Update version for 8.0.4 release

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
target/i386: Check CR0.TS before enter_mmx
2023-08-07 15:05:10 +03:00 · 2023-08-05 20:49:49 +03:00 · 2023-08-05 20:49:49 +03:00 · 2023-08-05 20:49:49 +03:00 · 2023-08-05 20:49:49 +03:00 · 2023-08-05 20:49:49 +03:00
3567 changed files with 96193 additions and 222806 deletions
--- a/.gitlab-ci.d/base.yml
+++ b/.gitlab-ci.d/base.yml
@@ -1,24 +1,10 @@

-variables:
-  # On stable branches this is changed by later rules. Should also
-  # be overridden per pipeline if running pipelines concurrently
-  # for different branches in contributor forks.
-  QEMU_CI_CONTAINER_TAG: latest
-
-  # For purposes of CI rules, upstream is the gitlab.com/qemu-project
-  # namespace. When testing CI, it might be usefult to override this
-  # to point to a fork repo
-  QEMU_CI_UPSTREAM: qemu-project
-
 # The order of rules defined here is critically important.
 # They are evaluated in order and first match wins.
 #
 # Thus we group them into a number of stages, ordered from
 # most restrictive to least restrictive
 #
-# For pipelines running for stable "staging-X.Y" branches
-# we must override QEMU_CI_CONTAINER_TAG
-#
 .base_job_template:
  variables:
    # Each script line from will be in a collapsible section in the job output
@@ -33,68 +19,48 @@ variables:
    # want jobs to run
    #############################################################

-    # Never run jobs upstream on stable branch, staging branch jobs already ran
-    - if: '$CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH =~ /^stable-/'
-      when: never
-
-    # Never run jobs upstream on tags, staging branch jobs already ran
-    - if: '$CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_TAG'
-      when: never
-
    # Cirrus jobs can't run unless the creds / target repo are set
    - if: '$QEMU_JOB_CIRRUS && ($CIRRUS_GITHUB_REPO == null || $CIRRUS_API_TOKEN == null)'
      when: never

    # Publishing jobs should only run on the default branch in upstream
-    - if: '$QEMU_JOB_PUBLISH == "1" && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH != $CI_DEFAULT_BRANCH'
+    - if: '$QEMU_JOB_PUBLISH == "1" && $CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH != $CI_DEFAULT_BRANCH'
      when: never

    # Non-publishing jobs should only run on staging branches in upstream
-    - if: '$QEMU_JOB_PUBLISH != "1" && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH !~ /staging/'
+    - if: '$QEMU_JOB_PUBLISH != "1" && $CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH !~ /staging/'
      when: never

    # Jobs only intended for forks should always be skipped on upstream
-    - if: '$QEMU_JOB_ONLY_FORKS == "1" && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM'
+    - if: '$QEMU_JOB_ONLY_FORKS == "1" && $CI_PROJECT_NAMESPACE == "qemu-project"'
      when: never

    # Forks don't get pipelines unless QEMU_CI=1 or QEMU_CI=2 is set
-    - if: '$QEMU_CI != "1" && $QEMU_CI != "2" && $CI_PROJECT_NAMESPACE != $QEMU_CI_UPSTREAM'
+    - if: '$QEMU_CI != "1" && $QEMU_CI != "2" && $CI_PROJECT_NAMESPACE != "qemu-project"'
      when: never

    # Avocado jobs don't run in forks unless $QEMU_CI_AVOCADO_TESTING is set
-    - if: '$QEMU_JOB_AVOCADO && $QEMU_CI_AVOCADO_TESTING != "1" && $CI_PROJECT_NAMESPACE != $QEMU_CI_UPSTREAM'
+    - if: '$QEMU_JOB_AVOCADO && $QEMU_CI_AVOCADO_TESTING != "1" && $CI_PROJECT_NAMESPACE != "qemu-project"'
      when: never


    #############################################################
    # 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
-    - if: '$QEMU_JOB_OPTIONAL && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH =~ /staging-[[:digit:]]+\.[[:digit:]]/'
-      when: manual
-      allow_failure: true
-      variables:
-        QEMU_CI_CONTAINER_TAG: $CI_COMMIT_REF_SLUG
-
    - if: '$QEMU_JOB_OPTIONAL'
      when: manual
      allow_failure: true

    # Skipped jobs should not be run unless manually triggered
-    - if: '$QEMU_JOB_SKIPPED && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH =~ /staging-[[:digit:]]+\.[[:digit:]]/'
-      when: manual
-      allow_failure: true
-      variables:
-        QEMU_CI_CONTAINER_TAG: $CI_COMMIT_REF_SLUG
-
    - if: '$QEMU_JOB_SKIPPED'
      when: manual
      allow_failure: true

    # Avocado jobs can be manually start in forks if $QEMU_CI_AVOCADO_TESTING is unset
-    - if: '$QEMU_JOB_AVOCADO && $CI_PROJECT_NAMESPACE != $QEMU_CI_UPSTREAM'
+    - if: '$QEMU_JOB_AVOCADO && $CI_PROJECT_NAMESPACE != "qemu-project"'
      when: manual
      allow_failure: true

@@ -106,23 +72,8 @@ variables:

    # Forks pipeline jobs don't start automatically unless
    # QEMU_CI=2 is set
-    - if: '$QEMU_CI != "2" && $CI_PROJECT_NAMESPACE != $QEMU_CI_UPSTREAM'
-      when: manual
-
-    # Upstream pipeline jobs start automatically unless told not to
-    # by setting QEMU_CI=1
-    - if: '$QEMU_CI == "1" && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH =~ /staging-[[:digit:]]+\.[[:digit:]]/'
-      when: manual
-      variables:
-        QEMU_CI_CONTAINER_TAG: $CI_COMMIT_REF_SLUG
-
-    - if: '$QEMU_CI == "1" && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM'
+    - if: '$QEMU_CI != "2" && $CI_PROJECT_NAMESPACE != "qemu-project"'
      when: manual

    # Jobs can run if any jobs they depend on were successful
-    - if: '$QEMU_JOB_SKIPPED && $CI_PROJECT_NAMESPACE == $QEMU_CI_UPSTREAM && $CI_COMMIT_BRANCH =~ /staging-[[:digit:]]+\.[[:digit:]]/'
-      when: on_success
-      variables:
-        QEMU_CI_CONTAINER_TAG: $CI_COMMIT_REF_SLUG
-
    - when: on_success
--- a/.gitlab-ci.d/buildtest-template.yml
+++ b/.gitlab-ci.d/buildtest-template.yml
@@ -1,42 +1,34 @@
 .native_build_job_template:
  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
+  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
  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:$PATH"
+    - if test -n "$LD_JOBS";
+      then
+        scripts/git-submodule.sh update meson ;
+      fi
    - mkdir build
    - cd build
-    - ccache --zero-stats
    - ../configure --enable-werror --disable-docs --enable-fdt=system
-          ${TARGETS:+--target-list="$TARGETS"}
+          ${LD_JOBS:+--meson=git} ${TARGETS:+--target-list="$TARGETS"}
          $CONFIGURE_ARGS ||
      { cat config.log meson-logs/meson-log.txt && exit 1; }
    - if test -n "$LD_JOBS";
      then
-        pyvenv/bin/meson configure . -Dbackend_max_links="$LD_JOBS" ;
+        ../meson/meson.py configure . -Dbackend_max_links="$LD_JOBS" ;
      fi || exit 1;
    - make -j"$JOBS"
    - if test -n "$MAKE_CHECK_ARGS";
      then
        make -j"$JOBS" $MAKE_CHECK_ARGS ;
      fi
-    - 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
@@ -52,10 +44,10 @@
 .common_test_job_template:
  extends: .base_job_template
  stage: test
-  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
  script:
-    - scripts/git-submodule.sh update roms/SLOF
-    - meson subprojects download $(cd build/subprojects && echo *)
+    - scripts/git-submodule.sh update
+        $(sed -n '/GIT_SUBMODULES=/ s/.*=// p' build/config-host.mak)
    - cd build
    - find . -type f -exec touch {} +
    # Avoid recompiling by hiding ninja with NINJA=":"
@@ -65,7 +57,6 @@
  extends: .common_test_job_template
  artifacts:
    name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
-    when: always
    expire_in: 7 days
    paths:
      - build/meson-logs/testlog.txt
@@ -81,7 +72,7 @@
    policy: pull-push
  artifacts:
    name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
-    when: always
+    when: on_failure
    expire_in: 7 days
    paths:
      - build/tests/results/latest/results.xml
--- a/.gitlab-ci.d/buildtest.yml
+++ b/.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 microblazeel-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:
@@ -73,7 +72,7 @@ build-system-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:
@@ -93,7 +92,6 @@ avocado-system-debian:
  variables:
    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
@@ -105,7 +103,7 @@ crash-test-debian:
  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:
@@ -215,7 +209,6 @@ avocado-system-opensuse:
  variables:
    IMAGE: opensuse-leap
    MAKE_CHECK_ARGS: check-avocado
-    AVOCADO_TAGS: arch:s390x arch:x86_64 arch:aarch64


 # This jobs explicitly disable TCG (--disable-tcg), KVM is detected by
@@ -256,7 +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:
@@ -266,18 +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:
@@ -290,9 +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:
@@ -300,18 +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
@@ -344,7 +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

@@ -487,7 +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
@@ -495,12 +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
@@ -531,7 +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
@@ -564,12 +527,12 @@ build-without-defaults:
      --disable-strip
    TARGETS: avr-softmmu mips64-softmmu s390x-softmmu sh4-softmmu
      sparc64-softmmu hexagon-linux-user i386-linux-user s390x-linux-user
-    MAKE_CHECK_ARGS: check
+    MAKE_CHECK_ARGS: check-unit check-qtest-avr check-qtest-mips64

 build-libvhost-user:
  extends: .base_job_template
  stage: build
-  image: $CI_REGISTRY_IMAGE/qemu/fedora:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/fedora:latest
  needs:
    job: amd64-fedora-container
  script:
@@ -609,7 +572,7 @@ build-tools-and-docs-debian:
 # of what topic branch they're currently using
 pages:
  extends: .base_job_template
-  image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:latest
  stage: test
  needs:
    - job: build-tools-and-docs-debian
@@ -624,7 +587,6 @@ pages:
    - make -C build install DESTDIR=$(pwd)/temp-install
    - mv temp-install/usr/local/share/doc/qemu/* public/
  artifacts:
-    when: on_success
    paths:
      - public
  variables:
--- a/.gitlab-ci.d/cirrus.yml
+++ b/.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"
@@ -46,13 +44,26 @@
  variables:
    QEMU_JOB_CIRRUS: 1

+x64-freebsd-12-build:
+  extends: .cirrus_build_job
+  variables:
+    NAME: freebsd-12
+    CIRRUS_VM_INSTANCE_TYPE: freebsd_instance
+    CIRRUS_VM_IMAGE_SELECTOR: image_family
+    CIRRUS_VM_IMAGE_NAME: freebsd-12-4
+    CIRRUS_VM_CPUS: 8
+    CIRRUS_VM_RAM: 8G
+    UPDATE_COMMAND: pkg update; pkg upgrade -y
+    INSTALL_COMMAND: pkg install -y
+    TEST_TARGETS: check
+
 x64-freebsd-13-build:
  extends: .cirrus_build_job
  variables:
    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
--- a/.gitlab-ci.d/cirrus/build.yml
+++ b/.gitlab-ci.d/cirrus/build.yml
@@ -16,8 +16,6 @@ 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@
--- a/.gitlab-ci.d/cirrus/freebsd-12.vars
+++ b/.gitlab-ci.d/cirrus/freebsd-12.vars
@@ -0,0 +1,16 @@
+# THIS FILE WAS AUTO-GENERATED
+#
+#  $ lcitool variables freebsd-12 qemu
+#
+# https://gitlab.com/libvirt/libvirt-ci
+
+CCACHE='/usr/local/bin/ccache'
+CPAN_PKGS=''
+CROSS_PKGS=''
+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 cdrkit-genisoimage 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 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 zstd'
+PYPI_PKGS=''
+PYTHON='/usr/local/bin/python3'
--- a/.gitlab-ci.d/cirrus/freebsd-13.vars
+++ b/.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 cdrkit-genisoimage 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 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 zstd'
 PYPI_PKGS=''
 PYTHON='/usr/local/bin/python3'
--- a/.gitlab-ci.d/cirrus/kvm-build.yml
+++ b/.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"
--- a/.gitlab-ci.d/cirrus/macos-12.vars
+++ b/.gitlab-ci.d/cirrus/macos-12.vars
@@ -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 ncurses nettle ninja pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy socat sparse spice-protocol tesseract usbredir vde vte3 zlib zstd'
+PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme'
 PYTHON='/opt/homebrew/bin/python3'
--- a/.gitlab-ci.d/container-cross.yml
+++ b/.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
@@ -40,11 +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
+
+m68k-debian-cross-container:
+  extends: .container_job_template
+  stage: containers
+  variables:
+    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
@@ -52,12 +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
@@ -71,7 +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
@@ -79,6 +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
--- a/.gitlab-ci.d/container-template.yml
+++ b/.gitlab-ci.d/container-template.yml
@@ -1,15 +1,15 @@
 .container_job_template:
  extends: .base_job_template
-  image: docker:latest
+  image: docker:stable
  stage: containers
  services:
    - docker:dind
  before_script:
-    - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:$QEMU_CI_CONTAINER_TAG"
-    # Always ':latest' because we always use upstream as a common cache source
+    - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest"
    - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/qemu/$NAME:latest"
+    - apk add python3
+    - docker info
    - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD"
-    - until docker info; do sleep 1; done
  script:
    - echo "TAG:$TAG"
    - echo "COMMON_TAG:$COMMON_TAG"
--- a/.gitlab-ci.d/crossbuild-template.yml
+++ b/.gitlab-ci.d/crossbuild-template.yml
@@ -1,21 +1,11 @@
 .cross_system_build_job:
  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
+  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
  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.
 #
@@ -38,17 +27,9 @@
 .cross_accel_build_job:
  extends: .base_job_template
  stage: build
-  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
  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
@@ -58,15 +39,8 @@
 .cross_user_build_job:
  extends: .base_job_template
  stage: build
-  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:$QEMU_CI_CONTAINER_TAG
-  cache:
-    paths:
-      - ccache/
-    key: "$CI_JOB_NAME"
+  image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
  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
--- a/.gitlab-ci.d/crossbuilds.yml
+++ b/.gitlab-ci.d/crossbuilds.yml
@@ -29,14 +29,6 @@ cross-arm64-user:
  variables:
    IMAGE: debian-arm64-cross

-cross-arm64-kvm-only:
-  extends: .cross_accel_build_job
-  needs:
-    job: arm64-debian-cross-container
-  variables:
-    IMAGE: debian-arm64-cross
-    EXTRA_CONFIGURE_OPTS: --disable-tcg --without-default-features
-
 cross-i386-user:
  extends:
    - .cross_user_build_job
@@ -57,7 +49,7 @@ cross-i386-tci:
  variables:
    IMAGE: fedora-i386-cross
    ACCEL: tcg-interpreter
-    EXTRA_CONFIGURE_OPTS: --target-list=i386-softmmu,i386-linux-user,aarch64-softmmu,aarch64-linux-user,ppc-softmmu,ppc-linux-user --disable-plugins
+    EXTRA_CONFIGURE_OPTS: --target-list=i386-softmmu,i386-linux-user,aarch64-softmmu,aarch64-linux-user,ppc-softmmu,ppc-linux-user
    MAKE_CHECK_ARGS: check check-tcg

 cross-mipsel-system:
@@ -165,11 +157,10 @@ cross-win32-system:
    job: win32-fedora-cross-container
  variables:
    IMAGE: fedora-win32-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 mips64el-softmmu nios2-softmmu
  artifacts:
-    when: on_success
    paths:
      - build/qemu-setup*.exe

@@ -179,13 +170,12 @@ 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

--- a/.gitlab-ci.d/custom-runners.yml
+++ b/.gitlab-ci.d/custom-runners.yml
@@ -20,10 +20,8 @@ variables:
  artifacts:
    name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
    expire_in: 7 days
-    when: always
    paths:
-      - build/build.ninja
-      - build/meson-logs
+      - build/meson-logs/testlog.txt
    reports:
      junit: build/meson-logs/testlog.junit.xml

--- a/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch32.yml
+++ b/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch32.yml
@@ -1,6 +1,6 @@
 # All ubuntu-22.04 jobs should run successfully in an environment
 # setup by the scripts/ci/setup/qemu/build-environment.yml task
-# "Install basic packages to build QEMU on Ubuntu 22.04"
+# "Install basic packages to build QEMU on Ubuntu 20.04"

 ubuntu-22.04-aarch32-all:
 extends: .custom_runner_template
--- a/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml
+++ b/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml
@@ -1,6 +1,6 @@
-# All ubuntu-22.04 jobs should run successfully in an environment
+# All ubuntu-20.04 jobs should run successfully in an environment
 # setup by the scripts/ci/setup/qemu/build-environment.yml task
-# "Install basic packages to build QEMU on Ubuntu 22.04"
+# "Install basic packages to build QEMU on Ubuntu 20.04"

 ubuntu-22.04-aarch64-all-linux-static:
 extends: .custom_runner_template
@@ -45,28 +45,6 @@ ubuntu-22.04-aarch64-all:
 - make --output-sync -j`nproc --ignore=40`
 - make --output-sync -j`nproc --ignore=40` check

-ubuntu-22.04-aarch64-without-defaults:
- extends: .custom_runner_template
- needs: []
- stage: build
- tags:
- - ubuntu_22.04
- - aarch64
- rules:
- - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
-   when: manual
-   allow_failure: true
- - if: "$AARCH64_RUNNER_AVAILABLE"
-   when: manual
-   allow_failure: true
- script:
- - mkdir build
- - cd build
- - ../configure --disable-user --without-default-devices --without-default-features
-   || { cat config.log meson-logs/meson-log.txt; exit 1; }
- - make --output-sync -j`nproc --ignore=40`
- - make --output-sync -j`nproc --ignore=40` check
-
 ubuntu-22.04-aarch64-alldbg:
 extends: .custom_runner_template
 needs: []
@@ -145,7 +123,7 @@ ubuntu-22.04-aarch64-notcg:
 script:
 - mkdir build
 - cd build
- - ../configure --disable-tcg --with-devices-aarch64=minimal
+ - ../configure --disable-tcg
   || { cat config.log meson-logs/meson-log.txt; exit 1; }
 - make --output-sync -j`nproc --ignore=40`
 - make --output-sync -j`nproc --ignore=40` check
--- a/.gitlab-ci.d/opensbi.yml
+++ b/.gitlab-ci.d/opensbi.yml
@@ -42,15 +42,17 @@
 docker-opensbi:
  extends: .opensbi_job_rules
  stage: containers
-  image: docker:latest
+  image: docker:stable
  services:
-    - docker:dind
+    - docker:stable-dind
  variables:
    GIT_DEPTH: 3
    IMAGE_TAG: $CI_REGISTRY_IMAGE:opensbi-cross-build
+    # We don't use TLS
+    DOCKER_HOST: tcp://docker:2375
+    DOCKER_TLS_CERTDIR: ""
  before_script:
    - docker login -u $CI_REGISTRY_USER -p $CI_REGISTRY_PASSWORD $CI_REGISTRY
-    - until docker info; do sleep 1; done
  script:
    - docker pull $IMAGE_TAG || true
    - docker build --cache-from $IMAGE_TAG --tag $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA
@@ -63,7 +65,6 @@ 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
--- a/.gitlab-ci.d/qemu-project.yml
+++ b/.gitlab-ci.d/qemu-project.yml
@@ -1,13 +1,6 @@
 # This file contains the set of jobs run by the QEMU project:
 # https://gitlab.com/qemu-project/qemu/-/pipelines

-variables:
-  RUNNER_TAG: ""
-
-default:
-  tags:
-    - $RUNNER_TAG
-
 include:
  - local: '/.gitlab-ci.d/base.yml'
  - local: '/.gitlab-ci.d/stages.yml'
--- a/.gitlab-ci.d/static_checks.yml
+++ b/.gitlab-ci.d/static_checks.yml
@@ -26,7 +26,7 @@ check-dco:
 check-python-minreqs:
  extends: .base_job_template
  stage: test
-  image: $CI_REGISTRY_IMAGE/qemu/python:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/python:latest
  script:
    - make -C python check-minreqs
  variables:
@@ -37,7 +37,7 @@ check-python-minreqs:
 check-python-tox:
  extends: .base_job_template
  stage: test
-  image: $CI_REGISTRY_IMAGE/qemu/python:$QEMU_CI_CONTAINER_TAG
+  image: $CI_REGISTRY_IMAGE/qemu/python:latest
  script:
    - make -C python check-tox
  variables:
--- a/.gitlab-ci.d/windows.yml
+++ b/.gitlab-ci.d/windows.yml
@@ -5,60 +5,21 @@
  - windows
  - windows-1809
  cache:
-    key: "$CI_JOB_NAME"
+    key: "${CI_JOB_NAME}-cache"
    paths:
-      - msys64/var/cache
-      - ccache
-    when: always
+      - ${CI_PROJECT_DIR}/msys64/var/cache
  needs: []
  stage: build
-  timeout: 100m
-  variables:
-    # This feature doesn't (currently) work with PowerShell, it stops
-    # the echo'ing of commands being run and doesn't show any timing
-    FF_SCRIPT_SECTIONS: 0
-  artifacts:
-    name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG"
-    expire_in: 7 days
-    paths:
-      - build/meson-logs/testlog.txt
-    reports:
-      junit: "build/meson-logs/testlog.junit.xml"
+  timeout: 80m
  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') |
@@ -67,75 +28,97 @@
  - .\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-libusb
-      $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-spice
-      $MINGW_TARGET-usbredir
-      $MINGW_TARGET-zstd "
-  - 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
-    # 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 output
+  - cd output
+  # 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
-  variables:
-    MINGW_TARGET: mingw-w64-i686
-    MSYSTEM: MINGW32
-    CONFIGURE_ARGS:  --target-list=ppc64-softmmu -Ddebug=false -Doptimization=0
-    TEST_ARGS: --no-suite qtest
+  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 output
+  - cd output
+  - ..\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; }'
--- a/.gitmodules
+++ b/.gitmodules
@@ -13,6 +13,9 @@
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
 	url = https://gitlab.com/qemu-project/qemu-palcode.git
+[submodule "dtc"]
+	path = dtc
+	url = https://gitlab.com/qemu-project/dtc.git
 [submodule "roms/u-boot"]
 	path = roms/u-boot
 	url = https://gitlab.com/qemu-project/u-boot.git
@@ -22,12 +25,21 @@
 [submodule "roms/QemuMacDrivers"]
 	path = roms/QemuMacDrivers
 	url = https://gitlab.com/qemu-project/QemuMacDrivers.git
+[submodule "ui/keycodemapdb"]
+	path = ui/keycodemapdb
+	url = https://gitlab.com/qemu-project/keycodemapdb.git
 [submodule "roms/seabios-hppa"]
 	path = roms/seabios-hppa
 	url = https://gitlab.com/qemu-project/seabios-hppa.git
 [submodule "roms/u-boot-sam460ex"]
 	path = roms/u-boot-sam460ex
 	url = https://gitlab.com/qemu-project/u-boot-sam460ex.git
+[submodule "tests/fp/berkeley-testfloat-3"]
+	path = tests/fp/berkeley-testfloat-3
+	url = https://gitlab.com/qemu-project/berkeley-testfloat-3.git
+[submodule "tests/fp/berkeley-softfloat-3"]
+	path = tests/fp/berkeley-softfloat-3
+	url = https://gitlab.com/qemu-project/berkeley-softfloat-3.git
 [submodule "roms/edk2"]
 	path = roms/edk2
 	url = https://gitlab.com/qemu-project/edk2.git
@@ -37,9 +49,15 @@
 [submodule "roms/qboot"]
 	path = roms/qboot
 	url = https://gitlab.com/qemu-project/qboot.git
+[submodule "meson"]
+	path = meson
+	url = https://gitlab.com/qemu-project/meson.git
 [submodule "roms/vbootrom"]
 	path = roms/vbootrom
 	url = https://gitlab.com/qemu-project/vbootrom.git
 [submodule "tests/lcitool/libvirt-ci"]
 	path = tests/lcitool/libvirt-ci
 	url = https://gitlab.com/libvirt/libvirt-ci.git
+[submodule "subprojects/libvfio-user"]
+	path = subprojects/libvfio-user
+	url = https://gitlab.com/qemu-project/libvfio-user.git
--- a/.mailmap
+++ b/.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>
@@ -70,7 +54,6 @@ Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> <amarkovic@wavecomp.com>
 Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> <arikalo@wavecomp.com>
 Aleksandar Rikalo <aleksandar.rikalo@syrmia.com> <aleksandar.rikalo@rt-rk.com>
 Alexander Graf <agraf@csgraf.de> <agraf@suse.de>
-Ani Sinha <anisinha@redhat.com> <ani@anisinha.ca>
 Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
 Christian Borntraeger <borntraeger@linux.ibm.com> <borntraeger@de.ibm.com>
 Damien Hedde <damien.hedde@dahe.fr> <damien.hedde@greensocs.com>
@@ -83,9 +66,6 @@ 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>
@@ -95,9 +75,7 @@ Paul Burton <paulburton@kernel.org> <pburton@wavecomp.com>
 Philippe Mathieu-Daudé <philmd@linaro.org> <f4bug@amsat.org>
 Philippe Mathieu-Daudé <philmd@linaro.org> <philmd@redhat.com>
 Philippe Mathieu-Daudé <philmd@linaro.org> <philmd@fungible.com>
-Roman Bolshakov <rbolshakov@ddn.com> <r.bolshakov@yadro.com>
 Stefan Brankovic <stefan.brankovic@syrmia.com> <stefan.brankovic@rt-rk.com.com>
-Taylor Simpson <ltaylorsimpson@gmail.com> <tsimpson@quicinc.com>
 Yongbok Kim <yongbok.kim@mips.com> <yongbok.kim@imgtec.com>

 # Also list preferred name forms where people have changed their
--- a/.travis.yml
+++ b/.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:
@@ -237,15 +237,13 @@ jobs:
          - libglib2.0-dev
          - libgnutls28-dev
          - ninja-build
-          - flex
-          - bison
      env:
        - CONFIG="--disable-containers --disable-system"

    - name: "[s390x] Clang (disable-tcg)"
      arch: s390x
      dist: focal
-      compiler: clang-10
+      compiler: clang
      addons:
        apt_packages:
          - libaio-dev
@@ -271,7 +269,6 @@ jobs:
          - libvdeplug-dev
          - libvte-2.91-dev
          - ninja-build
-          - clang-10
      env:
        - TEST_CMD="make check-unit"
        - CONFIG="--disable-containers --disable-tcg --enable-kvm --disable-tools
--- a/Kconfig.host
+++ b/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
--- a/399
+++ b/399
--- a/80
+++ b/80
@@ -26,9 +26,9 @@ quiet-command-run = $(if $(V),,$(if $2,printf "  %-7s %s\n" $2 $3 && ))$1
 quiet-@ = $(if $(V),,@)
 quiet-command = $(quiet-@)$(call quiet-command-run,$1,$2,$3)

-UNCHECKED_GOALS := TAGS gtags cscope ctags dist \
+UNCHECKED_GOALS := %clean TAGS 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
@@ -45,6 +45,18 @@ include config-host.mak
 include Makefile.prereqs
 Makefile.prereqs: config-host.mak

+git-submodule-update:
+.git-submodule-status: git-submodule-update config-host.mak
+Makefile: .git-submodule-status
+
+.PHONY: git-submodule-update
+git-submodule-update:
+ifneq ($(GIT_SUBMODULES_ACTION),ignore)
+	$(call quiet-command, \
+		(GIT="$(GIT)" "$(SRC_PATH)/scripts/git-submodule.sh" $(GIT_SUBMODULES_ACTION) $(GIT_SUBMODULES)), \
+		"GIT","$(GIT_SUBMODULES)")
+endif
+
 # 0. ensure the build tree is okay

 # Check that we're not trying to do an out-of-tree build from
@@ -83,17 +95,16 @@ config-host.mak: $(SRC_PATH)/configure $(SRC_PATH)/scripts/meson-buildoptions.sh
 	@if test -f meson-private/coredata.dat; then \
 	  ./config.status --skip-meson; \
 	else \
-	  ./config.status; \
+	  ./config.status && touch build.ninja.stamp; \
 	fi

 # 2. meson.stamp exists if meson has run at least once (so ninja reconfigure
 # works), but otherwise never needs to be updated
-
 meson-private/coredata.dat: meson.stamp
 meson.stamp: config-host.mak
 	@touch meson.stamp

-# 3. ensure meson-generated build files are up-to-date
+# 3. ensure generated build files are up-to-date

 ifneq ($(NINJA),)
 Makefile.ninja: build.ninja
@@ -104,23 +115,15 @@ Makefile.ninja: build.ninja
 	  $(NINJA) -t query build.ninja | sed -n '1,/^  input:/d; /^  outputs:/q; s/$$/ \\/p'; \
 	} > $@.tmp && mv $@.tmp $@
 -include Makefile.ninja
-endif

-ifneq ($(MESON),)
-# The path to meson always points to pyvenv/bin/meson, but the absolute
-# paths could change.  In that case, force a regeneration of build.ninja.
-# Note that this invocation of $(NINJA), just like when Make rebuilds
-# Makefiles, does not include -n.
+# A separate rule is needed for Makefile dependencies to avoid -n
 build.ninja: build.ninja.stamp
 $(build-files):
 build.ninja.stamp: meson.stamp $(build-files)
-	@if test "$$(cat build.ninja.stamp)" = "$(MESON)" && test -n "$(NINJA)"; then \
-	  $(NINJA) build.ninja; \
-	else \
-	  echo "$(MESON) setup --reconfigure $(SRC_PATH)"; \
-	  $(MESON) setup --reconfigure $(SRC_PATH); \
-	fi && echo "$(MESON)" > $@
+	$(NINJA) $(if $V,-v,) build.ninja && touch $@
+endif

+ifneq ($(MESON),)
 Makefile.mtest: build.ninja scripts/mtest2make.py
 	$(MESON) introspect --targets --tests --benchmarks | $(PYTHON) scripts/mtest2make.py > $@
 -include Makefile.mtest
@@ -164,9 +167,19 @@ ifneq ($(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 # $(CONFIG_PLUGIN)
+
 else # config-host.mak does not exist
+config-host.mak:
 ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
-$(error Please call configure before running make)
+	@echo "Please call configure before running make!"
+	@exit 1
 endif
 endif # config-host.mak does not exist

@@ -176,20 +189,15 @@ 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 +291,6 @@ 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 +301,7 @@ 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 +311,6 @@ 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 +321,7 @@ 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)
--- a/2
+++ b/2
@@ -1 +1 @@
-8.1.50
+8.0.4
--- a/accel/Kconfig
+++ b/accel/Kconfig
@@ -4,6 +4,9 @@ config WHPX
 config NVMM
    bool

+config HAX
+    bool
+
 config HVF
    bool

--- a/accel/accel-common.c
+++ b/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();
--- a/accel/accel-softmmu.c
+++ b/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);
--- a/accel/accel-softmmu.h
+++ b/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 */
--- a/accel/dummy-cpus.c
+++ b/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
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -52,7 +52,6 @@
 #include "qemu/main-loop.h"
 #include "exec/address-spaces.h"
 #include "exec/exec-all.h"
-#include "exec/gdbstub.h"
 #include "sysemu/cpus.h"
 #include "sysemu/hvf.h"
 #include "sysemu/hvf_int.h"
@@ -304,7 +303,7 @@ static void hvf_region_del(MemoryListener *listener,

 static MemoryListener hvf_memory_listener = {
    .name = "hvf",
-    .priority = MEMORY_LISTENER_PRIORITY_ACCEL,
+    .priority = 10,
    .region_add = hvf_region_add,
    .region_del = hvf_region_del,
    .log_start = hvf_log_start,
@@ -335,26 +334,18 @@ static int hvf_accel_init(MachineState *ms)
        s->slots[x].slot_id = x;
    }

-    QTAILQ_INIT(&s->hvf_sw_breakpoints);
-
    hvf_state = s;
    memory_listener_register(&hvf_memory_listener, &address_space_memory);

    return hvf_arch_init();
 }

-static inline int hvf_gdbstub_sstep_flags(void)
-{
-    return SSTEP_ENABLE | SSTEP_NOIRQ;
-}
-
 static void hvf_accel_class_init(ObjectClass *oc, void *data)
 {
    AccelClass *ac = ACCEL_CLASS(oc);
    ac->name = "HVF";
    ac->init_machine = hvf_accel_init;
    ac->allowed = &hvf_allowed;
-    ac->gdbstub_supported_sstep_flags = hvf_gdbstub_sstep_flags;
 }

 static const TypeInfo hvf_accel_type = {
@@ -372,19 +363,19 @@ type_init(hvf_type_init);

 static void hvf_vcpu_destroy(CPUState *cpu)
 {
-    hv_return_t ret = hv_vcpu_destroy(cpu->accel->fd);
+    hv_return_t ret = hv_vcpu_destroy(cpu->hvf->fd);
    assert_hvf_ok(ret);

    hvf_arch_vcpu_destroy(cpu);
-    g_free(cpu->accel);
-    cpu->accel = NULL;
+    g_free(cpu->hvf);
+    cpu->hvf = NULL;
 }

 static int hvf_init_vcpu(CPUState *cpu)
 {
    int r;

-    cpu->accel = g_new0(AccelCPUState, 1);
+    cpu->hvf = g_malloc0(sizeof(*cpu->hvf));

    /* init cpu signals */
    struct sigaction sigact;
@@ -393,20 +384,17 @@ static int hvf_init_vcpu(CPUState *cpu)
    sigact.sa_handler = dummy_signal;
    sigaction(SIG_IPI, &sigact, NULL);

-    pthread_sigmask(SIG_BLOCK, NULL, &cpu->accel->unblock_ipi_mask);
-    sigdelset(&cpu->accel->unblock_ipi_mask, SIG_IPI);
+    pthread_sigmask(SIG_BLOCK, NULL, &cpu->hvf->unblock_ipi_mask);
+    sigdelset(&cpu->hvf->unblock_ipi_mask, SIG_IPI);

 #ifdef __aarch64__
-    r = hv_vcpu_create(&cpu->accel->fd,
-                       (hv_vcpu_exit_t **)&cpu->accel->exit, NULL);
+    r = hv_vcpu_create(&cpu->hvf->fd, (hv_vcpu_exit_t **)&cpu->hvf->exit, NULL);
 #else
-    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->accel->fd, HV_VCPU_DEFAULT);
+    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf->fd, HV_VCPU_DEFAULT);
 #endif
    cpu->vcpu_dirty = 1;
    assert_hvf_ok(r);

-    cpu->accel->guest_debug_enabled = false;
-
    return hvf_arch_init_vcpu(cpu);
 }

@@ -428,7 +416,7 @@ 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);
@@ -474,108 +462,6 @@ 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)
-{
-    struct hvf_sw_breakpoint *bp;
-    int err;
-
-    if (type == GDB_BREAKPOINT_SW) {
-        bp = hvf_find_sw_breakpoint(cpu, addr);
-        if (bp) {
-            bp->use_count++;
-            return 0;
-        }
-
-        bp = g_new(struct hvf_sw_breakpoint, 1);
-        bp->pc = addr;
-        bp->use_count = 1;
-        err = hvf_arch_insert_sw_breakpoint(cpu, bp);
-        if (err) {
-            g_free(bp);
-            return err;
-        }
-
-        QTAILQ_INSERT_HEAD(&hvf_state->hvf_sw_breakpoints, bp, entry);
-    } else {
-        err = hvf_arch_insert_hw_breakpoint(addr, len, type);
-        if (err) {
-            return err;
-        }
-    }
-
-    CPU_FOREACH(cpu) {
-        err = hvf_update_guest_debug(cpu);
-        if (err) {
-            return err;
-        }
-    }
-    return 0;
-}
-
-static int hvf_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len)
-{
-    struct hvf_sw_breakpoint *bp;
-    int err;
-
-    if (type == GDB_BREAKPOINT_SW) {
-        bp = hvf_find_sw_breakpoint(cpu, addr);
-        if (!bp) {
-            return -ENOENT;
-        }
-
-        if (bp->use_count > 1) {
-            bp->use_count--;
-            return 0;
-        }
-
-        err = hvf_arch_remove_sw_breakpoint(cpu, bp);
-        if (err) {
-            return err;
-        }
-
-        QTAILQ_REMOVE(&hvf_state->hvf_sw_breakpoints, bp, entry);
-        g_free(bp);
-    } else {
-        err = hvf_arch_remove_hw_breakpoint(addr, len, type);
-        if (err) {
-            return err;
-        }
-    }
-
-    CPU_FOREACH(cpu) {
-        err = hvf_update_guest_debug(cpu);
-        if (err) {
-            return err;
-        }
-    }
-    return 0;
-}
-
-static void hvf_remove_all_breakpoints(CPUState *cpu)
-{
-    struct hvf_sw_breakpoint *bp, *next;
-    CPUState *tmpcpu;
-
-    QTAILQ_FOREACH_SAFE(bp, &hvf_state->hvf_sw_breakpoints, entry, next) {
-        if (hvf_arch_remove_sw_breakpoint(cpu, bp) != 0) {
-            /* Try harder to find a CPU that currently sees the breakpoint. */
-            CPU_FOREACH(tmpcpu)
-            {
-                if (hvf_arch_remove_sw_breakpoint(tmpcpu, bp) == 0) {
-                    break;
-                }
-            }
-        }
-        QTAILQ_REMOVE(&hvf_state->hvf_sw_breakpoints, bp, entry);
-        g_free(bp);
-    }
-    hvf_arch_remove_all_hw_breakpoints();
-
-    CPU_FOREACH(cpu) {
-        hvf_update_guest_debug(cpu);
-    }
-}
-
 static void hvf_accel_ops_class_init(ObjectClass *oc, void *data)
 {
    AccelOpsClass *ops = ACCEL_OPS_CLASS(oc);
@@ -587,12 +473,6 @@ static void hvf_accel_ops_class_init(ObjectClass *oc, void *data)
    ops->synchronize_post_init = hvf_cpu_synchronize_post_init;
    ops->synchronize_state = hvf_cpu_synchronize_state;
    ops->synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm;
-
-    ops->insert_breakpoint = hvf_insert_breakpoint;
-    ops->remove_breakpoint = hvf_remove_breakpoint;
-    ops->remove_all_breakpoints = hvf_remove_all_breakpoints;
-    ops->update_guest_debug = hvf_update_guest_debug;
-    ops->supports_guest_debug = hvf_arch_supports_guest_debug;
 };
 static const TypeInfo hvf_accel_ops_type = {
    .name = ACCEL_OPS_NAME("hvf"),
--- a/accel/hvf/hvf-all.c
+++ b/accel/hvf/hvf-all.c
@@ -38,38 +38,9 @@ void assert_hvf_ok(hv_return_t ret)
    case HV_UNSUPPORTED:
        error_report("Error: HV_UNSUPPORTED");
        break;
-#if defined(MAC_OS_VERSION_11_0) && \
-    MAC_OS_X_VERSION_MIN_REQUIRED >= MAC_OS_VERSION_11_0
-    case HV_DENIED:
-        error_report("Error: HV_DENIED");
-        break;
-#endif
    default:
        error_report("Unknown Error");
    }

    abort();
 }
-
-struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, vaddr pc)
-{
-    struct hvf_sw_breakpoint *bp;
-
-    QTAILQ_FOREACH(bp, &hvf_state->hvf_sw_breakpoints, entry) {
-        if (bp->pc == pc) {
-            return bp;
-        }
-    }
-    return NULL;
-}
-
-int hvf_sw_breakpoints_active(CPUState *cpu)
-{
-    return !QTAILQ_EMPTY(&hvf_state->hvf_sw_breakpoints);
-}
-
-int hvf_update_guest_debug(CPUState *cpu)
-{
-    hvf_arch_update_guest_debug(cpu);
-    return 0;
-}
--- a/accel/kvm/kvm-accel-ops.c
+++ b/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);
--- a/accel/kvm/kvm-all.c
+++ b/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)
 {
@@ -454,8 +450,6 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
                         "kvm_init_vcpu: kvm_arch_init_vcpu failed (%lu)",
                         kvm_arch_vcpu_id(cpu));
    }
-    cpu->kvm_vcpu_stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
-
 err:
    return ret;
 }
@@ -1105,6 +1099,12 @@ 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,
+};
+
 int kvm_check_extension(KVMState *s, unsigned int extension)
 {
    int ret;
@@ -1246,6 +1246,43 @@ 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)
 {
@@ -1324,10 +1361,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
                 */
                if (kvm_state->kvm_dirty_ring_size) {
                    kvm_dirty_ring_reap_locked(kvm_state, NULL);
-                    if (kvm_state->kvm_dirty_ring_with_bitmap) {
-                        kvm_slot_sync_dirty_pages(mem);
-                        kvm_slot_get_dirty_log(kvm_state, mem);
-                    }
                } else {
                    kvm_slot_get_dirty_log(kvm_state, mem);
                }
@@ -1347,7 +1380,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
            }
            start_addr += slot_size;
            size -= slot_size;
-            kml->nr_used_slots--;
        } while (size);
        return;
    }
@@ -1373,7 +1405,6 @@ 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);
 }

@@ -1416,74 +1447,13 @@ 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);
-}
-
-static int kvm_dirty_ring_init(KVMState *s)
-{
-    uint32_t ring_size = s->kvm_dirty_ring_size;
-    uint64_t ring_bytes = ring_size * sizeof(struct kvm_dirty_gfn);
-    unsigned int capability = KVM_CAP_DIRTY_LOG_RING;
-    int ret;
-
-    s->kvm_dirty_ring_size = 0;
-    s->kvm_dirty_ring_bytes = 0;
-
-    /* Bail if the dirty ring size isn't specified */
-    if (!ring_size) {
-        return 0;
-    }
-
-    /*
-     * Read the max supported pages. Fall back to dirty logging mode
-     * if the dirty ring isn't supported.
-     */
-    ret = kvm_vm_check_extension(s, capability);
-    if (ret <= 0) {
-        capability = KVM_CAP_DIRTY_LOG_RING_ACQ_REL;
-        ret = kvm_vm_check_extension(s, capability);
-    }
-
-    if (ret <= 0) {
-        warn_report("KVM dirty ring not available, using bitmap method");
-        return 0;
-    }
-
-    if (ring_bytes > ret) {
-        error_report("KVM dirty ring size %" PRIu32 " too big "
-                     "(maximum is %ld).  Please use a smaller value.",
-                     ring_size, (long)ret / sizeof(struct kvm_dirty_gfn));
-        return -EINVAL;
-    }
-
-    ret = kvm_vm_enable_cap(s, capability, 0, ring_bytes);
-    if (ret) {
-        error_report("Enabling of KVM dirty ring failed: %s. "
-                     "Suggested minimum value is 1024.", strerror(-ret));
-        return -EIO;
-    }
-
-    /* Enable the backup bitmap if it is supported */
-    ret = kvm_vm_check_extension(s, KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP);
-    if (ret > 0) {
-        ret = kvm_vm_enable_cap(s, KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP, 0);
-        if (ret) {
-            error_report("Enabling of KVM dirty ring's backup bitmap failed: "
-                         "%s. ", strerror(-ret));
-            return -EIO;
-        }
-
-        s->kvm_dirty_ring_with_bitmap = true;
-    }
-
-    s->kvm_dirty_ring_size = ring_size;
-    s->kvm_dirty_ring_bytes = ring_bytes;

    return 0;
 }
@@ -1593,7 +1563,7 @@ static void kvm_log_sync(MemoryListener *listener,
    kvm_slots_unlock();
 }

-static void kvm_log_sync_global(MemoryListener *l, bool last_stage)
+static void kvm_log_sync_global(MemoryListener *l)
 {
    KVMMemoryListener *kml = container_of(l, KVMMemoryListener, listener);
    KVMState *s = kvm_state;
@@ -1612,12 +1582,6 @@ static void kvm_log_sync_global(MemoryListener *l, bool last_stage)
        mem = &kml->slots[i];
        if (mem->memory_size && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
            kvm_slot_sync_dirty_pages(mem);
-
-            if (s->kvm_dirty_ring_with_bitmap && last_stage &&
-                kvm_slot_get_dirty_log(s, mem)) {
-                kvm_slot_sync_dirty_pages(mem);
-            }
-
            /*
             * This is not needed by KVM_GET_DIRTY_LOG because the
             * ioctl will unconditionally overwrite the whole region.
@@ -1738,7 +1702,7 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
    kml->listener.commit = kvm_region_commit;
    kml->listener.log_start = kvm_log_start;
    kml->listener.log_stop = kvm_log_stop;
-    kml->listener.priority = MEMORY_LISTENER_PRIORITY_ACCEL;
+    kml->listener.priority = 10;
    kml->listener.name = name;

    if (s->kvm_dirty_ring_size) {
@@ -1761,11 +1725,9 @@ 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,
+    .priority = 10,
 };

 int kvm_set_irq(KVMState *s, int irq, int level)
@@ -1804,7 +1766,7 @@ 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 +1778,12 @@ 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 +1903,41 @@ 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 +1947,63 @@ 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 +2130,10 @@ 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 +2294,6 @@ 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 +2382,7 @@ 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 +2447,6 @@ 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 {
@@ -2484,9 +2521,35 @@ static int kvm_init(MachineState *ms)
     * Enable KVM dirty ring if supported, otherwise fall back to
     * dirty logging mode
     */
-    ret = kvm_dirty_ring_init(s);
-    if (ret < 0) {
-        goto err;
+    if (s->kvm_dirty_ring_size > 0) {
+        uint64_t ring_bytes;
+
+        ring_bytes = s->kvm_dirty_ring_size * sizeof(struct kvm_dirty_gfn);
+
+        /* Read the max supported pages */
+        ret = kvm_vm_check_extension(s, KVM_CAP_DIRTY_LOG_RING);
+        if (ret > 0) {
+            if (ring_bytes > ret) {
+                error_report("KVM dirty ring size %" PRIu32 " too big "
+                             "(maximum is %ld).  Please use a smaller value.",
+                             s->kvm_dirty_ring_size,
+                             (long)ret / sizeof(struct kvm_dirty_gfn));
+                ret = -EINVAL;
+                goto err;
+            }
+
+            ret = kvm_vm_enable_cap(s, KVM_CAP_DIRTY_LOG_RING, 0, ring_bytes);
+            if (ret) {
+                error_report("Enabling of KVM dirty ring failed: %s. "
+                             "Suggested minimum value is 1024.", strerror(-ret));
+                goto err;
+            }
+
+            s->kvm_dirty_ring_bytes = ring_bytes;
+         } else {
+             warn_report("KVM dirty ring not available, using bitmap method");
+             s->kvm_dirty_ring_size = 0;
+        }
    }

    /*
@@ -2524,8 +2587,22 @@ 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 +2611,21 @@ 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 +2662,24 @@ 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 +2687,10 @@ 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 +2708,6 @@ err:
    if (s->fd != -1) {
        close(s->fd);
    }
-    g_free(s->as);
    g_free(s->memory_listener.slots);

    return ret;
@@ -2638,14 +2734,16 @@ 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 +2762,7 @@ 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 +2798,7 @@ 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 +2812,7 @@ 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 +2823,7 @@ 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 +2916,7 @@ 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 +3213,29 @@ 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 +3245,19 @@ 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;

@@ -3612,8 +3710,6 @@ static void kvm_accel_instance_init(Object *obj)
    s->kernel_irqchip_split = ON_OFF_AUTO_AUTO;
    /* 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;
@@ -3863,7 +3959,7 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd

    /* Read stats header */
    kvm_stats_header = &descriptors->kvm_stats_header;
-    ret = pread(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header), 0);
+    ret = read(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header));
    if (ret != sizeof(*kvm_stats_header)) {
        error_setg(errp, "KVM stats: failed to read stats header: "
                   "expected %zu actual %zu",
@@ -3894,8 +3990,7 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
 }

 static void query_stats(StatsResultList **result, StatsTarget target,
-                        strList *names, int stats_fd, CPUState *cpu,
-                        Error **errp)
+                        strList *names, int stats_fd, Error **errp)
 {
    struct kvm_stats_desc *kvm_stats_desc;
    struct kvm_stats_header *kvm_stats_header;
@@ -3953,7 +4048,7 @@ static void query_stats(StatsResultList **result, StatsTarget target,
        break;
    case STATS_TARGET_VCPU:
        add_stats_entry(result, STATS_PROVIDER_KVM,
-                        cpu->parent_obj.canonical_path,
+                        current_cpu->parent_obj.canonical_path,
                        stats_list);
        break;
    default:
@@ -3990,9 +4085,10 @@ static void query_stats_schema(StatsSchemaList **result, StatsTarget target,
    add_stats_schema(result, STATS_PROVIDER_KVM, target, stats_list);
 }

-static void query_stats_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
+static void query_stats_vcpu(CPUState *cpu, run_on_cpu_data data)
 {
-    int stats_fd = cpu->kvm_vcpu_stats_fd;
+    StatsArgs *kvm_stats_args = (StatsArgs *) data.host_ptr;
+    int stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
    Error *local_err = NULL;

    if (stats_fd == -1) {
@@ -4001,13 +4097,14 @@ static void query_stats_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
        return;
    }
    query_stats(kvm_stats_args->result.stats, STATS_TARGET_VCPU,
-                kvm_stats_args->names, stats_fd, cpu,
-                kvm_stats_args->errp);
+                kvm_stats_args->names, stats_fd, kvm_stats_args->errp);
+    close(stats_fd);
 }

-static void query_stats_schema_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
+static void query_stats_schema_vcpu(CPUState *cpu, run_on_cpu_data data)
 {
-    int stats_fd = cpu->kvm_vcpu_stats_fd;
+    StatsArgs *kvm_stats_args = (StatsArgs *) data.host_ptr;
+    int stats_fd = kvm_vcpu_ioctl(cpu, KVM_GET_STATS_FD, NULL);
    Error *local_err = NULL;

    if (stats_fd == -1) {
@@ -4017,6 +4114,7 @@ static void query_stats_schema_vcpu(CPUState *cpu, StatsArgs *kvm_stats_args)
    }
    query_stats_schema(kvm_stats_args->result.schema, STATS_TARGET_VCPU, stats_fd,
                       kvm_stats_args->errp);
+    close(stats_fd);
 }

 static void query_stats_cb(StatsResultList **result, StatsTarget target,
@@ -4034,7 +4132,7 @@ static void query_stats_cb(StatsResultList **result, StatsTarget target,
            error_setg_errno(errp, errno, "KVM stats: ioctl failed");
            return;
        }
-        query_stats(result, target, names, stats_fd, NULL, errp);
+        query_stats(result, target, names, stats_fd, errp);
        close(stats_fd);
        break;
    }
@@ -4048,7 +4146,7 @@ static void query_stats_cb(StatsResultList **result, StatsTarget target,
            if (!apply_str_list_filter(cpu->parent_obj.canonical_path, targets)) {
                continue;
            }
-            query_stats_vcpu(cpu, &stats_args);
+            run_on_cpu(cpu, query_stats_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
        }
        break;
    }
@@ -4074,6 +4172,6 @@ void query_stats_schemas_cb(StatsSchemaList **result, Error **errp)
    if (first_cpu) {
        stats_args.result.schema = result;
        stats_args.errp = errp;
-        query_stats_schema_vcpu(first_cpu, &stats_args);
+        run_on_cpu(first_cpu, query_stats_schema_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
    }
 }
--- a/accel/meson.build
+++ b/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'))
+softmmu_ss.add(files('accel-softmmu.c'))
 user_ss.add(files('accel-user.c'))

 subdir('tcg')
@@ -12,4 +12,4 @@ if have_system
 endif

 # qtest
-system_ss.add(files('dummy-cpus.c'))
+softmmu_ss.add(files('dummy-cpus.c'))
--- a/accel/qtest/meson.build
+++ b/accel/qtest/meson.build
@@ -1 +1 @@
-qtest_module_ss.add(when: ['CONFIG_SYSTEM_ONLY'], if_true: files('qtest.c'))
+qtest_module_ss.add(when: ['CONFIG_SOFTMMU'], if_true: files('qtest.c'))
--- a/accel/stubs/hax-stub.c
+++ b/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;
+}
--- a/accel/stubs/kvm-stub.c
+++ b/accel/stubs/kvm-stub.c
@@ -17,12 +17,15 @@
 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;

 void kvm_flush_coalesced_mmio_buffer(void)
@@ -38,6 +41,11 @@ 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 +91,11 @@ 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 +108,9 @@ 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)
--- a/accel/stubs/meson.build
+++ b/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_SOFTMMU'], if_true: sysemu_stubs_ss)
--- a/accel/stubs/tcg-stub.c
+++ b/accel/stubs/tcg-stub.c
@@ -18,18 +18,22 @@ void tb_flush(CPUState *cpu)
 {
 }

-void tlb_set_dirty(CPUState *cpu, vaddr vaddr)
+void tlb_set_dirty(CPUState *cpu, target_ulong vaddr)
 {
 }

-int probe_access_flags(CPUArchState *env, vaddr addr, int size,
+void tcg_flush_jmp_cache(CPUState *cpu)
+{
+}
+
+int probe_access_flags(CPUArchState *env, target_ulong addr, int size,
                       MMUAccessType access_type, int mmu_idx,
                       bool nonfault, void **phost, uintptr_t retaddr)
 {
     g_assert_not_reached();
 }

-void *probe_access(CPUArchState *env, vaddr addr, int size,
+void *probe_access(CPUArchState *env, target_ulong addr, int size,
                   MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
 {
     /* Handled by hardware accelerator. */
--- a/accel/tcg/atomic_common.c.inc
+++ b/accel/tcg/atomic_common.c.inc
@@ -13,12 +13,26 @@
 * See the COPYING file in the top-level directory.
 */

-static void atomic_trace_rmw_post(CPUArchState *env, uint64_t addr,
+static void atomic_trace_rmw_post(CPUArchState *env, target_ulong addr,
                                  MemOpIdx oi)
 {
    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_RW);
 }

+#if HAVE_ATOMIC128
+static void atomic_trace_ld_post(CPUArchState *env, target_ulong addr,
+                                 MemOpIdx oi)
+{
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+}
+
+static void atomic_trace_st_post(CPUArchState *env, target_ulong addr,
+                                 MemOpIdx oi)
+{
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+#endif
+
 /*
 * Atomic helpers callable from TCG.
 * These have a common interface and all defer to cpu_atomic_*
@@ -26,7 +40,7 @@ static void atomic_trace_rmw_post(CPUArchState *env, uint64_t addr,
 */

 #define CMPXCHG_HELPER(OP, TYPE) \
-    TYPE HELPER(atomic_##OP)(CPUArchState *env, uint64_t addr,      \
+    TYPE HELPER(atomic_##OP)(CPUArchState *env, target_ulong addr,  \
                             TYPE oldv, TYPE newv, uint32_t oi)     \
    { return cpu_atomic_##OP##_mmu(env, addr, oldv, newv, oi, GETPC()); }

@@ -41,23 +55,43 @@ 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

 #undef CMPXCHG_HELPER

-Int128 HELPER(nonatomic_cmpxchgo)(CPUArchState *env, uint64_t addr,
-                                  Int128 cmpv, Int128 newv, uint32_t oi)
+Int128 HELPER(nonatomic_cmpxchgo_be)(CPUArchState *env, target_ulong addr,
+                                     Int128 cmpv, Int128 newv, uint32_t oi)
 {
 #if TCG_TARGET_REG_BITS == 32
    uintptr_t ra = GETPC();
    Int128 oldv;

-    oldv = cpu_ld16_mmu(env, addr, oi, ra);
+    oldv = cpu_ld16_be_mmu(env, addr, oi, ra);
    if (int128_eq(oldv, cmpv)) {
-        cpu_st16_mmu(env, addr, newv, oi, ra);
+        cpu_st16_be_mmu(env, addr, newv, oi, ra);
+    } else {
+        /* Even with comparison failure, still need a write cycle. */
+        probe_write(env, addr, 16, get_mmuidx(oi), ra);
+    }
+    return oldv;
+#else
+    g_assert_not_reached();
+#endif
+}
+
+Int128 HELPER(nonatomic_cmpxchgo_le)(CPUArchState *env, target_ulong addr,
+                                     Int128 cmpv, Int128 newv, uint32_t oi)
+{
+#if TCG_TARGET_REG_BITS == 32
+    uintptr_t ra = GETPC();
+    Int128 oldv;
+
+    oldv = cpu_ld16_le_mmu(env, addr, oi, ra);
+    if (int128_eq(oldv, cmpv)) {
+        cpu_st16_le_mmu(env, addr, newv, oi, ra);
    } else {
        /* Even with comparison failure, still need a write cycle. */
        probe_write(env, addr, 16, get_mmuidx(oi), ra);
@@ -69,7 +103,7 @@ Int128 HELPER(nonatomic_cmpxchgo)(CPUArchState *env, uint64_t addr,
 }

 #define ATOMIC_HELPER(OP, TYPE) \
-    TYPE HELPER(glue(atomic_,OP))(CPUArchState *env, uint64_t addr,  \
+    TYPE HELPER(glue(atomic_,OP))(CPUArchState *env, target_ulong addr,  \
                                  TYPE val, uint32_t oi)                 \
    { return glue(glue(cpu_atomic_,OP),_mmu)(env, addr, val, oi, GETPC()); }

--- a/accel/tcg/atomic_template.h
+++ b/accel/tcg/atomic_template.h
@@ -69,12 +69,12 @@
 # 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,
+                                         PAGE_READ | PAGE_WRITE, retaddr);
    DATA_TYPE ret;

 #if DATA_SIZE == 16
@@ -87,12 +87,38 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
    return ret;
 }

-#if DATA_SIZE < 16
-ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
+#if DATA_SIZE >= 16
+#if HAVE_ATOMIC128
+ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr,
+                         MemOpIdx oi, uintptr_t retaddr)
+{
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE,
+                                         PAGE_READ, retaddr);
+    DATA_TYPE val;
+
+    val = atomic16_read(haddr);
+    ATOMIC_MMU_CLEANUP;
+    atomic_trace_ld_post(env, addr, oi);
+    return val;
+}
+
+void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val,
+                     MemOpIdx oi, uintptr_t retaddr)
+{
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE,
+                                         PAGE_WRITE, retaddr);
+
+    atomic16_set(haddr, val);
+    ATOMIC_MMU_CLEANUP;
+    atomic_trace_st_post(env, addr, oi);
+}
+#endif
+#else
+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,
+                                         PAGE_READ | PAGE_WRITE, retaddr);
    DATA_TYPE ret;

    ret = qatomic_xchg__nocheck(haddr, val);
@@ -102,11 +128,12 @@ 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);   \
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE,  \
+                                         PAGE_READ | PAGE_WRITE, retaddr); \
+    DATA_TYPE ret;                                                  \
    ret = qatomic_##X(haddr, val);                                  \
    ATOMIC_MMU_CLEANUP;                                             \
    atomic_trace_rmw_post(env, addr, oi);                           \
@@ -133,11 +160,12 @@ 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);   \
+    XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \
+                                          PAGE_READ | PAGE_WRITE, retaddr); \
+    XDATA_TYPE cmp, old, new, val = xval;                           \
    smp_mb();                                                       \
    cmp = qatomic_read__nocheck(haddr);                             \
    do {                                                            \
@@ -160,7 +188,7 @@ GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new)
 GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)

 #undef GEN_ATOMIC_HELPER_FN
-#endif /* DATA SIZE < 16 */
+#endif /* DATA SIZE >= 16 */

 #undef END

@@ -174,12 +202,12 @@ 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,
+                                         PAGE_READ | PAGE_WRITE, retaddr);
    DATA_TYPE ret;

 #if DATA_SIZE == 16
@@ -192,12 +220,39 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
    return BSWAP(ret);
 }

-#if DATA_SIZE < 16
-ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
+#if DATA_SIZE >= 16
+#if HAVE_ATOMIC128
+ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr,
+                         MemOpIdx oi, uintptr_t retaddr)
+{
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE,
+                                         PAGE_READ, retaddr);
+    DATA_TYPE val;
+
+    val = atomic16_read(haddr);
+    ATOMIC_MMU_CLEANUP;
+    atomic_trace_ld_post(env, addr, oi);
+    return BSWAP(val);
+}
+
+void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val,
+                     MemOpIdx oi, uintptr_t retaddr)
+{
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE,
+                                         PAGE_WRITE, retaddr);
+
+    val = BSWAP(val);
+    atomic16_set(haddr, val);
+    ATOMIC_MMU_CLEANUP;
+    atomic_trace_st_post(env, addr, oi);
+}
+#endif
+#else
+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,
+                                         PAGE_READ | PAGE_WRITE, retaddr);
    ABI_TYPE ret;

    ret = qatomic_xchg__nocheck(haddr, BSWAP(val));
@@ -207,11 +262,12 @@ 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);   \
+    DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE,  \
+                                         PAGE_READ | PAGE_WRITE, retaddr); \
+    DATA_TYPE ret;                                                  \
    ret = qatomic_##X(haddr, BSWAP(val));                           \
    ATOMIC_MMU_CLEANUP;                                             \
    atomic_trace_rmw_post(env, addr, oi);                           \
@@ -235,11 +291,12 @@ 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);   \
+    XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \
+                                          PAGE_READ | PAGE_WRITE, retaddr); \
+    XDATA_TYPE ldo, ldn, old, new, val = xval;                      \
    smp_mb();                                                       \
    ldn = qatomic_read__nocheck(haddr);                             \
    do {                                                            \
@@ -269,7 +326,7 @@ GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new)
 #undef ADD

 #undef GEN_ATOMIC_HELPER_FN
-#endif /* DATA_SIZE < 16 */
+#endif /* DATA_SIZE >= 16 */

 #undef END
 #endif /* DATA_SIZE > 1 */
--- a/accel/tcg/cpu-exec-common.c
+++ b/accel/tcg/cpu-exec-common.c
@@ -20,8 +20,8 @@
 #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"

 bool tcg_allowed;

@@ -32,10 +32,40 @@ 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);
@@ -51,8 +81,6 @@ void cpu_loop_exit_restore(CPUState *cpu, uintptr_t pc)

 void cpu_loop_exit_atomic(CPUState *cpu, uintptr_t pc)
 {
-    /* Prevent looping if already executing in a serial context. */
-    g_assert(!cpu_in_serial_context(cpu));
    cpu->exception_index = EXCP_ATOMIC;
    cpu_loop_exit_restore(cpu, pc);
 }
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -38,12 +38,11 @@
 #include "sysemu/cpu-timers.h"
 #include "exec/replay-core.h"
 #include "sysemu/tcg.h"
-#include "exec/helper-proto-common.h"
+#include "exec/helper-proto.h"
 #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;
    }
@@ -160,7 +159,7 @@ uint32_t curr_cflags(CPUState *cpu)
     */
    if (unlikely(cpu->singlestep_enabled)) {
        cflags |= CF_NO_GOTO_TB | CF_NO_GOTO_PTR | CF_SINGLE_STEP | 1;
-    } else if (qatomic_read(&one_insn_per_tb)) {
+    } else if (singlestep) {
        cflags |= CF_NO_GOTO_TB | 1;
    } else if (qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
        cflags |= CF_NO_GOTO_TB;
@@ -170,12 +169,13 @@ uint32_t curr_cflags(CPUState *cpu)
 }

 struct tb_desc {
-    vaddr pc;
-    uint64_t cs_base;
+    target_ulong pc;
+    target_ulong cs_base;
    CPUArchState *env;
    tb_page_addr_t page_addr0;
    uint32_t flags;
    uint32_t cflags;
+    uint32_t trace_vcpu_dstate;
 };

 static bool tb_lookup_cmp(const void *p, const void *d)
@@ -187,6 +187,7 @@ static bool tb_lookup_cmp(const void *p, const void *d)
        tb_page_addr0(tb) == desc->page_addr0 &&
        tb->cs_base == desc->cs_base &&
        tb->flags == desc->flags &&
+        tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
        tb_cflags(tb) == desc->cflags) {
        /* check next page if needed */
        tb_page_addr_t tb_phys_page1 = tb_page_addr1(tb);
@@ -194,7 +195,7 @@ static bool tb_lookup_cmp(const void *p, const void *d)
            return true;
        } else {
            tb_page_addr_t phys_page1;
-            vaddr virt_page1;
+            target_ulong virt_page1;

            /*
             * We know that the first page matched, and an otherwise valid TB
@@ -215,18 +216,19 @@ static bool tb_lookup_cmp(const void *p, const void *d)
    return false;
 }

-static TranslationBlock *tb_htable_lookup(CPUState *cpu, vaddr pc,
-                                          uint64_t cs_base, uint32_t flags,
+static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
+                                          target_ulong cs_base, uint32_t flags,
                                          uint32_t cflags)
 {
    tb_page_addr_t phys_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;
+    desc.trace_vcpu_dstate = *cpu->trace_dstate;
    desc.pc = pc;
    phys_pc = get_page_addr_code(desc.env, pc);
    if (phys_pc == -1) {
@@ -234,14 +236,14 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, vaddr pc,
    }
    desc.page_addr0 = phys_pc;
    h = tb_hash_func(phys_pc, (cflags & CF_PCREL ? 0 : pc),
-                     flags, cs_base, cflags);
+                     flags, cflags, *cpu->trace_dstate);
    return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
 }

 /* Might cause an exception, so have a longjmp destination ready */
-static inline TranslationBlock *tb_lookup(CPUState *cpu, vaddr pc,
-                                          uint64_t cs_base, uint32_t flags,
-                                          uint32_t cflags)
+static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc,
+                                          target_ulong cs_base,
+                                          uint32_t flags, uint32_t cflags)
 {
    TranslationBlock *tb;
    CPUJumpCache *jc;
@@ -261,6 +263,7 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, vaddr pc,
                   jc->array[hash].pc == pc &&
                   tb->cs_base == cs_base &&
                   tb->flags == flags &&
+                   tb->trace_vcpu_dstate == *cpu->trace_dstate &&
                   tb_cflags(tb) == cflags)) {
            return tb;
        }
@@ -279,6 +282,7 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, vaddr pc,
                   tb->pc == pc &&
                   tb->cs_base == cs_base &&
                   tb->flags == flags &&
+                   tb->trace_vcpu_dstate == *cpu->trace_dstate &&
                   tb_cflags(tb) == cflags)) {
            return tb;
        }
@@ -293,16 +297,17 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, vaddr pc,
    return tb;
 }

-static void log_cpu_exec(vaddr pc, CPUState *cpu,
+static void log_cpu_exec(target_ulong pc, CPUState *cpu,
                         const TranslationBlock *tb)
 {
    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",
+                      "Trace %d: %p [" TARGET_FMT_lx
+                      "/" TARGET_FMT_lx "/%08x/%08x] %s\n",
                      cpu->cpu_index, tb->tc.ptr, tb->cs_base, pc,
                      tb->flags, tb->cflags, lookup_symbol(pc));

+#if defined(DEBUG_DISAS)
        if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
            FILE *logfile = qemu_log_trylock();
            if (logfile) {
@@ -314,17 +319,15 @@ static void log_cpu_exec(vaddr pc, CPUState *cpu,
 #if defined(TARGET_I386)
                flags |= CPU_DUMP_CCOP;
 #endif
-                if (qemu_loglevel_mask(CPU_LOG_TB_VPU)) {
-                    flags |= CPU_DUMP_VPU;
-                }
                cpu_dump_state(cpu, logfile, flags);
                qemu_log_unlock(logfile);
            }
        }
+#endif /* DEBUG_DISAS */
    }
 }

-static bool check_for_breakpoints_slow(CPUState *cpu, vaddr pc,
+static bool check_for_breakpoints_slow(CPUState *cpu, target_ulong pc,
                                       uint32_t *cflags)
 {
    CPUBreakpoint *bp;
@@ -390,7 +393,7 @@ static bool check_for_breakpoints_slow(CPUState *cpu, vaddr pc,
    return false;
 }

-static inline bool check_for_breakpoints(CPUState *cpu, vaddr pc,
+static inline bool check_for_breakpoints(CPUState *cpu, target_ulong pc,
                                         uint32_t *cflags)
 {
    return unlikely(!QTAILQ_EMPTY(&cpu->breakpoints)) &&
@@ -409,8 +412,7 @@ const void *HELPER(lookup_tb_ptr)(CPUArchState *env)
 {
    CPUState *cpu = env_cpu(env);
    TranslationBlock *tb;
-    vaddr pc;
-    uint64_t cs_base;
+    target_ulong cs_base, pc;
    uint32_t flags, cflags;

    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
@@ -445,7 +447,7 @@ 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 +458,7 @@ 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
@@ -486,10 +488,10 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
            cc->set_pc(cpu, last_tb->pc);
        }
        if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
-            vaddr pc = log_pc(cpu, last_tb);
+            target_ulong pc = log_pc(cpu, last_tb);
            if (qemu_log_in_addr_range(pc)) {
-                qemu_log("Stopped execution of TB chain before %p [%016"
-                         VADDR_PRIx "] %s\n",
+                qemu_log("Stopped execution of TB chain before %p ["
+                         TARGET_FMT_lx "] %s\n",
                         last_tb->tc.ptr, pc, lookup_symbol(pc));
            }
        }
@@ -527,49 +529,11 @@ 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;
+    target_ulong cs_base, pc;
    uint32_t flags, cflags;
    int tb_exit;

@@ -606,7 +570,16 @@ void cpu_exec_step_atomic(CPUState *cpu)
        cpu_tb_exec(cpu, tb, &tb_exit);
        cpu_exec_exit(cpu);
    } else {
-        cpu_exec_longjmp_cleanup(cpu);
+#ifndef CONFIG_SOFTMMU
+        clear_helper_retaddr();
+        if (have_mmap_lock()) {
+            mmap_unlock();
+        }
+#endif
+        if (qemu_mutex_iothread_locked()) {
+            qemu_mutex_unlock_iothread();
+        }
+        assert_no_pages_locked();
    }

    /*
@@ -718,10 +691,10 @@ 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_LAST_IO | CF_NOIRQ | 1;
+                | CF_NOIRQ | 1;
        }
 #endif
        return false;
@@ -808,7 +781,7 @@ 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_mb_set(&cpu_neg(cpu)->icount_decr.u16.high, 0);

    if (unlikely(qatomic_read(&cpu->interrupt_request))) {
        int interrupt_request;
@@ -899,7 +872,7 @@ 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;
@@ -911,8 +884,8 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
 }

 static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
-                                    vaddr pc, TranslationBlock **last_tb,
-                                    int *tb_exit)
+                                    target_ulong pc,
+                                    TranslationBlock **last_tb, int *tb_exit)
 {
    int32_t insns_left;

@@ -924,7 +897,7 @@ 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 +916,7 @@ 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;

    /*
@@ -973,11 +946,10 @@ cpu_exec_loop(CPUState *cpu, SyncClocks *sc)

        while (!cpu_handle_interrupt(cpu, &last_tb)) {
            TranslationBlock *tb;
-            vaddr pc;
-            uint64_t cs_base;
+            target_ulong cs_base, pc;
            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 +1024,20 @@ 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);
+
+#ifndef CONFIG_SOFTMMU
+        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 +1074,7 @@ 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 +1090,6 @@ 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 */
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
--- a/accel/tcg/internal-common.h
+++ b/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
--- a/accel/tcg/internal-target.h
+++ b/accel/tcg/internal-target.h
@@ -1,132 +0,0 @@
-/*
- * Internal execution defines for qemu (target specific)
- *
- *  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
-
-#include "exec/exec-all.h"
-#include "exec/translate-all.h"
-
-/*
- * Access to the various translations structures need to be serialised
- * via locks for consistency.  In user-mode emulation access to the
- * memory related structures are protected with mmap_lock.
- * In !user-mode we use per-page locks.
- */
-#ifdef CONFIG_USER_ONLY
-#define assert_memory_lock() tcg_debug_assert(have_mmap_lock())
-#else
-#define assert_memory_lock()
-#endif
-
-#if defined(CONFIG_SOFTMMU) && defined(CONFIG_DEBUG_TCG)
-void assert_no_pages_locked(void);
-#else
-static inline void assert_no_pages_locked(void) { }
-#endif
-
-#ifdef CONFIG_USER_ONLY
-static inline void page_table_config_init(void) { }
-#else
-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,
-                                   uintptr_t retaddr);
-G_NORETURN void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr);
-#endif /* CONFIG_SOFTMMU */
-
-TranslationBlock *tb_gen_code(CPUState *cpu, vaddr pc,
-                              uint64_t cs_base, uint32_t flags,
-                              int cflags);
-void page_init(void);
-void tb_htable_init(void);
-void tb_reset_jump(TranslationBlock *tb, int n);
-TranslationBlock *tb_link_page(TranslationBlock *tb);
-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)
-{
-    if (tb_cflags(tb) & CF_PCREL) {
-        return cpu->cc->get_pc(cpu);
-    } else {
-        return tb->pc;
-    }
-}
-
-extern bool one_insn_per_tb;
-
-/**
- * tcg_req_mo:
- * @type: TCGBar
- *
- * Filter @type to the barrier that is required for the guest
- * memory ordering vs the host memory ordering.  A non-zero
- * result indicates that some barrier is required.
- *
- * If TCG_GUEST_DEFAULT_MO is not defined, assume that the
- * guest requires strict ordering.
- *
- * This is a macro so that it's constant even without optimization.
- */
-#ifdef TCG_GUEST_DEFAULT_MO
-# define tcg_req_mo(type) \
-    ((type) & TCG_GUEST_DEFAULT_MO & ~TCG_TARGET_DEFAULT_MO)
-#else
-# define tcg_req_mo(type) ((type) & ~TCG_TARGET_DEFAULT_MO)
-#endif
-
-/**
- * cpu_req_mo:
- * @type: TCGBar
- *
- * If tcg_req_mo indicates a barrier for @type is required
- * for the guest memory model, issue a host memory barrier.
- */
-#define cpu_req_mo(type)          \
-    do {                          \
-        if (tcg_req_mo(type)) {   \
-            smp_mb();             \
-        }                         \
-    } while (0)
-
-#endif /* ACCEL_TCG_INTERNAL_H */
--- a/accel/tcg/internal.h
+++ b/accel/tcg/internal.h
@@ -0,0 +1,70 @@
+/*
+ * Internal execution defines for qemu
+ *
+ *  Copyright (c) 2003 Fabrice Bellard
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+
+#ifndef ACCEL_TCG_INTERNAL_H
+#define ACCEL_TCG_INTERNAL_H
+
+#include "exec/exec-all.h"
+
+/*
+ * Access to the various translations structures need to be serialised
+ * via locks for consistency.  In user-mode emulation access to the
+ * memory related structures are protected with mmap_lock.
+ * In !user-mode we use per-page locks.
+ */
+#ifdef CONFIG_SOFTMMU
+#define assert_memory_lock()
+#else
+#define assert_memory_lock() tcg_debug_assert(have_mmap_lock())
+#endif
+
+#if defined(CONFIG_SOFTMMU) && defined(CONFIG_DEBUG_TCG)
+void assert_no_pages_locked(void);
+#else
+static inline void assert_no_pages_locked(void) { }
+#endif
+
+#ifdef CONFIG_USER_ONLY
+static inline void page_table_config_init(void) { }
+#else
+void page_table_config_init(void);
+#endif
+
+#ifdef CONFIG_SOFTMMU
+void tb_invalidate_phys_range_fast(ram_addr_t ram_addr,
+                                   unsigned size,
+                                   uintptr_t retaddr);
+G_NORETURN void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr);
+#endif /* CONFIG_SOFTMMU */
+
+TranslationBlock *tb_gen_code(CPUState *cpu, target_ulong pc,
+                              target_ulong cs_base, uint32_t flags,
+                              int cflags);
+void page_init(void);
+void tb_htable_init(void);
+void tb_reset_jump(TranslationBlock *tb, int n);
+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);
+
+/* Return the current PC from CPU, which may be cached in TB. */
+static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb)
+{
+    if (tb_cflags(tb) & CF_PCREL) {
+        return cpu->cc->get_pc(cpu);
+    } else {
+        return tb->pc;
+    }
+}
+
+extern int64_t max_delay;
+extern int64_t max_advance;
+
+#endif /* ACCEL_TCG_INTERNAL_H */
--- a/accel/tcg/ldst_atomicity.c.inc
+++ b/accel/tcg/ldst_atomicity.c.inc
--- a/accel/tcg/ldst_common.c.inc
+++ b/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)
@@ -251,7 +26,7 @@ uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                               int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_BEUW | MO_UNALN, mmu_idx);
-    return cpu_ldw_mmu(env, addr, oi, ra);
+    return cpu_ldw_be_mmu(env, addr, oi, ra);
 }

 int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
@@ -264,21 +39,21 @@ uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                              int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_BEUL | MO_UNALN, mmu_idx);
-    return cpu_ldl_mmu(env, addr, oi, ra);
+    return cpu_ldl_be_mmu(env, addr, oi, ra);
 }

 uint64_t cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                              int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_BEUQ | MO_UNALN, mmu_idx);
-    return cpu_ldq_mmu(env, addr, oi, ra);
+    return cpu_ldq_be_mmu(env, addr, oi, ra);
 }

 uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                               int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_LEUW | MO_UNALN, mmu_idx);
-    return cpu_ldw_mmu(env, addr, oi, ra);
+    return cpu_ldw_le_mmu(env, addr, oi, ra);
 }

 int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
@@ -291,14 +66,14 @@ uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                              int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_LEUL | MO_UNALN, mmu_idx);
-    return cpu_ldl_mmu(env, addr, oi, ra);
+    return cpu_ldl_le_mmu(env, addr, oi, ra);
 }

 uint64_t cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                              int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_LEUQ | MO_UNALN, mmu_idx);
-    return cpu_ldq_mmu(env, addr, oi, ra);
+    return cpu_ldq_le_mmu(env, addr, oi, ra);
 }

 void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
@@ -312,42 +87,42 @@ void cpu_stw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
                          int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_BEUW | MO_UNALN, mmu_idx);
-    cpu_stw_mmu(env, addr, val, oi, ra);
+    cpu_stw_be_mmu(env, addr, val, oi, ra);
 }

 void cpu_stl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
                          int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_BEUL | MO_UNALN, mmu_idx);
-    cpu_stl_mmu(env, addr, val, oi, ra);
+    cpu_stl_be_mmu(env, addr, val, oi, ra);
 }

 void cpu_stq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val,
                          int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_BEUQ | MO_UNALN, mmu_idx);
-    cpu_stq_mmu(env, addr, val, oi, ra);
+    cpu_stq_be_mmu(env, addr, val, oi, ra);
 }

 void cpu_stw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
                          int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_LEUW | MO_UNALN, mmu_idx);
-    cpu_stw_mmu(env, addr, val, oi, ra);
+    cpu_stw_le_mmu(env, addr, val, oi, ra);
 }

 void cpu_stl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
                          int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_LEUL | MO_UNALN, mmu_idx);
-    cpu_stl_mmu(env, addr, val, oi, ra);
+    cpu_stl_le_mmu(env, addr, val, oi, ra);
 }

 void cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val,
                          int mmu_idx, uintptr_t ra)
 {
    MemOpIdx oi = make_memop_idx(MO_LEUQ | MO_UNALN, mmu_idx);
-    cpu_stq_mmu(env, addr, val, oi, ra);
+    cpu_stq_le_mmu(env, addr, val, oi, ra);
 }

 /*--------------------------*/
--- a/accel/tcg/meson.build
+++ b/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',
@@ -12,24 +10,18 @@ tcg_ss.add(files(
  'translator.c',
 ))
 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_SOFTMMU', if_false: files('user-exec-stub.c'))
+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(
+specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files(
  'cputlb.c',
-))
-
-system_ss.add(when: ['CONFIG_TCG'], if_true: files(
-  'icount-common.c',
  'monitor.c',
 ))

-tcg_module_ss.add(when: ['CONFIG_SYSTEM_ONLY', 'CONFIG_TCG'], if_true: files(
+tcg_module_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files(
  'tcg-accel-ops.c',
  'tcg-accel-ops-mttcg.c',
  'tcg-accel-ops-icount.c',
--- a/accel/tcg/monitor.c
+++ b/accel/tcg/monitor.c
@@ -7,8 +7,6 @@
 */

 #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"
@@ -16,9 +14,7 @@
 #include "sysemu/cpus.h"
 #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)
@@ -40,165 +36,6 @@ static void dump_drift_info(GString *buf)
    }
 }

-static void dump_accel_info(GString *buf)
-{
-    AccelState *accel = current_accel();
-    bool one_insn_per_tb = object_property_get_bool(OBJECT(accel),
-                                                    "one-insn-per-tb",
-                                                    &error_fatal);
-
-    g_string_append_printf(buf, "Accelerator settings:\n");
-    g_string_append_printf(buf, "one-insn-per-tb: %s\n\n",
-                           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("");
@@ -208,18 +45,12 @@ HumanReadableText *qmp_x_query_jit(Error **errp)
        return NULL;
    }

-    dump_accel_info(buf);
    dump_exec_info(buf);
    dump_drift_info(buf);

    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("");
@@ -235,6 +66,37 @@ HumanReadableText *qmp_x_query_opcount(Error **errp)
    return human_readable_text_from_str(buf);
 }

+#ifdef CONFIG_PROFILER
+
+int64_t dev_time;
+
+HumanReadableText *qmp_x_query_profile(Error **errp)
+{
+    g_autoptr(GString) buf = g_string_new("");
+    static int64_t last_cpu_exec_time;
+    int64_t cpu_exec_time;
+    int64_t delta;
+
+    cpu_exec_time = tcg_cpu_exec_time();
+    delta = cpu_exec_time - last_cpu_exec_time;
+
+    g_string_append_printf(buf, "async time  %" PRId64 " (%0.3f)\n",
+                           dev_time, dev_time / (double)NANOSECONDS_PER_SECOND);
+    g_string_append_printf(buf, "qemu time   %" PRId64 " (%0.3f)\n",
+                           delta, delta / (double)NANOSECONDS_PER_SECOND);
+    last_cpu_exec_time = cpu_exec_time;
+    dev_time = 0;
+
+    return human_readable_text_from_str(buf);
+}
+#else
+HumanReadableText *qmp_x_query_profile(Error **errp)
+{
+    error_setg(errp, "Internal profiler not compiled");
+    return NULL;
+}
+#endif
+
 static void hmp_tcg_register(void)
 {
    monitor_register_hmp_info_hrt("jit", qmp_x_query_jit);
--- a/accel/tcg/perf.c
+++ b/accel/tcg/perf.c
@@ -111,8 +111,6 @@ static void write_perfmap_entry(const void *start, size_t insn,
 }

 static FILE *jitdump;
-static size_t perf_marker_size;
-static void *perf_marker = MAP_FAILED;

 #define JITHEADER_MAGIC 0x4A695444
 #define JITHEADER_VERSION 1
@@ -192,6 +190,7 @@ void perf_enable_jitdump(void)
 {
    struct jitheader header;
    char jitdump_file[32];
+    void *perf_marker;

    if (!use_rt_clock) {
        warn_report("CLOCK_MONOTONIC is not available, proceeding without jitdump");
@@ -211,8 +210,7 @@ void perf_enable_jitdump(void)
     * PERF_RECORD_MMAP or PERF_RECORD_MMAP2 event is of the form jit-%d.dump
     * and will process it as a jitdump file.
     */
-    perf_marker_size = qemu_real_host_page_size();
-    perf_marker = mmap(NULL, perf_marker_size, PROT_READ | PROT_EXEC,
+    perf_marker = mmap(NULL, qemu_real_host_page_size(), PROT_READ | PROT_EXEC,
                       MAP_PRIVATE, fileno(jitdump), 0);
    if (perf_marker == MAP_FAILED) {
        warn_report("Could not map %s: %s, proceeding without jitdump",
@@ -313,8 +311,7 @@ void perf_report_code(uint64_t guest_pc, TranslationBlock *tb,
                      const void *start)
 {
    struct debuginfo_query *q;
-    size_t insn, start_words;
-    uint64_t *gen_insn_data;
+    size_t insn;

    if (!perfmap && !jitdump) {
        return;
@@ -328,12 +325,9 @@ void perf_report_code(uint64_t guest_pc, TranslationBlock *tb,
    debuginfo_lock();

    /* Query debuginfo for each guest instruction. */
-    gen_insn_data = tcg_ctx->gen_insn_data;
-    start_words = tcg_ctx->insn_start_words;
-
    for (insn = 0; insn < tb->icount; insn++) {
        /* FIXME: This replicates the restore_state_to_opc() logic. */
-        q[insn].address = gen_insn_data[insn * start_words + 0];
+        q[insn].address = tcg_ctx->gen_insn_data[insn][0];
        if (tb_cflags(tb) & CF_PCREL) {
            q[insn].address |= (guest_pc & TARGET_PAGE_MASK);
        } else {
@@ -374,11 +368,6 @@ void perf_exit(void)
        perfmap = NULL;
    }

-    if (perf_marker != MAP_FAILED) {
-        munmap(perf_marker, perf_marker_size);
-        perf_marker = MAP_FAILED;
-    }
-
    if (jitdump) {
        fclose(jitdump);
        jitdump = NULL;
--- a/accel/tcg/plugin-gen.c
+++ b/accel/tcg/plugin-gen.c
@@ -43,18 +43,12 @@
 * CPU's index into a TCG temp, since the first callback did it already.
 */
 #include "qemu/osdep.h"
-#include "cpu.h"
 #include "tcg/tcg.h"
 #include "tcg/tcg-temp-internal.h"
 #include "tcg/tcg-op.h"
 #include "exec/exec-all.h"
 #include "exec/plugin-gen.h"
 #include "exec/translator.h"
-#include "exec/helper-proto-common.h"
-
-#define HELPER_H  "accel/tcg/plugin-helpers.h"
-#include "exec/helper-info.c.inc"
-#undef  HELPER_H

 #ifdef CONFIG_SOFTMMU
 # define CONFIG_SOFTMMU_GATE 1
@@ -98,13 +92,34 @@ void HELPER(plugin_vcpu_mem_cb)(unsigned int vcpu_index,
                                void *userdata)
 { }

+static void do_gen_mem_cb(TCGv vaddr, uint32_t info)
+{
+    TCGv_i32 cpu_index = tcg_temp_ebb_new_i32();
+    TCGv_i32 meminfo = tcg_temp_ebb_new_i32();
+    TCGv_i64 vaddr64 = tcg_temp_ebb_new_i64();
+    TCGv_ptr udata = tcg_temp_ebb_new_ptr();
+
+    tcg_gen_movi_i32(meminfo, info);
+    tcg_gen_movi_ptr(udata, 0);
+    tcg_gen_ld_i32(cpu_index, cpu_env,
+                   -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
+    tcg_gen_extu_tl_i64(vaddr64, vaddr);
+
+    gen_helper_plugin_vcpu_mem_cb(cpu_index, meminfo, vaddr64, udata);
+
+    tcg_temp_free_ptr(udata);
+    tcg_temp_free_i64(vaddr64);
+    tcg_temp_free_i32(meminfo);
+    tcg_temp_free_i32(cpu_index);
+}
+
 static void gen_empty_udata_cb(void)
 {
    TCGv_i32 cpu_index = tcg_temp_ebb_new_i32();
    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);

@@ -130,22 +145,9 @@ static void gen_empty_inline_cb(void)
    tcg_temp_free_i64(val);
 }

-static void gen_empty_mem_cb(TCGv_i64 addr, uint32_t info)
+static void gen_empty_mem_cb(TCGv addr, uint32_t info)
 {
-    TCGv_i32 cpu_index = tcg_temp_ebb_new_i32();
-    TCGv_i32 meminfo = tcg_temp_ebb_new_i32();
-    TCGv_ptr udata = tcg_temp_ebb_new_ptr();
-
-    tcg_gen_movi_i32(meminfo, info);
-    tcg_gen_movi_ptr(udata, 0);
-    tcg_gen_ld_i32(cpu_index, tcg_env,
-                   -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
-
-    gen_helper_plugin_vcpu_mem_cb(cpu_index, meminfo, addr, udata);
-
-    tcg_temp_free_ptr(udata);
-    tcg_temp_free_i32(meminfo);
-    tcg_temp_free_i32(cpu_index);
+    do_gen_mem_cb(addr, info);
 }

 /*
@@ -157,7 +159,7 @@ 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);
 }
@@ -200,17 +202,35 @@ static void plugin_gen_empty_callback(enum plugin_gen_from from)
    }
 }

-void plugin_gen_empty_mem_callback(TCGv_i64 addr, uint32_t info)
+union mem_gen_fn {
+    void (*mem_fn)(TCGv, uint32_t);
+    void (*inline_fn)(void);
+};
+
+static void gen_mem_wrapped(enum plugin_gen_cb type,
+                            const union mem_gen_fn *f, TCGv addr,
+                            uint32_t info, bool is_mem)
 {
    enum qemu_plugin_mem_rw rw = get_plugin_meminfo_rw(info);

-    gen_plugin_cb_start(PLUGIN_GEN_FROM_MEM, PLUGIN_GEN_CB_MEM, rw);
-    gen_empty_mem_cb(addr, info);
+    gen_plugin_cb_start(PLUGIN_GEN_FROM_MEM, type, rw);
+    if (is_mem) {
+        f->mem_fn(addr, info);
+    } else {
+        f->inline_fn();
+    }
    tcg_gen_plugin_cb_end();
+}

-    gen_plugin_cb_start(PLUGIN_GEN_FROM_MEM, PLUGIN_GEN_CB_INLINE, rw);
-    gen_empty_inline_cb();
-    tcg_gen_plugin_cb_end();
+void plugin_gen_empty_mem_callback(TCGv addr, uint32_t info)
+{
+    union mem_gen_fn fn;
+
+    fn.mem_fn = gen_empty_mem_cb;
+    gen_mem_wrapped(PLUGIN_GEN_CB_MEM, &fn, addr, info, true);
+
+    fn.inline_fn = gen_empty_inline_cb;
+    gen_mem_wrapped(PLUGIN_GEN_CB_INLINE, &fn, 0, info, false);
 }

 static TCGOp *find_op(TCGOp *op, TCGOpcode opc)
@@ -260,6 +280,33 @@ static TCGOp *copy_op(TCGOp **begin_op, TCGOp *op, TCGOpcode opc)
    return op;
 }

+static TCGOp *copy_extu_i32_i64(TCGOp **begin_op, TCGOp *op)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        /* mov_i32 */
+        op = copy_op(begin_op, op, INDEX_op_mov_i32);
+        /* mov_i32 w/ $0 */
+        op = copy_op(begin_op, op, INDEX_op_mov_i32);
+    } else {
+        /* extu_i32_i64 */
+        op = copy_op(begin_op, op, INDEX_op_extu_i32_i64);
+    }
+    return op;
+}
+
+static TCGOp *copy_mov_i64(TCGOp **begin_op, TCGOp *op)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        /* 2x mov_i32 */
+        op = copy_op(begin_op, op, INDEX_op_mov_i32);
+        op = copy_op(begin_op, op, INDEX_op_mov_i32);
+    } else {
+        /* mov_i64 */
+        op = copy_op(begin_op, op, INDEX_op_mov_i64);
+    }
+    return op;
+}
+
 static TCGOp *copy_const_ptr(TCGOp **begin_op, TCGOp *op, void *ptr)
 {
    if (UINTPTR_MAX == UINT32_MAX) {
@@ -274,6 +321,18 @@ static TCGOp *copy_const_ptr(TCGOp **begin_op, TCGOp *op, void *ptr)
    return op;
 }

+static TCGOp *copy_extu_tl_i64(TCGOp **begin_op, TCGOp *op)
+{
+    if (TARGET_LONG_BITS == 32) {
+        /* extu_i32_i64 */
+        op = copy_extu_i32_i64(begin_op, op);
+    } else {
+        /* mov_i64 */
+        op = copy_mov_i64(begin_op, op);
+    }
+    return op;
+}
+
 static TCGOp *copy_ld_i64(TCGOp **begin_op, TCGOp *op)
 {
    if (TCG_TARGET_REG_BITS == 32) {
@@ -327,7 +386,8 @@ 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 +431,8 @@ 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;
 }
@@ -416,9 +477,13 @@ static TCGOp *append_mem_cb(const struct qemu_plugin_dyn_cb *cb,
        tcg_debug_assert(begin_op && begin_op->opc == INDEX_op_ld_i32);
    }

+    /* extu_tl_i64 */
+    op = copy_extu_tl_i64(&begin_op, op);
+
    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 +643,7 @@ 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 +911,7 @@ 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 +928,10 @@ 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);

--- a/accel/tcg/tb-hash.h
+++ b/accel/tcg/tb-hash.h
@@ -35,16 +35,16 @@
 #define TB_JMP_ADDR_MASK (TB_JMP_PAGE_SIZE - 1)
 #define TB_JMP_PAGE_MASK (TB_JMP_CACHE_SIZE - TB_JMP_PAGE_SIZE)

-static inline unsigned int tb_jmp_cache_hash_page(vaddr pc)
+static inline unsigned int tb_jmp_cache_hash_page(target_ulong pc)
 {
-    vaddr tmp;
+    target_ulong tmp;
    tmp = pc ^ (pc >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS));
    return (tmp >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS)) & TB_JMP_PAGE_MASK;
 }

-static inline unsigned int tb_jmp_cache_hash_func(vaddr pc)
+static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
 {
-    vaddr tmp;
+    target_ulong tmp;
    tmp = pc ^ (pc >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS));
    return (((tmp >> (TARGET_PAGE_BITS - TB_JMP_PAGE_BITS)) & TB_JMP_PAGE_MASK)
           | (tmp & TB_JMP_ADDR_MASK));
@@ -53,7 +53,7 @@ static inline unsigned int tb_jmp_cache_hash_func(vaddr pc)
 #else

 /* In user-mode we can get better hashing because we do not have a TLB */
-static inline unsigned int tb_jmp_cache_hash_func(vaddr pc)
+static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
 {
    return (pc ^ (pc >> TB_JMP_CACHE_BITS)) & (TB_JMP_CACHE_SIZE - 1);
 }
@@ -61,10 +61,10 @@ static inline unsigned int tb_jmp_cache_hash_func(vaddr pc)
 #endif /* CONFIG_SOFTMMU */

 static inline
-uint32_t tb_hash_func(tb_page_addr_t phys_pc, vaddr pc,
-                      uint32_t flags, uint64_t flags2, uint32_t cf_mask)
+uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc, uint32_t flags,
+                      uint32_t cf_mask, uint32_t trace_vcpu_dstate)
 {
-    return qemu_xxhash8(phys_pc, pc, flags2, flags, cf_mask);
+    return qemu_xxhash7(phys_pc, pc, flags, cf_mask, trace_vcpu_dstate);
 }

 #endif
--- a/accel/tcg/tb-jmp-cache.h
+++ b/accel/tcg/tb-jmp-cache.h
@@ -21,7 +21,7 @@ struct CPUJumpCache {
    struct rcu_head rcu;
    struct {
        TranslationBlock *tb;
-        vaddr pc;
+        target_ulong pc;
    } array[TB_JMP_CACHE_SIZE];
 };

--- a/accel/tcg/tb-maint.c
+++ b/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. */
@@ -51,6 +50,7 @@ static bool tb_cmp(const void *ap, const void *bp)
            a->cs_base == b->cs_base &&
            a->flags == b->flags &&
            (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) &&
+            a->trace_vcpu_dstate == b->trace_vcpu_dstate &&
            tb_page_addr0(a) == tb_page_addr0(b) &&
            tb_page_addr1(a) == tb_page_addr1(b));
 }
@@ -71,7 +71,17 @@ 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,
@@ -87,9 +97,9 @@ 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;
+    target_ulong addr;
    int flags;

    assert_memory_lock();
@@ -208,12 +218,13 @@ 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 +392,12 @@ 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 +421,13 @@ 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 +605,8 @@ 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 +626,15 @@ 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 +654,74 @@ 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 */

@@ -775,7 +746,7 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)

    tcg_region_reset_all();
    /* XXX: flush processor icache at this point if cache flush is expensive */
-    qatomic_inc(&tb_ctx.tb_flush_count);
+    qatomic_mb_set(&tb_ctx.tb_flush_count, tb_ctx.tb_flush_count + 1);

 done:
    mmap_unlock();
@@ -787,9 +758,9 @@ done:
 void tb_flush(CPUState *cpu)
 {
    if (tcg_enabled()) {
-        unsigned tb_flush_count = qatomic_read(&tb_ctx.tb_flush_count);
+        unsigned tb_flush_count = qatomic_mb_read(&tb_ctx.tb_flush_count);

-        if (cpu_in_serial_context(cpu)) {
+        if (cpu_in_exclusive_context(cpu)) {
            do_tb_flush(cpu, RUN_ON_CPU_HOST_INT(tb_flush_count));
        } else {
            async_safe_run_on_cpu(cpu, do_tb_flush,
@@ -917,7 +888,7 @@ 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, (orig_cflags & CF_PCREL ? 0 : tb->pc),
-                     tb->flags, tb->cs_base, orig_cflags);
+                     tb->flags, orig_cflags, tb->trace_vcpu_dstate);
    if (!qht_remove(&tb_ctx.htable, tb, h)) {
        return;
    }
@@ -955,16 +926,18 @@ 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 +945,43 @@ 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->cflags & CF_PCREL ? 0 : tb->pc),
-                     tb->flags, tb->cs_base, tb->cflags);
+    h = tb_hash_func(phys_pc, (tb->cflags & CF_PCREL ? 0 : tb->pc),
+                     tb->flags, tb->cflags, tb->trace_vcpu_dstate);
    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;
 }

@@ -1083,8 +1070,7 @@ bool tb_invalidate_phys_page_unwind(tb_page_addr_t addr, uintptr_t pc)
    if (current_tb_modified) {
        /* Force execution of one insn next time.  */
        CPUState *cpu = current_cpu;
-        cpu->cflags_next_tb =
-            1 | CF_LAST_IO | CF_NOIRQ | curr_cflags(current_cpu);
+        cpu->cflags_next_tb = 1 | CF_NOIRQ | curr_cflags(current_cpu);
        return true;
    }
    return false;
@@ -1154,8 +1140,7 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
    if (current_tb_modified) {
        page_collection_unlock(pages);
        /* Force execution of one insn next time.  */
-        current_cpu->cflags_next_tb =
-            1 | CF_LAST_IO | CF_NOIRQ | curr_cflags(current_cpu);
+        current_cpu->cflags_next_tb = 1 | CF_NOIRQ | curr_cflags(current_cpu);
        mmap_unlock();
        cpu_loop_exit_noexc(current_cpu);
    }
--- a/accel/tcg/tcg-accel-ops-icount.c
+++ b/accel/tcg/tcg-accel-ops-icount.c
@@ -89,20 +89,7 @@ void icount_handle_deadline(void)
    }
 }

-/* Distribute the budget evenly across all CPUs */
-int64_t icount_percpu_budget(int cpu_count)
-{
-    int64_t limit = icount_get_limit();
-    int64_t timeslice = limit / cpu_count;
-
-    if (timeslice == 0) {
-        timeslice = limit;
-    }
-
-    return timeslice;
-}
-
-void icount_prepare_for_run(CPUState *cpu, int64_t cpu_budget)
+void icount_prepare_for_run(CPUState *cpu)
 {
    int insns_left;

@@ -111,16 +98,16 @@ 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);
+    cpu->icount_budget = icount_get_limit();
    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;

+    replay_mutex_lock();
+
    if (cpu->icount_budget == 0) {
        /*
         * We're called without the iothread lock, so must take it while
@@ -138,7 +125,7 @@ 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 +140,7 @@ 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");
    }
--- a/accel/tcg/tcg-accel-ops-icount.h
+++ b/accel/tcg/tcg-accel-ops-icount.h
@@ -11,8 +11,7 @@
 #define TCG_ACCEL_OPS_ICOUNT_H

 void icount_handle_deadline(void);
-void icount_prepare_for_run(CPUState *cpu, int64_t cpu_budget);
-int64_t icount_percpu_budget(int cpu_count);
+void icount_prepare_for_run(CPUState *cpu);
 void icount_process_data(CPUState *cpu);

 void icount_handle_interrupt(CPUState *cpu, int mask);
--- a/accel/tcg/tcg-accel-ops-mttcg.c
+++ b/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-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();
@@ -114,7 +119,7 @@ static void *mttcg_cpu_thread_fn(void *arg)
            }
        }

-        qatomic_set_mb(&cpu->exit_request, 0);
+        qatomic_mb_set(&cpu->exit_request, 0);
        qemu_wait_io_event(cpu);
    } while (!cpu->unplug || cpu_can_run(cpu));

@@ -147,4 +152,8 @@ void mttcg_start_vcpu_thread(CPUState *cpu)

    qemu_thread_create(cpu->thread, thread_name, mttcg_cpu_thread_fn,
                       cpu, QEMU_THREAD_JOINABLE);
+
+#ifdef _WIN32
+    cpu->hThread = qemu_thread_get_handle(cpu->thread);
+#endif
 }
--- a/accel/tcg/tcg-accel-ops-rr.c
+++ b/accel/tcg/tcg-accel-ops-rr.c
@@ -24,7 +24,6 @@
 */

 #include "qemu/osdep.h"
-#include "qemu/lockable.h"
 #include "sysemu/tcg.h"
 #include "sysemu/replay.h"
 #include "sysemu/cpu-timers.h"
@@ -32,7 +31,7 @@
 #include "qemu/notify.h"
 #include "qemu/guest-random.h"
 #include "exec/exec-all.h"
-#include "tcg/startup.h"
+
 #include "tcg-accel-ops.h"
 #include "tcg-accel-ops-rr.h"
 #include "tcg-accel-ops-icount.h"
@@ -72,13 +71,11 @@ static void rr_kick_next_cpu(void)
 {
    CPUState *cpu;
    do {
-        cpu = qatomic_read(&rr_current_cpu);
+        cpu = qatomic_mb_read(&rr_current_cpu);
        if (cpu) {
            cpu_exit(cpu);
        }
-        /* Finish kicking this cpu before reading again.  */
-        smp_mb();
-    } while (cpu != qatomic_read(&rr_current_cpu));
+    } while (cpu != qatomic_mb_read(&rr_current_cpu));
 }

 static void rr_kick_thread(void *opaque)
@@ -142,33 +139,6 @@ static void rr_force_rcu(Notifier *notify, void *data)
    rr_kick_next_cpu();
 }

-/*
- * Calculate the number of CPUs that we will process in a single iteration of
- * the main CPU thread loop so that we can fairly distribute the instruction
- * count across CPUs.
- *
- * The CPU count is cached based on the CPU list generation ID to avoid
- * iterating the list every time.
- */
-static int rr_cpu_count(void)
-{
-    static unsigned int last_gen_id = ~0;
-    static int cpu_count;
-    CPUState *cpu;
-
-    QEMU_LOCK_GUARD(&qemu_cpu_list_lock);
-
-    if (cpu_list_generation_id_get() != last_gen_id) {
-        cpu_count = 0;
-        CPU_FOREACH(cpu) {
-            ++cpu_count;
-        }
-        last_gen_id = cpu_list_generation_id_get();
-    }
-
-    return cpu_count;
-}
-
 /*
 * In the single-threaded case each vCPU is simulated in turn. If
 * there is more than a single vCPU we create a simple timer to kick
@@ -192,7 +162,7 @@ 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);

@@ -215,16 +185,11 @@ static void *rr_cpu_thread_fn(void *arg)
    cpu->exit_request = 1;

    while (1) {
-        /* Only used for icount_enabled() */
-        int64_t cpu_budget = 0;
-
        qemu_mutex_unlock_iothread();
        replay_mutex_lock();
        qemu_mutex_lock_iothread();

        if (icount_enabled()) {
-            int cpu_count = rr_cpu_count();
-
            /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
            icount_account_warp_timer();
            /*
@@ -232,8 +197,6 @@ static void *rr_cpu_thread_fn(void *arg)
             * waking up the I/O thread and waiting for completion.
             */
            icount_handle_deadline();
-
-            cpu_budget = icount_percpu_budget(cpu_count);
        }

        replay_mutex_unlock();
@@ -243,9 +206,8 @@ static void *rr_cpu_thread_fn(void *arg)
        }

        while (cpu && cpu_work_list_empty(cpu) && !cpu->exit_request) {
-            /* Store rr_current_cpu before evaluating cpu_can_run().  */
-            qatomic_set_mb(&rr_current_cpu, cpu);

+            qatomic_mb_set(&rr_current_cpu, cpu);
            current_cpu = cpu;

            qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
@@ -256,7 +218,7 @@ static void *rr_cpu_thread_fn(void *arg)

                qemu_mutex_unlock_iothread();
                if (icount_enabled()) {
-                    icount_prepare_for_run(cpu, cpu_budget);
+                    icount_prepare_for_run(cpu);
                }
                r = tcg_cpus_exec(cpu);
                if (icount_enabled()) {
@@ -283,11 +245,11 @@ static void *rr_cpu_thread_fn(void *arg)
            cpu = CPU_NEXT(cpu);
        } /* while (cpu && !cpu->exit_request).. */

-        /* Does not need a memory barrier because a spurious wakeup is okay.  */
+        /* Does not need qatomic_mb_set because a spurious wakeup is okay.  */
        qatomic_set(&rr_current_cpu, NULL);

        if (cpu && cpu->exit_request) {
-            qatomic_set_mb(&cpu->exit_request, 0);
+            qatomic_mb_set(&cpu->exit_request, 0);
        }

        if (icount_enabled() && all_cpu_threads_idle()) {
@@ -329,12 +291,15 @@ void rr_start_vcpu_thread(CPUState *cpu)

        single_tcg_halt_cond = cpu->halt_cond;
        single_tcg_cpu_thread = cpu->thread;
+#ifdef _WIN32
+        cpu->hThread = qemu_thread_get_handle(cpu->thread);
+#endif
    } else {
        /* we share the thread */
        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;
    }
 }
--- a/accel/tcg/tcg-accel-ops.c
+++ b/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"
@@ -71,20 +70,23 @@ void tcg_cpus_destroy(CPUState *cpu)
 int tcg_cpus_exec(CPUState *cpu)
 {
    int ret;
+#ifdef CONFIG_PROFILER
+    int64_t ti;
+#endif
    assert(tcg_enabled());
+#ifdef CONFIG_PROFILER
+    ti = profile_getclock();
+#endif
    cpu_exec_start(cpu);
    ret = cpu_exec(cpu);
    cpu_exec_end(cpu);
+#ifdef CONFIG_PROFILER
+    qatomic_set(&tcg_ctx->prof.cpu_exec_time,
+                tcg_ctx->prof.cpu_exec_time + profile_getclock() - ti);
+#endif
    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 +101,7 @@ 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 +215,6 @@ 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;
--- a/accel/tcg/tcg-all.c
+++ b/accel/tcg/tcg-all.c
@@ -27,24 +27,21 @@
 #include "sysemu/tcg.h"
 #include "exec/replay-core.h"
 #include "sysemu/cpu-timers.h"
-#include "tcg/startup.h"
-#include "tcg/oversized-guest.h"
+#include "tcg/tcg.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "qemu/accel.h"
-#include "qemu/atomic.h"
 #include "qapi/qapi-builtin-visit.h"
 #include "qemu/units.h"
 #if !defined(CONFIG_USER_ONLY)
 #include "hw/boards.h"
 #endif
-#include "internal-target.h"
+#include "internal.h"

 struct TCGState {
    AccelState parent_obj;

    bool mttcg_enabled;
-    bool one_insn_per_tb;
    int splitwx_enabled;
    unsigned long tb_size;
 };
@@ -64,23 +61,37 @@ DECLARE_INSTANCE_CHECKER(TCGState, TCG_STATE,
 * they can set the appropriate CONFIG flags in ${target}-softmmu.mak
 *
 * Once a guest architecture has been converted to the new primitives
- * there is one remaining limitation to check:
- *   - The guest can't be oversized (e.g. 64 bit guest on 32 bit host)
+ * there are two remaining limitations to check.
+ *
+ * - The guest can't be oversized (e.g. 64 bit guest on 32 bit host)
+ * - The host must have a stronger memory order than the guest
+ *
+ * It may be possible in future to support strong guests on weak hosts
+ * but that will require tagging all load/stores in a guest with their
+ * implicit memory order requirements which would likely slow things
+ * down a lot.
 */

+static bool check_tcg_memory_orders_compatible(void)
+{
+#if defined(TCG_GUEST_DEFAULT_MO) && defined(TCG_TARGET_DEFAULT_MO)
+    return (TCG_GUEST_DEFAULT_MO & ~TCG_TARGET_DEFAULT_MO) == 0;
+#else
+    return false;
+#endif
+}
+
 static bool default_mttcg_enabled(void)
 {
    if (icount_enabled() || TCG_OVERSIZED_GUEST) {
        return false;
-    }
+    } else {
 #ifdef TARGET_SUPPORTS_MTTCG
-# ifndef TCG_GUEST_DEFAULT_MO
-#  error "TARGET_SUPPORTS_MTTCG without TCG_GUEST_DEFAULT_MO"
-# endif
-    return true;
+        return check_tcg_memory_orders_compatible();
 #else
-    return false;
+        return false;
 #endif
+    }
 }

 static void tcg_accel_instance_init(Object *obj)
@@ -98,7 +109,6 @@ static void tcg_accel_instance_init(Object *obj)
 }

 bool mttcg_enabled;
-bool one_insn_per_tb;

 static int tcg_init_machine(MachineState *ms)
 {
@@ -121,7 +131,7 @@ 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;
@@ -148,6 +158,11 @@ static void tcg_set_thread(Object *obj, const char *value, Error **errp)
            warn_report("Guest not yet converted to MTTCG - "
                        "you may get unexpected results");
 #endif
+            if (!check_tcg_memory_orders_compatible()) {
+                warn_report("Guest expects a stronger memory ordering "
+                            "than the host provides");
+                error_printf("This may cause strange/hard to debug errors\n");
+            }
            s->mttcg_enabled = true;
        }
    } else if (strcmp(value, "single") == 0) {
@@ -193,20 +208,6 @@ static void tcg_set_splitwx(Object *obj, bool value, Error **errp)
    s->splitwx_enabled = value;
 }

-static bool tcg_get_one_insn_per_tb(Object *obj, Error **errp)
-{
-    TCGState *s = TCG_STATE(obj);
-    return s->one_insn_per_tb;
-}
-
-static void tcg_set_one_insn_per_tb(Object *obj, bool value, Error **errp)
-{
-    TCGState *s = TCG_STATE(obj);
-    s->one_insn_per_tb = value;
-    /* Set the global also: this changes the behaviour */
-    qatomic_set(&one_insn_per_tb, value);
-}
-
 static int tcg_gdbstub_supported_sstep_flags(void)
 {
    /*
@@ -227,8 +228,6 @@ 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;

@@ -246,12 +245,6 @@ static void tcg_accel_class_init(ObjectClass *oc, void *data)
        tcg_get_splitwx, tcg_set_splitwx);
    object_class_property_set_description(oc, "split-wx",
        "Map jit pages into separate RW and RX regions");
-
-    object_class_property_add_bool(oc, "one-insn-per-tb",
-                                   tcg_get_one_insn_per_tb,
-                                   tcg_set_one_insn_per_tb);
-    object_class_property_set_description(oc, "one-insn-per-tb",
-        "Only put one guest insn in each translation block");
 }

 static const TypeInfo tcg_accel_type = {
--- a/accel/tcg/tcg-runtime-gvec.c
+++ b/accel/tcg/tcg-runtime-gvec.c
@@ -20,7 +20,7 @@
 #include "qemu/osdep.h"
 #include "qemu/host-utils.h"
 #include "cpu.h"
-#include "exec/helper-proto-common.h"
+#include "exec/helper-proto.h"
 #include "tcg/tcg-gvec-desc.h"


@@ -550,17 +550,6 @@ void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
    clear_high(d, oprsz, desc);
 }

-void HELPER(gvec_andcs)(void *d, void *a, uint64_t b, uint32_t desc)
-{
-    intptr_t oprsz = simd_oprsz(desc);
-    intptr_t i;
-
-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & ~b;
-    }
-    clear_high(d, oprsz, desc);
-}
-
 void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
@@ -1042,32 +1031,6 @@ 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);
--- a/accel/tcg/tcg-runtime.c
+++ b/accel/tcg/tcg-runtime.c
@@ -24,17 +24,13 @@
 #include "qemu/osdep.h"
 #include "qemu/host-utils.h"
 #include "cpu.h"
-#include "exec/helper-proto-common.h"
+#include "exec/helper-proto.h"
 #include "exec/cpu_ldst.h"
 #include "exec/exec-all.h"
 #include "disas/disas.h"
 #include "exec/log.h"
 #include "tcg/tcg.h"

-#define HELPER_H  "accel/tcg/tcg-runtime.h"
-#include "exec/helper-info.c.inc"
-#undef  HELPER_H
-
 /* 32-bit helpers */

 int32_t HELPER(div_i32)(int32_t arg1, int32_t arg2)
--- a/accel/tcg/tcg-runtime.h
+++ b/accel/tcg/tcg-runtime.h
@@ -39,63 +39,62 @@ DEF_HELPER_FLAGS_1(exit_atomic, TCG_CALL_NO_WG, noreturn, env)
 DEF_HELPER_FLAGS_3(memset, TCG_CALL_NO_RWG, ptr, ptr, int, ptr)
 #endif /* IN_HELPER_PROTO */

-DEF_HELPER_FLAGS_3(ld_i128, TCG_CALL_NO_WG, i128, env, i64, i32)
-DEF_HELPER_FLAGS_4(st_i128, TCG_CALL_NO_WG, void, env, i64, i128, i32)
-
 DEF_HELPER_FLAGS_5(atomic_cmpxchgb, TCG_CALL_NO_WG,
-                   i32, env, i64, i32, i32, i32)
+                   i32, env, tl, i32, i32, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgw_be, TCG_CALL_NO_WG,
-                   i32, env, i64, i32, i32, i32)
+                   i32, env, tl, i32, i32, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgw_le, TCG_CALL_NO_WG,
-                   i32, env, i64, i32, i32, i32)
+                   i32, env, tl, i32, i32, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgl_be, TCG_CALL_NO_WG,
-                   i32, env, i64, i32, i32, i32)
+                   i32, env, tl, i32, i32, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgl_le, TCG_CALL_NO_WG,
-                   i32, env, i64, i32, i32, i32)
+                   i32, env, tl, i32, i32, i32)
 #ifdef CONFIG_ATOMIC64
 DEF_HELPER_FLAGS_5(atomic_cmpxchgq_be, TCG_CALL_NO_WG,
-                   i64, env, i64, i64, i64, i32)
+                   i64, env, tl, i64, i64, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgq_le, TCG_CALL_NO_WG,
-                   i64, env, i64, i64, i64, i32)
+                   i64, env, tl, 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)
+                   i128, env, tl, i128, i128, i32)
 DEF_HELPER_FLAGS_5(atomic_cmpxchgo_le, TCG_CALL_NO_WG,
-                   i128, env, i64, i128, i128, i32)
+                   i128, env, tl, i128, i128, i32)
 #endif

-DEF_HELPER_FLAGS_5(nonatomic_cmpxchgo, TCG_CALL_NO_WG,
-                   i128, env, i64, i128, i128, i32)
+DEF_HELPER_FLAGS_5(nonatomic_cmpxchgo_be, TCG_CALL_NO_WG,
+                   i128, env, tl, i128, i128, i32)
+DEF_HELPER_FLAGS_5(nonatomic_cmpxchgo_le, TCG_CALL_NO_WG,
+                   i128, env, tl, i128, i128, i32)

 #ifdef CONFIG_ATOMIC64
 #define GEN_ATOMIC_HELPERS(NAME)                                  \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), b),              \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), w_le),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), w_be),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), l_le),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), l_be),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), q_le),           \
-                       TCG_CALL_NO_WG, i64, env, i64, i64, i32)   \
+                       TCG_CALL_NO_WG, i64, env, tl, i64, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), q_be),           \
-                       TCG_CALL_NO_WG, i64, env, i64, i64, i32)
+                       TCG_CALL_NO_WG, i64, env, tl, i64, i32)
 #else
 #define GEN_ATOMIC_HELPERS(NAME)                                  \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), b),              \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), w_le),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), w_be),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), l_le),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)   \
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)    \
    DEF_HELPER_FLAGS_4(glue(glue(atomic_, NAME), l_be),           \
-                       TCG_CALL_NO_WG, i32, env, i64, i32, i32)
+                       TCG_CALL_NO_WG, i32, env, tl, i32, i32)
 #endif /* CONFIG_ATOMIC64 */

 GEN_ATOMIC_HELPERS(fetch_add)
@@ -218,7 +217,6 @@ DEF_HELPER_FLAGS_4(gvec_nor, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_eqv, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

 DEF_HELPER_FLAGS_4(gvec_ands, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
-DEF_HELPER_FLAGS_4(gvec_andcs, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_xors, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_ors, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)

@@ -297,29 +295,4 @@ 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)
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -19,6 +19,7 @@

 #include "qemu/osdep.h"

+#define NO_CPU_IO_DEFS
 #include "trace.h"
 #include "disas/disas.h"
 #include "exec/exec-all.h"
@@ -61,18 +62,19 @@
 #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"
+
+/* Make sure all possible CPU event bits fit in tb->trace_vcpu_dstate */
+QEMU_BUILD_BUG_ON(CPU_TRACE_DSTATE_MAX_EVENTS >
+                  sizeof_field(TranslationBlock, trace_vcpu_dstate)
+                  * BITS_PER_BYTE);

 TBContext tb_ctx;

-/*
- * Encode VAL as a signed leb128 sequence at P.
- * Return P incremented past the encoded value.
- */
-static uint8_t *encode_sleb128(uint8_t *p, int64_t val)
+/* Encode VAL as a signed leb128 sequence at P.
+   Return P incremented past the encoded value.  */
+static uint8_t *encode_sleb128(uint8_t *p, target_long val)
 {
    int more, byte;

@@ -90,23 +92,21 @@ static uint8_t *encode_sleb128(uint8_t *p, int64_t val)
    return p;
 }

-/*
- * Decode a signed leb128 sequence at *PP; increment *PP past the
- * decoded value.  Return the decoded value.
- */
-static int64_t decode_sleb128(const uint8_t **pp)
+/* Decode a signed leb128 sequence at *PP; increment *PP past the
+   decoded value.  Return the decoded value.  */
+static target_long decode_sleb128(const uint8_t **pp)
 {
    const uint8_t *p = *pp;
-    int64_t val = 0;
+    target_long val = 0;
    int byte, shift = 0;

    do {
        byte = *p++;
-        val |= (int64_t)(byte & 0x7f) << shift;
+        val |= (target_ulong)(byte & 0x7f) << shift;
        shift += 7;
    } while (byte & 0x80);
    if (shift < TARGET_LONG_BITS && (byte & 0x40)) {
-        val |= -(int64_t)1 << shift;
+        val |= -(target_ulong)1 << shift;
    }

    *pp = p;
@@ -128,26 +128,22 @@ static int64_t decode_sleb128(const uint8_t **pp)
 static int encode_search(TranslationBlock *tb, uint8_t *block)
 {
    uint8_t *highwater = tcg_ctx->code_gen_highwater;
-    uint64_t *insn_data = tcg_ctx->gen_insn_data;
-    uint16_t *insn_end_off = tcg_ctx->gen_insn_end_off;
    uint8_t *p = block;
    int i, j, n;

    for (i = 0, n = tb->icount; i < n; ++i) {
-        uint64_t prev, curr;
+        target_ulong prev;

        for (j = 0; j < TARGET_INSN_START_WORDS; ++j) {
            if (i == 0) {
                prev = (!(tb_cflags(tb) & CF_PCREL) && j == 0 ? tb->pc : 0);
            } else {
-                prev = insn_data[(i - 1) * TARGET_INSN_START_WORDS + j];
+                prev = tcg_ctx->gen_insn_data[i - 1][j];
            }
-            curr = insn_data[i * TARGET_INSN_START_WORDS + j];
-            p = encode_sleb128(p, curr - prev);
+            p = encode_sleb128(p, tcg_ctx->gen_insn_data[i][j] - prev);
        }
-        prev = (i == 0 ? 0 : insn_end_off[i - 1]);
-        curr = insn_end_off[i];
-        p = encode_sleb128(p, curr - prev);
+        prev = (i == 0 ? 0 : tcg_ctx->gen_insn_end_off[i - 1]);
+        p = encode_sleb128(p, tcg_ctx->gen_insn_end_off[i] - prev);

        /* Test for (pending) buffer overflow.  The assumption is that any
           one row beginning below the high water mark cannot overrun
@@ -203,6 +199,10 @@ void cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
                               uintptr_t host_pc)
 {
    uint64_t data[TARGET_INSN_START_WORDS];
+#ifdef CONFIG_PROFILER
+    TCGProfile *prof = &tcg_ctx->prof;
+    int64_t ti = profile_getclock();
+#endif
    int insns_left = cpu_unwind_data_from_tb(tb, host_pc, data);

    if (insns_left < 0) {
@@ -215,10 +215,16 @@ 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);
+
+#ifdef CONFIG_PROFILER
+    qatomic_set(&prof->restore_time,
+                prof->restore_time + profile_getclock() - ti);
+    qatomic_set(&prof->restore_count, prof->restore_count + 1);
+#endif
 }

 bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc)
@@ -265,7 +271,7 @@ void page_init(void)
 * Return the size of the generated code, or negative on error.
 */
 static int setjmp_gen_code(CPUArchState *env, TranslationBlock *tb,
-                           vaddr pc, void *host_pc,
+                           target_ulong pc, void *host_pc,
                           int *max_insns, int64_t *ti)
 {
    int ret = sigsetjmp(tcg_ctx->jmp_trans, 0);
@@ -281,19 +287,29 @@ static int setjmp_gen_code(CPUArchState *env, TranslationBlock *tb,
    tcg_ctx->cpu = NULL;
    *max_insns = tb->icount;

+#ifdef CONFIG_PROFILER
+    qatomic_set(&tcg_ctx->prof.tb_count, tcg_ctx->prof.tb_count + 1);
+    qatomic_set(&tcg_ctx->prof.interm_time,
+                tcg_ctx->prof.interm_time + profile_getclock() - *ti);
+    *ti = profile_getclock();
+#endif
+
    return tcg_gen_code(tcg_ctx, tb, pc);
 }

 /* Called with mmap_lock held for user mode emulation.  */
 TranslationBlock *tb_gen_code(CPUState *cpu,
-                              vaddr pc, uint64_t cs_base,
+                              target_ulong pc, target_ulong 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;
+#ifdef CONFIG_PROFILER
+    TCGProfile *prof = &tcg_ctx->prof;
+#endif
    int64_t ti;
    void *host_pc;

@@ -314,7 +330,6 @@ 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 */
@@ -333,27 +348,18 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
    tb->cs_base = cs_base;
    tb->flags = flags;
    tb->cflags = cflags;
+    tb->trace_vcpu_dstate = *cpu->trace_dstate;
    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;
-#endif
-    tcg_ctx->insn_start_words = TARGET_INSN_START_WORDS;
-#ifdef TCG_GUEST_DEFAULT_MO
-    tcg_ctx->guest_mo = TCG_GUEST_DEFAULT_MO;
-#else
-    tcg_ctx->guest_mo = TCG_MO_ALL;
+ tb_overflow:
+
+#ifdef CONFIG_PROFILER
+    /* includes aborted translations because of exceptions */
+    qatomic_set(&prof->tb_count1, prof->tb_count1 + 1);
+    ti = profile_getclock();
 #endif

- restart_translate:
    trace_translate_block(tb, pc, tb->tc.ptr);

    gen_code_size = setjmp_gen_code(env, tb, pc, host_pc, &max_insns, &ti);
@@ -372,8 +378,6 @@ 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:
@@ -392,39 +396,14 @@ 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;
@@ -435,6 +414,14 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     */
    perf_report_code(pc, tb, tcg_splitwx_to_rx(gen_code_buf));

+#ifdef CONFIG_PROFILER
+    qatomic_set(&prof->code_time, prof->code_time + profile_getclock() - ti);
+    qatomic_set(&prof->code_in_len, prof->code_in_len + tb->size);
+    qatomic_set(&prof->code_out_len, prof->code_out_len + gen_code_size);
+    qatomic_set(&prof->search_out_len, prof->search_out_len + search_size);
+#endif
+
+#ifdef DEBUG_DISAS
    if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) &&
        qemu_log_in_addr_range(pc)) {
        FILE *logfile = qemu_log_trylock();
@@ -457,8 +444,8 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
            /* Dump header and the first instruction */
            fprintf(logfile, "OUT: [size=%d]\n", gen_code_size);
            fprintf(logfile,
-                    "  -- guest addr 0x%016" PRIx64 " + tb prologue\n",
-                    tcg_ctx->gen_insn_data[insn * TARGET_INSN_START_WORDS]);
+                    "  -- guest addr 0x" TARGET_FMT_lx " + tb prologue\n",
+                    tcg_ctx->gen_insn_data[insn][0]);
            chunk_start = tcg_ctx->gen_insn_end_off[insn];
            disas(logfile, tb->tc.ptr, chunk_start);

@@ -470,8 +457,8 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
            while (insn < tb->icount) {
                size_t chunk_end = tcg_ctx->gen_insn_end_off[insn];
                if (chunk_end > chunk_start) {
-                    fprintf(logfile, "  -- guest addr 0x%016" PRIx64 "\n",
-                            tcg_ctx->gen_insn_data[insn * TARGET_INSN_START_WORDS]);
+                    fprintf(logfile, "  -- guest addr 0x" TARGET_FMT_lx "\n",
+                            tcg_ctx->gen_insn_data[insn][0]);
                    disas(logfile, tb->tc.ptr + chunk_start,
                          chunk_end - chunk_start);
                    chunk_start = chunk_end;
@@ -507,6 +494,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
            qemu_log_unlock(logfile);
        }
    }
+#endif

    qatomic_set(&tcg_ctx->code_gen_ptr, (void *)
        ROUND_UP((uintptr_t)gen_code_buf + gen_code_size + search_size,
@@ -534,7 +522,6 @@ 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;
    }

@@ -549,9 +536,7 @@ 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;
@@ -579,9 +564,8 @@ 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);
-        vaddr pc;
-        uint64_t cs_base;
+        CPUArchState *env = cpu->env_ptr;
+        target_ulong pc, cs_base;
        tb_page_addr_t addr;
        uint32_t flags;

@@ -622,7 +606,7 @@ 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;
    }

@@ -635,23 +619,150 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
    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);
+        target_ulong pc = log_pc(cpu, tb);
        if (qemu_log_in_addr_range(pc)) {
-            qemu_log("cpu_io_recompile: rewound execution of TB to %016"
-                     VADDR_PRIx "\n", pc);
+            qemu_log("cpu_io_recompile: rewound execution of TB to "
+                     TARGET_FMT_lx "\n", pc);
        }
    }

    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 */
@@ -673,3 +784,11 @@ 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
+}
--- a/accel/tcg/translator.c
+++ b/accel/tcg/translator.c
@@ -8,111 +8,17 @@
 */

 #include "qemu/osdep.h"
-#include "qemu/log.h"
 #include "qemu/error-report.h"
+#include "tcg/tcg.h"
+#include "tcg/tcg-op.h"
 #include "exec/exec-all.h"
+#include "exec/gen-icount.h"
+#include "exec/log.h"
 #include "exec/translator.h"
 #include "exec/plugin-gen.h"
-#include "tcg/tcg-op-common.h"
-#include "internal-target.h"
+#include "exec/replay-core.h"

-static void set_can_do_io(DisasContextBase *db, bool val)
-{
-    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));
-    }
-}
-
-bool translator_io_start(DisasContextBase *db)
-{
-    set_can_do_io(db, true);
-
-    /*
-     * Ensure that this instruction will be the last in the TB.
-     * The target may override this to something more forceful.
-     */
-    if (db->is_jmp == DISAS_NEXT) {
-        db->is_jmp = DISAS_TOO_MANY;
-    }
-    return true;
-}
-
-static TCGOp *gen_tb_start(DisasContextBase *db, uint32_t cflags)
-{
-    TCGv_i32 count = NULL;
-    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));
-    }
-
-    if (cflags & CF_USE_ICOUNT) {
-        /*
-         * We emit a sub with a dummy immediate argument. Keep the insn index
-         * of the sub so that we later (when we know the actual insn count)
-         * can update the argument with the actual insn count.
-         */
-        tcg_gen_sub_i32(count, count, tcg_constant_i32(0));
-        icount_start_insn = tcg_last_op();
-    }
-
-    /*
-     * Emit the check against icount_decr.u32 to see if we should exit
-     * unless we suppress the check with CF_NOIRQ. If we are using
-     * icount and have suppressed interruption the higher level code
-     * should have ensured we don't run more instructions than the
-     * budget.
-     */
-    if (cflags & CF_NOIRQ) {
-        tcg_ctx->exitreq_label = NULL;
-    } else {
-        tcg_ctx->exitreq_label = gen_new_label();
-        tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, tcg_ctx->exitreq_label);
-    }
-
-    if (cflags & CF_USE_ICOUNT) {
-        tcg_gen_st16_i32(count, tcg_env,
-                         offsetof(ArchCPU, parent_obj.neg.icount_decr.u16.low)
-                         - 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 && (cflags & CF_LAST_IO));
-
-    return icount_start_insn;
-}
-
-static void gen_tb_end(const TranslationBlock *tb, uint32_t cflags,
-                       TCGOp *icount_start_insn, int num_insns)
-{
-    if (cflags & CF_USE_ICOUNT) {
-        /*
-         * Update the num_insn immediate parameter now that we know
-         * the actual insn count.
-         */
-        tcg_set_insn_param(icount_start_insn, 2,
-                           tcgv_i32_arg(tcg_constant_i32(num_insns)));
-    }
-
-    if (tcg_ctx->exitreq_label) {
-        gen_set_label(tcg_ctx->exitreq_label);
-        tcg_gen_exit_tb(tb, TB_EXIT_REQUESTED);
-    }
-}
-
-bool translator_use_goto_tb(DisasContextBase *db, vaddr dest)
+bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest)
 {
    /* Suppress goto_tb if requested. */
    if (tb_cflags(db->tb) & CF_NO_GOTO_TB) {
@@ -124,11 +30,10 @@ bool translator_use_goto_tb(DisasContextBase *db, vaddr dest)
 }

 void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
-                     vaddr pc, void *host_pc, const TranslatorOps *ops,
-                     DisasContextBase *db)
+                     target_ulong pc, void *host_pc,
+                     const TranslatorOps *ops, DisasContextBase *db)
 {
    uint32_t cflags = tb_cflags(tb);
-    TCGOp *icount_start_insn;
    bool plugin_enabled;

    /* Initialize DisasContext */
@@ -139,26 +44,22 @@ 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);
+    gen_tb_start(db->tb);
    ops->tb_start(db, cpu);
    tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */

-    if (cflags & CF_MEMI_ONLY) {
-        /* We should only see CF_MEMI_ONLY for io_recompile. */
-        assert(cflags & CF_LAST_IO);
-        plugin_enabled = plugin_gen_tb_start(cpu, db, true);
-    } else {
-        plugin_enabled = plugin_gen_tb_start(cpu, db, false);
-    }
-    db->plugin_enabled = plugin_enabled;
+    plugin_enabled = plugin_gen_tb_start(cpu, db, cflags & CF_MEMI_ONLY);

    while (true) {
        *max_insns = ++db->num_insns;
@@ -175,9 +76,13 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
           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
@@ -207,16 +112,17 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,

    /* Emit code to exit the TB, as indicated by db->is_jmp.  */
    ops->tb_stop(db, cpu);
-    gen_tb_end(tb, cflags, icount_start_insn, db->num_insns);
+    gen_tb_end(db->tb, 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.  */
    tb->size = db->pc_next - db->pc_first;
    tb->icount = db->num_insns;

+#ifdef DEBUG_DISAS
    if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)
        && qemu_log_in_addr_range(db->pc_first)) {
        FILE *logfile = qemu_log_trylock();
@@ -227,13 +133,14 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
            qemu_log_unlock(logfile);
        }
    }
+#endif
 }

 static void *translator_access(CPUArchState *env, DisasContextBase *db,
-                               vaddr pc, size_t len)
+                               target_ulong pc, size_t len)
 {
    void *host;
-    vaddr base, end;
+    target_ulong base, end;
    TranslationBlock *tb;

    tb = db->tb;
@@ -251,36 +158,22 @@ 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];
        }

@@ -294,27 +187,6 @@ static void *translator_access(CPUArchState *env, DisasContextBase *db,
    return host + (pc - base);
 }

-static void plugin_insn_append(abi_ptr pc, const void *from, size_t size)
-{
-#ifdef CONFIG_PLUGIN
-    struct qemu_plugin_insn *insn = tcg_ctx->plugin_insn;
-    abi_ptr off;
-
-    if (insn == NULL) {
-        return;
-    }
-    off = pc - insn->vaddr;
-    if (off < insn->data->len) {
-        g_byte_array_set_size(insn->data, off);
-    } else if (off > insn->data->len) {
-        /* we have an unexpected gap */
-        g_assert_not_reached();
-    }
-
-    insn->data = g_byte_array_append(insn->data, from, size);
-#endif
-}
-
 uint8_t translator_ldub(CPUArchState *env, DisasContextBase *db, abi_ptr pc)
 {
    uint8_t ret;
@@ -373,8 +245,3 @@ uint64_t translator_ldq(CPUArchState *env, DisasContextBase *db, abi_ptr pc)
    plugin_insn_append(pc, &plug, sizeof(ret));
    return ret;
 }
-
-void translator_fake_ldb(uint8_t insn8, abi_ptr pc)
-{
-    plugin_insn_append(pc, &insn8, sizeof(insn8));
-}
--- a/accel/tcg/user-exec-stub.c
+++ b/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)
--- a/accel/tcg/user-exec.c
+++ b/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;
@@ -770,7 +721,7 @@ int page_unprotect(target_ulong address, uintptr_t pc)
    return current_tb_invalidated ? 2 : 1;
 }

-static int probe_access_internal(CPUArchState *env, vaddr addr,
+static int probe_access_internal(CPUArchState *env, target_ulong addr,
                                 int fault_size, MMUAccessType access_type,
                                 bool nonfault, uintptr_t ra)
 {
@@ -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);
@@ -812,7 +759,7 @@ static int probe_access_internal(CPUArchState *env, vaddr addr,
    cpu_loop_exit_sigsegv(env_cpu(env), addr, access_type, maperr, ra);
 }

-int probe_access_flags(CPUArchState *env, vaddr addr, int size,
+int probe_access_flags(CPUArchState *env, target_ulong addr, int size,
                       MMUAccessType access_type, int mmu_idx,
                       bool nonfault, void **phost, uintptr_t ra)
 {
@@ -820,23 +767,23 @@ 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;
 }

-void *probe_access(CPUArchState *env, vaddr addr, int size,
+void *probe_access(CPUArchState *env, target_ulong addr, int size,
                   MMUAccessType access_type, int mmu_idx, uintptr_t ra)
 {
    int flags;

    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;
 }

-tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, vaddr addr,
+tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr,
                                        void **hostp)
 {
    int flags;
@@ -940,185 +887,296 @@ 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,
-                            MemOp mop, uintptr_t ra, MMUAccessType type)
+/*
+ * Verify that we have passed the correct MemOp to the correct function.
+ *
+ * We could present one function to target code, and dispatch based on
+ * the MemOp, but so far we have worked hard to avoid an indirect function
+ * call along the memory path.
+ */
+static void validate_memop(MemOpIdx oi, MemOp expected)
 {
+#ifdef CONFIG_DEBUG_TCG
+    MemOp have = get_memop(oi) & (MO_SIZE | MO_BSWAP);
+    assert(have == expected);
+#endif
+}
+
+void helper_unaligned_ld(CPUArchState *env, target_ulong addr)
+{
+    cpu_loop_exit_sigbus(env_cpu(env), addr, MMU_DATA_LOAD, GETPC());
+}
+
+void helper_unaligned_st(CPUArchState *env, target_ulong addr)
+{
+    cpu_loop_exit_sigbus(env_cpu(env), addr, MMU_DATA_STORE, GETPC());
+}
+
+static void *cpu_mmu_lookup(CPUArchState *env, target_ulong addr,
+                            MemOpIdx oi, uintptr_t ra, MMUAccessType type)
+{
+    MemOp mop = get_memop(oi);
    int a_bits = get_alignment_bits(mop);
    void *ret;

    /* 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)
+uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr,
+                    MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
    uint8_t ret;

-    cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
-    haddr = cpu_mmu_lookup(cpu, addr, get_memop(oi), ra, access_type);
+    validate_memop(oi, MO_UB);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
    ret = ldub_p(haddr);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
    return ret;
 }

-static uint16_t do_ld2_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                           uintptr_t ra, MMUAccessType access_type)
+uint16_t cpu_ldw_be_mmu(CPUArchState *env, abi_ptr addr,
+                        MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
    uint16_t ret;
-    MemOp mop = get_memop(oi);

-    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);
+    validate_memop(oi, MO_BEUW);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = lduw_be_p(haddr);
    clear_helper_retaddr();
-
-    if (mop & MO_BSWAP) {
-        ret = bswap16(ret);
-    }
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
    return ret;
 }

-static uint32_t do_ld4_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                           uintptr_t ra, MMUAccessType access_type)
+uint32_t cpu_ldl_be_mmu(CPUArchState *env, abi_ptr addr,
+                        MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
    uint32_t ret;
-    MemOp mop = get_memop(oi);

-    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);
+    validate_memop(oi, MO_BEUL);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = ldl_be_p(haddr);
    clear_helper_retaddr();
-
-    if (mop & MO_BSWAP) {
-        ret = bswap32(ret);
-    }
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
    return ret;
 }

-static uint64_t do_ld8_mmu(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                           uintptr_t ra, MMUAccessType access_type)
+uint64_t cpu_ldq_be_mmu(CPUArchState *env, abi_ptr addr,
+                        MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
    uint64_t ret;
-    MemOp mop = get_memop(oi);

-    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);
+    validate_memop(oi, MO_BEUQ);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = ldq_be_p(haddr);
    clear_helper_retaddr();
-
-    if (mop & MO_BSWAP) {
-        ret = bswap64(ret);
-    }
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
    return ret;
 }

-static Int128 do_ld16_mmu(CPUState *cpu, abi_ptr addr,
-                          MemOpIdx oi, uintptr_t ra)
+uint16_t cpu_ldw_le_mmu(CPUArchState *env, abi_ptr addr,
+                        MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint16_t ret;
+
+    validate_memop(oi, MO_LEUW);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = lduw_le_p(haddr);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+uint32_t cpu_ldl_le_mmu(CPUArchState *env, abi_ptr addr,
+                        MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint32_t ret;
+
+    validate_memop(oi, MO_LEUL);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = ldl_le_p(haddr);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+uint64_t cpu_ldq_le_mmu(CPUArchState *env, abi_ptr addr,
+                        MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint64_t ret;
+
+    validate_memop(oi, MO_LEUQ);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = ldq_le_p(haddr);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+    return ret;
+}
+
+Int128 cpu_ld16_be_mmu(CPUArchState *env, abi_ptr addr,
+                       MemOpIdx oi, 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);
+    validate_memop(oi, MO_128 | MO_BE);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    memcpy(&ret, haddr, 16);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);

-    if (mop & MO_BSWAP) {
+    if (!HOST_BIG_ENDIAN) {
        ret = bswap128(ret);
    }
    return ret;
 }

-static void do_st1_mmu(CPUState *cpu, vaddr addr, uint8_t val,
+Int128 cpu_ld16_le_mmu(CPUArchState *env, abi_ptr addr,
                       MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
+    Int128 ret;

-    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, get_memop(oi), ra, MMU_DATA_STORE);
+    validate_memop(oi, MO_128 | MO_LE);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    memcpy(&ret, haddr, 16);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+
+    if (HOST_BIG_ENDIAN) {
+        ret = bswap128(ret);
+    }
+    return ret;
+}
+
+void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,
+                 MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+
+    validate_memop(oi, MO_UB);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
    stb_p(haddr, val);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
 }

-static void do_st2_mmu(CPUState *cpu, vaddr addr, uint16_t val,
-                       MemOpIdx oi, uintptr_t ra)
+void cpu_stw_be_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
+                    MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
-    MemOp mop = get_memop(oi);

-    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
-
-    if (mop & MO_BSWAP) {
-        val = bswap16(val);
-    }
-    store_atom_2(cpu, ra, haddr, mop, val);
+    validate_memop(oi, MO_BEUW);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    stw_be_p(haddr, val);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
 }

-static void do_st4_mmu(CPUState *cpu, vaddr addr, uint32_t val,
-                       MemOpIdx oi, uintptr_t ra)
+void cpu_stl_be_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
+                    MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
-    MemOp mop = get_memop(oi);

-    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
-
-    if (mop & MO_BSWAP) {
-        val = bswap32(val);
-    }
-    store_atom_4(cpu, ra, haddr, mop, val);
+    validate_memop(oi, MO_BEUL);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    stl_be_p(haddr, val);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
 }

-static void do_st8_mmu(CPUState *cpu, vaddr addr, uint64_t val,
-                       MemOpIdx oi, uintptr_t ra)
+void cpu_stq_be_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
+                    MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
-    MemOp mop = get_memop(oi);

-    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
-
-    if (mop & MO_BSWAP) {
-        val = bswap64(val);
-    }
-    store_atom_8(cpu, ra, haddr, mop, val);
+    validate_memop(oi, MO_BEUQ);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    stq_be_p(haddr, val);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
 }

-static void do_st16_mmu(CPUState *cpu, vaddr addr, Int128 val,
-                        MemOpIdx oi, uintptr_t ra)
+void cpu_stw_le_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
+                    MemOpIdx oi, uintptr_t ra)
 {
    void *haddr;
-    MemOpIdx mop = get_memop(oi);

-    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
-    haddr = cpu_mmu_lookup(cpu, addr, mop, ra, MMU_DATA_STORE);
+    validate_memop(oi, MO_LEUW);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    stw_le_p(haddr, val);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}

-    if (mop & MO_BSWAP) {
+void cpu_stl_le_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+
+    validate_memop(oi, MO_LEUL);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    stl_le_p(haddr, val);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+void cpu_stq_le_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
+                    MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+
+    validate_memop(oi, MO_LEUQ);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    stq_le_p(haddr, val);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+void cpu_st16_be_mmu(CPUArchState *env, abi_ptr addr,
+                     Int128 val, MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+
+    validate_memop(oi, MO_128 | MO_BE);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    if (!HOST_BIG_ENDIAN) {
        val = bswap128(val);
    }
-    store_atom_16(cpu, ra, haddr, mop, val);
+    memcpy(haddr, &val, 16);
    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+}
+
+void cpu_st16_le_mmu(CPUArchState *env, abi_ptr addr,
+                     Int128 val, MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+
+    validate_memop(oi, MO_128 | MO_LE);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE);
+    if (HOST_BIG_ENDIAN) {
+        val = bswap128(val);
+    }
+    memcpy(haddr, &val, 16);
+    clear_helper_retaddr();
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
 }

 uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr ptr)
@@ -1161,70 +1219,16 @@ uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr ptr)
    return ret;
 }

-uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr,
-                         MemOpIdx oi, uintptr_t ra)
-{
-    void *haddr;
-    uint8_t ret;
-
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_INST_FETCH);
-    ret = ldub_p(haddr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr,
-                          MemOpIdx oi, uintptr_t ra)
-{
-    void *haddr;
-    uint16_t ret;
-
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_INST_FETCH);
-    ret = lduw_p(haddr);
-    clear_helper_retaddr();
-    if (get_memop(oi) & MO_BSWAP) {
-        ret = bswap16(ret);
-    }
-    return ret;
-}
-
-uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr,
-                          MemOpIdx oi, uintptr_t ra)
-{
-    void *haddr;
-    uint32_t ret;
-
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_INST_FETCH);
-    ret = ldl_p(haddr);
-    clear_helper_retaddr();
-    if (get_memop(oi) & MO_BSWAP) {
-        ret = bswap32(ret);
-    }
-    return ret;
-}
-
-uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
-                          MemOpIdx oi, uintptr_t ra)
-{
-    void *haddr;
-    uint64_t ret;
-
-    haddr = cpu_mmu_lookup(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
-    ret = ldq_p(haddr);
-    clear_helper_retaddr();
-    if (get_memop(oi) & MO_BSWAP) {
-        ret = bswap64(ret);
-    }
-    return ret;
-}
-
 #include "ldst_common.c.inc"

 /*
 * Do not allow unaligned operations to proceed.  Return the host address.
+ *
+ * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE.
 */
-static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
-                               int size, uintptr_t retaddr)
+static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
+                               MemOpIdx oi, int size, int prot,
+                               uintptr_t retaddr)
 {
    MemOp mop = get_memop(oi);
    int a_bits = get_alignment_bits(mop);
@@ -1232,15 +1236,16 @@ 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);
+        MMUAccessType t = prot == PAGE_READ ? MMU_DATA_LOAD : MMU_DATA_STORE;
+        cpu_loop_exit_sigbus(env_cpu(env), addr, t, 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 +1275,7 @@ static void *atomic_mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi,
 #include "atomic_template.h"
 #endif

-#if defined(CONFIG_ATOMIC128) || HAVE_CMPXCHG128
+#if HAVE_ATOMIC128 || HAVE_CMPXCHG128
 #define DATA_SIZE 16
 #include "atomic_template.h"
 #endif
--- a/audio/alsaaudio.c
+++ b/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),
--- a/audio/audio-hmp-cmds.c
+++ b/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;
    }

--- a/audio/audio.c
+++ b/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);
@@ -1736,36 +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'\n", 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;
-            drvname = AudiodevDriver_str(dev->driver);
-            driver = audio_driver_lookup(drvname);
-            if (!audio_driver_init(s, driver, dev, NULL)) {
-                break;
-            }
-            QSIMPLEQ_REMOVE_HEAD(&default_audiodevs, next);
        }
    }
+    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;
@@ -1773,51 +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)
@@ -1839,8 +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) {
@@ -1861,8 +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));

@@ -1896,9 +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)
@@ -2021,9 +2061,6 @@ void audio_create_pdos(Audiodev *dev)
 #ifdef CONFIG_AUDIO_PA
        CASE(PA, pa, Pa);
 #endif
-#ifdef CONFIG_AUDIO_PIPEWIRE
-        CASE(PIPEWIRE, pipewire, Pipewire);
-#endif
 #ifdef CONFIG_AUDIO_SDL
        CASE(SDL, sdl, Sdl);
 #endif
@@ -2144,24 +2181,17 @@ 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)
@@ -2223,7 +2253,7 @@ 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) {
@@ -2232,7 +2262,6 @@ AudioState *audio_state_by_name(const char *name, Error **errp)
            return s;
        }
    }
-    error_setg(errp, "audiodev '%s' not found", name);
    return NULL;
 }

--- a/audio/audio.h
+++ b/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)         \
--- a/audio/audio_int.h
+++ b/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);
--- a/audio/audio_legacy.c
+++ b/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)
+{
+    unsigned long long ret;
+    if (parse_uint_full(str, &ret, 10) || 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);
+}
--- a/audio/audio_template.h
+++ b/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);
@@ -369,10 +362,6 @@ AudiodevPerDirectionOptions *glue(audio_get_pdo_, TYPE)(Audiodev *dev)
    case AUDIODEV_DRIVER_PA:
        return qapi_AudiodevPaPerDirectionOptions_base(dev->u.pa.TYPE);
 #endif
-#ifdef CONFIG_AUDIO_PIPEWIRE
-    case AUDIODEV_DRIVER_PIPEWIRE:
-        return qapi_AudiodevPipewirePerDirectionOptions_base(dev->u.pipewire.TYPE);
-#endif
 #ifdef CONFIG_AUDIO_SDL
    case AUDIODEV_DRIVER_SDL:
        return qapi_AudiodevSdlPerDirectionOptions_base(dev->u.sdl.TYPE);
--- a/audio/coreaudio.m
+++ b/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),
--- a/audio/dbusaudio.c
+++ b/audio/dbusaudio.c
@@ -29,11 +29,7 @@
 #include "qemu/timer.h"
 #include "qemu/dbus.h"

-#ifdef G_OS_UNIX
 #include <gio/gunixfdlist.h>
-#endif
-
-#include "ui/dbus.h"
 #include "ui/dbus-display1.h"

 #define AUDIO_CAP "dbus"
@@ -395,7 +391,7 @@ 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);

@@ -448,9 +444,7 @@ listener_in_vanished_cb(GDBusConnection *connection,
 static gboolean
 dbus_audio_register_listener(AudioState *s,
                             GDBusMethodInvocation *invocation,
-#ifdef G_OS_UNIX
                             GUnixFDList *fd_list,
-#endif
                             GVariant *arg_listener,
                             bool out)
 {
@@ -477,11 +471,6 @@ dbus_audio_register_listener(AudioState *s,
        return DBUS_METHOD_INVOCATION_HANDLED;
    }

-#ifdef G_OS_WIN32
-    if (!dbus_win32_import_socket(invocation, arg_listener, &fd)) {
-        return DBUS_METHOD_INVOCATION_HANDLED;
-    }
-#else
    fd = g_unix_fd_list_get(fd_list, g_variant_get_handle(arg_listener), &err);
    if (err) {
        g_dbus_method_invocation_return_error(invocation,
@@ -491,7 +480,6 @@ dbus_audio_register_listener(AudioState *s,
                                              err->message);
        return DBUS_METHOD_INVOCATION_HANDLED;
    }
-#endif

    socket = g_socket_new_from_fd(fd, &err);
    if (err) {
@@ -500,28 +488,15 @@ dbus_audio_register_listener(AudioState *s,
                                              DBUS_DISPLAY_ERROR_FAILED,
                                              "Couldn't make a socket: %s",
                                              err->message);
-#ifdef G_OS_WIN32
-        closesocket(fd);
-#else
-        close(fd);
-#endif
        return DBUS_METHOD_INVOCATION_HANDLED;
    }
    socket_conn = g_socket_connection_factory_create_connection(socket);
    if (out) {
        qemu_dbus_display1_audio_complete_register_out_listener(
-            da->iface, invocation
-#ifdef G_OS_UNIX
-            , NULL
-#endif
-            );
+            da->iface, invocation, NULL);
    } else {
        qemu_dbus_display1_audio_complete_register_in_listener(
-            da->iface, invocation
-#ifdef G_OS_UNIX
-            , NULL
-#endif
-            );
+            da->iface, invocation, NULL);
    }

    listener_conn =
@@ -599,32 +574,22 @@ dbus_audio_register_listener(AudioState *s,
 static gboolean
 dbus_audio_register_out_listener(AudioState *s,
                                 GDBusMethodInvocation *invocation,
-#ifdef G_OS_UNIX
                                 GUnixFDList *fd_list,
-#endif
                                 GVariant *arg_listener)
 {
    return dbus_audio_register_listener(s, invocation,
-#ifdef G_OS_UNIX
-                                        fd_list,
-#endif
-                                        arg_listener, true);
+                                        fd_list, arg_listener, true);

 }

 static gboolean
 dbus_audio_register_in_listener(AudioState *s,
                                GDBusMethodInvocation *invocation,
-#ifdef G_OS_UNIX
                                GUnixFDList *fd_list,
-#endif
                                GVariant *arg_listener)
 {
    return dbus_audio_register_listener(s, invocation,
-#ifdef G_OS_UNIX
-                                        fd_list,
-#endif
-                                        arg_listener, false);
+                                        fd_list, arg_listener, false);
 }

 static void
@@ -676,6 +641,7 @@ 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),
--- a/audio/dsoundaudio.c
+++ b/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),
--- a/audio/jackaudio.c
+++ b/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),
--- a/audio/meson.build
+++ b/audio/meson.build
@@ -1,14 +1,15 @@
-system_ss.add([spice_headers, files('audio.c')])
-system_ss.add(files(
+softmmu_ss.add([spice_headers, files('audio.c')])
+softmmu_ss.add(files(
  'audio-hmp-cmds.c',
+  'audio_legacy.c',
  'mixeng.c',
  'noaudio.c',
  'wavaudio.c',
  'wavcapture.c',
 ))

-system_ss.add(when: coreaudio, if_true: files('coreaudio.m'))
-system_ss.add(when: dsound, if_true: files('dsoundaudio.c', 'audio_win_int.c'))
+softmmu_ss.add(when: coreaudio, if_true: files('coreaudio.m'))
+softmmu_ss.add(when: dsound, if_true: files('dsoundaudio.c', 'audio_win_int.c'))

 audio_modules = {}
 foreach m : [
@@ -18,7 +19,6 @@ foreach m : [
  ['sdl', sdl, files('sdlaudio.c')],
  ['jack', jack, files('jackaudio.c')],
  ['sndio', sndio, files('sndioaudio.c')],
-  ['pipewire', pipewire, files('pwaudio.c')],
  ['spice', spice, files('spiceaudio.c')]
 ]
  if m[1].found()
@@ -30,7 +30,7 @@ endforeach

 if dbus_display
    module_ss = ss.source_set()
-    module_ss.add(when: [gio, pixman], if_true: files('dbusaudio.c'))
+    module_ss.add(when: gio, if_true: files('dbusaudio.c'))
    audio_modules += {'dbus': module_ss}
 endif

--- a/audio/mixeng.h
+++ b/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];

--- a/audio/noaudio.c
+++ b/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),
--- a/audio/ossaudio.c
+++ b/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),
--- a/audio/paaudio.c
+++ b/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),
--- a/audio/pwaudio.c
+++ b/audio/pwaudio.c
@@ -1,858 +0,0 @@
-/*
- * QEMU PipeWire audio driver
- *
- * Copyright (c) 2023 Red Hat Inc.
- *
- * Author: Dorinda Bassey       <dbassey@redhat.com>
- *
- * SPDX-License-Identifier: GPL-2.0-or-later
- */
-
-#include "qemu/osdep.h"
-#include "qemu/module.h"
-#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>
-#include <spa/param/props.h>
-
-#include <pipewire/pipewire.h>
-#include "trace.h"
-
-#define AUDIO_CAP "pipewire"
-#define RINGBUFFER_SIZE    (1u << 22)
-#define RINGBUFFER_MASK    (RINGBUFFER_SIZE - 1)
-
-#include "audio_int.h"
-
-typedef struct pwvolume {
-    uint32_t channels;
-    float values[SPA_AUDIO_MAX_CHANNELS];
-} pwvolume;
-
-typedef struct pwaudio {
-    Audiodev *dev;
-    struct pw_thread_loop *thread_loop;
-    struct pw_context *context;
-
-    struct pw_core *core;
-    struct spa_hook core_listener;
-    int last_seq, pending_seq, error;
-} pwaudio;
-
-typedef struct PWVoice {
-    pwaudio *g;
-    struct pw_stream *stream;
-    struct spa_hook stream_listener;
-    struct spa_audio_info_raw info;
-    uint32_t highwater_mark;
-    uint32_t frame_size, req;
-    struct spa_ringbuffer ring;
-    uint8_t buffer[RINGBUFFER_SIZE];
-
-    pwvolume volume;
-    bool muted;
-} PWVoice;
-
-typedef struct PWVoiceOut {
-    HWVoiceOut hw;
-    PWVoice v;
-} PWVoiceOut;
-
-typedef struct PWVoiceIn {
-    HWVoiceIn hw;
-    PWVoice v;
-} PWVoiceIn;
-
-#define PW_VOICE_IN(v) ((PWVoiceIn *)v)
-#define PW_VOICE_OUT(v) ((PWVoiceOut *)v)
-
-static void
-stream_destroy(void *data)
-{
-    PWVoice *v = (PWVoice *) data;
-    spa_hook_remove(&v->stream_listener);
-    v->stream = NULL;
-}
-
-/* output data processing function to read stuffs from the buffer */
-static void
-playback_on_process(void *data)
-{
-    PWVoice *v = data;
-    void *p;
-    struct pw_buffer *b;
-    struct spa_buffer *buf;
-    uint32_t req, index, n_bytes;
-    int32_t avail;
-
-    assert(v->stream);
-
-    /* obtain a buffer to read from */
-    b = pw_stream_dequeue_buffer(v->stream);
-    if (b == NULL) {
-        error_report("out of buffers: %s", strerror(errno));
-        return;
-    }
-
-    buf = b->buffer;
-    p = buf->datas[0].data;
-    if (p == NULL) {
-        return;
-    }
-    /* calculate the total no of bytes to read data from buffer */
-    req = b->requested * v->frame_size;
-    if (req == 0) {
-        req = v->req;
-    }
-    n_bytes = SPA_MIN(req, buf->datas[0].maxsize);
-
-    /* get no of available bytes to read data from buffer */
-    avail = spa_ringbuffer_get_read_index(&v->ring, &index);
-
-    if (avail <= 0) {
-        PWVoiceOut *vo = container_of(data, PWVoiceOut, v);
-        audio_pcm_info_clear_buf(&vo->hw.info, p, n_bytes / v->frame_size);
-    } else {
-        if ((uint32_t) avail < n_bytes) {
-            /*
-             * PipeWire immediately calls this callback again if we provide
-             * less than n_bytes. Then audio_pcm_info_clear_buf() fills the
-             * rest of the buffer with silence.
-             */
-            n_bytes = avail;
-        }
-
-        spa_ringbuffer_read_data(&v->ring,
-                                    v->buffer, RINGBUFFER_SIZE,
-                                    index & RINGBUFFER_MASK, p, n_bytes);
-
-        index += n_bytes;
-        spa_ringbuffer_read_update(&v->ring, index);
-
-    }
-    buf->datas[0].chunk->offset = 0;
-    buf->datas[0].chunk->stride = v->frame_size;
-    buf->datas[0].chunk->size = n_bytes;
-
-    /* queue the buffer for playback */
-    pw_stream_queue_buffer(v->stream, b);
-}
-
-/* output data processing function to generate stuffs in the buffer */
-static void
-capture_on_process(void *data)
-{
-    PWVoice *v = (PWVoice *) data;
-    void *p;
-    struct pw_buffer *b;
-    struct spa_buffer *buf;
-    int32_t filled;
-    uint32_t index, offs, n_bytes;
-
-    assert(v->stream);
-
-    /* obtain a buffer */
-    b = pw_stream_dequeue_buffer(v->stream);
-    if (b == NULL) {
-        error_report("out of buffers: %s", strerror(errno));
-        return;
-    }
-
-    /* Write data into buffer */
-    buf = b->buffer;
-    p = buf->datas[0].data;
-    if (p == NULL) {
-        return;
-    }
-    offs = SPA_MIN(buf->datas[0].chunk->offset, buf->datas[0].maxsize);
-    n_bytes = SPA_MIN(buf->datas[0].chunk->size, buf->datas[0].maxsize - offs);
-
-    filled = spa_ringbuffer_get_write_index(&v->ring, &index);
-
-
-    if (filled < 0) {
-        error_report("%p: underrun write:%u filled:%d", p, index, filled);
-    } else {
-        if ((uint32_t) filled + n_bytes > RINGBUFFER_SIZE) {
-            error_report("%p: overrun write:%u filled:%d + size:%u > max:%u",
-            p, index, filled, n_bytes, RINGBUFFER_SIZE);
-        }
-    }
-    spa_ringbuffer_write_data(&v->ring,
-                                v->buffer, RINGBUFFER_SIZE,
-                                index & RINGBUFFER_MASK,
-                                SPA_PTROFF(p, offs, void), n_bytes);
-    index += n_bytes;
-    spa_ringbuffer_write_update(&v->ring, index);
-
-    /* queue the buffer for playback */
-    pw_stream_queue_buffer(v->stream, b);
-}
-
-static void
-on_stream_state_changed(void *data, enum pw_stream_state old,
-                        enum pw_stream_state state, const char *error)
-{
-    PWVoice *v = (PWVoice *) data;
-
-    trace_pw_state_changed(pw_stream_get_node_id(v->stream),
-                           pw_stream_state_as_string(state));
-}
-
-static const struct pw_stream_events capture_stream_events = {
-    PW_VERSION_STREAM_EVENTS,
-    .destroy = stream_destroy,
-    .state_changed = on_stream_state_changed,
-    .process = capture_on_process
-};
-
-static const struct pw_stream_events playback_stream_events = {
-    PW_VERSION_STREAM_EVENTS,
-    .destroy = stream_destroy,
-    .state_changed = on_stream_state_changed,
-    .process = playback_on_process
-};
-
-static size_t
-qpw_read(HWVoiceIn *hw, void *data, size_t len)
-{
-    PWVoiceIn *pw = (PWVoiceIn *) hw;
-    PWVoice *v = &pw->v;
-    pwaudio *c = v->g;
-    const char *error = NULL;
-    size_t l;
-    int32_t avail;
-    uint32_t index;
-
-    pw_thread_loop_lock(c->thread_loop);
-    if (pw_stream_get_state(v->stream, &error) != PW_STREAM_STATE_STREAMING) {
-        /* wait for stream to become ready */
-        l = 0;
-        goto done_unlock;
-    }
-    /* get no of available bytes to read data from buffer */
-    avail = spa_ringbuffer_get_read_index(&v->ring, &index);
-
-    trace_pw_read(avail, index, len);
-
-    if (avail < (int32_t) len) {
-        len = avail;
-    }
-
-    spa_ringbuffer_read_data(&v->ring,
-                             v->buffer, RINGBUFFER_SIZE,
-                             index & RINGBUFFER_MASK, data, len);
-    index += len;
-    spa_ringbuffer_read_update(&v->ring, index);
-    l = len;
-
-done_unlock:
-    pw_thread_loop_unlock(c->thread_loop);
-    return l;
-}
-
-static size_t qpw_buffer_get_free(HWVoiceOut *hw)
-{
-    PWVoiceOut *pw = (PWVoiceOut *)hw;
-    PWVoice *v = &pw->v;
-    pwaudio *c = v->g;
-    const char *error = NULL;
-    int32_t filled, avail;
-    uint32_t index;
-
-    pw_thread_loop_lock(c->thread_loop);
-    if (pw_stream_get_state(v->stream, &error) != PW_STREAM_STATE_STREAMING) {
-        /* wait for stream to become ready */
-        avail = 0;
-        goto done_unlock;
-    }
-
-    filled = spa_ringbuffer_get_write_index(&v->ring, &index);
-    avail = v->highwater_mark - filled;
-
-done_unlock:
-    pw_thread_loop_unlock(c->thread_loop);
-    return avail;
-}
-
-static size_t
-qpw_write(HWVoiceOut *hw, void *data, size_t len)
-{
-    PWVoiceOut *pw = (PWVoiceOut *) hw;
-    PWVoice *v = &pw->v;
-    pwaudio *c = v->g;
-    const char *error = NULL;
-    int32_t filled, avail;
-    uint32_t index;
-
-    pw_thread_loop_lock(c->thread_loop);
-    if (pw_stream_get_state(v->stream, &error) != PW_STREAM_STATE_STREAMING) {
-        /* wait for stream to become ready */
-        len = 0;
-        goto done_unlock;
-    }
-    filled = spa_ringbuffer_get_write_index(&v->ring, &index);
-    avail = v->highwater_mark - filled;
-
-    trace_pw_write(filled, avail, index, len);
-
-    if (len > avail) {
-        len = avail;
-    }
-
-    if (filled < 0) {
-        error_report("%p: underrun write:%u filled:%d", pw, index, filled);
-    } else {
-        if ((uint32_t) filled + len > RINGBUFFER_SIZE) {
-            error_report("%p: overrun write:%u filled:%d + size:%zu > max:%u",
-            pw, index, filled, len, RINGBUFFER_SIZE);
-        }
-    }
-
-    spa_ringbuffer_write_data(&v->ring,
-                                v->buffer, RINGBUFFER_SIZE,
-                                index & RINGBUFFER_MASK, data, len);
-    index += len;
-    spa_ringbuffer_write_update(&v->ring, index);
-
-done_unlock:
-    pw_thread_loop_unlock(c->thread_loop);
-    return len;
-}
-
-static int
-audfmt_to_pw(AudioFormat fmt, int endianness)
-{
-    int format;
-
-    switch (fmt) {
-    case AUDIO_FORMAT_S8:
-        format = SPA_AUDIO_FORMAT_S8;
-        break;
-    case AUDIO_FORMAT_U8:
-        format = SPA_AUDIO_FORMAT_U8;
-        break;
-    case AUDIO_FORMAT_S16:
-        format = endianness ? SPA_AUDIO_FORMAT_S16_BE : SPA_AUDIO_FORMAT_S16_LE;
-        break;
-    case AUDIO_FORMAT_U16:
-        format = endianness ? SPA_AUDIO_FORMAT_U16_BE : SPA_AUDIO_FORMAT_U16_LE;
-        break;
-    case AUDIO_FORMAT_S32:
-        format = endianness ? SPA_AUDIO_FORMAT_S32_BE : SPA_AUDIO_FORMAT_S32_LE;
-        break;
-    case AUDIO_FORMAT_U32:
-        format = endianness ? SPA_AUDIO_FORMAT_U32_BE : SPA_AUDIO_FORMAT_U32_LE;
-        break;
-    case AUDIO_FORMAT_F32:
-        format = endianness ? SPA_AUDIO_FORMAT_F32_BE : SPA_AUDIO_FORMAT_F32_LE;
-        break;
-    default:
-        dolog("Internal logic error: Bad audio format %d\n", fmt);
-        format = SPA_AUDIO_FORMAT_U8;
-        break;
-    }
-    return format;
-}
-
-static AudioFormat
-pw_to_audfmt(enum spa_audio_format fmt, int *endianness,
-             uint32_t *sample_size)
-{
-    switch (fmt) {
-    case SPA_AUDIO_FORMAT_S8:
-        *sample_size = 1;
-        return AUDIO_FORMAT_S8;
-    case SPA_AUDIO_FORMAT_U8:
-        *sample_size = 1;
-        return AUDIO_FORMAT_U8;
-    case SPA_AUDIO_FORMAT_S16_BE:
-        *sample_size = 2;
-        *endianness = 1;
-        return AUDIO_FORMAT_S16;
-    case SPA_AUDIO_FORMAT_S16_LE:
-        *sample_size = 2;
-        *endianness = 0;
-        return AUDIO_FORMAT_S16;
-    case SPA_AUDIO_FORMAT_U16_BE:
-        *sample_size = 2;
-        *endianness = 1;
-        return AUDIO_FORMAT_U16;
-    case SPA_AUDIO_FORMAT_U16_LE:
-        *sample_size = 2;
-        *endianness = 0;
-        return AUDIO_FORMAT_U16;
-    case SPA_AUDIO_FORMAT_S32_BE:
-        *sample_size = 4;
-        *endianness = 1;
-        return AUDIO_FORMAT_S32;
-    case SPA_AUDIO_FORMAT_S32_LE:
-        *sample_size = 4;
-        *endianness = 0;
-        return AUDIO_FORMAT_S32;
-    case SPA_AUDIO_FORMAT_U32_BE:
-        *sample_size = 4;
-        *endianness = 1;
-        return AUDIO_FORMAT_U32;
-    case SPA_AUDIO_FORMAT_U32_LE:
-        *sample_size = 4;
-        *endianness = 0;
-        return AUDIO_FORMAT_U32;
-    case SPA_AUDIO_FORMAT_F32_BE:
-        *sample_size = 4;
-        *endianness = 1;
-        return AUDIO_FORMAT_F32;
-    case SPA_AUDIO_FORMAT_F32_LE:
-        *sample_size = 4;
-        *endianness = 0;
-        return AUDIO_FORMAT_F32;
-    default:
-        *sample_size = 1;
-        dolog("Internal logic error: Bad spa_audio_format %d\n", fmt);
-        return AUDIO_FORMAT_U8;
-    }
-}
-
-static int
-qpw_stream_new(pwaudio *c, PWVoice *v, const char *stream_name,
-               const char *name, enum spa_direction dir)
-{
-    int res;
-    uint32_t n_params;
-    const struct spa_pod *params[2];
-    uint8_t buffer[1024];
-    struct spa_pod_builder b;
-    uint64_t buf_samples;
-    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
-                    * 3 / 4 / 1000000;
-    pw_properties_setf(props, PW_KEY_NODE_LATENCY, "%" PRIu64 "/%u",
-                       buf_samples, v->info.rate);
-
-    trace_pw_period(buf_samples, v->info.rate);
-    if (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;
-    }
-
-    if (dir == SPA_DIRECTION_INPUT) {
-        pw_stream_add_listener(v->stream,
-                            &v->stream_listener, &capture_stream_events, v);
-    } else {
-        pw_stream_add_listener(v->stream,
-                            &v->stream_listener, &playback_stream_events, v);
-    }
-
-    n_params = 0;
-    spa_pod_builder_init(&b, buffer, sizeof(buffer));
-    params[n_params++] = spa_format_audio_raw_build(&b,
-                            SPA_PARAM_EnumFormat,
-                            &v->info);
-
-    /* connect the stream to a sink or source */
-    res = pw_stream_connect(v->stream,
-                            dir ==
-                            SPA_DIRECTION_INPUT ? PW_DIRECTION_INPUT :
-                            PW_DIRECTION_OUTPUT, PW_ID_ANY,
-                            PW_STREAM_FLAG_AUTOCONNECT |
-                            PW_STREAM_FLAG_INACTIVE |
-                            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;
-    }
-
-    return 0;
-}
-
-static void
-qpw_set_position(uint32_t channels, uint32_t position[SPA_AUDIO_MAX_CHANNELS])
-{
-    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) {
-    case 8:
-        position[6] = SPA_AUDIO_CHANNEL_SL;
-        position[7] = SPA_AUDIO_CHANNEL_SR;
-        /* fallthrough */
-    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 */
-    case 2:
-        position[0] = SPA_AUDIO_CHANNEL_FL;
-        position[1] = SPA_AUDIO_CHANNEL_FR;
-        break;
-    case 1:
-        position[0] = SPA_AUDIO_CHANNEL_MONO;
-        break;
-    default:
-        dolog("Internal error: unsupported channel count %d\n", channels);
-    }
-}
-
-static int
-qpw_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
-{
-    PWVoiceOut *pw = (PWVoiceOut *) hw;
-    PWVoice *v = &pw->v;
-    struct audsettings obt_as = *as;
-    pwaudio *c = v->g = drv_opaque;
-    AudiodevPipewireOptions *popts = &c->dev->u.pipewire;
-    AudiodevPipewirePerDirectionOptions *ppdo = popts->out;
-    int r;
-
-    pw_thread_loop_lock(c->thread_loop);
-
-    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 =
-        pw_to_audfmt(v->info.format, &obt_as.endianness, &v->frame_size);
-    v->frame_size *= as->nchannels;
-
-    v->req = (uint64_t)c->dev->timer_period * v->info.rate
-        * 1 / 2 / 1000000 * v->frame_size;
-
-    /* call the function that creates a new stream for playback */
-    r = qpw_stream_new(c, v, ppdo->stream_name ? : c->dev->id,
-                       ppdo->name, SPA_DIRECTION_OUTPUT);
-    if (r < 0) {
-        pw_thread_loop_unlock(c->thread_loop);
-        return -1;
-    }
-
-    /* report the audio format we support */
-    audio_pcm_init_info(&hw->info, &obt_as);
-
-    /* report the buffer size to qemu */
-    hw->samples = audio_buffer_frames(
-        qapi_AudiodevPipewirePerDirectionOptions_base(ppdo), &obt_as, 46440);
-    v->highwater_mark = MIN(RINGBUFFER_SIZE,
-                            (ppdo->has_latency ? ppdo->latency : 46440)
-                            * (uint64_t)v->info.rate / 1000000 * v->frame_size);
-
-    pw_thread_loop_unlock(c->thread_loop);
-    return 0;
-}
-
-static int
-qpw_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
-{
-    PWVoiceIn *pw = (PWVoiceIn *) hw;
-    PWVoice *v = &pw->v;
-    struct audsettings obt_as = *as;
-    pwaudio *c = v->g = drv_opaque;
-    AudiodevPipewireOptions *popts = &c->dev->u.pipewire;
-    AudiodevPipewirePerDirectionOptions *ppdo = popts->in;
-    int r;
-
-    pw_thread_loop_lock(c->thread_loop);
-
-    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 =
-        pw_to_audfmt(v->info.format, &obt_as.endianness, &v->frame_size);
-    v->frame_size *= as->nchannels;
-
-    /* call the function that creates a new stream for recording */
-    r = qpw_stream_new(c, v, ppdo->stream_name ? : c->dev->id,
-                       ppdo->name, SPA_DIRECTION_INPUT);
-    if (r < 0) {
-        pw_thread_loop_unlock(c->thread_loop);
-        return -1;
-    }
-
-    /* report the audio format we support */
-    audio_pcm_init_info(&hw->info, &obt_as);
-
-    /* report the buffer size to qemu */
-    hw->samples = audio_buffer_frames(
-        qapi_AudiodevPipewirePerDirectionOptions_base(ppdo), &obt_as, 46440);
-
-    pw_thread_loop_unlock(c->thread_loop);
-    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);
-}
-
-static void
-qpw_fini_in(HWVoiceIn *hw)
-{
-    qpw_voice_fini(&PW_VOICE_IN(hw)->v);
-}
-
-static void
-qpw_voice_set_enabled(PWVoice *v, bool enable)
-{
-    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);
-}
-
-static void
-qpw_voice_set_volume(PWVoice *v, Volume *vol)
-{
-    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 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);
-}
-
-static int wait_resync(pwaudio *pw)
-{
-    int res;
-    pw->pending_seq = pw_core_sync(pw->core, PW_ID_CORE, pw->pending_seq);
-
-    while (true) {
-        pw_thread_loop_wait(pw->thread_loop);
-
-        res = pw->error;
-        if (res < 0) {
-            pw->error = 0;
-            return res;
-        }
-        if (pw->pending_seq == pw->last_seq) {
-            break;
-        }
-    }
-    return 0;
-}
-
-static void
-on_core_error(void *data, uint32_t id, int seq, int res, const char *message)
-{
-    pwaudio *pw = data;
-
-    error_report("error id:%u seq:%d res:%d (%s): %s",
-                id, seq, res, spa_strerror(res), message);
-
-    /* stop and exit the thread loop */
-    pw_thread_loop_signal(pw->thread_loop, FALSE);
-}
-
-static void
-on_core_done(void *data, uint32_t id, int seq)
-{
-    pwaudio *pw = data;
-    assert(id == PW_ID_CORE);
-    pw->last_seq = seq;
-    if (pw->pending_seq == seq) {
-        /* stop and exit the thread loop */
-        pw_thread_loop_signal(pw->thread_loop, FALSE);
-    }
-}
-
-static const struct pw_core_events core_events = {
-    PW_VERSION_CORE_EVENTS,
-    .done = on_core_done,
-    .error = on_core_error,
-};
-
-static void *
-qpw_audio_init(Audiodev *dev, Error **errp)
-{
-    g_autofree pwaudio *pw = g_new0(pwaudio, 1);
-
-    assert(dev->driver == AUDIODEV_DRIVER_PIPEWIRE);
-    trace_pw_audio_init();
-
-    pw_init(NULL, NULL);
-
-    pw->dev = dev;
-    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");
-        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");
-        goto fail;
-    }
-
-    if (pw_thread_loop_start(pw->thread_loop) < 0) {
-        error_setg_errno(errp, errno, "Could not start PipeWire loop");
-        goto fail;
-    }
-
-    pw_thread_loop_lock(pw->thread_loop);
-
-    pw->core = pw_context_connect(pw->context, NULL, 0);
-    if (pw->core == NULL) {
-        pw_thread_loop_unlock(pw->thread_loop);
-        goto fail_error;
-    }
-
-    if (pw_core_add_listener(pw->core, &pw->core_listener,
-                             &core_events, pw) < 0) {
-        pw_thread_loop_unlock(pw->thread_loop);
-        goto fail_error;
-    }
-    if (wait_resync(pw) < 0) {
-        pw_thread_loop_unlock(pw->thread_loop);
-    }
-
-    pw_thread_loop_unlock(pw->thread_loop);
-
-    return g_steal_pointer(&pw);
-
-fail_error:
-    error_setg(errp, "Failed to initialize PW context");
-fail:
-    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);
-    return NULL;
-}
-
-static void
-qpw_audio_fini(void *opaque)
-{
-    pwaudio *pw = opaque;
-
-    if (pw->thread_loop) {
-        pw_thread_loop_stop(pw->thread_loop);
-    }
-
-    if (pw->core) {
-        spa_hook_remove(&pw->core_listener);
-        spa_zero(pw->core_listener);
-        pw_core_disconnect(pw->core);
-    }
-
-    if (pw->context) {
-        pw_context_destroy(pw->context);
-    }
-    pw_thread_loop_destroy(pw->thread_loop);
-
-    g_free(pw);
-}
-
-static struct audio_pcm_ops qpw_pcm_ops = {
-    .init_out = qpw_init_out,
-    .fini_out = qpw_fini_out,
-    .write = qpw_write,
-    .buffer_get_free = qpw_buffer_get_free,
-    .run_buffer_out = audio_generic_run_buffer_out,
-    .enable_out = qpw_enable_out,
-    .volume_out = qpw_volume_out,
-    .volume_in = qpw_volume_in,
-
-    .init_in = qpw_init_in,
-    .fini_in = qpw_fini_in,
-    .read = qpw_read,
-    .run_buffer_in = audio_generic_run_buffer_in,
-    .enable_in = qpw_enable_in
-};
-
-static struct audio_driver pw_audio_driver = {
-    .name = "pipewire",
-    .descr = "http://www.pipewire.org/",
-    .init = qpw_audio_init,
-    .fini = qpw_audio_fini,
-    .pcm_ops = &qpw_pcm_ops,
-    .max_voices_out = INT_MAX,
-    .max_voices_in = INT_MAX,
-    .voice_size_out = sizeof(PWVoiceOut),
-    .voice_size_in = sizeof(PWVoiceIn),
-};
-
-static void
-register_audio_pw(void)
-{
-    audio_driver_register(&pw_audio_driver);
-}
-
-type_init(register_audio_pw);
--- a/audio/sdlaudio.c
+++ b/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),
--- a/audio/sndioaudio.c
+++ b/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),
--- a/audio/spiceaudio.c
+++ b/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;
 }

--- a/audio/trace-events
+++ b/audio/trace-events
@@ -18,14 +18,6 @@ dbus_audio_register(const char *s, const char *dir) "sender = %s, dir = %s"
 dbus_audio_put_buffer_out(size_t len) "len = %zu"
 dbus_audio_read(size_t len) "len = %zu"

-# pwaudio.c
-pw_state_changed(int nodeid, const char *s) "node id: %d stream state: %s"
-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"
-
 # audio.c
 audio_timer_start(int interval) "interval %d ms"
 audio_timer_stop(void) ""
--- a/audio/wavaudio.c
+++ b/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),
--- a/backends/cryptodev-vhost-user.c
+++ b/backends/cryptodev-vhost-user.c
@@ -232,9 +232,9 @@ static void cryptodev_vhost_user_init(
    backend->conf.max_auth_key_len = VHOST_USER_MAX_AUTH_KEY_LEN;
 }

-static int64_t cryptodev_vhost_user_crypto_create_session(
+static int64_t cryptodev_vhost_user_sym_create_session(
           CryptoDevBackend *backend,
-           CryptoDevBackendSessionInfo *sess_info,
+           CryptoDevBackendSymSessionInfo *sess_info,
           uint32_t queue_index, Error **errp)
 {
    CryptoDevBackendClient *cc =
@@ -266,17 +266,18 @@ static int cryptodev_vhost_user_create_session(
           void *opaque)
 {
    uint32_t op_code = sess_info->op_code;
+    CryptoDevBackendSymSessionInfo *sym_sess_info;
    int64_t ret;
    Error *local_error = NULL;
    int status;

    switch (op_code) {
    case VIRTIO_CRYPTO_CIPHER_CREATE_SESSION:
-    case VIRTIO_CRYPTO_AKCIPHER_CREATE_SESSION:
    case VIRTIO_CRYPTO_HASH_CREATE_SESSION:
    case VIRTIO_CRYPTO_MAC_CREATE_SESSION:
    case VIRTIO_CRYPTO_AEAD_CREATE_SESSION:
-        ret = cryptodev_vhost_user_crypto_create_session(backend, sess_info,
+        sym_sess_info = &sess_info->u.sym_sess_info;
+        ret = cryptodev_vhost_user_sym_create_session(backend, sym_sess_info,
                   queue_index, &local_error);
        break;

--- a/backends/cryptodev.c
+++ b/backends/cryptodev.c
@@ -252,11 +252,10 @@ 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 +271,7 @@ 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 +283,7 @@ 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 +341,8 @@ 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);
    }

@@ -532,7 +532,7 @@ static int cryptodev_backend_stats_query(Object *obj, void *data)

    entry = g_new0(StatsResult, 1);
    entry->provider = STATS_PROVIDER_CRYPTODEV;
-    entry->qom_path = object_get_canonical_path(obj);
+    entry->qom_path = g_strdup(object_get_canonical_path(obj));
    entry->stats = stats_list;
    QAPI_LIST_PREPEND(*stats_results, entry);

--- a/backends/dbus-vmstate.c
+++ b/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");
    }
 }
--- a/backends/hostmem-file.c
+++ b/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)

@@ -29,11 +27,9 @@ struct HostMemoryBackendFile {

    char *mem_path;
    uint64_t align;
-    uint64_t offset;
    bool discard_data;
    bool is_pmem;
    bool readonly;
-    OnOffAuto rom;
 };

 static void
@@ -56,39 +52,13 @@ 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->readonly, errp);
    g_free(name);
 #endif
 }
@@ -155,36 +125,6 @@ static void file_memory_backend_set_align(Object *o, Visitor *v,
    fb->align = val;
 }

-static void file_memory_backend_get_offset(Object *o, Visitor *v,
-                                          const char *name, void *opaque,
-                                          Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-    uint64_t val = fb->offset;
-
-    visit_type_size(v, name, &val, errp);
-}
-
-static void file_memory_backend_set_offset(Object *o, Visitor *v,
-                                          const char *name, void *opaque,
-                                          Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-    uint64_t val;
-
-    if (host_memory_backend_mr_inited(backend)) {
-        error_setg(errp, "cannot change property '%s' of %s", name,
-                   object_get_typename(o));
-        return;
-    }
-
-    if (!visit_type_size(v, name, &val, errp)) {
-        return;
-    }
-    fb->offset = val;
-}
-
 #ifdef CONFIG_LIBPMEM
 static bool file_memory_backend_get_pmem(Object *o, Error **errp)
 {
@@ -228,32 +168,6 @@ 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);
@@ -283,12 +197,6 @@ file_backend_class_init(ObjectClass *oc, void *data)
        file_memory_backend_get_align,
        file_memory_backend_set_align,
        NULL, NULL);
-    object_class_property_add(oc, "offset", "int",
-        file_memory_backend_get_offset,
-        file_memory_backend_set_offset,
-        NULL, NULL);
-    object_class_property_set_description(oc, "offset",
-        "Offset into the target file (ex: 1G)");
 #ifdef CONFIG_LIBPMEM
    object_class_property_add_bool(oc, "pmem",
        file_memory_backend_get_pmem, file_memory_backend_set_pmem);
@@ -296,10 +204,6 @@ 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)
--- a/backends/meson.build
+++ b/backends/meson.build
@@ -1,4 +1,4 @@
-system_ss.add([files(
+softmmu_ss.add([files(
  'cryptodev-builtin.c',
  'cryptodev-hmp-cmds.c',
  'cryptodev.c',
@@ -10,20 +10,20 @@ system_ss.add([files(
  'confidential-guest-support.c',
 ), numa])

-system_ss.add(when: 'CONFIG_POSIX', if_true: files('rng-random.c'))
-system_ss.add(when: 'CONFIG_POSIX', if_true: files('hostmem-file.c'))
-system_ss.add(when: 'CONFIG_LINUX', if_true: files('hostmem-memfd.c'))
+softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files('rng-random.c'))
+softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files('hostmem-file.c'))
+softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files('hostmem-memfd.c'))
 if keyutils.found()
-    system_ss.add(keyutils, files('cryptodev-lkcf.c'))
+    softmmu_ss.add(keyutils, files('cryptodev-lkcf.c'))
 endif
 if have_vhost_user
-  system_ss.add(when: 'CONFIG_VIRTIO', if_true: files('vhost-user.c'))
+  softmmu_ss.add(when: 'CONFIG_VIRTIO', if_true: files('vhost-user.c'))
 endif
-system_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c'))
+softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c'))
 if have_vhost_user_crypto
-  system_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost-user.c'))
+  softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost-user.c'))
 endif
-system_ss.add(when: gio, if_true: files('dbus-vmstate.c'))
-system_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c'))
+softmmu_ss.add(when: gio, if_true: files('dbus-vmstate.c'))
+softmmu_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c'))

 subdir('tpm')
--- a/backends/tpm/meson.build
+++ b/backends/tpm/meson.build
@@ -1,6 +1,6 @@
 if have_tpm
-  system_ss.add(files('tpm_backend.c'))
-  system_ss.add(files('tpm_util.c'))
-  system_ss.add(when: 'CONFIG_TPM_PASSTHROUGH', if_true: files('tpm_passthrough.c'))
-  system_ss.add(when: 'CONFIG_TPM_EMULATOR', if_true: files('tpm_emulator.c'))
+  softmmu_ss.add(files('tpm_backend.c'))
+  softmmu_ss.add(files('tpm_util.c'))
+  softmmu_ss.add(when: 'CONFIG_TPM_PASSTHROUGH', if_true: files('tpm_passthrough.c'))
+  softmmu_ss.add(when: 'CONFIG_TPM_EMULATOR', if_true: files('tpm_emulator.c'))
 endif
--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .1.50
 .0.4