Update version for 4.1.1 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
mirror: Keep mirror_top_bs drained after dropping permissions
2019-11-14 12:04:03 -06:00 · 2019-11-12 16:31:49 -06:00 · 2019-11-12 16:31:38 -06:00 · 2019-11-12 16:23:54 -06:00 · 2019-11-12 16:23:54 -06:00 · 2019-11-12 16:23:49 -06:00
4035 changed files with 98623 additions and 226051 deletions
@@ -22,21 +22,6 @@ macos_task:
  install_script:
    - brew install pkg-config python gnu-sed glib pixman make sdl2
  script:
-    - mkdir build
-    - cd build
-    - ../configure --python=/usr/local/bin/python3 || { cat config.log; exit 1; }
-    - gmake -j$(sysctl -n hw.ncpu)
-    - gmake check -j$(sysctl -n hw.ncpu)
-
-macos_xcode_task:
-  osx_instance:
-    # this is an alias for the latest Xcode
-    image: mojave-xcode
-  install_script:
-    - brew install pkg-config gnu-sed glib pixman make sdl2
-  script:
-    - mkdir build
-    - cd build
-    - ../configure --cc=clang || { cat config.log; exit 1; }
+    - ./configure --python=/usr/local/bin/python3 || { cat config.log; exit 1; }
    - gmake -j$(sysctl -n hw.ncpu)
    - gmake check -j$(sysctl -n hw.ncpu)
@@ -1,34 +0,0 @@
-# Configuration for Repo Lockdown - https://github.com/dessant/repo-lockdown
-
-# Close issues and pull requests
-close: true
-
-# Lock issues and pull requests
-lock: true
-
-issues:
-  comment: |
-    Thank you for your interest in the QEMU project.
-
-    This repository is a read-only mirror of the project's master
-    repostories hosted on https://git.qemu.org/git/qemu.git.
-    The project does not process issues filed on GitHub.
-
-    The project issues are tracked on Launchpad:
-    https://bugs.launchpad.net/qemu
-
-    QEMU welcomes bug report contributions. You can file new ones on:
-    https://bugs.launchpad.net/qemu/+filebug
-
-pulls:
-  comment: |
-    Thank you for your interest in the QEMU project.
-
-    This repository is a read-only mirror of the project's master
-    repostories hosted on https://git.qemu.org/git/qemu.git.
-    The project does not process merge requests filed on GitHub.
-
-    QEMU welcomes contributions of code (either fixing bugs or adding new
-    functionality). However, we get a lot of patches, and so we have some
-    guidelines about contributing on the project website:
-    https://www.qemu.org/contribute/
@@ -6,7 +6,6 @@
 /config-target.*
 /config.status
 /config-temp
-/tools/virtiofsd/50-qemu-virtiofsd.json
 /elf2dmp
 /trace-events-all
 /trace/generated-events.h
@@ -38,14 +37,15 @@
 /qapi/qapi-emit-events.[ch]
 /qapi/qapi-events-*.[ch]
 /qapi/qapi-events.[ch]
-/qapi/qapi-init-commands.[ch]
 /qapi/qapi-introspect.[ch]
 /qapi/qapi-types-*.[ch]
 /qapi/qapi-types.[ch]
 /qapi/qapi-visit-*.[ch]
-!/qapi/qapi-visit-core.c
 /qapi/qapi-visit.[ch]
 /qapi/qapi-doc.texi
+/qemu-doc.html
+/qemu-doc.info
+/qemu-doc.txt
 /qemu-edid
 /qemu-img
 /qemu-nbd
@@ -65,8 +65,6 @@
 /scsi/qemu-pr-helper
 /vhost-user-scsi
 /vhost-user-blk
-/vhost-user-gpu
-/vhost-user-input
 /fsdev/virtfs-proxy-helper
 *.tmp
 *.[1-9]
@@ -133,7 +131,6 @@
 /docs/interop/qemu-qmp-ref.info*
 /docs/interop/qemu-qmp-ref.txt
 /docs/version.texi
-/contrib/vhost-user-gpu/50-qemu-gpu.json
 *.tps
 .stgit-*
 .git-submodule-status
@@ -1,49 +0,0 @@
-docker-edk2:
- stage: build
- rules: # Only run this job when the Dockerfile is modified
- - changes:
-   - .gitlab-ci-edk2.yml
-   - .gitlab-ci.d/edk2/Dockerfile
-   when: always
- image: docker:19.03.1
- services:
- - docker:19.03.1-dind
- variables:
-  GIT_DEPTH: 3
-  IMAGE_TAG: $CI_REGISTRY_IMAGE:edk2-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
- script:
- - docker pull $IMAGE_TAG || true
- - docker build --cache-from $IMAGE_TAG --tag $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA
-                                        --tag $IMAGE_TAG .gitlab-ci.d/edk2
- - docker push $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA
- - docker push $IMAGE_TAG
-
-build-edk2:
- rules: # Only run this job when ...
- - changes: # ... roms/edk2/ is modified (submodule updated)
-   - roms/edk2/*
-   when: always
- - if: '$CI_COMMIT_REF_NAME =~ /^edk2/' # or the branch/tag starts with 'edk2'
-   when: always
- - if: '$CI_COMMIT_MESSAGE =~ /edk2/i' # or last commit description contains 'EDK2'
-   when: always
- artifacts:
-   paths: # 'artifacts.zip' will contains the following files:
-   - pc-bios/edk2*bz2
-   - pc-bios/edk2-licenses.txt
-   - edk2-stdout.log
-   - edk2-stderr.log
- image: $CI_REGISTRY_IMAGE:edk2-cross-build
- variables:
-   GIT_DEPTH: 3
- script: # Clone the required submodules and build EDK2
- - git submodule update --init roms/edk2
- - git -C roms/edk2 submodule update --init
- - export JOBS=$(($(getconf _NPROCESSORS_ONLN) + 1))
- - echo "=== Using ${JOBS} simultaneous jobs ==="
- - make -j${JOBS} -C roms efi 2>&1 1>edk2-stdout.log | tee -a edk2-stderr.log >&2
@@ -1,63 +0,0 @@
-docker-opensbi:
- stage: build
- rules: # Only run this job when the Dockerfile is modified
- - changes:
-   - .gitlab-ci-opensbi.yml
-   - .gitlab-ci.d/opensbi/Dockerfile
-   when: always
- image: docker:19.03.1
- services:
- - docker:19.03.1-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
- script:
- - docker pull $IMAGE_TAG || true
- - docker build --cache-from $IMAGE_TAG --tag $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA
-                                        --tag $IMAGE_TAG .gitlab-ci.d/opensbi
- - docker push $CI_REGISTRY_IMAGE:$CI_COMMIT_SHA
- - docker push $IMAGE_TAG
-
-build-opensbi:
- rules: # Only run this job when ...
- - changes: # ... roms/opensbi/ is modified (submodule updated)
-   - roms/opensbi/*
-   when: always
- - if: '$CI_COMMIT_REF_NAME =~ /^opensbi/' # or the branch/tag starts with 'opensbi'
-   when: always
- - if: '$CI_COMMIT_MESSAGE =~ /opensbi/i' # or last commit description contains 'OpenSBI'
-   when: always
- artifacts:
-   paths: # 'artifacts.zip' will contains the following files:
-   - pc-bios/opensbi-riscv32-sifive_u-fw_jump.bin
-   - pc-bios/opensbi-riscv32-virt-fw_jump.bin
-   - pc-bios/opensbi-riscv64-sifive_u-fw_jump.bin
-   - pc-bios/opensbi-riscv64-virt-fw_jump.bin
-   - opensbi32-virt-stdout.log
-   - opensbi32-virt-stderr.log
-   - opensbi64-virt-stdout.log
-   - opensbi64-virt-stderr.log
-   - opensbi32-sifive_u-stdout.log
-   - opensbi32-sifive_u-stderr.log
-   - opensbi64-sifive_u-stdout.log
-   - opensbi64-sifive_u-stderr.log
- image: $CI_REGISTRY_IMAGE:opensbi-cross-build
- variables:
-   GIT_DEPTH: 3
- script: # Clone the required submodules and build OpenSBI
- - git submodule update --init roms/opensbi
- - export JOBS=$(($(getconf _NPROCESSORS_ONLN) + 1))
- - echo "=== Using ${JOBS} simultaneous jobs ==="
- - make -j${JOBS} -C roms/opensbi clean
- - make -j${JOBS} -C roms opensbi32-virt 2>&1 1>opensbi32-virt-stdout.log | tee -a opensbi32-virt-stderr.log >&2
- - make -j${JOBS} -C roms/opensbi clean
- - make -j${JOBS} -C roms opensbi64-virt 2>&1 1>opensbi64-virt-stdout.log | tee -a opensbi64-virt-stderr.log >&2
- - make -j${JOBS} -C roms/opensbi clean
- - make -j${JOBS} -C roms opensbi32-sifive_u 2>&1 1>opensbi32-sifive_u-stdout.log | tee -a opensbi32-sifive_u-stderr.log >&2
- - make -j${JOBS} -C roms/opensbi clean
- - make -j${JOBS} -C roms opensbi64-sifive_u 2>&1 1>opensbi64-sifive_u-stdout.log | tee -a opensbi64-sifive_u-stderr.log >&2
@@ -1,27 +0,0 @@
-#
-# Docker image to cross-compile EDK2 firmware binaries
-#
-FROM ubuntu:16.04
-
-MAINTAINER Philippe Mathieu-Daudé <philmd@redhat.com>
-
-# Install packages required to build EDK2
-RUN apt update \
-    && \
-    \
-    DEBIAN_FRONTEND=noninteractive \
-    apt install --assume-yes --no-install-recommends \
-        build-essential \
-        ca-certificates \
-        dos2unix \
-        gcc-aarch64-linux-gnu \
-        gcc-arm-linux-gnueabi \
-        git \
-        iasl \
-        make \
-        nasm \
-        python \
-        uuid-dev \
-    && \
-    \
-    rm -rf /var/lib/apt/lists/*
@@ -1,33 +0,0 @@
-#
-# Docker image to cross-compile OpenSBI firmware binaries
-#
-FROM ubuntu:18.04
-
-MAINTAINER Bin Meng <bmeng.cn@gmail.com>
-
-# Install packages required to build OpenSBI
-RUN apt update \
-    && \
-    \
-    DEBIAN_FRONTEND=noninteractive \
-    apt install --assume-yes --no-install-recommends \
-        build-essential \
-        ca-certificates \
-        git \
-        make \
-        wget \
-    && \
-    \
-    rm -rf /var/lib/apt/lists/*
-
-# Manually install the kernel.org "Crosstool" based toolchains for gcc-8.3
-RUN wget -O - \
-    https://mirrors.edge.kernel.org/pub/tools/crosstool/files/bin/x86_64/8.3.0/x86_64-gcc-8.3.0-nolibc-riscv32-linux.tar.xz \
-    | tar -C /opt -xJ
-RUN wget -O - \
-    https://mirrors.edge.kernel.org/pub/tools/crosstool/files/bin/x86_64/8.3.0/x86_64-gcc-8.3.0-nolibc-riscv64-linux.tar.xz \
-    | tar -C /opt -xJ
-
-# Export the toolchains to the system path
-ENV PATH="/opt/gcc-8.3.0-nolibc/riscv32-linux/bin:${PATH}"
-ENV PATH="/opt/gcc-8.3.0-nolibc/riscv64-linux/bin:${PATH}"
@@ -1,7 +1,3 @@
-include:
-  - local: '/.gitlab-ci-edk2.yml'
-  - local: '/.gitlab-ci-opensbi.yml'
-
 before_script:
 - apt-get update -qq
 - apt-get install -y -qq flex bison libglib2.0-dev libpixman-1-dev genisoimage
@@ -9,10 +5,8 @@ before_script:
 build-system1:
 script:
 - apt-get install -y -qq libgtk-3-dev libvte-dev nettle-dev libcacard-dev
-      libusb-dev libvde-dev libspice-protocol-dev libgl1-mesa-dev libvdeplug-dev
- - mkdir build
- - cd build
- - ../configure --enable-werror --target-list="aarch64-softmmu alpha-softmmu
+      libusb-dev libvde-dev libspice-protocol-dev libgl1-mesa-dev
+ - ./configure --enable-werror --target-list="aarch64-softmmu alpha-softmmu
      cris-softmmu hppa-softmmu lm32-softmmu moxie-softmmu microblazeel-softmmu
      mips64el-softmmu m68k-softmmu ppc-softmmu riscv64-softmmu sparc-softmmu"
 - make -j2
@@ -22,10 +16,7 @@ build-system2:
 script:
 - apt-get install -y -qq libsdl2-dev libgcrypt-dev libbrlapi-dev libaio-dev
      libfdt-dev liblzo2-dev librdmacm-dev libibverbs-dev libibumad-dev
-      libzstd-dev
- - mkdir build
- - cd build
- - ../configure --enable-werror --target-list="tricore-softmmu unicore32-softmmu
+ - ./configure --enable-werror --target-list="tricore-softmmu unicore32-softmmu
      microblaze-softmmu mips-softmmu riscv32-softmmu s390x-softmmu sh4-softmmu
      sparc64-softmmu x86_64-softmmu xtensa-softmmu nios2-softmmu or1k-softmmu"
 - make -j2
@@ -33,9 +24,7 @@ build-system2:

 build-disabled:
 script:
- - mkdir build
- - cd build
- - ../configure --enable-werror --disable-rdma --disable-slirp --disable-curl
+ - ./configure --enable-werror --disable-rdma --disable-slirp --disable-curl
      --disable-capstone --disable-live-block-migration --disable-glusterfs
      --disable-replication --disable-coroutine-pool --disable-smartcard
      --disable-guest-agent --disable-curses --disable-libxml2 --disable-tpm
@@ -47,38 +36,37 @@ build-disabled:

 build-tcg-disabled:
 script:
- - apt-get install -y -qq clang libgtk-3-dev libusb-dev
- - mkdir build
- - cd build
- - ../configure --cc=clang --enable-werror --disable-tcg --audio-drv-list=""
+ - apt-get install -y -qq clang libgtk-3-dev libbluetooth-dev libusb-dev
+ - ./configure --cc=clang --enable-werror --disable-tcg --audio-drv-list=""
 - make -j2
 - make check-unit
 - make check-qapi-schema
 - cd tests/qemu-iotests/
 - ./check -raw 001 002 003 004 005 008 009 010 011 012 021 025 032 033 048
-            052 063 077 086 101 104 106 113 148 150 151 152 157 159 160 163
-            170 171 183 184 192 194 197 208 215 221 222 226 227 236 253 277
- - ./check -qcow2 028 051 056 057 058 065 067 068 082 085 091 095 096 102 122
-            124 132 139 142 144 145 151 152 155 157 165 194 196 197 200 202
-            208 209 215 216 218 222 227 234 246 247 248 250 254 255 257 258
-            260 261 262 263 264 270 272 273 277 279
+            052 063 077 086 101 104 106 113 147 148 150 151 152 157 159 160
+            163 170 171 183 184 192 194 197 205 208 215 221 222 226 227 236
+ - ./check -qcow2 001 002 003 004 005 007 008 009 010 011 012 013 017 018 019
+            020 021 022 024 025 027 028 029 031 032 033 034 035 036 037 038
+            039 040 042 043 046 047 048 049 050 051 052 053 054 056 057 058
+            060 061 062 063 065 066 067 068 069 071 072 073 074 079 080 082
+            085 086 089 090 091 095 096 097 098 099 102 103 104 105 107 108
+            110 111 114 117 120 122 124 126 127 129 130 132 133 134 137 138
+            139 140 141 142 143 144 145 147 150 151 152 154 155 156 157 158
+            161 165 170 172 174 176 177 179 184 186 187 190 192 194 195 196
+            197 200 202 203 205 208 209 214 215 216 217 218 222 226 227 229 234

 build-user:
 script:
- - mkdir build
- - cd build
- - ../configure --enable-werror --disable-system --disable-guest-agent
+ - ./configure --enable-werror --disable-system --disable-guest-agent
               --disable-capstone --disable-slirp --disable-fdt
 - make -j2
 - make run-tcg-tests-i386-linux-user run-tcg-tests-x86_64-linux-user

 build-clang:
 script:
- - apt-get install -y -qq clang libsdl2-dev libattr1-dev libcap-ng-dev
+ - apt-get install -y -qq clang libsdl2-dev
      xfslibs-dev libiscsi-dev libnfs-dev libseccomp-dev gnutls-dev librbd-dev
- - mkdir build
- - cd build
- - ../configure --cc=clang --cxx=clang++ --enable-werror
+ - ./configure --cc=clang --cxx=clang++ --enable-werror
      --target-list="alpha-softmmu arm-softmmu m68k-softmmu mips64-softmmu
                     ppc-softmmu s390x-softmmu x86_64-softmmu arm-linux-user"
 - make -j2
@@ -87,18 +75,14 @@ build-clang:
 build-tci:
 script:
 - TARGETS="aarch64 alpha arm hppa m68k microblaze moxie ppc64 s390x x86_64"
- - mkdir build
- - cd build
- - ../configure --enable-tcg-interpreter
+ - ./configure --enable-tcg-interpreter
      --target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)"
 - make -j2
- - make run-tcg-tests-x86_64-softmmu
- - make tests/qtest/boot-serial-test tests/qtest/cdrom-test tests/qtest/pxe-test
+ - make tests/boot-serial-test tests/cdrom-test tests/pxe-test
 - for tg in $TARGETS ; do
     export QTEST_QEMU_BINARY="${tg}-softmmu/qemu-system-${tg}" ;
-     ./tests/qtest/boot-serial-test || exit 1 ;
-     ./tests/qtest/cdrom-test || exit 1 ;
+     ./tests/boot-serial-test || exit 1 ;
+     ./tests/cdrom-test || exit 1 ;
   done
- - QTEST_QEMU_BINARY="x86_64-softmmu/qemu-system-x86_64" ./tests/qtest/pxe-test
- - QTEST_QEMU_BINARY="s390x-softmmu/qemu-system-s390x"
-   ./tests/qtest/pxe-test -m slow
+ - QTEST_QEMU_BINARY="x86_64-softmmu/qemu-system-x86_64" ./tests/pxe-test
+ - QTEST_QEMU_BINARY="s390x-softmmu/qemu-system-s390x" ./tests/pxe-test -m slow
@@ -10,6 +10,9 @@
 [submodule "roms/openbios"]
 	path = roms/openbios
 	url = https://git.qemu.org/git/openbios.git
+[submodule "roms/openhackware"]
+	path = roms/openhackware
+	url = https://git.qemu.org/git/openhackware.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
 	url = https://git.qemu.org/git/qemu-palcode.git
@@ -55,6 +58,3 @@
 [submodule "roms/opensbi"]
 	path = roms/opensbi
 	url = 	https://git.qemu.org/git/opensbi.git
-[submodule "roms/qboot"]
-	path = roms/qboot
-	url = https://github.com/bonzini/qboot
@@ -1,29 +1,23 @@
 # This mailmap fixes up author names/addresses.
-#
-# If you are adding to this file consider if a similar change needs to
-# be made to contrib/gitdm/aliases. They are not however completely
-# analogous. .mailmap is concerned with fixing up damaged author
-# fields where as the gitdm equivalent is more concerned with making
-# sure multiple email addresses get mapped onto the same author.
-#
-# From man git-shortlog the forms are:
-#
-#  Proper Name <commit@email.xx>
-#  <proper@email.xx> <commit@email.xx>
-#  Proper Name <proper@email.xx> <commit@email.xx>
-#  Proper Name <proper@email.xx> Commit Name <commit@email.xx>
-#

 # The first section translates weird addresses from the original git import
 # into proper addresses so that they are counted properly by git shortlog.
 Andrzej Zaborowski <balrogg@gmail.com> balrog <balrog@c046a42c-6fe2-441c-8c8c-71466251a162>
 Anthony Liguori <anthony@codemonkey.ws> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
+Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
 Aurelien Jarno <aurelien@aurel32.net> aurel32 <aurel32@c046a42c-6fe2-441c-8c8c-71466251a162>
 Blue Swirl <blauwirbel@gmail.com> blueswir1 <blueswir1@c046a42c-6fe2-441c-8c8c-71466251a162>
 Edgar E. Iglesias <edgar.iglesias@gmail.com> edgar_igl <edgar_igl@c046a42c-6fe2-441c-8c8c-71466251a162>
 Fabrice Bellard <fabrice@bellard.org> bellard <bellard@c046a42c-6fe2-441c-8c8c-71466251a162>
+James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 Jocelyn Mayer <l_indien@magic.fr> j_mayer <j_mayer@c046a42c-6fe2-441c-8c8c-71466251a162>
 Paul Brook <paul@codesourcery.com> pbrook <pbrook@c046a42c-6fe2-441c-8c8c-71466251a162>
+Yongbok Kim <yongbok.kim@mips.com> <yongbok.kim@imgtec.com>
+Aleksandar Markovic <amarkovic@wavecomp.com> <aleksandar.markovic@mips.com>
+Aleksandar Markovic <amarkovic@wavecomp.com> <aleksandar.markovic@imgtec.com>
+Paul Burton <pburton@wavecomp.com> <paul.burton@mips.com>
+Paul Burton <pburton@wavecomp.com> <paul.burton@imgtec.com>
+Paul Burton <pburton@wavecomp.com> <paul@archlinuxmips.org>
 Thiemo Seufer <ths@networkno.de> ths <ths@c046a42c-6fe2-441c-8c8c-71466251a162>
 malc <av1474@comtv.ru> malc <malc@c046a42c-6fe2-441c-8c8c-71466251a162>

@@ -38,127 +32,8 @@ Ian McKellar <ianloic@google.com> Ian McKellar via Qemu-devel <qemu-devel@nongnu
 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>

-# Next, replace old addresses by a more recent one.
-Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> <aleksandar.markovic@mips.com>
-Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> <aleksandar.markovic@imgtec.com>
-Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> <amarkovic@wavecomp.com>
-Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com> <arikalo@wavecomp.com>
-Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
-James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
-Leif Lindholm <leif@nuviainc.com> <leif.lindholm@linaro.org>
-Paul Burton <pburton@wavecomp.com> <paul.burton@mips.com>
-Paul Burton <pburton@wavecomp.com> <paul.burton@imgtec.com>
-Paul Burton <pburton@wavecomp.com> <paul@archlinuxmips.org>
-Philippe Mathieu-Daudé <philmd@redhat.com> <f4bug@amsat.org>
-Yongbok Kim <yongbok.kim@mips.com> <yongbok.kim@imgtec.com>

 # Also list preferred name forms where people have changed their
 # git author config, or had utf8/latin1 encoding issues.
-Aaron Lindsay <aaron@os.amperecomputing.com>
-Alexey Gerasimenko <x1917x@gmail.com>
-Alex Ivanov <void@aleksoft.net>
-Andreas Färber <afaerber@suse.de>
-Bandan Das <bsd@redhat.com>
-Benjamin MARSILI <mlspirat42@gmail.com>
-Benoît Canet <benoit.canet@gmail.com>
-Benoît Canet <benoit.canet@irqsave.net>
-Benoît Canet <benoit.canet@nodalink.com>
-Boqun Feng <boqun.feng@gmail.com>
-Boqun Feng <boqun.feng@intel.com>
-Brad Smith <brad@comstyle.com>
-Brijesh Singh <brijesh.singh@amd.com>
-Brilly Wu <brillywu@viatech.com.cn>
-Cédric Vincent <cedric.vincent@st.com>
-CheneyLin <linzc@zju.edu.cn>
-Chen Gang <chengang@emindsoft.com.cn>
-Chen Gang <gang.chen.5i5j@gmail.com>
-Chen Gang <gang.chen@sunrus.com.cn>
-Chen Wei-Ren <chenwj@iis.sinica.edu.tw>
-Christophe Lyon <christophe.lyon@st.com>
-Collin L. Walling <walling@linux.ibm.com>
 Daniel P. Berrangé <berrange@redhat.com>
-Eduardo Otubo <otubo@redhat.com>
-Fabrice Desclaux <fabrice.desclaux@cea.fr>
-Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp>
-Fernando Luis Vázquez Cao <fernando@oss.ntt.co.jp>
-Gautham R. Shenoy <ego@in.ibm.com>
-Gautham R. Shenoy <ego@linux.vnet.ibm.com>
-Gonglei (Arei) <arei.gonglei@huawei.com>
-Guang Wang <wang.guang55@zte.com.cn>
-Hailiang Zhang <zhang.zhanghailiang@huawei.com>
-Hervé Poussineau <hpoussin@reactos.org>
-Jakub Jermář <jakub@jermar.eu>
-Jakub Jermář <jakub.jermar@kernkonzept.com>
-Jean-Christophe Dubois <jcd@tribudubois.net>
-Jindřich Makovička <makovick@gmail.com>
-John Arbuckle <programmingkidx@gmail.com>
-Juha Riihimäki <juha.riihimaki@nokia.com>
-Juha Riihimäki <Juha.Riihimaki@nokia.com>
-Jun Li <junmuzi@gmail.com>
-Laurent Vivier <Laurent@lvivier.info>
-Leandro Lupori <leandro.lupori@gmail.com>
-Li Guang <lig.fnst@cn.fujitsu.com>
-Liming Wang <walimisdev@gmail.com>
-linzhecheng <linzc@zju.edu.cn>
-Liran Schour <lirans@il.ibm.com>
-Liu Yu <yu.liu@freescale.com>
-Liu Yu <Yu.Liu@freescale.com>
-Li Zhang <zhlcindy@gmail.com>
-Li Zhang <zhlcindy@linux.vnet.ibm.com>
-Lluís Vilanova <vilanova@ac.upc.edu>
-Lluís Vilanova <xscript@gmx.net>
-Longpeng (Mike) <longpeng2@huawei.com>
-Luc Michel <luc.michel@git.antfield.fr>
-Luc Michel <luc.michel@greensocs.com>
-Marc Marí <marc.mari.barcelo@gmail.com>
-Marc Marí <markmb@redhat.com>
-Michael Avdienko <whitearchey@gmail.com>
-Michael S. Tsirkin <mst@redhat.com>
-Munkyu Im <munkyu.im@samsung.com>
-Nicholas Bellinger <nab@linux-iscsi.org>
-Nicholas Thomas <nick@bytemark.co.uk>
-Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
-Orit Wasserman <owasserm@redhat.com>
-Paolo Bonzini <pbonzini@redhat.com>
-Pavel Dovgaluk <dovgaluk@ispras.ru>
-Pavel Dovgaluk <pavel.dovgaluk@gmail.com>
-Pavel Dovgaluk <Pavel.Dovgaluk@ispras.ru>
-Peter Crosthwaite <crosthwaite.peter@gmail.com>
-Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-Peter Crosthwaite <peter.crosthwaite@xilinx.com>
-Prasad J Pandit <pjp@fedoraproject.org>
-Prasad J Pandit <ppandit@redhat.com>
-Qiao Nuohan <qiaonuohan@cn.fujitsu.com>
 Reimar Döffinger <Reimar.Doeffinger@gmx.de>
-Remy Noel <remy.noel@blade-group.com>
-Roger Pau Monné <roger.pau@citrix.com>
-Shin'ichiro Kawasaki <kawasaki@juno.dti.ne.jp>
-Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
-Sochin Jiang <sochin.jiang@huawei.com>
-Takashi Yoshii <takasi-y@ops.dti.ne.jp>
-Thomas Huth <thuth@redhat.com>
-Thomas Knych <thomaswk@google.com>
-Timothy Baldwin <T.E.Baldwin99@members.leeds.ac.uk>
-Tony Nguyen <tony.nguyen@bt.com>
-Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
-Vibi Sreenivasan <vibi_sreenivasan@cms.com>
-Vijaya Kumar K <vijayak@cavium.com>
-Vijaya Kumar K <Vijaya.Kumar@cavium.com>
-Vijay Kumar <vijaykumar@bravegnu.org>
-Vijay Kumar <vijaykumar@zilogic.com>
-Wang Guang <wang.guang55@zte.com.cn>
-Wenchao Xia <xiawenc@linux.vnet.ibm.com>
-Wenshuang Ma <kevinnma@tencent.com>
-Xiaoqiang Zhao <zxq_yx_007@163.com>
-Xinhua Cao <caoxinhua@huawei.com>
-Xiong Zhang <xiong.y.zhang@intel.com>
-Yin Yin <yin.yin@cs2c.com.cn>
-Yu-Chen Lin <npes87184@gmail.com>
-Yu-Chen Lin <npes87184@gmail.com> <yuchenlin@synology.com>
-YunQiang Su <syq@debian.org>
-YunQiang Su <ysu@wavecomp.com>
-Yuri Pudgorodskiy <yur@virtuozzo.com>
-Zhengui Li <lizhengui@huawei.com>
-Zhenwei Pi <pizhenwei@bytedance.com>
-Zhenwei Pi <zhenwei.pi@youruncloud.com>
-Zhuang Yanying <ann.zhuangyanying@huawei.com>
@@ -1,20 +0,0 @@
-# .readthedocs.yml
-# Read the Docs configuration file
-# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
-
-# Required
-version: 2
-
-# Build documentation in the docs/ directory with Sphinx
-sphinx:
-  configuration: docs/conf.py
-
-# We want all the document formats
-formats: all
-
-# For consistency, we require that QEMU's Sphinx extensions
-# run with at least the same minimum version of Python that
-# we require for other Python in our codebase (our conf.py
-# enforces this, and some code needs it.)
-python:
-  version: 3.5
@@ -35,7 +35,5 @@ build:
    options: "-e HOME=/root"
  ci:
    - unset CC
-    - mkdir build
-    - cd build
-    - ../configure --disable-docs ${QEMU_CONFIGURE_OPTS} --target-list=${TARGET_LIST}
+    - ./configure ${QEMU_CONFIGURE_OPTS} --target-list=${TARGET_LIST}
    - make -j$(($(getconf _NPROCESSORS_ONLN) + 1))
@@ -1,23 +1,11 @@
 # The current Travis default is a VM based 16.04 Xenial on GCE
 # Additional builds with specific requirements for a full VM need to
 # be added as additional matrix: entries later on
-os: linux
 dist: xenial
 language: c
 compiler:
  - gcc
-cache:
-  # There is one cache per branch and compiler version.
-  # characteristics of each job are used to identify the cache:
-  # - OS name (currently, linux, osx, or windows)
-  # - OS distribution (for Linux, xenial, trusty, or precise)
-  # - macOS image name (e.g., xcode7.2)
-  # - Names and values of visible environment variables set in .travis.yml or Settings panel
-  timeout: 1200
-  ccache: true
-  pip: true
-  directories:
-  - $HOME/avocado/data/cache
+cache: ccache


 addons:
@@ -29,7 +17,7 @@ addons:
      - libbrlapi-dev
      - libcap-ng-dev
      - libgcc-4.8-dev
-      - libgnutls28-dev
+      - libgnutls-dev
      - libgtk-3-dev
      - libiscsi-dev
      - liblttng-ust-dev
@@ -37,24 +25,25 @@ addons:
      - libnfs-dev
      - libnss3-dev
      - libpixman-1-dev
-      - libpng-dev
+      - libpng12-dev
      - librados-dev
-      - libsdl2-dev
-      - libsdl2-image-dev
+      - libsdl1.2-dev
      - libseccomp-dev
      - libspice-protocol-dev
      - libspice-server-dev
      - libssh-dev
      - liburcu-dev
      - libusb-1.0-0-dev
-      - libvdeplug-dev
      - libvte-2.91-dev
-      - libzstd-dev
      - sparse
      - uuid-dev
      - gcovr
-      # Tests dependencies
-      - genisoimage
+  homebrew:
+    packages:
+      - glib
+      - pixman
+      - gnu-sed
+    update: true


 # The channel name "irc.oftc.net#qemu" is encrypted against qemu/qemu
@@ -70,274 +59,190 @@ notifications:

 env:
  global:
-    - SRC_DIR=".."
-    - BUILD_DIR="build"
+    - SRC_DIR="."
+    - BUILD_DIR="."
    - BASE_CONFIG="--disable-docs --disable-tools"
-    - TEST_BUILD_CMD=""
-    - TEST_CMD="make check V=1"
+    - TEST_CMD="make check -j3 V=1"
    # 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
-    - G_MESSAGES_DEBUG=error
-
+    - MAIN_SOFTMMU_TARGETS="aarch64-softmmu,arm-softmmu,i386-softmmu,mips-softmmu,mips64-softmmu,ppc64-softmmu,riscv64-softmmu,s390x-softmmu,x86_64-softmmu"

 git:
  # we want to do this ourselves
  submodules: false

-# Common first phase for all steps
-before_install:
-  - if command -v ccache ; then ccache --zero-stats ; fi
-  - export JOBS=$(($(getconf _NPROCESSORS_ONLN) + 1))
-  - echo "=== Using ${JOBS} simultaneous jobs ==="

-# Configure step - may be overridden
 before_script:
  - mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
  - ${SRC_DIR}/configure ${BASE_CONFIG} ${CONFIG} || { cat config.log && exit 1; }
-
-# Main build & test - rarely overridden - controlled by TEST_CMD
 script:
-  - BUILD_RC=0 && make -j${JOBS} || BUILD_RC=$?
-  - |
-    if [ "$BUILD_RC" -eq 0 ] && [ -n "$TEST_BUILD_CMD" ]; then
-        ${TEST_BUILD_CMD} || BUILD_RC=$?
-    else
-        $(exit $BUILD_RC);
-    fi
-  - |
-    if [ "$BUILD_RC" -eq 0 ] ; then
-        ${TEST_CMD} ;
-    else
-        $(exit $BUILD_RC);
-    fi
-after_script:
-  - if command -v ccache ; then ccache --show-stats ; fi
+  - make -j3 && travis_retry ${TEST_CMD}


-jobs:
+matrix:
  include:
-    - name: "GCC static (user)"
-      env:
+    - env:
        - CONFIG="--disable-system --static"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"


    # we split the system builds as it takes a while to build them all
-    - name: "GCC (main-softmmu)"
-      env:
+    - env:
        - CONFIG="--disable-user --target-list=${MAIN_SOFTMMU_TARGETS}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"


-    - name: "GCC (other-softmmu)"
-      env:
-       - CONFIG="--disable-user --target-list-exclude=${MAIN_SOFTMMU_TARGETS}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
+    - env:
+        - CONFIG="--disable-user --target-list-exclude=${MAIN_SOFTMMU_TARGETS}"


    # Just build tools and run minimal unit and softfloat checks
-    - name: "GCC check-softfloat (user)"
-      env:
+    - env:
        - BASE_CONFIG="--enable-tools"
        - CONFIG="--disable-user --disable-system"
-        - TEST_CMD="make check-unit check-softfloat -j${JOBS}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
+        - TEST_CMD="make check-unit check-softfloat -j3"
+
+    - env:
+        - CONFIG="--enable-debug --enable-debug-tcg --disable-user"


-    # --enable-debug implies --enable-debug-tcg, also runs quite a bit slower
-    - name: "GCC debug (main-softmmu)"
-      env:
-        - CONFIG="--enable-debug --target-list=${MAIN_SOFTMMU_TARGETS}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug"
-
-
-    # TCG debug can be run just on its own and is mostly agnostic to user/softmmu distinctions
-    - name: "GCC debug (user)"
-      env:
+    # TCG debug can be run just on it's own and is mostly agnostic to user/softmmu distinctions
+    - env:
        - CONFIG="--enable-debug-tcg --disable-system"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"


-    - name: "GCC some libs disabled (main-softmmu)"
-      env:
+    - env:
        - CONFIG="--disable-linux-aio --disable-cap-ng --disable-attr --disable-brlapi --disable-libusb --disable-replication --target-list=${MAIN_SOFTMMU_TARGETS}"


    # Module builds are mostly of interest to major distros
-    - name: "GCC modules (main-softmmu)"
-      env:
+    - env:
        - CONFIG="--enable-modules --target-list=${MAIN_SOFTMMU_TARGETS}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"


    # Alternate coroutines implementations are only really of interest to KVM users
    # However we can't test against KVM on Travis so we can only run unit tests
-    - name: "check-unit coroutine=ucontext"
-      env:
+    - env:
        - CONFIG="--with-coroutine=ucontext --disable-tcg"
-        - TEST_CMD="make check-unit -j${JOBS} V=1"
+        - TEST_CMD="make check-unit -j3 V=1"


-    - name: "check-unit coroutine=sigaltstack"
-      env:
+    - env:
        - CONFIG="--with-coroutine=sigaltstack --disable-tcg"
-        - TEST_CMD="make check-unit -j${JOBS} V=1"
+        - TEST_CMD="make check-unit -j3 V=1"


    # Check we can build docs and tools (out of tree)
-    - name: "tools and docs (bionic)"
-      dist: bionic
-      env:
+    - env:
        - BUILD_DIR="out-of-tree/build/dir" SRC_DIR="../../.."
        - BASE_CONFIG="--enable-tools --enable-docs"
        - CONFIG="--target-list=x86_64-softmmu,aarch64-linux-user"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
      addons:
        apt:
          packages:
-            - python3-sphinx
+            - python-sphinx
            - texinfo
            - perl


    # Test with Clang for compile portability (Travis uses clang-5.0)
-    - name: "Clang (user)"
-      env:
+    - env:
        - CONFIG="--disable-system"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-clang-default"
      compiler: clang


-    - name: "Clang (main-softmmu)"
-      env:
+    - env:
+        - CONFIG="--disable-user --target-list=${MAIN_SOFTMMU_TARGETS}"
+      compiler: clang
+
+
+    - env:
        - CONFIG="--target-list=${MAIN_SOFTMMU_TARGETS} "
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-clang-sanitize"
      compiler: clang
      before_script:
-        - mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
-        - ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-fsanitize=undefined -Werror" || { cat config.log && exit 1; }
+        - ./configure ${CONFIG} --extra-cflags="-fsanitize=undefined -Werror" || { cat config.log && exit 1; }


-    - name: "Clang (other-softmmu)"
-      env:
+    - env:
        - CONFIG="--disable-user --target-list-exclude=${MAIN_SOFTMMU_TARGETS}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-clang-default"
      compiler: clang


    # gprof/gcov are GCC features
-    - name: "GCC gprof/gcov"
-      env:
+    - env:
        - CONFIG="--enable-gprof --enable-gcov --disable-pie --target-list=${MAIN_SOFTMMU_TARGETS}"
      after_success:
        - ${SRC_DIR}/scripts/travis/coverage-summary.sh


    # We manually include builds which we disable "make check" for
-    - name: "GCC without-default-devices (softmmu)"
-      env:
+    - env:
        - CONFIG="--without-default-devices --disable-user"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
        - TEST_CMD=""


-    # Check the TCG interpreter (TCI)
-    - name: "GCC TCI"
-      env:
-        - CONFIG="--enable-debug-tcg --enable-tcg-interpreter --disable-kvm --disable-containers
-            --target-list=alpha-softmmu,arm-softmmu,hppa-softmmu,m68k-softmmu,microblaze-softmmu,moxie-softmmu,ppc-softmmu,s390x-softmmu,x86_64-softmmu"
-        - TEST_CMD="make check-qtest check-tcg V=1"
+    # We manually include builds which we disable "make check" for
+    - env:
+        - CONFIG="--enable-debug --enable-tcg-interpreter"
+        - TEST_CMD=""


    # We don't need to exercise every backend with every front-end
-    - name: "GCC trace log,simple,syslog (user)"
-      env:
+    - env:
        - CONFIG="--enable-trace-backends=log,simple,syslog --disable-system"
        - TEST_CMD=""


-    - name: "GCC trace ftrace (x86_64-softmmu)"
-      env:
+    - env:
        - CONFIG="--enable-trace-backends=ftrace --target-list=x86_64-softmmu"
        - TEST_CMD=""


-    - name: "GCC trace ust (x86_64-softmmu)"
-      env:
+    - env:
        - CONFIG="--enable-trace-backends=ust --target-list=x86_64-softmmu"
        - TEST_CMD=""


-    # MacOSX builds - cirrus.yml also tests some MacOS builds including latest Xcode
+    # MacOSX builds
+    - env:
+        - CONFIG="--target-list=${MAIN_SOFTMMU_TARGETS}"
+      os: osx
+      osx_image: xcode9.4
+      compiler: clang

-    - name: "OSX Xcode 10.3"
-      env:
-        - BASE_CONFIG="--disable-docs --enable-tools"
+
+    - env:
        - CONFIG="--target-list=i386-softmmu,ppc-softmmu,ppc64-softmmu,m68k-softmmu,x86_64-softmmu"
      os: osx
-      osx_image: xcode10.3
+      osx_image: xcode10.2
      compiler: clang
-      addons:
-        homebrew:
-          packages:
-            - ccache
-            - glib
-            - pixman
-            - gnu-sed
-            - python
-          update: true
-      before_script:
-        - brew link --overwrite python
-        - export PATH="/usr/local/opt/ccache/libexec:$PATH"
-        - mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
-        - ${SRC_DIR}/configure ${BASE_CONFIG} ${CONFIG} || { cat config.log && exit 1; }


    # Python builds
-    - name: "GCC Python 3.5 (x86_64-softmmu)"
-      env:
+    - env:
        - CONFIG="--target-list=x86_64-softmmu"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
      language: python
-      python: 3.5
+      python:
+        - "3.4"


-    - name: "GCC Python 3.6 (x86_64-softmmu)"
-      env:
+    - env:
        - CONFIG="--target-list=x86_64-softmmu"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
      language: python
-      python: 3.6
+      python:
+        - "3.6"


    # Acceptance (Functional) tests
-    - name: "GCC check-acceptance"
-      dist: bionic
-      env:
-        - CONFIG="--enable-tools --target-list=aarch64-softmmu,alpha-softmmu,arm-softmmu,m68k-softmmu,microblaze-softmmu,mips-softmmu,mips64el-softmmu,nios2-softmmu,or1k-softmmu,ppc-softmmu,ppc64-softmmu,s390x-softmmu,sparc-softmmu,x86_64-softmmu,xtensa-softmmu"
+    - env:
+        - CONFIG="--python=/usr/bin/python3 --target-list=x86_64-softmmu,mips-softmmu,mips64el-softmmu,aarch64-softmmu,arm-softmmu,s390x-softmmu,alpha-softmmu"
        - TEST_CMD="make check-acceptance"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-acceptance"
-      after_script:
-        - python3 -c 'import json; r = json.load(open("tests/results/latest/results.json")); [print(t["logfile"]) for t in r["tests"] if t["status"] not in ("PASS", "SKIP")]' | xargs cat
-        - du -chs $HOME/avocado/data/cache
+      after_failure:
+        - cat tests/results/latest/job.log
      addons:
        apt:
          packages:
-            - python3-pil
            - python3-pip
-            - python3-numpy
-            - python3-opencv
-            - python3-venv
-            - rpm2cpio
-            - tesseract-ocr
-            - tesseract-ocr-eng
-
-
+            - python3.5-venv
    # Using newer GCC with sanitizers
-    - name: "GCC9 with sanitizers (softmmu)"
-      addons:
+    - addons:
        apt:
          update: true
          sources:
@@ -362,8 +267,7 @@ jobs:
            - libpixman-1-dev
            - libpng12-dev
            - librados-dev
-            - libsdl2-dev
-            - libsdl2-image-dev
+            - libsdl1.2-dev
            - libseccomp-dev
            - libspice-protocol-dev
            - libspice-server-dev
@@ -380,212 +284,15 @@ jobs:
        - CONFIG="--cc=gcc-9 --cxx=g++-9 --disable-pie --disable-linux-user"
        - TEST_CMD=""
      before_script:
-        - mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
-        - ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-g3 -O0 -Wno-error=stringop-truncation -fsanitize=thread" --extra-ldflags="-fuse-ld=gold" || { cat config.log && exit 1; }
+        - ./configure ${CONFIG} --extra-cflags="-g3 -O0 -Wno-error=stringop-truncation -fsanitize=thread -fuse-ld=gold" || { cat config.log && exit 1; }


    # Run check-tcg against linux-user
-    - name: "GCC check-tcg (user)"
-      env:
-        - CONFIG="--disable-system --enable-debug-tcg"
-        - TEST_BUILD_CMD="make build-tcg"
-        - TEST_CMD="make check-tcg"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
-
-
-    # Run check-tcg against linux-user (with plugins)
-    # we skip sparc64-linux-user until it has been fixed somewhat
-    # we skip cris-linux-user as it doesn't use the common run loop
-    - name: "GCC plugins check-tcg (user)"
-      env:
-        - CONFIG="--disable-system --enable-plugins --enable-debug-tcg --target-list-exclude=sparc64-linux-user,cris-linux-user"
-        - TEST_BUILD_CMD="make build-tcg"
-        - TEST_CMD="make check-tcg"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
-
+    - env:
+        - CONFIG="--disable-system"
+        - TEST_CMD="make -j3 check-tcg V=1"

    # Run check-tcg against softmmu targets
-    - name: "GCC check-tcg (some-softmmu)"
-      env:
-        - CONFIG="--enable-debug-tcg --target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu"
-        - TEST_BUILD_CMD="make build-tcg"
-        - TEST_CMD="make check-tcg"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
-
-
-    # Run check-tcg against softmmu targets (with plugins)
-    - name: "GCC plugins check-tcg (some-softmmu)"
-      env:
-        - CONFIG="--enable-plugins --enable-debug-tcg --target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu"
-        - TEST_BUILD_CMD="make build-tcg"
-        - TEST_CMD="make check-tcg"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
-
-    - name: "[aarch64] GCC check-tcg"
-      arch: arm64
-      dist: xenial
-      addons:
-        apt_packages:
-          - libaio-dev
-          - libattr1-dev
-          - libbrlapi-dev
-          - libcap-ng-dev
-          - libgcrypt20-dev
-          - libgnutls28-dev
-          - libgtk-3-dev
-          - libiscsi-dev
-          - liblttng-ust-dev
-          - libncurses5-dev
-          - libnfs-dev
-          - libnss3-dev
-          - libpixman-1-dev
-          - libpng-dev
-          - librados-dev
-          - libsdl2-dev
-          - libseccomp-dev
-          - liburcu-dev
-          - libusb-1.0-0-dev
-          - libvdeplug-dev
-          - libvte-2.91-dev
-          # Tests dependencies
-          - genisoimage
-      env:
-        - TEST_CMD="make check check-tcg V=1"
-        - CONFIG="--disable-containers --target-list=${MAIN_SOFTMMU_TARGETS}"
-
-    - name: "[ppc64] GCC check-tcg"
-      arch: ppc64le
-      dist: xenial
-      addons:
-        apt_packages:
-          - libaio-dev
-          - libattr1-dev
-          - libbrlapi-dev
-          - libcap-ng-dev
-          - libgcrypt20-dev
-          - libgnutls28-dev
-          - libgtk-3-dev
-          - libiscsi-dev
-          - liblttng-ust-dev
-          - libncurses5-dev
-          - libnfs-dev
-          - libnss3-dev
-          - libpixman-1-dev
-          - libpng-dev
-          - librados-dev
-          - libsdl2-dev
-          - libseccomp-dev
-          - liburcu-dev
-          - libusb-1.0-0-dev
-          - libvdeplug-dev
-          - libvte-2.91-dev
-          # Tests dependencies
-          - genisoimage
-      env:
-        - TEST_CMD="make check check-tcg V=1"
-        - CONFIG="--disable-containers --target-list=${MAIN_SOFTMMU_TARGETS},ppc64le-linux-user"
-
-    - name: "[s390x] GCC check-tcg"
-      arch: s390x
-      dist: bionic
-      addons:
-        apt_packages:
-          - libaio-dev
-          - libattr1-dev
-          - libbrlapi-dev
-          - libcap-ng-dev
-          - libgcrypt20-dev
-          - libgnutls28-dev
-          - libgtk-3-dev
-          - libiscsi-dev
-          - liblttng-ust-dev
-          - libncurses5-dev
-          - libnfs-dev
-          - libnss3-dev
-          - libpixman-1-dev
-          - libpng-dev
-          - librados-dev
-          - libsdl2-dev
-          - libseccomp-dev
-          - liburcu-dev
-          - libusb-1.0-0-dev
-          - libvdeplug-dev
-          - libvte-2.91-dev
-          # Tests dependencies
-          - genisoimage
-      env:
-        - TEST_CMD="make check check-tcg V=1"
-        - CONFIG="--disable-containers --target-list=${MAIN_SOFTMMU_TARGETS},s390x-linux-user"
-      script:
-        - ( cd ${SRC_DIR} ; git submodule update --init roms/SLOF )
-        - BUILD_RC=0 && make -j${JOBS} || BUILD_RC=$?
-        - |
-          if [ "$BUILD_RC" -eq 0 ] ; then
-              mv pc-bios/s390-ccw/*.img pc-bios/ ;
-              ${TEST_CMD} ;
-          else
-              $(exit $BUILD_RC);
-          fi
-
-    - name: "[s390x] GCC check (KVM)"
-      arch: s390x
-      dist: bionic
-      addons:
-        apt_packages:
-          - libaio-dev
-          - libattr1-dev
-          - libbrlapi-dev
-          - libcap-ng-dev
-          - libgcrypt20-dev
-          - libgnutls28-dev
-          - libgtk-3-dev
-          - libiscsi-dev
-          - liblttng-ust-dev
-          - libncurses5-dev
-          - libnfs-dev
-          - libnss3-dev
-          - libpixman-1-dev
-          - libpng-dev
-          - librados-dev
-          - libsdl2-dev
-          - libseccomp-dev
-          - liburcu-dev
-          - libusb-1.0-0-dev
-          - libvdeplug-dev
-          - libvte-2.91-dev
-          # Tests dependencies
-          - genisoimage
-      env:
-        - TEST_CMD="make check-unit"
-        - CONFIG="--disable-containers --disable-tcg --enable-kvm --disable-tools"
-      script:
-        - ( cd ${SRC_DIR} ; git submodule update --init roms/SLOF )
-        - BUILD_RC=0 && make -j${JOBS} || BUILD_RC=$?
-        - |
-          if [ "$BUILD_RC" -eq 0 ] ; then
-              mv pc-bios/s390-ccw/*.img pc-bios/ ;
-              ${TEST_CMD} ;
-          else
-              $(exit $BUILD_RC);
-          fi
-
-    # Release builds
-    # The make-release script expect a QEMU version, so our tag must start with a 'v'.
-    # This is the case when release candidate tags are created.
-    - name: "Release tarball"
-      if: tag IS present AND tag =~ /^v\d+\.\d+(\.\d+)?(-\S*)?$/
-      env:
-        # We want to build from the release tarball
-        - BUILD_DIR="release/build/dir" SRC_DIR="../../.."
-        - BASE_CONFIG="--prefix=$PWD/dist"
-        - CONFIG="--target-list=x86_64-softmmu,aarch64-softmmu,armeb-linux-user,ppc-linux-user"
-        - TEST_CMD="make install -j${JOBS}"
-        - QEMU_VERSION="${TRAVIS_TAG:1}"
-        - CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
-      script:
-        - make -C ${SRC_DIR} qemu-${QEMU_VERSION}.tar.bz2
-        - ls -l ${SRC_DIR}/qemu-${QEMU_VERSION}.tar.bz2
-        - tar -xf ${SRC_DIR}/qemu-${QEMU_VERSION}.tar.bz2 && cd qemu-${QEMU_VERSION}
-        - mkdir -p release-build && cd release-build
-        - ../configure ${BASE_CONFIG} ${CONFIG} || { cat config.log && exit 1; }
-        - make install
+    - env:
+        - CONFIG="--target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu"
+        - TEST_CMD="make -j3 check-tcg V=1"
@@ -0,0 +1,216 @@
+QEMU Coding Style
+=================
+
+Please use the script checkpatch.pl in the scripts directory to check
+patches before submitting.
+
+1. Whitespace
+
+Of course, the most important aspect in any coding style is whitespace.
+Crusty old coders who have trouble spotting the glasses on their noses
+can tell the difference between a tab and eight spaces from a distance
+of approximately fifteen parsecs.  Many a flamewar has been fought and
+lost on this issue.
+
+QEMU indents are four spaces.  Tabs are never used, except in Makefiles
+where they have been irreversibly coded into the syntax.
+Spaces of course are superior to tabs because:
+
+ - You have just one way to specify whitespace, not two.  Ambiguity breeds
+   mistakes.
+ - The confusion surrounding 'use tabs to indent, spaces to justify' is gone.
+ - Tab indents push your code to the right, making your screen seriously
+   unbalanced.
+ - Tabs will be rendered incorrectly on editors who are misconfigured not
+   to use tab stops of eight positions.
+ - Tabs are rendered badly in patches, causing off-by-one errors in almost
+   every line.
+ - It is the QEMU coding style.
+
+Do not leave whitespace dangling off the ends of lines.
+
+1.1 Multiline Indent
+
+There are several places where indent is necessary:
+
+ - if/else
+ - while/for
+ - function definition & call
+
+When breaking up a long line to fit within line width, we need a proper indent
+for the following lines.
+
+In case of if/else, while/for, align the secondary lines just after the
+opening parenthesis of the first.
+
+For example:
+
+    if (a == 1 &&
+        b == 2) {
+
+    while (a == 1 &&
+           b == 2) {
+
+In case of function, there are several variants:
+
+    * 4 spaces indent from the beginning
+    * align the secondary lines just after the opening parenthesis of the
+      first
+
+For example:
+
+    do_something(x, y,
+        z);
+
+    do_something(x, y,
+                 z);
+
+    do_something(x, do_another(y,
+                               z));
+
+2. Line width
+
+Lines should be 80 characters; try not to make them longer.
+
+Sometimes it is hard to do, especially when dealing with QEMU subsystems
+that use long function or symbol names.  Even in that case, do not make
+lines much longer than 80 characters.
+
+Rationale:
+ - Some people like to tile their 24" screens with a 6x4 matrix of 80x24
+   xterms and use vi in all of them.  The best way to punish them is to
+   let them keep doing it.
+ - Code and especially patches is much more readable if limited to a sane
+   line length.  Eighty is traditional.
+ - The four-space indentation makes the most common excuse ("But look
+   at all that white space on the left!") moot.
+ - It is the QEMU coding style.
+
+3. Naming
+
+Variables are lower_case_with_underscores; easy to type and read.  Structured
+type names are in CamelCase; harder to type but standing out.  Enum type
+names and function type names should also be in CamelCase.  Scalar type
+names are lower_case_with_underscores_ending_with_a_t, like the POSIX
+uint64_t and family.  Note that this last convention contradicts POSIX
+and is therefore likely to be changed.
+
+When wrapping standard library functions, use the prefix qemu_ to alert
+readers that they are seeing a wrapped version; otherwise avoid this prefix.
+
+4. Block structure
+
+Every indented statement is braced; even if the block contains just one
+statement.  The opening brace is on the line that contains the control
+flow statement that introduces the new block; the closing brace is on the
+same line as the else keyword, or on a line by itself if there is no else
+keyword.  Example:
+
+    if (a == 5) {
+        printf("a was 5.\n");
+    } else if (a == 6) {
+        printf("a was 6.\n");
+    } else {
+        printf("a was something else entirely.\n");
+    }
+
+Note that 'else if' is considered a single statement; otherwise a long if/
+else if/else if/.../else sequence would need an indent for every else
+statement.
+
+An exception is the opening brace for a function; for reasons of tradition
+and clarity it comes on a line by itself:
+
+    void a_function(void)
+    {
+        do_something();
+    }
+
+Rationale: a consistent (except for functions...) bracing style reduces
+ambiguity and avoids needless churn when lines are added or removed.
+Furthermore, it is the QEMU coding style.
+
+5. Declarations
+
+Mixed declarations (interleaving statements and declarations within
+blocks) are generally not allowed; declarations should be at the beginning
+of blocks.
+
+Every now and then, an exception is made for declarations inside a
+#ifdef or #ifndef block: if the code looks nicer, such declarations can
+be placed at the top of the block even if there are statements above.
+On the other hand, however, it's often best to move that #ifdef/#ifndef
+block to a separate function altogether.
+
+6. Conditional statements
+
+When comparing a variable for (in)equality with a constant, list the
+constant on the right, as in:
+
+    if (a == 1) {
+        /* Reads like: "If a equals 1" */
+        do_something();
+    }
+
+Rationale: Yoda conditions (as in 'if (1 == a)') are awkward to read.
+Besides, good compilers already warn users when '==' is mis-typed as '=',
+even when the constant is on the right.
+
+7. Comment style
+
+We use traditional C-style /* */ comments and avoid // comments.
+
+Rationale: The // form is valid in C99, so this is purely a matter of
+consistency of style. The checkpatch script will warn you about this.
+
+Multiline comment blocks should have a row of stars on the left,
+and the initial /* and terminating */ both on their own lines:
+    /*
+     * like
+     * this
+     */
+This is the same format required by the Linux kernel coding style.
+
+(Some of the existing comments in the codebase use the GNU Coding
+Standards form which does not have stars on the left, or other
+variations; avoid these when writing new comments, but don't worry
+about converting to the preferred form unless you're editing that
+comment anyway.)
+
+Rationale: Consistency, and ease of visually picking out a multiline
+comment from the surrounding code.
+
+8. trace-events style
+
+8.1 0x prefix
+
+In trace-events files, use a '0x' prefix to specify hex numbers, as in:
+
+some_trace(unsigned x, uint64_t y) "x 0x%x y 0x" PRIx64
+
+An exception is made for groups of numbers that are hexadecimal by
+convention and separated by the symbols '.', '/', ':', or ' ' (such as
+PCI bus id):
+
+another_trace(int cssid, int ssid, int dev_num) "bus id: %x.%x.%04x"
+
+However, you can use '0x' for such groups if you want. Anyway, be sure that
+it is obvious that numbers are in hex, ex.:
+
+data_dump(uint8_t c1, uint8_t c2, uint8_t c3) "bytes (in hex): %02x %02x %02x"
+
+Rationale: hex numbers are hard to read in logs when there is no 0x prefix,
+especially when (occasionally) the representation doesn't contain any letters
+and especially in one line with other decimal numbers. Number groups are allowed
+to not use '0x' because for some things notations like %x.%x.%x are used not
+only in Qemu. Also dumping raw data bytes with '0x' is less readable.
+
+8.2 '#' printf flag
+
+Do not use printf flag '#', like '%#x'.
+
+Rationale: there are two ways to add a '0x' prefix to printed number: '0x%...'
+and '%#...'. For consistency the only one way should be used. Arguments for
+'0x%' are:
+ - it is more popular
+ - '%#' omits the 0x for the value 0 which makes output inconsistent
@@ -1,641 +0,0 @@
-=================
-QEMU Coding Style
-=================
-
-.. contents:: Table of Contents
-
-Please use the script checkpatch.pl in the scripts directory to check
-patches before submitting.
-
-Formatting and style
-********************
-
-Whitespace
-==========
-
-Of course, the most important aspect in any coding style is whitespace.
-Crusty old coders who have trouble spotting the glasses on their noses
-can tell the difference between a tab and eight spaces from a distance
-of approximately fifteen parsecs.  Many a flamewar has been fought and
-lost on this issue.
-
-QEMU indents are four spaces.  Tabs are never used, except in Makefiles
-where they have been irreversibly coded into the syntax.
-Spaces of course are superior to tabs because:
-
-* You have just one way to specify whitespace, not two.  Ambiguity breeds
-  mistakes.
-* The confusion surrounding 'use tabs to indent, spaces to justify' is gone.
-* Tab indents push your code to the right, making your screen seriously
-  unbalanced.
-* Tabs will be rendered incorrectly on editors who are misconfigured not
-  to use tab stops of eight positions.
-* Tabs are rendered badly in patches, causing off-by-one errors in almost
-  every line.
-* It is the QEMU coding style.
-
-Do not leave whitespace dangling off the ends of lines.
-
-Multiline Indent
----------------
-
-There are several places where indent is necessary:
-
-* if/else
-* while/for
-* function definition & call
-
-When breaking up a long line to fit within line width, we need a proper indent
-for the following lines.
-
-In case of if/else, while/for, align the secondary lines just after the
-opening parenthesis of the first.
-
-For example:
-
-.. code-block:: c
-
-    if (a == 1 &&
-        b == 2) {
-
-    while (a == 1 &&
-           b == 2) {
-
-In case of function, there are several variants:
-
-* 4 spaces indent from the beginning
-* align the secondary lines just after the opening parenthesis of the first
-
-For example:
-
-.. code-block:: c
-
-    do_something(x, y,
-        z);
-
-    do_something(x, y,
-                 z);
-
-    do_something(x, do_another(y,
-                               z));
-
-Line width
-==========
-
-Lines should be 80 characters; try not to make them longer.
-
-Sometimes it is hard to do, especially when dealing with QEMU subsystems
-that use long function or symbol names.  Even in that case, do not make
-lines much longer than 80 characters.
-
-Rationale:
-
-* Some people like to tile their 24" screens with a 6x4 matrix of 80x24
-  xterms and use vi in all of them.  The best way to punish them is to
-  let them keep doing it.
-* Code and especially patches is much more readable if limited to a sane
-  line length.  Eighty is traditional.
-* The four-space indentation makes the most common excuse ("But look
-  at all that white space on the left!") moot.
-* It is the QEMU coding style.
-
-Naming
-======
-
-Variables are lower_case_with_underscores; easy to type and read.  Structured
-type names are in CamelCase; harder to type but standing out.  Enum type
-names and function type names should also be in CamelCase.  Scalar type
-names are lower_case_with_underscores_ending_with_a_t, like the POSIX
-uint64_t and family.  Note that this last convention contradicts POSIX
-and is therefore likely to be changed.
-
-When wrapping standard library functions, use the prefix ``qemu_`` to alert
-readers that they are seeing a wrapped version; otherwise avoid this prefix.
-
-Block structure
-===============
-
-Every indented statement is braced; even if the block contains just one
-statement.  The opening brace is on the line that contains the control
-flow statement that introduces the new block; the closing brace is on the
-same line as the else keyword, or on a line by itself if there is no else
-keyword.  Example:
-
-.. code-block:: c
-
-    if (a == 5) {
-        printf("a was 5.\n");
-    } else if (a == 6) {
-        printf("a was 6.\n");
-    } else {
-        printf("a was something else entirely.\n");
-    }
-
-Note that 'else if' is considered a single statement; otherwise a long if/
-else if/else if/.../else sequence would need an indent for every else
-statement.
-
-An exception is the opening brace for a function; for reasons of tradition
-and clarity it comes on a line by itself:
-
-.. code-block:: c
-
-    void a_function(void)
-    {
-        do_something();
-    }
-
-Rationale: a consistent (except for functions...) bracing style reduces
-ambiguity and avoids needless churn when lines are added or removed.
-Furthermore, it is the QEMU coding style.
-
-Declarations
-============
-
-Mixed declarations (interleaving statements and declarations within
-blocks) are generally not allowed; declarations should be at the beginning
-of blocks.
-
-Every now and then, an exception is made for declarations inside a
-#ifdef or #ifndef block: if the code looks nicer, such declarations can
-be placed at the top of the block even if there are statements above.
-On the other hand, however, it's often best to move that #ifdef/#ifndef
-block to a separate function altogether.
-
-Conditional statements
-======================
-
-When comparing a variable for (in)equality with a constant, list the
-constant on the right, as in:
-
-.. code-block:: c
-
-    if (a == 1) {
-        /* Reads like: "If a equals 1" */
-        do_something();
-    }
-
-Rationale: Yoda conditions (as in 'if (1 == a)') are awkward to read.
-Besides, good compilers already warn users when '==' is mis-typed as '=',
-even when the constant is on the right.
-
-Comment style
-=============
-
-We use traditional C-style /``*`` ``*``/ comments and avoid // comments.
-
-Rationale: The // form is valid in C99, so this is purely a matter of
-consistency of style. The checkpatch script will warn you about this.
-
-Multiline comment blocks should have a row of stars on the left,
-and the initial /``*`` and terminating ``*``/ both on their own lines:
-
-.. code-block:: c
-
-    /*
-     * like
-     * this
-     */
-
-This is the same format required by the Linux kernel coding style.
-
-(Some of the existing comments in the codebase use the GNU Coding
-Standards form which does not have stars on the left, or other
-variations; avoid these when writing new comments, but don't worry
-about converting to the preferred form unless you're editing that
-comment anyway.)
-
-Rationale: Consistency, and ease of visually picking out a multiline
-comment from the surrounding code.
-
-Language usage
-**************
-
-Preprocessor
-============
-
-Variadic macros
---------------
-
-For variadic macros, stick with this C99-like syntax:
-
-.. code-block:: c
-
-    #define DPRINTF(fmt, ...)                                       \
-        do { printf("IRQ: " fmt, ## __VA_ARGS__); } while (0)
-
-Include directives
------------------
-
-Order include directives as follows:
-
-.. code-block:: c
-
-    #include "qemu/osdep.h"  /* Always first... */
-    #include <...>           /* then system headers... */
-    #include "..."           /* and finally QEMU headers. */
-
-The "qemu/osdep.h" header contains preprocessor macros that affect the behavior
-of core system headers like <stdint.h>.  It must be the first include so that
-core system headers included by external libraries get the preprocessor macros
-that QEMU depends on.
-
-Do not include "qemu/osdep.h" from header files since the .c file will have
-already included it.
-
-C types
-=======
-
-It should be common sense to use the right type, but we have collected
-a few useful guidelines here.
-
-Scalars
-------
-
-If you're using "int" or "long", odds are good that there's a better type.
-If a variable is counting something, it should be declared with an
-unsigned type.
-
-If it's host memory-size related, size_t should be a good choice (use
-ssize_t only if required). Guest RAM memory offsets must use ram_addr_t,
-but only for RAM, it may not cover whole guest address space.
-
-If it's file-size related, use off_t.
-If it's file-offset related (i.e., signed), use off_t.
-If it's just counting small numbers use "unsigned int";
-(on all but oddball embedded systems, you can assume that that
-type is at least four bytes wide).
-
-In the event that you require a specific width, use a standard type
-like int32_t, uint32_t, uint64_t, etc.  The specific types are
-mandatory for VMState fields.
-
-Don't use Linux kernel internal types like u32, __u32 or __le32.
-
-Use hwaddr for guest physical addresses except pcibus_t
-for PCI addresses.  In addition, ram_addr_t is a QEMU internal address
-space that maps guest RAM physical addresses into an intermediate
-address space that can map to host virtual address spaces.  Generally
-speaking, the size of guest memory can always fit into ram_addr_t but
-it would not be correct to store an actual guest physical address in a
-ram_addr_t.
-
-For CPU virtual addresses there are several possible types.
-vaddr is the best type to use to hold a CPU virtual address in
-target-independent code. It is guaranteed to be large enough to hold a
-virtual address for any target, and it does not change size from target
-to target. It is always unsigned.
-target_ulong is a type the size of a virtual address on the CPU; this means
-it may be 32 or 64 bits depending on which target is being built. It should
-therefore be used only in target-specific code, and in some
-performance-critical built-per-target core code such as the TLB code.
-There is also a signed version, target_long.
-abi_ulong is for the ``*``-user targets, and represents a type the size of
-'void ``*``' in that target's ABI. (This may not be the same as the size of a
-full CPU virtual address in the case of target ABIs which use 32 bit pointers
-on 64 bit CPUs, like sparc32plus.) Definitions of structures that must match
-the target's ABI must use this type for anything that on the target is defined
-to be an 'unsigned long' or a pointer type.
-There is also a signed version, abi_long.
-
-Of course, take all of the above with a grain of salt.  If you're about
-to use some system interface that requires a type like size_t, pid_t or
-off_t, use matching types for any corresponding variables.
-
-Also, if you try to use e.g., "unsigned int" as a type, and that
-conflicts with the signedness of a related variable, sometimes
-it's best just to use the *wrong* type, if "pulling the thread"
-and fixing all related variables would be too invasive.
-
-Finally, while using descriptive types is important, be careful not to
-go overboard.  If whatever you're doing causes warnings, or requires
-casts, then reconsider or ask for help.
-
-Pointers
--------
-
-Ensure that all of your pointers are "const-correct".
-Unless a pointer is used to modify the pointed-to storage,
-give it the "const" attribute.  That way, the reader knows
-up-front that this is a read-only pointer.  Perhaps more
-importantly, if we're diligent about this, when you see a non-const
-pointer, you're guaranteed that it is used to modify the storage
-it points to, or it is aliased to another pointer that is.
-
-Typedefs
--------
-
-Typedefs are used to eliminate the redundant 'struct' keyword, since type
-names have a different style than other identifiers ("CamelCase" versus
-"snake_case").  Each named struct type should have a CamelCase name and a
-corresponding typedef.
-
-Since certain C compilers choke on duplicated typedefs, you should avoid
-them and declare a typedef only in one header file.  For common types,
-you can use "include/qemu/typedefs.h" for example.  However, as a matter
-of convenience it is also perfectly fine to use forward struct
-definitions instead of typedefs in headers and function prototypes; this
-avoids problems with duplicated typedefs and reduces the need to include
-headers from other headers.
-
-Reserved namespaces in C and POSIX
----------------------------------
-
-Underscore capital, double underscore, and underscore 't' suffixes should be
-avoided.
-
-Low level memory management
-===========================
-
-Use of the malloc/free/realloc/calloc/valloc/memalign/posix_memalign
-APIs is not allowed in the QEMU codebase. Instead of these routines,
-use the GLib memory allocation routines g_malloc/g_malloc0/g_new/
-g_new0/g_realloc/g_free or QEMU's qemu_memalign/qemu_blockalign/qemu_vfree
-APIs.
-
-Please note that g_malloc will exit on allocation failure, so there
-is no need to test for failure (as you would have to with malloc).
-Calling g_malloc with a zero size is valid and will return NULL.
-
-Prefer g_new(T, n) instead of g_malloc(sizeof(T) ``*`` n) for the following
-reasons:
-
-* It catches multiplication overflowing size_t;
-* It returns T ``*`` instead of void ``*``, letting compiler catch more type errors.
-
-Declarations like
-
-.. code-block:: c
-
-    T *v = g_malloc(sizeof(*v))
-
-are acceptable, though.
-
-Memory allocated by qemu_memalign or qemu_blockalign must be freed with
-qemu_vfree, since breaking this will cause problems on Win32.
-
-String manipulation
-===================
-
-Do not use the strncpy function.  As mentioned in the man page, it does *not*
-guarantee a NULL-terminated buffer, which makes it extremely dangerous to use.
-It also zeros trailing destination bytes out to the specified length.  Instead,
-use this similar function when possible, but note its different signature:
-
-.. code-block:: c
-
-    void pstrcpy(char *dest, int dest_buf_size, const char *src)
-
-Don't use strcat because it can't check for buffer overflows, but:
-
-.. code-block:: c
-
-    char *pstrcat(char *buf, int buf_size, const char *s)
-
-The same limitation exists with sprintf and vsprintf, so use snprintf and
-vsnprintf.
-
-QEMU provides other useful string functions:
-
-.. code-block:: c
-
-    int strstart(const char *str, const char *val, const char **ptr)
-    int stristart(const char *str, const char *val, const char **ptr)
-    int qemu_strnlen(const char *s, int max_len)
-
-There are also replacement character processing macros for isxyz and toxyz,
-so instead of e.g. isalnum you should use qemu_isalnum.
-
-Because of the memory management rules, you must use g_strdup/g_strndup
-instead of plain strdup/strndup.
-
-Printf-style functions
-======================
-
-Whenever you add a new printf-style function, i.e., one with a format
-string argument and following "..." in its prototype, be sure to use
-gcc's printf attribute directive in the prototype.
-
-This makes it so gcc's -Wformat and -Wformat-security options can do
-their jobs and cross-check format strings with the number and types
-of arguments.
-
-C standard, implementation defined and undefined behaviors
-==========================================================
-
-C code in QEMU should be written to the C99 language specification. A copy
-of the final version of the C99 standard with corrigenda TC1, TC2, and TC3
-included, formatted as a draft, can be downloaded from:
-
-    `<http://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf>`_
-
-The C language specification defines regions of undefined behavior and
-implementation defined behavior (to give compiler authors enough leeway to
-produce better code).  In general, code in QEMU should follow the language
-specification and avoid both undefined and implementation defined
-constructs. ("It works fine on the gcc I tested it with" is not a valid
-argument...) However there are a few areas where we allow ourselves to
-assume certain behaviors because in practice all the platforms we care about
-behave in the same way and writing strictly conformant code would be
-painful. These are:
-
-* you may assume that integers are 2s complement representation
-* you may assume that right shift of a signed integer duplicates
-  the sign bit (ie it is an arithmetic shift, not a logical shift)
-
-In addition, QEMU assumes that the compiler does not use the latitude
-given in C99 and C11 to treat aspects of signed '<<' as undefined, as
-documented in the GNU Compiler Collection manual starting at version 4.0.
-
-Automatic memory deallocation
-=============================
-
-QEMU has a mandatory dependency either the GCC or CLang compiler. As
-such it has the freedom to make use of a C language extension for
-automatically running a cleanup function when a stack variable goes
-out of scope. This can be used to simplify function cleanup paths,
-often allowing many goto jumps to be eliminated, through automatic
-free'ing of memory.
-
-The GLib2 library provides a number of functions/macros for enabling
-automatic cleanup:
-
-  `<https://developer.gnome.org/glib/stable/glib-Miscellaneous-Macros.html>`_
-
-Most notably:
-
-* g_autofree - will invoke g_free() on the variable going out of scope
-
-* g_autoptr - for structs / objects, will invoke the cleanup func created
-  by a previous use of G_DEFINE_AUTOPTR_CLEANUP_FUNC. This is
-  supported for most GLib data types and GObjects
-
-For example, instead of
-
-.. code-block:: c
-
-    int somefunc(void) {
-        int ret = -1;
-        char *foo = g_strdup_printf("foo%", "wibble");
-        GList *bar = .....
-
-        if (eek) {
-           goto cleanup;
-        }
-
-        ret = 0;
-
-      cleanup:
-        g_free(foo);
-        g_list_free(bar);
-        return ret;
-    }
-
-Using g_autofree/g_autoptr enables the code to be written as:
-
-.. code-block:: c
-
-    int somefunc(void) {
-        g_autofree char *foo = g_strdup_printf("foo%", "wibble");
-        g_autoptr (GList) bar = .....
-
-        if (eek) {
-           return -1;
-        }
-
-        return 0;
-    }
-
-While this generally results in simpler, less leak-prone code, there
-are still some caveats to beware of
-
-* Variables declared with g_auto* MUST always be initialized,
-  otherwise the cleanup function will use uninitialized stack memory
-
-* If a variable declared with g_auto* holds a value which must
-  live beyond the life of the function, that value must be saved
-  and the original variable NULL'd out. This can be simpler using
-  g_steal_pointer
-
-
-.. code-block:: c
-
-    char *somefunc(void) {
-        g_autofree char *foo = g_strdup_printf("foo%", "wibble");
-        g_autoptr (GList) bar = .....
-
-        if (eek) {
-           return NULL;
-        }
-
-        return g_steal_pointer(&foo);
-    }
-
-
-QEMU Specific Idioms
-********************
-
-Error handling and reporting
-============================
-
-Reporting errors to the human user
----------------------------------
-
-Do not use printf(), fprintf() or monitor_printf().  Instead, use
-error_report() or error_vreport() from error-report.h.  This ensures the
-error is reported in the right place (current monitor or stderr), and in
-a uniform format.
-
-Use error_printf() & friends to print additional information.
-
-error_report() prints the current location.  In certain common cases
-like command line parsing, the current location is tracked
-automatically.  To manipulate it manually, use the loc_``*``() from
-error-report.h.
-
-Propagating errors
------------------
-
-An error can't always be reported to the user right where it's detected,
-but often needs to be propagated up the call chain to a place that can
-handle it.  This can be done in various ways.
-
-The most flexible one is Error objects.  See error.h for usage
-information.
-
-Use the simplest suitable method to communicate success / failure to
-callers.  Stick to common methods: non-negative on success / -1 on
-error, non-negative / -errno, non-null / null, or Error objects.
-
-Example: when a function returns a non-null pointer on success, and it
-can fail only in one way (as far as the caller is concerned), returning
-null on failure is just fine, and certainly simpler and a lot easier on
-the eyes than propagating an Error object through an Error ``*````*`` parameter.
-
-Example: when a function's callers need to report details on failure
-only the function really knows, use Error ``*````*``, and set suitable errors.
-
-Do not report an error to the user when you're also returning an error
-for somebody else to handle.  Leave the reporting to the place that
-consumes the error returned.
-
-Handling errors
---------------
-
-Calling exit() is fine when handling configuration errors during
-startup.  It's problematic during normal operation.  In particular,
-monitor commands should never exit().
-
-Do not call exit() or abort() to handle an error that can be triggered
-by the guest (e.g., some unimplemented corner case in guest code
-translation or device emulation).  Guests should not be able to
-terminate QEMU.
-
-Note that &error_fatal is just another way to exit(1), and &error_abort
-is just another way to abort().
-
-
-trace-events style
-==================
-
-0x prefix
---------
-
-In trace-events files, use a '0x' prefix to specify hex numbers, as in:
-
-.. code-block::
-
-    some_trace(unsigned x, uint64_t y) "x 0x%x y 0x" PRIx64
-
-An exception is made for groups of numbers that are hexadecimal by
-convention and separated by the symbols '.', '/', ':', or ' ' (such as
-PCI bus id):
-
-.. code-block::
-
-    another_trace(int cssid, int ssid, int dev_num) "bus id: %x.%x.%04x"
-
-However, you can use '0x' for such groups if you want. Anyway, be sure that
-it is obvious that numbers are in hex, ex.:
-
-.. code-block::
-
-    data_dump(uint8_t c1, uint8_t c2, uint8_t c3) "bytes (in hex): %02x %02x %02x"
-
-Rationale: hex numbers are hard to read in logs when there is no 0x prefix,
-especially when (occasionally) the representation doesn't contain any letters
-and especially in one line with other decimal numbers. Number groups are allowed
-to not use '0x' because for some things notations like %x.%x.%x are used not
-only in Qemu. Also dumping raw data bytes with '0x' is less readable.
-
-'#' printf flag
---------------
-
-Do not use printf flag '#', like '%#x'.
-
-Rationale: there are two ways to add a '0x' prefix to printed number: '0x%...'
-and '%#...'. For consistency the only one way should be used. Arguments for
-'0x%' are:
-
-* it is more popular
-* '%#' omits the 0x for the value 0 which makes output inconsistent
@@ -0,0 +1,245 @@
+1. Preprocessor
+
+1.1. Variadic macros
+
+For variadic macros, stick with this C99-like syntax:
+
+#define DPRINTF(fmt, ...)                                       \
+    do { printf("IRQ: " fmt, ## __VA_ARGS__); } while (0)
+
+1.2. Include directives
+
+Order include directives as follows:
+
+#include "qemu/osdep.h"  /* Always first... */
+#include <...>           /* then system headers... */
+#include "..."           /* and finally QEMU headers. */
+
+The "qemu/osdep.h" header contains preprocessor macros that affect the behavior
+of core system headers like <stdint.h>.  It must be the first include so that
+core system headers included by external libraries get the preprocessor macros
+that QEMU depends on.
+
+Do not include "qemu/osdep.h" from header files since the .c file will have
+already included it.
+
+2. C types
+
+It should be common sense to use the right type, but we have collected
+a few useful guidelines here.
+
+2.1. Scalars
+
+If you're using "int" or "long", odds are good that there's a better type.
+If a variable is counting something, it should be declared with an
+unsigned type.
+
+If it's host memory-size related, size_t should be a good choice (use
+ssize_t only if required). Guest RAM memory offsets must use ram_addr_t,
+but only for RAM, it may not cover whole guest address space.
+
+If it's file-size related, use off_t.
+If it's file-offset related (i.e., signed), use off_t.
+If it's just counting small numbers use "unsigned int";
+(on all but oddball embedded systems, you can assume that that
+type is at least four bytes wide).
+
+In the event that you require a specific width, use a standard type
+like int32_t, uint32_t, uint64_t, etc.  The specific types are
+mandatory for VMState fields.
+
+Don't use Linux kernel internal types like u32, __u32 or __le32.
+
+Use hwaddr for guest physical addresses except pcibus_t
+for PCI addresses.  In addition, ram_addr_t is a QEMU internal address
+space that maps guest RAM physical addresses into an intermediate
+address space that can map to host virtual address spaces.  Generally
+speaking, the size of guest memory can always fit into ram_addr_t but
+it would not be correct to store an actual guest physical address in a
+ram_addr_t.
+
+For CPU virtual addresses there are several possible types.
+vaddr is the best type to use to hold a CPU virtual address in
+target-independent code. It is guaranteed to be large enough to hold a
+virtual address for any target, and it does not change size from target
+to target. It is always unsigned.
+target_ulong is a type the size of a virtual address on the CPU; this means
+it may be 32 or 64 bits depending on which target is being built. It should
+therefore be used only in target-specific code, and in some
+performance-critical built-per-target core code such as the TLB code.
+There is also a signed version, target_long.
+abi_ulong is for the *-user targets, and represents a type the size of
+'void *' in that target's ABI. (This may not be the same as the size of a
+full CPU virtual address in the case of target ABIs which use 32 bit pointers
+on 64 bit CPUs, like sparc32plus.) Definitions of structures that must match
+the target's ABI must use this type for anything that on the target is defined
+to be an 'unsigned long' or a pointer type.
+There is also a signed version, abi_long.
+
+Of course, take all of the above with a grain of salt.  If you're about
+to use some system interface that requires a type like size_t, pid_t or
+off_t, use matching types for any corresponding variables.
+
+Also, if you try to use e.g., "unsigned int" as a type, and that
+conflicts with the signedness of a related variable, sometimes
+it's best just to use the *wrong* type, if "pulling the thread"
+and fixing all related variables would be too invasive.
+
+Finally, while using descriptive types is important, be careful not to
+go overboard.  If whatever you're doing causes warnings, or requires
+casts, then reconsider or ask for help.
+
+2.2. Pointers
+
+Ensure that all of your pointers are "const-correct".
+Unless a pointer is used to modify the pointed-to storage,
+give it the "const" attribute.  That way, the reader knows
+up-front that this is a read-only pointer.  Perhaps more
+importantly, if we're diligent about this, when you see a non-const
+pointer, you're guaranteed that it is used to modify the storage
+it points to, or it is aliased to another pointer that is.
+
+2.3. Typedefs
+Typedefs are used to eliminate the redundant 'struct' keyword.
+
+2.4. Reserved namespaces in C and POSIX
+Underscore capital, double underscore, and underscore 't' suffixes should be
+avoided.
+
+3. Low level memory management
+
+Use of the malloc/free/realloc/calloc/valloc/memalign/posix_memalign
+APIs is not allowed in the QEMU codebase. Instead of these routines,
+use the GLib memory allocation routines g_malloc/g_malloc0/g_new/
+g_new0/g_realloc/g_free or QEMU's qemu_memalign/qemu_blockalign/qemu_vfree
+APIs.
+
+Please note that g_malloc will exit on allocation failure, so there
+is no need to test for failure (as you would have to with malloc).
+Calling g_malloc with a zero size is valid and will return NULL.
+
+Prefer g_new(T, n) instead of g_malloc(sizeof(T) * n) for the following
+reasons:
+
+  a. It catches multiplication overflowing size_t;
+  b. It returns T * instead of void *, letting compiler catch more type
+     errors.
+
+Declarations like T *v = g_malloc(sizeof(*v)) are acceptable, though.
+
+Memory allocated by qemu_memalign or qemu_blockalign must be freed with
+qemu_vfree, since breaking this will cause problems on Win32.
+
+4. String manipulation
+
+Do not use the strncpy function.  As mentioned in the man page, it does *not*
+guarantee a NULL-terminated buffer, which makes it extremely dangerous to use.
+It also zeros trailing destination bytes out to the specified length.  Instead,
+use this similar function when possible, but note its different signature:
+void pstrcpy(char *dest, int dest_buf_size, const char *src)
+
+Don't use strcat because it can't check for buffer overflows, but:
+char *pstrcat(char *buf, int buf_size, const char *s)
+
+The same limitation exists with sprintf and vsprintf, so use snprintf and
+vsnprintf.
+
+QEMU provides other useful string functions:
+int strstart(const char *str, const char *val, const char **ptr)
+int stristart(const char *str, const char *val, const char **ptr)
+int qemu_strnlen(const char *s, int max_len)
+
+There are also replacement character processing macros for isxyz and toxyz,
+so instead of e.g. isalnum you should use qemu_isalnum.
+
+Because of the memory management rules, you must use g_strdup/g_strndup
+instead of plain strdup/strndup.
+
+5. Printf-style functions
+
+Whenever you add a new printf-style function, i.e., one with a format
+string argument and following "..." in its prototype, be sure to use
+gcc's printf attribute directive in the prototype.
+
+This makes it so gcc's -Wformat and -Wformat-security options can do
+their jobs and cross-check format strings with the number and types
+of arguments.
+
+6. C standard, implementation defined and undefined behaviors
+
+C code in QEMU should be written to the C99 language specification. A copy
+of the final version of the C99 standard with corrigenda TC1, TC2, and TC3
+included, formatted as a draft, can be downloaded from:
+ http://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf
+
+The C language specification defines regions of undefined behavior and
+implementation defined behavior (to give compiler authors enough leeway to
+produce better code).  In general, code in QEMU should follow the language
+specification and avoid both undefined and implementation defined
+constructs. ("It works fine on the gcc I tested it with" is not a valid
+argument...) However there are a few areas where we allow ourselves to
+assume certain behaviors because in practice all the platforms we care about
+behave in the same way and writing strictly conformant code would be
+painful. These are:
+ * you may assume that integers are 2s complement representation
+ * you may assume that right shift of a signed integer duplicates
+   the sign bit (ie it is an arithmetic shift, not a logical shift)
+
+In addition, QEMU assumes that the compiler does not use the latitude
+given in C99 and C11 to treat aspects of signed '<<' as undefined, as
+documented in the GNU Compiler Collection manual starting at version 4.0.
+
+7. Error handling and reporting
+
+7.1 Reporting errors to the human user
+
+Do not use printf(), fprintf() or monitor_printf().  Instead, use
+error_report() or error_vreport() from error-report.h.  This ensures the
+error is reported in the right place (current monitor or stderr), and in
+a uniform format.
+
+Use error_printf() & friends to print additional information.
+
+error_report() prints the current location.  In certain common cases
+like command line parsing, the current location is tracked
+automatically.  To manipulate it manually, use the loc_*() from
+error-report.h.
+
+7.2 Propagating errors
+
+An error can't always be reported to the user right where it's detected,
+but often needs to be propagated up the call chain to a place that can
+handle it.  This can be done in various ways.
+
+The most flexible one is Error objects.  See error.h for usage
+information.
+
+Use the simplest suitable method to communicate success / failure to
+callers.  Stick to common methods: non-negative on success / -1 on
+error, non-negative / -errno, non-null / null, or Error objects.
+
+Example: when a function returns a non-null pointer on success, and it
+can fail only in one way (as far as the caller is concerned), returning
+null on failure is just fine, and certainly simpler and a lot easier on
+the eyes than propagating an Error object through an Error ** parameter.
+
+Example: when a function's callers need to report details on failure
+only the function really knows, use Error **, and set suitable errors.
+
+Do not report an error to the user when you're also returning an error
+for somebody else to handle.  Leave the reporting to the place that
+consumes the error returned.
+
+7.3 Handling errors
+
+Calling exit() is fine when handling configuration errors during
+startup.  It's problematic during normal operation.  In particular,
+monitor commands should never exit().
+
+Do not call exit() or abort() to handle an error that can be triggered
+by the guest (e.g., some unimplemented corner case in guest code
+translation or device emulation).  Guests should not be able to
+terminate QEMU.
+
+Note that &error_fatal is just another way to exit(1), and &error_abort
+is just another way to abort().
@@ -25,15 +25,9 @@ config TPM

 config VHOST_USER
    bool
-    select VHOST
-
-config VHOST_KERNEL
-    bool
-    select VHOST

 config XEN
    bool
-    select FSDEV_9P if VIRTFS

 config VIRTFS
    bool
@@ -18,9 +18,8 @@ As of July 2013, contributions under version 2 of the GNU General Public
 License (and no later version) are only accepted for the following files
 or directories: bsd-user/, linux-user/, hw/vfio/, hw/xen/xen_pt*.

-3) The Tiny Code Generator (TCG) is mostly under the BSD or MIT licenses;
-   but some parts may be GPLv2 or other licenses. Again, see the
-   specific licensing information in each source file.
+3) The Tiny Code Generator (TCG) is released under the BSD license
+   (see license headers in files).

 4) QEMU is a trademark of Fabrice Bellard.

@@ -15,6 +15,9 @@ UNCHECKED_GOALS := %clean TAGS cscope ctags dist \
    help check-help print-% \
    docker docker-% vm-help vm-test vm-build-%

+print-%:
+	@echo '$*=$($*)'
+
 # All following code might depend on configuration variables
 ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
@@ -71,12 +74,6 @@ CONFIG_ALL=y
 config-host.mak: $(SRC_PATH)/configure $(SRC_PATH)/pc-bios $(SRC_PATH)/VERSION
 	@echo $@ is out-of-date, running configure
 	@./config.status
-
-# Force configure to re-run if the API symbols are updated
-ifeq ($(CONFIG_PLUGIN),y)
-config-host.mak: $(SRC_PATH)/plugins/qemu-plugins.symbols
-endif
-
 else
 config-host.mak:
 ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
@@ -87,7 +84,8 @@ endif

 include $(SRC_PATH)/rules.mak

-# lor is defined in rules.mak
+# notempy and lor are defined in rules.mak
+CONFIG_TOOLS := $(call notempty,$(TOOLS))
 CONFIG_BLOCK := $(call lor,$(CONFIG_SOFTMMU),$(CONFIG_TOOLS))

 # Create QEMU_PKGVERSION and FULL_VERSION strings
@@ -114,7 +112,6 @@ GENERATED_QAPI_FILES += qapi/qapi-builtin-visit.h qapi/qapi-builtin-visit.c
 GENERATED_QAPI_FILES += qapi/qapi-visit.h qapi/qapi-visit.c
 GENERATED_QAPI_FILES += $(QAPI_MODULES:%=qapi/qapi-visit-%.h)
 GENERATED_QAPI_FILES += $(QAPI_MODULES:%=qapi/qapi-visit-%.c)
-GENERATED_QAPI_FILES += qapi/qapi-init-commands.h qapi/qapi-init-commands.c
 GENERATED_QAPI_FILES += qapi/qapi-commands.h qapi/qapi-commands.c
 GENERATED_QAPI_FILES += $(QAPI_MODULES:%=qapi/qapi-commands-%.h)
 GENERATED_QAPI_FILES += $(QAPI_MODULES:%=qapi/qapi-commands-%.c)
@@ -125,28 +122,7 @@ GENERATED_QAPI_FILES += $(QAPI_MODULES:%=qapi/qapi-events-%.c)
 GENERATED_QAPI_FILES += qapi/qapi-introspect.c qapi/qapi-introspect.h
 GENERATED_QAPI_FILES += qapi/qapi-doc.texi

-# The following list considers only the storage daemon main module. All other
-# modules are currently shared with the main schema, so we don't actually
-# generate additional files.
-
-GENERATED_STORAGE_DAEMON_QAPI_FILES = storage-daemon/qapi/qapi-commands.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-commands.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-emit-events.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-emit-events.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-events.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-events.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-init-commands.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-init-commands.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-introspect.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-introspect.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-types.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-types.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-visit.h
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-visit.c
-GENERATED_STORAGE_DAEMON_QAPI_FILES += storage-daemon/qapi/qapi-doc.texi
-
 generated-files-y += $(GENERATED_QAPI_FILES)
-generated-files-y += $(GENERATED_STORAGE_DAEMON_QAPI_FILES)

 generated-files-y += trace/generated-tcg-tracers.h

@@ -340,45 +316,26 @@ HELPERS-y =

 HELPERS-$(call land,$(CONFIG_SOFTMMU),$(CONFIG_LINUX)) = qemu-bridge-helper$(EXESUF)

-ifeq ($(CONFIG_LINUX)$(CONFIG_VIRGL)$(CONFIG_GBM)$(CONFIG_TOOLS),yyyy)
+ifdef CONFIG_LINUX
+ifdef CONFIG_VIRGL
+ifdef CONFIG_GBM
 HELPERS-y += vhost-user-gpu$(EXESUF)
 vhost-user-json-y += contrib/vhost-user-gpu/50-qemu-gpu.json
 endif
-
-ifeq ($(CONFIG_LINUX)$(CONFIG_SECCOMP)$(CONFIG_LIBCAP_NG),yyy)
-HELPERS-y += virtiofsd$(EXESUF)
-vhost-user-json-y += tools/virtiofsd/50-qemu-virtiofsd.json
 endif
-
-# Sphinx does not allow building manuals into the same directory as
-# the source files, so if we're doing an in-tree QEMU build we must
-# build the manuals into a subdirectory (and then install them from
-# there for 'make install'). For an out-of-tree build we can just
-# use the docs/ subdirectory in the build tree as normal.
-ifeq ($(realpath $(SRC_PATH)),$(realpath .))
-MANUAL_BUILDDIR := docs/built
-else
-MANUAL_BUILDDIR := docs
 endif

 ifdef BUILD_DOCS
-DOCS+=$(MANUAL_BUILDDIR)/system/qemu.1
-DOCS+=$(MANUAL_BUILDDIR)/tools/qemu-img.1
-DOCS+=$(MANUAL_BUILDDIR)/tools/qemu-nbd.8
-DOCS+=$(MANUAL_BUILDDIR)/interop/qemu-ga.8
-ifeq ($(CONFIG_LINUX)$(CONFIG_SECCOMP)$(CONFIG_LIBCAP_NG),yyy)
-DOCS+=$(MANUAL_BUILDDIR)/tools/virtiofsd.1
-endif
-DOCS+=$(MANUAL_BUILDDIR)/system/qemu-block-drivers.7
+DOCS=qemu-doc.html qemu-doc.txt qemu.1 qemu-img.1 qemu-nbd.8 qemu-ga.8
 DOCS+=docs/interop/qemu-qmp-ref.html docs/interop/qemu-qmp-ref.txt docs/interop/qemu-qmp-ref.7
 DOCS+=docs/interop/qemu-ga-ref.html docs/interop/qemu-ga-ref.txt docs/interop/qemu-ga-ref.7
-DOCS+=$(MANUAL_BUILDDIR)/system/qemu-cpu-models.7
-DOCS+=$(MANUAL_BUILDDIR)/index.html
+DOCS+=docs/qemu-block-drivers.7
+DOCS+=docs/qemu-cpu-models.7
 ifdef CONFIG_VIRTFS
-DOCS+=$(MANUAL_BUILDDIR)/tools/virtfs-proxy-helper.1
+DOCS+=fsdev/virtfs-proxy-helper.1
 endif
 ifdef CONFIG_TRACE_SYSTEMTAP
-DOCS+=$(MANUAL_BUILDDIR)/tools/qemu-trace-stap.1
+DOCS+=scripts/qemu-trace-stap.1
 endif
 else
 DOCS=
@@ -413,16 +370,14 @@ MINIKCONF_ARGS = \
    CONFIG_OPENGL=$(CONFIG_OPENGL) \
    CONFIG_X11=$(CONFIG_X11) \
    CONFIG_VHOST_USER=$(CONFIG_VHOST_USER) \
-    CONFIG_VHOST_KERNEL=$(CONFIG_VHOST_KERNEL) \
    CONFIG_VIRTFS=$(CONFIG_VIRTFS) \
    CONFIG_LINUX=$(CONFIG_LINUX) \
    CONFIG_PVRDMA=$(CONFIG_PVRDMA)

 MINIKCONF_INPUTS = $(SRC_PATH)/Kconfig.host $(SRC_PATH)/hw/Kconfig
-MINIKCONF_DEPS = $(MINIKCONF_INPUTS) $(wildcard $(SRC_PATH)/hw/*/Kconfig)
 MINIKCONF = $(PYTHON) $(SRC_PATH)/scripts/minikconf.py \

-$(SUBDIR_DEVICES_MAK): %/config-devices.mak: default-configs/%.mak $(MINIKCONF_DEPS) $(BUILD_DIR)/config-host.mak
+$(SUBDIR_DEVICES_MAK): %/config-devices.mak: default-configs/%.mak $(MINIKCONF_INPUTS) $(BUILD_DIR)/config-host.mak
 	$(call quiet-command, $(MINIKCONF) $(MINIKCONF_ARGS) > $@.tmp, "GEN", "$@.tmp")
 	$(call quiet-command, if test -f $@; then \
 	  if cmp -s $@.old $@; then \
@@ -458,7 +413,6 @@ dummy := $(call unnest-vars,, \
                elf2dmp-obj-y \
                ivshmem-client-obj-y \
                ivshmem-server-obj-y \
-                virtiofsd-obj-y \
                rdmacm-mux-obj-y \
                libvhost-user-obj-y \
                vhost-user-scsi-obj-y \
@@ -468,13 +422,16 @@ dummy := $(call unnest-vars,, \
                qga-vss-dll-obj-y \
                block-obj-y \
                block-obj-m \
-                storage-daemon-obj-y \
-                storage-daemon-obj-m \
                crypto-obj-y \
+                crypto-user-obj-y \
                qom-obj-y \
                io-obj-y \
                common-obj-y \
                common-obj-m \
+                ui-obj-y \
+                ui-obj-m \
+                audio-obj-y \
+                audio-obj-m \
                trace-obj-y)

 include $(SRC_PATH)/tests/Makefile.include
@@ -497,28 +454,16 @@ config-host.h-timestamp: config-host.mak
 qemu-options.def: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$@")

-TARGET_DIRS_RULES := $(foreach t, all fuzz clean install, $(addsuffix /$(t), $(TARGET_DIRS)))
+TARGET_DIRS_RULES := $(foreach t, all clean install, $(addsuffix /$(t), $(TARGET_DIRS)))

 SOFTMMU_ALL_RULES=$(filter %-softmmu/all, $(TARGET_DIRS_RULES))
 $(SOFTMMU_ALL_RULES): $(authz-obj-y)
 $(SOFTMMU_ALL_RULES): $(block-obj-y)
-$(SOFTMMU_ALL_RULES): $(storage-daemon-obj-y)
 $(SOFTMMU_ALL_RULES): $(chardev-obj-y)
 $(SOFTMMU_ALL_RULES): $(crypto-obj-y)
 $(SOFTMMU_ALL_RULES): $(io-obj-y)
 $(SOFTMMU_ALL_RULES): config-all-devices.mak
-ifdef DECOMPRESS_EDK2_BLOBS
 $(SOFTMMU_ALL_RULES): $(edk2-decompressed)
-endif
-
-SOFTMMU_FUZZ_RULES=$(filter %-softmmu/fuzz, $(TARGET_DIRS_RULES))
-$(SOFTMMU_FUZZ_RULES): $(authz-obj-y)
-$(SOFTMMU_FUZZ_RULES): $(block-obj-y)
-$(SOFTMMU_FUZZ_RULES): $(chardev-obj-y)
-$(SOFTMMU_FUZZ_RULES): $(crypto-obj-y)
-$(SOFTMMU_FUZZ_RULES): $(io-obj-y)
-$(SOFTMMU_FUZZ_RULES): config-all-devices.mak
-$(SOFTMMU_FUZZ_RULES): $(edk2-decompressed)

 .PHONY: $(TARGET_DIRS_RULES)
 # The $(TARGET_DIRS_RULES) are of the form SUBDIR/GOAL, so that
@@ -532,7 +477,7 @@ DTC_CPPFLAGS=-I$(BUILD_DIR)/dtc -I$(SRC_PATH)/dtc -I$(SRC_PATH)/dtc/libfdt

 .PHONY: dtc/all
 dtc/all: .git-submodule-status dtc/libfdt dtc/tests
-	$(call quiet-command,$(MAKE) $(DTC_MAKE_ARGS) CPPFLAGS="$(DTC_CPPFLAGS)" CFLAGS="$(DTC_CFLAGS)" LDFLAGS="$(QEMU_LDFLAGS)" ARFLAGS="$(ARFLAGS)" CC="$(CC)" AR="$(AR)" LD="$(LD)" $(SUBDIR_MAKEFLAGS) libfdt/libfdt.a,)
+	$(call quiet-command,$(MAKE) $(DTC_MAKE_ARGS) CPPFLAGS="$(DTC_CPPFLAGS)" CFLAGS="$(DTC_CFLAGS)" LDFLAGS="$(LDFLAGS)" ARFLAGS="$(ARFLAGS)" CC="$(CC)" AR="$(AR)" LD="$(LD)" $(SUBDIR_MAKEFLAGS) libfdt/libfdt.a,)

 dtc/%: .git-submodule-status
 	@mkdir -p $@
@@ -555,11 +500,7 @@ capstone/all: .git-submodule-status

 .PHONY: slirp/all
 slirp/all: .git-submodule-status
-	$(call quiet-command,$(MAKE) -C $(SRC_PATH)/slirp		\
-		BUILD_DIR="$(BUILD_DIR)/slirp" 			\
-		PKG_CONFIG="$(PKG_CONFIG)" 				\
-		CC="$(CC)" AR="$(AR)" 	LD="$(LD)" RANLIB="$(RANLIB)"	\
-		CFLAGS="$(QEMU_CFLAGS) $(CFLAGS)" LDFLAGS="$(QEMU_LDFLAGS)")
+	$(call quiet-command,$(MAKE) -C $(SRC_PATH)/slirp BUILD_DIR="$(BUILD_DIR)/slirp" CC="$(CC)" AR="$(AR)" LD="$(LD)" RANLIB="$(RANLIB)" CFLAGS="$(QEMU_CFLAGS) $(CFLAGS)" LDFLAGS="$(LDFLAGS)")

 # Compatibility gunk to keep make working across the rename of targets
 # for recursion, to be removed some time after 4.1.
@@ -568,9 +509,6 @@ subdir-capstone: capstone/all
 subdir-slirp: slirp/all

 $(filter %/all, $(TARGET_DIRS_RULES)): libqemuutil.a $(common-obj-y) \
-	$(qom-obj-y)
-
-$(filter %/fuzz, $(TARGET_DIRS_RULES)): libqemuutil.a $(common-obj-y) \
 	$(qom-obj-y) $(crypto-user-obj-$(CONFIG_USER_ONLY))

 ROM_DIRS = $(addprefix pc-bios/, $(ROMS))
@@ -582,7 +520,6 @@ $(ROM_DIRS_RULES):

 .PHONY: recurse-all recurse-clean recurse-install
 recurse-all: $(addsuffix /all, $(TARGET_DIRS) $(ROM_DIRS))
-recurse-fuzz: $(addsuffix /fuzz, $(TARGET_DIRS) $(ROM_DIRS))
 recurse-clean: $(addsuffix /clean, $(TARGET_DIRS) $(ROM_DIRS))
 recurse-install: $(addsuffix /install, $(TARGET_DIRS))
 $(addsuffix /install, $(TARGET_DIRS)): all
@@ -607,7 +544,6 @@ qemu-img.o: qemu-img-cmds.h
 qemu-img$(EXESUF): qemu-img.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
 qemu-nbd$(EXESUF): qemu-nbd.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
 qemu-io$(EXESUF): qemu-io.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
-qemu-storage-daemon$(EXESUF): qemu-storage-daemon.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(chardev-obj-y) $(io-obj-y) $(qom-obj-y) $(storage-daemon-obj-y) $(COMMON_LDADDS)

 qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o $(COMMON_LDADDS)

@@ -616,6 +552,7 @@ qemu-keymap$(EXESUF): qemu-keymap.o ui/input-keymap.o $(COMMON_LDADDS)
 qemu-edid$(EXESUF): qemu-edid.o hw/display/edid-generate.o $(COMMON_LDADDS)

 fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/9p-marshal.o fsdev/9p-iov-marshal.o $(COMMON_LDADDS)
+fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap

 scsi/qemu-pr-helper$(EXESUF): scsi/qemu-pr-helper.o scsi/utils.o $(authz-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
 ifdef CONFIG_MPATH
@@ -631,26 +568,18 @@ qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
 qemu-keymap$(EXESUF): LIBS += $(XKBCOMMON_LIBS)
 qemu-keymap$(EXESUF): QEMU_CFLAGS += $(XKBCOMMON_CFLAGS)

-qapi-py = $(SRC_PATH)/scripts/qapi/__init__.py \
-$(SRC_PATH)/scripts/qapi/commands.py \
-$(SRC_PATH)/scripts/qapi/common.py \
-$(SRC_PATH)/scripts/qapi/doc.py \
-$(SRC_PATH)/scripts/qapi/error.py \
+qapi-py = $(SRC_PATH)/scripts/qapi/commands.py \
 $(SRC_PATH)/scripts/qapi/events.py \
-$(SRC_PATH)/scripts/qapi/expr.py \
-$(SRC_PATH)/scripts/qapi/gen.py \
 $(SRC_PATH)/scripts/qapi/introspect.py \
-$(SRC_PATH)/scripts/qapi/parser.py \
-$(SRC_PATH)/scripts/qapi/schema.py \
-$(SRC_PATH)/scripts/qapi/source.py \
 $(SRC_PATH)/scripts/qapi/types.py \
 $(SRC_PATH)/scripts/qapi/visit.py \
+$(SRC_PATH)/scripts/qapi/common.py \
+$(SRC_PATH)/scripts/qapi/doc.py \
 $(SRC_PATH)/scripts/qapi-gen.py

 qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h \
 qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h \
 qga/qapi-generated/qga-qapi-commands.h qga/qapi-generated/qga-qapi-commands.c \
-qga/qapi-generated/qga-qapi-init-commands.h qga/qapi-generated/qga-qapi-init-commands.c \
 qga/qapi-generated/qga-qapi-doc.texi: \
 qga/qapi-generated/qapi-gen-timestamp ;
 qga/qapi-generated/qapi-gen-timestamp: $(SRC_PATH)/qga/qapi-schema.json $(qapi-py)
@@ -669,18 +598,7 @@ qapi-gen-timestamp: $(qapi-modules) $(qapi-py)
 		"GEN","$(@:%-timestamp=%)")
 	@>$@

-qapi-modules-storage-daemon = \
-	$(SRC_PATH)/storage-daemon/qapi/qapi-schema.json \
-    $(QAPI_MODULES_STORAGE_DAEMON:%=$(SRC_PATH)/qapi/%.json)
-
-$(GENERATED_STORAGE_DAEMON_QAPI_FILES): storage-daemon/qapi/qapi-gen-timestamp ;
-storage-daemon/qapi/qapi-gen-timestamp: $(qapi-modules-storage-daemon) $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-gen.py \
-		-o "storage-daemon/qapi" $<, \
-		"GEN","$(@:%-timestamp=%)")
-	@>$@
-
-QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qapi-commands.h qga-qapi-init-commands.h)
+QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qapi-commands.h)
 $(qga-obj-y): $(QGALIB_GEN)

 qemu-ga$(EXESUF): $(qga-obj-y) $(COMMON_LDADDS)
@@ -726,12 +644,6 @@ rdmacm-mux$(EXESUF): LIBS += "-libumad"
 rdmacm-mux$(EXESUF): $(rdmacm-mux-obj-y) $(COMMON_LDADDS)
 	$(call LINK, $^)

-# relies on Linux-specific syscalls
-ifeq ($(CONFIG_LINUX)$(CONFIG_SECCOMP)$(CONFIG_LIBCAP_NG),yyy)
-virtiofsd$(EXESUF): $(virtiofsd-obj-y) libvhost-user.a $(COMMON_LDADDS)
-	$(call LINK, $^)
-endif
-
 vhost-user-gpu$(EXESUF): $(vhost-user-gpu-obj-y) $(libvhost-user-obj-y) libqemuutil.a libqemustub.a
 	$(call LINK, $^)

@@ -769,7 +681,7 @@ clean: recurse-clean
 		! -path ./roms/edk2/BaseTools/Source/Python/UPT/Dll/sqlite3.dll \
 		-exec rm {} +
 	rm -f $(edk2-decompressed)
-	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) TAGS cscope.* *.pod *~ */*~
+	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga$(EXESUF) TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod scsi/*.pod
 	rm -f qemu-img-cmds.h
 	rm -f ui/shader/*-vert.h ui/shader/*-frag.h
@@ -778,7 +690,6 @@ clean: recurse-clean
 	rm -f trace/generated-tracers-dtrace.h*
 	rm -f $(foreach f,$(generated-files-y),$(f) $(f)-timestamp)
 	rm -f qapi-gen-timestamp
-	rm -f storage-daemon/qapi/qapi-gen-timestamp
 	rm -rf qga/qapi-generated
 	rm -f config-all-devices.mak

@@ -789,19 +700,32 @@ dist: qemu-$(VERSION).tar.bz2
 qemu-%.tar.bz2:
 	$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"

+# Sphinx does not allow building manuals into the same directory as
+# the source files, so if we're doing an in-tree QEMU build we must
+# build the manuals into a subdirectory (and then install them from
+# there for 'make install'). For an out-of-tree build we can just
+# use the docs/ subdirectory in the build tree as normal.
+ifeq ($(realpath $(SRC_PATH)),$(realpath .))
+MANUAL_BUILDDIR := docs/built
+else
+MANUAL_BUILDDIR := docs
+endif
+
 define clean-manual =
 rm -rf $(MANUAL_BUILDDIR)/$1/_static
 rm -f $(MANUAL_BUILDDIR)/$1/objects.inv $(MANUAL_BUILDDIR)/$1/searchindex.js $(MANUAL_BUILDDIR)/$1/*.html
 endef

 distclean: clean
-	rm -f config-host.mak config-host.h* $(DOCS)
-	rm -f tests/tcg/config-*.mak
+	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi qemu-monitor-info.texi
 	rm -f config-all-devices.mak config-all-disas.mak config.status
 	rm -f $(SUBDIR_DEVICES_MAK)
 	rm -f po/*.mo tests/qemu-iotests/common.env
 	rm -f roms/seabios/config.mak roms/vgabios/config.mak
-	rm -f qemu-plugins-ld.symbols qemu-plugins-ld64.symbols
+	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps
+	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
+	rm -f qemu-doc.log qemu-doc.pdf qemu-doc.pg qemu-doc.toc qemu-doc.tp
+	rm -f qemu-doc.vr qemu-doc.txt
 	rm -f config.log
 	rm -f linux-headers/asm
 	rm -f docs/version.texi
@@ -810,13 +734,12 @@ distclean: clean
 	rm -f docs/interop/qemu-qmp-ref.txt docs/interop/qemu-ga-ref.txt
 	rm -f docs/interop/qemu-qmp-ref.pdf docs/interop/qemu-ga-ref.pdf
 	rm -f docs/interop/qemu-qmp-ref.html docs/interop/qemu-ga-ref.html
+	rm -f docs/qemu-block-drivers.7
+	rm -f docs/qemu-cpu-models.7
 	rm -rf .doctrees
 	$(call clean-manual,devel)
 	$(call clean-manual,interop)
 	$(call clean-manual,specs)
-	$(call clean-manual,system)
-	$(call clean-manual,tools)
-	$(call clean-manual,user)
 	for d in $(TARGET_DIRS); do \
 	rm -rf $$d || exit 1 ; \
        done
@@ -829,10 +752,10 @@ de-ch  es     fo  fr-ca  hu     ja  mk  pt  sl     tr \
 bepo    cz

 ifdef INSTALL_BLOBS
-BLOBS=bios.bin bios-256k.bin bios-microvm.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
+BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin vgabios-virtio.bin \
 vgabios-ramfb.bin vgabios-bochs-display.bin vgabios-ati.bin \
-openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
+ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
 efi-e1000.rom efi-eepro100.rom efi-ne2k_pci.rom \
@@ -842,13 +765,13 @@ qemu-nsis.bmp \
 bamboo.dtb canyonlands.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
 multiboot.bin linuxboot.bin linuxboot_dma.bin kvmvapic.bin pvh.bin \
 s390-ccw.img s390-netboot.img \
-slof.bin skiboot.lid \
+spapr-rtas.bin slof.bin skiboot.lid \
 palcode-clipper \
 u-boot.e500 u-boot-sam460-20100605.bin \
 qemu_vga.ndrv \
 edk2-licenses.txt \
 hppa-firmware.img \
-opensbi-riscv32-sifive_u-fw_jump.bin opensbi-riscv32-virt-fw_jump.bin \
+opensbi-riscv32-virt-fw_jump.bin \
 opensbi-riscv64-sifive_u-fw_jump.bin opensbi-riscv64-virt-fw_jump.bin


@@ -860,11 +783,10 @@ DESCS=
 endif

 # Note that we manually filter-out the non-Sphinx documentation which
-# is currently built into the docs/interop directory in the build tree,
-# and also any sphinx-built manpages.
+# is currently built into the docs/interop directory in the build tree.
 define install-manual =
 for d in $$(cd $(MANUAL_BUILDDIR) && find $1 -type d); do $(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)/$$d"; done
-for f in $$(cd $(MANUAL_BUILDDIR) && find $1 -type f -a '!' '(' -name '*.[0-9]' -o -name 'qemu-*-qapi.*' -o -name 'qemu-*-ref.*' ')' ); do $(INSTALL_DATA) "$(MANUAL_BUILDDIR)/$$f" "$(DESTDIR)$(qemu_docdir)/$$f"; done
+for f in $$(cd $(MANUAL_BUILDDIR) && find $1 -type f -a '!' '(' -name 'qemu-*-qapi.*' -o -name 'qemu-*-ref.*' ')' ); do $(INSTALL_DATA) "$(MANUAL_BUILDDIR)/$$f" "$(DESTDIR)$(qemu_docdir)/$$f"; done
 endef

 # Note that we deliberately do not install the "devel" manual: it is
@@ -873,32 +795,30 @@ endef
 install-sphinxdocs: sphinxdocs
 	$(call install-manual,interop)
 	$(call install-manual,specs)
-	$(call install-manual,system)
-	$(call install-manual,tools)
-	$(call install-manual,user)

 install-doc: $(DOCS) install-sphinxdocs
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/index.html "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DATA) qemu-doc.html "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DATA) qemu-doc.txt "$(DESTDIR)$(qemu_docdir)"
 	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.html "$(DESTDIR)$(qemu_docdir)"
 	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.txt "$(DESTDIR)$(qemu_docdir)"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/system/qemu.1 "$(DESTDIR)$(mandir)/man1"
+	$(INSTALL_DATA) qemu.1 "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man7"
 	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.7 "$(DESTDIR)$(mandir)/man7"
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/system/qemu-block-drivers.7 "$(DESTDIR)$(mandir)/man7"
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/system/qemu-cpu-models.7 "$(DESTDIR)$(mandir)/man7"
-ifeq ($(CONFIG_TOOLS),y)
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/tools/qemu-img.1 "$(DESTDIR)$(mandir)/man1"
+	$(INSTALL_DATA) docs/qemu-block-drivers.7 "$(DESTDIR)$(mandir)/man7"
+	$(INSTALL_DATA) docs/qemu-cpu-models.7 "$(DESTDIR)$(mandir)/man7"
+ifneq ($(TOOLS),)
+	$(INSTALL_DATA) qemu-img.1 "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man8"
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/tools/qemu-nbd.8 "$(DESTDIR)$(mandir)/man8"
+	$(INSTALL_DATA) qemu-nbd.8 "$(DESTDIR)$(mandir)/man8"
 endif
 ifdef CONFIG_TRACE_SYSTEMTAP
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/tools/qemu-trace-stap.1 "$(DESTDIR)$(mandir)/man1"
+	$(INSTALL_DATA) scripts/qemu-trace-stap.1 "$(DESTDIR)$(mandir)/man1"
 endif
 ifneq (,$(findstring qemu-ga,$(TOOLS)))
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/interop/qemu-ga.8 "$(DESTDIR)$(mandir)/man8"
+	$(INSTALL_DATA) qemu-ga.8 "$(DESTDIR)$(mandir)/man8"
 	$(INSTALL_DATA) docs/interop/qemu-ga-ref.html "$(DESTDIR)$(qemu_docdir)"
 	$(INSTALL_DATA) docs/interop/qemu-ga-ref.txt "$(DESTDIR)$(qemu_docdir)"
 	$(INSTALL_DATA) docs/interop/qemu-ga-ref.7 "$(DESTDIR)$(mandir)/man7"
@@ -906,10 +826,7 @@ endif
 endif
 ifdef CONFIG_VIRTFS
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/tools/virtfs-proxy-helper.1 "$(DESTDIR)$(mandir)/man1"
-endif
-ifeq ($(CONFIG_LINUX)$(CONFIG_SECCOMP)$(CONFIG_LIBCAP_NG),yyy)
-	$(INSTALL_DATA) $(MANUAL_BUILDDIR)/tools/virtiofsd.1 "$(DESTDIR)$(mandir)/man1"
+	$(INSTALL_DATA) fsdev/virtfs-proxy-helper.1 "$(DESTDIR)$(mandir)/man1"
 endif

 install-datadir:
@@ -924,15 +841,11 @@ endif

 ICON_SIZES=16x16 24x24 32x32 48x48 64x64 128x128 256x256 512x512

-install-includedir:
-	$(INSTALL_DIR) "$(DESTDIR)$(includedir)"
-
-install: all $(if $(BUILD_DOCS),install-doc) \
-	install-datadir install-localstatedir install-includedir \
+install: all $(if $(BUILD_DOCS),install-doc) install-datadir install-localstatedir \
 	$(if $(INSTALL_BLOBS),$(edk2-decompressed)) \
 	recurse-install
 ifneq ($(TOOLS),)
-	$(call install-prog,$(TOOLS),$(DESTDIR)$(bindir))
+	$(call install-prog,$(subst qemu-ga,qemu-ga$(EXESUF),$(TOOLS)),$(DESTDIR)$(bindir))
 endif
 ifneq ($(CONFIG_MODULES),)
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
@@ -990,9 +903,6 @@ endif
 		"$(DESTDIR)$(qemu_desktopdir)/qemu.desktop"
 ifdef CONFIG_GTK
 	$(MAKE) -C po $@
-endif
-ifeq ($(CONFIG_PLUGIN),y)
-	$(INSTALL_DATA) $(SRC_PATH)/include/qemu/qemu-plugin.h "$(DESTDIR)$(includedir)/qemu-plugin.h"
 endif
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/keymaps"
 	set -e; for x in $(KEYMAPS); do \
@@ -1064,64 +974,33 @@ docs/version.texi: $(SRC_PATH)/VERSION config-host.mak
 # and handles "don't rebuild things unless necessary" itself.
 # The '.doctrees' files are cached information to speed this up.
 .PHONY: sphinxdocs
-sphinxdocs: $(MANUAL_BUILDDIR)/devel/index.html \
-            $(MANUAL_BUILDDIR)/interop/index.html \
-            $(MANUAL_BUILDDIR)/specs/index.html \
-            $(MANUAL_BUILDDIR)/system/index.html \
-            $(MANUAL_BUILDDIR)/tools/index.html \
-            $(MANUAL_BUILDDIR)/user/index.html
+sphinxdocs: $(MANUAL_BUILDDIR)/devel/index.html $(MANUAL_BUILDDIR)/interop/index.html $(MANUAL_BUILDDIR)/specs/index.html

 # Canned command to build a single manual
-# Arguments: $1 = manual name, $2 = Sphinx builder ('html' or 'man')
-# Note the use of different doctree for each (manual, builder) tuple;
-# this works around Sphinx not handling parallel invocation on
-# a single doctree: https://github.com/sphinx-doc/sphinx/issues/2946
-build-manual = $(call quiet-command,CONFDIR="$(qemu_confdir)" $(SPHINX_BUILD) $(if $(V),,-q) $(SPHINX_WERROR) -b $2 -D version=$(VERSION) -D release="$(FULL_VERSION)" -d .doctrees/$1-$2 $(SRC_PATH)/docs/$1 $(MANUAL_BUILDDIR)/$1 ,"SPHINX","$(MANUAL_BUILDDIR)/$1")
+build-manual = $(call quiet-command,sphinx-build $(if $(V),,-q) -W -n -b html -D version=$(VERSION) -D release="$(FULL_VERSION)" -d .doctrees/$1 $(SRC_PATH)/docs/$1 $(MANUAL_BUILDDIR)/$1 ,"SPHINX","$(MANUAL_BUILDDIR)/$1")
 # We assume all RST files in the manual's directory are used in it
-manual-deps = $(wildcard $(SRC_PATH)/docs/$1/*.rst $(SRC_PATH)/docs/$1/*/*.rst) \
-              $(SRC_PATH)/docs/defs.rst.inc \
-              $(SRC_PATH)/docs/$1/conf.py $(SRC_PATH)/docs/conf.py \
-              $(SRC_PATH)/docs/sphinx/*.py
-# Macro to write out the rule and dependencies for building manpages
-# Usage: $(call define-manpage-rule,manualname,manpage1 manpage2...[,extradeps])
-# 'extradeps' is optional, and specifies extra files (eg .hx files) that
-# the manual page depends on.
-define define-manpage-rule
-$(call atomic,$(foreach manpage,$2,$(MANUAL_BUILDDIR)/$1/$(manpage)),$(call manual-deps,$1) $3)
-	$(call build-manual,$1,man)
-endef
+manual-deps = $(wildcard $(SRC_PATH)/docs/$1/*.rst) $(SRC_PATH)/docs/$1/conf.py $(SRC_PATH)/docs/conf.py

 $(MANUAL_BUILDDIR)/devel/index.html: $(call manual-deps,devel)
-	$(call build-manual,devel,html)
+	$(call build-manual,devel)

 $(MANUAL_BUILDDIR)/interop/index.html: $(call manual-deps,interop)
-	$(call build-manual,interop,html)
+	$(call build-manual,interop)

 $(MANUAL_BUILDDIR)/specs/index.html: $(call manual-deps,specs)
-	$(call build-manual,specs,html)
+	$(call build-manual,specs)

-$(MANUAL_BUILDDIR)/system/index.html: $(call manual-deps,system) $(SRC_PATH)/hmp-commands.hx $(SRC_PATH)/hmp-commands-info.hx $(SRC_PATH)/qemu-options.hx
-	$(call build-manual,system,html)
+qemu-options.texi: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")

-$(MANUAL_BUILDDIR)/tools/index.html: $(call manual-deps,tools) $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/docs/qemu-option-trace.rst.inc
-	$(call build-manual,tools,html)
+qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx $(SRC_PATH)/scripts/hxtool
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")

-$(MANUAL_BUILDDIR)/user/index.html: $(call manual-deps,user)
-	$(call build-manual,user,html)
+qemu-monitor-info.texi: $(SRC_PATH)/hmp-commands-info.hx $(SRC_PATH)/scripts/hxtool
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")

-$(call define-manpage-rule,interop,qemu-ga.8)
-
-$(call define-manpage-rule,system,qemu.1 qemu-block-drivers.7 qemu-cpu-models.7)
-
-$(call define-manpage-rule,tools,\
-       qemu-img.1 qemu-nbd.8 qemu-trace-stap.1\
-       virtiofsd.1 virtfs-proxy-helper.1,\
-       $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/docs/qemu-option-trace.rst.inc)
-
-$(MANUAL_BUILDDIR)/index.html: $(SRC_PATH)/docs/index.html.in qemu-version.h
-	@mkdir -p "$(MANUAL_BUILDDIR)"
-	$(call quiet-command, sed "s|@@VERSION@@|${VERSION}|g" $< >$@, \
-             "GEN","$@")
+qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/scripts/hxtool
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")

 docs/interop/qemu-qmp-qapi.texi: qapi/qapi-doc.texi
 	@cp -p $< $@
@@ -1129,10 +1008,27 @@ docs/interop/qemu-qmp-qapi.texi: qapi/qapi-doc.texi
 docs/interop/qemu-ga-qapi.texi: qga/qapi-generated/qga-qapi-doc.texi
 	@cp -p $< $@

-html: docs/interop/qemu-qmp-ref.html docs/interop/qemu-ga-ref.html sphinxdocs
-info: docs/interop/qemu-qmp-ref.info docs/interop/qemu-ga-ref.info
-pdf: docs/interop/qemu-qmp-ref.pdf docs/interop/qemu-ga-ref.pdf
-txt: docs/interop/qemu-qmp-ref.txt docs/interop/qemu-ga-ref.txt
+qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi qemu-monitor-info.texi
+qemu.1: qemu-option-trace.texi
+qemu-img.1: qemu-img.texi qemu-option-trace.texi qemu-img-cmds.texi
+fsdev/virtfs-proxy-helper.1: fsdev/virtfs-proxy-helper.texi
+qemu-nbd.8: qemu-nbd.texi qemu-option-trace.texi
+qemu-ga.8: qemu-ga.texi
+docs/qemu-block-drivers.7: docs/qemu-block-drivers.texi
+docs/qemu-cpu-models.7: docs/qemu-cpu-models.texi
+scripts/qemu-trace-stap.1: scripts/qemu-trace-stap.texi
+
+html: qemu-doc.html docs/interop/qemu-qmp-ref.html docs/interop/qemu-ga-ref.html sphinxdocs
+info: qemu-doc.info docs/interop/qemu-qmp-ref.info docs/interop/qemu-ga-ref.info
+pdf: qemu-doc.pdf docs/interop/qemu-qmp-ref.pdf docs/interop/qemu-ga-ref.pdf
+txt: qemu-doc.txt docs/interop/qemu-qmp-ref.txt docs/interop/qemu-ga-ref.txt
+
+qemu-doc.html qemu-doc.info qemu-doc.pdf qemu-doc.txt: \
+	qemu-img.texi qemu-nbd.texi qemu-options.texi \
+	qemu-tech.texi qemu-option-trace.texi \
+	qemu-deprecated.texi qemu-monitor.texi qemu-img-cmds.texi qemu-ga.texi \
+	qemu-monitor-info.texi docs/qemu-block-drivers.texi \
+	docs/qemu-cpu-models.texi docs/security.texi

 docs/interop/qemu-ga-ref.dvi docs/interop/qemu-ga-ref.html \
    docs/interop/qemu-ga-ref.info docs/interop/qemu-ga-ref.pdf \
@@ -1235,57 +1131,50 @@ endif
 include $(SRC_PATH)/tests/docker/Makefile.include
 include $(SRC_PATH)/tests/vm/Makefile.include

-print-help-run = printf "  %-30s - %s\\n" "$1" "$2"
-print-help = $(quiet-@)$(call print-help-run,$1,$2)
-
 .PHONY: help
 help:
 	@echo  'Generic targets:'
-	$(call print-help,all,Build all)
+	@echo  '  all             - Build all'
 ifdef CONFIG_MODULES
-	$(call print-help,modules,Build all modules)
+	@echo  '  modules         - Build all modules'
 endif
-	$(call print-help,dir/file.o,Build specified target only)
-	$(call print-help,install,Install QEMU, documentation and tools)
-	$(call print-help,ctags/TAGS,Generate tags file for editors)
-	$(call print-help,cscope,Generate cscope index)
+	@echo  '  dir/file.o      - Build specified target only'
+	@echo  '  install         - Install QEMU, documentation and tools'
+	@echo  '  ctags/TAGS      - Generate tags file for editors'
+	@echo  '  cscope          - Generate cscope index'
 	@echo  ''
 	@$(if $(TARGET_DIRS), \
 		echo 'Architecture specific targets:'; \
 		$(foreach t, $(TARGET_DIRS), \
-		$(call print-help-run,$(t)/all,Build for $(t));) \
-		echo '')
-	@$(if $(TOOLS), \
-		echo 'Tools targets:'; \
-		$(foreach t, $(TOOLS), \
-		$(call print-help-run,$(t),Build $(shell basename $(t)) tool);) \
+		printf "  %-30s - Build for %s\\n" $(t)/all $(t);) \
 		echo '')
 	@echo  'Cleaning targets:'
-	$(call print-help,clean,Remove most generated files but keep the config)
+	@echo  '  clean           - Remove most generated files but keep the config'
 ifdef CONFIG_GCOV
-	$(call print-help,clean-coverage,Remove coverage files)
+	@echo  '  clean-coverage  - Remove coverage files'
 endif
-	$(call print-help,distclean,Remove all generated files)
-	$(call print-help,dist,Build a distributable tarball)
+	@echo  '  distclean       - Remove all generated files'
+	@echo  '  dist            - Build a distributable tarball'
 	@echo  ''
 	@echo  'Test targets:'
-	$(call print-help,check,Run all tests (check-help for details))
-	$(call print-help,docker,Help about targets running tests inside containers)
-	$(call print-help,vm-help,Help about targets running tests inside VM)
+	@echo  '  check           - Run all tests (check-help for details)'
+	@echo  '  docker          - Help about targets running tests inside Docker containers'
+	@echo  '  vm-help         - Help about targets running tests inside VM'
 	@echo  ''
 	@echo  'Documentation targets:'
-	$(call print-help,html info pdf txt,Build documentation in specified format)
+	@echo  '  html info pdf txt'
+	@echo  '                  - Build documentation in specified format'
 ifdef CONFIG_GCOV
-	$(call print-help,coverage-report,Create code coverage report)
+	@echo  '  coverage-report - Create code coverage report'
 endif
 	@echo  ''
 ifdef CONFIG_WIN32
 	@echo  'Windows targets:'
-	$(call print-help,installer,Build NSIS-based installer for QEMU)
+	@echo  '  installer       - Build NSIS-based installer for QEMU'
 ifdef QEMU_GA_MSI_ENABLED
-	$(call print-help,msi,Build MSI-based installer for qemu-ga)
+	@echo  '  msi             - Build MSI-based installer for qemu-ga'
 endif
 	@echo  ''
 endif
-	$(call print-help,$(MAKE) [targets],(quiet build, default))
-	$(call print-help,$(MAKE) V=1 [targets],(verbose build))
+	@echo  '  $(MAKE) [targets]      (quiet build, default)'
+	@echo  '  $(MAKE) V=1 [targets]  (verbose build)'
@@ -1,18 +1,18 @@
 #######################################################################
 # Common libraries for tools and emulators
-stub-obj-y = stubs/
-util-obj-y = crypto/ util/ qobject/ qapi/
-qom-obj-y = qom/
-
-#######################################################################
-# code used by both qemu system emulation and qemu-img
-
-ifeq ($(call lor,$(CONFIG_SOFTMMU),$(CONFIG_TOOLS)),y)
+stub-obj-y = stubs/ util/ crypto/
+util-obj-y = util/ qobject/ qapi/

 chardev-obj-y = chardev/

+#######################################################################
+# authz-obj-y is code used by both qemu system emulation and qemu-img
+
 authz-obj-y = authz/

+#######################################################################
+# block-obj-y is code used by both qemu system emulation and qemu-img
+
 block-obj-y = nbd/
 block-obj-y += block.o blockjob.o job.o
 block-obj-y += block/ scsi/
@@ -21,20 +21,21 @@ block-obj-$(CONFIG_REPLICATION) += replication.o

 block-obj-m = block/

+#######################################################################
+# crypto-obj-y is code used by both qemu system emulation and qemu-img
+
 crypto-obj-y = crypto/
-
-io-obj-y = io/
-
-endif # CONFIG_SOFTMMU or CONFIG_TOOLS
+crypto-user-obj-y = crypto/

 #######################################################################
-# storage-daemon-obj-y is code used by qemu-storage-daemon (these objects are
-# used for system emulation, too, but specified separately there)
+# qom-obj-y is code used by both qemu system emulation and qemu-img

-storage-daemon-obj-y = block/ monitor/ qapi/ qom/ storage-daemon/
-storage-daemon-obj-y += blockdev.o blockdev-nbd.o iothread.o job-qmp.o
-storage-daemon-obj-$(CONFIG_WIN32) += os-win32.o
-storage-daemon-obj-$(CONFIG_POSIX) += os-posix.o
+qom-obj-y = qom/
+
+#######################################################################
+# io-obj-y is code used by both qemu system emulation and qemu-img
+
+io-obj-y = io/

 ######################################################################
 # Target independent part of system emulation. The long term path is to
@@ -48,13 +49,12 @@ common-obj-y += dump/
 common-obj-y += job-qmp.o
 common-obj-y += monitor/
 common-obj-y += net/
-common-obj-y += qdev-monitor.o
+common-obj-y += qdev-monitor.o device-hotplug.o
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o

 common-obj-$(CONFIG_LINUX) += fsdev/

-common-obj-y += accel/
 common-obj-y += migration/

 common-obj-y += audio/
@@ -65,8 +65,12 @@ common-obj-y += replay/

 common-obj-y += ui/
 common-obj-m += ui/
+common-obj-y += bt-host.o bt-vhci.o
+bt-host.o-cflags := $(BLUEZ_CFLAGS)

 common-obj-y += dma-helpers.o
+common-obj-y += vl.o
+vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS)
 common-obj-$(CONFIG_TPM) += tpm.o

 common-obj-y += backends/
@@ -78,9 +82,11 @@ qemu-seccomp.o-libs := $(SECCOMP_LIBS)

 common-obj-$(CONFIG_FDT) += device_tree.o

-common-obj-y += qapi/
+######################################################################
+# qapi

-endif # CONFIG_SOFTMMU
+common-obj-y += qapi/
+endif

 #######################################################################
 # Target-independent parts used in system and user emulation
@@ -119,13 +125,11 @@ vhost-user-blk-obj-y = contrib/vhost-user-blk/
 rdmacm-mux-obj-y = contrib/rdmacm-mux/
 vhost-user-input-obj-y = contrib/vhost-user-input/
 vhost-user-gpu-obj-y = contrib/vhost-user-gpu/
-virtiofsd-obj-y = tools/virtiofsd/

 ######################################################################
 trace-events-subdirs =
 trace-events-subdirs += accel/kvm
 trace-events-subdirs += accel/tcg
-trace-events-subdirs += backends
 trace-events-subdirs += crypto
 trace-events-subdirs += monitor
 ifeq ($(CONFIG_USER_ONLY),y)
@@ -139,8 +143,8 @@ trace-events-subdirs += nbd
 trace-events-subdirs += scsi
 endif
 ifeq ($(CONFIG_SOFTMMU),y)
-trace-events-subdirs += audio
 trace-events-subdirs += chardev
+trace-events-subdirs += audio
 trace-events-subdirs += hw/9pfs
 trace-events-subdirs += hw/acpi
 trace-events-subdirs += hw/alpha
@@ -169,13 +173,11 @@ trace-events-subdirs += hw/pci-host
 trace-events-subdirs += hw/ppc
 trace-events-subdirs += hw/rdma
 trace-events-subdirs += hw/rdma/vmw
-trace-events-subdirs += hw/rtc
 trace-events-subdirs += hw/s390x
 trace-events-subdirs += hw/scsi
 trace-events-subdirs += hw/sd
 trace-events-subdirs += hw/sparc
 trace-events-subdirs += hw/sparc64
-trace-events-subdirs += hw/ssi
 trace-events-subdirs += hw/timer
 trace-events-subdirs += hw/tpm
 trace-events-subdirs += hw/usb
@@ -189,7 +191,6 @@ trace-events-subdirs += migration
 trace-events-subdirs += net
 trace-events-subdirs += ui
 endif
-trace-events-subdirs += hw/core
 trace-events-subdirs += hw/display
 trace-events-subdirs += qapi
 trace-events-subdirs += qom
@@ -12,7 +12,7 @@ endif

 $(call set-vpath, $(SRC_PATH):$(BUILD_DIR))
 ifdef CONFIG_LINUX
-QEMU_CFLAGS += -isystem ../linux-headers
+QEMU_CFLAGS += -I../linux-headers
 endif
 QEMU_CFLAGS += -iquote .. -iquote $(SRC_PATH)/target/$(TARGET_BASE_ARCH) -DNEED_CPU_H

@@ -39,6 +39,9 @@ endif
 PROGS=$(QEMU_PROG) $(QEMU_PROGW)
 STPFILES=

+# Makefile Tests
+include $(SRC_PATH)/tests/tcg/Makefile.include
+
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak

@@ -107,7 +110,7 @@ obj-y += trace/

 #########################################################
 # cpu emulator library
-obj-y += exec.o exec-vary.o
+obj-y += exec.o
 obj-y += accel/
 obj-$(CONFIG_TCG) += tcg/tcg.o tcg/tcg-op.o tcg/tcg-op-vec.o tcg/tcg-op-gvec.o
 obj-$(CONFIG_TCG) += tcg/tcg-common.o tcg/optimize.o
@@ -119,8 +122,6 @@ obj-y += disas.o
 obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
 LIBS := $(libs_cpu) $(LIBS)

-obj-$(CONFIG_PLUGIN) += plugins/
-
 #########################################################
 # Linux user emulator target

@@ -128,8 +129,7 @@ ifdef CONFIG_LINUX_USER

 QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) \
             -I$(SRC_PATH)/linux-user/host/$(ARCH) \
-             -I$(SRC_PATH)/linux-user \
-             -Ilinux-user/$(TARGET_ABI_DIR)
+             -I$(SRC_PATH)/linux-user

 obj-y += linux-user/
 obj-y += gdbstub.o thunk.o
@@ -161,7 +161,6 @@ obj-y += qapi/
 obj-y += memory.o
 obj-y += memory_mapping.o
 obj-y += migration/ram.o
-obj-y += softmmu/
 LIBS := $(libs_softmmu) $(LIBS)

 # Hardware support
@@ -186,6 +185,7 @@ dummy := $(call unnest-vars,.., \
               block-obj-m \
               chardev-obj-y \
               crypto-obj-y \
+               crypto-user-obj-y \
               qom-obj-y \
               io-obj-y \
               common-obj-y \
@@ -194,6 +194,7 @@ all-obj-y += $(common-obj-y)
 all-obj-y += $(qom-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(authz-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y) $(chardev-obj-y)
+all-obj-$(CONFIG_USER_ONLY) += $(crypto-user-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(crypto-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(io-obj-y)

@@ -204,7 +205,7 @@ endif
 COMMON_LDADDS = ../libqemuutil.a

 # build either PROG or PROGW
-$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS) $(softmmu-main-y)
+$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS)
 	$(call LINK, $(filter-out %.mak, $^))
 ifdef CONFIG_DARWIN
 	$(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"REZ","$(TARGET_DIR)$@")
@@ -229,22 +230,6 @@ ifdef CONFIG_TRACE_SYSTEMTAP
 	rm -f *.stp
 endif

-ifdef CONFIG_FUZZ
-include $(SRC_PATH)/tests/qtest/fuzz/Makefile.include
-include $(SRC_PATH)/tests/qtest/Makefile.include
-
-fuzz: fuzz-vars
-fuzz-vars: QEMU_CFLAGS := $(FUZZ_CFLAGS) $(QEMU_CFLAGS)
-fuzz-vars: QEMU_LDFLAGS := $(FUZZ_LDFLAGS) $(QEMU_LDFLAGS)
-fuzz-vars: $(QEMU_PROG_FUZZ)
-dummy := $(call unnest-vars,, fuzz-obj-y)
-
-
-$(QEMU_PROG_FUZZ): config-devices.mak $(all-obj-y) $(COMMON_LDADDS) $(fuzz-obj-y)
-	$(call LINK, $(filter-out %.mak, $^))
-
-endif
-
 install: all
 ifneq ($(PROGS),)
 	$(call install-prog,$(PROGS),$(DESTDIR)$(bindir))
@@ -1,6 +1,5 @@
-===========
-QEMU README
-===========
+         QEMU README
+         ===========

 QEMU is a generic and open source machine & userspace emulator and
 virtualizer.
@@ -38,9 +37,6 @@ QEMU is multi-platform software intended to be buildable on all modern
 Linux platforms, OS-X, Win32 (via the Mingw64 toolchain) and a variety
 of other UNIX targets. The simple steps to build QEMU are:

-
-.. code-block:: shell
-
  mkdir build
  cd build
  ../configure
@@ -48,9 +44,9 @@ of other UNIX targets. The simple steps to build QEMU are:

 Additional information can also be found online via the QEMU website:

-* `<https://qemu.org/Hosts/Linux>`_
-* `<https://qemu.org/Hosts/Mac>`_
-* `<https://qemu.org/Hosts/W32>`_
+  https://qemu.org/Hosts/Linux
+  https://qemu.org/Hosts/Mac
+  https://qemu.org/Hosts/W32


 Submitting patches
@@ -58,29 +54,24 @@ Submitting patches

 The QEMU source code is maintained under the GIT version control system.

-.. code-block:: shell
-
   git clone https://git.qemu.org/git/qemu.git

 When submitting patches, one common approach is to use 'git
 format-patch' and/or 'git send-email' to format & send the mail to the
 qemu-devel@nongnu.org mailing list. All patches submitted must contain
 a 'Signed-off-by' line from the author. Patches should follow the
-guidelines set out in the CODING_STYLE.rst file.
+guidelines set out in the HACKING and CODING_STYLE files.

 Additional information on submitting patches can be found online via
 the QEMU website

-* `<https://qemu.org/Contribute/SubmitAPatch>`_
-* `<https://qemu.org/Contribute/TrivialPatches>`_
+  https://qemu.org/Contribute/SubmitAPatch
+  https://qemu.org/Contribute/TrivialPatches

 The QEMU website is also maintained under source control.

-.. code-block:: shell
-
  git clone https://git.qemu.org/git/qemu-web.git
-
-* `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_
+  https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/

 A 'git-publish' utility was created to make above process less
 cumbersome, and is highly recommended for making regular contributions,
@@ -91,12 +82,10 @@ manually for once.

 For installation instructions, please go to

-*  `<https://github.com/stefanha/git-publish>`_
+  https://github.com/stefanha/git-publish

 The workflow with 'git-publish' is:

-.. code-block:: shell
-
  $ git checkout master -b my-feature
  $ # work on new commits, add your 'Signed-off-by' lines to each
  $ git publish
@@ -106,8 +95,6 @@ back to it in the future.

 Sending v2:

-.. code-block:: shell
-
  $ git checkout my-feature # same topic branch
  $ # making changes to the commits (using 'git rebase', for example)
  $ git publish
@@ -122,7 +109,7 @@ The QEMU project uses Launchpad as its primary upstream bug tracker. Bugs
 found when running code built from QEMU git or upstream released sources
 should be reported via:

-* `<https://bugs.launchpad.net/qemu/>`_
+  https://bugs.launchpad.net/qemu/

 If using QEMU via an operating system vendor pre-built binary package, it
 is preferable to report bugs to the vendor's own bug tracker first. If
@@ -131,7 +118,7 @@ reported via launchpad.

 For additional information on bug reporting consult:

-* `<https://qemu.org/Contribute/ReportABug>`_
+  https://qemu.org/Contribute/ReportABug


 Contact
@@ -140,11 +127,13 @@ Contact
 The QEMU community can be contacted in a number of ways, with the two
 main methods being email and IRC

-* `<mailto:qemu-devel@nongnu.org>`_
-* `<https://lists.nongnu.org/mailman/listinfo/qemu-devel>`_
-* #qemu on irc.oftc.net
+ - qemu-devel@nongnu.org
+   https://lists.nongnu.org/mailman/listinfo/qemu-devel
+ - #qemu on irc.oftc.net

 Information on additional methods of contacting the community can be
 found online via the QEMU website:

-* `<https://qemu.org/Contribute/StartHere>`_
+  https://qemu.org/Contribute/StartHere
+
+-- End
@@ -1 +1 @@
-5.0.1
+4.1.1
@@ -1,4 +1,4 @@
-common-obj-$(CONFIG_SOFTMMU) += accel.o
+obj-$(CONFIG_SOFTMMU) += accel.o
 obj-$(call land,$(CONFIG_SOFTMMU),$(CONFIG_POSIX)) += qtest.o
 obj-$(CONFIG_KVM) += kvm/
 obj-$(CONFIG_TCG) += tcg/
@@ -28,7 +28,13 @@
 #include "hw/boards.h"
 #include "sysemu/arch_init.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/kvm.h"
+#include "sysemu/qtest.h"
+#include "hw/xen/xen.h"
 #include "qom/object.h"
+#include "qemu/error-report.h"
+#include "qemu/option.h"
+#include "qapi/error.h"

 static const TypeInfo accel_type = {
    .name = TYPE_ACCEL,
@@ -38,7 +44,7 @@ static const TypeInfo accel_type = {
 };

 /* Lookup AccelClass from opt_name. Returns NULL if not found */
-AccelClass *accel_find(const char *opt_name)
+static AccelClass *accel_find(const char *opt_name)
 {
    char *class_name = g_strdup_printf(ACCEL_CLASS_NAME("%s"), opt_name);
    AccelClass *ac = ACCEL_CLASS(object_class_by_name(class_name));
@@ -46,9 +52,11 @@ AccelClass *accel_find(const char *opt_name)
    return ac;
 }

-int accel_init_machine(AccelState *accel, MachineState *ms)
+static int accel_init_machine(AccelClass *acc, MachineState *ms)
 {
-    AccelClass *acc = ACCEL_GET_CLASS(accel);
+    ObjectClass *oc = OBJECT_CLASS(acc);
+    const char *cname = object_class_get_name(oc);
+    AccelState *accel = ACCEL(object_new(cname));
    int ret;
    ms->accelerator = accel;
    *(acc->allowed) = true;
@@ -63,9 +71,63 @@ int accel_init_machine(AccelState *accel, MachineState *ms)
    return ret;
 }

-AccelState *current_accel(void)
+void configure_accelerator(MachineState *ms, const char *progname)
 {
-    return current_machine->accelerator;
+    const char *accel;
+    char **accel_list, **tmp;
+    int ret;
+    bool accel_initialised = false;
+    bool init_failed = false;
+    AccelClass *acc = NULL;
+
+    accel = qemu_opt_get(qemu_get_machine_opts(), "accel");
+    if (accel == NULL) {
+        /* Select the default accelerator */
+        int pnlen = strlen(progname);
+        if (pnlen >= 3 && g_str_equal(&progname[pnlen - 3], "kvm")) {
+            /* If the program name ends with "kvm", we prefer KVM */
+            accel = "kvm:tcg";
+        } else {
+#if defined(CONFIG_TCG)
+            accel = "tcg";
+#elif defined(CONFIG_KVM)
+            accel = "kvm";
+#else
+            error_report("No accelerator selected and"
+                         " no default accelerator available");
+            exit(1);
+#endif
+        }
+    }
+
+    accel_list = g_strsplit(accel, ":", 0);
+
+    for (tmp = accel_list; !accel_initialised && tmp && *tmp; tmp++) {
+        acc = accel_find(*tmp);
+        if (!acc) {
+            continue;
+        }
+        ret = accel_init_machine(acc, ms);
+        if (ret < 0) {
+            init_failed = true;
+            error_report("failed to initialize %s: %s",
+                         acc->name, strerror(-ret));
+        } else {
+            accel_initialised = true;
+        }
+    }
+    g_strfreev(accel_list);
+
+    if (!accel_initialised) {
+        if (!init_failed) {
+            error_report("-machine accel=%s: No accelerator found", accel);
+        }
+        exit(1);
+    }
+
+    if (init_failed) {
+        error_report("Back to %s accelerator", acc->name);
+    }
 }

 void accel_setup_post(MachineState *ms)
@@ -23,27 +23,22 @@
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
 #include "qapi/error.h"
+#include "hw/hw.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/msix.h"
 #include "hw/s390x/adapter.h"
 #include "exec/gdbstub.h"
 #include "sysemu/kvm_int.h"
-#include "sysemu/runstate.h"
 #include "sysemu/cpus.h"
-#include "sysemu/sysemu.h"
 #include "qemu/bswap.h"
 #include "exec/memory.h"
 #include "exec/ram_addr.h"
 #include "exec/address-spaces.h"
 #include "qemu/event_notifier.h"
-#include "qemu/main-loop.h"
 #include "trace.h"
 #include "hw/irq.h"
 #include "sysemu/sev.h"
 #include "sysemu/balloon.h"
-#include "qapi/visitor.h"
-#include "qapi/qapi-types-common.h"
-#include "qapi/qapi-visit-common.h"

 #include "hw/boards.h"

@@ -55,7 +50,7 @@
 /* KVM uses PAGE_SIZE in its definition of KVM_COALESCED_MMIO_MAX. We
 * need to use the real host PAGE_SIZE, as that's what KVM will use.
 */
-#define PAGE_SIZE qemu_real_host_page_size
+#define PAGE_SIZE getpagesize()

 //#define DEBUG_KVM

@@ -95,10 +90,6 @@ struct KVMState
    int max_nested_state_len;
    int many_ioeventfds;
    int intx_set_mask;
-    int kvm_shadow_mem;
-    bool kernel_irqchip_allowed;
-    bool kernel_irqchip_required;
-    OnOffAuto kernel_irqchip_split;
    bool sync_mmu;
    bool manual_dirty_log_protect;
    /* The man page (and posix) say ioctl numbers are signed int, but
@@ -147,7 +138,6 @@ bool kvm_direct_msi_allowed;
 bool kvm_ioeventfd_any_length_allowed;
 bool kvm_msi_use_devid;
 static bool kvm_immediate_exit;
-static hwaddr kvm_max_slot_size = ~0;

 static const KVMCapabilityInfo kvm_required_capabilites[] = {
    KVM_CAP_INFO(USER_MEMORY),
@@ -156,15 +146,12 @@ static const KVMCapabilityInfo kvm_required_capabilites[] = {
    KVM_CAP_LAST_INFO
 };

-static NotifierList kvm_irqchip_change_notifiers =
-    NOTIFIER_LIST_INITIALIZER(kvm_irqchip_change_notifiers);
-
 #define kvm_slots_lock(kml)      qemu_mutex_lock(&(kml)->slots_lock)
 #define kvm_slots_unlock(kml)    qemu_mutex_unlock(&(kml)->slots_lock)

 int kvm_get_max_memslots(void)
 {
-    KVMState *s = KVM_STATE(current_accel());
+    KVMState *s = KVM_STATE(current_machine->accelerator);

    return s->nr_slots;
 }
@@ -308,23 +295,13 @@ static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, boo
        /* Set the slot size to 0 before setting the slot to the desired
         * value. This is needed based on KVM commit 75d61fbc. */
        mem.memory_size = 0;
-        ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
-        if (ret < 0) {
-            goto err;
-        }
+        kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
    }
    mem.memory_size = slot->memory_size;
    ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
    slot->old_flags = mem.flags;
-err:
    trace_kvm_set_user_memory(mem.slot, mem.flags, mem.guest_phys_addr,
                              mem.memory_size, mem.userspace_addr, ret);
-    if (ret < 0) {
-        error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d,"
-                     " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s",
-                     __func__, mem.slot, slot->start_addr,
-                     (uint64_t)mem.memory_size, strerror(errno));
-    }
    return ret;
 }

@@ -458,7 +435,7 @@ static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem,
 static int kvm_section_update_flags(KVMMemoryListener *kml,
                                    MemoryRegionSection *section)
 {
-    hwaddr start_addr, size, slot_size;
+    hwaddr start_addr, size;
    KVMSlot *mem;
    int ret = 0;

@@ -469,19 +446,14 @@ static int kvm_section_update_flags(KVMMemoryListener *kml,

    kvm_slots_lock(kml);

-    while (size && !ret) {
-        slot_size = MIN(kvm_max_slot_size, size);
-        mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
-        if (!mem) {
-            /* We don't have a slot if we want to trap every access. */
-            goto out;
-        }
-
-        ret = kvm_slot_update_flags(kml, mem, section->mr);
-        start_addr += slot_size;
-        size -= slot_size;
+    mem = kvm_lookup_matching_slot(kml, start_addr, size);
+    if (!mem) {
+        /* We don't have a slot if we want to trap every access. */
+        goto out;
    }

+    ret = kvm_slot_update_flags(kml, mem, section->mr);
+
 out:
    kvm_slots_unlock(kml);
    return ret;
@@ -527,7 +499,7 @@ static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section,
 {
    ram_addr_t start = section->offset_within_region +
                       memory_region_get_ram_addr(section->mr);
-    ram_addr_t pages = int128_get64(section->size) / qemu_real_host_page_size;
+    ram_addr_t pages = int128_get64(section->size) / getpagesize();

    cpu_physical_memory_set_dirty_lebitmap(bitmap, start, pages);
    return 0;
@@ -535,27 +507,6 @@ static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section,

 #define ALIGN(x, y)  (((x)+(y)-1) & ~((y)-1))

-/* Allocate the dirty bitmap for a slot  */
-static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem)
-{
-    /*
-     * XXX bad kernel interface alert
-     * For dirty bitmap, kernel allocates array of size aligned to
-     * bits-per-long.  But for case when the kernel is 64bits and
-     * the userspace is 32bits, userspace can't align to the same
-     * bits-per-long, since sizeof(long) is different between kernel
-     * and user space.  This way, userspace will provide buffer which
-     * may be 4 bytes less than the kernel will use, resulting in
-     * userspace memory corruption (which is not detectable by valgrind
-     * too, in most cases).
-     * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
-     * a hope that sizeof(long) won't become >8 any time soon.
-     */
-    hwaddr bitmap_size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
-                                        /*HOST_LONG_BITS*/ 64) / 8;
-    mem->dirty_bmap = g_malloc0(bitmap_size);
-}
-
 /**
 * kvm_physical_sync_dirty_bitmap - Sync dirty bitmap from kernel space
 *
@@ -574,23 +525,33 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
    struct kvm_dirty_log d = {};
    KVMSlot *mem;
    hwaddr start_addr, size;
-    hwaddr slot_size, slot_offset = 0;
    int ret = 0;

    size = kvm_align_section(section, &start_addr);
-    while (size) {
-        MemoryRegionSection subsection = *section;
-
-        slot_size = MIN(kvm_max_slot_size, size);
-        mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
+    if (size) {
+        mem = kvm_lookup_matching_slot(kml, start_addr, size);
        if (!mem) {
            /* We don't have a slot if we want to trap every access. */
            goto out;
        }

+        /* XXX bad kernel interface alert
+         * For dirty bitmap, kernel allocates array of size aligned to
+         * bits-per-long.  But for case when the kernel is 64bits and
+         * the userspace is 32bits, userspace can't align to the same
+         * bits-per-long, since sizeof(long) is different between kernel
+         * and user space.  This way, userspace will provide buffer which
+         * may be 4 bytes less than the kernel will use, resulting in
+         * userspace memory corruption (which is not detectable by valgrind
+         * too, in most cases).
+         * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
+         * a hope that sizeof(long) won't become >8 any time soon.
+         */
+        size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
+                     /*HOST_LONG_BITS*/ 64) / 8;
        if (!mem->dirty_bmap) {
            /* Allocate on the first log_sync, once and for all */
-            kvm_memslot_init_dirty_bitmap(mem);
+            mem->dirty_bmap = g_malloc0(size);
        }

        d.dirty_bitmap = mem->dirty_bmap;
@@ -601,13 +562,7 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
            goto out;
        }

-        subsection.offset_within_region += slot_offset;
-        subsection.size = int128_make64(slot_size);
-        kvm_get_dirty_pages_log_range(&subsection, d.dirty_bitmap);
-
-        slot_offset += slot_size;
-        start_addr += slot_size;
-        size -= slot_size;
+        kvm_get_dirty_pages_log_range(section, d.dirty_bitmap);
    }
 out:
    return ret;
@@ -618,22 +573,63 @@ out:
 #define KVM_CLEAR_LOG_ALIGN  (qemu_real_host_page_size << KVM_CLEAR_LOG_SHIFT)
 #define KVM_CLEAR_LOG_MASK   (-KVM_CLEAR_LOG_ALIGN)

-static int kvm_log_clear_one_slot(KVMSlot *mem, int as_id, uint64_t start,
-                                  uint64_t size)
+/**
+ * kvm_physical_log_clear - Clear the kernel's dirty bitmap for range
+ *
+ * NOTE: this will be a no-op if we haven't enabled manual dirty log
+ * protection in the host kernel because in that case this operation
+ * will be done within log_sync().
+ *
+ * @kml:     the kvm memory listener
+ * @section: the memory range to clear dirty bitmap
+ */
+static int kvm_physical_log_clear(KVMMemoryListener *kml,
+                                  MemoryRegionSection *section)
 {
    KVMState *s = kvm_state;
-    uint64_t end, bmap_start, start_delta, bmap_npages;
    struct kvm_clear_dirty_log d;
+    uint64_t start, end, bmap_start, start_delta, bmap_npages, size;
    unsigned long *bmap_clear = NULL, psize = qemu_real_host_page_size;
-    int ret;
+    KVMSlot *mem = NULL;
+    int ret, i;
+
+    if (!s->manual_dirty_log_protect) {
+        /* No need to do explicit clear */
+        return 0;
+    }
+
+    start = section->offset_within_address_space;
+    size = int128_get64(section->size);
+
+    if (!size) {
+        /* Nothing more we can do... */
+        return 0;
+    }
+
+    kvm_slots_lock(kml);
+
+    /* Find any possible slot that covers the section */
+    for (i = 0; i < s->nr_slots; i++) {
+        mem = &kml->slots[i];
+        if (mem->start_addr <= start &&
+            start + size <= mem->start_addr + mem->memory_size) {
+            break;
+        }
+    }
+
+    /*
+     * We should always find one memslot until this point, otherwise
+     * there could be something wrong from the upper layer
+     */
+    assert(mem && i != s->nr_slots);

    /*
     * We need to extend either the start or the size or both to
     * satisfy the KVM interface requirement.  Firstly, do the start
     * page alignment on 64 host pages
     */
-    bmap_start = start & KVM_CLEAR_LOG_MASK;
-    start_delta = start - bmap_start;
+    bmap_start = (start - mem->start_addr) & KVM_CLEAR_LOG_MASK;
+    start_delta = start - mem->start_addr - bmap_start;
    bmap_start /= psize;

    /*
@@ -696,7 +692,7 @@ static int kvm_log_clear_one_slot(KVMSlot *mem, int as_id, uint64_t start,
    /* It should never overflow.  If it happens, say something */
    assert(bmap_npages <= UINT32_MAX);
    d.num_pages = bmap_npages;
-    d.slot = mem->slot | (as_id << 16);
+    d.slot = mem->slot | (kml->as_id << 16);

    if (kvm_vm_ioctl(s, KVM_CLEAR_DIRTY_LOG, &d) == -1) {
        ret = -errno;
@@ -719,66 +715,6 @@ static int kvm_log_clear_one_slot(KVMSlot *mem, int as_id, uint64_t start,
                 size / psize);
    /* This handles the NULL case well */
    g_free(bmap_clear);
-    return ret;
-}
-
-
-/**
- * kvm_physical_log_clear - Clear the kernel's dirty bitmap for range
- *
- * NOTE: this will be a no-op if we haven't enabled manual dirty log
- * protection in the host kernel because in that case this operation
- * will be done within log_sync().
- *
- * @kml:     the kvm memory listener
- * @section: the memory range to clear dirty bitmap
- */
-static int kvm_physical_log_clear(KVMMemoryListener *kml,
-                                  MemoryRegionSection *section)
-{
-    KVMState *s = kvm_state;
-    uint64_t start, size, offset, count;
-    KVMSlot *mem;
-    int ret = 0, i;
-
-    if (!s->manual_dirty_log_protect) {
-        /* No need to do explicit clear */
-        return ret;
-    }
-
-    start = section->offset_within_address_space;
-    size = int128_get64(section->size);
-
-    if (!size) {
-        /* Nothing more we can do... */
-        return ret;
-    }
-
-    kvm_slots_lock(kml);
-
-    for (i = 0; i < s->nr_slots; i++) {
-        mem = &kml->slots[i];
-        /* Discard slots that are empty or do not overlap the section */
-        if (!mem->memory_size ||
-            mem->start_addr > start + size - 1 ||
-            start > mem->start_addr + mem->memory_size - 1) {
-            continue;
-        }
-
-        if (start >= mem->start_addr) {
-            /* The slot starts before section or is aligned to it.  */
-            offset = start - mem->start_addr;
-            count = MIN(mem->memory_size - offset, size);
-        } else {
-            /* The slot starts after section.  */
-            offset = 0;
-            count = MIN(mem->memory_size, size - (mem->start_addr - start));
-        }
-        ret = kvm_log_clear_one_slot(mem, kml->as_id, offset, count);
-        if (ret < 0) {
-            break;
-        }
-    }

    kvm_slots_unlock(kml);

@@ -1015,14 +951,6 @@ kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
    return NULL;
 }

-void kvm_set_max_memslot_size(hwaddr max_slot_size)
-{
-    g_assert(
-        ROUND_UP(max_slot_size, qemu_real_host_page_size) == max_slot_size
-    );
-    kvm_max_slot_size = max_slot_size;
-}
-
 static void kvm_set_phys_mem(KVMMemoryListener *kml,
                             MemoryRegionSection *section, bool add)
 {
@@ -1030,7 +958,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
    int err;
    MemoryRegion *mr = section->mr;
    bool writeable = !mr->readonly && !mr->rom_device;
-    hwaddr start_addr, size, slot_size;
+    hwaddr start_addr, size;
    void *ram;

    if (!memory_region_is_ram(mr)) {
@@ -1055,59 +983,41 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
    kvm_slots_lock(kml);

    if (!add) {
-        do {
-            slot_size = MIN(kvm_max_slot_size, size);
-            mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
-            if (!mem) {
-                goto out;
-            }
-            if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
-                kvm_physical_sync_dirty_bitmap(kml, section);
-            }
+        mem = kvm_lookup_matching_slot(kml, start_addr, size);
+        if (!mem) {
+            goto out;
+        }
+        if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+            kvm_physical_sync_dirty_bitmap(kml, section);
+        }

-            /* unregister the slot */
-            g_free(mem->dirty_bmap);
-            mem->dirty_bmap = NULL;
-            mem->memory_size = 0;
-            mem->flags = 0;
-            err = kvm_set_user_memory_region(kml, mem, false);
-            if (err) {
-                fprintf(stderr, "%s: error unregistering slot: %s\n",
-                        __func__, strerror(-err));
-                abort();
-            }
-            start_addr += slot_size;
-            size -= slot_size;
-        } while (size);
+        /* unregister the slot */
+        g_free(mem->dirty_bmap);
+        mem->dirty_bmap = NULL;
+        mem->memory_size = 0;
+        mem->flags = 0;
+        err = kvm_set_user_memory_region(kml, mem, false);
+        if (err) {
+            fprintf(stderr, "%s: error unregistering slot: %s\n",
+                    __func__, strerror(-err));
+            abort();
+        }
        goto out;
    }

    /* register the new slot */
-    do {
-        slot_size = MIN(kvm_max_slot_size, size);
-        mem = kvm_alloc_slot(kml);
-        mem->memory_size = slot_size;
-        mem->start_addr = start_addr;
-        mem->ram = ram;
-        mem->flags = kvm_mem_flags(mr);
+    mem = kvm_alloc_slot(kml);
+    mem->memory_size = size;
+    mem->start_addr = start_addr;
+    mem->ram = ram;
+    mem->flags = kvm_mem_flags(mr);

-        if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
-            /*
-             * Reallocate the bmap; it means it doesn't disappear in
-             * middle of a migrate.
-             */
-            kvm_memslot_init_dirty_bitmap(mem);
-        }
-        err = kvm_set_user_memory_region(kml, mem, true);
-        if (err) {
-            fprintf(stderr, "%s: error registering slot: %s\n", __func__,
-                    strerror(-err));
-            abort();
-        }
-        start_addr += slot_size;
-        ram += slot_size;
-        size -= slot_size;
-    } while (size);
+    err = kvm_set_user_memory_region(kml, mem, true);
+    if (err) {
+        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
+                strerror(-err));
+        abort();
+    }

 out:
    kvm_slots_unlock(kml);
@@ -1430,21 +1340,6 @@ void kvm_irqchip_release_virq(KVMState *s, int virq)
    trace_kvm_irqchip_release_virq(virq);
 }

-void kvm_irqchip_add_change_notifier(Notifier *n)
-{
-    notifier_list_add(&kvm_irqchip_change_notifiers, n);
-}
-
-void kvm_irqchip_remove_change_notifier(Notifier *n)
-{
-    notifier_remove(n);
-}
-
-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
@@ -1789,11 +1684,10 @@ void kvm_irqchip_set_qemuirq_gsi(KVMState *s, qemu_irq irq, int gsi)
    g_hash_table_insert(s->gsimap, irq, GINT_TO_POINTER(gsi));
 }

-static void kvm_irqchip_create(KVMState *s)
+static void kvm_irqchip_create(MachineState *machine, KVMState *s)
 {
    int ret;

-    assert(s->kernel_irqchip_split != ON_OFF_AUTO_AUTO);
    if (kvm_check_extension(s, KVM_CAP_IRQCHIP)) {
        ;
    } else if (kvm_check_extension(s, KVM_CAP_S390_IRQCHIP)) {
@@ -1808,9 +1702,9 @@ static void kvm_irqchip_create(KVMState *s)

    /* 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);
+    ret = kvm_arch_irqchip_create(machine, s);
    if (ret == 0) {
-        if (s->kernel_irqchip_split == ON_OFF_AUTO_ON) {
+        if (machine_kernel_irqchip_split(machine)) {
            perror("Split IRQ chip mode not supported.");
            exit(1);
        } else {
@@ -1858,7 +1752,7 @@ static int kvm_max_vcpu_id(KVMState *s)

 bool kvm_vcpu_id_is_valid(int vcpu_id)
 {
-    KVMState *s = KVM_STATE(current_accel());
+    KVMState *s = KVM_STATE(current_machine->accelerator);
    return vcpu_id >= 0 && vcpu_id < kvm_max_vcpu_id(s);
 }

@@ -1891,7 +1785,7 @@ static int kvm_init(MachineState *ms)
     * even with KVM.  TARGET_PAGE_SIZE is assumed to be the minimum
     * page size for the system though.
     */
-    assert(TARGET_PAGE_SIZE <= qemu_real_host_page_size);
+    assert(TARGET_PAGE_SIZE <= getpagesize());

    s->sigmask_len = 8;

@@ -2081,12 +1975,8 @@ static int kvm_init(MachineState *ms)
        goto err;
    }

-    if (s->kernel_irqchip_split == ON_OFF_AUTO_AUTO) {
-        s->kernel_irqchip_split = mc->default_kernel_irqchip_split ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
-    }
-
-    if (s->kernel_irqchip_allowed) {
-        kvm_irqchip_create(s);
+    if (machine_kernel_irqchip_allowed(ms)) {
+        kvm_irqchip_create(ms, s);
    }

    if (kvm_eventfds_allowed) {
@@ -2188,9 +2078,9 @@ void kvm_flush_coalesced_mmio_buffer(void)
            ent = &ring->coalesced_mmio[ring->first];

            if (ent->pio == 1) {
-                address_space_write(&address_space_io, ent->phys_addr,
-                                    MEMTXATTRS_UNSPECIFIED, ent->data,
-                                    ent->len);
+                address_space_rw(&address_space_io, ent->phys_addr,
+                                 MEMTXATTRS_UNSPECIFIED, ent->data,
+                                 ent->len, true);
            } else {
                cpu_physical_memory_write(ent->phys_addr, ent->data, ent->len);
            }
@@ -2967,7 +2857,6 @@ static bool kvm_accel_has_memory(MachineState *ms, AddressSpace *as,

    for (i = 0; i < kvm->nr_as; ++i) {
        if (kvm->as[i].as == as && kvm->as[i].ml) {
-            size = MIN(kvm_max_slot_size, size);
            return NULL != kvm_lookup_matching_slot(kvm->as[i].ml,
                                                    start_addr, size);
        }
@@ -2976,95 +2865,6 @@ static bool kvm_accel_has_memory(MachineState *ms, AddressSpace *as,
    return false;
 }

-static void kvm_get_kvm_shadow_mem(Object *obj, Visitor *v,
-                                   const char *name, void *opaque,
-                                   Error **errp)
-{
-    KVMState *s = KVM_STATE(obj);
-    int64_t value = s->kvm_shadow_mem;
-
-    visit_type_int(v, name, &value, errp);
-}
-
-static void kvm_set_kvm_shadow_mem(Object *obj, Visitor *v,
-                                   const char *name, void *opaque,
-                                   Error **errp)
-{
-    KVMState *s = KVM_STATE(obj);
-    Error *error = NULL;
-    int64_t value;
-
-    visit_type_int(v, name, &value, &error);
-    if (error) {
-        error_propagate(errp, error);
-        return;
-    }
-
-    s->kvm_shadow_mem = value;
-}
-
-static void kvm_set_kernel_irqchip(Object *obj, Visitor *v,
-                                   const char *name, void *opaque,
-                                   Error **errp)
-{
-    Error *err = NULL;
-    KVMState *s = KVM_STATE(obj);
-    OnOffSplit mode;
-
-    visit_type_OnOffSplit(v, name, &mode, &err);
-    if (err) {
-        error_propagate(errp, err);
-        return;
-    } else {
-        switch (mode) {
-        case ON_OFF_SPLIT_ON:
-            s->kernel_irqchip_allowed = true;
-            s->kernel_irqchip_required = true;
-            s->kernel_irqchip_split = ON_OFF_AUTO_OFF;
-            break;
-        case ON_OFF_SPLIT_OFF:
-            s->kernel_irqchip_allowed = false;
-            s->kernel_irqchip_required = false;
-            s->kernel_irqchip_split = ON_OFF_AUTO_OFF;
-            break;
-        case ON_OFF_SPLIT_SPLIT:
-            s->kernel_irqchip_allowed = true;
-            s->kernel_irqchip_required = true;
-            s->kernel_irqchip_split = ON_OFF_AUTO_ON;
-            break;
-        default:
-            /* The value was checked in visit_type_OnOffSplit() above. If
-             * we get here, then something is wrong in QEMU.
-             */
-            abort();
-        }
-    }
-}
-
-bool kvm_kernel_irqchip_allowed(void)
-{
-    return kvm_state->kernel_irqchip_allowed;
-}
-
-bool kvm_kernel_irqchip_required(void)
-{
-    return kvm_state->kernel_irqchip_required;
-}
-
-bool kvm_kernel_irqchip_split(void)
-{
-    return kvm_state->kernel_irqchip_split == ON_OFF_AUTO_ON;
-}
-
-static void kvm_accel_instance_init(Object *obj)
-{
-    KVMState *s = KVM_STATE(obj);
-
-    s->kvm_shadow_mem = -1;
-    s->kernel_irqchip_allowed = true;
-    s->kernel_irqchip_split = ON_OFF_AUTO_AUTO;
-}
-
 static void kvm_accel_class_init(ObjectClass *oc, void *data)
 {
    AccelClass *ac = ACCEL_CLASS(oc);
@@ -3072,24 +2872,11 @@ static void kvm_accel_class_init(ObjectClass *oc, void *data)
    ac->init_machine = kvm_init;
    ac->has_memory = kvm_accel_has_memory;
    ac->allowed = &kvm_allowed;
-
-    object_class_property_add(oc, "kernel-irqchip", "on|off|split",
-        NULL, kvm_set_kernel_irqchip,
-        NULL, NULL, &error_abort);
-    object_class_property_set_description(oc, "kernel-irqchip",
-        "Configure KVM in-kernel irqchip", &error_abort);
-
-    object_class_property_add(oc, "kvm-shadow-mem", "int",
-        kvm_get_kvm_shadow_mem, kvm_set_kvm_shadow_mem,
-        NULL, NULL, &error_abort);
-    object_class_property_set_description(oc, "kvm-shadow-mem",
-        "KVM shadow MMU size", &error_abort);
 }

 static const TypeInfo kvm_accel_type = {
    .name = TYPE_KVM_ACCEL,
    .parent = TYPE_ACCEL,
-    .instance_init = kvm_accel_instance_init,
    .class_init = kvm_accel_class_init,
    .instance_size = sizeof(KVMState),
 };
@@ -138,18 +138,6 @@ void kvm_irqchip_commit_routes(KVMState *s)
 {
 }

-void kvm_irqchip_add_change_notifier(Notifier *n)
-{
-}
-
-void kvm_irqchip_remove_change_notifier(Notifier *n)
-{
-}
-
-void kvm_irqchip_change_notify(void)
-{
-}
-
 int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
 {
    return -ENOSYS;
@@ -11,8 +11,10 @@
 */

 #include "qemu/osdep.h"
+#include "qemu-common.h"
 #include "cpu.h"
 #include "tcg/tcg.h"
+#include "exec/cpu-common.h"
 #include "exec/exec-all.h"

 void tb_flush(CPUState *cpu)
@@ -6,4 +6,3 @@ obj-y += translator.o

 obj-$(CONFIG_USER_ONLY) += user-exec.o
 obj-$(call lnot,$(CONFIG_SOFTMMU)) += user-exec-stub.o
-obj-$(CONFIG_PLUGIN) += plugin-gen.o
@@ -1,54 +0,0 @@
-/*
- * Common Atomic Helper Functions
- *
- * This file should be included before the various instantiations of
- * the atomic_template.h helpers.
- *
- * Copyright (c) 2019 Linaro
- * Written by Alex Bennée <alex.bennee@linaro.org>
- *
- * SPDX-License-Identifier: GPL-2.0-or-later
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-static inline
-void atomic_trace_rmw_pre(CPUArchState *env, target_ulong addr, uint16_t info)
-{
-    CPUState *cpu = env_cpu(env);
-
-    trace_guest_mem_before_exec(cpu, addr, info);
-    trace_guest_mem_before_exec(cpu, addr, info | TRACE_MEM_ST);
-}
-
-static inline void
-atomic_trace_rmw_post(CPUArchState *env, target_ulong addr, uint16_t info)
-{
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info);
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info | TRACE_MEM_ST);
-}
-
-static inline
-void atomic_trace_ld_pre(CPUArchState *env, target_ulong addr, uint16_t info)
-{
-    trace_guest_mem_before_exec(env_cpu(env), addr, info);
-}
-
-static inline
-void atomic_trace_ld_post(CPUArchState *env, target_ulong addr, uint16_t info)
-{
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info);
-}
-
-static inline
-void atomic_trace_st_pre(CPUArchState *env, target_ulong addr, uint16_t info)
-{
-    trace_guest_mem_before_exec(env_cpu(env), addr, info);
-}
-
-static inline
-void atomic_trace_st_post(CPUArchState *env, target_ulong addr, uint16_t info)
-{
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info);
-}
@@ -18,7 +18,6 @@
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */

-#include "qemu/plugin.h"
 #include "trace/mem.h"

 #if DATA_SIZE == 16
@@ -60,14 +59,37 @@
 # define ABI_TYPE  uint32_t
 #endif

+#define ATOMIC_TRACE_RMW do {                                           \
+        uint8_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false); \
+                                                                        \
+        trace_guest_mem_before_exec(env_cpu(env), addr, info);      \
+        trace_guest_mem_before_exec(env_cpu(env), addr,             \
+                                    info | TRACE_MEM_ST);               \
+    } while (0)
+
+#define ATOMIC_TRACE_LD do {                                            \
+        uint8_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false); \
+                                                                        \
+        trace_guest_mem_before_exec(env_cpu(env), addr, info);      \
+    } while (0)
+
+# define ATOMIC_TRACE_ST do {                                           \
+        uint8_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, true); \
+                                                                        \
+        trace_guest_mem_before_exec(env_cpu(env), addr, info);      \
+    } while (0)
+
 /* Define host-endian atomic operations.  Note that END is used within
   the ATOMIC_NAME macro, and redefined below.  */
 #if DATA_SIZE == 1
 # define END
+# define MEND _be /* either le or be would be fine */
 #elif defined(HOST_WORDS_BIGENDIAN)
 # define END  _be
+# define MEND _be
 #else
 # define END  _le
+# define MEND _le
 #endif

 ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
@@ -76,17 +98,14 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
    ATOMIC_MMU_DECLS;
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
    DATA_TYPE ret;
-    uint16_t info = trace_mem_build_info(SHIFT, false, 0, false,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_rmw_pre(env, addr, info);
+    ATOMIC_TRACE_RMW;
 #if DATA_SIZE == 16
    ret = atomic16_cmpxchg(haddr, cmpv, newv);
 #else
    ret = atomic_cmpxchg__nocheck(haddr, cmpv, newv);
 #endif
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_rmw_post(env, addr, info);
    return ret;
 }

@@ -96,13 +115,10 @@ ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS)
 {
    ATOMIC_MMU_DECLS;
    DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP;
-    uint16_t info = trace_mem_build_info(SHIFT, false, 0, false,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_ld_pre(env, addr, info);
+    ATOMIC_TRACE_LD;
    val = atomic16_read(haddr);
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_ld_post(env, addr, info);
    return val;
 }

@@ -111,13 +127,10 @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr,
 {
    ATOMIC_MMU_DECLS;
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    uint16_t info = trace_mem_build_info(SHIFT, false, 0, true,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_st_pre(env, addr, info);
+    ATOMIC_TRACE_ST;
    atomic16_set(haddr, val);
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_st_post(env, addr, info);
 }
 #endif
 #else
@@ -127,29 +140,24 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr,
    ATOMIC_MMU_DECLS;
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
    DATA_TYPE ret;
-    uint16_t info = trace_mem_build_info(SHIFT, false, 0, false,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_rmw_pre(env, addr, info);
+    ATOMIC_TRACE_RMW;
    ret = atomic_xchg__nocheck(haddr, val);
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_rmw_post(env, addr, info);
    return ret;
 }

 #define GEN_ATOMIC_HELPER(X)                                        \
 ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
-                        ABI_TYPE val EXTRA_ARGS)                    \
+                 ABI_TYPE val EXTRA_ARGS)                           \
 {                                                                   \
    ATOMIC_MMU_DECLS;                                               \
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                           \
    DATA_TYPE ret;                                                  \
-    uint16_t info = trace_mem_build_info(SHIFT, false, 0, false,    \
-                                         ATOMIC_MMU_IDX);           \
-    atomic_trace_rmw_pre(env, addr, info);                          \
+                                                                    \
+    ATOMIC_TRACE_RMW;                                               \
    ret = atomic_##X(haddr, val);                                   \
    ATOMIC_MMU_CLEANUP;                                             \
-    atomic_trace_rmw_post(env, addr, info);                         \
    return ret;                                                     \
 }

@@ -178,9 +186,8 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
    ATOMIC_MMU_DECLS;                                               \
    XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                          \
    XDATA_TYPE cmp, old, new, val = xval;                           \
-    uint16_t info = trace_mem_build_info(SHIFT, false, 0, false,    \
-                                         ATOMIC_MMU_IDX);           \
-    atomic_trace_rmw_pre(env, addr, info);                          \
+                                                                    \
+    ATOMIC_TRACE_RMW;                                               \
    smp_mb();                                                       \
    cmp = atomic_read__nocheck(haddr);                              \
    do {                                                            \
@@ -188,7 +195,6 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
        cmp = atomic_cmpxchg__nocheck(haddr, old, new);             \
    } while (cmp != old);                                           \
    ATOMIC_MMU_CLEANUP;                                             \
-    atomic_trace_rmw_post(env, addr, info);                         \
    return RET;                                                     \
 }

@@ -206,6 +212,7 @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)
 #endif /* DATA SIZE >= 16 */

 #undef END
+#undef MEND

 #if DATA_SIZE > 1

@@ -213,8 +220,10 @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)
   within the ATOMIC_NAME macro.  */
 #ifdef HOST_WORDS_BIGENDIAN
 # define END  _le
+# define MEND _le
 #else
 # define END  _be
+# define MEND _be
 #endif

 ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
@@ -223,17 +232,14 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
    ATOMIC_MMU_DECLS;
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
    DATA_TYPE ret;
-    uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_rmw_pre(env, addr, info);
+    ATOMIC_TRACE_RMW;
 #if DATA_SIZE == 16
    ret = atomic16_cmpxchg(haddr, BSWAP(cmpv), BSWAP(newv));
 #else
    ret = atomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv));
 #endif
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_rmw_post(env, addr, info);
    return BSWAP(ret);
 }

@@ -243,13 +249,10 @@ ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS)
 {
    ATOMIC_MMU_DECLS;
    DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP;
-    uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_ld_pre(env, addr, info);
+    ATOMIC_TRACE_LD;
    val = atomic16_read(haddr);
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_ld_post(env, addr, info);
    return BSWAP(val);
 }

@@ -258,15 +261,11 @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr,
 {
    ATOMIC_MMU_DECLS;
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, true,
-                                         ATOMIC_MMU_IDX);

-    val = BSWAP(val);
-    atomic_trace_st_pre(env, addr, info);
+    ATOMIC_TRACE_ST;
    val = BSWAP(val);
    atomic16_set(haddr, val);
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_st_post(env, addr, info);
 }
 #endif
 #else
@@ -276,29 +275,24 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr,
    ATOMIC_MMU_DECLS;
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
    ABI_TYPE ret;
-    uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false,
-                                         ATOMIC_MMU_IDX);

-    atomic_trace_rmw_pre(env, addr, info);
+    ATOMIC_TRACE_RMW;
    ret = atomic_xchg__nocheck(haddr, BSWAP(val));
    ATOMIC_MMU_CLEANUP;
-    atomic_trace_rmw_post(env, addr, info);
    return BSWAP(ret);
 }

 #define GEN_ATOMIC_HELPER(X)                                        \
 ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
-                        ABI_TYPE val EXTRA_ARGS)                    \
+                 ABI_TYPE val EXTRA_ARGS)                           \
 {                                                                   \
    ATOMIC_MMU_DECLS;                                               \
    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                           \
    DATA_TYPE ret;                                                  \
-    uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP,    \
-                                         false, ATOMIC_MMU_IDX);    \
-    atomic_trace_rmw_pre(env, addr, info);                          \
+                                                                    \
+    ATOMIC_TRACE_RMW;                                               \
    ret = atomic_##X(haddr, BSWAP(val));                            \
    ATOMIC_MMU_CLEANUP;                                             \
-    atomic_trace_rmw_post(env, addr, info);                         \
    return BSWAP(ret);                                              \
 }

@@ -325,9 +319,8 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
    ATOMIC_MMU_DECLS;                                               \
    XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                          \
    XDATA_TYPE ldo, ldn, old, new, val = xval;                      \
-    uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP,    \
-                                         false, ATOMIC_MMU_IDX);    \
-    atomic_trace_rmw_pre(env, addr, info);                          \
+                                                                    \
+    ATOMIC_TRACE_RMW;                                               \
    smp_mb();                                                       \
    ldn = atomic_read__nocheck(haddr);                              \
    do {                                                            \
@@ -335,7 +328,6 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
        ldn = atomic_cmpxchg__nocheck(haddr, ldo, BSWAP(new));      \
    } while (ldo != ldn);                                           \
    ATOMIC_MMU_CLEANUP;                                             \
-    atomic_trace_rmw_post(env, addr, info);                         \
    return RET;                                                     \
 }

@@ -360,8 +352,13 @@ GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new)
 #endif /* DATA_SIZE >= 16 */

 #undef END
+#undef MEND
 #endif /* DATA_SIZE > 1 */

+#undef ATOMIC_TRACE_ST
+#undef ATOMIC_TRACE_LD
+#undef ATOMIC_TRACE_RMW
+
 #undef BSWAP
 #undef ABI_TYPE
 #undef DATA_TYPE
@@ -23,7 +23,7 @@
 #include "trace.h"
 #include "disas/disas.h"
 #include "exec/exec-all.h"
-#include "tcg/tcg.h"
+#include "tcg.h"
 #include "qemu/atomic.h"
 #include "sysemu/qtest.h"
 #include "qemu/timer.h"
@@ -156,7 +156,7 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
 #if defined(DEBUG_DISAS)
    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
        && qemu_log_in_addr_range(itb->pc)) {
-        FILE *logfile = qemu_log_lock();
+        qemu_log_lock();
        int flags = 0;
        if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) {
            flags |= CPU_DUMP_FPU;
@@ -165,10 +165,11 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
        flags |= CPU_DUMP_CCOP;
 #endif
        log_cpu_state(cpu, flags);
-        qemu_log_unlock(logfile);
+        qemu_log_unlock();
    }
 #endif /* DEBUG_DISAS */

+    cpu->can_do_io = !use_icount;
    ret = tcg_qemu_tb_exec(env, tb_ptr);
    cpu->can_do_io = 1;
    last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
@@ -238,10 +239,10 @@ void cpu_exec_step_atomic(CPUState *cpu)
    uint32_t flags;
    uint32_t cflags = 1;
    uint32_t cf_mask = cflags & CF_HASH_MASK;
+    /* volatile because we modify it between setjmp and longjmp */
+    volatile bool in_exclusive_region = false;

    if (sigsetjmp(cpu->jmp_env, 0) == 0) {
-        start_exclusive();
-
        tb = tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask);
        if (tb == NULL) {
            mmap_lock();
@@ -249,8 +250,11 @@ void cpu_exec_step_atomic(CPUState *cpu)
            mmap_unlock();
        }

+        start_exclusive();
+
        /* Since we got here, we know that parallel_cpus must be true.  */
        parallel_cpus = false;
+        in_exclusive_region = true;
        cc->cpu_exec_enter(cpu);
        /* execute the generated code */
        trace_exec_tb(tb, pc);
@@ -268,18 +272,16 @@ void cpu_exec_step_atomic(CPUState *cpu)
            qemu_mutex_unlock_iothread();
        }
        assert_no_pages_locked();
-        qemu_plugin_disable_mem_helpers(cpu);
    }

-
-    /*
-     * As we start the exclusive region before codegen we must still
-     * be in the region if we longjump out of either the codegen or
-     * the execution.
-     */
-    g_assert(cpu_in_exclusive_context(cpu));
-    parallel_cpus = true;
-    end_exclusive();
+    if (in_exclusive_region) {
+        /* We might longjump out of either the codegen or the
+         * execution, so must make sure we only end the exclusive
+         * region if we started it.
+         */
+        parallel_cpus = true;
+        end_exclusive();
+    }
 }

 struct tb_desc {
@@ -703,8 +705,6 @@ int cpu_exec(CPUState *cpu)
        if (qemu_mutex_iothread_locked()) {
            qemu_mutex_unlock_iothread();
        }
-        qemu_plugin_disable_mem_helpers(cpu);
-
        assert_no_pages_locked();
    }

@@ -1,932 +0,0 @@
-/*
- * plugin-gen.c - TCG-related bits of plugin infrastructure
- *
- * Copyright (C) 2018, Emilio G. Cota <cota@braap.org>
- * License: GNU GPL, version 2 or later.
- *   See the COPYING file in the top-level directory.
- *
- * We support instrumentation at an instruction granularity. That is,
- * if a plugin wants to instrument the memory accesses performed by a
- * particular instruction, it can just do that instead of instrumenting
- * all memory accesses. Thus, in order to do this we first have to
- * translate a TB, so that plugins can decide what/where to instrument.
- *
- * Injecting the desired instrumentation could be done with a second
- * translation pass that combined the instrumentation requests, but that
- * would be ugly and inefficient since we would decode the guest code twice.
- * Instead, during TB translation we add "empty" instrumentation calls for all
- * possible instrumentation events, and then once we collect the instrumentation
- * requests from plugins, we either "fill in" those empty events or remove them
- * if they have no requests.
- *
- * When "filling in" an event we first copy the empty callback's TCG ops. This
- * might seem unnecessary, but it is done to support an arbitrary number
- * of callbacks per event. Take for example a regular instruction callback.
- * We first generate a callback to an empty helper function. Then, if two
- * plugins register one callback each for this instruction, we make two copies
- * of the TCG ops generated for the empty callback, substituting the function
- * pointer that points to the empty helper function with the plugins' desired
- * callback functions. After that we remove the empty callback's ops.
- *
- * Note that the location in TCGOp.args[] of the pointer to a helper function
- * varies across different guest and host architectures. Instead of duplicating
- * the logic that figures this out, we rely on the fact that the empty
- * callbacks point to empty functions that are unique pointers in the program.
- * Thus, to find the right location we just have to look for a match in
- * TCGOp.args[]. This is the main reason why we first copy an empty callback's
- * TCG ops and then fill them in; regardless of whether we have one or many
- * callbacks for that event, the logic to add all of them is the same.
- *
- * When generating more than one callback per event, we make a small
- * optimization to avoid generating redundant operations. For instance, for the
- * second and all subsequent callbacks of an event, we do not need to reload the
- * 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-op.h"
-#include "trace/mem.h"
-#include "exec/exec-all.h"
-#include "exec/plugin-gen.h"
-#include "exec/translator.h"
-
-#ifdef CONFIG_SOFTMMU
-# define CONFIG_SOFTMMU_GATE 1
-#else
-# define CONFIG_SOFTMMU_GATE 0
-#endif
-
-/*
- * plugin_cb_start TCG op args[]:
- * 0: enum plugin_gen_from
- * 1: enum plugin_gen_cb
- * 2: set to 1 for mem callback that is a write, 0 otherwise.
- */
-
-enum plugin_gen_from {
-    PLUGIN_GEN_FROM_TB,
-    PLUGIN_GEN_FROM_INSN,
-    PLUGIN_GEN_FROM_MEM,
-    PLUGIN_GEN_AFTER_INSN,
-    PLUGIN_GEN_N_FROMS,
-};
-
-enum plugin_gen_cb {
-    PLUGIN_GEN_CB_UDATA,
-    PLUGIN_GEN_CB_INLINE,
-    PLUGIN_GEN_CB_MEM,
-    PLUGIN_GEN_ENABLE_MEM_HELPER,
-    PLUGIN_GEN_DISABLE_MEM_HELPER,
-    PLUGIN_GEN_N_CBS,
-};
-
-/*
- * These helpers are stubs that get dynamically switched out for calls
- * direct to the plugin if they are subscribed to.
- */
-void HELPER(plugin_vcpu_udata_cb)(uint32_t cpu_index, void *udata)
-{ }
-
-void HELPER(plugin_vcpu_mem_cb)(unsigned int vcpu_index,
-                                qemu_plugin_meminfo_t info, uint64_t vaddr,
-                                void *userdata)
-{ }
-
-static void do_gen_mem_cb(TCGv vaddr, uint32_t info)
-{
-    TCGv_i32 cpu_index = tcg_temp_new_i32();
-    TCGv_i32 meminfo = tcg_const_i32(info);
-    TCGv_i64 vaddr64 = tcg_temp_new_i64();
-    TCGv_ptr udata = tcg_const_ptr(NULL);
-
-    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_new_i32();
-    TCGv_ptr udata = tcg_const_ptr(NULL); /* will be overwritten later */
-
-    tcg_gen_ld_i32(cpu_index, cpu_env,
-                   -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
-    gen_helper_plugin_vcpu_udata_cb(cpu_index, udata);
-
-    tcg_temp_free_ptr(udata);
-    tcg_temp_free_i32(cpu_index);
-}
-
-/*
- * For now we only support addi_i64.
- * When we support more ops, we can generate one empty inline cb for each.
- */
-static void gen_empty_inline_cb(void)
-{
-    TCGv_i64 val = tcg_temp_new_i64();
-    TCGv_ptr ptr = tcg_const_ptr(NULL); /* overwritten later */
-
-    tcg_gen_ld_i64(val, ptr, 0);
-    /* pass an immediate != 0 so that it doesn't get optimized away */
-    tcg_gen_addi_i64(val, val, 0xdeadface);
-    tcg_gen_st_i64(val, ptr, 0);
-    tcg_temp_free_ptr(ptr);
-    tcg_temp_free_i64(val);
-}
-
-static void gen_empty_mem_cb(TCGv addr, uint32_t info)
-{
-    do_gen_mem_cb(addr, info);
-}
-
-/*
- * Share the same function for enable/disable. When enabling, the NULL
- * pointer will be overwritten later.
- */
-static void gen_empty_mem_helper(void)
-{
-    TCGv_ptr ptr;
-
-    ptr = tcg_const_ptr(NULL);
-    tcg_gen_st_ptr(ptr, cpu_env, offsetof(CPUState, plugin_mem_cbs) -
-                                 offsetof(ArchCPU, env));
-    tcg_temp_free_ptr(ptr);
-}
-
-static inline
-void gen_plugin_cb_start(enum plugin_gen_from from,
-                         enum plugin_gen_cb type, unsigned wr)
-{
-    TCGOp *op;
-
-    tcg_gen_plugin_cb_start(from, type, wr);
-    op = tcg_last_op();
-    QSIMPLEQ_INSERT_TAIL(&tcg_ctx->plugin_ops, op, plugin_link);
-}
-
-static void gen_wrapped(enum plugin_gen_from from,
-                        enum plugin_gen_cb type, void (*func)(void))
-{
-    gen_plugin_cb_start(from, type, 0);
-    func();
-    tcg_gen_plugin_cb_end();
-}
-
-static inline void plugin_gen_empty_callback(enum plugin_gen_from from)
-{
-    switch (from) {
-    case PLUGIN_GEN_AFTER_INSN:
-        gen_wrapped(from, PLUGIN_GEN_DISABLE_MEM_HELPER,
-                    gen_empty_mem_helper);
-        break;
-    case PLUGIN_GEN_FROM_INSN:
-        /*
-         * Note: plugin_gen_inject() relies on ENABLE_MEM_HELPER being
-         * the first callback of an instruction
-         */
-        gen_wrapped(from, PLUGIN_GEN_ENABLE_MEM_HELPER,
-                    gen_empty_mem_helper);
-        /* fall through */
-    case PLUGIN_GEN_FROM_TB:
-        gen_wrapped(from, PLUGIN_GEN_CB_UDATA, gen_empty_udata_cb);
-        gen_wrapped(from, PLUGIN_GEN_CB_INLINE, gen_empty_inline_cb);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
-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)
-{
-    int wr = !!(info & TRACE_MEM_ST);
-
-    gen_plugin_cb_start(PLUGIN_GEN_FROM_MEM, type, wr);
-    if (is_mem) {
-        f->mem_fn(addr, info);
-    } else {
-        f->inline_fn();
-    }
-    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)
-{
-    while (op) {
-        if (op->opc == opc) {
-            return op;
-        }
-        op = QTAILQ_NEXT(op, link);
-    }
-    return NULL;
-}
-
-static TCGOp *rm_ops_range(TCGOp *begin, TCGOp *end)
-{
-    TCGOp *ret = QTAILQ_NEXT(end, link);
-
-    QTAILQ_REMOVE_SEVERAL(&tcg_ctx->ops, begin, end, link);
-    return ret;
-}
-
-/* remove all ops until (and including) plugin_cb_end */
-static TCGOp *rm_ops(TCGOp *op)
-{
-    TCGOp *end_op = find_op(op, INDEX_op_plugin_cb_end);
-
-    tcg_debug_assert(end_op);
-    return rm_ops_range(op, end_op);
-}
-
-static TCGOp *copy_op_nocheck(TCGOp **begin_op, TCGOp *op)
-{
-    *begin_op = QTAILQ_NEXT(*begin_op, link);
-    tcg_debug_assert(*begin_op);
-    op = tcg_op_insert_after(tcg_ctx, op, (*begin_op)->opc);
-    memcpy(op->args, (*begin_op)->args, sizeof(op->args));
-    return op;
-}
-
-static TCGOp *copy_op(TCGOp **begin_op, TCGOp *op, TCGOpcode opc)
-{
-    op = copy_op_nocheck(begin_op, op);
-    tcg_debug_assert((*begin_op)->opc == 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);
-        /* movi_i32 */
-        op = copy_op(begin_op, op, INDEX_op_movi_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_movi_i64(TCGOp **begin_op, TCGOp *op, uint64_t v)
-{
-    if (TCG_TARGET_REG_BITS == 32) {
-        /* 2x movi_i32 */
-        op = copy_op(begin_op, op, INDEX_op_movi_i32);
-        op->args[1] = v;
-
-        op = copy_op(begin_op, op, INDEX_op_movi_i32);
-        op->args[1] = v >> 32;
-    } else {
-        /* movi_i64 */
-        op = copy_op(begin_op, op, INDEX_op_movi_i64);
-        op->args[1] = v;
-    }
-    return op;
-}
-
-static TCGOp *copy_const_ptr(TCGOp **begin_op, TCGOp *op, void *ptr)
-{
-    if (UINTPTR_MAX == UINT32_MAX) {
-        /* movi_i32 */
-        op = copy_op(begin_op, op, INDEX_op_movi_i32);
-        op->args[1] = (uintptr_t)ptr;
-    } else {
-        /* movi_i64 */
-        op = copy_movi_i64(begin_op, op, (uint64_t)(uintptr_t)ptr);
-    }
-    return op;
-}
-
-static TCGOp *copy_const_i64(TCGOp **begin_op, TCGOp *op, uint64_t v)
-{
-    return copy_movi_i64(begin_op, op, v);
-}
-
-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) {
-        /* 2x ld_i32 */
-        op = copy_op(begin_op, op, INDEX_op_ld_i32);
-        op = copy_op(begin_op, op, INDEX_op_ld_i32);
-    } else {
-        /* ld_i64 */
-        op = copy_op(begin_op, op, INDEX_op_ld_i64);
-    }
-    return op;
-}
-
-static TCGOp *copy_st_i64(TCGOp **begin_op, TCGOp *op)
-{
-    if (TCG_TARGET_REG_BITS == 32) {
-        /* 2x st_i32 */
-        op = copy_op(begin_op, op, INDEX_op_st_i32);
-        op = copy_op(begin_op, op, INDEX_op_st_i32);
-    } else {
-        /* st_i64 */
-        op = copy_op(begin_op, op, INDEX_op_st_i64);
-    }
-    return op;
-}
-
-static TCGOp *copy_add_i64(TCGOp **begin_op, TCGOp *op)
-{
-    if (TCG_TARGET_REG_BITS == 32) {
-        /* all 32-bit backends must implement add2_i32 */
-        g_assert(TCG_TARGET_HAS_add2_i32);
-        op = copy_op(begin_op, op, INDEX_op_add2_i32);
-    } else {
-        op = copy_op(begin_op, op, INDEX_op_add_i64);
-    }
-    return op;
-}
-
-static TCGOp *copy_st_ptr(TCGOp **begin_op, TCGOp *op)
-{
-    if (UINTPTR_MAX == UINT32_MAX) {
-        /* st_i32 */
-        op = copy_op(begin_op, op, INDEX_op_st_i32);
-    } else {
-        /* st_i64 */
-        op = copy_st_i64(begin_op, op);
-    }
-    return op;
-}
-
-static TCGOp *copy_call(TCGOp **begin_op, TCGOp *op, void *empty_func,
-                        void *func, unsigned tcg_flags, int *cb_idx)
-{
-    /* copy all ops until the call */
-    do {
-        op = copy_op_nocheck(begin_op, op);
-    } while (op->opc != INDEX_op_call);
-
-    /* fill in the op call */
-    op->param1 = (*begin_op)->param1;
-    op->param2 = (*begin_op)->param2;
-    tcg_debug_assert(op->life == 0);
-    if (*cb_idx == -1) {
-        int i;
-
-        /*
-         * Instead of working out the position of the callback in args[], just
-         * look for @empty_func, since it should be a unique pointer.
-         */
-        for (i = 0; i < MAX_OPC_PARAM_ARGS; i++) {
-            if ((uintptr_t)(*begin_op)->args[i] == (uintptr_t)empty_func) {
-                *cb_idx = i;
-                break;
-            }
-        }
-        tcg_debug_assert(i < MAX_OPC_PARAM_ARGS);
-    }
-    op->args[*cb_idx] = (uintptr_t)func;
-    op->args[*cb_idx + 1] = tcg_flags;
-
-    return op;
-}
-
-static TCGOp *append_udata_cb(const struct qemu_plugin_dyn_cb *cb,
-                              TCGOp *begin_op, TCGOp *op, int *cb_idx)
-{
-    /* const_ptr */
-    op = copy_const_ptr(&begin_op, op, cb->userp);
-
-    /* copy the ld_i32, but note that we only have to copy it once */
-    begin_op = QTAILQ_NEXT(begin_op, link);
-    tcg_debug_assert(begin_op && begin_op->opc == INDEX_op_ld_i32);
-    if (*cb_idx == -1) {
-        op = tcg_op_insert_after(tcg_ctx, op, INDEX_op_ld_i32);
-        memcpy(op->args, begin_op->args, sizeof(op->args));
-    }
-
-    /* call */
-    op = copy_call(&begin_op, op, HELPER(plugin_vcpu_udata_cb),
-                   cb->f.vcpu_udata, cb->tcg_flags, cb_idx);
-
-    return op;
-}
-
-static TCGOp *append_inline_cb(const struct qemu_plugin_dyn_cb *cb,
-                               TCGOp *begin_op, TCGOp *op,
-                               int *unused)
-{
-    /* const_ptr */
-    op = copy_const_ptr(&begin_op, op, cb->userp);
-
-    /* ld_i64 */
-    op = copy_ld_i64(&begin_op, op);
-
-    /* const_i64 */
-    op = copy_const_i64(&begin_op, op, cb->inline_insn.imm);
-
-    /* add_i64 */
-    op = copy_add_i64(&begin_op, op);
-
-    /* st_i64 */
-    op = copy_st_i64(&begin_op, op);
-
-    return op;
-}
-
-static TCGOp *append_mem_cb(const struct qemu_plugin_dyn_cb *cb,
-                            TCGOp *begin_op, TCGOp *op, int *cb_idx)
-{
-    enum plugin_gen_cb type = begin_op->args[1];
-
-    tcg_debug_assert(type == PLUGIN_GEN_CB_MEM);
-
-    /* const_i32 == movi_i32 ("info", so it remains as is) */
-    op = copy_op(&begin_op, op, INDEX_op_movi_i32);
-
-    /* const_ptr */
-    op = copy_const_ptr(&begin_op, op, cb->userp);
-
-    /* copy the ld_i32, but note that we only have to copy it once */
-    begin_op = QTAILQ_NEXT(begin_op, link);
-    tcg_debug_assert(begin_op && begin_op->opc == INDEX_op_ld_i32);
-    if (*cb_idx == -1) {
-        op = tcg_op_insert_after(tcg_ctx, op, INDEX_op_ld_i32);
-        memcpy(op->args, begin_op->args, sizeof(op->args));
-    }
-
-    /* extu_tl_i64 */
-    op = copy_extu_tl_i64(&begin_op, op);
-
-    if (type == PLUGIN_GEN_CB_MEM) {
-        /* call */
-        op = copy_call(&begin_op, op, HELPER(plugin_vcpu_mem_cb),
-                       cb->f.vcpu_udata, cb->tcg_flags, cb_idx);
-    }
-
-    return op;
-}
-
-typedef TCGOp *(*inject_fn)(const struct qemu_plugin_dyn_cb *cb,
-                            TCGOp *begin_op, TCGOp *op, int *intp);
-typedef bool (*op_ok_fn)(const TCGOp *op, const struct qemu_plugin_dyn_cb *cb);
-
-static bool op_ok(const TCGOp *op, const struct qemu_plugin_dyn_cb *cb)
-{
-    return true;
-}
-
-static bool op_rw(const TCGOp *op, const struct qemu_plugin_dyn_cb *cb)
-{
-    int w;
-
-    w = op->args[2];
-    return !!(cb->rw & (w + 1));
-}
-
-static inline
-void inject_cb_type(const GArray *cbs, TCGOp *begin_op, inject_fn inject,
-                    op_ok_fn ok)
-{
-    TCGOp *end_op;
-    TCGOp *op;
-    int cb_idx = -1;
-    int i;
-
-    if (!cbs || cbs->len == 0) {
-        rm_ops(begin_op);
-        return;
-    }
-
-    end_op = find_op(begin_op, INDEX_op_plugin_cb_end);
-    tcg_debug_assert(end_op);
-
-    op = end_op;
-    for (i = 0; i < cbs->len; i++) {
-        struct qemu_plugin_dyn_cb *cb =
-            &g_array_index(cbs, struct qemu_plugin_dyn_cb, i);
-
-        if (!ok(begin_op, cb)) {
-            continue;
-        }
-        op = inject(cb, begin_op, op, &cb_idx);
-    }
-    rm_ops_range(begin_op, end_op);
-}
-
-static void
-inject_udata_cb(const GArray *cbs, TCGOp *begin_op)
-{
-    inject_cb_type(cbs, begin_op, append_udata_cb, op_ok);
-}
-
-static void
-inject_inline_cb(const GArray *cbs, TCGOp *begin_op, op_ok_fn ok)
-{
-    inject_cb_type(cbs, begin_op, append_inline_cb, ok);
-}
-
-static void
-inject_mem_cb(const GArray *cbs, TCGOp *begin_op)
-{
-    inject_cb_type(cbs, begin_op, append_mem_cb, op_rw);
-}
-
-/* we could change the ops in place, but we can reuse more code by copying */
-static void inject_mem_helper(TCGOp *begin_op, GArray *arr)
-{
-    TCGOp *orig_op = begin_op;
-    TCGOp *end_op;
-    TCGOp *op;
-
-    end_op = find_op(begin_op, INDEX_op_plugin_cb_end);
-    tcg_debug_assert(end_op);
-
-    /* const ptr */
-    op = copy_const_ptr(&begin_op, end_op, arr);
-
-    /* st_ptr */
-    op = copy_st_ptr(&begin_op, op);
-
-    rm_ops_range(orig_op, end_op);
-}
-
-/*
- * Tracking memory accesses performed from helpers requires extra work.
- * If an instruction is emulated with helpers, we do two things:
- * (1) copy the CB descriptors, and keep track of it so that they can be
- * freed later on, and (2) point CPUState.plugin_mem_cbs to the descriptors, so
- * that we can read them at run-time (i.e. when the helper executes).
- * This run-time access is performed from qemu_plugin_vcpu_mem_cb.
- *
- * Note that plugin_gen_disable_mem_helpers undoes (2). Since it
- * is possible that the code we generate after the instruction is
- * dead, we also add checks before generating tb_exit etc.
- */
-static void inject_mem_enable_helper(struct qemu_plugin_insn *plugin_insn,
-                                     TCGOp *begin_op)
-{
-    GArray *cbs[2];
-    GArray *arr;
-    size_t n_cbs, i;
-
-    cbs[0] = plugin_insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_REGULAR];
-    cbs[1] = plugin_insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_INLINE];
-
-    n_cbs = 0;
-    for (i = 0; i < ARRAY_SIZE(cbs); i++) {
-        n_cbs += cbs[i]->len;
-    }
-
-    plugin_insn->mem_helper = plugin_insn->calls_helpers && n_cbs;
-    if (likely(!plugin_insn->mem_helper)) {
-        rm_ops(begin_op);
-        return;
-    }
-
-    arr = g_array_sized_new(false, false,
-                            sizeof(struct qemu_plugin_dyn_cb), n_cbs);
-
-    for (i = 0; i < ARRAY_SIZE(cbs); i++) {
-        g_array_append_vals(arr, cbs[i]->data, cbs[i]->len);
-    }
-
-    qemu_plugin_add_dyn_cb_arr(arr);
-    inject_mem_helper(begin_op, arr);
-}
-
-static void inject_mem_disable_helper(struct qemu_plugin_insn *plugin_insn,
-                                      TCGOp *begin_op)
-{
-    if (likely(!plugin_insn->mem_helper)) {
-        rm_ops(begin_op);
-        return;
-    }
-    inject_mem_helper(begin_op, NULL);
-}
-
-/* called before finishing a TB with exit_tb, goto_tb or goto_ptr */
-void plugin_gen_disable_mem_helpers(void)
-{
-    TCGv_ptr ptr;
-
-    if (likely(tcg_ctx->plugin_insn == NULL ||
-               !tcg_ctx->plugin_insn->mem_helper)) {
-        return;
-    }
-    ptr = tcg_const_ptr(NULL);
-    tcg_gen_st_ptr(ptr, cpu_env, offsetof(CPUState, plugin_mem_cbs) -
-                                 offsetof(ArchCPU, env));
-    tcg_temp_free_ptr(ptr);
-    tcg_ctx->plugin_insn->mem_helper = false;
-}
-
-static void plugin_gen_tb_udata(const struct qemu_plugin_tb *ptb,
-                                TCGOp *begin_op)
-{
-    inject_udata_cb(ptb->cbs[PLUGIN_CB_REGULAR], begin_op);
-}
-
-static void plugin_gen_tb_inline(const struct qemu_plugin_tb *ptb,
-                                 TCGOp *begin_op)
-{
-    inject_inline_cb(ptb->cbs[PLUGIN_CB_INLINE], begin_op, op_ok);
-}
-
-static void plugin_gen_insn_udata(const struct qemu_plugin_tb *ptb,
-                                  TCGOp *begin_op, int insn_idx)
-{
-    struct qemu_plugin_insn *insn = g_ptr_array_index(ptb->insns, insn_idx);
-
-    inject_udata_cb(insn->cbs[PLUGIN_CB_INSN][PLUGIN_CB_REGULAR], begin_op);
-}
-
-static void plugin_gen_insn_inline(const struct qemu_plugin_tb *ptb,
-                                   TCGOp *begin_op, int insn_idx)
-{
-    struct qemu_plugin_insn *insn = g_ptr_array_index(ptb->insns, insn_idx);
-    inject_inline_cb(insn->cbs[PLUGIN_CB_INSN][PLUGIN_CB_INLINE],
-                     begin_op, op_ok);
-}
-
-static void plugin_gen_mem_regular(const struct qemu_plugin_tb *ptb,
-                                   TCGOp *begin_op, int insn_idx)
-{
-    struct qemu_plugin_insn *insn = g_ptr_array_index(ptb->insns, insn_idx);
-    inject_mem_cb(insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_REGULAR], begin_op);
-}
-
-static void plugin_gen_mem_inline(const struct qemu_plugin_tb *ptb,
-                                  TCGOp *begin_op, int insn_idx)
-{
-    const GArray *cbs;
-    struct qemu_plugin_insn *insn = g_ptr_array_index(ptb->insns, insn_idx);
-
-    cbs = insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_INLINE];
-    inject_inline_cb(cbs, begin_op, op_rw);
-}
-
-static void plugin_gen_enable_mem_helper(const struct qemu_plugin_tb *ptb,
-                                         TCGOp *begin_op, int insn_idx)
-{
-    struct qemu_plugin_insn *insn = g_ptr_array_index(ptb->insns, insn_idx);
-    inject_mem_enable_helper(insn, begin_op);
-}
-
-static void plugin_gen_disable_mem_helper(const struct qemu_plugin_tb *ptb,
-                                          TCGOp *begin_op, int insn_idx)
-{
-    struct qemu_plugin_insn *insn = g_ptr_array_index(ptb->insns, insn_idx);
-    inject_mem_disable_helper(insn, begin_op);
-}
-
-static void plugin_inject_cb(const struct qemu_plugin_tb *ptb, TCGOp *begin_op,
-                             int insn_idx)
-{
-    enum plugin_gen_from from = begin_op->args[0];
-    enum plugin_gen_cb type = begin_op->args[1];
-
-    switch (from) {
-    case PLUGIN_GEN_FROM_TB:
-        switch (type) {
-        case PLUGIN_GEN_CB_UDATA:
-            plugin_gen_tb_udata(ptb, begin_op);
-            return;
-        case PLUGIN_GEN_CB_INLINE:
-            plugin_gen_tb_inline(ptb, begin_op);
-            return;
-        default:
-            g_assert_not_reached();
-        }
-    case PLUGIN_GEN_FROM_INSN:
-        switch (type) {
-        case PLUGIN_GEN_CB_UDATA:
-            plugin_gen_insn_udata(ptb, begin_op, insn_idx);
-            return;
-        case PLUGIN_GEN_CB_INLINE:
-            plugin_gen_insn_inline(ptb, begin_op, insn_idx);
-            return;
-        case PLUGIN_GEN_ENABLE_MEM_HELPER:
-            plugin_gen_enable_mem_helper(ptb, begin_op, insn_idx);
-            return;
-        default:
-            g_assert_not_reached();
-        }
-    case PLUGIN_GEN_FROM_MEM:
-        switch (type) {
-        case PLUGIN_GEN_CB_MEM:
-            plugin_gen_mem_regular(ptb, begin_op, insn_idx);
-            return;
-        case PLUGIN_GEN_CB_INLINE:
-            plugin_gen_mem_inline(ptb, begin_op, insn_idx);
-            return;
-        default:
-            g_assert_not_reached();
-        }
-    case PLUGIN_GEN_AFTER_INSN:
-        switch (type) {
-        case PLUGIN_GEN_DISABLE_MEM_HELPER:
-            plugin_gen_disable_mem_helper(ptb, begin_op, insn_idx);
-            return;
-        default:
-            g_assert_not_reached();
-        }
-    default:
-        g_assert_not_reached();
-    }
-}
-
-/* #define DEBUG_PLUGIN_GEN_OPS */
-static void pr_ops(void)
-{
-#ifdef DEBUG_PLUGIN_GEN_OPS
-    TCGOp *op;
-    int i = 0;
-
-    QTAILQ_FOREACH(op, &tcg_ctx->ops, link) {
-        const char *name = "";
-        const char *type = "";
-
-        if (op->opc == INDEX_op_plugin_cb_start) {
-            switch (op->args[0]) {
-            case PLUGIN_GEN_FROM_TB:
-                name = "tb";
-                break;
-            case PLUGIN_GEN_FROM_INSN:
-                name = "insn";
-                break;
-            case PLUGIN_GEN_FROM_MEM:
-                name = "mem";
-                break;
-            case PLUGIN_GEN_AFTER_INSN:
-                name = "after insn";
-                break;
-            default:
-                break;
-            }
-            switch (op->args[1]) {
-            case PLUGIN_GEN_CB_UDATA:
-                type = "udata";
-                break;
-            case PLUGIN_GEN_CB_INLINE:
-                type = "inline";
-                break;
-            case PLUGIN_GEN_CB_MEM:
-                type = "mem";
-                break;
-            case PLUGIN_GEN_ENABLE_MEM_HELPER:
-                type = "enable mem helper";
-                break;
-            case PLUGIN_GEN_DISABLE_MEM_HELPER:
-                type = "disable mem helper";
-                break;
-            default:
-                break;
-            }
-        }
-        printf("op[%2i]: %s %s %s\n", i, tcg_op_defs[op->opc].name, name, type);
-        i++;
-    }
-#endif
-}
-
-static void plugin_gen_inject(const struct qemu_plugin_tb *plugin_tb)
-{
-    TCGOp *op;
-    int insn_idx;
-
-    pr_ops();
-    insn_idx = -1;
-    QSIMPLEQ_FOREACH(op, &tcg_ctx->plugin_ops, plugin_link) {
-        enum plugin_gen_from from = op->args[0];
-        enum plugin_gen_cb type = op->args[1];
-
-        tcg_debug_assert(op->opc == INDEX_op_plugin_cb_start);
-        /* ENABLE_MEM_HELPER is the first callback of an instruction */
-        if (from == PLUGIN_GEN_FROM_INSN &&
-            type == PLUGIN_GEN_ENABLE_MEM_HELPER) {
-            insn_idx++;
-        }
-        plugin_inject_cb(plugin_tb, op, insn_idx);
-    }
-    pr_ops();
-}
-
-bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb)
-{
-    struct qemu_plugin_tb *ptb = tcg_ctx->plugin_tb;
-    bool ret = false;
-
-    if (test_bit(QEMU_PLUGIN_EV_VCPU_TB_TRANS, cpu->plugin_mask)) {
-        ret = true;
-
-        QSIMPLEQ_INIT(&tcg_ctx->plugin_ops);
-        ptb->vaddr = tb->pc;
-        ptb->vaddr2 = -1;
-        get_page_addr_code_hostp(cpu->env_ptr, tb->pc, &ptb->haddr1);
-        ptb->haddr2 = NULL;
-
-        plugin_gen_empty_callback(PLUGIN_GEN_FROM_TB);
-    }
-    return ret;
-}
-
-void plugin_gen_insn_start(CPUState *cpu, const DisasContextBase *db)
-{
-    struct qemu_plugin_tb *ptb = tcg_ctx->plugin_tb;
-    struct qemu_plugin_insn *pinsn;
-
-    pinsn = qemu_plugin_tb_insn_get(ptb);
-    tcg_ctx->plugin_insn = pinsn;
-    pinsn->vaddr = db->pc_next;
-    plugin_gen_empty_callback(PLUGIN_GEN_FROM_INSN);
-
-    /*
-     * Detect page crossing to get the new host address.
-     * Note that we skip this when haddr1 == NULL, e.g. when we're
-     * fetching instructions from a region not backed by RAM.
-     */
-    if (likely(ptb->haddr1 != NULL && ptb->vaddr2 == -1) &&
-        unlikely((db->pc_next & TARGET_PAGE_MASK) !=
-                 (db->pc_first & TARGET_PAGE_MASK))) {
-        get_page_addr_code_hostp(cpu->env_ptr, db->pc_next,
-                                 &ptb->haddr2);
-        ptb->vaddr2 = db->pc_next;
-    }
-    if (likely(ptb->vaddr2 == -1)) {
-        pinsn->haddr = ptb->haddr1 + pinsn->vaddr - ptb->vaddr;
-    } else {
-        pinsn->haddr = ptb->haddr2 + pinsn->vaddr - ptb->vaddr2;
-    }
-}
-
-void plugin_gen_insn_end(void)
-{
-    plugin_gen_empty_callback(PLUGIN_GEN_AFTER_INSN);
-}
-
-void plugin_gen_tb_end(CPUState *cpu)
-{
-    struct qemu_plugin_tb *ptb = tcg_ctx->plugin_tb;
-    int i;
-
-    /* collect instrumentation requests */
-    qemu_plugin_tb_trans_cb(cpu, ptb);
-
-    /* inject the instrumentation at the appropriate places */
-    plugin_gen_inject(ptb);
-
-    /* clean up */
-    for (i = 0; i < PLUGIN_N_CB_SUBTYPES; i++) {
-        if (ptb->cbs[i]) {
-            g_array_set_size(ptb->cbs[i], 0);
-        }
-    }
-    ptb->n = 0;
-    tcg_ctx->plugin_insn = NULL;
-}
@@ -1,5 +0,0 @@
-#ifdef CONFIG_PLUGIN
-/* Note: no TCG flags because those are overwritten later */
-DEF_HELPER_2(plugin_vcpu_udata_cb, void, i32, ptr)
-DEF_HELPER_4(plugin_vcpu_mem_cb, void, i32, i32, i64, ptr)
-#endif
@@ -25,28 +25,14 @@

 #include "qemu/osdep.h"
 #include "sysemu/accel.h"
+#include "sysemu/sysemu.h"
 #include "sysemu/tcg.h"
 #include "qom/object.h"
 #include "cpu.h"
 #include "sysemu/cpus.h"
 #include "qemu/main-loop.h"
-#include "tcg/tcg.h"
-#include "qapi/error.h"
-#include "qemu/error-report.h"
-#include "hw/boards.h"
-#include "qapi/qapi-builtin-visit.h"

-typedef struct TCGState {
-    AccelState parent_obj;
-
-    bool mttcg_enabled;
-    unsigned long tb_size;
-} TCGState;
-
-#define TYPE_TCG_ACCEL ACCEL_CLASS_NAME("tcg")
-
-#define TCG_STATE(obj) \
-        OBJECT_CHECK(TCGState, (obj), TYPE_TCG_ACCEL)
+unsigned long tcg_tb_size;

 /* mask must never be zero, except for A20 change call */
 static void tcg_handle_interrupt(CPUState *cpu, int mask)
@@ -73,153 +59,27 @@ static void tcg_handle_interrupt(CPUState *cpu, int mask)
    }
 }

-/*
- * We default to false if we know other options have been enabled
- * which are currently incompatible with MTTCG. Otherwise when each
- * guest (target) has been updated to support:
- *   - atomic instructions
- *   - memory ordering primitives (barriers)
- * they can set the appropriate CONFIG flags in ${target}-softmmu.mak
- *
- * Once a guest architecture has been converted to the new primitives
- * 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 (use_icount || TCG_OVERSIZED_GUEST) {
-        return false;
-    } else {
-#ifdef TARGET_SUPPORTS_MTTCG
-        return check_tcg_memory_orders_compatible();
-#else
-        return false;
-#endif
-    }
-}
-
-static void tcg_accel_instance_init(Object *obj)
-{
-    TCGState *s = TCG_STATE(obj);
-
-    s->mttcg_enabled = default_mttcg_enabled();
-}
-
 static int tcg_init(MachineState *ms)
 {
-    TCGState *s = TCG_STATE(current_accel());
-
-    tcg_exec_init(s->tb_size * 1024 * 1024);
+    tcg_exec_init(tcg_tb_size * 1024 * 1024);
    cpu_interrupt_handler = tcg_handle_interrupt;
-    mttcg_enabled = s->mttcg_enabled;
    return 0;
 }

-static char *tcg_get_thread(Object *obj, Error **errp)
-{
-    TCGState *s = TCG_STATE(obj);
-
-    return g_strdup(s->mttcg_enabled ? "multi" : "single");
-}
-
-static void tcg_set_thread(Object *obj, const char *value, Error **errp)
-{
-    TCGState *s = TCG_STATE(obj);
-
-    if (strcmp(value, "multi") == 0) {
-        if (TCG_OVERSIZED_GUEST) {
-            error_setg(errp, "No MTTCG when guest word size > hosts");
-        } else if (use_icount) {
-            error_setg(errp, "No MTTCG when icount is enabled");
-        } else {
-#ifndef TARGET_SUPPORTS_MTTCG
-            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) {
-        s->mttcg_enabled = false;
-    } else {
-        error_setg(errp, "Invalid 'thread' setting %s", value);
-    }
-}
-
-static void tcg_get_tb_size(Object *obj, Visitor *v,
-                            const char *name, void *opaque,
-                            Error **errp)
-{
-    TCGState *s = TCG_STATE(obj);
-    uint32_t value = s->tb_size;
-
-    visit_type_uint32(v, name, &value, errp);
-}
-
-static void tcg_set_tb_size(Object *obj, Visitor *v,
-                            const char *name, void *opaque,
-                            Error **errp)
-{
-    TCGState *s = TCG_STATE(obj);
-    Error *error = NULL;
-    uint32_t value;
-
-    visit_type_uint32(v, name, &value, &error);
-    if (error) {
-        error_propagate(errp, error);
-        return;
-    }
-
-    s->tb_size = value;
-}
-
 static void tcg_accel_class_init(ObjectClass *oc, void *data)
 {
    AccelClass *ac = ACCEL_CLASS(oc);
    ac->name = "tcg";
    ac->init_machine = tcg_init;
    ac->allowed = &tcg_allowed;
-
-    object_class_property_add_str(oc, "thread",
-                                  tcg_get_thread,
-                                  tcg_set_thread,
-                                  NULL);
-
-    object_class_property_add(oc, "tb-size", "int",
-        tcg_get_tb_size, tcg_set_tb_size,
-        NULL, NULL, &error_abort);
-    object_class_property_set_description(oc, "tb-size",
-        "TCG translation block cache size", &error_abort);
-
 }

+#define TYPE_TCG_ACCEL ACCEL_CLASS_NAME("tcg")
+
 static const TypeInfo tcg_accel_type = {
    .name = TYPE_TCG_ACCEL,
    .parent = TYPE_ACCEL,
-    .instance_init = tcg_accel_instance_init,
    .class_init = tcg_accel_class_init,
-    .instance_size = sizeof(TCGState),
 };

 static void register_accel_types(void)
@@ -21,9 +21,51 @@
 #include "qemu/host-utils.h"
 #include "cpu.h"
 #include "exec/helper-proto.h"
-#include "tcg/tcg-gvec-desc.h"
+#include "tcg-gvec-desc.h"


+/* Virtually all hosts support 16-byte vectors.  Those that don't can emulate
+ * them via GCC's generic vector extension.  This turns out to be simpler and
+ * more reliable than getting the compiler to autovectorize.
+ *
+ * In tcg-op-gvec.c, we asserted that both the size and alignment of the data
+ * are multiples of 16.
+ *
+ * When the compiler does not support all of the operations we require, the
+ * loops are written so that we can always fall back on the base types.
+ */
+#ifdef CONFIG_VECTOR16
+typedef uint8_t vec8 __attribute__((vector_size(16)));
+typedef uint16_t vec16 __attribute__((vector_size(16)));
+typedef uint32_t vec32 __attribute__((vector_size(16)));
+typedef uint64_t vec64 __attribute__((vector_size(16)));
+
+typedef int8_t svec8 __attribute__((vector_size(16)));
+typedef int16_t svec16 __attribute__((vector_size(16)));
+typedef int32_t svec32 __attribute__((vector_size(16)));
+typedef int64_t svec64 __attribute__((vector_size(16)));
+
+#define DUP16(X)  { X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, X }
+#define DUP8(X)   { X, X, X, X, X, X, X, X }
+#define DUP4(X)   { X, X, X, X }
+#define DUP2(X)   { X, X }
+#else
+typedef uint8_t vec8;
+typedef uint16_t vec16;
+typedef uint32_t vec32;
+typedef uint64_t vec64;
+
+typedef int8_t svec8;
+typedef int16_t svec16;
+typedef int32_t svec32;
+typedef int64_t svec64;
+
+#define DUP16(X)  X
+#define DUP8(X)   X
+#define DUP4(X)   X
+#define DUP2(X)   X
+#endif /* CONFIG_VECTOR16 */
+
 static inline void clear_high(void *d, intptr_t oprsz, uint32_t desc)
 {
    intptr_t maxsz = simd_maxsz(desc);
@@ -41,8 +83,8 @@ void HELPER(gvec_add8)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) + *(uint8_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) + *(vec8 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -52,8 +94,8 @@ void HELPER(gvec_add16)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) + *(uint16_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) + *(vec16 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -63,8 +105,8 @@ void HELPER(gvec_add32)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) + *(uint32_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) + *(vec32 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -74,8 +116,8 @@ void HELPER(gvec_add64)(void *d, void *a, void *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) + *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) + *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -83,10 +125,11 @@ void HELPER(gvec_add64)(void *d, void *a, void *b, uint32_t desc)
 void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec8 vecb = (vec8)DUP16(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) + (uint8_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) + vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -94,10 +137,11 @@ void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec16 vecb = (vec16)DUP8(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) + (uint16_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) + vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -105,10 +149,11 @@ void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec32 vecb = (vec32)DUP4(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) + (uint32_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) + vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -116,10 +161,11 @@ void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_adds64)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec64 vecb = (vec64)DUP2(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) + b;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) + vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -129,8 +175,8 @@ void HELPER(gvec_sub8)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) - *(uint8_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) - *(vec8 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -140,8 +186,8 @@ void HELPER(gvec_sub16)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) - *(uint16_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) - *(vec16 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -151,8 +197,8 @@ void HELPER(gvec_sub32)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) - *(uint32_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) - *(vec32 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -162,8 +208,8 @@ void HELPER(gvec_sub64)(void *d, void *a, void *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) - *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) - *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -171,10 +217,11 @@ void HELPER(gvec_sub64)(void *d, void *a, void *b, uint32_t desc)
 void HELPER(gvec_subs8)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec8 vecb = (vec8)DUP16(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) - (uint8_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) - vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -182,10 +229,11 @@ void HELPER(gvec_subs8)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_subs16)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec16 vecb = (vec16)DUP8(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) - (uint16_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) - vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -193,10 +241,11 @@ void HELPER(gvec_subs16)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_subs32)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec32 vecb = (vec32)DUP4(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) - (uint32_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) - vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -204,10 +253,11 @@ void HELPER(gvec_subs32)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_subs64)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec64 vecb = (vec64)DUP2(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) - b;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) - vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -217,8 +267,8 @@ void HELPER(gvec_mul8)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) * *(uint8_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) * *(vec8 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -228,8 +278,8 @@ void HELPER(gvec_mul16)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) * *(uint16_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) * *(vec16 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -239,8 +289,8 @@ void HELPER(gvec_mul32)(void *d, void *a, void *b, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) * *(uint32_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) * *(vec32 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -250,8 +300,8 @@ void HELPER(gvec_mul64)(void *d, void *a, void *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) * *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) * *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -259,10 +309,11 @@ void HELPER(gvec_mul64)(void *d, void *a, void *b, uint32_t desc)
 void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec8 vecb = (vec8)DUP16(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) * (uint8_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) * vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -270,10 +321,11 @@ void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec16 vecb = (vec16)DUP8(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) * (uint16_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) * vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -281,10 +333,11 @@ void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec32 vecb = (vec32)DUP4(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) * (uint32_t)b;
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) * vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -292,10 +345,11 @@ void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_muls64)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec64 vecb = (vec64)DUP2(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) * b;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) * vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -305,8 +359,8 @@ void HELPER(gvec_neg8)(void *d, void *a, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = -*(uint8_t *)(a + i);
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = -*(vec8 *)(a + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -316,8 +370,8 @@ void HELPER(gvec_neg16)(void *d, void *a, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = -*(uint16_t *)(a + i);
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = -*(vec16 *)(a + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -327,8 +381,8 @@ void HELPER(gvec_neg32)(void *d, void *a, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = -*(uint32_t *)(a + i);
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = -*(vec32 *)(a + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -338,8 +392,8 @@ void HELPER(gvec_neg64)(void *d, void *a, 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);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = -*(vec64 *)(a + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -445,8 +499,8 @@ void HELPER(gvec_not)(void *d, void *a, 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);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = ~*(vec64 *)(a + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -456,8 +510,8 @@ void HELPER(gvec_and)(void *d, void *a, void *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) & *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) & *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -467,8 +521,8 @@ void HELPER(gvec_or)(void *d, void *a, void *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) | *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) | *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -478,8 +532,8 @@ void HELPER(gvec_xor)(void *d, void *a, void *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) ^ *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) ^ *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -489,8 +543,8 @@ void HELPER(gvec_andc)(void *d, void *a, void *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) &~ *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) &~ *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -500,8 +554,8 @@ void HELPER(gvec_orc)(void *d, void *a, void *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) |~ *(uint64_t *)(b + i);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) |~ *(vec64 *)(b + i);
    }
    clear_high(d, oprsz, desc);
 }
@@ -511,8 +565,8 @@ void HELPER(gvec_nand)(void *d, void *a, void *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) & *(uint64_t *)(b + i));
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = ~(*(vec64 *)(a + i) & *(vec64 *)(b + i));
    }
    clear_high(d, oprsz, desc);
 }
@@ -522,8 +576,8 @@ void HELPER(gvec_nor)(void *d, void *a, void *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) | *(uint64_t *)(b + i));
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = ~(*(vec64 *)(a + i) | *(vec64 *)(b + i));
    }
    clear_high(d, oprsz, desc);
 }
@@ -533,8 +587,8 @@ void HELPER(gvec_eqv)(void *d, void *a, void *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) ^ *(uint64_t *)(b + i));
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = ~(*(vec64 *)(a + i) ^ *(vec64 *)(b + i));
    }
    clear_high(d, oprsz, desc);
 }
@@ -542,10 +596,11 @@ void HELPER(gvec_eqv)(void *d, void *a, void *b, uint32_t desc)
 void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec64 vecb = (vec64)DUP2(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & b;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) & vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -553,10 +608,11 @@ void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec64 vecb = (vec64)DUP2(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) ^ b;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) ^ vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -564,10 +620,11 @@ void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
 void HELPER(gvec_ors)(void *d, void *a, uint64_t b, uint32_t desc)
 {
    intptr_t oprsz = simd_oprsz(desc);
+    vec64 vecb = (vec64)DUP2(b);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) | b;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) | vecb;
    }
    clear_high(d, oprsz, desc);
 }
@@ -578,8 +635,8 @@ void HELPER(gvec_shl8i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) << shift;
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) << shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -590,8 +647,8 @@ void HELPER(gvec_shl16i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) << shift;
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) << shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -602,8 +659,8 @@ void HELPER(gvec_shl32i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) << shift;
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) << shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -614,8 +671,8 @@ void HELPER(gvec_shl64i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) << shift;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) << shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -626,8 +683,8 @@ void HELPER(gvec_shr8i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(vec8 *)(d + i) = *(vec8 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -638,8 +695,8 @@ void HELPER(gvec_shr16i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(vec16 *)(d + i) = *(vec16 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -650,8 +707,8 @@ void HELPER(gvec_shr32i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(vec32 *)(d + i) = *(vec32 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -662,8 +719,8 @@ void HELPER(gvec_shr64i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(vec64 *)(d + i) = *(vec64 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -674,8 +731,8 @@ void HELPER(gvec_sar8i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        *(int8_t *)(d + i) = *(int8_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(svec8 *)(d + i) = *(svec8 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -686,8 +743,8 @@ void HELPER(gvec_sar16i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        *(int16_t *)(d + i) = *(int16_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec16)) {
+        *(svec16 *)(d + i) = *(svec16 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -698,8 +755,8 @@ void HELPER(gvec_sar32i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        *(int32_t *)(d + i) = *(int32_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(svec32 *)(d + i) = *(svec32 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -710,8 +767,8 @@ void HELPER(gvec_sar64i)(void *d, void *a, uint32_t desc)
    int shift = simd_data(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        *(int64_t *)(d + i) = *(int64_t *)(a + i) >> shift;
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(svec64 *)(d + i) = *(svec64 *)(a + i) >> shift;
    }
    clear_high(d, oprsz, desc);
 }
@@ -860,30 +917,39 @@ void HELPER(gvec_sar64v)(void *d, void *a, void *b, uint32_t desc)
    clear_high(d, oprsz, desc);
 }

+/* If vectors are enabled, the compiler fills in -1 for true.
+   Otherwise, we must take care of this by hand.  */
+#ifdef CONFIG_VECTOR16
+# define DO_CMP0(X)  X
+#else
+# define DO_CMP0(X)  -(X)
+#endif
+
 #define DO_CMP1(NAME, TYPE, OP)                                            \
 void HELPER(NAME)(void *d, void *a, void *b, uint32_t desc)                \
 {                                                                          \
    intptr_t oprsz = simd_oprsz(desc);                                     \
    intptr_t i;                                                            \
    for (i = 0; i < oprsz; i += sizeof(TYPE)) {                            \
-        *(TYPE *)(d + i) = -(*(TYPE *)(a + i) OP *(TYPE *)(b + i));        \
+        *(TYPE *)(d + i) = DO_CMP0(*(TYPE *)(a + i) OP *(TYPE *)(b + i));  \
    }                                                                      \
    clear_high(d, oprsz, desc);                                            \
 }

 #define DO_CMP2(SZ) \
-    DO_CMP1(gvec_eq##SZ, uint##SZ##_t, ==)    \
-    DO_CMP1(gvec_ne##SZ, uint##SZ##_t, !=)    \
-    DO_CMP1(gvec_lt##SZ, int##SZ##_t, <)      \
-    DO_CMP1(gvec_le##SZ, int##SZ##_t, <=)     \
-    DO_CMP1(gvec_ltu##SZ, uint##SZ##_t, <)    \
-    DO_CMP1(gvec_leu##SZ, uint##SZ##_t, <=)
+    DO_CMP1(gvec_eq##SZ, vec##SZ, ==)    \
+    DO_CMP1(gvec_ne##SZ, vec##SZ, !=)    \
+    DO_CMP1(gvec_lt##SZ, svec##SZ, <)    \
+    DO_CMP1(gvec_le##SZ, svec##SZ, <=)   \
+    DO_CMP1(gvec_ltu##SZ, vec##SZ, <)    \
+    DO_CMP1(gvec_leu##SZ, vec##SZ, <=)

 DO_CMP2(8)
 DO_CMP2(16)
 DO_CMP2(32)
 DO_CMP2(64)

+#undef DO_CMP0
 #undef DO_CMP1
 #undef DO_CMP2

@@ -1384,11 +1450,11 @@ void HELPER(gvec_bitsel)(void *d, void *a, void *b, void *c, uint32_t desc)
    intptr_t oprsz = simd_oprsz(desc);
    intptr_t i;

-    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        uint64_t aa = *(uint64_t *)(a + i);
-        uint64_t bb = *(uint64_t *)(b + i);
-        uint64_t cc = *(uint64_t *)(c + i);
-        *(uint64_t *)(d + i) = (bb & aa) | (cc & ~aa);
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        vec64 aa = *(vec64 *)(a + i);
+        vec64 bb = *(vec64 *)(b + i);
+        vec64 cc = *(vec64 *)(c + i);
+        *(vec64 *)(d + i) = (bb & aa) | (cc & ~aa);
    }
    clear_high(d, oprsz, desc);
 }
@@ -30,7 +30,6 @@
 #include "exec/tb-lookup.h"
 #include "disas/disas.h"
 #include "exec/log.h"
-#include "tcg/tcg.h"

 /* 32-bit helpers */

@@ -18,7 +18,6 @@
 */

 #include "qemu/osdep.h"
-#include "qemu/units.h"
 #include "qemu-common.h"

 #define NO_CPU_IO_DEFS
@@ -26,7 +25,7 @@
 #include "trace.h"
 #include "disas/disas.h"
 #include "exec/exec-all.h"
-#include "tcg/tcg.h"
+#include "tcg.h"
 #if defined(CONFIG_USER_ONLY)
 #include "qemu.h"
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -892,61 +891,43 @@ static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1,
    }
 }

+#if defined(CONFIG_USER_ONLY)
+/* Currently it is not recommended to allocate big chunks of data in
+   user mode. It will change when a dedicated libc will be used.  */
+/* ??? 64-bit hosts ought to have no problem mmaping data outside the
+   region in which the guest needs to run.  Revisit this.  */
+#define USE_STATIC_CODE_GEN_BUFFER
+#endif
+
 /* Minimum size of the code gen buffer.  This number is randomly chosen,
   but not so small that we can't have a fair number of TB's live.  */
-#define MIN_CODE_GEN_BUFFER_SIZE     (1 * MiB)
+#define MIN_CODE_GEN_BUFFER_SIZE     (1024u * 1024)

 /* Maximum size of the code gen buffer we'd like to use.  Unless otherwise
   indicated, this is constrained by the range of direct branches on the
   host cpu, as used by the TCG implementation of goto_tb.  */
 #if defined(__x86_64__)
-# define MAX_CODE_GEN_BUFFER_SIZE  (2 * GiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
 #elif defined(__sparc__)
-# define MAX_CODE_GEN_BUFFER_SIZE  (2 * GiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
 #elif defined(__powerpc64__)
-# define MAX_CODE_GEN_BUFFER_SIZE  (2 * GiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
 #elif defined(__powerpc__)
-# define MAX_CODE_GEN_BUFFER_SIZE  (32 * MiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (32u * 1024 * 1024)
 #elif defined(__aarch64__)
-# define MAX_CODE_GEN_BUFFER_SIZE  (2 * GiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
 #elif defined(__s390x__)
  /* We have a +- 4GB range on the branches; leave some slop.  */
-# define MAX_CODE_GEN_BUFFER_SIZE  (3 * GiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (3ul * 1024 * 1024 * 1024)
 #elif defined(__mips__)
  /* We have a 256MB branch region, but leave room to make sure the
     main executable is also within that region.  */
-# define MAX_CODE_GEN_BUFFER_SIZE  (128 * MiB)
+# define MAX_CODE_GEN_BUFFER_SIZE  (128ul * 1024 * 1024)
 #else
 # define MAX_CODE_GEN_BUFFER_SIZE  ((size_t)-1)
 #endif

-#if TCG_TARGET_REG_BITS == 32
-#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (32 * MiB)
-#ifdef CONFIG_USER_ONLY
-/*
- * For user mode on smaller 32 bit systems we may run into trouble
- * allocating big chunks of data in the right place. On these systems
- * we utilise a static code generation buffer directly in the binary.
- */
-#define USE_STATIC_CODE_GEN_BUFFER
-#endif
-#else /* TCG_TARGET_REG_BITS == 64 */
-#ifdef CONFIG_USER_ONLY
-/*
- * As user-mode emulation typically means running multiple instances
- * of the translator don't go too nuts with our default code gen
- * buffer lest we make things too hard for the OS.
- */
-#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (128 * MiB)
-#else
-/*
- * We expect most system emulation to run one or two guests per host.
- * Users running large scale system emulation may want to tweak their
- * runtime setup via the tb-size control on the command line.
- */
-#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (1 * GiB)
-#endif
-#endif
+#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (32u * 1024 * 1024)

 #define DEFAULT_CODE_GEN_BUFFER_SIZE \
  (DEFAULT_CODE_GEN_BUFFER_SIZE_1 < MAX_CODE_GEN_BUFFER_SIZE \
@@ -956,7 +937,15 @@ static inline size_t size_code_gen_buffer(size_t tb_size)
 {
    /* Size the buffer.  */
    if (tb_size == 0) {
+#ifdef USE_STATIC_CODE_GEN_BUFFER
        tb_size = DEFAULT_CODE_GEN_BUFFER_SIZE;
+#else
+        /* ??? Needs adjustments.  */
+        /* ??? If we relax the requirement that CONFIG_USER_ONLY use the
+           static buffer, we could size this on RESERVED_VA, on the text
+           segment size of the executable, or continue to use the default.  */
+        tb_size = (unsigned long)(ram_size / 4);
+#endif
    }
    if (tb_size < MIN_CODE_GEN_BUFFER_SIZE) {
        tb_size = MIN_CODE_GEN_BUFFER_SIZE;
@@ -1043,20 +1032,47 @@ static inline void *alloc_code_gen_buffer(void)
 {
    int prot = PROT_WRITE | PROT_READ | PROT_EXEC;
    int flags = MAP_PRIVATE | MAP_ANONYMOUS;
+    uintptr_t start = 0;
    size_t size = tcg_ctx->code_gen_buffer_size;
    void *buf;

-    buf = mmap(NULL, size, prot, flags, -1, 0);
+    /* Constrain the position of the buffer based on the host cpu.
+       Note that these addresses are chosen in concert with the
+       addresses assigned in the relevant linker script file.  */
+# if defined(__PIE__) || defined(__PIC__)
+    /* Don't bother setting a preferred location if we're building
+       a position-independent executable.  We're more likely to get
+       an address near the main executable if we let the kernel
+       choose the address.  */
+# elif defined(__x86_64__) && defined(MAP_32BIT)
+    /* Force the memory down into low memory with the executable.
+       Leave the choice of exact location with the kernel.  */
+    flags |= MAP_32BIT;
+    /* Cannot expect to map more than 800MB in low memory.  */
+    if (size > 800u * 1024 * 1024) {
+        tcg_ctx->code_gen_buffer_size = size = 800u * 1024 * 1024;
+    }
+# elif defined(__sparc__)
+    start = 0x40000000ul;
+# elif defined(__s390x__)
+    start = 0x90000000ul;
+# elif defined(__mips__)
+#  if _MIPS_SIM == _ABI64
+    start = 0x128000000ul;
+#  else
+    start = 0x08000000ul;
+#  endif
+# endif
+
+    buf = mmap((void *)start, size, prot, flags, -1, 0);
    if (buf == MAP_FAILED) {
        return NULL;
    }

 #ifdef __mips__
    if (cross_256mb(buf, size)) {
-        /*
-         * Try again, with the original still mapped, to avoid re-acquiring
-         * the same 256mb crossing.
-         */
+        /* Try again, with the original still mapped, to avoid re-acquiring
+           that 256mb crossing.  This time don't specify an address.  */
        size_t size2;
        void *buf2 = mmap(NULL, size, prot, flags, -1, 0);
        switch ((int)(buf2 != MAP_FAILED)) {
@@ -1140,6 +1156,23 @@ void tcg_exec_init(unsigned long tb_size)
 #endif
 }

+/*
+ * Allocate a new translation block. Flush the translation buffer if
+ * too many translation blocks or too much generated code.
+ */
+static TranslationBlock *tb_alloc(target_ulong pc)
+{
+    TranslationBlock *tb;
+
+    assert_memory_lock();
+
+    tb = tcg_tb_alloc(tcg_ctx);
+    if (unlikely(tb == NULL)) {
+        return NULL;
+    }
+    return tb;
+}
+
 /* call with @p->lock held */
 static inline void invalidate_page_bitmap(PageDesc *p)
 {
@@ -1198,8 +1231,6 @@ static gboolean tb_host_size_iter(gpointer key, gpointer value, gpointer data)
 /* flush all the translation blocks */
 static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)
 {
-    bool did_flush = false;
-
    mmap_lock();
    /* If it is already been done on request of another CPU,
     * just retry.
@@ -1207,7 +1238,6 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)
    if (tb_ctx.tb_flush_count != tb_flush_count.host_int) {
        goto done;
    }
-    did_flush = true;

    if (DEBUG_TB_FLUSH_GATE) {
        size_t nb_tbs = tcg_nb_tbs();
@@ -1232,22 +1262,14 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)

 done:
    mmap_unlock();
-    if (did_flush) {
-        qemu_plugin_flush_cb();
-    }
 }

 void tb_flush(CPUState *cpu)
 {
    if (tcg_enabled()) {
        unsigned tb_flush_count = atomic_mb_read(&tb_ctx.tb_flush_count);
-
-        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,
-                                  RUN_ON_CPU_HOST_INT(tb_flush_count));
-        }
+        async_safe_run_on_cpu(cpu, do_tb_flush,
+                              RUN_ON_CPU_HOST_INT(tb_flush_count));
    }
 }

@@ -1659,7 +1681,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
    TCGProfile *prof = &tcg_ctx->prof;
    int64_t ti;
 #endif
-
    assert_memory_lock();

    phys_pc = get_page_addr_code(env, pc);
@@ -1685,7 +1706,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
    }

 buffer_overflow:
-    tb = tcg_tb_alloc(tcg_ctx);
+    tb = tb_alloc(pc);
    if (unlikely(!tb)) {
        /* flush must be done */
        tb_flush(cpu);
@@ -1701,7 +1722,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
    tb->cs_base = cs_base;
    tb->flags = flags;
    tb->cflags = cflags;
-    tb->orig_tb = NULL;
    tb->trace_vcpu_dstate = *cpu->trace_dstate;
    tcg_ctx->tb_cflags = cflags;
 tb_overflow:
@@ -1788,7 +1808,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 #ifdef DEBUG_DISAS
    if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) &&
        qemu_log_in_addr_range(tb->pc)) {
-        FILE *logfile = qemu_log_lock();
+        qemu_log_lock();
        qemu_log("OUT: [size=%d]\n", gen_code_size);
        if (tcg_ctx->data_gen_ptr) {
            size_t code_size = tcg_ctx->data_gen_ptr - tb->tc.ptr;
@@ -1813,7 +1833,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
        }
        qemu_log("\n");
        qemu_log_flush();
-        qemu_log_unlock(logfile);
+        qemu_log_unlock();
    }
 #endif

@@ -1869,7 +1889,7 @@ static void
 tb_invalidate_phys_page_range__locked(struct page_collection *pages,
                                      PageDesc *p, tb_page_addr_t start,
                                      tb_page_addr_t end,
-                                      uintptr_t retaddr)
+                                      int is_cpu_write_access)
 {
    TranslationBlock *tb;
    tb_page_addr_t tb_start, tb_end;
@@ -1877,9 +1897,9 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
 #ifdef TARGET_HAS_PRECISE_SMC
    CPUState *cpu = current_cpu;
    CPUArchState *env = NULL;
-    bool current_tb_not_found = retaddr != 0;
-    bool current_tb_modified = false;
+    int current_tb_not_found = is_cpu_write_access;
    TranslationBlock *current_tb = NULL;
+    int current_tb_modified = 0;
    target_ulong current_pc = 0;
    target_ulong current_cs_base = 0;
    uint32_t current_flags = 0;
@@ -1911,21 +1931,24 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
        if (!(tb_end <= start || tb_start >= end)) {
 #ifdef TARGET_HAS_PRECISE_SMC
            if (current_tb_not_found) {
-                current_tb_not_found = false;
-                /* now we have a real cpu fault */
-                current_tb = tcg_tb_lookup(retaddr);
+                current_tb_not_found = 0;
+                current_tb = NULL;
+                if (cpu->mem_io_pc) {
+                    /* now we have a real cpu fault */
+                    current_tb = tcg_tb_lookup(cpu->mem_io_pc);
+                }
            }
            if (current_tb == tb &&
                (tb_cflags(current_tb) & CF_COUNT_MASK) != 1) {
-                /*
-                 * If we are modifying the current TB, we must stop
-                 * its execution. We could be more precise by checking
-                 * that the modification is after the current PC, but it
-                 * would require a specialized function to partially
-                 * restore the CPU state.
-                 */
-                current_tb_modified = true;
-                cpu_restore_state_from_tb(cpu, current_tb, retaddr, true);
+                /* If we are modifying the current TB, we must stop
+                its execution. We could be more precise by checking
+                that the modification is after the current PC, but it
+                would require a specialized function to partially
+                restore the CPU state */
+
+                current_tb_modified = 1;
+                cpu_restore_state_from_tb(cpu, current_tb,
+                                          cpu->mem_io_pc, true);
                cpu_get_tb_cpu_state(env, &current_pc, &current_cs_base,
                                     &current_flags);
            }
@@ -1960,7 +1983,8 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
 *
 * Called with mmap_lock held for user-mode emulation
 */
-void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end)
+void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
+                                   int is_cpu_write_access)
 {
    struct page_collection *pages;
    PageDesc *p;
@@ -1972,7 +1996,8 @@ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end)
        return;
    }
    pages = page_collection_lock(start, end);
-    tb_invalidate_phys_page_range__locked(pages, p, start, end, 0);
+    tb_invalidate_phys_page_range__locked(pages, p, start, end,
+                                          is_cpu_write_access);
    page_collection_unlock(pages);
 }

@@ -2019,8 +2044,7 @@ void tb_invalidate_phys_range(target_ulong start, target_ulong end)
 * Call with all @pages in the range [@start, @start + len[ locked.
 */
 void tb_invalidate_phys_page_fast(struct page_collection *pages,
-                                  tb_page_addr_t start, int len,
-                                  uintptr_t retaddr)
+                                  tb_page_addr_t start, int len)
 {
    PageDesc *p;

@@ -2047,8 +2071,7 @@ void tb_invalidate_phys_page_fast(struct page_collection *pages,
        }
    } else {
    do_invalidate:
-        tb_invalidate_phys_page_range__locked(pages, p, start, start + len,
-                                              retaddr);
+        tb_invalidate_phys_page_range__locked(pages, p, start, start + len, 1);
    }
 }
 #else
@@ -2122,16 +2145,16 @@ static bool tb_invalidate_phys_page(tb_page_addr_t addr, uintptr_t pc)
 #endif

 /* user-mode: call with mmap_lock held */
-void tb_check_watchpoint(CPUState *cpu, uintptr_t retaddr)
+void tb_check_watchpoint(CPUState *cpu)
 {
    TranslationBlock *tb;

    assert_memory_lock();

-    tb = tcg_tb_lookup(retaddr);
+    tb = tcg_tb_lookup(cpu->mem_io_pc);
    if (tb) {
        /* We can use retranslation to find the PC.  */
-        cpu_restore_state_from_tb(cpu, tb, retaddr, true);
+        cpu_restore_state_from_tb(cpu, tb, cpu->mem_io_pc, true);
        tb_phys_invalidate(tb, -1);
    } else {
        /* The exception probably happened in a helper.  The CPU state should
@@ -27,10 +27,10 @@ struct page_collection *page_collection_lock(tb_page_addr_t start,
                                             tb_page_addr_t end);
 void page_collection_unlock(struct page_collection *set);
 void tb_invalidate_phys_page_fast(struct page_collection *pages,
-                                  tb_page_addr_t start, int len,
-                                  uintptr_t retaddr);
-void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end);
-void tb_check_watchpoint(CPUState *cpu, uintptr_t retaddr);
+                                  tb_page_addr_t start, int len);
+void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
+                                   int is_cpu_write_access);
+void tb_check_watchpoint(CPUState *cpu);

 #ifdef CONFIG_USER_ONLY
 int page_unprotect(target_ulong address, uintptr_t pc);
@@ -16,7 +16,6 @@
 #include "exec/gen-icount.h"
 #include "exec/log.h"
 #include "exec/translator.h"
-#include "exec/plugin-gen.h"

 /* Pairs with tcg_clear_temp_count.
   To be called by #TranslatorOps.{translate_insn,tb_stop} if
@@ -35,7 +34,6 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
                     CPUState *cpu, TranslationBlock *tb, int max_insns)
 {
    int bp_insn = 0;
-    bool plugin_enabled;

    /* Initialize DisasContext */
    db->tb = tb;
@@ -57,17 +55,11 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
    ops->tb_start(db, cpu);
    tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */

-    plugin_enabled = plugin_gen_tb_start(cpu, tb);
-
    while (true) {
        db->num_insns++;
        ops->insn_start(db, cpu);
        tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */

-        if (plugin_enabled) {
-            plugin_gen_insn_start(cpu, db);
-        }
-
        /* Pass breakpoint hits to target for further processing */
        if (!db->singlestep_enabled
            && unlikely(!QTAILQ_EMPTY(&cpu->breakpoints))) {
@@ -98,6 +90,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
            /* Accept I/O on the last instruction.  */
            gen_io_start();
            ops->translate_insn(db, cpu);
+            gen_io_end();
        } else {
            ops->translate_insn(db, cpu);
        }
@@ -107,14 +100,6 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
            break;
        }

-        /*
-         * We can't instrument after instructions that change control
-         * flow although this only really affects post-load operations.
-         */
-        if (plugin_enabled) {
-            plugin_gen_insn_end();
-        }
-
        /* Stop translation if the output buffer is full,
           or we have executed all of the allowed instructions.  */
        if (tcg_op_buf_full() || db->num_insns >= db->max_insns) {
@@ -127,10 +112,6 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
    ops->tb_stop(db, cpu);
    gen_tb_end(db->tb, db->num_insns - bp_insn);

-    if (plugin_enabled) {
-        plugin_gen_tb_end(cpu);
-    }
-
    /* The disas_log hook may use these values rather than recompute.  */
    db->tb->size = db->pc_next - db->pc_first;
    db->tb->icount = db->num_insns;
@@ -138,11 +119,11 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
 #ifdef DEBUG_DISAS
    if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)
        && qemu_log_in_addr_range(db->pc_first)) {
-        FILE *logfile = qemu_log_lock();
+        qemu_log_lock();
        qemu_log("----------------\n");
        ops->disas_log(db, cpu);
        qemu_log("\n");
-        qemu_log_unlock(logfile);
+        qemu_log_unlock();
    }
 #endif
 }
@@ -1,5 +1,5 @@
 #include "qemu/osdep.h"
-#include "hw/core/cpu.h"
+#include "qom/cpu.h"
 #include "sysemu/replay.h"
 #include "sysemu/sysemu.h"

@@ -20,14 +20,12 @@
 #include "cpu.h"
 #include "disas/disas.h"
 #include "exec/exec-all.h"
-#include "tcg/tcg.h"
+#include "tcg.h"
 #include "qemu/bitops.h"
 #include "exec/cpu_ldst.h"
 #include "translate-all.h"
 #include "exec/helper-proto.h"
 #include "qemu/atomic128.h"
-#include "trace-root.h"
-#include "trace/mem.h"

 #undef EAX
 #undef ECX
@@ -190,38 +188,6 @@ static inline int handle_cpu_signal(uintptr_t pc, siginfo_t *info,
    g_assert_not_reached();
 }

-void *probe_access(CPUArchState *env, target_ulong addr, int size,
-                   MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int flags;
-
-    g_assert(-(addr | TARGET_PAGE_MASK) >= size);
-
-    switch (access_type) {
-    case MMU_DATA_STORE:
-        flags = PAGE_WRITE;
-        break;
-    case MMU_DATA_LOAD:
-        flags = PAGE_READ;
-        break;
-    case MMU_INST_FETCH:
-        flags = PAGE_EXEC;
-        break;
-    default:
-        g_assert_not_reached();
-    }
-
-    if (!guest_addr_valid(addr) || page_check_range(addr, size, flags) < 0) {
-        CPUState *cpu = env_cpu(env);
-        CPUClass *cc = CPU_GET_CLASS(cpu);
-        cc->tlb_fill(cpu, addr, size, access_type, MMU_USER_IDX, false,
-                     retaddr);
-        g_assert_not_reached();
-    }
-
-    return size ? g2h(addr) : NULL;
-}
-
 #if defined(__i386__)

 #if defined(__NetBSD__)
@@ -736,240 +702,6 @@ int cpu_signal_handler(int host_signum, void *pinfo,

 /* The softmmu versions of these helpers are in cputlb.c.  */

-uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr)
-{
-    uint32_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_UB, MMU_USER_IDX, false);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldub_p(g2h(ptr));
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-    return ret;
-}
-
-int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr)
-{
-    int ret;
-    uint16_t meminfo = trace_mem_get_info(MO_SB, MMU_USER_IDX, false);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldsb_p(g2h(ptr));
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-    return ret;
-}
-
-uint32_t cpu_lduw_data(CPUArchState *env, abi_ptr ptr)
-{
-    uint32_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TEUW, MMU_USER_IDX, false);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = lduw_p(g2h(ptr));
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-    return ret;
-}
-
-int cpu_ldsw_data(CPUArchState *env, abi_ptr ptr)
-{
-    int ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TESW, MMU_USER_IDX, false);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldsw_p(g2h(ptr));
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-    return ret;
-}
-
-uint32_t cpu_ldl_data(CPUArchState *env, abi_ptr ptr)
-{
-    uint32_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TEUL, MMU_USER_IDX, false);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldl_p(g2h(ptr));
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-    return ret;
-}
-
-uint64_t cpu_ldq_data(CPUArchState *env, abi_ptr ptr)
-{
-    uint64_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TEQ, MMU_USER_IDX, false);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldq_p(g2h(ptr));
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-    return ret;
-}
-
-uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
-{
-    uint32_t ret;
-
-    set_helper_retaddr(retaddr);
-    ret = cpu_ldub_data(env, ptr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
-{
-    int ret;
-
-    set_helper_retaddr(retaddr);
-    ret = cpu_ldsb_data(env, ptr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint32_t cpu_lduw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
-{
-    uint32_t ret;
-
-    set_helper_retaddr(retaddr);
-    ret = cpu_lduw_data(env, ptr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-int cpu_ldsw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
-{
-    int ret;
-
-    set_helper_retaddr(retaddr);
-    ret = cpu_ldsw_data(env, ptr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint32_t cpu_ldl_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
-{
-    uint32_t ret;
-
-    set_helper_retaddr(retaddr);
-    ret = cpu_ldl_data(env, ptr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint64_t cpu_ldq_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
-{
-    uint64_t ret;
-
-    set_helper_retaddr(retaddr);
-    ret = cpu_ldq_data(env, ptr);
-    clear_helper_retaddr();
-    return ret;
-}
-
-void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
-{
-    uint16_t meminfo = trace_mem_get_info(MO_UB, MMU_USER_IDX, true);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stb_p(g2h(ptr), val);
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-}
-
-void cpu_stw_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
-{
-    uint16_t meminfo = trace_mem_get_info(MO_TEUW, MMU_USER_IDX, true);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stw_p(g2h(ptr), val);
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-}
-
-void cpu_stl_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
-{
-    uint16_t meminfo = trace_mem_get_info(MO_TEUL, MMU_USER_IDX, true);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stl_p(g2h(ptr), val);
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-}
-
-void cpu_stq_data(CPUArchState *env, abi_ptr ptr, uint64_t val)
-{
-    uint16_t meminfo = trace_mem_get_info(MO_TEQ, MMU_USER_IDX, true);
-
-    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stq_p(g2h(ptr), val);
-    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
-}
-
-void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr)
-{
-    set_helper_retaddr(retaddr);
-    cpu_stb_data(env, ptr, val);
-    clear_helper_retaddr();
-}
-
-void cpu_stw_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr)
-{
-    set_helper_retaddr(retaddr);
-    cpu_stw_data(env, ptr, val);
-    clear_helper_retaddr();
-}
-
-void cpu_stl_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr)
-{
-    set_helper_retaddr(retaddr);
-    cpu_stl_data(env, ptr, val);
-    clear_helper_retaddr();
-}
-
-void cpu_stq_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint64_t val, uintptr_t retaddr)
-{
-    set_helper_retaddr(retaddr);
-    cpu_stq_data(env, ptr, val);
-    clear_helper_retaddr();
-}
-
-uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr ptr)
-{
-    uint32_t ret;
-
-    set_helper_retaddr(1);
-    ret = ldub_p(g2h(ptr));
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr ptr)
-{
-    uint32_t ret;
-
-    set_helper_retaddr(1);
-    ret = lduw_p(g2h(ptr));
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr ptr)
-{
-    uint32_t ret;
-
-    set_helper_retaddr(1);
-    ret = ldl_p(g2h(ptr));
-    clear_helper_retaddr();
-    return ret;
-}
-
-uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr ptr)
-{
-    uint64_t ret;
-
-    set_helper_retaddr(1);
-    ret = ldq_p(g2h(ptr));
-    clear_helper_retaddr();
-    return ret;
-}
-
 /* Do not allow unaligned operations to proceed.  Return the host address.  */
 static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
                               int size, uintptr_t retaddr)
@@ -987,13 +719,10 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
 #define ATOMIC_MMU_DECLS do {} while (0)
 #define ATOMIC_MMU_LOOKUP  atomic_mmu_lookup(env, addr, DATA_SIZE, GETPC())
 #define ATOMIC_MMU_CLEANUP do { clear_helper_retaddr(); } while (0)
-#define ATOMIC_MMU_IDX MMU_USER_IDX

 #define ATOMIC_NAME(X)   HELPER(glue(glue(atomic_ ## X, SUFFIX), END))
 #define EXTRA_ARGS

-#include "atomic_common.inc.c"
-
 #define DATA_SIZE 1
 #include "atomic_template.h"

@@ -38,10 +38,6 @@
 int graphic_width = 1024;
 int graphic_height = 768;
 int graphic_depth = 8;
-#elif defined(TARGET_M68K)
-int graphic_width = 800;
-int graphic_height = 600;
-int graphic_depth = 8;
 #else
 int graphic_width = 800;
 int graphic_height = 600;
@@ -77,8 +73,6 @@ int graphic_depth = 32;
 #define QEMU_ARCH QEMU_ARCH_PPC
 #elif defined(TARGET_RISCV)
 #define QEMU_ARCH QEMU_ARCH_RISCV
-#elif defined(TARGET_RX)
-#define QEMU_ARCH QEMU_ARCH_RX
 #elif defined(TARGET_S390X)
 #define QEMU_ARCH QEMU_ARCH_S390X
 #elif defined(TARGET_SH4)
@@ -112,3 +106,14 @@ int xen_available(void)
    return 0;
 #endif
 }
+
+
+TargetInfo *qmp_query_target(Error **errp)
+{
+    TargetInfo *info = g_malloc0(sizeof(*info));
+
+    info->arch = qapi_enum_parse(&SysEmuTarget_lookup, TARGET_NAME, -1,
+                                 &error_abort);
+
+    return info;
+}
@@ -2,6 +2,7 @@ common-obj-y = audio.o audio_legacy.o noaudio.o wavaudio.o mixeng.o
 common-obj-$(CONFIG_SPICE) += spiceaudio.o
 common-obj-$(CONFIG_AUDIO_COREAUDIO) += coreaudio.o
 common-obj-$(CONFIG_AUDIO_DSOUND) += dsoundaudio.o
+common-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
 common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
 common-obj-y += wavcapture.o

@@ -39,11 +39,13 @@ struct pollhlp {
    struct pollfd *pfds;
    int count;
    int mask;
-    AudioState *s;
 };

 typedef struct ALSAVoiceOut {
    HWVoiceOut hw;
+    int wpos;
+    int pending;
+    void *pcm_buf;
    snd_pcm_t *handle;
    struct pollhlp pollhlp;
    Audiodev *dev;
@@ -52,6 +54,7 @@ typedef struct ALSAVoiceOut {
 typedef struct ALSAVoiceIn {
    HWVoiceIn hw;
    snd_pcm_t *handle;
+    void *pcm_buf;
    struct pollhlp pollhlp;
    Audiodev *dev;
 } ALSAVoiceIn;
@@ -196,11 +199,11 @@ static void alsa_poll_handler (void *opaque)
        break;

    case SND_PCM_STATE_PREPARED:
-        audio_run(hlp->s, "alsa run (prepared)");
+        audio_run ("alsa run (prepared)");
        break;

    case SND_PCM_STATE_RUNNING:
-        audio_run(hlp->s, "alsa run (running)");
+        audio_run ("alsa run (running)");
        break;

    default:
@@ -266,6 +269,11 @@ static int alsa_poll_in (HWVoiceIn *hw)
    return alsa_poll_helper (alsa->handle, &alsa->pollhlp, POLLIN);
 }

+static int alsa_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
 static snd_pcm_format_t aud_to_alsafmt (AudioFormat fmt, int endianness)
 {
    switch (fmt) {
@@ -307,13 +315,6 @@ static snd_pcm_format_t aud_to_alsafmt (AudioFormat fmt, int endianness)
            return SND_PCM_FORMAT_U32_LE;
        }

-    case AUDIO_FORMAT_F32:
-        if (endianness) {
-            return SND_PCM_FORMAT_FLOAT_BE;
-        } else {
-            return SND_PCM_FORMAT_FLOAT_LE;
-        }
-
    default:
        dolog ("Internal logic error: Bad audio format %d\n", fmt);
 #ifdef DEBUG_AUDIO
@@ -377,16 +378,6 @@ static int alsa_to_audfmt (snd_pcm_format_t alsafmt, AudioFormat *fmt,
        *fmt = AUDIO_FORMAT_U32;
        break;

-    case SND_PCM_FORMAT_FLOAT_LE:
-        *endianness = 0;
-        *fmt = AUDIO_FORMAT_F32;
-        break;
-
-    case SND_PCM_FORMAT_FLOAT_BE:
-        *endianness = 1;
-        *fmt = AUDIO_FORMAT_F32;
-        break;
-
    default:
        dolog ("Unrecognized audio format %d\n", alsafmt);
        return -1;
@@ -510,6 +501,13 @@ static int alsa_open(bool in, struct alsa_params_req *req,
        goto err;
    }

+    if (nchannels != 1 && nchannels != 2) {
+        alsa_logerr2 (err, typ,
+                      "Can not handle obtained number of channels %d\n",
+                      nchannels);
+        goto err;
+    }
+
    if (apdo->buffer_length) {
        int dir = 0;
        unsigned int btime = apdo->buffer_length;
@@ -608,64 +606,102 @@ static int alsa_open(bool in, struct alsa_params_req *req,
    return -1;
 }

-static size_t alsa_write(HWVoiceOut *hw, void *buf, size_t len)
+static snd_pcm_sframes_t alsa_get_avail (snd_pcm_t *handle)
 {
-    ALSAVoiceOut *alsa = (ALSAVoiceOut *) hw;
-    size_t pos = 0;
-    size_t len_frames = len / hw->info.bytes_per_frame;
+    snd_pcm_sframes_t avail;

-    while (len_frames) {
-        char *src = advance(buf, pos);
-        snd_pcm_sframes_t written;
-
-        written = snd_pcm_writei(alsa->handle, src, len_frames);
-
-        if (written <= 0) {
-            switch (written) {
-            case 0:
-                trace_alsa_wrote_zero(len_frames);
-                return pos;
-
-            case -EPIPE:
-                if (alsa_recover(alsa->handle)) {
-                    alsa_logerr(written, "Failed to write %zu frames\n",
-                                len_frames);
-                    return pos;
-                }
-                trace_alsa_xrun_out();
-                continue;
-
-            case -ESTRPIPE:
-                /*
-                 * stream is suspended and waiting for an application
-                 * recovery
-                 */
-                if (alsa_resume(alsa->handle)) {
-                    alsa_logerr(written, "Failed to write %zu frames\n",
-                                len_frames);
-                    return pos;
-                }
-                trace_alsa_resume_out();
-                continue;
-
-            case -EAGAIN:
-                return pos;
-
-            default:
-                alsa_logerr(written, "Failed to write %zu frames from %p\n",
-                            len, src);
-                return pos;
+    avail = snd_pcm_avail_update (handle);
+    if (avail < 0) {
+        if (avail == -EPIPE) {
+            if (!alsa_recover (handle)) {
+                avail = snd_pcm_avail_update (handle);
            }
        }

-        pos += written * hw->info.bytes_per_frame;
-        if (written < len_frames) {
-            break;
+        if (avail < 0) {
+            alsa_logerr (avail,
+                         "Could not obtain number of available frames\n");
+            return -1;
        }
-        len_frames -= written;
    }

-    return pos;
+    return avail;
+}
+
+static void alsa_write_pending (ALSAVoiceOut *alsa)
+{
+    HWVoiceOut *hw = &alsa->hw;
+
+    while (alsa->pending) {
+        int left_till_end_samples = hw->samples - alsa->wpos;
+        int len = audio_MIN (alsa->pending, left_till_end_samples);
+        char *src = advance (alsa->pcm_buf, alsa->wpos << hw->info.shift);
+
+        while (len) {
+            snd_pcm_sframes_t written;
+
+            written = snd_pcm_writei (alsa->handle, src, len);
+
+            if (written <= 0) {
+                switch (written) {
+                case 0:
+                    trace_alsa_wrote_zero(len);
+                    return;
+
+                case -EPIPE:
+                    if (alsa_recover (alsa->handle)) {
+                        alsa_logerr (written, "Failed to write %d frames\n",
+                                     len);
+                        return;
+                    }
+                    trace_alsa_xrun_out();
+                    continue;
+
+                case -ESTRPIPE:
+                    /* stream is suspended and waiting for an
+                       application recovery */
+                    if (alsa_resume (alsa->handle)) {
+                        alsa_logerr (written, "Failed to write %d frames\n",
+                                     len);
+                        return;
+                    }
+                    trace_alsa_resume_out();
+                    continue;
+
+                case -EAGAIN:
+                    return;
+
+                default:
+                    alsa_logerr (written, "Failed to write %d frames from %p\n",
+                                 len, src);
+                    return;
+                }
+            }
+
+            alsa->wpos = (alsa->wpos + written) % hw->samples;
+            alsa->pending -= written;
+            len -= written;
+        }
+    }
+}
+
+static int alsa_run_out (HWVoiceOut *hw, int live)
+{
+    ALSAVoiceOut *alsa = (ALSAVoiceOut *) hw;
+    int decr;
+    snd_pcm_sframes_t avail;
+
+    avail = alsa_get_avail (alsa->handle);
+    if (avail < 0) {
+        dolog ("Could not get number of available playback frames\n");
+        return 0;
+    }
+
+    decr = audio_MIN (live, avail);
+    decr = audio_pcm_hw_clip_out (hw, alsa->pcm_buf, decr, alsa->pending);
+    alsa->pending += decr;
+    alsa_write_pending (alsa);
+    return decr;
 }

 static void alsa_fini_out (HWVoiceOut *hw)
@@ -674,6 +710,9 @@ static void alsa_fini_out (HWVoiceOut *hw)

    ldebug ("alsa_fini\n");
    alsa_anal_close (&alsa->handle, &alsa->pollhlp);
+
+    g_free(alsa->pcm_buf);
+    alsa->pcm_buf = NULL;
 }

 static int alsa_init_out(HWVoiceOut *hw, struct audsettings *as,
@@ -702,7 +741,14 @@ static int alsa_init_out(HWVoiceOut *hw, struct audsettings *as,
    audio_pcm_init_info (&hw->info, &obt_as);
    hw->samples = obt.samples;

-    alsa->pollhlp.s = hw->s;
+    alsa->pcm_buf = audio_calloc(__func__, obt.samples, 1 << hw->info.shift);
+    if (!alsa->pcm_buf) {
+        dolog ("Could not allocate DAC buffer (%d samples, each %d bytes)\n",
+               hw->samples, 1 << hw->info.shift);
+        alsa_anal_close1 (&handle);
+        return -1;
+    }
+
    alsa->handle = handle;
    alsa->dev = dev;
    return 0;
@@ -741,28 +787,34 @@ static int alsa_voice_ctl (snd_pcm_t *handle, const char *typ, int ctl)
    return 0;
 }

-static void alsa_enable_out(HWVoiceOut *hw, bool enable)
+static int alsa_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
    ALSAVoiceOut *alsa = (ALSAVoiceOut *) hw;
    AudiodevAlsaPerDirectionOptions *apdo = alsa->dev->u.alsa.out;

-    if (enable) {
-        bool poll_mode = apdo->try_poll;
+    switch (cmd) {
+    case VOICE_ENABLE:
+        {
+            bool poll_mode = apdo->try_poll;

-        ldebug("enabling voice\n");
-        if (poll_mode && alsa_poll_out(hw)) {
-            poll_mode = 0;
+            ldebug ("enabling voice\n");
+            if (poll_mode && alsa_poll_out (hw)) {
+                poll_mode = 0;
+            }
+            hw->poll_mode = poll_mode;
+            return alsa_voice_ctl (alsa->handle, "playback", VOICE_CTL_PREPARE);
        }
-        hw->poll_mode = poll_mode;
-        alsa_voice_ctl(alsa->handle, "playback", VOICE_CTL_PREPARE);
-    } else {
-        ldebug("disabling voice\n");
+
+    case VOICE_DISABLE:
+        ldebug ("disabling voice\n");
        if (hw->poll_mode) {
            hw->poll_mode = 0;
-            alsa_fini_poll(&alsa->pollhlp);
+            alsa_fini_poll (&alsa->pollhlp);
        }
-        alsa_voice_ctl(alsa->handle, "playback", VOICE_CTL_PAUSE);
+        return alsa_voice_ctl (alsa->handle, "playback", VOICE_CTL_PAUSE);
    }
+
+    return -1;
 }

 static int alsa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
@@ -790,7 +842,14 @@ static int alsa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    audio_pcm_init_info (&hw->info, &obt_as);
    hw->samples = obt.samples;

-    alsa->pollhlp.s = hw->s;
+    alsa->pcm_buf = audio_calloc(__func__, hw->samples, 1 << hw->info.shift);
+    if (!alsa->pcm_buf) {
+        dolog ("Could not allocate ADC buffer (%d samples, each %d bytes)\n",
+               hw->samples, 1 << hw->info.shift);
+        alsa_anal_close1 (&handle);
+        return -1;
+    }
+
    alsa->handle = handle;
    alsa->dev = dev;
    return 0;
@@ -801,74 +860,165 @@ static void alsa_fini_in (HWVoiceIn *hw)
    ALSAVoiceIn *alsa = (ALSAVoiceIn *) hw;

    alsa_anal_close (&alsa->handle, &alsa->pollhlp);
+
+    g_free(alsa->pcm_buf);
+    alsa->pcm_buf = NULL;
 }

-static size_t alsa_read(HWVoiceIn *hw, void *buf, size_t len)
+static int alsa_run_in (HWVoiceIn *hw)
 {
    ALSAVoiceIn *alsa = (ALSAVoiceIn *) hw;
-    size_t pos = 0;
+    int hwshift = hw->info.shift;
+    int i;
+    int live = audio_pcm_hw_get_live_in (hw);
+    int dead = hw->samples - live;
+    int decr;
+    struct {
+        int add;
+        int len;
+    } bufs[2] = {
+        { .add = hw->wpos, .len = 0 },
+        { .add = 0,        .len = 0 }
+    };
+    snd_pcm_sframes_t avail;
+    snd_pcm_uframes_t read_samples = 0;

-    while (len) {
-        void *dst = advance(buf, pos);
-        snd_pcm_sframes_t nread;
-
-        nread = snd_pcm_readi(
-            alsa->handle, dst, len / hw->info.bytes_per_frame);
-
-        if (nread <= 0) {
-            switch (nread) {
-            case 0:
-                trace_alsa_read_zero(len);
-                return pos;
-
-            case -EPIPE:
-                if (alsa_recover(alsa->handle)) {
-                    alsa_logerr(nread, "Failed to read %zu frames\n", len);
-                    return pos;
-                }
-                trace_alsa_xrun_in();
-                continue;
-
-            case -EAGAIN:
-                return pos;
-
-            default:
-                alsa_logerr(nread, "Failed to read %zu frames to %p\n",
-                            len, dst);
-                return pos;
-            }
-        }
-
-        pos += nread * hw->info.bytes_per_frame;
-        len -= nread * hw->info.bytes_per_frame;
+    if (!dead) {
+        return 0;
    }

-    return pos;
+    avail = alsa_get_avail (alsa->handle);
+    if (avail < 0) {
+        dolog ("Could not get number of captured frames\n");
+        return 0;
+    }
+
+    if (!avail) {
+        snd_pcm_state_t state;
+
+        state = snd_pcm_state (alsa->handle);
+        switch (state) {
+        case SND_PCM_STATE_PREPARED:
+            avail = hw->samples;
+            break;
+        case SND_PCM_STATE_SUSPENDED:
+            /* stream is suspended and waiting for an application recovery */
+            if (alsa_resume (alsa->handle)) {
+                dolog ("Failed to resume suspended input stream\n");
+                return 0;
+            }
+            trace_alsa_resume_in();
+            break;
+        default:
+            trace_alsa_no_frames(state);
+            return 0;
+        }
+    }
+
+    decr = audio_MIN (dead, avail);
+    if (!decr) {
+        return 0;
+    }
+
+    if (hw->wpos + decr > hw->samples) {
+        bufs[0].len = (hw->samples - hw->wpos);
+        bufs[1].len = (decr - (hw->samples - hw->wpos));
+    }
+    else {
+        bufs[0].len = decr;
+    }
+
+    for (i = 0; i < 2; ++i) {
+        void *src;
+        struct st_sample *dst;
+        snd_pcm_sframes_t nread;
+        snd_pcm_uframes_t len;
+
+        len = bufs[i].len;
+
+        src = advance (alsa->pcm_buf, bufs[i].add << hwshift);
+        dst = hw->conv_buf + bufs[i].add;
+
+        while (len) {
+            nread = snd_pcm_readi (alsa->handle, src, len);
+
+            if (nread <= 0) {
+                switch (nread) {
+                case 0:
+                    trace_alsa_read_zero(len);
+                    goto exit;
+
+                case -EPIPE:
+                    if (alsa_recover (alsa->handle)) {
+                        alsa_logerr (nread, "Failed to read %ld frames\n", len);
+                        goto exit;
+                    }
+                    trace_alsa_xrun_in();
+                    continue;
+
+                case -EAGAIN:
+                    goto exit;
+
+                default:
+                    alsa_logerr (
+                        nread,
+                        "Failed to read %ld frames from %p\n",
+                        len,
+                        src
+                        );
+                    goto exit;
+                }
+            }
+
+            hw->conv (dst, src, nread);
+
+            src = advance (src, nread << hwshift);
+            dst += nread;
+
+            read_samples += nread;
+            len -= nread;
+        }
+    }
+
+ exit:
+    hw->wpos = (hw->wpos + read_samples) % hw->samples;
+    return read_samples;
 }

-static void alsa_enable_in(HWVoiceIn *hw, bool enable)
+static int alsa_read (SWVoiceIn *sw, void *buf, int size)
+{
+    return audio_pcm_sw_read (sw, buf, size);
+}
+
+static int alsa_ctl_in (HWVoiceIn *hw, int cmd, ...)
 {
    ALSAVoiceIn *alsa = (ALSAVoiceIn *) hw;
    AudiodevAlsaPerDirectionOptions *apdo = alsa->dev->u.alsa.in;

-    if (enable) {
-        bool poll_mode = apdo->try_poll;
+    switch (cmd) {
+    case VOICE_ENABLE:
+        {
+            bool poll_mode = apdo->try_poll;

-        ldebug("enabling voice\n");
-        if (poll_mode && alsa_poll_in(hw)) {
-            poll_mode = 0;
+            ldebug ("enabling voice\n");
+            if (poll_mode && alsa_poll_in (hw)) {
+                poll_mode = 0;
+            }
+            hw->poll_mode = poll_mode;
+
+            return alsa_voice_ctl (alsa->handle, "capture", VOICE_CTL_START);
        }
-        hw->poll_mode = poll_mode;

-        alsa_voice_ctl(alsa->handle, "capture", VOICE_CTL_START);
-    } else {
+    case VOICE_DISABLE:
        ldebug ("disabling voice\n");
        if (hw->poll_mode) {
            hw->poll_mode = 0;
-            alsa_fini_poll(&alsa->pollhlp);
+            alsa_fini_poll (&alsa->pollhlp);
        }
-        alsa_voice_ctl(alsa->handle, "capture", VOICE_CTL_PAUSE);
+        return alsa_voice_ctl (alsa->handle, "capture", VOICE_CTL_PAUSE);
    }
+
+    return -1;
 }

 static void alsa_init_per_direction(AudiodevAlsaPerDirectionOptions *apdo)
@@ -922,14 +1072,15 @@ static void alsa_audio_fini (void *opaque)
 static struct audio_pcm_ops alsa_pcm_ops = {
    .init_out = alsa_init_out,
    .fini_out = alsa_fini_out,
+    .run_out  = alsa_run_out,
    .write    = alsa_write,
-    .run_buffer_out = audio_generic_run_buffer_out,
-    .enable_out = alsa_enable_out,
+    .ctl_out  = alsa_ctl_out,

    .init_in  = alsa_init_in,
    .fini_in  = alsa_fini_in,
+    .run_in   = alsa_run_in,
    .read     = alsa_read,
-    .enable_in = alsa_enable_in,
+    .ctl_in   = alsa_ctl_in,
 };

 static struct audio_driver alsa_audio_driver = {
@@ -27,7 +27,6 @@

 #include "qemu/queue.h"
 #include "qapi/qapi-types-audio.h"
-#include "hw/qdev-properties.h"

 typedef void (*audio_callback_fn) (void *opaque, int avail);

@@ -79,10 +78,8 @@ typedef struct SWVoiceOut SWVoiceOut;
 typedef struct CaptureVoiceOut CaptureVoiceOut;
 typedef struct SWVoiceIn SWVoiceIn;

-typedef struct AudioState AudioState;
 typedef struct QEMUSoundCard {
    char *name;
-    AudioState *state;
    QLIST_ENTRY (QEMUSoundCard) entries;
 } QEMUSoundCard;

@@ -95,8 +92,7 @@ void AUD_log (const char *cap, const char *fmt, ...) GCC_FMT_ATTR(2, 3);

 void AUD_register_card (const char *name, QEMUSoundCard *card);
 void AUD_remove_card (QEMUSoundCard *card);
-CaptureVoiceOut *AUD_add_capture(
-    AudioState *s,
+CaptureVoiceOut *AUD_add_capture (
    struct audsettings *as,
    struct audio_capture_ops *ops,
    void *opaque
@@ -113,7 +109,7 @@ SWVoiceOut *AUD_open_out (
    );

 void AUD_close_out (QEMUSoundCard *card, SWVoiceOut *sw);
-size_t AUD_write (SWVoiceOut *sw, void *pcm_buf, size_t size);
+int  AUD_write (SWVoiceOut *sw, void *pcm_buf, int size);
 int  AUD_get_buffer_size_out (SWVoiceOut *sw);
 void AUD_set_active_out (SWVoiceOut *sw, int on);
 int  AUD_is_active_out (SWVoiceOut *sw);
@@ -124,16 +120,6 @@ uint64_t AUD_get_elapsed_usec_out (SWVoiceOut *sw, QEMUAudioTimeStamp *ts);
 void AUD_set_volume_out (SWVoiceOut *sw, int mute, uint8_t lvol, uint8_t rvol);
 void AUD_set_volume_in (SWVoiceIn *sw, int mute, uint8_t lvol, uint8_t rvol);

-#define AUDIO_MAX_CHANNELS 16
-typedef struct Volume {
-    bool mute;
-    int channels;
-    uint8_t vol[AUDIO_MAX_CHANNELS];
-} Volume;
-
-void audio_set_volume_out(SWVoiceOut *sw, Volume *vol);
-void audio_set_volume_in(SWVoiceIn *sw, Volume *vol);
-
 SWVoiceIn *AUD_open_in (
    QEMUSoundCard *card,
    SWVoiceIn *sw,
@@ -144,7 +130,7 @@ SWVoiceIn *AUD_open_in (
    );

 void AUD_close_in (QEMUSoundCard *card, SWVoiceIn *sw);
-size_t AUD_read (SWVoiceIn *sw, void *pcm_buf, size_t size);
+int  AUD_read (SWVoiceIn *sw, void *pcm_buf, int size);
 void AUD_set_active_in (SWVoiceIn *sw, int on);
 int  AUD_is_active_in (SWVoiceIn *sw);

@@ -157,8 +143,25 @@ static inline void *advance (void *p, int incr)
    return (d + incr);
 }

-int wav_start_capture(AudioState *state, CaptureState *s, const char *path,
-                      int freq, int bits, int nchannels);
+#ifdef __GNUC__
+#define audio_MIN(a, b) ( __extension__ ({      \
+    __typeof (a) ta = a;                        \
+    __typeof (b) tb = b;                        \
+    ((ta)>(tb)?(tb):(ta));                      \
+}))
+
+#define audio_MAX(a, b) ( __extension__ ({      \
+    __typeof (a) ta = a;                        \
+    __typeof (b) tb = b;                        \
+    ((ta)<(tb)?(tb):(ta));                      \
+}))
+#else
+#define audio_MIN(a, b) ((a)>(b)?(b):(a))
+#define audio_MAX(a, b) ((a)<(b)?(b):(a))
+#endif
+
+int wav_start_capture (CaptureState *s, const char *path, int freq,
+                       int bits, int nchannels);

 bool audio_is_cleaning_up(void);
 void audio_cleanup(void);
@@ -172,10 +175,4 @@ void audio_parse_option(const char *opt);
 void audio_init_audiodevs(void);
 void audio_legacy_help(void);

-AudioState *audio_state_by_name(const char *name);
-const char *audio_get_id(QEMUSoundCard *card);
-
-#define DEFINE_AUDIO_PROPERTIES(_s, _f)         \
-    DEFINE_PROP_AUDIODEV("audiodev", _s, _f)
-
 #endif /* QEMU_AUDIO_H */
@@ -40,74 +40,66 @@ struct audio_callback {

 struct audio_pcm_info {
    int bits;
-    bool is_signed;
-    bool is_float;
+    int sign;
    int freq;
    int nchannels;
-    int bytes_per_frame;
+    int align;
+    int shift;
    int bytes_per_second;
    int swap_endianness;
 };

-typedef struct AudioState AudioState;
 typedef struct SWVoiceCap SWVoiceCap;

-typedef struct STSampleBuffer {
-    size_t pos, size;
-    st_sample samples[];
-} STSampleBuffer;
-
 typedef struct HWVoiceOut {
-    AudioState *s;
    int enabled;
    int poll_mode;
    int pending_disable;
    struct audio_pcm_info info;

    f_sample *clip;
+
+    int rpos;
    uint64_t ts_helper;

-    STSampleBuffer *mix_buf;
-    void *buf_emul;
-    size_t pos_emul, pending_emul, size_emul;
+    struct st_sample *mix_buf;

-    size_t samples;
+    int samples;
    QLIST_HEAD (sw_out_listhead, SWVoiceOut) sw_head;
    QLIST_HEAD (sw_cap_listhead, SWVoiceCap) cap_head;
+    int ctl_caps;
    struct audio_pcm_ops *pcm_ops;
    QLIST_ENTRY (HWVoiceOut) entries;
 } HWVoiceOut;

 typedef struct HWVoiceIn {
-    AudioState *s;
    int enabled;
    int poll_mode;
    struct audio_pcm_info info;

    t_sample *conv;

-    size_t total_samples_captured;
+    int wpos;
+    int total_samples_captured;
    uint64_t ts_helper;

-    STSampleBuffer *conv_buf;
-    void *buf_emul;
-    size_t pos_emul, pending_emul, size_emul;
+    struct st_sample *conv_buf;

-    size_t samples;
+    int samples;
    QLIST_HEAD (sw_in_listhead, SWVoiceIn) sw_head;
+    int ctl_caps;
    struct audio_pcm_ops *pcm_ops;
    QLIST_ENTRY (HWVoiceIn) entries;
 } HWVoiceIn;

 struct SWVoiceOut {
    QEMUSoundCard *card;
-    AudioState *s;
    struct audio_pcm_info info;
    t_sample *conv;
    int64_t ratio;
    struct st_sample *buf;
    void *rate;
-    size_t total_hw_samples_mixed;
+    int total_hw_samples_mixed;
    int active;
    int empty;
    HWVoiceOut *hw;
@@ -119,12 +111,11 @@ struct SWVoiceOut {

 struct SWVoiceIn {
    QEMUSoundCard *card;
-    AudioState *s;
    int active;
    struct audio_pcm_info info;
    int64_t ratio;
    void *rate;
-    size_t total_hw_samples_acquired;
+    int total_hw_samples_acquired;
    struct st_sample *buf;
    f_sample *clip;
    HWVoiceIn *hw;
@@ -146,46 +137,24 @@ struct audio_driver {
    int max_voices_in;
    int voice_size_out;
    int voice_size_in;
+    int ctl_caps;
    QLIST_ENTRY(audio_driver) next;
 };

 struct audio_pcm_ops {
-    int    (*init_out)(HWVoiceOut *hw, audsettings *as, void *drv_opaque);
-    void   (*fini_out)(HWVoiceOut *hw);
-    size_t (*write)   (HWVoiceOut *hw, void *buf, size_t size);
-    void   (*run_buffer_out)(HWVoiceOut *hw);
-    /*
-     * get a buffer that after later can be passed to put_buffer_out; optional
-     * returns the buffer, and writes it's size to size (in bytes)
-     * this is unrelated to the above buffer_size_out function
-     */
-    void  *(*get_buffer_out)(HWVoiceOut *hw, size_t *size);
-    /*
-     * put back the buffer returned by get_buffer_out; optional
-     * buf must be equal the pointer returned by get_buffer_out,
-     * size may be smaller
-     */
-    size_t (*put_buffer_out)(HWVoiceOut *hw, void *buf, size_t size);
-    void   (*enable_out)(HWVoiceOut *hw, bool enable);
-    void   (*volume_out)(HWVoiceOut *hw, Volume *vol);
+    int  (*init_out)(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque);
+    void (*fini_out)(HWVoiceOut *hw);
+    int  (*run_out) (HWVoiceOut *hw, int live);
+    int  (*write)   (SWVoiceOut *sw, void *buf, int size);
+    int  (*ctl_out) (HWVoiceOut *hw, int cmd, ...);

-    int    (*init_in) (HWVoiceIn *hw, audsettings *as, void *drv_opaque);
-    void   (*fini_in) (HWVoiceIn *hw);
-    size_t (*read)    (HWVoiceIn *hw, void *buf, size_t size);
-    void  *(*get_buffer_in)(HWVoiceIn *hw, size_t *size);
-    void   (*put_buffer_in)(HWVoiceIn *hw, void *buf, size_t size);
-    void   (*enable_in)(HWVoiceIn *hw, bool enable);
-    void   (*volume_in)(HWVoiceIn *hw, Volume *vol);
+    int  (*init_in) (HWVoiceIn *hw, struct audsettings *as, void *drv_opaque);
+    void (*fini_in) (HWVoiceIn *hw);
+    int  (*run_in)  (HWVoiceIn *hw);
+    int  (*read)    (SWVoiceIn *sw, void *buf, int size);
+    int  (*ctl_in)  (HWVoiceIn *hw, int cmd, ...);
 };

-void *audio_generic_get_buffer_in(HWVoiceIn *hw, size_t *size);
-void audio_generic_put_buffer_in(HWVoiceIn *hw, void *buf, size_t size);
-void audio_generic_run_buffer_out(HWVoiceOut *hw);
-void *audio_generic_get_buffer_out(HWVoiceOut *hw, size_t *size);
-size_t audio_generic_put_buffer_out(HWVoiceOut *hw, void *buf, size_t size);
-size_t audio_generic_write(HWVoiceOut *hw, void *buf, size_t size);
-size_t audio_generic_read(HWVoiceIn *hw, void *buf, size_t size);
-
 struct capture_callback {
    struct audio_capture_ops ops;
    void *opaque;
@@ -219,11 +188,6 @@ typedef struct AudioState {
    int nb_hw_voices_in;
    int vm_running;
    int64_t period_ticks;
-
-    bool timer_running;
-    uint64_t timer_last;
-
-    QTAILQ_ENTRY(AudioState) list;
 } AudioState;

 extern const struct mixeng_volume nominal_volume;
@@ -236,21 +200,26 @@ 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);

+int  audio_pcm_sw_write (SWVoiceOut *sw, void *buf, int len);
+int  audio_pcm_hw_get_live_in (HWVoiceIn *hw);
+
+int  audio_pcm_sw_read (SWVoiceIn *sw, void *buf, int len);
+
+int audio_pcm_hw_clip_out (HWVoiceOut *hw, void *pcm_buf,
+                           int live, int pending);
+
 int audio_bug (const char *funcname, int cond);
 void *audio_calloc (const char *funcname, int nmemb, size_t size);

-void audio_run(AudioState *s, const char *msg);
+void audio_run (const char *msg);

-typedef struct RateCtl {
-    int64_t start_ticks;
-    int64_t bytes_sent;
-} RateCtl;
+#define VOICE_ENABLE 1
+#define VOICE_DISABLE 2
+#define VOICE_VOLUME 3

-void audio_rate_start(RateCtl *rate);
-size_t audio_rate_get_bytes(struct audio_pcm_info *info, RateCtl *rate,
-                            size_t bytes_avail);
+#define VOICE_VOLUME_CAP (1 << VOICE_VOLUME)

-static inline size_t audio_ring_dist(size_t dst, size_t src, size_t len)
+static inline int audio_ring_dist (int dst, int src, int len)
 {
    return (dst >= src) ? (dst - src) : (len - src + dst);
 }
@@ -0,0 +1,173 @@
+#include "qemu/osdep.h"
+#include "audio.h"
+
+#define AUDIO_CAP "audio-pt"
+
+#include "audio_int.h"
+#include "audio_pt_int.h"
+
+static void GCC_FMT_ATTR(3, 4) logerr (struct audio_pt *pt, int err,
+                                       const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (pt->drv, fmt, ap);
+    va_end (ap);
+
+    AUD_log (NULL, "\n");
+    AUD_log (pt->drv, "Reason: %s\n", strerror (err));
+}
+
+int audio_pt_init (struct audio_pt *p, void *(*func) (void *),
+                   void *opaque, const char *drv, const char *cap)
+{
+    int err, err2;
+    const char *efunc;
+    sigset_t set, old_set;
+
+    p->drv = drv;
+
+    err = sigfillset (&set);
+    if (err) {
+        logerr(p, errno, "%s(%s): sigfillset failed", cap, __func__);
+        return -1;
+    }
+
+    err = pthread_mutex_init (&p->mutex, NULL);
+    if (err) {
+        efunc = "pthread_mutex_init";
+        goto err0;
+    }
+
+    err = pthread_cond_init (&p->cond, NULL);
+    if (err) {
+        efunc = "pthread_cond_init";
+        goto err1;
+    }
+
+    err = pthread_sigmask (SIG_BLOCK, &set, &old_set);
+    if (err) {
+        efunc = "pthread_sigmask";
+        goto err2;
+    }
+
+    err = pthread_create (&p->thread, NULL, func, opaque);
+
+    err2 = pthread_sigmask (SIG_SETMASK, &old_set, NULL);
+    if (err2) {
+        logerr(p, err2, "%s(%s): pthread_sigmask (restore) failed",
+               cap, __func__);
+        /* We have failed to restore original signal mask, all bets are off,
+           so terminate the process */
+        exit (EXIT_FAILURE);
+    }
+
+    if (err) {
+        efunc = "pthread_create";
+        goto err2;
+    }
+
+    return 0;
+
+ err2:
+    err2 = pthread_cond_destroy (&p->cond);
+    if (err2) {
+        logerr(p, err2, "%s(%s): pthread_cond_destroy failed", cap, __func__);
+    }
+
+ err1:
+    err2 = pthread_mutex_destroy (&p->mutex);
+    if (err2) {
+        logerr(p, err2, "%s(%s): pthread_mutex_destroy failed", cap, __func__);
+    }
+
+ err0:
+    logerr(p, err, "%s(%s): %s failed", cap, __func__, efunc);
+    return -1;
+}
+
+int audio_pt_fini (struct audio_pt *p, const char *cap)
+{
+    int err, ret = 0;
+
+    err = pthread_cond_destroy (&p->cond);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_cond_destroy failed", cap, __func__);
+        ret = -1;
+    }
+
+    err = pthread_mutex_destroy (&p->mutex);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_mutex_destroy failed", cap, __func__);
+        ret = -1;
+    }
+    return ret;
+}
+
+int audio_pt_lock (struct audio_pt *p, const char *cap)
+{
+    int err;
+
+    err = pthread_mutex_lock (&p->mutex);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_mutex_lock failed", cap, __func__);
+        return -1;
+    }
+    return 0;
+}
+
+int audio_pt_unlock (struct audio_pt *p, const char *cap)
+{
+    int err;
+
+    err = pthread_mutex_unlock (&p->mutex);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_mutex_unlock failed", cap, __func__);
+        return -1;
+    }
+    return 0;
+}
+
+int audio_pt_wait (struct audio_pt *p, const char *cap)
+{
+    int err;
+
+    err = pthread_cond_wait (&p->cond, &p->mutex);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_cond_wait failed", cap, __func__);
+        return -1;
+    }
+    return 0;
+}
+
+int audio_pt_unlock_and_signal (struct audio_pt *p, const char *cap)
+{
+    int err;
+
+    err = pthread_mutex_unlock (&p->mutex);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_mutex_unlock failed", cap, __func__);
+        return -1;
+    }
+    err = pthread_cond_signal (&p->cond);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_cond_signal failed", cap, __func__);
+        return -1;
+    }
+    return 0;
+}
+
+int audio_pt_join (struct audio_pt *p, void **arg, const char *cap)
+{
+    int err;
+    void *ret;
+
+    err = pthread_join (p->thread, &ret);
+    if (err) {
+        logerr(p, err, "%s(%s): pthread_join failed", cap, __func__);
+        return -1;
+    }
+    *arg = ret;
+    return 0;
+}
@@ -0,0 +1,22 @@
+#ifndef QEMU_AUDIO_PT_INT_H
+#define QEMU_AUDIO_PT_INT_H
+
+#include <pthread.h>
+
+struct audio_pt {
+    const char *drv;
+    pthread_t thread;
+    pthread_cond_t cond;
+    pthread_mutex_t mutex;
+};
+
+int audio_pt_init (struct audio_pt *, void *(*) (void *), void *,
+                   const char *, const char *);
+int audio_pt_fini (struct audio_pt *, const char *);
+int audio_pt_lock (struct audio_pt *, const char *);
+int audio_pt_unlock (struct audio_pt *, const char *);
+int audio_pt_wait (struct audio_pt *, const char *);
+int audio_pt_unlock_and_signal (struct audio_pt *, const char *);
+int audio_pt_join (struct audio_pt *, void **, const char *);
+
+#endif /* QEMU_AUDIO_PT_INT_H */
@@ -36,9 +36,9 @@
 #define HWBUF hw->conv_buf
 #endif

-static void glue(audio_init_nb_voices_, TYPE)(AudioState *s,
-                                              struct audio_driver *drv)
+static void glue (audio_init_nb_voices_, TYPE) (struct audio_driver *drv)
 {
+    AudioState *s = &glob_audio_state;
    int max_voices = glue (drv->max_voices_, TYPE);
    int voice_size = glue (drv->voice_size_, TYPE);

@@ -71,24 +71,20 @@ static void glue(audio_init_nb_voices_, TYPE)(AudioState *s,

 static void glue (audio_pcm_hw_free_resources_, TYPE) (HW *hw)
 {
-    g_free(hw->buf_emul);
    g_free (HWBUF);
    HWBUF = NULL;
 }

-static void glue(audio_pcm_hw_alloc_resources_, TYPE)(HW *hw)
+static int glue (audio_pcm_hw_alloc_resources_, TYPE) (HW *hw)
 {
-    if (glue(audio_get_pdo_, TYPE)(hw->s->dev)->mixing_engine) {
-        size_t samples = hw->samples;
-        if (audio_bug(__func__, samples == 0)) {
-            dolog("Attempted to allocate empty buffer\n");
-        }
-
-        HWBUF = g_malloc0(sizeof(STSampleBuffer) + sizeof(st_sample) * samples);
-        HWBUF->size = samples;
-    } else {
-        HWBUF = NULL;
+    HWBUF = audio_calloc(__func__, hw->samples, sizeof(struct st_sample));
+    if (!HWBUF) {
+        dolog ("Could not allocate " NAME " buffer (%d samples)\n",
+               hw->samples);
+        return -1;
    }
+
+    return 0;
 }

 static void glue (audio_pcm_sw_free_resources_, TYPE) (SW *sw)
@@ -107,11 +103,7 @@ static int glue (audio_pcm_sw_alloc_resources_, TYPE) (SW *sw)
 {
    int samples;

-    if (!glue(audio_get_pdo_, TYPE)(sw->s->dev)->mixing_engine) {
-        return 0;
-    }
-
-    samples = ((int64_t) sw->HWBUF->size << 32) / sw->ratio;
+    samples = ((int64_t) sw->hw->samples << 32) / sw->ratio;

    sw->buf = audio_calloc(__func__, samples, sizeof(struct st_sample));
    if (!sw->buf) {
@@ -153,23 +145,15 @@ static int glue (audio_pcm_sw_init_, TYPE) (
    sw->ratio = ((int64_t) sw->info.freq << 32) / sw->hw->info.freq;
 #endif

-    if (sw->info.is_float) {
 #ifdef DAC
-        sw->conv = mixeng_conv_float[sw->info.nchannels == 2];
+    sw->conv = mixeng_conv
 #else
-        sw->clip = mixeng_clip_float[sw->info.nchannels == 2];
+    sw->clip = mixeng_clip
 #endif
-    } else {
-#ifdef DAC
-        sw->conv = mixeng_conv
-#else
-        sw->clip = mixeng_clip
-#endif
-            [sw->info.nchannels == 2]
-            [sw->info.is_signed]
-            [sw->info.swap_endianness]
-            [audio_bits_to_index(sw->info.bits)];
-    }
+        [sw->info.nchannels == 2]
+        [sw->info.sign]
+        [sw->info.swap_endianness]
+        [audio_bits_to_index (sw->info.bits)];

    sw->name = g_strdup (name);
    err = glue (audio_pcm_sw_alloc_resources_, TYPE) (sw);
@@ -199,8 +183,8 @@ static void glue (audio_pcm_hw_del_sw_, TYPE) (SW *sw)

 static void glue (audio_pcm_hw_gc_, TYPE) (HW **hwp)
 {
+    AudioState *s = &glob_audio_state;
    HW *hw = *hwp;
-    AudioState *s = hw->s;

    if (!hw->sw_head.lh_first) {
 #ifdef DAC
@@ -215,14 +199,15 @@ static void glue (audio_pcm_hw_gc_, TYPE) (HW **hwp)
    }
 }

-static HW *glue(audio_pcm_hw_find_any_, TYPE)(AudioState *s, HW *hw)
+static HW *glue (audio_pcm_hw_find_any_, TYPE) (HW *hw)
 {
+    AudioState *s = &glob_audio_state;
    return hw ? hw->entries.le_next : glue (s->hw_head_, TYPE).lh_first;
 }

-static HW *glue(audio_pcm_hw_find_any_enabled_, TYPE)(AudioState *s, HW *hw)
+static HW *glue (audio_pcm_hw_find_any_enabled_, TYPE) (HW *hw)
 {
-    while ((hw = glue(audio_pcm_hw_find_any_, TYPE)(s, hw))) {
+    while ((hw = glue (audio_pcm_hw_find_any_, TYPE) (hw))) {
        if (hw->enabled) {
            return hw;
        }
@@ -230,10 +215,12 @@ static HW *glue(audio_pcm_hw_find_any_enabled_, TYPE)(AudioState *s, HW *hw)
    return NULL;
 }

-static HW *glue(audio_pcm_hw_find_specific_, TYPE)(AudioState *s, HW *hw,
-                                                   struct audsettings *as)
+static HW *glue (audio_pcm_hw_find_specific_, TYPE) (
+    HW *hw,
+    struct audsettings *as
+    )
 {
-    while ((hw = glue(audio_pcm_hw_find_any_, TYPE)(s, hw))) {
+    while ((hw = glue (audio_pcm_hw_find_any_, TYPE) (hw))) {
        if (audio_pcm_info_eq (&hw->info, as)) {
            return hw;
        }
@@ -241,10 +228,10 @@ static HW *glue(audio_pcm_hw_find_specific_, TYPE)(AudioState *s, HW *hw,
    return NULL;
 }

-static HW *glue(audio_pcm_hw_add_new_, TYPE)(AudioState *s,
-                                             struct audsettings *as)
+static HW *glue (audio_pcm_hw_add_new_, TYPE) (struct audsettings *as)
 {
    HW *hw;
+    AudioState *s = &glob_audio_state;
    struct audio_driver *drv = s->drv;

    if (!glue (s->nb_hw_voices_, TYPE)) {
@@ -268,8 +255,8 @@ static HW *glue(audio_pcm_hw_add_new_, TYPE)(AudioState *s,
        return NULL;
    }

-    hw->s = s;
    hw->pcm_ops = drv->pcm_ops;
+    hw->ctl_caps = drv->ctl_caps;

    QLIST_INIT (&hw->sw_head);
 #ifdef DAC
@@ -280,29 +267,23 @@ static HW *glue(audio_pcm_hw_add_new_, TYPE)(AudioState *s,
    }

    if (audio_bug(__func__, hw->samples <= 0)) {
-        dolog("hw->samples=%zd\n", hw->samples);
+        dolog ("hw->samples=%d\n", hw->samples);
        goto err1;
    }

-    if (hw->info.is_float) {
 #ifdef DAC
-        hw->clip = mixeng_clip_float[hw->info.nchannels == 2];
+    hw->clip = mixeng_clip
 #else
-        hw->conv = mixeng_conv_float[hw->info.nchannels == 2];
+    hw->conv = mixeng_conv
 #endif
-    } else {
-#ifdef DAC
-        hw->clip = mixeng_clip
-#else
-        hw->conv = mixeng_conv
-#endif
-            [hw->info.nchannels == 2]
-            [hw->info.is_signed]
-            [hw->info.swap_endianness]
-            [audio_bits_to_index(hw->info.bits)];
-    }
+        [hw->info.nchannels == 2]
+        [hw->info.sign]
+        [hw->info.swap_endianness]
+        [audio_bits_to_index (hw->info.bits)];

-    glue(audio_pcm_hw_alloc_resources_, TYPE)(hw);
+    if (glue (audio_pcm_hw_alloc_resources_, TYPE) (hw)) {
+        goto err1;
+    }

    QLIST_INSERT_HEAD (&s->glue (hw_head_, TYPE), hw, entries);
    glue (s->nb_hw_voices_, TYPE) -= 1;
@@ -347,33 +328,33 @@ AudiodevPerDirectionOptions *glue(audio_get_pdo_, TYPE)(Audiodev *dev)
    abort();
 }

-static HW *glue(audio_pcm_hw_add_, TYPE)(AudioState *s, struct audsettings *as)
+static HW *glue (audio_pcm_hw_add_, TYPE) (struct audsettings *as)
 {
    HW *hw;
+    AudioState *s = &glob_audio_state;
    AudiodevPerDirectionOptions *pdo = glue(audio_get_pdo_, TYPE)(s->dev);

-    if (!pdo->mixing_engine || pdo->fixed_settings) {
-        hw = glue(audio_pcm_hw_add_new_, TYPE)(s, as);
-        if (!pdo->mixing_engine || hw) {
+    if (pdo->fixed_settings) {
+        hw = glue (audio_pcm_hw_add_new_, TYPE) (as);
+        if (hw) {
            return hw;
        }
    }

-    hw = glue(audio_pcm_hw_find_specific_, TYPE)(s, NULL, as);
+    hw = glue (audio_pcm_hw_find_specific_, TYPE) (NULL, as);
    if (hw) {
        return hw;
    }

-    hw = glue(audio_pcm_hw_add_new_, TYPE)(s, as);
+    hw = glue (audio_pcm_hw_add_new_, TYPE) (as);
    if (hw) {
        return hw;
    }

-    return glue(audio_pcm_hw_find_any_, TYPE)(s, NULL);
+    return glue (audio_pcm_hw_find_any_, TYPE) (NULL);
 }

-static SW *glue(audio_pcm_create_voice_pair_, TYPE)(
-    AudioState *s,
+static SW *glue (audio_pcm_create_voice_pair_, TYPE) (
    const char *sw_name,
    struct audsettings *as
    )
@@ -381,6 +362,7 @@ static SW *glue(audio_pcm_create_voice_pair_, TYPE)(
    SW *sw;
    HW *hw;
    struct audsettings hw_as;
+    AudioState *s = &glob_audio_state;
    AudiodevPerDirectionOptions *pdo = glue(audio_get_pdo_, TYPE)(s->dev);

    if (pdo->fixed_settings) {
@@ -396,9 +378,8 @@ static SW *glue(audio_pcm_create_voice_pair_, TYPE)(
               sw_name ? sw_name : "unknown", sizeof (*sw));
        goto err1;
    }
-    sw->s = s;

-    hw = glue(audio_pcm_hw_add_, TYPE)(s, &hw_as);
+    hw = glue (audio_pcm_hw_add_, TYPE) (&hw_as);
    if (!hw) {
        goto err2;
    }
@@ -449,8 +430,8 @@ SW *glue (AUD_open_, TYPE) (
    struct audsettings *as
    )
 {
-    AudioState *s;
-    AudiodevPerDirectionOptions *pdo;
+    AudioState *s = &glob_audio_state;
+    AudiodevPerDirectionOptions *pdo = glue(audio_get_pdo_, TYPE)(s->dev);

    if (audio_bug(__func__, !card || !name || !callback_fn || !as)) {
        dolog ("card=%p name=%p callback_fn=%p as=%p\n",
@@ -458,9 +439,6 @@ SW *glue (AUD_open_, TYPE) (
        goto fail;
    }

-    s = card->state;
-    pdo = glue(audio_get_pdo_, TYPE)(s->dev);
-
    ldebug ("open %s, freq %d, nchannels %d, fmt %d\n",
            name, as->freq, as->nchannels, as->fmt);

@@ -498,7 +476,7 @@ SW *glue (AUD_open_, TYPE) (
        }
    }
    else {
-        sw = glue(audio_pcm_create_voice_pair_, TYPE)(s, name, as);
+        sw = glue (audio_pcm_create_voice_pair_, TYPE) (name, as);
        if (!sw) {
            dolog ("Failed to create voice `%s'\n", name);
            return NULL;
@@ -43,6 +43,9 @@ typedef struct coreaudioVoiceOut {
    UInt32 audioDevicePropertyBufferFrameSize;
    AudioStreamBasicDescription outputStreamBasicDescription;
    AudioDeviceIOProcID ioprocid;
+    int live;
+    int decr;
+    int rpos;
 } coreaudioVoiceOut;

 #if MAC_OS_X_VERSION_MAX_ALLOWED >= MAC_OS_X_VERSION_10_6
@@ -394,29 +397,31 @@ static int coreaudio_unlock (coreaudioVoiceOut *core, const char *fn_name)
    return 0;
 }

-#define COREAUDIO_WRAPPER_FUNC(name, ret_type, args_decl, args) \
-    static ret_type glue(coreaudio_, name)args_decl             \
-    {                                                           \
-        coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;     \
-        ret_type ret;                                           \
-                                                                \
-        if (coreaudio_lock(core, "coreaudio_" #name)) {         \
-            return 0;                                           \
-        }                                                       \
-                                                                \
-        ret = glue(audio_generic_, name)args;                   \
-                                                                \
-        coreaudio_unlock(core, "coreaudio_" #name);             \
-        return ret;                                             \
+static int coreaudio_run_out (HWVoiceOut *hw, int live)
+{
+    int decr;
+    coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
+
+    if (coreaudio_lock (core, "coreaudio_run_out")) {
+        return 0;
    }
-COREAUDIO_WRAPPER_FUNC(get_buffer_out, void *, (HWVoiceOut *hw, size_t *size),
-                       (hw, size))
-COREAUDIO_WRAPPER_FUNC(put_buffer_out, size_t,
-                       (HWVoiceOut *hw, void *buf, size_t size),
-                       (hw, buf, size))
-COREAUDIO_WRAPPER_FUNC(write, size_t, (HWVoiceOut *hw, void *buf, size_t size),
-                       (hw, buf, size))
-#undef COREAUDIO_WRAPPER_FUNC
+
+    if (core->decr > live) {
+        ldebug ("core->decr %d live %d core->live %d\n",
+                core->decr,
+                live,
+                core->live);
+    }
+
+    decr = audio_MIN (core->decr, live);
+    core->decr -= decr;
+
+    core->live = live - decr;
+    hw->rpos = core->rpos;
+
+    coreaudio_unlock (core, "coreaudio_run_out");
+    return decr;
+}

 /* callback to feed audiooutput buffer */
 static OSStatus audioDeviceIOProc(
@@ -428,11 +433,19 @@ static OSStatus audioDeviceIOProc(
    const AudioTimeStamp* inOutputTime,
    void* hwptr)
 {
-    UInt32 frameCount, pending_frames;
-    void *out = outOutputData->mBuffers[0].mData;
+    UInt32 frame, frameCount;
+    float *out = outOutputData->mBuffers[0].mData;
    HWVoiceOut *hw = hwptr;
    coreaudioVoiceOut *core = (coreaudioVoiceOut *) hwptr;
-    size_t len;
+    int rpos, live;
+    struct st_sample *src;
+#ifndef FLOAT_MIXENG
+#ifdef RECIPROCAL
+    const float scale = 1.f / UINT_MAX;
+#else
+    const float scale = UINT_MAX;
+#endif
+#endif

    if (coreaudio_lock (core, "audioDeviceIOProc")) {
        inInputTime = 0;
@@ -440,37 +453,47 @@ static OSStatus audioDeviceIOProc(
    }

    frameCount = core->audioDevicePropertyBufferFrameSize;
-    pending_frames = hw->pending_emul / hw->info.bytes_per_frame;
+    live = core->live;

    /* if there are not enough samples, set signal and return */
-    if (pending_frames < frameCount) {
+    if (live < frameCount) {
        inInputTime = 0;
        coreaudio_unlock (core, "audioDeviceIOProc(empty)");
        return 0;
    }

-    len = frameCount * hw->info.bytes_per_frame;
-    while (len) {
-        size_t write_len;
-        ssize_t start = ((ssize_t) hw->pos_emul) - hw->pending_emul;
-        if (start < 0) {
-            start += hw->size_emul;
-        }
-        assert(start >= 0 && start < hw->size_emul);
+    rpos = core->rpos;
+    src = hw->mix_buf + rpos;

-        write_len = MIN(MIN(hw->pending_emul, len),
-                        hw->size_emul - start);
-
-        memcpy(out, hw->buf_emul + start, write_len);
-        hw->pending_emul -= write_len;
-        len -= write_len;
-        out += write_len;
+    /* fill buffer */
+    for (frame = 0; frame < frameCount; frame++) {
+#ifdef FLOAT_MIXENG
+        *out++ = src[frame].l; /* left channel */
+        *out++ = src[frame].r; /* right channel */
+#else
+#ifdef RECIPROCAL
+        *out++ = src[frame].l * scale; /* left channel */
+        *out++ = src[frame].r * scale; /* right channel */
+#else
+        *out++ = src[frame].l / scale; /* left channel */
+        *out++ = src[frame].r / scale; /* right channel */
+#endif
+#endif
    }

+    rpos = (rpos + frameCount) % hw->samples;
+    core->decr += frameCount;
+    core->rpos = rpos;
+
    coreaudio_unlock (core, "audioDeviceIOProc");
    return 0;
 }

+static int coreaudio_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
 static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
                              void *drv_opaque)
 {
@@ -482,7 +505,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
    Audiodev *dev = drv_opaque;
    AudiodevCoreaudioPerDirectionOptions *cpdo = dev->u.coreaudio.out;
    int frames;
-    struct audsettings fake_as;

    /* create mutex */
    err = pthread_mutex_init(&core->mutex, NULL);
@@ -491,9 +513,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
        return -1;
    }

-    fake_as = *as;
-    as = &fake_as;
-    as->fmt = AUDIO_FORMAT_F32;
    audio_pcm_init_info (&hw->info, as);

    status = coreaudio_get_voice(&core->outputDeviceID);
@@ -562,7 +581,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,

    /* set Samplerate */
    core->outputStreamBasicDescription.mSampleRate = (Float64) as->freq;
-
    status = coreaudio_set_streamformat(core->outputDeviceID,
                                        &core->outputStreamBasicDescription);
    if (status != kAudioHardwareNoError) {
@@ -629,12 +647,13 @@ static void coreaudio_fini_out (HWVoiceOut *hw)
    }
 }

-static void coreaudio_enable_out(HWVoiceOut *hw, bool enable)
+static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
    OSStatus status;
    coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;

-    if (enable) {
+    switch (cmd) {
+    case VOICE_ENABLE:
        /* start playback */
        if (!isPlaying(core->outputDeviceID)) {
            status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
@@ -642,7 +661,9 @@ static void coreaudio_enable_out(HWVoiceOut *hw, bool enable)
                coreaudio_logerr (status, "Could not resume playback\n");
            }
        }
-    } else {
+        break;
+
+    case VOICE_DISABLE:
        /* stop playback */
        if (!audio_is_cleaning_up()) {
            if (isPlaying(core->outputDeviceID)) {
@@ -653,7 +674,9 @@ static void coreaudio_enable_out(HWVoiceOut *hw, bool enable)
                }
            }
        }
+        break;
    }
+    return 0;
 }

 static void *coreaudio_audio_init(Audiodev *dev)
@@ -668,13 +691,9 @@ static void coreaudio_audio_fini (void *opaque)
 static struct audio_pcm_ops coreaudio_pcm_ops = {
    .init_out = coreaudio_init_out,
    .fini_out = coreaudio_fini_out,
-  /* wrapper for audio_generic_write */
+    .run_out  = coreaudio_run_out,
    .write    = coreaudio_write,
-  /* wrapper for audio_generic_get_buffer_out */
-    .get_buffer_out = coreaudio_get_buffer_out,
-  /* wrapper for audio_generic_put_buffer_out */
-    .put_buffer_out = coreaudio_put_buffer_out,
-    .enable_out = coreaudio_enable_out
+    .ctl_out  = coreaudio_ctl_out
 };

 static struct audio_driver coreaudio_audio_driver = {
@@ -29,8 +29,6 @@
 #define BUFPTR LPDIRECTSOUNDCAPTUREBUFFER
 #define FIELD dsound_capture_buffer
 #define FIELD2 dsound_capture
-#define HWVOICE HWVoiceIn
-#define DSOUNDVOICE DSoundVoiceIn
 #else
 #define NAME "playback buffer"
 #define NAME2 "DirectSound"
@@ -39,8 +37,6 @@
 #define BUFPTR LPDIRECTSOUNDBUFFER
 #define FIELD dsound_buffer
 #define FIELD2 dsound
-#define HWVOICE HWVoiceOut
-#define DSOUNDVOICE DSoundVoiceOut
 #endif

 static int glue (dsound_unlock_, TYPE) (
@@ -76,6 +72,8 @@ static int glue (dsound_lock_, TYPE) (
    )
 {
    HRESULT hr;
+    LPVOID p1 = NULL, p2 = NULL;
+    DWORD blen1 = 0, blen2 = 0;
    DWORD flag;

 #ifdef DSBTYPE_IN
@@ -83,7 +81,7 @@ static int glue (dsound_lock_, TYPE) (
 #else
    flag = entire ? DSBLOCK_ENTIREBUFFER : 0;
 #endif
-    hr = glue(IFACE, _Lock)(buf, pos, len, p1p, blen1p, p2p, blen2p, flag);
+    hr = glue(IFACE, _Lock)(buf, pos, len, &p1, &blen1, &p2, &blen2, flag);

    if (FAILED (hr)) {
 #ifndef DSBTYPE_IN
@@ -98,34 +96,34 @@ static int glue (dsound_lock_, TYPE) (
        goto fail;
    }

-    if ((p1p && *p1p && (*blen1p % info->bytes_per_frame)) ||
-        (p2p && *p2p && (*blen2p % info->bytes_per_frame))) {
-        dolog("DirectSound returned misaligned buffer %ld %ld\n",
-              *blen1p, *blen2p);
-        glue(dsound_unlock_, TYPE)(buf, *p1p, p2p ? *p2p : NULL, *blen1p,
-                                   blen2p ? *blen2p : 0);
+    if ((p1 && (blen1 & info->align)) || (p2 && (blen2 & info->align))) {
+        dolog ("DirectSound returned misaligned buffer %ld %ld\n",
+               blen1, blen2);
+        glue (dsound_unlock_, TYPE) (buf, p1, p2, blen1, blen2);
        goto fail;
    }

-    if (p1p && !*p1p && *blen1p) {
-        dolog("warning: !p1 && blen1=%ld\n", *blen1p);
-        *blen1p = 0;
+    if (!p1 && blen1) {
+        dolog ("warning: !p1 && blen1=%ld\n", blen1);
+        blen1 = 0;
    }

-    if (p2p && !*p2p && *blen2p) {
-        dolog("warning: !p2 && blen2=%ld\n", *blen2p);
-        *blen2p = 0;
+    if (!p2 && blen2) {
+        dolog ("warning: !p2 && blen2=%ld\n", blen2);
+        blen2 = 0;
    }

+    *p1p = p1;
+    *p2p = p2;
+    *blen1p = blen1;
+    *blen2p = blen2;
    return 0;

 fail:
    *p1p = NULL - 1;
+    *p2p = NULL - 1;
    *blen1p = -1;
-    if (p2p) {
-        *p2p = NULL - 1;
-        *blen2p = -1;
-    }
+    *blen2p = -1;
    return -1;
 }

@@ -244,23 +242,25 @@ static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
        goto fail0;
    }

-    ds->first_time = true;
+    ds->first_time = 1;
    obt_as.endianness = 0;
    audio_pcm_init_info (&hw->info, &obt_as);

-    if (bc.dwBufferBytes % hw->info.bytes_per_frame) {
+    if (bc.dwBufferBytes & hw->info.align) {
        dolog (
            "GetCaps returned misaligned buffer size %ld, alignment %d\n",
-            bc.dwBufferBytes, hw->info.bytes_per_frame
+            bc.dwBufferBytes, hw->info.align + 1
            );
    }
-    hw->size_emul = bc.dwBufferBytes;
-    hw->samples = bc.dwBufferBytes / hw->info.bytes_per_frame;
+    hw->samples = bc.dwBufferBytes >> hw->info.shift;
    ds->s = s;

 #ifdef DEBUG_DSOUND
    dolog ("caps %ld, desc %ld\n",
           bc.dwBufferBytes, bd.dwBufferBytes);
+
+    dolog ("bufsize %d, freq %d, chan %d, fmt %d\n",
+           hw->bufsize, settings.freq, settings.nchannels, settings.fmt);
 #endif
    return 0;

@@ -276,5 +276,3 @@ static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
 #undef BUFPTR
 #undef FIELD
 #undef FIELD2
-#undef HWVOICE
-#undef DSOUNDVOICE
@@ -53,14 +53,20 @@ typedef struct {
 typedef struct {
    HWVoiceOut hw;
    LPDIRECTSOUNDBUFFER dsound_buffer;
-    bool first_time;
+    DWORD old_pos;
+    int first_time;
    dsound *s;
+#ifdef DEBUG_DSOUND
+    DWORD old_ppos;
+    DWORD played;
+    DWORD mixed;
+#endif
 } DSoundVoiceOut;

 typedef struct {
    HWVoiceIn hw;
+    int first_time;
    LPDIRECTSOUNDCAPTUREBUFFER dsound_capture_buffer;
-    bool first_time;
    dsound *s;
 } DSoundVoiceIn;

@@ -237,6 +243,11 @@ static void GCC_FMT_ATTR (3, 4) dsound_logerr2 (
    dsound_log_hresult (hr);
 }

+static uint64_t usecs_to_bytes(struct audio_pcm_info *info, uint32_t usecs)
+{
+    return muldiv64(usecs, info->bytes_per_second, 1000000);
+}
+
 #ifdef DEBUG_DSOUND
 static void print_wave_format (WAVEFORMATEX *wfx)
 {
@@ -279,7 +290,7 @@ static int dsound_get_status_out (LPDIRECTSOUNDBUFFER dsb, DWORD *statusp,
        return -1;
    }

-    if (*statusp & DSBSTATUS_BUFFERLOST) {
+    if (*statusp & DSERR_BUFFERLOST) {
        dsound_restore_out(dsb, s);
        return -1;
    }
@@ -301,6 +312,33 @@ static int dsound_get_status_in (LPDIRECTSOUNDCAPTUREBUFFER dscb,
    return 0;
 }

+static void dsound_write_sample (HWVoiceOut *hw, uint8_t *dst, int dst_len)
+{
+    int src_len1 = dst_len;
+    int src_len2 = 0;
+    int pos = hw->rpos + dst_len;
+    struct st_sample *src1 = hw->mix_buf + hw->rpos;
+    struct st_sample *src2 = NULL;
+
+    if (pos > hw->samples) {
+        src_len1 = hw->samples - hw->rpos;
+        src2 = hw->mix_buf;
+        src_len2 = dst_len - src_len1;
+        pos = src_len2;
+    }
+
+    if (src_len1) {
+        hw->clip (dst, src1, src_len1);
+    }
+
+    if (src_len2) {
+        dst = advance (dst, src_len1 << hw->info.shift);
+        hw->clip (dst, src2, src_len2);
+    }
+
+    hw->rpos = pos % hw->samples;
+}
+
 static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
                                 dsound *s)
 {
@@ -312,7 +350,7 @@ static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
        dsb,
        &hw->info,
        0,
-        hw->size_emul,
+        hw->samples << hw->info.shift,
        &p1, &p2,
        &blen1, &blen2,
        1,
@@ -322,8 +360,8 @@ static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
        return;
    }

-    len1 = blen1 / hw->info.bytes_per_frame;
-    len2 = blen2 / hw->info.bytes_per_frame;
+    len1 = blen1 >> hw->info.shift;
+    len2 = blen2 >> hw->info.shift;

 #ifdef DEBUG_DSOUND
    dolog ("clear %p,%ld,%ld %p,%ld,%ld\n",
@@ -363,7 +401,7 @@ static int dsound_open (dsound *s)
    return 0;
 }

-static void dsound_enable_out(HWVoiceOut *hw, bool enable)
+static int dsound_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
    HRESULT hr;
    DWORD status;
@@ -373,17 +411,18 @@ static void dsound_enable_out(HWVoiceOut *hw, bool enable)

    if (!dsb) {
        dolog ("Attempt to control voice without a buffer\n");
-        return;
+        return 0;
    }

-    if (enable) {
+    switch (cmd) {
+    case VOICE_ENABLE:
        if (dsound_get_status_out (dsb, &status, s)) {
-            return;
+            return -1;
        }

        if (status & DSBSTATUS_PLAYING) {
            dolog ("warning: Voice is already playing\n");
-            return;
+            return 0;
        }

        dsound_clear_sample (hw, dsb, s);
@@ -391,85 +430,170 @@ static void dsound_enable_out(HWVoiceOut *hw, bool enable)
        hr = IDirectSoundBuffer_Play (dsb, 0, 0, DSBPLAY_LOOPING);
        if (FAILED (hr)) {
            dsound_logerr (hr, "Could not start playing buffer\n");
-            return;
+            return -1;
        }
-    } else {
+        break;
+
+    case VOICE_DISABLE:
        if (dsound_get_status_out (dsb, &status, s)) {
-            return;
+            return -1;
        }

        if (status & DSBSTATUS_PLAYING) {
            hr = IDirectSoundBuffer_Stop (dsb);
            if (FAILED (hr)) {
                dsound_logerr (hr, "Could not stop playing buffer\n");
-                return;
+                return -1;
            }
        }
        else {
            dolog ("warning: Voice is not playing\n");
        }
+        break;
    }
+    return 0;
 }

-static void *dsound_get_buffer_out(HWVoiceOut *hw, size_t *size)
+static int dsound_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
+static int dsound_run_out (HWVoiceOut *hw, int live)
 {
-    DSoundVoiceOut *ds = (DSoundVoiceOut *) hw;
-    LPDIRECTSOUNDBUFFER dsb = ds->dsound_buffer;
-    HRESULT hr;
-    DWORD ppos, wpos, act_size;
-    size_t req_size;
    int err;
-    void *ret;
-
-    hr = IDirectSoundBuffer_GetCurrentPosition(
-        dsb, &ppos, ds->first_time ? &wpos : NULL);
-    if (FAILED(hr)) {
-        dsound_logerr(hr, "Could not get playback buffer position\n");
-        *size = 0;
-        return NULL;
-    }
-
-    if (ds->first_time) {
-        hw->pos_emul = wpos;
-        ds->first_time = false;
-    }
-
-    req_size = audio_ring_dist(ppos, hw->pos_emul, hw->size_emul);
-    req_size = MIN(req_size, hw->size_emul - hw->pos_emul);
-
-    if (req_size == 0) {
-        *size = 0;
-        return NULL;
-    }
-
-    err = dsound_lock_out(dsb, &hw->info, hw->pos_emul, req_size, &ret, NULL,
-                          &act_size, NULL, false, ds->s);
-    if (err) {
-        dolog("Failed to lock buffer\n");
-        *size = 0;
-        return NULL;
-    }
-
-    *size = act_size;
-    return ret;
-}
-
-static size_t dsound_put_buffer_out(HWVoiceOut *hw, void *buf, size_t len)
-{
+    HRESULT hr;
    DSoundVoiceOut *ds = (DSoundVoiceOut *) hw;
    LPDIRECTSOUNDBUFFER dsb = ds->dsound_buffer;
-    int err = dsound_unlock_out(dsb, buf, NULL, len, 0);
+    int len, hwshift;
+    DWORD blen1, blen2;
+    DWORD len1, len2;
+    DWORD decr;
+    DWORD wpos, ppos, old_pos;
+    LPVOID p1, p2;
+    int bufsize;
+    dsound *s = ds->s;
+    AudiodevDsoundOptions *dso = &s->dev->u.dsound;

-    if (err) {
-        dolog("Failed to unlock buffer!!\n");
+    if (!dsb) {
+        dolog ("Attempt to run empty with playback buffer\n");
        return 0;
    }
-    hw->pos_emul = (hw->pos_emul + len) % hw->size_emul;

-    return len;
+    hwshift = hw->info.shift;
+    bufsize = hw->samples << hwshift;
+
+    hr = IDirectSoundBuffer_GetCurrentPosition (
+        dsb,
+        &ppos,
+        ds->first_time ? &wpos : NULL
+        );
+    if (FAILED (hr)) {
+        dsound_logerr (hr, "Could not get playback buffer position\n");
+        return 0;
+    }
+
+    len = live << hwshift;
+
+    if (ds->first_time) {
+        if (dso->latency) {
+            DWORD cur_blat;
+
+            cur_blat = audio_ring_dist (wpos, ppos, bufsize);
+            ds->first_time = 0;
+            old_pos = wpos;
+            old_pos +=
+                usecs_to_bytes(&hw->info, dso->latency) - cur_blat;
+            old_pos %= bufsize;
+            old_pos &= ~hw->info.align;
+        }
+        else {
+            old_pos = wpos;
+        }
+#ifdef DEBUG_DSOUND
+        ds->played = 0;
+        ds->mixed = 0;
+#endif
+    }
+    else {
+        if (ds->old_pos == ppos) {
+#ifdef DEBUG_DSOUND
+            dolog ("old_pos == ppos\n");
+#endif
+            return 0;
+        }
+
+#ifdef DEBUG_DSOUND
+        ds->played += audio_ring_dist (ds->old_pos, ppos, hw->bufsize);
+#endif
+        old_pos = ds->old_pos;
+    }
+
+    if ((old_pos < ppos) && ((old_pos + len) > ppos)) {
+        len = ppos - old_pos;
+    }
+    else {
+        if ((old_pos > ppos) && ((old_pos + len) > (ppos + bufsize))) {
+            len = bufsize - old_pos + ppos;
+        }
+    }
+
+    if (audio_bug(__func__, len < 0 || len > bufsize)) {
+        dolog ("len=%d bufsize=%d old_pos=%ld ppos=%ld\n",
+               len, bufsize, old_pos, ppos);
+        return 0;
+    }
+
+    len &= ~hw->info.align;
+    if (!len) {
+        return 0;
+    }
+
+#ifdef DEBUG_DSOUND
+    ds->old_ppos = ppos;
+#endif
+    err = dsound_lock_out (
+        dsb,
+        &hw->info,
+        old_pos,
+        len,
+        &p1, &p2,
+        &blen1, &blen2,
+        0,
+        s
+        );
+    if (err) {
+        return 0;
+    }
+
+    len1 = blen1 >> hwshift;
+    len2 = blen2 >> hwshift;
+    decr = len1 + len2;
+
+    if (p1 && len1) {
+        dsound_write_sample (hw, p1, len1);
+    }
+
+    if (p2 && len2) {
+        dsound_write_sample (hw, p2, len2);
+    }
+
+    dsound_unlock_out (dsb, p1, p2, blen1, blen2);
+    ds->old_pos = (old_pos + (decr << hwshift)) % bufsize;
+
+#ifdef DEBUG_DSOUND
+    ds->mixed += decr << hwshift;
+
+    dolog ("played %lu mixed %lu diff %ld sec %f\n",
+           ds->played,
+           ds->mixed,
+           ds->mixed - ds->played,
+           abs (ds->mixed - ds->played) / (double) hw->info.bytes_per_second);
+#endif
+    return decr;
 }

-static void dsound_enable_in(HWVoiceIn *hw, bool enable)
+static int dsound_ctl_in (HWVoiceIn *hw, int cmd, ...)
 {
    HRESULT hr;
    DWORD status;
@@ -478,17 +602,18 @@ static void dsound_enable_in(HWVoiceIn *hw, bool enable)

    if (!dscb) {
        dolog ("Attempt to control capture voice without a buffer\n");
-        return;
+        return -1;
    }

-    if (enable) {
+    switch (cmd) {
+    case VOICE_ENABLE:
        if (dsound_get_status_in (dscb, &status)) {
-            return;
+            return -1;
        }

        if (status & DSCBSTATUS_CAPTURING) {
            dolog ("warning: Voice is already capturing\n");
-            return;
+            return 0;
        }

        /* clear ?? */
@@ -496,80 +621,125 @@ static void dsound_enable_in(HWVoiceIn *hw, bool enable)
        hr = IDirectSoundCaptureBuffer_Start (dscb, DSCBSTART_LOOPING);
        if (FAILED (hr)) {
            dsound_logerr (hr, "Could not start capturing\n");
-            return;
+            return -1;
        }
-    } else {
+        break;
+
+    case VOICE_DISABLE:
        if (dsound_get_status_in (dscb, &status)) {
-            return;
+            return -1;
        }

        if (status & DSCBSTATUS_CAPTURING) {
            hr = IDirectSoundCaptureBuffer_Stop (dscb);
            if (FAILED (hr)) {
                dsound_logerr (hr, "Could not stop capturing\n");
-                return;
+                return -1;
            }
        }
        else {
            dolog ("warning: Voice is not capturing\n");
        }
+        break;
    }
+    return 0;
 }

-static void *dsound_get_buffer_in(HWVoiceIn *hw, size_t *size)
+static int dsound_read (SWVoiceIn *sw, void *buf, int len)
 {
+    return audio_pcm_sw_read (sw, buf, len);
+}
+
+static int dsound_run_in (HWVoiceIn *hw)
+{
+    int err;
+    HRESULT hr;
    DSoundVoiceIn *ds = (DSoundVoiceIn *) hw;
    LPDIRECTSOUNDCAPTUREBUFFER dscb = ds->dsound_capture_buffer;
-    HRESULT hr;
-    DWORD cpos, rpos, act_size;
-    size_t req_size;
-    int err;
-    void *ret;
+    int live, len, dead;
+    DWORD blen1, blen2;
+    DWORD len1, len2;
+    DWORD decr;
+    DWORD cpos, rpos;
+    LPVOID p1, p2;
+    int hwshift;
+    dsound *s = ds->s;

-    hr = IDirectSoundCaptureBuffer_GetCurrentPosition(
-        dscb, &cpos, ds->first_time ? &rpos : NULL);
-    if (FAILED(hr)) {
-        dsound_logerr(hr, "Could not get capture buffer position\n");
-        *size = 0;
-        return NULL;
+    if (!dscb) {
+        dolog ("Attempt to run without capture buffer\n");
+        return 0;
+    }
+
+    hwshift = hw->info.shift;
+
+    live = audio_pcm_hw_get_live_in (hw);
+    dead = hw->samples - live;
+    if (!dead) {
+        return 0;
+    }
+
+    hr = IDirectSoundCaptureBuffer_GetCurrentPosition (
+        dscb,
+        &cpos,
+        ds->first_time ? &rpos : NULL
+        );
+    if (FAILED (hr)) {
+        dsound_logerr (hr, "Could not get capture buffer position\n");
+        return 0;
    }

    if (ds->first_time) {
-        hw->pos_emul = rpos;
-        ds->first_time = false;
+        ds->first_time = 0;
+        if (rpos & hw->info.align) {
+            ldebug ("warning: Misaligned capture read position %ld(%d)\n",
+                    rpos, hw->info.align);
+        }
+        hw->wpos = rpos >> hwshift;
    }

-    req_size = audio_ring_dist(cpos, hw->pos_emul, hw->size_emul);
-    req_size = MIN(*size, MIN(req_size, hw->size_emul - hw->pos_emul));
-
-    if (req_size == 0) {
-        *size = 0;
-        return NULL;
+    if (cpos & hw->info.align) {
+        ldebug ("warning: Misaligned capture position %ld(%d)\n",
+                cpos, hw->info.align);
    }
+    cpos >>= hwshift;

-    err = dsound_lock_in(dscb, &hw->info, hw->pos_emul, req_size, &ret, NULL,
-                         &act_size, NULL, false, ds->s);
+    len = audio_ring_dist (cpos, hw->wpos, hw->samples);
+    if (!len) {
+        return 0;
+    }
+    len = audio_MIN (len, dead);
+
+    err = dsound_lock_in (
+        dscb,
+        &hw->info,
+        hw->wpos << hwshift,
+        len << hwshift,
+        &p1,
+        &p2,
+        &blen1,
+        &blen2,
+        0,
+        s
+        );
    if (err) {
-        dolog("Failed to lock buffer\n");
-        *size = 0;
-        return NULL;
+        return 0;
    }

-    *size = act_size;
-    return ret;
-}
+    len1 = blen1 >> hwshift;
+    len2 = blen2 >> hwshift;
+    decr = len1 + len2;

-static void dsound_put_buffer_in(HWVoiceIn *hw, void *buf, size_t len)
-{
-    DSoundVoiceIn *ds = (DSoundVoiceIn *) hw;
-    LPDIRECTSOUNDCAPTUREBUFFER dscb = ds->dsound_capture_buffer;
-    int err = dsound_unlock_in(dscb, buf, NULL, len, 0);
-
-    if (err) {
-        dolog("Failed to unlock buffer!!\n");
-        return;
+    if (p1 && len1) {
+        hw->conv (hw->conv_buf + hw->wpos, p1, len1);
    }
-    hw->pos_emul = (hw->pos_emul + len) % hw->size_emul;
+
+    if (p2 && len2) {
+        hw->conv (hw->conv_buf, p2, len2);
+    }
+
+    dsound_unlock_in (dscb, p1, p2, blen1, blen2);
+    hw->wpos = (hw->wpos + decr) % hw->samples;
+    return decr;
 }

 static void dsound_audio_fini (void *opaque)
@@ -685,17 +855,15 @@ static void *dsound_audio_init(Audiodev *dev)
 static struct audio_pcm_ops dsound_pcm_ops = {
    .init_out = dsound_init_out,
    .fini_out = dsound_fini_out,
-    .write    = audio_generic_write,
-    .get_buffer_out = dsound_get_buffer_out,
-    .put_buffer_out = dsound_put_buffer_out,
-    .enable_out = dsound_enable_out,
+    .run_out  = dsound_run_out,
+    .write    = dsound_write,
+    .ctl_out  = dsound_ctl_out,

    .init_in  = dsound_init_in,
    .fini_in  = dsound_fini_in,
-    .read     = audio_generic_read,
-    .get_buffer_in = dsound_get_buffer_in,
-    .put_buffer_in = dsound_put_buffer_in,
-    .enable_in = dsound_enable_in,
+    .run_in   = dsound_run_in,
+    .read     = dsound_read,
+    .ctl_in   = dsound_ctl_in
 };

 static struct audio_driver dsound_audio_driver = {
@@ -267,76 +267,6 @@ f_sample *mixeng_clip[2][2][2][3] = {
    }
 };

-#ifdef FLOAT_MIXENG
-#define CONV_NATURAL_FLOAT(x) (x)
-#define CLIP_NATURAL_FLOAT(x) (x)
-#else
-static const float float_scale = UINT_MAX / 2.f;
-#define CONV_NATURAL_FLOAT(x) ((x) * float_scale)
-
-#ifdef RECIPROCAL
-static const float float_scale_reciprocal = 2.f / UINT_MAX;
-#define CLIP_NATURAL_FLOAT(x) ((x) * float_scale_reciprocal)
-#else
-#define CLIP_NATURAL_FLOAT(x) ((x) / float_scale)
-#endif
-#endif
-
-static void conv_natural_float_to_mono(struct st_sample *dst, const void *src,
-                                       int samples)
-{
-    float *in = (float *)src;
-
-    while (samples--) {
-        dst->r = dst->l = CONV_NATURAL_FLOAT(*in++);
-        dst++;
-    }
-}
-
-static void conv_natural_float_to_stereo(struct st_sample *dst, const void *src,
-                                         int samples)
-{
-    float *in = (float *)src;
-
-    while (samples--) {
-        dst->l = CONV_NATURAL_FLOAT(*in++);
-        dst->r = CONV_NATURAL_FLOAT(*in++);
-        dst++;
-    }
-}
-
-t_sample *mixeng_conv_float[2] = {
-    conv_natural_float_to_mono,
-    conv_natural_float_to_stereo,
-};
-
-static void clip_natural_float_from_mono(void *dst, const struct st_sample *src,
-                                         int samples)
-{
-    float *out = (float *)dst;
-
-    while (samples--) {
-        *out++ = CLIP_NATURAL_FLOAT(src->l + src->r);
-        src++;
-    }
-}
-
-static void clip_natural_float_from_stereo(
-    void *dst, const struct st_sample *src, int samples)
-{
-    float *out = (float *)dst;
-
-    while (samples--) {
-        *out++ = CLIP_NATURAL_FLOAT(src->l);
-        *out++ = CLIP_NATURAL_FLOAT(src->r);
-        src++;
-    }
-}
-
-f_sample *mixeng_clip_float[2] = {
-    clip_natural_float_from_mono,
-    clip_natural_float_from_stereo,
-};

 void audio_sample_to_uint64(void *samples, int pos,
                            uint64_t *left, uint64_t *right)
@@ -33,24 +33,18 @@ struct st_sample { mixeng_real l; mixeng_real r; };
 struct mixeng_volume { int mute; int64_t r; int64_t l; };
 struct st_sample { int64_t l; int64_t r; };
 #endif
-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 endiannes][8, 16 or 32-bits] */
 extern t_sample *mixeng_conv[2][2][2][3];
 extern f_sample *mixeng_clip[2][2][2][3];

-/* indices: [stereo] */
-extern t_sample *mixeng_conv_float[2];
-extern f_sample *mixeng_clip_float[2];
-
 void *st_rate_start (int inrate, int outrate);
-void st_rate_flow(void *opaque, st_sample *ibuf, st_sample *obuf,
-                  size_t *isamp, size_t *osamp);
-void st_rate_flow_mix(void *opaque, st_sample *ibuf, st_sample *obuf,
-                      size_t *isamp, size_t *osamp);
+void st_rate_flow (void *opaque, struct st_sample *ibuf, struct st_sample *obuf,
+                   int *isamp, int *osamp);
+void st_rate_flow_mix (void *opaque, struct st_sample *ibuf, struct st_sample *obuf,
+                       int *isamp, int *osamp);
 void st_rate_stop (void *opaque);
 void mixeng_clear (struct st_sample *buf, int len);
 void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol);
@@ -41,31 +41,32 @@ static inline mixeng_real glue (conv_, ET) (IN_T v)

 #ifdef RECIPROCAL
 #ifdef SIGNED
-    return nv * (2.f / ((mixeng_real)IN_MAX - IN_MIN));
+    return nv * (1.f / (mixeng_real) (IN_MAX - IN_MIN));
 #else
-    return (nv - HALF) * (2.f / (mixeng_real)IN_MAX);
+    return (nv - HALF) * (1.f / (mixeng_real) IN_MAX);
 #endif
 #else  /* !RECIPROCAL */
 #ifdef SIGNED
-    return nv / (((mixeng_real)IN_MAX - IN_MIN) / 2.f);
+    return nv / (mixeng_real) ((mixeng_real) IN_MAX - IN_MIN);
 #else
-    return (nv - HALF) / ((mixeng_real)IN_MAX / 2.f);
+    return (nv - HALF) / (mixeng_real) IN_MAX;
 #endif
 #endif
 }

 static inline IN_T glue (clip_, ET) (mixeng_real v)
 {
-    if (v >= 1.f) {
+    if (v >= 0.5) {
        return IN_MAX;
-    } else if (v < -1.f) {
+    }
+    else if (v < -0.5) {
        return IN_MIN;
    }

 #ifdef SIGNED
-    return ENDIAN_CONVERT((IN_T)(v * (((mixeng_real)IN_MAX - IN_MIN) / 2.f)));
+    return ENDIAN_CONVERT ((IN_T) (v * ((mixeng_real) IN_MAX - IN_MIN)));
 #else
-    return ENDIAN_CONVERT((IN_T)((v * ((mixeng_real)IN_MAX / 2.f)) + HALF));
+    return ENDIAN_CONVERT ((IN_T) ((v * IN_MAX) + HALF));
 #endif
 }

@@ -83,9 +84,10 @@ static inline int64_t glue (conv_, ET) (IN_T v)

 static inline IN_T glue (clip_, ET) (int64_t v)
 {
-    if (v >= 0x7fffffffLL) {
+    if (v >= 0x7f000000) {
        return IN_MAX;
-    } else if (v < -2147483648LL) {
+    }
+    else if (v < -2147483648LL) {
        return IN_MIN;
    }

@@ -33,27 +33,43 @@

 typedef struct NoVoiceOut {
    HWVoiceOut hw;
-    RateCtl rate;
+    int64_t old_ticks;
 } NoVoiceOut;

 typedef struct NoVoiceIn {
    HWVoiceIn hw;
-    RateCtl rate;
+    int64_t old_ticks;
 } NoVoiceIn;

-static size_t no_write(HWVoiceOut *hw, void *buf, size_t len)
+static int no_run_out (HWVoiceOut *hw, int live)
 {
    NoVoiceOut *no = (NoVoiceOut *) hw;
-    return audio_rate_get_bytes(&hw->info, &no->rate, len);
+    int decr, samples;
+    int64_t now;
+    int64_t ticks;
+    int64_t bytes;
+
+    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    ticks = now - no->old_ticks;
+    bytes = muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
+    bytes = audio_MIN(bytes, INT_MAX);
+    samples = bytes >> hw->info.shift;
+
+    no->old_ticks = now;
+    decr = audio_MIN (live, samples);
+    hw->rpos = (hw->rpos + decr) % hw->samples;
+    return decr;
+}
+
+static int no_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write(sw, buf, len);
 }

 static int no_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
 {
-    NoVoiceOut *no = (NoVoiceOut *) hw;
-
    audio_pcm_init_info (&hw->info, as);
    hw->samples = 1024;
-    audio_rate_start(&no->rate);
    return 0;
 }

@@ -62,22 +78,17 @@ static void no_fini_out (HWVoiceOut *hw)
    (void) hw;
 }

-static void no_enable_out(HWVoiceOut *hw, bool enable)
+static int no_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
-    NoVoiceOut *no = (NoVoiceOut *) hw;
-
-    if (enable) {
-        audio_rate_start(&no->rate);
-    }
+    (void) hw;
+    (void) cmd;
+    return 0;
 }

 static int no_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
 {
-    NoVoiceIn *no = (NoVoiceIn *) hw;
-
    audio_pcm_init_info (&hw->info, as);
    hw->samples = 1024;
-    audio_rate_start(&no->rate);
    return 0;
 }

@@ -86,22 +97,44 @@ static void no_fini_in (HWVoiceIn *hw)
    (void) hw;
 }

-static size_t no_read(HWVoiceIn *hw, void *buf, size_t size)
+static int no_run_in (HWVoiceIn *hw)
 {
    NoVoiceIn *no = (NoVoiceIn *) hw;
-    int64_t bytes = audio_rate_get_bytes(&hw->info, &no->rate, size);
+    int live = audio_pcm_hw_get_live_in (hw);
+    int dead = hw->samples - live;
+    int samples = 0;

-    audio_pcm_info_clear_buf(&hw->info, buf, bytes / hw->info.bytes_per_frame);
-    return bytes;
+    if (dead) {
+        int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+        int64_t ticks = now - no->old_ticks;
+        int64_t bytes =
+            muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
+
+        no->old_ticks = now;
+        bytes = audio_MIN (bytes, INT_MAX);
+        samples = bytes >> hw->info.shift;
+        samples = audio_MIN (samples, dead);
+    }
+    return samples;
 }

-static void no_enable_in(HWVoiceIn *hw, bool enable)
+static int no_read (SWVoiceIn *sw, void *buf, int size)
 {
-    NoVoiceIn *no = (NoVoiceIn *) hw;
+    /* use custom code here instead of audio_pcm_sw_read() to avoid
+     * useless resampling/mixing */
+    int samples = size >> sw->info.shift;
+    int total = sw->hw->total_samples_captured - sw->total_hw_samples_acquired;
+    int to_clear = audio_MIN (samples, total);
+    sw->total_hw_samples_acquired += total;
+    audio_pcm_info_clear_buf (&sw->info, buf, to_clear);
+    return to_clear << sw->info.shift;
+}

-    if (enable) {
-        audio_rate_start(&no->rate);
-    }
+static int no_ctl_in (HWVoiceIn *hw, int cmd, ...)
+{
+    (void) hw;
+    (void) cmd;
+    return 0;
 }

 static void *no_audio_init(Audiodev *dev)
@@ -117,14 +150,15 @@ static void no_audio_fini (void *opaque)
 static struct audio_pcm_ops no_pcm_ops = {
    .init_out = no_init_out,
    .fini_out = no_fini_out,
+    .run_out  = no_run_out,
    .write    = no_write,
-    .run_buffer_out = audio_generic_run_buffer_out,
-    .enable_out = no_enable_out,
+    .ctl_out  = no_ctl_out,

    .init_in  = no_init_in,
    .fini_in  = no_fini_in,
+    .run_in   = no_run_in,
    .read     = no_read,
-    .enable_in = no_enable_in
+    .ctl_in   = no_ctl_in
 };

 static struct audio_driver no_audio_driver = {
@@ -40,15 +40,19 @@

 typedef struct OSSVoiceOut {
    HWVoiceOut hw;
+    void *pcm_buf;
    int fd;
+    int wpos;
    int nfrags;
    int fragsize;
    int mmapped;
+    int pending;
    Audiodev *dev;
 } OSSVoiceOut;

 typedef struct OSSVoiceIn {
    HWVoiceIn hw;
+    void *pcm_buf;
    int fd;
    int nfrags;
    int fragsize;
@@ -106,28 +110,33 @@ static void oss_anal_close (int *fdp)

 static void oss_helper_poll_out (void *opaque)
 {
-    AudioState *s = opaque;
-    audio_run(s, "oss_poll_out");
+    (void) opaque;
+    audio_run ("oss_poll_out");
 }

 static void oss_helper_poll_in (void *opaque)
 {
-    AudioState *s = opaque;
-    audio_run(s, "oss_poll_in");
+    (void) opaque;
+    audio_run ("oss_poll_in");
 }

 static void oss_poll_out (HWVoiceOut *hw)
 {
    OSSVoiceOut *oss = (OSSVoiceOut *) hw;

-    qemu_set_fd_handler(oss->fd, NULL, oss_helper_poll_out, hw->s);
+    qemu_set_fd_handler (oss->fd, NULL, oss_helper_poll_out, NULL);
 }

 static void oss_poll_in (HWVoiceIn *hw)
 {
    OSSVoiceIn *oss = (OSSVoiceIn *) hw;

-    qemu_set_fd_handler(oss->fd, oss_helper_poll_in, NULL, hw->s);
+    qemu_set_fd_handler (oss->fd, oss_helper_poll_in, NULL, NULL);
+}
+
+static int oss_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
 }

 static int aud_to_ossfmt (AudioFormat fmt, int endianness)
@@ -367,96 +376,97 @@ static int oss_open(int in, struct oss_params *req, audsettings *as,
    return -1;
 }

-static size_t oss_get_available_bytes(OSSVoiceOut *oss)
+static void oss_write_pending (OSSVoiceOut *oss)
 {
-    int err;
-    struct count_info cntinfo;
-    assert(oss->mmapped);
-
-    err = ioctl(oss->fd, SNDCTL_DSP_GETOPTR, &cntinfo);
-    if (err < 0) {
-        oss_logerr(errno, "SNDCTL_DSP_GETOPTR failed\n");
-        return 0;
-    }
-
-    return audio_ring_dist(cntinfo.ptr, oss->hw.pos_emul, oss->hw.size_emul);
-}
-
-static void oss_run_buffer_out(HWVoiceOut *hw)
-{
-    OSSVoiceOut *oss = (OSSVoiceOut *)hw;
-
-    if (!oss->mmapped) {
-        audio_generic_run_buffer_out(hw);
-    }
-}
-
-static void *oss_get_buffer_out(HWVoiceOut *hw, size_t *size)
-{
-    OSSVoiceOut *oss = (OSSVoiceOut *) hw;
-    if (oss->mmapped) {
-        *size = MIN(oss_get_available_bytes(oss), hw->size_emul - hw->pos_emul);
-        return hw->buf_emul + hw->pos_emul;
-    } else {
-        return audio_generic_get_buffer_out(hw, size);
-    }
-}
-
-static size_t oss_put_buffer_out(HWVoiceOut *hw, void *buf, size_t size)
-{
-    OSSVoiceOut *oss = (OSSVoiceOut *) hw;
-    if (oss->mmapped) {
-        assert(buf == hw->buf_emul + hw->pos_emul && size < hw->size_emul);
-
-        hw->pos_emul = (hw->pos_emul + size) % hw->size_emul;
-        return size;
-    } else {
-        return audio_generic_put_buffer_out(hw, buf, size);
-    }
-}
-
-static size_t oss_write(HWVoiceOut *hw, void *buf, size_t len)
-{
-    OSSVoiceOut *oss = (OSSVoiceOut *) hw;
-    size_t pos;
+    HWVoiceOut *hw = &oss->hw;

    if (oss->mmapped) {
-        size_t total_len;
-        len = MIN(len, oss_get_available_bytes(oss));
-
-        total_len = len;
-        while (len) {
-            size_t to_copy = MIN(len, hw->size_emul - hw->pos_emul);
-            memcpy(hw->buf_emul + hw->pos_emul, buf, to_copy);
-
-            hw->pos_emul = (hw->pos_emul + to_copy) % hw->size_emul;
-            buf += to_copy;
-            len -= to_copy;
-        }
-        return total_len;
+        return;
    }

-    pos = 0;
-    while (len) {
+    while (oss->pending) {
+        int samples_written;
        ssize_t bytes_written;
-        void *pcm = advance(buf, pos);
+        int samples_till_end = hw->samples - oss->wpos;
+        int samples_to_write = audio_MIN (oss->pending, samples_till_end);
+        int bytes_to_write = samples_to_write << hw->info.shift;
+        void *pcm = advance (oss->pcm_buf, oss->wpos << hw->info.shift);

-        bytes_written = write(oss->fd, pcm, len);
+        bytes_written = write (oss->fd, pcm, bytes_to_write);
        if (bytes_written < 0) {
            if (errno != EAGAIN) {
-                oss_logerr(errno, "failed to write %zu bytes\n",
-                           len);
+                oss_logerr (errno, "failed to write %d bytes\n",
+                            bytes_to_write);
            }
-            return pos;
-        }
-
-        pos += bytes_written;
-        if (bytes_written < len) {
            break;
        }
-        len -= bytes_written;
+
+        if (bytes_written & hw->info.align) {
+            dolog ("misaligned write asked for %d, but got %zd\n",
+                   bytes_to_write, bytes_written);
+            return;
+        }
+
+        samples_written = bytes_written >> hw->info.shift;
+        oss->pending -= samples_written;
+        oss->wpos = (oss->wpos + samples_written) % hw->samples;
+        if (bytes_written - bytes_to_write) {
+            break;
+        }
    }
-    return pos;
+}
+
+static int oss_run_out (HWVoiceOut *hw, int live)
+{
+    OSSVoiceOut *oss = (OSSVoiceOut *) hw;
+    int err, decr;
+    struct audio_buf_info abinfo;
+    struct count_info cntinfo;
+    int bufsize;
+
+    bufsize = hw->samples << hw->info.shift;
+
+    if (oss->mmapped) {
+        int bytes, pos;
+
+        err = ioctl (oss->fd, SNDCTL_DSP_GETOPTR, &cntinfo);
+        if (err < 0) {
+            oss_logerr (errno, "SNDCTL_DSP_GETOPTR failed\n");
+            return 0;
+        }
+
+        pos = hw->rpos << hw->info.shift;
+        bytes = audio_ring_dist (cntinfo.ptr, pos, bufsize);
+        decr = audio_MIN (bytes >> hw->info.shift, live);
+    }
+    else {
+        err = ioctl (oss->fd, SNDCTL_DSP_GETOSPACE, &abinfo);
+        if (err < 0) {
+            oss_logerr (errno, "SNDCTL_DSP_GETOPTR failed\n");
+            return 0;
+        }
+
+        if (abinfo.bytes > bufsize) {
+            trace_oss_invalid_available_size(abinfo.bytes, bufsize);
+            abinfo.bytes = bufsize;
+        }
+
+        if (abinfo.bytes < 0) {
+            trace_oss_invalid_available_size(abinfo.bytes, bufsize);
+            return 0;
+        }
+
+        decr = audio_MIN (abinfo.bytes >> hw->info.shift, live);
+        if (!decr) {
+            return 0;
+        }
+    }
+
+    decr = audio_pcm_hw_clip_out (hw, oss->pcm_buf, decr, oss->pending);
+    oss->pending += decr;
+    oss_write_pending (oss);
+
+    return decr;
 }

 static void oss_fini_out (HWVoiceOut *hw)
@@ -467,13 +477,18 @@ static void oss_fini_out (HWVoiceOut *hw)
    ldebug ("oss_fini\n");
    oss_anal_close (&oss->fd);

-    if (oss->mmapped && hw->buf_emul) {
-        err = munmap(hw->buf_emul, hw->size_emul);
-        if (err) {
-            oss_logerr(errno, "Failed to unmap buffer %p, size %zu\n",
-                       hw->buf_emul, hw->size_emul);
+    if (oss->pcm_buf) {
+        if (oss->mmapped) {
+            err = munmap (oss->pcm_buf, hw->samples << hw->info.shift);
+            if (err) {
+                oss_logerr (errno, "Failed to unmap buffer %p, size %d\n",
+                            oss->pcm_buf, hw->samples << hw->info.shift);
+            }
        }
-        hw->buf_emul = NULL;
+        else {
+            g_free (oss->pcm_buf);
+        }
+        oss->pcm_buf = NULL;
    }
 }

@@ -515,29 +530,28 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
    oss->nfrags = obt.nfrags;
    oss->fragsize = obt.fragsize;

-    if (obt.nfrags * obt.fragsize % hw->info.bytes_per_frame) {
+    if (obt.nfrags * obt.fragsize & hw->info.align) {
        dolog ("warning: Misaligned DAC buffer, size %d, alignment %d\n",
-               obt.nfrags * obt.fragsize, hw->info.bytes_per_frame);
+               obt.nfrags * obt.fragsize, hw->info.align + 1);
    }

-    hw->samples = (obt.nfrags * obt.fragsize) / hw->info.bytes_per_frame;
+    hw->samples = (obt.nfrags * obt.fragsize) >> hw->info.shift;

    oss->mmapped = 0;
    if (oopts->has_try_mmap && oopts->try_mmap) {
-        hw->size_emul = hw->samples * hw->info.bytes_per_frame;
-        hw->buf_emul = mmap(
+        oss->pcm_buf = mmap (
            NULL,
-            hw->size_emul,
+            hw->samples << hw->info.shift,
            PROT_READ | PROT_WRITE,
            MAP_SHARED,
            fd,
            0
            );
-        if (hw->buf_emul == MAP_FAILED) {
-            oss_logerr(errno, "Failed to map %zu bytes of DAC\n",
-                       hw->size_emul);
-            hw->buf_emul = NULL;
-        } else {
+        if (oss->pcm_buf == MAP_FAILED) {
+            oss_logerr (errno, "Failed to map %d bytes of DAC\n",
+                        hw->samples << hw->info.shift);
+        }
+        else {
            int err;
            int trig = 0;
            if (ioctl (fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
@@ -557,63 +571,88 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
            }

            if (!oss->mmapped) {
-                err = munmap(hw->buf_emul, hw->size_emul);
+                err = munmap (oss->pcm_buf, hw->samples << hw->info.shift);
                if (err) {
-                    oss_logerr(errno, "Failed to unmap buffer %p size %zu\n",
-                               hw->buf_emul, hw->size_emul);
+                    oss_logerr (errno, "Failed to unmap buffer %p size %d\n",
+                                oss->pcm_buf, hw->samples << hw->info.shift);
                }
-                hw->buf_emul = NULL;
            }
        }
    }

+    if (!oss->mmapped) {
+        oss->pcm_buf = audio_calloc(__func__,
+                                    hw->samples,
+                                    1 << hw->info.shift);
+        if (!oss->pcm_buf) {
+            dolog (
+                "Could not allocate DAC buffer (%d samples, each %d bytes)\n",
+                hw->samples,
+                1 << hw->info.shift
+                );
+            oss_anal_close (&fd);
+            return -1;
+        }
+    }
+
    oss->fd = fd;
    oss->dev = dev;
    return 0;
 }

-static void oss_enable_out(HWVoiceOut *hw, bool enable)
+static int oss_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
    int trig;
    OSSVoiceOut *oss = (OSSVoiceOut *) hw;
    AudiodevOssPerDirectionOptions *opdo = oss->dev->u.oss.out;

-    if (enable) {
-        hw->poll_mode = opdo->try_poll;
+    switch (cmd) {
+    case VOICE_ENABLE:
+        {
+            bool poll_mode = opdo->try_poll;

-        ldebug("enabling voice\n");
-        if (hw->poll_mode) {
-            oss_poll_out(hw);
-        }
+            ldebug ("enabling voice\n");
+            if (poll_mode) {
+                oss_poll_out (hw);
+                poll_mode = 0;
+            }
+            hw->poll_mode = poll_mode;

-        if (!oss->mmapped) {
-            return;
-        }
+            if (!oss->mmapped) {
+                return 0;
+            }

-        audio_pcm_info_clear_buf(&hw->info, hw->buf_emul, hw->samples);
-        trig = PCM_ENABLE_OUTPUT;
-        if (ioctl(oss->fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
-            oss_logerr(errno,
-                       "SNDCTL_DSP_SETTRIGGER PCM_ENABLE_OUTPUT failed\n");
-            return;
+            audio_pcm_info_clear_buf (&hw->info, oss->pcm_buf, hw->samples);
+            trig = PCM_ENABLE_OUTPUT;
+            if (ioctl (oss->fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
+                oss_logerr (
+                    errno,
+                    "SNDCTL_DSP_SETTRIGGER PCM_ENABLE_OUTPUT failed\n"
+                    );
+                return -1;
+            }
        }
-    } else {
+        break;
+
+    case VOICE_DISABLE:
        if (hw->poll_mode) {
            qemu_set_fd_handler (oss->fd, NULL, NULL, NULL);
            hw->poll_mode = 0;
        }

        if (!oss->mmapped) {
-            return;
+            return 0;
        }

        ldebug ("disabling voice\n");
        trig = 0;
        if (ioctl (oss->fd, SNDCTL_DSP_SETTRIGGER, &trig) < 0) {
            oss_logerr (errno, "SNDCTL_DSP_SETTRIGGER 0 failed\n");
-            return;
+            return -1;
        }
+        break;
    }
+    return 0;
 }

 static int oss_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
@@ -651,12 +690,19 @@ static int oss_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    oss->nfrags = obt.nfrags;
    oss->fragsize = obt.fragsize;

-    if (obt.nfrags * obt.fragsize % hw->info.bytes_per_frame) {
+    if (obt.nfrags * obt.fragsize & hw->info.align) {
        dolog ("warning: Misaligned ADC buffer, size %d, alignment %d\n",
-               obt.nfrags * obt.fragsize, hw->info.bytes_per_frame);
+               obt.nfrags * obt.fragsize, hw->info.align + 1);
    }

-    hw->samples = (obt.nfrags * obt.fragsize) / hw->info.bytes_per_frame;
+    hw->samples = (obt.nfrags * obt.fragsize) >> hw->info.shift;
+    oss->pcm_buf = audio_calloc(__func__, hw->samples, 1 << hw->info.shift);
+    if (!oss->pcm_buf) {
+        dolog ("Could not allocate ADC buffer (%d samples, each %d bytes)\n",
+               hw->samples, 1 << hw->info.shift);
+        oss_anal_close (&fd);
+        return -1;
+    }

    oss->fd = fd;
    oss->dev = dev;
@@ -668,55 +714,111 @@ static void oss_fini_in (HWVoiceIn *hw)
    OSSVoiceIn *oss = (OSSVoiceIn *) hw;

    oss_anal_close (&oss->fd);
+
+    g_free(oss->pcm_buf);
+    oss->pcm_buf = NULL;
 }

-static size_t oss_read(HWVoiceIn *hw, void *buf, size_t len)
+static int oss_run_in (HWVoiceIn *hw)
 {
    OSSVoiceIn *oss = (OSSVoiceIn *) hw;
-    size_t pos = 0;
+    int hwshift = hw->info.shift;
+    int i;
+    int live = audio_pcm_hw_get_live_in (hw);
+    int dead = hw->samples - live;
+    size_t read_samples = 0;
+    struct {
+        int add;
+        int len;
+    } bufs[2] = {
+        { .add = hw->wpos, .len = 0 },
+        { .add = 0,        .len = 0 }
+    };

-    while (len) {
+    if (!dead) {
+        return 0;
+    }
+
+    if (hw->wpos + dead > hw->samples) {
+        bufs[0].len = (hw->samples - hw->wpos) << hwshift;
+        bufs[1].len = (dead - (hw->samples - hw->wpos)) << hwshift;
+    }
+    else {
+        bufs[0].len = dead << hwshift;
+    }
+
+    for (i = 0; i < 2; ++i) {
        ssize_t nread;

-        void *dst = advance(buf, pos);
-        nread = read(oss->fd, dst, len);
+        if (bufs[i].len) {
+            void *p = advance (oss->pcm_buf, bufs[i].add << hwshift);
+            nread = read (oss->fd, p, bufs[i].len);

-        if (nread == -1) {
-            switch (errno) {
-            case EINTR:
-            case EAGAIN:
-                break;
-            default:
-                oss_logerr(errno, "Failed to read %zu bytes of audio (to %p)\n",
-                           len, dst);
+            if (nread > 0) {
+                if (nread & hw->info.align) {
+                    dolog ("warning: Misaligned read %zd (requested %d), "
+                           "alignment %d\n", nread, bufs[i].add << hwshift,
+                           hw->info.align + 1);
+                }
+                read_samples += nread >> hwshift;
+                hw->conv (hw->conv_buf + bufs[i].add, p, nread >> hwshift);
+            }
+
+            if (bufs[i].len - nread) {
+                if (nread == -1) {
+                    switch (errno) {
+                    case EINTR:
+                    case EAGAIN:
+                        break;
+                    default:
+                        oss_logerr (
+                            errno,
+                            "Failed to read %d bytes of audio (to %p)\n",
+                            bufs[i].len, p
+                            );
+                        break;
+                    }
+                }
                break;
            }
        }
-
-        pos += nread;
-        len -= nread;
    }

-    return pos;
+    hw->wpos = (hw->wpos + read_samples) % hw->samples;
+    return read_samples;
 }

-static void oss_enable_in(HWVoiceIn *hw, bool enable)
+static int oss_read (SWVoiceIn *sw, void *buf, int size)
+{
+    return audio_pcm_sw_read (sw, buf, size);
+}
+
+static int oss_ctl_in (HWVoiceIn *hw, int cmd, ...)
 {
    OSSVoiceIn *oss = (OSSVoiceIn *) hw;
    AudiodevOssPerDirectionOptions *opdo = oss->dev->u.oss.out;

-    if (enable) {
-        hw->poll_mode = opdo->try_poll;
+    switch (cmd) {
+    case VOICE_ENABLE:
+        {
+            bool poll_mode = opdo->try_poll;

-        if (hw->poll_mode) {
-            oss_poll_in(hw);
+            if (poll_mode) {
+                oss_poll_in (hw);
+                poll_mode = 0;
+            }
+            hw->poll_mode = poll_mode;
        }
-    } else {
+        break;
+
+    case VOICE_DISABLE:
        if (hw->poll_mode) {
-            qemu_set_fd_handler (oss->fd, NULL, NULL, NULL);
            hw->poll_mode = 0;
+            qemu_set_fd_handler (oss->fd, NULL, NULL, NULL);
        }
+        break;
    }
+    return 0;
 }

 static void oss_init_per_direction(AudiodevOssPerDirectionOptions *opdo)
@@ -752,16 +854,15 @@ static void oss_audio_fini (void *opaque)
 static struct audio_pcm_ops oss_pcm_ops = {
    .init_out = oss_init_out,
    .fini_out = oss_fini_out,
+    .run_out  = oss_run_out,
    .write    = oss_write,
-    .run_buffer_out = oss_run_buffer_out,
-    .get_buffer_out = oss_get_buffer_out,
-    .put_buffer_out = oss_put_buffer_out,
-    .enable_out = oss_enable_out,
+    .ctl_out  = oss_ctl_out,

    .init_in  = oss_init_in,
    .fini_in  = oss_fini_in,
+    .run_in   = oss_run_in,
    .read     = oss_read,
-    .enable_in = oss_enable_in
+    .ctl_in   = oss_ctl_in
 };

 static struct audio_driver oss_audio_driver = {
@@ -28,7 +28,7 @@
 * Return number of samples processed.
 */
 void NAME (void *opaque, struct st_sample *ibuf, struct st_sample *obuf,
-           size_t *isamp, size_t *osamp)
+           int *isamp, int *osamp)
 {
    struct rate *rate = opaque;
    struct st_sample *istart, *iend;
@@ -41,6 +41,8 @@

 typedef struct SDLVoiceOut {
    HWVoiceOut hw;
+    int live;
+    int decr;
 } SDLVoiceOut;

 static struct SDLAudioState {
@@ -77,14 +79,6 @@ static int aud_to_sdlfmt (AudioFormat fmt)
    case AUDIO_FORMAT_U16:
        return AUDIO_U16LSB;

-    case AUDIO_FORMAT_S32:
-        return AUDIO_S32LSB;
-
-    /* no unsigned 32-bit support in SDL */
-
-    case AUDIO_FORMAT_F32:
-        return AUDIO_F32LSB;
-
    default:
        dolog ("Internal logic error: Bad audio format %d\n", fmt);
 #ifdef DEBUG_AUDIO
@@ -127,26 +121,6 @@ static int sdl_to_audfmt(int sdlfmt, AudioFormat *fmt, int *endianness)
        *fmt = AUDIO_FORMAT_U16;
        break;

-    case AUDIO_S32LSB:
-        *endianness = 0;
-        *fmt = AUDIO_FORMAT_S32;
-        break;
-
-    case AUDIO_S32MSB:
-        *endianness = 1;
-        *fmt = AUDIO_FORMAT_S32;
-        break;
-
-    case AUDIO_F32LSB:
-        *endianness = 0;
-        *fmt = AUDIO_FORMAT_F32;
-        break;
-
-    case AUDIO_F32MSB:
-        *endianness = 1;
-        *fmt = AUDIO_FORMAT_F32;
-        break;
-
    default:
        dolog ("Unrecognized SDL audio format %d\n", sdlfmt);
        return -1;
@@ -210,59 +184,67 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
    SDLVoiceOut *sdl = opaque;
    SDLAudioState *s = &glob_sdl;
    HWVoiceOut *hw = &sdl->hw;
+    int samples = len >> hw->info.shift;
+    int to_mix, decr;

-    if (s->exit) {
+    if (s->exit || !sdl->live) {
        return;
    }

-    /* dolog ("in callback samples=%zu live=%zu\n", samples, sdl->live); */
+    /* dolog ("in callback samples=%d live=%d\n", samples, sdl->live); */

-    while (hw->pending_emul && len) {
-        size_t write_len;
-        ssize_t start = ((ssize_t) hw->pos_emul) - hw->pending_emul;
-        if (start < 0) {
-            start += hw->size_emul;
-        }
-        assert(start >= 0 && start < hw->size_emul);
+    to_mix = audio_MIN(samples, sdl->live);
+    decr = to_mix;
+    while (to_mix) {
+        int chunk = audio_MIN(to_mix, hw->samples - hw->rpos);
+        struct st_sample *src = hw->mix_buf + hw->rpos;

-        write_len = MIN(MIN(hw->pending_emul, len),
-                        hw->size_emul - start);
-
-        memcpy(buf, hw->buf_emul + start, write_len);
-        hw->pending_emul -= write_len;
-        len -= write_len;
-        buf += write_len;
+        /* dolog ("in callback to_mix %d, chunk %d\n", to_mix, chunk); */
+        hw->clip(buf, src, chunk);
+        hw->rpos = (hw->rpos + chunk) % hw->samples;
+        to_mix -= chunk;
+        buf += chunk << hw->info.shift;
    }
+    samples -= decr;
+    sdl->live -= decr;
+    sdl->decr += decr;

-    /* clear remaining buffer that we couldn't fill with data */
-    if (len) {
-        memset(buf, 0, len);
+    /* dolog ("done len=%d\n", len); */
+
+    /* SDL2 does not clear the remaining buffer for us, so do it on our own */
+    if (samples) {
+        memset(buf, 0, samples << hw->info.shift);
    }
 }

-#define SDL_WRAPPER_FUNC(name, ret_type, args_decl, args, fail, unlock) \
-    static ret_type glue(sdl_, name)args_decl                           \
-    {                                                                   \
-        ret_type ret;                                                   \
-                                                                        \
-        SDL_LockAudio();                                                \
-                                                                        \
-        ret = glue(audio_generic_, name)args;                           \
-                                                                        \
-        SDL_UnlockAudio();                                              \
-        return ret;                                                     \
+static int sdl_write_out (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
+static int sdl_run_out (HWVoiceOut *hw, int live)
+{
+    int decr;
+    SDLVoiceOut *sdl = (SDLVoiceOut *) hw;
+
+    SDL_LockAudio();
+
+    if (sdl->decr > live) {
+        ldebug ("sdl->decr %d live %d sdl->live %d\n",
+                sdl->decr,
+                live,
+                sdl->live);
    }

-SDL_WRAPPER_FUNC(get_buffer_out, void *, (HWVoiceOut *hw, size_t *size),
-                 (hw, size), *size = 0, sdl_unlock)
-SDL_WRAPPER_FUNC(put_buffer_out, size_t,
-                 (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size),
-                 /*nothing*/, sdl_unlock_and_post)
-SDL_WRAPPER_FUNC(write, size_t,
-                 (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size),
-                 /*nothing*/, sdl_unlock_and_post)
+    decr = audio_MIN (sdl->decr, live);
+    sdl->decr -= decr;

-#undef SDL_WRAPPER_FUNC
+    sdl->live = live;
+
+    SDL_UnlockAudio();
+
+    return decr;
+}

 static void sdl_fini_out (HWVoiceOut *hw)
 {
@@ -313,9 +295,20 @@ static int sdl_init_out(HWVoiceOut *hw, struct audsettings *as,
    return 0;
 }

-static void sdl_enable_out(HWVoiceOut *hw, bool enable)
+static int sdl_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
-    SDL_PauseAudio(!enable);
+    (void) hw;
+
+    switch (cmd) {
+    case VOICE_ENABLE:
+        SDL_PauseAudio (0);
+        break;
+
+    case VOICE_DISABLE:
+        SDL_PauseAudio (1);
+        break;
+    }
+    return 0;
 }

 static void *sdl_audio_init(Audiodev *dev)
@@ -348,13 +341,9 @@ static void sdl_audio_fini (void *opaque)
 static struct audio_pcm_ops sdl_pcm_ops = {
    .init_out = sdl_init_out,
    .fini_out = sdl_fini_out,
-  /* wrapper for audio_generic_write */
-    .write    = sdl_write,
-  /* wrapper for audio_generic_get_buffer_out */
-    .get_buffer_out = sdl_get_buffer_out,
-  /* wrapper for audio_generic_put_buffer_out */
-    .put_buffer_out = sdl_put_buffer_out,
-    .enable_out = sdl_enable_out,
+    .run_out  = sdl_run_out,
+    .write    = sdl_write_out,
+    .ctl_out  = sdl_ctl_out,
 };

 static struct audio_driver sdl_audio_driver = {
@@ -18,6 +18,7 @@
 */

 #include "qemu/osdep.h"
+#include "hw/hw.h"
 #include "qemu/host-utils.h"
 #include "qemu/module.h"
 #include "qemu/error-report.h"
@@ -40,21 +41,27 @@
 #define LINE_IN_SAMPLES (256 * 4)
 #endif

+typedef struct SpiceRateCtl {
+    int64_t               start_ticks;
+    int64_t               bytes_sent;
+} SpiceRateCtl;
+
 typedef struct SpiceVoiceOut {
    HWVoiceOut            hw;
    SpicePlaybackInstance sin;
-    RateCtl               rate;
+    SpiceRateCtl          rate;
    int                   active;
    uint32_t              *frame;
-    uint32_t              fpos;
+    uint32_t              *fpos;
    uint32_t              fsize;
 } SpiceVoiceOut;

 typedef struct SpiceVoiceIn {
    HWVoiceIn             hw;
    SpiceRecordInstance   sin;
-    RateCtl               rate;
+    SpiceRateCtl          rate;
    int                   active;
+    uint32_t              samples[LINE_IN_SAMPLES];
 } SpiceVoiceIn;

 static const SpicePlaybackInterface playback_sif = {
@@ -84,6 +91,32 @@ static void spice_audio_fini (void *opaque)
    /* nothing */
 }

+static void rate_start (SpiceRateCtl *rate)
+{
+    memset (rate, 0, sizeof (*rate));
+    rate->start_ticks = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+}
+
+static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
+{
+    int64_t now;
+    int64_t ticks;
+    int64_t bytes;
+    int64_t samples;
+
+    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    ticks = now - rate->start_ticks;
+    bytes = muldiv64(ticks, info->bytes_per_second, NANOSECONDS_PER_SECOND);
+    samples = (bytes - rate->bytes_sent) >> info->shift;
+    if (samples < 0 || samples > 65536) {
+        error_report("Resetting rate control (%" PRId64 " samples)", samples);
+        rate_start(rate);
+        samples = 0;
+    }
+    rate->bytes_sent += samples << info->shift;
+    return samples;
+}
+
 /* playback */

 static int line_out_init(HWVoiceOut *hw, struct audsettings *as,
@@ -120,78 +153,98 @@ static void line_out_fini (HWVoiceOut *hw)
    spice_server_remove_interface (&out->sin.base);
 }

-static void *line_out_get_buffer(HWVoiceOut *hw, size_t *size)
+static int line_out_run (HWVoiceOut *hw, int live)
 {
-    SpiceVoiceOut *out = container_of(hw, SpiceVoiceOut, hw);
+    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
+    int rpos, decr;
+    int samples;

-    if (!out->frame) {
-        spice_server_playback_get_buffer(&out->sin, &out->frame, &out->fsize);
-        out->fpos = 0;
+    if (!live) {
+        return 0;
    }

-    if (out->frame) {
-        *size = audio_rate_get_bytes(
-            &hw->info, &out->rate,
-            (out->fsize - out->fpos) * hw->info.bytes_per_frame);
-    } else {
-        audio_rate_start(&out->rate);
+    decr = rate_get_samples (&hw->info, &out->rate);
+    decr = audio_MIN (live, decr);
+
+    samples = decr;
+    rpos = hw->rpos;
+    while (samples) {
+        int left_till_end_samples = hw->samples - rpos;
+        int len = audio_MIN (samples, left_till_end_samples);
+
+        if (!out->frame) {
+            spice_server_playback_get_buffer (&out->sin, &out->frame, &out->fsize);
+            out->fpos = out->frame;
+        }
+        if (out->frame) {
+            len = audio_MIN (len, out->fsize);
+            hw->clip (out->fpos, hw->mix_buf + rpos, len);
+            out->fsize -= len;
+            out->fpos  += len;
+            if (out->fsize == 0) {
+                spice_server_playback_put_samples (&out->sin, out->frame);
+                out->frame = out->fpos = NULL;
+            }
+        }
+        rpos = (rpos + len) % hw->samples;
+        samples -= len;
    }
-    return out->frame + out->fpos;
+    hw->rpos = rpos;
+    return decr;
 }

-static size_t line_out_put_buffer(HWVoiceOut *hw, void *buf, size_t size)
+static int line_out_write (SWVoiceOut *sw, void *buf, int len)
 {
-    SpiceVoiceOut *out = container_of(hw, SpiceVoiceOut, hw);
-
-    assert(buf == out->frame + out->fpos && out->fpos <= out->fsize);
-    out->fpos += size >> 2;
-
-    if (out->fpos == out->fsize) { /* buffer full */
-        spice_server_playback_put_samples(&out->sin, out->frame);
-        out->frame = NULL;
-    }
-
-    return size;
+    return audio_pcm_sw_write (sw, buf, len);
 }

-static void line_out_enable(HWVoiceOut *hw, bool enable)
+static int line_out_ctl (HWVoiceOut *hw, int cmd, ...)
 {
    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);

-    if (enable) {
+    switch (cmd) {
+    case VOICE_ENABLE:
        if (out->active) {
-            return;
+            break;
        }
        out->active = 1;
-        audio_rate_start(&out->rate);
+        rate_start (&out->rate);
        spice_server_playback_start (&out->sin);
-    } else {
+        break;
+    case VOICE_DISABLE:
        if (!out->active) {
-            return;
+            break;
        }
        out->active = 0;
        if (out->frame) {
-            memset(out->frame + out->fpos, 0, (out->fsize - out->fpos) << 2);
+            memset (out->fpos, 0, out->fsize << 2);
            spice_server_playback_put_samples (&out->sin, out->frame);
-            out->frame = NULL;
+            out->frame = out->fpos = NULL;
        }
        spice_server_playback_stop (&out->sin);
-    }
-}
-
+        break;
+    case VOICE_VOLUME:
+        {
 #if ((SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && (SPICE_INTERFACE_PLAYBACK_MINOR >= 2))
-static void line_out_volume(HWVoiceOut *hw, Volume *vol)
-{
-    SpiceVoiceOut *out = container_of(hw, SpiceVoiceOut, hw);
-    uint16_t svol[2];
+            SWVoiceOut *sw;
+            va_list ap;
+            uint16_t vol[2];

-    assert(vol->channels == 2);
-    svol[0] = vol->vol[0] * 257;
-    svol[1] = vol->vol[1] * 257;
-    spice_server_playback_set_volume(&out->sin, 2, svol);
-    spice_server_playback_set_mute(&out->sin, vol->mute);
-}
+            va_start (ap, cmd);
+            sw = va_arg (ap, SWVoiceOut *);
+            va_end (ap);
+
+            vol[0] = sw->vol.l / ((1ULL << 16) + 1);
+            vol[1] = sw->vol.r / ((1ULL << 16) + 1);
+            spice_server_playback_set_volume (&out->sin, 2, vol);
+            spice_server_playback_set_mute (&out->sin, sw->vol.mute);
 #endif
+            break;
+        }
+    }
+
+    return 0;
+}

 /* record */

@@ -228,74 +281,111 @@ static void line_in_fini (HWVoiceIn *hw)
    spice_server_remove_interface (&in->sin.base);
 }

-static size_t line_in_read(HWVoiceIn *hw, void *buf, size_t len)
+static int line_in_run (HWVoiceIn *hw)
 {
    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
-    uint64_t to_read = audio_rate_get_bytes(&hw->info, &in->rate, len) >> 2;
-    size_t ready = spice_server_record_get_samples(&in->sin, buf, to_read);
+    int num_samples;
+    int ready;
+    int len[2];
+    uint64_t delta_samp;
+    const uint32_t *samples;

-    /* XXX: do we need this? */
-    if (ready == 0) {
-        memset(buf, 0, to_read << 2);
-        ready = to_read;
+    if (!(num_samples = hw->samples - audio_pcm_hw_get_live_in (hw))) {
+        return 0;
    }

-    return ready << 2;
+    delta_samp = rate_get_samples (&hw->info, &in->rate);
+    num_samples = audio_MIN (num_samples, delta_samp);
+
+    ready = spice_server_record_get_samples (&in->sin, in->samples, num_samples);
+    samples = in->samples;
+    if (ready == 0) {
+        static const uint32_t silence[LINE_IN_SAMPLES];
+        samples = silence;
+        ready = LINE_IN_SAMPLES;
+    }
+
+    num_samples = audio_MIN (ready, num_samples);
+
+    if (hw->wpos + num_samples > hw->samples) {
+        len[0] = hw->samples - hw->wpos;
+        len[1] = num_samples - len[0];
+    } else {
+        len[0] = num_samples;
+        len[1] = 0;
+    }
+
+    hw->conv (hw->conv_buf + hw->wpos, samples, len[0]);
+
+    if (len[1]) {
+        hw->conv (hw->conv_buf, samples + len[0], len[1]);
+    }
+
+    hw->wpos = (hw->wpos + num_samples) % hw->samples;
+
+    return num_samples;
 }

-static void line_in_enable(HWVoiceIn *hw, bool enable)
+static int line_in_read (SWVoiceIn *sw, void *buf, int size)
+{
+    return audio_pcm_sw_read (sw, buf, size);
+}
+
+static int line_in_ctl (HWVoiceIn *hw, int cmd, ...)
 {
    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);

-    if (enable) {
+    switch (cmd) {
+    case VOICE_ENABLE:
        if (in->active) {
-            return;
+            break;
        }
        in->active = 1;
-        audio_rate_start(&in->rate);
+        rate_start (&in->rate);
        spice_server_record_start (&in->sin);
-    } else {
+        break;
+    case VOICE_DISABLE:
        if (!in->active) {
-            return;
+            break;
        }
        in->active = 0;
        spice_server_record_stop (&in->sin);
-    }
-}
-
+        break;
+    case VOICE_VOLUME:
+        {
 #if ((SPICE_INTERFACE_RECORD_MAJOR >= 2) && (SPICE_INTERFACE_RECORD_MINOR >= 2))
-static void line_in_volume(HWVoiceIn *hw, Volume *vol)
-{
-    SpiceVoiceIn *in = container_of(hw, SpiceVoiceIn, hw);
-    uint16_t svol[2];
+            SWVoiceIn *sw;
+            va_list ap;
+            uint16_t vol[2];

-    assert(vol->channels == 2);
-    svol[0] = vol->vol[0] * 257;
-    svol[1] = vol->vol[1] * 257;
-    spice_server_record_set_volume(&in->sin, 2, svol);
-    spice_server_record_set_mute(&in->sin, vol->mute);
-}
+            va_start (ap, cmd);
+            sw = va_arg (ap, SWVoiceIn *);
+            va_end (ap);
+
+            vol[0] = sw->vol.l / ((1ULL << 16) + 1);
+            vol[1] = sw->vol.r / ((1ULL << 16) + 1);
+            spice_server_record_set_volume (&in->sin, 2, vol);
+            spice_server_record_set_mute (&in->sin, sw->vol.mute);
 #endif
+            break;
+        }
+    }
+
+    return 0;
+}

 static struct audio_pcm_ops audio_callbacks = {
    .init_out = line_out_init,
    .fini_out = line_out_fini,
-    .write    = audio_generic_write,
-    .get_buffer_out = line_out_get_buffer,
-    .put_buffer_out = line_out_put_buffer,
-    .enable_out = line_out_enable,
-#if (SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && \
-        (SPICE_INTERFACE_PLAYBACK_MINOR >= 2)
-    .volume_out = line_out_volume,
-#endif
+    .run_out  = line_out_run,
+    .write    = line_out_write,
+    .ctl_out  = line_out_ctl,

    .init_in  = line_in_init,
    .fini_in  = line_in_fini,
+    .run_in   = line_in_run,
    .read     = line_in_read,
-    .enable_in = line_in_enable,
-#if ((SPICE_INTERFACE_RECORD_MAJOR >= 2) && (SPICE_INTERFACE_RECORD_MINOR >= 2))
-    .volume_in = line_in_volume,
-#endif
+    .ctl_in   = line_in_ctl,
 };

 static struct audio_driver spice_audio_driver = {
@@ -308,6 +398,9 @@ static struct audio_driver spice_audio_driver = {
    .max_voices_in  = 1,
    .voice_size_out = sizeof (SpiceVoiceOut),
    .voice_size_in  = sizeof (SpiceVoiceIn),
+#if ((SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && (SPICE_INTERFACE_PLAYBACK_MINOR >= 2))
+    .ctl_caps       = VOICE_VOLUME_CAP
+#endif
 };

 void qemu_spice_audio_init (void)
@@ -35,23 +35,58 @@
 typedef struct WAVVoiceOut {
    HWVoiceOut hw;
    FILE *f;
-    RateCtl rate;
+    int64_t old_ticks;
+    void *pcm_buf;
    int total_samples;
 } WAVVoiceOut;

-static size_t wav_write_out(HWVoiceOut *hw, void *buf, size_t len)
+static int wav_run_out (HWVoiceOut *hw, int live)
 {
    WAVVoiceOut *wav = (WAVVoiceOut *) hw;
-    int64_t bytes = audio_rate_get_bytes(&hw->info, &wav->rate, len);
-    assert(bytes % hw->info.bytes_per_frame == 0);
+    int rpos, decr, samples;
+    uint8_t *dst;
+    struct st_sample *src;
+    int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    int64_t ticks = now - wav->old_ticks;
+    int64_t bytes =
+        muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);

-    if (bytes && fwrite(buf, bytes, 1, wav->f) != 1) {
-        dolog("wav_write_out: fwrite of %" PRId64 " bytes failed\nReason: %s\n",
-              bytes, strerror(errno));
+    if (bytes > INT_MAX) {
+        samples = INT_MAX >> hw->info.shift;
+    }
+    else {
+        samples = bytes >> hw->info.shift;
    }

-    wav->total_samples += bytes / hw->info.bytes_per_frame;
-    return bytes;
+    wav->old_ticks = now;
+    decr = audio_MIN (live, samples);
+    samples = decr;
+    rpos = hw->rpos;
+    while (samples) {
+        int left_till_end_samples = hw->samples - rpos;
+        int convert_samples = audio_MIN (samples, left_till_end_samples);
+
+        src = hw->mix_buf + rpos;
+        dst = advance (wav->pcm_buf, rpos << hw->info.shift);
+
+        hw->clip (dst, src, convert_samples);
+        if (fwrite (dst, convert_samples << hw->info.shift, 1, wav->f) != 1) {
+            dolog ("wav_run_out: fwrite of %d bytes failed\nReaons: %s\n",
+                   convert_samples << hw->info.shift, strerror (errno));
+        }
+
+        rpos = (rpos + convert_samples) % hw->samples;
+        samples -= convert_samples;
+        wav->total_samples += convert_samples;
+    }
+
+    hw->rpos = rpos;
+    return decr;
+}
+
+static int wav_write_out (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
 }

 /* VICE code: Store number as little endian. */
@@ -107,6 +142,13 @@ static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
    audio_pcm_init_info (&hw->info, &wav_as);

    hw->samples = 1024;
+    wav->pcm_buf = audio_calloc(__func__, hw->samples, 1 << hw->info.shift);
+    if (!wav->pcm_buf) {
+        dolog ("Could not allocate buffer (%d bytes)\n",
+               hw->samples << hw->info.shift);
+        return -1;
+    }
+
    le_store (hdr + 22, hw->info.nchannels, 2);
    le_store (hdr + 24, hw->info.freq, 4);
    le_store (hdr + 28, hw->info.freq << (bits16 + stereo), 4);
@@ -116,6 +158,8 @@ static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
    if (!wav->f) {
        dolog ("Failed to open wave file `%s'\nReason: %s\n",
               wav_path, strerror(errno));
+        g_free (wav->pcm_buf);
+        wav->pcm_buf = NULL;
        return -1;
    }

@@ -124,8 +168,6 @@ static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
               strerror(errno));
        return -1;
    }
-
-    audio_rate_start(&wav->rate);
    return 0;
 }

@@ -134,7 +176,7 @@ static void wav_fini_out (HWVoiceOut *hw)
    WAVVoiceOut *wav = (WAVVoiceOut *) hw;
    uint8_t rlen[4];
    uint8_t dlen[4];
-    uint32_t datalen = wav->total_samples * hw->info.bytes_per_frame;
+    uint32_t datalen = wav->total_samples << hw->info.shift;
    uint32_t rifflen = datalen + 36;

    if (!wav->f) {
@@ -171,15 +213,16 @@ static void wav_fini_out (HWVoiceOut *hw)
               wav->f, strerror (errno));
    }
    wav->f = NULL;
+
+    g_free (wav->pcm_buf);
+    wav->pcm_buf = NULL;
 }

-static void wav_enable_out(HWVoiceOut *hw, bool enable)
+static int wav_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
-    WAVVoiceOut *wav = (WAVVoiceOut *) hw;
-
-    if (enable) {
-        audio_rate_start(&wav->rate);
-    }
+    (void) hw;
+    (void) cmd;
+    return 0;
 }

 static void *wav_audio_init(Audiodev *dev)
@@ -196,9 +239,9 @@ static void wav_audio_fini (void *opaque)
 static struct audio_pcm_ops wav_pcm_ops = {
    .init_out = wav_init_out,
    .fini_out = wav_fini_out,
+    .run_out  = wav_run_out,
    .write    = wav_write_out,
-    .run_buffer_out = audio_generic_run_buffer_out,
-    .enable_out = wav_enable_out,
+    .ctl_out  = wav_ctl_out,
 };

 static struct audio_driver wav_audio_driver = {
@@ -1,4 +1,5 @@
 #include "qemu/osdep.h"
+#include "hw/hw.h"
 #include "monitor/monitor.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
@@ -104,8 +105,8 @@ static struct capture_ops wav_capture_ops = {
    .info = wav_capture_info
 };

-int wav_start_capture(AudioState *state, CaptureState *s, const char *path,
-                      int freq, int bits, int nchannels)
+int wav_start_capture (CaptureState *s, const char *path, int freq,
+                       int bits, int nchannels)
 {
    WAVState *wav;
    uint8_t hdr[] = {
@@ -170,7 +171,7 @@ int wav_start_capture(AudioState *state, CaptureState *s, const char *path,
        goto error_free;
    }

-    cap = AUD_add_capture(state, &as, &ops, wav);
+    cap = AUD_add_capture (&as, &ops, wav);
    if (!cap) {
        error_report("Failed to add audio capture");
        goto error_free;
@@ -239,7 +239,7 @@ qauthz_list_file_init(Object *obj)

    authz->file_watch = -1;
 #ifdef CONFIG_INOTIFY1
-    authz->refresh = true;
+    authz->refresh = TRUE;
 #endif
 }

@@ -1,4 +1,4 @@
-common-obj-y += rng.o rng-egd.o rng-builtin.o
+common-obj-y += rng.o rng-egd.o
 common-obj-$(CONFIG_POSIX) += rng-random.o

 common-obj-$(CONFIG_TPM) += tpm.o
@@ -17,7 +17,3 @@ endif
 common-obj-$(call land,$(CONFIG_VHOST_USER),$(CONFIG_VIRTIO)) += vhost-user.o

 common-obj-$(CONFIG_LINUX) += hostmem-memfd.o
-
-common-obj-$(CONFIG_GIO) += dbus-vmstate.o
-dbus-vmstate.o-cflags = $(GIO_CFLAGS)
-dbus-vmstate.o-libs = $(GIO_LIBS)
@@ -23,6 +23,7 @@

 #include "qemu/osdep.h"
 #include "sysemu/cryptodev.h"
+#include "hw/boards.h"
 #include "qapi/error.h"
 #include "standard-headers/linux/virtio_crypto.h"
 #include "crypto/cipher.h"
@@ -22,6 +22,7 @@
 */

 #include "qemu/osdep.h"
+#include "hw/boards.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
@@ -152,7 +153,7 @@ cryptodev_vhost_claim_chardev(CryptoDevBackendVhostUser *s,
    return chr;
 }

-static void cryptodev_vhost_user_event(void *opaque, QEMUChrEvent event)
+static void cryptodev_vhost_user_event(void *opaque, int event)
 {
    CryptoDevBackendVhostUser *s = opaque;
    CryptoDevBackend *b = CRYPTODEV_BACKEND(s);
@@ -171,11 +172,6 @@ static void cryptodev_vhost_user_event(void *opaque, QEMUChrEvent event)
        b->ready = false;
        cryptodev_vhost_user_stop(queues, s);
        break;
-    case CHR_EVENT_BREAK:
-    case CHR_EVENT_MUX_IN:
-    case CHR_EVENT_MUX_OUT:
-        /* Ignore */
-        break;
    }
 }

@@ -23,6 +23,7 @@

 #include "qemu/osdep.h"
 #include "sysemu/cryptodev.h"
+#include "hw/boards.h"
 #include "qapi/error.h"
 #include "qapi/visitor.h"
 #include "qemu/config-file.h"
@@ -176,10 +177,19 @@ cryptodev_backend_complete(UserCreatable *uc, Error **errp)
 {
    CryptoDevBackend *backend = CRYPTODEV_BACKEND(uc);
    CryptoDevBackendClass *bc = CRYPTODEV_BACKEND_GET_CLASS(uc);
+    Error *local_err = NULL;

    if (bc->init) {
-        bc->init(backend, errp);
+        bc->init(backend, &local_err);
+        if (local_err) {
+            goto out;
+        }
    }
+
+    return;
+
+out:
+    error_propagate(errp, local_err);
 }

 void cryptodev_backend_set_used(CryptoDevBackend *backend, bool used)
@@ -1,511 +0,0 @@
-/*
- * QEMU dbus-vmstate
- *
- * Copyright (C) 2019 Red Hat Inc
- *
- * Authors:
- *  Marc-André Lureau <marcandre.lureau@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/osdep.h"
-#include "qemu/units.h"
-#include "qemu/dbus.h"
-#include "qemu/error-report.h"
-#include "qapi/error.h"
-#include "qom/object_interfaces.h"
-#include "qapi/qmp/qerror.h"
-#include "migration/vmstate.h"
-#include "trace.h"
-
-typedef struct DBusVMState DBusVMState;
-typedef struct DBusVMStateClass DBusVMStateClass;
-
-#define TYPE_DBUS_VMSTATE "dbus-vmstate"
-#define DBUS_VMSTATE(obj)                                \
-    OBJECT_CHECK(DBusVMState, (obj), TYPE_DBUS_VMSTATE)
-#define DBUS_VMSTATE_GET_CLASS(obj)                              \
-    OBJECT_GET_CLASS(DBusVMStateClass, (obj), TYPE_DBUS_VMSTATE)
-#define DBUS_VMSTATE_CLASS(klass)                                    \
-    OBJECT_CLASS_CHECK(DBusVMStateClass, (klass), TYPE_DBUS_VMSTATE)
-
-struct DBusVMStateClass {
-    ObjectClass parent_class;
-};
-
-struct DBusVMState {
-    Object parent;
-
-    GDBusConnection *bus;
-    char *dbus_addr;
-    char *id_list;
-
-    uint32_t data_size;
-    uint8_t *data;
-};
-
-static const GDBusPropertyInfo vmstate_property_info[] = {
-    { -1, (char *) "Id", (char *) "s",
-      G_DBUS_PROPERTY_INFO_FLAGS_READABLE, NULL },
-};
-
-static const GDBusPropertyInfo * const vmstate_property_info_pointers[] = {
-    &vmstate_property_info[0],
-    NULL
-};
-
-static const GDBusInterfaceInfo vmstate1_interface_info = {
-    -1,
-    (char *) "org.qemu.VMState1",
-    (GDBusMethodInfo **) NULL,
-    (GDBusSignalInfo **) NULL,
-    (GDBusPropertyInfo **) &vmstate_property_info_pointers,
-    NULL,
-};
-
-#define DBUS_VMSTATE_SIZE_LIMIT (1 * MiB)
-
-static GHashTable *
-get_id_list_set(DBusVMState *self)
-{
-    g_auto(GStrv) ids = NULL;
-    g_autoptr(GHashTable) set = NULL;
-    int i;
-
-    if (!self->id_list) {
-        return NULL;
-    }
-
-    ids = g_strsplit(self->id_list, ",", -1);
-    set = g_hash_table_new_full(g_str_hash, g_str_equal, g_free, NULL);
-    for (i = 0; ids[i]; i++) {
-        g_hash_table_add(set, ids[i]);
-        ids[i] = NULL;
-    }
-
-    return g_steal_pointer(&set);
-}
-
-static GHashTable *
-dbus_get_proxies(DBusVMState *self, GError **err)
-{
-    g_autoptr(GHashTable) proxies = NULL;
-    g_autoptr(GHashTable) ids = NULL;
-    g_auto(GStrv) names = NULL;
-    Error *error = NULL;
-    size_t i;
-
-    ids = get_id_list_set(self);
-    proxies = g_hash_table_new_full(g_str_hash, g_str_equal,
-                                    g_free, g_object_unref);
-
-    names = qemu_dbus_get_queued_owners(self->bus, "org.qemu.VMState1", &error);
-    if (!names) {
-        g_set_error(err, G_IO_ERROR, G_IO_ERROR_FAILED, "%s",
-                    error_get_pretty(error));
-        error_free(error);
-        return NULL;
-    }
-
-    for (i = 0; names[i]; i++) {
-        g_autoptr(GDBusProxy) proxy = NULL;
-        g_autoptr(GVariant) result = NULL;
-        g_autofree char *id = NULL;
-        size_t size;
-
-        proxy = g_dbus_proxy_new_sync(self->bus, G_DBUS_PROXY_FLAGS_NONE,
-                    (GDBusInterfaceInfo *) &vmstate1_interface_info,
-                    names[i],
-                    "/org/qemu/VMState1",
-                    "org.qemu.VMState1",
-                    NULL, err);
-        if (!proxy) {
-            return NULL;
-        }
-
-        result = g_dbus_proxy_get_cached_property(proxy, "Id");
-        if (!result) {
-            g_set_error_literal(err, G_IO_ERROR, G_IO_ERROR_FAILED,
-                                "VMState Id property is missing.");
-            return NULL;
-        }
-
-        id = g_variant_dup_string(result, &size);
-        if (ids && !g_hash_table_remove(ids, id)) {
-            g_clear_pointer(&id, g_free);
-            g_clear_object(&proxy);
-            continue;
-        }
-        if (size == 0 || size >= 256) {
-            g_set_error(err, G_IO_ERROR, G_IO_ERROR_FAILED,
-                        "VMState Id '%s' is invalid.", id);
-            return NULL;
-        }
-
-        if (!g_hash_table_insert(proxies, id, proxy)) {
-            g_set_error(err, G_IO_ERROR, G_IO_ERROR_FAILED,
-                        "Duplicated VMState Id '%s'", id);
-            return NULL;
-        }
-        id = NULL;
-        proxy = NULL;
-
-        g_clear_pointer(&result, g_variant_unref);
-    }
-
-    if (ids) {
-        g_autofree char **left = NULL;
-
-        left = (char **)g_hash_table_get_keys_as_array(ids, NULL);
-        if (*left) {
-            g_autofree char *leftids = g_strjoinv(",", left);
-            g_set_error(err, G_IO_ERROR, G_IO_ERROR_FAILED,
-                        "Required VMState Id are missing: %s", leftids);
-            return NULL;
-        }
-    }
-
-    return g_steal_pointer(&proxies);
-}
-
-static int
-dbus_load_state_proxy(GDBusProxy *proxy, const uint8_t *data, size_t size)
-{
-    g_autoptr(GError) err = NULL;
-    g_autoptr(GVariant) result = NULL;
-    g_autoptr(GVariant) value = NULL;
-
-    value = g_variant_new_fixed_array(G_VARIANT_TYPE_BYTE,
-                                      data, size, sizeof(char));
-    result = g_dbus_proxy_call_sync(proxy, "Load",
-                                    g_variant_new("(@ay)",
-                                                  g_steal_pointer(&value)),
-                                    G_DBUS_CALL_FLAGS_NO_AUTO_START,
-                                    -1, NULL, &err);
-    if (!result) {
-        error_report("%s: Failed to Load: %s", __func__, err->message);
-        return -1;
-    }
-
-    return 0;
-}
-
-static int dbus_vmstate_post_load(void *opaque, int version_id)
-{
-    DBusVMState *self = DBUS_VMSTATE(opaque);
-    g_autoptr(GInputStream) m = NULL;
-    g_autoptr(GDataInputStream) s = NULL;
-    g_autoptr(GError) err = NULL;
-    g_autoptr(GHashTable) proxies = NULL;
-    uint32_t nelem;
-
-    trace_dbus_vmstate_post_load(version_id);
-
-    proxies = dbus_get_proxies(self, &err);
-    if (!proxies) {
-        error_report("%s: Failed to get proxies: %s", __func__, err->message);
-        return -1;
-    }
-
-    m = g_memory_input_stream_new_from_data(self->data, self->data_size, NULL);
-    s = g_data_input_stream_new(m);
-    g_data_input_stream_set_byte_order(s, G_DATA_STREAM_BYTE_ORDER_BIG_ENDIAN);
-
-    nelem = g_data_input_stream_read_uint32(s, NULL, &err);
-    if (err) {
-        goto error;
-    }
-
-    while (nelem > 0) {
-        GDBusProxy *proxy = NULL;
-        uint32_t len;
-        gsize bytes_read, avail;
-        char id[256];
-
-        len = g_data_input_stream_read_uint32(s, NULL, &err);
-        if (err) {
-            goto error;
-        }
-        if (len >= 256) {
-            error_report("%s: Invalid DBus vmstate proxy name %u",
-                         __func__, len);
-            return -1;
-        }
-        if (!g_input_stream_read_all(G_INPUT_STREAM(s), id, len,
-                                     &bytes_read, NULL, &err)) {
-            goto error;
-        }
-        g_return_val_if_fail(bytes_read == len, -1);
-        id[len] = 0;
-
-        trace_dbus_vmstate_loading(id);
-
-        proxy = g_hash_table_lookup(proxies, id);
-        if (!proxy) {
-            error_report("%s: Failed to find proxy Id '%s'", __func__, id);
-            return -1;
-        }
-
-        len = g_data_input_stream_read_uint32(s, NULL, &err);
-        avail = g_buffered_input_stream_get_available(
-            G_BUFFERED_INPUT_STREAM(s));
-
-        if (len > DBUS_VMSTATE_SIZE_LIMIT || len > avail) {
-            error_report("%s: Invalid vmstate size: %u", __func__, len);
-            return -1;
-        }
-
-        if (dbus_load_state_proxy(proxy,
-                g_buffered_input_stream_peek_buffer(G_BUFFERED_INPUT_STREAM(s),
-                                                    NULL),
-                len) < 0) {
-            error_report("%s: Failed to restore Id '%s'", __func__, id);
-            return -1;
-        }
-
-        if (!g_seekable_seek(G_SEEKABLE(s), len, G_SEEK_CUR, NULL, &err)) {
-            goto error;
-        }
-
-        nelem -= 1;
-    }
-
-    return 0;
-
-error:
-    error_report("%s: Failed to read from stream: %s", __func__, err->message);
-    return -1;
-}
-
-static void
-dbus_save_state_proxy(gpointer key,
-                      gpointer value,
-                      gpointer user_data)
-{
-    GDataOutputStream *s = user_data;
-    const char *id = key;
-    GDBusProxy *proxy = value;
-    g_autoptr(GVariant) result = NULL;
-    g_autoptr(GVariant) child = NULL;
-    g_autoptr(GError) err = NULL;
-    const uint8_t *data;
-    gsize size;
-
-    trace_dbus_vmstate_saving(id);
-
-    result = g_dbus_proxy_call_sync(proxy, "Save",
-                                    NULL, G_DBUS_CALL_FLAGS_NO_AUTO_START,
-                                    -1, NULL, &err);
-    if (!result) {
-        error_report("%s: Failed to Save: %s", __func__, err->message);
-        return;
-    }
-
-    child = g_variant_get_child_value(result, 0);
-    data = g_variant_get_fixed_array(child, &size, sizeof(char));
-    if (!data) {
-        error_report("%s: Failed to Save: not a byte array", __func__);
-        return;
-    }
-    if (size > DBUS_VMSTATE_SIZE_LIMIT) {
-        error_report("%s: Too large vmstate data to save: %zu",
-                     __func__, (size_t)size);
-        return;
-    }
-
-    if (!g_data_output_stream_put_uint32(s, strlen(id), NULL, &err) ||
-        !g_data_output_stream_put_string(s, id, NULL, &err) ||
-        !g_data_output_stream_put_uint32(s, size, NULL, &err) ||
-        !g_output_stream_write_all(G_OUTPUT_STREAM(s),
-                                   data, size, NULL, NULL, &err)) {
-        error_report("%s: Failed to write to stream: %s",
-                     __func__, err->message);
-    }
-}
-
-static int dbus_vmstate_pre_save(void *opaque)
-{
-    DBusVMState *self = DBUS_VMSTATE(opaque);
-    g_autoptr(GOutputStream) m = NULL;
-    g_autoptr(GDataOutputStream) s = NULL;
-    g_autoptr(GHashTable) proxies = NULL;
-    g_autoptr(GError) err = NULL;
-
-    trace_dbus_vmstate_pre_save();
-
-    proxies = dbus_get_proxies(self, &err);
-    if (!proxies) {
-        error_report("%s: Failed to get proxies: %s", __func__, err->message);
-        return -1;
-    }
-
-    m = g_memory_output_stream_new_resizable();
-    s = g_data_output_stream_new(m);
-    g_data_output_stream_set_byte_order(s, G_DATA_STREAM_BYTE_ORDER_BIG_ENDIAN);
-
-    if (!g_data_output_stream_put_uint32(s, g_hash_table_size(proxies),
-                                         NULL, &err)) {
-        error_report("%s: Failed to write to stream: %s",
-                     __func__, err->message);
-        return -1;
-    }
-
-    g_hash_table_foreach(proxies, dbus_save_state_proxy, s);
-
-    if (g_memory_output_stream_get_size(G_MEMORY_OUTPUT_STREAM(m))
-        > UINT32_MAX) {
-        error_report("%s: DBus vmstate buffer is too large", __func__);
-        return -1;
-    }
-
-    if (!g_output_stream_close(G_OUTPUT_STREAM(m), NULL, &err)) {
-        error_report("%s: Failed to close stream: %s", __func__, err->message);
-        return -1;
-    }
-
-    g_free(self->data);
-    self->data_size =
-        g_memory_output_stream_get_size(G_MEMORY_OUTPUT_STREAM(m));
-    self->data =
-        g_memory_output_stream_steal_data(G_MEMORY_OUTPUT_STREAM(m));
-
-    return 0;
-}
-
-static const VMStateDescription dbus_vmstate = {
-    .name = TYPE_DBUS_VMSTATE,
-    .version_id = 0,
-    .pre_save = dbus_vmstate_pre_save,
-    .post_load = dbus_vmstate_post_load,
-    .fields = (VMStateField[]) {
-        VMSTATE_UINT32(data_size, DBusVMState),
-        VMSTATE_VBUFFER_ALLOC_UINT32(data, DBusVMState, 0, 0, data_size),
-        VMSTATE_END_OF_LIST()
-    }
-};
-
-static void
-dbus_vmstate_complete(UserCreatable *uc, Error **errp)
-{
-    DBusVMState *self = DBUS_VMSTATE(uc);
-    g_autoptr(GError) err = NULL;
-
-    if (!object_resolve_path_type("", TYPE_DBUS_VMSTATE, NULL)) {
-        error_setg(errp, "There is already an instance of %s",
-                   TYPE_DBUS_VMSTATE);
-        return;
-    }
-
-    if (!self->dbus_addr) {
-        error_setg(errp, QERR_MISSING_PARAMETER, "addr");
-        return;
-    }
-
-    self->bus = g_dbus_connection_new_for_address_sync(self->dbus_addr,
-                    G_DBUS_CONNECTION_FLAGS_AUTHENTICATION_CLIENT |
-                    G_DBUS_CONNECTION_FLAGS_MESSAGE_BUS_CONNECTION,
-                    NULL, NULL, &err);
-    if (err) {
-        error_setg(errp, "failed to connect to DBus: '%s'", err->message);
-        return;
-    }
-
-    if (vmstate_register(VMSTATE_IF(self), VMSTATE_INSTANCE_ID_ANY,
-                         &dbus_vmstate, self) < 0) {
-        error_setg(errp, "Failed to register vmstate");
-    }
-}
-
-static void
-dbus_vmstate_finalize(Object *o)
-{
-    DBusVMState *self = DBUS_VMSTATE(o);
-
-    vmstate_unregister(VMSTATE_IF(self), &dbus_vmstate, self);
-
-    g_clear_object(&self->bus);
-    g_free(self->dbus_addr);
-    g_free(self->id_list);
-    g_free(self->data);
-}
-
-static char *
-get_dbus_addr(Object *o, Error **errp)
-{
-    DBusVMState *self = DBUS_VMSTATE(o);
-
-    return g_strdup(self->dbus_addr);
-}
-
-static void
-set_dbus_addr(Object *o, const char *str, Error **errp)
-{
-    DBusVMState *self = DBUS_VMSTATE(o);
-
-    g_free(self->dbus_addr);
-    self->dbus_addr = g_strdup(str);
-}
-
-static char *
-get_id_list(Object *o, Error **errp)
-{
-    DBusVMState *self = DBUS_VMSTATE(o);
-
-    return g_strdup(self->id_list);
-}
-
-static void
-set_id_list(Object *o, const char *str, Error **errp)
-{
-    DBusVMState *self = DBUS_VMSTATE(o);
-
-    g_free(self->id_list);
-    self->id_list = g_strdup(str);
-}
-
-static char *
-dbus_vmstate_get_id(VMStateIf *vmif)
-{
-    return g_strdup(TYPE_DBUS_VMSTATE);
-}
-
-static void
-dbus_vmstate_class_init(ObjectClass *oc, void *data)
-{
-    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
-    VMStateIfClass *vc = VMSTATE_IF_CLASS(oc);
-
-    ucc->complete = dbus_vmstate_complete;
-    vc->get_id = dbus_vmstate_get_id;
-
-    object_class_property_add_str(oc, "addr",
-                                  get_dbus_addr, set_dbus_addr,
-                                  &error_abort);
-    object_class_property_add_str(oc, "id-list",
-                                  get_id_list, set_id_list,
-                                  &error_abort);
-}
-
-static const TypeInfo dbus_vmstate_info = {
-    .name = TYPE_DBUS_VMSTATE,
-    .parent = TYPE_OBJECT,
-    .instance_size = sizeof(DBusVMState),
-    .instance_finalize = dbus_vmstate_finalize,
-    .class_size = sizeof(DBusVMStateClass),
-    .class_init = dbus_vmstate_class_init,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_USER_CREATABLE },
-        { TYPE_VMSTATE_IF },
-        { }
-    }
-};
-
-static void
-register_types(void)
-{
-    type_register_static(&dbus_vmstate_info);
-}
-
-type_init(register_types);
@@ -18,6 +18,13 @@
 #include "sysemu/sysemu.h"
 #include "qom/object_interfaces.h"

+/* hostmem-file.c */
+/**
+ * @TYPE_MEMORY_BACKEND_FILE:
+ * name of backend that uses mmap on a file descriptor
+ */
+#define TYPE_MEMORY_BACKEND_FILE "memory-backend-file"
+
 #define MEMORY_BACKEND_FILE(obj) \
    OBJECT_CHECK(HostMemoryBackendFile, (obj), TYPE_MEMORY_BACKEND_FILE)

@@ -51,6 +58,29 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
        return;
    }

+    /*
+     * Verify pmem file size since starting a guest with an incorrect size
+     * leads to confusing failures inside the guest.
+     */
+    if (fb->is_pmem) {
+        Error *local_err = NULL;
+        uint64_t size;
+
+        size = qemu_get_pmem_size(fb->mem_path, &local_err);
+        if (!size) {
+            error_propagate(errp, local_err);
+            return;
+        }
+
+        if (backend->size > size) {
+            error_setg(errp, "size property %" PRIu64 " is larger than "
+                       "pmem file \"%s\" size %" PRIu64, backend->size,
+                       fb->mem_path, size);
+            return;
+        }
+    }
+
+    backend->force_prealloc = mem_prealloc;
    name = host_memory_backend_get_name(backend);
    memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
                                     name,
@@ -45,6 +45,7 @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
        return;
    }

+    backend->force_prealloc = mem_prealloc;
    fd = qemu_memfd_create(TYPE_MEMORY_BACKEND_MEMFD, backend->size,
                           m->hugetlb, m->hugetlbsize, m->seal ?
                           F_SEAL_GROW | F_SEAL_SHRINK | F_SEAL_SEAL : 0,
@@ -16,6 +16,8 @@
 #include "qemu/module.h"
 #include "qom/object_interfaces.h"

+#define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"
+
 static void
 ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
 {
@@ -12,7 +12,6 @@

 #include "qemu/osdep.h"
 #include "sysemu/hostmem.h"
-#include "sysemu/sysemu.h"
 #include "hw/boards.h"
 #include "qapi/error.h"
 #include "qapi/qapi-builtin-visit.h"
@@ -215,7 +214,7 @@ static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
 {
    HostMemoryBackend *backend = MEMORY_BACKEND(obj);

-    return backend->prealloc;
+    return backend->prealloc || backend->force_prealloc;
 }

 static void host_memory_backend_set_prealloc(Object *obj, bool value,
@@ -223,6 +222,15 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
 {
    Error *local_err = NULL;
    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    MachineState *ms = MACHINE(qdev_get_machine());
+
+    if (backend->force_prealloc) {
+        if (value) {
+            error_setg(errp,
+                       "remove -mem-prealloc to use the prealloc property");
+            return;
+        }
+    }

    if (!host_memory_backend_mr_inited(backend)) {
        backend->prealloc = value;
@@ -234,7 +242,7 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
        void *ptr = memory_region_get_ram_ptr(&backend->mr);
        uint64_t sz = memory_region_size(&backend->mr);

-        os_mem_prealloc(fd, ptr, sz, backend->prealloc_threads, &local_err);
+        os_mem_prealloc(fd, ptr, sz, ms->smp.cpus, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
@@ -243,44 +251,14 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
    }
 }

-static void host_memory_backend_get_prealloc_threads(Object *obj, Visitor *v,
-    const char *name, void *opaque, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    visit_type_uint32(v, name, &backend->prealloc_threads, errp);
-}
-
-static void host_memory_backend_set_prealloc_threads(Object *obj, Visitor *v,
-    const char *name, void *opaque, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    Error *local_err = NULL;
-    uint32_t value;
-
-    visit_type_uint32(v, name, &value, &local_err);
-    if (local_err) {
-        goto out;
-    }
-    if (value <= 0) {
-        error_setg(&local_err,
-                   "property '%s' of %s doesn't take value '%d'",
-                   name, object_get_typename(obj), value);
-        goto out;
-    }
-    backend->prealloc_threads = value;
-out:
-    error_propagate(errp, local_err);
-}
-
 static void host_memory_backend_init(Object *obj)
 {
    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
    MachineState *machine = MACHINE(qdev_get_machine());

-    /* TODO: convert access to globals to compat properties */
    backend->merge = machine_mem_merge(machine);
    backend->dump = machine_dump_guest_core(machine);
-    backend->prealloc_threads = 1;
+    backend->prealloc = mem_prealloc;
 }

 static void host_memory_backend_post_init(Object *obj)
@@ -325,7 +303,7 @@ size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
 #else
 size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
 {
-    return qemu_real_host_page_size;
+    return getpagesize();
 }
 #endif

@@ -334,6 +312,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
 {
    HostMemoryBackend *backend = MEMORY_BACKEND(uc);
    HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
+    MachineState *ms = MACHINE(qdev_get_machine());
    Error *local_err = NULL;
    void *ptr;
    uint64_t sz;
@@ -383,10 +362,8 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
        assert(sizeof(backend->host_nodes) >=
               BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
        assert(maxnode <= MAX_NODES);
-
-        if (maxnode &&
-            mbind(ptr, sz, backend->policy, backend->host_nodes, maxnode + 1,
-                  flags)) {
+        if (mbind(ptr, sz, backend->policy,
+                  maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
            if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
                error_setg_errno(errp, errno,
                                 "cannot bind memory to host NUMA nodes");
@@ -400,7 +377,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
         */
        if (backend->prealloc) {
            os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz,
-                            backend->prealloc_threads, &local_err);
+                            ms->smp.cpus, &local_err);
            if (local_err) {
                goto out;
            }
@@ -478,12 +455,6 @@ host_memory_backend_class_init(ObjectClass *oc, void *data)
        host_memory_backend_set_prealloc, &error_abort);
    object_class_property_set_description(oc, "prealloc",
        "Preallocate memory", &error_abort);
-    object_class_property_add(oc, "prealloc-threads", "int",
-        host_memory_backend_get_prealloc_threads,
-        host_memory_backend_set_prealloc_threads,
-        NULL, NULL, &error_abort);
-    object_class_property_set_description(oc, "prealloc-threads",
-        "Number of CPU threads to use for prealloc", &error_abort);
    object_class_property_add(oc, "size", "int",
        host_memory_backend_get_size,
        host_memory_backend_set_size,
@@ -1,77 +0,0 @@
-/*
- * QEMU Builtin Random Number Generator Backend
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/osdep.h"
-#include "sysemu/rng.h"
-#include "qemu/main-loop.h"
-#include "qemu/guest-random.h"
-
-#define RNG_BUILTIN(obj) OBJECT_CHECK(RngBuiltin, (obj), TYPE_RNG_BUILTIN)
-
-typedef struct RngBuiltin {
-    RngBackend parent;
-    QEMUBH *bh;
-} RngBuiltin;
-
-static void rng_builtin_receive_entropy_bh(void *opaque)
-{
-    RngBuiltin *s = opaque;
-
-    while (!QSIMPLEQ_EMPTY(&s->parent.requests)) {
-        RngRequest *req = QSIMPLEQ_FIRST(&s->parent.requests);
-
-        qemu_guest_getrandom_nofail(req->data, req->size);
-
-        req->receive_entropy(req->opaque, req->data, req->size);
-
-        rng_backend_finalize_request(&s->parent, req);
-    }
-}
-
-static void rng_builtin_request_entropy(RngBackend *b, RngRequest *req)
-{
-    RngBuiltin *s = RNG_BUILTIN(b);
-
-    qemu_bh_schedule(s->bh);
-}
-
-static void rng_builtin_init(Object *obj)
-{
-    RngBuiltin *s = RNG_BUILTIN(obj);
-
-    s->bh = qemu_bh_new(rng_builtin_receive_entropy_bh, s);
-}
-
-static void rng_builtin_finalize(Object *obj)
-{
-    RngBuiltin *s = RNG_BUILTIN(obj);
-
-    qemu_bh_delete(s->bh);
-}
-
-static void rng_builtin_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_builtin_request_entropy;
-}
-
-static const TypeInfo rng_builtin_info = {
-    .name = TYPE_RNG_BUILTIN,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RngBuiltin),
-    .instance_init = rng_builtin_init,
-    .instance_finalize = rng_builtin_finalize,
-    .class_init = rng_builtin_class_init,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_builtin_info);
-}
-
-type_init(register_types);
@@ -1,7 +0,0 @@
-# See docs/devel/tracing.txt for syntax documentation.
-
-# dbus-vmstate.c
-dbus_vmstate_pre_save(void)
-dbus_vmstate_post_load(int version_id) "version_id: %d"
-dbus_vmstate_loading(const char *id) "id: %s"
-dbus_vmstate_saving(const char *id) "id: %s"
@@ -12,6 +12,7 @@


 #include "qemu/osdep.h"
+#include "hw/qdev.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
@@ -46,7 +47,7 @@ vhost_user_backend_dev_init(VhostUserBackend *b, VirtIODevice *vdev,

    b->vdev = vdev;
    b->dev.nvqs = nvqs;
-    b->dev.vqs = g_new0(struct vhost_virtqueue, nvqs);
+    b->dev.vqs = g_new(struct vhost_virtqueue, nvqs);

    ret = vhost_dev_init(&b->dev, &b->vhost_user, VHOST_BACKEND_TYPE_USER, 0);
    if (ret < 0) {
@@ -26,6 +26,7 @@

 #include "qemu/osdep.h"
 #include "qemu/atomic.h"
+#include "exec/cpu-common.h"
 #include "sysemu/kvm.h"
 #include "sysemu/balloon.h"
 #include "trace-root.h"
@@ -18,7 +18,6 @@ block-obj-y += block-backend.o snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += file-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-block-obj-$(CONFIG_LINUX_IO_URING) += io_uring.o
 block-obj-y += null.o mirror.o commit.o io.o create.o
 block-obj-y += throttle-groups.o
 block-obj-$(CONFIG_LINUX) += nvme.o
@@ -38,18 +37,10 @@ block-obj-y += write-threshold.o
 block-obj-y += backup.o
 block-obj-$(CONFIG_REPLICATION) += replication.o
 block-obj-y += throttle.o copy-on-read.o
-block-obj-y += block-copy.o

 block-obj-y += crypto.o

-block-obj-y += aio_task.o
-block-obj-y += backup-top.o
-block-obj-y += filter-compress.o
-common-obj-y += monitor/
-
-block-obj-y += stream.o
-
-common-obj-y += qapi-sysemu.o
+common-obj-y += stream.o

 nfs.o-libs         := $(LIBNFS_LIBS)
 iscsi.o-cflags     := $(LIBISCSI_CFLAGS)
@@ -70,7 +61,5 @@ block-obj-$(if $(CONFIG_LZFSE),m,n) += dmg-lzfse.o
 dmg-lzfse.o-libs   := $(LZFSE_LIBS)
 qcow.o-libs        := -lz
 linux-aio.o-libs   := -laio
-io_uring.o-cflags  := $(LINUX_IO_URING_CFLAGS)
-io_uring.o-libs    := $(LINUX_IO_URING_LIBS)
 parallels.o-cflags := $(LIBXML2_CFLAGS)
 parallels.o-libs   := $(LIBXML2_LIBS)
@@ -195,10 +195,6 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,

    assert(cookie->type < BLOCK_MAX_IOTYPE);

-    if (cookie->type == BLOCK_ACCT_NONE) {
-        return;
-    }
-
    qemu_mutex_lock(&stats->lock);

    if (failed) {
@@ -221,8 +217,6 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
    }

    qemu_mutex_unlock(&stats->lock);
-
-    cookie->type = BLOCK_ACCT_NONE;
 }

 void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
@@ -1,124 +0,0 @@
-/*
- * Aio tasks loops
- *
- * Copyright (c) 2019 Virtuozzo International GmbH.
- *
- * 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 "block/aio.h"
-#include "block/aio_task.h"
-
-struct AioTaskPool {
-    Coroutine *main_co;
-    int status;
-    int max_busy_tasks;
-    int busy_tasks;
-    bool waiting;
-};
-
-static void coroutine_fn aio_task_co(void *opaque)
-{
-    AioTask *task = opaque;
-    AioTaskPool *pool = task->pool;
-
-    assert(pool->busy_tasks < pool->max_busy_tasks);
-    pool->busy_tasks++;
-
-    task->ret = task->func(task);
-
-    pool->busy_tasks--;
-
-    if (task->ret < 0 && pool->status == 0) {
-        pool->status = task->ret;
-    }
-
-    g_free(task);
-
-    if (pool->waiting) {
-        pool->waiting = false;
-        aio_co_wake(pool->main_co);
-    }
-}
-
-void coroutine_fn aio_task_pool_wait_one(AioTaskPool *pool)
-{
-    assert(pool->busy_tasks > 0);
-    assert(qemu_coroutine_self() == pool->main_co);
-
-    pool->waiting = true;
-    qemu_coroutine_yield();
-
-    assert(!pool->waiting);
-    assert(pool->busy_tasks < pool->max_busy_tasks);
-}
-
-void coroutine_fn aio_task_pool_wait_slot(AioTaskPool *pool)
-{
-    if (pool->busy_tasks < pool->max_busy_tasks) {
-        return;
-    }
-
-    aio_task_pool_wait_one(pool);
-}
-
-void coroutine_fn aio_task_pool_wait_all(AioTaskPool *pool)
-{
-    while (pool->busy_tasks > 0) {
-        aio_task_pool_wait_one(pool);
-    }
-}
-
-void coroutine_fn aio_task_pool_start_task(AioTaskPool *pool, AioTask *task)
-{
-    aio_task_pool_wait_slot(pool);
-
-    task->pool = pool;
-    qemu_coroutine_enter(qemu_coroutine_create(aio_task_co, task));
-}
-
-AioTaskPool *coroutine_fn aio_task_pool_new(int max_busy_tasks)
-{
-    AioTaskPool *pool = g_new0(AioTaskPool, 1);
-
-    pool->main_co = qemu_coroutine_self();
-    pool->max_busy_tasks = max_busy_tasks;
-
-    return pool;
-}
-
-void aio_task_pool_free(AioTaskPool *pool)
-{
-    g_free(pool);
-}
-
-int aio_task_pool_status(AioTaskPool *pool)
-{
-    if (!pool) {
-        return 0; /* Sugar for lazy allocation of aio pool */
-    }
-
-    return pool->status;
-}
-
-bool aio_task_pool_empty(AioTaskPool *pool)
-{
-    return pool->busy_tasks == 0;
-}
@@ -1,285 +0,0 @@
-/*
- * backup-top filter driver
- *
- * The driver performs Copy-Before-Write (CBW) operation: it is injected above
- * some node, and before each write it copies _old_ data to the target node.
- *
- * Copyright (c) 2018-2019 Virtuozzo International GmbH.
- *
- * Author:
- *  Sementsov-Ogievskiy Vladimir <vsementsov@virtuozzo.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "qemu/osdep.h"
-
-#include "sysemu/block-backend.h"
-#include "qemu/cutils.h"
-#include "qapi/error.h"
-#include "block/block_int.h"
-#include "block/qdict.h"
-#include "block/block-copy.h"
-
-#include "block/backup-top.h"
-
-typedef struct BDRVBackupTopState {
-    BlockCopyState *bcs;
-    BdrvChild *target;
-    bool active;
-    int64_t cluster_size;
-} BDRVBackupTopState;
-
-static coroutine_fn int backup_top_co_preadv(
-        BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-        QEMUIOVector *qiov, int flags)
-{
-    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
-}
-
-static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset,
-                                       uint64_t bytes, BdrvRequestFlags flags)
-{
-    BDRVBackupTopState *s = bs->opaque;
-    uint64_t off, end;
-
-    if (flags & BDRV_REQ_WRITE_UNCHANGED) {
-        return 0;
-    }
-
-    off = QEMU_ALIGN_DOWN(offset, s->cluster_size);
-    end = QEMU_ALIGN_UP(offset + bytes, s->cluster_size);
-
-    return block_copy(s->bcs, off, end - off, NULL);
-}
-
-static int coroutine_fn backup_top_co_pdiscard(BlockDriverState *bs,
-                                               int64_t offset, int bytes)
-{
-    int ret = backup_top_cbw(bs, offset, bytes, 0);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return bdrv_co_pdiscard(bs->backing, offset, bytes);
-}
-
-static int coroutine_fn backup_top_co_pwrite_zeroes(BlockDriverState *bs,
-        int64_t offset, int bytes, BdrvRequestFlags flags)
-{
-    int ret = backup_top_cbw(bs, offset, bytes, flags);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return bdrv_co_pwrite_zeroes(bs->backing, offset, bytes, flags);
-}
-
-static coroutine_fn int backup_top_co_pwritev(BlockDriverState *bs,
-                                              uint64_t offset,
-                                              uint64_t bytes,
-                                              QEMUIOVector *qiov, int flags)
-{
-    int ret = backup_top_cbw(bs, offset, bytes, flags);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return bdrv_co_pwritev(bs->backing, offset, bytes, qiov, flags);
-}
-
-static int coroutine_fn backup_top_co_flush(BlockDriverState *bs)
-{
-    if (!bs->backing) {
-        return 0;
-    }
-
-    return bdrv_co_flush(bs->backing->bs);
-}
-
-static void backup_top_refresh_filename(BlockDriverState *bs)
-{
-    if (bs->backing == NULL) {
-        /*
-         * we can be here after failed bdrv_attach_child in
-         * bdrv_set_backing_hd
-         */
-        return;
-    }
-    pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
-            bs->backing->bs->filename);
-}
-
-static void backup_top_child_perm(BlockDriverState *bs, BdrvChild *c,
-                                  const BdrvChildRole *role,
-                                  BlockReopenQueue *reopen_queue,
-                                  uint64_t perm, uint64_t shared,
-                                  uint64_t *nperm, uint64_t *nshared)
-{
-    BDRVBackupTopState *s = bs->opaque;
-
-    if (!s->active) {
-        /*
-         * The filter node may be in process of bdrv_append(), which firstly do
-         * bdrv_set_backing_hd() and then bdrv_replace_node(). This means that
-         * we can't unshare BLK_PERM_WRITE during bdrv_append() operation. So,
-         * let's require nothing during bdrv_append() and refresh permissions
-         * after it (see bdrv_backup_top_append()).
-         */
-        *nperm = 0;
-        *nshared = BLK_PERM_ALL;
-        return;
-    }
-
-    if (role == &child_file) {
-        /*
-         * Target child
-         *
-         * Share write to target (child_file), to not interfere
-         * with guest writes to its disk which may be in target backing chain.
-         */
-        *nshared = BLK_PERM_ALL;
-        *nperm = BLK_PERM_WRITE;
-    } else {
-        /* Source child */
-        bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared,
-                                  nperm, nshared);
-
-        if (perm & BLK_PERM_WRITE) {
-            *nperm = *nperm | BLK_PERM_CONSISTENT_READ;
-        }
-        *nshared &= ~BLK_PERM_WRITE;
-    }
-}
-
-BlockDriver bdrv_backup_top_filter = {
-    .format_name = "backup-top",
-    .instance_size = sizeof(BDRVBackupTopState),
-
-    .bdrv_co_preadv             = backup_top_co_preadv,
-    .bdrv_co_pwritev            = backup_top_co_pwritev,
-    .bdrv_co_pwrite_zeroes      = backup_top_co_pwrite_zeroes,
-    .bdrv_co_pdiscard           = backup_top_co_pdiscard,
-    .bdrv_co_flush              = backup_top_co_flush,
-
-    .bdrv_co_block_status       = bdrv_co_block_status_from_backing,
-
-    .bdrv_refresh_filename      = backup_top_refresh_filename,
-
-    .bdrv_child_perm            = backup_top_child_perm,
-
-    .is_filter = true,
-};
-
-BlockDriverState *bdrv_backup_top_append(BlockDriverState *source,
-                                         BlockDriverState *target,
-                                         const char *filter_node_name,
-                                         uint64_t cluster_size,
-                                         BdrvRequestFlags write_flags,
-                                         BlockCopyState **bcs,
-                                         Error **errp)
-{
-    Error *local_err = NULL;
-    BDRVBackupTopState *state;
-    BlockDriverState *top = bdrv_new_open_driver(&bdrv_backup_top_filter,
-                                                 filter_node_name,
-                                                 BDRV_O_RDWR, errp);
-    bool appended = false;
-
-    if (!top) {
-        return NULL;
-    }
-
-    state = top->opaque;
-    top->total_sectors = source->total_sectors;
-    top->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
-            (BDRV_REQ_FUA & source->supported_write_flags);
-    top->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
-            ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) &
-             source->supported_zero_flags);
-
-    bdrv_ref(target);
-    state->target = bdrv_attach_child(top, target, "target", &child_file, errp);
-    if (!state->target) {
-        bdrv_unref(target);
-        bdrv_unref(top);
-        return NULL;
-    }
-
-    bdrv_drained_begin(source);
-
-    bdrv_ref(top);
-    bdrv_append(top, source, &local_err);
-    if (local_err) {
-        error_prepend(&local_err, "Cannot append backup-top filter: ");
-        goto fail;
-    }
-    appended = true;
-
-    /*
-     * bdrv_append() finished successfully, now we can require permissions
-     * we want.
-     */
-    state->active = true;
-    bdrv_child_refresh_perms(top, top->backing, &local_err);
-    if (local_err) {
-        error_prepend(&local_err,
-                      "Cannot set permissions for backup-top filter: ");
-        goto fail;
-    }
-
-    state->cluster_size = cluster_size;
-    state->bcs = block_copy_state_new(top->backing, state->target,
-                                      cluster_size, write_flags, &local_err);
-    if (local_err) {
-        error_prepend(&local_err, "Cannot create block-copy-state: ");
-        goto fail;
-    }
-    *bcs = state->bcs;
-
-    bdrv_drained_end(source);
-
-    return top;
-
-fail:
-    if (appended) {
-        state->active = false;
-        bdrv_backup_top_drop(top);
-    } else {
-        bdrv_unref(top);
-    }
-
-    bdrv_drained_end(source);
-    error_propagate(errp, local_err);
-
-    return NULL;
-}
-
-void bdrv_backup_top_drop(BlockDriverState *bs)
-{
-    BDRVBackupTopState *s = bs->opaque;
-
-    bdrv_drained_begin(bs);
-
-    block_copy_state_free(s->bcs);
-
-    s->active = false;
-    bdrv_child_refresh_perms(bs, bs->backing, &error_abort);
-    bdrv_replace_node(bs, backing_bs(bs), &error_abort);
-    bdrv_set_backing_hd(bs, NULL, &error_abort);
-
-    bdrv_drained_end(bs);
-
-    bdrv_unref(bs);
-}
@@ -1,41 +0,0 @@
-/*
- * backup-top filter driver
- *
- * The driver performs Copy-Before-Write (CBW) operation: it is injected above
- * some node, and before each write it copies _old_ data to the target node.
- *
- * Copyright (c) 2018-2019 Virtuozzo International GmbH.
- *
- * Author:
- *  Sementsov-Ogievskiy Vladimir <vsementsov@virtuozzo.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef BACKUP_TOP_H
-#define BACKUP_TOP_H
-
-#include "block/block_int.h"
-#include "block/block-copy.h"
-
-BlockDriverState *bdrv_backup_top_append(BlockDriverState *source,
-                                         BlockDriverState *target,
-                                         const char *filter_node_name,
-                                         uint64_t cluster_size,
-                                         BdrvRequestFlags write_flags,
-                                         BlockCopyState **bcs,
-                                         Error **errp);
-void bdrv_backup_top_drop(BlockDriverState *bs);
-
-#endif /* BACKUP_TOP_H */
@@ -2,7 +2,6 @@
 * QEMU backup
 *
 * Copyright (C) 2013 Proxmox Server Solutions
- * Copyright (c) 2019 Virtuozzo International GmbH.
 *
 * Authors:
 *  Dietmar Maurer (dietmar@proxmox.com)
@@ -19,7 +18,6 @@
 #include "block/block_int.h"
 #include "block/blockjob_int.h"
 #include "block/block_backup.h"
-#include "block/block-copy.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
@@ -28,82 +26,262 @@
 #include "qemu/bitmap.h"
 #include "qemu/error-report.h"

-#include "block/backup-top.h"
-
 #define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)

+typedef struct CowRequest {
+    int64_t start_byte;
+    int64_t end_byte;
+    QLIST_ENTRY(CowRequest) list;
+    CoQueue wait_queue; /* coroutines blocked on this request */
+} CowRequest;
+
 typedef struct BackupBlockJob {
    BlockJob common;
-    BlockDriverState *backup_top;
-    BlockDriverState *source_bs;
-
+    BlockBackend *target;
+    /* bitmap for sync=incremental */
    BdrvDirtyBitmap *sync_bitmap;
-
    MirrorSyncMode sync_mode;
-    BitmapSyncMode bitmap_mode;
    BlockdevOnError on_source_error;
    BlockdevOnError on_target_error;
+    CoRwlock flush_rwlock;
    uint64_t len;
    uint64_t bytes_read;
    int64_t cluster_size;
+    bool compress;
+    NotifierWithReturn before_write;
+    QLIST_HEAD(, CowRequest) inflight_reqs;

-    BlockCopyState *bcs;
+    HBitmap *copy_bitmap;
+    bool use_copy_range;
+    int64_t copy_range_size;
+
+    bool serialize_target_writes;
 } BackupBlockJob;

 static const BlockJobDriver backup_job_driver;

-static void backup_progress_bytes_callback(int64_t bytes, void *opaque)
+/* See if in-flight requests overlap and wait for them to complete */
+static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
+                                                       int64_t start,
+                                                       int64_t end)
 {
-    BackupBlockJob *s = opaque;
+    CowRequest *req;
+    bool retry;

-    s->bytes_read += bytes;
+    do {
+        retry = false;
+        QLIST_FOREACH(req, &job->inflight_reqs, list) {
+            if (end > req->start_byte && start < req->end_byte) {
+                qemu_co_queue_wait(&req->wait_queue, NULL);
+                retry = true;
+                break;
+            }
+        }
+    } while (retry);
+}
+
+/* Keep track of an in-flight request */
+static void cow_request_begin(CowRequest *req, BackupBlockJob *job,
+                              int64_t start, int64_t end)
+{
+    req->start_byte = start;
+    req->end_byte = end;
+    qemu_co_queue_init(&req->wait_queue);
+    QLIST_INSERT_HEAD(&job->inflight_reqs, req, list);
+}
+
+/* Forget about a completed request */
+static void cow_request_end(CowRequest *req)
+{
+    QLIST_REMOVE(req, list);
+    qemu_co_queue_restart_all(&req->wait_queue);
+}
+
+/* Copy range to target with a bounce buffer and return the bytes copied. If
+ * error occurred, return a negative error number */
+static int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job,
+                                                      int64_t start,
+                                                      int64_t end,
+                                                      bool is_write_notifier,
+                                                      bool *error_is_read,
+                                                      void **bounce_buffer)
+{
+    int ret;
+    BlockBackend *blk = job->common.blk;
+    int nbytes;
+    int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0;
+    int write_flags = job->serialize_target_writes ? BDRV_REQ_SERIALISING : 0;
+
+    assert(QEMU_IS_ALIGNED(start, job->cluster_size));
+    hbitmap_reset(job->copy_bitmap, start, job->cluster_size);
+    nbytes = MIN(job->cluster_size, job->len - start);
+    if (!*bounce_buffer) {
+        *bounce_buffer = blk_blockalign(blk, job->cluster_size);
+    }
+
+    ret = blk_co_pread(blk, start, nbytes, *bounce_buffer, read_flags);
+    if (ret < 0) {
+        trace_backup_do_cow_read_fail(job, start, ret);
+        if (error_is_read) {
+            *error_is_read = true;
+        }
+        goto fail;
+    }
+
+    if (buffer_is_zero(*bounce_buffer, nbytes)) {
+        ret = blk_co_pwrite_zeroes(job->target, start,
+                                   nbytes, write_flags | BDRV_REQ_MAY_UNMAP);
+    } else {
+        ret = blk_co_pwrite(job->target, start,
+                            nbytes, *bounce_buffer, write_flags |
+                            (job->compress ? BDRV_REQ_WRITE_COMPRESSED : 0));
+    }
+    if (ret < 0) {
+        trace_backup_do_cow_write_fail(job, start, ret);
+        if (error_is_read) {
+            *error_is_read = false;
+        }
+        goto fail;
+    }
+
+    return nbytes;
+fail:
+    hbitmap_set(job->copy_bitmap, start, job->cluster_size);
+    return ret;
+
+}
+
+/* Copy range to target and return the bytes copied. If error occurred, return a
+ * negative error number. */
+static int coroutine_fn backup_cow_with_offload(BackupBlockJob *job,
+                                                int64_t start,
+                                                int64_t end,
+                                                bool is_write_notifier)
+{
+    int ret;
+    int nr_clusters;
+    BlockBackend *blk = job->common.blk;
+    int nbytes;
+    int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0;
+    int write_flags = job->serialize_target_writes ? BDRV_REQ_SERIALISING : 0;
+
+    assert(QEMU_IS_ALIGNED(job->copy_range_size, job->cluster_size));
+    assert(QEMU_IS_ALIGNED(start, job->cluster_size));
+    nbytes = MIN(job->copy_range_size, MIN(end, job->len) - start);
+    nr_clusters = DIV_ROUND_UP(nbytes, job->cluster_size);
+    hbitmap_reset(job->copy_bitmap, start, job->cluster_size * nr_clusters);
+    ret = blk_co_copy_range(blk, start, job->target, start, nbytes,
+                            read_flags, write_flags);
+    if (ret < 0) {
+        trace_backup_do_cow_copy_range_fail(job, start, ret);
+        hbitmap_set(job->copy_bitmap, start, job->cluster_size * nr_clusters);
+        return ret;
+    }
+
+    return nbytes;
 }

 static int coroutine_fn backup_do_cow(BackupBlockJob *job,
                                      int64_t offset, uint64_t bytes,
-                                      bool *error_is_read)
+                                      bool *error_is_read,
+                                      bool is_write_notifier)
 {
+    CowRequest cow_request;
    int ret = 0;
    int64_t start, end; /* bytes */
+    void *bounce_buffer = NULL;
+
+    qemu_co_rwlock_rdlock(&job->flush_rwlock);

    start = QEMU_ALIGN_DOWN(offset, job->cluster_size);
    end = QEMU_ALIGN_UP(bytes + offset, job->cluster_size);

    trace_backup_do_cow_enter(job, start, offset, bytes);

-    ret = block_copy(job->bcs, start, end - start, error_is_read);
+    wait_for_overlapping_requests(job, start, end);
+    cow_request_begin(&cow_request, job, start, end);
+
+    while (start < end) {
+        int64_t dirty_end;
+
+        if (!hbitmap_get(job->copy_bitmap, start)) {
+            trace_backup_do_cow_skip(job, start);
+            start += job->cluster_size;
+            continue; /* already copied */
+        }
+
+        dirty_end = hbitmap_next_zero(job->copy_bitmap, start, (end - start));
+        if (dirty_end < 0) {
+            dirty_end = end;
+        }
+
+        trace_backup_do_cow_process(job, start);
+
+        if (job->use_copy_range) {
+            ret = backup_cow_with_offload(job, start, dirty_end,
+                                          is_write_notifier);
+            if (ret < 0) {
+                job->use_copy_range = false;
+            }
+        }
+        if (!job->use_copy_range) {
+            ret = backup_cow_with_bounce_buffer(job, start, dirty_end,
+                                                is_write_notifier,
+                                                error_is_read, &bounce_buffer);
+        }
+        if (ret < 0) {
+            break;
+        }
+
+        /* Publish progress, guest I/O counts as progress too.  Note that the
+         * offset field is an opaque progress value, it is not a disk offset.
+         */
+        start += ret;
+        job->bytes_read += ret;
+        job_progress_update(&job->common.job, ret);
+        ret = 0;
+    }
+
+    if (bounce_buffer) {
+        qemu_vfree(bounce_buffer);
+    }
+
+    cow_request_end(&cow_request);

    trace_backup_do_cow_return(job, offset, bytes, ret);

+    qemu_co_rwlock_unlock(&job->flush_rwlock);
+
    return ret;
 }

+static int coroutine_fn backup_before_write_notify(
+        NotifierWithReturn *notifier,
+        void *opaque)
+{
+    BackupBlockJob *job = container_of(notifier, BackupBlockJob, before_write);
+    BdrvTrackedRequest *req = opaque;
+
+    assert(req->bs == blk_bs(job->common.blk));
+    assert(QEMU_IS_ALIGNED(req->offset, BDRV_SECTOR_SIZE));
+    assert(QEMU_IS_ALIGNED(req->bytes, BDRV_SECTOR_SIZE));
+
+    return backup_do_cow(job, req->offset, req->bytes, NULL, true);
+}
+
 static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
 {
    BdrvDirtyBitmap *bm;
-    bool sync = (((ret == 0) || (job->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS)) \
-                 && (job->bitmap_mode != BITMAP_SYNC_MODE_NEVER));
+    BlockDriverState *bs = blk_bs(job->common.blk);

-    if (sync) {
-        /*
-         * We succeeded, or we always intended to sync the bitmap.
-         * Delete this bitmap and install the child.
-         */
-        bm = bdrv_dirty_bitmap_abdicate(job->sync_bitmap, NULL);
+    if (ret < 0) {
+        /* Merge the successor back into the parent, delete nothing. */
+        bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL);
+        assert(bm);
    } else {
-        /*
-         * We failed, or we never intended to sync the bitmap anyway.
-         * Merge the successor back into the parent, keeping all data.
-         */
-        bm = bdrv_reclaim_dirty_bitmap(job->sync_bitmap, NULL);
-    }
-
-    assert(bm);
-
-    if (ret < 0 && job->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS) {
-        /* If we failed and synced, merge in the bits we didn't copy: */
-        bdrv_dirty_bitmap_merge_internal(bm, block_copy_dirty_bitmap(job->bcs),
-                                         NULL, true);
+        /* Everything is fine, delete this bitmap and install the backup. */
+        bm = bdrv_dirty_bitmap_abdicate(bs, job->sync_bitmap, NULL);
+        assert(bm);
    }
 }

@@ -126,7 +304,14 @@ static void backup_abort(Job *job)
 static void backup_clean(Job *job)
 {
    BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
-    bdrv_backup_top_drop(s->backup_top);
+    assert(s->target);
+    blk_unref(s->target);
+    s->target = NULL;
+
+    if (s->copy_bitmap) {
+        hbitmap_free(s->copy_bitmap);
+        s->copy_bitmap = NULL;
+    }
 }

 void backup_do_checkpoint(BlockJob *job, Error **errp)
@@ -141,8 +326,22 @@ void backup_do_checkpoint(BlockJob *job, Error **errp)
        return;
    }

-    bdrv_set_dirty_bitmap(block_copy_dirty_bitmap(backup_job->bcs), 0,
-                          backup_job->len);
+    hbitmap_set(backup_job->copy_bitmap, 0, backup_job->len);
+}
+
+static void backup_drain(BlockJob *job)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+    /* Need to keep a reference in case blk_drain triggers execution
+     * of backup_complete...
+     */
+    if (s->target) {
+        BlockBackend *target = s->target;
+        blk_ref(target);
+        blk_drain(target);
+        blk_unref(target);
+    }
 }

 static BlockErrorAction backup_error_action(BackupBlockJob *job,
@@ -165,10 +364,8 @@ static bool coroutine_fn yield_and_check(BackupBlockJob *job)
        return true;
    }

-    /*
-     * We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
-     * return. Without a yield, the VM would not reboot.
-     */
+    /* We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
+     * return. Without a yield, the VM would not reboot. */
    delay_ns = block_job_ratelimit_get_delay(&job->common, job->bytes_read);
    job->bytes_read = 0;
    job_sleep_ns(&job->common.job, delay_ns);
@@ -180,102 +377,117 @@ static bool coroutine_fn yield_and_check(BackupBlockJob *job)
    return false;
 }

+static bool bdrv_is_unallocated_range(BlockDriverState *bs,
+                                      int64_t offset, int64_t bytes)
+{
+    int64_t end = offset + bytes;
+
+    while (offset < end && !bdrv_is_allocated(bs, offset, bytes, &bytes)) {
+        if (bytes == 0) {
+            return true;
+        }
+        offset += bytes;
+        bytes = end - offset;
+    }
+
+    return offset >= end;
+}
+
 static int coroutine_fn backup_loop(BackupBlockJob *job)
 {
+    int ret;
    bool error_is_read;
    int64_t offset;
-    BdrvDirtyBitmapIter *bdbi;
-    int ret = 0;
+    HBitmapIter hbi;
+    BlockDriverState *bs = blk_bs(job->common.blk);
+
+    hbitmap_iter_init(&hbi, job->copy_bitmap, 0);
+    while ((offset = hbitmap_iter_next(&hbi)) != -1) {
+        if (job->sync_mode == MIRROR_SYNC_MODE_TOP &&
+            bdrv_is_unallocated_range(bs, offset, job->cluster_size))
+        {
+            hbitmap_reset(job->copy_bitmap, offset, job->cluster_size);
+            continue;
+        }

-    bdbi = bdrv_dirty_iter_new(block_copy_dirty_bitmap(job->bcs));
-    while ((offset = bdrv_dirty_iter_next(bdbi)) != -1) {
        do {
            if (yield_and_check(job)) {
-                goto out;
+                return 0;
            }
-            ret = backup_do_cow(job, offset, job->cluster_size, &error_is_read);
+            ret = backup_do_cow(job, offset,
+                                job->cluster_size, &error_is_read, false);
            if (ret < 0 && backup_error_action(job, error_is_read, -ret) ==
                           BLOCK_ERROR_ACTION_REPORT)
            {
-                goto out;
+                return ret;
            }
        } while (ret < 0);
    }

- out:
-    bdrv_dirty_iter_free(bdbi);
-    return ret;
+    return 0;
 }

-static void backup_init_bcs_bitmap(BackupBlockJob *job)
+/* init copy_bitmap from sync_bitmap */
+static void backup_incremental_init_copy_bitmap(BackupBlockJob *job)
 {
-    bool ret;
-    uint64_t estimate;
-    BdrvDirtyBitmap *bcs_bitmap = block_copy_dirty_bitmap(job->bcs);
+    uint64_t offset = 0;
+    uint64_t bytes = job->len;

-    if (job->sync_mode == MIRROR_SYNC_MODE_BITMAP) {
-        ret = bdrv_dirty_bitmap_merge_internal(bcs_bitmap, job->sync_bitmap,
-                                               NULL, true);
-        assert(ret);
-    } else {
-        if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
-            /*
-             * We can't hog the coroutine to initialize this thoroughly.
-             * Set a flag and resume work when we are able to yield safely.
-             */
-            block_copy_set_skip_unallocated(job->bcs, true);
+    while (bdrv_dirty_bitmap_next_dirty_area(job->sync_bitmap,
+                                             &offset, &bytes))
+    {
+        hbitmap_set(job->copy_bitmap, offset, bytes);
+
+        offset += bytes;
+        if (offset >= job->len) {
+            break;
        }
-        bdrv_set_dirty_bitmap(bcs_bitmap, 0, job->len);
+        bytes = job->len - offset;
    }

-    estimate = bdrv_get_dirty_count(bcs_bitmap);
-    job_progress_set_remaining(&job->common.job, estimate);
+    /* TODO job_progress_set_remaining() would make more sense */
+    job_progress_update(&job->common.job,
+        job->len - hbitmap_count(job->copy_bitmap));
 }

 static int coroutine_fn backup_run(Job *job, Error **errp)
 {
    BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+    BlockDriverState *bs = blk_bs(s->common.blk);
    int ret = 0;

-    backup_init_bcs_bitmap(s);
+    QLIST_INIT(&s->inflight_reqs);
+    qemu_co_rwlock_init(&s->flush_rwlock);

-    if (s->sync_mode == MIRROR_SYNC_MODE_TOP) {
-        int64_t offset = 0;
-        int64_t count;
+    job_progress_set_remaining(job, s->len);

-        for (offset = 0; offset < s->len; ) {
-            if (yield_and_check(s)) {
-                ret = -ECANCELED;
-                goto out;
-            }
-
-            ret = block_copy_reset_unallocated(s->bcs, offset, &count);
-            if (ret < 0) {
-                goto out;
-            }
-
-            offset += count;
-        }
-        block_copy_set_skip_unallocated(s->bcs, false);
+    if (s->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
+        backup_incremental_init_copy_bitmap(s);
+    } else {
+        hbitmap_set(s->copy_bitmap, 0, s->len);
    }

+    s->before_write.notify = backup_before_write_notify;
+    bdrv_add_before_write_notifier(bs, &s->before_write);
+
    if (s->sync_mode == MIRROR_SYNC_MODE_NONE) {
-        /*
-         * All bits are set in bcs bitmap to allow any cluster to be copied.
-         * This does not actually require them to be copied.
-         */
+        /* All bits are set in copy_bitmap to allow any cluster to be copied.
+         * This does not actually require them to be copied. */
        while (!job_is_cancelled(job)) {
-            /*
-             * Yield until the job is cancelled.  We just let our before_write
-             * notify callback service CoW requests.
-             */
+            /* Yield until the job is cancelled.  We just let our before_write
+             * notify callback service CoW requests. */
            job_yield(job);
        }
    } else {
        ret = backup_loop(s);
    }

- out:
+    notifier_with_return_remove(&s->before_write);
+
+    /* wait until pending backup_do_cow() calls have completed */
+    qemu_co_rwlock_wrlock(&s->flush_rwlock);
+    qemu_co_rwlock_unlock(&s->flush_rwlock);
+
    return ret;
 }

@@ -285,11 +497,13 @@ static const BlockJobDriver backup_job_driver = {
        .job_type               = JOB_TYPE_BACKUP,
        .free                   = block_job_free,
        .user_resume            = block_job_user_resume,
+        .drain                  = block_job_drain,
        .run                    = backup_run,
        .commit                 = backup_commit,
        .abort                  = backup_abort,
        .clean                  = backup_clean,
-    }
+    },
+    .drain                  = backup_drain,
 };

 static int64_t backup_calculate_cluster_size(BlockDriverState *target,
@@ -331,9 +545,7 @@ static int64_t backup_calculate_cluster_size(BlockDriverState *target,
 BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
                  BlockDriverState *target, int64_t speed,
                  MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
-                  BitmapSyncMode bitmap_mode,
                  bool compress,
-                  const char *filter_node_name,
                  BlockdevOnError on_source_error,
                  BlockdevOnError on_target_error,
                  int creation_flags,
@@ -342,18 +554,13 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
 {
    int64_t len;
    BackupBlockJob *job = NULL;
+    int ret;
    int64_t cluster_size;
-    BdrvRequestFlags write_flags;
-    BlockDriverState *backup_top = NULL;
-    BlockCopyState *bcs = NULL;
+    HBitmap *copy_bitmap = NULL;

    assert(bs);
    assert(target);

-    /* QMP interface protects us from these cases */
-    assert(sync_mode != MIRROR_SYNC_MODE_INCREMENTAL);
-    assert(sync_bitmap || sync_mode != MIRROR_SYNC_MODE_BITMAP);
-
    if (bs == target) {
        error_setg(errp, "Source and target cannot be the same");
        return NULL;
@@ -371,7 +578,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
        return NULL;
    }

-    if (compress && !block_driver_can_compress(target->drv)) {
+    if (compress && target->drv->bdrv_co_pwritev_compressed == NULL) {
        error_setg(errp, "Compression is not supported for this drive %s",
                   bdrv_get_device_name(target));
        return NULL;
@@ -385,17 +592,23 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
        return NULL;
    }

-    if (sync_bitmap) {
-        /* If we need to write to this bitmap, check that we can: */
-        if (bitmap_mode != BITMAP_SYNC_MODE_NEVER &&
-            bdrv_dirty_bitmap_check(sync_bitmap, BDRV_BITMAP_DEFAULT, errp)) {
+    if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
+        if (!sync_bitmap) {
+            error_setg(errp, "must provide a valid bitmap name for "
+                             "\"incremental\" sync mode");
            return NULL;
        }

        /* Create a new bitmap, and freeze/disable this one. */
-        if (bdrv_dirty_bitmap_create_successor(sync_bitmap, errp) < 0) {
+        if (bdrv_dirty_bitmap_create_successor(bs, sync_bitmap, errp) < 0) {
            return NULL;
        }
+    } else if (sync_bitmap) {
+        error_setg(errp,
+                   "a sync_bitmap was provided to backup_run, "
+                   "but received an incompatible sync_mode (%s)",
+                   MirrorSyncMode_str(sync_mode));
+        return NULL;
    }

    len = bdrv_getlength(bs);
@@ -410,63 +623,72 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
        goto error;
    }

-    /*
-     * If source is in backing chain of target assume that target is going to be
-     * used for "image fleecing", i.e. it should represent a kind of snapshot of
-     * source at backup-start point in time. And target is going to be read by
-     * somebody (for example, used as NBD export) during backup job.
-     *
-     * In this case, we need to add BDRV_REQ_SERIALISING write flag to avoid
-     * intersection of backup writes and third party reads from target,
-     * otherwise reading from target we may occasionally read already updated by
-     * guest data.
-     *
-     * For more information see commit f8d59dfb40bb and test
-     * tests/qemu-iotests/222
-     */
-    write_flags = (bdrv_chain_contains(target, bs) ? BDRV_REQ_SERIALISING : 0) |
-                  (compress ? BDRV_REQ_WRITE_COMPRESSED : 0),
-
-    backup_top = bdrv_backup_top_append(bs, target, filter_node_name,
-                                        cluster_size, write_flags, &bcs, errp);
-    if (!backup_top) {
-        goto error;
-    }
+    copy_bitmap = hbitmap_alloc(len, ctz32(cluster_size));

    /* job->len is fixed, so we can't allow resize */
-    job = block_job_create(job_id, &backup_job_driver, txn, backup_top,
-                           0, BLK_PERM_ALL,
+    job = block_job_create(job_id, &backup_job_driver, txn, bs,
+                           BLK_PERM_CONSISTENT_READ,
+                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
+                           BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD,
                           speed, creation_flags, cb, opaque, errp);
    if (!job) {
        goto error;
    }

-    job->backup_top = backup_top;
-    job->source_bs = bs;
+    /* The target must match the source in size, so no resize here either */
+    job->target = blk_new(job->common.job.aio_context,
+                          BLK_PERM_WRITE,
+                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
+                          BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD);
+    ret = blk_insert_bs(job->target, target, errp);
+    if (ret < 0) {
+        goto error;
+    }
+
    job->on_source_error = on_source_error;
    job->on_target_error = on_target_error;
    job->sync_mode = sync_mode;
-    job->sync_bitmap = sync_bitmap;
-    job->bitmap_mode = bitmap_mode;
-    job->bcs = bcs;
+    job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
+                       sync_bitmap : NULL;
+    job->compress = compress;
+
+    /* Detect image-fleecing (and similar) schemes */
+    job->serialize_target_writes = bdrv_chain_contains(target, bs);
    job->cluster_size = cluster_size;
-    job->len = len;
+    job->copy_bitmap = copy_bitmap;
+    copy_bitmap = NULL;
+    job->copy_range_size = MIN_NON_ZERO(blk_get_max_transfer(job->common.blk),
+                                        blk_get_max_transfer(job->target));
+    job->copy_range_size = QEMU_ALIGN_DOWN(job->copy_range_size,
+                                           job->cluster_size);
+    /*
+     * Set use_copy_range, consider the following:
+     * 1. Compression is not supported for copy_range.
+     * 2. copy_range does not respect max_transfer (it's a TODO), so we factor
+     *    that in here. If max_transfer is smaller than the job->cluster_size,
+     *    we do not use copy_range (in that case it's zero after aligning down
+     *    above).
+     */
+    job->use_copy_range = !compress && job->copy_range_size > 0;

-    block_copy_set_progress_callback(bcs, backup_progress_bytes_callback, job);
-    block_copy_set_progress_meter(bcs, &job->common.job.progress);
-
-    /* Required permissions are already taken by backup-top target */
+    /* Required permissions are already taken with target's blk_new() */
    block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
                       &error_abort);
+    job->len = len;

    return &job->common;

 error:
-    if (sync_bitmap) {
-        bdrv_reclaim_dirty_bitmap(sync_bitmap, NULL);
+    if (copy_bitmap) {
+        assert(!job || !job->copy_bitmap);
+        hbitmap_free(copy_bitmap);
    }
-    if (backup_top) {
-        bdrv_backup_top_drop(backup_top);
+    if (sync_bitmap) {
+        bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
+    }
+    if (job) {
+        backup_clean(&job->common.job);
+        job_early_fail(&job->common.job);
    }

    return NULL;
@@ -28,14 +28,10 @@
 #include "qemu/cutils.h"
 #include "qemu/config-file.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
-#include "qapi/qapi-visit-block-core.h"
 #include "qapi/qmp/qdict.h"
-#include "qapi/qmp/qlist.h"
 #include "qapi/qmp/qstring.h"
-#include "qapi/qobject-input-visitor.h"
 #include "sysemu/qtest.h"

 typedef struct BDRVBlkdebugState {
@@ -48,9 +44,6 @@ typedef struct BDRVBlkdebugState {
    uint64_t opt_discard;
    uint64_t max_discard;

-    uint64_t take_child_perms;
-    uint64_t unshare_child_perms;
-
    /* For blkdebug_refresh_filename() */
    char *config_file;

@@ -351,69 +344,6 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
    qdict_put_str(options, "x-image", filename);
 }

-static int blkdebug_parse_perm_list(uint64_t *dest, QDict *options,
-                                    const char *prefix, Error **errp)
-{
-    int ret = 0;
-    QDict *subqdict = NULL;
-    QObject *crumpled_subqdict = NULL;
-    Visitor *v = NULL;
-    BlockPermissionList *perm_list = NULL, *element;
-    Error *local_err = NULL;
-
-    *dest = 0;
-
-    qdict_extract_subqdict(options, &subqdict, prefix);
-    if (!qdict_size(subqdict)) {
-        goto out;
-    }
-
-    crumpled_subqdict = qdict_crumple(subqdict, errp);
-    if (!crumpled_subqdict) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    v = qobject_input_visitor_new(crumpled_subqdict);
-    visit_type_BlockPermissionList(v, NULL, &perm_list, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto out;
-    }
-
-    for (element = perm_list; element; element = element->next) {
-        *dest |= bdrv_qapi_perm_to_blk_perm(element->value);
-    }
-
-out:
-    qapi_free_BlockPermissionList(perm_list);
-    visit_free(v);
-    qobject_unref(subqdict);
-    qobject_unref(crumpled_subqdict);
-    return ret;
-}
-
-static int blkdebug_parse_perms(BDRVBlkdebugState *s, QDict *options,
-                                Error **errp)
-{
-    int ret;
-
-    ret = blkdebug_parse_perm_list(&s->take_child_perms, options,
-                                   "take-child-perms.", errp);
-    if (ret < 0) {
-        return ret;
-    }
-
-    ret = blkdebug_parse_perm_list(&s->unshare_child_perms, options,
-                                   "unshare-child-perms.", errp);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return 0;
-}
-
 static QemuOptsList runtime_opts = {
    .name = "blkdebug",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
@@ -489,12 +419,6 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
    /* Set initial state */
    s->state = 1;

-    /* Parse permissions modifiers before opening the image file */
-    ret = blkdebug_parse_perms(s, options, errp);
-    if (ret < 0) {
-        goto out;
-    }
-
    /* Open the image file */
    bs->file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options, "image",
                               bs, &child_file, false, &local_err);
@@ -992,21 +916,6 @@ static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state,
    return 0;
 }

-static void blkdebug_child_perm(BlockDriverState *bs, BdrvChild *c,
-                                const BdrvChildRole *role,
-                                BlockReopenQueue *reopen_queue,
-                                uint64_t perm, uint64_t shared,
-                                uint64_t *nperm, uint64_t *nshared)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-
-    bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared,
-                              nperm, nshared);
-
-    *nperm |= s->take_child_perms;
-    *nshared &= ~s->unshare_child_perms;
-}
-
 static const char *const blkdebug_strong_runtime_opts[] = {
    "config",
    "inject-error.",
@@ -1031,7 +940,7 @@ static BlockDriver bdrv_blkdebug = {
    .bdrv_file_open         = blkdebug_open,
    .bdrv_close             = blkdebug_close,
    .bdrv_reopen_prepare    = blkdebug_reopen_prepare,
-    .bdrv_child_perm        = blkdebug_child_perm,
+    .bdrv_child_perm        = bdrv_filter_default_perms,

    .bdrv_getlength         = blkdebug_getlength,
    .bdrv_refresh_filename  = blkdebug_refresh_filename,
@@ -126,12 +126,6 @@ static int coroutine_fn blkreplay_co_flush(BlockDriverState *bs)
    return ret;
 }

-static int blkreplay_snapshot_goto(BlockDriverState *bs,
-                                   const char *snapshot_id)
-{
-    return bdrv_snapshot_goto(bs->file->bs, snapshot_id, NULL);
-}
-
 static BlockDriver bdrv_blkreplay = {
    .format_name            = "blkreplay",
    .instance_size          = 0,
@@ -146,8 +140,6 @@ static BlockDriver bdrv_blkreplay = {
    .bdrv_co_pwrite_zeroes  = blkreplay_co_pwrite_zeroes,
    .bdrv_co_pdiscard       = blkreplay_co_pdiscard,
    .bdrv_co_flush          = blkreplay_co_flush,
-
-    .bdrv_snapshot_goto     = blkreplay_snapshot_goto,
 };

 static void bdrv_blkreplay_init(void)
@@ -268,18 +268,18 @@ static int blkverify_co_flush(BlockDriverState *bs)
    return bdrv_co_flush(s->test_file->bs);
 }

-static bool blkverify_recurse_can_replace(BlockDriverState *bs,
-                                          BlockDriverState *to_replace)
+static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
+                                                  BlockDriverState *candidate)
 {
    BDRVBlkverifyState *s = bs->opaque;

-    /*
-     * blkverify quits the whole qemu process if there is a mismatch
-     * between bs->file->bs and s->test_file->bs.  Therefore, we know
-     * know that both must match bs and we can recurse down to either.
-     */
-    return bdrv_recurse_can_replace(bs->file->bs, to_replace) ||
-           bdrv_recurse_can_replace(s->test_file->bs, to_replace);
+    bool perm = bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
+
+    if (perm) {
+        return true;
+    }
+
+    return bdrv_recurse_is_first_non_filter(s->test_file->bs, candidate);
 }

 static void blkverify_refresh_filename(BlockDriverState *bs)
@@ -327,7 +327,7 @@ static BlockDriver bdrv_blkverify = {
    .bdrv_co_flush                    = blkverify_co_flush,

    .is_filter                        = true,
-    .bdrv_recurse_can_replace         = blkverify_recurse_can_replace,
+    .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,
 };

 static void bdrv_blkverify_init(void)
@@ -15,15 +15,11 @@
 #include "block/block_int.h"
 #include "block/blockjob.h"
 #include "block/throttle-groups.h"
-#include "hw/qdev-core.h"
 #include "sysemu/blockdev.h"
-#include "sysemu/runstate.h"
 #include "sysemu/sysemu.h"
-#include "sysemu/replay.h"
 #include "qapi/error.h"
 #include "qapi/qapi-events-block.h"
 #include "qemu/id.h"
-#include "qemu/main-loop.h"
 #include "qemu/option.h"
 #include "trace.h"
 #include "migration/misc.h"
@@ -83,9 +79,6 @@ struct BlockBackend {
    QLIST_HEAD(, BlockBackendAioNotifier) aio_notifiers;

    int quiesce_counter;
-    CoQueue queued_requests;
-    bool disable_request_queuing;
-
    VMChangeStateEntry *vmsh;
    bool force_allow_inactivate;

@@ -346,7 +339,6 @@ BlockBackend *blk_new(AioContext *ctx, uint64_t perm, uint64_t shared_perm)

    block_acct_init(&blk->stats);

-    qemu_co_queue_init(&blk->queued_requests);
    notifier_list_init(&blk->remove_bs_notifiers);
    notifier_list_init(&blk->insert_bs_notifiers);
    QLIST_INIT(&blk->aio_notifiers);
@@ -1104,11 +1096,6 @@ void blk_set_allow_aio_context_change(BlockBackend *blk, bool allow)
    blk->allow_aio_context_change = allow;
 }

-void blk_set_disable_request_queuing(BlockBackend *blk, bool disable)
-{
-    blk->disable_request_queuing = disable;
-}
-
 static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
                                  size_t size)
 {
@@ -1140,30 +1127,13 @@ static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
    return 0;
 }

-/* To be called between exactly one pair of blk_inc/dec_in_flight() */
-static void coroutine_fn blk_wait_while_drained(BlockBackend *blk)
-{
-    assert(blk->in_flight > 0);
-
-    if (blk->quiesce_counter && !blk->disable_request_queuing) {
-        blk_dec_in_flight(blk);
-        qemu_co_queue_wait(&blk->queued_requests, NULL);
-        blk_inc_in_flight(blk);
-    }
-}
-
-/* To be called between exactly one pair of blk_inc/dec_in_flight() */
-static int coroutine_fn
-blk_do_preadv(BlockBackend *blk, int64_t offset, unsigned int bytes,
-              QEMUIOVector *qiov, BdrvRequestFlags flags)
+int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
+                               unsigned int bytes, QEMUIOVector *qiov,
+                               BdrvRequestFlags flags)
 {
    int ret;
-    BlockDriverState *bs;
+    BlockDriverState *bs = blk_bs(blk);

-    blk_wait_while_drained(blk);
-
-    /* Call blk_bs() only after waiting, the graph may have changed */
-    bs = blk_bs(blk);
    trace_blk_co_preadv(blk, bs, offset, bytes, flags);

    ret = blk_check_byte_request(blk, offset, bytes);
@@ -1184,32 +1154,13 @@ blk_do_preadv(BlockBackend *blk, int64_t offset, unsigned int bytes,
    return ret;
 }

-int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
-                               unsigned int bytes, QEMUIOVector *qiov,
-                               BdrvRequestFlags flags)
+int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
+                                unsigned int bytes, QEMUIOVector *qiov,
+                                BdrvRequestFlags flags)
 {
    int ret;
+    BlockDriverState *bs = blk_bs(blk);

-    blk_inc_in_flight(blk);
-    ret = blk_do_preadv(blk, offset, bytes, qiov, flags);
-    blk_dec_in_flight(blk);
-
-    return ret;
-}
-
-/* To be called between exactly one pair of blk_inc/dec_in_flight() */
-static int coroutine_fn
-blk_do_pwritev_part(BlockBackend *blk, int64_t offset, unsigned int bytes,
-                    QEMUIOVector *qiov, size_t qiov_offset,
-                    BdrvRequestFlags flags)
-{
-    int ret;
-    BlockDriverState *bs;
-
-    blk_wait_while_drained(blk);
-
-    /* Call blk_bs() only after waiting, the graph may have changed */
-    bs = blk_bs(blk);
    trace_blk_co_pwritev(blk, bs, offset, bytes, flags);

    ret = blk_check_byte_request(blk, offset, bytes);
@@ -1228,33 +1179,11 @@ blk_do_pwritev_part(BlockBackend *blk, int64_t offset, unsigned int bytes,
        flags |= BDRV_REQ_FUA;
    }

-    ret = bdrv_co_pwritev_part(blk->root, offset, bytes, qiov, qiov_offset,
-                               flags);
+    ret = bdrv_co_pwritev(blk->root, offset, bytes, qiov, flags);
    bdrv_dec_in_flight(bs);
    return ret;
 }

-int coroutine_fn blk_co_pwritev_part(BlockBackend *blk, int64_t offset,
-                                     unsigned int bytes,
-                                     QEMUIOVector *qiov, size_t qiov_offset,
-                                     BdrvRequestFlags flags)
-{
-    int ret;
-
-    blk_inc_in_flight(blk);
-    ret = blk_do_pwritev_part(blk, offset, bytes, qiov, qiov_offset, flags);
-    blk_dec_in_flight(blk);
-
-    return ret;
-}
-
-int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
-                                unsigned int bytes, QEMUIOVector *qiov,
-                                BdrvRequestFlags flags)
-{
-    return blk_co_pwritev_part(blk, offset, bytes, qiov, 0, flags);
-}
-
 typedef struct BlkRwCo {
    BlockBackend *blk;
    int64_t offset;
@@ -1268,7 +1197,7 @@ static void blk_read_entry(void *opaque)
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

-    rwco->ret = blk_do_preadv(rwco->blk, rwco->offset, qiov->size,
+    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, qiov->size,
                              qiov, rwco->flags);
    aio_wait_kick();
 }
@@ -1278,8 +1207,8 @@ static void blk_write_entry(void *opaque)
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

-    rwco->ret = blk_do_pwritev_part(rwco->blk, rwco->offset, qiov->size,
-                                    qiov, 0, rwco->flags);
+    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, qiov->size,
+                               qiov, rwco->flags);
    aio_wait_kick();
 }

@@ -1296,7 +1225,6 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
        .ret    = NOT_DONE,
    };

-    blk_inc_in_flight(blk);
    if (qemu_in_coroutine()) {
        /* Fast-path if already in coroutine context */
        co_entry(&rwco);
@@ -1305,11 +1233,26 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
        bdrv_coroutine_enter(blk_bs(blk), co);
        BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
    }
-    blk_dec_in_flight(blk);

    return rwco.ret;
 }

+int blk_pread_unthrottled(BlockBackend *blk, int64_t offset, uint8_t *buf,
+                          int count)
+{
+    int ret;
+
+    ret = blk_check_byte_request(blk, offset, count);
+    if (ret < 0) {
+        return ret;
+    }
+
+    blk_root_drained_begin(blk->root);
+    ret = blk_pread(blk, offset, buf, count);
+    blk_root_drained_end(blk->root, NULL);
+    return ret;
+}
+
 int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                      int bytes, BdrvRequestFlags flags)
 {
@@ -1353,8 +1296,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
    acb->blk = blk;
    acb->ret = ret;

-    replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
-                                     error_callback_bh, acb);
+    aio_bh_schedule_oneshot(blk_get_aio_context(blk), error_callback_bh, acb);
    return &acb->common;
 }

@@ -1410,8 +1352,8 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,

    acb->has_returned = true;
    if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(blk_get_aio_context(blk),
-                                         blk_aio_complete_bh, acb);
+        aio_bh_schedule_oneshot(blk_get_aio_context(blk),
+                                blk_aio_complete_bh, acb);
    }

    return &acb->common;
@@ -1424,7 +1366,7 @@ static void blk_aio_read_entry(void *opaque)
    QEMUIOVector *qiov = rwco->iobuf;

    assert(qiov->size == acb->bytes);
-    rwco->ret = blk_do_preadv(rwco->blk, rwco->offset, acb->bytes,
+    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, acb->bytes,
                              qiov, rwco->flags);
    blk_aio_complete(acb);
 }
@@ -1436,8 +1378,8 @@ static void blk_aio_write_entry(void *opaque)
    QEMUIOVector *qiov = rwco->iobuf;

    assert(!qiov || qiov->size == acb->bytes);
-    rwco->ret = blk_do_pwritev_part(rwco->blk, rwco->offset, acb->bytes,
-                                    qiov, 0, rwco->flags);
+    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, acb->bytes,
+                               qiov, rwco->flags);
    blk_aio_complete(acb);
 }

@@ -1512,6 +1454,38 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset,
                        blk_aio_write_entry, flags, cb, opaque);
 }

+static void blk_aio_flush_entry(void *opaque)
+{
+    BlkAioEmAIOCB *acb = opaque;
+    BlkRwCo *rwco = &acb->rwco;
+
+    rwco->ret = blk_co_flush(rwco->blk);
+    blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_flush(BlockBackend *blk,
+                          BlockCompletionFunc *cb, void *opaque)
+{
+    return blk_aio_prwv(blk, 0, 0, NULL, blk_aio_flush_entry, 0, cb, opaque);
+}
+
+static void blk_aio_pdiscard_entry(void *opaque)
+{
+    BlkAioEmAIOCB *acb = opaque;
+    BlkRwCo *rwco = &acb->rwco;
+
+    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, acb->bytes);
+    blk_aio_complete(acb);
+}
+
+BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk,
+                             int64_t offset, int bytes,
+                             BlockCompletionFunc *cb, void *opaque)
+{
+    return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_pdiscard_entry, 0,
+                        cb, opaque);
+}
+
 void blk_aio_cancel(BlockAIOCB *acb)
 {
    bdrv_aio_cancel(acb);
@@ -1522,12 +1496,8 @@ void blk_aio_cancel_async(BlockAIOCB *acb)
    bdrv_aio_cancel_async(acb);
 }

-/* To be called between exactly one pair of blk_inc/dec_in_flight() */
-static int coroutine_fn
-blk_do_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
+int blk_co_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
 {
-    blk_wait_while_drained(blk);
-
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }
@@ -1540,7 +1510,8 @@ static void blk_ioctl_entry(void *opaque)
    BlkRwCo *rwco = opaque;
    QEMUIOVector *qiov = rwco->iobuf;

-    rwco->ret = blk_do_ioctl(rwco->blk, rwco->offset, qiov->iov[0].iov_base);
+    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset,
+                             qiov->iov[0].iov_base);
    aio_wait_kick();
 }

@@ -1554,7 +1525,7 @@ static void blk_aio_ioctl_entry(void *opaque)
    BlkAioEmAIOCB *acb = opaque;
    BlkRwCo *rwco = &acb->rwco;

-    rwco->ret = blk_do_ioctl(rwco->blk, rwco->offset, rwco->iobuf);
+    rwco->ret = blk_co_ioctl(rwco->blk, rwco->offset, rwco->iobuf);

    blk_aio_complete(acb);
 }
@@ -1565,15 +1536,9 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
    return blk_aio_prwv(blk, req, 0, buf, blk_aio_ioctl_entry, 0, cb, opaque);
 }

-/* To be called between exactly one pair of blk_inc/dec_in_flight() */
-static int coroutine_fn
-blk_do_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
 {
-    int ret;
-
-    blk_wait_while_drained(blk);
-
-    ret = blk_check_byte_request(blk, offset, bytes);
+    int ret = blk_check_byte_request(blk, offset, bytes);
    if (ret < 0) {
        return ret;
    }
@@ -1581,53 +1546,8 @@ blk_do_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
    return bdrv_co_pdiscard(blk->root, offset, bytes);
 }

-static void blk_aio_pdiscard_entry(void *opaque)
+int blk_co_flush(BlockBackend *blk)
 {
-    BlkAioEmAIOCB *acb = opaque;
-    BlkRwCo *rwco = &acb->rwco;
-
-    rwco->ret = blk_do_pdiscard(rwco->blk, rwco->offset, acb->bytes);
-    blk_aio_complete(acb);
-}
-
-BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk,
-                             int64_t offset, int bytes,
-                             BlockCompletionFunc *cb, void *opaque)
-{
-    return blk_aio_prwv(blk, offset, bytes, NULL, blk_aio_pdiscard_entry, 0,
-                        cb, opaque);
-}
-
-int coroutine_fn blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
-{
-    int ret;
-
-    blk_inc_in_flight(blk);
-    ret = blk_do_pdiscard(blk, offset, bytes);
-    blk_dec_in_flight(blk);
-
-    return ret;
-}
-
-static void blk_pdiscard_entry(void *opaque)
-{
-    BlkRwCo *rwco = opaque;
-    QEMUIOVector *qiov = rwco->iobuf;
-
-    rwco->ret = blk_do_pdiscard(rwco->blk, rwco->offset, qiov->size);
-    aio_wait_kick();
-}
-
-int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
-{
-    return blk_prw(blk, offset, NULL, bytes, blk_pdiscard_entry, 0);
-}
-
-/* To be called between exactly one pair of blk_inc/dec_in_flight() */
-static int coroutine_fn blk_do_flush(BlockBackend *blk)
-{
-    blk_wait_while_drained(blk);
-
    if (!blk_is_available(blk)) {
        return -ENOMEDIUM;
    }
@@ -1635,36 +1555,10 @@ static int coroutine_fn blk_do_flush(BlockBackend *blk)
    return bdrv_co_flush(blk_bs(blk));
 }

-static void blk_aio_flush_entry(void *opaque)
-{
-    BlkAioEmAIOCB *acb = opaque;
-    BlkRwCo *rwco = &acb->rwco;
-
-    rwco->ret = blk_do_flush(rwco->blk);
-    blk_aio_complete(acb);
-}
-
-BlockAIOCB *blk_aio_flush(BlockBackend *blk,
-                          BlockCompletionFunc *cb, void *opaque)
-{
-    return blk_aio_prwv(blk, 0, 0, NULL, blk_aio_flush_entry, 0, cb, opaque);
-}
-
-int coroutine_fn blk_co_flush(BlockBackend *blk)
-{
-    int ret;
-
-    blk_inc_in_flight(blk);
-    ret = blk_do_flush(blk);
-    blk_dec_in_flight(blk);
-
-    return ret;
-}
-
 static void blk_flush_entry(void *opaque)
 {
    BlkRwCo *rwco = opaque;
-    rwco->ret = blk_do_flush(rwco->blk);
+    rwco->ret = blk_co_flush(rwco->blk);
    aio_wait_kick();
 }

@@ -2136,15 +2030,29 @@ int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
                   BDRV_REQ_WRITE_COMPRESSED);
 }

-int blk_truncate(BlockBackend *blk, int64_t offset, bool exact,
-                 PreallocMode prealloc, Error **errp)
+int blk_truncate(BlockBackend *blk, int64_t offset, PreallocMode prealloc,
+                 Error **errp)
 {
    if (!blk_is_available(blk)) {
        error_setg(errp, "No medium inserted");
        return -ENOMEDIUM;
    }

-    return bdrv_truncate(blk->root, offset, exact, prealloc, errp);
+    return bdrv_truncate(blk->root, offset, prealloc, errp);
+}
+
+static void blk_pdiscard_entry(void *opaque)
+{
+    BlkRwCo *rwco = opaque;
+    QEMUIOVector *qiov = rwco->iobuf;
+
+    rwco->ret = blk_co_pdiscard(rwco->blk, rwco->offset, qiov->size);
+    aio_wait_kick();
+}
+
+int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
+{
+    return blk_prw(blk, offset, NULL, bytes, blk_pdiscard_entry, 0);
 }

 int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
@@ -2340,9 +2248,6 @@ static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter)
        if (blk->dev_ops && blk->dev_ops->drained_end) {
            blk->dev_ops->drained_end(blk->dev_opaque);
        }
-        while (qemu_co_enter_next(&blk->queued_requests, NULL)) {
-            /* Resume all queued requests */
-        }
    }
 }

@@ -1,578 +0,0 @@
-/*
- * block_copy API
- *
- * Copyright (C) 2013 Proxmox Server Solutions
- * Copyright (c) 2019 Virtuozzo International GmbH.
- *
- * Authors:
- *  Dietmar Maurer (dietmar@proxmox.com)
- *  Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/osdep.h"
-
-#include "trace.h"
-#include "qapi/error.h"
-#include "block/block-copy.h"
-#include "sysemu/block-backend.h"
-#include "qemu/units.h"
-
-#define BLOCK_COPY_MAX_COPY_RANGE (16 * MiB)
-#define BLOCK_COPY_MAX_BUFFER (1 * MiB)
-#define BLOCK_COPY_MAX_MEM (128 * MiB)
-
-typedef struct BlockCopyInFlightReq {
-    int64_t offset;
-    int64_t bytes;
-    QLIST_ENTRY(BlockCopyInFlightReq) list;
-    CoQueue wait_queue; /* coroutines blocked on this request */
-} BlockCopyInFlightReq;
-
-typedef struct BlockCopyState {
-    /*
-     * BdrvChild objects are not owned or managed by block-copy. They are
-     * provided by block-copy user and user is responsible for appropriate
-     * permissions on these children.
-     */
-    BdrvChild *source;
-    BdrvChild *target;
-    BdrvDirtyBitmap *copy_bitmap;
-    int64_t in_flight_bytes;
-    int64_t cluster_size;
-    bool use_copy_range;
-    int64_t copy_size;
-    uint64_t len;
-    QLIST_HEAD(, BlockCopyInFlightReq) inflight_reqs;
-
-    BdrvRequestFlags write_flags;
-
-    /*
-     * skip_unallocated:
-     *
-     * Used by sync=top jobs, which first scan the source node for unallocated
-     * areas and clear them in the copy_bitmap.  During this process, the bitmap
-     * is thus not fully initialized: It may still have bits set for areas that
-     * are unallocated and should actually not be copied.
-     *
-     * This is indicated by skip_unallocated.
-     *
-     * In this case, block_copy() will query the source’s allocation status,
-     * skip unallocated regions, clear them in the copy_bitmap, and invoke
-     * block_copy_reset_unallocated() every time it does.
-     */
-    bool skip_unallocated;
-
-    ProgressMeter *progress;
-    /* progress_bytes_callback: called when some copying progress is done. */
-    ProgressBytesCallbackFunc progress_bytes_callback;
-    void *progress_opaque;
-
-    SharedResource *mem;
-} BlockCopyState;
-
-static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s,
-                                                           int64_t offset,
-                                                           int64_t bytes)
-{
-    BlockCopyInFlightReq *req;
-
-    QLIST_FOREACH(req, &s->inflight_reqs, list) {
-        if (offset + bytes > req->offset && offset < req->offset + req->bytes) {
-            return req;
-        }
-    }
-
-    return NULL;
-}
-
-/*
- * If there are no intersecting requests return false. Otherwise, wait for the
- * first found intersecting request to finish and return true.
- */
-static bool coroutine_fn block_copy_wait_one(BlockCopyState *s, int64_t offset,
-                                             int64_t bytes)
-{
-    BlockCopyInFlightReq *req = find_conflicting_inflight_req(s, offset, bytes);
-
-    if (!req) {
-        return false;
-    }
-
-    qemu_co_queue_wait(&req->wait_queue, NULL);
-
-    return true;
-}
-
-/* Called only on full-dirty region */
-static void block_copy_inflight_req_begin(BlockCopyState *s,
-                                          BlockCopyInFlightReq *req,
-                                          int64_t offset, int64_t bytes)
-{
-    assert(!find_conflicting_inflight_req(s, offset, bytes));
-
-    bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
-    s->in_flight_bytes += bytes;
-
-    req->offset = offset;
-    req->bytes = bytes;
-    qemu_co_queue_init(&req->wait_queue);
-    QLIST_INSERT_HEAD(&s->inflight_reqs, req, list);
-}
-
-/*
- * block_copy_inflight_req_shrink
- *
- * Drop the tail of the request to be handled later. Set dirty bits back and
- * wake up all requests waiting for us (may be some of them are not intersecting
- * with shrunk request)
- */
-static void coroutine_fn block_copy_inflight_req_shrink(BlockCopyState *s,
-        BlockCopyInFlightReq *req, int64_t new_bytes)
-{
-    if (new_bytes == req->bytes) {
-        return;
-    }
-
-    assert(new_bytes > 0 && new_bytes < req->bytes);
-
-    s->in_flight_bytes -= req->bytes - new_bytes;
-    bdrv_set_dirty_bitmap(s->copy_bitmap,
-                          req->offset + new_bytes, req->bytes - new_bytes);
-
-    req->bytes = new_bytes;
-    qemu_co_queue_restart_all(&req->wait_queue);
-}
-
-static void coroutine_fn block_copy_inflight_req_end(BlockCopyState *s,
-                                                     BlockCopyInFlightReq *req,
-                                                     int ret)
-{
-    s->in_flight_bytes -= req->bytes;
-    if (ret < 0) {
-        bdrv_set_dirty_bitmap(s->copy_bitmap, req->offset, req->bytes);
-    }
-    QLIST_REMOVE(req, list);
-    qemu_co_queue_restart_all(&req->wait_queue);
-}
-
-void block_copy_state_free(BlockCopyState *s)
-{
-    if (!s) {
-        return;
-    }
-
-    bdrv_release_dirty_bitmap(s->copy_bitmap);
-    shres_destroy(s->mem);
-    g_free(s);
-}
-
-static uint32_t block_copy_max_transfer(BdrvChild *source, BdrvChild *target)
-{
-    return MIN_NON_ZERO(INT_MAX,
-                        MIN_NON_ZERO(source->bs->bl.max_transfer,
-                                     target->bs->bl.max_transfer));
-}
-
-BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
-                                     int64_t cluster_size,
-                                     BdrvRequestFlags write_flags, Error **errp)
-{
-    BlockCopyState *s;
-    BdrvDirtyBitmap *copy_bitmap;
-
-    copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL,
-                                           errp);
-    if (!copy_bitmap) {
-        return NULL;
-    }
-    bdrv_disable_dirty_bitmap(copy_bitmap);
-
-    s = g_new(BlockCopyState, 1);
-    *s = (BlockCopyState) {
-        .source = source,
-        .target = target,
-        .copy_bitmap = copy_bitmap,
-        .cluster_size = cluster_size,
-        .len = bdrv_dirty_bitmap_size(copy_bitmap),
-        .write_flags = write_flags,
-        .mem = shres_create(BLOCK_COPY_MAX_MEM),
-    };
-
-    if (block_copy_max_transfer(source, target) < cluster_size) {
-        /*
-         * copy_range does not respect max_transfer. We don't want to bother
-         * with requests smaller than block-copy cluster size, so fallback to
-         * buffered copying (read and write respect max_transfer on their
-         * behalf).
-         */
-        s->use_copy_range = false;
-        s->copy_size = cluster_size;
-    } else if (write_flags & BDRV_REQ_WRITE_COMPRESSED) {
-        /* Compression supports only cluster-size writes and no copy-range. */
-        s->use_copy_range = false;
-        s->copy_size = cluster_size;
-    } else {
-        /*
-         * We enable copy-range, but keep small copy_size, until first
-         * successful copy_range (look at block_copy_do_copy).
-         */
-        s->use_copy_range = true;
-        s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
-    }
-
-    QLIST_INIT(&s->inflight_reqs);
-
-    return s;
-}
-
-void block_copy_set_progress_callback(
-        BlockCopyState *s,
-        ProgressBytesCallbackFunc progress_bytes_callback,
-        void *progress_opaque)
-{
-    s->progress_bytes_callback = progress_bytes_callback;
-    s->progress_opaque = progress_opaque;
-}
-
-void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm)
-{
-    s->progress = pm;
-}
-
-/*
- * block_copy_do_copy
- *
- * Do copy of cluster-aligned chunk. Requested region is allowed to exceed
- * s->len only to cover last cluster when s->len is not aligned to clusters.
- *
- * No sync here: nor bitmap neighter intersecting requests handling, only copy.
- *
- * Returns 0 on success.
- */
-static int coroutine_fn block_copy_do_copy(BlockCopyState *s,
-                                           int64_t offset, int64_t bytes,
-                                           bool zeroes, bool *error_is_read)
-{
-    int ret;
-    int64_t nbytes = MIN(offset + bytes, s->len) - offset;
-    void *bounce_buffer = NULL;
-
-    assert(offset >= 0 && bytes > 0 && INT64_MAX - offset >= bytes);
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-    assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
-    assert(offset < s->len);
-    assert(offset + bytes <= s->len ||
-           offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size));
-    assert(nbytes < INT_MAX);
-
-    if (zeroes) {
-        ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags &
-                                    ~BDRV_REQ_WRITE_COMPRESSED);
-        if (ret < 0) {
-            trace_block_copy_write_zeroes_fail(s, offset, ret);
-            if (error_is_read) {
-                *error_is_read = false;
-            }
-        }
-        return ret;
-    }
-
-    if (s->use_copy_range) {
-        ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes,
-                                 0, s->write_flags);
-        if (ret < 0) {
-            trace_block_copy_copy_range_fail(s, offset, ret);
-            s->use_copy_range = false;
-            s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
-            /* Fallback to read+write with allocated buffer */
-        } else {
-            if (s->use_copy_range) {
-                /*
-                 * Successful copy-range. Now increase copy_size.  copy_range
-                 * does not respect max_transfer (it's a TODO), so we factor
-                 * that in here.
-                 *
-                 * Note: we double-check s->use_copy_range for the case when
-                 * parallel block-copy request unsets it during previous
-                 * bdrv_co_copy_range call.
-                 */
-                s->copy_size =
-                        MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE),
-                            QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source,
-                                                                    s->target),
-                                            s->cluster_size));
-            }
-            goto out;
-        }
-    }
-
-    /*
-     * In case of failed copy_range request above, we may proceed with buffered
-     * request larger than BLOCK_COPY_MAX_BUFFER. Still, further requests will
-     * be properly limited, so don't care too much. Moreover the most likely
-     * case (copy_range is unsupported for the configuration, so the very first
-     * copy_range request fails) is handled by setting large copy_size only
-     * after first successful copy_range.
-     */
-
-    bounce_buffer = qemu_blockalign(s->source->bs, nbytes);
-
-    ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0);
-    if (ret < 0) {
-        trace_block_copy_read_fail(s, offset, ret);
-        if (error_is_read) {
-            *error_is_read = true;
-        }
-        goto out;
-    }
-
-    ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer,
-                         s->write_flags);
-    if (ret < 0) {
-        trace_block_copy_write_fail(s, offset, ret);
-        if (error_is_read) {
-            *error_is_read = false;
-        }
-        goto out;
-    }
-
-out:
-    qemu_vfree(bounce_buffer);
-
-    return ret;
-}
-
-static int block_copy_block_status(BlockCopyState *s, int64_t offset,
-                                   int64_t bytes, int64_t *pnum)
-{
-    int64_t num;
-    BlockDriverState *base;
-    int ret;
-
-    if (s->skip_unallocated && s->source->bs->backing) {
-        base = s->source->bs->backing->bs;
-    } else {
-        base = NULL;
-    }
-
-    ret = bdrv_block_status_above(s->source->bs, base, offset, bytes, &num,
-                                  NULL, NULL);
-    if (ret < 0 || num < s->cluster_size) {
-        /*
-         * On error or if failed to obtain large enough chunk just fallback to
-         * copy one cluster.
-         */
-        num = s->cluster_size;
-        ret = BDRV_BLOCK_ALLOCATED | BDRV_BLOCK_DATA;
-    } else if (offset + num == s->len) {
-        num = QEMU_ALIGN_UP(num, s->cluster_size);
-    } else {
-        num = QEMU_ALIGN_DOWN(num, s->cluster_size);
-    }
-
-    *pnum = num;
-    return ret;
-}
-
-/*
- * Check if the cluster starting at offset is allocated or not.
- * return via pnum the number of contiguous clusters sharing this allocation.
- */
-static int block_copy_is_cluster_allocated(BlockCopyState *s, int64_t offset,
-                                           int64_t *pnum)
-{
-    BlockDriverState *bs = s->source->bs;
-    int64_t count, total_count = 0;
-    int64_t bytes = s->len - offset;
-    int ret;
-
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-
-    while (true) {
-        ret = bdrv_is_allocated(bs, offset, bytes, &count);
-        if (ret < 0) {
-            return ret;
-        }
-
-        total_count += count;
-
-        if (ret || count == 0) {
-            /*
-             * ret: partial segment(s) are considered allocated.
-             * otherwise: unallocated tail is treated as an entire segment.
-             */
-            *pnum = DIV_ROUND_UP(total_count, s->cluster_size);
-            return ret;
-        }
-
-        /* Unallocated segment(s) with uncertain following segment(s) */
-        if (total_count >= s->cluster_size) {
-            *pnum = total_count / s->cluster_size;
-            return 0;
-        }
-
-        offset += count;
-        bytes -= count;
-    }
-}
-
-/*
- * Reset bits in copy_bitmap starting at offset if they represent unallocated
- * data in the image. May reset subsequent contiguous bits.
- * @return 0 when the cluster at @offset was unallocated,
- *         1 otherwise, and -ret on error.
- */
-int64_t block_copy_reset_unallocated(BlockCopyState *s,
-                                     int64_t offset, int64_t *count)
-{
-    int ret;
-    int64_t clusters, bytes;
-
-    ret = block_copy_is_cluster_allocated(s, offset, &clusters);
-    if (ret < 0) {
-        return ret;
-    }
-
-    bytes = clusters * s->cluster_size;
-
-    if (!ret) {
-        bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
-        progress_set_remaining(s->progress,
-                               bdrv_get_dirty_count(s->copy_bitmap) +
-                               s->in_flight_bytes);
-    }
-
-    *count = bytes;
-    return ret;
-}
-
-/*
- * block_copy_dirty_clusters
- *
- * Copy dirty clusters in @offset/@bytes range.
- * Returns 1 if dirty clusters found and successfully copied, 0 if no dirty
- * clusters found and -errno on failure.
- */
-static int coroutine_fn block_copy_dirty_clusters(BlockCopyState *s,
-                                                  int64_t offset, int64_t bytes,
-                                                  bool *error_is_read)
-{
-    int ret = 0;
-    bool found_dirty = false;
-
-    /*
-     * block_copy() user is responsible for keeping source and target in same
-     * aio context
-     */
-    assert(bdrv_get_aio_context(s->source->bs) ==
-           bdrv_get_aio_context(s->target->bs));
-
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-    assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
-
-    while (bytes) {
-        BlockCopyInFlightReq req;
-        int64_t next_zero, cur_bytes, status_bytes;
-
-        if (!bdrv_dirty_bitmap_get(s->copy_bitmap, offset)) {
-            trace_block_copy_skip(s, offset);
-            offset += s->cluster_size;
-            bytes -= s->cluster_size;
-            continue; /* already copied */
-        }
-
-        found_dirty = true;
-
-        cur_bytes = MIN(bytes, s->copy_size);
-
-        next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, offset,
-                                                cur_bytes);
-        if (next_zero >= 0) {
-            assert(next_zero > offset); /* offset is dirty */
-            assert(next_zero < offset + cur_bytes); /* no need to do MIN() */
-            cur_bytes = next_zero - offset;
-        }
-        block_copy_inflight_req_begin(s, &req, offset, cur_bytes);
-
-        ret = block_copy_block_status(s, offset, cur_bytes, &status_bytes);
-        assert(ret >= 0); /* never fail */
-        cur_bytes = MIN(cur_bytes, status_bytes);
-        block_copy_inflight_req_shrink(s, &req, cur_bytes);
-        if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) {
-            block_copy_inflight_req_end(s, &req, 0);
-            progress_set_remaining(s->progress,
-                                   bdrv_get_dirty_count(s->copy_bitmap) +
-                                   s->in_flight_bytes);
-            trace_block_copy_skip_range(s, offset, status_bytes);
-            offset += status_bytes;
-            bytes -= status_bytes;
-            continue;
-        }
-
-        trace_block_copy_process(s, offset);
-
-        co_get_from_shres(s->mem, cur_bytes);
-        ret = block_copy_do_copy(s, offset, cur_bytes, ret & BDRV_BLOCK_ZERO,
-                                 error_is_read);
-        co_put_to_shres(s->mem, cur_bytes);
-        block_copy_inflight_req_end(s, &req, ret);
-        if (ret < 0) {
-            return ret;
-        }
-
-        progress_work_done(s->progress, cur_bytes);
-        s->progress_bytes_callback(cur_bytes, s->progress_opaque);
-        offset += cur_bytes;
-        bytes -= cur_bytes;
-    }
-
-    return found_dirty;
-}
-
-/*
- * block_copy
- *
- * Copy requested region, accordingly to dirty bitmap.
- * Collaborate with parallel block_copy requests: if they succeed it will help
- * us. If they fail, we will retry not-copied regions. So, if we return error,
- * it means that some I/O operation failed in context of _this_ block_copy call,
- * not some parallel operation.
- */
-int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes,
-                            bool *error_is_read)
-{
-    int ret;
-
-    do {
-        ret = block_copy_dirty_clusters(s, offset, bytes, error_is_read);
-
-        if (ret == 0) {
-            ret = block_copy_wait_one(s, offset, bytes);
-        }
-
-        /*
-         * We retry in two cases:
-         * 1. Some progress done
-         *    Something was copied, which means that there were yield points
-         *    and some new dirty bits may have appeared (due to failed parallel
-         *    block-copy requests).
-         * 2. We have waited for some intersecting block-copy request
-         *    It may have failed and produced new dirty bits.
-         */
-    } while (ret > 0);
-
-    return ret;
-}
-
-BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s)
-{
-    return s->copy_bitmap;
-}
-
-void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip)
-{
-    s->skip_unallocated = skip;
-}
@@ -248,8 +248,8 @@ bochs_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
    QEMUIOVector local_qiov;
    int ret;

-    assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
-    assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));
+    assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
+    assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);

    qemu_iovec_init(&local_qiov, qiov->niov);
    qemu_co_mutex_lock(&s->lock);
@@ -253,8 +253,8 @@ cloop_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
    int nb_sectors = bytes >> BDRV_SECTOR_BITS;
    int ret, i;

-    assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
-    assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE));
+    assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
+    assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);

    qemu_co_mutex_lock(&s->lock);

@@ -43,6 +43,27 @@ typedef struct CommitBlockJob {
    char *backing_file_str;
 } CommitBlockJob;

+static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base,
+                                        int64_t offset, uint64_t bytes,
+                                        void *buf)
+{
+    int ret = 0;
+
+    assert(bytes < SIZE_MAX);
+
+    ret = blk_co_pread(bs, offset, bytes, buf, 0);
+    if (ret < 0) {
+        return ret;
+    }
+
+    ret = blk_co_pwrite(base, offset, bytes, buf, 0);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return 0;
+}
+
 static int commit_prepare(Job *job)
 {
    CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
@@ -119,6 +140,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp)
    int ret = 0;
    int64_t n = 0; /* bytes */
    void *buf = NULL;
+    int bytes_written = 0;
    int64_t len, base_len;

    ret = len = blk_getlength(s->top);
@@ -133,7 +155,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp)
    }

    if (base_len < len) {
-        ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, NULL);
+        ret = blk_truncate(s->base, len, PREALLOC_MODE_OFF, NULL);
        if (ret) {
            goto out;
        }
@@ -143,7 +165,6 @@ static int coroutine_fn commit_run(Job *job, Error **errp)

    for (offset = 0; offset < len; offset += n) {
        bool copy;
-        bool error_in_source = true;

        /* Note that even when no rate limit is applied we need to yield
         * with no pending I/O here so that bdrv_drain_all() returns.
@@ -158,20 +179,12 @@ static int coroutine_fn commit_run(Job *job, Error **errp)
        copy = (ret == 1);
        trace_commit_one_iteration(s, offset, n, ret);
        if (copy) {
-            assert(n < SIZE_MAX);
-
-            ret = blk_co_pread(s->top, offset, n, buf, 0);
-            if (ret >= 0) {
-                ret = blk_co_pwrite(s->base, offset, n, buf, 0);
-                if (ret < 0) {
-                    error_in_source = false;
-                }
-            }
+            ret = commit_populate(s->top, s->base, offset, n, buf);
+            bytes_written += n;
        }
        if (ret < 0) {
            BlockErrorAction action =
-                block_job_error_action(&s->common, s->on_error,
-                                       error_in_source, -ret);
+                block_job_error_action(&s->common, false, s->on_error, -ret);
            if (action == BLOCK_ERROR_ACTION_REPORT) {
                goto out;
            } else {
@@ -203,6 +216,7 @@ static const BlockJobDriver commit_job_driver = {
        .job_type      = JOB_TYPE_COMMIT,
        .free          = block_job_free,
        .user_resume   = block_job_user_resume,
+        .drain         = block_job_drain,
        .run           = commit_run,
        .prepare       = commit_prepare,
        .abort         = commit_abort,
@@ -336,7 +350,6 @@ void commit_start(const char *job_id, BlockDriverState *bs,
    if (ret < 0) {
        goto fail;
    }
-    blk_set_disable_request_queuing(s->base, true);
    s->base_bs = base;

    /* Required permissions are already taken with block_job_add_bdrv() */
@@ -345,7 +358,6 @@ void commit_start(const char *job_id, BlockDriverState *bs,
    if (ret < 0) {
        goto fail;
    }
-    blk_set_disable_request_queuing(s->top, true);

    s->backing_file_str = g_strdup(backing_file_str);
    s->on_error = on_error;
@@ -458,8 +470,7 @@ int bdrv_commit(BlockDriverState *bs)
     * grow the backing file image if possible.  If not possible,
     * we must return an error */
    if (length > backing_length) {
-        ret = blk_truncate(backing, length, false, PREALLOC_MODE_OFF,
-                           &local_err);
+        ret = blk_truncate(backing, length, PREALLOC_MODE_OFF, &local_err);
        if (ret < 0) {
            error_report_err(local_err);
            goto ro_cleanup;
@@ -73,6 +73,13 @@ static int64_t cor_getlength(BlockDriverState *bs)
 }


+static int coroutine_fn cor_co_truncate(BlockDriverState *bs, int64_t offset,
+                                        PreallocMode prealloc, Error **errp)
+{
+    return bdrv_co_truncate(bs->file, offset, prealloc, errp);
+}
+
+
 static int coroutine_fn cor_co_preadv(BlockDriverState *bs,
                                      uint64_t offset, uint64_t bytes,
                                      QEMUIOVector *qiov, int flags)
@@ -118,6 +125,13 @@ static void cor_lock_medium(BlockDriverState *bs, bool locked)
 }


+static bool cor_recurse_is_first_non_filter(BlockDriverState *bs,
+                                            BlockDriverState *candidate)
+{
+    return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
+}
+
+
 static BlockDriver bdrv_copy_on_read = {
    .format_name                        = "copy-on-read",

@@ -125,6 +139,7 @@ static BlockDriver bdrv_copy_on_read = {
    .bdrv_child_perm                    = cor_child_perm,

    .bdrv_getlength                     = cor_getlength,
+    .bdrv_co_truncate                   = cor_co_truncate,

    .bdrv_co_preadv                     = cor_co_preadv,
    .bdrv_co_pwritev                    = cor_co_pwritev,
@@ -136,6 +151,8 @@ static BlockDriver bdrv_copy_on_read = {

    .bdrv_co_block_status               = bdrv_co_block_status_from_file,

+    .bdrv_recurse_is_first_non_filter   = cor_recurse_is_first_non_filter,
+
    .has_variable_length                = true,
    .is_filter                          = true,
 };
@@ -25,7 +25,6 @@
 #include "qemu/osdep.h"
 #include "block/block_int.h"
 #include "qemu/job.h"
-#include "qemu/main-loop.h"
 #include "qapi/qapi-commands-block-core.h"
 #include "qapi/qapi-visit-block-core.h"
 #include "qapi/clone-visitor.h"
@@ -30,7 +30,6 @@
 #include "qapi/error.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
-#include "qemu/cutils.h"
 #include "crypto.h"

 typedef struct BlockCrypto BlockCrypto;
@@ -75,7 +74,6 @@ static ssize_t block_crypto_read_func(QCryptoBlock *block,
 struct BlockCryptoCreateData {
    BlockBackend *blk;
    uint64_t size;
-    PreallocMode prealloc;
 };


@@ -114,8 +112,8 @@ static ssize_t block_crypto_init_func(QCryptoBlock *block,
     * available to the guest, so we must take account of that
     * which will be used by the crypto header
     */
-    return blk_truncate(data->blk, data->size + headerlen, false,
-                        data->prealloc, errp);
+    return blk_truncate(data->blk, data->size + headerlen, PREALLOC_MODE_OFF,
+                        errp);
 }


@@ -253,7 +251,6 @@ static int block_crypto_open_generic(QCryptoBlockFormat format,
 static int block_crypto_co_create_generic(BlockDriverState *bs,
                                          int64_t size,
                                          QCryptoBlockCreateOptions *opts,
-                                          PreallocMode prealloc,
                                          Error **errp)
 {
    int ret;
@@ -269,14 +266,9 @@ static int block_crypto_co_create_generic(BlockDriverState *bs,
        goto cleanup;
    }

-    if (prealloc == PREALLOC_MODE_METADATA) {
-        prealloc = PREALLOC_MODE_OFF;
-    }
-
    data = (struct BlockCryptoCreateData) {
        .blk = blk,
        .size = size,
-        .prealloc = prealloc,
    };

    crypto = qcrypto_block_create(opts, NULL,
@@ -298,7 +290,7 @@ static int block_crypto_co_create_generic(BlockDriverState *bs,
 }

 static int coroutine_fn
-block_crypto_co_truncate(BlockDriverState *bs, int64_t offset, bool exact,
+block_crypto_co_truncate(BlockDriverState *bs, int64_t offset,
                         PreallocMode prealloc, Error **errp)
 {
    BlockCrypto *crypto = bs->opaque;
@@ -312,7 +304,7 @@ block_crypto_co_truncate(BlockDriverState *bs, int64_t offset, bool exact,

    offset += payload_offset;

-    return bdrv_co_truncate(bs->file, offset, exact, prealloc, errp);
+    return bdrv_co_truncate(bs->file, offset, prealloc, errp);
 }

 static void block_crypto_close(BlockDriverState *bs)
@@ -485,67 +477,6 @@ static int64_t block_crypto_getlength(BlockDriverState *bs)
 }


-static BlockMeasureInfo *block_crypto_measure(QemuOpts *opts,
-                                              BlockDriverState *in_bs,
-                                              Error **errp)
-{
-    g_autoptr(QCryptoBlockCreateOptions) create_opts = NULL;
-    Error *local_err = NULL;
-    BlockMeasureInfo *info;
-    uint64_t size;
-    size_t luks_payload_size;
-    QDict *cryptoopts;
-
-    /*
-     * Preallocation mode doesn't affect size requirements but we must consume
-     * the option.
-     */
-    g_free(qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC));
-
-    size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-
-    if (in_bs) {
-        int64_t ssize = bdrv_getlength(in_bs);
-
-        if (ssize < 0) {
-            error_setg_errno(&local_err, -ssize,
-                             "Unable to get image virtual_size");
-            goto err;
-        }
-
-        size = ssize;
-    }
-
-    cryptoopts = qemu_opts_to_qdict_filtered(opts, NULL,
-            &block_crypto_create_opts_luks, true);
-    qdict_put_str(cryptoopts, "format", "luks");
-    create_opts = block_crypto_create_opts_init(cryptoopts, &local_err);
-    qobject_unref(cryptoopts);
-    if (!create_opts) {
-        goto err;
-    }
-
-    if (!qcrypto_block_calculate_payload_offset(create_opts, NULL,
-                                                &luks_payload_size,
-                                                &local_err)) {
-        goto err;
-    }
-
-    /*
-     * Unallocated blocks are still encrypted so allocation status makes no
-     * difference to the file size.
-     */
-    info = g_new(BlockMeasureInfo, 1);
-    info->fully_allocated = luks_payload_size + size;
-    info->required = luks_payload_size + size;
-    return info;
-
-err:
-    error_propagate(errp, local_err);
-    return NULL;
-}
-
-
 static int block_crypto_probe_luks(const uint8_t *buf,
                                   int buf_size,
                                   const char *filename) {
@@ -569,7 +500,6 @@ block_crypto_co_create_luks(BlockdevCreateOptions *create_options, Error **errp)
    BlockdevCreateOptionsLUKS *luks_opts;
    BlockDriverState *bs = NULL;
    QCryptoBlockCreateOptions create_opts;
-    PreallocMode preallocation = PREALLOC_MODE_OFF;
    int ret;

    assert(create_options->driver == BLOCKDEV_DRIVER_LUKS);
@@ -585,12 +515,8 @@ block_crypto_co_create_luks(BlockdevCreateOptions *create_options, Error **errp)
        .u.luks = *qapi_BlockdevCreateOptionsLUKS_base(luks_opts),
    };

-    if (luks_opts->has_preallocation) {
-        preallocation = luks_opts->preallocation;
-    }
-
    ret = block_crypto_co_create_generic(bs, luks_opts->size, &create_opts,
-                                         preallocation, errp);
+                                         errp);
    if (ret < 0) {
        goto fail;
    }
@@ -601,32 +527,19 @@ fail:
    return ret;
 }

-static int coroutine_fn block_crypto_co_create_opts_luks(BlockDriver *drv,
-                                                         const char *filename,
+static int coroutine_fn block_crypto_co_create_opts_luks(const char *filename,
                                                         QemuOpts *opts,
                                                         Error **errp)
 {
    QCryptoBlockCreateOptions *create_opts = NULL;
    BlockDriverState *bs = NULL;
    QDict *cryptoopts;
-    PreallocMode prealloc;
-    char *buf = NULL;
    int64_t size;
    int ret;
-    Error *local_err = NULL;

    /* Parse options */
    size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);

-    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    prealloc = qapi_enum_parse(&PreallocMode_lookup, buf,
-                               PREALLOC_MODE_OFF, &local_err);
-    g_free(buf);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return -EINVAL;
-    }
-
    cryptoopts = qemu_opts_to_qdict_filtered(opts, NULL,
                                             &block_crypto_create_opts_luks,
                                             true);
@@ -652,30 +565,13 @@ static int coroutine_fn block_crypto_co_create_opts_luks(BlockDriver *drv,
    }

    /* Create format layer */
-    ret = block_crypto_co_create_generic(bs, size, create_opts, prealloc, errp);
+    ret = block_crypto_co_create_generic(bs, size, create_opts, errp);
    if (ret < 0) {
        goto fail;
    }

    ret = 0;
 fail:
-    /*
-     * If an error occurred, delete 'filename'. Even if the file existed
-     * beforehand, it has been truncated and corrupted in the process.
-     */
-    if (ret && bs) {
-        Error *local_delete_err = NULL;
-        int r_del = bdrv_co_delete_file(bs, &local_delete_err);
-        /*
-         * ENOTSUP will happen if the block driver doesn't support
-         * the 'bdrv_co_delete_file' interface. This is a predictable
-         * scenario and shouldn't be reported back to the user.
-         */
-        if ((r_del < 0) && (r_del != -ENOTSUP)) {
-            error_report_err(local_delete_err);
-        }
-    }
-
    bdrv_unref(bs);
    qapi_free_QCryptoBlockCreateOptions(create_opts);
    qobject_unref(cryptoopts);
@@ -750,7 +646,6 @@ static BlockDriver bdrv_crypto_luks = {
    .bdrv_co_preadv     = block_crypto_co_preadv,
    .bdrv_co_pwritev    = block_crypto_co_pwritev,
    .bdrv_getlength     = block_crypto_getlength,
-    .bdrv_measure       = block_crypto_measure,
    .bdrv_get_info      = block_crypto_get_info_luks,
    .bdrv_get_specific_info = block_crypto_get_specific_info_luks,

@@ -214,35 +214,11 @@ static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
    BDRVCURLState *s = opaque;
    size_t realsize = size * nmemb;
-    const char *header = (char *)ptr;
-    const char *end = header + realsize;
-    const char *accept_ranges = "accept-ranges:";
-    const char *bytes = "bytes";
+    const char *accept_line = "Accept-Ranges: bytes";

-    if (realsize >= strlen(accept_ranges)
-        && g_ascii_strncasecmp(header, accept_ranges,
-                               strlen(accept_ranges)) == 0) {
-
-        char *p = strchr(header, ':') + 1;
-
-        /* Skip whitespace between the header name and value. */
-        while (p < end && *p && g_ascii_isspace(*p)) {
-            p++;
-        }
-
-        if (end - p >= strlen(bytes)
-            && strncmp(p, bytes, strlen(bytes)) == 0) {
-
-            /* Check that there is nothing but whitespace after the value. */
-            p += strlen(bytes);
-            while (p < end && *p && g_ascii_isspace(*p)) {
-                p++;
-            }
-
-            if (p == end || !*p) {
-                s->accept_range = true;
-            }
-        }
+    if (realsize >= strlen(accept_line)
+        && strncmp((char *)ptr, accept_line, strlen(accept_line)) == 0) {
+        s->accept_range = true;
    }

    return realsize;
@@ -906,13 +882,7 @@ static void curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
    trace_curl_setup_preadv(acb->bytes, start, state->range);
    curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);

-    if (curl_multi_add_handle(s->multi, state->curl) != CURLM_OK) {
-        state->acb[0] = NULL;
-        acb->ret = -EIO;
-
-        curl_clean_state(state);
-        goto out;
-    }
+    curl_multi_add_handle(s->multi, state->curl);

    /* Tell curl it needs to kick things off */
    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
@@ -1 +1 @@
 .0.1
 .1.1