tests/qtest: migration-test: Add tests for file-based migration

Add basic tests for file-based migration.

Signed-off-by: Fabiano Rosas <farosas@suse.de>

.gitlab-ci.d/base.yml

@@ -68,7 +68,7 @@ variables:
 
     #############################################################
     # Stage 2: fine tune execution of jobs in specific scenarios
-    # where the catch all logic is inappropriate
+    # where the catch all logic is inapprorpaite
     #############################################################
 
     # Optional jobs should not be run unless manually triggered

.gitlab-ci.d/buildtest-template.yml

@@ -2,21 +2,11 @@
   extends: .base_job_template
   stage: build
   image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
-  cache:
-    paths:
-      - ccache
-    key: "$CI_JOB_NAME"
-    when: always
   before_script:
     - JOBS=$(expr $(nproc) + 1)
   script:
-    - export CCACHE_BASEDIR="$(pwd)"
-    - export CCACHE_DIR="$CCACHE_BASEDIR/ccache"
-    - export CCACHE_MAXSIZE="500M"
-    - export PATH="$CCACHE_WRAPPERSDIR:$PATH"
     - mkdir build
     - cd build
-    - ccache --zero-stats
     - ../configure --enable-werror --disable-docs --enable-fdt=system
           ${TARGETS:+--target-list="$TARGETS"}
           $CONFIGURE_ARGS ||
@@ -30,13 +20,11 @@
       then
         make -j"$JOBS" $MAKE_CHECK_ARGS ;
       fi
-    - ccache --show-stats
 
 # We jump some hoops in common_test_job_template to avoid
 # rebuilding all the object files we skip in the artifacts
 .native_build_artifact_template:
   artifacts:
-    when: on_success
     expire_in: 2 days
     paths:
       - build
@@ -65,7 +53,6 @@
   extends: .common_test_job_template
   artifacts:
     name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
-    when: always
     expire_in: 7 days
     paths:
       - build/meson-logs/testlog.txt
@@ -81,7 +68,7 @@
     policy: pull-push
   artifacts:
     name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
-    when: always
+    when: on_failure
     expire_in: 7 days
     paths:
       - build/tests/results/latest/results.xml

.gitlab-ci.d/buildtest.yml

@@ -30,7 +30,6 @@ avocado-system-alpine:
   variables:
     IMAGE: alpine
     MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:avr arch:loongarch64 arch:mips64 arch:mipsel
 
 build-system-ubuntu:
   extends:
@@ -41,7 +40,8 @@ build-system-ubuntu:
   variables:
     IMAGE: ubuntu2204
     CONFIGURE_ARGS: --enable-docs
-    TARGETS: alpha-softmmu microblaze-softmmu mips64el-softmmu
+    TARGETS: alpha-softmmu cris-softmmu hppa-softmmu
+      microblazeel-softmmu mips64el-softmmu
     MAKE_CHECK_ARGS: check-build
 
 check-system-ubuntu:
@@ -61,7 +61,6 @@ avocado-system-ubuntu:
   variables:
     IMAGE: ubuntu2204
     MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:alpha arch:microblaze arch:mips64el
 
 build-system-debian:
   extends:
@@ -70,10 +69,10 @@ build-system-debian:
   needs:
     job: amd64-debian-container
   variables:
-    IMAGE: debian
+    IMAGE: debian-amd64
     CONFIGURE_ARGS: --with-coroutine=sigaltstack
     TARGETS: arm-softmmu i386-softmmu riscv64-softmmu sh4eb-softmmu
-      sparc-softmmu xtensa-softmmu
+      sparc-softmmu xtensaeb-softmmu
     MAKE_CHECK_ARGS: check-build
 
 check-system-debian:
@@ -82,7 +81,7 @@ check-system-debian:
     - job: build-system-debian
       artifacts: true
   variables:
-    IMAGE: debian
+    IMAGE: debian-amd64
     MAKE_CHECK_ARGS: check
 
 avocado-system-debian:
@@ -91,9 +90,8 @@ avocado-system-debian:
     - job: build-system-debian
       artifacts: true
   variables:
-    IMAGE: debian
+    IMAGE: debian-amd64
     MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:arm arch:i386 arch:riscv64 arch:sh4 arch:sparc arch:xtensa
 
 crash-test-debian:
   extends: .native_test_job_template
@@ -101,11 +99,11 @@ crash-test-debian:
     - job: build-system-debian
       artifacts: true
   variables:
-    IMAGE: debian
+    IMAGE: debian-amd64
   script:
     - cd build
     - make NINJA=":" check-venv
-    - pyvenv/bin/python3 scripts/device-crash-test -q --tcg-only ./qemu-system-i386
+    - tests/venv/bin/python3 scripts/device-crash-test -q --tcg-only ./qemu-system-i386
 
 build-system-fedora:
   extends:
@@ -116,7 +114,7 @@ build-system-fedora:
   variables:
     IMAGE: fedora
     CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs
-    TARGETS: microblaze-softmmu mips-softmmu
+    TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu
       xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu
     MAKE_CHECK_ARGS: check-build
 
@@ -137,8 +135,6 @@ avocado-system-fedora:
   variables:
     IMAGE: fedora
     MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:microblaze arch:mips arch:xtensa arch:m68k
-      arch:riscv32 arch:ppc arch:sparc64
 
 crash-test-fedora:
   extends: .native_test_job_template
@@ -150,8 +146,8 @@ crash-test-fedora:
   script:
     - cd build
     - make NINJA=":" check-venv
-    - pyvenv/bin/python3 scripts/device-crash-test -q ./qemu-system-ppc
-    - pyvenv/bin/python3 scripts/device-crash-test -q ./qemu-system-riscv32
+    - tests/venv/bin/python3 scripts/device-crash-test -q ./qemu-system-ppc
+    - tests/venv/bin/python3 scripts/device-crash-test -q ./qemu-system-riscv32
 
 build-system-centos:
   extends:
@@ -184,8 +180,6 @@ avocado-system-centos:
   variables:
     IMAGE: centos8
     MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:ppc64 arch:or1k arch:390x arch:x86_64 arch:rx
-      arch:sh4 arch:nios2
 
 build-system-opensuse:
   extends:
@@ -215,38 +209,7 @@ avocado-system-opensuse:
   variables:
     IMAGE: opensuse-leap
     MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:s390x arch:x86_64 arch:aarch64
 
-#
-# Flaky tests. We don't run these by default and they are allow fail
-# but often the CI system is the only way to trigger the failures.
-#
-
-build-system-flaky:
-  extends:
-    - .native_build_job_template
-    - .native_build_artifact_template
-  needs:
-    job: amd64-debian-container
-  variables:
-    IMAGE: debian
-    QEMU_JOB_OPTIONAL: 1
-    TARGETS: aarch64-softmmu arm-softmmu mips64el-softmmu
-      ppc64-softmmu rx-softmmu s390x-softmmu sh4-softmmu x86_64-softmmu
-    MAKE_CHECK_ARGS: check-build
-
-avocado-system-flaky:
-  extends: .avocado_test_job_template
-  needs:
-    - job: build-system-flaky
-      artifacts: true
-  allow_failure: true
-  variables:
-    IMAGE: debian
-    MAKE_CHECK_ARGS: check-avocado
-    QEMU_JOB_OPTIONAL: 1
-    QEMU_TEST_FLAKY_TESTS: 1
-    AVOCADO_TAGS: flaky
 
 # This jobs explicitly disable TCG (--disable-tcg), KVM is detected by
 # the configure script. The container doesn't contain Xen headers so
@@ -286,7 +249,6 @@ build-user:
   variables:
     IMAGE: debian-all-test-cross
     CONFIGURE_ARGS: --disable-tools --disable-system
-      --target-list-exclude=alpha-linux-user,sh4-linux-user
     MAKE_CHECK_ARGS: check-tcg
 
 build-user-static:
@@ -296,18 +258,6 @@ build-user-static:
   variables:
     IMAGE: debian-all-test-cross
     CONFIGURE_ARGS: --disable-tools --disable-system --static
-      --target-list-exclude=alpha-linux-user,sh4-linux-user
-    MAKE_CHECK_ARGS: check-tcg
-
-# targets stuck on older compilers
-build-legacy:
-  extends: .native_build_job_template
-  needs:
-    job: amd64-debian-legacy-cross-container
-  variables:
-    IMAGE: debian-legacy-test-cross
-    TARGETS: alpha-linux-user alpha-softmmu sh4-linux-user
-    CONFIGURE_ARGS: --disable-tools
     MAKE_CHECK_ARGS: check-tcg
 
 build-user-hexagon:
@@ -320,9 +270,7 @@ build-user-hexagon:
     CONFIGURE_ARGS: --disable-tools --disable-docs --enable-debug-tcg
     MAKE_CHECK_ARGS: check-tcg
 
-# Build the softmmu targets we have check-tcg tests and compilers in
-# our omnibus all-test-cross container. Those targets that haven't got
-# Debian cross compiler support need to use special containers.
+# Only build the softmmu targets we have check-tcg tests for
 build-some-softmmu:
   extends: .native_build_job_template
   needs:
@@ -330,18 +278,7 @@ build-some-softmmu:
   variables:
     IMAGE: debian-all-test-cross
     CONFIGURE_ARGS: --disable-tools --enable-debug
-    TARGETS: arm-softmmu aarch64-softmmu i386-softmmu riscv64-softmmu
-      s390x-softmmu x86_64-softmmu
-    MAKE_CHECK_ARGS: check-tcg
-
-build-loongarch64:
-  extends: .native_build_job_template
-  needs:
-    job: loongarch-debian-cross-container
-  variables:
-    IMAGE: debian-loongarch-cross
-    CONFIGURE_ARGS: --disable-tools --enable-debug
-    TARGETS: loongarch64-linux-user loongarch64-softmmu
+    TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu
     MAKE_CHECK_ARGS: check-tcg
 
 # We build tricore in a very minimal tricore only container
@@ -374,7 +311,7 @@ clang-user:
   variables:
     IMAGE: debian-all-test-cross
     CONFIGURE_ARGS: --cc=clang --cxx=clang++ --disable-system
-      --target-list-exclude=alpha-linux-user,microblazeel-linux-user,aarch64_be-linux-user,i386-linux-user,m68k-linux-user,mipsn32el-linux-user,xtensaeb-linux-user
+      --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
 
@@ -517,7 +454,7 @@ gcov:
     IMAGE: ubuntu2204
     CONFIGURE_ARGS: --enable-gcov
     TARGETS: aarch64-softmmu ppc64-softmmu s390x-softmmu x86_64-softmmu
-    MAKE_CHECK_ARGS: check-unit check-softfloat
+    MAKE_CHECK_ARGS: check
   after_script:
     - cd build
     - gcovr --xml-pretty --exclude-unreachable-branches --print-summary
@@ -525,12 +462,8 @@ gcov:
   coverage: /^\s*lines:\s*\d+.\d+\%/
   artifacts:
     name: ${CI_JOB_NAME}-${CI_COMMIT_REF_NAME}-${CI_COMMIT_SHA}
-    when: always
     expire_in: 2 days
-    paths:
-      - build/meson-logs/testlog.txt
     reports:
-      junit: build/meson-logs/testlog.junit.xml
       coverage_report:
         coverage_format: cobertura
         path: build/coverage.xml
@@ -561,7 +494,7 @@ build-tci:
   variables:
     IMAGE: debian-all-test-cross
   script:
-    - TARGETS="aarch64 arm hppa m68k microblaze ppc64 s390x x86_64"
+    - TARGETS="aarch64 alpha arm hppa m68k microblaze ppc64 s390x x86_64"
     - mkdir build
     - cd build
     - ../configure --enable-tcg-interpreter --disable-docs --disable-gtk --disable-vnc
@@ -619,7 +552,7 @@ build-tools-and-docs-debian:
     # when running on 'master' we use pre-existing container
     optional: true
   variables:
-    IMAGE: debian
+    IMAGE: debian-amd64
     MAKE_CHECK_ARGS: check-unit ctags TAGS cscope
     CONFIGURE_ARGS: --disable-system --disable-user --enable-docs --enable-tools
     QEMU_JOB_PUBLISH: 1
@@ -639,7 +572,7 @@ build-tools-and-docs-debian:
 # of what topic branch they're currently using
 pages:
   extends: .base_job_template
-  image: $CI_REGISTRY_IMAGE/qemu/debian:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:$QEMU_CI_CONTAINER_TAG
   stage: test
   needs:
     - job: build-tools-and-docs-debian
@@ -647,17 +580,13 @@ pages:
     - mkdir -p public
     # HTML-ised source tree
     - make gtags
-    # We unset variables to work around a bug in some htags versions
-    # which causes it to fail when the environment is large
-    - CI_COMMIT_MESSAGE= CI_COMMIT_TAG_MESSAGE= htags
-        -anT --tree-view=filetree -m qemu_init
+    - 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:
-    when: on_success
     paths:
       - public
   variables:

.gitlab-ci.d/cirrus.yml

@@ -15,10 +15,8 @@
   stage: build
   image: registry.gitlab.com/libvirt/libvirt-ci/cirrus-run:master
   needs: []
-  # 20 mins larger than "timeout_in" in cirrus/build.yml
-  # as there's often a 5-10 minute delay before Cirrus CI
-  # actually starts the task
   timeout: 80m
+  allow_failure: true
   script:
     - source .gitlab-ci.d/cirrus/$NAME.vars
     - sed -e "s|[@]CI_REPOSITORY_URL@|$CI_REPOSITORY_URL|g"
@@ -52,20 +50,20 @@ x64-freebsd-13-build:
     NAME: freebsd-13
     CIRRUS_VM_INSTANCE_TYPE: freebsd_instance
     CIRRUS_VM_IMAGE_SELECTOR: image_family
-    CIRRUS_VM_IMAGE_NAME: freebsd-13-2
+    CIRRUS_VM_IMAGE_NAME: freebsd-13-1
     CIRRUS_VM_CPUS: 8
     CIRRUS_VM_RAM: 8G
     UPDATE_COMMAND: pkg update; pkg upgrade -y
     INSTALL_COMMAND: pkg install -y
     TEST_TARGETS: check
 
-aarch64-macos-13-base-build:
+aarch64-macos-12-base-build:
   extends: .cirrus_build_job
   variables:
-    NAME: macos-13
+    NAME: macos-12
     CIRRUS_VM_INSTANCE_TYPE: macos_instance
     CIRRUS_VM_IMAGE_SELECTOR: image
-    CIRRUS_VM_IMAGE_NAME: ghcr.io/cirruslabs/macos-ventura-base:latest
+    CIRRUS_VM_IMAGE_NAME: ghcr.io/cirruslabs/macos-monterey-base:latest
     CIRRUS_VM_CPUS: 12
     CIRRUS_VM_RAM: 24G
     UPDATE_COMMAND: brew update
@@ -74,22 +72,6 @@ aarch64-macos-13-base-build:
     PKG_CONFIG_PATH: /opt/homebrew/curl/lib/pkgconfig:/opt/homebrew/ncurses/lib/pkgconfig:/opt/homebrew/readline/lib/pkgconfig
     TEST_TARGETS: check-unit check-block check-qapi-schema check-softfloat check-qtest-x86_64
 
-aarch64-macos-14-base-build:
-  extends: .cirrus_build_job
-  variables:
-    NAME: macos-14
-    CIRRUS_VM_INSTANCE_TYPE: macos_instance
-    CIRRUS_VM_IMAGE_SELECTOR: image
-    CIRRUS_VM_IMAGE_NAME: ghcr.io/cirruslabs/macos-sonoma-base:latest
-    CIRRUS_VM_CPUS: 12
-    CIRRUS_VM_RAM: 24G
-    UPDATE_COMMAND: brew update
-    INSTALL_COMMAND: brew install
-    PATH_EXTRA: /opt/homebrew/ccache/libexec:/opt/homebrew/gettext/bin
-    PKG_CONFIG_PATH: /opt/homebrew/curl/lib/pkgconfig:/opt/homebrew/ncurses/lib/pkgconfig:/opt/homebrew/readline/lib/pkgconfig
-    TEST_TARGETS: check-unit check-block check-qapi-schema check-softfloat check-qtest-x86_64
-    QEMU_JOB_OPTIONAL: 1
-
 
 # The following jobs run VM-based tests via KVM on a Linux-based Cirrus-CI job
 .cirrus_kvm_job:

.gitlab-ci.d/cirrus/build.yml

@@ -16,12 +16,10 @@ env:
   TEST_TARGETS: "@TEST_TARGETS@"
 
 build_task:
-  # A little shorter than GitLab timeout in ../cirrus.yml
-  timeout_in: 60m
   install_script:
     - @UPDATE_COMMAND@
     - @INSTALL_COMMAND@ @PKGS@
-    - if test -n "@PYPI_PKGS@" ; then PYLIB=$(@PYTHON@ -c 'import sysconfig; print(sysconfig.get_path("stdlib"))'); rm -f $PYLIB/EXTERNALLY-MANAGED; @PIP3@ install @PYPI_PKGS@ ; fi
+    - if test -n "@PYPI_PKGS@" ; then @PIP3@ install @PYPI_PKGS@ ; fi
   clone_script:
     - git clone --depth 100 "$CI_REPOSITORY_URL" .
     - git fetch origin "$CI_COMMIT_REF_NAME"

.gitlab-ci.d/cirrus/freebsd-13.vars

@@ -11,6 +11,6 @@ MAKE='/usr/local/bin/gmake'
 NINJA='/usr/local/bin/ninja'
 PACKAGING_COMMAND='pkg'
 PIP3='/usr/local/bin/pip-3.8'
-PKGS='alsa-lib bash bison bzip2 ca_root_nss capstone4 ccache cmocka ctags curl cyrus-sasl dbus diffutils dtc flex fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 json-c libepoxy libffi libgcrypt libjpeg-turbo libnfs libslirp libspice-server libssh libtasn1 llvm lzo2 meson mtools ncurses nettle ninja opencv pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-tomli py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy sndio socat spice-protocol tesseract usbredir virglrenderer vte3 xorriso zstd'
+PKGS='alsa-lib bash bison bzip2 ca_root_nss capstone4 ccache cmocka ctags curl cyrus-sasl dbus diffutils dtc flex fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 json-c libepoxy libffi libgcrypt libjpeg-turbo libnfs libslirp libspice-server libssh libtasn1 llvm lzo2 meson mtools ncurses nettle ninja opencv pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy sndio socat spice-protocol tesseract usbredir virglrenderer vte3 xorriso zstd'
 PYPI_PKGS=''
 PYTHON='/usr/local/bin/python3'

.gitlab-ci.d/cirrus/kvm-build.yml

@@ -15,7 +15,7 @@ env:
     folder: $HOME/.cache/qemu-vm
   install_script:
     - dnf update -y
-    - dnf install -y git make openssh-clients qemu-img qemu-system-x86 wget meson
+    - dnf install -y git make openssh-clients qemu-img qemu-system-x86 wget
   clone_script:
     - git clone --depth 100 "$CI_REPOSITORY_URL" .
     - git fetch origin "$CI_COMMIT_REF_NAME"

.gitlab-ci.d/cirrus/macos-12.vars

@@ -1,6 +1,6 @@
 # THIS FILE WAS AUTO-GENERATED
 #
-#  $ lcitool variables macos-13 qemu
+#  $ lcitool variables macos-12 qemu
 #
 # https://gitlab.com/libvirt/libvirt-ci
 
@@ -11,6 +11,6 @@ MAKE='/opt/homebrew/bin/gmake'
 NINJA='/opt/homebrew/bin/ninja'
 PACKAGING_COMMAND='brew'
 PIP3='/opt/homebrew/bin/pip3'
-PKGS='bash bc bison bzip2 capstone ccache cmocka ctags curl dbus diffutils dtc flex gcovr gettext git glib gnu-sed gnutls gtk+3 jemalloc jpeg-turbo json-c libepoxy libffi libgcrypt libiscsi libnfs libpng libslirp libssh libtasn1 libusb llvm lzo make meson mtools ncurses nettle ninja pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy socat sparse spice-protocol swtpm tesseract usbredir vde vte3 xorriso zlib zstd'
-PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme tomli'
+PKGS='bash bc bison bzip2 capstone ccache cmocka ctags curl dbus diffutils dtc flex gcovr gettext git glib gnu-sed gnutls gtk+3 jemalloc jpeg-turbo json-c libepoxy libffi libgcrypt libiscsi libnfs libpng libslirp libssh libtasn1 libusb llvm lzo make meson mtools ncurses nettle ninja pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy socat sparse spice-protocol tesseract usbredir vde vte3 xorriso zlib zstd'
+PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme'
 PYTHON='/opt/homebrew/bin/python3'

.gitlab-ci.d/cirrus/macos-14.vars

@@ -1,16 +0,0 @@
-# THIS FILE WAS AUTO-GENERATED
-#
-#  $ lcitool variables macos-14 qemu
-#
-# https://gitlab.com/libvirt/libvirt-ci
-
-CCACHE='/opt/homebrew/bin/ccache'
-CPAN_PKGS=''
-CROSS_PKGS=''
-MAKE='/opt/homebrew/bin/gmake'
-NINJA='/opt/homebrew/bin/ninja'
-PACKAGING_COMMAND='brew'
-PIP3='/opt/homebrew/bin/pip3'
-PKGS='bash bc bison bzip2 capstone ccache cmocka ctags curl dbus diffutils dtc flex gcovr gettext git glib gnu-sed gnutls gtk+3 jemalloc jpeg-turbo json-c libepoxy libffi libgcrypt libiscsi libnfs libpng libslirp libssh libtasn1 libusb llvm lzo make meson mtools ncurses nettle ninja pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy socat sparse spice-protocol swtpm tesseract usbredir vde vte3 xorriso zlib zstd'
-PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme tomli'
-PYTHON='/opt/homebrew/bin/python3'

.gitlab-ci.d/container-cross.yml

@@ -1,3 +1,9 @@
+alpha-debian-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-alpha-cross
+
 amd64-debian-cross-container:
   extends: .container_job_template
   stage: containers
@@ -10,12 +16,6 @@ amd64-debian-user-cross-container:
   variables:
     NAME: debian-all-test-cross
 
-amd64-debian-legacy-cross-container:
-  extends: .container_job_template
-  stage: containers
-  variables:
-    NAME: debian-legacy-test-cross
-
 arm64-debian-cross-container:
   extends: .container_job_template
   stage: containers
@@ -40,17 +40,23 @@ hexagon-cross-container:
   variables:
     NAME: debian-hexagon-cross
 
-loongarch-debian-cross-container:
+hppa-debian-cross-container:
   extends: .container_job_template
   stage: containers
   variables:
-    NAME: debian-loongarch-cross
+    NAME: debian-hppa-cross
 
-i686-debian-cross-container:
+m68k-debian-cross-container:
   extends: .container_job_template
   stage: containers
   variables:
-    NAME: debian-i686-cross
+    NAME: debian-m68k-cross
+
+mips64-debian-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-mips64-cross
 
 mips64el-debian-cross-container:
   extends: .container_job_template
@@ -58,12 +64,24 @@ mips64el-debian-cross-container:
   variables:
     NAME: debian-mips64el-cross
 
+mips-debian-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-mips-cross
+
 mipsel-debian-cross-container:
   extends: .container_job_template
   stage: containers
   variables:
     NAME: debian-mipsel-cross
 
+powerpc-test-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-powerpc-test-cross
+
 ppc64el-debian-cross-container:
   extends: .container_job_template
   stage: containers
@@ -77,7 +95,13 @@ riscv64-debian-cross-container:
   allow_failure: true
   variables:
     NAME: debian-riscv64-cross
-    QEMU_JOB_OPTIONAL: 1
+
+# we can however build TCG tests using a non-sid base
+riscv64-debian-test-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-riscv64-test-cross
 
 s390x-debian-cross-container:
   extends: .container_job_template
@@ -85,6 +109,18 @@ s390x-debian-cross-container:
   variables:
     NAME: debian-s390x-cross
 
+sh4-debian-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-sh4-cross
+
+sparc64-debian-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    NAME: debian-sparc64-cross
+
 tricore-debian-cross-container:
   extends: .container_job_template
   stage: containers
@@ -101,6 +137,11 @@ cris-fedora-cross-container:
   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:

.gitlab-ci.d/containers.yml

@@ -11,7 +11,7 @@ amd64-debian-container:
   extends: .container_job_template
   stage: containers
   variables:
-    NAME: debian
+    NAME: debian-amd64
 
 amd64-ubuntu2204-container:
   extends: .container_job_template

.gitlab-ci.d/crossbuild-template.yml

@@ -2,20 +2,10 @@
   extends: .base_job_template
   stage: build
   image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
-  cache:
-    paths:
-      - ccache
-    key: "$CI_JOB_NAME"
-    when: always
   timeout: 80m
   script:
-    - export CCACHE_BASEDIR="$(pwd)"
-    - export CCACHE_DIR="$CCACHE_BASEDIR/ccache"
-    - export CCACHE_MAXSIZE="500M"
-    - export PATH="$CCACHE_WRAPPERSDIR:$PATH"
     - mkdir build
     - cd build
-    - ccache --zero-stats
     - ../configure --enable-werror --disable-docs --enable-fdt=system
         --disable-user $QEMU_CONFIGURE_OPTS $EXTRA_CONFIGURE_OPTS
         --target-list-exclude="arm-softmmu cris-softmmu
@@ -28,7 +18,6 @@
       version="$(git describe --match v[0-9]* 2>/dev/null || git rev-parse --short HEAD)";
       mv -v qemu-setup*.exe qemu-setup-${version}.exe;
       fi
-    - ccache --show-stats
 
 # Job to cross-build specific accelerators.
 #
@@ -40,15 +29,7 @@
   stage: build
   image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
   timeout: 30m
-  cache:
-    paths:
-      - ccache/
-    key: "$CI_JOB_NAME"
   script:
-    - export CCACHE_BASEDIR="$(pwd)"
-    - export CCACHE_DIR="$CCACHE_BASEDIR/ccache"
-    - export CCACHE_MAXSIZE="500M"
-    - export PATH="$CCACHE_WRAPPERSDIR:$PATH"
     - mkdir build
     - cd build
     - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS
@@ -59,14 +40,7 @@
   extends: .base_job_template
   stage: build
   image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
-  cache:
-    paths:
-      - ccache/
-    key: "$CI_JOB_NAME"
   script:
-    - export CCACHE_BASEDIR="$(pwd)"
-    - export CCACHE_DIR="$CCACHE_BASEDIR/ccache"
-    - export CCACHE_MAXSIZE="500M"
     - mkdir build
     - cd build
     - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS
@@ -81,7 +55,6 @@
 .cross_test_artifacts:
   artifacts:
     name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
-    when: always
     expire_in: 7 days
     paths:
       - build/meson-logs/testlog.txt

.gitlab-ci.d/crossbuilds.yml

@@ -37,25 +37,25 @@ cross-arm64-kvm-only:
     IMAGE: debian-arm64-cross
     EXTRA_CONFIGURE_OPTS: --disable-tcg --without-default-features
 
-cross-i686-user:
+cross-i386-user:
   extends:
     - .cross_user_build_job
     - .cross_test_artifacts
   needs:
-    job: i686-debian-cross-container
+    job: i386-fedora-cross-container
   variables:
-    IMAGE: debian-i686-cross
+    IMAGE: fedora-i386-cross
     MAKE_CHECK_ARGS: check
 
-cross-i686-tci:
+cross-i386-tci:
   extends:
     - .cross_accel_build_job
     - .cross_test_artifacts
   timeout: 60m
   needs:
-    job: i686-debian-cross-container
+    job: i386-fedora-cross-container
   variables:
-    IMAGE: debian-i686-cross
+    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 --disable-plugins
     MAKE_CHECK_ARGS: check check-tcg
@@ -169,7 +169,6 @@ cross-win32-system:
     CROSS_SKIP_TARGETS: alpha-softmmu avr-softmmu hppa-softmmu m68k-softmmu
                         microblazeel-softmmu mips64el-softmmu nios2-softmmu
   artifacts:
-    when: on_success
     paths:
       - build/qemu-setup*.exe
 
@@ -179,13 +178,12 @@ cross-win64-system:
     job: win64-fedora-cross-container
   variables:
     IMAGE: fedora-win64-cross
-    EXTRA_CONFIGURE_OPTS: --enable-fdt=internal --disable-plugins
+    EXTRA_CONFIGURE_OPTS: --enable-fdt=internal
     CROSS_SKIP_TARGETS: alpha-softmmu avr-softmmu hppa-softmmu
                         m68k-softmmu microblazeel-softmmu nios2-softmmu
                         or1k-softmmu rx-softmmu sh4eb-softmmu sparc64-softmmu
                         tricore-softmmu xtensaeb-softmmu
   artifacts:
-    when: on_success
     paths:
       - build/qemu-setup*.exe
 

.gitlab-ci.d/opensbi.yml

@@ -63,7 +63,6 @@ build-opensbi:
   stage: build
   needs: ['docker-opensbi']
   artifacts:
-    when: on_success
     paths: # 'artifacts.zip' will contains the following files:
       - pc-bios/opensbi-riscv32-generic-fw_dynamic.bin
       - pc-bios/opensbi-riscv64-generic-fw_dynamic.bin

.gitlab-ci.d/windows.yml

@@ -5,18 +5,12 @@
   - windows
   - windows-1809
   cache:
-    key: "$CI_JOB_NAME"
+    key: "${CI_JOB_NAME}-cache"
     paths:
-      - msys64/var/cache
-      - ccache
-    when: always
+      - ${CI_PROJECT_DIR}/msys64/var/cache
   needs: []
   stage: build
-  timeout: 100m
-  variables:
-    # This feature doesn't (currently) work with PowerShell, it stops
-    # the echo'ing of commands being run and doesn't show any timing
-    FF_SCRIPT_SECTIONS: 0
+  timeout: 80m
   artifacts:
     name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
     expire_in: 7 days
@@ -25,40 +19,14 @@
     reports:
       junit: "build/meson-logs/testlog.junit.xml"
   before_script:
-  - Write-Output "Acquiring msys2.exe installer at $(Get-Date -Format u)"
   - If ( !(Test-Path -Path msys64\var\cache ) ) {
       mkdir msys64\var\cache
     }
-  - Invoke-WebRequest
-    "https://repo.msys2.org/distrib/msys2-x86_64-latest.sfx.exe.sig"
-    -outfile "msys2.exe.sig"
-  - if ( Test-Path -Path msys64\var\cache\msys2.exe.sig ) {
-      Write-Output "Cached installer sig" ;
-      if ( ((Get-FileHash msys2.exe.sig).Hash -ne (Get-FileHash msys64\var\cache\msys2.exe.sig).Hash) ) {
-        Write-Output "Mis-matched installer sig, new installer download required" ;
-        Remove-Item -Path msys64\var\cache\msys2.exe.sig ;
-        if ( Test-Path -Path msys64\var\cache\msys2.exe ) {
-          Remove-Item -Path msys64\var\cache\msys2.exe
-        }
-      } else {
-        Write-Output "Matched installer sig, cached installer still valid"
-      }
-    } else {
-      Write-Output "No cached installer sig, new installer download required" ;
-      if ( Test-Path -Path msys64\var\cache\msys2.exe ) {
-        Remove-Item -Path msys64\var\cache\msys2.exe
-      }
-    }
-  - if ( !(Test-Path -Path msys64\var\cache\msys2.exe ) ) {
-      Write-Output "Fetching latest installer" ;
+  - If ( !(Test-Path -Path msys64\var\cache\msys2.exe ) ) {
       Invoke-WebRequest
-      "https://repo.msys2.org/distrib/msys2-x86_64-latest.sfx.exe"
-      -outfile "msys64\var\cache\msys2.exe" ;
-      Copy-Item -Path msys2.exe.sig -Destination msys64\var\cache\msys2.exe.sig
-    } else {
-      Write-Output "Using cached installer"
+      "https://github.com/msys2/msys2-installer/releases/download/2022-06-03/msys2-base-x86_64-20220603.sfx.exe"
+      -outfile "msys64\var\cache\msys2.exe"
     }
-  - Write-Output "Invoking msys2.exe installer at $(Get-Date -Format u)"
   - msys64\var\cache\msys2.exe -y
   - ((Get-Content -path .\msys64\etc\\post-install\\07-pacman-key.post -Raw)
       -replace '--refresh-keys', '--version') |
@@ -67,67 +35,97 @@
   - .\msys64\usr\bin\bash -lc 'pacman --noconfirm -Syuu'  # Core update
   - .\msys64\usr\bin\bash -lc 'pacman --noconfirm -Syuu'  # Normal update
   - taskkill /F /FI "MODULES eq msys-2.0.dll"
-  script:
-  - Write-Output "Installing mingw packages at $(Get-Date -Format u)"
-  - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed
-      bison diffutils flex
-      git grep make sed
-      $MINGW_TARGET-binutils
-      $MINGW_TARGET-capstone
-      $MINGW_TARGET-ccache
-      $MINGW_TARGET-curl
-      $MINGW_TARGET-cyrus-sasl
-      $MINGW_TARGET-dtc
-      $MINGW_TARGET-gcc
-      $MINGW_TARGET-glib2
-      $MINGW_TARGET-gnutls
-      $MINGW_TARGET-gtk3
-      $MINGW_TARGET-libgcrypt
-      $MINGW_TARGET-libjpeg-turbo
-      $MINGW_TARGET-libnfs
-      $MINGW_TARGET-libpng
-      $MINGW_TARGET-libssh
-      $MINGW_TARGET-libtasn1
-      $MINGW_TARGET-lzo2
-      $MINGW_TARGET-nettle
-      $MINGW_TARGET-ninja
-      $MINGW_TARGET-pixman
-      $MINGW_TARGET-pkgconf
-      $MINGW_TARGET-python
-      $MINGW_TARGET-SDL2
-      $MINGW_TARGET-SDL2_image
-      $MINGW_TARGET-snappy
-      $MINGW_TARGET-zstd
-      $EXTRA_PACKAGES "
-  - Write-Output "Running build at $(Get-Date -Format u)"
-  - $env:CHERE_INVOKING = 'yes'  # Preserve the current working directory
-  - $env:MSYS = 'winsymlinks:native' # Enable native Windows symlink
-  - $env:CCACHE_BASEDIR = "$env:CI_PROJECT_DIR"
-  - $env:CCACHE_DIR = "$env:CCACHE_BASEDIR/ccache"
-  - $env:CCACHE_MAXSIZE = "500M"
-  - $env:CCACHE_DEPEND = 1 # cache misses are too expensive with preprocessor mode
-  - $env:CC = "ccache gcc"
-  - mkdir build
-  - cd build
-  - ..\msys64\usr\bin\bash -lc "ccache --zero-stats"
-  - ..\msys64\usr\bin\bash -lc "../configure --enable-fdt=system $CONFIGURE_ARGS"
-  - ..\msys64\usr\bin\bash -lc "make"
-  - ..\msys64\usr\bin\bash -lc "make check MTESTARGS='$TEST_ARGS' || { cat meson-logs/testlog.txt; exit 1; } ;"
-  - ..\msys64\usr\bin\bash -lc "ccache --show-stats"
-  - Write-Output "Finished build at $(Get-Date -Format u)"
 
 msys2-64bit:
   extends: .shared_msys2_builder
-  variables:
-    MINGW_TARGET: mingw-w64-x86_64
-    MSYSTEM: MINGW64
-    # msys2 only ship these packages for 64-bit, not 32-bit
-    EXTRA_PACKAGES: $MINGW_TARGET-libusb $MINGW_TARGET-usbredir $MINGW_TARGET-spice
-    # do not remove "--without-default-devices"!
-    # commit 9f8e6cad65a6 ("gitlab-ci: Speed up the msys2-64bit job by using --without-default-devices"
-    # changed to compile QEMU with the --without-default-devices switch
-    # for the msys2 64-bit job, due to the build could not complete within
-    CONFIGURE_ARGS:  --target-list=x86_64-softmmu --without-default-devices -Ddebug=false -Doptimization=0
-    # qTests don't run successfully with "--without-default-devices",
-    # so let's exclude the qtests from CI for now.
-    TEST_ARGS: --no-suite qtest
+  script:
+  - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed
+      bison diffutils flex
+      git grep make sed
+      mingw-w64-x86_64-capstone
+      mingw-w64-x86_64-curl
+      mingw-w64-x86_64-cyrus-sasl
+      mingw-w64-x86_64-dtc
+      mingw-w64-x86_64-gcc
+      mingw-w64-x86_64-glib2
+      mingw-w64-x86_64-gnutls
+      mingw-w64-x86_64-gtk3
+      mingw-w64-x86_64-libgcrypt
+      mingw-w64-x86_64-libjpeg-turbo
+      mingw-w64-x86_64-libnfs
+      mingw-w64-x86_64-libpng
+      mingw-w64-x86_64-libssh
+      mingw-w64-x86_64-libtasn1
+      mingw-w64-x86_64-libusb
+      mingw-w64-x86_64-lzo2
+      mingw-w64-x86_64-nettle
+      mingw-w64-x86_64-ninja
+      mingw-w64-x86_64-pixman
+      mingw-w64-x86_64-pkgconf
+      mingw-w64-x86_64-python
+      mingw-w64-x86_64-SDL2
+      mingw-w64-x86_64-SDL2_image
+      mingw-w64-x86_64-snappy
+      mingw-w64-x86_64-spice
+      mingw-w64-x86_64-usbredir
+      mingw-w64-x86_64-zstd "
+  - $env:CHERE_INVOKING = 'yes'  # Preserve the current working directory
+  - $env:MSYSTEM = 'MINGW64'     # Start a 64-bit MinGW environment
+  - $env:MSYS = 'winsymlinks:native' # Enable native Windows symlink
+  - mkdir build
+  - cd build
+  # Note: do not remove "--without-default-devices"!
+  # commit 9f8e6cad65a6 ("gitlab-ci: Speed up the msys2-64bit job by using --without-default-devices"
+  # changed to compile QEMU with the --without-default-devices switch
+  # for the msys2 64-bit job, due to the build could not complete within
+  # the project timeout.
+  - ..\msys64\usr\bin\bash -lc '../configure --target-list=x86_64-softmmu
+      --without-default-devices --enable-fdt=system'
+  - ..\msys64\usr\bin\bash -lc 'make'
+  # qTests don't run successfully with "--without-default-devices",
+  # so let's exclude the qtests from CI for now.
+  - ..\msys64\usr\bin\bash -lc 'make check MTESTARGS=\"--no-suite qtest\" || { cat meson-logs/testlog.txt; exit 1; } ;'
+
+msys2-32bit:
+  extends: .shared_msys2_builder
+  script:
+  - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed
+      bison diffutils flex
+      git grep make sed
+      mingw-w64-i686-capstone
+      mingw-w64-i686-curl
+      mingw-w64-i686-cyrus-sasl
+      mingw-w64-i686-dtc
+      mingw-w64-i686-gcc
+      mingw-w64-i686-glib2
+      mingw-w64-i686-gnutls
+      mingw-w64-i686-gtk3
+      mingw-w64-i686-libgcrypt
+      mingw-w64-i686-libjpeg-turbo
+      mingw-w64-i686-libnfs
+      mingw-w64-i686-libpng
+      mingw-w64-i686-libssh
+      mingw-w64-i686-libtasn1
+      mingw-w64-i686-libusb
+      mingw-w64-i686-lzo2
+      mingw-w64-i686-nettle
+      mingw-w64-i686-ninja
+      mingw-w64-i686-pixman
+      mingw-w64-i686-pkgconf
+      mingw-w64-i686-python
+      mingw-w64-i686-SDL2
+      mingw-w64-i686-SDL2_image
+      mingw-w64-i686-snappy
+      mingw-w64-i686-spice
+      mingw-w64-i686-usbredir
+      mingw-w64-i686-zstd "
+  - $env:CHERE_INVOKING = 'yes'  # Preserve the current working directory
+  - $env:MSYSTEM = 'MINGW32'     # Start a 32-bit MinGW environment
+  - $env:MSYS = 'winsymlinks:native' # Enable native Windows symlink
+  - mkdir build
+  - cd build
+  - ..\msys64\usr\bin\bash -lc '../configure --target-list=ppc64-softmmu
+                                --enable-fdt=system'
+  - ..\msys64\usr\bin\bash -lc 'make'
+  - ..\msys64\usr\bin\bash -lc 'make check MTESTARGS=\"--no-suite qtest\" ||
+                                { cat meson-logs/testlog.txt; exit 1; }'

.mailmap

@@ -30,38 +30,22 @@ malc <av1474@comtv.ru> malc <malc@c046a42c-6fe2-441c-8c8c-71466251a162>
 # Corrupted Author fields
 Aaron Larson <alarson@ddci.com> alarson@ddci.com
 Andreas Färber <andreas.faerber@web.de> Andreas Färber <andreas.faerber>
-fanwenjie <fanwj@mail.ustc.edu.cn> fanwj@mail.ustc.edu.cn <fanwj@mail.ustc.edu.cn>
 Jason Wang <jasowang@redhat.com> Jason Wang <jasowang>
 Marek Dolata <mkdolata@us.ibm.com> mkdolata@us.ibm.com <mkdolata@us.ibm.com>
 Michael Ellerman <mpe@ellerman.id.au> michael@ozlabs.org <michael@ozlabs.org>
 Nick Hudson <hnick@vmware.com> hnick@vmware.com <hnick@vmware.com>
-Timothée Cocault <timothee.cocault@gmail.com> timothee.cocault@gmail.com <timothee.cocault@gmail.com>
 
 # There is also a:
 #    (no author) <(no author)@c046a42c-6fe2-441c-8c8c-71466251a162>
 # for the cvs2svn initialization commit e63c3dc74bf.
 
 # Next, translate a few commits where mailman rewrote the From: line due
-# to strict SPF and DMARC.  Usually, our build process should be flagging
-# commits like these before maintainer merges; if you find the need to add
-# a line here, please also report a bug against the part of the build
-# process that let the mis-attribution slip through in the first place.
-#
-# If the mailing list munges your emails, use:
-#   git config sendemail.from '"Your Name" <your.email@example.com>'
-# the use of "" in that line will differ from the typically unquoted
-# 'git config user.name', which in turn is sufficient for 'git send-email'
-# to add an extra From: line in the body of your email that takes
-# precedence over any munged From: in the mail's headers.
-# See https://lists.openembedded.org/g/openembedded-core/message/166515
-# and https://lists.gnu.org/archive/html/qemu-devel/2023-09/msg06784.html
+# to strict SPF, although we prefer to avoid adding more entries like that.
 Ed Swierk <eswierk@skyportsystems.com> Ed Swierk via Qemu-devel <qemu-devel@nongnu.org>
 Ian McKellar <ianloic@google.com> Ian McKellar via Qemu-devel <qemu-devel@nongnu.org>
 Julia Suvorova <jusual@mail.ru> Julia Suvorova via Qemu-devel <qemu-devel@nongnu.org>
 Justin Terry (VM) <juterry@microsoft.com> Justin Terry (VM) via Qemu-devel <qemu-devel@nongnu.org>
 Stefan Weil <sw@weilnetz.de> Stefan Weil via <qemu-devel@nongnu.org>
-Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> Andrey Drobyshev via <qemu-block@nongnu.org>
-BALATON Zoltan <balaton@eik.bme.hu> BALATON Zoltan via <qemu-ppc@nongnu.org>
 
 # Next, replace old addresses by a more recent one.
 Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> <aleksandar.markovic@mips.com>
@@ -83,9 +67,6 @@ Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn>
 James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 Leif Lindholm <quic_llindhol@quicinc.com> <leif.lindholm@linaro.org>
 Leif Lindholm <quic_llindhol@quicinc.com> <leif@nuviainc.com>
-Luc Michel <luc@lmichel.fr> <luc.michel@git.antfield.fr>
-Luc Michel <luc@lmichel.fr> <luc.michel@greensocs.com>
-Luc Michel <luc@lmichel.fr> <lmichel@kalray.eu>
 Radoslaw Biernacki <rad@semihalf.com> <radoslaw.biernacki@linaro.org>
 Paul Brook <paul@nowt.org> <paul@codesourcery.com>
 Paul Burton <paulburton@kernel.org> <paul.burton@mips.com>

.readthedocs.yml

@@ -5,21 +5,16 @@
 # Required
 version: 2
 
-# Set the version of Python and other tools you might need
-build:
-  os: ubuntu-22.04
-  tools:
-    python: "3.11"
-
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/conf.py
 
-# We recommend specifying your dependencies to enable reproducible builds:
-# https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
-python:
-  install:
-    - requirements: docs/requirements.txt
-
 # We want all the document formats
 formats: all
+
+# For consistency, we require that QEMU's Sphinx extensions
+# run with at least the same minimum version of Python that
+# we require for other Python in our codebase (our conf.py
+# enforces this, and some code needs it.)
+python:
+  version: 3.6

.travis.yml

@@ -34,7 +34,7 @@ env:
     - BASE_CONFIG="--disable-docs --disable-tools"
     - TEST_BUILD_CMD=""
     - TEST_CMD="make check V=1"
-    # This is broadly a list of "mainline" system targets which have support across the major distros
+    # This is broadly a list of "mainline" softmmu targets which have support across the major distros
     - MAIN_SOFTMMU_TARGETS="aarch64-softmmu,mips64-softmmu,ppc64-softmmu,riscv64-softmmu,s390x-softmmu,x86_64-softmmu"
     - CCACHE_SLOPPINESS="include_file_ctime,include_file_mtime"
     - CCACHE_MAXSIZE=1G
@@ -197,7 +197,7 @@ jobs:
               $(exit $BUILD_RC);
           fi
 
-    - name: "[s390x] GCC (other-system)"
+    - name: "[s390x] GCC (other-softmmu)"
       arch: s390x
       dist: focal
       addons:

Kconfig.host

@@ -11,9 +11,6 @@ config OPENGL
 config X11
     bool
 
-config PIXMAN
-    bool
-
 config SPICE
     bool
 
@@ -49,6 +46,3 @@ config FUZZ
 config VFIO_USER_SERVER_ALLOWED
     bool
     imply VFIO_USER_SERVER
-
-config HV_BALLOON_POSSIBLE
-    bool

Makefile

@@ -28,7 +28,7 @@ quiet-command = $(quiet-@)$(call quiet-command-run,$1,$2,$3)
 
 UNCHECKED_GOALS := TAGS gtags cscope ctags dist \
     help check-help print-% \
-    docker docker-% lcitool-refresh vm-help vm-test vm-build-%
+    docker docker-% vm-help vm-test vm-build-%
 
 all:
 .PHONY: all clean distclean recurse-all dist msi FORCE
@@ -164,6 +164,14 @@ ifneq ($(filter $(ninja-targets), $(ninja-cmd-goals)),)
 endif
 endif
 
+ifeq ($(CONFIG_PLUGIN),y)
+.PHONY: plugins
+plugins:
+	$(call quiet-command,\
+		$(MAKE) $(SUBDIR_MAKEFLAGS) -C contrib/plugins V="$(V)", \
+		"BUILD", "example plugins")
+endif # $(CONFIG_PLUGIN)
+
 else # config-host.mak does not exist
 ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 $(error Please call configure before running make)
@@ -176,20 +184,15 @@ include $(SRC_PATH)/tests/Makefile.include
 
 all: recurse-all
 
-SUBDIR_RULES=$(foreach t, all clean distclean, $(addsuffix /$(t), $(SUBDIRS)))
-.PHONY: $(SUBDIR_RULES)
-$(SUBDIR_RULES):
+ROMS_RULES=$(foreach t, all clean distclean, $(addsuffix /$(t), $(ROMS)))
+.PHONY: $(ROMS_RULES)
+$(ROMS_RULES):
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $(dir $@) V="$(V)" TARGET_DIR="$(dir $@)" $(notdir $@),)
 
-ifneq ($(filter contrib/plugins, $(SUBDIRS)),)
-.PHONY: plugins
-plugins: contrib/plugins/all
-endif
-
 .PHONY: recurse-all recurse-clean
-recurse-all: $(addsuffix /all, $(SUBDIRS))
-recurse-clean: $(addsuffix /clean, $(SUBDIRS))
-recurse-distclean: $(addsuffix /distclean, $(SUBDIRS))
+recurse-all: $(addsuffix /all, $(ROMS))
+recurse-clean: $(addsuffix /clean, $(ROMS))
+recurse-distclean: $(addsuffix /distclean, $(ROMS))
 
 ######################################################################
 
@@ -283,13 +286,6 @@ include $(SRC_PATH)/tests/vm/Makefile.include
 print-help-run = printf "  %-30s - %s\\n" "$1" "$2"
 print-help = @$(call print-help-run,$1,$2)
 
-.PHONY: update-linux-vdso
-update-linux-vdso:
-	@for m in $(SRC_PATH)/linux-user/*/Makefile.vdso; do \
-	  $(MAKE) $(SUBDIR_MAKEFLAGS) -C $$(dirname $$m) -f Makefile.vdso \
-		SRC_PATH=$(SRC_PATH) BUILD_DIR=$(BUILD_DIR); \
-	done
-
 .PHONY: help
 help:
 	@echo  'Generic targets:'
@@ -300,7 +296,7 @@ help:
 	$(call print-help,cscope,Generate cscope index)
 	$(call print-help,sparse,Run sparse on the QEMU source)
 	@echo  ''
-ifneq ($(filter contrib/plugins, $(SUBDIRS)),)
+ifeq ($(CONFIG_PLUGIN),y)
 	@echo  'Plugin targets:'
 	$(call print-help,plugins,Build the example TCG plugins)
 	@echo  ''
@@ -310,9 +306,6 @@ endif
 	$(call print-help,distclean,Remove all generated files)
 	$(call print-help,dist,Build a distributable tarball)
 	@echo  ''
-	@echo  'Linux-user targets:'
-	$(call print-help,update-linux-vdso,Build linux-user vdso images)
-	@echo  ''
 	@echo  'Test targets:'
 	$(call print-help,check,Run all tests (check-help for details))
 	$(call print-help,bench,Run all benchmarks)
@@ -323,7 +316,7 @@ endif
 	@echo  'Documentation targets:'
 	$(call print-help,html man,Build documentation in specified format)
 	@echo  ''
-ifneq ($(filter msi, $(ninja-targets)),)
+ifdef CONFIG_WIN32
 	@echo  'Windows targets:'
 	$(call print-help,installer,Build NSIS-based installer for QEMU)
 	$(call print-help,msi,Build MSI-based installer for qemu-ga)

VERSION

@@ -1 +1 @@
-8.2.2
+8.0.50

accel/Kconfig

@@ -4,6 +4,9 @@ config WHPX
 config NVMM
     bool
 
+config HAX
+    bool
+
 config HVF
     bool
 

accel/accel-common.c

@@ -30,7 +30,7 @@
 #include "hw/core/accel-cpu.h"
 
 #ifndef CONFIG_USER_ONLY
-#include "accel-system.h"
+#include "accel-softmmu.h"
 #endif /* !CONFIG_USER_ONLY */
 
 static const TypeInfo accel_type = {
@@ -119,37 +119,16 @@ void accel_cpu_instance_init(CPUState *cpu)
     }
 }
 
-bool accel_cpu_common_realize(CPUState *cpu, Error **errp)
+bool accel_cpu_realizefn(CPUState *cpu, Error **errp)
 {
     CPUClass *cc = CPU_GET_CLASS(cpu);
-    AccelState *accel = current_accel();
-    AccelClass *acc = ACCEL_GET_CLASS(accel);
 
-    /* target specific realization */
-    if (cc->accel_cpu && cc->accel_cpu->cpu_target_realize
-        && !cc->accel_cpu->cpu_target_realize(cpu, errp)) {
-        return false;
+    if (cc->accel_cpu && cc->accel_cpu->cpu_realizefn) {
+        return cc->accel_cpu->cpu_realizefn(cpu, errp);
     }
-
-    /* generic realization */
-    if (acc->cpu_common_realize && !acc->cpu_common_realize(cpu, errp)) {
-        return false;
-    }
-
     return true;
 }
 
-void accel_cpu_common_unrealize(CPUState *cpu)
-{
-    AccelState *accel = current_accel();
-    AccelClass *acc = ACCEL_GET_CLASS(accel);
-
-    /* generic unrealization */
-    if (acc->cpu_common_unrealize) {
-        acc->cpu_common_unrealize(cpu);
-    }
-}
-
 int accel_supported_gdbstub_sstep_flags(void)
 {
     AccelState *accel = current_accel();

accel/accel-softmmu.c

@@ -28,7 +28,7 @@
 #include "hw/boards.h"
 #include "sysemu/cpus.h"
 #include "qemu/error-report.h"
-#include "accel-system.h"
+#include "accel-softmmu.h"
 
 int accel_init_machine(AccelState *accel, MachineState *ms)
 {
@@ -99,8 +99,8 @@ static const TypeInfo accel_ops_type_info = {
     .class_size = sizeof(AccelOpsClass),
 };
 
-static void accel_system_register_types(void)
+static void accel_softmmu_register_types(void)
 {
     type_register_static(&accel_ops_type_info);
 }
-type_init(accel_system_register_types);
+type_init(accel_softmmu_register_types);

accel/accel-softmmu.h

@@ -7,9 +7,9 @@
  * See the COPYING file in the top-level directory.
  */
 
-#ifndef ACCEL_SYSTEM_H
-#define ACCEL_SYSTEM_H
+#ifndef ACCEL_SOFTMMU_H
+#define ACCEL_SOFTMMU_H
 
 void accel_init_ops_interfaces(AccelClass *ac);
 
-#endif /* ACCEL_SYSTEM_H */
+#endif /* ACCEL_SOFTMMU_H */

accel/dummy-cpus.c

@@ -27,7 +27,7 @@ static void *dummy_cpu_thread_fn(void *arg)
     qemu_mutex_lock_iothread();
     qemu_thread_get_self(cpu->thread);
     cpu->thread_id = qemu_get_thread_id();
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     current_cpu = cpu;
 
 #ifndef _WIN32

accel/hvf/hvf-accel-ops.c

@@ -428,7 +428,7 @@ static void *hvf_cpu_thread_fn(void *arg)
     qemu_thread_get_self(cpu->thread);
 
     cpu->thread_id = qemu_get_thread_id();
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     current_cpu = cpu;
 
     hvf_init_vcpu(cpu);
@@ -474,7 +474,7 @@ static void hvf_start_vcpu_thread(CPUState *cpu)
                        cpu, QEMU_THREAD_JOINABLE);
 }
 
-static int hvf_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len)
+static int hvf_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
 {
     struct hvf_sw_breakpoint *bp;
     int err;
@@ -512,7 +512,7 @@ static int hvf_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len)
     return 0;
 }
 
-static int hvf_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len)
+static int hvf_remove_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
 {
     struct hvf_sw_breakpoint *bp;
     int err;

accel/hvf/hvf-all.c

@@ -51,7 +51,7 @@ void assert_hvf_ok(hv_return_t ret)
     abort();
 }
 
-struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, vaddr pc)
+struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, target_ulong pc)
 {
     struct hvf_sw_breakpoint *bp;
 

accel/kvm/kvm-accel-ops.c

@@ -36,7 +36,7 @@ static void *kvm_vcpu_thread_fn(void *arg)
     qemu_mutex_lock_iothread();
     qemu_thread_get_self(cpu->thread);
     cpu->thread_id = qemu_get_thread_id();
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     current_cpu = cpu;
 
     r = kvm_init_vcpu(cpu, &error_fatal);

accel/kvm/kvm-all.c

@@ -90,6 +90,8 @@ bool kvm_kernel_irqchip;
 bool kvm_split_irqchip;
 bool kvm_async_interrupts_allowed;
 bool kvm_halt_in_kernel_allowed;
+bool kvm_eventfds_allowed;
+bool kvm_irqfds_allowed;
 bool kvm_resamplefds_allowed;
 bool kvm_msi_via_irqfd_allowed;
 bool kvm_gsi_routing_allowed;
@@ -97,6 +99,8 @@ bool kvm_gsi_direct_mapping;
 bool kvm_allowed;
 bool kvm_readonly_mem_allowed;
 bool kvm_vm_attributes_allowed;
+bool kvm_direct_msi_allowed;
+bool kvm_ioeventfd_any_length_allowed;
 bool kvm_msi_use_devid;
 bool kvm_has_guest_debug;
 static int kvm_sstep_flags;
@@ -107,9 +111,6 @@ static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_INFO(USER_MEMORY),
     KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS),
     KVM_CAP_INFO(JOIN_MEMORY_REGIONS_WORKS),
-    KVM_CAP_INFO(INTERNAL_ERROR_DATA),
-    KVM_CAP_INFO(IOEVENTFD),
-    KVM_CAP_INFO(IOEVENTFD_ANY_LENGTH),
     KVM_CAP_LAST_INFO
 };
 
@@ -173,31 +174,13 @@ void kvm_resample_fd_notify(int gsi)
     }
 }
 
-unsigned int kvm_get_max_memslots(void)
+int kvm_get_max_memslots(void)
 {
     KVMState *s = KVM_STATE(current_accel());
 
     return s->nr_slots;
 }
 
-unsigned int kvm_get_free_memslots(void)
-{
-    unsigned int used_slots = 0;
-    KVMState *s = kvm_state;
-    int i;
-
-    kvm_slots_lock();
-    for (i = 0; i < s->nr_as; i++) {
-        if (!s->as[i].ml) {
-            continue;
-        }
-        used_slots = MAX(used_slots, s->as[i].ml->nr_used_slots);
-    }
-    kvm_slots_unlock();
-
-    return s->nr_slots - used_slots;
-}
-
 /* Called with KVMMemoryListener.slots_lock held */
 static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
 {
@@ -213,6 +196,19 @@ static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
     return NULL;
 }
 
+bool kvm_has_free_slot(MachineState *ms)
+{
+    KVMState *s = KVM_STATE(ms->accelerator);
+    bool result;
+    KVMMemoryListener *kml = &s->memory_listener;
+
+    kvm_slots_lock();
+    result = !!kvm_get_free_slot(kml);
+    kvm_slots_unlock();
+
+    return result;
+}
+
 /* Called with KVMMemoryListener.slots_lock held */
 static KVMSlot *kvm_alloc_slot(KVMMemoryListener *kml)
 {
@@ -1105,6 +1101,13 @@ static void kvm_coalesce_pio_del(MemoryListener *listener,
      }
 }
 
+static MemoryListener kvm_coalesced_pio_listener = {
+    .name = "kvm-coalesced-pio",
+    .coalesced_io_add = kvm_coalesce_pio_add,
+    .coalesced_io_del = kvm_coalesce_pio_del,
+    .priority = MEMORY_LISTENER_PRIORITY_MIN,
+};
+
 int kvm_check_extension(KVMState *s, unsigned int extension)
 {
     int ret;
@@ -1246,6 +1249,43 @@ static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val,
 }
 
 
+static int kvm_check_many_ioeventfds(void)
+{
+    /* Userspace can use ioeventfd for io notification.  This requires a host
+     * that supports eventfd(2) and an I/O thread; since eventfd does not
+     * support SIGIO it cannot interrupt the vcpu.
+     *
+     * Older kernels have a 6 device limit on the KVM io bus.  Find out so we
+     * can avoid creating too many ioeventfds.
+     */
+#if defined(CONFIG_EVENTFD)
+    int ioeventfds[7];
+    int i, ret = 0;
+    for (i = 0; i < ARRAY_SIZE(ioeventfds); i++) {
+        ioeventfds[i] = eventfd(0, EFD_CLOEXEC);
+        if (ioeventfds[i] < 0) {
+            break;
+        }
+        ret = kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, true, 2, true);
+        if (ret < 0) {
+            close(ioeventfds[i]);
+            break;
+        }
+    }
+
+    /* Decide whether many devices are supported or not */
+    ret = i == ARRAY_SIZE(ioeventfds);
+
+    while (i-- > 0) {
+        kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, false, 2, true);
+        close(ioeventfds[i]);
+    }
+    return ret;
+#else
+    return 0;
+#endif
+}
+
 static const KVMCapabilityInfo *
 kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
 {
@@ -1347,7 +1387,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
             }
             start_addr += slot_size;
             size -= slot_size;
-            kml->nr_used_slots--;
         } while (size);
         return;
     }
@@ -1373,7 +1412,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
         ram_start_offset += slot_size;
         ram += slot_size;
         size -= slot_size;
-        kml->nr_used_slots++;
     } while (size);
 }
 
@@ -1416,13 +1454,15 @@ static void *kvm_dirty_ring_reaper_thread(void *data)
     return NULL;
 }
 
-static void kvm_dirty_ring_reaper_init(KVMState *s)
+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 int kvm_dirty_ring_init(KVMState *s)
@@ -1761,8 +1801,6 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
 
 static MemoryListener kvm_io_listener = {
     .name = "kvm-io",
-    .coalesced_io_add = kvm_coalesce_pio_add,
-    .coalesced_io_del = kvm_coalesce_pio_del,
     .eventfd_add = kvm_io_ioeventfd_add,
     .eventfd_del = kvm_io_ioeventfd_del,
     .priority = MEMORY_LISTENER_PRIORITY_DEV_BACKEND,
@@ -1804,7 +1842,7 @@ static void clear_gsi(KVMState *s, unsigned int gsi)
 
 void kvm_init_irq_routing(KVMState *s)
 {
-    int gsi_count;
+    int gsi_count, i;
 
     gsi_count = kvm_check_extension(s, KVM_CAP_IRQ_ROUTING) - 1;
     if (gsi_count > 0) {
@@ -1816,6 +1854,12 @@ void kvm_init_irq_routing(KVMState *s)
     s->irq_routes = g_malloc0(sizeof(*s->irq_routes));
     s->nr_allocated_irq_routes = 0;
 
+    if (!kvm_direct_msi_allowed) {
+        for (i = 0; i < KVM_MSI_HASHTAB_SIZE; i++) {
+            QTAILQ_INIT(&s->msi_hashtab[i]);
+        }
+    }
+
     kvm_arch_init_irq_routing(s);
 }
 
@@ -1935,10 +1979,41 @@ void kvm_irqchip_change_notify(void)
     notifier_list_notify(&kvm_irqchip_change_notifiers, NULL);
 }
 
+static unsigned int kvm_hash_msi(uint32_t data)
+{
+    /* This is optimized for IA32 MSI layout. However, no other arch shall
+     * repeat the mistake of not providing a direct MSI injection API. */
+    return data & 0xff;
+}
+
+static void kvm_flush_dynamic_msi_routes(KVMState *s)
+{
+    KVMMSIRoute *route, *next;
+    unsigned int hash;
+
+    for (hash = 0; hash < KVM_MSI_HASHTAB_SIZE; hash++) {
+        QTAILQ_FOREACH_SAFE(route, &s->msi_hashtab[hash], entry, next) {
+            kvm_irqchip_release_virq(s, route->kroute.gsi);
+            QTAILQ_REMOVE(&s->msi_hashtab[hash], route, entry);
+            g_free(route);
+        }
+    }
+}
+
 static int kvm_irqchip_get_virq(KVMState *s)
 {
     int next_virq;
 
+    /*
+     * PIC and IOAPIC share the first 16 GSI numbers, thus the available
+     * GSI numbers are more than the number of IRQ route. Allocating a GSI
+     * number can succeed even though a new route entry cannot be added.
+     * When this happens, flush dynamic MSI entries to free IRQ route entries.
+     */
+    if (!kvm_direct_msi_allowed && s->irq_routes->nr == s->gsi_count) {
+        kvm_flush_dynamic_msi_routes(s);
+    }
+
     /* Return the lowest unused GSI in the bitmap */
     next_virq = find_first_zero_bit(s->used_gsi_bitmap, s->gsi_count);
     if (next_virq >= s->gsi_count) {
@@ -1948,17 +2023,63 @@ static int kvm_irqchip_get_virq(KVMState *s)
     }
 }
 
+static KVMMSIRoute *kvm_lookup_msi_route(KVMState *s, MSIMessage msg)
+{
+    unsigned int hash = kvm_hash_msi(msg.data);
+    KVMMSIRoute *route;
+
+    QTAILQ_FOREACH(route, &s->msi_hashtab[hash], entry) {
+        if (route->kroute.u.msi.address_lo == (uint32_t)msg.address &&
+            route->kroute.u.msi.address_hi == (msg.address >> 32) &&
+            route->kroute.u.msi.data == le32_to_cpu(msg.data)) {
+            return route;
+        }
+    }
+    return NULL;
+}
+
 int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg)
 {
     struct kvm_msi msi;
+    KVMMSIRoute *route;
 
-    msi.address_lo = (uint32_t)msg.address;
-    msi.address_hi = msg.address >> 32;
-    msi.data = le32_to_cpu(msg.data);
-    msi.flags = 0;
-    memset(msi.pad, 0, sizeof(msi.pad));
+    if (kvm_direct_msi_allowed) {
+        msi.address_lo = (uint32_t)msg.address;
+        msi.address_hi = msg.address >> 32;
+        msi.data = le32_to_cpu(msg.data);
+        msi.flags = 0;
+        memset(msi.pad, 0, sizeof(msi.pad));
 
-    return kvm_vm_ioctl(s, KVM_SIGNAL_MSI, &msi);
+        return kvm_vm_ioctl(s, KVM_SIGNAL_MSI, &msi);
+    }
+
+    route = kvm_lookup_msi_route(s, msg);
+    if (!route) {
+        int virq;
+
+        virq = kvm_irqchip_get_virq(s);
+        if (virq < 0) {
+            return virq;
+        }
+
+        route = g_new0(KVMMSIRoute, 1);
+        route->kroute.gsi = virq;
+        route->kroute.type = KVM_IRQ_ROUTING_MSI;
+        route->kroute.flags = 0;
+        route->kroute.u.msi.address_lo = (uint32_t)msg.address;
+        route->kroute.u.msi.address_hi = msg.address >> 32;
+        route->kroute.u.msi.data = le32_to_cpu(msg.data);
+
+        kvm_add_routing_entry(s, &route->kroute);
+        kvm_irqchip_commit_routes(s);
+
+        QTAILQ_INSERT_TAIL(&s->msi_hashtab[kvm_hash_msi(msg.data)], route,
+                           entry);
+    }
+
+    assert(route->kroute.type == KVM_IRQ_ROUTING_MSI);
+
+    return kvm_set_irq(s, route->kroute.gsi, 1);
 }
 
 int kvm_irqchip_add_msi_route(KVMRouteChange *c, int vector, PCIDevice *dev)
@@ -2085,6 +2206,10 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, EventNotifier *event,
         }
     }
 
+    if (!kvm_irqfds_enabled()) {
+        return -ENOSYS;
+    }
+
     return kvm_vm_ioctl(s, KVM_IRQFD, &irqfd);
 }
 
@@ -2245,11 +2370,6 @@ static void kvm_irqchip_create(KVMState *s)
         return;
     }
 
-    if (kvm_check_extension(s, KVM_CAP_IRQFD) <= 0) {
-        fprintf(stderr, "kvm: irqfd not implemented\n");
-        exit(1);
-    }
-
     /* First probe and see if there's a arch-specific hook to create the
      * in-kernel irqchip for us */
     ret = kvm_arch_irqchip_create(s);
@@ -2338,7 +2458,7 @@ static int kvm_init(MachineState *ms)
     KVMState *s;
     const KVMCapabilityInfo *missing_cap;
     int ret;
-    int type;
+    int type = 0;
     uint64_t dirty_log_manual_caps;
 
     qemu_mutex_init(&kml_slots_lock);
@@ -2403,13 +2523,6 @@ static int kvm_init(MachineState *ms)
         type = mc->kvm_type(ms, kvm_type);
     } else if (mc->kvm_type) {
         type = mc->kvm_type(ms, NULL);
-    } else {
-        type = kvm_arch_get_default_type(ms);
-    }
-
-    if (type < 0) {
-        ret = -EINVAL;
-        goto err;
     }
 
     do {
@@ -2524,8 +2637,22 @@ static int kvm_init(MachineState *ms)
 #ifdef KVM_CAP_VCPU_EVENTS
     s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS);
 #endif
+
+    s->robust_singlestep =
+        kvm_check_extension(s, KVM_CAP_X86_ROBUST_SINGLESTEP);
+
+#ifdef KVM_CAP_DEBUGREGS
+    s->debugregs = kvm_check_extension(s, KVM_CAP_DEBUGREGS);
+#endif
+
     s->max_nested_state_len = kvm_check_extension(s, KVM_CAP_NESTED_STATE);
 
+#ifdef KVM_CAP_IRQ_ROUTING
+    kvm_direct_msi_allowed = (kvm_check_extension(s, KVM_CAP_SIGNAL_MSI) > 0);
+#endif
+
+    s->intx_set_mask = kvm_check_extension(s, KVM_CAP_PCI_2_3);
+
     s->irq_set_ioctl = KVM_IRQ_LINE;
     if (kvm_check_extension(s, KVM_CAP_IRQ_INJECT_STATUS)) {
         s->irq_set_ioctl = KVM_IRQ_LINE_STATUS;
@@ -2534,12 +2661,21 @@ static int kvm_init(MachineState *ms)
     kvm_readonly_mem_allowed =
         (kvm_check_extension(s, KVM_CAP_READONLY_MEM) > 0);
 
+    kvm_eventfds_allowed =
+        (kvm_check_extension(s, KVM_CAP_IOEVENTFD) > 0);
+
+    kvm_irqfds_allowed =
+        (kvm_check_extension(s, KVM_CAP_IRQFD) > 0);
+
     kvm_resamplefds_allowed =
         (kvm_check_extension(s, KVM_CAP_IRQFD_RESAMPLE) > 0);
 
     kvm_vm_attributes_allowed =
         (kvm_check_extension(s, KVM_CAP_VM_ATTRIBUTES) > 0);
 
+    kvm_ioeventfd_any_length_allowed =
+        (kvm_check_extension(s, KVM_CAP_IOEVENTFD_ANY_LENGTH) > 0);
+
 #ifdef KVM_CAP_SET_GUEST_DEBUG
     kvm_has_guest_debug =
         (kvm_check_extension(s, KVM_CAP_SET_GUEST_DEBUG) > 0);
@@ -2576,16 +2712,24 @@ static int kvm_init(MachineState *ms)
         kvm_irqchip_create(s);
     }
 
-    s->memory_listener.listener.eventfd_add = kvm_mem_ioeventfd_add;
-    s->memory_listener.listener.eventfd_del = kvm_mem_ioeventfd_del;
+    if (kvm_eventfds_allowed) {
+        s->memory_listener.listener.eventfd_add = kvm_mem_ioeventfd_add;
+        s->memory_listener.listener.eventfd_del = kvm_mem_ioeventfd_del;
+    }
     s->memory_listener.listener.coalesced_io_add = kvm_coalesce_mmio_region;
     s->memory_listener.listener.coalesced_io_del = kvm_uncoalesce_mmio_region;
 
     kvm_memory_listener_register(s, &s->memory_listener,
                                  &address_space_memory, 0, "kvm-memory");
-    memory_listener_register(&kvm_io_listener,
+    if (kvm_eventfds_allowed) {
+        memory_listener_register(&kvm_io_listener,
+                                 &address_space_io);
+    }
+    memory_listener_register(&kvm_coalesced_pio_listener,
                              &address_space_io);
 
+    s->many_ioeventfds = kvm_check_many_ioeventfds();
+
     s->sync_mmu = !!kvm_vm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
     if (!s->sync_mmu) {
         ret = ram_block_discard_disable(true);
@@ -2593,7 +2737,10 @@ static int kvm_init(MachineState *ms)
     }
 
     if (s->kvm_dirty_ring_size) {
-        kvm_dirty_ring_reaper_init(s);
+        ret = kvm_dirty_ring_reaper_init(s);
+        if (ret) {
+            goto err;
+        }
     }
 
     if (kvm_check_extension(kvm_state, KVM_CAP_BINARY_STATS_FD)) {
@@ -2611,7 +2758,6 @@ err:
     if (s->fd != -1) {
         close(s->fd);
     }
-    g_free(s->as);
     g_free(s->memory_listener.slots);
 
     return ret;
@@ -2638,14 +2784,16 @@ static void kvm_handle_io(uint16_t port, MemTxAttrs attrs, void *data, int direc
 
 static int kvm_handle_internal_error(CPUState *cpu, struct kvm_run *run)
 {
-    int i;
-
     fprintf(stderr, "KVM internal error. Suberror: %d\n",
             run->internal.suberror);
 
-    for (i = 0; i < run->internal.ndata; ++i) {
-        fprintf(stderr, "extra data[%d]: 0x%016"PRIx64"\n",
-                i, (uint64_t)run->internal.data[i]);
+    if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
+        int i;
+
+        for (i = 0; i < run->internal.ndata; ++i) {
+            fprintf(stderr, "extra data[%d]: 0x%016"PRIx64"\n",
+                    i, (uint64_t)run->internal.data[i]);
+        }
     }
     if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
         fprintf(stderr, "emulation failure\n");
@@ -2664,7 +2812,7 @@ void kvm_flush_coalesced_mmio_buffer(void)
 {
     KVMState *s = kvm_state;
 
-    if (!s || s->coalesced_flush_in_progress) {
+    if (s->coalesced_flush_in_progress) {
         return;
     }
 
@@ -2700,13 +2848,7 @@ bool kvm_cpu_check_are_resettable(void)
 static void do_kvm_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
 {
     if (!cpu->vcpu_dirty) {
-        int ret = kvm_arch_get_registers(cpu);
-        if (ret) {
-            error_report("Failed to get registers: %s", strerror(-ret));
-            cpu_dump_state(cpu, stderr, CPU_DUMP_CODE);
-            vm_stop(RUN_STATE_INTERNAL_ERROR);
-        }
-
+        kvm_arch_get_registers(cpu);
         cpu->vcpu_dirty = true;
     }
 }
@@ -2720,13 +2862,7 @@ void kvm_cpu_synchronize_state(CPUState *cpu)
 
 static void do_kvm_cpu_synchronize_post_reset(CPUState *cpu, run_on_cpu_data arg)
 {
-    int ret = kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE);
-    if (ret) {
-        error_report("Failed to put registers after reset: %s", strerror(-ret));
-        cpu_dump_state(cpu, stderr, CPU_DUMP_CODE);
-        vm_stop(RUN_STATE_INTERNAL_ERROR);
-    }
-
+    kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE);
     cpu->vcpu_dirty = false;
 }
 
@@ -2737,12 +2873,7 @@ void kvm_cpu_synchronize_post_reset(CPUState *cpu)
 
 static void do_kvm_cpu_synchronize_post_init(CPUState *cpu, run_on_cpu_data arg)
 {
-    int ret = kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE);
-    if (ret) {
-        error_report("Failed to put registers after init: %s", strerror(-ret));
-        exit(1);
-    }
-
+    kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE);
     cpu->vcpu_dirty = false;
 }
 
@@ -2835,14 +2966,7 @@ int kvm_cpu_exec(CPUState *cpu)
         MemTxAttrs attrs;
 
         if (cpu->vcpu_dirty) {
-            ret = kvm_arch_put_registers(cpu, KVM_PUT_RUNTIME_STATE);
-            if (ret) {
-                error_report("Failed to put registers after init: %s",
-                             strerror(-ret));
-                ret = -1;
-                break;
-            }
-
+            kvm_arch_put_registers(cpu, KVM_PUT_RUNTIME_STATE);
             cpu->vcpu_dirty = false;
         }
 
@@ -3139,11 +3263,29 @@ int kvm_has_vcpu_events(void)
     return kvm_state->vcpu_events;
 }
 
+int kvm_has_robust_singlestep(void)
+{
+    return kvm_state->robust_singlestep;
+}
+
+int kvm_has_debugregs(void)
+{
+    return kvm_state->debugregs;
+}
+
 int kvm_max_nested_state_length(void)
 {
     return kvm_state->max_nested_state_len;
 }
 
+int kvm_has_many_ioeventfds(void)
+{
+    if (!kvm_enabled()) {
+        return 0;
+    }
+    return kvm_state->many_ioeventfds;
+}
+
 int kvm_has_gsi_routing(void)
 {
 #ifdef KVM_CAP_IRQ_ROUTING
@@ -3153,13 +3295,19 @@ int kvm_has_gsi_routing(void)
 #endif
 }
 
+int kvm_has_intx_set_mask(void)
+{
+    return kvm_state->intx_set_mask;
+}
+
 bool kvm_arm_supports_user_irq(void)
 {
     return kvm_check_extension(kvm_state, KVM_CAP_ARM_USER_IRQ);
 }
 
 #ifdef KVM_CAP_SET_GUEST_DEBUG
-struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *cpu, vaddr pc)
+struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *cpu,
+                                                 target_ulong pc)
 {
     struct kvm_sw_breakpoint *bp;
 
@@ -3613,7 +3761,6 @@ static void kvm_accel_instance_init(Object *obj)
     /* KVM dirty ring is by default off */
     s->kvm_dirty_ring_size = 0;
     s->kvm_dirty_ring_with_bitmap = false;
-    s->kvm_eager_split_size = 0;
     s->notify_vmexit = NOTIFY_VMEXIT_OPTION_RUN;
     s->notify_window = 0;
     s->xen_version = 0;

accel/meson.build

@@ -1,5 +1,5 @@
-specific_ss.add(files('accel-target.c'))
-system_ss.add(files('accel-system.c', 'accel-blocker.c'))
+specific_ss.add(files('accel-common.c', 'accel-blocker.c'))
+system_ss.add(files('accel-softmmu.c'))
 user_ss.add(files('accel-user.c'))
 
 subdir('tcg')

accel/stubs/hax-stub.c

@@ -0,0 +1,24 @@
+/*
+ * QEMU HAXM support
+ *
+ * Copyright (c) 2015, Intel Corporation
+ *
+ * Copyright 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/hax.h"
+
+bool hax_allowed;
+
+int hax_sync_vcpus(void)
+{
+    return 0;
+}

accel/stubs/kvm-stub.c

@@ -17,13 +17,17 @@
 KVMState *kvm_state;
 bool kvm_kernel_irqchip;
 bool kvm_async_interrupts_allowed;
+bool kvm_eventfds_allowed;
+bool kvm_irqfds_allowed;
 bool kvm_resamplefds_allowed;
 bool kvm_msi_via_irqfd_allowed;
 bool kvm_gsi_routing_allowed;
 bool kvm_gsi_direct_mapping;
 bool kvm_allowed;
 bool kvm_readonly_mem_allowed;
+bool kvm_ioeventfd_any_length_allowed;
 bool kvm_msi_use_devid;
+bool kvm_direct_msi_allowed;
 
 void kvm_flush_coalesced_mmio_buffer(void)
 {
@@ -38,6 +42,11 @@ bool kvm_has_sync_mmu(void)
     return false;
 }
 
+int kvm_has_many_ioeventfds(void)
+{
+    return 0;
+}
+
 int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
 {
     return 1;
@@ -83,6 +92,11 @@ void kvm_irqchip_change_notify(void)
 {
 }
 
+int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
+{
+    return -ENOSYS;
+}
+
 int kvm_irqchip_add_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
                                        EventNotifier *rn, int virq)
 {
@@ -95,14 +109,9 @@ int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
     return -ENOSYS;
 }
 
-unsigned int kvm_get_max_memslots(void)
+bool kvm_has_free_slot(MachineState *ms)
 {
-    return 0;
-}
-
-unsigned int kvm_get_free_memslots(void)
-{
-    return 0;
+    return false;
 }
 
 void kvm_init_cpu_signals(CPUState *cpu)

accel/stubs/meson.build

@@ -1,6 +1,7 @@
-system_stubs_ss = ss.source_set()
-system_stubs_ss.add(when: 'CONFIG_XEN', if_false: files('xen-stub.c'))
-system_stubs_ss.add(when: 'CONFIG_KVM', if_false: files('kvm-stub.c'))
-system_stubs_ss.add(when: 'CONFIG_TCG', if_false: files('tcg-stub.c'))
+sysemu_stubs_ss = ss.source_set()
+sysemu_stubs_ss.add(when: 'CONFIG_HAX', if_false: files('hax-stub.c'))
+sysemu_stubs_ss.add(when: 'CONFIG_XEN', if_false: files('xen-stub.c'))
+sysemu_stubs_ss.add(when: 'CONFIG_KVM', if_false: files('kvm-stub.c'))
+sysemu_stubs_ss.add(when: 'CONFIG_TCG', if_false: files('tcg-stub.c'))
 
-specific_ss.add_all(when: ['CONFIG_SYSTEM_ONLY'], if_true: system_stubs_ss)
+specific_ss.add_all(when: ['CONFIG_SYSTEM_ONLY'], if_true: sysemu_stubs_ss)

accel/stubs/tcg-stub.c

@@ -22,6 +22,10 @@ void tlb_set_dirty(CPUState *cpu, vaddr vaddr)
 {
 }
 
+void tcg_flush_jmp_cache(CPUState *cpu)
+{
+}
+
 int probe_access_flags(CPUArchState *env, vaddr addr, int size,
                        MMUAccessType access_type, int mmu_idx,
                        bool nonfault, void **phost, uintptr_t retaddr)

accel/tcg/atomic_common.c.inc

@@ -41,7 +41,7 @@ CMPXCHG_HELPER(cmpxchgq_be, uint64_t)
 CMPXCHG_HELPER(cmpxchgq_le, uint64_t)
 #endif
 
-#if HAVE_CMPXCHG128
+#ifdef CONFIG_CMPXCHG128
 CMPXCHG_HELPER(cmpxchgo_be, Int128)
 CMPXCHG_HELPER(cmpxchgo_le, Int128)
 #endif

accel/tcg/atomic_template.h

@@ -69,12 +69,11 @@
 # define END  _le
 #endif
 
-ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
+ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
                               ABI_TYPE cmpv, ABI_TYPE newv,
                               MemOpIdx oi, uintptr_t retaddr)
 {
-    DATA_TYPE *haddr = atomic_mmu_lookup(env_cpu(env), addr, oi,
-                                         DATA_SIZE, retaddr);
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
     DATA_TYPE ret;
 
 #if DATA_SIZE == 16
@@ -88,11 +87,10 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
 }
 
 #if DATA_SIZE < 16
-ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
+ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val,
                            MemOpIdx oi, uintptr_t retaddr)
 {
-    DATA_TYPE *haddr = atomic_mmu_lookup(env_cpu(env), addr, oi,
-                                         DATA_SIZE, retaddr);
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
     DATA_TYPE ret;
 
     ret = qatomic_xchg__nocheck(haddr, val);
@@ -102,11 +100,11 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
 }
 
 #define GEN_ATOMIC_HELPER(X)                                        \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr,            \
+ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
                         ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \
 {                                                                   \
     DATA_TYPE *haddr, ret;                                          \
-    haddr = atomic_mmu_lookup(env_cpu(env), addr, oi, DATA_SIZE, retaddr);   \
+    haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);   \
     ret = qatomic_##X(haddr, val);                                  \
     ATOMIC_MMU_CLEANUP;                                             \
     atomic_trace_rmw_post(env, addr, oi);                           \
@@ -133,11 +131,11 @@ GEN_ATOMIC_HELPER(xor_fetch)
  * of CF_PARALLEL's value, we'll trace just a read and a write.
  */
 #define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET)                \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr,            \
+ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
                         ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \
 {                                                                   \
     XDATA_TYPE *haddr, cmp, old, new, val = xval;                   \
-    haddr = atomic_mmu_lookup(env_cpu(env), addr, oi, DATA_SIZE, retaddr);   \
+    haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);   \
     smp_mb();                                                       \
     cmp = qatomic_read__nocheck(haddr);                             \
     do {                                                            \
@@ -174,12 +172,11 @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)
 # define END  _be
 #endif
 
-ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
+ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
                               ABI_TYPE cmpv, ABI_TYPE newv,
                               MemOpIdx oi, uintptr_t retaddr)
 {
-    DATA_TYPE *haddr = atomic_mmu_lookup(env_cpu(env), addr, oi,
-                                         DATA_SIZE, retaddr);
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
     DATA_TYPE ret;
 
 #if DATA_SIZE == 16
@@ -193,11 +190,10 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
 }
 
 #if DATA_SIZE < 16
-ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
+ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val,
                            MemOpIdx oi, uintptr_t retaddr)
 {
-    DATA_TYPE *haddr = atomic_mmu_lookup(env_cpu(env), addr, oi,
-                                         DATA_SIZE, retaddr);
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);
     ABI_TYPE ret;
 
     ret = qatomic_xchg__nocheck(haddr, BSWAP(val));
@@ -207,11 +203,11 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
 }
 
 #define GEN_ATOMIC_HELPER(X)                                        \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr,            \
+ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
                         ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \
 {                                                                   \
     DATA_TYPE *haddr, ret;                                          \
-    haddr = atomic_mmu_lookup(env_cpu(env), addr, oi, DATA_SIZE, retaddr);   \
+    haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);   \
     ret = qatomic_##X(haddr, BSWAP(val));                           \
     ATOMIC_MMU_CLEANUP;                                             \
     atomic_trace_rmw_post(env, addr, oi);                           \
@@ -235,11 +231,11 @@ GEN_ATOMIC_HELPER(xor_fetch)
  * of CF_PARALLEL's value, we'll trace just a read and a write.
  */
 #define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET)                \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr,            \
+ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
                         ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \
 {                                                                   \
     XDATA_TYPE *haddr, ldo, ldn, old, new, val = xval;              \
-    haddr = atomic_mmu_lookup(env_cpu(env), addr, oi, DATA_SIZE, retaddr);   \
+    haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, retaddr);   \
     smp_mb();                                                       \
     ldn = qatomic_read__nocheck(haddr);                             \
     do {                                                            \

accel/tcg/cpu-exec-common.c

@@ -20,8 +20,9 @@
 #include "qemu/osdep.h"
 #include "sysemu/cpus.h"
 #include "sysemu/tcg.h"
+#include "exec/exec-all.h"
 #include "qemu/plugin.h"
-#include "internal-common.h"
+#include "internal.h"
 
 bool tcg_allowed;
 
@@ -32,10 +33,40 @@ void cpu_loop_exit_noexc(CPUState *cpu)
     cpu_loop_exit(cpu);
 }
 
+#if defined(CONFIG_SOFTMMU)
+void cpu_reloading_memory_map(void)
+{
+    if (qemu_in_vcpu_thread() && current_cpu->running) {
+        /* The guest can in theory prolong the RCU critical section as long
+         * as it feels like. The major problem with this is that because it
+         * can do multiple reconfigurations of the memory map within the
+         * critical section, we could potentially accumulate an unbounded
+         * collection of memory data structures awaiting reclamation.
+         *
+         * Because the only thing we're currently protecting with RCU is the
+         * memory data structures, it's sufficient to break the critical section
+         * in this callback, which we know will get called every time the
+         * memory map is rearranged.
+         *
+         * (If we add anything else in the system that uses RCU to protect
+         * its data structures, we will need to implement some other mechanism
+         * to force TCG CPUs to exit the critical section, at which point this
+         * part of this callback might become unnecessary.)
+         *
+         * This pair matches cpu_exec's rcu_read_lock()/rcu_read_unlock(), which
+         * only protects cpu->as->dispatch. Since we know our caller is about
+         * to reload it, it's safe to split the critical section.
+         */
+        rcu_read_unlock();
+        rcu_read_lock();
+    }
+}
+#endif
+
 void cpu_loop_exit(CPUState *cpu)
 {
     /* Undo the setting in cpu_tb_exec.  */
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     /* Undo any setting in generated code.  */
     qemu_plugin_disable_mem_helpers(cpu);
     siglongjmp(cpu->jmp_env, 1);

accel/tcg/cpu-exec.c

@@ -42,8 +42,7 @@
 #include "tb-jmp-cache.h"
 #include "tb-hash.h"
 #include "tb-context.h"
-#include "internal-common.h"
-#include "internal-target.h"
+#include "internal.h"
 
 /* -icount align implementation. */
 
@@ -74,7 +73,7 @@ static void align_clocks(SyncClocks *sc, CPUState *cpu)
         return;
     }
 
-    cpu_icount = cpu->icount_extra + cpu->neg.icount_decr.u16.low;
+    cpu_icount = cpu->icount_extra + cpu_neg(cpu)->icount_decr.u16.low;
     sc->diff_clk += icount_to_ns(sc->last_cpu_icount - cpu_icount);
     sc->last_cpu_icount = cpu_icount;
 
@@ -125,7 +124,7 @@ static void init_delay_params(SyncClocks *sc, CPUState *cpu)
     sc->realtime_clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
     sc->diff_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - sc->realtime_clock;
     sc->last_cpu_icount
-        = cpu->icount_extra + cpu->neg.icount_decr.u16.low;
+        = cpu->icount_extra + cpu_neg(cpu)->icount_decr.u16.low;
     if (sc->diff_clk < max_delay) {
         max_delay = sc->diff_clk;
     }
@@ -183,7 +182,7 @@ static bool tb_lookup_cmp(const void *p, const void *d)
     const TranslationBlock *tb = p;
     const struct tb_desc *desc = d;
 
-    if (tb->pc == desc->pc &&
+    if ((tb_cflags(tb) & CF_PCREL || tb->pc == desc->pc) &&
         tb_page_addr0(tb) == desc->page_addr0 &&
         tb->cs_base == desc->cs_base &&
         tb->flags == desc->flags &&
@@ -223,7 +222,7 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, vaddr pc,
     struct tb_desc desc;
     uint32_t h;
 
-    desc.env = cpu_env(cpu);
+    desc.env = cpu->env_ptr;
     desc.cs_base = cs_base;
     desc.flags = flags;
     desc.cflags = cflags;
@@ -233,7 +232,7 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, vaddr pc,
         return NULL;
     }
     desc.page_addr0 = phys_pc;
-    h = tb_hash_func(phys_pc, pc,
+    h = tb_hash_func(phys_pc, (cflags & CF_PCREL ? 0 : pc),
                      flags, cs_base, cflags);
     return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
 }
@@ -299,7 +298,7 @@ static void log_cpu_exec(vaddr pc, CPUState *cpu,
     if (qemu_log_in_addr_range(pc)) {
         qemu_log_mask(CPU_LOG_EXEC,
                       "Trace %d: %p [%08" PRIx64
-                      "/%016" VADDR_PRIx "/%08x/%08x] %s\n",
+                      "/%" VADDR_PRIx "/%08x/%08x] %s\n",
                       cpu->cpu_index, tb->tc.ptr, tb->cs_base, pc,
                       tb->flags, tb->cflags, lookup_symbol(pc));
 
@@ -445,7 +444,7 @@ const void *HELPER(lookup_tb_ptr)(CPUArchState *env)
 static inline TranslationBlock * QEMU_DISABLE_CFI
 cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
 {
-    CPUArchState *env = cpu_env(cpu);
+    CPUArchState *env = cpu->env_ptr;
     uintptr_t ret;
     TranslationBlock *last_tb;
     const void *tb_ptr = itb->tc.ptr;
@@ -456,7 +455,7 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
 
     qemu_thread_jit_execute();
     ret = tcg_qemu_tb_exec(env, tb_ptr);
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     qemu_plugin_disable_mem_helpers(cpu);
     /*
      * TODO: Delay swapping back to the read-write region of the TB
@@ -488,7 +487,7 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
         if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
             vaddr pc = log_pc(cpu, last_tb);
             if (qemu_log_in_addr_range(pc)) {
-                qemu_log("Stopped execution of TB chain before %p [%016"
+                qemu_log("Stopped execution of TB chain before %p [%"
                          VADDR_PRIx "] %s\n",
                          last_tb->tc.ptr, pc, lookup_symbol(pc));
             }
@@ -527,46 +526,9 @@ static void cpu_exec_exit(CPUState *cpu)
     }
 }
 
-static void cpu_exec_longjmp_cleanup(CPUState *cpu)
-{
-    /* Non-buggy compilers preserve this; assert the correct value. */
-    g_assert(cpu == current_cpu);
-
-#ifdef CONFIG_USER_ONLY
-    clear_helper_retaddr();
-    if (have_mmap_lock()) {
-        mmap_unlock();
-    }
-#else
-    /*
-     * For softmmu, a tlb_fill fault during translation will land here,
-     * and we need to release any page locks held.  In system mode we
-     * have one tcg_ctx per thread, so we know it was this cpu doing
-     * the translation.
-     *
-     * Alternative 1: Install a cleanup to be called via an exception
-     * handling safe longjmp.  It seems plausible that all our hosts
-     * support such a thing.  We'd have to properly register unwind info
-     * for the JIT for EH, rather that just for GDB.
-     *
-     * Alternative 2: Set and restore cpu->jmp_env in tb_gen_code to
-     * capture the cpu_loop_exit longjmp, perform the cleanup, and
-     * jump again to arrive here.
-     */
-    if (tcg_ctx->gen_tb) {
-        tb_unlock_pages(tcg_ctx->gen_tb);
-        tcg_ctx->gen_tb = NULL;
-    }
-#endif
-    if (qemu_mutex_iothread_locked()) {
-        qemu_mutex_unlock_iothread();
-    }
-    assert_no_pages_locked();
-}
-
 void cpu_exec_step_atomic(CPUState *cpu)
 {
-    CPUArchState *env = cpu_env(cpu);
+    CPUArchState *env = cpu->env_ptr;
     TranslationBlock *tb;
     vaddr pc;
     uint64_t cs_base;
@@ -606,7 +568,16 @@ void cpu_exec_step_atomic(CPUState *cpu)
         cpu_tb_exec(cpu, tb, &tb_exit);
         cpu_exec_exit(cpu);
     } else {
-        cpu_exec_longjmp_cleanup(cpu);
+#ifdef CONFIG_USER_ONLY
+        clear_helper_retaddr();
+        if (have_mmap_lock()) {
+            mmap_unlock();
+        }
+#endif
+        if (qemu_mutex_iothread_locked()) {
+            qemu_mutex_unlock_iothread();
+        }
+        assert_no_pages_locked();
     }
 
     /*
@@ -718,7 +689,7 @@ static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
     if (cpu->exception_index < 0) {
 #ifndef CONFIG_USER_ONLY
         if (replay_has_exception()
-            && cpu->neg.icount_decr.u16.low + cpu->icount_extra == 0) {
+            && cpu_neg(cpu)->icount_decr.u16.low + cpu->icount_extra == 0) {
             /* Execute just one insn to trigger exception pending in the log */
             cpu->cflags_next_tb = (curr_cflags(cpu) & ~CF_USE_ICOUNT)
                 | CF_NOIRQ | 1;
@@ -808,7 +779,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
      * Ensure zeroing happens before reading cpu->exit_request or
      * cpu->interrupt_request (see also smp_wmb in cpu_exit())
      */
-    qatomic_set_mb(&cpu->neg.icount_decr.u16.high, 0);
+    qatomic_set_mb(&cpu_neg(cpu)->icount_decr.u16.high, 0);
 
     if (unlikely(qatomic_read(&cpu->interrupt_request))) {
         int interrupt_request;
@@ -899,7 +870,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
     if (unlikely(qatomic_read(&cpu->exit_request))
         || (icount_enabled()
             && (cpu->cflags_next_tb == -1 || cpu->cflags_next_tb & CF_USE_ICOUNT)
-            && cpu->neg.icount_decr.u16.low + cpu->icount_extra == 0)) {
+            && cpu_neg(cpu)->icount_decr.u16.low + cpu->icount_extra == 0)) {
         qatomic_set(&cpu->exit_request, 0);
         if (cpu->exception_index == -1) {
             cpu->exception_index = EXCP_INTERRUPT;
@@ -924,7 +895,7 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
     }
 
     *last_tb = NULL;
-    insns_left = qatomic_read(&cpu->neg.icount_decr.u32);
+    insns_left = qatomic_read(&cpu_neg(cpu)->icount_decr.u32);
     if (insns_left < 0) {
         /* Something asked us to stop executing chained TBs; just
          * continue round the main loop. Whatever requested the exit
@@ -943,7 +914,7 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
     icount_update(cpu);
     /* Refill decrementer and continue execution.  */
     insns_left = MIN(0xffff, cpu->icount_budget);
-    cpu->neg.icount_decr.u16.low = insns_left;
+    cpu_neg(cpu)->icount_decr.u16.low = insns_left;
     cpu->icount_extra = cpu->icount_budget - insns_left;
 
     /*
@@ -977,7 +948,7 @@ cpu_exec_loop(CPUState *cpu, SyncClocks *sc)
             uint64_t cs_base;
             uint32_t flags, cflags;
 
-            cpu_get_tb_cpu_state(cpu_env(cpu), &pc, &cs_base, &flags);
+            cpu_get_tb_cpu_state(cpu->env_ptr, &pc, &cs_base, &flags);
 
             /*
              * When requested, use an exact setting for cflags for the next
@@ -1052,7 +1023,20 @@ static int cpu_exec_setjmp(CPUState *cpu, SyncClocks *sc)
 {
     /* Prepare setjmp context for exception handling. */
     if (unlikely(sigsetjmp(cpu->jmp_env, 0) != 0)) {
-        cpu_exec_longjmp_cleanup(cpu);
+        /* Non-buggy compilers preserve this; assert the correct value. */
+        g_assert(cpu == current_cpu);
+
+#ifdef CONFIG_USER_ONLY
+        clear_helper_retaddr();
+        if (have_mmap_lock()) {
+            mmap_unlock();
+        }
+#endif
+        if (qemu_mutex_iothread_locked()) {
+            qemu_mutex_unlock_iothread();
+        }
+
+        assert_no_pages_locked();
     }
 
     return cpu_exec_loop(cpu, sc);
@@ -1089,7 +1073,7 @@ int cpu_exec(CPUState *cpu)
     return ret;
 }
 
-bool tcg_exec_realizefn(CPUState *cpu, Error **errp)
+void tcg_exec_realizefn(CPUState *cpu, Error **errp)
 {
     static bool tcg_target_initialized;
     CPUClass *cc = CPU_GET_CLASS(cpu);
@@ -1105,8 +1089,6 @@ bool tcg_exec_realizefn(CPUState *cpu, Error **errp)
     tcg_iommu_init_notifier_list(cpu);
 #endif /* !CONFIG_USER_ONLY */
     /* qemu_plugin_vcpu_init_hook delayed until cpu_index assigned. */
-
-    return true;
 }
 
 /* undo the initializations in reverse order */

accel/tcg/internal-common.h

@@ -1,26 +0,0 @@
-/*
- * Internal execution defines for qemu (target agnostic)
- *
- *  Copyright (c) 2003 Fabrice Bellard
- *
- * SPDX-License-Identifier: LGPL-2.1-or-later
- */
-
-#ifndef ACCEL_TCG_INTERNAL_COMMON_H
-#define ACCEL_TCG_INTERNAL_COMMON_H
-
-#include "exec/translation-block.h"
-
-extern int64_t max_delay;
-extern int64_t max_advance;
-
-/*
- * Return true if CS is not running in parallel with other cpus, either
- * because there are no other cpus or we are within an exclusive context.
- */
-static inline bool cpu_in_serial_context(CPUState *cs)
-{
-    return !(cs->tcg_cflags & CF_PARALLEL) || cpu_in_exclusive_context(cs);
-}
-
-#endif

accel/tcg/internal.h

@@ -1,16 +1,15 @@
 /*
- * Internal execution defines for qemu (target specific)
+ * Internal execution defines for qemu
  *
  *  Copyright (c) 2003 Fabrice Bellard
  *
  * SPDX-License-Identifier: LGPL-2.1-or-later
  */
 
-#ifndef ACCEL_TCG_INTERNAL_TARGET_H
-#define ACCEL_TCG_INTERNAL_TARGET_H
+#ifndef ACCEL_TCG_INTERNAL_H
+#define ACCEL_TCG_INTERNAL_H
 
 #include "exec/exec-all.h"
-#include "exec/translate-all.h"
 
 /*
  * Access to the various translations structures need to be serialised
@@ -36,32 +35,6 @@ static inline void page_table_config_init(void) { }
 void page_table_config_init(void);
 #endif
 
-#ifdef CONFIG_USER_ONLY
-/*
- * For user-only, page_protect sets the page read-only.
- * Since most execution is already on read-only pages, and we'd need to
- * account for other TBs on the same page, defer undoing any page protection
- * until we receive the write fault.
- */
-static inline void tb_lock_page0(tb_page_addr_t p0)
-{
-    page_protect(p0);
-}
-
-static inline void tb_lock_page1(tb_page_addr_t p0, tb_page_addr_t p1)
-{
-    page_protect(p1);
-}
-
-static inline void tb_unlock_page1(tb_page_addr_t p0, tb_page_addr_t p1) { }
-static inline void tb_unlock_pages(TranslationBlock *tb) { }
-#else
-void tb_lock_page0(tb_page_addr_t);
-void tb_lock_page1(tb_page_addr_t, tb_page_addr_t);
-void tb_unlock_page1(tb_page_addr_t, tb_page_addr_t);
-void tb_unlock_pages(TranslationBlock *);
-#endif
-
 #ifdef CONFIG_SOFTMMU
 void tb_invalidate_phys_range_fast(ram_addr_t ram_addr,
                                    unsigned size,
@@ -75,14 +48,12 @@ TranslationBlock *tb_gen_code(CPUState *cpu, vaddr pc,
 void page_init(void);
 void tb_htable_init(void);
 void tb_reset_jump(TranslationBlock *tb, int n);
-TranslationBlock *tb_link_page(TranslationBlock *tb);
+TranslationBlock *tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
+                               tb_page_addr_t phys_page2);
 bool tb_invalidate_phys_page_unwind(tb_page_addr_t addr, uintptr_t pc);
 void cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
                                uintptr_t host_pc);
 
-bool tcg_exec_realizefn(CPUState *cpu, Error **errp);
-void tcg_exec_unrealizefn(CPUState *cpu);
-
 /* Return the current PC from CPU, which may be cached in TB. */
 static inline vaddr log_pc(CPUState *cpu, const TranslationBlock *tb)
 {
@@ -93,6 +64,18 @@ static inline vaddr log_pc(CPUState *cpu, const TranslationBlock *tb)
     }
 }
 
+/*
+ * Return true if CS is not running in parallel with other cpus, either
+ * because there are no other cpus or we are within an exclusive context.
+ */
+static inline bool cpu_in_serial_context(CPUState *cs)
+{
+    return !(cs->tcg_cflags & CF_PARALLEL) || cpu_in_exclusive_context(cs);
+}
+
+extern int64_t max_delay;
+extern int64_t max_advance;
+
 extern bool one_insn_per_tb;
 
 /**

accel/tcg/ldst_atomicity.c.inc

@@ -26,7 +26,7 @@
  * If the operation must be split into two operations to be
  * examined separately for atomicity, return -lg2.
  */
-static int required_atomicity(CPUState *cpu, uintptr_t p, MemOp memop)
+static int required_atomicity(CPUArchState *env, uintptr_t p, MemOp memop)
 {
     MemOp atom = memop & MO_ATOM_MASK;
     MemOp size = memop & MO_SIZE;
@@ -93,7 +93,7 @@ static int required_atomicity(CPUState *cpu, uintptr_t p, MemOp memop)
      * host atomicity in order to avoid racing.  This reduction
      * avoids looping with cpu_loop_exit_atomic.
      */
-    if (cpu_in_serial_context(cpu)) {
+    if (cpu_in_serial_context(env_cpu(env))) {
         return MO_8;
     }
     return atmax;
@@ -139,14 +139,14 @@ static inline uint64_t load_atomic8(void *pv)
 
 /**
  * load_atomic8_or_exit:
- * @cpu: generic cpu state
+ * @env: cpu context
  * @ra: host unwind address
  * @pv: host address
  *
  * Atomically load 8 aligned bytes from @pv.
  * If this is not possible, longjmp out to restart serially.
  */
-static uint64_t load_atomic8_or_exit(CPUState *cpu, uintptr_t ra, void *pv)
+static uint64_t load_atomic8_or_exit(CPUArchState *env, uintptr_t ra, void *pv)
 {
     if (HAVE_al8) {
         return load_atomic8(pv);
@@ -159,28 +159,26 @@ static uint64_t load_atomic8_or_exit(CPUState *cpu, uintptr_t ra, void *pv)
      * another process, because the fallback start_exclusive solution
      * provides no protection across processes.
      */
-    WITH_MMAP_LOCK_GUARD() {
-        if (!page_check_range(h2g(pv), 8, PAGE_WRITE_ORG)) {
-            uint64_t *p = __builtin_assume_aligned(pv, 8);
-            return *p;
-        }
+    if (!page_check_range(h2g(pv), 8, PAGE_WRITE_ORG)) {
+        uint64_t *p = __builtin_assume_aligned(pv, 8);
+        return *p;
     }
 #endif
 
     /* Ultimate fallback: re-execute in serial context. */
-    cpu_loop_exit_atomic(cpu, ra);
+    cpu_loop_exit_atomic(env_cpu(env), ra);
 }
 
 /**
  * load_atomic16_or_exit:
- * @cpu: generic cpu state
+ * @env: cpu context
  * @ra: host unwind address
  * @pv: host address
  *
  * Atomically load 16 aligned bytes from @pv.
  * If this is not possible, longjmp out to restart serially.
  */
-static Int128 load_atomic16_or_exit(CPUState *cpu, uintptr_t ra, void *pv)
+static Int128 load_atomic16_or_exit(CPUArchState *env, uintptr_t ra, void *pv)
 {
     Int128 *p = __builtin_assume_aligned(pv, 16);
 
@@ -188,31 +186,29 @@ static Int128 load_atomic16_or_exit(CPUState *cpu, uintptr_t ra, void *pv)
         return atomic16_read_ro(p);
     }
 
+#ifdef CONFIG_USER_ONLY
     /*
      * We can only use cmpxchg to emulate a load if the page is writable.
      * If the page is not writable, then assume the value is immutable
      * and requires no locking.  This ignores the case of MAP_SHARED with
      * another process, because the fallback start_exclusive solution
      * provides no protection across processes.
-     *
-     * In system mode all guest pages are writable.  For user mode,
-     * we must take mmap_lock so that the query remains valid until
-     * the write is complete -- tests/tcg/multiarch/munmap-pthread.c
-     * is an example that can race.
      */
-    WITH_MMAP_LOCK_GUARD() {
-#ifdef CONFIG_USER_ONLY
-        if (!page_check_range(h2g(p), 16, PAGE_WRITE_ORG)) {
-            return *p;
-        }
+    if (!page_check_range(h2g(p), 16, PAGE_WRITE_ORG)) {
+        return *p;
+    }
 #endif
-        if (HAVE_ATOMIC128_RW) {
-            return atomic16_read_rw(p);
-        }
+
+    /*
+     * In system mode all guest pages are writable, and for user-only
+     * we have just checked writability.  Try cmpxchg.
+     */
+    if (HAVE_ATOMIC128_RW) {
+        return atomic16_read_rw(p);
     }
 
     /* Ultimate fallback: re-execute in serial context. */
-    cpu_loop_exit_atomic(cpu, ra);
+    cpu_loop_exit_atomic(env_cpu(env), ra);
 }
 
 /**
@@ -263,7 +259,7 @@ static uint64_t load_atom_extract_al8x2(void *pv)
 
 /**
  * load_atom_extract_al8_or_exit:
- * @cpu: generic cpu state
+ * @env: cpu context
  * @ra: host unwind address
  * @pv: host address
  * @s: object size in bytes, @s <= 4.
@@ -273,7 +269,7 @@ static uint64_t load_atom_extract_al8x2(void *pv)
  * 8-byte load and extract.
  * The value is returned in the low bits of a uint32_t.
  */
-static uint32_t load_atom_extract_al8_or_exit(CPUState *cpu, uintptr_t ra,
+static uint32_t load_atom_extract_al8_or_exit(CPUArchState *env, uintptr_t ra,
                                               void *pv, int s)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -281,12 +277,12 @@ static uint32_t load_atom_extract_al8_or_exit(CPUState *cpu, uintptr_t ra,
     int shr = (HOST_BIG_ENDIAN ? 8 - s - o : o) * 8;
 
     pv = (void *)(pi & ~7);
-    return load_atomic8_or_exit(cpu, ra, pv) >> shr;
+    return load_atomic8_or_exit(env, ra, pv) >> shr;
 }
 
 /**
  * load_atom_extract_al16_or_exit:
- * @cpu: generic cpu state
+ * @env: cpu context
  * @ra: host unwind address
  * @p: host address
  * @s: object size in bytes, @s <= 8.
@@ -299,7 +295,7 @@ static uint32_t load_atom_extract_al8_or_exit(CPUState *cpu, uintptr_t ra,
  *
  * If this is not possible, longjmp out to restart serially.
  */
-static uint64_t load_atom_extract_al16_or_exit(CPUState *cpu, uintptr_t ra,
+static uint64_t load_atom_extract_al16_or_exit(CPUArchState *env, uintptr_t ra,
                                                void *pv, int s)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -312,7 +308,7 @@ static uint64_t load_atom_extract_al16_or_exit(CPUState *cpu, uintptr_t ra,
      * Provoke SIGBUS if possible otherwise.
      */
     pv = (void *)(pi & ~7);
-    r = load_atomic16_or_exit(cpu, ra, pv);
+    r = load_atomic16_or_exit(env, ra, pv);
 
     r = int128_urshift(r, shr);
     return int128_getlo(r);
@@ -394,7 +390,7 @@ static inline uint64_t load_atom_8_by_8_or_4(void *pv)
  *
  * Load 2 bytes from @p, honoring the atomicity of @memop.
  */
-static uint16_t load_atom_2(CPUState *cpu, uintptr_t ra,
+static uint16_t load_atom_2(CPUArchState *env, uintptr_t ra,
                             void *pv, MemOp memop)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -404,13 +400,10 @@ static uint16_t load_atom_2(CPUState *cpu, uintptr_t ra,
         return load_atomic2(pv);
     }
     if (HAVE_ATOMIC128_RO) {
-        intptr_t left_in_page = -(pi | TARGET_PAGE_MASK);
-        if (likely(left_in_page > 8)) {
-            return load_atom_extract_al16_or_al8(pv, 2);
-        }
+        return load_atom_extract_al16_or_al8(pv, 2);
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     switch (atmax) {
     case MO_8:
         return lduw_he_p(pv);
@@ -421,9 +414,9 @@ static uint16_t load_atom_2(CPUState *cpu, uintptr_t ra,
             return load_atomic4(pv - 1) >> 8;
         }
         if ((pi & 15) != 7) {
-            return load_atom_extract_al8_or_exit(cpu, ra, pv, 2);
+            return load_atom_extract_al8_or_exit(env, ra, pv, 2);
         }
-        return load_atom_extract_al16_or_exit(cpu, ra, pv, 2);
+        return load_atom_extract_al16_or_exit(env, ra, pv, 2);
     default:
         g_assert_not_reached();
     }
@@ -436,7 +429,7 @@ static uint16_t load_atom_2(CPUState *cpu, uintptr_t ra,
  *
  * Load 4 bytes from @p, honoring the atomicity of @memop.
  */
-static uint32_t load_atom_4(CPUState *cpu, uintptr_t ra,
+static uint32_t load_atom_4(CPUArchState *env, uintptr_t ra,
                             void *pv, MemOp memop)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -446,13 +439,10 @@ static uint32_t load_atom_4(CPUState *cpu, uintptr_t ra,
         return load_atomic4(pv);
     }
     if (HAVE_ATOMIC128_RO) {
-        intptr_t left_in_page = -(pi | TARGET_PAGE_MASK);
-        if (likely(left_in_page > 8)) {
-            return load_atom_extract_al16_or_al8(pv, 4);
-        }
+        return load_atom_extract_al16_or_al8(pv, 4);
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     switch (atmax) {
     case MO_8:
     case MO_16:
@@ -466,9 +456,9 @@ static uint32_t load_atom_4(CPUState *cpu, uintptr_t ra,
         return load_atom_extract_al4x2(pv);
     case MO_32:
         if (!(pi & 4)) {
-            return load_atom_extract_al8_or_exit(cpu, ra, pv, 4);
+            return load_atom_extract_al8_or_exit(env, ra, pv, 4);
         }
-        return load_atom_extract_al16_or_exit(cpu, ra, pv, 4);
+        return load_atom_extract_al16_or_exit(env, ra, pv, 4);
     default:
         g_assert_not_reached();
     }
@@ -481,7 +471,7 @@ static uint32_t load_atom_4(CPUState *cpu, uintptr_t ra,
  *
  * Load 8 bytes from @p, honoring the atomicity of @memop.
  */
-static uint64_t load_atom_8(CPUState *cpu, uintptr_t ra,
+static uint64_t load_atom_8(CPUArchState *env, uintptr_t ra,
                             void *pv, MemOp memop)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -498,12 +488,12 @@ static uint64_t load_atom_8(CPUState *cpu, uintptr_t ra,
         return load_atom_extract_al16_or_al8(pv, 8);
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     if (atmax == MO_64) {
         if (!HAVE_al8 && (pi & 7) == 0) {
-            load_atomic8_or_exit(cpu, ra, pv);
+            load_atomic8_or_exit(env, ra, pv);
         }
-        return load_atom_extract_al16_or_exit(cpu, ra, pv, 8);
+        return load_atom_extract_al16_or_exit(env, ra, pv, 8);
     }
     if (HAVE_al8_fast) {
         return load_atom_extract_al8x2(pv);
@@ -519,7 +509,7 @@ static uint64_t load_atom_8(CPUState *cpu, uintptr_t ra,
         if (HAVE_al8) {
             return load_atom_extract_al8x2(pv);
         }
-        cpu_loop_exit_atomic(cpu, ra);
+        cpu_loop_exit_atomic(env_cpu(env), ra);
     default:
         g_assert_not_reached();
     }
@@ -532,7 +522,7 @@ static uint64_t load_atom_8(CPUState *cpu, uintptr_t ra,
  *
  * Load 16 bytes from @p, honoring the atomicity of @memop.
  */
-static Int128 load_atom_16(CPUState *cpu, uintptr_t ra,
+static Int128 load_atom_16(CPUArchState *env, uintptr_t ra,
                            void *pv, MemOp memop)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -548,7 +538,7 @@ static Int128 load_atom_16(CPUState *cpu, uintptr_t ra,
         return atomic16_read_ro(pv);
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     switch (atmax) {
     case MO_8:
         memcpy(&r, pv, 16);
@@ -563,20 +553,20 @@ static Int128 load_atom_16(CPUState *cpu, uintptr_t ra,
         break;
     case MO_64:
         if (!HAVE_al8) {
-            cpu_loop_exit_atomic(cpu, ra);
+            cpu_loop_exit_atomic(env_cpu(env), ra);
         }
         a = load_atomic8(pv);
         b = load_atomic8(pv + 8);
         break;
     case -MO_64:
         if (!HAVE_al8) {
-            cpu_loop_exit_atomic(cpu, ra);
+            cpu_loop_exit_atomic(env_cpu(env), ra);
         }
         a = load_atom_extract_al8x2(pv);
         b = load_atom_extract_al8x2(pv + 8);
         break;
     case MO_128:
-        return load_atomic16_or_exit(cpu, ra, pv);
+        return load_atomic16_or_exit(env, ra, pv);
     default:
         g_assert_not_reached();
     }
@@ -825,7 +815,7 @@ static uint64_t store_whole_le16(void *pv, int size, Int128 val_le)
     int sh = o * 8;
     Int128 m, v;
 
-    qemu_build_assert(HAVE_CMPXCHG128);
+    qemu_build_assert(HAVE_ATOMIC128_RW);
 
     /* Like MAKE_64BIT_MASK(0, sz), but larger. */
     if (sz <= 64) {
@@ -857,7 +847,7 @@ static uint64_t store_whole_le16(void *pv, int size, Int128 val_le)
  *
  * Store 2 bytes to @p, honoring the atomicity of @memop.
  */
-static void store_atom_2(CPUState *cpu, uintptr_t ra,
+static void store_atom_2(CPUArchState *env, uintptr_t ra,
                          void *pv, MemOp memop, uint16_t val)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -868,7 +858,7 @@ static void store_atom_2(CPUState *cpu, uintptr_t ra,
         return;
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     if (atmax == MO_8) {
         stw_he_p(pv, val);
         return;
@@ -887,7 +877,7 @@ static void store_atom_2(CPUState *cpu, uintptr_t ra,
             return;
         }
     } else if ((pi & 15) == 7) {
-        if (HAVE_CMPXCHG128) {
+        if (HAVE_ATOMIC128_RW) {
             Int128 v = int128_lshift(int128_make64(val), 56);
             Int128 m = int128_lshift(int128_make64(0xffff), 56);
             store_atom_insert_al16(pv - 7, v, m);
@@ -897,7 +887,7 @@ static void store_atom_2(CPUState *cpu, uintptr_t ra,
         g_assert_not_reached();
     }
 
-    cpu_loop_exit_atomic(cpu, ra);
+    cpu_loop_exit_atomic(env_cpu(env), ra);
 }
 
 /**
@@ -908,7 +898,7 @@ static void store_atom_2(CPUState *cpu, uintptr_t ra,
  *
  * Store 4 bytes to @p, honoring the atomicity of @memop.
  */
-static void store_atom_4(CPUState *cpu, uintptr_t ra,
+static void store_atom_4(CPUArchState *env, uintptr_t ra,
                          void *pv, MemOp memop, uint32_t val)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -919,7 +909,7 @@ static void store_atom_4(CPUState *cpu, uintptr_t ra,
         return;
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     switch (atmax) {
     case MO_8:
         stl_he_p(pv, val);
@@ -956,12 +946,12 @@ static void store_atom_4(CPUState *cpu, uintptr_t ra,
                 return;
             }
         } else {
-            if (HAVE_CMPXCHG128) {
+            if (HAVE_ATOMIC128_RW) {
                 store_whole_le16(pv, 4, int128_make64(cpu_to_le32(val)));
                 return;
             }
         }
-        cpu_loop_exit_atomic(cpu, ra);
+        cpu_loop_exit_atomic(env_cpu(env), ra);
     default:
         g_assert_not_reached();
     }
@@ -975,7 +965,7 @@ static void store_atom_4(CPUState *cpu, uintptr_t ra,
  *
  * Store 8 bytes to @p, honoring the atomicity of @memop.
  */
-static void store_atom_8(CPUState *cpu, uintptr_t ra,
+static void store_atom_8(CPUArchState *env, uintptr_t ra,
                          void *pv, MemOp memop, uint64_t val)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -986,7 +976,7 @@ static void store_atom_8(CPUState *cpu, uintptr_t ra,
         return;
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
     switch (atmax) {
     case MO_8:
         stq_he_p(pv, val);
@@ -1021,7 +1011,7 @@ static void store_atom_8(CPUState *cpu, uintptr_t ra,
         }
         break;
     case MO_64:
-        if (HAVE_CMPXCHG128) {
+        if (HAVE_ATOMIC128_RW) {
             store_whole_le16(pv, 8, int128_make64(cpu_to_le64(val)));
             return;
         }
@@ -1029,7 +1019,7 @@ static void store_atom_8(CPUState *cpu, uintptr_t ra,
     default:
         g_assert_not_reached();
     }
-    cpu_loop_exit_atomic(cpu, ra);
+    cpu_loop_exit_atomic(env_cpu(env), ra);
 }
 
 /**
@@ -1040,7 +1030,7 @@ static void store_atom_8(CPUState *cpu, uintptr_t ra,
  *
  * Store 16 bytes to @p, honoring the atomicity of @memop.
  */
-static void store_atom_16(CPUState *cpu, uintptr_t ra,
+static void store_atom_16(CPUArchState *env, uintptr_t ra,
                           void *pv, MemOp memop, Int128 val)
 {
     uintptr_t pi = (uintptr_t)pv;
@@ -1052,7 +1042,7 @@ static void store_atom_16(CPUState *cpu, uintptr_t ra,
         return;
     }
 
-    atmax = required_atomicity(cpu, pi, memop);
+    atmax = required_atomicity(env, pi, memop);
 
     a = HOST_BIG_ENDIAN ? int128_gethi(val) : int128_getlo(val);
     b = HOST_BIG_ENDIAN ? int128_getlo(val) : int128_gethi(val);
@@ -1076,7 +1066,7 @@ static void store_atom_16(CPUState *cpu, uintptr_t ra,
         }
         break;
     case -MO_64:
-        if (HAVE_CMPXCHG128) {
+        if (HAVE_ATOMIC128_RW) {
             uint64_t val_le;
             int s2 = pi & 15;
             int s1 = 16 - s2;
@@ -1103,9 +1093,13 @@ static void store_atom_16(CPUState *cpu, uintptr_t ra,
         }
         break;
     case MO_128:
+        if (HAVE_ATOMIC128_RW) {
+            atomic16_set(pv, val);
+            return;
+        }
         break;
     default:
         g_assert_not_reached();
     }
-    cpu_loop_exit_atomic(cpu, ra);
+    cpu_loop_exit_atomic(env_cpu(env), ra);
 }

accel/tcg/ldst_common.c.inc

@@ -8,231 +8,6 @@
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
  */
-/*
- * Load helpers for tcg-ldst.h
- */
-
-tcg_target_ulong helper_ldub_mmu(CPUArchState *env, uint64_t addr,
-                                 MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_8);
-    return do_ld1_mmu(env_cpu(env), addr, oi, retaddr, MMU_DATA_LOAD);
-}
-
-tcg_target_ulong helper_lduw_mmu(CPUArchState *env, uint64_t addr,
-                                 MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
-    return do_ld2_mmu(env_cpu(env), addr, oi, retaddr, MMU_DATA_LOAD);
-}
-
-tcg_target_ulong helper_ldul_mmu(CPUArchState *env, uint64_t addr,
-                                 MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
-    return do_ld4_mmu(env_cpu(env), addr, oi, retaddr, MMU_DATA_LOAD);
-}
-
-uint64_t helper_ldq_mmu(CPUArchState *env, uint64_t addr,
-                        MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
-    return do_ld8_mmu(env_cpu(env), addr, oi, retaddr, MMU_DATA_LOAD);
-}
-
-/*
- * Provide signed versions of the load routines as well.  We can of course
- * avoid this for 64-bit data, or for 32-bit data on 32-bit host.
- */
-
-tcg_target_ulong helper_ldsb_mmu(CPUArchState *env, uint64_t addr,
-                                 MemOpIdx oi, uintptr_t retaddr)
-{
-    return (int8_t)helper_ldub_mmu(env, addr, oi, retaddr);
-}
-
-tcg_target_ulong helper_ldsw_mmu(CPUArchState *env, uint64_t addr,
-                                 MemOpIdx oi, uintptr_t retaddr)
-{
-    return (int16_t)helper_lduw_mmu(env, addr, oi, retaddr);
-}
-
-tcg_target_ulong helper_ldsl_mmu(CPUArchState *env, uint64_t addr,
-                                 MemOpIdx oi, uintptr_t retaddr)
-{
-    return (int32_t)helper_ldul_mmu(env, addr, oi, retaddr);
-}
-
-Int128 helper_ld16_mmu(CPUArchState *env, uint64_t addr,
-                       MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
-    return do_ld16_mmu(env_cpu(env), addr, oi, retaddr);
-}
-
-Int128 helper_ld_i128(CPUArchState *env, uint64_t addr, uint32_t oi)
-{
-    return helper_ld16_mmu(env, addr, oi, GETPC());
-}
-
-/*
- * Store helpers for tcg-ldst.h
- */
-
-void helper_stb_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
-                    MemOpIdx oi, uintptr_t ra)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_8);
-    do_st1_mmu(env_cpu(env), addr, val, oi, ra);
-}
-
-void helper_stw_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
-                    MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
-    do_st2_mmu(env_cpu(env), addr, val, oi, retaddr);
-}
-
-void helper_stl_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
-                    MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
-    do_st4_mmu(env_cpu(env), addr, val, oi, retaddr);
-}
-
-void helper_stq_mmu(CPUArchState *env, uint64_t addr, uint64_t val,
-                    MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
-    do_st8_mmu(env_cpu(env), addr, val, oi, retaddr);
-}
-
-void helper_st16_mmu(CPUArchState *env, uint64_t addr, Int128 val,
-                     MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
-    do_st16_mmu(env_cpu(env), addr, val, oi, retaddr);
-}
-
-void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
-{
-    helper_st16_mmu(env, addr, val, oi, GETPC());
-}
-
-/*
- * Load helpers for cpu_ldst.h
- */
-
-static void plugin_load_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
-{
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
-}
-
-uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra)
-{
-    uint8_t ret;
-
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_UB);
-    ret = do_ld1_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
-    plugin_load_cb(env, addr, oi);
-    return ret;
-}
-
-uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr addr,
-                     MemOpIdx oi, uintptr_t ra)
-{
-    uint16_t ret;
-
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
-    ret = do_ld2_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
-    plugin_load_cb(env, addr, oi);
-    return ret;
-}
-
-uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr addr,
-                     MemOpIdx oi, uintptr_t ra)
-{
-    uint32_t ret;
-
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
-    ret = do_ld4_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
-    plugin_load_cb(env, addr, oi);
-    return ret;
-}
-
-uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr addr,
-                     MemOpIdx oi, uintptr_t ra)
-{
-    uint64_t ret;
-
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
-    ret = do_ld8_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
-    plugin_load_cb(env, addr, oi);
-    return ret;
-}
-
-Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
-                    MemOpIdx oi, uintptr_t ra)
-{
-    Int128 ret;
-
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
-    ret = do_ld16_mmu(env_cpu(env), addr, oi, ra);
-    plugin_load_cb(env, addr, oi);
-    return ret;
-}
-
-/*
- * Store helpers for cpu_ldst.h
- */
-
-static void plugin_store_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
-{
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
-}
-
-void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,
-                 MemOpIdx oi, uintptr_t retaddr)
-{
-    helper_stb_mmu(env, addr, val, oi, retaddr);
-    plugin_store_cb(env, addr, oi);
-}
-
-void cpu_stw_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
-                 MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
-    do_st2_mmu(env_cpu(env), addr, val, oi, retaddr);
-    plugin_store_cb(env, addr, oi);
-}
-
-void cpu_stl_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
-                    MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
-    do_st4_mmu(env_cpu(env), addr, val, oi, retaddr);
-    plugin_store_cb(env, addr, oi);
-}
-
-void cpu_stq_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
-                 MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
-    do_st8_mmu(env_cpu(env), addr, val, oi, retaddr);
-    plugin_store_cb(env, addr, oi);
-}
-
-void cpu_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val,
-                  MemOpIdx oi, uintptr_t retaddr)
-{
-    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
-    do_st16_mmu(env_cpu(env), addr, val, oi, retaddr);
-    plugin_store_cb(env, addr, oi);
-}
-
-/*
- * Wrappers of the above
- */
 
 uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                             int mmu_idx, uintptr_t ra)

accel/tcg/meson.build

@@ -1,9 +1,7 @@
 tcg_ss = ss.source_set()
-common_ss.add(when: 'CONFIG_TCG', if_true: files(
-  'cpu-exec-common.c',
-))
 tcg_ss.add(files(
   'tcg-all.c',
+  'cpu-exec-common.c',
   'cpu-exec.c',
   'tb-maint.c',
   'tcg-runtime-gvec.c',
@@ -13,19 +11,13 @@ tcg_ss.add(files(
 ))
 tcg_ss.add(when: 'CONFIG_USER_ONLY', if_true: files('user-exec.c'))
 tcg_ss.add(when: 'CONFIG_SYSTEM_ONLY', if_false: files('user-exec-stub.c'))
-if get_option('plugins')
-  tcg_ss.add(files('plugin-gen.c'))
-endif
+tcg_ss.add(when: 'CONFIG_PLUGIN', if_true: [files('plugin-gen.c')])
 tcg_ss.add(when: libdw, if_true: files('debuginfo.c'))
 tcg_ss.add(when: 'CONFIG_LINUX', if_true: files('perf.c'))
 specific_ss.add_all(when: 'CONFIG_TCG', if_true: tcg_ss)
 
 specific_ss.add(when: ['CONFIG_SYSTEM_ONLY', 'CONFIG_TCG'], if_true: files(
   'cputlb.c',
-))
-
-system_ss.add(when: ['CONFIG_TCG'], if_true: files(
-  'icount-common.c',
   'monitor.c',
 ))
 

accel/tcg/monitor.c

@@ -8,7 +8,6 @@
 
 #include "qemu/osdep.h"
 #include "qemu/accel.h"
-#include "qemu/qht.h"
 #include "qapi/error.h"
 #include "qapi/type-helpers.h"
 #include "qapi/qapi-commands-machine.h"
@@ -17,8 +16,7 @@
 #include "sysemu/cpu-timers.h"
 #include "sysemu/tcg.h"
 #include "tcg/tcg.h"
-#include "internal-common.h"
-#include "tb-context.h"
+#include "internal.h"
 
 
 static void dump_drift_info(GString *buf)
@@ -52,153 +50,6 @@ static void dump_accel_info(GString *buf)
                            one_insn_per_tb ? "on" : "off");
 }
 
-static void print_qht_statistics(struct qht_stats hst, GString *buf)
-{
-    uint32_t hgram_opts;
-    size_t hgram_bins;
-    char *hgram;
-
-    if (!hst.head_buckets) {
-        return;
-    }
-    g_string_append_printf(buf, "TB hash buckets     %zu/%zu "
-                           "(%0.2f%% head buckets used)\n",
-                           hst.used_head_buckets, hst.head_buckets,
-                           (double)hst.used_head_buckets /
-                           hst.head_buckets * 100);
-
-    hgram_opts =  QDIST_PR_BORDER | QDIST_PR_LABELS;
-    hgram_opts |= QDIST_PR_100X   | QDIST_PR_PERCENT;
-    if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
-        hgram_opts |= QDIST_PR_NODECIMAL;
-    }
-    hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
-    g_string_append_printf(buf, "TB hash occupancy   %0.2f%% avg chain occ. "
-                           "Histogram: %s\n",
-                           qdist_avg(&hst.occupancy) * 100, hgram);
-    g_free(hgram);
-
-    hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
-    hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
-    if (hgram_bins > 10) {
-        hgram_bins = 10;
-    } else {
-        hgram_bins = 0;
-        hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
-    }
-    hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
-    g_string_append_printf(buf, "TB hash avg chain   %0.3f buckets. "
-                           "Histogram: %s\n",
-                           qdist_avg(&hst.chain), hgram);
-    g_free(hgram);
-}
-
-struct tb_tree_stats {
-    size_t nb_tbs;
-    size_t host_size;
-    size_t target_size;
-    size_t max_target_size;
-    size_t direct_jmp_count;
-    size_t direct_jmp2_count;
-    size_t cross_page;
-};
-
-static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data)
-{
-    const TranslationBlock *tb = value;
-    struct tb_tree_stats *tst = data;
-
-    tst->nb_tbs++;
-    tst->host_size += tb->tc.size;
-    tst->target_size += tb->size;
-    if (tb->size > tst->max_target_size) {
-        tst->max_target_size = tb->size;
-    }
-    if (tb->page_addr[1] != -1) {
-        tst->cross_page++;
-    }
-    if (tb->jmp_reset_offset[0] != TB_JMP_OFFSET_INVALID) {
-        tst->direct_jmp_count++;
-        if (tb->jmp_reset_offset[1] != TB_JMP_OFFSET_INVALID) {
-            tst->direct_jmp2_count++;
-        }
-    }
-    return false;
-}
-
-static void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)
-{
-    CPUState *cpu;
-    size_t full = 0, part = 0, elide = 0;
-
-    CPU_FOREACH(cpu) {
-        full += qatomic_read(&cpu->neg.tlb.c.full_flush_count);
-        part += qatomic_read(&cpu->neg.tlb.c.part_flush_count);
-        elide += qatomic_read(&cpu->neg.tlb.c.elide_flush_count);
-    }
-    *pfull = full;
-    *ppart = part;
-    *pelide = elide;
-}
-
-static void tcg_dump_info(GString *buf)
-{
-    g_string_append_printf(buf, "[TCG profiler not compiled]\n");
-}
-
-static void dump_exec_info(GString *buf)
-{
-    struct tb_tree_stats tst = {};
-    struct qht_stats hst;
-    size_t nb_tbs, flush_full, flush_part, flush_elide;
-
-    tcg_tb_foreach(tb_tree_stats_iter, &tst);
-    nb_tbs = tst.nb_tbs;
-    /* XXX: avoid using doubles ? */
-    g_string_append_printf(buf, "Translation buffer state:\n");
-    /*
-     * Report total code size including the padding and TB structs;
-     * otherwise users might think "-accel tcg,tb-size" is not honoured.
-     * For avg host size we use the precise numbers from tb_tree_stats though.
-     */
-    g_string_append_printf(buf, "gen code size       %zu/%zu\n",
-                           tcg_code_size(), tcg_code_capacity());
-    g_string_append_printf(buf, "TB count            %zu\n", nb_tbs);
-    g_string_append_printf(buf, "TB avg target size  %zu max=%zu bytes\n",
-                           nb_tbs ? tst.target_size / nb_tbs : 0,
-                           tst.max_target_size);
-    g_string_append_printf(buf, "TB avg host size    %zu bytes "
-                           "(expansion ratio: %0.1f)\n",
-                           nb_tbs ? tst.host_size / nb_tbs : 0,
-                           tst.target_size ?
-                           (double)tst.host_size / tst.target_size : 0);
-    g_string_append_printf(buf, "cross page TB count %zu (%zu%%)\n",
-                           tst.cross_page,
-                           nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
-    g_string_append_printf(buf, "direct jump count   %zu (%zu%%) "
-                           "(2 jumps=%zu %zu%%)\n",
-                           tst.direct_jmp_count,
-                           nb_tbs ? (tst.direct_jmp_count * 100) / nb_tbs : 0,
-                           tst.direct_jmp2_count,
-                           nb_tbs ? (tst.direct_jmp2_count * 100) / nb_tbs : 0);
-
-    qht_statistics_init(&tb_ctx.htable, &hst);
-    print_qht_statistics(hst, buf);
-    qht_statistics_destroy(&hst);
-
-    g_string_append_printf(buf, "\nStatistics:\n");
-    g_string_append_printf(buf, "TB flush count      %u\n",
-                           qatomic_read(&tb_ctx.tb_flush_count));
-    g_string_append_printf(buf, "TB invalidate count %u\n",
-                           qatomic_read(&tb_ctx.tb_phys_invalidate_count));
-
-    tlb_flush_counts(&flush_full, &flush_part, &flush_elide);
-    g_string_append_printf(buf, "TLB full flushes    %zu\n", flush_full);
-    g_string_append_printf(buf, "TLB partial flushes %zu\n", flush_part);
-    g_string_append_printf(buf, "TLB elided flushes  %zu\n", flush_elide);
-    tcg_dump_info(buf);
-}
-
 HumanReadableText *qmp_x_query_jit(Error **errp)
 {
     g_autoptr(GString) buf = g_string_new("");
@@ -215,11 +66,6 @@ HumanReadableText *qmp_x_query_jit(Error **errp)
     return human_readable_text_from_str(buf);
 }
 
-static void tcg_dump_op_count(GString *buf)
-{
-    g_string_append_printf(buf, "[TCG profiler not compiled]\n");
-}
-
 HumanReadableText *qmp_x_query_opcount(Error **errp)
 {
     g_autoptr(GString) buf = g_string_new("");

accel/tcg/plugin-gen.c

@@ -104,7 +104,7 @@ static void gen_empty_udata_cb(void)
     TCGv_ptr udata = tcg_temp_ebb_new_ptr();
 
     tcg_gen_movi_ptr(udata, 0);
-    tcg_gen_ld_i32(cpu_index, tcg_env,
+    tcg_gen_ld_i32(cpu_index, cpu_env,
                    -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
     gen_helper_plugin_vcpu_udata_cb(cpu_index, udata);
 
@@ -138,7 +138,7 @@ static void gen_empty_mem_cb(TCGv_i64 addr, uint32_t info)
 
     tcg_gen_movi_i32(meminfo, info);
     tcg_gen_movi_ptr(udata, 0);
-    tcg_gen_ld_i32(cpu_index, tcg_env,
+    tcg_gen_ld_i32(cpu_index, cpu_env,
                    -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
 
     gen_helper_plugin_vcpu_mem_cb(cpu_index, meminfo, addr, udata);
@@ -157,7 +157,7 @@ static void gen_empty_mem_helper(void)
     TCGv_ptr ptr = tcg_temp_ebb_new_ptr();
 
     tcg_gen_movi_ptr(ptr, 0);
-    tcg_gen_st_ptr(ptr, tcg_env, offsetof(CPUState, plugin_mem_cbs) -
+    tcg_gen_st_ptr(ptr, cpu_env, offsetof(CPUState, plugin_mem_cbs) -
                                  offsetof(ArchCPU, env));
     tcg_temp_free_ptr(ptr);
 }
@@ -327,7 +327,8 @@ static TCGOp *copy_st_ptr(TCGOp **begin_op, TCGOp *op)
     return op;
 }
 
-static TCGOp *copy_call(TCGOp **begin_op, TCGOp *op, void *func, int *cb_idx)
+static TCGOp *copy_call(TCGOp **begin_op, TCGOp *op, void *empty_func,
+                        void *func, int *cb_idx)
 {
     TCGOp *old_op;
     int func_idx;
@@ -371,7 +372,8 @@ static TCGOp *append_udata_cb(const struct qemu_plugin_dyn_cb *cb,
     }
 
     /* call */
-    op = copy_call(&begin_op, op, cb->f.vcpu_udata, cb_idx);
+    op = copy_call(&begin_op, op, HELPER(plugin_vcpu_udata_cb),
+                   cb->f.vcpu_udata, cb_idx);
 
     return op;
 }
@@ -418,7 +420,8 @@ static TCGOp *append_mem_cb(const struct qemu_plugin_dyn_cb *cb,
 
     if (type == PLUGIN_GEN_CB_MEM) {
         /* call */
-        op = copy_call(&begin_op, op, cb->f.vcpu_udata, cb_idx);
+        op = copy_call(&begin_op, op, HELPER(plugin_vcpu_mem_cb),
+                       cb->f.vcpu_udata, cb_idx);
     }
 
     return op;
@@ -578,7 +581,7 @@ void plugin_gen_disable_mem_helpers(void)
     if (!tcg_ctx->plugin_tb->mem_helper) {
         return;
     }
-    tcg_gen_st_ptr(tcg_constant_ptr(NULL), tcg_env,
+    tcg_gen_st_ptr(tcg_constant_ptr(NULL), cpu_env,
                    offsetof(CPUState, plugin_mem_cbs) - offsetof(ArchCPU, env));
 }
 
@@ -846,7 +849,7 @@ void plugin_gen_insn_start(CPUState *cpu, const DisasContextBase *db)
     } else {
         if (ptb->vaddr2 == -1) {
             ptb->vaddr2 = TARGET_PAGE_ALIGN(db->pc_first);
-            get_page_addr_code_hostp(cpu_env(cpu), ptb->vaddr2, &ptb->haddr2);
+            get_page_addr_code_hostp(cpu->env_ptr, ptb->vaddr2, &ptb->haddr2);
         }
         pinsn->haddr = ptb->haddr2 + pinsn->vaddr - ptb->vaddr2;
     }
@@ -863,14 +866,10 @@ void plugin_gen_insn_end(void)
  * do any clean-up here and make sure things are reset in
  * plugin_gen_tb_start.
  */
-void plugin_gen_tb_end(CPUState *cpu, size_t num_insns)
+void plugin_gen_tb_end(CPUState *cpu)
 {
     struct qemu_plugin_tb *ptb = tcg_ctx->plugin_tb;
 
-    /* translator may have removed instructions, update final count */
-    g_assert(num_insns <= ptb->n);
-    ptb->n = num_insns;
-
     /* collect instrumentation requests */
     qemu_plugin_tb_trans_cb(cpu, ptb);
 

accel/tcg/tb-maint.c

@@ -1,5 +1,5 @@
 /*
- * Translation Block Maintenance
+ * Translation Block Maintaince
  *
  *  Copyright (c) 2003 Fabrice Bellard
  *
@@ -29,8 +29,7 @@
 #include "tcg/tcg.h"
 #include "tb-hash.h"
 #include "tb-context.h"
-#include "internal-common.h"
-#include "internal-target.h"
+#include "internal.h"
 
 
 /* List iterators for lists of tagged pointers in TranslationBlock. */
@@ -47,7 +46,7 @@ static bool tb_cmp(const void *ap, const void *bp)
     const TranslationBlock *a = ap;
     const TranslationBlock *b = bp;
 
-    return (a->pc == b->pc &&
+    return ((tb_cflags(a) & CF_PCREL || a->pc == b->pc) &&
             a->cs_base == b->cs_base &&
             a->flags == b->flags &&
             (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) &&
@@ -71,7 +70,17 @@ typedef struct PageDesc PageDesc;
  */
 #define assert_page_locked(pd) tcg_debug_assert(have_mmap_lock())
 
-static inline void tb_lock_pages(const TranslationBlock *tb) { }
+static inline void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1,
+                                  PageDesc **ret_p2, tb_page_addr_t phys2,
+                                  bool alloc)
+{
+    *ret_p1 = NULL;
+    *ret_p2 = NULL;
+}
+
+static inline void page_unlock(PageDesc *pd) { }
+static inline void page_lock_tb(const TranslationBlock *tb) { }
+static inline void page_unlock_tb(const TranslationBlock *tb) { }
 
 /*
  * For user-only, since we are protecting all of memory with a single lock,
@@ -87,7 +96,7 @@ static void tb_remove_all(void)
 }
 
 /* Call with mmap_lock held. */
-static void tb_record(TranslationBlock *tb)
+static void tb_record(TranslationBlock *tb, PageDesc *p1, PageDesc *p2)
 {
     vaddr addr;
     int flags;
@@ -208,12 +217,13 @@ static PageDesc *page_find_alloc(tb_page_addr_t index, bool alloc)
 {
     PageDesc *pd;
     void **lp;
+    int i;
 
     /* Level 1.  Always allocated.  */
     lp = l1_map + ((index >> v_l1_shift) & (v_l1_size - 1));
 
     /* Level 2..N-1.  */
-    for (int i = v_l2_levels; i > 0; i--) {
+    for (i = v_l2_levels; i > 0; i--) {
         void **p = qatomic_rcu_read(lp);
 
         if (p == NULL) {
@@ -381,108 +391,12 @@ static void page_lock(PageDesc *pd)
     qemu_spin_lock(&pd->lock);
 }
 
-/* Like qemu_spin_trylock, returns false on success */
-static bool page_trylock(PageDesc *pd)
-{
-    bool busy = qemu_spin_trylock(&pd->lock);
-    if (!busy) {
-        page_lock__debug(pd);
-    }
-    return busy;
-}
-
 static void page_unlock(PageDesc *pd)
 {
     qemu_spin_unlock(&pd->lock);
     page_unlock__debug(pd);
 }
 
-void tb_lock_page0(tb_page_addr_t paddr)
-{
-    page_lock(page_find_alloc(paddr >> TARGET_PAGE_BITS, true));
-}
-
-void tb_lock_page1(tb_page_addr_t paddr0, tb_page_addr_t paddr1)
-{
-    tb_page_addr_t pindex0 = paddr0 >> TARGET_PAGE_BITS;
-    tb_page_addr_t pindex1 = paddr1 >> TARGET_PAGE_BITS;
-    PageDesc *pd0, *pd1;
-
-    if (pindex0 == pindex1) {
-        /* Identical pages, and the first page is already locked. */
-        return;
-    }
-
-    pd1 = page_find_alloc(pindex1, true);
-    if (pindex0 < pindex1) {
-        /* Correct locking order, we may block. */
-        page_lock(pd1);
-        return;
-    }
-
-    /* Incorrect locking order, we cannot block lest we deadlock. */
-    if (!page_trylock(pd1)) {
-        return;
-    }
-
-    /*
-     * Drop the lock on page0 and get both page locks in the right order.
-     * Restart translation via longjmp.
-     */
-    pd0 = page_find_alloc(pindex0, false);
-    page_unlock(pd0);
-    page_lock(pd1);
-    page_lock(pd0);
-    siglongjmp(tcg_ctx->jmp_trans, -3);
-}
-
-void tb_unlock_page1(tb_page_addr_t paddr0, tb_page_addr_t paddr1)
-{
-    tb_page_addr_t pindex0 = paddr0 >> TARGET_PAGE_BITS;
-    tb_page_addr_t pindex1 = paddr1 >> TARGET_PAGE_BITS;
-
-    if (pindex0 != pindex1) {
-        page_unlock(page_find_alloc(pindex1, false));
-    }
-}
-
-static void tb_lock_pages(TranslationBlock *tb)
-{
-    tb_page_addr_t paddr0 = tb_page_addr0(tb);
-    tb_page_addr_t paddr1 = tb_page_addr1(tb);
-    tb_page_addr_t pindex0 = paddr0 >> TARGET_PAGE_BITS;
-    tb_page_addr_t pindex1 = paddr1 >> TARGET_PAGE_BITS;
-
-    if (unlikely(paddr0 == -1)) {
-        return;
-    }
-    if (unlikely(paddr1 != -1) && pindex0 != pindex1) {
-        if (pindex0 < pindex1) {
-            page_lock(page_find_alloc(pindex0, true));
-            page_lock(page_find_alloc(pindex1, true));
-            return;
-        }
-        page_lock(page_find_alloc(pindex1, true));
-    }
-    page_lock(page_find_alloc(pindex0, true));
-}
-
-void tb_unlock_pages(TranslationBlock *tb)
-{
-    tb_page_addr_t paddr0 = tb_page_addr0(tb);
-    tb_page_addr_t paddr1 = tb_page_addr1(tb);
-    tb_page_addr_t pindex0 = paddr0 >> TARGET_PAGE_BITS;
-    tb_page_addr_t pindex1 = paddr1 >> TARGET_PAGE_BITS;
-
-    if (unlikely(paddr0 == -1)) {
-        return;
-    }
-    if (unlikely(paddr1 != -1) && pindex0 != pindex1) {
-        page_unlock(page_find_alloc(pindex1, false));
-    }
-    page_unlock(page_find_alloc(pindex0, false));
-}
-
 static inline struct page_entry *
 page_entry_new(PageDesc *pd, tb_page_addr_t index)
 {
@@ -506,10 +420,13 @@ static void page_entry_destroy(gpointer p)
 /* returns false on success */
 static bool page_entry_trylock(struct page_entry *pe)
 {
-    bool busy = page_trylock(pe->pd);
+    bool busy;
+
+    busy = qemu_spin_trylock(&pe->pd->lock);
     if (!busy) {
         g_assert(!pe->locked);
         pe->locked = true;
+        page_lock__debug(pe->pd);
     }
     return busy;
 }
@@ -687,7 +604,8 @@ static void tb_remove_all(void)
  * Add the tb in the target page and protect it if necessary.
  * Called with @p->lock held.
  */
-static void tb_page_add(PageDesc *p, TranslationBlock *tb, unsigned int n)
+static inline void tb_page_add(PageDesc *p, TranslationBlock *tb,
+                               unsigned int n)
 {
     bool page_already_protected;
 
@@ -707,21 +625,15 @@ static void tb_page_add(PageDesc *p, TranslationBlock *tb, unsigned int n)
     }
 }
 
-static void tb_record(TranslationBlock *tb)
+static void tb_record(TranslationBlock *tb, PageDesc *p1, PageDesc *p2)
 {
-    tb_page_addr_t paddr0 = tb_page_addr0(tb);
-    tb_page_addr_t paddr1 = tb_page_addr1(tb);
-    tb_page_addr_t pindex0 = paddr0 >> TARGET_PAGE_BITS;
-    tb_page_addr_t pindex1 = paddr0 >> TARGET_PAGE_BITS;
-
-    assert(paddr0 != -1);
-    if (unlikely(paddr1 != -1) && pindex0 != pindex1) {
-        tb_page_add(page_find_alloc(pindex1, false), tb, 1);
+    tb_page_add(p1, tb, 0);
+    if (unlikely(p2)) {
+        tb_page_add(p2, tb, 1);
     }
-    tb_page_add(page_find_alloc(pindex0, false), tb, 0);
 }
 
-static void tb_page_remove(PageDesc *pd, TranslationBlock *tb)
+static inline void tb_page_remove(PageDesc *pd, TranslationBlock *tb)
 {
     TranslationBlock *tb1;
     uintptr_t *pprev;
@@ -741,16 +653,74 @@ static void tb_page_remove(PageDesc *pd, TranslationBlock *tb)
 
 static void tb_remove(TranslationBlock *tb)
 {
-    tb_page_addr_t paddr0 = tb_page_addr0(tb);
-    tb_page_addr_t paddr1 = tb_page_addr1(tb);
-    tb_page_addr_t pindex0 = paddr0 >> TARGET_PAGE_BITS;
-    tb_page_addr_t pindex1 = paddr0 >> TARGET_PAGE_BITS;
+    PageDesc *pd;
 
-    assert(paddr0 != -1);
-    if (unlikely(paddr1 != -1) && pindex0 != pindex1) {
-        tb_page_remove(page_find_alloc(pindex1, false), tb);
+    pd = page_find(tb->page_addr[0] >> TARGET_PAGE_BITS);
+    tb_page_remove(pd, tb);
+    if (unlikely(tb->page_addr[1] != -1)) {
+        pd = page_find(tb->page_addr[1] >> TARGET_PAGE_BITS);
+        tb_page_remove(pd, tb);
+    }
+}
+
+static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1,
+                           PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc)
+{
+    PageDesc *p1, *p2;
+    tb_page_addr_t page1;
+    tb_page_addr_t page2;
+
+    assert_memory_lock();
+    g_assert(phys1 != -1);
+
+    page1 = phys1 >> TARGET_PAGE_BITS;
+    page2 = phys2 >> TARGET_PAGE_BITS;
+
+    p1 = page_find_alloc(page1, alloc);
+    if (ret_p1) {
+        *ret_p1 = p1;
+    }
+    if (likely(phys2 == -1)) {
+        page_lock(p1);
+        return;
+    } else if (page1 == page2) {
+        page_lock(p1);
+        if (ret_p2) {
+            *ret_p2 = p1;
+        }
+        return;
+    }
+    p2 = page_find_alloc(page2, alloc);
+    if (ret_p2) {
+        *ret_p2 = p2;
+    }
+    if (page1 < page2) {
+        page_lock(p1);
+        page_lock(p2);
+    } else {
+        page_lock(p2);
+        page_lock(p1);
+    }
+}
+
+/* lock the page(s) of a TB in the correct acquisition order */
+static void page_lock_tb(const TranslationBlock *tb)
+{
+    page_lock_pair(NULL, tb_page_addr0(tb), NULL, tb_page_addr1(tb), false);
+}
+
+static void page_unlock_tb(const TranslationBlock *tb)
+{
+    PageDesc *p1 = page_find(tb_page_addr0(tb) >> TARGET_PAGE_BITS);
+
+    page_unlock(p1);
+    if (unlikely(tb_page_addr1(tb) != -1)) {
+        PageDesc *p2 = page_find(tb_page_addr1(tb) >> TARGET_PAGE_BITS);
+
+        if (p2 != p1) {
+            page_unlock(p2);
+        }
     }
-    tb_page_remove(page_find_alloc(pindex0, false), tb);
 }
 #endif /* CONFIG_USER_ONLY */
 
@@ -916,7 +886,7 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)
 
     /* remove the TB from the hash list */
     phys_pc = tb_page_addr0(tb);
-    h = tb_hash_func(phys_pc, tb->pc,
+    h = tb_hash_func(phys_pc, (orig_cflags & CF_PCREL ? 0 : tb->pc),
                      tb->flags, tb->cs_base, orig_cflags);
     if (!qht_remove(&tb_ctx.htable, tb, h)) {
         return;
@@ -955,16 +925,18 @@ static void tb_phys_invalidate__locked(TranslationBlock *tb)
 void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
 {
     if (page_addr == -1 && tb_page_addr0(tb) != -1) {
-        tb_lock_pages(tb);
+        page_lock_tb(tb);
         do_tb_phys_invalidate(tb, true);
-        tb_unlock_pages(tb);
+        page_unlock_tb(tb);
     } else {
         do_tb_phys_invalidate(tb, false);
     }
 }
 
 /*
- * Add a new TB and link it to the physical page tables.
+ * Add a new TB and link it to the physical page tables. phys_page2 is
+ * (-1) to indicate that only one page contains the TB.
+ *
  * Called with mmap_lock held for user-mode emulation.
  *
  * Returns a pointer @tb, or a pointer to an existing TB that matches @tb.
@@ -972,29 +944,43 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
  * for the same block of guest code that @tb corresponds to. In that case,
  * the caller should discard the original @tb, and use instead the returned TB.
  */
-TranslationBlock *tb_link_page(TranslationBlock *tb)
+TranslationBlock *tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
+                               tb_page_addr_t phys_page2)
 {
+    PageDesc *p;
+    PageDesc *p2 = NULL;
     void *existing_tb = NULL;
     uint32_t h;
 
     assert_memory_lock();
     tcg_debug_assert(!(tb->cflags & CF_INVALID));
 
-    tb_record(tb);
+    /*
+     * Add the TB to the page list, acquiring first the pages's locks.
+     * We keep the locks held until after inserting the TB in the hash table,
+     * so that if the insertion fails we know for sure that the TBs are still
+     * in the page descriptors.
+     * Note that inserting into the hash table first isn't an option, since
+     * we can only insert TBs that are fully initialized.
+     */
+    page_lock_pair(&p, phys_pc, &p2, phys_page2, true);
+    tb_record(tb, p, p2);
 
     /* add in the hash table */
-    h = tb_hash_func(tb_page_addr0(tb), tb->pc,
+    h = tb_hash_func(phys_pc, (tb->cflags & CF_PCREL ? 0 : tb->pc),
                      tb->flags, tb->cs_base, tb->cflags);
     qht_insert(&tb_ctx.htable, tb, h, &existing_tb);
 
     /* remove TB from the page(s) if we couldn't insert it */
     if (unlikely(existing_tb)) {
         tb_remove(tb);
-        tb_unlock_pages(tb);
-        return existing_tb;
+        tb = existing_tb;
     }
 
-    tb_unlock_pages(tb);
+    if (p2 && p2 != p) {
+        page_unlock(p2);
+    }
+    page_unlock(p);
     return tb;
 }
 
@@ -1106,9 +1092,6 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
     TranslationBlock *current_tb = retaddr ? tcg_tb_lookup(retaddr) : NULL;
 #endif /* TARGET_HAS_PRECISE_SMC */
 
-    /* Range may not cross a page. */
-    tcg_debug_assert(((start ^ last) & TARGET_PAGE_MASK) == 0);
-
     /*
      * We remove all the TBs in the range [start, last].
      * XXX: see if in some cases it could be faster to invalidate all the code
@@ -1199,17 +1182,15 @@ void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t last)
     index_last = last >> TARGET_PAGE_BITS;
     for (index = start >> TARGET_PAGE_BITS; index <= index_last; index++) {
         PageDesc *pd = page_find(index);
-        tb_page_addr_t page_start, page_last;
+        tb_page_addr_t bound;
 
         if (pd == NULL) {
             continue;
         }
         assert_page_locked(pd);
-        page_start = index << TARGET_PAGE_BITS;
-        page_last = page_start | ~TARGET_PAGE_MASK;
-        page_last = MIN(page_last, last);
-        tb_invalidate_phys_page_range__locked(pages, pd,
-                                              page_start, page_last, 0);
+        bound = (index << TARGET_PAGE_BITS) | ~TARGET_PAGE_MASK;
+        bound = MIN(bound, last);
+        tb_invalidate_phys_page_range__locked(pages, pd, start, bound, 0);
     }
     page_collection_unlock(pages);
 }

accel/tcg/tcg-accel-ops-icount.c

@@ -111,14 +111,14 @@ void icount_prepare_for_run(CPUState *cpu, int64_t cpu_budget)
      * each vCPU execution. However u16.high can be raised
      * asynchronously by cpu_exit/cpu_interrupt/tcg_handle_interrupt
      */
-    g_assert(cpu->neg.icount_decr.u16.low == 0);
+    g_assert(cpu_neg(cpu)->icount_decr.u16.low == 0);
     g_assert(cpu->icount_extra == 0);
 
     replay_mutex_lock();
 
     cpu->icount_budget = MIN(icount_get_limit(), cpu_budget);
     insns_left = MIN(0xffff, cpu->icount_budget);
-    cpu->neg.icount_decr.u16.low = insns_left;
+    cpu_neg(cpu)->icount_decr.u16.low = insns_left;
     cpu->icount_extra = cpu->icount_budget - insns_left;
 
     if (cpu->icount_budget == 0) {
@@ -138,7 +138,7 @@ void icount_process_data(CPUState *cpu)
     icount_update(cpu);
 
     /* Reset the counters */
-    cpu->neg.icount_decr.u16.low = 0;
+    cpu_neg(cpu)->icount_decr.u16.low = 0;
     cpu->icount_extra = 0;
     cpu->icount_budget = 0;
 
@@ -153,7 +153,7 @@ void icount_handle_interrupt(CPUState *cpu, int mask)
 
     tcg_handle_interrupt(cpu, mask);
     if (qemu_cpu_is_self(cpu) &&
-        !cpu->neg.can_do_io
+        !cpu->can_do_io
         && (mask & ~old_mask) != 0) {
         cpu_abort(cpu, "Raised interrupt while not in I/O function");
     }

accel/tcg/tcg-accel-ops-mttcg.c

@@ -32,7 +32,7 @@
 #include "qemu/guest-random.h"
 #include "exec/exec-all.h"
 #include "hw/boards.h"
-#include "tcg/startup.h"
+#include "tcg/tcg.h"
 #include "tcg-accel-ops.h"
 #include "tcg-accel-ops-mttcg.h"
 
@@ -80,7 +80,7 @@ static void *mttcg_cpu_thread_fn(void *arg)
     qemu_thread_get_self(cpu->thread);
 
     cpu->thread_id = qemu_get_thread_id();
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     current_cpu = cpu;
     cpu_thread_signal_created(cpu);
     qemu_guest_random_seed_thread_part2(cpu->random_seed);
@@ -100,9 +100,14 @@ static void *mttcg_cpu_thread_fn(void *arg)
                 break;
             case EXCP_HALTED:
                 /*
-                 * Usually cpu->halted is set, but may have already been
-                 * reset by another thread by the time we arrive here.
+                 * during start-up the vCPU is reset and the thread is
+                 * kicked several times. If we don't ensure we go back
+                 * to sleep in the halted state we won't cleanly
+                 * start-up when the vCPU is enabled.
+                 *
+                 * cpu->halted should ensure we sleep in wait_io_event
                  */
+                g_assert(cpu->halted);
                 break;
             case EXCP_ATOMIC:
                 qemu_mutex_unlock_iothread();

accel/tcg/tcg-accel-ops-rr.c

@@ -32,7 +32,7 @@
 #include "qemu/notify.h"
 #include "qemu/guest-random.h"
 #include "exec/exec-all.h"
-#include "tcg/startup.h"
+#include "tcg/tcg.h"
 #include "tcg-accel-ops.h"
 #include "tcg-accel-ops-rr.h"
 #include "tcg-accel-ops-icount.h"
@@ -192,7 +192,7 @@ static void *rr_cpu_thread_fn(void *arg)
     qemu_thread_get_self(cpu->thread);
 
     cpu->thread_id = qemu_get_thread_id();
-    cpu->neg.can_do_io = true;
+    cpu->can_do_io = 1;
     cpu_thread_signal_created(cpu);
     qemu_guest_random_seed_thread_part2(cpu->random_seed);
 
@@ -334,7 +334,7 @@ void rr_start_vcpu_thread(CPUState *cpu)
         cpu->thread = single_tcg_cpu_thread;
         cpu->halt_cond = single_tcg_halt_cond;
         cpu->thread_id = first_cpu->thread_id;
-        cpu->neg.can_do_io = 1;
+        cpu->can_do_io = 1;
         cpu->created = true;
     }
 }

accel/tcg/tcg-accel-ops.c

@@ -34,7 +34,6 @@
 #include "qemu/timer.h"
 #include "exec/exec-all.h"
 #include "exec/hwaddr.h"
-#include "exec/tb-flush.h"
 #include "exec/gdbstub.h"
 
 #include "tcg-accel-ops.h"
@@ -78,13 +77,6 @@ int tcg_cpus_exec(CPUState *cpu)
     return ret;
 }
 
-static void tcg_cpu_reset_hold(CPUState *cpu)
-{
-    tcg_flush_jmp_cache(cpu);
-
-    tlb_flush(cpu);
-}
-
 /* mask must never be zero, except for A20 change call */
 void tcg_handle_interrupt(CPUState *cpu, int mask)
 {
@@ -99,7 +91,7 @@ void tcg_handle_interrupt(CPUState *cpu, int mask)
     if (!qemu_cpu_is_self(cpu)) {
         qemu_cpu_kick(cpu);
     } else {
-        qatomic_set(&cpu->neg.icount_decr.u16.high, -1);
+        qatomic_set(&cpu_neg(cpu)->icount_decr.u16.high, -1);
     }
 }
 
@@ -213,7 +205,6 @@ static void tcg_accel_ops_init(AccelOpsClass *ops)
         }
     }
 
-    ops->cpu_reset_hold = tcg_cpu_reset_hold;
     ops->supports_guest_debug = tcg_supports_guest_debug;
     ops->insert_breakpoint = tcg_insert_breakpoint;
     ops->remove_breakpoint = tcg_remove_breakpoint;

accel/tcg/tcg-all.c

@@ -27,7 +27,7 @@
 #include "sysemu/tcg.h"
 #include "exec/replay-core.h"
 #include "sysemu/cpu-timers.h"
-#include "tcg/startup.h"
+#include "tcg/tcg.h"
 #include "tcg/oversized-guest.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
@@ -38,7 +38,7 @@
 #if !defined(CONFIG_USER_ONLY)
 #include "hw/boards.h"
 #endif
-#include "internal-target.h"
+#include "internal.h"
 
 struct TCGState {
     AccelState parent_obj;
@@ -121,7 +121,7 @@ static int tcg_init_machine(MachineState *ms)
      * There's no guest base to take into account, so go ahead and
      * initialize the prologue now.
      */
-    tcg_prologue_init();
+    tcg_prologue_init(tcg_ctx);
 #endif
 
     return 0;
@@ -227,8 +227,6 @@ static void tcg_accel_class_init(ObjectClass *oc, void *data)
     AccelClass *ac = ACCEL_CLASS(oc);
     ac->name = "tcg";
     ac->init_machine = tcg_init_machine;
-    ac->cpu_common_realize = tcg_exec_realizefn;
-    ac->cpu_common_unrealize = tcg_exec_unrealizefn;
     ac->allowed = &tcg_allowed;
     ac->gdbstub_supported_sstep_flags = tcg_gdbstub_supported_sstep_flags;
 

accel/tcg/tcg-runtime-gvec.c

@@ -1042,32 +1042,6 @@ DO_CMP2(64)
 #undef DO_CMP1
 #undef DO_CMP2
 
-#define DO_CMP1(NAME, TYPE, OP)                                            \
-void HELPER(NAME)(void *d, void *a, uint64_t b64, uint32_t desc)           \
-{                                                                          \
-    intptr_t oprsz = simd_oprsz(desc);                                     \
-    TYPE inv = simd_data(desc), b = b64;                                   \
-    for (intptr_t i = 0; i < oprsz; i += sizeof(TYPE)) {                   \
-        *(TYPE *)(d + i) = -((*(TYPE *)(a + i) OP b) ^ inv);               \
-    }                                                                      \
-    clear_high(d, oprsz, desc);                                            \
-}
-
-#define DO_CMP2(SZ) \
-    DO_CMP1(gvec_eqs##SZ, uint##SZ##_t, ==)    \
-    DO_CMP1(gvec_lts##SZ, int##SZ##_t, <)      \
-    DO_CMP1(gvec_les##SZ, int##SZ##_t, <=)     \
-    DO_CMP1(gvec_ltus##SZ, uint##SZ##_t, <)    \
-    DO_CMP1(gvec_leus##SZ, uint##SZ##_t, <=)
-
-DO_CMP2(8)
-DO_CMP2(16)
-DO_CMP2(32)
-DO_CMP2(64)
-
-#undef DO_CMP1
-#undef DO_CMP2
-
 void HELPER(gvec_ssadd8)(void *d, void *a, void *b, uint32_t desc)
 {
     intptr_t oprsz = simd_oprsz(desc);

accel/tcg/tcg-runtime.h

@@ -58,7 +58,7 @@ DEF_HELPER_FLAGS_5(atomic_cmpxchgq_be, TCG_CALL_NO_WG,
 DEF_HELPER_FLAGS_5(atomic_cmpxchgq_le, TCG_CALL_NO_WG,
                    i64, env, i64, i64, i64, i32)
 #endif
-#if HAVE_CMPXCHG128
+#ifdef CONFIG_CMPXCHG128
 DEF_HELPER_FLAGS_5(atomic_cmpxchgo_be, TCG_CALL_NO_WG,
                    i128, env, i64, i128, i128, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgo_le, TCG_CALL_NO_WG,
@@ -297,29 +297,4 @@ DEF_HELPER_FLAGS_4(gvec_leu16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_leu32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_leu64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_4(gvec_eqs8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_eqs16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_eqs32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_eqs64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-
-DEF_HELPER_FLAGS_4(gvec_lts8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_lts16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_lts32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_lts64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-
-DEF_HELPER_FLAGS_4(gvec_les8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_les16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_les32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_les64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-
-DEF_HELPER_FLAGS_4(gvec_ltus8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_ltus16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_ltus32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_ltus64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-
-DEF_HELPER_FLAGS_4(gvec_leus8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_leus16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_leus32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_leus64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-
 DEF_HELPER_FLAGS_5(gvec_bitsel, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)

accel/tcg/translate-all.c

@@ -61,8 +61,7 @@
 #include "tb-jmp-cache.h"
 #include "tb-hash.h"
 #include "tb-context.h"
-#include "internal-common.h"
-#include "internal-target.h"
+#include "internal.h"
 #include "perf.h"
 #include "tcg/insn-start-words.h"
 
@@ -215,7 +214,7 @@ void cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
          * Reset the cycle counter to the start of the block and
          * shift if to the number of actually executed instructions.
          */
-        cpu->neg.icount_decr.u16.low += insns_left;
+        cpu_neg(cpu)->icount_decr.u16.low += insns_left;
     }
 
     cpu->cc->tcg_ops->restore_state_to_opc(cpu, tb, data);
@@ -289,9 +288,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
                               vaddr pc, uint64_t cs_base,
                               uint32_t flags, int cflags)
 {
-    CPUArchState *env = cpu_env(cpu);
+    CPUArchState *env = cpu->env_ptr;
     TranslationBlock *tb, *existing_tb;
-    tb_page_addr_t phys_pc, phys_p2;
+    tb_page_addr_t phys_pc;
     tcg_insn_unit *gen_code_buf;
     int gen_code_size, search_size, max_insns;
     int64_t ti;
@@ -304,7 +303,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 
     if (phys_pc == -1) {
         /* Generate a one-shot TB with 1 insn in it */
-        cflags = (cflags & ~CF_COUNT_MASK) | 1;
+        cflags = (cflags & ~CF_COUNT_MASK) | CF_LAST_IO | 1;
     }
 
     max_insns = cflags & CF_COUNT_MASK;
@@ -314,7 +313,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     QEMU_BUILD_BUG_ON(CF_COUNT_MASK + 1 != TCG_MAX_INSNS);
 
  buffer_overflow:
-    assert_no_pages_locked();
     tb = tcg_tb_alloc(tcg_ctx);
     if (unlikely(!tb)) {
         /* flush must be done */
@@ -327,22 +325,22 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 
     gen_code_buf = tcg_ctx->code_gen_ptr;
     tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf);
-    tb->pc = pc;
+    if (!(cflags & CF_PCREL)) {
+        tb->pc = pc;
+    }
     tb->cs_base = cs_base;
     tb->flags = flags;
     tb->cflags = cflags;
     tb_set_page_addr0(tb, phys_pc);
     tb_set_page_addr1(tb, -1);
-    if (phys_pc != -1) {
-        tb_lock_page0(phys_pc);
-    }
-
     tcg_ctx->gen_tb = tb;
     tcg_ctx->addr_type = TARGET_LONG_BITS == 32 ? TCG_TYPE_I32 : TCG_TYPE_I64;
 #ifdef CONFIG_SOFTMMU
     tcg_ctx->page_bits = TARGET_PAGE_BITS;
     tcg_ctx->page_mask = TARGET_PAGE_MASK;
     tcg_ctx->tlb_dyn_max_bits = CPU_TLB_DYN_MAX_BITS;
+    tcg_ctx->tlb_fast_offset =
+        (int)offsetof(ArchCPU, neg.tlb.f) - (int)offsetof(ArchCPU, env);
 #endif
     tcg_ctx->insn_start_words = TARGET_INSN_START_WORDS;
 #ifdef TCG_GUEST_DEFAULT_MO
@@ -351,7 +349,8 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     tcg_ctx->guest_mo = TCG_MO_ALL;
 #endif
 
- restart_translate:
+ tb_overflow:
+
     trace_translate_block(tb, pc, tb->tc.ptr);
 
     gen_code_size = setjmp_gen_code(env, tb, pc, host_pc, &max_insns, &ti);
@@ -370,8 +369,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
             qemu_log_mask(CPU_LOG_TB_OP | CPU_LOG_TB_OP_OPT,
                           "Restarting code generation for "
                           "code_gen_buffer overflow\n");
-            tb_unlock_pages(tb);
-            tcg_ctx->gen_tb = NULL;
             goto buffer_overflow;
 
         case -2:
@@ -390,39 +387,14 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
                           "Restarting code generation with "
                           "smaller translation block (max %d insns)\n",
                           max_insns);
-
-            /*
-             * The half-sized TB may not cross pages.
-             * TODO: Fix all targets that cross pages except with
-             * the first insn, at which point this can't be reached.
-             */
-            phys_p2 = tb_page_addr1(tb);
-            if (unlikely(phys_p2 != -1)) {
-                tb_unlock_page1(phys_pc, phys_p2);
-                tb_set_page_addr1(tb, -1);
-            }
-            goto restart_translate;
-
-        case -3:
-            /*
-             * We had a page lock ordering problem.  In order to avoid
-             * deadlock we had to drop the lock on page0, which means
-             * that everything we translated so far is compromised.
-             * Restart with locks held on both pages.
-             */
-            qemu_log_mask(CPU_LOG_TB_OP | CPU_LOG_TB_OP_OPT,
-                          "Restarting code generation with re-locked pages");
-            goto restart_translate;
+            goto tb_overflow;
 
         default:
             g_assert_not_reached();
         }
     }
-    tcg_ctx->gen_tb = NULL;
-
     search_size = encode_search(tb, (void *)gen_code_buf + gen_code_size);
     if (unlikely(search_size < 0)) {
-        tb_unlock_pages(tb);
         goto buffer_overflow;
     }
     tb->tc.size = gen_code_size;
@@ -532,7 +504,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
      * before attempting to link to other TBs or add to the lookup table.
      */
     if (tb_page_addr0(tb) == -1) {
-        assert_no_pages_locked();
         return tb;
     }
 
@@ -547,9 +518,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
      * No explicit memory barrier is required -- tb_link_page() makes the
      * TB visible in a consistent state.
      */
-    existing_tb = tb_link_page(tb);
-    assert_no_pages_locked();
-
+    existing_tb = tb_link_page(tb, tb_page_addr0(tb), tb_page_addr1(tb));
     /* if the TB already exists, discard what we just translated */
     if (unlikely(existing_tb != tb)) {
         uintptr_t orig_aligned = (uintptr_t)gen_code_buf;
@@ -577,7 +546,7 @@ void tb_check_watchpoint(CPUState *cpu, uintptr_t retaddr)
     } else {
         /* The exception probably happened in a helper.  The CPU state should
            have been saved before calling it. Fetch the PC from there.  */
-        CPUArchState *env = cpu_env(cpu);
+        CPUArchState *env = cpu->env_ptr;
         vaddr pc;
         uint64_t cs_base;
         tb_page_addr_t addr;
@@ -620,7 +589,7 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     cc = CPU_GET_CLASS(cpu);
     if (cc->tcg_ops->io_recompile_replay_branch &&
         cc->tcg_ops->io_recompile_replay_branch(cpu, tb)) {
-        cpu->neg.icount_decr.u16.low++;
+        cpu_neg(cpu)->icount_decr.u16.low++;
         n = 2;
     }
 
@@ -630,12 +599,12 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
      * operations only (which execute after completion) so we don't
      * double instrument the instruction.
      */
-    cpu->cflags_next_tb = curr_cflags(cpu) | CF_MEMI_ONLY | n;
+    cpu->cflags_next_tb = curr_cflags(cpu) | CF_MEMI_ONLY | CF_LAST_IO | n;
 
     if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
         vaddr pc = log_pc(cpu, tb);
         if (qemu_log_in_addr_range(pc)) {
-            qemu_log("cpu_io_recompile: rewound execution of TB to %016"
+            qemu_log("cpu_io_recompile: rewound execution of TB to %"
                      VADDR_PRIx "\n", pc);
         }
     }
@@ -643,13 +612,140 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     cpu_loop_exit_noexc(cpu);
 }
 
+static void print_qht_statistics(struct qht_stats hst, GString *buf)
+{
+    uint32_t hgram_opts;
+    size_t hgram_bins;
+    char *hgram;
+
+    if (!hst.head_buckets) {
+        return;
+    }
+    g_string_append_printf(buf, "TB hash buckets     %zu/%zu "
+                           "(%0.2f%% head buckets used)\n",
+                           hst.used_head_buckets, hst.head_buckets,
+                           (double)hst.used_head_buckets /
+                           hst.head_buckets * 100);
+
+    hgram_opts =  QDIST_PR_BORDER | QDIST_PR_LABELS;
+    hgram_opts |= QDIST_PR_100X   | QDIST_PR_PERCENT;
+    if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
+        hgram_opts |= QDIST_PR_NODECIMAL;
+    }
+    hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
+    g_string_append_printf(buf, "TB hash occupancy   %0.2f%% avg chain occ. "
+                           "Histogram: %s\n",
+                           qdist_avg(&hst.occupancy) * 100, hgram);
+    g_free(hgram);
+
+    hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
+    hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
+    if (hgram_bins > 10) {
+        hgram_bins = 10;
+    } else {
+        hgram_bins = 0;
+        hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
+    }
+    hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
+    g_string_append_printf(buf, "TB hash avg chain   %0.3f buckets. "
+                           "Histogram: %s\n",
+                           qdist_avg(&hst.chain), hgram);
+    g_free(hgram);
+}
+
+struct tb_tree_stats {
+    size_t nb_tbs;
+    size_t host_size;
+    size_t target_size;
+    size_t max_target_size;
+    size_t direct_jmp_count;
+    size_t direct_jmp2_count;
+    size_t cross_page;
+};
+
+static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data)
+{
+    const TranslationBlock *tb = value;
+    struct tb_tree_stats *tst = data;
+
+    tst->nb_tbs++;
+    tst->host_size += tb->tc.size;
+    tst->target_size += tb->size;
+    if (tb->size > tst->max_target_size) {
+        tst->max_target_size = tb->size;
+    }
+    if (tb_page_addr1(tb) != -1) {
+        tst->cross_page++;
+    }
+    if (tb->jmp_reset_offset[0] != TB_JMP_OFFSET_INVALID) {
+        tst->direct_jmp_count++;
+        if (tb->jmp_reset_offset[1] != TB_JMP_OFFSET_INVALID) {
+            tst->direct_jmp2_count++;
+        }
+    }
+    return false;
+}
+
+void dump_exec_info(GString *buf)
+{
+    struct tb_tree_stats tst = {};
+    struct qht_stats hst;
+    size_t nb_tbs, flush_full, flush_part, flush_elide;
+
+    tcg_tb_foreach(tb_tree_stats_iter, &tst);
+    nb_tbs = tst.nb_tbs;
+    /* XXX: avoid using doubles ? */
+    g_string_append_printf(buf, "Translation buffer state:\n");
+    /*
+     * Report total code size including the padding and TB structs;
+     * otherwise users might think "-accel tcg,tb-size" is not honoured.
+     * For avg host size we use the precise numbers from tb_tree_stats though.
+     */
+    g_string_append_printf(buf, "gen code size       %zu/%zu\n",
+                           tcg_code_size(), tcg_code_capacity());
+    g_string_append_printf(buf, "TB count            %zu\n", nb_tbs);
+    g_string_append_printf(buf, "TB avg target size  %zu max=%zu bytes\n",
+                           nb_tbs ? tst.target_size / nb_tbs : 0,
+                           tst.max_target_size);
+    g_string_append_printf(buf, "TB avg host size    %zu bytes "
+                           "(expansion ratio: %0.1f)\n",
+                           nb_tbs ? tst.host_size / nb_tbs : 0,
+                           tst.target_size ?
+                           (double)tst.host_size / tst.target_size : 0);
+    g_string_append_printf(buf, "cross page TB count %zu (%zu%%)\n",
+                           tst.cross_page,
+                           nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
+    g_string_append_printf(buf, "direct jump count   %zu (%zu%%) "
+                           "(2 jumps=%zu %zu%%)\n",
+                           tst.direct_jmp_count,
+                           nb_tbs ? (tst.direct_jmp_count * 100) / nb_tbs : 0,
+                           tst.direct_jmp2_count,
+                           nb_tbs ? (tst.direct_jmp2_count * 100) / nb_tbs : 0);
+
+    qht_statistics_init(&tb_ctx.htable, &hst);
+    print_qht_statistics(hst, buf);
+    qht_statistics_destroy(&hst);
+
+    g_string_append_printf(buf, "\nStatistics:\n");
+    g_string_append_printf(buf, "TB flush count      %u\n",
+                           qatomic_read(&tb_ctx.tb_flush_count));
+    g_string_append_printf(buf, "TB invalidate count %u\n",
+                           qatomic_read(&tb_ctx.tb_phys_invalidate_count));
+
+    tlb_flush_counts(&flush_full, &flush_part, &flush_elide);
+    g_string_append_printf(buf, "TLB full flushes    %zu\n", flush_full);
+    g_string_append_printf(buf, "TLB partial flushes %zu\n", flush_part);
+    g_string_append_printf(buf, "TLB elided flushes  %zu\n", flush_elide);
+    tcg_dump_info(buf);
+}
+
 #else /* CONFIG_USER_ONLY */
 
 void cpu_interrupt(CPUState *cpu, int mask)
 {
     g_assert(qemu_mutex_iothread_locked());
     cpu->interrupt_request |= mask;
-    qatomic_set(&cpu->neg.icount_decr.u16.high, -1);
+    qatomic_set(&cpu_neg(cpu)->icount_decr.u16.high, -1);
 }
 
 #endif /* CONFIG_USER_ONLY */
@@ -671,3 +767,11 @@ void tcg_flush_jmp_cache(CPUState *cpu)
         qatomic_set(&jc->array[i].tb, NULL);
     }
 }
+
+/* This is a wrapper for common code that can not use CONFIG_SOFTMMU */
+void tcg_flush_softmmu_tlb(CPUState *cs)
+{
+#ifdef CONFIG_SOFTMMU
+    tlb_flush(cs);
+#endif
+}

accel/tcg/translator.c

@@ -12,25 +12,30 @@
 #include "qemu/error-report.h"
 #include "exec/exec-all.h"
 #include "exec/translator.h"
+#include "exec/translate-all.h"
 #include "exec/plugin-gen.h"
 #include "tcg/tcg-op-common.h"
-#include "internal-target.h"
 
-static void set_can_do_io(DisasContextBase *db, bool val)
+static void gen_io_start(void)
 {
-    if (db->saved_can_do_io != val) {
-        db->saved_can_do_io = val;
-
-        QEMU_BUILD_BUG_ON(sizeof_field(CPUState, neg.can_do_io) != 1);
-        tcg_gen_st8_i32(tcg_constant_i32(val), tcg_env,
-                        offsetof(ArchCPU, parent_obj.neg.can_do_io) -
-                        offsetof(ArchCPU, env));
-    }
+    tcg_gen_st_i32(tcg_constant_i32(1), cpu_env,
+                   offsetof(ArchCPU, parent_obj.can_do_io) -
+                   offsetof(ArchCPU, env));
 }
 
 bool translator_io_start(DisasContextBase *db)
 {
-    set_can_do_io(db, true);
+    uint32_t cflags = tb_cflags(db->tb);
+
+    if (!(cflags & CF_USE_ICOUNT)) {
+        return false;
+    }
+    if (db->num_insns == db->max_insns && (cflags & CF_LAST_IO)) {
+        /* Already started in translator_loop. */
+        return true;
+    }
+
+    gen_io_start();
 
     /*
      * Ensure that this instruction will be the last in the TB.
@@ -42,17 +47,14 @@ bool translator_io_start(DisasContextBase *db)
     return true;
 }
 
-static TCGOp *gen_tb_start(DisasContextBase *db, uint32_t cflags)
+static TCGOp *gen_tb_start(uint32_t cflags)
 {
-    TCGv_i32 count = NULL;
+    TCGv_i32 count = tcg_temp_new_i32();
     TCGOp *icount_start_insn = NULL;
 
-    if ((cflags & CF_USE_ICOUNT) || !(cflags & CF_NOIRQ)) {
-        count = tcg_temp_new_i32();
-        tcg_gen_ld_i32(count, tcg_env,
-                       offsetof(ArchCPU, parent_obj.neg.icount_decr.u32)
-                       - offsetof(ArchCPU, env));
-    }
+    tcg_gen_ld_i32(count, cpu_env,
+                   offsetof(ArchCPU, neg.icount_decr.u32) -
+                   offsetof(ArchCPU, env));
 
     if (cflags & CF_USE_ICOUNT) {
         /*
@@ -79,18 +81,21 @@ static TCGOp *gen_tb_start(DisasContextBase *db, uint32_t cflags)
     }
 
     if (cflags & CF_USE_ICOUNT) {
-        tcg_gen_st16_i32(count, tcg_env,
-                         offsetof(ArchCPU, parent_obj.neg.icount_decr.u16.low)
-                         - offsetof(ArchCPU, env));
+        tcg_gen_st16_i32(count, cpu_env,
+                         offsetof(ArchCPU, neg.icount_decr.u16.low) -
+                         offsetof(ArchCPU, env));
+        /*
+         * cpu->can_do_io is cleared automatically here at the beginning of
+         * each translation block.  The cost is minimal and only paid for
+         * -icount, plus it would be very easy to forget doing it in the
+         * translator. Doing it here means we don't need a gen_io_end() to
+         * go with gen_io_start().
+         */
+        tcg_gen_st_i32(tcg_constant_i32(0), cpu_env,
+                       offsetof(ArchCPU, parent_obj.can_do_io) -
+                       offsetof(ArchCPU, env));
     }
 
-    /*
-     * cpu->neg.can_do_io is set automatically here at the beginning of
-     * each translation block.  The cost is minimal, plus it would be
-     * very easy to forget doing it in the translator.
-     */
-    set_can_do_io(db, db->max_insns == 1);
-
     return icount_start_insn;
 }
 
@@ -139,20 +144,22 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
     db->num_insns = 0;
     db->max_insns = *max_insns;
     db->singlestep_enabled = cflags & CF_SINGLE_STEP;
-    db->saved_can_do_io = -1;
     db->host_addr[0] = host_pc;
     db->host_addr[1] = NULL;
 
+#ifdef CONFIG_USER_ONLY
+    page_protect(pc);
+#endif
+
     ops->init_disas_context(db, cpu);
     tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
 
     /* Start translating.  */
-    icount_start_insn = gen_tb_start(db, cflags);
+    icount_start_insn = gen_tb_start(cflags);
     ops->tb_start(db, cpu);
     tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
 
     plugin_enabled = plugin_gen_tb_start(cpu, db, cflags & CF_MEMI_ONLY);
-    db->plugin_enabled = plugin_enabled;
 
     while (true) {
         *max_insns = ++db->num_insns;
@@ -163,17 +170,19 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
             plugin_gen_insn_start(cpu, db);
         }
 
-        /*
-         * Disassemble one instruction.  The translate_insn hook should
-         * update db->pc_next and db->is_jmp to indicate what should be
-         * done next -- either exiting this loop or locate the start of
-         * the next instruction.
-         */
-        if (db->num_insns == db->max_insns) {
+        /* Disassemble one instruction.  The translate_insn hook should
+           update db->pc_next and db->is_jmp to indicate what should be
+           done next -- either exiting this loop or locate the start of
+           the next instruction.  */
+        if (db->num_insns == db->max_insns && (cflags & CF_LAST_IO)) {
             /* Accept I/O on the last instruction.  */
-            set_can_do_io(db, true);
+            gen_io_start();
+            ops->translate_insn(db, cpu);
+        } else {
+            /* we should only see CF_MEMI_ONLY for io_recompile */
+            tcg_debug_assert(!(cflags & CF_MEMI_ONLY));
+            ops->translate_insn(db, cpu);
         }
-        ops->translate_insn(db, cpu);
 
         /*
          * We can't instrument after instructions that change control
@@ -206,7 +215,7 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
     gen_tb_end(tb, cflags, icount_start_insn, db->num_insns);
 
     if (plugin_enabled) {
-        plugin_gen_tb_end(cpu, db->num_insns);
+        plugin_gen_tb_end(cpu);
     }
 
     /* The disas_log hook may use these values rather than recompute.  */
@@ -247,36 +256,22 @@ static void *translator_access(CPUArchState *env, DisasContextBase *db,
         host = db->host_addr[1];
         base = TARGET_PAGE_ALIGN(db->pc_first);
         if (host == NULL) {
-            tb_page_addr_t page0, old_page1, new_page1;
-
-            new_page1 = get_page_addr_code_hostp(env, base, &db->host_addr[1]);
+            tb_page_addr_t phys_page =
+                get_page_addr_code_hostp(env, base, &db->host_addr[1]);
 
             /*
              * If the second page is MMIO, treat as if the first page
              * was MMIO as well, so that we do not cache the TB.
              */
-            if (unlikely(new_page1 == -1)) {
-                tb_unlock_pages(tb);
+            if (unlikely(phys_page == -1)) {
                 tb_set_page_addr0(tb, -1);
                 return NULL;
             }
 
-            /*
-             * If this is not the first time around, and page1 matches,
-             * then we already have the page locked.  Alternately, we're
-             * not doing anything to prevent the PTE from changing, so
-             * we might wind up with a different page, requiring us to
-             * re-do the locking.
-             */
-            old_page1 = tb_page_addr1(tb);
-            if (likely(new_page1 != old_page1)) {
-                page0 = tb_page_addr0(tb);
-                if (unlikely(old_page1 != -1)) {
-                    tb_unlock_page1(page0, old_page1);
-                }
-                tb_set_page_addr1(tb, new_page1);
-                tb_lock_page1(page0, new_page1);
-            }
+            tb_set_page_addr1(tb, phys_page);
+#ifdef CONFIG_USER_ONLY
+            page_protect(end);
+#endif
             host = db->host_addr[1];
         }
 

accel/tcg/user-exec-stub.c

@@ -2,6 +2,8 @@
 #include "hw/core/cpu.h"
 #include "exec/replay-core.h"
 
+bool enable_cpu_pm = false;
+
 void cpu_resume(CPUState *cpu)
 {
 }
@@ -14,10 +16,6 @@ void qemu_init_vcpu(CPUState *cpu)
 {
 }
 
-void cpu_exec_reset_hold(CPUState *cpu)
-{
-}
-
 /* User mode emulation does not support record/replay yet.  */
 
 bool replay_exception(void)

accel/tcg/user-exec.c

@@ -29,8 +29,7 @@
 #include "qemu/atomic128.h"
 #include "trace/trace-root.h"
 #include "tcg/tcg-ldst.h"
-#include "internal-common.h"
-#include "internal-target.h"
+#include "internal.h"
 
 __thread uintptr_t helper_retaddr;
 
@@ -145,7 +144,7 @@ typedef struct PageFlagsNode {
 
 static IntervalTreeRoot pageflags_root;
 
-static PageFlagsNode *pageflags_find(target_ulong start, target_ulong last)
+static PageFlagsNode *pageflags_find(target_ulong start, target_long last)
 {
     IntervalTreeNode *n;
 
@@ -154,7 +153,7 @@ static PageFlagsNode *pageflags_find(target_ulong start, target_ulong last)
 }
 
 static PageFlagsNode *pageflags_next(PageFlagsNode *p, target_ulong start,
-                                     target_ulong last)
+                                     target_long last)
 {
     IntervalTreeNode *n;
 
@@ -521,19 +520,19 @@ void page_set_flags(target_ulong start, target_ulong last, int flags)
     }
 }
 
-bool page_check_range(target_ulong start, target_ulong len, int flags)
+int page_check_range(target_ulong start, target_ulong len, int flags)
 {
     target_ulong last;
     int locked;  /* tri-state: =0: unlocked, +1: global, -1: local */
-    bool ret;
+    int ret;
 
     if (len == 0) {
-        return true;  /* trivial length */
+        return 0;  /* trivial length */
     }
 
     last = start + len - 1;
     if (last < start) {
-        return false; /* wrap around */
+        return -1; /* wrap around */
     }
 
     locked = have_mmap_lock();
@@ -552,33 +551,33 @@ bool page_check_range(target_ulong start, target_ulong len, int flags)
                 p = pageflags_find(start, last);
             }
             if (!p) {
-                ret = false; /* entire region invalid */
+                ret = -1; /* entire region invalid */
                 break;
             }
         }
         if (start < p->itree.start) {
-            ret = false; /* initial bytes invalid */
+            ret = -1; /* initial bytes invalid */
             break;
         }
 
         missing = flags & ~p->flags;
-        if (missing & ~PAGE_WRITE) {
-            ret = false; /* page doesn't match */
+        if (missing & PAGE_READ) {
+            ret = -1; /* page not readable */
             break;
         }
         if (missing & PAGE_WRITE) {
             if (!(p->flags & PAGE_WRITE_ORG)) {
-                ret = false; /* page not writable */
+                ret = -1; /* page not writable */
                 break;
             }
             /* Asking about writable, but has been protected: undo. */
             if (!page_unprotect(start, 0)) {
-                ret = false;
+                ret = -1;
                 break;
             }
             /* TODO: page_unprotect should take a range, not a single page. */
             if (last - start < TARGET_PAGE_SIZE) {
-                ret = true; /* ok */
+                ret = 0; /* ok */
                 break;
             }
             start += TARGET_PAGE_SIZE;
@@ -586,7 +585,7 @@ bool page_check_range(target_ulong start, target_ulong len, int flags)
         }
 
         if (last <= p->itree.last) {
-            ret = true; /* ok */
+            ret = 0; /* ok */
             break;
         }
         start = p->itree.last + 1;
@@ -599,54 +598,6 @@ bool page_check_range(target_ulong start, target_ulong len, int flags)
     return ret;
 }
 
-bool page_check_range_empty(target_ulong start, target_ulong last)
-{
-    assert(last >= start);
-    assert_memory_lock();
-    return pageflags_find(start, last) == NULL;
-}
-
-target_ulong page_find_range_empty(target_ulong min, target_ulong max,
-                                   target_ulong len, target_ulong align)
-{
-    target_ulong len_m1, align_m1;
-
-    assert(min <= max);
-    assert(max <= GUEST_ADDR_MAX);
-    assert(len != 0);
-    assert(is_power_of_2(align));
-    assert_memory_lock();
-
-    len_m1 = len - 1;
-    align_m1 = align - 1;
-
-    /* Iteratively narrow the search region. */
-    while (1) {
-        PageFlagsNode *p;
-
-        /* Align min and double-check there's enough space remaining. */
-        min = (min + align_m1) & ~align_m1;
-        if (min > max) {
-            return -1;
-        }
-        if (len_m1 > max - min) {
-            return -1;
-        }
-
-        p = pageflags_find(min, min + len_m1);
-        if (p == NULL) {
-            /* Found! */
-            return min;
-        }
-        if (max <= p->itree.last) {
-            /* Existing allocation fills the remainder of the search region. */
-            return -1;
-        }
-        /* Skip across existing allocation. */
-        min = p->itree.last + 1;
-    }
-}
-
 void page_protect(tb_page_addr_t address)
 {
     PageFlagsNode *p;
@@ -794,10 +745,6 @@ static int probe_access_internal(CPUArchState *env, vaddr addr,
     if (guest_addr_valid_untagged(addr)) {
         int page_flags = page_get_flags(addr);
         if (page_flags & acc_flag) {
-            if ((acc_flag == PAGE_READ || acc_flag == PAGE_WRITE)
-                && cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
-                return TLB_MMIO;
-            }
             return 0; /* success */
         }
         maperr = !(page_flags & PAGE_VALID);
@@ -820,7 +767,7 @@ int probe_access_flags(CPUArchState *env, vaddr addr, int size,
 
     g_assert(-(addr | TARGET_PAGE_MASK) >= size);
     flags = probe_access_internal(env, addr, size, access_type, nonfault, ra);
-    *phost = (flags & TLB_INVALID_MASK) ? NULL : g2h(env_cpu(env), addr);
+    *phost = flags ? NULL : g2h(env_cpu(env), addr);
     return flags;
 }
 
@@ -831,7 +778,7 @@ void *probe_access(CPUArchState *env, vaddr addr, int size,
 
     g_assert(-(addr | TARGET_PAGE_MASK) >= size);
     flags = probe_access_internal(env, addr, size, access_type, false, ra);
-    g_assert((flags & ~TLB_MMIO) == 0);
+    g_assert(flags == 0);
 
     return size ? g2h(env_cpu(env), addr) : NULL;
 }
@@ -940,9 +887,9 @@ void *page_get_target_data(target_ulong address)
 void page_reset_target_data(target_ulong start, target_ulong last) { }
 #endif /* TARGET_PAGE_DATA_SIZE */
 
-/* The system-mode versions of these helpers are in cputlb.c.  */
+/* The softmmu versions of these helpers are in cputlb.c.  */
 
-static void *cpu_mmu_lookup(CPUState *cpu, vaddr addr,
+static void *cpu_mmu_lookup(CPUArchState *env, vaddr addr,
                             MemOp mop, uintptr_t ra, MMUAccessType type)
 {
     int a_bits = get_alignment_bits(mop);
@@ -950,39 +897,60 @@ static void *cpu_mmu_lookup(CPUState *cpu, vaddr addr,
 
     /* Enforce guest required alignment.  */
     if (unlikely(addr & ((1 << a_bits) - 1))) {
-        cpu_loop_exit_sigbus(cpu, addr, type, ra);
+        cpu_loop_exit_sigbus(env_cpu(env), addr, type, ra);
     }
 
-    ret = g2h(cpu, addr);
+    ret = g2h(env_cpu(env), addr);
     set_helper_retaddr(ra);
     return ret;
 }
 
 #include "ldst_atomicity.c.inc"
 
-static uint8_t do_ld1_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                          uintptr_t ra, MMUAccessType access_type)
+static uint8_t do_ld1_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOp mop, uintptr_t ra)
 {
     void *haddr;
     uint8_t ret;
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_8);
     cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
-    haddr = cpu_mmu_lookup(cpu, addr, get_memop(oi), ra, access_type);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD);
     ret = ldub_p(haddr);
     clear_helper_retaddr();
     return ret;
 }
 
-static uint16_t do_ld2_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                           uintptr_t ra, MMUAccessType access_type)
+tcg_target_ulong helper_ldub_mmu(CPUArchState *env, uint64_t addr,
+                                 MemOpIdx oi, uintptr_t ra)
+{
+    return do_ld1_mmu(env, addr, get_memop(oi), ra);
+}
+
+tcg_target_ulong helper_ldsb_mmu(CPUArchState *env, uint64_t addr,
+                                 MemOpIdx oi, uintptr_t ra)
+{
+    return (int8_t)do_ld1_mmu(env, addr, get_memop(oi), ra);
+}
+
+uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    uint8_t ret = do_ld1_mmu(env, addr, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+static uint16_t do_ld2_mmu(CPUArchState *env, abi_ptr addr,
+                           MemOp mop, uintptr_t ra)
 {
     void *haddr;
     uint16_t ret;
-    MemOp mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_16);
     cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, access_type);
-    ret = load_atom_2(cpu, ra, haddr, mop);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD);
+    ret = load_atom_2(env, ra, haddr, mop);
     clear_helper_retaddr();
 
     if (mop & MO_BSWAP) {
@@ -991,16 +959,36 @@ static uint16_t do_ld2_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
     return ret;
 }
 
-static uint32_t do_ld4_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                           uintptr_t ra, MMUAccessType access_type)
+tcg_target_ulong helper_lduw_mmu(CPUArchState *env, uint64_t addr,
+                                 MemOpIdx oi, uintptr_t ra)
+{
+    return do_ld2_mmu(env, addr, get_memop(oi), ra);
+}
+
+tcg_target_ulong helper_ldsw_mmu(CPUArchState *env, uint64_t addr,
+                                 MemOpIdx oi, uintptr_t ra)
+{
+    return (int16_t)do_ld2_mmu(env, addr, get_memop(oi), ra);
+}
+
+uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr addr,
+                     MemOpIdx oi, uintptr_t ra)
+{
+    uint16_t ret = do_ld2_mmu(env, addr, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+static uint32_t do_ld4_mmu(CPUArchState *env, abi_ptr addr,
+                           MemOp mop, uintptr_t ra)
 {
     void *haddr;
     uint32_t ret;
-    MemOp mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_32);
     cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, access_type);
-    ret = load_atom_4(cpu, ra, haddr, mop);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD);
+    ret = load_atom_4(env, ra, haddr, mop);
     clear_helper_retaddr();
 
     if (mop & MO_BSWAP) {
@@ -1009,16 +997,36 @@ static uint32_t do_ld4_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
     return ret;
 }
 
-static uint64_t do_ld8_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                           uintptr_t ra, MMUAccessType access_type)
+tcg_target_ulong helper_ldul_mmu(CPUArchState *env, uint64_t addr,
+                                 MemOpIdx oi, uintptr_t ra)
+{
+    return do_ld4_mmu(env, addr, get_memop(oi), ra);
+}
+
+tcg_target_ulong helper_ldsl_mmu(CPUArchState *env, uint64_t addr,
+                                 MemOpIdx oi, uintptr_t ra)
+{
+    return (int32_t)do_ld4_mmu(env, addr, get_memop(oi), ra);
+}
+
+uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr addr,
+                     MemOpIdx oi, uintptr_t ra)
+{
+    uint32_t ret = do_ld4_mmu(env, addr, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+static uint64_t do_ld8_mmu(CPUArchState *env, abi_ptr addr,
+                           MemOp mop, uintptr_t ra)
 {
     void *haddr;
     uint64_t ret;
-    MemOp mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_64);
     cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, access_type);
-    ret = load_atom_8(cpu, ra, haddr, mop);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD);
+    ret = load_atom_8(env, ra, haddr, mop);
     clear_helper_retaddr();
 
     if (mop & MO_BSWAP) {
@@ -1027,17 +1035,30 @@ static uint64_t do_ld8_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
     return ret;
 }
 
-static Int128 do_ld16_mmu(CPUState *cpu, abi_ptr addr,
-                          MemOpIdx oi, uintptr_t ra)
+uint64_t helper_ldq_mmu(CPUArchState *env, uint64_t addr,
+                        MemOpIdx oi, uintptr_t ra)
+{
+    return do_ld8_mmu(env, addr, get_memop(oi), ra);
+}
+
+uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr addr,
+                     MemOpIdx oi, uintptr_t ra)
+{
+    uint64_t ret = do_ld8_mmu(env, addr, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+static Int128 do_ld16_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOp mop, uintptr_t ra)
 {
     void *haddr;
     Int128 ret;
-    MemOp mop = get_memop(oi);
 
     tcg_debug_assert((mop & MO_SIZE) == MO_128);
     cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_LOAD);
-    ret = load_atom_16(cpu, ra, haddr, mop);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_LOAD);
+    ret = load_atom_16(env, ra, haddr, mop);
     clear_helper_retaddr();
 
     if (mop & MO_BSWAP) {
@@ -1046,81 +1067,171 @@ static Int128 do_ld16_mmu(CPUState *cpu, abi_ptr addr,
     return ret;
 }
 
-static void do_st1_mmu(CPUState *cpu, vaddr addr, uint8_t val,
+Int128 helper_ld16_mmu(CPUArchState *env, uint64_t addr,
                        MemOpIdx oi, uintptr_t ra)
+{
+    return do_ld16_mmu(env, addr, get_memop(oi), ra);
+}
+
+Int128 helper_ld_i128(CPUArchState *env, uint64_t addr, MemOpIdx oi)
+{
+    return helper_ld16_mmu(env, addr, oi, GETPC());
+}
+
+Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    Int128 ret = do_ld16_mmu(env, addr, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+static void do_st1_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,
+                       MemOp mop, uintptr_t ra)
 {
     void *haddr;
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_8);
     cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, get_memop(oi), ra, MMU_DATA_STORE);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE);
     stb_p(haddr, val);
     clear_helper_retaddr();
 }
 
-static void do_st2_mmu(CPUState *cpu, vaddr addr, uint16_t val,
-                       MemOpIdx oi, uintptr_t ra)
+void helper_stb_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    do_st1_mmu(env, addr, val, get_memop(oi), ra);
+}
+
+void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,
+                 MemOpIdx oi, uintptr_t ra)
+{
+    do_st1_mmu(env, addr, val, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+static void do_st2_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
+                       MemOp mop, uintptr_t ra)
 {
     void *haddr;
-    MemOp mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_16);
     cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE);
 
     if (mop & MO_BSWAP) {
         val = bswap16(val);
     }
-    store_atom_2(cpu, ra, haddr, mop, val);
+    store_atom_2(env, ra, haddr, mop, val);
     clear_helper_retaddr();
 }
 
-static void do_st4_mmu(CPUState *cpu, vaddr addr, uint32_t val,
-                       MemOpIdx oi, uintptr_t ra)
+void helper_stw_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    do_st2_mmu(env, addr, val, get_memop(oi), ra);
+}
+
+void cpu_stw_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    do_st2_mmu(env, addr, val, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+static void do_st4_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
+                       MemOp mop, uintptr_t ra)
 {
     void *haddr;
-    MemOp mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_32);
     cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE);
 
     if (mop & MO_BSWAP) {
         val = bswap32(val);
     }
-    store_atom_4(cpu, ra, haddr, mop, val);
+    store_atom_4(env, ra, haddr, mop, val);
     clear_helper_retaddr();
 }
 
-static void do_st8_mmu(CPUState *cpu, vaddr addr, uint64_t val,
-                       MemOpIdx oi, uintptr_t ra)
+void helper_stl_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    do_st4_mmu(env, addr, val, get_memop(oi), ra);
+}
+
+void cpu_stl_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
+                 MemOpIdx oi, uintptr_t ra)
+{
+    do_st4_mmu(env, addr, val, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+static void do_st8_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
+                       MemOp mop, uintptr_t ra)
 {
     void *haddr;
-    MemOp mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_64);
     cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE);
 
     if (mop & MO_BSWAP) {
         val = bswap64(val);
     }
-    store_atom_8(cpu, ra, haddr, mop, val);
+    store_atom_8(env, ra, haddr, mop, val);
     clear_helper_retaddr();
 }
 
-static void do_st16_mmu(CPUState *cpu, vaddr addr, Int128 val,
-                        MemOpIdx oi, uintptr_t ra)
+void helper_stq_mmu(CPUArchState *env, uint64_t addr, uint64_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    do_st8_mmu(env, addr, val, get_memop(oi), ra);
+}
+
+void cpu_stq_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    do_st8_mmu(env, addr, val, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+static void do_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val,
+                        MemOp mop, uintptr_t ra)
 {
     void *haddr;
-    MemOpIdx mop = get_memop(oi);
 
+    tcg_debug_assert((mop & MO_SIZE) == MO_128);
     cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
+    haddr = cpu_mmu_lookup(env, addr, mop, ra, MMU_DATA_STORE);
 
     if (mop & MO_BSWAP) {
         val = bswap128(val);
     }
-    store_atom_16(cpu, ra, haddr, mop, val);
+    store_atom_16(env, ra, haddr, mop, val);
     clear_helper_retaddr();
 }
 
+void helper_st16_mmu(CPUArchState *env, uint64_t addr, Int128 val,
+                     MemOpIdx oi, uintptr_t ra)
+{
+    do_st16_mmu(env, addr, val, get_memop(oi), ra);
+}
+
+void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
+{
+    helper_st16_mmu(env, addr, val, oi, GETPC());
+}
+
+void cpu_st16_mmu(CPUArchState *env, abi_ptr addr,
+                  Int128 val, MemOpIdx oi, uintptr_t ra)
+{
+    do_st16_mmu(env, addr, val, get_memop(oi), ra);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
 uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr ptr)
 {
     uint32_t ret;
@@ -1167,7 +1278,7 @@ uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr,
     void *haddr;
     uint8_t ret;
 
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_INST_FETCH);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_INST_FETCH);
     ret = ldub_p(haddr);
     clear_helper_retaddr();
     return ret;
@@ -1179,7 +1290,7 @@ uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr,
     void *haddr;
     uint16_t ret;
 
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_INST_FETCH);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_INST_FETCH);
     ret = lduw_p(haddr);
     clear_helper_retaddr();
     if (get_memop(oi) & MO_BSWAP) {
@@ -1194,7 +1305,7 @@ uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr,
     void *haddr;
     uint32_t ret;
 
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_INST_FETCH);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_INST_FETCH);
     ret = ldl_p(haddr);
     clear_helper_retaddr();
     if (get_memop(oi) & MO_BSWAP) {
@@ -1209,7 +1320,7 @@ uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
     void *haddr;
     uint64_t ret;
 
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
     ret = ldq_p(haddr);
     clear_helper_retaddr();
     if (get_memop(oi) & MO_BSWAP) {
@@ -1223,7 +1334,7 @@ uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
 /*
  * Do not allow unaligned operations to proceed.  Return the host address.
  */
-static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
+static void *atomic_mmu_lookup(CPUArchState *env, vaddr addr, MemOpIdx oi,
                                int size, uintptr_t retaddr)
 {
     MemOp mop = get_memop(oi);
@@ -1232,15 +1343,15 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
 
     /* Enforce guest required alignment.  */
     if (unlikely(addr & ((1 << a_bits) - 1))) {
-        cpu_loop_exit_sigbus(cpu, addr, MMU_DATA_STORE, retaddr);
+        cpu_loop_exit_sigbus(env_cpu(env), addr, MMU_DATA_STORE, retaddr);
     }
 
     /* Enforce qemu required alignment.  */
     if (unlikely(addr & (size - 1))) {
-        cpu_loop_exit_atomic(cpu, retaddr);
+        cpu_loop_exit_atomic(env_cpu(env), retaddr);
     }
 
-    ret = g2h(cpu, addr);
+    ret = g2h(env_cpu(env), addr);
     set_helper_retaddr(retaddr);
     return ret;
 }
@@ -1270,7 +1381,7 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
 #include "atomic_template.h"
 #endif
 
-#if defined(CONFIG_ATOMIC128) || HAVE_CMPXCHG128
+#if defined(CONFIG_ATOMIC128) || defined(CONFIG_CMPXCHG128)
 #define DATA_SIZE 16
 #include "atomic_template.h"
 #endif

audio/alsaaudio.c

@@ -904,7 +904,7 @@ static void alsa_init_per_direction(AudiodevAlsaPerDirectionOptions *apdo)
     }
 }
 
-static void *alsa_audio_init(Audiodev *dev, Error **errp)
+static void *alsa_audio_init(Audiodev *dev)
 {
     AudiodevAlsaOptions *aopts;
     assert(dev->driver == AUDIODEV_DRIVER_ALSA);
@@ -960,6 +960,7 @@ static struct audio_driver alsa_audio_driver = {
     .init           = alsa_audio_init,
     .fini           = alsa_audio_fini,
     .pcm_ops        = &alsa_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof (ALSAVoiceOut),

audio/audio-hmp-cmds.c

@@ -26,7 +26,6 @@
 #include "audio/audio.h"
 #include "monitor/hmp.h"
 #include "monitor/monitor.h"
-#include "qapi/error.h"
 #include "qapi/qmp/qdict.h"
 
 static QLIST_HEAD (capture_list_head, CaptureState) capture_head;
@@ -66,11 +65,10 @@ void hmp_wavcapture(Monitor *mon, const QDict *qdict)
     int nchannels = qdict_get_try_int(qdict, "nchannels", 2);
     const char *audiodev = qdict_get_str(qdict, "audiodev");
     CaptureState *s;
-    Error *local_err = NULL;
-    AudioState *as = audio_state_by_name(audiodev, &local_err);
+    AudioState *as = audio_state_by_name(audiodev);
 
     if (!as) {
-        error_report_err(local_err);
+        monitor_printf(mon, "Audiodev '%s' not found\n", audiodev);
         return;
     }
 

audio/audio.c

@@ -32,9 +32,7 @@
 #include "qapi/qobject-input-visitor.h"
 #include "qapi/qapi-visit-audio.h"
 #include "qapi/qapi-commands-audio.h"
-#include "qapi/qmp/qdict.h"
 #include "qemu/cutils.h"
-#include "qemu/error-report.h"
 #include "qemu/log.h"
 #include "qemu/module.h"
 #include "qemu/help_option.h"
@@ -63,22 +61,19 @@ const char *audio_prio_list[] = {
     "spice",
     CONFIG_AUDIO_DRIVERS
     "none",
+    "wav",
     NULL
 };
 
 static QLIST_HEAD(, audio_driver) audio_drivers;
-static AudiodevListHead audiodevs =
-    QSIMPLEQ_HEAD_INITIALIZER(audiodevs);
-static AudiodevListHead default_audiodevs =
-    QSIMPLEQ_HEAD_INITIALIZER(default_audiodevs);
-
+static AudiodevListHead audiodevs = QSIMPLEQ_HEAD_INITIALIZER(audiodevs);
 
 void audio_driver_register(audio_driver *drv)
 {
     QLIST_INSERT_HEAD(&audio_drivers, drv, next);
 }
 
-static audio_driver *audio_driver_lookup(const char *name)
+audio_driver *audio_driver_lookup(const char *name)
 {
     struct audio_driver *d;
     Error *local_err = NULL;
@@ -104,7 +99,6 @@ static audio_driver *audio_driver_lookup(const char *name)
 
 static QTAILQ_HEAD(AudioStateHead, AudioState) audio_states =
     QTAILQ_HEAD_INITIALIZER(audio_states);
-static AudioState *default_audio_state;
 
 const struct mixeng_volume nominal_volume = {
     .mute = 0,
@@ -117,6 +111,8 @@ const struct mixeng_volume nominal_volume = {
 #endif
 };
 
+static bool legacy_config = true;
+
 int audio_bug (const char *funcname, int cond)
 {
     if (cond) {
@@ -1557,11 +1553,9 @@ size_t audio_generic_read(HWVoiceIn *hw, void *buf, size_t size)
 }
 
 static int audio_driver_init(AudioState *s, struct audio_driver *drv,
-                             Audiodev *dev, Error **errp)
+                             bool msg, Audiodev *dev)
 {
-    Error *local_err = NULL;
-
-    s->drv_opaque = drv->init(dev, &local_err);
+    s->drv_opaque = drv->init(dev);
 
     if (s->drv_opaque) {
         if (!drv->pcm_ops->get_buffer_in) {
@@ -1573,15 +1567,13 @@ static int audio_driver_init(AudioState *s, struct audio_driver *drv,
             drv->pcm_ops->put_buffer_out = audio_generic_put_buffer_out;
         }
 
-        audio_init_nb_voices_out(s, drv, 1);
-        audio_init_nb_voices_in(s, drv, 0);
+        audio_init_nb_voices_out(s, drv);
+        audio_init_nb_voices_in(s, drv);
         s->drv = drv;
         return 0;
     } else {
-        if (local_err) {
-            error_propagate(errp, local_err);
-        } else {
-            error_setg(errp, "Could not init `%s' audio driver", drv->name);
+        if (msg) {
+            dolog("Could not init `%s' audio driver\n", drv->name);
         }
         return -1;
     }
@@ -1661,7 +1653,6 @@ static void free_audio_state(AudioState *s)
 
 void audio_cleanup(void)
 {
-    default_audio_state = NULL;
     while (!QTAILQ_EMPTY(&audio_states)) {
         AudioState *s = QTAILQ_FIRST(&audio_states);
         QTAILQ_REMOVE(&audio_states, s, list);
@@ -1688,25 +1679,19 @@ static const VMStateDescription vmstate_audio = {
     }
 };
 
-void audio_create_default_audiodevs(void)
+static void audio_validate_opts(Audiodev *dev, Error **errp);
+
+static AudiodevListEntry *audiodev_find(
+    AudiodevListHead *head, const char *drvname)
 {
-    for (int i = 0; audio_prio_list[i]; i++) {
-        if (audio_driver_lookup(audio_prio_list[i])) {
-            QDict *dict = qdict_new();
-            Audiodev *dev = NULL;
-            Visitor *v;
-
-            qdict_put_str(dict, "driver", audio_prio_list[i]);
-            qdict_put_str(dict, "id", "#default");
-
-            v = qobject_input_visitor_new_keyval(QOBJECT(dict));
-            qobject_unref(dict);
-            visit_type_Audiodev(v, NULL, &dev, &error_fatal);
-            visit_free(v);
-
-            audio_define_default(dev, &error_abort);
+    AudiodevListEntry *e;
+    QSIMPLEQ_FOREACH(e, head, next) {
+        if (strcmp(AudiodevDriver_str(e->dev->driver), drvname) == 0) {
+            return e;
         }
     }
+
+    return NULL;
 }
 
 /*
@@ -1715,16 +1700,62 @@ void audio_create_default_audiodevs(void)
  * if dev == NULL => legacy implicit initialization, return the already created
  *   state or create a new one
  */
-static AudioState *audio_init(Audiodev *dev, Error **errp)
+static AudioState *audio_init(Audiodev *dev, const char *name)
 {
     static bool atexit_registered;
+    size_t i;
     int done = 0;
-    const char *drvname;
-    VMChangeStateEntry *vmse;
+    const char *drvname = NULL;
+    VMChangeStateEntry *e;
     AudioState *s;
     struct audio_driver *driver;
+    /* silence gcc warning about uninitialized variable */
+    AudiodevListHead head = QSIMPLEQ_HEAD_INITIALIZER(head);
+
+    if (using_spice) {
+        /*
+         * When using spice allow the spice audio driver being picked
+         * as default.
+         *
+         * Temporary hack.  Using audio devices without explicit
+         * audiodev= property is already deprecated.  Same goes for
+         * the -soundhw switch.  Once this support gets finally
+         * removed we can also drop the concept of a default audio
+         * backend and this can go away.
+         */
+        driver = audio_driver_lookup("spice");
+        if (driver) {
+            driver->can_be_default = 1;
+        }
+    }
+
+    if (dev) {
+        /* -audiodev option */
+        legacy_config = false;
+        drvname = AudiodevDriver_str(dev->driver);
+    } else if (!QTAILQ_EMPTY(&audio_states)) {
+        if (!legacy_config) {
+            dolog("Device %s: audiodev default parameter is deprecated, please "
+                  "specify audiodev=%s\n", name,
+                  QTAILQ_FIRST(&audio_states)->dev->id);
+        }
+        return QTAILQ_FIRST(&audio_states);
+    } else {
+        /* legacy implicit initialization */
+        head = audio_handle_legacy_opts();
+        /*
+         * In case of legacy initialization, all Audiodevs in the list will have
+         * the same configuration (except the driver), so it doesn't matter which
+         * one we chose.  We need an Audiodev to set up AudioState before we can
+         * init a driver.  Also note that dev at this point is still in the
+         * list.
+         */
+        dev = QSIMPLEQ_FIRST(&head)->dev;
+        audio_validate_opts(dev, &error_abort);
+    }
 
     s = g_new0(AudioState, 1);
+    s->dev = dev;
 
     QLIST_INIT (&s->hw_head_out);
     QLIST_INIT (&s->hw_head_in);
@@ -1736,39 +1767,56 @@ static AudioState *audio_init(Audiodev *dev, Error **errp)
 
     s->ts = timer_new_ns(QEMU_CLOCK_VIRTUAL, audio_timer, s);
 
-    if (dev) {
-        /* -audiodev option */
-        s->dev = dev;
-        drvname = AudiodevDriver_str(dev->driver);
+    s->nb_hw_voices_out = audio_get_pdo_out(dev)->voices;
+    s->nb_hw_voices_in = audio_get_pdo_in(dev)->voices;
+
+    if (s->nb_hw_voices_out < 1) {
+        dolog ("Bogus number of playback voices %d, setting to 1\n",
+               s->nb_hw_voices_out);
+        s->nb_hw_voices_out = 1;
+    }
+
+    if (s->nb_hw_voices_in < 0) {
+        dolog ("Bogus number of capture voices %d, setting to 0\n",
+               s->nb_hw_voices_in);
+        s->nb_hw_voices_in = 0;
+    }
+
+    if (drvname) {
         driver = audio_driver_lookup(drvname);
         if (driver) {
-            done = !audio_driver_init(s, driver, dev, errp);
+            done = !audio_driver_init(s, driver, true, dev);
         } else {
-            error_setg(errp, "Unknown audio driver `%s'", drvname);
+            dolog ("Unknown audio driver `%s'\n", drvname);
         }
         if (!done) {
-            goto out;
+            free_audio_state(s);
+            return NULL;
         }
     } else {
-        assert(!default_audio_state);
-        for (;;) {
-            AudiodevListEntry *e = QSIMPLEQ_FIRST(&default_audiodevs);
-            if (!e) {
-                error_setg(errp, "no default audio driver available");
-                goto out;
+        for (i = 0; audio_prio_list[i]; i++) {
+            AudiodevListEntry *e = audiodev_find(&head, audio_prio_list[i]);
+            driver = audio_driver_lookup(audio_prio_list[i]);
+
+            if (e && driver) {
+                s->dev = dev = e->dev;
+                audio_validate_opts(dev, &error_abort);
+                done = !audio_driver_init(s, driver, false, dev);
+                if (done) {
+                    e->dev = NULL;
+                    break;
+                }
             }
-            s->dev = dev = e->dev;
-            QSIMPLEQ_REMOVE_HEAD(&default_audiodevs, next);
-            g_free(e);
-            drvname = AudiodevDriver_str(dev->driver);
-            driver = audio_driver_lookup(drvname);
-            if (!audio_driver_init(s, driver, dev, NULL)) {
-                break;
-            }
-            qapi_free_Audiodev(dev);
-            s->dev = NULL;
         }
     }
+    audio_free_audiodev_list(&head);
+
+    if (!done) {
+        driver = audio_driver_lookup("none");
+        done = !audio_driver_init(s, driver, false, dev);
+        assert(done);
+        dolog("warning: Using timer based audio emulation\n");
+    }
 
     if (dev->timer_period <= 0) {
         s->period_ticks = 1;
@@ -1776,51 +1824,37 @@ static AudioState *audio_init(Audiodev *dev, Error **errp)
         s->period_ticks = dev->timer_period * (int64_t)SCALE_US;
     }
 
-    vmse = qemu_add_vm_change_state_handler (audio_vm_change_state_handler, s);
-    if (!vmse) {
+    e = qemu_add_vm_change_state_handler (audio_vm_change_state_handler, s);
+    if (!e) {
         dolog ("warning: Could not register change state handler\n"
                "(Audio can continue looping even after stopping the VM)\n");
     }
 
     QTAILQ_INSERT_TAIL(&audio_states, s, list);
     QLIST_INIT (&s->card_head);
-    vmstate_register_any(NULL, &vmstate_audio, s);
+    vmstate_register (NULL, 0, &vmstate_audio, s);
     return s;
-
-out:
-    free_audio_state(s);
-    return NULL;
 }
 
-AudioState *audio_get_default_audio_state(Error **errp)
+void audio_free_audiodev_list(AudiodevListHead *head)
 {
-    if (!default_audio_state) {
-        default_audio_state = audio_init(NULL, errp);
-        if (!default_audio_state) {
-            if (!QSIMPLEQ_EMPTY(&audiodevs)) {
-                error_append_hint(errp, "Perhaps you wanted to use -audio or set audiodev=%s?\n",
-                                  QSIMPLEQ_FIRST(&audiodevs)->dev->id);
-            }
-        }
+    AudiodevListEntry *e;
+    while ((e = QSIMPLEQ_FIRST(head))) {
+        QSIMPLEQ_REMOVE_HEAD(head, next);
+        qapi_free_Audiodev(e->dev);
+        g_free(e);
     }
-
-    return default_audio_state;
 }
 
-bool AUD_register_card (const char *name, QEMUSoundCard *card, Error **errp)
+void AUD_register_card (const char *name, QEMUSoundCard *card)
 {
     if (!card->state) {
-        card->state = audio_get_default_audio_state(errp);
-        if (!card->state) {
-            return false;
-        }
+        card->state = audio_init(NULL, name);
     }
 
     card->name = g_strdup (name);
     memset (&card->entries, 0, sizeof (card->entries));
     QLIST_INSERT_HEAD(&card->state->card_head, card, entries);
-
-    return true;
 }
 
 void AUD_remove_card (QEMUSoundCard *card)
@@ -1842,8 +1876,10 @@ CaptureVoiceOut *AUD_add_capture(
     struct capture_callback *cb;
 
     if (!s) {
-        error_report("Capturing without setting an audiodev is not supported");
-        abort();
+        if (!legacy_config) {
+            dolog("Capturing without setting an audiodev is deprecated\n");
+        }
+        s = audio_init(NULL, NULL);
     }
 
     if (!audio_get_pdo_out(s->dev)->mixing_engine) {
@@ -1864,8 +1900,10 @@ CaptureVoiceOut *AUD_add_capture(
     cap = audio_pcm_capture_find_specific(s, as);
     if (cap) {
         QLIST_INSERT_HEAD (&cap->cb_head, cb, entries);
+        return cap;
     } else {
         HWVoiceOut *hw;
+        CaptureVoiceOut *cap;
 
         cap = g_malloc0(sizeof(*cap));
 
@@ -1899,9 +1937,8 @@ CaptureVoiceOut *AUD_add_capture(
         QLIST_FOREACH(hw, &s->hw_head_out, entries) {
             audio_attach_capture (hw);
         }
+        return cap;
     }
-
-    return cap;
 }
 
 void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
@@ -2147,24 +2184,17 @@ void audio_define(Audiodev *dev)
     QSIMPLEQ_INSERT_TAIL(&audiodevs, e, next);
 }
 
-void audio_define_default(Audiodev *dev, Error **errp)
-{
-    AudiodevListEntry *e;
-
-    audio_validate_opts(dev, errp);
-
-    e = g_new0(AudiodevListEntry, 1);
-    e->dev = dev;
-    QSIMPLEQ_INSERT_TAIL(&default_audiodevs, e, next);
-}
-
-void audio_init_audiodevs(void)
+bool audio_init_audiodevs(void)
 {
     AudiodevListEntry *e;
 
     QSIMPLEQ_FOREACH(e, &audiodevs, next) {
-        audio_init(e->dev, &error_fatal);
+        if (!audio_init(e->dev, NULL)) {
+            return false;
+        }
     }
+
+    return true;
 }
 
 audsettings audiodev_to_audsettings(AudiodevPerDirectionOptions *pdo)
@@ -2226,7 +2256,7 @@ int audio_buffer_bytes(AudiodevPerDirectionOptions *pdo,
         audioformat_bytes_per_sample(as->fmt);
 }
 
-AudioState *audio_state_by_name(const char *name, Error **errp)
+AudioState *audio_state_by_name(const char *name)
 {
     AudioState *s;
     QTAILQ_FOREACH(s, &audio_states, list) {
@@ -2235,7 +2265,6 @@ AudioState *audio_state_by_name(const char *name, Error **errp)
             return s;
         }
     }
-    error_setg(errp, "audiodev '%s' not found", name);
     return NULL;
 }
 

audio/audio.h

@@ -94,7 +94,7 @@ typedef struct QEMUAudioTimeStamp {
 void AUD_vlog (const char *cap, const char *fmt, va_list ap) G_GNUC_PRINTF(2, 0);
 void AUD_log (const char *cap, const char *fmt, ...) G_GNUC_PRINTF(2, 3);
 
-bool AUD_register_card (const char *name, QEMUSoundCard *card, Error **errp);
+void AUD_register_card (const char *name, QEMUSoundCard *card);
 void AUD_remove_card (QEMUSoundCard *card);
 CaptureVoiceOut *AUD_add_capture(
     AudioState *s,
@@ -169,14 +169,12 @@ void audio_sample_from_uint64(void *samples, int pos,
                             uint64_t left, uint64_t right);
 
 void audio_define(Audiodev *audio);
-void audio_define_default(Audiodev *dev, Error **errp);
 void audio_parse_option(const char *opt);
-void audio_create_default_audiodevs(void);
-void audio_init_audiodevs(void);
+bool audio_init_audiodevs(void);
 void audio_help(void);
+void audio_legacy_help(void);
 
-AudioState *audio_state_by_name(const char *name, Error **errp);
-AudioState *audio_get_default_audio_state(Error **errp);
+AudioState *audio_state_by_name(const char *name);
 const char *audio_get_id(QEMUSoundCard *card);
 
 #define DEFINE_AUDIO_PROPERTIES(_s, _f)         \

audio/audio_int.h

@@ -140,12 +140,13 @@ typedef struct audio_driver audio_driver;
 struct audio_driver {
     const char *name;
     const char *descr;
-    void *(*init) (Audiodev *, Error **);
+    void *(*init) (Audiodev *);
     void (*fini) (void *);
 #ifdef CONFIG_GIO
     void (*set_dbus_server) (AudioState *s, GDBusObjectManagerServer *manager, bool p2p);
 #endif
     struct audio_pcm_ops *pcm_ops;
+    int can_be_default;
     int max_voices_out;
     int max_voices_in;
     size_t voice_size_out;
@@ -242,6 +243,7 @@ extern const struct mixeng_volume nominal_volume;
 extern const char *audio_prio_list[];
 
 void audio_driver_register(audio_driver *drv);
+audio_driver *audio_driver_lookup(const char *name);
 
 void audio_pcm_init_info (struct audio_pcm_info *info, struct audsettings *as);
 void audio_pcm_info_clear_buf (struct audio_pcm_info *info, void *buf, int len);
@@ -295,6 +297,9 @@ typedef struct AudiodevListEntry {
 } AudiodevListEntry;
 
 typedef QSIMPLEQ_HEAD(, AudiodevListEntry) AudiodevListHead;
+AudiodevListHead audio_handle_legacy_opts(void);
+
+void audio_free_audiodev_list(AudiodevListHead *head);
 
 void audio_create_pdos(Audiodev *dev);
 AudiodevPerDirectionOptions *audio_get_pdo_in(Audiodev *dev);

audio/audio_legacy.c

@@ -0,0 +1,591 @@
+/*
+ * QEMU Audio subsystem: legacy configuration handling
+ *
+ * Copyright (c) 2015-2019 Zoltán Kővágó <DirtY.iCE.hu@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "qemu/osdep.h"
+#include "audio.h"
+#include "audio_int.h"
+#include "qemu/cutils.h"
+#include "qemu/timer.h"
+#include "qapi/error.h"
+#include "qapi/qapi-visit-audio.h"
+#include "qapi/visitor-impl.h"
+
+#define AUDIO_CAP "audio-legacy"
+#include "audio_int.h"
+
+static uint32_t toui32(const char *str)
+{
+    uint64_t ret;
+    if (parse_uint_full(str, 10, &ret) || ret > UINT32_MAX) {
+        dolog("Invalid integer value `%s'\n", str);
+        exit(1);
+    }
+    return ret;
+}
+
+/* helper functions to convert env variables */
+static void get_bool(const char *env, bool *dst, bool *has_dst)
+{
+    const char *val = getenv(env);
+    if (val) {
+        *dst = toui32(val) != 0;
+        *has_dst = true;
+    }
+}
+
+static void get_int(const char *env, uint32_t *dst, bool *has_dst)
+{
+    const char *val = getenv(env);
+    if (val) {
+        *dst = toui32(val);
+        *has_dst = true;
+    }
+}
+
+static void get_str(const char *env, char **dst)
+{
+    const char *val = getenv(env);
+    if (val) {
+        g_free(*dst);
+        *dst = g_strdup(val);
+    }
+}
+
+static void get_fmt(const char *env, AudioFormat *dst, bool *has_dst)
+{
+    const char *val = getenv(env);
+    if (val) {
+        size_t i;
+        for (i = 0; AudioFormat_lookup.size; ++i) {
+            if (strcasecmp(val, AudioFormat_lookup.array[i]) == 0) {
+                *dst = i;
+                *has_dst = true;
+                return;
+            }
+        }
+
+        dolog("Invalid audio format `%s'\n", val);
+        exit(1);
+    }
+}
+
+
+#if defined(CONFIG_AUDIO_ALSA) || defined(CONFIG_AUDIO_DSOUND)
+static void get_millis_to_usecs(const char *env, uint32_t *dst, bool *has_dst)
+{
+    const char *val = getenv(env);
+    if (val) {
+        *dst = toui32(val) * 1000;
+        *has_dst = true;
+    }
+}
+#endif
+
+#if defined(CONFIG_AUDIO_ALSA) || defined(CONFIG_AUDIO_COREAUDIO) || \
+    defined(CONFIG_AUDIO_PA) || defined(CONFIG_AUDIO_SDL) || \
+    defined(CONFIG_AUDIO_DSOUND) || defined(CONFIG_AUDIO_OSS)
+static uint32_t frames_to_usecs(uint32_t frames,
+                                AudiodevPerDirectionOptions *pdo)
+{
+    uint32_t freq = pdo->has_frequency ? pdo->frequency : 44100;
+    return (frames * 1000000 + freq / 2) / freq;
+}
+#endif
+
+#ifdef CONFIG_AUDIO_COREAUDIO
+static void get_frames_to_usecs(const char *env, uint32_t *dst, bool *has_dst,
+                                AudiodevPerDirectionOptions *pdo)
+{
+    const char *val = getenv(env);
+    if (val) {
+        *dst = frames_to_usecs(toui32(val), pdo);
+        *has_dst = true;
+    }
+}
+#endif
+
+#if defined(CONFIG_AUDIO_PA) || defined(CONFIG_AUDIO_SDL) || \
+    defined(CONFIG_AUDIO_DSOUND) || defined(CONFIG_AUDIO_OSS)
+static uint32_t samples_to_usecs(uint32_t samples,
+                                 AudiodevPerDirectionOptions *pdo)
+{
+    uint32_t channels = pdo->has_channels ? pdo->channels : 2;
+    return frames_to_usecs(samples / channels, pdo);
+}
+#endif
+
+#if defined(CONFIG_AUDIO_PA) || defined(CONFIG_AUDIO_SDL)
+static void get_samples_to_usecs(const char *env, uint32_t *dst, bool *has_dst,
+                                 AudiodevPerDirectionOptions *pdo)
+{
+    const char *val = getenv(env);
+    if (val) {
+        *dst = samples_to_usecs(toui32(val), pdo);
+        *has_dst = true;
+    }
+}
+#endif
+
+#if defined(CONFIG_AUDIO_DSOUND) || defined(CONFIG_AUDIO_OSS)
+static uint32_t bytes_to_usecs(uint32_t bytes, AudiodevPerDirectionOptions *pdo)
+{
+    AudioFormat fmt = pdo->has_format ? pdo->format : AUDIO_FORMAT_S16;
+    uint32_t bytes_per_sample = audioformat_bytes_per_sample(fmt);
+    return samples_to_usecs(bytes / bytes_per_sample, pdo);
+}
+
+static void get_bytes_to_usecs(const char *env, uint32_t *dst, bool *has_dst,
+                               AudiodevPerDirectionOptions *pdo)
+{
+    const char *val = getenv(env);
+    if (val) {
+        *dst = bytes_to_usecs(toui32(val), pdo);
+        *has_dst = true;
+    }
+}
+#endif
+
+/* backend specific functions */
+
+#ifdef CONFIG_AUDIO_ALSA
+/* ALSA */
+static void handle_alsa_per_direction(
+    AudiodevAlsaPerDirectionOptions *apdo, const char *prefix)
+{
+    char buf[64];
+    size_t len = strlen(prefix);
+    bool size_in_usecs = false;
+    bool dummy;
+
+    memcpy(buf, prefix, len);
+    strcpy(buf + len, "TRY_POLL");
+    get_bool(buf, &apdo->try_poll, &apdo->has_try_poll);
+
+    strcpy(buf + len, "DEV");
+    get_str(buf, &apdo->dev);
+
+    strcpy(buf + len, "SIZE_IN_USEC");
+    get_bool(buf, &size_in_usecs, &dummy);
+
+    strcpy(buf + len, "PERIOD_SIZE");
+    get_int(buf, &apdo->period_length, &apdo->has_period_length);
+    if (apdo->has_period_length && !size_in_usecs) {
+        apdo->period_length = frames_to_usecs(
+            apdo->period_length,
+            qapi_AudiodevAlsaPerDirectionOptions_base(apdo));
+    }
+
+    strcpy(buf + len, "BUFFER_SIZE");
+    get_int(buf, &apdo->buffer_length, &apdo->has_buffer_length);
+    if (apdo->has_buffer_length && !size_in_usecs) {
+        apdo->buffer_length = frames_to_usecs(
+            apdo->buffer_length,
+            qapi_AudiodevAlsaPerDirectionOptions_base(apdo));
+    }
+}
+
+static void handle_alsa(Audiodev *dev)
+{
+    AudiodevAlsaOptions *aopt = &dev->u.alsa;
+    handle_alsa_per_direction(aopt->in, "QEMU_ALSA_ADC_");
+    handle_alsa_per_direction(aopt->out, "QEMU_ALSA_DAC_");
+
+    get_millis_to_usecs("QEMU_ALSA_THRESHOLD",
+                        &aopt->threshold, &aopt->has_threshold);
+}
+#endif
+
+#ifdef CONFIG_AUDIO_COREAUDIO
+/* coreaudio */
+static void handle_coreaudio(Audiodev *dev)
+{
+    get_frames_to_usecs(
+        "QEMU_COREAUDIO_BUFFER_SIZE",
+        &dev->u.coreaudio.out->buffer_length,
+        &dev->u.coreaudio.out->has_buffer_length,
+        qapi_AudiodevCoreaudioPerDirectionOptions_base(dev->u.coreaudio.out));
+    get_int("QEMU_COREAUDIO_BUFFER_COUNT",
+            &dev->u.coreaudio.out->buffer_count,
+            &dev->u.coreaudio.out->has_buffer_count);
+}
+#endif
+
+#ifdef CONFIG_AUDIO_DSOUND
+/* dsound */
+static void handle_dsound(Audiodev *dev)
+{
+    get_millis_to_usecs("QEMU_DSOUND_LATENCY_MILLIS",
+                        &dev->u.dsound.latency, &dev->u.dsound.has_latency);
+    get_bytes_to_usecs("QEMU_DSOUND_BUFSIZE_OUT",
+                       &dev->u.dsound.out->buffer_length,
+                       &dev->u.dsound.out->has_buffer_length,
+                       dev->u.dsound.out);
+    get_bytes_to_usecs("QEMU_DSOUND_BUFSIZE_IN",
+                       &dev->u.dsound.in->buffer_length,
+                       &dev->u.dsound.in->has_buffer_length,
+                       dev->u.dsound.in);
+}
+#endif
+
+#ifdef CONFIG_AUDIO_OSS
+/* OSS */
+static void handle_oss_per_direction(
+    AudiodevOssPerDirectionOptions *opdo, const char *try_poll_env,
+    const char *dev_env)
+{
+    get_bool(try_poll_env, &opdo->try_poll, &opdo->has_try_poll);
+    get_str(dev_env, &opdo->dev);
+
+    get_bytes_to_usecs("QEMU_OSS_FRAGSIZE",
+                       &opdo->buffer_length, &opdo->has_buffer_length,
+                       qapi_AudiodevOssPerDirectionOptions_base(opdo));
+    get_int("QEMU_OSS_NFRAGS", &opdo->buffer_count,
+            &opdo->has_buffer_count);
+}
+
+static void handle_oss(Audiodev *dev)
+{
+    AudiodevOssOptions *oopt = &dev->u.oss;
+    handle_oss_per_direction(oopt->in, "QEMU_AUDIO_ADC_TRY_POLL",
+                             "QEMU_OSS_ADC_DEV");
+    handle_oss_per_direction(oopt->out, "QEMU_AUDIO_DAC_TRY_POLL",
+                             "QEMU_OSS_DAC_DEV");
+
+    get_bool("QEMU_OSS_MMAP", &oopt->try_mmap, &oopt->has_try_mmap);
+    get_bool("QEMU_OSS_EXCLUSIVE", &oopt->exclusive, &oopt->has_exclusive);
+    get_int("QEMU_OSS_POLICY", &oopt->dsp_policy, &oopt->has_dsp_policy);
+}
+#endif
+
+#ifdef CONFIG_AUDIO_PA
+/* pulseaudio */
+static void handle_pa_per_direction(
+    AudiodevPaPerDirectionOptions *ppdo, const char *env)
+{
+    get_str(env, &ppdo->name);
+}
+
+static void handle_pa(Audiodev *dev)
+{
+    handle_pa_per_direction(dev->u.pa.in, "QEMU_PA_SOURCE");
+    handle_pa_per_direction(dev->u.pa.out, "QEMU_PA_SINK");
+
+    get_samples_to_usecs(
+        "QEMU_PA_SAMPLES", &dev->u.pa.in->buffer_length,
+        &dev->u.pa.in->has_buffer_length,
+        qapi_AudiodevPaPerDirectionOptions_base(dev->u.pa.in));
+    get_samples_to_usecs(
+        "QEMU_PA_SAMPLES", &dev->u.pa.out->buffer_length,
+        &dev->u.pa.out->has_buffer_length,
+        qapi_AudiodevPaPerDirectionOptions_base(dev->u.pa.out));
+
+    get_str("QEMU_PA_SERVER", &dev->u.pa.server);
+}
+#endif
+
+#ifdef CONFIG_AUDIO_SDL
+/* SDL */
+static void handle_sdl(Audiodev *dev)
+{
+    /* SDL is output only */
+    get_samples_to_usecs("QEMU_SDL_SAMPLES", &dev->u.sdl.out->buffer_length,
+        &dev->u.sdl.out->has_buffer_length,
+        qapi_AudiodevSdlPerDirectionOptions_base(dev->u.sdl.out));
+}
+#endif
+
+/* wav */
+static void handle_wav(Audiodev *dev)
+{
+    get_int("QEMU_WAV_FREQUENCY",
+            &dev->u.wav.out->frequency, &dev->u.wav.out->has_frequency);
+    get_fmt("QEMU_WAV_FORMAT", &dev->u.wav.out->format,
+            &dev->u.wav.out->has_format);
+    get_int("QEMU_WAV_DAC_FIXED_CHANNELS",
+            &dev->u.wav.out->channels, &dev->u.wav.out->has_channels);
+    get_str("QEMU_WAV_PATH", &dev->u.wav.path);
+}
+
+/* general */
+static void handle_per_direction(
+    AudiodevPerDirectionOptions *pdo, const char *prefix)
+{
+    char buf[64];
+    size_t len = strlen(prefix);
+
+    memcpy(buf, prefix, len);
+    strcpy(buf + len, "FIXED_SETTINGS");
+    get_bool(buf, &pdo->fixed_settings, &pdo->has_fixed_settings);
+
+    strcpy(buf + len, "FIXED_FREQ");
+    get_int(buf, &pdo->frequency, &pdo->has_frequency);
+
+    strcpy(buf + len, "FIXED_FMT");
+    get_fmt(buf, &pdo->format, &pdo->has_format);
+
+    strcpy(buf + len, "FIXED_CHANNELS");
+    get_int(buf, &pdo->channels, &pdo->has_channels);
+
+    strcpy(buf + len, "VOICES");
+    get_int(buf, &pdo->voices, &pdo->has_voices);
+}
+
+static AudiodevListEntry *legacy_opt(const char *drvname)
+{
+    AudiodevListEntry *e = g_new0(AudiodevListEntry, 1);
+    e->dev = g_new0(Audiodev, 1);
+    e->dev->id = g_strdup(drvname);
+    e->dev->driver = qapi_enum_parse(
+        &AudiodevDriver_lookup, drvname, -1, &error_abort);
+
+    audio_create_pdos(e->dev);
+
+    handle_per_direction(audio_get_pdo_in(e->dev), "QEMU_AUDIO_ADC_");
+    handle_per_direction(audio_get_pdo_out(e->dev), "QEMU_AUDIO_DAC_");
+
+    /* Original description: Timer period in HZ (0 - use lowest possible) */
+    get_int("QEMU_AUDIO_TIMER_PERIOD",
+            &e->dev->timer_period, &e->dev->has_timer_period);
+    if (e->dev->has_timer_period && e->dev->timer_period) {
+        e->dev->timer_period = NANOSECONDS_PER_SECOND / 1000 /
+                               e->dev->timer_period;
+    }
+
+    switch (e->dev->driver) {
+#ifdef CONFIG_AUDIO_ALSA
+    case AUDIODEV_DRIVER_ALSA:
+        handle_alsa(e->dev);
+        break;
+#endif
+
+#ifdef CONFIG_AUDIO_COREAUDIO
+    case AUDIODEV_DRIVER_COREAUDIO:
+        handle_coreaudio(e->dev);
+        break;
+#endif
+
+#ifdef CONFIG_AUDIO_DSOUND
+    case AUDIODEV_DRIVER_DSOUND:
+        handle_dsound(e->dev);
+        break;
+#endif
+
+#ifdef CONFIG_AUDIO_OSS
+    case AUDIODEV_DRIVER_OSS:
+        handle_oss(e->dev);
+        break;
+#endif
+
+#ifdef CONFIG_AUDIO_PA
+    case AUDIODEV_DRIVER_PA:
+        handle_pa(e->dev);
+        break;
+#endif
+
+#ifdef CONFIG_AUDIO_SDL
+    case AUDIODEV_DRIVER_SDL:
+        handle_sdl(e->dev);
+        break;
+#endif
+
+    case AUDIODEV_DRIVER_WAV:
+        handle_wav(e->dev);
+        break;
+
+    default:
+        break;
+    }
+
+    return e;
+}
+
+AudiodevListHead audio_handle_legacy_opts(void)
+{
+    const char *drvname = getenv("QEMU_AUDIO_DRV");
+    AudiodevListHead head = QSIMPLEQ_HEAD_INITIALIZER(head);
+
+    if (drvname) {
+        AudiodevListEntry *e;
+        audio_driver *driver = audio_driver_lookup(drvname);
+        if (!driver) {
+            dolog("Unknown audio driver `%s'\n", drvname);
+            exit(1);
+        }
+        e = legacy_opt(drvname);
+        QSIMPLEQ_INSERT_TAIL(&head, e, next);
+    } else {
+        for (int i = 0; audio_prio_list[i]; i++) {
+            audio_driver *driver = audio_driver_lookup(audio_prio_list[i]);
+            if (driver && driver->can_be_default) {
+                AudiodevListEntry *e = legacy_opt(driver->name);
+                QSIMPLEQ_INSERT_TAIL(&head, e, next);
+            }
+        }
+        if (QSIMPLEQ_EMPTY(&head)) {
+            dolog("Internal error: no default audio driver available\n");
+            exit(1);
+        }
+    }
+
+    return head;
+}
+
+/* visitor to print -audiodev option */
+typedef struct {
+    Visitor visitor;
+
+    bool comma;
+    GList *path;
+} LegacyPrintVisitor;
+
+static bool lv_start_struct(Visitor *v, const char *name, void **obj,
+                            size_t size, Error **errp)
+{
+    LegacyPrintVisitor *lv = (LegacyPrintVisitor *) v;
+    lv->path = g_list_append(lv->path, g_strdup(name));
+    return true;
+}
+
+static void lv_end_struct(Visitor *v, void **obj)
+{
+    LegacyPrintVisitor *lv = (LegacyPrintVisitor *) v;
+    lv->path = g_list_delete_link(lv->path, g_list_last(lv->path));
+}
+
+static void lv_print_key(Visitor *v, const char *name)
+{
+    GList *e;
+    LegacyPrintVisitor *lv = (LegacyPrintVisitor *) v;
+    if (lv->comma) {
+        putchar(',');
+    } else {
+        lv->comma = true;
+    }
+
+    for (e = lv->path; e; e = e->next) {
+        if (e->data) {
+            printf("%s.", (const char *) e->data);
+        }
+    }
+
+    printf("%s=", name);
+}
+
+static bool lv_type_int64(Visitor *v, const char *name, int64_t *obj,
+                          Error **errp)
+{
+    lv_print_key(v, name);
+    printf("%" PRIi64, *obj);
+    return true;
+}
+
+static bool lv_type_uint64(Visitor *v, const char *name, uint64_t *obj,
+                           Error **errp)
+{
+    lv_print_key(v, name);
+    printf("%" PRIu64, *obj);
+    return true;
+}
+
+static bool lv_type_bool(Visitor *v, const char *name, bool *obj, Error **errp)
+{
+    lv_print_key(v, name);
+    printf("%s", *obj ? "on" : "off");
+    return true;
+}
+
+static bool lv_type_str(Visitor *v, const char *name, char **obj, Error **errp)
+{
+    const char *str = *obj;
+    lv_print_key(v, name);
+
+    while (*str) {
+        if (*str == ',') {
+            putchar(',');
+        }
+        putchar(*str++);
+    }
+    return true;
+}
+
+static void lv_complete(Visitor *v, void *opaque)
+{
+    LegacyPrintVisitor *lv = (LegacyPrintVisitor *) v;
+    assert(lv->path == NULL);
+}
+
+static void lv_free(Visitor *v)
+{
+    LegacyPrintVisitor *lv = (LegacyPrintVisitor *) v;
+
+    g_list_free_full(lv->path, g_free);
+    g_free(lv);
+}
+
+static Visitor *legacy_visitor_new(void)
+{
+    LegacyPrintVisitor *lv = g_new0(LegacyPrintVisitor, 1);
+
+    lv->visitor.start_struct = lv_start_struct;
+    lv->visitor.end_struct = lv_end_struct;
+    /* lists not supported */
+    lv->visitor.type_int64 = lv_type_int64;
+    lv->visitor.type_uint64 = lv_type_uint64;
+    lv->visitor.type_bool = lv_type_bool;
+    lv->visitor.type_str = lv_type_str;
+
+    lv->visitor.type = VISITOR_OUTPUT;
+    lv->visitor.complete = lv_complete;
+    lv->visitor.free = lv_free;
+
+    return &lv->visitor;
+}
+
+void audio_legacy_help(void)
+{
+    AudiodevListHead head;
+    AudiodevListEntry *e;
+
+    printf("Environment variable based configuration deprecated.\n");
+    printf("Please use the new -audiodev option.\n");
+
+    head = audio_handle_legacy_opts();
+    printf("\nEquivalent -audiodev to your current environment variables:\n");
+    if (!getenv("QEMU_AUDIO_DRV")) {
+        printf("(Since you didn't specify QEMU_AUDIO_DRV, I'll list all "
+               "possibilities)\n");
+    }
+
+    QSIMPLEQ_FOREACH(e, &head, next) {
+        Visitor *v;
+        Audiodev *dev = e->dev;
+        printf("-audiodev ");
+
+        v = legacy_visitor_new();
+        visit_type_Audiodev(v, NULL, &dev, &error_abort);
+        visit_free(v);
+
+        printf("\n");
+    }
+    audio_free_audiodev_list(&head);
+}

audio/audio_template.h

@@ -37,12 +37,11 @@
 #endif
 
 static void glue(audio_init_nb_voices_, TYPE)(AudioState *s,
-                                              struct audio_driver *drv, int min_voices)
+                                              struct audio_driver *drv)
 {
     int max_voices = glue (drv->max_voices_, TYPE);
     size_t voice_size = glue(drv->voice_size_, TYPE);
 
-    glue (s->nb_hw_voices_, TYPE) = glue(audio_get_pdo_, TYPE)(s->dev)->voices;
     if (glue (s->nb_hw_voices_, TYPE) > max_voices) {
         if (!max_voices) {
 #ifdef DAC
@@ -57,12 +56,6 @@ static void glue(audio_init_nb_voices_, TYPE)(AudioState *s,
         glue (s->nb_hw_voices_, TYPE) = max_voices;
     }
 
-    if (glue (s->nb_hw_voices_, TYPE) < min_voices) {
-        dolog ("Bogus number of " NAME " voices %d, setting to %d\n",
-               glue (s->nb_hw_voices_, TYPE),
-               min_voices);
-    }
-
     if (audio_bug(__func__, !voice_size && max_voices)) {
         dolog ("drv=`%s' voice_size=0 max_voices=%d\n",
                drv->name, max_voices);

audio/coreaudio.m

@@ -644,7 +644,7 @@ static void coreaudio_enable_out(HWVoiceOut *hw, bool enable)
     update_device_playback_state(core);
 }
 
-static void *coreaudio_audio_init(Audiodev *dev, Error **errp)
+static void *coreaudio_audio_init(Audiodev *dev)
 {
     return dev;
 }
@@ -673,6 +673,7 @@ static struct audio_driver coreaudio_audio_driver = {
     .init           = coreaudio_audio_init,
     .fini           = coreaudio_audio_fini,
     .pcm_ops        = &coreaudio_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = 1,
     .max_voices_in  = 0,
     .voice_size_out = sizeof (coreaudioVoiceOut),

audio/dbusaudio.c

@@ -395,7 +395,7 @@ dbus_enable_in(HWVoiceIn *hw, bool enable)
 }
 
 static void *
-dbus_audio_init(Audiodev *dev, Error **errp)
+dbus_audio_init(Audiodev *dev)
 {
     DBusAudio *da = g_new0(DBusAudio, 1);
 
@@ -676,6 +676,7 @@ static struct audio_driver dbus_audio_driver = {
     .fini            = dbus_audio_fini,
     .set_dbus_server = dbus_audio_set_server,
     .pcm_ops         = &dbus_pcm_ops,
+    .can_be_default  = 1,
     .max_voices_out  = INT_MAX,
     .max_voices_in   = INT_MAX,
     .voice_size_out  = sizeof(DBusVoiceOut),

audio/dsoundaudio.c

@@ -619,7 +619,7 @@ static void dsound_audio_fini (void *opaque)
     g_free(s);
 }
 
-static void *dsound_audio_init(Audiodev *dev, Error **errp)
+static void *dsound_audio_init(Audiodev *dev)
 {
     int err;
     HRESULT hr;
@@ -721,6 +721,7 @@ static struct audio_driver dsound_audio_driver = {
     .init           = dsound_audio_init,
     .fini           = dsound_audio_fini,
     .pcm_ops        = &dsound_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = 1,
     .voice_size_out = sizeof (DSoundVoiceOut),

audio/jackaudio.c

@@ -70,9 +70,6 @@ typedef struct QJackClient {
     int             buffersize;
     jack_port_t   **port;
     QJackBuffer     fifo;
-
-    /* Used as workspace by qjack_process() */
-    float **process_buffers;
 }
 QJackClient;
 
@@ -270,21 +267,22 @@ static int qjack_process(jack_nframes_t nframes, void *arg)
     }
 
     /* get the buffers for the ports */
+    float *buffers[c->nchannels];
     for (int i = 0; i < c->nchannels; ++i) {
-        c->process_buffers[i] = jack_port_get_buffer(c->port[i], nframes);
+        buffers[i] = jack_port_get_buffer(c->port[i], nframes);
     }
 
     if (c->out) {
         if (likely(c->enabled)) {
-            qjack_buffer_read_l(&c->fifo, c->process_buffers, nframes);
+            qjack_buffer_read_l(&c->fifo, buffers, nframes);
         } else {
             for (int i = 0; i < c->nchannels; ++i) {
-                memset(c->process_buffers[i], 0, nframes * sizeof(float));
+                memset(buffers[i], 0, nframes * sizeof(float));
             }
         }
     } else {
         if (likely(c->enabled)) {
-            qjack_buffer_write_l(&c->fifo, c->process_buffers, nframes);
+            qjack_buffer_write_l(&c->fifo, buffers, nframes);
         }
     }
 
@@ -402,8 +400,7 @@ static void qjack_client_connect_ports(QJackClient *c)
 static int qjack_client_init(QJackClient *c)
 {
     jack_status_t status;
-    int client_name_len = jack_client_name_size(); /* includes NUL */
-    g_autofree char *client_name = g_new(char, client_name_len);
+    char client_name[jack_client_name_size()];
     jack_options_t options = JackNullOption;
 
     if (c->state == QJACK_STATE_RUNNING) {
@@ -412,7 +409,7 @@ static int qjack_client_init(QJackClient *c)
 
     c->connect_ports = true;
 
-    snprintf(client_name, client_name_len, "%s-%s",
+    snprintf(client_name, sizeof(client_name), "%s-%s",
         c->out ? "out" : "in",
         c->opt->client_name ? c->opt->client_name : audio_application_name());
 
@@ -450,9 +447,6 @@ static int qjack_client_init(QJackClient *c)
           jack_get_client_name(c->client));
     }
 
-    /* Allocate working buffer for process callback */
-    c->process_buffers = g_new(float *, c->nchannels);
-
     jack_set_process_callback(c->client, qjack_process , c);
     jack_set_port_registration_callback(c->client, qjack_port_registration, c);
     jack_set_xrun_callback(c->client, qjack_xrun, c);
@@ -584,7 +578,6 @@ static void qjack_client_fini_locked(QJackClient *c)
 
         qjack_buffer_free(&c->fifo);
         g_free(c->port);
-        g_free(c->process_buffers);
 
         c->state = QJACK_STATE_DISCONNECTED;
         /* fallthrough */
@@ -645,7 +638,7 @@ static int qjack_thread_creator(jack_native_thread_t *thread,
 }
 #endif
 
-static void *qjack_init(Audiodev *dev, Error **errp)
+static void *qjack_init(Audiodev *dev)
 {
     assert(dev->driver == AUDIODEV_DRIVER_JACK);
     return dev;
@@ -676,6 +669,7 @@ static struct audio_driver jack_driver = {
     .init           = qjack_init,
     .fini           = qjack_fini,
     .pcm_ops        = &jack_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof(QJackOut),

audio/meson.build

@@ -1,6 +1,7 @@
 system_ss.add([spice_headers, files('audio.c')])
 system_ss.add(files(
   'audio-hmp-cmds.c',
+  'audio_legacy.c',
   'mixeng.c',
   'noaudio.c',
   'wavaudio.c',
@@ -30,8 +31,7 @@ endforeach
 
 if dbus_display
     module_ss = ss.source_set()
-    module_ss.add(when: [gio, dbus_display1_dep, pixman],
-                  if_true: files('dbusaudio.c'))
+    module_ss.add(when: gio, if_true: files('dbusaudio.c'))
     audio_modules += {'dbus': module_ss}
 endif
 

audio/mixeng.h

@@ -38,7 +38,7 @@ typedef struct st_sample st_sample;
 typedef void (t_sample) (struct st_sample *dst, const void *src, int samples);
 typedef void (f_sample) (void *dst, const struct st_sample *src, int samples);
 
-/* indices: [stereo][signed][swap endianness][8, 16 or 32-bits] */
+/* indices: [stereo][signed][swap endiannes][8, 16 or 32-bits] */
 extern t_sample *mixeng_conv[2][2][2][3];
 extern f_sample *mixeng_clip[2][2][2][3];
 

audio/noaudio.c

@@ -104,7 +104,7 @@ static void no_enable_in(HWVoiceIn *hw, bool enable)
     }
 }
 
-static void *no_audio_init(Audiodev *dev, Error **errp)
+static void *no_audio_init(Audiodev *dev)
 {
     return &no_audio_init;
 }
@@ -135,6 +135,7 @@ static struct audio_driver no_audio_driver = {
     .init           = no_audio_init,
     .fini           = no_audio_fini,
     .pcm_ops        = &no_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof (NoVoiceOut),

audio/ossaudio.c

@@ -28,7 +28,6 @@
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
 #include "qemu/host-utils.h"
-#include "qapi/error.h"
 #include "audio.h"
 #include "trace.h"
 
@@ -549,6 +548,7 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
                        hw->size_emul);
             hw->buf_emul = NULL;
         } else {
+            int err;
             int trig = 0;
             if (ioctl (fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
                 oss_logerr (errno, "SNDCTL_DSP_SETTRIGGER 0 failed\n");
@@ -736,7 +736,7 @@ static void oss_init_per_direction(AudiodevOssPerDirectionOptions *opdo)
     }
 }
 
-static void *oss_audio_init(Audiodev *dev, Error **errp)
+static void *oss_audio_init(Audiodev *dev)
 {
     AudiodevOssOptions *oopts;
     assert(dev->driver == AUDIODEV_DRIVER_OSS);
@@ -745,12 +745,8 @@ static void *oss_audio_init(Audiodev *dev, Error **errp)
     oss_init_per_direction(oopts->in);
     oss_init_per_direction(oopts->out);
 
-    if (access(oopts->in->dev ?: "/dev/dsp", R_OK | W_OK) < 0) {
-        error_setg_errno(errp, errno, "%s not accessible", oopts->in->dev ?: "/dev/dsp");
-        return NULL;
-    }
-    if (access(oopts->out->dev ?: "/dev/dsp", R_OK | W_OK) < 0) {
-        error_setg_errno(errp, errno, "%s not accessible", oopts->out->dev ?: "/dev/dsp");
+    if (access(oopts->in->dev ?: "/dev/dsp", R_OK | W_OK) < 0 ||
+        access(oopts->out->dev ?: "/dev/dsp", R_OK | W_OK) < 0) {
         return NULL;
     }
     return dev;
@@ -783,6 +779,7 @@ static struct audio_driver oss_audio_driver = {
     .init           = oss_audio_init,
     .fini           = oss_audio_fini,
     .pcm_ops        = &oss_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof (OSSVoiceOut),

audio/paaudio.c

@@ -3,7 +3,7 @@
 #include "qemu/osdep.h"
 #include "qemu/module.h"
 #include "audio.h"
-#include "qapi/error.h"
+#include "qapi/opts-visitor.h"
 
 #include <pulse/pulseaudio.h>
 
@@ -818,7 +818,7 @@ fail:
     return NULL;
 }
 
-static void *qpa_audio_init(Audiodev *dev, Error **errp)
+static void *qpa_audio_init(Audiodev *dev)
 {
     paaudio *g;
     AudiodevPaOptions *popts = &dev->u.pa;
@@ -834,12 +834,10 @@ static void *qpa_audio_init(Audiodev *dev, Error **errp)
 
         runtime = getenv("XDG_RUNTIME_DIR");
         if (!runtime) {
-            error_setg(errp, "XDG_RUNTIME_DIR not set");
             return NULL;
         }
         snprintf(pidfile, sizeof(pidfile), "%s/pulse/pid", runtime);
         if (stat(pidfile, &st) != 0) {
-            error_setg_errno(errp, errno, "could not stat pidfile %s", pidfile);
             return NULL;
         }
     }
@@ -869,7 +867,6 @@ static void *qpa_audio_init(Audiodev *dev, Error **errp)
     }
     if (!g->conn) {
         g_free(g);
-        error_setg(errp, "could not connect to PulseAudio server");
         return NULL;
     }
 
@@ -931,6 +928,7 @@ static struct audio_driver pa_audio_driver = {
     .init           = qpa_audio_init,
     .fini           = qpa_audio_fini,
     .pcm_ops        = &qpa_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof (PAVoiceOut),

audio/pwaudio.c

@@ -1,5 +1,5 @@
 /*
- * QEMU PipeWire audio driver
+ * QEMU Pipewire audio driver
  *
  * Copyright (c) 2023 Red Hat Inc.
  *
@@ -13,7 +13,6 @@
 #include "audio.h"
 #include <errno.h>
 #include "qemu/error-report.h"
-#include "qapi/error.h"
 #include <spa/param/audio/format-utils.h>
 #include <spa/utils/ringbuffer.h>
 #include <spa/utils/result.h>
@@ -67,9 +66,6 @@ typedef struct PWVoiceIn {
     PWVoice v;
 } PWVoiceIn;
 
-#define PW_VOICE_IN(v) ((PWVoiceIn *)v)
-#define PW_VOICE_OUT(v) ((PWVoiceOut *)v)
-
 static void
 stream_destroy(void *data)
 {
@@ -201,6 +197,16 @@ on_stream_state_changed(void *data, enum pw_stream_state old,
 
     trace_pw_state_changed(pw_stream_get_node_id(v->stream),
                            pw_stream_state_as_string(state));
+
+    switch (state) {
+    case PW_STREAM_STATE_ERROR:
+    case PW_STREAM_STATE_UNCONNECTED:
+        break;
+    case PW_STREAM_STATE_PAUSED:
+    case PW_STREAM_STATE_CONNECTING:
+    case PW_STREAM_STATE_STREAMING:
+        break;
+    }
 }
 
 static const struct pw_stream_events capture_stream_events = {
@@ -418,8 +424,8 @@ pw_to_audfmt(enum spa_audio_format fmt, int *endianness,
 }
 
 static int
-qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
-               const char *name, enum spa_direction dir)
+create_stream(pwaudio *c, PWVoice *v, const char *stream_name,
+              const char *name, enum spa_direction dir)
 {
     int res;
     uint32_t n_params;
@@ -430,10 +436,6 @@ qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
     struct pw_properties *props;
 
     props = pw_properties_new(NULL, NULL);
-    if (!props) {
-        error_report("Failed to create PW properties: %s", g_strerror(errno));
-        return -1;
-    }
 
     /* 75% of the timer period for faster updates */
     buf_samples = (uint64_t)v->g->dev->timer_period * v->info.rate
@@ -446,8 +448,8 @@ qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
         pw_properties_set(props, PW_KEY_TARGET_OBJECT, name);
     }
     v->stream = pw_stream_new(c->core, stream_name, props);
+
     if (v->stream == NULL) {
-        error_report("Failed to create PW stream: %s", g_strerror(errno));
         return -1;
     }
 
@@ -475,7 +477,6 @@ qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
                             PW_STREAM_FLAG_MAP_BUFFERS |
                             PW_STREAM_FLAG_RT_PROCESS, params, n_params);
     if (res < 0) {
-        error_report("Failed to connect PW stream: %s", g_strerror(errno));
         pw_stream_destroy(v->stream);
         return -1;
     }
@@ -483,37 +484,71 @@ qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
     return 0;
 }
 
-static void
-qpw_set_position(uint32_t channels, uint32_t position[SPA_AUDIO_MAX_CHANNELS])
+static int
+qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
+               const char *name, enum spa_direction dir)
 {
-    memcpy(position, (uint32_t[SPA_AUDIO_MAX_CHANNELS]) { SPA_AUDIO_CHANNEL_UNKNOWN, },
-           sizeof(uint32_t) * SPA_AUDIO_MAX_CHANNELS);
-    /*
-     * TODO: This currently expects the only frontend supporting more than 2
-     * channels is the usb-audio.  We will need some means to set channel
-     * order when a new frontend gains multi-channel support.
-     */
-    switch (channels) {
+    int r;
+
+    switch (v->info.channels) {
     case 8:
-        position[6] = SPA_AUDIO_CHANNEL_SL;
-        position[7] = SPA_AUDIO_CHANNEL_SR;
-        /* fallthrough */
+        v->info.position[0] = SPA_AUDIO_CHANNEL_FL;
+        v->info.position[1] = SPA_AUDIO_CHANNEL_FR;
+        v->info.position[2] = SPA_AUDIO_CHANNEL_FC;
+        v->info.position[3] = SPA_AUDIO_CHANNEL_LFE;
+        v->info.position[4] = SPA_AUDIO_CHANNEL_RL;
+        v->info.position[5] = SPA_AUDIO_CHANNEL_RR;
+        v->info.position[6] = SPA_AUDIO_CHANNEL_SL;
+        v->info.position[7] = SPA_AUDIO_CHANNEL_SR;
+        break;
     case 6:
-        position[2] = SPA_AUDIO_CHANNEL_FC;
-        position[3] = SPA_AUDIO_CHANNEL_LFE;
-        position[4] = SPA_AUDIO_CHANNEL_RL;
-        position[5] = SPA_AUDIO_CHANNEL_RR;
-        /* fallthrough */
+        v->info.position[0] = SPA_AUDIO_CHANNEL_FL;
+        v->info.position[1] = SPA_AUDIO_CHANNEL_FR;
+        v->info.position[2] = SPA_AUDIO_CHANNEL_FC;
+        v->info.position[3] = SPA_AUDIO_CHANNEL_LFE;
+        v->info.position[4] = SPA_AUDIO_CHANNEL_RL;
+        v->info.position[5] = SPA_AUDIO_CHANNEL_RR;
+        break;
+    case 5:
+        v->info.position[0] = SPA_AUDIO_CHANNEL_FL;
+        v->info.position[1] = SPA_AUDIO_CHANNEL_FR;
+        v->info.position[2] = SPA_AUDIO_CHANNEL_FC;
+        v->info.position[3] = SPA_AUDIO_CHANNEL_LFE;
+        v->info.position[4] = SPA_AUDIO_CHANNEL_RC;
+        break;
+    case 4:
+        v->info.position[0] = SPA_AUDIO_CHANNEL_FL;
+        v->info.position[1] = SPA_AUDIO_CHANNEL_FR;
+        v->info.position[2] = SPA_AUDIO_CHANNEL_FC;
+        v->info.position[3] = SPA_AUDIO_CHANNEL_RC;
+        break;
+    case 3:
+        v->info.position[0] = SPA_AUDIO_CHANNEL_FL;
+        v->info.position[1] = SPA_AUDIO_CHANNEL_FR;
+        v->info.position[2] = SPA_AUDIO_CHANNEL_LFE;
+        break;
     case 2:
-        position[0] = SPA_AUDIO_CHANNEL_FL;
-        position[1] = SPA_AUDIO_CHANNEL_FR;
+        v->info.position[0] = SPA_AUDIO_CHANNEL_FL;
+        v->info.position[1] = SPA_AUDIO_CHANNEL_FR;
         break;
     case 1:
-        position[0] = SPA_AUDIO_CHANNEL_MONO;
+        v->info.position[0] = SPA_AUDIO_CHANNEL_MONO;
         break;
     default:
-        dolog("Internal error: unsupported channel count %d\n", channels);
+        for (size_t i = 0; i < v->info.channels; i++) {
+            v->info.position[i] = SPA_AUDIO_CHANNEL_UNKNOWN;
+        }
+        break;
     }
+
+    /* create a new unconnected pwstream */
+    r = create_stream(c, v, stream_name, name, dir);
+    if (r < 0) {
+        AUD_log(AUDIO_CAP, "Failed to create stream.");
+        return -1;
+    }
+
+    return r;
 }
 
 static int
@@ -531,7 +566,6 @@ qpw_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
 
     v->info.format = audfmt_to_pw(as->fmt, as->endianness);
     v->info.channels = as->nchannels;
-    qpw_set_position(as->nchannels, v->info.position);
     v->info.rate = as->freq;
 
     obt_as.fmt =
@@ -545,6 +579,7 @@ qpw_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
     r = qpw_stream_new(c, v, ppdo->stream_name ? : c->dev->id,
                        ppdo->name, SPA_DIRECTION_OUTPUT);
     if (r < 0) {
+        error_report("qpw_stream_new for playback failed");
         pw_thread_loop_unlock(c->thread_loop);
         return -1;
     }
@@ -578,7 +613,6 @@ qpw_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
 
     v->info.format = audfmt_to_pw(as->fmt, as->endianness);
     v->info.channels = as->nchannels;
-    qpw_set_position(as->nchannels, v->info.position);
     v->info.rate = as->freq;
 
     obt_as.fmt =
@@ -589,6 +623,7 @@ qpw_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
     r = qpw_stream_new(c, v, ppdo->stream_name ? : c->dev->id,
                        ppdo->name, SPA_DIRECTION_INPUT);
     if (r < 0) {
+        error_report("qpw_stream_new for recording failed");
         pw_thread_loop_unlock(c->thread_loop);
         return -1;
     }
@@ -604,56 +639,63 @@ qpw_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
     return 0;
 }
 
-static void
-qpw_voice_fini(PWVoice *v)
-{
-    pwaudio *c = v->g;
-
-    if (!v->stream) {
-        return;
-    }
-    pw_thread_loop_lock(c->thread_loop);
-    pw_stream_destroy(v->stream);
-    v->stream = NULL;
-    pw_thread_loop_unlock(c->thread_loop);
-}
-
 static void
 qpw_fini_out(HWVoiceOut *hw)
 {
-    qpw_voice_fini(&PW_VOICE_OUT(hw)->v);
+    PWVoiceOut *pw = (PWVoiceOut *) hw;
+    PWVoice *v = &pw->v;
+
+    if (v->stream) {
+        pwaudio *c = v->g;
+        pw_thread_loop_lock(c->thread_loop);
+        pw_stream_destroy(v->stream);
+        v->stream = NULL;
+        pw_thread_loop_unlock(c->thread_loop);
+    }
 }
 
 static void
 qpw_fini_in(HWVoiceIn *hw)
 {
-    qpw_voice_fini(&PW_VOICE_IN(hw)->v);
+    PWVoiceIn *pw = (PWVoiceIn *) hw;
+    PWVoice *v = &pw->v;
+
+    if (v->stream) {
+        pwaudio *c = v->g;
+        pw_thread_loop_lock(c->thread_loop);
+        pw_stream_destroy(v->stream);
+        v->stream = NULL;
+        pw_thread_loop_unlock(c->thread_loop);
+    }
 }
 
 static void
-qpw_voice_set_enabled(PWVoice *v, bool enable)
+qpw_enable_out(HWVoiceOut *hw, bool enable)
 {
+    PWVoiceOut *po = (PWVoiceOut *) hw;
+    PWVoice *v = &po->v;
     pwaudio *c = v->g;
     pw_thread_loop_lock(c->thread_loop);
     pw_stream_set_active(v->stream, enable);
     pw_thread_loop_unlock(c->thread_loop);
 }
 
-static void
-qpw_enable_out(HWVoiceOut *hw, bool enable)
-{
-    qpw_voice_set_enabled(&PW_VOICE_OUT(hw)->v, enable);
-}
-
 static void
 qpw_enable_in(HWVoiceIn *hw, bool enable)
 {
-    qpw_voice_set_enabled(&PW_VOICE_IN(hw)->v, enable);
+    PWVoiceIn *pi = (PWVoiceIn *) hw;
+    PWVoice *v = &pi->v;
+    pwaudio *c = v->g;
+    pw_thread_loop_lock(c->thread_loop);
+    pw_stream_set_active(v->stream, enable);
+    pw_thread_loop_unlock(c->thread_loop);
 }
 
 static void
-qpw_voice_set_volume(PWVoice *v, Volume *vol)
+qpw_volume_out(HWVoiceOut *hw, Volume *vol)
 {
+    PWVoiceOut *pw = (PWVoiceOut *) hw;
+    PWVoice *v = &pw->v;
     pwaudio *c = v->g;
     int i, ret;
 
@@ -674,16 +716,29 @@ qpw_voice_set_volume(PWVoice *v, Volume *vol)
     pw_thread_loop_unlock(c->thread_loop);
 }
 
-static void
-qpw_volume_out(HWVoiceOut *hw, Volume *vol)
-{
-    qpw_voice_set_volume(&PW_VOICE_OUT(hw)->v, vol);
-}
-
 static void
 qpw_volume_in(HWVoiceIn *hw, Volume *vol)
 {
-    qpw_voice_set_volume(&PW_VOICE_IN(hw)->v, vol);
+    PWVoiceIn *pw = (PWVoiceIn *) hw;
+    PWVoice *v = &pw->v;
+    pwaudio *c = v->g;
+    int i, ret;
+
+    pw_thread_loop_lock(c->thread_loop);
+    v->volume.channels = vol->channels;
+
+    for (i = 0; i < vol->channels; ++i) {
+        v->volume.values[i] = (float)vol->vol[i] / 255;
+    }
+
+    ret = pw_stream_set_control(v->stream,
+        SPA_PROP_channelVolumes, v->volume.channels, v->volume.values, 0);
+    trace_pw_vol(ret == 0 ? "success" : "failed");
+
+    v->muted = vol->mute;
+    float val = v->muted ? 1.f : 0.f;
+    ret = pw_stream_set_control(v->stream, SPA_PROP_mute, 1, &val, 0);
+    pw_thread_loop_unlock(c->thread_loop);
 }
 
 static int wait_resync(pwaudio *pw)
@@ -705,7 +760,6 @@ static int wait_resync(pwaudio *pw)
     }
     return 0;
 }
-
 static void
 on_core_error(void *data, uint32_t id, int seq, int res, const char *message)
 {
@@ -737,31 +791,30 @@ static const struct pw_core_events core_events = {
 };
 
 static void *
-qpw_audio_init(Audiodev *dev, Error **errp)
+qpw_audio_init(Audiodev *dev)
 {
     g_autofree pwaudio *pw = g_new0(pwaudio, 1);
-
-    assert(dev->driver == AUDIODEV_DRIVER_PIPEWIRE);
-    trace_pw_audio_init();
-
     pw_init(NULL, NULL);
 
+    trace_pw_audio_init();
+    assert(dev->driver == AUDIODEV_DRIVER_PIPEWIRE);
+
     pw->dev = dev;
-    pw->thread_loop = pw_thread_loop_new("PipeWire thread loop", NULL);
+    pw->thread_loop = pw_thread_loop_new("Pipewire thread loop", NULL);
     if (pw->thread_loop == NULL) {
-        error_setg_errno(errp, errno, "Could not create PipeWire loop");
+        error_report("Could not create Pipewire loop");
         goto fail;
     }
 
     pw->context =
         pw_context_new(pw_thread_loop_get_loop(pw->thread_loop), NULL, 0);
     if (pw->context == NULL) {
-        error_setg_errno(errp, errno, "Could not create PipeWire context");
+        error_report("Could not create Pipewire context");
         goto fail;
     }
 
     if (pw_thread_loop_start(pw->thread_loop) < 0) {
-        error_setg_errno(errp, errno, "Could not start PipeWire loop");
+        error_report("Could not start Pipewire loop");
         goto fail;
     }
 
@@ -770,13 +823,13 @@ qpw_audio_init(Audiodev *dev, Error **errp)
     pw->core = pw_context_connect(pw->context, NULL, 0);
     if (pw->core == NULL) {
         pw_thread_loop_unlock(pw->thread_loop);
-        goto fail_error;
+        goto fail;
     }
 
     if (pw_core_add_listener(pw->core, &pw->core_listener,
                              &core_events, pw) < 0) {
         pw_thread_loop_unlock(pw->thread_loop);
-        goto fail_error;
+        goto fail;
     }
     if (wait_resync(pw) < 0) {
         pw_thread_loop_unlock(pw->thread_loop);
@@ -786,14 +839,17 @@ qpw_audio_init(Audiodev *dev, Error **errp)
 
     return g_steal_pointer(&pw);
 
-fail_error:
-    error_setg(errp, "Failed to initialize PW context");
 fail:
+    AUD_log(AUDIO_CAP, "Failed to initialize PW context");
     if (pw->thread_loop) {
         pw_thread_loop_stop(pw->thread_loop);
     }
-    g_clear_pointer(&pw->context, pw_context_destroy);
-    g_clear_pointer(&pw->thread_loop, pw_thread_loop_destroy);
+    if (pw->context) {
+        g_clear_pointer(&pw->context, pw_context_destroy);
+    }
+    if (pw->thread_loop) {
+        g_clear_pointer(&pw->thread_loop, pw_thread_loop_destroy);
+    }
     return NULL;
 }
 
@@ -843,6 +899,7 @@ static struct audio_driver pw_audio_driver = {
     .init = qpw_audio_init,
     .fini = qpw_audio_fini,
     .pcm_ops = &qpw_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in = INT_MAX,
     .voice_size_out = sizeof(PWVoiceOut),

audio/sdlaudio.c

@@ -26,7 +26,6 @@
 #include <SDL.h>
 #include <SDL_thread.h>
 #include "qemu/module.h"
-#include "qapi/error.h"
 #include "audio.h"
 
 #ifndef _WIN32
@@ -450,10 +449,10 @@ static void sdl_enable_in(HWVoiceIn *hw, bool enable)
     SDL_PauseAudioDevice(sdl->devid, !enable);
 }
 
-static void *sdl_audio_init(Audiodev *dev, Error **errp)
+static void *sdl_audio_init(Audiodev *dev)
 {
     if (SDL_InitSubSystem (SDL_INIT_AUDIO)) {
-        error_setg(errp, "SDL failed to initialize audio subsystem");
+        sdl_logerr ("SDL failed to initialize audio subsystem\n");
         return NULL;
     }
 
@@ -494,6 +493,7 @@ static struct audio_driver sdl_audio_driver = {
     .init           = sdl_audio_init,
     .fini           = sdl_audio_fini,
     .pcm_ops        = &sdl_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof(SDLVoiceOut),

audio/sndioaudio.c

@@ -518,7 +518,7 @@ static void sndio_fini_in(HWVoiceIn *hw)
     sndio_fini(self);
 }
 
-static void *sndio_audio_init(Audiodev *dev, Error **errp)
+static void *sndio_audio_init(Audiodev *dev)
 {
     assert(dev->driver == AUDIODEV_DRIVER_SNDIO);
     return dev;
@@ -550,6 +550,7 @@ static struct audio_driver sndio_audio_driver = {
     .init           = sndio_audio_init,
     .fini           = sndio_audio_fini,
     .pcm_ops        = &sndio_pcm_ops,
+    .can_be_default = 1,
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof(SndioVoice),

audio/spiceaudio.c

@@ -22,7 +22,6 @@
 #include "qemu/module.h"
 #include "qemu/error-report.h"
 #include "qemu/timer.h"
-#include "qapi/error.h"
 #include "ui/qemu-spice.h"
 
 #define AUDIO_CAP "spice"
@@ -72,13 +71,11 @@ static const SpiceRecordInterface record_sif = {
     .base.minor_version = SPICE_INTERFACE_RECORD_MINOR,
 };
 
-static void *spice_audio_init(Audiodev *dev, Error **errp)
+static void *spice_audio_init(Audiodev *dev)
 {
     if (!using_spice) {
-        error_setg(errp, "Cannot use spice audio without -spice");
         return NULL;
     }
-
     return &spice_audio_init;
 }
 

audio/trace-events

@@ -24,7 +24,7 @@ pw_read(int32_t avail, uint32_t index, size_t len) "avail=%d index=%u len=%zu"
 pw_write(int32_t filled, int32_t avail, uint32_t index, size_t len) "filled=%d avail=%d index=%u len=%zu"
 pw_vol(const char *ret) "set volume: %s"
 pw_period(uint64_t quantum, uint32_t rate) "period =%" PRIu64 "/%u"
-pw_audio_init(void) "Initialize PipeWire context"
+pw_audio_init(void) "Initialize Pipewire context"
 
 # audio.c
 audio_timer_start(int interval) "interval %d ms"

audio/wavaudio.c

@@ -97,10 +97,6 @@ static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
         dolog ("WAVE files can not handle 32bit formats\n");
         return -1;
 
-    case AUDIO_FORMAT_F32:
-        dolog("WAVE files can not handle float formats\n");
-        return -1;
-
     default:
         abort();
     }
@@ -186,7 +182,7 @@ static void wav_enable_out(HWVoiceOut *hw, bool enable)
     }
 }
 
-static void *wav_audio_init(Audiodev *dev, Error **errp)
+static void *wav_audio_init(Audiodev *dev)
 {
     assert(dev->driver == AUDIODEV_DRIVER_WAV);
     return dev;
@@ -212,6 +208,7 @@ static struct audio_driver wav_audio_driver = {
     .init           = wav_audio_init,
     .fini           = wav_audio_fini,
     .pcm_ops        = &wav_pcm_ops,
+    .can_be_default = 0,
     .max_voices_out = 1,
     .max_voices_in  = 0,
     .voice_size_out = sizeof (WAVVoiceOut),

backends/cryptodev.c

@@ -191,11 +191,6 @@ static int cryptodev_backend_account(CryptoDevBackend *backend,
     if (algtype == QCRYPTODEV_BACKEND_ALG_ASYM) {
         CryptoDevBackendAsymOpInfo *asym_op_info = op_info->u.asym_op_info;
         len = asym_op_info->src_len;
-
-        if (unlikely(!backend->asym_stat)) {
-            error_report("cryptodev: Unexpected asym operation");
-            return -VIRTIO_CRYPTO_NOTSUPP;
-        }
         switch (op_info->op_code) {
         case VIRTIO_CRYPTO_AKCIPHER_ENCRYPT:
             CryptodevAsymStatIncEncrypt(backend, len);
@@ -215,11 +210,6 @@ static int cryptodev_backend_account(CryptoDevBackend *backend,
     } else if (algtype == QCRYPTODEV_BACKEND_ALG_SYM) {
         CryptoDevBackendSymOpInfo *sym_op_info = op_info->u.sym_op_info;
         len = sym_op_info->src_len;
-
-        if (unlikely(!backend->sym_stat)) {
-            error_report("cryptodev: Unexpected sym operation");
-            return -VIRTIO_CRYPTO_NOTSUPP;
-        }
         switch (op_info->op_code) {
         case VIRTIO_CRYPTO_CIPHER_ENCRYPT:
             CryptodevSymStatIncEncrypt(backend, len);
@@ -252,11 +242,10 @@ static void cryptodev_backend_throttle_timer_cb(void *opaque)
             continue;
         }
 
-        throttle_account(&backend->ts, THROTTLE_WRITE, ret);
+        throttle_account(&backend->ts, true, ret);
         cryptodev_backend_operation(backend, op_info);
         if (throttle_enabled(&backend->tc) &&
-            throttle_schedule_timer(&backend->ts, &backend->tt,
-                                    THROTTLE_WRITE)) {
+            throttle_schedule_timer(&backend->ts, &backend->tt, true)) {
             break;
         }
     }
@@ -272,7 +261,7 @@ int cryptodev_backend_crypto_operation(
         goto do_account;
     }
 
-    if (throttle_schedule_timer(&backend->ts, &backend->tt, THROTTLE_WRITE) ||
+    if (throttle_schedule_timer(&backend->ts, &backend->tt, true) ||
         !QTAILQ_EMPTY(&backend->opinfos)) {
         QTAILQ_INSERT_TAIL(&backend->opinfos, op_info, next);
         return 0;
@@ -284,7 +273,7 @@ do_account:
         return ret;
     }
 
-    throttle_account(&backend->ts, THROTTLE_WRITE, ret);
+    throttle_account(&backend->ts, true, ret);
 
     return cryptodev_backend_operation(backend, op_info);
 }
@@ -342,7 +331,8 @@ static void cryptodev_backend_set_throttle(CryptoDevBackend *backend, int field,
     if (!enabled) {
         throttle_init(&backend->ts);
         throttle_timers_init(&backend->tt, qemu_get_aio_context(),
-                             QEMU_CLOCK_REALTIME, NULL,
+                             QEMU_CLOCK_REALTIME,
+                             cryptodev_backend_throttle_timer_cb, /* FIXME */
                              cryptodev_backend_throttle_timer_cb, backend);
     }
 
@@ -398,7 +388,6 @@ static void cryptodev_backend_set_ops(Object *obj, Visitor *v,
 static void
 cryptodev_backend_complete(UserCreatable *uc, Error **errp)
 {
-    ERRP_GUARD();
     CryptoDevBackend *backend = CRYPTODEV_BACKEND(uc);
     CryptoDevBackendClass *bc = CRYPTODEV_BACKEND_GET_CLASS(uc);
     uint32_t services;
@@ -407,20 +396,11 @@ cryptodev_backend_complete(UserCreatable *uc, Error **errp)
     QTAILQ_INIT(&backend->opinfos);
     value = backend->tc.buckets[THROTTLE_OPS_TOTAL].avg;
     cryptodev_backend_set_throttle(backend, THROTTLE_OPS_TOTAL, value, errp);
-    if (*errp) {
-        return;
-    }
     value = backend->tc.buckets[THROTTLE_BPS_TOTAL].avg;
     cryptodev_backend_set_throttle(backend, THROTTLE_BPS_TOTAL, value, errp);
-    if (*errp) {
-        return;
-    }
 
     if (bc->init) {
         bc->init(backend, errp);
-        if (*errp) {
-            return;
-        }
     }
 
     services = backend->conf.crypto_services;

backends/dbus-vmstate.c

@@ -426,7 +426,8 @@ dbus_vmstate_complete(UserCreatable *uc, Error **errp)
         return;
     }
 
-    if (vmstate_register_any(VMSTATE_IF(self), &dbus_vmstate, self) < 0) {
+    if (vmstate_register(VMSTATE_IF(self), VMSTATE_INSTANCE_ID_ANY,
+                         &dbus_vmstate, self) < 0) {
         error_setg(errp, "Failed to register vmstate");
     }
 }

backends/hostmem-file.c

@@ -18,8 +18,6 @@
 #include "sysemu/hostmem.h"
 #include "qom/object_interfaces.h"
 #include "qom/object.h"
-#include "qapi/visitor.h"
-#include "qapi/qapi-visit-common.h"
 
 OBJECT_DECLARE_SIMPLE_TYPE(HostMemoryBackendFile, MEMORY_BACKEND_FILE)
 
@@ -33,7 +31,6 @@ struct HostMemoryBackendFile {
     bool discard_data;
     bool is_pmem;
     bool readonly;
-    OnOffAuto rom;
 };
 
 static void
@@ -56,39 +53,15 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
         return;
     }
 
-    switch (fb->rom) {
-    case ON_OFF_AUTO_AUTO:
-        /* Traditionally, opening the file readonly always resulted in ROM. */
-        fb->rom = fb->readonly ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
-        break;
-    case ON_OFF_AUTO_ON:
-        if (!fb->readonly) {
-            error_setg(errp, "property 'rom' = 'on' is not supported with"
-                       " 'readonly' = 'off'");
-            return;
-        }
-        break;
-    case ON_OFF_AUTO_OFF:
-        if (fb->readonly && backend->share) {
-            error_setg(errp, "property 'rom' = 'off' is incompatible with"
-                       " 'readonly' = 'on' and 'share' = 'on'");
-            return;
-        }
-        break;
-    default:
-        assert(false);
-    }
-
     name = host_memory_backend_get_name(backend);
     ram_flags = backend->share ? RAM_SHARED : 0;
-    ram_flags |= fb->readonly ? RAM_READONLY_FD : 0;
-    ram_flags |= fb->rom == ON_OFF_AUTO_ON ? RAM_READONLY : 0;
     ram_flags |= backend->reserve ? 0 : RAM_NORESERVE;
     ram_flags |= fb->is_pmem ? RAM_PMEM : 0;
     ram_flags |= RAM_NAMED_FILE;
     memory_region_init_ram_from_file(&backend->mr, OBJECT(backend), name,
                                      backend->size, fb->align, ram_flags,
-                                     fb->mem_path, fb->offset, errp);
+                                     fb->mem_path, fb->offset, fb->readonly,
+                                     errp);
     g_free(name);
 #endif
 }
@@ -228,32 +201,6 @@ static void file_memory_backend_set_readonly(Object *obj, bool value,
     fb->readonly = value;
 }
 
-static void file_memory_backend_get_rom(Object *obj, Visitor *v,
-                                        const char *name, void *opaque,
-                                        Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
-    OnOffAuto rom = fb->rom;
-
-    visit_type_OnOffAuto(v, name, &rom, errp);
-}
-
-static void file_memory_backend_set_rom(Object *obj, Visitor *v,
-                                        const char *name, void *opaque,
-                                        Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
-
-    if (host_memory_backend_mr_inited(backend)) {
-        error_setg(errp, "cannot change property '%s' of %s.", name,
-                   object_get_typename(obj));
-        return;
-    }
-
-    visit_type_OnOffAuto(v, name, &fb->rom, errp);
-}
-
 static void file_backend_unparent(Object *obj)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
@@ -296,10 +243,6 @@ file_backend_class_init(ObjectClass *oc, void *data)
     object_class_property_add_bool(oc, "readonly",
         file_memory_backend_get_readonly,
         file_memory_backend_set_readonly);
-    object_class_property_add(oc, "rom", "OnOffAuto",
-        file_memory_backend_get_rom, file_memory_backend_set_rom, NULL, NULL);
-    object_class_property_set_description(oc, "rom",
-        "Whether to create Read Only Memory (ROM)");
 }
 
 static void file_backend_instance_finalize(Object *o)

backends/tpm/tpm_emulator.c

@@ -534,8 +534,11 @@ static int tpm_emulator_block_migration(TPMEmulator *tpm_emu)
         error_setg(&tpm_emu->migration_blocker,
                    "Migration disabled: TPM emulator does not support "
                    "migration");
-        if (migrate_add_blocker(&tpm_emu->migration_blocker, &err) < 0) {
+        if (migrate_add_blocker(tpm_emu->migration_blocker, &err) < 0) {
             error_report_err(err);
+            error_free(tpm_emu->migration_blocker);
+            tpm_emu->migration_blocker = NULL;
+
             return -1;
         }
     }
@@ -975,7 +978,8 @@ static void tpm_emulator_inst_init(Object *obj)
         qemu_add_vm_change_state_handler(tpm_emulator_vm_state_change,
                                          tpm_emu);
 
-    vmstate_register_any(NULL, &vmstate_tpm_emulator, obj);
+    vmstate_register(NULL, VMSTATE_INSTANCE_ID_ANY,
+                     &vmstate_tpm_emulator, obj);
 }
 
 /*
@@ -1012,7 +1016,10 @@ static void tpm_emulator_inst_finalize(Object *obj)
 
     qapi_free_TPMEmulatorOptions(tpm_emu->options);
 
-    migrate_del_blocker(&tpm_emu->migration_blocker);
+    if (tpm_emu->migration_blocker) {
+        migrate_del_blocker(tpm_emu->migration_blocker);
+        error_free(tpm_emu->migration_blocker);
+    }
 
     tpm_sized_buffer_reset(&state_blobs->volatil);
     tpm_sized_buffer_reset(&state_blobs->permanent);

backends/tpm/tpm_ioctl.h

@@ -238,7 +238,7 @@ struct ptm_lockstorage {
         } req; /* request */
         struct {
             ptm_res tpm_result;
-        } resp; /* response */
+        } resp; /* reponse */
     } u;
 };
 

backends/tpm/tpm_util.c

@@ -112,8 +112,12 @@ static int tpm_util_request(int fd,
                             void *response,
                             size_t responselen)
 {
-    GPollFD fds[1] = { {.fd = fd, .events = G_IO_IN } };
+    fd_set readfds;
     int n;
+    struct timeval tv = {
+        .tv_sec = 1,
+        .tv_usec = 0,
+    };
 
     n = write(fd, request, requestlen);
     if (n < 0) {
@@ -123,8 +127,11 @@ static int tpm_util_request(int fd,
         return -EFAULT;
     }
 
+    FD_ZERO(&readfds);
+    FD_SET(fd, &readfds);
+
     /* wait for a second */
-    n = RETRY_ON_EINTR(g_poll(fds, 1, 1000));
+    n = select(fd + 1, &readfds, NULL, NULL, &tv);
     if (n != 1) {
         return -errno;
     }

block/backup.c

@@ -384,33 +384,31 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         return NULL;
     }
 
-    bdrv_graph_rdlock_main_loop();
     if (!bdrv_is_inserted(bs)) {
         error_setg(errp, "Device is not inserted: %s",
                    bdrv_get_device_name(bs));
-        goto error_rdlock;
+        return NULL;
     }
 
     if (!bdrv_is_inserted(target)) {
         error_setg(errp, "Device is not inserted: %s",
                    bdrv_get_device_name(target));
-        goto error_rdlock;
+        return NULL;
     }
 
     if (compress && !bdrv_supports_compressed_writes(target)) {
         error_setg(errp, "Compression is not supported for this drive %s",
                    bdrv_get_device_name(target));
-        goto error_rdlock;
+        return NULL;
     }
 
     if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
-        goto error_rdlock;
+        return NULL;
     }
 
     if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_BACKUP_TARGET, errp)) {
-        goto error_rdlock;
+        return NULL;
     }
-    bdrv_graph_rdunlock_main_loop();
 
     if (perf->max_workers < 1 || perf->max_workers > INT_MAX) {
         error_setg(errp, "max-workers must be between 1 and %d", INT_MAX);
@@ -438,7 +436,6 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
 
     len = bdrv_getlength(bs);
     if (len < 0) {
-        GRAPH_RDLOCK_GUARD_MAINLOOP();
         error_setg_errno(errp, -len, "Unable to get length for '%s'",
                          bdrv_get_device_or_node_name(bs));
         goto error;
@@ -446,7 +443,6 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
 
     target_len = bdrv_getlength(target);
     if (target_len < 0) {
-        GRAPH_RDLOCK_GUARD_MAINLOOP();
         error_setg_errno(errp, -target_len, "Unable to get length for '%s'",
                          bdrv_get_device_or_node_name(bs));
         goto error;
@@ -496,10 +492,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
     block_copy_set_speed(bcs, speed);
 
     /* Required permissions are taken by copy-before-write filter target */
-    bdrv_graph_wrlock(target);
     block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
                        &error_abort);
-    bdrv_graph_wrunlock(target);
 
     return &job->common;
 
@@ -512,8 +506,4 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
     }
 
     return NULL;
-
-error_rdlock:
-    bdrv_graph_rdunlock_main_loop();
-    return NULL;
 }

block/blkdebug.c

@@ -508,8 +508,6 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
         goto out;
     }
 
-    bdrv_graph_rdlock_main_loop();
-
     bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
         (BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
     bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
@@ -522,7 +520,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     if (s->align && (s->align >= INT_MAX || !is_power_of_2(s->align))) {
         error_setg(errp, "Cannot meet constraints with align %" PRIu64,
                    s->align);
-        goto out_rdlock;
+        goto out;
     }
     align = MAX(s->align, bs->file->bs->bl.request_alignment);
 
@@ -532,7 +530,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
          !QEMU_IS_ALIGNED(s->max_transfer, align))) {
         error_setg(errp, "Cannot meet constraints with max-transfer %" PRIu64,
                    s->max_transfer);
-        goto out_rdlock;
+        goto out;
     }
 
     s->opt_write_zero = qemu_opt_get_size(opts, "opt-write-zero", 0);
@@ -541,7 +539,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
          !QEMU_IS_ALIGNED(s->opt_write_zero, align))) {
         error_setg(errp, "Cannot meet constraints with opt-write-zero %" PRIu64,
                    s->opt_write_zero);
-        goto out_rdlock;
+        goto out;
     }
 
     s->max_write_zero = qemu_opt_get_size(opts, "max-write-zero", 0);
@@ -551,7 +549,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
                           MAX(s->opt_write_zero, align)))) {
         error_setg(errp, "Cannot meet constraints with max-write-zero %" PRIu64,
                    s->max_write_zero);
-        goto out_rdlock;
+        goto out;
     }
 
     s->opt_discard = qemu_opt_get_size(opts, "opt-discard", 0);
@@ -560,7 +558,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
          !QEMU_IS_ALIGNED(s->opt_discard, align))) {
         error_setg(errp, "Cannot meet constraints with opt-discard %" PRIu64,
                    s->opt_discard);
-        goto out_rdlock;
+        goto out;
     }
 
     s->max_discard = qemu_opt_get_size(opts, "max-discard", 0);
@@ -570,14 +568,12 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
                           MAX(s->opt_discard, align)))) {
         error_setg(errp, "Cannot meet constraints with max-discard %" PRIu64,
                    s->max_discard);
-        goto out_rdlock;
+        goto out;
     }
 
     bdrv_debug_event(bs, BLKDBG_NONE);
 
     ret = 0;
-out_rdlock:
-    bdrv_graph_rdunlock_main_loop();
 out:
     if (ret < 0) {
         qemu_mutex_destroy(&s->lock);
@@ -750,10 +746,13 @@ blkdebug_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)
     return bdrv_co_pdiscard(bs->file, offset, bytes);
 }
 
-static int coroutine_fn GRAPH_RDLOCK
-blkdebug_co_block_status(BlockDriverState *bs, bool want_zero, int64_t offset,
-                         int64_t bytes, int64_t *pnum, int64_t *map,
-                         BlockDriverState **file)
+static int coroutine_fn blkdebug_co_block_status(BlockDriverState *bs,
+                                                 bool want_zero,
+                                                 int64_t offset,
+                                                 int64_t bytes,
+                                                 int64_t *pnum,
+                                                 int64_t *map,
+                                                 BlockDriverState **file)
 {
     int err;
 
@@ -974,7 +973,7 @@ blkdebug_co_getlength(BlockDriverState *bs)
     return bdrv_co_getlength(bs->file->bs);
 }
 
-static void GRAPH_RDLOCK blkdebug_refresh_filename(BlockDriverState *bs)
+static void blkdebug_refresh_filename(BlockDriverState *bs)
 {
     BDRVBlkdebugState *s = bs->opaque;
     const QDictEntry *e;

block/blkio.c

@@ -13,7 +13,6 @@
 #include "block/block_int.h"
 #include "exec/memory.h"
 #include "exec/cpu-common.h" /* for qemu_ram_get_fd() */
-#include "qemu/defer-call.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "qapi/qmp/qdict.h"
@@ -23,6 +22,16 @@
 
 #include "block/block-io.h"
 
+/*
+ * Keep the QEMU BlockDriver names identical to the libblkio driver names.
+ * Using macros instead of typing out the string literals avoids typos.
+ */
+#define DRIVER_IO_URING "io_uring"
+#define DRIVER_NVME_IO_URING "nvme-io_uring"
+#define DRIVER_VIRTIO_BLK_VFIO_PCI "virtio-blk-vfio-pci"
+#define DRIVER_VIRTIO_BLK_VHOST_USER "virtio-blk-vhost-user"
+#define DRIVER_VIRTIO_BLK_VHOST_VDPA "virtio-blk-vhost-vdpa"
+
 /*
  * Allocated bounce buffers are kept in a list sorted by buffer address.
  */
@@ -68,7 +77,7 @@ typedef struct {
     CoQueue bounce_available;
 
     /* The value of the "mem-region-alignment" property */
-    uint64_t mem_region_alignment;
+    size_t mem_region_alignment;
 
     /* Can we skip adding/deleting blkio_mem_regions? */
     bool needs_mem_regions;
@@ -313,10 +322,10 @@ static void blkio_detach_aio_context(BlockDriverState *bs)
 }
 
 /*
- * Called by defer_call_end() or immediately if not in a deferred section.
- * Called without blkio_lock.
+ * Called by blk_io_unplug() or immediately if not plugged. Called without
+ * blkio_lock.
  */
-static void blkio_deferred_fn(void *opaque)
+static void blkio_unplug_fn(void *opaque)
 {
     BDRVBlkioState *s = opaque;
 
@@ -333,7 +342,7 @@ static void blkio_submit_io(BlockDriverState *bs)
 {
     BDRVBlkioState *s = bs->opaque;
 
-    defer_call(blkio_deferred_fn, s);
+    blk_io_plug_call(blkio_unplug_fn, s);
 }
 
 static int coroutine_fn
@@ -604,8 +613,8 @@ static void blkio_unregister_buf(BlockDriverState *bs, void *host, size_t size)
     }
 }
 
-static int blkio_io_uring_connect(BlockDriverState *bs, QDict *options,
-                                  int flags, Error **errp)
+static int blkio_io_uring_open(BlockDriverState *bs, QDict *options, int flags,
+                               Error **errp)
 {
     const char *filename = qdict_get_str(options, "filename");
     BDRVBlkioState *s = bs->opaque;
@@ -628,18 +637,11 @@ static int blkio_io_uring_connect(BlockDriverState *bs, QDict *options,
         }
     }
 
-    ret = blkio_connect(s->blkio);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "blkio_connect failed: %s",
-                         blkio_get_error_msg());
-        return ret;
-    }
-
     return 0;
 }
 
-static int blkio_nvme_io_uring_connect(BlockDriverState *bs, QDict *options,
-                                       int flags, Error **errp)
+static int blkio_nvme_io_uring(BlockDriverState *bs, QDict *options, int flags,
+                               Error **errp)
 {
     const char *path = qdict_get_try_str(options, "path");
     BDRVBlkioState *s = bs->opaque;
@@ -663,23 +665,16 @@ static int blkio_nvme_io_uring_connect(BlockDriverState *bs, QDict *options,
         return -EINVAL;
     }
 
-    ret = blkio_connect(s->blkio);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "blkio_connect failed: %s",
-                         blkio_get_error_msg());
-        return ret;
-    }
-
     return 0;
 }
 
-static int blkio_virtio_blk_connect(BlockDriverState *bs, QDict *options,
-                                    int flags, Error **errp)
+static int blkio_virtio_blk_common_open(BlockDriverState *bs,
+        QDict *options, int flags, Error **errp)
 {
     const char *path = qdict_get_try_str(options, "path");
     BDRVBlkioState *s = bs->opaque;
     bool fd_supported = false;
-    int fd = -1, ret;
+    int fd, ret;
 
     if (!path) {
         error_setg(errp, "missing 'path' option");
@@ -691,7 +686,7 @@ static int blkio_virtio_blk_connect(BlockDriverState *bs, QDict *options,
         return -EINVAL;
     }
 
-    if (blkio_set_int(s->blkio, "fd", -1) == 0) {
+    if (blkio_get_int(s->blkio, "fd", &fd) == 0) {
         fd_supported = true;
     }
 
@@ -701,86 +696,33 @@ static int blkio_virtio_blk_connect(BlockDriverState *bs, QDict *options,
      * layer through the "/dev/fdset/N" special path.
      */
     if (fd_supported) {
-        /*
-         * `path` can contain the path of a character device
-         * (e.g. /dev/vhost-vdpa-0 or /dev/vfio/vfio) or a unix socket.
-         *
-         * So, we should always open it with O_RDWR flag, also if BDRV_O_RDWR
-         * is not set in the open flags, because the exchange of IOCTL commands
-         * for example will fail.
-         *
-         * In order to open the device read-only, we are using the `read-only`
-         * property of the libblkio driver in blkio_file_open().
-         */
-        fd = qemu_open(path, O_RDWR, NULL);
-        if (fd < 0) {
-            /*
-             * qemu_open() can fail if the user specifies a path that is not
-             * a file or device, for example in the case of Unix Domain Socket
-             * for the virtio-blk-vhost-user driver. In such cases let's have
-             * libblkio open the path directly.
-             */
-            fd_supported = false;
+        int open_flags;
+
+        if (flags & BDRV_O_RDWR) {
+            open_flags = O_RDWR;
         } else {
-            ret = blkio_set_int(s->blkio, "fd", fd);
-            if (ret < 0) {
-                fd_supported = false;
-                qemu_close(fd);
-                fd = -1;
-            }
+            open_flags = O_RDONLY;
         }
-    }
 
-    if (!fd_supported) {
-        ret = blkio_set_str(s->blkio, "path", path);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "failed to set path: %s",
-                             blkio_get_error_msg());
-            return ret;
+        fd = qemu_open(path, open_flags, errp);
+        if (fd < 0) {
+            return -EINVAL;
         }
-    }
 
-    ret = blkio_connect(s->blkio);
-    if (ret < 0 && fd >= 0) {
-        /* Failed to give the FD to libblkio, close it */
-        qemu_close(fd);
-        fd = -1;
-    }
-
-    /*
-     * Before https://gitlab.com/libblkio/libblkio/-/merge_requests/208
-     * (libblkio <= v1.3.0), setting the `fd` property is not enough to check
-     * whether the driver supports the `fd` property or not. In that case,
-     * blkio_connect() will fail with -EINVAL.
-     * So let's try calling blkio_connect() again by directly setting `path`
-     * to cover this scenario.
-     */
-    if (fd_supported && ret == -EINVAL) {
-        /*
-         * We need to clear the `fd` property we set previously by setting
-         * it to -1.
-         */
-        ret = blkio_set_int(s->blkio, "fd", -1);
+        ret = blkio_set_int(s->blkio, "fd", fd);
         if (ret < 0) {
             error_setg_errno(errp, -ret, "failed to set fd: %s",
                              blkio_get_error_msg());
+            qemu_close(fd);
             return ret;
         }
-
+    } else {
         ret = blkio_set_str(s->blkio, "path", path);
         if (ret < 0) {
             error_setg_errno(errp, -ret, "failed to set path: %s",
                              blkio_get_error_msg());
             return ret;
         }
-
-        ret = blkio_connect(s->blkio);
-    }
-
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "blkio_connect failed: %s",
-                         blkio_get_error_msg());
-        return ret;
     }
 
     qdict_del(options, "path");
@@ -802,6 +744,24 @@ static int blkio_file_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
 
+    if (strcmp(blkio_driver, DRIVER_IO_URING) == 0) {
+        ret = blkio_io_uring_open(bs, options, flags, errp);
+    } else if (strcmp(blkio_driver, DRIVER_NVME_IO_URING) == 0) {
+        ret = blkio_nvme_io_uring(bs, options, flags, errp);
+    } else if (strcmp(blkio_driver, DRIVER_VIRTIO_BLK_VFIO_PCI) == 0) {
+        ret = blkio_virtio_blk_common_open(bs, options, flags, errp);
+    } else if (strcmp(blkio_driver, DRIVER_VIRTIO_BLK_VHOST_USER) == 0) {
+        ret = blkio_virtio_blk_common_open(bs, options, flags, errp);
+    } else if (strcmp(blkio_driver, DRIVER_VIRTIO_BLK_VHOST_VDPA) == 0) {
+        ret = blkio_virtio_blk_common_open(bs, options, flags, errp);
+    } else {
+        g_assert_not_reached();
+    }
+    if (ret < 0) {
+        blkio_destroy(&s->blkio);
+        return ret;
+    }
+
     if (!(flags & BDRV_O_RDWR)) {
         ret = blkio_set_bool(s->blkio, "read-only", true);
         if (ret < 0) {
@@ -812,20 +772,10 @@ static int blkio_file_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
-    if (strcmp(blkio_driver, "io_uring") == 0) {
-        ret = blkio_io_uring_connect(bs, options, flags, errp);
-    } else if (strcmp(blkio_driver, "nvme-io_uring") == 0) {
-        ret = blkio_nvme_io_uring_connect(bs, options, flags, errp);
-    } else if (strcmp(blkio_driver, "virtio-blk-vfio-pci") == 0) {
-        ret = blkio_virtio_blk_connect(bs, options, flags, errp);
-    } else if (strcmp(blkio_driver, "virtio-blk-vhost-user") == 0) {
-        ret = blkio_virtio_blk_connect(bs, options, flags, errp);
-    } else if (strcmp(blkio_driver, "virtio-blk-vhost-vdpa") == 0) {
-        ret = blkio_virtio_blk_connect(bs, options, flags, errp);
-    } else {
-        g_assert_not_reached();
-    }
+    ret = blkio_connect(s->blkio);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "blkio_connect failed: %s",
+                         blkio_get_error_msg());
         blkio_destroy(&s->blkio);
         return ret;
     }
@@ -905,7 +855,6 @@ static int blkio_file_open(BlockDriverState *bs, QDict *options, int flags,
     QLIST_INIT(&s->bounce_bufs);
     s->blkioq = blkio_get_queue(s->blkio, 0);
     s->completion_fd = blkioq_get_completion_fd(s->blkioq);
-    blkioq_set_completion_fd_enabled(s->blkioq, true);
 
     blkio_attach_aio_context(bs, bdrv_get_aio_context(bs));
     return 0;
@@ -1079,63 +1028,49 @@ static void blkio_refresh_limits(BlockDriverState *bs, Error **errp)
  * - truncate
  */
 
-/*
- * Do not include .format_name and .protocol_name because module_block.py
- * does not parse macros in the source code.
- */
-#define BLKIO_DRIVER_COMMON \
-    .instance_size           = sizeof(BDRVBlkioState), \
-    .bdrv_file_open          = blkio_file_open, \
-    .bdrv_close              = blkio_close, \
-    .bdrv_co_getlength       = blkio_co_getlength, \
-    .bdrv_co_truncate        = blkio_truncate, \
-    .bdrv_co_get_info        = blkio_co_get_info, \
-    .bdrv_attach_aio_context = blkio_attach_aio_context, \
-    .bdrv_detach_aio_context = blkio_detach_aio_context, \
-    .bdrv_co_pdiscard        = blkio_co_pdiscard, \
-    .bdrv_co_preadv          = blkio_co_preadv, \
-    .bdrv_co_pwritev         = blkio_co_pwritev, \
-    .bdrv_co_flush_to_disk   = blkio_co_flush, \
-    .bdrv_co_pwrite_zeroes   = blkio_co_pwrite_zeroes, \
-    .bdrv_refresh_limits     = blkio_refresh_limits, \
-    .bdrv_register_buf       = blkio_register_buf, \
-    .bdrv_unregister_buf     = blkio_unregister_buf,
+#define BLKIO_DRIVER(name, ...) \
+    { \
+        .format_name             = name, \
+        .protocol_name           = name, \
+        .instance_size           = sizeof(BDRVBlkioState), \
+        .bdrv_file_open          = blkio_file_open, \
+        .bdrv_close              = blkio_close, \
+        .bdrv_co_getlength       = blkio_co_getlength, \
+        .bdrv_co_truncate        = blkio_truncate, \
+        .bdrv_co_get_info        = blkio_co_get_info, \
+        .bdrv_attach_aio_context = blkio_attach_aio_context, \
+        .bdrv_detach_aio_context = blkio_detach_aio_context, \
+        .bdrv_co_pdiscard        = blkio_co_pdiscard, \
+        .bdrv_co_preadv          = blkio_co_preadv, \
+        .bdrv_co_pwritev         = blkio_co_pwritev, \
+        .bdrv_co_flush_to_disk   = blkio_co_flush, \
+        .bdrv_co_pwrite_zeroes   = blkio_co_pwrite_zeroes, \
+        .bdrv_refresh_limits     = blkio_refresh_limits, \
+        .bdrv_register_buf       = blkio_register_buf, \
+        .bdrv_unregister_buf     = blkio_unregister_buf, \
+        __VA_ARGS__ \
+    }
 
-/*
- * Use the same .format_name and .protocol_name as the libblkio driver name for
- * consistency.
- */
-
-static BlockDriver bdrv_io_uring = {
-    .format_name         = "io_uring",
-    .protocol_name       = "io_uring",
+static BlockDriver bdrv_io_uring = BLKIO_DRIVER(
+    DRIVER_IO_URING,
     .bdrv_needs_filename = true,
-    BLKIO_DRIVER_COMMON
-};
+);
 
-static BlockDriver bdrv_nvme_io_uring = {
-    .format_name         = "nvme-io_uring",
-    .protocol_name       = "nvme-io_uring",
-    BLKIO_DRIVER_COMMON
-};
+static BlockDriver bdrv_nvme_io_uring = BLKIO_DRIVER(
+    DRIVER_NVME_IO_URING,
+);
 
-static BlockDriver bdrv_virtio_blk_vfio_pci = {
-    .format_name         = "virtio-blk-vfio-pci",
-    .protocol_name       = "virtio-blk-vfio-pci",
-    BLKIO_DRIVER_COMMON
-};
+static BlockDriver bdrv_virtio_blk_vfio_pci = BLKIO_DRIVER(
+    DRIVER_VIRTIO_BLK_VFIO_PCI
+);
 
-static BlockDriver bdrv_virtio_blk_vhost_user = {
-    .format_name         = "virtio-blk-vhost-user",
-    .protocol_name       = "virtio-blk-vhost-user",
-    BLKIO_DRIVER_COMMON
-};
+static BlockDriver bdrv_virtio_blk_vhost_user = BLKIO_DRIVER(
+    DRIVER_VIRTIO_BLK_VHOST_USER
+);
 
-static BlockDriver bdrv_virtio_blk_vhost_vdpa = {
-    .format_name         = "virtio-blk-vhost-vdpa",
-    .protocol_name       = "virtio-blk-vhost-vdpa",
-    BLKIO_DRIVER_COMMON
-};
+static BlockDriver bdrv_virtio_blk_vhost_vdpa = BLKIO_DRIVER(
+    DRIVER_VIRTIO_BLK_VHOST_VDPA
+);
 
 static void bdrv_blkio_init(void)
 {

block/blklogwrites.c

@@ -251,9 +251,7 @@ static int blk_log_writes_open(BlockDriverState *bs, QDict *options, int flags,
     ret = 0;
 fail_log:
     if (ret < 0) {
-        bdrv_graph_wrlock(NULL);
         bdrv_unref_child(bs, s->log_file);
-        bdrv_graph_wrunlock(NULL);
         s->log_file = NULL;
     }
 fail:
@@ -265,10 +263,8 @@ static void blk_log_writes_close(BlockDriverState *bs)
 {
     BDRVBlkLogWritesState *s = bs->opaque;
 
-    bdrv_graph_wrlock(NULL);
     bdrv_unref_child(bs, s->log_file);
     s->log_file = NULL;
-    bdrv_graph_wrunlock(NULL);
 }
 
 static int64_t coroutine_fn GRAPH_RDLOCK
@@ -328,39 +324,22 @@ static void coroutine_fn GRAPH_RDLOCK
 blk_log_writes_co_do_log(BlkLogWritesLogReq *lr)
 {
     BDRVBlkLogWritesState *s = lr->bs->opaque;
-
-    /*
-     * Determine the offsets and sizes of different parts of the entry, and
-     * update the state of the driver.
-     *
-     * This needs to be done in one go, before any actual I/O is done, as the
-     * log entry may have to be written in two parts, and the state of the
-     * driver may be modified by other driver operations while waiting for the
-     * I/O to complete.
-     */
-    const uint64_t entry_start_sector = s->cur_log_sector;
-    const uint64_t entry_offset = entry_start_sector << s->sectorbits;
-    const uint64_t qiov_aligned_size = ROUND_UP(lr->qiov->size, s->sectorsize);
-    const uint64_t entry_aligned_size = qiov_aligned_size +
-        ROUND_UP(lr->zero_size, s->sectorsize);
-    const uint64_t entry_nr_sectors = entry_aligned_size >> s->sectorbits;
+    uint64_t cur_log_offset = s->cur_log_sector << s->sectorbits;
 
     s->nr_entries++;
-    s->cur_log_sector += entry_nr_sectors;
+    s->cur_log_sector +=
+            ROUND_UP(lr->qiov->size, s->sectorsize) >> s->sectorbits;
 
-    /*
-     * Write the log entry. Note that if this is a "write zeroes" operation,
-     * only the entry header is written here, with the zeroing being done
-     * separately below.
-     */
-    lr->log_ret = bdrv_co_pwritev(s->log_file, entry_offset, lr->qiov->size,
+    lr->log_ret = bdrv_co_pwritev(s->log_file, cur_log_offset, lr->qiov->size,
                                   lr->qiov, 0);
 
     /* Logging for the "write zeroes" operation */
     if (lr->log_ret == 0 && lr->zero_size) {
-        const uint64_t zeroes_offset = entry_offset + qiov_aligned_size;
+        cur_log_offset = s->cur_log_sector << s->sectorbits;
+        s->cur_log_sector +=
+                ROUND_UP(lr->zero_size, s->sectorsize) >> s->sectorbits;
 
-        lr->log_ret = bdrv_co_pwrite_zeroes(s->log_file, zeroes_offset,
+        lr->log_ret = bdrv_co_pwrite_zeroes(s->log_file, cur_log_offset,
                                             lr->zero_size, 0);
     }
 

block/blkreplay.c

@@ -130,13 +130,7 @@ static int coroutine_fn GRAPH_RDLOCK blkreplay_co_flush(BlockDriverState *bs)
 static int blkreplay_snapshot_goto(BlockDriverState *bs,
                                    const char *snapshot_id)
 {
-    BlockDriverState *file_bs;
-
-    bdrv_graph_rdlock_main_loop();
-    file_bs = bs->file->bs;
-    bdrv_graph_rdunlock_main_loop();
-
-    return bdrv_snapshot_goto(file_bs, snapshot_id, NULL);
+    return bdrv_snapshot_goto(bs->file->bs, snapshot_id, NULL);
 }
 
 static BlockDriver bdrv_blkreplay = {

block/blkverify.c

@@ -33,8 +33,8 @@ typedef struct BlkverifyRequest {
     uint64_t bytes;
     int flags;
 
-    int GRAPH_RDLOCK_PTR (*request_fn)(
-        BdrvChild *, int64_t, int64_t, QEMUIOVector *, BdrvRequestFlags);
+    int (*request_fn)(BdrvChild *, int64_t, int64_t, QEMUIOVector *,
+                      BdrvRequestFlags);
 
     int ret;                    /* test image result */
     int raw_ret;                /* raw image result */
@@ -151,10 +151,8 @@ static void blkverify_close(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 
-    bdrv_graph_wrlock(NULL);
     bdrv_unref_child(bs, s->test_file);
     s->test_file = NULL;
-    bdrv_graph_wrunlock(NULL);
 }
 
 static int64_t coroutine_fn GRAPH_RDLOCK
@@ -170,11 +168,8 @@ static void coroutine_fn blkverify_do_test_req(void *opaque)
     BlkverifyRequest *r = opaque;
     BDRVBlkverifyState *s = r->bs->opaque;
 
-    bdrv_graph_co_rdlock();
     r->ret = r->request_fn(s->test_file, r->offset, r->bytes, r->qiov,
                            r->flags);
-    bdrv_graph_co_rdunlock();
-
     r->done++;
     qemu_coroutine_enter_if_inactive(r->co);
 }
@@ -183,16 +178,13 @@ static void coroutine_fn blkverify_do_raw_req(void *opaque)
 {
     BlkverifyRequest *r = opaque;
 
-    bdrv_graph_co_rdlock();
     r->raw_ret = r->request_fn(r->bs->file, r->offset, r->bytes, r->raw_qiov,
                                r->flags);
-    bdrv_graph_co_rdunlock();
-
     r->done++;
     qemu_coroutine_enter_if_inactive(r->co);
 }
 
-static int coroutine_fn GRAPH_RDLOCK
+static int coroutine_fn
 blkverify_co_prwv(BlockDriverState *bs, BlkverifyRequest *r, uint64_t offset,
                   uint64_t bytes, QEMUIOVector *qiov, QEMUIOVector *raw_qiov,
                   int flags, bool is_write)
@@ -228,7 +220,7 @@ blkverify_co_prwv(BlockDriverState *bs, BlkverifyRequest *r, uint64_t offset,
     return r->ret;
 }
 
-static int coroutine_fn GRAPH_RDLOCK
+static int coroutine_fn
 blkverify_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
                     QEMUIOVector *qiov, BdrvRequestFlags flags)
 {
@@ -257,7 +249,7 @@ blkverify_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
     return ret;
 }
 
-static int coroutine_fn GRAPH_RDLOCK
+static int coroutine_fn
 blkverify_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
                      QEMUIOVector *qiov, BdrvRequestFlags flags)
 {
@@ -288,7 +280,7 @@ blkverify_recurse_can_replace(BlockDriverState *bs,
            bdrv_recurse_can_replace(s->test_file->bs, to_replace);
 }
 
-static void GRAPH_RDLOCK blkverify_refresh_filename(BlockDriverState *bs)
+static void blkverify_refresh_filename(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 

block/block-backend.c

@@ -33,6 +33,8 @@
 
 #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
 
+static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb);
+
 typedef struct BlockBackendAioNotifier {
     void (*attached_aio_context)(AioContext *new_context, void *opaque);
     void (*detach_aio_context)(void *opaque);
@@ -101,6 +103,7 @@ typedef struct BlockBackendAIOCB {
 } BlockBackendAIOCB;
 
 static const AIOCBInfo block_backend_aiocb_info = {
+    .get_aio_context = blk_aiocb_get_aio_context,
     .aiocb_size = sizeof(BlockBackendAIOCB),
 };
 
@@ -118,10 +121,6 @@ static QTAILQ_HEAD(, BlockBackend) block_backends =
 static QTAILQ_HEAD(, BlockBackend) monitor_block_backends =
     QTAILQ_HEAD_INITIALIZER(monitor_block_backends);
 
-static int coroutine_mixed_fn GRAPH_RDLOCK
-blk_set_perm_locked(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
-                    Error **errp);
-
 static void blk_root_inherit_options(BdrvChildRole role, bool parent_is_format,
                                      int *child_flags, QDict *child_options,
                                      int parent_flags, QDict *parent_options)
@@ -187,7 +186,7 @@ static void blk_vm_state_changed(void *opaque, bool running, RunState state)
  *
  * If an error is returned, the VM cannot be allowed to be resumed.
  */
-static void GRAPH_RDLOCK blk_root_activate(BdrvChild *child, Error **errp)
+static void blk_root_activate(BdrvChild *child, Error **errp)
 {
     BlockBackend *blk = child->opaque;
     Error *local_err = NULL;
@@ -208,7 +207,7 @@ static void GRAPH_RDLOCK blk_root_activate(BdrvChild *child, Error **errp)
      */
     saved_shared_perm = blk->shared_perm;
 
-    blk_set_perm_locked(blk, blk->perm, BLK_PERM_ALL, &local_err);
+    blk_set_perm(blk, blk->perm, BLK_PERM_ALL, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         blk->disable_perm = true;
@@ -227,7 +226,7 @@ static void GRAPH_RDLOCK blk_root_activate(BdrvChild *child, Error **errp)
         return;
     }
 
-    blk_set_perm_locked(blk, blk->perm, blk->shared_perm, &local_err);
+    blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         blk->disable_perm = true;
@@ -260,7 +259,7 @@ static bool blk_can_inactivate(BlockBackend *blk)
     return blk->force_allow_inactivate;
 }
 
-static int GRAPH_RDLOCK blk_root_inactivate(BdrvChild *child)
+static int blk_root_inactivate(BdrvChild *child)
 {
     BlockBackend *blk = child->opaque;
 
@@ -780,12 +779,11 @@ BlockDriverState *blk_bs(BlockBackend *blk)
     return blk->root ? blk->root->bs : NULL;
 }
 
-static BlockBackend * GRAPH_RDLOCK bdrv_first_blk(BlockDriverState *bs)
+static BlockBackend *bdrv_first_blk(BlockDriverState *bs)
 {
     BdrvChild *child;
 
     GLOBAL_STATE_CODE();
-    assert_bdrv_graph_readable();
 
     QLIST_FOREACH(child, &bs->parents, next_parent) {
         if (child->klass == &child_root) {
@@ -813,8 +811,6 @@ bool bdrv_is_root_node(BlockDriverState *bs)
     BdrvChild *c;
 
     GLOBAL_STATE_CODE();
-    assert_bdrv_graph_readable();
-
     QLIST_FOREACH(c, &bs->parents, next_parent) {
         if (c->klass != &child_root) {
             return false;
@@ -882,14 +878,11 @@ BlockBackend *blk_by_public(BlockBackendPublic *public)
 
 /*
  * Disassociates the currently associated BlockDriverState from @blk.
- *
- * The caller must hold the AioContext lock for the BlockBackend.
  */
 void blk_remove_bs(BlockBackend *blk)
 {
     ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
     BdrvChild *root;
-    AioContext *ctx;
 
     GLOBAL_STATE_CODE();
 
@@ -918,11 +911,7 @@ void blk_remove_bs(BlockBackend *blk)
     blk_drain(blk);
     root = blk->root;
     blk->root = NULL;
-
-    ctx = bdrv_get_aio_context(root->bs);
-    bdrv_graph_wrlock(root->bs);
     bdrv_root_unref_child(root);
-    bdrv_graph_wrunlock_ctx(ctx);
 }
 
 /*
@@ -933,16 +922,12 @@ void blk_remove_bs(BlockBackend *blk)
 int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
 {
     ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
-    AioContext *ctx = bdrv_get_aio_context(bs);
-
     GLOBAL_STATE_CODE();
     bdrv_ref(bs);
-    bdrv_graph_wrlock(bs);
     blk->root = bdrv_root_attach_child(bs, "root", &child_root,
                                        BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
                                        blk->perm, blk->shared_perm,
                                        blk, errp);
-    bdrv_graph_wrunlock_ctx(ctx);
     if (blk->root == NULL) {
         return -EPERM;
     }
@@ -968,9 +953,8 @@ int blk_replace_bs(BlockBackend *blk, BlockDriverState *new_bs, Error **errp)
 /*
  * Sets the permission bitmasks that the user of the BlockBackend needs.
  */
-static int coroutine_mixed_fn GRAPH_RDLOCK
-blk_set_perm_locked(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
-                    Error **errp)
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+                 Error **errp)
 {
     int ret;
     GLOBAL_STATE_CODE();
@@ -988,15 +972,6 @@ blk_set_perm_locked(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
     return 0;
 }
 
-int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
-                 Error **errp)
-{
-    GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
-    return blk_set_perm_locked(blk, perm, shared_perm, errp);
-}
-
 void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
 {
     GLOBAL_STATE_CODE();
@@ -1366,7 +1341,7 @@ blk_co_do_preadv_part(BlockBackend *blk, int64_t offset, int64_t bytes,
     /* throttling disk I/O */
     if (blk->public.throttle_group_member.throttle_state) {
         throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
-                bytes, THROTTLE_READ);
+                bytes, false);
     }
 
     ret = bdrv_co_preadv_part(blk->root, offset, bytes, qiov, qiov_offset,
@@ -1440,7 +1415,7 @@ blk_co_do_pwritev_part(BlockBackend *blk, int64_t offset, int64_t bytes,
     /* throttling disk I/O */
     if (blk->public.throttle_group_member.throttle_state) {
         throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
-                bytes, THROTTLE_WRITE);
+                bytes, true);
     }
 
     if (!blk->enable_write_cache) {
@@ -1558,7 +1533,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
     acb->blk = blk;
     acb->ret = ret;
 
-    replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+    replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
                                      error_callback_bh, acb);
     return &acb->common;
 }
@@ -1570,8 +1545,16 @@ typedef struct BlkAioEmAIOCB {
     bool has_returned;
 } BlkAioEmAIOCB;
 
+static AioContext *blk_aio_em_aiocb_get_aio_context(BlockAIOCB *acb_)
+{
+    BlkAioEmAIOCB *acb = container_of(acb_, BlkAioEmAIOCB, common);
+
+    return blk_get_aio_context(acb->rwco.blk);
+}
+
 static const AIOCBInfo blk_aio_em_aiocb_info = {
     .aiocb_size         = sizeof(BlkAioEmAIOCB),
+    .get_aio_context    = blk_aio_em_aiocb_get_aio_context,
 };
 
 static void blk_aio_complete(BlkAioEmAIOCB *acb)
@@ -1612,11 +1595,11 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset,
     acb->has_returned = false;
 
     co = qemu_coroutine_create(co_entry, acb);
-    aio_co_enter(qemu_get_current_aio_context(), co);
+    aio_co_enter(blk_get_aio_context(blk), co);
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+        replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
                                          blk_aio_complete_bh, acb);
     }
 
@@ -1918,11 +1901,11 @@ BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
     acb->has_returned = false;
 
     co = qemu_coroutine_create(blk_aio_zone_report_entry, acb);
-    aio_co_enter(qemu_get_current_aio_context(), co);
+    aio_co_enter(blk_get_aio_context(blk), co);
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+        replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
                                          blk_aio_complete_bh, acb);
     }
 
@@ -1959,11 +1942,11 @@ BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
     acb->has_returned = false;
 
     co = qemu_coroutine_create(blk_aio_zone_mgmt_entry, acb);
-    aio_co_enter(qemu_get_current_aio_context(), co);
+    aio_co_enter(blk_get_aio_context(blk), co);
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+        replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
                                          blk_aio_complete_bh, acb);
     }
 
@@ -1999,10 +1982,10 @@ BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset,
     acb->has_returned = false;
 
     co = qemu_coroutine_create(blk_aio_zone_append_entry, acb);
-    aio_co_enter(qemu_get_current_aio_context(), co);
+    aio_co_enter(blk_get_aio_context(blk), co);
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+        replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
                                          blk_aio_complete_bh, acb);
     }
 
@@ -2270,7 +2253,6 @@ void blk_activate(BlockBackend *blk, Error **errp)
     if (qemu_in_coroutine()) {
         bdrv_co_activate(bs, errp);
     } else {
-        GRAPH_RDLOCK_GUARD_MAINLOOP();
         bdrv_activate(bs, errp);
     }
 }
@@ -2396,7 +2378,6 @@ bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
 {
     BlockDriverState *bs = blk_bs(blk);
     GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
 
     if (!bs) {
         return false;
@@ -2453,6 +2434,12 @@ AioContext *blk_get_aio_context(BlockBackend *blk)
     return blk->ctx;
 }
 
+static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb)
+{
+    BlockBackendAIOCB *blk_acb = DO_UPCAST(BlockBackendAIOCB, common, acb);
+    return blk_get_aio_context(blk_acb->blk);
+}
+
 int blk_set_aio_context(BlockBackend *blk, AioContext *new_context,
                         Error **errp)
 {
@@ -2674,8 +2661,6 @@ int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)
 int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz)
 {
     GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
@@ -2736,7 +2721,6 @@ int blk_commit_all(void)
 {
     BlockBackend *blk = NULL;
     GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
 
     while ((blk = blk_all_next(blk)) != NULL) {
         AioContext *aio_context = blk_get_aio_context(blk);
@@ -2917,8 +2901,6 @@ const BdrvChild *blk_root(BlockBackend *blk)
 int blk_make_empty(BlockBackend *blk, Error **errp)
 {
     GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
     if (!blk_is_available(blk)) {
         error_setg(errp, "No medium inserted");
         return -ENOMEDIUM;

block/block-copy.c

@@ -67,7 +67,7 @@ typedef struct BlockCopyCallState {
     QLIST_ENTRY(BlockCopyCallState) list;
 
     /*
-     * Fields that report information about return values and errors.
+     * Fields that report information about return values and erros.
      * Protected by lock in BlockCopyState.
      */
     bool error_is_read;
@@ -313,12 +313,7 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
 {
     int ret;
     BlockDriverInfo bdi;
-    bool target_does_cow;
-
-    GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
-    target_does_cow = bdrv_backing_chain_next(target);
+    bool target_does_cow = bdrv_backing_chain_next(target);
 
     /*
      * If there is no backing file on the target, we cannot rely on COW if our
@@ -360,8 +355,6 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
     BdrvDirtyBitmap *copy_bitmap;
     bool is_fleecing;
 
-    GLOBAL_STATE_CODE();
-
     cluster_size = block_copy_calculate_cluster_size(target->bs, errp);
     if (cluster_size < 0) {
         return NULL;
@@ -399,9 +392,7 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
      * For more information see commit f8d59dfb40bb and test
      * tests/qemu-iotests/222
      */
-    bdrv_graph_rdlock_main_loop();
     is_fleecing = bdrv_chain_contains(target->bs, source->bs);
-    bdrv_graph_rdunlock_main_loop();
 
     s = g_new(BlockCopyState, 1);
     *s = (BlockCopyState) {
@@ -471,7 +462,7 @@ static coroutine_fn int block_copy_task_run(AioTaskPool *pool,
  * Do copy of cluster-aligned chunk. Requested region is allowed to exceed
  * s->len only to cover last cluster when s->len is not aligned to clusters.
  *
- * No sync here: neither bitmap nor intersecting requests handling, only copy.
+ * No sync here: nor bitmap neighter intersecting requests handling, only copy.
  *
  * @method is an in-out argument, so that copy_range can be either extended to
  * a full-size buffer or disabled if the copy_range attempt fails.  The output

block/bochs.c

@@ -105,12 +105,8 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
     struct bochs_header bochs;
     int ret;
 
-    GLOBAL_STATE_CODE();
-
     /* No write support yet */
-    bdrv_graph_rdlock_main_loop();
     ret = bdrv_apply_auto_read_only(bs, NULL, errp);
-    bdrv_graph_rdunlock_main_loop();
     if (ret < 0) {
         return ret;
     }
@@ -120,8 +116,6 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
 
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
     ret = bdrv_pread(bs->file, 0, sizeof(bochs), &bochs, 0);
     if (ret < 0) {
         return ret;

block/cloop.c

@@ -67,11 +67,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     uint32_t offsets_size, max_compressed_block_size = 1, i;
     int ret;
 
-    GLOBAL_STATE_CODE();
-
-    bdrv_graph_rdlock_main_loop();
     ret = bdrv_apply_auto_read_only(bs, NULL, errp);
-    bdrv_graph_rdunlock_main_loop();
     if (ret < 0) {
         return ret;
     }
@@ -81,8 +77,6 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
 
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
     /* read header */
     ret = bdrv_pread(bs->file, 128, 4, &s->block_size, 0);
     if (ret < 0) {

block/commit.c

@@ -48,10 +48,8 @@ static int commit_prepare(Job *job)
 {
     CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
 
-    bdrv_graph_rdlock_main_loop();
     bdrv_unfreeze_backing_chain(s->commit_top_bs, s->base_bs);
     s->chain_frozen = false;
-    bdrv_graph_rdunlock_main_loop();
 
     /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
      * the normal backing chain can be restored. */
@@ -68,12 +66,9 @@ static void commit_abort(Job *job)
 {
     CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
     BlockDriverState *top_bs = blk_bs(s->top);
-    BlockDriverState *commit_top_backing_bs;
 
     if (s->chain_frozen) {
-        bdrv_graph_rdlock_main_loop();
         bdrv_unfreeze_backing_chain(s->commit_top_bs, s->base_bs);
-        bdrv_graph_rdunlock_main_loop();
     }
 
     /* Make sure commit_top_bs and top stay around until bdrv_replace_node() */
@@ -95,15 +90,8 @@ static void commit_abort(Job *job)
      * XXX Can (or should) we somehow keep 'consistent read' blocked even
      * after the failed/cancelled commit job is gone? If we already wrote
      * something to base, the intermediate images aren't valid any more. */
-    bdrv_graph_rdlock_main_loop();
-    commit_top_backing_bs = s->commit_top_bs->backing->bs;
-    bdrv_graph_rdunlock_main_loop();
-
-    bdrv_drained_begin(commit_top_backing_bs);
-    bdrv_graph_wrlock(commit_top_backing_bs);
-    bdrv_replace_node(s->commit_top_bs, commit_top_backing_bs, &error_abort);
-    bdrv_graph_wrunlock(commit_top_backing_bs);
-    bdrv_drained_end(commit_top_backing_bs);
+    bdrv_replace_node(s->commit_top_bs, s->commit_top_bs->backing->bs,
+                      &error_abort);
 
     bdrv_unref(s->commit_top_bs);
     bdrv_unref(top_bs);
@@ -222,7 +210,7 @@ bdrv_commit_top_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
     return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
 }
 
-static GRAPH_RDLOCK void bdrv_commit_top_refresh_filename(BlockDriverState *bs)
+static void bdrv_commit_top_refresh_filename(BlockDriverState *bs)
 {
     pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
             bs->backing->bs->filename);
@@ -267,13 +255,10 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     GLOBAL_STATE_CODE();
 
     assert(top != bs);
-    bdrv_graph_rdlock_main_loop();
     if (bdrv_skip_filters(top) == bdrv_skip_filters(base)) {
         error_setg(errp, "Invalid files for merge: top and base are the same");
-        bdrv_graph_rdunlock_main_loop();
         return;
     }
-    bdrv_graph_rdunlock_main_loop();
 
     base_size = bdrv_getlength(base);
     if (base_size < 0) {
@@ -339,7 +324,6 @@ void commit_start(const char *job_id, BlockDriverState *bs,
      * this is the responsibility of the interface (i.e. whoever calls
      * commit_start()).
      */
-    bdrv_graph_wrlock(top);
     s->base_overlay = bdrv_find_overlay(top, base);
     assert(s->base_overlay);
 
@@ -370,20 +354,16 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
                                  iter_shared_perms, errp);
         if (ret < 0) {
-            bdrv_graph_wrunlock(top);
             goto fail;
         }
     }
 
     if (bdrv_freeze_backing_chain(commit_top_bs, base, errp) < 0) {
-        bdrv_graph_wrunlock(top);
         goto fail;
     }
     s->chain_frozen = true;
 
     ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
-    bdrv_graph_wrunlock(top);
-
     if (ret < 0) {
         goto fail;
     }
@@ -416,9 +396,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 
 fail:
     if (s->chain_frozen) {
-        bdrv_graph_rdlock_main_loop();
         bdrv_unfreeze_backing_chain(commit_top_bs, base);
-        bdrv_graph_rdunlock_main_loop();
     }
     if (s->base) {
         blk_unref(s->base);
@@ -433,11 +411,7 @@ fail:
     /* commit_top_bs has to be replaced after deleting the block job,
      * otherwise this would fail because of lack of permissions. */
     if (commit_top_bs) {
-        bdrv_drained_begin(top);
-        bdrv_graph_wrlock(top);
         bdrv_replace_node(commit_top_bs, top, &error_abort);
-        bdrv_graph_wrunlock(top);
-        bdrv_drained_end(top);
     }
 }
 
@@ -460,7 +434,6 @@ int bdrv_commit(BlockDriverState *bs)
     Error *local_err = NULL;
 
     GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
 
     if (!drv)
         return -ENOMEDIUM;