vmx_cap_preemption_timer; -} hvf_vcpu_caps; - -struct HVFState { - AccelState parent; - hvf_slot slots[32]; - int num_slots; - - hvf_vcpu_caps *hvf_caps; -}; -extern HVFState *hvf_state; - -void hvf_set_phys_mem(MemoryRegionSection *, bool); void hvf_handle_io(CPUArchState *, uint16_t, void *, int, int, int); -hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); #ifdef NEED_CPU_H /* Functions exported to host specific mode */ diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c index f044181d06..346dbcc26f 100644 --- a/target/i386/hvf/hvf.c +++ b/target/i386/hvf/hvf.c @@ -51,6 +51,7 @@ #include "qemu/error-report.h" #include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "sysemu/runstate.h" #include "hvf-i386.h" #include "vmcs.h" @@ -72,171 +73,6 @@ #include "qemu/accel.h" #include "target/i386/cpu.h" -#include "hvf-accel-ops.h" - -HVFState *hvf_state; - -static void assert_hvf_ok(hv_return_t ret) -{ - if (ret == HV_SUCCESS) { - return; - } - - switch (ret) { - case HV_ERROR: - error_report("Error: HV_ERROR"); - break; - case HV_BUSY: - error_report("Error: HV_BUSY"); - break; - case HV_BAD_ARGUMENT: - error_report("Error: HV_BAD_ARGUMENT"); - break; - case HV_NO_RESOURCES: - error_report("Error: HV_NO_RESOURCES"); - break; - case HV_NO_DEVICE: - error_report("Error: HV_NO_DEVICE"); - break; - case HV_UNSUPPORTED: - error_report("Error: HV_UNSUPPORTED"); - break; - default: - error_report("Unknown Error"); - } - - abort(); -} - -/* Memory slots */ -hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) -{ - hvf_slot *slot; - int x; - for (x = 0; x < hvf_state->num_slots; ++x) { - slot = &hvf_state->slots[x]; - if (slot->size && start < (slot->start + slot->size) && - (start + size) > slot->start) { - return slot; - } - } - return NULL; -} - -struct mac_slot { - int present; - uint64_t size; - uint64_t gpa_start; - uint64_t gva; -}; - -struct mac_slot mac_slots[32]; - -static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) -{ - struct mac_slot *macslot; - hv_return_t ret; - - macslot = &mac_slots[slot->slot_id]; - - if (macslot->present) { - if (macslot->size != slot->size) { - macslot->present = 0; - ret = hv_vm_unmap(macslot->gpa_start, macslot->size); - assert_hvf_ok(ret); - } - } - - if (!slot->size) { - return 0; - } - - macslot->present = 1; - macslot->gpa_start = slot->start; - macslot->size = slot->size; - ret = hv_vm_map((hv_uvaddr_t)slot->mem, slot->start, slot->size, flags); - assert_hvf_ok(ret); - return 0; -} - -void hvf_set_phys_mem(MemoryRegionSection *section, bool add) -{ - hvf_slot *mem; - MemoryRegion *area = section->mr; - bool writeable = !area->readonly && !area->rom_device; - hv_memory_flags_t flags; - - if (!memory_region_is_ram(area)) { - if (writeable) { - return; - } else if (!memory_region_is_romd(area)) { - /* - * If the memory device is not in romd_mode, then we actually want - * to remove the hvf memory slot so all accesses will trap. - */ - add = false; - } - } - - mem = hvf_find_overlap_slot( - section->offset_within_address_space, - int128_get64(section->size)); - - if (mem && add) { - if (mem->size == int128_get64(section->size) && - mem->start == section->offset_within_address_space && - mem->mem == (memory_region_get_ram_ptr(area) + - section->offset_within_region)) { - return; /* Same region was attempted to register, go away. */ - } - } - - /* Region needs to be reset. set the size to 0 and remap it. */ - if (mem) { - mem->size = 0; - if (do_hvf_set_memory(mem, 0)) { - error_report("Failed to reset overlapping slot"); - abort(); - } - } - - if (!add) { - return; - } - - if (area->readonly || - (!memory_region_is_ram(area) && memory_region_is_romd(area))) { - flags = HV_MEMORY_READ | HV_MEMORY_EXEC; - } else { - flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; - } - - /* Now make a new slot. */ - int x; - - for (x = 0; x < hvf_state->num_slots; ++x) { - mem = &hvf_state->slots[x]; - if (!mem->size) { - break; - } - } - - if (x == hvf_state->num_slots) { - error_report("No free slots"); - abort(); - } - - mem->size = int128_get64(section->size); - mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region; - mem->start = section->offset_within_address_space; - mem->region = area; - - if (do_hvf_set_memory(mem, flags)) { - error_report("Error registering new memory slot"); - abort(); - } -} - void vmx_update_tpr(CPUState *cpu) { /* TODO: need integrate APIC handling */ @@ -244,11 +80,11 @@ void vmx_update_tpr(CPUState *cpu) int tpr = cpu_get_apic_tpr(x86_cpu->apic_state) << 4; int irr = apic_get_highest_priority_irr(x86_cpu->apic_state); - wreg(cpu->hvf_fd, HV_X86_TPR, tpr); + wreg(cpu->hvf->fd, HV_X86_TPR, tpr); if (irr == -1) { - wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0); + wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, 0); } else { - wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 : + wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 : irr >> 4); } } @@ -256,7 +92,7 @@ void vmx_update_tpr(CPUState *cpu) static void update_apic_tpr(CPUState *cpu) { X86CPU *x86_cpu = X86_CPU(cpu); - int tpr = rreg(cpu->hvf_fd, HV_X86_TPR) >> 4; + int tpr = rreg(cpu->hvf->fd, HV_X86_TPR) >> 4; cpu_set_apic_tpr(x86_cpu->apic_state, tpr); } @@ -276,56 +112,6 @@ void hvf_handle_io(CPUArchState *env, uint16_t port, void *buffer, } } -static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) -{ - if (!cpu->vcpu_dirty) { - hvf_get_registers(cpu); - cpu->vcpu_dirty = true; - } -} - -void hvf_cpu_synchronize_state(CPUState *cpu) -{ - if (!cpu->vcpu_dirty) { - run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); - } -} - -static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu, - run_on_cpu_data arg) -{ - hvf_put_registers(cpu); - cpu->vcpu_dirty = false; -} - -void hvf_cpu_synchronize_post_reset(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL); -} - -static void do_hvf_cpu_synchronize_post_init(CPUState *cpu, - run_on_cpu_data arg) -{ - hvf_put_registers(cpu); - cpu->vcpu_dirty = false; -} - -void hvf_cpu_synchronize_post_init(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL); -} - -static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu, - run_on_cpu_data arg) -{ - cpu->vcpu_dirty = true; -} - -void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) -{ - run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); -} - static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual) { int read, write; @@ -370,90 +156,12 @@ static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual) return false; } -static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) -{ - hvf_slot *slot; - - slot = hvf_find_overlap_slot( - section->offset_within_address_space, - int128_get64(section->size)); - - /* protect region against writes; begin tracking it */ - if (on) { - slot->flags |= HVF_SLOT_LOG; - hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size, - HV_MEMORY_READ); - /* stop tracking region*/ - } else { - slot->flags &= ~HVF_SLOT_LOG; - hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size, - HV_MEMORY_READ | HV_MEMORY_WRITE); - } -} - -static void hvf_log_start(MemoryListener *listener, - MemoryRegionSection *section, int old, int new) -{ - if (old != 0) { - return; - } - - hvf_set_dirty_tracking(section, 1); -} - -static void hvf_log_stop(MemoryListener *listener, - MemoryRegionSection *section, int old, int new) -{ - if (new != 0) { - return; - } - - hvf_set_dirty_tracking(section, 0); -} - -static void hvf_log_sync(MemoryListener *listener, - MemoryRegionSection *section) -{ - /* - * sync of dirty pages is handled elsewhere; just make sure we keep - * tracking the region. - */ - hvf_set_dirty_tracking(section, 1); -} - -static void hvf_region_add(MemoryListener *listener, - MemoryRegionSection *section) -{ - hvf_set_phys_mem(section, true); -} - -static void hvf_region_del(MemoryListener *listener, - MemoryRegionSection *section) -{ - hvf_set_phys_mem(section, false); -} - -static MemoryListener hvf_memory_listener = { - .priority = 10, - .region_add = hvf_region_add, - .region_del = hvf_region_del, - .log_start = hvf_log_start, - .log_stop = hvf_log_stop, - .log_sync = hvf_log_sync, -}; - -void hvf_vcpu_destroy(CPUState *cpu) +void hvf_arch_vcpu_destroy(CPUState *cpu) { X86CPU *x86_cpu = X86_CPU(cpu); CPUX86State *env = &x86_cpu->env; - hv_return_t ret = hv_vcpu_destroy((hv_vcpuid_t)cpu->hvf_fd); g_free(env->hvf_mmio_buf); - assert_hvf_ok(ret); -} - -static void dummy_signal(int sig) -{ } static void init_tsc_freq(CPUX86State *env) @@ -498,23 +206,10 @@ static inline bool apic_bus_freq_is_known(CPUX86State *env) return env->apic_bus_freq != 0; } -int hvf_init_vcpu(CPUState *cpu) +int hvf_arch_init_vcpu(CPUState *cpu) { - X86CPU *x86cpu = X86_CPU(cpu); CPUX86State *env = &x86cpu->env; - int r; - - /* init cpu signals */ - sigset_t set; - struct sigaction sigact; - - memset(&sigact, 0, sizeof(sigact)); - sigact.sa_handler = dummy_signal; - sigaction(SIG_IPI, &sigact, NULL); - - pthread_sigmask(SIG_BLOCK, NULL, &set); - sigdelset(&set, SIG_IPI); init_emu(); init_decoder(); @@ -531,10 +226,6 @@ int hvf_init_vcpu(CPUState *cpu) } } - r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT); - cpu->vcpu_dirty = 1; - assert_hvf_ok(r); - if (hv_vmx_read_capability(HV_VMX_CAP_PINBASED, &hvf_state->hvf_caps->vmx_cap_pinbased)) { abort(); @@ -553,43 +244,43 @@ int hvf_init_vcpu(CPUState *cpu) } /* set VMCS control fields */ - wvmcs(cpu->hvf_fd, VMCS_PIN_BASED_CTLS, + wvmcs(cpu->hvf->fd, VMCS_PIN_BASED_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_pinbased, VMCS_PIN_BASED_CTLS_EXTINT | VMCS_PIN_BASED_CTLS_NMI | VMCS_PIN_BASED_CTLS_VNMI)); - wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, + wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased, VMCS_PRI_PROC_BASED_CTLS_HLT | VMCS_PRI_PROC_BASED_CTLS_MWAIT | VMCS_PRI_PROC_BASED_CTLS_TSC_OFFSET | VMCS_PRI_PROC_BASED_CTLS_TPR_SHADOW) | VMCS_PRI_PROC_BASED_CTLS_SEC_CONTROL); - wvmcs(cpu->hvf_fd, VMCS_SEC_PROC_BASED_CTLS, + wvmcs(cpu->hvf->fd, VMCS_SEC_PROC_BASED_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased2, VMCS_PRI_PROC_BASED2_CTLS_APIC_ACCESSES)); - wvmcs(cpu->hvf_fd, VMCS_ENTRY_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_entry, + wvmcs(cpu->hvf->fd, VMCS_ENTRY_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_entry, 0)); - wvmcs(cpu->hvf_fd, VMCS_EXCEPTION_BITMAP, 0); /* Double fault */ + wvmcs(cpu->hvf->fd, VMCS_EXCEPTION_BITMAP, 0); /* Double fault */ - wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0); + wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, 0); x86cpu = X86_CPU(cpu); x86cpu->env.xsave_buf = qemu_memalign(4096, 4096); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_STAR, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_LSTAR, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_CSTAR, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FMASK, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FSBASE, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_GSBASE, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_KERNELGSBASE, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_TSC_AUX, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_TSC, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_CS, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_EIP, 1); - hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_ESP, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_STAR, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_LSTAR, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_CSTAR, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_FMASK, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_FSBASE, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_GSBASE, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_KERNELGSBASE, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_TSC_AUX, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_TSC, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_SYSENTER_CS, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_SYSENTER_EIP, 1); + hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_SYSENTER_ESP, 1); return 0; } @@ -630,16 +321,16 @@ static void hvf_store_events(CPUState *cpu, uint32_t ins_len, uint64_t idtvec_in } if (idtvec_info & VMCS_IDT_VEC_ERRCODE_VALID) { env->has_error_code = true; - env->error_code = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_ERROR); + env->error_code = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_ERROR); } } - if ((rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) & + if ((rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY) & VMCS_INTERRUPTIBILITY_NMI_BLOCKING)) { env->hflags2 |= HF2_NMI_MASK; } else { env->hflags2 &= ~HF2_NMI_MASK; } - if (rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) & + if (rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY) & (VMCS_INTERRUPTIBILITY_STI_BLOCKING | VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) { env->hflags |= HF_INHIBIT_IRQ_MASK; @@ -718,20 +409,20 @@ int hvf_vcpu_exec(CPUState *cpu) return EXCP_HLT; } - hv_return_t r = hv_vcpu_run(cpu->hvf_fd); + hv_return_t r = hv_vcpu_run(cpu->hvf->fd); assert_hvf_ok(r); /* handle VMEXIT */ - uint64_t exit_reason = rvmcs(cpu->hvf_fd, VMCS_EXIT_REASON); - uint64_t exit_qual = rvmcs(cpu->hvf_fd, VMCS_EXIT_QUALIFICATION); - uint32_t ins_len = (uint32_t)rvmcs(cpu->hvf_fd, + uint64_t exit_reason = rvmcs(cpu->hvf->fd, VMCS_EXIT_REASON); + uint64_t exit_qual = rvmcs(cpu->hvf->fd, VMCS_EXIT_QUALIFICATION); + uint32_t ins_len = (uint32_t)rvmcs(cpu->hvf->fd, VMCS_EXIT_INSTRUCTION_LENGTH); - uint64_t idtvec_info = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO); + uint64_t idtvec_info = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_INFO); hvf_store_events(cpu, ins_len, idtvec_info); - rip = rreg(cpu->hvf_fd, HV_X86_RIP); - env->eflags = rreg(cpu->hvf_fd, HV_X86_RFLAGS); + rip = rreg(cpu->hvf->fd, HV_X86_RIP); + env->eflags = rreg(cpu->hvf->fd, HV_X86_RFLAGS); qemu_mutex_lock_iothread(); @@ -761,7 +452,7 @@ int hvf_vcpu_exec(CPUState *cpu) case EXIT_REASON_EPT_FAULT: { hvf_slot *slot; - uint64_t gpa = rvmcs(cpu->hvf_fd, VMCS_GUEST_PHYSICAL_ADDRESS); + uint64_t gpa = rvmcs(cpu->hvf->fd, VMCS_GUEST_PHYSICAL_ADDRESS); if (((idtvec_info & VMCS_IDT_VEC_VALID) == 0) && ((exit_qual & EXIT_QUAL_NMIUDTI) != 0)) { @@ -806,7 +497,7 @@ int hvf_vcpu_exec(CPUState *cpu) store_regs(cpu); break; } else if (!string && !in) { - RAX(env) = rreg(cpu->hvf_fd, HV_X86_RAX); + RAX(env) = rreg(cpu->hvf->fd, HV_X86_RAX); hvf_handle_io(env, port, &RAX(env), 1, size, 1); macvm_set_rip(cpu, rip + ins_len); break; @@ -822,21 +513,21 @@ int hvf_vcpu_exec(CPUState *cpu) break; } case EXIT_REASON_CPUID: { - uint32_t rax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX); - uint32_t rbx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RBX); - uint32_t rcx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX); - uint32_t rdx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX); + uint32_t rax = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RAX); + uint32_t rbx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RBX); + uint32_t rcx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RCX); + uint32_t rdx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RDX); if (rax == 1) { /* CPUID1.ecx.OSXSAVE needs to know CR4 */ - env->cr[4] = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR4); + env->cr[4] = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR4); } hvf_cpu_x86_cpuid(env, rax, rcx, &rax, &rbx, &rcx, &rdx); - wreg(cpu->hvf_fd, HV_X86_RAX, rax); - wreg(cpu->hvf_fd, HV_X86_RBX, rbx); - wreg(cpu->hvf_fd, HV_X86_RCX, rcx); - wreg(cpu->hvf_fd, HV_X86_RDX, rdx); + wreg(cpu->hvf->fd, HV_X86_RAX, rax); + wreg(cpu->hvf->fd, HV_X86_RBX, rbx); + wreg(cpu->hvf->fd, HV_X86_RCX, rcx); + wreg(cpu->hvf->fd, HV_X86_RDX, rdx); macvm_set_rip(cpu, rip + ins_len); break; @@ -844,16 +535,16 @@ int hvf_vcpu_exec(CPUState *cpu) case EXIT_REASON_XSETBV: { X86CPU *x86_cpu = X86_CPU(cpu); CPUX86State *env = &x86_cpu->env; - uint32_t eax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX); - uint32_t ecx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX); - uint32_t edx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX); + uint32_t eax = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RAX); + uint32_t ecx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RCX); + uint32_t edx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RDX); if (ecx) { macvm_set_rip(cpu, rip + ins_len); break; } env->xcr0 = ((uint64_t)edx << 32) | eax; - wreg(cpu->hvf_fd, HV_X86_XCR0, env->xcr0 | 1); + wreg(cpu->hvf->fd, HV_X86_XCR0, env->xcr0 | 1); macvm_set_rip(cpu, rip + ins_len); break; } @@ -892,11 +583,11 @@ int hvf_vcpu_exec(CPUState *cpu) switch (cr) { case 0x0: { - macvm_set_cr0(cpu->hvf_fd, RRX(env, reg)); + macvm_set_cr0(cpu->hvf->fd, RRX(env, reg)); break; } case 4: { - macvm_set_cr4(cpu->hvf_fd, RRX(env, reg)); + macvm_set_cr4(cpu->hvf->fd, RRX(env, reg)); break; } case 8: { @@ -932,7 +623,7 @@ int hvf_vcpu_exec(CPUState *cpu) break; } case EXIT_REASON_TASK_SWITCH: { - uint64_t vinfo = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO); + uint64_t vinfo = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_INFO); x68_segment_selector sel = {.sel = exit_qual & 0xffff}; vmx_handle_task_switch(cpu, sel, (exit_qual >> 30) & 0x3, vinfo & VMCS_INTR_VALID, vinfo & VECTORING_INFO_VECTOR_MASK, vinfo @@ -945,8 +636,8 @@ int hvf_vcpu_exec(CPUState *cpu) break; } case EXIT_REASON_RDPMC: - wreg(cpu->hvf_fd, HV_X86_RAX, 0); - wreg(cpu->hvf_fd, HV_X86_RDX, 0); + wreg(cpu->hvf->fd, HV_X86_RAX, 0); + wreg(cpu->hvf->fd, HV_X86_RDX, 0); macvm_set_rip(cpu, rip + ins_len); break; case VMX_REASON_VMCALL: @@ -962,48 +653,3 @@ int hvf_vcpu_exec(CPUState *cpu) return ret; } - -bool hvf_allowed; - -static int hvf_accel_init(MachineState *ms) -{ - int x; - hv_return_t ret; - HVFState *s; - - ret = hv_vm_create(HV_VM_DEFAULT); - assert_hvf_ok(ret); - - s = g_new0(HVFState, 1); - - s->num_slots = 32; - for (x = 0; x < s->num_slots; ++x) { - s->slots[x].size = 0; - s->slots[x].slot_id = x; - } - - hvf_state = s; - memory_listener_register(&hvf_memory_listener, &address_space_memory); - return 0; -} - -static void hvf_accel_class_init(ObjectClass *oc, void *data) -{ - AccelClass *ac = ACCEL_CLASS(oc); - ac->name = "HVF"; - ac->init_machine = hvf_accel_init; - ac->allowed = &hvf_allowed; -} - -static const TypeInfo hvf_accel_type = { - .name = TYPE_HVF_ACCEL, - .parent = TYPE_ACCEL, - .class_init = hvf_accel_class_init, -}; - -static void hvf_type_init(void) -{ - type_register_static(&hvf_accel_type); -} - -type_init(hvf_type_init); diff --git a/target/i386/hvf/meson.build b/target/i386/hvf/meson.build index d253d5fd10..f6d4c394d3 100644 --- a/target/i386/hvf/meson.build +++ b/target/i386/hvf/meson.build @@ -1,6 +1,5 @@ i386_softmmu_ss.add(when: [hvf, 'CONFIG_HVF'], if_true: files( 'hvf.c', - 'hvf-accel-ops.c', 'x86.c', 'x86_cpuid.c', 'x86_decode.c', diff --git a/target/i386/hvf/vmx.h b/target/i386/hvf/vmx.h index 24c4cdf0be..6df87116f6 100644 --- a/target/i386/hvf/vmx.h +++ b/target/i386/hvf/vmx.h @@ -30,6 +30,8 @@ #include "vmcs.h" #include "cpu.h" #include "x86.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" #include "exec/address-spaces.h" @@ -179,15 +181,15 @@ static inline void macvm_set_rip(CPUState *cpu, uint64_t rip) uint64_t val; /* BUG, should take considering overlap.. */ - wreg(cpu->hvf_fd, HV_X86_RIP, rip); + wreg(cpu->hvf->fd, HV_X86_RIP, rip); env->eip = rip; /* after moving forward in rip, we need to clean INTERRUPTABILITY */ - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY); if (val & (VMCS_INTERRUPTIBILITY_STI_BLOCKING | VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) { env->hflags &= ~HF_INHIBIT_IRQ_MASK; - wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, + wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, val & ~(VMCS_INTERRUPTIBILITY_STI_BLOCKING | VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)); } @@ -199,9 +201,9 @@ static inline void vmx_clear_nmi_blocking(CPUState *cpu) CPUX86State *env = &x86_cpu->env; env->hflags2 &= ~HF2_NMI_MASK; - uint32_t gi = (uint32_t) rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY); + uint32_t gi = (uint32_t) rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY); gi &= ~VMCS_INTERRUPTIBILITY_NMI_BLOCKING; - wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, gi); + wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, gi); } static inline void vmx_set_nmi_blocking(CPUState *cpu) @@ -210,16 +212,16 @@ static inline void vmx_set_nmi_blocking(CPUState *cpu) CPUX86State *env = &x86_cpu->env; env->hflags2 |= HF2_NMI_MASK; - uint32_t gi = (uint32_t)rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY); + uint32_t gi = (uint32_t)rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY); gi |= VMCS_INTERRUPTIBILITY_NMI_BLOCKING; - wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, gi); + wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, gi); } static inline void vmx_set_nmi_window_exiting(CPUState *cpu) { uint64_t val; - val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS); - wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val | + val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS); + wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val | VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING); } @@ -228,8 +230,8 @@ static inline void vmx_clear_nmi_window_exiting(CPUState *cpu) { uint64_t val; - val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS); - wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val & + val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS); + wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val & ~VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING); } diff --git a/target/i386/hvf/x86.c b/target/i386/hvf/x86.c index cd045183a8..2898bb70a8 100644 --- a/target/i386/hvf/x86.c +++ b/target/i386/hvf/x86.c @@ -62,11 +62,11 @@ bool x86_read_segment_descriptor(struct CPUState *cpu, } if (GDT_SEL == sel.ti) { - base = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE); - limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT); + base = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_BASE); + limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_LIMIT); } else { - base = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE); - limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT); + base = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_BASE); + limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_LIMIT); } if (sel.index * 8 >= limit) { @@ -85,11 +85,11 @@ bool x86_write_segment_descriptor(struct CPUState *cpu, uint32_t limit; if (GDT_SEL == sel.ti) { - base = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE); - limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT); + base = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_BASE); + limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_LIMIT); } else { - base = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE); - limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT); + base = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_BASE); + limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_LIMIT); } if (sel.index * 8 >= limit) { @@ -103,8 +103,8 @@ bool x86_write_segment_descriptor(struct CPUState *cpu, bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc, int gate) { - target_ulong base = rvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_BASE); - uint32_t limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_LIMIT); + target_ulong base = rvmcs(cpu->hvf->fd, VMCS_GUEST_IDTR_BASE); + uint32_t limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_IDTR_LIMIT); memset(idt_desc, 0, sizeof(*idt_desc)); if (gate * 8 >= limit) { @@ -118,7 +118,7 @@ bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc, bool x86_is_protected(struct CPUState *cpu) { - uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0); + uint64_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0); return cr0 & CR0_PE; } @@ -136,7 +136,7 @@ bool x86_is_v8086(struct CPUState *cpu) bool x86_is_long_mode(struct CPUState *cpu) { - return rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA; + return rvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA; } bool x86_is_long64_mode(struct CPUState *cpu) @@ -149,13 +149,13 @@ bool x86_is_long64_mode(struct CPUState *cpu) bool x86_is_paging_mode(struct CPUState *cpu) { - uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0); + uint64_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0); return cr0 & CR0_PG; } bool x86_is_pae_enabled(struct CPUState *cpu) { - uint64_t cr4 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR4); + uint64_t cr4 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR4); return cr4 & CR4_PAE; } diff --git a/target/i386/hvf/x86_descr.c b/target/i386/hvf/x86_descr.c index 9f539e73f6..af15c06ac5 100644 --- a/target/i386/hvf/x86_descr.c +++ b/target/i386/hvf/x86_descr.c @@ -48,47 +48,47 @@ static const struct vmx_segment_field { uint32_t vmx_read_segment_limit(CPUState *cpu, X86Seg seg) { - return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit); + return (uint32_t)rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].limit); } uint32_t vmx_read_segment_ar(CPUState *cpu, X86Seg seg) { - return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].ar_bytes); + return (uint32_t)rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].ar_bytes); } uint64_t vmx_read_segment_base(CPUState *cpu, X86Seg seg) { - return rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].base); + return rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].base); } x68_segment_selector vmx_read_segment_selector(CPUState *cpu, X86Seg seg) { x68_segment_selector sel; - sel.sel = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector); + sel.sel = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].selector); return sel; } void vmx_write_segment_selector(struct CPUState *cpu, x68_segment_selector selector, X86Seg seg) { - wvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector, selector.sel); + wvmcs(cpu->hvf->fd, vmx_segment_fields[seg].selector, selector.sel); } void vmx_read_segment_descriptor(struct CPUState *cpu, struct vmx_segment *desc, X86Seg seg) { - desc->sel = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector); - desc->base = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].base); - desc->limit = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit); - desc->ar = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].ar_bytes); + desc->sel = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].selector); + desc->base = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].base); + desc->limit = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].limit); + desc->ar = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].ar_bytes); } void vmx_write_segment_descriptor(CPUState *cpu, struct vmx_segment *desc, X86Seg seg) { const struct vmx_segment_field *sf = &vmx_segment_fields[seg]; - wvmcs(cpu->hvf_fd, sf->base, desc->base); - wvmcs(cpu->hvf_fd, sf->limit, desc->limit); - wvmcs(cpu->hvf_fd, sf->selector, desc->sel); - wvmcs(cpu->hvf_fd, sf->ar_bytes, desc->ar); + wvmcs(cpu->hvf->fd, sf->base, desc->base); + wvmcs(cpu->hvf->fd, sf->limit, desc->limit); + wvmcs(cpu->hvf->fd, sf->selector, desc->sel); + wvmcs(cpu->hvf->fd, sf->ar_bytes, desc->ar); } void x86_segment_descriptor_to_vmx(struct CPUState *cpu, x68_segment_selector selector, struct x86_segment_descriptor *desc, struct vmx_segment *vmx_desc) diff --git a/target/i386/hvf/x86_emu.c b/target/i386/hvf/x86_emu.c index e52c39ddb1..7c8203b21f 100644 --- a/target/i386/hvf/x86_emu.c +++ b/target/i386/hvf/x86_emu.c @@ -674,7 +674,7 @@ void simulate_rdmsr(struct CPUState *cpu) switch (msr) { case MSR_IA32_TSC: - val = rdtscp() + rvmcs(cpu->hvf_fd, VMCS_TSC_OFFSET); + val = rdtscp() + rvmcs(cpu->hvf->fd, VMCS_TSC_OFFSET); break; case MSR_IA32_APICBASE: val = cpu_get_apic_base(X86_CPU(cpu)->apic_state); @@ -683,16 +683,16 @@ void simulate_rdmsr(struct CPUState *cpu) val = x86_cpu->ucode_rev; break; case MSR_EFER: - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER); break; case MSR_FSBASE: - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_FS_BASE); break; case MSR_GSBASE: - val = rvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE); + val = rvmcs(cpu->hvf->fd, VMCS_GUEST_GS_BASE); break; case MSR_KERNELGSBASE: - val = rvmcs(cpu->hvf_fd, VMCS_HOST_FS_BASE); + val = rvmcs(cpu->hvf->fd, VMCS_HOST_FS_BASE); break; case MSR_STAR: abort(); @@ -780,13 +780,13 @@ void simulate_wrmsr(struct CPUState *cpu) cpu_set_apic_base(X86_CPU(cpu)->apic_state, data); break; case MSR_FSBASE: - wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE, data); + wvmcs(cpu->hvf->fd, VMCS_GUEST_FS_BASE, data); break; case MSR_GSBASE: - wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE, data); + wvmcs(cpu->hvf->fd, VMCS_GUEST_GS_BASE, data); break; case MSR_KERNELGSBASE: - wvmcs(cpu->hvf_fd, VMCS_HOST_FS_BASE, data); + wvmcs(cpu->hvf->fd, VMCS_HOST_FS_BASE, data); break; case MSR_STAR: abort(); @@ -799,9 +799,9 @@ void simulate_wrmsr(struct CPUState *cpu) break; case MSR_EFER: /*printf("new efer %llx\n", EFER(cpu));*/ - wvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER, data); + wvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER, data); if (data & MSR_EFER_NXE) { - hv_vcpu_invalidate_tlb(cpu->hvf_fd); + hv_vcpu_invalidate_tlb(cpu->hvf->fd); } break; case MSR_MTRRphysBase(0): @@ -1425,21 +1425,21 @@ void load_regs(struct CPUState *cpu) CPUX86State *env = &x86_cpu->env; int i = 0; - RRX(env, R_EAX) = rreg(cpu->hvf_fd, HV_X86_RAX); - RRX(env, R_EBX) = rreg(cpu->hvf_fd, HV_X86_RBX); - RRX(env, R_ECX) = rreg(cpu->hvf_fd, HV_X86_RCX); - RRX(env, R_EDX) = rreg(cpu->hvf_fd, HV_X86_RDX); - RRX(env, R_ESI) = rreg(cpu->hvf_fd, HV_X86_RSI); - RRX(env, R_EDI) = rreg(cpu->hvf_fd, HV_X86_RDI); - RRX(env, R_ESP) = rreg(cpu->hvf_fd, HV_X86_RSP); - RRX(env, R_EBP) = rreg(cpu->hvf_fd, HV_X86_RBP); + RRX(env, R_EAX) = rreg(cpu->hvf->fd, HV_X86_RAX); + RRX(env, R_EBX) = rreg(cpu->hvf->fd, HV_X86_RBX); + RRX(env, R_ECX) = rreg(cpu->hvf->fd, HV_X86_RCX); + RRX(env, R_EDX) = rreg(cpu->hvf->fd, HV_X86_RDX); + RRX(env, R_ESI) = rreg(cpu->hvf->fd, HV_X86_RSI); + RRX(env, R_EDI) = rreg(cpu->hvf->fd, HV_X86_RDI); + RRX(env, R_ESP) = rreg(cpu->hvf->fd, HV_X86_RSP); + RRX(env, R_EBP) = rreg(cpu->hvf->fd, HV_X86_RBP); for (i = 8; i < 16; i++) { - RRX(env, i) = rreg(cpu->hvf_fd, HV_X86_RAX + i); + RRX(env, i) = rreg(cpu->hvf->fd, HV_X86_RAX + i); } - env->eflags = rreg(cpu->hvf_fd, HV_X86_RFLAGS); + env->eflags = rreg(cpu->hvf->fd, HV_X86_RFLAGS); rflags_to_lflags(env); - env->eip = rreg(cpu->hvf_fd, HV_X86_RIP); + env->eip = rreg(cpu->hvf->fd, HV_X86_RIP); } void store_regs(struct CPUState *cpu) @@ -1448,20 +1448,20 @@ void store_regs(struct CPUState *cpu) CPUX86State *env = &x86_cpu->env; int i = 0; - wreg(cpu->hvf_fd, HV_X86_RAX, RAX(env)); - wreg(cpu->hvf_fd, HV_X86_RBX, RBX(env)); - wreg(cpu->hvf_fd, HV_X86_RCX, RCX(env)); - wreg(cpu->hvf_fd, HV_X86_RDX, RDX(env)); - wreg(cpu->hvf_fd, HV_X86_RSI, RSI(env)); - wreg(cpu->hvf_fd, HV_X86_RDI, RDI(env)); - wreg(cpu->hvf_fd, HV_X86_RBP, RBP(env)); - wreg(cpu->hvf_fd, HV_X86_RSP, RSP(env)); + wreg(cpu->hvf->fd, HV_X86_RAX, RAX(env)); + wreg(cpu->hvf->fd, HV_X86_RBX, RBX(env)); + wreg(cpu->hvf->fd, HV_X86_RCX, RCX(env)); + wreg(cpu->hvf->fd, HV_X86_RDX, RDX(env)); + wreg(cpu->hvf->fd, HV_X86_RSI, RSI(env)); + wreg(cpu->hvf->fd, HV_X86_RDI, RDI(env)); + wreg(cpu->hvf->fd, HV_X86_RBP, RBP(env)); + wreg(cpu->hvf->fd, HV_X86_RSP, RSP(env)); for (i = 8; i < 16; i++) { - wreg(cpu->hvf_fd, HV_X86_RAX + i, RRX(env, i)); + wreg(cpu->hvf->fd, HV_X86_RAX + i, RRX(env, i)); } lflags_to_rflags(env); - wreg(cpu->hvf_fd, HV_X86_RFLAGS, env->eflags); + wreg(cpu->hvf->fd, HV_X86_RFLAGS, env->eflags); macvm_set_rip(cpu, env->eip); } diff --git a/target/i386/hvf/x86_mmu.c b/target/i386/hvf/x86_mmu.c index 78fff04684..e9ed0f5aa1 100644 --- a/target/i386/hvf/x86_mmu.c +++ b/target/i386/hvf/x86_mmu.c @@ -127,7 +127,7 @@ static bool test_pt_entry(struct CPUState *cpu, struct gpt_translation *pt, pt->err_code |= MMU_PAGE_PT; } - uint32_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0); + uint32_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0); /* check protection */ if (cr0 & CR0_WP) { if (pt->write_access && !pte_write_access(pte)) { @@ -172,7 +172,7 @@ static bool walk_gpt(struct CPUState *cpu, target_ulong addr, int err_code, { int top_level, level; bool is_large = false; - target_ulong cr3 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR3); + target_ulong cr3 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR3); uint64_t page_mask = pae ? PAE_PTE_PAGE_MASK : LEGACY_PTE_PAGE_MASK; memset(pt, 0, sizeof(*pt)); diff --git a/target/i386/hvf/x86_task.c b/target/i386/hvf/x86_task.c index d66dfd7669..422156128b 100644 --- a/target/i386/hvf/x86_task.c +++ b/target/i386/hvf/x86_task.c @@ -62,7 +62,7 @@ static void load_state_from_tss32(CPUState *cpu, struct x86_tss_segment32 *tss) X86CPU *x86_cpu = X86_CPU(cpu); CPUX86State *env = &x86_cpu->env; - wvmcs(cpu->hvf_fd, VMCS_GUEST_CR3, tss->cr3); + wvmcs(cpu->hvf->fd, VMCS_GUEST_CR3, tss->cr3); env->eip = tss->eip; env->eflags = tss->eflags | 2; @@ -111,11 +111,11 @@ static int task_switch_32(CPUState *cpu, x68_segment_selector tss_sel, x68_segme void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel, int reason, bool gate_valid, uint8_t gate, uint64_t gate_type) { - uint64_t rip = rreg(cpu->hvf_fd, HV_X86_RIP); + uint64_t rip = rreg(cpu->hvf->fd, HV_X86_RIP); if (!gate_valid || (gate_type != VMCS_INTR_T_HWEXCEPTION && gate_type != VMCS_INTR_T_HWINTR && gate_type != VMCS_INTR_T_NMI)) { - int ins_len = rvmcs(cpu->hvf_fd, VMCS_EXIT_INSTRUCTION_LENGTH); + int ins_len = rvmcs(cpu->hvf->fd, VMCS_EXIT_INSTRUCTION_LENGTH); macvm_set_rip(cpu, rip + ins_len); return; } @@ -174,12 +174,12 @@ void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel, int rea //ret = task_switch_16(cpu, tss_sel, old_tss_sel, old_tss_base, &next_tss_desc); VM_PANIC("task_switch_16"); - macvm_set_cr0(cpu->hvf_fd, rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0) | CR0_TS); + macvm_set_cr0(cpu->hvf->fd, rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0) | CR0_TS); x86_segment_descriptor_to_vmx(cpu, tss_sel, &next_tss_desc, &vmx_seg); vmx_write_segment_descriptor(cpu, &vmx_seg, R_TR); store_regs(cpu); - hv_vcpu_invalidate_tlb(cpu->hvf_fd); - hv_vcpu_flush(cpu->hvf_fd); + hv_vcpu_invalidate_tlb(cpu->hvf->fd); + hv_vcpu_flush(cpu->hvf->fd); } diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c index 0d7533742e..2ced2c2478 100644 --- a/target/i386/hvf/x86hvf.c +++ b/target/i386/hvf/x86hvf.c @@ -26,14 +26,13 @@ #include "cpu.h" #include "x86_descr.h" #include "x86_decode.h" +#include "sysemu/hw_accel.h" #include "hw/i386/apic_internal.h" #include <Hypervisor/hv.h> #include <Hypervisor/hv_vmx.h> -#include "hvf-accel-ops.h" - void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg, SegmentCache *qseg, bool is_tr) { @@ -81,7 +80,7 @@ void hvf_put_xsave(CPUState *cpu_state) x86_cpu_xsave_all_areas(X86_CPU(cpu_state), xsave); - if (hv_vcpu_write_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) { + if (hv_vcpu_write_fpstate(cpu_state->hvf->fd, (void*)xsave, 4096)) { abort(); } } @@ -91,19 +90,19 @@ void hvf_put_segments(CPUState *cpu_state) CPUX86State *env = &X86_CPU(cpu_state)->env; struct vmx_segment seg; - wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_LIMIT, env->idt.limit); - wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_BASE, env->idt.base); + wvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_LIMIT, env->idt.limit); + wvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_BASE, env->idt.base); - wvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_LIMIT, env->gdt.limit); - wvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_BASE, env->gdt.base); + wvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_LIMIT, env->gdt.limit); + wvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_BASE, env->gdt.base); - /* wvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR2, env->cr[2]); */ - wvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR3, env->cr[3]); + /* wvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR2, env->cr[2]); */ + wvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR3, env->cr[3]); vmx_update_tpr(cpu_state); - wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IA32_EFER, env->efer); + wvmcs(cpu_state->hvf->fd, VMCS_GUEST_IA32_EFER, env->efer); - macvm_set_cr4(cpu_state->hvf_fd, env->cr[4]); - macvm_set_cr0(cpu_state->hvf_fd, env->cr[0]); + macvm_set_cr4(cpu_state->hvf->fd, env->cr[4]); + macvm_set_cr0(cpu_state->hvf->fd, env->cr[0]); hvf_set_segment(cpu_state, &seg, &env->segs[R_CS], false); vmx_write_segment_descriptor(cpu_state, &seg, R_CS); @@ -129,31 +128,31 @@ void hvf_put_segments(CPUState *cpu_state) hvf_set_segment(cpu_state, &seg, &env->ldt, false); vmx_write_segment_descriptor(cpu_state, &seg, R_LDTR); - hv_vcpu_flush(cpu_state->hvf_fd); + hv_vcpu_flush(cpu_state->hvf->fd); } void hvf_put_msrs(CPUState *cpu_state) { CPUX86State *env = &X86_CPU(cpu_state)->env; - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_CS, + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_CS, env->sysenter_cs); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_ESP, + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_ESP, env->sysenter_esp); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_EIP, + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_EIP, env->sysenter_eip); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_STAR, env->star); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_STAR, env->star); #ifdef TARGET_X86_64 - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_CSTAR, env->cstar); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_KERNELGSBASE, env->kernelgsbase); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_FMASK, env->fmask); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_LSTAR, env->lstar); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_CSTAR, env->cstar); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_KERNELGSBASE, env->kernelgsbase); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_FMASK, env->fmask); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_LSTAR, env->lstar); #endif - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_GSBASE, env->segs[R_GS].base); - hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_FSBASE, env->segs[R_FS].base); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_GSBASE, env->segs[R_GS].base); + hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_FSBASE, env->segs[R_FS].base); } @@ -163,7 +162,7 @@ void hvf_get_xsave(CPUState *cpu_state) xsave = X86_CPU(cpu_state)->env.xsave_buf; - if (hv_vcpu_read_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) { + if (hv_vcpu_read_fpstate(cpu_state->hvf->fd, (void*)xsave, 4096)) { abort(); } @@ -202,17 +201,17 @@ void hvf_get_segments(CPUState *cpu_state) vmx_read_segment_descriptor(cpu_state, &seg, R_LDTR); hvf_get_segment(&env->ldt, &seg); - env->idt.limit = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_LIMIT); - env->idt.base = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_BASE); - env->gdt.limit = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_LIMIT); - env->gdt.base = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_BASE); + env->idt.limit = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_LIMIT); + env->idt.base = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_BASE); + env->gdt.limit = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_LIMIT); + env->gdt.base = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_BASE); - env->cr[0] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR0); + env->cr[0] = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR0); env->cr[2] = 0; - env->cr[3] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR3); - env->cr[4] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR4); + env->cr[3] = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR3); + env->cr[4] = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR4); - env->efer = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IA32_EFER); + env->efer = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IA32_EFER); } void hvf_get_msrs(CPUState *cpu_state) @@ -220,27 +219,27 @@ void hvf_get_msrs(CPUState *cpu_state) CPUX86State *env = &X86_CPU(cpu_state)->env; uint64_t tmp; - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_CS, &tmp); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_CS, &tmp); env->sysenter_cs = tmp; - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_ESP, &tmp); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_ESP, &tmp); env->sysenter_esp = tmp; - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_EIP, &tmp); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_EIP, &tmp); env->sysenter_eip = tmp; - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_STAR, &env->star); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_STAR, &env->star); #ifdef TARGET_X86_64 - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_CSTAR, &env->cstar); - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_KERNELGSBASE, &env->kernelgsbase); - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_FMASK, &env->fmask); - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_LSTAR, &env->lstar); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_CSTAR, &env->cstar); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_KERNELGSBASE, &env->kernelgsbase); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_FMASK, &env->fmask); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_LSTAR, &env->lstar); #endif - hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_APICBASE, &tmp); + hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_APICBASE, &tmp); - env->tsc = rdtscp() + rvmcs(cpu_state->hvf_fd, VMCS_TSC_OFFSET); + env->tsc = rdtscp() + rvmcs(cpu_state->hvf->fd, VMCS_TSC_OFFSET); } int hvf_put_registers(CPUState *cpu_state) @@ -248,26 +247,26 @@ int hvf_put_registers(CPUState *cpu_state) X86CPU *x86cpu = X86_CPU(cpu_state); CPUX86State *env = &x86cpu->env; - wreg(cpu_state->hvf_fd, HV_X86_RAX, env->regs[R_EAX]); - wreg(cpu_state->hvf_fd, HV_X86_RBX, env->regs[R_EBX]); - wreg(cpu_state->hvf_fd, HV_X86_RCX, env->regs[R_ECX]); - wreg(cpu_state->hvf_fd, HV_X86_RDX, env->regs[R_EDX]); - wreg(cpu_state->hvf_fd, HV_X86_RBP, env->regs[R_EBP]); - wreg(cpu_state->hvf_fd, HV_X86_RSP, env->regs[R_ESP]); - wreg(cpu_state->hvf_fd, HV_X86_RSI, env->regs[R_ESI]); - wreg(cpu_state->hvf_fd, HV_X86_RDI, env->regs[R_EDI]); - wreg(cpu_state->hvf_fd, HV_X86_R8, env->regs[8]); - wreg(cpu_state->hvf_fd, HV_X86_R9, env->regs[9]); - wreg(cpu_state->hvf_fd, HV_X86_R10, env->regs[10]); - wreg(cpu_state->hvf_fd, HV_X86_R11, env->regs[11]); - wreg(cpu_state->hvf_fd, HV_X86_R12, env->regs[12]); - wreg(cpu_state->hvf_fd, HV_X86_R13, env->regs[13]); - wreg(cpu_state->hvf_fd, HV_X86_R14, env->regs[14]); - wreg(cpu_state->hvf_fd, HV_X86_R15, env->regs[15]); - wreg(cpu_state->hvf_fd, HV_X86_RFLAGS, env->eflags); - wreg(cpu_state->hvf_fd, HV_X86_RIP, env->eip); + wreg(cpu_state->hvf->fd, HV_X86_RAX, env->regs[R_EAX]); + wreg(cpu_state->hvf->fd, HV_X86_RBX, env->regs[R_EBX]); + wreg(cpu_state->hvf->fd, HV_X86_RCX, env->regs[R_ECX]); + wreg(cpu_state->hvf->fd, HV_X86_RDX, env->regs[R_EDX]); + wreg(cpu_state->hvf->fd, HV_X86_RBP, env->regs[R_EBP]); + wreg(cpu_state->hvf->fd, HV_X86_RSP, env->regs[R_ESP]); + wreg(cpu_state->hvf->fd, HV_X86_RSI, env->regs[R_ESI]); + wreg(cpu_state->hvf->fd, HV_X86_RDI, env->regs[R_EDI]); + wreg(cpu_state->hvf->fd, HV_X86_R8, env->regs[8]); + wreg(cpu_state->hvf->fd, HV_X86_R9, env->regs[9]); + wreg(cpu_state->hvf->fd, HV_X86_R10, env->regs[10]); + wreg(cpu_state->hvf->fd, HV_X86_R11, env->regs[11]); + wreg(cpu_state->hvf->fd, HV_X86_R12, env->regs[12]); + wreg(cpu_state->hvf->fd, HV_X86_R13, env->regs[13]); + wreg(cpu_state->hvf->fd, HV_X86_R14, env->regs[14]); + wreg(cpu_state->hvf->fd, HV_X86_R15, env->regs[15]); + wreg(cpu_state->hvf->fd, HV_X86_RFLAGS, env->eflags); + wreg(cpu_state->hvf->fd, HV_X86_RIP, env->eip); - wreg(cpu_state->hvf_fd, HV_X86_XCR0, env->xcr0); + wreg(cpu_state->hvf->fd, HV_X86_XCR0, env->xcr0); hvf_put_xsave(cpu_state); @@ -275,14 +274,14 @@ int hvf_put_registers(CPUState *cpu_state) hvf_put_msrs(cpu_state); - wreg(cpu_state->hvf_fd, HV_X86_DR0, env->dr[0]); - wreg(cpu_state->hvf_fd, HV_X86_DR1, env->dr[1]); - wreg(cpu_state->hvf_fd, HV_X86_DR2, env->dr[2]); - wreg(cpu_state->hvf_fd, HV_X86_DR3, env->dr[3]); - wreg(cpu_state->hvf_fd, HV_X86_DR4, env->dr[4]); - wreg(cpu_state->hvf_fd, HV_X86_DR5, env->dr[5]); - wreg(cpu_state->hvf_fd, HV_X86_DR6, env->dr[6]); - wreg(cpu_state->hvf_fd, HV_X86_DR7, env->dr[7]); + wreg(cpu_state->hvf->fd, HV_X86_DR0, env->dr[0]); + wreg(cpu_state->hvf->fd, HV_X86_DR1, env->dr[1]); + wreg(cpu_state->hvf->fd, HV_X86_DR2, env->dr[2]); + wreg(cpu_state->hvf->fd, HV_X86_DR3, env->dr[3]); + wreg(cpu_state->hvf->fd, HV_X86_DR4, env->dr[4]); + wreg(cpu_state->hvf->fd, HV_X86_DR5, env->dr[5]); + wreg(cpu_state->hvf->fd, HV_X86_DR6, env->dr[6]); + wreg(cpu_state->hvf->fd, HV_X86_DR7, env->dr[7]); return 0; } @@ -292,40 +291,40 @@ int hvf_get_registers(CPUState *cpu_state) X86CPU *x86cpu = X86_CPU(cpu_state); CPUX86State *env = &x86cpu->env; - env->regs[R_EAX] = rreg(cpu_state->hvf_fd, HV_X86_RAX); - env->regs[R_EBX] = rreg(cpu_state->hvf_fd, HV_X86_RBX); - env->regs[R_ECX] = rreg(cpu_state->hvf_fd, HV_X86_RCX); - env->regs[R_EDX] = rreg(cpu_state->hvf_fd, HV_X86_RDX); - env->regs[R_EBP] = rreg(cpu_state->hvf_fd, HV_X86_RBP); - env->regs[R_ESP] = rreg(cpu_state->hvf_fd, HV_X86_RSP); - env->regs[R_ESI] = rreg(cpu_state->hvf_fd, HV_X86_RSI); - env->regs[R_EDI] = rreg(cpu_state->hvf_fd, HV_X86_RDI); - env->regs[8] = rreg(cpu_state->hvf_fd, HV_X86_R8); - env->regs[9] = rreg(cpu_state->hvf_fd, HV_X86_R9); - env->regs[10] = rreg(cpu_state->hvf_fd, HV_X86_R10); - env->regs[11] = rreg(cpu_state->hvf_fd, HV_X86_R11); - env->regs[12] = rreg(cpu_state->hvf_fd, HV_X86_R12); - env->regs[13] = rreg(cpu_state->hvf_fd, HV_X86_R13); - env->regs[14] = rreg(cpu_state->hvf_fd, HV_X86_R14); - env->regs[15] = rreg(cpu_state->hvf_fd, HV_X86_R15); + env->regs[R_EAX] = rreg(cpu_state->hvf->fd, HV_X86_RAX); + env->regs[R_EBX] = rreg(cpu_state->hvf->fd, HV_X86_RBX); + env->regs[R_ECX] = rreg(cpu_state->hvf->fd, HV_X86_RCX); + env->regs[R_EDX] = rreg(cpu_state->hvf->fd, HV_X86_RDX); + env->regs[R_EBP] = rreg(cpu_state->hvf->fd, HV_X86_RBP); + env->regs[R_ESP] = rreg(cpu_state->hvf->fd, HV_X86_RSP); + env->regs[R_ESI] = rreg(cpu_state->hvf->fd, HV_X86_RSI); + env->regs[R_EDI] = rreg(cpu_state->hvf->fd, HV_X86_RDI); + env->regs[8] = rreg(cpu_state->hvf->fd, HV_X86_R8); + env->regs[9] = rreg(cpu_state->hvf->fd, HV_X86_R9); + env->regs[10] = rreg(cpu_state->hvf->fd, HV_X86_R10); + env->regs[11] = rreg(cpu_state->hvf->fd, HV_X86_R11); + env->regs[12] = rreg(cpu_state->hvf->fd, HV_X86_R12); + env->regs[13] = rreg(cpu_state->hvf->fd, HV_X86_R13); + env->regs[14] = rreg(cpu_state->hvf->fd, HV_X86_R14); + env->regs[15] = rreg(cpu_state->hvf->fd, HV_X86_R15); - env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS); - env->eip = rreg(cpu_state->hvf_fd, HV_X86_RIP); + env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS); + env->eip = rreg(cpu_state->hvf->fd, HV_X86_RIP); hvf_get_xsave(cpu_state); - env->xcr0 = rreg(cpu_state->hvf_fd, HV_X86_XCR0); + env->xcr0 = rreg(cpu_state->hvf->fd, HV_X86_XCR0); hvf_get_segments(cpu_state); hvf_get_msrs(cpu_state); - env->dr[0] = rreg(cpu_state->hvf_fd, HV_X86_DR0); - env->dr[1] = rreg(cpu_state->hvf_fd, HV_X86_DR1); - env->dr[2] = rreg(cpu_state->hvf_fd, HV_X86_DR2); - env->dr[3] = rreg(cpu_state->hvf_fd, HV_X86_DR3); - env->dr[4] = rreg(cpu_state->hvf_fd, HV_X86_DR4); - env->dr[5] = rreg(cpu_state->hvf_fd, HV_X86_DR5); - env->dr[6] = rreg(cpu_state->hvf_fd, HV_X86_DR6); - env->dr[7] = rreg(cpu_state->hvf_fd, HV_X86_DR7); + env->dr[0] = rreg(cpu_state->hvf->fd, HV_X86_DR0); + env->dr[1] = rreg(cpu_state->hvf->fd, HV_X86_DR1); + env->dr[2] = rreg(cpu_state->hvf->fd, HV_X86_DR2); + env->dr[3] = rreg(cpu_state->hvf->fd, HV_X86_DR3); + env->dr[4] = rreg(cpu_state->hvf->fd, HV_X86_DR4); + env->dr[5] = rreg(cpu_state->hvf->fd, HV_X86_DR5); + env->dr[6] = rreg(cpu_state->hvf->fd, HV_X86_DR6); + env->dr[7] = rreg(cpu_state->hvf->fd, HV_X86_DR7); x86_update_hflags(env); return 0; @@ -334,16 +333,16 @@ int hvf_get_registers(CPUState *cpu_state) static void vmx_set_int_window_exiting(CPUState *cpu) { uint64_t val; - val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS); - wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val | + val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS); + wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val | VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING); } void vmx_clear_int_window_exiting(CPUState *cpu) { uint64_t val; - val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS); - wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val & + val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS); + wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val & ~VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING); } @@ -379,7 +378,7 @@ bool hvf_inject_interrupts(CPUState *cpu_state) uint64_t info = 0; if (have_event) { info = vector | intr_type | VMCS_INTR_VALID; - uint64_t reason = rvmcs(cpu_state->hvf_fd, VMCS_EXIT_REASON); + uint64_t reason = rvmcs(cpu_state->hvf->fd, VMCS_EXIT_REASON); if (env->nmi_injected && reason != EXIT_REASON_TASK_SWITCH) { vmx_clear_nmi_blocking(cpu_state); } @@ -388,17 +387,17 @@ bool hvf_inject_interrupts(CPUState *cpu_state) info &= ~(1 << 12); /* clear undefined bit */ if (intr_type == VMCS_INTR_T_SWINTR || intr_type == VMCS_INTR_T_SWEXCEPTION) { - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INST_LENGTH, env->ins_len); + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INST_LENGTH, env->ins_len); } if (env->has_error_code) { - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_EXCEPTION_ERROR, + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_EXCEPTION_ERROR, env->error_code); /* Indicate that VMCS_ENTRY_EXCEPTION_ERROR is valid */ info |= VMCS_INTR_DEL_ERRCODE; } /*printf("reinject %lx err %d\n", info, err);*/ - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info); + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, info); }; } @@ -406,7 +405,7 @@ bool hvf_inject_interrupts(CPUState *cpu_state) if (!(env->hflags2 & HF2_NMI_MASK) && !(info & VMCS_INTR_VALID)) { cpu_state->interrupt_request &= ~CPU_INTERRUPT_NMI; info = VMCS_INTR_VALID | VMCS_INTR_T_NMI | EXCP02_NMI; - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info); + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, info); } else { vmx_set_nmi_window_exiting(cpu_state); } @@ -418,7 +417,7 @@ bool hvf_inject_interrupts(CPUState *cpu_state) int line = cpu_get_pic_interrupt(&x86cpu->env); cpu_state->interrupt_request &= ~CPU_INTERRUPT_HARD; if (line >= 0) { - wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, line | + wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, line | VMCS_INTR_VALID | VMCS_INTR_T_HWINTR); } } @@ -434,10 +433,13 @@ int hvf_process_events(CPUState *cpu_state) X86CPU *cpu = X86_CPU(cpu_state); CPUX86State *env = &cpu->env; - env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS); + if (!cpu_state->vcpu_dirty) { + /* light weight sync for CPU_INTERRUPT_HARD and IF_MASK */ + env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS); + } if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) { - hvf_cpu_synchronize_state(cpu_state); + cpu_synchronize_state(cpu_state); do_cpu_init(cpu); } @@ -451,12 +453,12 @@ int hvf_process_events(CPUState *cpu_state) cpu_state->halted = 0; } if (cpu_state->interrupt_request & CPU_INTERRUPT_SIPI) { - hvf_cpu_synchronize_state(cpu_state); + cpu_synchronize_state(cpu_state); do_cpu_sipi(cpu); } if (cpu_state->interrupt_request & CPU_INTERRUPT_TPR) { cpu_state->interrupt_request &= ~CPU_INTERRUPT_TPR; - hvf_cpu_synchronize_state(cpu_state); + cpu_synchronize_state(cpu_state); apic_handle_tpr_access_report(cpu->apic_state, env->eip, env->tpr_access_type); } diff --git a/target/i386/hvf/x86hvf.h b/target/i386/hvf/x86hvf.h index 635ab0f34e..99ed8d608d 100644 --- a/target/i386/hvf/x86hvf.h +++ b/target/i386/hvf/x86hvf.h @@ -21,8 +21,6 @@ #include "x86_descr.h" int hvf_process_events(CPUState *); -int hvf_put_registers(CPUState *); -int hvf_get_registers(CPUState *); bool hvf_inject_interrupts(CPUState *); void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg, SegmentCache *qseg, bool is_tr); diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c index c660ad4293..5235bce8dc 100644 --- a/target/i386/kvm/kvm-cpu.c +++ b/target/i386/kvm/kvm-cpu.c @@ -47,6 +47,11 @@ static bool kvm_cpu_realizefn(CPUState *cs, Error **errp) /* * KVM-specific features that are automatically added/removed * from all CPU models when KVM is enabled. + * + * NOTE: features can be enabled by default only if they were + * already available in the oldest kernel version supported + * by the KVM accelerator (see "OS requirements" section at + * docs/system/target-i386.rst) */ static PropValue kvm_default_props[] = { { "kvmclock", "on" }, diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index d972eb4705..c676ee8b38 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -129,6 +129,7 @@ static int has_exception_payload; static bool has_msr_mcg_ext_ctl; static struct kvm_cpuid2 *cpuid_cache; +static struct kvm_cpuid2 *hv_cpuid_cache; static struct kvm_msr_list *kvm_feature_msrs; int kvm_has_pit_state2(void) @@ -715,8 +716,7 @@ unsigned long kvm_arch_vcpu_id(CPUState *cs) static bool hyperv_enabled(X86CPU *cpu) { - CPUState *cs = CPU(cpu); - return kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV) > 0 && + return kvm_check_extension(kvm_state, KVM_CAP_HYPERV) > 0 && ((cpu->hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_NOTIFY) || cpu->hyperv_features || cpu->hyperv_passthrough); } @@ -801,7 +801,8 @@ static bool tsc_is_stable_and_known(CPUX86State *env) static struct { const char *desc; struct { - uint32_t fw; + uint32_t func; + int reg; uint32_t bits; } flags[2]; uint64_t dependencies; @@ -809,25 +810,25 @@ static struct { [HYPERV_FEAT_RELAXED] = { .desc = "relaxed timing (hv-relaxed)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_HYPERCALL_AVAILABLE}, - {.fw = FEAT_HV_RECOMM_EAX, + {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, .bits = HV_RELAXED_TIMING_RECOMMENDED} } }, [HYPERV_FEAT_VAPIC] = { .desc = "virtual APIC (hv-vapic)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_HYPERCALL_AVAILABLE | HV_APIC_ACCESS_AVAILABLE}, - {.fw = FEAT_HV_RECOMM_EAX, + {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, .bits = HV_APIC_ACCESS_RECOMMENDED} } }, [HYPERV_FEAT_TIME] = { .desc = "clocksources (hv-time)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_HYPERCALL_AVAILABLE | HV_TIME_REF_COUNT_AVAILABLE | HV_REFERENCE_TSC_AVAILABLE} } @@ -835,42 +836,42 @@ static struct { [HYPERV_FEAT_CRASH] = { .desc = "crash MSRs (hv-crash)", .flags = { - {.fw = FEAT_HYPERV_EDX, + {.func = HV_CPUID_FEATURES, .reg = R_EDX, .bits = HV_GUEST_CRASH_MSR_AVAILABLE} } }, [HYPERV_FEAT_RESET] = { .desc = "reset MSR (hv-reset)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_RESET_AVAILABLE} } }, [HYPERV_FEAT_VPINDEX] = { .desc = "VP_INDEX MSR (hv-vpindex)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_VP_INDEX_AVAILABLE} } }, [HYPERV_FEAT_RUNTIME] = { .desc = "VP_RUNTIME MSR (hv-runtime)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_VP_RUNTIME_AVAILABLE} } }, [HYPERV_FEAT_SYNIC] = { .desc = "synthetic interrupt controller (hv-synic)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_SYNIC_AVAILABLE} } }, [HYPERV_FEAT_STIMER] = { .desc = "synthetic timers (hv-stimer)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_SYNTIMERS_AVAILABLE} }, .dependencies = BIT(HYPERV_FEAT_SYNIC) | BIT(HYPERV_FEAT_TIME) @@ -878,23 +879,23 @@ static struct { [HYPERV_FEAT_FREQUENCIES] = { .desc = "frequency MSRs (hv-frequencies)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_ACCESS_FREQUENCY_MSRS}, - {.fw = FEAT_HYPERV_EDX, + {.func = HV_CPUID_FEATURES, .reg = R_EDX, .bits = HV_FREQUENCY_MSRS_AVAILABLE} } }, [HYPERV_FEAT_REENLIGHTENMENT] = { .desc = "reenlightenment MSRs (hv-reenlightenment)", .flags = { - {.fw = FEAT_HYPERV_EAX, + {.func = HV_CPUID_FEATURES, .reg = R_EAX, .bits = HV_ACCESS_REENLIGHTENMENTS_CONTROL} } }, [HYPERV_FEAT_TLBFLUSH] = { .desc = "paravirtualized TLB flush (hv-tlbflush)", .flags = { - {.fw = FEAT_HV_RECOMM_EAX, + {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, .bits = HV_REMOTE_TLB_FLUSH_RECOMMENDED | HV_EX_PROCESSOR_MASKS_RECOMMENDED} }, @@ -903,7 +904,7 @@ static struct { [HYPERV_FEAT_EVMCS] = { .desc = "enlightened VMCS (hv-evmcs)", .flags = { - {.fw = FEAT_HV_RECOMM_EAX, + {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, .bits = HV_ENLIGHTENED_VMCS_RECOMMENDED} }, .dependencies = BIT(HYPERV_FEAT_VAPIC) @@ -911,7 +912,7 @@ static struct { [HYPERV_FEAT_IPI] = { .desc = "paravirtualized IPI (hv-ipi)", .flags = { - {.fw = FEAT_HV_RECOMM_EAX, + {.func = HV_CPUID_ENLIGHTMENT_INFO, .reg = R_EAX, .bits = HV_CLUSTER_IPI_RECOMMENDED | HV_EX_PROCESSOR_MASKS_RECOMMENDED} }, @@ -920,14 +921,15 @@ static struct { [HYPERV_FEAT_STIMER_DIRECT] = { .desc = "direct mode synthetic timers (hv-stimer-direct)", .flags = { - {.fw = FEAT_HYPERV_EDX, + {.func = HV_CPUID_FEATURES, .reg = R_EDX, .bits = HV_STIMER_DIRECT_MODE_AVAILABLE} }, .dependencies = BIT(HYPERV_FEAT_STIMER) }, }; -static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max) +static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max, + bool do_sys_ioctl) { struct kvm_cpuid2 *cpuid; int r, size; @@ -936,7 +938,11 @@ static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max) cpuid = g_malloc0(size); cpuid->nent = max; - r = kvm_vcpu_ioctl(cs, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + if (do_sys_ioctl) { + r = kvm_ioctl(kvm_state, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + } else { + r = kvm_vcpu_ioctl(cs, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + } if (r == 0 && cpuid->nent >= max) { r = -E2BIG; } @@ -960,16 +966,38 @@ static struct kvm_cpuid2 *try_get_hv_cpuid(CPUState *cs, int max) static struct kvm_cpuid2 *get_supported_hv_cpuid(CPUState *cs) { struct kvm_cpuid2 *cpuid; - int max = 7; /* 0x40000000..0x40000005, 0x4000000A */ + /* 0x40000000..0x40000005, 0x4000000A, 0x40000080..0x40000080 leaves */ + int max = 10; + int i; + bool do_sys_ioctl; + + do_sys_ioctl = + kvm_check_extension(kvm_state, KVM_CAP_SYS_HYPERV_CPUID) > 0; /* * When the buffer is too small, KVM_GET_SUPPORTED_HV_CPUID fails with * -E2BIG, however, it doesn't report back the right size. Keep increasing * it and re-trying until we succeed. */ - while ((cpuid = try_get_hv_cpuid(cs, max)) == NULL) { + while ((cpuid = try_get_hv_cpuid(cs, max, do_sys_ioctl)) == NULL) { max++; } + + /* + * KVM_GET_SUPPORTED_HV_CPUID does not set EVMCS CPUID bit before + * KVM_CAP_HYPERV_ENLIGHTENED_VMCS is enabled but we want to get the + * information early, just check for the capability and set the bit + * manually. + */ + if (!do_sys_ioctl && kvm_check_extension(cs->kvm_state, + KVM_CAP_HYPERV_ENLIGHTENED_VMCS) > 0) { + for (i = 0; i < cpuid->nent; i++) { + if (cpuid->entries[i].function == HV_CPUID_ENLIGHTMENT_INFO) { + cpuid->entries[i].eax |= HV_ENLIGHTENED_VMCS_RECOMMENDED; + } + } + } + return cpuid; } @@ -1066,56 +1094,62 @@ static struct kvm_cpuid2 *get_supported_hv_cpuid_legacy(CPUState *cs) return cpuid; } -static int hv_cpuid_get_fw(struct kvm_cpuid2 *cpuid, int fw, uint32_t *r) +static uint32_t hv_cpuid_get_host(CPUState *cs, uint32_t func, int reg) { struct kvm_cpuid_entry2 *entry; - uint32_t func; - int reg; + struct kvm_cpuid2 *cpuid; - switch (fw) { - case FEAT_HYPERV_EAX: - reg = R_EAX; - func = HV_CPUID_FEATURES; - break; - case FEAT_HYPERV_EDX: - reg = R_EDX; - func = HV_CPUID_FEATURES; - break; - case FEAT_HV_RECOMM_EAX: - reg = R_EAX; - func = HV_CPUID_ENLIGHTMENT_INFO; - break; - default: - return -EINVAL; + if (hv_cpuid_cache) { + cpuid = hv_cpuid_cache; + } else { + if (kvm_check_extension(kvm_state, KVM_CAP_HYPERV_CPUID) > 0) { + cpuid = get_supported_hv_cpuid(cs); + } else { + cpuid = get_supported_hv_cpuid_legacy(cs); + } + hv_cpuid_cache = cpuid; + } + + if (!cpuid) { + return 0; } entry = cpuid_find_entry(cpuid, func, 0); if (!entry) { - return -ENOENT; + return 0; } - switch (reg) { - case R_EAX: - *r = entry->eax; - break; - case R_EDX: - *r = entry->edx; - break; - default: - return -EINVAL; + return cpuid_entry_get_reg(entry, reg); +} + +static bool hyperv_feature_supported(CPUState *cs, int feature) +{ + uint32_t func, bits; + int i, reg; + + for (i = 0; i < ARRAY_SIZE(kvm_hyperv_properties[feature].flags); i++) { + + func = kvm_hyperv_properties[feature].flags[i].func; + reg = kvm_hyperv_properties[feature].flags[i].reg; + bits = kvm_hyperv_properties[feature].flags[i].bits; + + if (!func) { + continue; + } + + if ((hv_cpuid_get_host(cs, func, reg) & bits) != bits) { + return false; + } } - return 0; + return true; } -static int hv_cpuid_check_and_set(CPUState *cs, struct kvm_cpuid2 *cpuid, - int feature) +static int hv_cpuid_check_and_set(CPUState *cs, int feature, Error **errp) { X86CPU *cpu = X86_CPU(cs); - CPUX86State *env = &cpu->env; - uint32_t r, fw, bits; uint64_t deps; - int i, dep_feat; + int dep_feat; if (!hyperv_feat_enabled(cpu, feature) && !cpu->hyperv_passthrough) { return 0; @@ -1125,35 +1159,22 @@ static int hv_cpuid_check_and_set(CPUState *cs, struct kvm_cpuid2 *cpuid, while (deps) { dep_feat = ctz64(deps); if (!(hyperv_feat_enabled(cpu, dep_feat))) { - fprintf(stderr, - "Hyper-V %s requires Hyper-V %s\n", - kvm_hyperv_properties[feature].desc, - kvm_hyperv_properties[dep_feat].desc); - return 1; + error_setg(errp, "Hyper-V %s requires Hyper-V %s", + kvm_hyperv_properties[feature].desc, + kvm_hyperv_properties[dep_feat].desc); + return 1; } deps &= ~(1ull << dep_feat); } - for (i = 0; i < ARRAY_SIZE(kvm_hyperv_properties[feature].flags); i++) { - fw = kvm_hyperv_properties[feature].flags[i].fw; - bits = kvm_hyperv_properties[feature].flags[i].bits; - - if (!fw) { - continue; - } - - if (hv_cpuid_get_fw(cpuid, fw, &r) || (r & bits) != bits) { - if (hyperv_feat_enabled(cpu, feature)) { - fprintf(stderr, - "Hyper-V %s is not supported by kernel\n", - kvm_hyperv_properties[feature].desc); - return 1; - } else { - return 0; - } + if (!hyperv_feature_supported(cs, feature)) { + if (hyperv_feat_enabled(cpu, feature)) { + error_setg(errp, "Hyper-V %s is not supported by kernel", + kvm_hyperv_properties[feature].desc); + return 1; + } else { + return 0; } - - env->features[fw] |= bits; } if (cpu->hyperv_passthrough) { @@ -1163,157 +1184,156 @@ static int hv_cpuid_check_and_set(CPUState *cs, struct kvm_cpuid2 *cpuid, return 0; } -/* - * Fill in Hyper-V CPUIDs. Returns the number of entries filled in cpuid_ent in - * case of success, errno < 0 in case of failure and 0 when no Hyper-V - * extentions are enabled. - */ -static int hyperv_handle_properties(CPUState *cs, - struct kvm_cpuid_entry2 *cpuid_ent) +static uint32_t hv_build_cpuid_leaf(CPUState *cs, uint32_t func, int reg) { X86CPU *cpu = X86_CPU(cs); - CPUX86State *env = &cpu->env; - struct kvm_cpuid2 *cpuid; - struct kvm_cpuid_entry2 *c; - uint32_t cpuid_i = 0; - int r; + uint32_t r = 0; + int i, j; - if (!hyperv_enabled(cpu)) - return 0; - - if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS) || - cpu->hyperv_passthrough) { - uint16_t evmcs_version; - - r = kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_ENLIGHTENED_VMCS, 0, - (uintptr_t)&evmcs_version); - - if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS) && r) { - fprintf(stderr, "Hyper-V %s is not supported by kernel\n", - kvm_hyperv_properties[HYPERV_FEAT_EVMCS].desc); - return -ENOSYS; - } - - if (!r) { - env->features[FEAT_HV_RECOMM_EAX] |= - HV_ENLIGHTENED_VMCS_RECOMMENDED; - env->features[FEAT_HV_NESTED_EAX] = evmcs_version; - } - } - - if (kvm_check_extension(cs->kvm_state, KVM_CAP_HYPERV_CPUID) > 0) { - cpuid = get_supported_hv_cpuid(cs); - } else { - cpuid = get_supported_hv_cpuid_legacy(cs); - } - - if (cpu->hyperv_passthrough) { - memcpy(cpuid_ent, &cpuid->entries[0], - cpuid->nent * sizeof(cpuid->entries[0])); - - c = cpuid_find_entry(cpuid, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, 0); - if (c) { - cpu->hyperv_vendor_id[0] = c->ebx; - cpu->hyperv_vendor_id[1] = c->ecx; - cpu->hyperv_vendor_id[2] = c->edx; - } - - c = cpuid_find_entry(cpuid, HV_CPUID_INTERFACE, 0); - if (c) { - cpu->hyperv_interface_id[0] = c->eax; - cpu->hyperv_interface_id[1] = c->ebx; - cpu->hyperv_interface_id[2] = c->ecx; - cpu->hyperv_interface_id[3] = c->edx; + for (i = 0; i < ARRAY_SIZE(kvm_hyperv_properties); i++) { + if (!hyperv_feat_enabled(cpu, i)) { + continue; } - c = cpuid_find_entry(cpuid, HV_CPUID_VERSION, 0); - if (c) { - cpu->hyperv_version_id[0] = c->eax; - cpu->hyperv_version_id[1] = c->ebx; - cpu->hyperv_version_id[2] = c->ecx; - cpu->hyperv_version_id[3] = c->edx; - } + for (j = 0; j < ARRAY_SIZE(kvm_hyperv_properties[i].flags); j++) { + if (kvm_hyperv_properties[i].flags[j].func != func) { + continue; + } + if (kvm_hyperv_properties[i].flags[j].reg != reg) { + continue; + } - c = cpuid_find_entry(cpuid, HV_CPUID_FEATURES, 0); - if (c) { - env->features[FEAT_HYPERV_EAX] = c->eax; - env->features[FEAT_HYPERV_EBX] = c->ebx; - env->features[FEAT_HYPERV_EDX] = c->edx; + r |= kvm_hyperv_properties[i].flags[j].bits; } + } - c = cpuid_find_entry(cpuid, HV_CPUID_IMPLEMENT_LIMITS, 0); - if (c) { - cpu->hv_max_vps = c->eax; - cpu->hyperv_limits[0] = c->ebx; - cpu->hyperv_limits[1] = c->ecx; - cpu->hyperv_limits[2] = c->edx; - } + return r; +} - c = cpuid_find_entry(cpuid, HV_CPUID_ENLIGHTMENT_INFO, 0); - if (c) { - env->features[FEAT_HV_RECOMM_EAX] = c->eax; +/* + * Expand Hyper-V CPU features. In partucular, check that all the requested + * features are supported by the host and the sanity of the configuration + * (that all the required dependencies are included). Also, this takes care + * of 'hv_passthrough' mode and fills the environment with all supported + * Hyper-V features. + */ +static void hyperv_expand_features(CPUState *cs, Error **errp) +{ + X86CPU *cpu = X86_CPU(cs); - /* hv-spinlocks may have been overriden */ - if (cpu->hyperv_spinlock_attempts != HYPERV_SPINLOCK_NEVER_NOTIFY) { - c->ebx = cpu->hyperv_spinlock_attempts; - } - } - c = cpuid_find_entry(cpuid, HV_CPUID_NESTED_FEATURES, 0); - if (c) { - env->features[FEAT_HV_NESTED_EAX] = c->eax; - } - } + if (!hyperv_enabled(cpu)) + return; - if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_ON) { - env->features[FEAT_HV_RECOMM_EAX] |= HV_NO_NONARCH_CORESHARING; - } else if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_AUTO) { - c = cpuid_find_entry(cpuid, HV_CPUID_ENLIGHTMENT_INFO, 0); - if (c) { - env->features[FEAT_HV_RECOMM_EAX] |= - c->eax & HV_NO_NONARCH_CORESHARING; - } + if (cpu->hyperv_passthrough) { + cpu->hyperv_vendor_id[0] = + hv_cpuid_get_host(cs, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, R_EBX); + cpu->hyperv_vendor_id[1] = + hv_cpuid_get_host(cs, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, R_ECX); + cpu->hyperv_vendor_id[2] = + hv_cpuid_get_host(cs, HV_CPUID_VENDOR_AND_MAX_FUNCTIONS, R_EDX); + cpu->hyperv_vendor = g_realloc(cpu->hyperv_vendor, + sizeof(cpu->hyperv_vendor_id) + 1); + memcpy(cpu->hyperv_vendor, cpu->hyperv_vendor_id, + sizeof(cpu->hyperv_vendor_id)); + cpu->hyperv_vendor[sizeof(cpu->hyperv_vendor_id)] = 0; + + cpu->hyperv_interface_id[0] = + hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EAX); + cpu->hyperv_interface_id[1] = + hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EBX); + cpu->hyperv_interface_id[2] = + hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_ECX); + cpu->hyperv_interface_id[3] = + hv_cpuid_get_host(cs, HV_CPUID_INTERFACE, R_EDX); + + cpu->hyperv_version_id[0] = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EAX); + cpu->hyperv_version_id[1] = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EBX); + cpu->hyperv_version_id[2] = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_ECX); + cpu->hyperv_version_id[3] = + hv_cpuid_get_host(cs, HV_CPUID_VERSION, R_EDX); + + cpu->hv_max_vps = hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, + R_EAX); + cpu->hyperv_limits[0] = + hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_EBX); + cpu->hyperv_limits[1] = + hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_ECX); + cpu->hyperv_limits[2] = + hv_cpuid_get_host(cs, HV_CPUID_IMPLEMENT_LIMITS, R_EDX); + + cpu->hyperv_spinlock_attempts = + hv_cpuid_get_host(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EBX); } /* Features */ - r = hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_RELAXED); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_VAPIC); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_TIME); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_CRASH); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_RESET); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_VPINDEX); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_RUNTIME); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_SYNIC); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_STIMER); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_FREQUENCIES); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_REENLIGHTENMENT); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_TLBFLUSH); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_EVMCS); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_IPI); - r |= hv_cpuid_check_and_set(cs, cpuid, HYPERV_FEAT_STIMER_DIRECT); + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_RELAXED, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_VAPIC, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_TIME, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_CRASH, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_RESET, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_VPINDEX, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_RUNTIME, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_SYNIC, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_STIMER, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_FREQUENCIES, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_REENLIGHTENMENT, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_TLBFLUSH, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_EVMCS, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_IPI, errp)) { + return; + } + if (hv_cpuid_check_and_set(cs, HYPERV_FEAT_STIMER_DIRECT, errp)) { + return; + } /* Additional dependencies not covered by kvm_hyperv_properties[] */ if (hyperv_feat_enabled(cpu, HYPERV_FEAT_SYNIC) && !cpu->hyperv_synic_kvm_only && !hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX)) { - fprintf(stderr, "Hyper-V %s requires Hyper-V %s\n", - kvm_hyperv_properties[HYPERV_FEAT_SYNIC].desc, - kvm_hyperv_properties[HYPERV_FEAT_VPINDEX].desc); - r |= 1; - } - - /* Not exposed by KVM but needed to make CPU hotplug in Windows work */ - env->features[FEAT_HYPERV_EDX] |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE; - - if (r) { - r = -ENOSYS; - goto free; + error_setg(errp, "Hyper-V %s requires Hyper-V %s", + kvm_hyperv_properties[HYPERV_FEAT_SYNIC].desc, + kvm_hyperv_properties[HYPERV_FEAT_VPINDEX].desc); } +} - if (cpu->hyperv_passthrough) { - /* We already copied all feature words from KVM as is */ - r = cpuid->nent; - goto free; - } +/* + * Fill in Hyper-V CPUIDs. Returns the number of entries filled in cpuid_ent. + */ +static int hyperv_fill_cpuids(CPUState *cs, + struct kvm_cpuid_entry2 *cpuid_ent) +{ + X86CPU *cpu = X86_CPU(cs); + struct kvm_cpuid_entry2 *c; + uint32_t cpuid_i = 0; c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_VENDOR_AND_MAX_FUNCTIONS; @@ -1339,15 +1359,25 @@ static int hyperv_handle_properties(CPUState *cs, c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_FEATURES; - c->eax = env->features[FEAT_HYPERV_EAX]; - c->ebx = env->features[FEAT_HYPERV_EBX]; - c->edx = env->features[FEAT_HYPERV_EDX]; + c->eax = hv_build_cpuid_leaf(cs, HV_CPUID_FEATURES, R_EAX); + c->ebx = hv_build_cpuid_leaf(cs, HV_CPUID_FEATURES, R_EBX); + c->edx = hv_build_cpuid_leaf(cs, HV_CPUID_FEATURES, R_EDX); + + /* Not exposed by KVM but needed to make CPU hotplug in Windows work */ + c->edx |= HV_CPU_DYNAMIC_PARTITIONING_AVAILABLE; c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_ENLIGHTMENT_INFO; - c->eax = env->features[FEAT_HV_RECOMM_EAX]; + c->eax = hv_build_cpuid_leaf(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EAX); c->ebx = cpu->hyperv_spinlock_attempts; + if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_ON) { + c->eax |= HV_NO_NONARCH_CORESHARING; + } else if (cpu->hyperv_no_nonarch_cs == ON_OFF_AUTO_AUTO) { + c->eax |= hv_cpuid_get_host(cs, HV_CPUID_ENLIGHTMENT_INFO, R_EAX) & + HV_NO_NONARCH_CORESHARING; + } + c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_IMPLEMENT_LIMITS; c->eax = cpu->hv_max_vps; @@ -1367,14 +1397,10 @@ static int hyperv_handle_properties(CPUState *cs, c = &cpuid_ent[cpuid_i++]; c->function = HV_CPUID_NESTED_FEATURES; - c->eax = env->features[FEAT_HV_NESTED_EAX]; + c->eax = cpu->hyperv_nested[0]; } - r = cpuid_i; - -free: - g_free(cpuid); - return r; + return cpuid_i; } static Error *hv_passthrough_mig_blocker; @@ -1458,6 +1484,21 @@ static int hyperv_init_vcpu(X86CPU *cpu) } } + if (hyperv_feat_enabled(cpu, HYPERV_FEAT_EVMCS)) { + uint16_t evmcs_version; + + ret = kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_ENLIGHTENED_VMCS, 0, + (uintptr_t)&evmcs_version); + + if (ret < 0) { + fprintf(stderr, "Hyper-V %s is not supported by kernel\n", + kvm_hyperv_properties[HYPERV_FEAT_EVMCS].desc); + return ret; + } + + cpu->hyperv_nested[0] = evmcs_version; + } + return 0; } @@ -1516,11 +1557,19 @@ int kvm_arch_init_vcpu(CPUState *cs) env->apic_bus_freq = KVM_APIC_BUS_FREQUENCY; /* Paravirtualization CPUIDs */ - r = hyperv_handle_properties(cs, cpuid_data.entries); - if (r < 0) { - return r; - } else if (r > 0) { - cpuid_i = r; + hyperv_expand_features(cs, &local_err); + if (local_err) { + error_report_err(local_err); + return -ENOSYS; + } + + if (hyperv_enabled(cpu)) { + r = hyperv_init_vcpu(cpu); + if (r) { + return r; + } + + cpuid_i = hyperv_fill_cpuids(cs, cpuid_data.entries); kvm_base = KVM_CPUID_SIGNATURE_NEXT; has_msr_hv_hypercall = true; } @@ -1869,11 +1918,6 @@ int kvm_arch_init_vcpu(CPUState *cs) kvm_init_msrs(cpu); - r = hyperv_init_vcpu(cpu); - if (r) { - goto fail; - } - return 0; fail: diff --git a/target/i386/kvm/trace-events b/target/i386/kvm/trace-events index b4e2d9e4ea..7c369db1e1 100644 --- a/target/i386/kvm/trace-events +++ b/target/i386/kvm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # kvm.c kvm_x86_fixup_msi_error(uint32_t gsi) "VT-d failed to remap interrupt for GSI %" PRIu32 diff --git a/target/i386/monitor.c b/target/i386/monitor.c index 5994408bee..119211f0b0 100644 --- a/target/i386/monitor.c +++ b/target/i386/monitor.c @@ -757,3 +757,9 @@ void qmp_sev_inject_launch_secret(const char *packet_hdr, sev_inject_launch_secret(packet_hdr, secret, gpa, errp); } + +SevAttestationReport * +qmp_query_sev_attestation_report(const char *mnonce, Error **errp) +{ + return sev_get_attestation_report(mnonce, errp); +} diff --git a/target/i386/sev-stub.c b/target/i386/sev-stub.c index 0207f1c5aa..0227cb5177 100644 --- a/target/i386/sev-stub.c +++ b/target/i386/sev-stub.c @@ -74,3 +74,10 @@ int sev_es_save_reset_vector(void *flash_ptr, uint64_t flash_size) { abort(); } + +SevAttestationReport * +sev_get_attestation_report(const char *mnonce, Error **errp) +{ + error_setg(errp, "SEV is not available in this QEMU"); + return NULL; +} diff --git a/target/i386/sev.c b/target/i386/sev.c index 41f7800b5f..83df8c09f6 100644 --- a/target/i386/sev.c +++ b/target/i386/sev.c @@ -87,29 +87,31 @@ static SevGuestState *sev_guest; static Error *sev_mig_blocker; static const char *const sev_fw_errlist[] = { - "", - "Platform state is invalid", - "Guest state is invalid", - "Platform configuration is invalid", - "Buffer too small", - "Platform is already owned", - "Certificate is invalid", - "Policy is not allowed", - "Guest is not active", - "Invalid address", - "Bad signature", - "Bad measurement", - "Asid is already owned", - "Invalid ASID", - "WBINVD is required", - "DF_FLUSH is required", - "Guest handle is invalid", - "Invalid command", - "Guest is active", - "Hardware error", - "Hardware unsafe", - "Feature not supported", - "Invalid parameter" + [SEV_RET_SUCCESS] = "", + [SEV_RET_INVALID_PLATFORM_STATE] = "Platform state is invalid", + [SEV_RET_INVALID_GUEST_STATE] = "Guest state is invalid", + [SEV_RET_INAVLID_CONFIG] = "Platform configuration is invalid", + [SEV_RET_INVALID_LEN] = "Buffer too small", + [SEV_RET_ALREADY_OWNED] = "Platform is already owned", + [SEV_RET_INVALID_CERTIFICATE] = "Certificate is invalid", + [SEV_RET_POLICY_FAILURE] = "Policy is not allowed", + [SEV_RET_INACTIVE] = "Guest is not active", + [SEV_RET_INVALID_ADDRESS] = "Invalid address", + [SEV_RET_BAD_SIGNATURE] = "Bad signature", + [SEV_RET_BAD_MEASUREMENT] = "Bad measurement", + [SEV_RET_ASID_OWNED] = "ASID is already owned", + [SEV_RET_INVALID_ASID] = "Invalid ASID", + [SEV_RET_WBINVD_REQUIRED] = "WBINVD is required", + [SEV_RET_DFFLUSH_REQUIRED] = "DF_FLUSH is required", + [SEV_RET_INVALID_GUEST] = "Guest handle is invalid", + [SEV_RET_INVALID_COMMAND] = "Invalid command", + [SEV_RET_ACTIVE] = "Guest is active", + [SEV_RET_HWSEV_RET_PLATFORM] = "Hardware error", + [SEV_RET_HWSEV_RET_UNSAFE] = "Hardware unsafe", + [SEV_RET_UNSUPPORTED] = "Feature not supported", + [SEV_RET_INVALID_PARAM] = "Invalid parameter", + [SEV_RET_RESOURCE_LIMIT] = "Required firmware resource depleted", + [SEV_RET_SECURE_DATA_INVALID] = "Part-specific integrity check failure", }; #define SEV_FW_MAX_ERROR ARRAY_SIZE(sev_fw_errlist) @@ -492,6 +494,73 @@ out: return cap; } +SevAttestationReport * +sev_get_attestation_report(const char *mnonce, Error **errp) +{ + struct kvm_sev_attestation_report input = {}; + SevAttestationReport *report = NULL; + SevGuestState *sev = sev_guest; + guchar *data; + guchar *buf; + gsize len; + int err = 0, ret; + + if (!sev_enabled()) { + error_setg(errp, "SEV is not enabled"); + return NULL; + } + + /* lets decode the mnonce string */ + buf = g_base64_decode(mnonce, &len); + if (!buf) { + error_setg(errp, "SEV: failed to decode mnonce input"); + return NULL; + } + + /* verify the input mnonce length */ + if (len != sizeof(input.mnonce)) { + error_setg(errp, "SEV: mnonce must be %zu bytes (got %" G_GSIZE_FORMAT ")", + sizeof(input.mnonce), len); + g_free(buf); + return NULL; + } + + /* Query the report length */ + ret = sev_ioctl(sev->sev_fd, KVM_SEV_GET_ATTESTATION_REPORT, + &input, &err); + if (ret < 0) { + if (err != SEV_RET_INVALID_LEN) { + error_setg(errp, "failed to query the attestation report length " + "ret=%d fw_err=%d (%s)", ret, err, fw_error_to_str(err)); + g_free(buf); + return NULL; + } + } + + data = g_malloc(input.len); + input.uaddr = (unsigned long)data; + memcpy(input.mnonce, buf, sizeof(input.mnonce)); + + /* Query the report */ + ret = sev_ioctl(sev->sev_fd, KVM_SEV_GET_ATTESTATION_REPORT, + &input, &err); + if (ret) { + error_setg_errno(errp, errno, "Failed to get attestation report" + " ret=%d fw_err=%d (%s)", ret, err, fw_error_to_str(err)); + goto e_free_data; + } + + report = g_new0(SevAttestationReport, 1); + report->data = g_base64_encode(data, input.len); + + trace_kvm_sev_attestation_report(mnonce, report->data); + +e_free_data: + g_free(data); + g_free(buf); + return report; +} + static int sev_read_file_base64(const char *filename, guchar **data, gsize *len) { diff --git a/target/i386/sev_i386.h b/target/i386/sev_i386.h index ae221d4c72..ae6d840478 100644 --- a/target/i386/sev_i386.h +++ b/target/i386/sev_i386.h @@ -35,5 +35,7 @@ extern uint32_t sev_get_cbit_position(void); extern uint32_t sev_get_reduced_phys_bits(void); extern char *sev_get_launch_measurement(void); extern SevCapability *sev_get_capabilities(Error **errp); +extern SevAttestationReport * +sev_get_attestation_report(const char *mnonce, Error **errp); #endif diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index 1b30f1bb73..4e11965067 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -673,38 +673,40 @@ uint32_t helper_fnstcw(CPUX86State *env) void update_fp_status(CPUX86State *env) { - int rnd_type; + FloatRoundMode rnd_mode; + FloatX80RoundPrec rnd_prec; /* set rounding mode */ switch (env->fpuc & FPU_RC_MASK) { default: case FPU_RC_NEAR: - rnd_type = float_round_nearest_even; + rnd_mode = float_round_nearest_even; break; case FPU_RC_DOWN: - rnd_type = float_round_down; + rnd_mode = float_round_down; break; case FPU_RC_UP: - rnd_type = float_round_up; + rnd_mode = float_round_up; break; case FPU_RC_CHOP: - rnd_type = float_round_to_zero; + rnd_mode = float_round_to_zero; break; } - set_float_rounding_mode(rnd_type, &env->fp_status); + set_float_rounding_mode(rnd_mode, &env->fp_status); + switch ((env->fpuc >> 8) & 3) { case 0: - rnd_type = 32; + rnd_prec = floatx80_precision_s; break; case 2: - rnd_type = 64; + rnd_prec = floatx80_precision_d; break; case 3: default: - rnd_type = 80; + rnd_prec = floatx80_precision_x; break; } - set_floatx80_rounding_precision(rnd_type, &env->fp_status); + set_floatx80_rounding_precision(rnd_prec, &env->fp_status); } void helper_fldcw(CPUX86State *env, uint32_t val) @@ -1074,7 +1076,8 @@ void helper_f2xm1(CPUX86State *env) &sig2); /* This result is inexact. */ sig1 |= 1; - ST0 = normalizeRoundAndPackFloatx80(80, sign, exp, sig0, sig1, + ST0 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + sign, exp, sig0, sig1, &env->fp_status); } } else { @@ -1083,9 +1086,10 @@ void helper_f2xm1(CPUX86State *env) int32_t n, aexp, bexp; uint64_t asig0, asig1, asig2, bsig0, bsig1; FloatRoundMode save_mode = env->fp_status.float_rounding_mode; - signed char save_prec = env->fp_status.floatx80_rounding_precision; + FloatX80RoundPrec save_prec = + env->fp_status.floatx80_rounding_precision; env->fp_status.float_rounding_mode = float_round_nearest_even; - env->fp_status.floatx80_rounding_precision = 80; + env->fp_status.floatx80_rounding_precision = floatx80_precision_x; /* Find the nearest multiple of 1/32 to the argument. */ tmp = floatx80_scalbn(ST0, 5, &env->fp_status); @@ -1183,7 +1187,8 @@ void helper_f2xm1(CPUX86State *env) env->fp_status.float_rounding_mode = save_mode; /* This result is inexact. */ asig1 |= 1; - ST0 = normalizeRoundAndPackFloatx80(80, asign, aexp, asig0, asig1, + ST0 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + asign, aexp, asig0, asig1, &env->fp_status); } @@ -1301,8 +1306,9 @@ void helper_fpatan(CPUX86State *env) * division is exact, the result of fpatan is still inexact * (and underflowing where appropriate). */ - signed char save_prec = env->fp_status.floatx80_rounding_precision; - env->fp_status.floatx80_rounding_precision = 80; + FloatX80RoundPrec save_prec = + env->fp_status.floatx80_rounding_precision; + env->fp_status.floatx80_rounding_precision = floatx80_precision_x; ST1 = floatx80_div(ST1, ST0, &env->fp_status); env->fp_status.floatx80_rounding_precision = save_prec; if (!floatx80_is_zero(ST1) && @@ -1321,7 +1327,8 @@ void helper_fpatan(CPUX86State *env) if (exp == 0) { normalizeFloatx80Subnormal(sig, &exp, &sig); } - ST1 = normalizeRoundAndPackFloatx80(80, sign, exp, sig - 1, + ST1 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + sign, exp, sig - 1, -1, &env->fp_status); } } else { @@ -1377,9 +1384,10 @@ void helper_fpatan(CPUX86State *env) uint64_t azsig2, azsig3, axsig0, axsig1; floatx80 x8; FloatRoundMode save_mode = env->fp_status.float_rounding_mode; - signed char save_prec = env->fp_status.floatx80_rounding_precision; + FloatX80RoundPrec save_prec = + env->fp_status.floatx80_rounding_precision; env->fp_status.float_rounding_mode = float_round_nearest_even; - env->fp_status.floatx80_rounding_precision = 80; + env->fp_status.floatx80_rounding_precision = floatx80_precision_x; if (arg0_exp == 0) { normalizeFloatx80Subnormal(arg0_sig, &arg0_exp, &arg0_sig); @@ -1448,7 +1456,8 @@ void helper_fpatan(CPUX86State *env) * Split x as x = t + y, where t = n/8 is the nearest * multiple of 1/8 to x. */ - x8 = normalizeRoundAndPackFloatx80(80, false, xexp + 3, xsig0, + x8 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + false, xexp + 3, xsig0, xsig1, &env->fp_status); n = floatx80_to_int32(x8, &env->fp_status); if (n == 0) { @@ -1569,7 +1578,7 @@ void helper_fpatan(CPUX86State *env) /* Compute z^2. */ mul128To256(zsig0, zsig1, zsig0, zsig1, &z2sig0, &z2sig1, &z2sig2, &z2sig3); - z2 = normalizeRoundAndPackFloatx80(80, false, + z2 = normalizeRoundAndPackFloatx80(floatx80_precision_x, false, zexp + zexp - 0x3ffe, z2sig0, z2sig1, &env->fp_status); @@ -1689,7 +1698,7 @@ void helper_fpatan(CPUX86State *env) } /* This result is inexact. */ rsig1 |= 1; - ST1 = normalizeRoundAndPackFloatx80(80, rsign, rexp, + ST1 = normalizeRoundAndPackFloatx80(floatx80_precision_x, rsign, rexp, rsig0, rsig1, &env->fp_status); } @@ -1890,7 +1899,8 @@ static void helper_fyl2x_common(CPUX86State *env, floatx80 arg, int32_t *exp, */ mul128To256(tsig0, tsig1, tsig0, tsig1, &t2sig0, &t2sig1, &t2sig2, &t2sig3); - t2 = normalizeRoundAndPackFloatx80(80, false, texp + texp - 0x3ffe, + t2 = normalizeRoundAndPackFloatx80(floatx80_precision_x, false, + texp + texp - 0x3ffe, t2sig0, t2sig1, &env->fp_status); /* Compute the lower parts of the polynomial expansion. */ @@ -2004,15 +2014,17 @@ void helper_fyl2xp1(CPUX86State *env) exp += arg1_exp - 0x3ffe; /* This result is inexact. */ sig1 |= 1; - ST1 = normalizeRoundAndPackFloatx80(80, arg0_sign ^ arg1_sign, exp, + ST1 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + arg0_sign ^ arg1_sign, exp, sig0, sig1, &env->fp_status); } else { int32_t aexp; uint64_t asig0, asig1, asig2; FloatRoundMode save_mode = env->fp_status.float_rounding_mode; - signed char save_prec = env->fp_status.floatx80_rounding_precision; + FloatX80RoundPrec save_prec = + env->fp_status.floatx80_rounding_precision; env->fp_status.float_rounding_mode = float_round_nearest_even; - env->fp_status.floatx80_rounding_precision = 80; + env->fp_status.floatx80_rounding_precision = floatx80_precision_x; helper_fyl2x_common(env, ST0, &aexp, &asig0, &asig1); /* @@ -2027,7 +2039,8 @@ void helper_fyl2xp1(CPUX86State *env) /* This result is inexact. */ asig1 |= 1; env->fp_status.float_rounding_mode = save_mode; - ST1 = normalizeRoundAndPackFloatx80(80, arg0_sign ^ arg1_sign, aexp, + ST1 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + arg0_sign ^ arg1_sign, aexp, asig0, asig1, &env->fp_status); env->fp_status.floatx80_rounding_precision = save_prec; } @@ -2111,9 +2124,10 @@ void helper_fyl2x(CPUX86State *env) int32_t int_exp; floatx80 arg0_m1; FloatRoundMode save_mode = env->fp_status.float_rounding_mode; - signed char save_prec = env->fp_status.floatx80_rounding_precision; + FloatX80RoundPrec save_prec = + env->fp_status.floatx80_rounding_precision; env->fp_status.float_rounding_mode = float_round_nearest_even; - env->fp_status.floatx80_rounding_precision = 80; + env->fp_status.floatx80_rounding_precision = floatx80_precision_x; if (arg0_exp == 0) { normalizeFloatx80Subnormal(arg0_sig, &arg0_exp, &arg0_sig); @@ -2170,7 +2184,8 @@ void helper_fyl2x(CPUX86State *env) /* This result is inexact. */ asig1 |= 1; env->fp_status.float_rounding_mode = save_mode; - ST1 = normalizeRoundAndPackFloatx80(80, asign ^ arg1_sign, aexp, + ST1 = normalizeRoundAndPackFloatx80(floatx80_precision_x, + asign ^ arg1_sign, aexp, asig0, asig1, &env->fp_status); } @@ -2252,12 +2267,12 @@ void helper_fscale(CPUX86State *env) } } else { int n; - signed char save = env->fp_status.floatx80_rounding_precision; + FloatX80RoundPrec save = env->fp_status.floatx80_rounding_precision; uint8_t save_flags = get_float_exception_flags(&env->fp_status); set_float_exception_flags(0, &env->fp_status); n = floatx80_to_int32_round_to_zero(ST1, &env->fp_status); set_float_exception_flags(save_flags, &env->fp_status); - env->fp_status.floatx80_rounding_precision = 80; + env->fp_status.floatx80_rounding_precision = floatx80_precision_x; ST0 = floatx80_scalbn(ST0, n, &env->fp_status); env->fp_status.floatx80_rounding_precision = save; } diff --git a/target/i386/tcg/tcg-cpu.c b/target/i386/tcg/tcg-cpu.c index ba39531aa5..014ebea2f6 100644 --- a/target/i386/tcg/tcg-cpu.c +++ b/target/i386/tcg/tcg-cpu.c @@ -56,7 +56,7 @@ static void x86_cpu_synchronize_from_tb(CPUState *cs, #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps x86_tcg_ops = { +static const struct TCGCPUOps x86_tcg_ops = { .initialize = tcg_x86_init, .synchronize_from_tb = x86_cpu_synchronize_from_tb, .cpu_exec_enter = x86_cpu_exec_enter, diff --git a/target/i386/trace-events b/target/i386/trace-events index a22ab24e21..2cd8726eeb 100644 --- a/target/i386/trace-events +++ b/target/i386/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # sev.c kvm_sev_init(void) "" @@ -10,3 +10,4 @@ kvm_sev_launch_update_data(void *addr, uint64_t len) "addr %p len 0x%" PRIx64 kvm_sev_launch_measurement(const char *value) "data %s" kvm_sev_launch_finish(void) "" kvm_sev_launch_secret(uint64_t hpa, uint64_t hva, uint64_t secret, int len) "hpa 0x%" PRIx64 " hva 0x%" PRIx64 " data 0x%" PRIx64 " len %d" +kvm_sev_attestation_report(const char *mnonce, const char *data) "mnonce %s data %s" diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index a14874b4da..72de6e9726 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -503,9 +503,17 @@ static const VMStateDescription vmstate_m68k_cpu = { }; #endif +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps m68k_sysemu_ops = { + .get_phys_page_debug = m68k_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps m68k_tcg_ops = { +static const struct TCGCPUOps m68k_tcg_ops = { .initialize = m68k_tcg_init, .cpu_exec_interrupt = m68k_cpu_exec_interrupt, .tlb_fill = m68k_cpu_tlb_fill, @@ -533,8 +541,8 @@ static void m68k_cpu_class_init(ObjectClass *c, void *data) cc->gdb_read_register = m68k_cpu_gdb_read_register; cc->gdb_write_register = m68k_cpu_gdb_write_register; #if defined(CONFIG_SOFTMMU) - cc->get_phys_page_debug = m68k_cpu_get_phys_page_debug; dc->vmsd = &vmstate_m68k_cpu; + cc->sysemu_ops = &m68k_sysemu_ops; #endif cc->disas_set_info = m68k_cpu_disas_set_info; diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h index 402c86c876..997d588911 100644 --- a/target/m68k/cpu.h +++ b/target/m68k/cpu.h @@ -230,6 +230,9 @@ typedef enum { #define SR_T_SHIFT 14 #define SR_T 0xc000 +#define M68K_SR_TRACE(sr) ((sr & SR_T) >> SR_T_SHIFT) +#define M68K_SR_TRACE_ANY_INS 0x2 + #define M68K_SSP 0 #define M68K_USP 1 #define M68K_ISP 2 @@ -590,6 +593,8 @@ typedef M68kCPU ArchCPU; #define TB_FLAGS_SFC_S (1 << TB_FLAGS_SFC_S_BIT) #define TB_FLAGS_DFC_S_BIT 15 #define TB_FLAGS_DFC_S (1 << TB_FLAGS_DFC_S_BIT) +#define TB_FLAGS_TRACE 16 +#define TB_FLAGS_TRACE_BIT (1 << TB_FLAGS_TRACE) static inline void cpu_get_tb_cpu_state(CPUM68KState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *flags) @@ -602,6 +607,9 @@ static inline void cpu_get_tb_cpu_state(CPUM68KState *env, target_ulong *pc, *flags |= (env->sfc << (TB_FLAGS_SFC_S_BIT - 2)) & TB_FLAGS_SFC_S; *flags |= (env->dfc << (TB_FLAGS_DFC_S_BIT - 2)) & TB_FLAGS_DFC_S; } + if (M68K_SR_TRACE(env->sr) == M68K_SR_TRACE_ANY_INS) { + *flags |= TB_FLAGS_TRACE; + } } void dump_mmu(CPUM68KState *env); diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c index 797000e748..fdc4937e29 100644 --- a/target/m68k/fpu_helper.c +++ b/target/m68k/fpu_helper.c @@ -94,13 +94,13 @@ static void m68k_restore_precision_mode(CPUM68KState *env) { switch (env->fpcr & FPCR_PREC_MASK) { case FPCR_PREC_X: /* extended */ - set_floatx80_rounding_precision(80, &env->fp_status); + set_floatx80_rounding_precision(floatx80_precision_x, &env->fp_status); break; case FPCR_PREC_S: /* single */ - set_floatx80_rounding_precision(32, &env->fp_status); + set_floatx80_rounding_precision(floatx80_precision_s, &env->fp_status); break; case FPCR_PREC_D: /* double */ - set_floatx80_rounding_precision(64, &env->fp_status); + set_floatx80_rounding_precision(floatx80_precision_d, &env->fp_status); break; case FPCR_PREC_U: /* undefined */ default: @@ -111,9 +111,9 @@ static void m68k_restore_precision_mode(CPUM68KState *env) static void cf_restore_precision_mode(CPUM68KState *env) { if (env->fpcr & FPCR_PREC_S) { /* single */ - set_floatx80_rounding_precision(32, &env->fp_status); + set_floatx80_rounding_precision(floatx80_precision_s, &env->fp_status); } else { /* double */ - set_floatx80_rounding_precision(64, &env->fp_status); + set_floatx80_rounding_precision(floatx80_precision_d, &env->fp_status); } } @@ -166,8 +166,8 @@ void HELPER(set_fpcr)(CPUM68KState *env, uint32_t val) #define PREC_BEGIN(prec) \ do { \ - int old; \ - old = get_floatx80_rounding_precision(&env->fp_status); \ + FloatX80RoundPrec old = \ + get_floatx80_rounding_precision(&env->fp_status); \ set_floatx80_rounding_precision(prec, &env->fp_status) \ #define PREC_END() \ @@ -176,14 +176,14 @@ void HELPER(set_fpcr)(CPUM68KState *env, uint32_t val) void HELPER(fsround)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_round(val->d, &env->fp_status); PREC_END(); } void HELPER(fdround)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_round(val->d, &env->fp_status); PREC_END(); } @@ -195,14 +195,14 @@ void HELPER(fsqrt)(CPUM68KState *env, FPReg *res, FPReg *val) void HELPER(fssqrt)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_sqrt(val->d, &env->fp_status); PREC_END(); } void HELPER(fdsqrt)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_sqrt(val->d, &env->fp_status); PREC_END(); } @@ -214,14 +214,14 @@ void HELPER(fabs)(CPUM68KState *env, FPReg *res, FPReg *val) void HELPER(fsabs)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_round(floatx80_abs(val->d), &env->fp_status); PREC_END(); } void HELPER(fdabs)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_round(floatx80_abs(val->d), &env->fp_status); PREC_END(); } @@ -233,14 +233,14 @@ void HELPER(fneg)(CPUM68KState *env, FPReg *res, FPReg *val) void HELPER(fsneg)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_round(floatx80_chs(val->d), &env->fp_status); PREC_END(); } void HELPER(fdneg)(CPUM68KState *env, FPReg *res, FPReg *val) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_round(floatx80_chs(val->d), &env->fp_status); PREC_END(); } @@ -252,14 +252,14 @@ void HELPER(fadd)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) void HELPER(fsadd)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_add(val0->d, val1->d, &env->fp_status); PREC_END(); } void HELPER(fdadd)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_add(val0->d, val1->d, &env->fp_status); PREC_END(); } @@ -271,14 +271,14 @@ void HELPER(fsub)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) void HELPER(fssub)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_sub(val1->d, val0->d, &env->fp_status); PREC_END(); } void HELPER(fdsub)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_sub(val1->d, val0->d, &env->fp_status); PREC_END(); } @@ -290,14 +290,14 @@ void HELPER(fmul)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) void HELPER(fsmul)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_mul(val0->d, val1->d, &env->fp_status); PREC_END(); } void HELPER(fdmul)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_mul(val0->d, val1->d, &env->fp_status); PREC_END(); } @@ -307,7 +307,7 @@ void HELPER(fsglmul)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) FloatRoundMode rounding_mode = get_float_rounding_mode(&env->fp_status); floatx80 a, b; - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); set_float_rounding_mode(float_round_to_zero, &env->fp_status); a = floatx80_round(val0->d, &env->fp_status); b = floatx80_round(val1->d, &env->fp_status); @@ -323,14 +323,14 @@ void HELPER(fdiv)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) void HELPER(fsdiv)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); res->d = floatx80_div(val1->d, val0->d, &env->fp_status); PREC_END(); } void HELPER(fddiv)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) { - PREC_BEGIN(64); + PREC_BEGIN(floatx80_precision_d); res->d = floatx80_div(val1->d, val0->d, &env->fp_status); PREC_END(); } @@ -340,7 +340,7 @@ void HELPER(fsgldiv)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) FloatRoundMode rounding_mode = get_float_rounding_mode(&env->fp_status); floatx80 a, b; - PREC_BEGIN(32); + PREC_BEGIN(floatx80_precision_s); set_float_rounding_mode(float_round_to_zero, &env->fp_status); a = floatx80_round(val1->d, &env->fp_status); b = floatx80_round(val0->d, &env->fp_status); diff --git a/target/m68k/softfloat.c b/target/m68k/softfloat.c index b6d0ed7acf..02dcc03d15 100644 --- a/target/m68k/softfloat.c +++ b/target/m68k/softfloat.c @@ -227,7 +227,8 @@ floatx80 floatx80_lognp1(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig, fSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, j, k; floatx80 fp0, fp1, fp2, fp3, f, logof2, klog2, saveu; @@ -270,7 +271,7 @@ floatx80 floatx80_lognp1(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -426,7 +427,8 @@ floatx80 floatx80_logn(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig, fSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, j, k, adjk; floatx80 fp0, fp1, fp2, fp3, f, logof2, klog2, saveu; @@ -469,7 +471,7 @@ floatx80 floatx80_logn(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -594,7 +596,8 @@ floatx80 floatx80_log10(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; floatx80 fp0, fp1; @@ -626,7 +629,7 @@ floatx80 floatx80_log10(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; fp0 = floatx80_logn(a, status); fp1 = packFloatx80(0, 0x3FFD, UINT64_C(0xDE5BD8A937287195)); /* INV_L10 */ @@ -651,7 +654,8 @@ floatx80 floatx80_log2(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; floatx80 fp0, fp1; @@ -686,7 +690,7 @@ floatx80 floatx80_log2(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; if (aSig == one_sig) { /* X is 2^k */ status->float_rounding_mode = user_rnd_mode; @@ -718,7 +722,8 @@ floatx80 floatx80_etox(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, n, j, k, m, m1; floatx80 fp0, fp1, fp2, fp3, l2, scale, adjscale; @@ -746,7 +751,7 @@ floatx80 floatx80_etox(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; adjflag = 0; @@ -902,7 +907,8 @@ floatx80 floatx80_twotox(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, n, j, l, m, m1; floatx80 fp0, fp1, fp2, fp3, adjfact, fact1, fact2; @@ -929,7 +935,7 @@ floatx80 floatx80_twotox(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; fp0 = a; @@ -1052,7 +1058,8 @@ floatx80 floatx80_tentox(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, n, j, l, m, m1; floatx80 fp0, fp1, fp2, fp3, adjfact, fact1, fact2; @@ -1079,7 +1086,7 @@ floatx80 floatx80_tentox(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; fp0 = a; @@ -1207,7 +1214,8 @@ floatx80 floatx80_tan(floatx80 a, float_status *status) int32_t aExp, xExp; uint64_t aSig, xSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, l, n, j; floatx80 fp0, fp1, fp2, fp3, fp4, fp5, invtwopi, twopi1, twopi2; @@ -1233,7 +1241,7 @@ floatx80 floatx80_tan(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -1417,7 +1425,8 @@ floatx80 floatx80_sin(floatx80 a, float_status *status) int32_t aExp, xExp; uint64_t aSig, xSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, l, n, j; floatx80 fp0, fp1, fp2, fp3, fp4, fp5, x, invtwopi, twopi1, twopi2; @@ -1443,7 +1452,7 @@ floatx80 floatx80_sin(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -1656,7 +1665,8 @@ floatx80 floatx80_cos(floatx80 a, float_status *status) int32_t aExp, xExp; uint64_t aSig, xSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, l, n, j; floatx80 fp0, fp1, fp2, fp3, fp4, fp5, x, invtwopi, twopi1, twopi2; @@ -1682,7 +1692,7 @@ floatx80 floatx80_cos(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -1893,7 +1903,8 @@ floatx80 floatx80_atan(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, tbl_index; floatx80 fp0, fp1, fp2, fp3, xsave; @@ -1920,7 +1931,7 @@ floatx80 floatx80_atan(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; if (compact < 0x3FFB8000 || compact > 0x4002FFFF) { /* |X| >= 16 or |X| < 1/16 */ @@ -2090,7 +2101,8 @@ floatx80 floatx80_asin(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact; floatx80 fp0, fp1, fp2, one; @@ -2124,7 +2136,7 @@ floatx80 floatx80_asin(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; one = packFloatx80(0, one_exp, one_sig); fp0 = a; @@ -2155,7 +2167,8 @@ floatx80 floatx80_acos(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact; floatx80 fp0, fp1, one; @@ -2193,7 +2206,7 @@ floatx80 floatx80_acos(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; one = packFloatx80(0, one_exp, one_sig); fp0 = a; @@ -2224,7 +2237,8 @@ floatx80 floatx80_atanh(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact; floatx80 fp0, fp1, fp2, one; @@ -2257,7 +2271,7 @@ floatx80 floatx80_atanh(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; one = packFloatx80(0, one_exp, one_sig); fp2 = packFloatx80(aSign, 0x3FFE, one_sig); /* SIGN(X) * (1/2) */ @@ -2289,7 +2303,8 @@ floatx80 floatx80_etoxm1(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact, n, j, m, m1; floatx80 fp0, fp1, fp2, fp3, l2, sc, onebysc; @@ -2316,7 +2331,7 @@ floatx80 floatx80_etoxm1(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; if (aExp >= 0x3FFD) { /* |X| >= 1/4 */ compact = floatx80_make_compact(aExp, aSig); @@ -2541,7 +2556,8 @@ floatx80 floatx80_tanh(floatx80 a, float_status *status) int32_t aExp, vExp; uint64_t aSig, vSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact; floatx80 fp0, fp1; @@ -2565,7 +2581,7 @@ floatx80 floatx80_tanh(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -2656,7 +2672,8 @@ floatx80 floatx80_sinh(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact; floatx80 fp0, fp1, fp2; @@ -2681,7 +2698,7 @@ floatx80 floatx80_sinh(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); @@ -2744,7 +2761,8 @@ floatx80 floatx80_cosh(floatx80 a, float_status *status) int32_t aExp; uint64_t aSig; - int8_t user_rnd_mode, user_rnd_prec; + FloatRoundMode user_rnd_mode; + FloatX80RoundPrec user_rnd_prec; int32_t compact; floatx80 fp0, fp1; @@ -2767,7 +2785,7 @@ floatx80 floatx80_cosh(floatx80 a, float_status *status) user_rnd_mode = status->float_rounding_mode; user_rnd_prec = status->floatx80_rounding_precision; status->float_rounding_mode = float_round_nearest_even; - status->floatx80_rounding_precision = 80; + status->floatx80_rounding_precision = floatx80_precision_x; compact = floatx80_make_compact(aExp, aSig); diff --git a/target/m68k/translate.c b/target/m68k/translate.c index 200018ae6a..f0c5bf9154 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -124,6 +124,7 @@ typedef struct DisasContext { #define MAX_TO_RELEASE 8 int release_count; TCGv release[MAX_TO_RELEASE]; + bool ss_active; } DisasContext; static void init_release_array(DisasContext *s) @@ -194,6 +195,18 @@ static void do_writebacks(DisasContext *s) } } +static bool is_singlestepping(DisasContext *s) +{ + /* + * Return true if we are singlestepping either because of + * architectural singlestep or QEMU gdbstub singlestep. This does + * not include the command line '-singlestep' mode which is rather + * misnamed as it only means "one instruction per TB" and doesn't + * affect the code we generate. + */ + return s->base.singlestep_enabled || s->ss_active; +} + /* is_jmp field values */ #define DISAS_JUMP DISAS_TARGET_0 /* only pc was modified dynamically */ #define DISAS_EXIT DISAS_TARGET_1 /* cpu state was modified dynamically */ @@ -308,6 +321,20 @@ static void gen_exception(DisasContext *s, uint32_t dest, int nr) s->base.is_jmp = DISAS_NORETURN; } +static void gen_singlestep_exception(DisasContext *s) +{ + /* + * Generate the right kind of exception for singlestep, which is + * either the architectural singlestep or EXCP_DEBUG for QEMU's + * gdb singlestepping. + */ + if (s->ss_active) { + gen_raise_exception(EXCP_TRACE); + } else { + gen_raise_exception(EXCP_DEBUG); + } +} + static inline void gen_addr_fault(DisasContext *s) { gen_exception(s, s->base.pc_next, EXCP_ADDRESS); @@ -1506,8 +1533,10 @@ static inline bool use_goto_tb(DisasContext *s, uint32_t dest) /* Generate a jump to an immediate address. */ static void gen_jmp_tb(DisasContext *s, int n, uint32_t dest) { - if (unlikely(s->base.singlestep_enabled)) { - gen_exception(s, dest, EXCP_DEBUG); + if (unlikely(is_singlestepping(s))) { + update_cc_op(s); + tcg_gen_movi_i32(QREG_PC, dest); + gen_singlestep_exception(s); } else if (use_goto_tb(s, dest)) { tcg_gen_goto_tb(n); tcg_gen_movi_i32(QREG_PC, dest); @@ -6172,6 +6201,12 @@ static void m68k_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cpu) dc->done_mac = 0; dc->writeback_mask = 0; init_release_array(dc); + + dc->ss_active = (M68K_SR_TRACE(env->sr) == M68K_SR_TRACE_ANY_INS); + /* If architectural single step active, limit to 1 */ + if (is_singlestepping(dc)) { + dc->base.max_insns = 1; + } } static void m68k_tr_tb_start(DisasContextBase *dcbase, CPUState *cpu) @@ -6245,17 +6280,17 @@ static void m68k_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) break; case DISAS_TOO_MANY: update_cc_op(dc); - if (dc->base.singlestep_enabled) { + if (is_singlestepping(dc)) { tcg_gen_movi_i32(QREG_PC, dc->pc); - gen_raise_exception(EXCP_DEBUG); + gen_singlestep_exception(dc); } else { gen_jmp_tb(dc, 0, dc->pc); } break; case DISAS_JUMP: /* We updated CC_OP and PC in gen_jmp/gen_jmp_im. */ - if (dc->base.singlestep_enabled) { - gen_raise_exception(EXCP_DEBUG); + if (is_singlestepping(dc)) { + gen_singlestep_exception(dc); } else { tcg_gen_lookup_and_goto_ptr(); } @@ -6265,8 +6300,8 @@ static void m68k_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) * We updated CC_OP and PC in gen_exit_tb, but also modified * other state that may require returning to the main loop. */ - if (dc->base.singlestep_enabled) { - gen_raise_exception(EXCP_DEBUG); + if (is_singlestepping(dc)) { + gen_singlestep_exception(dc); } else { tcg_gen_exit_tb(NULL, 0); } diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index 433ba20203..72d8f2a0da 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -352,9 +352,17 @@ static ObjectClass *mb_cpu_class_by_name(const char *cpu_model) return object_class_by_name(TYPE_MICROBLAZE_CPU); } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps mb_sysemu_ops = { + .get_phys_page_attrs_debug = mb_cpu_get_phys_page_attrs_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps mb_tcg_ops = { +static const struct TCGCPUOps mb_tcg_ops = { .initialize = mb_tcg_init, .synchronize_from_tb = mb_cpu_synchronize_from_tb, .cpu_exec_interrupt = mb_cpu_exec_interrupt, @@ -386,8 +394,8 @@ static void mb_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_write_register = mb_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_attrs_debug = mb_cpu_get_phys_page_attrs_debug; dc->vmsd = &vmstate_mb_cpu; + cc->sysemu_ops = &mb_sysemu_ops; #endif device_class_set_props(dc, mb_properties); cc->gdb_num_core_regs = 32 + 27; diff --git a/target/mips/cpu-qom.h b/target/mips/cpu-qom.h index 826ab13019..dda0c911fa 100644 --- a/target/mips/cpu-qom.h +++ b/target/mips/cpu-qom.h @@ -47,6 +47,9 @@ struct MIPSCPUClass { DeviceRealize parent_realize; DeviceReset parent_reset; const struct mips_def_t *cpu_def; + + /* Used for the jazz board to modify mips_cpu_do_transaction_failed. */ + bool no_data_aborts; }; diff --git a/target/mips/cpu.c b/target/mips/cpu.c index 1ad2fe4aa3..96236abc00 100644 --- a/target/mips/cpu.c +++ b/target/mips/cpu.c @@ -521,13 +521,22 @@ static Property mips_cpu_properties[] = { DEFINE_PROP_END_OF_LIST() }; +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps mips_sysemu_ops = { + .get_phys_page_debug = mips_cpu_get_phys_page_debug, + .legacy_vmsd = &vmstate_mips_cpu, +}; +#endif + #ifdef CONFIG_TCG #include "hw/core/tcg-cpu-ops.h" /* * NB: cannot be const, as some elements are changed for specific * mips hardware (see hw/mips/jazz.c). */ -static struct TCGCPUOps mips_tcg_ops = { +static const struct TCGCPUOps mips_tcg_ops = { .initialize = mips_tcg_init, .synchronize_from_tb = mips_cpu_synchronize_from_tb, .cpu_exec_interrupt = mips_cpu_exec_interrupt, @@ -560,8 +569,7 @@ static void mips_cpu_class_init(ObjectClass *c, void *data) cc->gdb_read_register = mips_cpu_gdb_read_register; cc->gdb_write_register = mips_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = mips_cpu_get_phys_page_debug; - cc->vmsd = &vmstate_mips_cpu; + cc->sysemu_ops = &mips_sysemu_ops; #endif cc->disas_set_info = mips_cpu_disas_set_info; cc->gdb_num_core_regs = 73; diff --git a/target/mips/tcg/op_helper.c b/target/mips/tcg/op_helper.c index ce1549c985..fafbf1faca 100644 --- a/target/mips/tcg/op_helper.c +++ b/target/mips/tcg/op_helper.c @@ -409,11 +409,12 @@ void mips_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, MemTxResult response, uintptr_t retaddr) { MIPSCPU *cpu = MIPS_CPU(cs); + MIPSCPUClass *mcc = MIPS_CPU_GET_CLASS(cpu); CPUMIPSState *env = &cpu->env; if (access_type == MMU_INST_FETCH) { do_raise_exception(env, EXCP_IBE, retaddr); - } else { + } else if (!mcc->no_data_aborts) { do_raise_exception(env, EXCP_DBE, retaddr); } } diff --git a/target/mips/trace-events b/target/mips/trace-events index ba87fe6062..0c55e0bbad 100644 --- a/target/mips/trace-events +++ b/target/mips/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # translate.c mips_translate_c0(const char *instr, const char *rn, int reg, int sel) "%s %s (reg %d sel %d)" diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index e9c9fc3a38..5e37defef8 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -207,9 +207,17 @@ static Property nios2_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps nios2_sysemu_ops = { + .get_phys_page_debug = nios2_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps nios2_tcg_ops = { +static const struct TCGCPUOps nios2_tcg_ops = { .initialize = nios2_tcg_init, .cpu_exec_interrupt = nios2_cpu_exec_interrupt, .tlb_fill = nios2_cpu_tlb_fill, @@ -237,7 +245,7 @@ static void nios2_cpu_class_init(ObjectClass *oc, void *data) cc->set_pc = nios2_cpu_set_pc; cc->disas_set_info = nios2_cpu_disas_set_info; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = nios2_cpu_get_phys_page_debug; + cc->sysemu_ops = &nios2_sysemu_ops; #endif cc->gdb_read_register = nios2_cpu_gdb_read_register; cc->gdb_write_register = nios2_cpu_gdb_write_register; diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index 2c64842f46..bd34e429ec 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -174,9 +174,17 @@ static void openrisc_any_initfn(Object *obj) | (IMMUCFGR_NTS & (ctz32(TLB_SIZE) << 2)); } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps openrisc_sysemu_ops = { + .get_phys_page_debug = openrisc_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps openrisc_tcg_ops = { +static const struct TCGCPUOps openrisc_tcg_ops = { .initialize = openrisc_translate_init, .cpu_exec_interrupt = openrisc_cpu_exec_interrupt, .tlb_fill = openrisc_cpu_tlb_fill, @@ -203,8 +211,8 @@ static void openrisc_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = openrisc_cpu_gdb_read_register; cc->gdb_write_register = openrisc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = openrisc_cpu_get_phys_page_debug; dc->vmsd = &vmstate_openrisc_cpu; + cc->sysemu_ops = &openrisc_sysemu_ops; #endif cc->gdb_num_core_regs = 32 + 3; cc->disas_set_info = openrisc_disas_set_info; diff --git a/target/ppc/cpu.c b/target/ppc/cpu.c index d957d1a687..19d67b5b07 100644 --- a/target/ppc/cpu.c +++ b/target/ppc/cpu.c @@ -24,6 +24,8 @@ #include "exec/log.h" #include "fpu/softfloat-helpers.h" #include "mmu-hash64.h" +#include "helper_regs.h" +#include "sysemu/tcg.h" target_ulong cpu_read_xer(CPUPPCState *env) { @@ -77,13 +79,13 @@ void ppc_store_sdr1(CPUPPCState *env, target_ulong value) target_ulong htabsize = value & SDR_64_HTABSIZE; if (value & ~sdr_mask) { - error_report("Invalid bits 0x"TARGET_FMT_lx" set in SDR1", - value & ~sdr_mask); + qemu_log_mask(LOG_GUEST_ERROR, "Invalid bits 0x"TARGET_FMT_lx + " set in SDR1", value & ~sdr_mask); value &= sdr_mask; } if (htabsize > 28) { - error_report("Invalid HTABSIZE 0x" TARGET_FMT_lx" stored in SDR1", - htabsize); + qemu_log_mask(LOG_GUEST_ERROR, "Invalid HTABSIZE 0x" TARGET_FMT_lx + " stored in SDR1", htabsize); return; } } @@ -92,3 +94,61 @@ void ppc_store_sdr1(CPUPPCState *env, target_ulong value) env->spr[SPR_SDR1] = value; } #endif /* CONFIG_SOFTMMU */ + +/* GDBstub can read and write MSR... */ +void ppc_store_msr(CPUPPCState *env, target_ulong value) +{ + hreg_store_msr(env, value, 0); +} + +void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val) +{ + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + CPUPPCState *env = &cpu->env; + + env->spr[SPR_LPCR] = val & pcc->lpcr_mask; + /* The gtse bit affects hflags */ + hreg_compute_hflags(env); +} + +static inline void fpscr_set_rounding_mode(CPUPPCState *env) +{ + int rnd_type; + + /* Set rounding mode */ + switch (fpscr_rn) { + case 0: + /* Best approximation (round to nearest) */ + rnd_type = float_round_nearest_even; + break; + case 1: + /* Smaller magnitude (round toward zero) */ + rnd_type = float_round_to_zero; + break; + case 2: + /* Round toward +infinite */ + rnd_type = float_round_up; + break; + default: + case 3: + /* Round toward -infinite */ + rnd_type = float_round_down; + break; + } + set_float_rounding_mode(rnd_type, &env->fp_status); +} + +void ppc_store_fpscr(CPUPPCState *env, target_ulong val) +{ + val &= ~(FP_VX | FP_FEX); + if (val & FPSCR_IX) { + val |= FP_VX; + } + if ((val >> FPSCR_XX) & (val >> FPSCR_XE) & 0x1f) { + val |= FP_FEX; + } + env->fpscr = val; + if (tcg_enabled()) { + fpscr_set_rounding_mode(env); + } +} diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index cab33a3680..b4de0db7ff 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -144,6 +144,7 @@ enum { POWERPC_EXCP_ALIGN_PROT = 0x04, /* Access cross protection boundary */ POWERPC_EXCP_ALIGN_BAT = 0x05, /* Access cross a BAT/seg boundary */ POWERPC_EXCP_ALIGN_CACHE = 0x06, /* Impossible dcbz access */ + POWERPC_EXCP_ALIGN_INSN = 0x07, /* Pref. insn x-ing 64-byte boundary */ /* Exception subtypes for POWERPC_EXCP_PROGRAM */ /* FP exceptions */ POWERPC_EXCP_FP = 0x10, @@ -675,11 +676,11 @@ enum { #define fpscr_ni (((env->fpscr) >> FPSCR_NI) & 0x1) #define fpscr_rn (((env->fpscr) >> FPSCR_RN0) & 0x3) /* Invalid operation exception summary */ -#define fpscr_ix ((env->fpscr) & ((1 << FPSCR_VXSNAN) | (1 << FPSCR_VXISI) | \ - (1 << FPSCR_VXIDI) | (1 << FPSCR_VXZDZ) | \ - (1 << FPSCR_VXIMZ) | (1 << FPSCR_VXVC) | \ - (1 << FPSCR_VXSOFT) | (1 << FPSCR_VXSQRT) | \ - (1 << FPSCR_VXCVI))) +#define FPSCR_IX ((1 << FPSCR_VXSNAN) | (1 << FPSCR_VXISI) | \ + (1 << FPSCR_VXIDI) | (1 << FPSCR_VXZDZ) | \ + (1 << FPSCR_VXIMZ) | (1 << FPSCR_VXVC) | \ + (1 << FPSCR_VXSOFT) | (1 << FPSCR_VXSQRT) | \ + (1 << FPSCR_VXCVI)) /* exception summary */ #define fpscr_ex (((env->fpscr) >> FPSCR_XX) & 0x1F) /* enabled exception summary */ @@ -1256,7 +1257,6 @@ DECLARE_OBJ_CHECKERS(PPCVirtualHypervisor, PPCVirtualHypervisorClass, void ppc_cpu_do_interrupt(CPUState *cpu); bool ppc_cpu_exec_interrupt(CPUState *cpu, int int_req); void ppc_cpu_dump_state(CPUState *cpu, FILE *f, int flags); -void ppc_cpu_dump_statistics(CPUState *cpu, int flags); hwaddr ppc_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); int ppc_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int ppc_cpu_gdb_read_register_apple(CPUState *cpu, GByteArray *buf, int reg); @@ -1290,7 +1290,6 @@ bool ppc_cpu_tlb_fill(CPUState *cs, vaddr address, int size, #if !defined(CONFIG_USER_ONLY) void ppc_store_sdr1(CPUPPCState *env, target_ulong value); -void ppc_store_ptcr(CPUPPCState *env, target_ulong value); #endif /* !defined(CONFIG_USER_ONLY) */ void ppc_store_msr(CPUPPCState *env, target_ulong value); void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val); @@ -1334,7 +1333,7 @@ void cpu_ppc_set_vhyp(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp); #endif #endif -void store_fpscr(CPUPPCState *env, uint64_t arg, uint32_t mask); +void ppc_store_fpscr(CPUPPCState *env, target_ulong val); void helper_hfscr_facility_check(CPUPPCState *env, uint32_t bit, const char *caller, uint32_t cause); diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index 22ecbccad8..d0411e7302 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -43,7 +43,6 @@ #include "fpu/softfloat.h" #include "qapi/qapi-commands-machine-target.h" -#include "exec/helper-proto.h" #include "helper_regs.h" #include "internal.h" #include "spr_tcg.h" @@ -1206,15 +1205,12 @@ static void register_BookE206_sprs(CPUPPCState *env, uint32_t mas_mask, /* TLB assist registers */ /* XXX : not implemented */ for (i = 0; i < 8; i++) { - void (*uea_write)(DisasContext *ctx, int sprn, int gprn) = - &spr_write_generic32; - if (i == 2 && (mas_mask & (1 << i)) && (env->insns_flags & PPC_64B)) { - uea_write = &spr_write_generic; - } if (mas_mask & (1 << i)) { spr_register(env, mas_sprn[i], mas_names[i], SPR_NOACCESS, SPR_NOACCESS, - &spr_read_generic, uea_write, + &spr_read_generic, + (i == 2 && (env->insns_flags & PPC_64B)) + ? &spr_write_generic : &spr_write_generic32, 0x00000000); } } @@ -8545,45 +8541,6 @@ static void init_ppc_proc(PowerPCCPU *cpu) } } -#if defined(PPC_DUMP_CPU) -static void dump_ppc_sprs(CPUPPCState *env) -{ - ppc_spr_t *spr; -#if !defined(CONFIG_USER_ONLY) - uint32_t sr, sw; -#endif - uint32_t ur, uw; - int i, j, n; - - printf("Special purpose registers:\n"); - for (i = 0; i < 32; i++) { - for (j = 0; j < 32; j++) { - n = (i << 5) | j; - spr = &env->spr_cb[n]; - uw = spr->uea_write != NULL && spr->uea_write != SPR_NOACCESS; - ur = spr->uea_read != NULL && spr->uea_read != SPR_NOACCESS; -#if !defined(CONFIG_USER_ONLY) - sw = spr->oea_write != NULL && spr->oea_write != SPR_NOACCESS; - sr = spr->oea_read != NULL && spr->oea_read != SPR_NOACCESS; - if (sw || sr || uw || ur) { - printf("SPR: %4d (%03x) %-8s s%c%c u%c%c\n", - (i << 5) | j, (i << 5) | j, spr->name, - sw ? 'w' : '-', sr ? 'r' : '-', - uw ? 'w' : '-', ur ? 'r' : '-'); - } -#else - if (uw || ur) { - printf("SPR: %4d (%03x) %-8s u%c%c\n", - (i << 5) | j, (i << 5) | j, spr->name, - uw ? 'w' : '-', ur ? 'r' : '-'); - } -#endif - } - } - fflush(stdout); - fflush(stderr); -} -#endif static void ppc_cpu_realize(DeviceState *dev, Error **errp) { @@ -8620,172 +8577,6 @@ static void ppc_cpu_realize(DeviceState *dev, Error **errp) pcc->parent_realize(dev, errp); -#if defined(PPC_DUMP_CPU) - { - CPUPPCState *env = &cpu->env; - const char *mmu_model, *excp_model, *bus_model; - switch (env->mmu_model) { - case POWERPC_MMU_32B: - mmu_model = "PowerPC 32"; - break; - case POWERPC_MMU_SOFT_6xx: - mmu_model = "PowerPC 6xx/7xx with software driven TLBs"; - break; - case POWERPC_MMU_SOFT_74xx: - mmu_model = "PowerPC 74xx with software driven TLBs"; - break; - case POWERPC_MMU_SOFT_4xx: - mmu_model = "PowerPC 4xx with software driven TLBs"; - break; - case POWERPC_MMU_SOFT_4xx_Z: - mmu_model = "PowerPC 4xx with software driven TLBs " - "and zones protections"; - break; - case POWERPC_MMU_REAL: - mmu_model = "PowerPC real mode only"; - break; - case POWERPC_MMU_MPC8xx: - mmu_model = "PowerPC MPC8xx"; - break; - case POWERPC_MMU_BOOKE: - mmu_model = "PowerPC BookE"; - break; - case POWERPC_MMU_BOOKE206: - mmu_model = "PowerPC BookE 2.06"; - break; - case POWERPC_MMU_601: - mmu_model = "PowerPC 601"; - break; -#if defined(TARGET_PPC64) - case POWERPC_MMU_64B: - mmu_model = "PowerPC 64"; - break; -#endif - default: - mmu_model = "Unknown or invalid"; - break; - } - switch (env->excp_model) { - case POWERPC_EXCP_STD: - excp_model = "PowerPC"; - break; - case POWERPC_EXCP_40x: - excp_model = "PowerPC 40x"; - break; - case POWERPC_EXCP_601: - excp_model = "PowerPC 601"; - break; - case POWERPC_EXCP_602: - excp_model = "PowerPC 602"; - break; - case POWERPC_EXCP_603: - excp_model = "PowerPC 603"; - break; - case POWERPC_EXCP_603E: - excp_model = "PowerPC 603e"; - break; - case POWERPC_EXCP_604: - excp_model = "PowerPC 604"; - break; - case POWERPC_EXCP_7x0: - excp_model = "PowerPC 740/750"; - break; - case POWERPC_EXCP_7x5: - excp_model = "PowerPC 745/755"; - break; - case POWERPC_EXCP_74xx: - excp_model = "PowerPC 74xx"; - break; - case POWERPC_EXCP_BOOKE: - excp_model = "PowerPC BookE"; - break; -#if defined(TARGET_PPC64) - case POWERPC_EXCP_970: - excp_model = "PowerPC 970"; - break; -#endif - default: - excp_model = "Unknown or invalid"; - break; - } - switch (env->bus_model) { - case PPC_FLAGS_INPUT_6xx: - bus_model = "PowerPC 6xx"; - break; - case PPC_FLAGS_INPUT_BookE: - bus_model = "PowerPC BookE"; - break; - case PPC_FLAGS_INPUT_405: - bus_model = "PowerPC 405"; - break; - case PPC_FLAGS_INPUT_401: - bus_model = "PowerPC 401/403"; - break; - case PPC_FLAGS_INPUT_RCPU: - bus_model = "RCPU / MPC8xx"; - break; -#if defined(TARGET_PPC64) - case PPC_FLAGS_INPUT_970: - bus_model = "PowerPC 970"; - break; -#endif - default: - bus_model = "Unknown or invalid"; - break; - } - printf("PowerPC %-12s : PVR %08x MSR %016" PRIx64 "\n" - " MMU model : %s\n", - object_class_get_name(OBJECT_CLASS(pcc)), - pcc->pvr, pcc->msr_mask, mmu_model); -#if !defined(CONFIG_USER_ONLY) - if (env->tlb.tlb6) { - printf(" %d %s TLB in %d ways\n", - env->nb_tlb, env->id_tlbs ? "splitted" : "merged", - env->nb_ways); - } -#endif - printf(" Exceptions model : %s\n" - " Bus model : %s\n", - excp_model, bus_model); - printf(" MSR features :\n"); - if (env->flags & POWERPC_FLAG_SPE) { - printf(" signal processing engine enable" - "\n"); - } else if (env->flags & POWERPC_FLAG_VRE) { - printf(" vector processor enable\n"); - } - if (env->flags & POWERPC_FLAG_TGPR) { - printf(" temporary GPRs\n"); - } else if (env->flags & POWERPC_FLAG_CE) { - printf(" critical input enable\n"); - } - if (env->flags & POWERPC_FLAG_SE) { - printf(" single-step trace mode\n"); - } else if (env->flags & POWERPC_FLAG_DWE) { - printf(" debug wait enable\n"); - } else if (env->flags & POWERPC_FLAG_UBLE) { - printf(" user BTB lock enable\n"); - } - if (env->flags & POWERPC_FLAG_BE) { - printf(" branch-step trace mode\n"); - } else if (env->flags & POWERPC_FLAG_DE) { - printf(" debug interrupt enable\n"); - } - if (env->flags & POWERPC_FLAG_PX) { - printf(" inclusive protection\n"); - } else if (env->flags & POWERPC_FLAG_PMM) { - printf(" performance monitor mark\n"); - } - if (env->flags == POWERPC_FLAG_NONE) { - printf(" none\n"); - } - printf(" Time-base/decrementer clock source: %s\n", - env->flags & POWERPC_FLAG_RTC_CLK ? "RTC clock" : "bus clock"); - dump_ppc_insns(env); - dump_ppc_sprs(env); - fflush(stdout); - } -#endif return; unrealize: @@ -9263,10 +9054,22 @@ static Property ppc_cpu_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps ppc_sysemu_ops = { + .get_phys_page_debug = ppc_cpu_get_phys_page_debug, + .write_elf32_note = ppc32_cpu_write_elf32_note, + .write_elf64_note = ppc64_cpu_write_elf64_note, + .virtio_is_big_endian = ppc_cpu_is_big_endian, + .legacy_vmsd = &vmstate_ppc_cpu, +}; +#endif + #ifdef CONFIG_TCG #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps ppc_tcg_ops = { +static const struct TCGCPUOps ppc_tcg_ops = { .initialize = ppc_translate_init, .cpu_exec_interrupt = ppc_cpu_exec_interrupt, .tlb_fill = ppc_cpu_tlb_fill, @@ -9299,17 +9102,11 @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data) cc->class_by_name = ppc_cpu_class_by_name; cc->has_work = ppc_cpu_has_work; cc->dump_state = ppc_cpu_dump_state; - cc->dump_statistics = ppc_cpu_dump_statistics; cc->set_pc = ppc_cpu_set_pc; cc->gdb_read_register = ppc_cpu_gdb_read_register; cc->gdb_write_register = ppc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = ppc_cpu_get_phys_page_debug; - cc->vmsd = &vmstate_ppc_cpu; -#endif -#if defined(CONFIG_SOFTMMU) - cc->write_elf64_note = ppc64_cpu_write_elf64_note; - cc->write_elf32_note = ppc32_cpu_write_elf32_note; + cc->sysemu_ops = &ppc_sysemu_ops; #endif cc->gdb_num_core_regs = 71; @@ -9328,9 +9125,6 @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data) #else cc->gdb_core_xml_file = "power-core.xml"; #endif -#ifndef CONFIG_USER_ONLY - cc->virtio_is_big_endian = ppc_cpu_is_big_endian; -#endif cc->disas_set_info = ppc_disas_set_info; dc->fw_name = "PowerPC,UNKNOWN"; diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c index f4f15279eb..fd147e2a37 100644 --- a/target/ppc/excp_helper.c +++ b/target/ppc/excp_helper.c @@ -19,12 +19,15 @@ #include "qemu/osdep.h" #include "qemu/main-loop.h" #include "cpu.h" -#include "exec/helper-proto.h" #include "exec/exec-all.h" -#include "exec/cpu_ldst.h" #include "internal.h" #include "helper_regs.h" +#ifdef CONFIG_TCG +#include "exec/helper-proto.h" +#include "exec/cpu_ldst.h" +#endif + /* #define DEBUG_OP */ /* #define DEBUG_SOFTWARE_TLB */ /* #define DEBUG_EXCEPTIONS */ @@ -67,18 +70,6 @@ static inline void dump_syscall(CPUPPCState *env) ppc_dump_gpr(env, 8), env->nip); } -static inline void dump_syscall_vectored(CPUPPCState *env) -{ - qemu_log_mask(CPU_LOG_INT, "syscall r0=%016" PRIx64 - " r3=%016" PRIx64 " r4=%016" PRIx64 " r5=%016" PRIx64 - " r6=%016" PRIx64 " r7=%016" PRIx64 " r8=%016" PRIx64 - " nip=" TARGET_FMT_lx "\n", - ppc_dump_gpr(env, 0), ppc_dump_gpr(env, 3), - ppc_dump_gpr(env, 4), ppc_dump_gpr(env, 5), - ppc_dump_gpr(env, 6), ppc_dump_gpr(env, 7), - ppc_dump_gpr(env, 8), env->nip); -} - static inline void dump_hcall(CPUPPCState *env) { qemu_log_mask(CPU_LOG_INT, "hypercall r3=%016" PRIx64 @@ -330,7 +321,6 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) CPUPPCState *env = &cpu->env; target_ulong msr, new_msr, vector; int srr0, srr1, asrr0, asrr1, lev = -1; - bool lpes0; qemu_log_mask(CPU_LOG_INT, "Raise exception at " TARGET_FMT_lx " => %08x (%02x)\n", env->nip, excp, env->error_code); @@ -363,27 +353,6 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) } /* - * Exception targeting modifiers - * - * LPES0 is supported on POWER7/8/9 - * LPES1 is not supported (old iSeries mode) - * - * On anything else, we behave as if LPES0 is 1 - * (externals don't alter MSR:HV) - */ -#if defined(TARGET_PPC64) - if (excp_model == POWERPC_EXCP_POWER7 || - excp_model == POWERPC_EXCP_POWER8 || - excp_model == POWERPC_EXCP_POWER9 || - excp_model == POWERPC_EXCP_POWER10) { - lpes0 = !!(env->spr[SPR_LPCR] & LPCR_LPES0); - } else -#endif /* defined(TARGET_PPC64) */ - { - lpes0 = true; - } - - /* * Hypervisor emulation assistance interrupt only exists on server * arch 2.05 server or later. We also don't want to generate it if * we don't have HVB in msr_mask (PAPR mode). @@ -470,8 +439,32 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) msr |= env->error_code; break; case POWERPC_EXCP_EXTERNAL: /* External input */ + { + bool lpes0; + cs = CPU(cpu); + /* + * Exception targeting modifiers + * + * LPES0 is supported on POWER7/8/9 + * LPES1 is not supported (old iSeries mode) + * + * On anything else, we behave as if LPES0 is 1 + * (externals don't alter MSR:HV) + */ +#if defined(TARGET_PPC64) + if (excp_model == POWERPC_EXCP_POWER7 || + excp_model == POWERPC_EXCP_POWER8 || + excp_model == POWERPC_EXCP_POWER9 || + excp_model == POWERPC_EXCP_POWER10) { + lpes0 = !!(env->spr[SPR_LPCR] & LPCR_LPES0); + } else +#endif /* defined(TARGET_PPC64) */ + { + lpes0 = true; + } + if (!lpes0) { new_msr |= (target_ulong)MSR_HVB; new_msr |= env->msr & ((target_ulong)1 << MSR_RI); @@ -483,6 +476,7 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) env->spr[SPR_BOOKE_EPR] = ldl_phys(cs->as, env->mpic_iack); } break; + } case POWERPC_EXCP_ALIGN: /* Alignment exception */ /* Get rS/rD and rA from faulting opcode */ /* @@ -558,7 +552,7 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) break; case POWERPC_EXCP_SYSCALL_VECTORED: /* scv exception */ lev = env->error_code; - dump_syscall_vectored(env); + dump_syscall(env); env->nip += 4; new_msr |= env->msr & ((target_ulong)1 << MSR_EE); new_msr |= env->msr & ((target_ulong)1 << MSR_RI); @@ -695,52 +689,20 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) "is not implemented yet !\n"); break; case POWERPC_EXCP_IFTLB: /* Instruction fetch TLB error */ - switch (excp_model) { - case POWERPC_EXCP_602: - case POWERPC_EXCP_603: - case POWERPC_EXCP_603E: - case POWERPC_EXCP_G2: - goto tlb_miss_tgpr; - case POWERPC_EXCP_7x5: - goto tlb_miss; - case POWERPC_EXCP_74xx: - goto tlb_miss_74xx; - default: - cpu_abort(cs, "Invalid instruction TLB miss exception\n"); - break; - } - break; case POWERPC_EXCP_DLTLB: /* Data load TLB miss */ - switch (excp_model) { - case POWERPC_EXCP_602: - case POWERPC_EXCP_603: - case POWERPC_EXCP_603E: - case POWERPC_EXCP_G2: - goto tlb_miss_tgpr; - case POWERPC_EXCP_7x5: - goto tlb_miss; - case POWERPC_EXCP_74xx: - goto tlb_miss_74xx; - default: - cpu_abort(cs, "Invalid data load TLB miss exception\n"); - break; - } - break; case POWERPC_EXCP_DSTLB: /* Data store TLB miss */ switch (excp_model) { case POWERPC_EXCP_602: case POWERPC_EXCP_603: case POWERPC_EXCP_603E: case POWERPC_EXCP_G2: - tlb_miss_tgpr: /* Swap temporary saved registers with GPRs */ if (!(new_msr & ((target_ulong)1 << MSR_TGPR))) { new_msr |= (target_ulong)1 << MSR_TGPR; hreg_swap_gpr_tgpr(env); } - goto tlb_miss; + /* fall through */ case POWERPC_EXCP_7x5: - tlb_miss: #if defined(DEBUG_SOFTWARE_TLB) if (qemu_log_enabled()) { const char *es; @@ -775,7 +737,6 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) msr |= ((env->last_way + 1) & (env->nb_ways - 1)) << 17; break; case POWERPC_EXCP_74xx: - tlb_miss_74xx: #if defined(DEBUG_SOFTWARE_TLB) if (qemu_log_enabled()) { const char *es; @@ -805,7 +766,7 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) msr |= env->error_code; /* key bit */ break; default: - cpu_abort(cs, "Invalid data store TLB miss exception\n"); + cpu_abort(cs, "Invalid TLB miss exception\n"); break; } break; @@ -1208,6 +1169,7 @@ void raise_exception_ra(CPUPPCState *env, uint32_t exception, raise_exception_err_ra(env, exception, 0, raddr); } +#ifdef CONFIG_TCG void helper_raise_exception_err(CPUPPCState *env, uint32_t exception, uint32_t error_code) { @@ -1218,8 +1180,10 @@ void helper_raise_exception(CPUPPCState *env, uint32_t exception) { raise_exception_err_ra(env, exception, 0, 0); } +#endif #if !defined(CONFIG_USER_ONLY) +#ifdef CONFIG_TCG void helper_store_msr(CPUPPCState *env, target_ulong val) { uint32_t excp = hreg_store_msr(env, val, 0); @@ -1259,6 +1223,7 @@ void helper_pminsn(CPUPPCState *env, powerpc_pm_insn_t insn) (env->spr[SPR_PSSCR] & PSSCR_EC); } #endif /* defined(TARGET_PPC64) */ +#endif /* CONFIG_TCG */ static inline void do_rfi(CPUPPCState *env, target_ulong nip, target_ulong msr) { @@ -1293,6 +1258,7 @@ static inline void do_rfi(CPUPPCState *env, target_ulong nip, target_ulong msr) check_tlb_flush(env, false); } +#ifdef CONFIG_TCG void helper_rfi(CPUPPCState *env) { do_rfi(env, env->spr[SPR_SRR0], env->spr[SPR_SRR1] & 0xfffffffful); @@ -1345,8 +1311,10 @@ void helper_rfmci(CPUPPCState *env) /* FIXME: choose CSRR1 or MCSRR1 based on cpu type */ do_rfi(env, env->spr[SPR_BOOKE_MCSRR0], env->spr[SPR_BOOKE_MCSRR1]); } -#endif +#endif /* CONFIG_TCG */ +#endif /* !defined(CONFIG_USER_ONLY) */ +#ifdef CONFIG_TCG void helper_tw(CPUPPCState *env, target_ulong arg1, target_ulong arg2, uint32_t flags) { @@ -1374,11 +1342,13 @@ void helper_td(CPUPPCState *env, target_ulong arg1, target_ulong arg2, } } #endif +#endif #if !defined(CONFIG_USER_ONLY) /*****************************************************************************/ /* PowerPC 601 specific instructions (POWER bridge) */ +#ifdef CONFIG_TCG void helper_rfsvc(CPUPPCState *env) { do_rfi(env, env->lr, env->ctr & 0x0000FFFF); @@ -1523,8 +1493,10 @@ void helper_book3s_msgsndp(CPUPPCState *env, target_ulong rb) book3s_msgsnd_common(pir, PPC_INTERRUPT_DOORBELL); } #endif +#endif /* CONFIG_TCG */ #endif +#ifdef CONFIG_TCG void ppc_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr) @@ -1540,3 +1512,4 @@ void ppc_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, env->error_code = insn & 0x03FF0000; cpu_loop_exit(cs); } +#endif diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index 44315fca0b..c4896cecc8 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -383,247 +383,35 @@ static inline void float_inexact_excp(CPUPPCState *env) } } -static inline void fpscr_set_rounding_mode(CPUPPCState *env) -{ - int rnd_type; - - /* Set rounding mode */ - switch (fpscr_rn) { - case 0: - /* Best approximation (round to nearest) */ - rnd_type = float_round_nearest_even; - break; - case 1: - /* Smaller magnitude (round toward zero) */ - rnd_type = float_round_to_zero; - break; - case 2: - /* Round toward +infinite */ - rnd_type = float_round_up; - break; - default: - case 3: - /* Round toward -infinite */ - rnd_type = float_round_down; - break; - } - set_float_rounding_mode(rnd_type, &env->fp_status); -} - void helper_fpscr_clrbit(CPUPPCState *env, uint32_t bit) { - int prev; - - prev = (env->fpscr >> bit) & 1; - env->fpscr &= ~(1 << bit); - if (prev == 1) { - switch (bit) { - case FPSCR_RN1: - case FPSCR_RN0: - fpscr_set_rounding_mode(env); - break; - case FPSCR_VXSNAN: - case FPSCR_VXISI: - case FPSCR_VXIDI: - case FPSCR_VXZDZ: - case FPSCR_VXIMZ: - case FPSCR_VXVC: - case FPSCR_VXSOFT: - case FPSCR_VXSQRT: - case FPSCR_VXCVI: - if (!fpscr_ix) { - /* Set VX bit to zero */ - env->fpscr &= ~FP_VX; - } - break; - case FPSCR_OX: - case FPSCR_UX: - case FPSCR_ZX: - case FPSCR_XX: - case FPSCR_VE: - case FPSCR_OE: - case FPSCR_UE: - case FPSCR_ZE: - case FPSCR_XE: - if (!fpscr_eex) { - /* Set the FEX bit */ - env->fpscr &= ~FP_FEX; - } - break; - default: - break; - } + uint32_t mask = 1u << bit; + if (env->fpscr & mask) { + ppc_store_fpscr(env, env->fpscr & ~(target_ulong)mask); } } void helper_fpscr_setbit(CPUPPCState *env, uint32_t bit) { - CPUState *cs = env_cpu(env); - int prev; - - prev = (env->fpscr >> bit) & 1; - env->fpscr |= 1 << bit; - if (prev == 0) { - switch (bit) { - case FPSCR_VX: - env->fpscr |= FP_FX; - if (fpscr_ve) { - goto raise_ve; - } - break; - case FPSCR_OX: - env->fpscr |= FP_FX; - if (fpscr_oe) { - goto raise_oe; - } - break; - case FPSCR_UX: - env->fpscr |= FP_FX; - if (fpscr_ue) { - goto raise_ue; - } - break; - case FPSCR_ZX: - env->fpscr |= FP_FX; - if (fpscr_ze) { - goto raise_ze; - } - break; - case FPSCR_XX: - env->fpscr |= FP_FX; - if (fpscr_xe) { - goto raise_xe; - } - break; - case FPSCR_VXSNAN: - case FPSCR_VXISI: - case FPSCR_VXIDI: - case FPSCR_VXZDZ: - case FPSCR_VXIMZ: - case FPSCR_VXVC: - case FPSCR_VXSOFT: - case FPSCR_VXSQRT: - case FPSCR_VXCVI: - env->fpscr |= FP_VX; - env->fpscr |= FP_FX; - if (fpscr_ve != 0) { - goto raise_ve; - } - break; - case FPSCR_VE: - if (fpscr_vx != 0) { - raise_ve: - env->error_code = POWERPC_EXCP_FP; - if (fpscr_vxsnan) { - env->error_code |= POWERPC_EXCP_FP_VXSNAN; - } - if (fpscr_vxisi) { - env->error_code |= POWERPC_EXCP_FP_VXISI; - } - if (fpscr_vxidi) { - env->error_code |= POWERPC_EXCP_FP_VXIDI; - } - if (fpscr_vxzdz) { - env->error_code |= POWERPC_EXCP_FP_VXZDZ; - } - if (fpscr_vximz) { - env->error_code |= POWERPC_EXCP_FP_VXIMZ; - } - if (fpscr_vxvc) { - env->error_code |= POWERPC_EXCP_FP_VXVC; - } - if (fpscr_vxsoft) { - env->error_code |= POWERPC_EXCP_FP_VXSOFT; - } - if (fpscr_vxsqrt) { - env->error_code |= POWERPC_EXCP_FP_VXSQRT; - } - if (fpscr_vxcvi) { - env->error_code |= POWERPC_EXCP_FP_VXCVI; - } - goto raise_excp; - } - break; - case FPSCR_OE: - if (fpscr_ox != 0) { - raise_oe: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_OX; - goto raise_excp; - } - break; - case FPSCR_UE: - if (fpscr_ux != 0) { - raise_ue: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_UX; - goto raise_excp; - } - break; - case FPSCR_ZE: - if (fpscr_zx != 0) { - raise_ze: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_ZX; - goto raise_excp; - } - break; - case FPSCR_XE: - if (fpscr_xx != 0) { - raise_xe: - env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_XX; - goto raise_excp; - } - break; - case FPSCR_RN1: - case FPSCR_RN0: - fpscr_set_rounding_mode(env); - break; - default: - break; - raise_excp: - /* Update the floating-point enabled exception summary */ - env->fpscr |= FP_FEX; - /* We have to update Rc1 before raising the exception */ - cs->exception_index = POWERPC_EXCP_PROGRAM; - break; - } + uint32_t mask = 1u << bit; + if (!(env->fpscr & mask)) { + ppc_store_fpscr(env, env->fpscr | mask); } } -void helper_store_fpscr(CPUPPCState *env, uint64_t arg, uint32_t mask) +void helper_store_fpscr(CPUPPCState *env, uint64_t val, uint32_t nibbles) { - CPUState *cs = env_cpu(env); - target_ulong prev, new; + target_ulong mask = 0; int i; - prev = env->fpscr; - new = (target_ulong)arg; - new &= ~(FP_FEX | FP_VX); - new |= prev & (FP_FEX | FP_VX); + /* TODO: push this extension back to translation time */ for (i = 0; i < sizeof(target_ulong) * 2; i++) { - if (mask & (1 << i)) { - env->fpscr &= ~(0xFLL << (4 * i)); - env->fpscr |= new & (0xFLL << (4 * i)); + if (nibbles & (1 << i)) { + mask |= (target_ulong) 0xf << (4 * i); } } - /* Update VX and FEX */ - if (fpscr_ix != 0) { - env->fpscr |= FP_VX; - } else { - env->fpscr &= ~FP_VX; - } - if ((fpscr_ex & fpscr_eex) != 0) { - env->fpscr |= FP_FEX; - cs->exception_index = POWERPC_EXCP_PROGRAM; - /* XXX: we should compute it properly */ - env->error_code = POWERPC_EXCP_FP; - } else { - env->fpscr &= ~FP_FEX; - } - fpscr_set_rounding_mode(env); -} - -void store_fpscr(CPUPPCState *env, uint64_t arg, uint32_t mask) -{ - helper_store_fpscr(env, arg, mask); + val = (val & mask) | (env->fpscr & ~mask); + ppc_store_fpscr(env, val); } static void do_float_check_status(CPUPPCState *env, uintptr_t raddr) @@ -822,6 +610,7 @@ static inline uint64_t do_fri(CPUPPCState *env, uint64_t arg, int rounding_mode) { CPU_DoubleU farg; + FloatRoundMode old_rounding_mode = get_float_rounding_mode(&env->fp_status); farg.ll = arg; @@ -834,8 +623,7 @@ static inline uint64_t do_fri(CPUPPCState *env, uint64_t arg, float_flag_inexact; set_float_rounding_mode(rounding_mode, &env->fp_status); farg.ll = float64_round_to_int(farg.d, &env->fp_status); - /* Restore rounding mode from FPSCR */ - fpscr_set_rounding_mode(env); + set_float_rounding_mode(old_rounding_mode, &env->fp_status); /* fri* does not set FPSCR[XX] */ if (!inexact) { @@ -3136,8 +2924,10 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \ { \ ppc_vsr_t t = *xt; \ int i; \ + FloatRoundMode curr_rounding_mode; \ \ if (rmode != FLOAT_ROUND_CURRENT) { \ + curr_rounding_mode = get_float_rounding_mode(&env->fp_status); \ set_float_rounding_mode(rmode, &env->fp_status); \ } \ \ @@ -3160,7 +2950,7 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \ * mode from FPSCR \ */ \ if (rmode != FLOAT_ROUND_CURRENT) { \ - fpscr_set_rounding_mode(env); \ + set_float_rounding_mode(curr_rounding_mode, &env->fp_status); \ env->fp_status.float_exception_flags &= ~float_flag_inexact; \ } \ \ diff --git a/target/ppc/gdbstub.c b/target/ppc/gdbstub.c index 9339e7eafe..09ff1328d4 100644 --- a/target/ppc/gdbstub.c +++ b/target/ppc/gdbstub.c @@ -20,7 +20,6 @@ #include "qemu/osdep.h" #include "cpu.h" #include "exec/gdbstub.h" -#include "exec/helper-proto.h" #include "internal.h" static int ppc_gdb_register_len_apple(int n) @@ -272,7 +271,7 @@ int ppc_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) break; case 70: /* fpscr */ - store_fpscr(env, ldtul_p(mem_buf), 0xffffffff); + ppc_store_fpscr(env, ldtul_p(mem_buf)); break; } } @@ -322,7 +321,7 @@ int ppc_cpu_gdb_write_register_apple(CPUState *cs, uint8_t *mem_buf, int n) break; case 70 + 32: /* fpscr */ - store_fpscr(env, ldq_p(mem_buf), 0xffffffff); + ppc_store_fpscr(env, ldq_p(mem_buf)); break; } } @@ -475,7 +474,7 @@ static int gdb_set_float_reg(CPUPPCState *env, uint8_t *mem_buf, int n) } if (n == 32) { ppc_maybe_bswap_register(env, mem_buf, 4); - store_fpscr(env, ldl_p(mem_buf), 0xffffffff); + ppc_store_fpscr(env, ldl_p(mem_buf)); return 4; } return 0; diff --git a/target/ppc/helper.h b/target/ppc/helper.h index ea9f2a236c..c517b9f025 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -46,6 +46,7 @@ DEF_HELPER_4(divwe, tl, env, tl, tl, i32) DEF_HELPER_FLAGS_1(popcntb, TCG_CALL_NO_RWG_SE, tl, tl) DEF_HELPER_FLAGS_2(cmpb, TCG_CALL_NO_RWG_SE, tl, tl, tl) DEF_HELPER_3(sraw, tl, env, tl, tl) +DEF_HELPER_FLAGS_2(cfuged, TCG_CALL_NO_RWG_SE, i64, i64, i64) #if defined(TARGET_PPC64) DEF_HELPER_FLAGS_2(cmpeqb, TCG_CALL_NO_RWG_SE, i32, tl, tl) DEF_HELPER_FLAGS_1(popcntw, TCG_CALL_NO_RWG_SE, tl, tl) diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode new file mode 100644 index 0000000000..9fd8d6b817 --- /dev/null +++ b/target/ppc/insn32.decode @@ -0,0 +1,126 @@ +# +# Power ISA decode for 32-bit insns (opcode space 0) +# +# Copyright (c) 2021 Instituto de Pesquisas Eldorado (eldorado.org.br) +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. +# + +&D rt ra si:int64_t +@D ...... rt:5 ra:5 si:s16 &D + +&D_bf bf l:bool ra imm +@D_bfs ...... bf:3 - l:1 ra:5 imm:s16 &D_bf +@D_bfu ...... bf:3 - l:1 ra:5 imm:16 &D_bf + +%ds_si 2:s14 !function=times_4 +@DS ...... rt:5 ra:5 .............. .. &D si=%ds_si + +&DX rt d +%dx_d 6:s10 16:5 0:1 +@DX ...... rt:5 ..... .......... ..... . &DX d=%dx_d + +&VX vrt vra vrb +@VX ...... vrt:5 vra:5 vrb:5 .......... . &VX + +&X rt ra rb +@X ...... rt:5 ra:5 rb:5 .......... . &X + +&X_bi rt bi +@X_bi ...... rt:5 bi:5 ----- .......... - &X_bi + +&X_bfl bf l:bool ra rb +@X_bfl ...... bf:3 - l:1 ra:5 rb:5 ..........- &X_bfl + +### Fixed-Point Load Instructions + +LBZ 100010 ..... ..... ................ @D +LBZU 100011 ..... ..... ................ @D +LBZX 011111 ..... ..... ..... 0001010111 - @X +LBZUX 011111 ..... ..... ..... 0001110111 - @X + +LHZ 101000 ..... ..... ................ @D +LHZU 101001 ..... ..... ................ @D +LHZX 011111 ..... ..... ..... 0100010111 - @X +LHZUX 011111 ..... ..... ..... 0100110111 - @X + +LHA 101010 ..... ..... ................ @D +LHAU 101011 ..... ..... ................ @D +LHAX 011111 ..... ..... ..... 0101010111 - @X +LHAXU 011111 ..... ..... ..... 0101110111 - @X + +LWZ 100000 ..... ..... ................ @D +LWZU 100001 ..... ..... ................ @D +LWZX 011111 ..... ..... ..... 0000010111 - @X +LWZUX 011111 ..... ..... ..... 0000110111 - @X + +LWA 111010 ..... ..... ..............10 @DS +LWAX 011111 ..... ..... ..... 0101010101 - @X +LWAUX 011111 ..... ..... ..... 0101110101 - @X + +LD 111010 ..... ..... ..............00 @DS +LDU 111010 ..... ..... ..............01 @DS +LDX 011111 ..... ..... ..... 0000010101 - @X +LDUX 011111 ..... ..... ..... 0000110101 - @X + +### Fixed-Point Store Instructions + +STB 100110 ..... ..... ................ @D +STBU 100111 ..... ..... ................ @D +STBX 011111 ..... ..... ..... 0011010111 - @X +STBUX 011111 ..... ..... ..... 0011110111 - @X + +STH 101100 ..... ..... ................ @D +STHU 101101 ..... ..... ................ @D +STHX 011111 ..... ..... ..... 0110010111 - @X +STHUX 011111 ..... ..... ..... 0110110111 - @X + +STW 100100 ..... ..... ................ @D +STWU 100101 ..... ..... ................ @D +STWX 011111 ..... ..... ..... 0010010111 - @X +STWUX 011111 ..... ..... ..... 0010110111 - @X + +STD 111110 ..... ..... ..............00 @DS +STDU 111110 ..... ..... ..............01 @DS +STDX 011111 ..... ..... ..... 0010010101 - @X +STDUX 011111 ..... ..... ..... 0010110101 - @X + +### Fixed-Point Compare Instructions + +CMP 011111 ... - . ..... ..... 0000000000 - @X_bfl +CMPL 011111 ... - . ..... ..... 0000100000 - @X_bfl +CMPI 001011 ... - . ..... ................ @D_bfs +CMPLI 001010 ... - . ..... ................ @D_bfu + +### Fixed-Point Arithmetic Instructions + +ADDI 001110 ..... ..... ................ @D +ADDIS 001111 ..... ..... ................ @D + +ADDPCIS 010011 ..... ..... .......... 00010 . @DX + +## Fixed-Point Logical Instructions + +CFUGED 011111 ..... ..... ..... 0011011100 - @X + +### Move To/From System Register Instructions + +SETBC 011111 ..... ..... ----- 0110000000 - @X_bi +SETBCR 011111 ..... ..... ----- 0110100000 - @X_bi +SETNBC 011111 ..... ..... ----- 0111000000 - @X_bi +SETNBCR 011111 ..... ..... ----- 0111100000 - @X_bi + +## Vector Bit Manipulation Instruction + +VCFUGED 000100 ..... ..... ..... 10101001101 @VX diff --git a/target/ppc/insn64.decode b/target/ppc/insn64.decode new file mode 100644 index 0000000000..72c5944a53 --- /dev/null +++ b/target/ppc/insn64.decode @@ -0,0 +1,124 @@ +# +# Power ISA decode for 64-bit prefixed insns (opcode space 0 and 1) +# +# Copyright (c) 2021 Instituto de Pesquisas Eldorado (eldorado.org.br) +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. +# + +# Format MLS:D and 8LS:D +&PLS_D rt ra si:int64_t r:bool +%pls_si 32:s18 0:16 +@PLS_D ...... .. ... r:1 .. .................. \ + ...... rt:5 ra:5 ................ \ + &PLS_D si=%pls_si + +### Fixed-Point Load Instructions + +PLBZ 000001 10 0--.-- .................. \ + 100010 ..... ..... ................ @PLS_D +PLHZ 000001 10 0--.-- .................. \ + 101000 ..... ..... ................ @PLS_D +PLHA 000001 10 0--.-- .................. \ + 101010 ..... ..... ................ @PLS_D +PLWZ 000001 10 0--.-- .................. \ + 100000 ..... ..... ................ @PLS_D +PLWA 000001 00 0--.-- .................. \ + 101001 ..... ..... ................ @PLS_D +PLD 000001 00 0--.-- .................. \ + 111001 ..... ..... ................ @PLS_D + +### Fixed-Point Store Instructions + +PSTW 000001 10 0--.-- .................. \ + 100100 ..... ..... ................ @PLS_D +PSTB 000001 10 0--.-- .................. \ + 100110 ..... ..... ................ @PLS_D +PSTH 000001 10 0--.-- .................. \ + 101100 ..... ..... ................ @PLS_D + +PSTD 000001 00 0--.-- .................. \ + 111101 ..... ..... ................ @PLS_D + +### Fixed-Point Arithmetic Instructions + +PADDI 000001 10 0--.-- .................. \ + 001110 ..... ..... ................ @PLS_D + +### Prefixed No-operation Instruction + +@PNOP 000001 11 0000-- 000000000000000000 \ + ................................ + +{ + [ + ## Invalid suffixes: Branch instruction + # bc[l][a] + INVALID ................................ \ + 010000-------------------------- @PNOP + # b[l][a] + INVALID ................................ \ + 010010-------------------------- @PNOP + # bclr[l] + INVALID ................................ \ + 010011---------------0000010000- @PNOP + # bcctr[l] + INVALID ................................ \ + 010011---------------1000010000- @PNOP + # bctar[l] + INVALID ................................ \ + 010011---------------1000110000- @PNOP + + ## Invalid suffixes: rfebb + INVALID ................................ \ + 010011---------------0010010010- @PNOP + + ## Invalid suffixes: context synchronizing other than isync + # sc + INVALID ................................ \ + 010001------------------------1- @PNOP + # scv + INVALID ................................ \ + 010001------------------------01 @PNOP + # rfscv + INVALID ................................ \ + 010011---------------0001010010- @PNOP + # rfid + INVALID ................................ \ + 010011---------------0000010010- @PNOP + # hrfid + INVALID ................................ \ + 010011---------------0100010010- @PNOP + # urfid + INVALID ................................ \ + 010011---------------0100110010- @PNOP + # stop + INVALID ................................ \ + 010011---------------0101110010- @PNOP + # mtmsr w/ L=0 + INVALID ................................ \ + 011111---------0-----0010010010- @PNOP + # mtmsrd w/ L=0 + INVALID ................................ \ + 011111---------0-----0010110010- @PNOP + + ## Invalid suffixes: Service Processor Attention + INVALID ................................ \ + 000000----------------100000000- @PNOP + ] + + ## Valid suffixes + PNOP ................................ \ + -------------------------------- @PNOP +} diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index 41f8477d4b..efa833ef64 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -320,6 +320,68 @@ target_ulong helper_popcntb(target_ulong val) } #endif +uint64_t helper_cfuged(uint64_t src, uint64_t mask) +{ + /* + * Instead of processing the mask bit-by-bit from the most significant to + * the least significant bit, as described in PowerISA, we'll handle it in + * blocks of 'n' zeros/ones from LSB to MSB. To avoid the decision to use + * ctz or cto, we negate the mask at the end of the loop. + */ + target_ulong m, left = 0, right = 0; + unsigned int n, i = 64; + bool bit = false; /* tracks if we are processing zeros or ones */ + + if (mask == 0 || mask == -1) { + return src; + } + + /* Processes the mask in blocks, from LSB to MSB */ + while (i) { + /* Find how many bits we should take */ + n = ctz64(mask); + if (n > i) { + n = i; + } + + /* + * Extracts 'n' trailing bits of src and put them on the leading 'n' + * bits of 'right' or 'left', pushing down the previously extracted + * values. + */ + m = (1ll << n) - 1; + if (bit) { + right = ror64(right | (src & m), n); + } else { + left = ror64(left | (src & m), n); + } + + /* + * Discards the processed bits from 'src' and 'mask'. Note that we are + * removing 'n' trailing zeros from 'mask', but the logical shift will + * add 'n' leading zeros back, so the population count of 'mask' is kept + * the same. + */ + src >>= n; + mask >>= n; + i -= n; + bit = !bit; + mask = ~mask; + } + + /* + * At the end, right was ror'ed ctpop(mask) times. To put it back in place, + * we'll shift it more 64-ctpop(mask) times. + */ + if (bit) { + n = ctpop64(mask); + } else { + n = 64 - ctpop64(mask); + } + + return left | (right >> n); +} + /*****************************************************************************/ /* PowerPC 601 specific instructions (POWER bridge) */ target_ulong helper_div(CPUPPCState *env, target_ulong arg1, target_ulong arg2) diff --git a/target/ppc/internal.h b/target/ppc/internal.h index 2b4b06eb76..f1fd3c8d04 100644 --- a/target/ppc/internal.h +++ b/target/ppc/internal.h @@ -218,8 +218,6 @@ void ppc_cpu_do_unaligned_access(CPUState *cs, vaddr addr, /* translate.c */ -/* #define PPC_DUMP_CPU */ - int ppc_fixup_cpu(PowerPCCPU *cpu); void create_ppc_opcodes(PowerPCCPU *cpu, Error **errp); void destroy_ppc_opcodes(PowerPCCPU *cpu); diff --git a/target/ppc/meson.build b/target/ppc/meson.build index d1aa7d5d39..a4f18ff414 100644 --- a/target/ppc/meson.build +++ b/target/ppc/meson.build @@ -3,11 +3,14 @@ ppc_ss.add(files( 'cpu-models.c', 'cpu.c', 'cpu_init.c', - 'dfp_helper.c', 'excp_helper.c', - 'fpu_helper.c', 'gdbstub.c', 'helper_regs.c', +)) + +ppc_ss.add(when: 'CONFIG_TCG', if_true: files( + 'dfp_helper.c', + 'fpu_helper.c', 'int_helper.c', 'mem_helper.c', 'misc_helper.c', @@ -17,6 +20,15 @@ ppc_ss.add(files( ppc_ss.add(libdecnumber) +gen = [ + decodetree.process('insn32.decode', + extra_args: '--static-decode=decode_insn32'), + decodetree.process('insn64.decode', + extra_args: ['--static-decode=decode_insn64', + '--insnwidth=64']), +] +ppc_ss.add(gen) + ppc_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c'), if_false: files('kvm-stub.c')) ppc_ss.add(when: 'CONFIG_USER_ONLY', if_true: files('user_only_helper.c')) @@ -28,6 +40,10 @@ ppc_softmmu_ss.add(files( 'mmu_helper.c', 'monitor.c', )) +ppc_softmmu_ss.add(when: 'CONFIG_TCG', if_false: files( + 'tcg-stub.c' +)) + ppc_softmmu_ss.add(when: 'TARGET_PPC64', if_true: files( 'compat.c', 'mmu-book3s-v3.c', diff --git a/target/ppc/misc_helper.c b/target/ppc/misc_helper.c index 08a31da289..c33f5f39b9 100644 --- a/target/ppc/misc_helper.c +++ b/target/ppc/misc_helper.c @@ -23,6 +23,7 @@ #include "exec/helper-proto.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" +#include "mmu-book3s-v3.h" #include "helper_regs.h" @@ -116,7 +117,28 @@ void helper_store_sdr1(CPUPPCState *env, target_ulong val) void helper_store_ptcr(CPUPPCState *env, target_ulong val) { if (env->spr[SPR_PTCR] != val) { - ppc_store_ptcr(env, val); + PowerPCCPU *cpu = env_archcpu(env); + target_ulong ptcr_mask = PTCR_PATB | PTCR_PATS; + target_ulong patbsize = val & PTCR_PATS; + + qemu_log_mask(CPU_LOG_MMU, "%s: " TARGET_FMT_lx "\n", __func__, val); + + assert(!cpu->vhyp); + assert(env->mmu_model & POWERPC_MMU_3_00); + + if (val & ~ptcr_mask) { + error_report("Invalid bits 0x"TARGET_FMT_lx" set in PTCR", + val & ~ptcr_mask); + val &= ptcr_mask; + } + + if (patbsize > 24) { + error_report("Invalid Partition Table size 0x" TARGET_FMT_lx + " stored in PTCR", patbsize); + return; + } + + env->spr[SPR_PTCR] = val; tlb_flush(env_cpu(env)); } } @@ -255,22 +277,6 @@ target_ulong helper_clcs(CPUPPCState *env, uint32_t arg) /*****************************************************************************/ /* Special registers manipulation */ -/* GDBstub can read and write MSR... */ -void ppc_store_msr(CPUPPCState *env, target_ulong value) -{ - hreg_store_msr(env, value, 0); -} - -void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val) -{ - PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); - CPUPPCState *env = &cpu->env; - - env->spr[SPR_LPCR] = val & pcc->lpcr_mask; - /* The gtse bit affects hflags */ - hreg_compute_hflags(env); -} - /* * This code is lifted from MacOnLinux. It is called whenever THRM1,2 * or 3 is read an fixes up the values in such a way that will make diff --git a/target/ppc/mmu-hash32.c b/target/ppc/mmu-hash32.c index 744a763f44..9f0a497657 100644 --- a/target/ppc/mmu-hash32.c +++ b/target/ppc/mmu-hash32.c @@ -21,7 +21,6 @@ #include "qemu/osdep.h" #include "cpu.h" #include "exec/exec-all.h" -#include "exec/helper-proto.h" #include "sysemu/kvm.h" #include "kvm_ppc.h" #include "internal.h" diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index f48b625f48..708dffc31b 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -21,7 +21,6 @@ #include "qemu/units.h" #include "cpu.h" #include "exec/exec-all.h" -#include "exec/helper-proto.h" #include "qemu/error-report.h" #include "qemu/qemu-print.h" #include "sysemu/hw_accel.h" @@ -33,6 +32,10 @@ #include "mmu-book3s-v3.h" #include "helper_regs.h" +#ifdef CONFIG_TCG +#include "exec/helper-proto.h" +#endif + /* #define DEBUG_SLB */ #ifdef DEBUG_SLB @@ -97,6 +100,7 @@ void dump_slb(PowerPCCPU *cpu) } } +#ifdef CONFIG_TCG void helper_slbia(CPUPPCState *env, uint32_t ih) { PowerPCCPU *cpu = env_archcpu(env); @@ -202,6 +206,7 @@ void helper_slbieg(CPUPPCState *env, target_ulong addr) { __helper_slbie(env, addr, true); } +#endif int ppc_store_slb(PowerPCCPU *cpu, target_ulong slot, target_ulong esid, target_ulong vsid) @@ -255,6 +260,7 @@ int ppc_store_slb(PowerPCCPU *cpu, target_ulong slot, return 0; } +#ifdef CONFIG_TCG static int ppc_load_slb_esid(PowerPCCPU *cpu, target_ulong rb, target_ulong *rt) { @@ -348,6 +354,7 @@ target_ulong helper_load_slb_vsid(CPUPPCState *env, target_ulong rb) } return rt; } +#endif /* Check No-Execute or Guarded Storage */ static inline int ppc_hash64_pte_noexec_guard(PowerPCCPU *cpu, @@ -1139,12 +1146,14 @@ void ppc_hash64_tlb_flush_hpte(PowerPCCPU *cpu, target_ulong ptex, cpu->env.tlb_need_flush = TLB_NEED_GLOBAL_FLUSH | TLB_NEED_LOCAL_FLUSH; } +#ifdef CONFIG_TCG void helper_store_lpcr(CPUPPCState *env, target_ulong val) { PowerPCCPU *cpu = env_archcpu(env); ppc_store_lpcr(cpu, val); } +#endif void ppc_hash64_init(PowerPCCPU *cpu) { diff --git a/target/ppc/mmu-radix64.c b/target/ppc/mmu-radix64.c index 7972153f23..b6d191c1d8 100644 --- a/target/ppc/mmu-radix64.c +++ b/target/ppc/mmu-radix64.c @@ -20,7 +20,6 @@ #include "qemu/osdep.h" #include "cpu.h" #include "exec/exec-all.h" -#include "exec/helper-proto.h" #include "qemu/error-report.h" #include "sysemu/kvm.h" #include "kvm_ppc.h" diff --git a/target/ppc/mmu_helper.c b/target/ppc/mmu_helper.c index 37986c59ba..1ecb36e85a 100644 --- a/target/ppc/mmu_helper.c +++ b/target/ppc/mmu_helper.c @@ -20,13 +20,11 @@ #include "qemu/osdep.h" #include "qemu/units.h" #include "cpu.h" -#include "exec/helper-proto.h" #include "sysemu/kvm.h" #include "kvm_ppc.h" #include "mmu-hash64.h" #include "mmu-hash32.h" #include "exec/exec-all.h" -#include "exec/cpu_ldst.h" #include "exec/log.h" #include "helper_regs.h" #include "qemu/error-report.h" @@ -36,6 +34,10 @@ #include "mmu-book3s-v3.h" #include "mmu-radix64.h" +#ifdef CONFIG_TCG +#include "exec/helper-proto.h" +#include "exec/cpu_ldst.h" +#endif /* #define DEBUG_MMU */ /* #define DEBUG_BATS */ /* #define DEBUG_SOFTWARE_TLB */ @@ -268,6 +270,7 @@ static inline void ppc6xx_tlb_invalidate_virt(CPUPPCState *env, ppc6xx_tlb_invalidate_virt2(env, eaddr, is_code, 0); } +#ifdef CONFIG_TCG static void ppc6xx_tlb_store(CPUPPCState *env, target_ulong EPN, int way, int is_code, target_ulong pte0, target_ulong pte1) { @@ -286,6 +289,7 @@ static void ppc6xx_tlb_store(CPUPPCState *env, target_ulong EPN, int way, /* Store last way for LRU mechanism */ env->last_way = way; } +#endif static int ppc6xx_tlb_check(CPUPPCState *env, mmu_ctx_t *ctx, target_ulong eaddr, MMUAccessType access_type) @@ -626,6 +630,7 @@ static int ppcemb_tlb_check(CPUPPCState *env, ppcemb_tlb_t *tlb, return 0; } +#ifdef CONFIG_TCG /* Generic TLB search function for PowerPC embedded implementations */ static int ppcemb_tlb_search(CPUPPCState *env, target_ulong address, uint32_t pid) @@ -646,6 +651,7 @@ static int ppcemb_tlb_search(CPUPPCState *env, target_ulong address, return ret; } +#endif /* Helpers specific to PowerPC 40x implementations */ static inline void ppc4xx_tlb_invalidate_all(CPUPPCState *env) @@ -1420,12 +1426,14 @@ static int get_physical_address_wtlb(CPUPPCState *env, mmu_ctx_t *ctx, return ret; } +#ifdef CONFIG_TCG static int get_physical_address(CPUPPCState *env, mmu_ctx_t *ctx, target_ulong eaddr, MMUAccessType access_type, int type) { return get_physical_address_wtlb(env, ctx, eaddr, access_type, type, 0); } +#endif hwaddr ppc_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) { @@ -1752,6 +1760,7 @@ static int cpu_ppc_handle_mmu_fault(CPUPPCState *env, target_ulong address, return ret; } +#ifdef CONFIG_TCG /*****************************************************************************/ /* BATs management */ #if !defined(FLUSH_ALL_TLBS) @@ -1941,6 +1950,7 @@ void helper_store_601_batl(CPUPPCState *env, uint32_t nr, target_ulong value) #endif } } +#endif /*****************************************************************************/ /* TLB management */ @@ -1986,6 +1996,7 @@ void ppc_tlb_invalidate_all(CPUPPCState *env) } } +#ifdef CONFIG_TCG void ppc_tlb_invalidate_one(CPUPPCState *env, target_ulong addr) { #if !defined(FLUSH_ALL_TLBS) @@ -2030,34 +2041,6 @@ void ppc_tlb_invalidate_one(CPUPPCState *env, target_ulong addr) /*****************************************************************************/ /* Special registers manipulation */ -#if defined(TARGET_PPC64) -void ppc_store_ptcr(CPUPPCState *env, target_ulong value) -{ - PowerPCCPU *cpu = env_archcpu(env); - target_ulong ptcr_mask = PTCR_PATB | PTCR_PATS; - target_ulong patbsize = value & PTCR_PATS; - - qemu_log_mask(CPU_LOG_MMU, "%s: " TARGET_FMT_lx "\n", __func__, value); - - assert(!cpu->vhyp); - assert(env->mmu_model & POWERPC_MMU_3_00); - - if (value & ~ptcr_mask) { - error_report("Invalid bits 0x"TARGET_FMT_lx" set in PTCR", - value & ~ptcr_mask); - value &= ptcr_mask; - } - - if (patbsize > 24) { - error_report("Invalid Partition Table size 0x" TARGET_FMT_lx - " stored in PTCR", patbsize); - return; - } - - env->spr[SPR_PTCR] = value; -} - -#endif /* defined(TARGET_PPC64) */ /* Segment registers load and store */ target_ulong helper_load_sr(CPUPPCState *env, target_ulong sr_num) @@ -2955,6 +2938,7 @@ void helper_check_tlb_flush_global(CPUPPCState *env) { check_tlb_flush(env, true); } +#endif /* CONFIG_TCG */ /*****************************************************************************/ diff --git a/target/ppc/tcg-stub.c b/target/ppc/tcg-stub.c new file mode 100644 index 0000000000..aadcf59d26 --- /dev/null +++ b/target/ppc/tcg-stub.c @@ -0,0 +1,45 @@ +/* + * PowerPC CPU initialization for qemu. + * + * Copyright (C) 2021 Instituto de Pesquisas Eldorado (eldorado.org.br) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ +#include "qemu/osdep.h" +#include "cpu.h" +#include "internal.h" +#include "hw/ppc/spapr.h" + +void create_ppc_opcodes(PowerPCCPU *cpu, Error **errp) +{ +} + +void destroy_ppc_opcodes(PowerPCCPU *cpu) +{ +} + +target_ulong softmmu_resize_hpt_prepare(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong shift) +{ + g_assert_not_reached(); +} + +target_ulong softmmu_resize_hpt_commit(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong flags, + target_ulong shift) +{ + g_assert_not_reached(); +} diff --git a/target/ppc/trace-events b/target/ppc/trace-events index bc0d4e6f8b..c88cfccf8d 100644 --- a/target/ppc/trace-events +++ b/target/ppc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # kvm.c kvm_failed_spr_set(int spr, const char *msg) "Warning: Unable to set SPR %d to KVM: %s" diff --git a/target/ppc/translate.c b/target/ppc/translate.c index ea200f9637..f65d1e81ea 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -47,7 +47,6 @@ /* Include definitions for instructions classes and implementations flags */ /* #define PPC_DEBUG_DISAS */ -/* #define DO_PPC_STATISTICS */ #ifdef PPC_DEBUG_DISAS # define LOG_DISAS(...) qemu_log_mask(CPU_LOG_TB_IN_ASM, ## __VA_ARGS__) @@ -217,12 +216,6 @@ struct opc_handler_t { uint64_t type2; /* handler */ void (*handler)(DisasContext *ctx); -#if defined(DO_PPC_STATISTICS) || defined(PPC_DUMP_CPU) - const char *oname; -#endif -#if defined(DO_PPC_STATISTICS) - uint64_t count; -#endif }; /* SPR load/store helpers */ @@ -1345,7 +1338,6 @@ typedef struct opcode_t { /*****************************************************************************/ /* PowerPC instructions table */ -#if defined(DO_PPC_STATISTICS) #define GEN_OPCODE(name, op1, op2, op3, invl, _typ, _typ2) \ { \ .opc1 = op1, \ @@ -1357,7 +1349,6 @@ typedef struct opcode_t { .type = _typ, \ .type2 = _typ2, \ .handler = &gen_##name, \ - .oname = stringify(name), \ }, \ .oname = stringify(name), \ } @@ -1373,7 +1364,6 @@ typedef struct opcode_t { .type = _typ, \ .type2 = _typ2, \ .handler = &gen_##name, \ - .oname = stringify(name), \ }, \ .oname = stringify(name), \ } @@ -1388,7 +1378,6 @@ typedef struct opcode_t { .type = _typ, \ .type2 = _typ2, \ .handler = &gen_##name, \ - .oname = onam, \ }, \ .oname = onam, \ } @@ -1403,7 +1392,6 @@ typedef struct opcode_t { .type = _typ, \ .type2 = _typ2, \ .handler = &gen_##name, \ - .oname = stringify(name), \ }, \ .oname = stringify(name), \ } @@ -1418,83 +1406,9 @@ typedef struct opcode_t { .type = _typ, \ .type2 = _typ2, \ .handler = &gen_##name, \ - .oname = onam, \ }, \ .oname = onam, \ } -#else -#define GEN_OPCODE(name, op1, op2, op3, invl, _typ, _typ2) \ -{ \ - .opc1 = op1, \ - .opc2 = op2, \ - .opc3 = op3, \ - .opc4 = 0xff, \ - .handler = { \ - .inval1 = invl, \ - .type = _typ, \ - .type2 = _typ2, \ - .handler = &gen_##name, \ - }, \ - .oname = stringify(name), \ -} -#define GEN_OPCODE_DUAL(name, op1, op2, op3, invl1, invl2, _typ, _typ2) \ -{ \ - .opc1 = op1, \ - .opc2 = op2, \ - .opc3 = op3, \ - .opc4 = 0xff, \ - .handler = { \ - .inval1 = invl1, \ - .inval2 = invl2, \ - .type = _typ, \ - .type2 = _typ2, \ - .handler = &gen_##name, \ - }, \ - .oname = stringify(name), \ -} -#define GEN_OPCODE2(name, onam, op1, op2, op3, invl, _typ, _typ2) \ -{ \ - .opc1 = op1, \ - .opc2 = op2, \ - .opc3 = op3, \ - .opc4 = 0xff, \ - .handler = { \ - .inval1 = invl, \ - .type = _typ, \ - .type2 = _typ2, \ - .handler = &gen_##name, \ - }, \ - .oname = onam, \ -} -#define GEN_OPCODE3(name, op1, op2, op3, op4, invl, _typ, _typ2) \ -{ \ - .opc1 = op1, \ - .opc2 = op2, \ - .opc3 = op3, \ - .opc4 = op4, \ - .handler = { \ - .inval1 = invl, \ - .type = _typ, \ - .type2 = _typ2, \ - .handler = &gen_##name, \ - }, \ - .oname = stringify(name), \ -} -#define GEN_OPCODE4(name, onam, op1, op2, op3, op4, invl, _typ, _typ2) \ -{ \ - .opc1 = op1, \ - .opc2 = op2, \ - .opc3 = op3, \ - .opc4 = op4, \ - .handler = { \ - .inval1 = invl, \ - .type = _typ, \ - .type2 = _typ2, \ - .handler = &gen_##name, \ - }, \ - .oname = onam, \ -} -#endif /* Invalid instruction */ static void gen_invalid(DisasContext *ctx) @@ -1575,54 +1489,6 @@ static inline void gen_set_Rc0(DisasContext *ctx, TCGv reg) } } -/* cmp */ -static void gen_cmp(DisasContext *ctx) -{ - if ((ctx->opcode & 0x00200000) && (ctx->insns_flags & PPC_64B)) { - gen_op_cmp(cpu_gpr[rA(ctx->opcode)], cpu_gpr[rB(ctx->opcode)], - 1, crfD(ctx->opcode)); - } else { - gen_op_cmp32(cpu_gpr[rA(ctx->opcode)], cpu_gpr[rB(ctx->opcode)], - 1, crfD(ctx->opcode)); - } -} - -/* cmpi */ -static void gen_cmpi(DisasContext *ctx) -{ - if ((ctx->opcode & 0x00200000) && (ctx->insns_flags & PPC_64B)) { - gen_op_cmpi(cpu_gpr[rA(ctx->opcode)], SIMM(ctx->opcode), - 1, crfD(ctx->opcode)); - } else { - gen_op_cmpi32(cpu_gpr[rA(ctx->opcode)], SIMM(ctx->opcode), - 1, crfD(ctx->opcode)); - } -} - -/* cmpl */ -static void gen_cmpl(DisasContext *ctx) -{ - if ((ctx->opcode & 0x00200000) && (ctx->insns_flags & PPC_64B)) { - gen_op_cmp(cpu_gpr[rA(ctx->opcode)], cpu_gpr[rB(ctx->opcode)], - 0, crfD(ctx->opcode)); - } else { - gen_op_cmp32(cpu_gpr[rA(ctx->opcode)], cpu_gpr[rB(ctx->opcode)], - 0, crfD(ctx->opcode)); - } -} - -/* cmpli */ -static void gen_cmpli(DisasContext *ctx) -{ - if ((ctx->opcode & 0x00200000) && (ctx->insns_flags & PPC_64B)) { - gen_op_cmpi(cpu_gpr[rA(ctx->opcode)], UIMM(ctx->opcode), - 0, crfD(ctx->opcode)); - } else { - gen_op_cmpi32(cpu_gpr[rA(ctx->opcode)], UIMM(ctx->opcode), - 0, crfD(ctx->opcode)); - } -} - /* cmprb - range comparison: isupper, isaplha, islower*/ static void gen_cmprb(DisasContext *ctx) { @@ -1846,19 +1712,6 @@ GEN_INT_ARITH_ADD(addex, 0x05, cpu_ov, 1, 1, 0); /* addze addze. addzeo addzeo.*/ GEN_INT_ARITH_ADD_CONST(addze, 0x06, 0, cpu_ca, 1, 1, 0) GEN_INT_ARITH_ADD_CONST(addzeo, 0x16, 0, cpu_ca, 1, 1, 1) -/* addi */ -static void gen_addi(DisasContext *ctx) -{ - target_long simm = SIMM(ctx->opcode); - - if (rA(ctx->opcode) == 0) { - /* li case */ - tcg_gen_movi_tl(cpu_gpr[rD(ctx->opcode)], simm); - } else { - tcg_gen_addi_tl(cpu_gpr[rD(ctx->opcode)], - cpu_gpr[rA(ctx->opcode)], simm); - } -} /* addic addic.*/ static inline void gen_op_addic(DisasContext *ctx, bool compute_rc0) { @@ -1878,28 +1731,6 @@ static void gen_addic_(DisasContext *ctx) gen_op_addic(ctx, 1); } -/* addis */ -static void gen_addis(DisasContext *ctx) -{ - target_long simm = SIMM(ctx->opcode); - - if (rA(ctx->opcode) == 0) { - /* lis case */ - tcg_gen_movi_tl(cpu_gpr[rD(ctx->opcode)], simm << 16); - } else { - tcg_gen_addi_tl(cpu_gpr[rD(ctx->opcode)], - cpu_gpr[rA(ctx->opcode)], simm << 16); - } -} - -/* addpcis */ -static void gen_addpcis(DisasContext *ctx) -{ - target_long d = DX(ctx->opcode); - - tcg_gen_movi_tl(cpu_gpr[rD(ctx->opcode)], ctx->base.pc_next + (d << 16)); -} - static inline void gen_op_arith_divw(DisasContext *ctx, TCGv ret, TCGv arg1, TCGv arg2, int sign, int compute_ov) { @@ -3412,7 +3243,9 @@ static void glue(gen_qemu_, stop)(DisasContext *ctx, \ tcg_gen_qemu_st_tl(val, addr, ctx->mem_idx, op); \ } +#if defined(TARGET_PPC64) || !defined(CONFIG_USER_ONLY) GEN_QEMU_STORE_TL(st8, DEF_MEMOP(MO_UB)) +#endif GEN_QEMU_STORE_TL(st16, DEF_MEMOP(MO_UW)) GEN_QEMU_STORE_TL(st32, DEF_MEMOP(MO_UL)) @@ -3436,54 +3269,6 @@ GEN_QEMU_STORE_64(st64, DEF_MEMOP(MO_Q)) GEN_QEMU_STORE_64(st64r, BSWAP_MEMOP(MO_Q)) #endif -#define GEN_LD(name, ldop, opc, type) \ -static void glue(gen_, name)(DisasContext *ctx) \ -{ \ - TCGv EA; \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - gen_addr_imm_index(ctx, EA, 0); \ - gen_qemu_##ldop(ctx, cpu_gpr[rD(ctx->opcode)], EA); \ - tcg_temp_free(EA); \ -} - -#define GEN_LDU(name, ldop, opc, type) \ -static void glue(gen_, name##u)(DisasContext *ctx) \ -{ \ - TCGv EA; \ - if (unlikely(rA(ctx->opcode) == 0 || \ - rA(ctx->opcode) == rD(ctx->opcode))) { \ - gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL); \ - return; \ - } \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - if (type == PPC_64B) \ - gen_addr_imm_index(ctx, EA, 0x03); \ - else \ - gen_addr_imm_index(ctx, EA, 0); \ - gen_qemu_##ldop(ctx, cpu_gpr[rD(ctx->opcode)], EA); \ - tcg_gen_mov_tl(cpu_gpr[rA(ctx->opcode)], EA); \ - tcg_temp_free(EA); \ -} - -#define GEN_LDUX(name, ldop, opc2, opc3, type) \ -static void glue(gen_, name##ux)(DisasContext *ctx) \ -{ \ - TCGv EA; \ - if (unlikely(rA(ctx->opcode) == 0 || \ - rA(ctx->opcode) == rD(ctx->opcode))) { \ - gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL); \ - return; \ - } \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - gen_addr_reg_index(ctx, EA); \ - gen_qemu_##ldop(ctx, cpu_gpr[rD(ctx->opcode)], EA); \ - tcg_gen_mov_tl(cpu_gpr[rA(ctx->opcode)], EA); \ - tcg_temp_free(EA); \ -} - #define GEN_LDX_E(name, ldop, opc2, opc3, type, type2, chk) \ static void glue(gen_, name##x)(DisasContext *ctx) \ { \ @@ -3502,21 +3287,6 @@ static void glue(gen_, name##x)(DisasContext *ctx) \ #define GEN_LDX_HVRM(name, ldop, opc2, opc3, type) \ GEN_LDX_E(name, ldop, opc2, opc3, type, PPC_NONE, CHK_HVRM) -#define GEN_LDS(name, ldop, op, type) \ -GEN_LD(name, ldop, op | 0x20, type); \ -GEN_LDU(name, ldop, op | 0x21, type); \ -GEN_LDUX(name, ldop, 0x17, op | 0x01, type); \ -GEN_LDX(name, ldop, 0x17, op | 0x00, type) - -/* lbz lbzu lbzux lbzx */ -GEN_LDS(lbz, ld8u, 0x02, PPC_INTEGER); -/* lha lhau lhaux lhax */ -GEN_LDS(lha, ld16s, 0x0A, PPC_INTEGER); -/* lhz lhzu lhzux lhzx */ -GEN_LDS(lhz, ld16u, 0x08, PPC_INTEGER); -/* lwz lwzu lwzux lwzx */ -GEN_LDS(lwz, ld32u, 0x00, PPC_INTEGER); - #define GEN_LDEPX(name, ldop, opc2, opc3) \ static void glue(gen_, name##epx)(DisasContext *ctx) \ { \ @@ -3537,47 +3307,12 @@ GEN_LDEPX(ld, DEF_MEMOP(MO_Q), 0x1D, 0x00) #endif #if defined(TARGET_PPC64) -/* lwaux */ -GEN_LDUX(lwa, ld32s, 0x15, 0x0B, PPC_64B); -/* lwax */ -GEN_LDX(lwa, ld32s, 0x15, 0x0A, PPC_64B); -/* ldux */ -GEN_LDUX(ld, ld64_i64, 0x15, 0x01, PPC_64B); -/* ldx */ -GEN_LDX(ld, ld64_i64, 0x15, 0x00, PPC_64B); - /* CI load/store variants */ GEN_LDX_HVRM(ldcix, ld64_i64, 0x15, 0x1b, PPC_CILDST) GEN_LDX_HVRM(lwzcix, ld32u, 0x15, 0x15, PPC_CILDST) GEN_LDX_HVRM(lhzcix, ld16u, 0x15, 0x19, PPC_CILDST) GEN_LDX_HVRM(lbzcix, ld8u, 0x15, 0x1a, PPC_CILDST) -static void gen_ld(DisasContext *ctx) -{ - TCGv EA; - if (Rc(ctx->opcode)) { - if (unlikely(rA(ctx->opcode) == 0 || - rA(ctx->opcode) == rD(ctx->opcode))) { - gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL); - return; - } - } - gen_set_access_type(ctx, ACCESS_INT); - EA = tcg_temp_new(); - gen_addr_imm_index(ctx, EA, 0x03); - if (ctx->opcode & 0x02) { - /* lwa (lwau is undefined) */ - gen_qemu_ld32s(ctx, cpu_gpr[rD(ctx->opcode)], EA); - } else { - /* ld - ldu */ - gen_qemu_ld64_i64(ctx, cpu_gpr[rD(ctx->opcode)], EA); - } - if (Rc(ctx->opcode)) { - tcg_gen_mov_tl(cpu_gpr[rA(ctx->opcode)], EA); - } - tcg_temp_free(EA); -} - /* lq */ static void gen_lq(DisasContext *ctx) { @@ -3643,52 +3378,6 @@ static void gen_lq(DisasContext *ctx) #endif /*** Integer store ***/ -#define GEN_ST(name, stop, opc, type) \ -static void glue(gen_, name)(DisasContext *ctx) \ -{ \ - TCGv EA; \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - gen_addr_imm_index(ctx, EA, 0); \ - gen_qemu_##stop(ctx, cpu_gpr[rS(ctx->opcode)], EA); \ - tcg_temp_free(EA); \ -} - -#define GEN_STU(name, stop, opc, type) \ -static void glue(gen_, stop##u)(DisasContext *ctx) \ -{ \ - TCGv EA; \ - if (unlikely(rA(ctx->opcode) == 0)) { \ - gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL); \ - return; \ - } \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - if (type == PPC_64B) \ - gen_addr_imm_index(ctx, EA, 0x03); \ - else \ - gen_addr_imm_index(ctx, EA, 0); \ - gen_qemu_##stop(ctx, cpu_gpr[rS(ctx->opcode)], EA); \ - tcg_gen_mov_tl(cpu_gpr[rA(ctx->opcode)], EA); \ - tcg_temp_free(EA); \ -} - -#define GEN_STUX(name, stop, opc2, opc3, type) \ -static void glue(gen_, name##ux)(DisasContext *ctx) \ -{ \ - TCGv EA; \ - if (unlikely(rA(ctx->opcode) == 0)) { \ - gen_inval_exception(ctx, POWERPC_EXCP_INVAL_INVAL); \ - return; \ - } \ - gen_set_access_type(ctx, ACCESS_INT); \ - EA = tcg_temp_new(); \ - gen_addr_reg_index(ctx, EA); \ - gen_qemu_##stop(ctx, cpu_gpr[rS(ctx->opcode)], EA); \ - tcg_gen_mov_tl(cpu_gpr[rA(ctx->opcode)], EA); \ - tcg_temp_free(EA); \ -} - #define GEN_STX_E(name, stop, opc2, opc3, type, type2, chk) \ static void glue(gen_, name##x)(DisasContext *ctx) \ { \ @@ -3706,19 +3395,6 @@ static void glue(gen_, name##x)(DisasContext *ctx) \ #define GEN_STX_HVRM(name, stop, opc2, opc3, type) \ GEN_STX_E(name, stop, opc2, opc3, type, PPC_NONE, CHK_HVRM) -#define GEN_STS(name, stop, op, type) \ -GEN_ST(name, stop, op | 0x20, type); \ -GEN_STU(name, stop, op | 0x21, type); \ -GEN_STUX(name, stop, 0x17, op | 0x01, type); \ -GEN_STX(name, stop, 0x17, op | 0x00, type) - -/* stb stbu stbux stbx */ -GEN_STS(stb, st8, 0x06, PPC_INTEGER); -/* sth sthu sthux sthx */ -GEN_STS(sth, st16, 0x0C, PPC_INTEGER); -/* stw stwu stwux stwx */ -GEN_STS(stw, st32, 0x04, PPC_INTEGER); - #define GEN_STEPX(name, stop, opc2, opc3) \ static void glue(gen_, name##epx)(DisasContext *ctx) \ { \ @@ -3740,8 +3416,6 @@ GEN_STEPX(std, DEF_MEMOP(MO_Q), 0x1d, 0x04) #endif #if defined(TARGET_PPC64) -GEN_STUX(std, st64_i64, 0x15, 0x05, PPC_64B); -GEN_STX(std, st64_i64, 0x15, 0x04, PPC_64B); GEN_STX_HVRM(stdcix, st64_i64, 0x15, 0x1f, PPC_CILDST) GEN_STX_HVRM(stwcix, st32, 0x15, 0x1c, PPC_CILDST) GEN_STX_HVRM(sthcix, st16, 0x15, 0x1d, PPC_CILDST) @@ -4646,8 +4320,7 @@ static void gen_lookup_and_goto_ptr(DisasContext *ctx) if (sse & GDBSTUB_SINGLE_STEP) { gen_debug_exception(ctx); } else if (sse & (CPU_SINGLE_STEP | CPU_BRANCH_STEP)) { - uint32_t excp = gen_prep_dbgex(ctx); - gen_exception(ctx, excp); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(gen_prep_dbgex(ctx))); } else { tcg_gen_exit_tb(NULL, 0); } @@ -7750,11 +7423,65 @@ static inline void set_avr64(int regno, TCGv_i64 src, bool high) tcg_gen_st_i64(src, cpu_env, avr64_offset(regno, high)); } +/* + * Helpers for decodetree used by !function for decoding arguments. + */ +static int times_4(DisasContext *ctx, int x) +{ + return x * 4; +} + +/* + * Helpers for trans_* functions to check for specific insns flags. + * Use token pasting to ensure that we use the proper flag with the + * proper variable. + */ +#define REQUIRE_INSNS_FLAGS(CTX, NAME) \ + do { \ + if (((CTX)->insns_flags & PPC_##NAME) == 0) { \ + return false; \ + } \ + } while (0) + +#define REQUIRE_INSNS_FLAGS2(CTX, NAME) \ + do { \ + if (((CTX)->insns_flags2 & PPC2_##NAME) == 0) { \ + return false; \ + } \ + } while (0) + +/* Then special-case the check for 64-bit so that we elide code for ppc32. */ +#if TARGET_LONG_BITS == 32 +# define REQUIRE_64BIT(CTX) return false +#else +# define REQUIRE_64BIT(CTX) REQUIRE_INSNS_FLAGS(CTX, 64B) +#endif + +/* + * Helpers for implementing sets of trans_* functions. + * Defer the implementation of NAME to FUNC, with optional extra arguments. + */ +#define TRANS(NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ + { return FUNC(ctx, a, __VA_ARGS__); } + +#define TRANS64(NAME, FUNC, ...) \ + static bool trans_##NAME(DisasContext *ctx, arg_##NAME *a) \ + { REQUIRE_64BIT(ctx); return FUNC(ctx, a, __VA_ARGS__); } + +/* TODO: More TRANS* helpers for extra insn_flags checks. */ + + +#include "decode-insn32.c.inc" +#include "decode-insn64.c.inc" +#include "translate/fixedpoint-impl.c.inc" + #include "translate/fp-impl.c.inc" #include "translate/vmx-impl.c.inc" #include "translate/vsx-impl.c.inc" +#include "translate/vector-impl.c.inc" #include "translate/dfp-impl.c.inc" @@ -7863,21 +7590,14 @@ GEN_HANDLER_E(brw, 0x1F, 0x1B, 0x04, 0x0000F801, PPC_NONE, PPC2_ISA310), GEN_HANDLER_E(brh, 0x1F, 0x1B, 0x06, 0x0000F801, PPC_NONE, PPC2_ISA310), #endif GEN_HANDLER(invalid, 0x00, 0x00, 0x00, 0xFFFFFFFF, PPC_NONE), -GEN_HANDLER(cmp, 0x1F, 0x00, 0x00, 0x00400000, PPC_INTEGER), -GEN_HANDLER(cmpi, 0x0B, 0xFF, 0xFF, 0x00400000, PPC_INTEGER), -GEN_HANDLER(cmpl, 0x1F, 0x00, 0x01, 0x00400001, PPC_INTEGER), -GEN_HANDLER(cmpli, 0x0A, 0xFF, 0xFF, 0x00400000, PPC_INTEGER), #if defined(TARGET_PPC64) GEN_HANDLER_E(cmpeqb, 0x1F, 0x00, 0x07, 0x00600000, PPC_NONE, PPC2_ISA300), #endif GEN_HANDLER_E(cmpb, 0x1F, 0x1C, 0x0F, 0x00000001, PPC_NONE, PPC2_ISA205), GEN_HANDLER_E(cmprb, 0x1F, 0x00, 0x06, 0x00400001, PPC_NONE, PPC2_ISA300), GEN_HANDLER(isel, 0x1F, 0x0F, 0xFF, 0x00000001, PPC_ISEL), -GEN_HANDLER(addi, 0x0E, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), GEN_HANDLER(addic, 0x0C, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), GEN_HANDLER2(addic_, "addic.", 0x0D, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), -GEN_HANDLER(addis, 0x0F, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), -GEN_HANDLER_E(addpcis, 0x13, 0x2, 0xFF, 0x00000000, PPC_NONE, PPC2_ISA300), GEN_HANDLER(mulhw, 0x1F, 0x0B, 0x02, 0x00000400, PPC_INTEGER), GEN_HANDLER(mulhwu, 0x1F, 0x0B, 0x00, 0x00000400, PPC_INTEGER), GEN_HANDLER(mullw, 0x1F, 0x0B, 0x07, 0x00000000, PPC_INTEGER), @@ -7932,7 +7652,6 @@ GEN_HANDLER2_E(extswsli1, "extswsli", 0x1F, 0x1B, 0x1B, 0x00000000, PPC_NONE, PPC2_ISA300), #endif #if defined(TARGET_PPC64) -GEN_HANDLER(ld, 0x3A, 0xFF, 0xFF, 0x00000000, PPC_64B), GEN_HANDLER(lq, 0x38, 0xFF, 0xFF, 0x00000000, PPC_64BX), GEN_HANDLER(std, 0x3E, 0xFF, 0xFF, 0x00000000, PPC_64B), #endif @@ -8298,34 +8017,11 @@ GEN_PPC64_R2(rldcr, 0x1E, 0x09), GEN_PPC64_R4(rldimi, 0x1E, 0x06), #endif -#undef GEN_LD -#undef GEN_LDU -#undef GEN_LDUX #undef GEN_LDX_E -#undef GEN_LDS -#define GEN_LD(name, ldop, opc, type) \ -GEN_HANDLER(name, opc, 0xFF, 0xFF, 0x00000000, type), -#define GEN_LDU(name, ldop, opc, type) \ -GEN_HANDLER(name##u, opc, 0xFF, 0xFF, 0x00000000, type), -#define GEN_LDUX(name, ldop, opc2, opc3, type) \ -GEN_HANDLER(name##ux, 0x1F, opc2, opc3, 0x00000001, type), #define GEN_LDX_E(name, ldop, opc2, opc3, type, type2, chk) \ GEN_HANDLER_E(name##x, 0x1F, opc2, opc3, 0x00000001, type, type2), -#define GEN_LDS(name, ldop, op, type) \ -GEN_LD(name, ldop, op | 0x20, type) \ -GEN_LDU(name, ldop, op | 0x21, type) \ -GEN_LDUX(name, ldop, 0x17, op | 0x01, type) \ -GEN_LDX(name, ldop, 0x17, op | 0x00, type) - -GEN_LDS(lbz, ld8u, 0x02, PPC_INTEGER) -GEN_LDS(lha, ld16s, 0x0A, PPC_INTEGER) -GEN_LDS(lhz, ld16u, 0x08, PPC_INTEGER) -GEN_LDS(lwz, ld32u, 0x00, PPC_INTEGER) + #if defined(TARGET_PPC64) -GEN_LDUX(lwa, ld32s, 0x15, 0x0B, PPC_64B) -GEN_LDX(lwa, ld32s, 0x15, 0x0A, PPC_64B) -GEN_LDUX(ld, ld64_i64, 0x15, 0x01, PPC_64B) -GEN_LDX(ld, ld64_i64, 0x15, 0x00, PPC_64B) GEN_LDX_E(ldbr, ld64ur_i64, 0x14, 0x10, PPC_NONE, PPC2_DBRX, CHK_NONE) /* HV/P7 and later only */ @@ -8350,31 +8046,11 @@ GEN_LDEPX(lw, DEF_MEMOP(MO_UL), 0x1F, 0x00) GEN_LDEPX(ld, DEF_MEMOP(MO_Q), 0x1D, 0x00) #endif -#undef GEN_ST -#undef GEN_STU -#undef GEN_STUX #undef GEN_STX_E -#undef GEN_STS -#define GEN_ST(name, stop, opc, type) \ -GEN_HANDLER(name, opc, 0xFF, 0xFF, 0x00000000, type), -#define GEN_STU(name, stop, opc, type) \ -GEN_HANDLER(stop##u, opc, 0xFF, 0xFF, 0x00000000, type), -#define GEN_STUX(name, stop, opc2, opc3, type) \ -GEN_HANDLER(name##ux, 0x1F, opc2, opc3, 0x00000001, type), #define GEN_STX_E(name, stop, opc2, opc3, type, type2, chk) \ GEN_HANDLER_E(name##x, 0x1F, opc2, opc3, 0x00000000, type, type2), -#define GEN_STS(name, stop, op, type) \ -GEN_ST(name, stop, op | 0x20, type) \ -GEN_STU(name, stop, op | 0x21, type) \ -GEN_STUX(name, stop, 0x17, op | 0x01, type) \ -GEN_STX(name, stop, 0x17, op | 0x00, type) - -GEN_STS(stb, st8, 0x06, PPC_INTEGER) -GEN_STS(sth, st16, 0x0C, PPC_INTEGER) -GEN_STS(stw, st32, 0x04, PPC_INTEGER) + #if defined(TARGET_PPC64) -GEN_STUX(std, st64_i64, 0x15, 0x05, PPC_64B) -GEN_STX(std, st64_i64, 0x15, 0x04, PPC_64B) GEN_STX_E(stdbr, st64r_i64, 0x14, 0x14, PPC_NONE, PPC2_DBRX, CHK_NONE) GEN_STX_HVRM(stdcix, st64_i64, 0x15, 0x1f, PPC_CILDST) GEN_STX_HVRM(stwcix, st32, 0x15, 0x1c, PPC_CILDST) @@ -8546,10 +8222,6 @@ static int register_direct_insn(opc_handler_t **ppc_opcodes, if (insert_in_table(ppc_opcodes, idx, handler) < 0) { printf("*** ERROR: opcode %02x already assigned in main " "opcode table\n", idx); -#if defined(DO_PPC_STATISTICS) || defined(PPC_DUMP_CPU) - printf(" Registered handler '%s' - new handler '%s'\n", - ppc_opcodes[idx]->oname, handler->oname); -#endif return -1; } @@ -8570,10 +8242,6 @@ static int register_ind_in_table(opc_handler_t **table, if (!is_indirect_opcode(table[idx1])) { printf("*** ERROR: idx %02x already assigned to a direct " "opcode\n", idx1); -#if defined(DO_PPC_STATISTICS) || defined(PPC_DUMP_CPU) - printf(" Registered handler '%s' - new handler '%s'\n", - ind_table(table[idx1])[idx2]->oname, handler->oname); -#endif return -1; } } @@ -8581,10 +8249,6 @@ static int register_ind_in_table(opc_handler_t **table, insert_in_table(ind_table(table[idx1]), idx2, handler) < 0) { printf("*** ERROR: opcode %02x already assigned in " "opcode table %02x\n", idx2, idx1); -#if defined(DO_PPC_STATISTICS) || defined(PPC_DUMP_CPU) - printf(" Registered handler '%s' - new handler '%s'\n", - ind_table(table[idx1])[idx2]->oname, handler->oname); -#endif return -1; } @@ -8766,96 +8430,6 @@ void destroy_ppc_opcodes(PowerPCCPU *cpu) } } -#if defined(PPC_DUMP_CPU) -static void dump_ppc_insns(CPUPPCState *env) -{ - opc_handler_t **table, *handler; - const char *p, *q; - uint8_t opc1, opc2, opc3, opc4; - - printf("Instructions set:\n"); - /* opc1 is 6 bits long */ - for (opc1 = 0x00; opc1 < PPC_CPU_OPCODES_LEN; opc1++) { - table = env->opcodes; - handler = table[opc1]; - if (is_indirect_opcode(handler)) { - /* opc2 is 5 bits long */ - for (opc2 = 0; opc2 < PPC_CPU_INDIRECT_OPCODES_LEN; opc2++) { - table = env->opcodes; - handler = env->opcodes[opc1]; - table = ind_table(handler); - handler = table[opc2]; - if (is_indirect_opcode(handler)) { - table = ind_table(handler); - /* opc3 is 5 bits long */ - for (opc3 = 0; opc3 < PPC_CPU_INDIRECT_OPCODES_LEN; - opc3++) { - handler = table[opc3]; - if (is_indirect_opcode(handler)) { - table = ind_table(handler); - /* opc4 is 5 bits long */ - for (opc4 = 0; opc4 < PPC_CPU_INDIRECT_OPCODES_LEN; - opc4++) { - handler = table[opc4]; - if (handler->handler != &gen_invalid) { - printf("INSN: %02x %02x %02x %02x -- " - "(%02d %04d %02d) : %s\n", - opc1, opc2, opc3, opc4, - opc1, (opc3 << 5) | opc2, opc4, - handler->oname); - } - } - } else { - if (handler->handler != &gen_invalid) { - /* Special hack to properly dump SPE insns */ - p = strchr(handler->oname, '_'); - if (p == NULL) { - printf("INSN: %02x %02x %02x (%02d %04d) : " - "%s\n", - opc1, opc2, opc3, opc1, - (opc3 << 5) | opc2, - handler->oname); - } else { - q = "speundef"; - if ((p - handler->oname) != strlen(q) - || (memcmp(handler->oname, q, strlen(q)) - != 0)) { - /* First instruction */ - printf("INSN: %02x %02x %02x" - "(%02d %04d) : %.*s\n", - opc1, opc2 << 1, opc3, opc1, - (opc3 << 6) | (opc2 << 1), - (int)(p - handler->oname), - handler->oname); - } - if (strcmp(p + 1, q) != 0) { - /* Second instruction */ - printf("INSN: %02x %02x %02x " - "(%02d %04d) : %s\n", opc1, - (opc2 << 1) | 1, opc3, opc1, - (opc3 << 6) | (opc2 << 1) | 1, - p + 1); - } - } - } - } - } - } else { - if (handler->handler != &gen_invalid) { - printf("INSN: %02x %02x -- (%02d %04d) : %s\n", - opc1, opc2, opc1, opc2, handler->oname); - } - } - } - } else { - if (handler->handler != &gen_invalid) { - printf("INSN: %02x -- -- (%02d ----) : %s\n", - opc1, opc1, handler->oname); - } - } - } -} -#endif int ppc_fixup_cpu(PowerPCCPU *cpu) { CPUPPCState *env = &cpu->env; @@ -8881,57 +8455,6 @@ int ppc_fixup_cpu(PowerPCCPU *cpu) return 0; } - -void ppc_cpu_dump_statistics(CPUState *cs, int flags) -{ -#if defined(DO_PPC_STATISTICS) - PowerPCCPU *cpu = POWERPC_CPU(cs); - opc_handler_t **t1, **t2, **t3, *handler; - int op1, op2, op3; - - t1 = cpu->env.opcodes; - for (op1 = 0; op1 < 64; op1++) { - handler = t1[op1]; - if (is_indirect_opcode(handler)) { - t2 = ind_table(handler); - for (op2 = 0; op2 < 32; op2++) { - handler = t2[op2]; - if (is_indirect_opcode(handler)) { - t3 = ind_table(handler); - for (op3 = 0; op3 < 32; op3++) { - handler = t3[op3]; - if (handler->count == 0) { - continue; - } - qemu_printf("%02x %02x %02x (%02x %04d) %16s: " - "%016" PRIx64 " %" PRId64 "\n", - op1, op2, op3, op1, (op3 << 5) | op2, - handler->oname, - handler->count, handler->count); - } - } else { - if (handler->count == 0) { - continue; - } - qemu_printf("%02x %02x (%02x %04d) %16s: " - "%016" PRIx64 " %" PRId64 "\n", - op1, op2, op1, op2, handler->oname, - handler->count, handler->count); - } - } - } else { - if (handler->count == 0) { - continue; - } - qemu_printf("%02x (%02x ) %16s: %016" PRIx64 - " %" PRId64 "\n", - op1, op1, handler->oname, - handler->count, handler->count); - } - } -#endif -} - static bool decode_legacy(PowerPCCPU *cpu, DisasContext *ctx, uint32_t insn) { opc_handler_t **table, *handler; @@ -9034,9 +8557,6 @@ static void ppc_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) if (ctx->singlestep_enabled & (CPU_SINGLE_STEP | GDBSTUB_SINGLE_STEP)) { ctx->base.max_insns = 1; - } else { - int bound = -(ctx->base.pc_first | TARGET_PAGE_MASK) / 4; - ctx->base.max_insns = MIN(ctx->base.max_insns, bound); } } @@ -9066,11 +8586,18 @@ static bool ppc_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cs, return true; } +static bool is_prefix_insn(DisasContext *ctx, uint32_t insn) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + return opc1(insn) == 1; +} + static void ppc_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) { DisasContext *ctx = container_of(dcbase, DisasContext, base); PowerPCCPU *cpu = POWERPC_CPU(cs); CPUPPCState *env = cs->env_ptr; + target_ulong pc; uint32_t insn; bool ok; @@ -9078,18 +8605,34 @@ static void ppc_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) LOG_DISAS("nip=" TARGET_FMT_lx " super=%d ir=%d\n", ctx->base.pc_next, ctx->mem_idx, (int)msr_ir); - ctx->cia = ctx->base.pc_next; - insn = translator_ldl_swap(env, ctx->base.pc_next, need_byteswap(ctx)); - ctx->base.pc_next += 4; + ctx->cia = pc = ctx->base.pc_next; + insn = translator_ldl_swap(env, pc, need_byteswap(ctx)); + ctx->base.pc_next = pc += 4; - ok = decode_legacy(cpu, ctx, insn); + if (!is_prefix_insn(ctx, insn)) { + ok = (decode_insn32(ctx, insn) || + decode_legacy(cpu, ctx, insn)); + } else if ((pc & 63) == 0) { + /* + * Power v3.1, section 1.9 Exceptions: + * attempt to execute a prefixed instruction that crosses a + * 64-byte address boundary (system alignment error). + */ + gen_exception_err(ctx, POWERPC_EXCP_ALIGN, POWERPC_EXCP_ALIGN_INSN); + ok = true; + } else { + uint32_t insn2 = translator_ldl_swap(env, pc, need_byteswap(ctx)); + ctx->base.pc_next = pc += 4; + ok = decode_insn64(ctx, deposit64(insn2, 32, 32, insn)); + } if (!ok) { gen_invalid(ctx); } -#if defined(DO_PPC_STATISTICS) - handler->count++; -#endif + /* End the TB when crossing a page boundary. */ + if (ctx->base.is_jmp == DISAS_NEXT && !(pc & ~TARGET_PAGE_MASK)) { + ctx->base.is_jmp = DISAS_TOO_MANY; + } translator_loop_temp_check(&ctx->base); } @@ -9128,7 +8671,7 @@ static void ppc_tr_tb_stop(DisasContextBase *dcbase, CPUState *cs) } /* else CPU_SINGLE_STEP... */ if (nip <= 0x100 || nip > 0xf00) { - gen_exception(ctx, gen_prep_dbgex(ctx)); + gen_helper_raise_exception(cpu_env, tcg_constant_i32(gen_prep_dbgex(ctx))); return; } } diff --git a/target/ppc/translate/fixedpoint-impl.c.inc b/target/ppc/translate/fixedpoint-impl.c.inc new file mode 100644 index 0000000000..8864ac4516 --- /dev/null +++ b/target/ppc/translate/fixedpoint-impl.c.inc @@ -0,0 +1,279 @@ +/* + * Power ISA decode for Fixed-Point Facility instructions + * + * Copyright (c) 2021 Instituto de Pesquisas Eldorado (eldorado.org.br) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +/* + * Incorporate CIA into the constant when R=1. + * Validate that when R=1, RA=0. + */ +static bool resolve_PLS_D(DisasContext *ctx, arg_D *d, arg_PLS_D *a) +{ + d->rt = a->rt; + d->ra = a->ra; + d->si = a->si; + if (a->r) { + if (unlikely(a->ra != 0)) { + gen_invalid(ctx); + return false; + } + d->si += ctx->cia; + } + return true; +} + +/* + * Fixed-Point Load/Store Instructions + */ + +static bool do_ldst(DisasContext *ctx, int rt, int ra, TCGv displ, bool update, + bool store, MemOp mop) +{ + TCGv ea; + + if (update && (ra == 0 || (!store && ra == rt))) { + gen_invalid(ctx); + return true; + } + gen_set_access_type(ctx, ACCESS_INT); + + ea = tcg_temp_new(); + if (ra) { + tcg_gen_add_tl(ea, cpu_gpr[ra], displ); + } else { + tcg_gen_mov_tl(ea, displ); + } + if (NARROW_MODE(ctx)) { + tcg_gen_ext32u_tl(ea, ea); + } + mop ^= ctx->default_tcg_memop_mask; + if (store) { + tcg_gen_qemu_st_tl(cpu_gpr[rt], ea, ctx->mem_idx, mop); + } else { + tcg_gen_qemu_ld_tl(cpu_gpr[rt], ea, ctx->mem_idx, mop); + } + if (update) { + tcg_gen_mov_tl(cpu_gpr[ra], ea); + } + tcg_temp_free(ea); + + return true; +} + +static bool do_ldst_D(DisasContext *ctx, arg_D *a, bool update, bool store, + MemOp mop) +{ + return do_ldst(ctx, a->rt, a->ra, tcg_constant_tl(a->si), update, store, mop); +} + +static bool do_ldst_PLS_D(DisasContext *ctx, arg_PLS_D *a, bool update, + bool store, MemOp mop) +{ + arg_D d; + if (!resolve_PLS_D(ctx, &d, a)) { + return true; + } + return do_ldst_D(ctx, &d, update, store, mop); +} + +static bool do_ldst_X(DisasContext *ctx, arg_X *a, bool update, + bool store, MemOp mop) +{ + return do_ldst(ctx, a->rt, a->ra, cpu_gpr[a->rb], update, store, mop); +} + +/* Load Byte and Zero */ +TRANS(LBZ, do_ldst_D, false, false, MO_UB) +TRANS(LBZX, do_ldst_X, false, false, MO_UB) +TRANS(LBZU, do_ldst_D, true, false, MO_UB) +TRANS(LBZUX, do_ldst_X, true, false, MO_UB) +TRANS(PLBZ, do_ldst_PLS_D, false, false, MO_UB) + +/* Load Halfword and Zero */ +TRANS(LHZ, do_ldst_D, false, false, MO_UW) +TRANS(LHZX, do_ldst_X, false, false, MO_UW) +TRANS(LHZU, do_ldst_D, true, false, MO_UW) +TRANS(LHZUX, do_ldst_X, true, false, MO_UW) +TRANS(PLHZ, do_ldst_PLS_D, false, false, MO_UW) + +/* Load Halfword Algebraic */ +TRANS(LHA, do_ldst_D, false, false, MO_SW) +TRANS(LHAX, do_ldst_X, false, false, MO_SW) +TRANS(LHAU, do_ldst_D, true, false, MO_SW) +TRANS(LHAXU, do_ldst_X, true, false, MO_SW) +TRANS(PLHA, do_ldst_PLS_D, false, false, MO_SW) + +/* Load Word and Zero */ +TRANS(LWZ, do_ldst_D, false, false, MO_UL) +TRANS(LWZX, do_ldst_X, false, false, MO_UL) +TRANS(LWZU, do_ldst_D, true, false, MO_UL) +TRANS(LWZUX, do_ldst_X, true, false, MO_UL) +TRANS(PLWZ, do_ldst_PLS_D, false, false, MO_UL) + +/* Load Word Algebraic */ +TRANS64(LWA, do_ldst_D, false, false, MO_SL) +TRANS64(LWAX, do_ldst_X, false, false, MO_SL) +TRANS64(LWAUX, do_ldst_X, true, false, MO_SL) +TRANS64(PLWA, do_ldst_PLS_D, false, false, MO_SL) + +/* Load Doubleword */ +TRANS64(LD, do_ldst_D, false, false, MO_Q) +TRANS64(LDX, do_ldst_X, false, false, MO_Q) +TRANS64(LDU, do_ldst_D, true, false, MO_Q) +TRANS64(LDUX, do_ldst_X, true, false, MO_Q) +TRANS64(PLD, do_ldst_PLS_D, false, false, MO_Q) + +/* Store Byte */ +TRANS(STB, do_ldst_D, false, true, MO_UB) +TRANS(STBX, do_ldst_X, false, true, MO_UB) +TRANS(STBU, do_ldst_D, true, true, MO_UB) +TRANS(STBUX, do_ldst_X, true, true, MO_UB) +TRANS(PSTB, do_ldst_PLS_D, false, true, MO_UB) + +/* Store Halfword */ +TRANS(STH, do_ldst_D, false, true, MO_UW) +TRANS(STHX, do_ldst_X, false, true, MO_UW) +TRANS(STHU, do_ldst_D, true, true, MO_UW) +TRANS(STHUX, do_ldst_X, true, true, MO_UW) +TRANS(PSTH, do_ldst_PLS_D, false, true, MO_UW) + +/* Store Word */ +TRANS(STW, do_ldst_D, false, true, MO_UL) +TRANS(STWX, do_ldst_X, false, true, MO_UL) +TRANS(STWU, do_ldst_D, true, true, MO_UL) +TRANS(STWUX, do_ldst_X, true, true, MO_UL) +TRANS(PSTW, do_ldst_PLS_D, false, true, MO_UL) + +/* Store Doubleword */ +TRANS64(STD, do_ldst_D, false, true, MO_Q) +TRANS64(STDX, do_ldst_X, false, true, MO_Q) +TRANS64(STDU, do_ldst_D, true, true, MO_Q) +TRANS64(STDUX, do_ldst_X, true, true, MO_Q) +TRANS64(PSTD, do_ldst_PLS_D, false, true, MO_Q) + +/* + * Fixed-Point Compare Instructions + */ + +static bool do_cmp_X(DisasContext *ctx, arg_X_bfl *a, bool s) +{ + if (a->l) { + REQUIRE_64BIT(ctx); + gen_op_cmp(cpu_gpr[a->ra], cpu_gpr[a->rb], s, a->bf); + } else { + gen_op_cmp32(cpu_gpr[a->ra], cpu_gpr[a->rb], s, a->bf); + } + return true; +} + +static bool do_cmp_D(DisasContext *ctx, arg_D_bf *a, bool s) +{ + if (a->l) { + REQUIRE_64BIT(ctx); + gen_op_cmp(cpu_gpr[a->ra], tcg_constant_tl(a->imm), s, a->bf); + } else { + gen_op_cmp32(cpu_gpr[a->ra], tcg_constant_tl(a->imm), s, a->bf); + } + return true; +} + +TRANS(CMP, do_cmp_X, true); +TRANS(CMPL, do_cmp_X, false); +TRANS(CMPI, do_cmp_D, true); +TRANS(CMPLI, do_cmp_D, false); + +/* + * Fixed-Point Arithmetic Instructions + */ + +static bool trans_ADDI(DisasContext *ctx, arg_D *a) +{ + if (a->ra) { + tcg_gen_addi_tl(cpu_gpr[a->rt], cpu_gpr[a->ra], a->si); + } else { + tcg_gen_movi_tl(cpu_gpr[a->rt], a->si); + } + return true; +} + +static bool trans_PADDI(DisasContext *ctx, arg_PLS_D *a) +{ + arg_D d; + if (!resolve_PLS_D(ctx, &d, a)) { + return true; + } + return trans_ADDI(ctx, &d); +} + +static bool trans_ADDIS(DisasContext *ctx, arg_D *a) +{ + a->si <<= 16; + return trans_ADDI(ctx, a); +} + +static bool trans_ADDPCIS(DisasContext *ctx, arg_DX *a) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA300); + tcg_gen_movi_tl(cpu_gpr[a->rt], ctx->base.pc_next + (a->d << 16)); + return true; +} + +static bool trans_INVALID(DisasContext *ctx, arg_INVALID *a) +{ + gen_invalid(ctx); + return true; +} + +static bool trans_PNOP(DisasContext *ctx, arg_PNOP *a) +{ + return true; +} + +static bool do_set_bool_cond(DisasContext *ctx, arg_X_bi *a, bool neg, bool rev) +{ + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + uint32_t mask = 0x08 >> (a->bi & 0x03); + TCGCond cond = rev ? TCG_COND_EQ : TCG_COND_NE; + TCGv temp = tcg_temp_new(); + + tcg_gen_extu_i32_tl(temp, cpu_crf[a->bi >> 2]); + tcg_gen_andi_tl(temp, temp, mask); + tcg_gen_setcondi_tl(cond, cpu_gpr[a->rt], temp, 0); + if (neg) { + tcg_gen_neg_tl(cpu_gpr[a->rt], cpu_gpr[a->rt]); + } + tcg_temp_free(temp); + + return true; +} + +TRANS(SETBC, do_set_bool_cond, false, false) +TRANS(SETBCR, do_set_bool_cond, false, true) +TRANS(SETNBC, do_set_bool_cond, true, false) +TRANS(SETNBCR, do_set_bool_cond, true, true) + +static bool trans_CFUGED(DisasContext *ctx, arg_X *a) +{ + REQUIRE_64BIT(ctx); + REQUIRE_INSNS_FLAGS2(ctx, ISA310); +#if defined(TARGET_PPC64) + gen_helper_cfuged(cpu_gpr[a->ra], cpu_gpr[a->rt], cpu_gpr[a->rb]); +#else + qemu_build_not_reached(); +#endif + return true; +} diff --git a/target/ppc/translate/vector-impl.c.inc b/target/ppc/translate/vector-impl.c.inc new file mode 100644 index 0000000000..117ce9b137 --- /dev/null +++ b/target/ppc/translate/vector-impl.c.inc @@ -0,0 +1,56 @@ +/* + * Power ISA decode for Vector Facility instructions + * + * Copyright (c) 2021 Instituto de Pesquisas Eldorado (eldorado.org.br) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#define REQUIRE_ALTIVEC(CTX) \ + do { \ + if (unlikely(!(CTX)->altivec_enabled)) { \ + gen_exception((CTX), POWERPC_EXCP_VPU); \ + return true; \ + } \ + } while (0) + +static bool trans_VCFUGED(DisasContext *ctx, arg_VX *a) +{ + TCGv_i64 tgt, src, mask; + + REQUIRE_INSNS_FLAGS2(ctx, ISA310); + REQUIRE_ALTIVEC(ctx); + + tgt = tcg_temp_new_i64(); + src = tcg_temp_new_i64(); + mask = tcg_temp_new_i64(); + + /* centrifuge lower double word */ + get_cpu_vsrl(src, a->vra + 32); + get_cpu_vsrl(mask, a->vrb + 32); + gen_helper_cfuged(tgt, src, mask); + set_cpu_vsrl(a->vrt + 32, tgt); + + /* centrifuge higher double word */ + get_cpu_vsrh(src, a->vra + 32); + get_cpu_vsrh(mask, a->vrb + 32); + gen_helper_cfuged(tgt, src, mask); + set_cpu_vsrh(a->vrt + 32, tgt); + + tcg_temp_free_i64(tgt); + tcg_temp_free_i64(src); + tcg_temp_free_i64(mask); + + return true; +} diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 3191fd0082..1f1cef1d6a 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -596,9 +596,20 @@ static const char *riscv_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname) return NULL; } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps riscv_sysemu_ops = { + .get_phys_page_debug = riscv_cpu_get_phys_page_debug, + .write_elf64_note = riscv_cpu_write_elf64_note, + .write_elf32_note = riscv_cpu_write_elf32_note, + .legacy_vmsd = &vmstate_riscv_cpu, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps riscv_tcg_ops = { +static const struct TCGCPUOps riscv_tcg_ops = { .initialize = riscv_translate_init, .synchronize_from_tb = riscv_cpu_synchronize_from_tb, .cpu_exec_interrupt = riscv_cpu_exec_interrupt, @@ -637,11 +648,7 @@ static void riscv_cpu_class_init(ObjectClass *c, void *data) cc->gdb_stop_before_watchpoint = true; cc->disas_set_info = riscv_cpu_disas_set_info; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = riscv_cpu_get_phys_page_debug; - /* For now, mark unmigratable: */ - cc->vmsd = &vmstate_riscv_cpu; - cc->write_elf64_note = riscv_cpu_write_elf64_note; - cc->write_elf32_note = riscv_cpu_write_elf32_note; + cc->sysemu_ops = &riscv_sysemu_ops; #endif cc->gdb_arch_name = riscv_gdb_arch_name; cc->gdb_get_dynamic_xml = riscv_gdb_get_dynamic_xml; diff --git a/target/rx/cpu.c b/target/rx/cpu.c index 7ac6618b26..96cc96e514 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -173,9 +173,17 @@ static void rx_cpu_init(Object *obj) qdev_init_gpio_in(DEVICE(cpu), rx_cpu_set_irq, 2); } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps rx_sysemu_ops = { + .get_phys_page_debug = rx_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps rx_tcg_ops = { +static const struct TCGCPUOps rx_tcg_ops = { .initialize = rx_translate_init, .synchronize_from_tb = rx_cpu_synchronize_from_tb, .cpu_exec_interrupt = rx_cpu_exec_interrupt, @@ -202,9 +210,11 @@ static void rx_cpu_class_init(ObjectClass *klass, void *data) cc->dump_state = rx_cpu_dump_state; cc->set_pc = rx_cpu_set_pc; +#ifndef CONFIG_USER_ONLY + cc->sysemu_ops = &rx_sysemu_ops; +#endif cc->gdb_read_register = rx_cpu_gdb_read_register; cc->gdb_write_register = rx_cpu_gdb_write_register; - cc->get_phys_page_debug = rx_cpu_get_phys_page_debug; cc->disas_set_info = rx_cpu_disas_set_info; cc->gdb_num_core_regs = 26; diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index 64455cf309..890f382a36 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -476,10 +476,21 @@ static void s390_cpu_reset_full(DeviceState *dev) return s390_cpu_reset(s, S390_CPU_RESET_CLEAR); } +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps s390_sysemu_ops = { + .get_phys_page_debug = s390_cpu_get_phys_page_debug, + .get_crash_info = s390_cpu_get_crash_info, + .write_elf64_note = s390_cpu_write_elf64_note, + .legacy_vmsd = &vmstate_s390_cpu, +}; +#endif + #ifdef CONFIG_TCG #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps s390_tcg_ops = { +static const struct TCGCPUOps s390_tcg_ops = { .initialize = s390x_translate_init, .tlb_fill = s390_cpu_tlb_fill, @@ -515,10 +526,7 @@ static void s390_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = s390_cpu_gdb_read_register; cc->gdb_write_register = s390_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = s390_cpu_get_phys_page_debug; - cc->vmsd = &vmstate_s390_cpu; - cc->get_crash_info = s390_cpu_get_crash_info; - cc->write_elf64_note = s390_cpu_write_elf64_note; + cc->sysemu_ops = &s390_sysemu_ops; #endif cc->disas_set_info = s390_cpu_disas_set_info; cc->gdb_num_core_regs = S390_NUM_CORE_REGS; diff --git a/target/s390x/trace-events b/target/s390x/trace-events index fda1ee8220..e661a81e3a 100644 --- a/target/s390x/trace-events +++ b/target/s390x/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # mmu_helper.c get_skeys_nonzero(int rc) "SKEY: Call to get_skeys unexpectedly returned %d" diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index ac65c88f1f..8326922942 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -218,14 +218,22 @@ static void superh_cpu_initfn(Object *obj) env->movcal_backup_tail = &(env->movcal_backup); } +#ifndef CONFIG_USER_ONLY static const VMStateDescription vmstate_sh_cpu = { .name = "cpu", .unmigratable = 1, }; +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps sh4_sysemu_ops = { + .get_phys_page_debug = superh_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps superh_tcg_ops = { +static const struct TCGCPUOps superh_tcg_ops = { .initialize = sh4_translate_init, .synchronize_from_tb = superh_cpu_synchronize_from_tb, .cpu_exec_interrupt = superh_cpu_exec_interrupt, @@ -256,13 +264,12 @@ static void superh_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = superh_cpu_gdb_read_register; cc->gdb_write_register = superh_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = superh_cpu_get_phys_page_debug; + cc->sysemu_ops = &sh4_sysemu_ops; + dc->vmsd = &vmstate_sh_cpu; #endif cc->disas_set_info = superh_cpu_disas_set_info; cc->gdb_num_core_regs = 59; - - dc->vmsd = &vmstate_sh_cpu; cc->tcg_ops = &superh_tcg_ops; } diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index aece2c7dc8..da6b30ec74 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -848,10 +848,19 @@ static Property sparc_cpu_properties[] = { DEFINE_PROP_END_OF_LIST() }; +#ifndef CONFIG_USER_ONLY +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps sparc_sysemu_ops = { + .get_phys_page_debug = sparc_cpu_get_phys_page_debug, + .legacy_vmsd = &vmstate_sparc_cpu, +}; +#endif + #ifdef CONFIG_TCG #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps sparc_tcg_ops = { +static const struct TCGCPUOps sparc_tcg_ops = { .initialize = sparc_tcg_init, .synchronize_from_tb = sparc_cpu_synchronize_from_tb, .cpu_exec_interrupt = sparc_cpu_exec_interrupt, @@ -888,8 +897,7 @@ static void sparc_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_read_register = sparc_cpu_gdb_read_register; cc->gdb_write_register = sparc_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = sparc_cpu_get_phys_page_debug; - cc->vmsd = &vmstate_sparc_cpu; + cc->sysemu_ops = &sparc_sysemu_ops; #endif cc->disas_set_info = cpu_sparc_disas_set_info; diff --git a/target/sparc/trace-events b/target/sparc/trace-events index 75e7093d5f..de9833283d 100644 --- a/target/sparc/trace-events +++ b/target/sparc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # mmu_helper.c mmu_helper_dfault(uint64_t address, uint64_t context, int mmu_idx, uint32_t tl) "DFAULT at 0x%"PRIx64" context 0x%"PRIx64" mmu_idx=%d tl=%d" diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c index 0b1e139bcb..b95682b7f0 100644 --- a/target/tricore/cpu.c +++ b/target/tricore/cpu.c @@ -142,9 +142,15 @@ static void tc27x_initfn(Object *obj) set_feature(&cpu->env, TRICORE_FEATURE_161); } +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps tricore_sysemu_ops = { + .get_phys_page_debug = tricore_cpu_get_phys_page_debug, +}; + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps tricore_tcg_ops = { +static const struct TCGCPUOps tricore_tcg_ops = { .initialize = tricore_tcg_init, .synchronize_from_tb = tricore_cpu_synchronize_from_tb, .tlb_fill = tricore_cpu_tlb_fill, @@ -170,7 +176,7 @@ static void tricore_cpu_class_init(ObjectClass *c, void *data) cc->dump_state = tricore_cpu_dump_state; cc->set_pc = tricore_cpu_set_pc; - cc->get_phys_page_debug = tricore_cpu_get_phys_page_debug; + cc->sysemu_ops = &tricore_sysemu_ops; cc->tcg_ops = &tricore_tcg_ops; } diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index 210ef80092..58ec3a0862 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -175,14 +175,22 @@ static void xtensa_cpu_initfn(Object *obj) #endif } +#ifndef CONFIG_USER_ONLY static const VMStateDescription vmstate_xtensa_cpu = { .name = "cpu", .unmigratable = 1, }; +#include "hw/core/sysemu-cpu-ops.h" + +static const struct SysemuCPUOps xtensa_sysemu_ops = { + .get_phys_page_debug = xtensa_cpu_get_phys_page_debug, +}; +#endif + #include "hw/core/tcg-cpu-ops.h" -static struct TCGCPUOps xtensa_tcg_ops = { +static const struct TCGCPUOps xtensa_tcg_ops = { .initialize = xtensa_translate_init, .cpu_exec_interrupt = xtensa_cpu_exec_interrupt, .tlb_fill = xtensa_cpu_tlb_fill, @@ -214,10 +222,10 @@ static void xtensa_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_write_register = xtensa_cpu_gdb_write_register; cc->gdb_stop_before_watchpoint = true; #ifndef CONFIG_USER_ONLY - cc->get_phys_page_debug = xtensa_cpu_get_phys_page_debug; + cc->sysemu_ops = &xtensa_sysemu_ops; + dc->vmsd = &vmstate_xtensa_cpu; #endif cc->disas_set_info = xtensa_cpu_disas_set_info; - dc->vmsd = &vmstate_xtensa_cpu; cc->tcg_ops = &xtensa_tcg_ops; } diff --git a/tcg/README b/tcg/README index 0cf9e2727c..8510d823e3 100644 --- a/tcg/README +++ b/tcg/README @@ -461,7 +461,7 @@ when MTTCG is enabled. The guest translators should generate this opcode for all guest instructions which have ordering side effects. -Please see docs/devel/atomics.txt for more information on memory barriers. +Please see docs/devel/atomics.rst for more information on memory barriers. ********* 64-bit guest on 32-bit host support diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc index f07ba98aa4..5bd366f2d4 100644 --- a/tcg/aarch64/tcg-target.c.inc +++ b/tcg/aarch64/tcg-target.c.inc @@ -1291,9 +1291,8 @@ static inline void tcg_out_rotr(TCGContext *s, TCGType ext, static inline void tcg_out_rotl(TCGContext *s, TCGType ext, TCGReg rd, TCGReg rn, unsigned int m) { - int bits = ext ? 64 : 32; - int max = bits - 1; - tcg_out_extr(s, ext, rd, rn, rn, bits - (m & max)); + int max = ext ? 63 : 31; + tcg_out_extr(s, ext, rd, rn, rn, -m & max); } static inline void tcg_out_dep(TCGContext *s, TCGType ext, TCGReg rd, diff --git a/tests/acceptance/avocado_qemu/__init__.py b/tests/acceptance/avocado_qemu/__init__.py index 83b1741ec8..93c4b9851f 100644 --- a/tests/acceptance/avocado_qemu/__init__.py +++ b/tests/acceptance/avocado_qemu/__init__.py @@ -20,6 +20,7 @@ import avocado from avocado.utils import cloudinit from avocado.utils import datadrainer from avocado.utils import network +from avocado.utils import ssh from avocado.utils import vmimage from avocado.utils.path import find_command @@ -40,9 +41,12 @@ else: sys.path.append(os.path.join(SOURCE_DIR, 'python')) -from qemu.accel import kvm_available -from qemu.accel import tcg_available from qemu.machine import QEMUMachine +from qemu.utils import ( + get_info_usernet_hostfwd_port, + kvm_available, + tcg_available, +) def is_readable_executable_file(path): return os.path.isfile(path) and os.access(path, os.R_OK | os.X_OK) @@ -253,7 +257,50 @@ class Test(avocado.Test): cancel_on_missing=cancel_on_missing) -class LinuxTest(Test): +class LinuxSSHMixIn: + """Contains utility methods for interacting with a guest via SSH.""" + + def ssh_connect(self, username, credential, credential_is_key=True): + self.ssh_logger = logging.getLogger('ssh') + res = self.vm.command('human-monitor-command', + command_line='info usernet') + port = get_info_usernet_hostfwd_port(res) + self.assertIsNotNone(port) + self.assertGreater(port, 0) + self.log.debug('sshd listening on port: %d', port) + if credential_is_key: + self.ssh_session = ssh.Session('127.0.0.1', port=port, + user=username, key=credential) + else: + self.ssh_session = ssh.Session('127.0.0.1', port=port, + user=username, password=credential) + for i in range(10): + try: + self.ssh_session.connect() + return + except: + time.sleep(4) + pass + self.fail('ssh connection timeout') + + def ssh_command(self, command): + self.ssh_logger.info(command) + result = self.ssh_session.cmd(command) + stdout_lines = [line.rstrip() for line + in result.stdout_text.splitlines()] + for line in stdout_lines: + self.ssh_logger.info(line) + stderr_lines = [line.rstrip() for line + in result.stderr_text.splitlines()] + for line in stderr_lines: + self.ssh_logger.warning(line) + + self.assertEqual(result.exit_status, 0, + f'Guest command failed: {command}') + return stdout_lines, stderr_lines + + +class LinuxTest(Test, LinuxSSHMixIn): """Facilitates having a cloud-image Linux based available. For tests that indend to interact with guests, this is a better choice @@ -262,11 +309,16 @@ class LinuxTest(Test): timeout = 900 chksum = None + username = 'root' + password = 'password' - def setUp(self, ssh_pubkey=None): + def setUp(self, ssh_pubkey=None, network_device_type='virtio-net'): super(LinuxTest, self).setUp() self.vm.add_args('-smp', '2') self.vm.add_args('-m', '1024') + # The following network device allows for SSH connections + self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22', + '-device', '%s,netdev=vnet' % network_device_type) self.set_up_boot() if ssh_pubkey is None: ssh_pubkey, self.ssh_key = self.set_up_existing_ssh_keys() @@ -322,8 +374,8 @@ class LinuxTest(Test): with open(ssh_pubkey) as pubkey: pubkey_content = pubkey.read() cloudinit.iso(cloudinit_iso, self.name, - username='root', - password='password', + username=self.username, + password=self.password, # QEMU's hard coded usermode router address phone_home_host='10.0.2.2', phone_home_port=self.phone_home_port, @@ -340,7 +392,7 @@ class LinuxTest(Test): cloudinit_iso = self.prepare_cloudinit(ssh_pubkey) self.vm.add_args('-drive', 'file=%s,format=raw' % cloudinit_iso) - def launch_and_wait(self): + def launch_and_wait(self, set_up_ssh_connection=True): self.vm.set_console() self.vm.launch() console_drainer = datadrainer.LineLogger(self.vm.console_socket.fileno(), @@ -348,3 +400,6 @@ class LinuxTest(Test): console_drainer.start() self.log.info('VM launched, waiting for boot confirmation from guest') cloudinit.wait_for_phone_home(('0.0.0.0', self.phone_home_port), self.name) + if set_up_ssh_connection: + self.log.info('Setting up the SSH connection') + self.ssh_connect(self.username, self.ssh_key) diff --git a/tests/acceptance/boot_linux.py b/tests/acceptance/boot_linux.py index 0d178038a0..314370fd1f 100644 --- a/tests/acceptance/boot_linux.py +++ b/tests/acceptance/boot_linux.py @@ -29,7 +29,7 @@ class BootLinuxX8664(LinuxTest): """ self.require_accelerator("tcg") self.vm.add_args("-accel", "tcg") - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) def test_pc_i440fx_kvm(self): """ @@ -38,7 +38,7 @@ class BootLinuxX8664(LinuxTest): """ self.require_accelerator("kvm") self.vm.add_args("-accel", "kvm") - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) def test_pc_q35_tcg(self): """ @@ -47,7 +47,7 @@ class BootLinuxX8664(LinuxTest): """ self.require_accelerator("tcg") self.vm.add_args("-accel", "tcg") - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) def test_pc_q35_kvm(self): """ @@ -56,7 +56,7 @@ class BootLinuxX8664(LinuxTest): """ self.require_accelerator("kvm") self.vm.add_args("-accel", "kvm") - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) class BootLinuxAarch64(LinuxTest): @@ -85,7 +85,7 @@ class BootLinuxAarch64(LinuxTest): self.vm.add_args("-cpu", "max") self.vm.add_args("-machine", "virt,gic-version=2") self.add_common_args() - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) def test_virt_kvm_gicv2(self): """ @@ -98,7 +98,7 @@ class BootLinuxAarch64(LinuxTest): self.vm.add_args("-cpu", "host") self.vm.add_args("-machine", "virt,gic-version=2") self.add_common_args() - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) def test_virt_kvm_gicv3(self): """ @@ -111,7 +111,7 @@ class BootLinuxAarch64(LinuxTest): self.vm.add_args("-cpu", "host") self.vm.add_args("-machine", "virt,gic-version=3") self.add_common_args() - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) class BootLinuxPPC64(LinuxTest): @@ -128,7 +128,7 @@ class BootLinuxPPC64(LinuxTest): """ self.require_accelerator("tcg") self.vm.add_args("-accel", "tcg") - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) class BootLinuxS390X(LinuxTest): @@ -146,4 +146,4 @@ class BootLinuxS390X(LinuxTest): """ self.require_accelerator("tcg") self.vm.add_args("-accel", "tcg") - self.launch_and_wait() + self.launch_and_wait(set_up_ssh_connection=False) diff --git a/tests/acceptance/hotplug_cpu.py b/tests/acceptance/hotplug_cpu.py new file mode 100644 index 0000000000..6374bf1b54 --- /dev/null +++ b/tests/acceptance/hotplug_cpu.py @@ -0,0 +1,37 @@ +# Functional test that hotplugs a CPU and checks it on a Linux guest +# +# Copyright (c) 2021 Red Hat, Inc. +# +# Author: +# Cleber Rosa <crosa@redhat.com> +# +# This work is licensed under the terms of the GNU GPL, version 2 or +# later. See the COPYING file in the top-level directory. + +from avocado_qemu import LinuxTest + + +class HotPlugCPU(LinuxTest): + + def test(self): + """ + :avocado: tags=arch:x86_64 + :avocado: tags=machine:q35 + :avocado: tags=accel:kvm + """ + self.require_accelerator('kvm') + self.vm.add_args('-accel', 'kvm') + self.vm.add_args('-cpu', 'Haswell') + self.vm.add_args('-smp', '1,sockets=1,cores=2,threads=1,maxcpus=2') + self.launch_and_wait() + + self.ssh_command('test -e /sys/devices/system/cpu/cpu0') + with self.assertRaises(AssertionError): + self.ssh_command('test -e /sys/devices/system/cpu/cpu1') + + self.vm.command('device_add', + driver='Haswell-x86_64-cpu', + socket_id=0, + core_id=1, + thread_id=0) + self.ssh_command('test -e /sys/devices/system/cpu/cpu1') diff --git a/tests/acceptance/info_usernet.py b/tests/acceptance/info_usernet.py new file mode 100644 index 0000000000..9c1fd903a0 --- /dev/null +++ b/tests/acceptance/info_usernet.py @@ -0,0 +1,29 @@ +# Test for the hmp command "info usernet" +# +# Copyright (c) 2021 Red Hat, Inc. +# +# Author: +# Cleber Rosa <crosa@redhat.com> +# +# This work is licensed under the terms of the GNU GPL, version 2 or +# later. See the COPYING file in the top-level directory. + +from avocado_qemu import Test + +from qemu.utils import get_info_usernet_hostfwd_port + + +class InfoUsernet(Test): + + def test_hostfwd(self): + self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22') + self.vm.launch() + res = self.vm.command('human-monitor-command', + command_line='info usernet') + port = get_info_usernet_hostfwd_port(res) + self.assertIsNotNone(port, + ('"info usernet" output content does not seem to ' + 'contain the redirected port')) + self.assertGreater(port, 0, + ('Found a redirected port that is not greater than' + ' zero')) diff --git a/tests/acceptance/linux_ssh_mips_malta.py b/tests/acceptance/linux_ssh_mips_malta.py index 6dbd02d49d..61c9079d04 100644 --- a/tests/acceptance/linux_ssh_mips_malta.py +++ b/tests/acceptance/linux_ssh_mips_malta.py @@ -12,14 +12,14 @@ import logging import time from avocado import skipUnless -from avocado_qemu import Test +from avocado_qemu import Test, LinuxSSHMixIn from avocado_qemu import wait_for_console_pattern from avocado.utils import process from avocado.utils import archive from avocado.utils import ssh -class LinuxSSH(Test): +class LinuxSSH(Test, LinuxSSHMixIn): timeout = 150 # Not for 'configure --enable-debug --enable-debug-tcg' @@ -70,45 +70,9 @@ class LinuxSSH(Test): def setUp(self): super(LinuxSSH, self).setUp() - def get_portfwd(self): - res = self.vm.command('human-monitor-command', - command_line='info usernet') - line = res.split('\r\n')[2] - port = re.split(r'.*TCP.HOST_FORWARD.*127\.0\.0\.1 (\d+)\s+10\..*', - line)[1] - self.log.debug("sshd listening on port:" + port) - return port - - def ssh_connect(self, username, password): - self.ssh_logger = logging.getLogger('ssh') - port = self.get_portfwd() - self.ssh_session = ssh.Session(self.VM_IP, port=int(port), - user=username, password=password) - for i in range(10): - try: - self.ssh_session.connect() - return - except: - time.sleep(4) - pass - self.fail("ssh connection timeout") - def ssh_disconnect_vm(self): self.ssh_session.quit() - def ssh_command(self, command, is_root=True): - self.ssh_logger.info(command) - result = self.ssh_session.cmd(command) - stdout_lines = [line.rstrip() for line - in result.stdout_text.splitlines()] - for line in stdout_lines: - self.ssh_logger.info(line) - stderr_lines = [line.rstrip() for line - in result.stderr_text.splitlines()] - for line in stderr_lines: - self.ssh_logger.warning(line) - return stdout_lines, stderr_lines - def boot_debian_wheezy_image_and_ssh_login(self, endianess, kernel_path): image_url, image_hash = self.get_image_info(endianess) image_path = self.fetch_asset(image_url, asset_hash=image_hash) @@ -129,7 +93,7 @@ class LinuxSSH(Test): wait_for_console_pattern(self, console_pattern, 'Oops') self.log.info('sshd ready') - self.ssh_connect('root', 'root') + self.ssh_connect('root', 'root', False) def shutdown_via_ssh(self): self.ssh_command('poweroff') diff --git a/tests/acceptance/virtio-gpu.py b/tests/acceptance/virtio-gpu.py index ab18cddbb7..e7979343e9 100644 --- a/tests/acceptance/virtio-gpu.py +++ b/tests/acceptance/virtio-gpu.py @@ -10,7 +10,7 @@ from avocado_qemu import wait_for_console_pattern from avocado_qemu import exec_command_and_wait_for_pattern from avocado_qemu import is_readable_executable_file -from qemu.accel import kvm_available +from qemu.utils import kvm_available import os import socket diff --git a/tests/acceptance/virtiofs_submounts.py b/tests/acceptance/virtiofs_submounts.py index 46fa65392a..21ad7d792e 100644 --- a/tests/acceptance/virtiofs_submounts.py +++ b/tests/acceptance/virtiofs_submounts.py @@ -70,56 +70,9 @@ def has_cmds(*cmds): class VirtiofsSubmountsTest(LinuxTest): """ :avocado: tags=arch:x86_64 + :avocado: tags=accel:kvm """ - def get_portfwd(self): - port = None - - res = self.vm.command('human-monitor-command', - command_line='info usernet') - for line in res.split('\r\n'): - match = \ - re.search(r'TCP.HOST_FORWARD.*127\.0\.0\.1\s+(\d+)\s+10\.', - line) - if match is not None: - port = int(match[1]) - break - - self.assertIsNotNone(port) - self.assertGreater(port, 0) - self.log.debug('sshd listening on port: %d', port) - return port - - def ssh_connect(self, username, keyfile): - self.ssh_logger = logging.getLogger('ssh') - port = self.get_portfwd() - self.ssh_session = ssh.Session('127.0.0.1', port=port, - user=username, key=keyfile) - for i in range(10): - try: - self.ssh_session.connect() - return - except: - time.sleep(4) - pass - self.fail('ssh connection timeout') - - def ssh_command(self, command): - self.ssh_logger.info(command) - result = self.ssh_session.cmd(command) - stdout_lines = [line.rstrip() for line - in result.stdout_text.splitlines()] - for line in stdout_lines: - self.ssh_logger.info(line) - stderr_lines = [line.rstrip() for line - in result.stderr_text.splitlines()] - for line in stderr_lines: - self.ssh_logger.warning(line) - - self.assertEqual(result.exit_status, 0, - f'Guest command failed: {command}') - return stdout_lines, stderr_lines - def run(self, args, ignore_error=False): stdout, stderr, ret = run_cmd(args) @@ -181,10 +134,6 @@ class VirtiofsSubmountsTest(LinuxTest): '-numa', 'node,memdev=mem') - def launch_vm(self): - self.launch_and_wait() - self.ssh_connect('root', self.ssh_key) - def set_up_nested_mounts(self): scratch_dir = os.path.join(self.shared_dir, 'scratch') try: @@ -246,18 +195,14 @@ class VirtiofsSubmountsTest(LinuxTest): self.run(('ssh-keygen', '-N', '', '-t', 'ed25519', '-f', self.ssh_key)) - pubkey = open(self.ssh_key + '.pub').read() + pubkey = self.ssh_key + '.pub' super(VirtiofsSubmountsTest, self).setUp(pubkey) - if len(vmlinuz) > 0: + if vmlinuz: self.vm.add_args('-kernel', vmlinuz, '-append', 'console=ttyS0 root=/dev/sda1') - # Allow us to connect to SSH - self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22', - '-device', 'virtio-net,netdev=vnet') - self.require_accelerator("kvm") self.vm.add_args('-accel', 'kvm') @@ -277,7 +222,7 @@ class VirtiofsSubmountsTest(LinuxTest): self.set_up_nested_mounts() self.set_up_virtiofs() - self.launch_vm() + self.launch_and_wait() self.mount_in_guest() self.check_in_guest() @@ -287,14 +232,14 @@ class VirtiofsSubmountsTest(LinuxTest): self.set_up_nested_mounts() - self.launch_vm() + self.launch_and_wait() self.mount_in_guest() self.check_in_guest() def test_post_launch_set_up(self): self.set_up_shared_dir() self.set_up_virtiofs() - self.launch_vm() + self.launch_and_wait() self.set_up_nested_mounts() @@ -304,7 +249,7 @@ class VirtiofsSubmountsTest(LinuxTest): def test_post_mount_set_up(self): self.set_up_shared_dir() self.set_up_virtiofs() - self.launch_vm() + self.launch_and_wait() self.mount_in_guest() self.set_up_nested_mounts() @@ -317,7 +262,7 @@ class VirtiofsSubmountsTest(LinuxTest): self.set_up_nested_mounts() self.set_up_virtiofs() - self.launch_vm() + self.launch_and_wait() self.mount_in_guest() self.check_in_guest() diff --git a/tests/docker/dockerfiles/centos7.docker b/tests/docker/dockerfiles/centos7.docker deleted file mode 100644 index 75fdb53c7c..0000000000 --- a/tests/docker/dockerfiles/centos7.docker +++ /dev/null @@ -1,43 +0,0 @@ -FROM centos:7 -RUN yum install -y epel-release centos-release-xen-48 - -RUN yum -y update - -# Please keep this list sorted alphabetically -ENV PACKAGES \ - bzip2 \ - bzip2-devel \ - ccache \ - csnappy-devel \ - dbus-daemon \ - gcc-c++ \ - gcc \ - gettext \ - git \ - glib2-devel \ - glibc-static \ - gnutls-devel \ - libaio-devel \ - libepoxy-devel \ - libfdt-devel \ - libgcrypt-devel \ - librdmacm-devel \ - libzstd-devel \ - lzo-devel \ - make \ - mesa-libEGL-devel \ - mesa-libgbm-devel \ - nettle-devel \ - ninja-build \ - perl-Test-Harness \ - pixman-devel \ - python3 \ - SDL2-devel \ - spice-glib-devel \ - spice-server-devel \ - tar \ - vte-devel \ - xen-devel \ - zlib-devel -RUN yum install -y $PACKAGES -RUN rpm -q $PACKAGES | sort > /packages.txt diff --git a/tests/docker/dockerfiles/python.docker b/tests/docker/dockerfiles/python.docker new file mode 100644 index 0000000000..56d88417df --- /dev/null +++ b/tests/docker/dockerfiles/python.docker @@ -0,0 +1,18 @@ +# Python library testing environment + +FROM fedora:latest +MAINTAINER John Snow <jsnow@redhat.com> + +# Please keep this list sorted alphabetically +ENV PACKAGES \ + gcc \ + make \ + pipenv \ + python3 \ + python3-pip \ + python3-tox \ + python3-virtualenv \ + python3.10 + +RUN dnf install -y $PACKAGES +RUN rpm -q $PACKAGES | sort > /packages.txt diff --git a/tests/fp/fp-test-log2.c b/tests/fp/fp-test-log2.c new file mode 100644 index 0000000000..4eae93eb7c --- /dev/null +++ b/tests/fp/fp-test-log2.c @@ -0,0 +1,118 @@ +/* + * fp-test-log2.c - test QEMU's softfloat log2 + * + * Copyright (C) 2020, Linaro, Ltd. + * + * License: GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#ifndef HW_POISON_H +#error Must define HW_POISON_H to work around TARGET_* poisoning +#endif + +#include "qemu/osdep.h" +#include "qemu/cutils.h" +#include <math.h> +#include "fpu/softfloat.h" + +typedef union { + double d; + float64 i; +} ufloat64; + +static int errors; + +static void compare(ufloat64 test, ufloat64 real, ufloat64 soft, bool exact) +{ + int msb; + uint64_t ulp = UINT64_MAX; + + if (real.i == soft.i) { + return; + } + msb = 63 - __builtin_clzll(real.i ^ soft.i); + + if (msb < 52) { + if (real.i > soft.i) { + ulp = real.i - soft.i; + } else { + ulp = soft.i - real.i; + } + } + + /* glibc allows 3 ulp error in its libm-test-ulps; allow 4 here */ + if (!exact && ulp <= 4) { + return; + } + + printf("test: %016" PRIx64 " %+.13a\n" + " sf: %016" PRIx64 " %+.13a\n" + "libm: %016" PRIx64 " %+.13a\n", + test.i, test.d, soft.i, soft.d, real.i, real.d); + + if (msb == 63) { + printf("Error in sign!\n\n"); + } else if (msb >= 52) { + printf("Error in exponent: %d\n\n", + (int)(soft.i >> 52) - (int)(real.i >> 52)); + } else { + printf("Error in fraction: %" PRIu64 " ulp\n\n", ulp); + } + + if (++errors == 20) { + exit(1); + } +} + +int main(int ac, char **av) +{ + ufloat64 test, real, soft; + float_status qsf = {0}; + int i; + + set_float_rounding_mode(float_round_nearest_even, &qsf); + + test.d = 0.0; + real.d = -__builtin_inf(); + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, true); + + test.d = 1.0; + real.d = 0.0; + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, true); + + test.d = 2.0; + real.d = 1.0; + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, true); + + test.d = 4.0; + real.d = 2.0; + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, true); + + test.d = 0x1p64; + real.d = 64.0; + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, true); + + test.d = __builtin_inf(); + real.d = __builtin_inf(); + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, true); + + for (i = 0; i < 10000; ++i) { + test.d = drand48() + 1.0; /* [1.0, 2.0) */ + real.d = log2(test.d); + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, false); + + test.d = drand48() * 100; /* [0.0, 100) */ + real.d = log2(test.d); + soft.i = float64_log2(test.i, &qsf); + compare(test, real, soft, false); + } + + return 0; +} diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index ff131afbde..352dd71c44 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -963,18 +963,21 @@ static void QEMU_NORETURN run_test(void) verCases_usesExact = !!(attrs & FUNC_ARG_EXACT); for (k = 0; k < 3; k++) { - int prec80 = 32; + FloatX80RoundPrec qsf_prec80 = floatx80_precision_x; + int prec80 = 80; int l; if (k == 1) { prec80 = 64; + qsf_prec80 = floatx80_precision_d; } else if (k == 2) { - prec80 = 80; + prec80 = 32; + qsf_prec80 = floatx80_precision_s; } verCases_roundingPrecision = 0; slow_extF80_roundingPrecision = prec80; - qsf.floatx80_rounding_precision = prec80; + qsf.floatx80_rounding_precision = qsf_prec80; if (attrs & FUNC_EFF_ROUNDINGPRECISION) { verCases_roundingPrecision = prec80; diff --git a/tests/fp/meson.build b/tests/fp/meson.build index 1c3eee9955..07e2cdc8d2 100644 --- a/tests/fp/meson.build +++ b/tests/fp/meson.build @@ -556,7 +556,9 @@ softfloat_conv_tests = { 'extF80_to_f64 extF80_to_f128 ' + 'f128_to_f16', 'int-to-float': 'i32_to_f16 i64_to_f16 i32_to_f32 i64_to_f32 ' + - 'i32_to_f64 i64_to_f64 i32_to_f128 i64_to_f128', + 'i32_to_f64 i64_to_f64 ' + + 'i32_to_extF80 i64_to_extF80 ' + + 'i32_to_f128 i64_to_f128', 'uint-to-float': 'ui32_to_f16 ui64_to_f16 ui32_to_f32 ui64_to_f32 ' + 'ui32_to_f64 ui64_to_f64 ui64_to_f128 ' + 'ui32_to_extF80 ui64_to_extF80', @@ -581,7 +583,7 @@ softfloat_conv_tests = { 'extF80_to_ui64 extF80_to_ui64_r_minMag ' + 'f128_to_ui64 f128_to_ui64_r_minMag', 'round-to-integer': 'f16_roundToInt f32_roundToInt ' + - 'f64_roundToInt f128_roundToInt' + 'f64_roundToInt extF80_roundToInt f128_roundToInt' } softfloat_tests = { 'eq_signaling' : 'compare', @@ -602,24 +604,20 @@ fptest_args = ['-s', '-l', '1'] fptest_rounding_args = ['-r', 'all'] # Conversion Routines: -# FIXME: i32_to_extF80 (broken), i64_to_extF80 (broken) -# extF80_roundToInt (broken) foreach k, v : softfloat_conv_tests test('fp-test-' + k, fptest, args: fptest_args + fptest_rounding_args + v.split(), suite: ['softfloat', 'softfloat-conv']) endforeach -# FIXME: extF80_{lt_quiet, rem} (broken), -# extF80_{mulAdd} (missing) foreach k, v : softfloat_tests - extF80_broken = ['lt_quiet', 'rem'].contains(k) test('fp-test-' + k, fptest, args: fptest_args + fptest_rounding_args + - ['f16_' + k, 'f32_' + k, 'f64_' + k, 'f128_' + k] + - (extF80_broken ? [] : ['extF80_' + k]), + ['f16_' + k, 'f32_' + k, 'f64_' + k, 'f128_' + k, 'extF80_' + k], suite: ['softfloat', 'softfloat-' + v]) endforeach + +# FIXME: extF80_{mulAdd} (missing) test('fp-test-mulAdd', fptest, # no fptest_rounding_args args: fptest_args + @@ -634,3 +632,14 @@ fpbench = executable( include_directories: [sfinc, include_directories(tfdir)], c_args: fpcflags, ) + +fptestlog2 = executable( + 'fp-test-log2', + ['fp-test-log2.c', '../../fpu/softfloat.c'], + link_with: [libsoftfloat], + dependencies: [qemuutil], + include_directories: [sfinc], + c_args: fpcflags, +) +test('fp-test-log2', fptestlog2, + suite: ['softfloat', 'softfloat-ops']) diff --git a/tests/fp/wrap.c.inc b/tests/fp/wrap.c.inc index cb1bb77e4c..9ff884c140 100644 --- a/tests/fp/wrap.c.inc +++ b/tests/fp/wrap.c.inc @@ -643,7 +643,7 @@ WRAP_CMP80(qemu_extF80M_eq, floatx80_eq_quiet) WRAP_CMP80(qemu_extF80M_le, floatx80_le) WRAP_CMP80(qemu_extF80M_lt, floatx80_lt) WRAP_CMP80(qemu_extF80M_le_quiet, floatx80_le_quiet) -WRAP_CMP80(qemu_extF80M_lt_quiet, floatx80_le_quiet) +WRAP_CMP80(qemu_extF80M_lt_quiet, floatx80_lt_quiet) #undef WRAP_CMP80 #define WRAP_CMP128(name, func) \ diff --git a/tests/plugin/syscall.c b/tests/plugin/syscall.c index 53ee2ab6c4..6dd71092e1 100644 --- a/tests/plugin/syscall.c +++ b/tests/plugin/syscall.c @@ -16,32 +16,120 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION; +typedef struct { + int64_t num; + int64_t calls; + int64_t errors; +} SyscallStats; + +static GMutex lock; +static GHashTable *statistics; + +static SyscallStats *get_or_create_entry(int64_t num) +{ + SyscallStats *entry = + (SyscallStats *) g_hash_table_lookup(statistics, GINT_TO_POINTER(num)); + + if (!entry) { + entry = g_new0(SyscallStats, 1); + entry->num = num; + g_hash_table_insert(statistics, GINT_TO_POINTER(num), (gpointer) entry); + } + + return entry; +} + static void vcpu_syscall(qemu_plugin_id_t id, unsigned int vcpu_index, int64_t num, uint64_t a1, uint64_t a2, uint64_t a3, uint64_t a4, uint64_t a5, uint64_t a6, uint64_t a7, uint64_t a8) { - g_autofree gchar *out = g_strdup_printf("syscall #%" PRIi64 "\n", num); - qemu_plugin_outs(out); + if (statistics) { + SyscallStats *entry; + g_mutex_lock(&lock); + entry = get_or_create_entry(num); + entry->calls++; + g_mutex_unlock(&lock); + } else { + g_autofree gchar *out = g_strdup_printf("syscall #%" PRIi64 "\n", num); + qemu_plugin_outs(out); + } } static void vcpu_syscall_ret(qemu_plugin_id_t id, unsigned int vcpu_idx, int64_t num, int64_t ret) { + if (statistics) { + SyscallStats *entry; + + g_mutex_lock(&lock); + /* Should always return an existent entry. */ + entry = get_or_create_entry(num); + if (ret < 0) { + entry->errors++; + } + g_mutex_unlock(&lock); + } else { + g_autofree gchar *out; + out = g_strdup_printf("syscall #%" PRIi64 " returned -> %" PRIi64 "\n", + num, ret); + qemu_plugin_outs(out); + } +} + +static void print_entry(gpointer val, gpointer user_data) +{ g_autofree gchar *out; - out = g_strdup_printf("syscall #%" PRIi64 " returned -> %" PRIi64 "\n", - num, ret); + SyscallStats *entry = (SyscallStats *) val; + int64_t syscall_num = entry->num; + out = g_strdup_printf( + "%-13" PRIi64 "%-6" PRIi64 " %" PRIi64 "\n", + syscall_num, entry->calls, entry->errors); qemu_plugin_outs(out); } +static gint comp_func(gconstpointer ea, gconstpointer eb) +{ + SyscallStats *ent_a = (SyscallStats *) ea; + SyscallStats *ent_b = (SyscallStats *) eb; + + return ent_a->calls > ent_b->calls ? -1 : 1; +} + /* ************************************************************************* */ +static void plugin_exit(qemu_plugin_id_t id, void *p) +{ + if (!statistics) { + return; + } + + g_mutex_lock(&lock); + GList *entries = g_hash_table_get_values(statistics); + entries = g_list_sort(entries, comp_func); + qemu_plugin_outs("syscall no. calls errors\n"); -static void plugin_exit(qemu_plugin_id_t id, void *p) {} + g_list_foreach(entries, print_entry, NULL); + + g_list_free(entries); + g_hash_table_destroy(statistics); + g_mutex_unlock(&lock); +} QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info, int argc, char **argv) { + if (argc == 0) { + statistics = g_hash_table_new_full(NULL, g_direct_equal, NULL, g_free); + } else { + for (int i = 0; i < argc; i++) { + if (g_strcmp0(argv[i], "print") != 0) { + fprintf(stderr, "unsupported argument: %s\n", argv[i]); + return -1; + } + } + } + qemu_plugin_register_vcpu_syscall_cb(id, vcpu_syscall); qemu_plugin_register_vcpu_syscall_ret_cb(id, vcpu_syscall_ret); qemu_plugin_register_atexit_cb(id, plugin_exit, NULL); diff --git a/tests/qapi-schema/meson.build b/tests/qapi-schema/meson.build index 9e8f658ce3..b8de58116a 100644 --- a/tests/qapi-schema/meson.build +++ b/tests/qapi-schema/meson.build @@ -208,7 +208,7 @@ schemas += [meson.current_source_dir() / 'missing-schema.json'] # Because people may want to use test-qapi.py from the command line, we # are not using the "#! /usr/bin/env python3" trick here. See -# docs/devel/build-system.txt +# docs/devel/build-system.rst test('QAPI schema regression tests', python, args: files('test-qapi.py') + schemas, env: test_env, suite: ['qapi-schema', 'qapi-frontend']) diff --git a/tests/qemu-iotests/283.out b/tests/qemu-iotests/283.out index 97e62a4c94..c6e12b15c5 100644 --- a/tests/qemu-iotests/283.out +++ b/tests/qemu-iotests/283.out @@ -5,7 +5,7 @@ {"execute": "blockdev-add", "arguments": {"driver": "blkdebug", "image": "base", "node-name": "other", "take-child-perms": ["write"]}} {"return": {}} {"execute": "blockdev-backup", "arguments": {"device": "source", "sync": "full", "target": "target"}} -{"error": {"class": "GenericError", "desc": "Cannot append backup-top filter: Conflicts with use by source as 'image', which does not allow 'write' on base"}} +{"error": {"class": "GenericError", "desc": "Cannot append backup-top filter: Permission conflict on node 'base': permissions 'write' are both required by node 'other' (uses node 'base' as 'image' child) and unshared by node 'source' (uses node 'base' as 'image' child)."}} === backup-top should be gone after job-finalize === diff --git a/tests/qemu-iotests/297 b/tests/qemu-iotests/297 index a37910b42d..433b732336 100755 --- a/tests/qemu-iotests/297 +++ b/tests/qemu-iotests/297 @@ -95,6 +95,7 @@ def run_linters(): '--warn-redundant-casts', '--warn-unused-ignores', '--no-implicit-reexport', + '--namespace-packages', filename), env=env, check=False, diff --git a/tests/qemu-iotests/300 b/tests/qemu-iotests/300 index b475a92c47..fe94de84ed 100755 --- a/tests/qemu-iotests/300 +++ b/tests/qemu-iotests/300 @@ -28,7 +28,7 @@ import iotests # Import qemu after iotests.py has amended sys.path # pylint: disable=wrong-import-order -import qemu +from qemu.machine import machine BlockBitmapMapping = List[Dict[str, object]] @@ -466,7 +466,7 @@ class TestBlockBitmapMappingErrors(TestDirtyBitmapMigration): # the failed migration try: self.vm_b.shutdown() - except qemu.machine.AbnormalShutdown: + except machine.AbnormalShutdown: pass def test_aliased_bitmap_name_too_long(self) -> None: diff --git a/tests/qemu-iotests/307.out b/tests/qemu-iotests/307.out index daa8ad2da0..4b0c7e155a 100644 --- a/tests/qemu-iotests/307.out +++ b/tests/qemu-iotests/307.out @@ -53,7 +53,7 @@ exports available: 1 === Add a writable export === {"execute": "block-export-add", "arguments": {"description": "This is the writable second export", "id": "export1", "name": "export1", "node-name": "fmt", "type": "nbd", "writable": true, "writethrough": true}} -{"error": {"class": "GenericError", "desc": "Conflicts with use by sda as 'root', which does not allow 'write' on fmt"}} +{"error": {"class": "GenericError", "desc": "Permission conflict on node 'fmt': permissions 'write' are both required by an unnamed block device (uses node 'fmt' as 'root' child) and unshared by block device 'sda' (uses node 'fmt' as 'root' child)."}} {"execute": "device_del", "arguments": {"id": "sda"}} {"return": {}} {"data": {"device": "sda", "path": "/machine/peripheral/sda"}, "event": "DEVICE_DELETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index 777fa2ec0e..89663dac06 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -38,7 +38,7 @@ from contextlib import contextmanager # pylint: disable=import-error, wrong-import-position sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..', 'python')) -from qemu import qtest +from qemu.machine import qtest from qemu.qmp import QMPMessage # Use this logger for logging messages directly from the iotests module @@ -571,7 +571,7 @@ class VM(qtest.QEMUQtestMachine): def __init__(self, path_suffix=''): name = "qemu%s-%d" % (path_suffix, os.getpid()) super().__init__(qemu_prog, qemu_opts, name=name, - test_dir=test_dir, + base_temp_dir=test_dir, socket_scm_helper=socket_scm_helper, sock_dir=sock_dir) self._num_drives = 0 diff --git a/tests/qemu-iotests/tests/qsd-jobs.out b/tests/qemu-iotests/tests/qsd-jobs.out index 9f52255da8..189423354b 100644 --- a/tests/qemu-iotests/tests/qsd-jobs.out +++ b/tests/qemu-iotests/tests/qsd-jobs.out @@ -16,7 +16,7 @@ QMP_VERSION {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "job0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "job0"}} -{"error": {"class": "GenericError", "desc": "Conflicts with use by stream job 'job0' as 'intermediate node', which does not allow 'write' on fmt_base"}} +{"error": {"class": "GenericError", "desc": "Permission conflict on node 'fmt_base': permissions 'write' are both required by an unnamed block device (uses node 'fmt_base' as 'root' child) and unshared by stream job 'job0' (uses node 'fmt_base' as 'intermediate node' child)."}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_EXPORT_DELETED", "data": {"id": "export1"}} *** done diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index 156d4174aa..51d3a4e239 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -489,10 +489,14 @@ static void test_acpi_asl(test_data *data) exp_sdt->asl_file, sdt->asl_file); int out = dup(STDOUT_FILENO); int ret G_GNUC_UNUSED; + int dupret; - dup2(STDERR_FILENO, STDOUT_FILENO); + g_assert(out >= 0); + dupret = dup2(STDERR_FILENO, STDOUT_FILENO); + g_assert(dupret >= 0); ret = system(diff) ; - dup2(out, STDOUT_FILENO); + dupret = dup2(out, STDOUT_FILENO); + g_assert(dupret >= 0); close(out); g_free(diff); } diff --git a/tests/qtest/e1000e-test.c b/tests/qtest/e1000e-test.c index fc226fdfeb..0273fe4c15 100644 --- a/tests/qtest/e1000e-test.c +++ b/tests/qtest/e1000e-test.c @@ -93,7 +93,8 @@ static void e1000e_send_verify(QE1000E *d, int *test_sockets, QGuestAllocator *a /* Check data sent to the backend */ ret = qemu_recv(test_sockets[0], &recv_len, sizeof(recv_len), 0); g_assert_cmpint(ret, == , sizeof(recv_len)); - qemu_recv(test_sockets[0], buffer, 64, 0); + ret = qemu_recv(test_sockets[0], buffer, 64, 0); + g_assert_cmpint(ret, >=, 5); g_assert_cmpstr(buffer, == , "TEST"); /* Free test data buffer */ diff --git a/tests/qtest/fuzz/fuzz.c b/tests/qtest/fuzz/fuzz.c index 04b70e114b..5f77c84983 100644 --- a/tests/qtest/fuzz/fuzz.c +++ b/tests/qtest/fuzz/fuzz.c @@ -16,6 +16,7 @@ #include <wordexp.h> #include "qemu/datadir.h" +#include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "sysemu/runstate.h" #include "qemu/main-loop.h" diff --git a/tests/qtest/hd-geo-test.c b/tests/qtest/hd-geo-test.c index f7b7cfbc2d..113126ae06 100644 --- a/tests/qtest/hd-geo-test.c +++ b/tests/qtest/hd-geo-test.c @@ -464,7 +464,7 @@ static char *create_qcow2_with_mbr(MBRpartitions mbr, uint64_t sectors) } fd = mkstemp(raw_path); - g_assert(fd); + g_assert(fd >= 0); close(fd); fd = open(raw_path, O_WRONLY); @@ -474,7 +474,7 @@ static char *create_qcow2_with_mbr(MBRpartitions mbr, uint64_t sectors) close(fd); fd = mkstemp(qcow2_path); - g_assert(fd); + g_assert(fd >= 0); close(fd); qemu_img_path = getenv("QTEST_QEMU_IMG"); diff --git a/tests/qtest/pflash-cfi02-test.c b/tests/qtest/pflash-cfi02-test.c index 60db81a3a2..6168edc821 100644 --- a/tests/qtest/pflash-cfi02-test.c +++ b/tests/qtest/pflash-cfi02-test.c @@ -406,7 +406,7 @@ static void test_geometry(const void *opaque) for (int region = 0; region < nb_erase_regions; ++region) { for (uint32_t i = 0; i < c->nb_blocs[region]; ++i) { - uint64_t byte_addr = i * c->sector_len[region]; + uint64_t byte_addr = (uint64_t)i * c->sector_len[region]; g_assert_cmphex(flash_read(c, byte_addr), ==, bank_mask(c)); } } diff --git a/tests/qtest/tpm-tests.c b/tests/qtest/tpm-tests.c index 0da3a8a4df..25073d1f9e 100644 --- a/tests/qtest/tpm-tests.c +++ b/tests/qtest/tpm-tests.c @@ -123,14 +123,10 @@ void tpm_test_swtpm_migration_test(const char *src_tpm_path, qtest_quit(src_qemu); tpm_util_swtpm_kill(dst_tpm_pid); - if (dst_tpm_addr) { - g_unlink(dst_tpm_addr->u.q_unix.path); - qapi_free_SocketAddress(dst_tpm_addr); - } + g_unlink(dst_tpm_addr->u.q_unix.path); + qapi_free_SocketAddress(dst_tpm_addr); tpm_util_swtpm_kill(src_tpm_pid); - if (src_tpm_addr) { - g_unlink(src_tpm_addr->u.q_unix.path); - qapi_free_SocketAddress(src_tpm_addr); - } + g_unlink(src_tpm_addr->u.q_unix.path); + qapi_free_SocketAddress(src_tpm_addr); } diff --git a/tests/requirements.txt b/tests/requirements.txt index 91f3a343b9..a21b59b443 100644 --- a/tests/requirements.txt +++ b/tests/requirements.txt @@ -1,5 +1,5 @@ # Add Python module requirements, one per line, to be installed # in the tests/venv Python virtual environment. For more info, # refer to: https://pip.pypa.io/en/stable/user_guide/#id1 -avocado-framework==85.0 +avocado-framework==88.1 pycdlib==1.11.0 diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index 8cf172cb7a..c39e70b2f5 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -194,13 +194,11 @@ static void test_sync_op_truncate(BdrvChild *c) g_assert_cmpint(ret, ==, -EINVAL); /* Error: Read-only image */ - c->bs->read_only = true; c->bs->open_flags &= ~BDRV_O_RDWR; ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, -EACCES); - c->bs->read_only = false; c->bs->open_flags |= BDRV_O_RDWR; } @@ -236,13 +234,11 @@ static void test_sync_op_flush(BdrvChild *c) g_assert_cmpint(ret, ==, 0); /* Early success: Read-only image */ - c->bs->read_only = true; c->bs->open_flags &= ~BDRV_O_RDWR; ret = bdrv_flush(c->bs); g_assert_cmpint(ret, ==, 0); - c->bs->read_only = false; c->bs->open_flags |= BDRV_O_RDWR; } @@ -256,13 +252,11 @@ static void test_sync_op_blk_flush(BlockBackend *blk) g_assert_cmpint(ret, ==, 0); /* Early success: Read-only image */ - bs->read_only = true; bs->open_flags &= ~BDRV_O_RDWR; ret = blk_flush(blk); g_assert_cmpint(ret, ==, 0); - bs->read_only = false; bs->open_flags |= BDRV_O_RDWR; } diff --git a/tests/unit/test-replication.c b/tests/unit/test-replication.c index b067240add..afff908d77 100644 --- a/tests/unit/test-replication.c +++ b/tests/unit/test-replication.c @@ -14,7 +14,7 @@ #include "qapi/qmp/qdict.h" #include "qemu/option.h" #include "qemu/main-loop.h" -#include "replication.h" +#include "block/replication.h" #include "block/block_int.h" #include "block/qdict.h" #include "sysemu/block-backend.h" diff --git a/tests/unit/test-vmstate.c b/tests/unit/test-vmstate.c index a001879585..4688c03ea7 100644 --- a/tests/unit/test-vmstate.c +++ b/tests/unit/test-vmstate.c @@ -40,10 +40,12 @@ static int temp_fd; /* Duplicate temp_fd and seek to the beginning of the file */ static QEMUFile *open_test_file(bool write) { - int fd = dup(temp_fd); + int fd; QIOChannel *ioc; QEMUFile *f; + fd = dup(temp_fd); + g_assert(fd >= 0); lseek(fd, 0, SEEK_SET); if (write) { g_assert_cmpint(ftruncate(fd, 0), ==, 0); @@ -1486,6 +1488,7 @@ int main(int argc, char **argv) g_autofree char *temp_file = g_strdup_printf("%s/vmst.test.XXXXXX", g_get_tmp_dir()); temp_fd = mkstemp(temp_file); + g_assert(temp_fd >= 0); module_call_init(MODULE_INIT_QOM); diff --git a/tests/vm/aarch64vm.py b/tests/vm/aarch64vm.py index d70ab843b6..b00cce07eb 100644 --- a/tests/vm/aarch64vm.py +++ b/tests/vm/aarch64vm.py @@ -14,7 +14,7 @@ import os import sys import subprocess import basevm -from qemu.accel import kvm_available +from qemu.utils import kvm_available # This is the config needed for current version of QEMU. # This works for both kvm and tcg. diff --git a/tests/vm/basevm.py b/tests/vm/basevm.py index 00f1d5ca8d..0f2e436ed3 100644 --- a/tests/vm/basevm.py +++ b/tests/vm/basevm.py @@ -19,8 +19,8 @@ import logging import time import datetime sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..', 'python')) -from qemu.accel import kvm_available from qemu.machine import QEMUMachine +from qemu.utils import get_info_usernet_hostfwd_port, kvm_available import subprocess import hashlib import argparse @@ -227,7 +227,7 @@ class BaseVM(object): "-o", "UserKnownHostsFile=" + os.devnull, "-o", "ConnectTimeout={}".format(self._config["ssh_timeout"]), - "-p", self.ssh_port, "-i", self._ssh_tmp_key_file] + "-p", str(self.ssh_port), "-i", self._ssh_tmp_key_file] # If not in debug mode, set ssh to quiet mode to # avoid printing the results of commands. if not self.debug: @@ -305,12 +305,8 @@ class BaseVM(object): # Init console so we can start consuming the chars. self.console_init() usernet_info = guest.qmp("human-monitor-command", - command_line="info usernet") - self.ssh_port = None - for l in usernet_info["return"].splitlines(): - fields = l.split() - if "TCP[HOST_FORWARD]" in fields and "22" in fields: - self.ssh_port = l.split()[3] + command_line="info usernet").get("return") + self.ssh_port = get_info_usernet_hostfwd_port(usernet_info) if not self.ssh_port: raise Exception("Cannot find ssh port from 'info usernet':\n%s" % \ usernet_info) diff --git a/tests/vm/centos b/tests/vm/centos index efe3dbbb36..5c7bc1c1a9 100755 --- a/tests/vm/centos +++ b/tests/vm/centos @@ -26,24 +26,23 @@ class CentosVM(basevm.BaseVM): export SRC_ARCHIVE=/dev/vdb; sudo chmod a+r $SRC_ARCHIVE; tar -xf $SRC_ARCHIVE; - make docker-test-block@centos7 {verbose} J={jobs} NETWORK=1; - make docker-test-quick@centos7 {verbose} J={jobs} NETWORK=1; + make docker-test-block@centos8 {verbose} J={jobs} NETWORK=1; + make docker-test-quick@centos8 {verbose} J={jobs} NETWORK=1; make docker-test-mingw@fedora {verbose} J={jobs} NETWORK=1; """ def build_image(self, img): - cimg = self._download_with_cache("https://cloud.centos.org/centos/7/images/CentOS-7-x86_64-GenericCloud-1802.qcow2.xz") + cimg = self._download_with_cache("https://cloud.centos.org/centos/8/x86_64/images/CentOS-8-GenericCloud-8.3.2011-20201204.2.x86_64.qcow2") img_tmp = img + ".tmp" - sys.stderr.write("Extracting the image...\n") - subprocess.check_call(["ln", "-f", cimg, img_tmp + ".xz"]) - subprocess.check_call(["xz", "--keep", "-dvf", img_tmp + ".xz"]) + subprocess.check_call(["ln", "-f", cimg, img_tmp]) self.exec_qemu_img("resize", img_tmp, "50G") self.boot(img_tmp, extra_args = ["-cdrom", self.gen_cloud_init_iso()]) self.wait_ssh() self.ssh_root_check("touch /etc/cloud/cloud-init.disabled") - self.ssh_root_check("yum update -y") - self.ssh_root_check("yum install -y docker make ninja-build git python3") - self.ssh_root_check("systemctl enable docker") + self.ssh_root_check("dnf update -y") + self.ssh_root_check("dnf install -y dnf-plugins-core") + self.ssh_root_check("dnf config-manager --set-enabled powertools") + self.ssh_root_check("dnf install -y podman make ninja-build git python3") self.ssh_root("poweroff") self.wait() os.rename(img_tmp, img) diff --git a/tools/virtiofsd/buffer.c b/tools/virtiofsd/buffer.c index 874f01c488..b5f04be356 100644 --- a/tools/virtiofsd/buffer.c +++ b/tools/virtiofsd/buffer.c @@ -37,7 +37,7 @@ static ssize_t fuse_buf_writev(struct fuse_buf *out_buf, struct iovec *iov; int fd = out_buf->fd; - iov = calloc(iovcnt, sizeof(struct iovec)); + iov = g_try_new0(struct iovec, iovcnt); if (!iov) { return -ENOMEM; } @@ -61,7 +61,7 @@ static ssize_t fuse_buf_writev(struct fuse_buf *out_buf, res = -errno; } - free(iov); + g_free(iov); return res; } diff --git a/tools/virtiofsd/fuse_opt.c b/tools/virtiofsd/fuse_opt.c index f0ab8d22f4..9d371448e9 100644 --- a/tools/virtiofsd/fuse_opt.c +++ b/tools/virtiofsd/fuse_opt.c @@ -272,7 +272,7 @@ static int process_opt_sep_arg(struct fuse_opt_context *ctx, } param = ctx->argv[ctx->argctr]; - newarg = malloc(sep + strlen(param) + 1); + newarg = g_try_malloc(sep + strlen(param) + 1); if (!newarg) { return alloc_failed(); } @@ -280,7 +280,7 @@ static int process_opt_sep_arg(struct fuse_opt_context *ctx, memcpy(newarg, arg, sep); strcpy(newarg + sep, param); res = process_opt(ctx, opt, sep, newarg, iso); - free(newarg); + g_free(newarg); return res; } diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c index 9efdbd8ffd..fa4aff9b0e 100644 --- a/tools/virtiofsd/fuse_virtio.c +++ b/tools/virtiofsd/fuse_virtio.c @@ -366,14 +366,12 @@ int virtio_send_data_iov(struct fuse_session *se, struct fuse_chan *ch, if (in_len < sizeof(struct fuse_out_header)) { fuse_log(FUSE_LOG_ERR, "%s: elem %d too short for out_header\n", __func__, elem->index); - ret = E2BIG; - goto err; + return E2BIG; } if (in_len < tosend_len) { fuse_log(FUSE_LOG_ERR, "%s: elem %d too small for data len %zd\n", __func__, elem->index, tosend_len); - ret = E2BIG; - goto err; + return E2BIG; } /* TODO: Limit to 'len' */ @@ -389,68 +387,46 @@ int virtio_send_data_iov(struct fuse_session *se, struct fuse_chan *ch, memcpy(in_sg_cpy, in_sg, sizeof(struct iovec) * in_num); /* These get updated as we skip */ struct iovec *in_sg_ptr = in_sg_cpy; - int in_sg_cpy_count = in_num; + unsigned int in_sg_cpy_count = in_num; /* skip over parts of in_sg that contained the header iov */ - size_t skip_size = iov_len; + iov_discard_front(&in_sg_ptr, &in_sg_cpy_count, iov_len); - size_t in_sg_left = 0; do { - while (skip_size != 0 && in_sg_cpy_count) { - if (skip_size >= in_sg_ptr[0].iov_len) { - skip_size -= in_sg_ptr[0].iov_len; - in_sg_ptr++; - in_sg_cpy_count--; - } else { - in_sg_ptr[0].iov_len -= skip_size; - in_sg_ptr[0].iov_base += skip_size; - break; - } - } + fuse_log(FUSE_LOG_DEBUG, "%s: in_sg_cpy_count=%d len remaining=%zd\n", + __func__, in_sg_cpy_count, len); - int i; - for (i = 0, in_sg_left = 0; i < in_sg_cpy_count; i++) { - in_sg_left += in_sg_ptr[i].iov_len; - } - fuse_log(FUSE_LOG_DEBUG, - "%s: after skip skip_size=%zd in_sg_cpy_count=%d " - "in_sg_left=%zd\n", - __func__, skip_size, in_sg_cpy_count, in_sg_left); ret = preadv(buf->buf[0].fd, in_sg_ptr, in_sg_cpy_count, buf->buf[0].pos); if (ret == -1) { ret = errno; + if (ret == EINTR) { + continue; + } fuse_log(FUSE_LOG_DEBUG, "%s: preadv failed (%m) len=%zd\n", __func__, len); - goto err; + return ret; } - fuse_log(FUSE_LOG_DEBUG, "%s: preadv ret=%d len=%zd\n", __func__, - ret, len); - if (ret < len && ret) { - fuse_log(FUSE_LOG_DEBUG, "%s: ret < len\n", __func__); - /* Skip over this much next time around */ - skip_size = ret; - buf->buf[0].pos += ret; - len -= ret; - /* Lets do another read */ - continue; - } if (!ret) { /* EOF case? */ - fuse_log(FUSE_LOG_DEBUG, "%s: !ret in_sg_left=%zd\n", __func__, - in_sg_left); + fuse_log(FUSE_LOG_DEBUG, "%s: !ret len remaining=%zd\n", __func__, + len); break; } - if (ret != len) { - fuse_log(FUSE_LOG_DEBUG, "%s: ret!=len\n", __func__); - ret = EIO; - goto err; - } - in_sg_left -= ret; + fuse_log(FUSE_LOG_DEBUG, "%s: preadv ret=%d len=%zd\n", __func__, + ret, len); + len -= ret; - } while (in_sg_left); + /* Short read. Retry reading remaining bytes */ + if (len) { + fuse_log(FUSE_LOG_DEBUG, "%s: ret < len\n", __func__); + /* Skip over this much next time around */ + iov_discard_front(&in_sg_ptr, &in_sg_cpy_count, ret); + buf->buf[0].pos += ret; + } + } while (len); /* Need to fix out->len on EOF */ if (len) { @@ -460,21 +436,14 @@ int virtio_send_data_iov(struct fuse_session *se, struct fuse_chan *ch, out_sg->len = tosend_len; } - ret = 0; - vu_dispatch_rdlock(qi->virtio_dev); pthread_mutex_lock(&qi->vq_lock); vu_queue_push(dev, q, elem, tosend_len); vu_queue_notify(dev, q); pthread_mutex_unlock(&qi->vq_lock); vu_dispatch_unlock(qi->virtio_dev); - -err: - if (ret == 0) { - req->reply_sent = true; - } - - return ret; + req->reply_sent = true; + return 0; } static __thread bool clone_fs_called; diff --git a/trace-events b/trace-events index ac7cef9335..765fe251e6 100644 --- a/trace-events +++ b/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # # This file is processed by the tracetool script during the build. # diff --git a/ui/meson.build b/ui/meson.build index b5aed14886..a3a187d633 100644 --- a/ui/meson.build +++ b/ui/meson.build @@ -12,6 +12,7 @@ softmmu_ss.add(files( 'kbd-state.c', 'keymaps.c', 'qemu-pixman.c', + 'udmabuf.c', )) softmmu_ss.add([spice_headers, files('spice-module.c')]) softmmu_ss.add(when: spice_protocol, if_true: files('vdagent.c')) diff --git a/ui/qemu-pixman.c b/ui/qemu-pixman.c index 85f2945e88..3ab7e2e958 100644 --- a/ui/qemu-pixman.c +++ b/ui/qemu-pixman.c @@ -89,21 +89,34 @@ pixman_format_code_t qemu_default_pixman_format(int bpp, bool native_endian) } /* Note: drm is little endian, pixman is native endian */ +static const struct { + uint32_t drm_format; + pixman_format_code_t pixman_format; +} drm_format_pixman_map[] = { + { DRM_FORMAT_RGB888, PIXMAN_LE_r8g8b8 }, + { DRM_FORMAT_ARGB8888, PIXMAN_LE_a8r8g8b8 }, + { DRM_FORMAT_XRGB8888, PIXMAN_LE_x8r8g8b8 } +}; + pixman_format_code_t qemu_drm_format_to_pixman(uint32_t drm_format) { - static const struct { - uint32_t drm_format; - pixman_format_code_t pixman; - } map[] = { - { DRM_FORMAT_RGB888, PIXMAN_LE_r8g8b8 }, - { DRM_FORMAT_ARGB8888, PIXMAN_LE_a8r8g8b8 }, - { DRM_FORMAT_XRGB8888, PIXMAN_LE_x8r8g8b8 } - }; int i; - for (i = 0; i < ARRAY_SIZE(map); i++) { - if (drm_format == map[i].drm_format) { - return map[i].pixman; + for (i = 0; i < ARRAY_SIZE(drm_format_pixman_map); i++) { + if (drm_format == drm_format_pixman_map[i].drm_format) { + return drm_format_pixman_map[i].pixman_format; + } + } + return 0; +} + +uint32_t qemu_pixman_to_drm_format(pixman_format_code_t pixman_format) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(drm_format_pixman_map); i++) { + if (pixman_format == drm_format_pixman_map[i].pixman_format) { + return drm_format_pixman_map[i].drm_format; } } return 0; diff --git a/ui/trace-events b/ui/trace-events index c86542e2b6..1b5f87bc09 100644 --- a/ui/trace-events +++ b/ui/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # console.c console_gfx_new(void) "" diff --git a/ui/udmabuf.c b/ui/udmabuf.c new file mode 100644 index 0000000000..23abe1e7eb --- /dev/null +++ b/ui/udmabuf.c @@ -0,0 +1,40 @@ +/* + * udmabuf helper functions. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "ui/console.h" + +#ifdef CONFIG_LINUX + +#include <fcntl.h> +#include <sys/ioctl.h> + +int udmabuf_fd(void) +{ + static bool first = true; + static int udmabuf; + + if (!first) { + return udmabuf; + } + first = false; + + udmabuf = open("/dev/udmabuf", O_RDWR); + if (udmabuf < 0) { + warn_report("open /dev/udmabuf: %s", strerror(errno)); + } + return udmabuf; +} + +#else + +int udmabuf_fd(void) +{ + return -1; +} + +#endif diff --git a/util/oslib-win32.c b/util/oslib-win32.c index 05e4ee5033..ca99356fdf 100644 --- a/util/oslib-win32.c +++ b/util/oslib-win32.c @@ -347,210 +347,6 @@ const char *qemu_get_exec_dir(void) return exec_dir; } -#if !GLIB_CHECK_VERSION(2, 50, 0) -/* - * The original implementation of g_poll from glib has a problem on Windows - * when using timeouts < 10 ms. - * - * Whenever g_poll is called with timeout < 10 ms, it does a quick poll instead - * of wait. This causes significant performance degradation of QEMU. - * - * The following code is a copy of the original code from glib/gpoll.c - * (glib commit 20f4d1820b8d4d0fc4447188e33efffd6d4a88d8 from 2014-02-19). - * Some debug code was removed and the code was reformatted. - * All other code modifications are marked with 'QEMU'. - */ - -/* - * gpoll.c: poll(2) abstraction - * Copyright 1998 Owen Taylor - * Copyright 2008 Red Hat, Inc. - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ - -static int poll_rest(gboolean poll_msgs, HANDLE *handles, gint nhandles, - GPollFD *fds, guint nfds, gint timeout) -{ - DWORD ready; - GPollFD *f; - int recursed_result; - - if (poll_msgs) { - /* Wait for either messages or handles - * -> Use MsgWaitForMultipleObjectsEx - */ - ready = MsgWaitForMultipleObjectsEx(nhandles, handles, timeout, - QS_ALLINPUT, MWMO_ALERTABLE); - - if (ready == WAIT_FAILED) { - gchar *emsg = g_win32_error_message(GetLastError()); - g_warning("MsgWaitForMultipleObjectsEx failed: %s", emsg); - g_free(emsg); - } - } else if (nhandles == 0) { - /* No handles to wait for, just the timeout */ - if (timeout == INFINITE) { - ready = WAIT_FAILED; - } else { - SleepEx(timeout, TRUE); - ready = WAIT_TIMEOUT; - } - } else { - /* Wait for just handles - * -> Use WaitForMultipleObjectsEx - */ - ready = - WaitForMultipleObjectsEx(nhandles, handles, FALSE, timeout, TRUE); - if (ready == WAIT_FAILED) { - gchar *emsg = g_win32_error_message(GetLastError()); - g_warning("WaitForMultipleObjectsEx failed: %s", emsg); - g_free(emsg); - } - } - - if (ready == WAIT_FAILED) { - return -1; - } else if (ready == WAIT_TIMEOUT || ready == WAIT_IO_COMPLETION) { - return 0; - } else if (poll_msgs && ready == WAIT_OBJECT_0 + nhandles) { - for (f = fds; f < &fds[nfds]; ++f) { - if (f->fd == G_WIN32_MSG_HANDLE && f->events & G_IO_IN) { - f->revents |= G_IO_IN; - } - } - - /* If we have a timeout, or no handles to poll, be satisfied - * with just noticing we have messages waiting. - */ - if (timeout != 0 || nhandles == 0) { - return 1; - } - - /* If no timeout and handles to poll, recurse to poll them, - * too. - */ - recursed_result = poll_rest(FALSE, handles, nhandles, fds, nfds, 0); - return (recursed_result == -1) ? -1 : 1 + recursed_result; - } else if (/* QEMU: removed the following unneeded statement which causes - * a compiler warning: ready >= WAIT_OBJECT_0 && */ - ready < WAIT_OBJECT_0 + nhandles) { - for (f = fds; f < &fds[nfds]; ++f) { - if ((HANDLE) f->fd == handles[ready - WAIT_OBJECT_0]) { - f->revents = f->events; - } - } - - /* If no timeout and polling several handles, recurse to poll - * the rest of them. - */ - if (timeout == 0 && nhandles > 1) { - /* Remove the handle that fired */ - int i; - for (i = ready - WAIT_OBJECT_0 + 1; i < nhandles; i++) { - handles[i-1] = handles[i]; - } - nhandles--; - recursed_result = poll_rest(FALSE, handles, nhandles, fds, nfds, 0); - return (recursed_result == -1) ? -1 : 1 + recursed_result; - } - return 1; - } - - return 0; -} - -gint g_poll_fixed(GPollFD *fds, guint nfds, gint timeout) -{ - HANDLE handles[MAXIMUM_WAIT_OBJECTS]; - gboolean poll_msgs = FALSE; - GPollFD *f; - gint nhandles = 0; - int retval; - - for (f = fds; f < &fds[nfds]; ++f) { - if (f->fd == G_WIN32_MSG_HANDLE && (f->events & G_IO_IN)) { - poll_msgs = TRUE; - } else if (f->fd > 0) { - /* Don't add the same handle several times into the array, as - * docs say that is not allowed, even if it actually does seem - * to work. - */ - gint i; - - for (i = 0; i < nhandles; i++) { - if (handles[i] == (HANDLE) f->fd) { - break; - } - } - - if (i == nhandles) { - if (nhandles == MAXIMUM_WAIT_OBJECTS) { - g_warning("Too many handles to wait for!\n"); - break; - } else { - handles[nhandles++] = (HANDLE) f->fd; - } - } - } - } - - for (f = fds; f < &fds[nfds]; ++f) { - f->revents = 0; - } - - if (timeout == -1) { - timeout = INFINITE; - } - - /* Polling for several things? */ - if (nhandles > 1 || (nhandles > 0 && poll_msgs)) { - /* First check if one or several of them are immediately - * available - */ - retval = poll_rest(poll_msgs, handles, nhandles, fds, nfds, 0); - - /* If not, and we have a significant timeout, poll again with - * timeout then. Note that this will return indication for only - * one event, or only for messages. We ignore timeouts less than - * ten milliseconds as they are mostly pointless on Windows, the - * MsgWaitForMultipleObjectsEx() call will timeout right away - * anyway. - * - * Modification for QEMU: replaced timeout >= 10 by timeout > 0. - */ - if (retval == 0 && (timeout == INFINITE || timeout > 0)) { - retval = poll_rest(poll_msgs, handles, nhandles, - fds, nfds, timeout); - } - } else { - /* Just polling for one thing, so no need to check first if - * available immediately - */ - retval = poll_rest(poll_msgs, handles, nhandles, fds, nfds, timeout); - } - - if (retval == -1) { - for (f = fds; f < &fds[nfds]; ++f) { - f->revents = 0; - } - } - - return retval; -} -#endif - int getpagesize(void) { SYSTEM_INFO system_info; diff --git a/util/qemu-config.c b/util/qemu-config.c index 670bd6ebca..34974c4b47 100644 --- a/util/qemu-config.c +++ b/util/qemu-config.c @@ -16,6 +16,7 @@ static QemuOptsList *find_list(QemuOptsList **lists, const char *group, { int i; + qemu_load_module_for_opts(group); for (i = 0; lists[i] != NULL; i++) { if (strcmp(lists[i]->name, group) == 0) break; diff --git a/util/trace-events b/util/trace-events index bac0924899..806cac14a7 100644 --- a/util/trace-events +++ b/util/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # aio-posix.c run_poll_handlers_begin(void *ctx, int64_t max_ns, int64_t timeout) "ctx %p max_ns %"PRId64 " timeout %"PRId64 |