Merge conflicts

.cirrus.yml

@@ -10,9 +10,9 @@ windows_msys2_task:
     memory: 8G
   env:
     CIRRUS_SHELL: powershell
-    MSYS: winsymlinks:nativestrict
+    MSYS: winsymlinks:native
     MSYSTEM: MINGW64
-    MSYS2_URL: https://github.com/msys2/msys2-installer/releases/download/2022-05-03/msys2-base-x86_64-20220503.sfx.exe
+    MSYS2_URL: https://github.com/msys2/msys2-installer/releases/download/2022-06-03/msys2-base-x86_64-20220603.sfx.exe
     MSYS2_FINGERPRINT: 0
     MSYS2_PACKAGES: "
       diffutils git grep make pkg-config sed

.gitignore

@@ -2,6 +2,7 @@
 /qemu_libafl_bridge/target/
 /GNUmakefile
 /build/
+/.cache/
 *.pyc
 .sdk
 .stgit-*

.gitlab-ci.d/buildtest.yml

@@ -41,8 +41,7 @@ build-system-ubuntu:
     job: amd64-ubuntu2004-container
   variables:
     IMAGE: ubuntu2004
-    CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-slirp=system
+    CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-capstone
-        --enable-capstone
     TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu
       microblazeel-softmmu mips64el-softmmu
     MAKE_CHECK_ARGS: check-build
@@ -120,7 +119,7 @@ build-system-fedora:
   variables:
     IMAGE: fedora
     CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs
-             --enable-fdt=system --enable-slirp=system --enable-capstone
+             --enable-fdt=system --enable-slirp --enable-capstone
     TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu
       xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu
     MAKE_CHECK_ARGS: check-build
@@ -339,10 +338,8 @@ clang-user:
 # On gitlab runners, default value sometimes end up calling 2 lds concurrently and
 # triggers an Out-Of-Memory error
 #
-# Since slirp callbacks are used in QEMU Timers, slirp needs to be compiled together
+# Since slirp callbacks are used in QEMU Timers, we cannot use libslirp with
-# with QEMU and linked as a static library to avoid false positives in CFI checks.
+# CFI builds, and thus have to disable it here.
-# This can be accomplished by using -enable-slirp=git, which avoids the use of
-# a system-wide version of the library
 #
 # Split in three sets of build/check/avocado to limit the execution time of each
 # job
@@ -355,7 +352,7 @@ build-cfi-aarch64:
     AR: llvm-ar
     IMAGE: fedora
     CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug
-      --enable-safe-stack --enable-slirp=git
+      --enable-safe-stack --disable-slirp
     TARGETS: aarch64-softmmu
     MAKE_CHECK_ARGS: check-build
     # FIXME: This job is often failing, likely due to out-of-memory problems in
@@ -395,7 +392,7 @@ build-cfi-ppc64-s390x:
     AR: llvm-ar
     IMAGE: fedora
     CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug
-      --enable-safe-stack --enable-slirp=git
+      --enable-safe-stack --disable-slirp
     TARGETS: ppc64-softmmu s390x-softmmu
     MAKE_CHECK_ARGS: check-build
     # FIXME: This job is often failing, likely due to out-of-memory problems in
@@ -435,7 +432,7 @@ build-cfi-x86_64:
     AR: llvm-ar
     IMAGE: fedora
     CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug
-      --enable-safe-stack --enable-slirp=git
+      --enable-safe-stack --disable-slirp
     TARGETS: x86_64-softmmu
     MAKE_CHECK_ARGS: check-build
   timeout: 70m
@@ -469,7 +466,7 @@ tsan-build:
   variables:
     IMAGE: ubuntu2004
     CONFIGURE_ARGS: --enable-tsan --cc=clang-10 --cxx=clang++-10
-          --enable-trace-backends=ust --enable-fdt=system --enable-slirp=system
+          --enable-trace-backends=ust --enable-fdt=system --disable-slirp
     TARGETS: x86_64-softmmu ppc64-softmmu riscv64-softmmu x86_64-linux-user
     MAKE_CHECK_ARGS: bench V=1
 
@@ -571,7 +568,6 @@ build-without-default-features:
       --disable-capstone
       --disable-pie
       --disable-qom-cast-debug
-      --disable-slirp
       --disable-strip
     TARGETS: avr-softmmu i386-softmmu mips64-softmmu s390x-softmmu sh4-softmmu
       sparc64-softmmu hexagon-linux-user i386-linux-user s390x-linux-user

.gitlab-ci.d/cirrus.yml

@@ -63,7 +63,7 @@ x64-freebsd-13-build:
     NAME: freebsd-13
     CIRRUS_VM_INSTANCE_TYPE: freebsd_instance
     CIRRUS_VM_IMAGE_SELECTOR: image_family
-    CIRRUS_VM_IMAGE_NAME: freebsd-13-0
+    CIRRUS_VM_IMAGE_NAME: freebsd-13-1
     CIRRUS_VM_CPUS: 8
     CIRRUS_VM_RAM: 8G
     UPDATE_COMMAND: pkg update

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

@@ -32,5 +32,6 @@ build_task:
     - $MAKE -j$(sysctl -n hw.ncpu)
     - for TARGET in $TEST_TARGETS ;
       do
-        $MAKE -j$(sysctl -n hw.ncpu) $TARGET V=1 ;
+        $MAKE -j$(sysctl -n hw.ncpu) $TARGET V=1
+        || { cat meson-logs/testlog.txt; exit 1; } ;
       done

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

@@ -1,5 +1,4 @@
 # THIS FILE WAS AUTO-GENERATED
-# ... and then edited to fix py39, pending proper lcitool update.
 #
 #  $ lcitool variables freebsd-12 qemu
 #
@@ -12,6 +11,6 @@ MAKE='/usr/local/bin/gmake'
 NINJA='/usr/local/bin/ninja'
 PACKAGING_COMMAND='pkg'
 PIP3='/usr/local/bin/pip-3.8'
-PKGS='alsa-lib bash bzip2 ca_root_nss capstone4 ccache cdrkit-genisoimage ctags curl cyrus-sasl dbus diffutils dtc fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 libepoxy libffi libgcrypt libjpeg-turbo libnfs libspice-server libssh libtasn1 llvm lzo2 meson ncurses nettle ninja opencv perl5 pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-virtualenv py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy spice-protocol tesseract texinfo usbredir virglrenderer vte3 zstd'
+PKGS='alsa-lib bash bison bzip2 ca_root_nss capstone4 ccache cdrkit-genisoimage cmocka ctags curl cyrus-sasl dbus diffutils dtc flex fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 json-c libepoxy libffi libgcrypt libjpeg-turbo libnfs libslirp libspice-server libssh libtasn1 llvm lzo2 meson ncurses nettle ninja opencv perl5 pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy spice-protocol tesseract texinfo usbredir virglrenderer vte3 zstd'
 PYPI_PKGS=''
 PYTHON='/usr/local/bin/python3'

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

@@ -1,5 +1,4 @@
 # THIS FILE WAS AUTO-GENERATED
-# ... and then edited to fix py39, pending proper lcitool update.
 #
 #  $ lcitool variables freebsd-13 qemu
 #
@@ -12,6 +11,6 @@ MAKE='/usr/local/bin/gmake'
 NINJA='/usr/local/bin/ninja'
 PACKAGING_COMMAND='pkg'
 PIP3='/usr/local/bin/pip-3.8'
-PKGS='alsa-lib bash bzip2 ca_root_nss capstone4 ccache cdrkit-genisoimage ctags curl cyrus-sasl dbus diffutils dtc fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 libepoxy libffi libgcrypt libjpeg-turbo libnfs libspice-server libssh libtasn1 llvm lzo2 meson ncurses nettle ninja opencv perl5 pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-virtualenv py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy spice-protocol tesseract texinfo usbredir virglrenderer vte3 zstd'
+PKGS='alsa-lib bash bison bzip2 ca_root_nss capstone4 ccache cdrkit-genisoimage cmocka ctags curl cyrus-sasl dbus diffutils dtc flex fusefs-libs3 gettext git glib gmake gnutls gsed gtk3 json-c libepoxy libffi libgcrypt libjpeg-turbo libnfs libslirp libspice-server libssh libtasn1 llvm lzo2 meson ncurses nettle ninja opencv perl5 pixman pkgconf png py39-numpy py39-pillow py39-pip py39-sphinx py39-sphinx_rtd_theme py39-yaml python3 rpm2cpio sdl2 sdl2_image snappy spice-protocol tesseract texinfo usbredir virglrenderer vte3 zstd'
 PYPI_PKGS=''
 PYTHON='/usr/local/bin/python3'

.gitlab-ci.d/cirrus/macos-11.vars

@@ -11,6 +11,6 @@ MAKE='/usr/local/bin/gmake'
 NINJA='/usr/local/bin/ninja'
 PACKAGING_COMMAND='brew'
 PIP3='/usr/local/bin/pip3'
-PKGS='bash bc bzip2 capstone ccache ctags curl dbus diffutils dtc gcovr gettext git glib gnu-sed gnutls gtk+3 jemalloc jpeg-turbo libepoxy libffi libgcrypt libiscsi libnfs libpng libslirp libssh libtasn1 libusb llvm lzo make meson ncurses nettle ninja perl pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy sparse spice-protocol tesseract texinfo usbredir vde vte3 zlib zstd'
+PKGS='bash bc bison bzip2 capstone ccache cmocka ctags curl dbus diffutils dtc flex gcovr gettext git glib gnu-sed gnutls gtk+3 jemalloc jpeg-turbo json-c libepoxy libffi libgcrypt libiscsi libnfs libpng libslirp libssh libtasn1 libusb llvm lzo make meson ncurses nettle ninja perl pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy sparse spice-protocol tesseract texinfo usbredir vde vte3 zlib zstd'
-PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme virtualenv'
+PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme'
 PYTHON='/usr/local/bin/python3'

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

@@ -10,8 +10,3 @@ amd64-fedora-container:
   extends: .container_job_template
   variables:
     NAME: fedora
-
-amd64-debian10-container:
-  extends: .container_job_template
-  variables:
-    NAME: debian10

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

@@ -1,21 +1,18 @@
 alpha-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-alpha-cross
 
 amd64-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-amd64-cross
 
 amd64-debian-user-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-all-test-cross
 
@@ -65,22 +62,19 @@ hexagon-cross-container:
 
 hppa-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-hppa-cross
 
 m68k-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-m68k-cross
 
 mips64-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-mips64-cross
 
@@ -92,8 +86,7 @@ mips64el-debian-cross-container:
 
 mips-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-mips-cross
 
@@ -105,8 +98,7 @@ mipsel-debian-cross-container:
 
 powerpc-test-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian11-container']
   variables:
     NAME: debian-powerpc-test-cross
 
@@ -127,8 +119,7 @@ riscv64-debian-cross-container:
 # we can however build TCG tests using a non-sid base
 riscv64-debian-test-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian11-container']
   variables:
     NAME: debian-riscv64-test-cross
 
@@ -140,22 +131,19 @@ s390x-debian-cross-container:
 
 sh4-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-sh4-cross
 
 sparc64-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-sparc64-cross
 
 tricore-debian-cross-container:
   extends: .container_job_template
-  stage: containers-layer2
+  stage: containers
-  needs: ['amd64-debian10-container']
   variables:
     NAME: debian-tricore-cross
 

.gitlab-ci.d/containers.yml

@@ -7,11 +7,6 @@ amd64-alpine-container:
   variables:
     NAME: alpine
 
-amd64-debian11-container:
-  extends: .container_job_template
-  variables:
-    NAME: debian11
-
 amd64-debian-container:
   extends: .container_job_template
   stage: containers

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

@@ -46,5 +46,8 @@
     - cd build
     - PKG_CONFIG_PATH=$PKG_CONFIG_PATH
       ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS
-        --disable-system
+        --disable-system --target-list-exclude="aarch64_be-linux-user
+          alpha-linux-user cris-linux-user m68k-linux-user microblazeel-linux-user
+          nios2-linux-user or1k-linux-user ppc-linux-user sparc-linux-user
+          xtensa-linux-user $CROSS_SKIP_TARGETS"
     - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS

.gitlab-ci.d/crossbuilds.yml

@@ -70,20 +70,6 @@ cross-i386-tci:
     EXTRA_CONFIGURE_OPTS: --target-list=i386-softmmu,i386-linux-user,aarch64-softmmu,aarch64-linux-user,ppc-softmmu,ppc-linux-user
     MAKE_CHECK_ARGS: check check-tcg
 
-cross-mips-system:
-  extends: .cross_system_build_job
-  needs:
-    job: mips-debian-cross-container
-  variables:
-    IMAGE: debian-mips-cross
-
-cross-mips-user:
-  extends: .cross_user_build_job
-  needs:
-    job: mips-debian-cross-container
-  variables:
-    IMAGE: debian-mips-cross
-
 cross-mipsel-system:
   extends: .cross_system_build_job
   needs:

.gitlab-ci.d/custom-runners.yml

@@ -15,6 +15,6 @@ variables:
 
 include:
   - local: '/.gitlab-ci.d/custom-runners/ubuntu-20.04-s390x.yml'
-  - local: '/.gitlab-ci.d/custom-runners/ubuntu-20.04-aarch64.yml'
+  - local: '/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml'
-  - local: '/.gitlab-ci.d/custom-runners/ubuntu-20.04-aarch32.yml'
+  - local: '/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch32.yml'
   - local: '/.gitlab-ci.d/custom-runners/centos-stream-8-x86_64.yml'

.gitlab-ci.d/custom-runners/centos-stream-8-x86_64.yml

@@ -23,6 +23,8 @@ centos-stream-8-x86_64:
  - mkdir build
  - cd build
  - ../scripts/ci/org.centos/stream/8/x86_64/configure
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make -j"$JOBS"
  - make NINJA=":" check
+   || { cat meson-logs/testlog.txt; exit 1; } ;
  - ../scripts/ci/org.centos/stream/8/x86_64/test-avocado

.gitlab-ci.d/custom-runners/ubuntu-20.04-s390x.yml

@@ -17,9 +17,12 @@ ubuntu-20.04-s390x-all-linux-static:
  - mkdir build
  - cd build
  - ../configure --enable-debug --static --disable-system --disable-glusterfs --disable-libssh
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc`
  - make --output-sync -j`nproc` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
  - make --output-sync -j`nproc` check-tcg V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
 ubuntu-20.04-s390x-all:
  needs: []
@@ -35,8 +38,10 @@ ubuntu-20.04-s390x-all:
  - mkdir build
  - cd build
  - ../configure --disable-libssh
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc`
  - make --output-sync -j`nproc` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
 ubuntu-20.04-s390x-alldbg:
  needs: []
@@ -55,9 +60,11 @@ ubuntu-20.04-s390x-alldbg:
  - mkdir build
  - cd build
  - ../configure --enable-debug --disable-libssh
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make clean
  - make --output-sync -j`nproc`
  - make --output-sync -j`nproc` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
 ubuntu-20.04-s390x-clang:
  needs: []
@@ -76,8 +83,10 @@ ubuntu-20.04-s390x-clang:
  - mkdir build
  - cd build
  - ../configure --disable-libssh --cc=clang --cxx=clang++ --enable-sanitizers
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc`
  - make --output-sync -j`nproc` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
 ubuntu-20.04-s390x-tci:
  needs: []
@@ -96,6 +105,7 @@ ubuntu-20.04-s390x-tci:
  - mkdir build
  - cd build
  - ../configure --disable-libssh --enable-tcg-interpreter
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc`
 
 ubuntu-20.04-s390x-notcg:
@@ -115,5 +125,7 @@ ubuntu-20.04-s390x-notcg:
  - mkdir build
  - cd build
  - ../configure --disable-libssh --disable-tcg
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc`
  - make --output-sync -j`nproc` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;

.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch32.yml

@@ -1,12 +1,12 @@
-# All ubuntu-20.04 jobs should run successfully in an environment
+# All ubuntu-22.04 jobs should run successfully in an environment
 # setup by the scripts/ci/setup/qemu/build-environment.yml task
 # "Install basic packages to build QEMU on Ubuntu 20.04"
 
-ubuntu-20.04-aarch32-all:
+ubuntu-22.04-aarch32-all:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch32
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
@@ -19,5 +19,7 @@ ubuntu-20.04-aarch32-all:
  - mkdir build
  - cd build
  - ../configure --cross-prefix=arm-linux-gnueabihf-
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc --ignore=40`
  - make --output-sync -j`nproc --ignore=40` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;

.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml

@@ -2,30 +2,33 @@
 # setup by the scripts/ci/setup/qemu/build-environment.yml task
 # "Install basic packages to build QEMU on Ubuntu 20.04"
 
-ubuntu-20.04-aarch64-all-linux-static:
+ubuntu-22.04-aarch64-all-linux-static:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch64
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
  - if: "$AARCH64_RUNNER_AVAILABLE"
  script:
- # --disable-libssh is needed because of https://bugs.launchpad.net/qemu/+bug/1838763
- # --disable-glusterfs is needed because there's no static version of those libs in distro supplied packages
  - mkdir build
  - cd build
- - ../configure --enable-debug --static --disable-system --disable-glusterfs --disable-libssh
+ # Disable -static-pie due to build error with system libc:
+ # https://bugs.launchpad.net/ubuntu/+source/glibc/+bug/1987438
+ - ../configure --enable-debug --static --disable-system --disable-pie
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc --ignore=40`
  - make --output-sync -j`nproc --ignore=40` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
  - make --output-sync -j`nproc --ignore=40` check-tcg V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
-ubuntu-20.04-aarch64-all:
+ubuntu-22.04-aarch64-all:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch64
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
@@ -37,15 +40,17 @@ ubuntu-20.04-aarch64-all:
  script:
  - mkdir build
  - cd build
- - ../configure --disable-libssh
+ - ../configure
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc --ignore=40`
  - make --output-sync -j`nproc --ignore=40` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
-ubuntu-20.04-aarch64-alldbg:
+ubuntu-22.04-aarch64-alldbg:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch64
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
@@ -53,16 +58,18 @@ ubuntu-20.04-aarch64-alldbg:
  script:
  - mkdir build
  - cd build
- - ../configure --enable-debug --disable-libssh
+ - ../configure --enable-debug
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make clean
  - make --output-sync -j`nproc --ignore=40`
  - make --output-sync -j`nproc --ignore=40` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
-ubuntu-20.04-aarch64-clang:
+ubuntu-22.04-aarch64-clang:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch64
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
@@ -75,14 +82,16 @@ ubuntu-20.04-aarch64-clang:
  - mkdir build
  - cd build
  - ../configure --disable-libssh --cc=clang-10 --cxx=clang++-10 --enable-sanitizers
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc --ignore=40`
  - make --output-sync -j`nproc --ignore=40` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;
 
-ubuntu-20.04-aarch64-tci:
+ubuntu-22.04-aarch64-tci:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch64
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
@@ -94,14 +103,15 @@ ubuntu-20.04-aarch64-tci:
  script:
  - mkdir build
  - cd build
- - ../configure --disable-libssh --enable-tcg-interpreter
+ - ../configure --enable-tcg-interpreter
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc --ignore=40`
 
-ubuntu-20.04-aarch64-notcg:
+ubuntu-22.04-aarch64-notcg:
  needs: []
  stage: build
  tags:
- - ubuntu_20.04
+ - ubuntu_22.04
  - aarch64
  rules:
  - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/'
@@ -113,6 +123,8 @@ ubuntu-20.04-aarch64-notcg:
  script:
  - mkdir build
  - cd build
- - ../configure --disable-libssh --disable-tcg
+ - ../configure --disable-tcg
+   || { cat config.log meson-logs/meson-log.txt; exit 1; }
  - make --output-sync -j`nproc --ignore=40`
  - make --output-sync -j`nproc --ignore=40` check V=1
+   || { cat meson-logs/testlog.txt; exit 1; } ;

.gitlab-ci.d/stages.yml

@@ -3,6 +3,5 @@
 #  - test (for test stages, using build artefacts from a build stage)
 stages:
   - containers
-  - containers-layer2
   - build
   - test

.gitlab-ci.d/windows.yml

@@ -17,7 +17,7 @@
     }
   - If ( !(Test-Path -Path msys64\var\cache\msys2.exe ) ) {
       Invoke-WebRequest
-      "https://github.com/msys2/msys2-installer/releases/download/2022-05-03/msys2-base-x86_64-20220503.sfx.exe"
+      "https://github.com/msys2/msys2-installer/releases/download/2022-06-03/msys2-base-x86_64-20220603.sfx.exe"
       -outfile "msys64\var\cache\msys2.exe"
     }
   - msys64\var\cache\msys2.exe -y
@@ -33,7 +33,8 @@ msys2-64bit:
   extends: .shared_msys2_builder
   script:
   - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed
-      diffutils git grep make sed
+      bison diffutils flex
+      git grep make sed
       mingw-w64-x86_64-capstone
       mingw-w64-x86_64-curl
       mingw-w64-x86_64-cyrus-sasl
@@ -57,17 +58,18 @@ msys2-64bit:
       mingw-w64-x86_64-zstd "
   - $env:CHERE_INVOKING = 'yes'  # Preserve the current working directory
   - $env:MSYSTEM = 'MINGW64'     # Start a 64 bit Mingw environment
+  - $env:MSYS = 'winsymlinks:native' # Enable native Windows symlink
   - .\msys64\usr\bin\bash -lc './configure --target-list=x86_64-softmmu
       --enable-capstone --without-default-devices'
-  - .\msys64\usr\bin\bash -lc "sed -i '/^ROMS=/d' build/config-host.mak"
+  - .\msys64\usr\bin\bash -lc 'make'
-  - .\msys64\usr\bin\bash -lc 'make -j2'
+  - .\msys64\usr\bin\bash -lc 'make check || { cat build/meson-logs/testlog.txt; exit 1; } ;'
-  - .\msys64\usr\bin\bash -lc 'make check'
 
 msys2-32bit:
   extends: .shared_msys2_builder
   script:
   - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed
-      diffutils git grep make sed
+      bison diffutils flex
+      git grep make sed
       mingw-w64-i686-capstone
       mingw-w64-i686-curl
       mingw-w64-i686-cyrus-sasl
@@ -89,8 +91,9 @@ msys2-32bit:
       mingw-w64-i686-usbredir "
   - $env:CHERE_INVOKING = 'yes'  # Preserve the current working directory
   - $env:MSYSTEM = 'MINGW32'     # Start a 32-bit MinG environment
+  - $env:MSYS = 'winsymlinks:native' # Enable native Windows symlink
   - mkdir output
   - cd output
   - ..\msys64\usr\bin\bash -lc "../configure --target-list=ppc64-softmmu"
-  - ..\msys64\usr\bin\bash -lc 'make -j2'
+  - ..\msys64\usr\bin\bash -lc 'make'
-  - ..\msys64\usr\bin\bash -lc 'make check'
+  - ..\msys64\usr\bin\bash -lc 'make check || { cat meson-logs/testlog.txt; exit 1; } ;'

.gitmodules

@@ -46,9 +46,6 @@
 [submodule "roms/edk2"]
 	path = roms/edk2
 	url = https://gitlab.com/qemu-project/edk2.git
-[submodule "slirp"]
-	path = slirp
-	url = https://gitlab.com/qemu-project/libslirp.git
 [submodule "roms/opensbi"]
 	path = roms/opensbi
 	url = 	https://gitlab.com/qemu-project/opensbi.git

.mailmap

@@ -65,6 +65,7 @@ James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 Leif Lindholm <quic_llindhol@quicinc.com> <leif.lindholm@linaro.org>
 Leif Lindholm <quic_llindhol@quicinc.com> <leif@nuviainc.com>
 Radoslaw Biernacki <rad@semihalf.com> <radoslaw.biernacki@linaro.org>
+Paul Brook <paul@nowt.org> <paul@codesourcery.com>
 Paul Burton <paulburton@kernel.org> <paul.burton@mips.com>
 Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com>
 Paul Burton <paulburton@kernel.org> <paul@archlinuxmips.org>

MAINTAINERS

@@ -1129,7 +1129,7 @@ Virt
 M: Xiaojuan Yang <yangxiaojuan@loongson.cn>
 M: Song Gao <gaosong@loongson.cn>
 S: Maintained
-F: docs/system/loongarch/loongson3.rst
+F: docs/system/loongarch/virt.rst
 F: configs/targets/loongarch64-softmmu.mak
 F: configs/devices/loongarch64-softmmu/default.mak
 F: hw/loongarch/
@@ -1282,7 +1282,7 @@ F: hw/openrisc/openrisc_sim.c
 
 PowerPC Machines
 ----------------
-405 (ref405ep and taihu)
+405 (ref405ep)
 L: qemu-ppc@nongnu.org
 S: Orphan
 F: hw/ppc/ppc405_boards.c
@@ -2030,8 +2030,10 @@ virtio-blk
 M: Stefan Hajnoczi <stefanha@redhat.com>
 L: qemu-block@nongnu.org
 S: Supported
+F: hw/block/virtio-blk-common.c
 F: hw/block/virtio-blk.c
 F: hw/block/dataplane/*
+F: include/hw/virtio/virtio-blk-common.h
 F: tests/qtest/virtio-blk-test.c
 T: git https://github.com/stefanha/qemu.git block
 
@@ -2098,6 +2100,14 @@ F: hw/virtio/vhost-user-rng-pci.c
 F: include/hw/virtio/vhost-user-rng.h
 F: tools/vhost-user-rng/*
 
+vhost-user-gpio
+M: Alex Bennée <alex.bennee@linaro.org>
+R: Viresh Kumar <viresh.kumar@linaro.org>
+S: Maintained
+F: hw/virtio/vhost-user-gpio*
+F: include/hw/virtio/vhost-user-gpio.h
+F: tests/qtest/libqos/virtio-gpio.*
+
 virtio-crypto
 M: Gonglei <arei.gonglei@huawei.com>
 S: Supported
@@ -2271,11 +2281,13 @@ S: Maintained
 F: contrib/vhost-user-blk/
 F: contrib/vhost-user-scsi/
 F: hw/block/vhost-user-blk.c
+F: hw/block/virtio-blk-common.c
 F: hw/scsi/vhost-user-scsi.c
 F: hw/virtio/vhost-user-blk-pci.c
 F: hw/virtio/vhost-user-scsi-pci.c
 F: include/hw/virtio/vhost-user-blk.h
 F: include/hw/virtio/vhost-user-scsi.h
+F: include/hw/virtio/virtio-blk-common.h
 
 vhost-user-gpu
 M: Marc-André Lureau <marcandre.lureau@redhat.com>
@@ -2438,6 +2450,7 @@ X: audio/jackaudio.c
 X: audio/ossaudio.c
 X: audio/paaudio.c
 X: audio/sdlaudio.c
+X: audio/sndioaudio.c
 X: audio/spiceaudio.c
 F: qapi/audio.json
 
@@ -2482,6 +2495,12 @@ R: Thomas Huth <huth@tuxfamily.org>
 S: Odd Fixes
 F: audio/sdlaudio.c
 
+Sndio Audio backend
+M: Gerd Hoffmann <kraxel@redhat.com>
+R: Alexandre Ratchov <alex@caoua.org>
+S: Odd Fixes
+F: audio/sndioaudio.c
+
 Block layer core
 M: Kevin Wolf <kwolf@redhat.com>
 M: Hanna Reitz <hreitz@redhat.com>
@@ -2670,7 +2689,7 @@ GDB stub
 M: Alex Bennée <alex.bennee@linaro.org>
 R: Philippe Mathieu-Daudé <f4bug@amsat.org>
 S: Maintained
-F: gdbstub*
+F: gdbstub/*
 F: include/exec/gdbstub.h
 F: gdb-xml/
 F: tests/tcg/multiarch/gdbstub/
@@ -2978,7 +2997,6 @@ F: include/hw/registerfields.h
 SLIRP
 M: Samuel Thibault <samuel.thibault@ens-lyon.org>
 S: Maintained
-F: slirp/
 F: net/slirp.c
 F: include/net/slirp.h
 T: git https://people.debian.org/~sthibault/qemu.git slirp
@@ -3724,7 +3742,8 @@ GitLab custom runner (Works On Arm Sponsored)
 M: Alex Bennée <alex.bennee@linaro.org>
 M: Philippe Mathieu-Daudé <f4bug@amsat.org>
 S: Maintained
-F: .gitlab-ci.d/custom-runners/ubuntu-20.04-aarch64.yml
+F: .gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml
+F: .gitlab-ci.d/custom-runners/ubuntu-22.04-aarch32.yml
 
 Documentation
 -------------

Makefile

@@ -42,6 +42,9 @@ configure: ;
 ifneq ($(wildcard config-host.mak),)
 include config-host.mak
 
+include Makefile.prereqs
+Makefile.prereqs: config-host.mak
+
 git-submodule-update:
 .git-submodule-status: git-submodule-update config-host.mak
 Makefile: .git-submodule-status
@@ -145,7 +148,7 @@ NINJAFLAGS = $(if $V,-v) $(if $(MAKE.n), -n) $(if $(MAKE.k), -k0) \
         $(filter-out -j, $(lastword -j1 $(filter -l% -j%, $(MAKEFLAGS)))) \
         -d keepdepfile
 ninja-cmd-goals = $(or $(MAKECMDGOALS), all)
-ninja-cmd-goals += $(foreach g, $(MAKECMDGOALS), $(.ninja-goals.$g))))
+ninja-cmd-goals += $(foreach g, $(MAKECMDGOALS), $(.ninja-goals.$g))
 
 makefile-targets := build.ninja ctags TAGS cscope dist clean uninstall
 # "ninja -t targets" also lists all prerequisites.  If build system
@@ -186,7 +189,7 @@ include $(SRC_PATH)/tests/Makefile.include
 
 all: recurse-all
 
-ROMS_RULES=$(foreach t, all clean, $(addsuffix /$(t), $(ROMS)))
+ROMS_RULES=$(foreach t, all clean distclean, $(addsuffix /$(t), $(ROMS)))
 .PHONY: $(ROMS_RULES)
 $(ROMS_RULES):
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $(dir $@) V="$(V)" TARGET_DIR="$(dir $@)" $(notdir $@),)
@@ -194,6 +197,7 @@ $(ROMS_RULES):
 .PHONY: recurse-all recurse-clean
 recurse-all: $(addsuffix /all, $(ROMS))
 recurse-clean: $(addsuffix /clean, $(ROMS))
+recurse-distclean: $(addsuffix /distclean, $(ROMS))
 
 ######################################################################
 
@@ -214,10 +218,10 @@ dist: qemu-$(VERSION).tar.bz2
 qemu-%.tar.bz2:
 	$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"
 
-distclean: clean
+distclean: clean recurse-distclean
 	-$(quiet-@)test -f build.ninja && $(NINJA) $(NINJAFLAGS) -t clean -g || :
-	rm -f config-host.mak qemu-bundle
+	rm -f config-host.mak Makefile.prereqs qemu-bundle
-	rm -f tests/tcg/config-*.mak
+	rm -f tests/tcg/*/config-target.mak tests/tcg/config-host.mak
 	rm -f config.status
 	rm -f roms/seabios/config.mak
 	rm -f qemu-plugins-ld.symbols qemu-plugins-ld64.symbols

README.qemu.rst

@@ -39,7 +39,7 @@ Documentation can be found hosted online at
 current development version that is available at
 `<https://www.qemu.org/docs/master/>`_ is generated from the ``docs/``
 folder in the source tree, and is built by `Sphinx
-<https://www.sphinx-doc.org/en/master/>_`.
+<https://www.sphinx-doc.org/en/master/>`_.
 
 
 Building
@@ -78,7 +78,7 @@ 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 `style section
-<https://www.qemu.org/docs/master/devel/style.html>` of
+<https://www.qemu.org/docs/master/devel/style.html>`_ of
 the Developers Guide.
 
 Additional information on submitting patches can be found online via

VERSION

@@ -1 +1 @@
-7.0.50
+7.1.50

accel/accel-common.c

@@ -129,6 +129,16 @@ bool accel_cpu_realizefn(CPUState *cpu, Error **errp)
     return true;
 }
 
+int accel_supported_gdbstub_sstep_flags(void)
+{
+    AccelState *accel = current_accel();
+    AccelClass *acc = ACCEL_GET_CLASS(accel);
+    if (acc->gdbstub_supported_sstep_flags) {
+        return acc->gdbstub_supported_sstep_flags();
+    }
+    return 0;
+}
+
 static const TypeInfo accel_cpu_type = {
     .name = TYPE_ACCEL_CPU,
     .parent = TYPE_OBJECT,

accel/kvm/kvm-accel-ops.c

@@ -16,12 +16,14 @@
 #include "qemu/osdep.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
+#include "sysemu/kvm.h"
 #include "sysemu/kvm_int.h"
 #include "sysemu/runstate.h"
 #include "sysemu/cpus.h"
 #include "qemu/guest-random.h"
 #include "qapi/error.h"
 
+#include <linux/kvm.h>
 #include "kvm-cpus.h"
 
 static void *kvm_vcpu_thread_fn(void *arg)
@@ -95,6 +97,13 @@ static void kvm_accel_ops_class_init(ObjectClass *oc, void *data)
     ops->synchronize_post_init = kvm_cpu_synchronize_post_init;
     ops->synchronize_state = kvm_cpu_synchronize_state;
     ops->synchronize_pre_loadvm = kvm_cpu_synchronize_pre_loadvm;
+
+#ifdef KVM_CAP_SET_GUEST_DEBUG
+    ops->supports_guest_debug = kvm_supports_guest_debug;
+    ops->insert_breakpoint = kvm_insert_breakpoint;
+    ops->remove_breakpoint = kvm_remove_breakpoint;
+    ops->remove_all_breakpoints = kvm_remove_all_breakpoints;
+#endif
 }
 
 static const TypeInfo kvm_accel_ops_type = {

accel/kvm/kvm-all.c

@@ -175,7 +175,7 @@ bool kvm_direct_msi_allowed;
 bool kvm_ioeventfd_any_length_allowed;
 bool kvm_msi_use_devid;
 bool kvm_has_guest_debug;
-int kvm_sstep_flags;
+static int kvm_sstep_flags;
 static bool kvm_immediate_exit;
 static hwaddr kvm_max_slot_size = ~0;
 
@@ -719,12 +719,32 @@ static void kvm_dirty_ring_mark_page(KVMState *s, uint32_t as_id,
 
 static bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn)
 {
-    return gfn->flags == KVM_DIRTY_GFN_F_DIRTY;
+    /*
+     * Read the flags before the value.  Pairs with barrier in
+     * KVM's kvm_dirty_ring_push() function.
+     */
+    return qatomic_load_acquire(&gfn->flags) == KVM_DIRTY_GFN_F_DIRTY;
 }
 
 static void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn)
 {
-    gfn->flags = KVM_DIRTY_GFN_F_RESET;
+    /*
+     * Use a store-release so that the CPU that executes KVM_RESET_DIRTY_RINGS
+     * sees the full content of the ring:
+     *
+     * CPU0                     CPU1                         CPU2
+     * ------------------------------------------------------------------------------
+     *                                                       fill gfn0
+     *                                                       store-rel flags for gfn0
+     * load-acq flags for gfn0
+     * store-rel RESET for gfn0
+     *                          ioctl(RESET_RINGS)
+     *                            load-acq flags for gfn0
+     *                            check if flags have RESET
+     *
+     * The synchronization goes from CPU2 to CPU0 to CPU1.
+     */
+    qatomic_store_release(&gfn->flags, KVM_DIRTY_GFN_F_RESET);
 }
 
 /*
@@ -2265,7 +2285,7 @@ static void kvm_irqchip_create(KVMState *s)
     ret = kvm_arch_irqchip_create(s);
     if (ret == 0) {
         if (s->kernel_irqchip_split == ON_OFF_AUTO_ON) {
-            perror("Split IRQ chip mode not supported.");
+            error_report("Split IRQ chip mode not supported.");
             exit(1);
         } else {
             ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP);
@@ -3267,8 +3287,13 @@ int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap)
     return data.err;
 }
 
-int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
+bool kvm_supports_guest_debug(void)
-                          target_ulong len, int type)
+{
+    /* probed during kvm_init() */
+    return kvm_has_guest_debug;
+}
+
+int kvm_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
 {
     struct kvm_sw_breakpoint *bp;
     int err;
@@ -3306,8 +3331,7 @@ int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
     return 0;
 }
 
-int kvm_remove_breakpoint(CPUState *cpu, target_ulong addr,
+int kvm_remove_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
-                          target_ulong len, int type)
 {
     struct kvm_sw_breakpoint *bp;
     int err;
@@ -3371,28 +3395,6 @@ void kvm_remove_all_breakpoints(CPUState *cpu)
     }
 }
 
-#else /* !KVM_CAP_SET_GUEST_DEBUG */
-
-int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap)
-{
-    return -EINVAL;
-}
-
-int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
-                          target_ulong len, int type)
-{
-    return -EINVAL;
-}
-
-int kvm_remove_breakpoint(CPUState *cpu, target_ulong addr,
-                          target_ulong len, int type)
-{
-    return -EINVAL;
-}
-
-void kvm_remove_all_breakpoints(CPUState *cpu)
-{
-}
 #endif /* !KVM_CAP_SET_GUEST_DEBUG */
 
 static int kvm_set_signal_mask(CPUState *cpu, const sigset_t *sigset)
@@ -3692,6 +3694,17 @@ static void kvm_accel_instance_init(Object *obj)
     s->kvm_dirty_ring_size = 0;
 }
 
+/**
+ * kvm_gdbstub_sstep_flags():
+ *
+ * Returns: SSTEP_* flags that KVM supports for guest debug. The
+ * support is probed during kvm_init()
+ */
+static int kvm_gdbstub_sstep_flags(void)
+{
+    return kvm_sstep_flags;
+}
+
 static void kvm_accel_class_init(ObjectClass *oc, void *data)
 {
     AccelClass *ac = ACCEL_CLASS(oc);
@@ -3699,6 +3712,7 @@ 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;
+    ac->gdbstub_supported_sstep_flags = kvm_gdbstub_sstep_flags;
 
     object_class_property_add(oc, "kernel-irqchip", "on|off|split",
         NULL, kvm_set_kernel_irqchip,
@@ -3888,7 +3902,7 @@ exit:
 typedef struct StatsDescriptors {
     const char *ident; /* cache key, currently the StatsTarget */
     struct kvm_stats_desc *kvm_stats_desc;
-    struct kvm_stats_header *kvm_stats_header;
+    struct kvm_stats_header kvm_stats_header;
     QTAILQ_ENTRY(StatsDescriptors) next;
 } StatsDescriptors;
 
@@ -3919,7 +3933,7 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
     descriptors = g_new0(StatsDescriptors, 1);
 
     /* Read stats header */
-    kvm_stats_header = g_malloc(sizeof(*kvm_stats_header));
+    kvm_stats_header = &descriptors->kvm_stats_header;
     ret = read(stats_fd, kvm_stats_header, sizeof(*kvm_stats_header));
     if (ret != sizeof(*kvm_stats_header)) {
         error_setg(errp, "KVM stats: failed to read stats header: "
@@ -3944,7 +3958,6 @@ static StatsDescriptors *find_stats_descriptors(StatsTarget target, int stats_fd
         g_free(kvm_stats_desc);
         return NULL;
     }
-    descriptors->kvm_stats_header = kvm_stats_header;
     descriptors->kvm_stats_desc = kvm_stats_desc;
     descriptors->ident = ident;
     QTAILQ_INSERT_TAIL(&stats_descriptors, descriptors, next);
@@ -3969,7 +3982,7 @@ static void query_stats(StatsResultList **result, StatsTarget target,
         return;
     }
 
-    kvm_stats_header = descriptors->kvm_stats_header;
+    kvm_stats_header = &descriptors->kvm_stats_header;
     kvm_stats_desc = descriptors->kvm_stats_desc;
     size_desc = sizeof(*kvm_stats_desc) + kvm_stats_header->name_size;
 
@@ -4034,7 +4047,7 @@ static void query_stats_schema(StatsSchemaList **result, StatsTarget target,
         return;
     }
 
-    kvm_stats_header = descriptors->kvm_stats_header;
+    kvm_stats_header = &descriptors->kvm_stats_header;
     kvm_stats_desc = descriptors->kvm_stats_desc;
     size_desc = sizeof(*kvm_stats_desc) + kvm_stats_header->name_size;
 
@@ -4131,7 +4144,9 @@ void query_stats_schemas_cb(StatsSchemaList **result, Error **errp)
     query_stats_schema(result, STATS_TARGET_VM, stats_fd, errp);
     close(stats_fd);
 
-    stats_args.result.schema = result;
+    if (first_cpu) {
-    stats_args.errp = errp;
+        stats_args.result.schema = result;
-    run_on_cpu(first_cpu, query_stats_schema_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
+        stats_args.errp = errp;
+        run_on_cpu(first_cpu, query_stats_schema_vcpu, RUN_ON_CPU_HOST_PTR(&stats_args));
+    }
 }

accel/kvm/kvm-cpus.h

@@ -18,5 +18,9 @@ void kvm_destroy_vcpu(CPUState *cpu);
 void kvm_cpu_synchronize_post_reset(CPUState *cpu);
 void kvm_cpu_synchronize_post_init(CPUState *cpu);
 void kvm_cpu_synchronize_pre_loadvm(CPUState *cpu);
+bool kvm_supports_guest_debug(void);
+int kvm_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len);
+int kvm_remove_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len);
+void kvm_remove_all_breakpoints(CPUState *cpu);
 
 #endif /* KVM_CPUS_H */

accel/stubs/kvm-stub.c

@@ -46,27 +46,6 @@ int kvm_has_many_ioeventfds(void)
     return 0;
 }
 
-int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap)
-{
-    return -ENOSYS;
-}
-
-int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
-                          target_ulong len, int type)
-{
-    return -EINVAL;
-}
-
-int kvm_remove_breakpoint(CPUState *cpu, target_ulong addr,
-                          target_ulong len, int type)
-{
-    return -EINVAL;
-}
-
-void kvm_remove_all_breakpoints(CPUState *cpu)
-{
-}
-
 int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
 {
     return 1;

accel/stubs/tcg-stub.c

@@ -21,6 +21,10 @@ void tlb_set_dirty(CPUState *cpu, target_ulong vaddr)
 {
 }
 
+void tcg_flush_jmp_cache(CPUState *cpu)
+{
+}
+
 int probe_access_flags(CPUArchState *env, target_ulong addr,
                        MMUAccessType access_type, int mmu_idx,
                        bool nonfault, void **phost, uintptr_t retaddr)

accel/tcg/cpu-exec.c

@@ -42,6 +42,7 @@
 #include "sysemu/replay.h"
 #include "sysemu/tcg.h"
 #include "exec/helper-proto.h"
+#include "tb-jmp-cache.h"
 #include "tb-hash.h"
 #include "tb-context.h"
 #include "internal.h"
@@ -170,22 +171,95 @@ uint32_t curr_cflags(CPUState *cpu)
     return cflags;
 }
 
+struct tb_desc {
+    target_ulong pc;
+    target_ulong cs_base;
+    CPUArchState *env;
+    tb_page_addr_t page_addr0;
+    uint32_t flags;
+    uint32_t cflags;
+    uint32_t trace_vcpu_dstate;
+};
+
+static bool tb_lookup_cmp(const void *p, const void *d)
+{
+    const TranslationBlock *tb = p;
+    const struct tb_desc *desc = d;
+
+    if ((TARGET_TB_PCREL || tb_pc(tb) == desc->pc) &&
+        tb->page_addr[0] == desc->page_addr0 &&
+        tb->cs_base == desc->cs_base &&
+        tb->flags == desc->flags &&
+        tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
+        tb_cflags(tb) == desc->cflags) {
+        /* check next page if needed */
+        if (tb->page_addr[1] == -1) {
+            return true;
+        } else {
+            tb_page_addr_t phys_page1;
+            target_ulong virt_page1;
+
+            /*
+             * We know that the first page matched, and an otherwise valid TB
+             * encountered an incomplete instruction at the end of that page,
+             * therefore we know that generating a new TB from the current PC
+             * must also require reading from the next page -- even if the
+             * second pages do not match, and therefore the resulting insn
+             * is different for the new TB.  Therefore any exception raised
+             * here by the faulting lookup is not premature.
+             */
+            virt_page1 = TARGET_PAGE_ALIGN(desc->pc);
+            phys_page1 = get_page_addr_code(desc->env, virt_page1);
+            if (tb->page_addr[1] == phys_page1) {
+                return true;
+            }
+        }
+    }
+    return false;
+}
+
+static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
+                                          target_ulong cs_base, uint32_t flags,
+                                          uint32_t cflags)
+{
+    tb_page_addr_t phys_pc;
+    struct tb_desc desc;
+    uint32_t h;
+
+    desc.env = cpu->env_ptr;
+    desc.cs_base = cs_base;
+    desc.flags = flags;
+    desc.cflags = cflags;
+    desc.trace_vcpu_dstate = *cpu->trace_dstate;
+    desc.pc = pc;
+    phys_pc = get_page_addr_code(desc.env, pc);
+    if (phys_pc == -1) {
+        return NULL;
+    }
+    desc.page_addr0 = phys_pc;
+    h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : pc),
+                     flags, cflags, *cpu->trace_dstate);
+    return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
+}
+
 /* Might cause an exception, so have a longjmp destination ready */
 static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc,
                                           target_ulong cs_base,
                                           uint32_t flags, uint32_t cflags)
 {
     TranslationBlock *tb;
+    CPUJumpCache *jc;
     uint32_t hash;
 
     /* we should never be trying to look up an INVALID tb */
     tcg_debug_assert(!(cflags & CF_INVALID));
 
     hash = tb_jmp_cache_hash_func(pc);
-    tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]);
+    jc = cpu->tb_jmp_cache;
+    tb = tb_jmp_cache_get_tb(jc, hash);
 
     if (likely(tb &&
-               tb->pc == pc &&
+               tb_jmp_cache_get_pc(jc, hash, tb) == pc &&
                tb->cs_base == cs_base &&
                tb->flags == flags &&
                tb->trace_vcpu_dstate == *cpu->trace_dstate &&
@@ -196,16 +270,14 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc,
     if (tb == NULL) {
         return NULL;
     }
-    qatomic_set(&cpu->tb_jmp_cache[hash], tb);
+    tb_jmp_cache_set(jc, hash, tb, pc);
     return tb;
 }
 
-static inline void log_cpu_exec(target_ulong pc, CPUState *cpu,
+static void log_cpu_exec(target_ulong pc, CPUState *cpu,
-                                const TranslationBlock *tb)
+                         const TranslationBlock *tb)
 {
-    if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC))
+    if (qemu_log_in_addr_range(pc)) {
-        && qemu_log_in_addr_range(pc)) {
-
         qemu_log_mask(CPU_LOG_EXEC,
                       "Trace %d: %p [" TARGET_FMT_lx
                       "/" TARGET_FMT_lx "/%08x/%08x] %s\n",
@@ -329,7 +401,9 @@ const void *HELPER(lookup_tb_ptr)(CPUArchState *env)
         return tcg_code_gen_epilogue;
     }
 
-    log_cpu_exec(pc, cpu, tb);
+    if (qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) {
+        log_cpu_exec(pc, cpu, tb);
+    }
 
     return tb->tc.ptr;
 }
@@ -352,7 +426,9 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
     TranslationBlock *last_tb;
     const void *tb_ptr = itb->tc.ptr;
 
-    log_cpu_exec(itb->pc, cpu, itb);
+    if (qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) {
+        log_cpu_exec(log_pc(cpu, itb), cpu, itb);
+    }
 
     qemu_thread_jit_execute();
     ret = tcg_qemu_tb_exec(env, tb_ptr);
@@ -376,16 +452,21 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
          * of the start of the TB.
          */
         CPUClass *cc = CPU_GET_CLASS(cpu);
-        qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc,
+
-                               "Stopped execution of TB chain before %p ["
-                               TARGET_FMT_lx "] %s\n",
-                               last_tb->tc.ptr, last_tb->pc,
-                               lookup_symbol(last_tb->pc));
         if (cc->tcg_ops->synchronize_from_tb) {
             cc->tcg_ops->synchronize_from_tb(cpu, last_tb);
         } else {
+            assert(!TARGET_TB_PCREL);
             assert(cc->set_pc);
-            cc->set_pc(cpu, last_tb->pc);
+            cc->set_pc(cpu, tb_pc(last_tb));
+        }
+        if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
+            target_ulong pc = log_pc(cpu, last_tb);
+            if (qemu_log_in_addr_range(pc)) {
+                qemu_log("Stopped execution of TB chain before %p ["
+                         TARGET_FMT_lx "] %s\n",
+                         last_tb->tc.ptr, pc, lookup_symbol(pc));
+            }
         }
     }
 
@@ -462,13 +543,11 @@ void cpu_exec_step_atomic(CPUState *cpu)
         cpu_tb_exec(cpu, tb, &tb_exit);
         cpu_exec_exit(cpu);
     } else {
-        /*
-         * The mmap_lock is dropped by tb_gen_code if it runs out of
-         * memory.
-         */
 #ifndef CONFIG_SOFTMMU
         clear_helper_retaddr();
-        tcg_debug_assert(!have_mmap_lock());
+        if (have_mmap_lock()) {
+            mmap_unlock();
+        }
 #endif
         if (qemu_mutex_iothread_locked()) {
             qemu_mutex_unlock_iothread();
@@ -487,67 +566,6 @@ void cpu_exec_step_atomic(CPUState *cpu)
     end_exclusive();
 }
 
-struct tb_desc {
-    target_ulong pc;
-    target_ulong cs_base;
-    CPUArchState *env;
-    tb_page_addr_t phys_page1;
-    uint32_t flags;
-    uint32_t cflags;
-    uint32_t trace_vcpu_dstate;
-};
-
-static bool tb_lookup_cmp(const void *p, const void *d)
-{
-    const TranslationBlock *tb = p;
-    const struct tb_desc *desc = d;
-
-    if (tb->pc == desc->pc &&
-        tb->page_addr[0] == desc->phys_page1 &&
-        tb->cs_base == desc->cs_base &&
-        tb->flags == desc->flags &&
-        tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
-        tb_cflags(tb) == desc->cflags) {
-        /* check next page if needed */
-        if (tb->page_addr[1] == -1) {
-            return true;
-        } else {
-            tb_page_addr_t phys_page2;
-            target_ulong virt_page2;
-
-            virt_page2 = (desc->pc & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
-            phys_page2 = get_page_addr_code(desc->env, virt_page2);
-            if (tb->page_addr[1] == phys_page2) {
-                return true;
-            }
-        }
-    }
-    return false;
-}
-
-TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
-                                   target_ulong cs_base, uint32_t flags,
-                                   uint32_t cflags)
-{
-    tb_page_addr_t phys_pc;
-    struct tb_desc desc;
-    uint32_t h;
-
-    desc.env = cpu->env_ptr;
-    desc.cs_base = cs_base;
-    desc.flags = flags;
-    desc.cflags = cflags;
-    desc.trace_vcpu_dstate = *cpu->trace_dstate;
-    desc.pc = pc;
-    phys_pc = get_page_addr_code(desc.env, pc);
-    if (phys_pc == -1) {
-        return NULL;
-    }
-    desc.phys_page1 = phys_pc & TARGET_PAGE_MASK;
-    h = tb_hash_func(phys_pc, pc, flags, cflags, *cpu->trace_dstate);
-    return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
-}
-
 void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)
 {
     if (TCG_TARGET_HAS_direct_jump) {
@@ -590,11 +608,8 @@ static inline void tb_add_jump(TranslationBlock *tb, int n,
 
     qemu_spin_unlock(&tb_next->jmp_lock);
 
-    qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc,
+    qemu_log_mask(CPU_LOG_EXEC, "Linking TBs %p index %d -> %p\n",
-                           "Linking TBs %p [" TARGET_FMT_lx
+                  tb->tc.ptr, n, tb_next->tc.ptr);
-                           "] index %d -> %p [" TARGET_FMT_lx "]\n",
-                           tb->tc.ptr, tb->pc, n,
-                           tb_next->tc.ptr, tb_next->pc);
     return;
 
  out_unlock_next:
@@ -852,11 +867,12 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
 }
 
 static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
+                                    target_ulong pc,
                                     TranslationBlock **last_tb, int *tb_exit)
 {
     int32_t insns_left;
 
-    trace_exec_tb(tb, tb->pc);
+    trace_exec_tb(tb, pc);
     tb = cpu_tb_exec(cpu, tb, tb_exit);
     if (*tb_exit != TB_EXIT_REQUESTED) {
         *last_tb = tb;
@@ -964,7 +980,9 @@ int cpu_exec(CPUState *cpu)
 
 #ifndef CONFIG_SOFTMMU
         clear_helper_retaddr();
-        tcg_debug_assert(!have_mmap_lock());
+        if (have_mmap_lock()) {
+            mmap_unlock();
+        }
 #endif
         if (qemu_mutex_iothread_locked()) {
             qemu_mutex_unlock_iothread();
@@ -1006,6 +1024,8 @@ int cpu_exec(CPUState *cpu)
 
             tb = tb_lookup(cpu, pc, cs_base, flags, cflags);
             if (tb == NULL) {
+                uint32_t h;
+
                 mmap_lock();
                 tb = tb_gen_code(cpu, pc, cs_base, flags, cflags);
                 mmap_unlock();
@@ -1013,7 +1033,8 @@ int cpu_exec(CPUState *cpu)
                  * We add the TB in the virtual pc hash table
                  * for the fast lookup
                  */
-                qatomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
+                h = tb_jmp_cache_hash_func(pc);
+                tb_jmp_cache_set(cpu->tb_jmp_cache, h, tb, pc);
             }
 
 #ifndef CONFIG_USER_ONLY
@@ -1052,7 +1073,7 @@ int cpu_exec(CPUState *cpu)
                 //// --- End LibAFL code ---
             }
 
-            cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit);
+            cpu_loop_exec_tb(cpu, tb, pc, &last_tb, &tb_exit);
 
             /* Try to align the host and virtual clocks
                if the guest is in advance */

accel/tcg/cputlb.c

@@ -100,21 +100,14 @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,
 
 static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr)
 {
-    unsigned int i, i0 = tb_jmp_cache_hash_page(page_addr);
+    int i, i0 = tb_jmp_cache_hash_page(page_addr);
+    CPUJumpCache *jc = cpu->tb_jmp_cache;
 
     for (i = 0; i < TB_JMP_PAGE_SIZE; i++) {
-        qatomic_set(&cpu->tb_jmp_cache[i0 + i], NULL);
+        qatomic_set(&jc->array[i0 + i].tb, NULL);
     }
 }
 
-static void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr)
-{
-    /* Discard jump cache entries for any tb which might potentially
-       overlap the flushed page.  */
-    tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE);
-    tb_jmp_cache_clear_page(cpu, addr);
-}
-
 /**
  * tlb_mmu_resize_locked() - perform TLB resize bookkeeping; resize if necessary
  * @desc: The CPUTLBDesc portion of the TLB
@@ -200,13 +193,13 @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,
     }
 
     g_free(fast->table);
-    g_free(desc->iotlb);
+    g_free(desc->fulltlb);
 
     tlb_window_reset(desc, now, 0);
     /* desc->n_used_entries is cleared by the caller */
     fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
     fast->table = g_try_new(CPUTLBEntry, new_size);
-    desc->iotlb = g_try_new(CPUIOTLBEntry, new_size);
+    desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size);
 
     /*
      * If the allocations fail, try smaller sizes. We just freed some
@@ -215,7 +208,7 @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,
      * allocations to fail though, so we progressively reduce the allocation
      * size, aborting if we cannot even allocate the smallest TLB we support.
      */
-    while (fast->table == NULL || desc->iotlb == NULL) {
+    while (fast->table == NULL || desc->fulltlb == NULL) {
         if (new_size == (1 << CPU_TLB_DYN_MIN_BITS)) {
             error_report("%s: %s", __func__, strerror(errno));
             abort();
@@ -224,9 +217,9 @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,
         fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
 
         g_free(fast->table);
-        g_free(desc->iotlb);
+        g_free(desc->fulltlb);
         fast->table = g_try_new(CPUTLBEntry, new_size);
-        desc->iotlb = g_try_new(CPUIOTLBEntry, new_size);
+        desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size);
     }
 }
 
@@ -258,7 +251,7 @@ static void tlb_mmu_init(CPUTLBDesc *desc, CPUTLBDescFast *fast, int64_t now)
     desc->n_used_entries = 0;
     fast->mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS;
     fast->table = g_new(CPUTLBEntry, n_entries);
-    desc->iotlb = g_new(CPUIOTLBEntry, n_entries);
+    desc->fulltlb = g_new(CPUTLBEntryFull, n_entries);
     tlb_mmu_flush_locked(desc, fast);
 }
 
@@ -299,7 +292,7 @@ void tlb_destroy(CPUState *cpu)
         CPUTLBDescFast *fast = &env_tlb(env)->f[i];
 
         g_free(fast->table);
-        g_free(desc->iotlb);
+        g_free(desc->fulltlb);
     }
 }
 
@@ -364,7 +357,7 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
 
     qemu_spin_unlock(&env_tlb(env)->c.lock);
 
-    cpu_tb_jmp_cache_clear(cpu);
+    tcg_flush_jmp_cache(cpu);
 
     if (to_clean == ALL_MMUIDX_BITS) {
         qatomic_set(&env_tlb(env)->c.full_flush_count,
@@ -541,7 +534,12 @@ static void tlb_flush_page_by_mmuidx_async_0(CPUState *cpu,
     }
     qemu_spin_unlock(&env_tlb(env)->c.lock);
 
-    tb_flush_jmp_cache(cpu, addr);
+    /*
+     * Discard jump cache entries for any tb which might potentially
+     * overlap the flushed page, which includes the previous.
+     */
+    tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE);
+    tb_jmp_cache_clear_page(cpu, addr);
 }
 
 /**
@@ -788,12 +786,18 @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu,
      * longer to clear each entry individually than it will to clear it all.
      */
     if (d.len >= (TARGET_PAGE_SIZE * TB_JMP_CACHE_SIZE)) {
-        cpu_tb_jmp_cache_clear(cpu);
+        tcg_flush_jmp_cache(cpu);
         return;
     }
 
-    for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) {
+    /*
-        tb_flush_jmp_cache(cpu, d.addr + i);
+     * Discard jump cache entries for any tb which might potentially
+     * overlap the flushed pages, which includes the previous.
+     */
+    d.addr -= TARGET_PAGE_SIZE;
+    for (target_ulong i = 0, n = d.len / TARGET_PAGE_SIZE + 1; i < n; i++) {
+        tb_jmp_cache_clear_page(cpu, d.addr);
+        d.addr += TARGET_PAGE_SIZE;
     }
 }
 
@@ -951,7 +955,8 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
    can be detected */
 void tlb_protect_code(ram_addr_t ram_addr)
 {
-    cpu_physical_memory_test_and_clear_dirty(ram_addr, TARGET_PAGE_SIZE,
+    cpu_physical_memory_test_and_clear_dirty(ram_addr & TARGET_PAGE_MASK,
+                                             TARGET_PAGE_SIZE,
                                              DIRTY_MEMORY_CODE);
 }
 
@@ -1095,16 +1100,16 @@ static void tlb_add_large_page(CPUArchState *env, int mmu_idx,
     env_tlb(env)->d[mmu_idx].large_page_mask = lp_mask;
 }
 
-/* Add a new TLB entry. At most one entry for a given virtual address
+/*
+ * Add a new TLB entry. At most one entry for a given virtual address
  * is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the
  * supplied size is only used by tlb_flush_page.
  *
  * Called from TCG-generated code, which is under an RCU read-side
  * critical section.
  */
-void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
+void tlb_set_page_full(CPUState *cpu, int mmu_idx,
-                             hwaddr paddr, MemTxAttrs attrs, int prot,
+                       target_ulong vaddr, CPUTLBEntryFull *full)
-                             int mmu_idx, target_ulong size)
 {
     CPUArchState *env = cpu->env_ptr;
     CPUTLB *tlb = env_tlb(env);
@@ -1117,35 +1122,36 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
     CPUTLBEntry *te, tn;
     hwaddr iotlb, xlat, sz, paddr_page;
     target_ulong vaddr_page;
-    int asidx = cpu_asidx_from_attrs(cpu, attrs);
+    int asidx, wp_flags, prot;
-    int wp_flags;
     bool is_ram, is_romd;
 
     assert_cpu_is_self(cpu);
 
-    if (size <= TARGET_PAGE_SIZE) {
+    if (full->lg_page_size <= TARGET_PAGE_BITS) {
         sz = TARGET_PAGE_SIZE;
     } else {
-        tlb_add_large_page(env, mmu_idx, vaddr, size);
+        sz = (hwaddr)1 << full->lg_page_size;
-        sz = size;
+        tlb_add_large_page(env, mmu_idx, vaddr, sz);
     }
     vaddr_page = vaddr & TARGET_PAGE_MASK;
-    paddr_page = paddr & TARGET_PAGE_MASK;
+    paddr_page = full->phys_addr & TARGET_PAGE_MASK;
 
+    prot = full->prot;
+    asidx = cpu_asidx_from_attrs(cpu, full->attrs);
     section = address_space_translate_for_iotlb(cpu, asidx, paddr_page,
-                                                &xlat, &sz, attrs, &prot);
+                                                &xlat, &sz, full->attrs, &prot);
     assert(sz >= TARGET_PAGE_SIZE);
 
     tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
               " prot=%x idx=%d\n",
-              vaddr, paddr, prot, mmu_idx);
+              vaddr, full->phys_addr, prot, mmu_idx);
 
     address = vaddr_page;
-    if (size < TARGET_PAGE_SIZE) {
+    if (full->lg_page_size < TARGET_PAGE_BITS) {
         /* Repeat the MMU check and TLB fill on every access.  */
         address |= TLB_INVALID_MASK;
     }
-    if (attrs.byte_swap) {
+    if (full->attrs.byte_swap) {
         address |= TLB_BSWAP;
     }
 
@@ -1219,7 +1225,7 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
 
         /* Evict the old entry into the victim tlb.  */
         copy_tlb_helper_locked(tv, te);
-        desc->viotlb[vidx] = desc->iotlb[index];
+        desc->vfulltlb[vidx] = desc->fulltlb[index];
         tlb_n_used_entries_dec(env, mmu_idx);
     }
 
@@ -1236,8 +1242,10 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
      * subtract here is that of the page base, and not the same as the
      * vaddr we add back in io_readx()/io_writex()/get_page_addr_code().
      */
-    desc->iotlb[index].addr = iotlb - vaddr_page;
+    desc->fulltlb[index] = *full;
-    desc->iotlb[index].attrs = attrs;
+    desc->fulltlb[index].xlat_section = iotlb - vaddr_page;
+    desc->fulltlb[index].phys_addr = paddr_page;
+    desc->fulltlb[index].prot = prot;
 
     /* Now calculate the new entry */
     tn.addend = addend - vaddr_page;
@@ -1272,9 +1280,21 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
     qemu_spin_unlock(&tlb->c.lock);
 }
 
-/* Add a new TLB entry, but without specifying the memory
+void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
- * transaction attributes to be used.
+                             hwaddr paddr, MemTxAttrs attrs, int prot,
- */
+                             int mmu_idx, target_ulong size)
+{
+    CPUTLBEntryFull full = {
+        .phys_addr = paddr,
+        .attrs = attrs,
+        .prot = prot,
+        .lg_page_size = ctz64(size)
+    };
+
+    assert(is_power_of_2(size));
+    tlb_set_page_full(cpu, mmu_idx, vaddr, &full);
+}
+
 void tlb_set_page(CPUState *cpu, target_ulong vaddr,
                   hwaddr paddr, int prot,
                   int mmu_idx, target_ulong size)
@@ -1283,18 +1303,6 @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr,
                             prot, mmu_idx, size);
 }
 
-static inline ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr)
-{
-    ram_addr_t ram_addr;
-
-    ram_addr = qemu_ram_addr_from_host(ptr);
-    if (ram_addr == RAM_ADDR_INVALID) {
-        error_report("Bad ram pointer %p", ptr);
-        abort();
-    }
-    return ram_addr;
-}
-
 /*
  * Note: tlb_fill() can trigger a resize of the TLB. This means that all of the
  * caller's prior references to the TLB table (e.g. CPUTLBEntry pointers) must
@@ -1303,15 +1311,14 @@ static inline ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr)
 static void tlb_fill(CPUState *cpu, target_ulong addr, int size,
                      MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
 {
-    CPUClass *cc = CPU_GET_CLASS(cpu);
     bool ok;
 
     /*
      * This is not a probe, so only valid return is success; failure
      * should result in exception + longjmp to the cpu loop.
      */
-    ok = cc->tcg_ops->tlb_fill(cpu, addr, size,
+    ok = cpu->cc->tcg_ops->tlb_fill(cpu, addr, size,
-                               access_type, mmu_idx, false, retaddr);
+                                    access_type, mmu_idx, false, retaddr);
     assert(ok);
 }
 
@@ -1319,9 +1326,8 @@ static inline void cpu_unaligned_access(CPUState *cpu, vaddr addr,
                                         MMUAccessType access_type,
                                         int mmu_idx, uintptr_t retaddr)
 {
-    CPUClass *cc = CPU_GET_CLASS(cpu);
+    cpu->cc->tcg_ops->do_unaligned_access(cpu, addr, access_type,
-
+                                          mmu_idx, retaddr);
-    cc->tcg_ops->do_unaligned_access(cpu, addr, access_type, mmu_idx, retaddr);
 }
 
 static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr,
@@ -1341,7 +1347,7 @@ static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr,
     }
 }
 
-static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
+static uint64_t io_readx(CPUArchState *env, CPUTLBEntryFull *full,
                          int mmu_idx, target_ulong addr, uintptr_t retaddr,
                          MMUAccessType access_type, MemOp op)
 {
@@ -1353,9 +1359,9 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     bool locked = false;
     MemTxResult r;
 
-    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
+    section = iotlb_to_section(cpu, full->xlat_section, full->attrs);
     mr = section->mr;
-    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+    mr_offset = (full->xlat_section & TARGET_PAGE_MASK) + addr;
     cpu->mem_io_pc = retaddr;
     if (!cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
@@ -1365,14 +1371,14 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    r = memory_region_dispatch_read(mr, mr_offset, &val, op, iotlbentry->attrs);
+    r = memory_region_dispatch_read(mr, mr_offset, &val, op, full->attrs);
     if (r != MEMTX_OK) {
         hwaddr physaddr = mr_offset +
             section->offset_within_address_space -
             section->offset_within_region;
 
         cpu_transaction_failed(cpu, physaddr, addr, memop_size(op), access_type,
-                               mmu_idx, iotlbentry->attrs, r, retaddr);
+                               mmu_idx, full->attrs, r, retaddr);
     }
     if (locked) {
         qemu_mutex_unlock_iothread();
@@ -1382,22 +1388,21 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
 }
 
 /*
- * Save a potentially trashed IOTLB entry for later lookup by plugin.
+ * Save a potentially trashed CPUTLBEntryFull for later lookup by plugin.
- * This is read by tlb_plugin_lookup if the iotlb entry doesn't match
+ * This is read by tlb_plugin_lookup if the fulltlb entry doesn't match
  * because of the side effect of io_writex changing memory layout.
  */
-static void save_iotlb_data(CPUState *cs, hwaddr addr,
+static void save_iotlb_data(CPUState *cs, MemoryRegionSection *section,
-                            MemoryRegionSection *section, hwaddr mr_offset)
+                            hwaddr mr_offset)
 {
 #ifdef CONFIG_PLUGIN
     SavedIOTLB *saved = &cs->saved_iotlb;
-    saved->addr = addr;
     saved->section = section;
     saved->mr_offset = mr_offset;
 #endif
 }
 
-static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
+static void io_writex(CPUArchState *env, CPUTLBEntryFull *full,
                       int mmu_idx, uint64_t val, target_ulong addr,
                       uintptr_t retaddr, MemOp op)
 {
@@ -1408,9 +1413,9 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     bool locked = false;
     MemTxResult r;
 
-    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
+    section = iotlb_to_section(cpu, full->xlat_section, full->attrs);
     mr = section->mr;
-    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+    mr_offset = (full->xlat_section & TARGET_PAGE_MASK) + addr;
     if (!cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
     }
@@ -1420,20 +1425,20 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
      * The memory_region_dispatch may trigger a flush/resize
      * so for plugins we save the iotlb_data just in case.
      */
-    save_iotlb_data(cpu, iotlbentry->addr, section, mr_offset);
+    save_iotlb_data(cpu, section, mr_offset);
 
     if (!qemu_mutex_iothread_locked()) {
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    r = memory_region_dispatch_write(mr, mr_offset, val, op, iotlbentry->attrs);
+    r = memory_region_dispatch_write(mr, mr_offset, val, op, full->attrs);
     if (r != MEMTX_OK) {
         hwaddr physaddr = mr_offset +
             section->offset_within_address_space -
             section->offset_within_region;
 
         cpu_transaction_failed(cpu, physaddr, addr, memop_size(op),
-                               MMU_DATA_STORE, mmu_idx, iotlbentry->attrs, r,
+                               MMU_DATA_STORE, mmu_idx, full->attrs, r,
                                retaddr);
     }
     if (locked) {
@@ -1480,9 +1485,10 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
             copy_tlb_helper_locked(vtlb, &tmptlb);
             qemu_spin_unlock(&env_tlb(env)->c.lock);
 
-            CPUIOTLBEntry tmpio, *io = &env_tlb(env)->d[mmu_idx].iotlb[index];
+            CPUTLBEntryFull *f1 = &env_tlb(env)->d[mmu_idx].fulltlb[index];
-            CPUIOTLBEntry *vio = &env_tlb(env)->d[mmu_idx].viotlb[vidx];
+            CPUTLBEntryFull *f2 = &env_tlb(env)->d[mmu_idx].vfulltlb[vidx];
-            tmpio = *io; *io = *vio; *vio = tmpio;
+            CPUTLBEntryFull tmpf;
+            tmpf = *f1; *f1 = *f2; *f2 = tmpf;
             return true;
         }
     }
@@ -1494,65 +1500,10 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
   victim_tlb_hit(env, mmu_idx, index, offsetof(CPUTLBEntry, TY), \
                  (ADDR) & TARGET_PAGE_MASK)
 
-/*
- * Return a ram_addr_t for the virtual address for execution.
- *
- * Return -1 if we can't translate and execute from an entire page
- * of RAM.  This will force us to execute by loading and translating
- * one insn at a time, without caching.
- *
- * NOTE: This function will trigger an exception if the page is
- * not executable.
- */
-tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr,
-                                        void **hostp)
-{
-    uintptr_t mmu_idx = cpu_mmu_index(env, true);
-    uintptr_t index = tlb_index(env, mmu_idx, addr);
-    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
-    void *p;
-
-    if (unlikely(!tlb_hit(entry->addr_code, addr))) {
-        if (!VICTIM_TLB_HIT(addr_code, addr)) {
-            tlb_fill(env_cpu(env), addr, 0, MMU_INST_FETCH, mmu_idx, 0);
-            index = tlb_index(env, mmu_idx, addr);
-            entry = tlb_entry(env, mmu_idx, addr);
-
-            if (unlikely(entry->addr_code & TLB_INVALID_MASK)) {
-                /*
-                 * The MMU protection covers a smaller range than a target
-                 * page, so we must redo the MMU check for every insn.
-                 */
-                return -1;
-            }
-        }
-        assert(tlb_hit(entry->addr_code, addr));
-    }
-
-    if (unlikely(entry->addr_code & TLB_MMIO)) {
-        /* The region is not backed by RAM.  */
-        if (hostp) {
-            *hostp = NULL;
-        }
-        return -1;
-    }
-
-    p = (void *)((uintptr_t)addr + entry->addend);
-    if (hostp) {
-        *hostp = p;
-    }
-    return qemu_ram_addr_from_host_nofail(p);
-}
-
-tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
-{
-    return get_page_addr_code_hostp(env, addr, NULL);
-}
-
 static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size,
-                           CPUIOTLBEntry *iotlbentry, uintptr_t retaddr)
+                           CPUTLBEntryFull *full, uintptr_t retaddr)
 {
-    ram_addr_t ram_addr = mem_vaddr + iotlbentry->addr;
+    ram_addr_t ram_addr = mem_vaddr + full->xlat_section;
 
     trace_memory_notdirty_write_access(mem_vaddr, ram_addr, size);
 
@@ -1579,7 +1530,8 @@ static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size,
 static int probe_access_internal(CPUArchState *env, target_ulong addr,
                                  int fault_size, MMUAccessType access_type,
                                  int mmu_idx, bool nonfault,
-                                 void **phost, uintptr_t retaddr)
+                                 void **phost, CPUTLBEntryFull **pfull,
+                                 uintptr_t retaddr)
 {
     uintptr_t index = tlb_index(env, mmu_idx, addr);
     CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
@@ -1602,25 +1554,36 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr,
     }
     tlb_addr = tlb_read_ofs(entry, elt_ofs);
 
+    flags = TLB_FLAGS_MASK;
     page_addr = addr & TARGET_PAGE_MASK;
     if (!tlb_hit_page(tlb_addr, page_addr)) {
         if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) {
             CPUState *cs = env_cpu(env);
-            CPUClass *cc = CPU_GET_CLASS(cs);
 
-            if (!cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type,
+            if (!cs->cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type,
-                                       mmu_idx, nonfault, retaddr)) {
+                                           mmu_idx, nonfault, retaddr)) {
                 /* Non-faulting page table read failed.  */
                 *phost = NULL;
+                *pfull = NULL;
                 return TLB_INVALID_MASK;
             }
 
             /* TLB resize via tlb_fill may have moved the entry.  */
+            index = tlb_index(env, mmu_idx, addr);
             entry = tlb_entry(env, mmu_idx, addr);
+
+            /*
+             * With PAGE_WRITE_INV, we set TLB_INVALID_MASK immediately,
+             * to force the next access through tlb_fill.  We've just
+             * called tlb_fill, so we know that this entry *is* valid.
+             */
+            flags &= ~TLB_INVALID_MASK;
         }
         tlb_addr = tlb_read_ofs(entry, elt_ofs);
     }
-    flags = tlb_addr & TLB_FLAGS_MASK;
+    flags &= tlb_addr;
+
+    *pfull = &env_tlb(env)->d[mmu_idx].fulltlb[index];
 
     /* Fold all "mmio-like" bits into TLB_MMIO.  This is not RAM.  */
     if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) {
@@ -1633,37 +1596,44 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr,
     return flags;
 }
 
-int probe_access_flags(CPUArchState *env, target_ulong addr,
+int probe_access_full(CPUArchState *env, target_ulong addr,
-                       MMUAccessType access_type, int mmu_idx,
+                      MMUAccessType access_type, int mmu_idx,
-                       bool nonfault, void **phost, uintptr_t retaddr)
+                      bool nonfault, void **phost, CPUTLBEntryFull **pfull,
+                      uintptr_t retaddr)
 {
-    int flags;
+    int flags = probe_access_internal(env, addr, 0, access_type, mmu_idx,
-
+                                      nonfault, phost, pfull, retaddr);
-    flags = probe_access_internal(env, addr, 0, access_type, mmu_idx,
-                                  nonfault, phost, retaddr);
 
     /* Handle clean RAM pages.  */
     if (unlikely(flags & TLB_NOTDIRTY)) {
-        uintptr_t index = tlb_index(env, mmu_idx, addr);
+        notdirty_write(env_cpu(env), addr, 1, *pfull, retaddr);
-        CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
-
-        notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr);
         flags &= ~TLB_NOTDIRTY;
     }
 
     return flags;
 }
 
+int probe_access_flags(CPUArchState *env, target_ulong addr,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool nonfault, void **phost, uintptr_t retaddr)
+{
+    CPUTLBEntryFull *full;
+
+    return probe_access_full(env, addr, access_type, mmu_idx,
+                             nonfault, phost, &full, retaddr);
+}
+
 void *probe_access(CPUArchState *env, target_ulong addr, int size,
                    MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
 {
+    CPUTLBEntryFull *full;
     void *host;
     int flags;
 
     g_assert(-(addr | TARGET_PAGE_MASK) >= size);
 
     flags = probe_access_internal(env, addr, size, access_type, mmu_idx,
-                                  false, &host, retaddr);
+                                  false, &host, &full, retaddr);
 
     /* Per the interface, size == 0 merely faults the access. */
     if (size == 0) {
@@ -1671,20 +1641,17 @@ void *probe_access(CPUArchState *env, target_ulong addr, int size,
     }
 
     if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) {
-        uintptr_t index = tlb_index(env, mmu_idx, addr);
-        CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
-
         /* Handle watchpoints.  */
         if (flags & TLB_WATCHPOINT) {
             int wp_access = (access_type == MMU_DATA_STORE
                              ? BP_MEM_WRITE : BP_MEM_READ);
             cpu_check_watchpoint(env_cpu(env), addr, size,
-                                 iotlbentry->attrs, wp_access, retaddr);
+                                 full->attrs, wp_access, retaddr);
         }
 
         /* Handle clean RAM pages.  */
         if (flags & TLB_NOTDIRTY) {
-            notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr);
+            notdirty_write(env_cpu(env), addr, 1, full, retaddr);
         }
     }
 
@@ -1694,16 +1661,44 @@ void *probe_access(CPUArchState *env, target_ulong addr, int size,
 void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
                         MMUAccessType access_type, int mmu_idx)
 {
+    CPUTLBEntryFull *full;
     void *host;
     int flags;
 
     flags = probe_access_internal(env, addr, 0, access_type,
-                                  mmu_idx, true, &host, 0);
+                                  mmu_idx, true, &host, &full, 0);
 
     /* No combination of flags are expected by the caller. */
     return flags ? NULL : host;
 }
 
+/*
+ * Return a ram_addr_t for the virtual address for execution.
+ *
+ * Return -1 if we can't translate and execute from an entire page
+ * of RAM.  This will force us to execute by loading and translating
+ * one insn at a time, without caching.
+ *
+ * NOTE: This function will trigger an exception if the page is
+ * not executable.
+ */
+tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr,
+                                        void **hostp)
+{
+    CPUTLBEntryFull *full;
+    void *p;
+
+    (void)probe_access_internal(env, addr, 1, MMU_INST_FETCH,
+                                cpu_mmu_index(env, true), false, &p, &full, 0);
+    if (p == NULL) {
+        return -1;
+    }
+    if (hostp) {
+        *hostp = p;
+    }
+    return qemu_ram_addr_from_host_nofail(p);
+}
+
 #ifdef CONFIG_PLUGIN
 /*
  * Perform a TLB lookup and populate the qemu_plugin_hwaddr structure.
@@ -1715,7 +1710,7 @@ void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
  * should have just filled the TLB. The one corner case is io_writex
  * which can cause TLB flushes and potential resizing of the TLBs
  * losing the information we need. In those cases we need to recover
- * data from a copy of the iotlbentry. As long as this always occurs
+ * data from a copy of the CPUTLBEntryFull. As long as this always occurs
  * from the same thread (which a mem callback will be) this is safe.
  */
 
@@ -1730,11 +1725,12 @@ bool tlb_plugin_lookup(CPUState *cpu, target_ulong addr, int mmu_idx,
     if (likely(tlb_hit(tlb_addr, addr))) {
         /* We must have an iotlb entry for MMIO */
         if (tlb_addr & TLB_MMIO) {
-            CPUIOTLBEntry *iotlbentry;
+            CPUTLBEntryFull *full;
-            iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
+            full = &env_tlb(env)->d[mmu_idx].fulltlb[index];
             data->is_io = true;
-            data->v.io.section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
+            data->v.io.section =
-            data->v.io.offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+                iotlb_to_section(cpu, full->xlat_section, full->attrs);
+            data->v.io.offset = (full->xlat_section & TARGET_PAGE_MASK) + addr;
         } else {
             data->is_io = false;
             data->v.ram.hostaddr = (void *)((uintptr_t)addr + tlbe->addend);
@@ -1842,7 +1838,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
 
     if (unlikely(tlb_addr & TLB_NOTDIRTY)) {
         notdirty_write(env_cpu(env), addr, size,
-                       &env_tlb(env)->d[mmu_idx].iotlb[index], retaddr);
+                       &env_tlb(env)->d[mmu_idx].fulltlb[index], retaddr);
     }
 
     return hostaddr;
@@ -1950,7 +1946,7 @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi,
 
     /* Handle anything that isn't just a straight memory access.  */
     if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) {
-        CPUIOTLBEntry *iotlbentry;
+        CPUTLBEntryFull *full;
         bool need_swap;
 
         /* For anything that is unaligned, recurse through full_load.  */
@@ -1958,20 +1954,20 @@ load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi,
             goto do_unaligned_access;
         }
 
-        iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
+        full = &env_tlb(env)->d[mmu_idx].fulltlb[index];
 
         /* Handle watchpoints.  */
         if (unlikely(tlb_addr & TLB_WATCHPOINT)) {
             /* On watchpoint hit, this will longjmp out.  */
             cpu_check_watchpoint(env_cpu(env), addr, size,
-                                 iotlbentry->attrs, BP_MEM_READ, retaddr);
+                                 full->attrs, BP_MEM_READ, retaddr);
         }
 
         need_swap = size > 1 && (tlb_addr & TLB_BSWAP);
 
         /* Handle I/O access.  */
         if (likely(tlb_addr & TLB_MMIO)) {
-            return io_readx(env, iotlbentry, mmu_idx, addr, retaddr,
+            return io_readx(env, full, mmu_idx, addr, retaddr,
                             access_type, op ^ (need_swap * MO_BSWAP));
         }
 
@@ -2286,12 +2282,12 @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val,
      */
     if (unlikely(tlb_addr & TLB_WATCHPOINT)) {
         cpu_check_watchpoint(env_cpu(env), addr, size - size2,
-                             env_tlb(env)->d[mmu_idx].iotlb[index].attrs,
+                             env_tlb(env)->d[mmu_idx].fulltlb[index].attrs,
                              BP_MEM_WRITE, retaddr);
     }
     if (unlikely(tlb_addr2 & TLB_WATCHPOINT)) {
         cpu_check_watchpoint(env_cpu(env), page2, size2,
-                             env_tlb(env)->d[mmu_idx].iotlb[index2].attrs,
+                             env_tlb(env)->d[mmu_idx].fulltlb[index2].attrs,
                              BP_MEM_WRITE, retaddr);
     }
 
@@ -2355,7 +2351,7 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
 
     /* Handle anything that isn't just a straight memory access.  */
     if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) {
-        CPUIOTLBEntry *iotlbentry;
+        CPUTLBEntryFull *full;
         bool need_swap;
 
         /* For anything that is unaligned, recurse through byte stores.  */
@@ -2363,20 +2359,20 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
             goto do_unaligned_access;
         }
 
-        iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
+        full = &env_tlb(env)->d[mmu_idx].fulltlb[index];
 
         /* Handle watchpoints.  */
         if (unlikely(tlb_addr & TLB_WATCHPOINT)) {
             /* On watchpoint hit, this will longjmp out.  */
             cpu_check_watchpoint(env_cpu(env), addr, size,
-                                 iotlbentry->attrs, BP_MEM_WRITE, retaddr);
+                                 full->attrs, BP_MEM_WRITE, retaddr);
         }
 
         need_swap = size > 1 && (tlb_addr & TLB_BSWAP);
 
         /* Handle I/O access.  */
         if (tlb_addr & TLB_MMIO) {
-            io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr,
+            io_writex(env, full, mmu_idx, val, addr, retaddr,
                       op ^ (need_swap * MO_BSWAP));
             return;
         }
@@ -2388,7 +2384,7 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
 
         /* Handle clean RAM pages.  */
         if (tlb_addr & TLB_NOTDIRTY) {
-            notdirty_write(env_cpu(env), addr, size, iotlbentry, retaddr);
+            notdirty_write(env_cpu(env), addr, size, full, retaddr);
         }
 
         haddr = (void *)((uintptr_t)addr + entry->addend);

accel/tcg/internal.h

@@ -18,4 +18,14 @@ G_NORETURN void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr);
 void page_init(void);
 void tb_htable_init(void);
 
+/* Return the current PC from CPU, which may be cached in TB. */
+static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb)
+{
+#if TARGET_TB_PCREL
+    return cpu->cc->get_pc(cpu);
+#else
+    return tb_pc(tb);
+#endif
+}
+
 #endif /* ACCEL_TCG_INTERNAL_H */

accel/tcg/plugin-gen.c

@@ -852,7 +852,8 @@ static void plugin_gen_inject(const struct qemu_plugin_tb *plugin_tb)
     pr_ops();
 }
 
-bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_only)
+bool plugin_gen_tb_start(CPUState *cpu, const DisasContextBase *db,
+                         bool mem_only)
 {
     bool ret = false;
 
@@ -870,9 +871,9 @@ bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_onl
 
         ret = true;
 
-        ptb->vaddr = tb->pc;
+        ptb->vaddr = db->pc_first;
         ptb->vaddr2 = -1;
-        get_page_addr_code_hostp(cpu->env_ptr, tb->pc, &ptb->haddr1);
+        ptb->haddr1 = db->host_addr[0];
         ptb->haddr2 = NULL;
         ptb->mem_only = mem_only;
 
@@ -898,16 +899,15 @@ void plugin_gen_insn_start(CPUState *cpu, const DisasContextBase *db)
      * 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) &&
+    if (ptb->haddr1 == NULL) {
-        unlikely((db->pc_next & TARGET_PAGE_MASK) !=
+        pinsn->haddr = NULL;
-                 (db->pc_first & TARGET_PAGE_MASK))) {
+    } else if (is_same_page(db, db->pc_next)) {
-        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 {
+        if (ptb->vaddr2 == -1) {
+            ptb->vaddr2 = TARGET_PAGE_ALIGN(db->pc_first);
+            get_page_addr_code_hostp(cpu->env_ptr, ptb->vaddr2, &ptb->haddr2);
+        }
         pinsn->haddr = ptb->haddr2 + pinsn->vaddr - ptb->vaddr2;
     }
 }

accel/tcg/tb-hash.h

@@ -23,6 +23,7 @@
 #include "exec/cpu-defs.h"
 #include "exec/exec-all.h"
 #include "qemu/xxhash.h"
+#include "tb-jmp-cache.h"
 
 #ifdef CONFIG_SOFTMMU
 

accel/tcg/tb-jmp-cache.h

@@ -0,0 +1,65 @@
+/*
+ * The per-CPU TranslationBlock jump cache.
+ *
+ *  Copyright (c) 2003 Fabrice Bellard
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef ACCEL_TCG_TB_JMP_CACHE_H
+#define ACCEL_TCG_TB_JMP_CACHE_H
+
+#define TB_JMP_CACHE_BITS 12
+#define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS)
+
+/*
+ * Accessed in parallel; all accesses to 'tb' must be atomic.
+ * For TARGET_TB_PCREL, accesses to 'pc' must be protected by
+ * a load_acquire/store_release to 'tb'.
+ */
+struct CPUJumpCache {
+    struct {
+        TranslationBlock *tb;
+#if TARGET_TB_PCREL
+        target_ulong pc;
+#endif
+    } array[TB_JMP_CACHE_SIZE];
+};
+
+static inline TranslationBlock *
+tb_jmp_cache_get_tb(CPUJumpCache *jc, uint32_t hash)
+{
+#if TARGET_TB_PCREL
+    /* Use acquire to ensure current load of pc from jc. */
+    return qatomic_load_acquire(&jc->array[hash].tb);
+#else
+    /* Use rcu_read to ensure current load of pc from *tb. */
+    return qatomic_rcu_read(&jc->array[hash].tb);
+#endif
+}
+
+static inline target_ulong
+tb_jmp_cache_get_pc(CPUJumpCache *jc, uint32_t hash, TranslationBlock *tb)
+{
+#if TARGET_TB_PCREL
+    return jc->array[hash].pc;
+#else
+    return tb_pc(tb);
+#endif
+}
+
+static inline void
+tb_jmp_cache_set(CPUJumpCache *jc, uint32_t hash,
+                 TranslationBlock *tb, target_ulong pc)
+{
+#if TARGET_TB_PCREL
+    jc->array[hash].pc = pc;
+    /* Use store_release on tb to ensure pc is written first. */
+    qatomic_store_release(&jc->array[hash].tb, tb);
+#else
+    /* Use the pc value already stored in tb->pc. */
+    qatomic_set(&jc->array[hash].tb, tb);
+#endif
+}
+
+#endif /* ACCEL_TCG_TB_JMP_CACHE_H */

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

@@ -109,7 +109,13 @@ void icount_prepare_for_run(CPUState *cpu)
     replay_mutex_lock();
 
     if (cpu->icount_budget == 0) {
+        /*
+         * We're called without the iothread lock, so must take it while
+         * we're calling timer handlers.
+         */
+        qemu_mutex_lock_iothread();
         icount_notify_aio_contexts();
+        qemu_mutex_unlock_iothread();
     }
 }
 

accel/tcg/tcg-accel-ops.c

@@ -32,6 +32,8 @@
 #include "qemu/main-loop.h"
 #include "qemu/guest-random.h"
 #include "exec/exec-all.h"
+#include "exec/hwaddr.h"
+#include "exec/gdbstub.h"
 
 #include "tcg-accel-ops.h"
 #include "tcg-accel-ops-mttcg.h"
@@ -91,6 +93,97 @@ void tcg_handle_interrupt(CPUState *cpu, int mask)
     }
 }
 
+static bool tcg_supports_guest_debug(void)
+{
+    return true;
+}
+
+/* Translate GDB watchpoint type to a flags value for cpu_watchpoint_* */
+static inline int xlat_gdb_type(CPUState *cpu, int gdbtype)
+{
+    static const int xlat[] = {
+        [GDB_WATCHPOINT_WRITE]  = BP_GDB | BP_MEM_WRITE,
+        [GDB_WATCHPOINT_READ]   = BP_GDB | BP_MEM_READ,
+        [GDB_WATCHPOINT_ACCESS] = BP_GDB | BP_MEM_ACCESS,
+    };
+
+    CPUClass *cc = CPU_GET_CLASS(cpu);
+    int cputype = xlat[gdbtype];
+
+    if (cc->gdb_stop_before_watchpoint) {
+        cputype |= BP_STOP_BEFORE_ACCESS;
+    }
+    return cputype;
+}
+
+static int tcg_insert_breakpoint(CPUState *cs, int type, hwaddr addr, hwaddr len)
+{
+    CPUState *cpu;
+    int err = 0;
+
+    switch (type) {
+    case GDB_BREAKPOINT_SW:
+    case GDB_BREAKPOINT_HW:
+        CPU_FOREACH(cpu) {
+            err = cpu_breakpoint_insert(cpu, addr, BP_GDB, NULL);
+            if (err) {
+                break;
+            }
+        }
+        return err;
+    case GDB_WATCHPOINT_WRITE:
+    case GDB_WATCHPOINT_READ:
+    case GDB_WATCHPOINT_ACCESS:
+        CPU_FOREACH(cpu) {
+            err = cpu_watchpoint_insert(cpu, addr, len,
+                                        xlat_gdb_type(cpu, type), NULL);
+            if (err) {
+                break;
+            }
+        }
+        return err;
+    default:
+        return -ENOSYS;
+    }
+}
+
+static int tcg_remove_breakpoint(CPUState *cs, int type, hwaddr addr, hwaddr len)
+{
+    CPUState *cpu;
+    int err = 0;
+
+    switch (type) {
+    case GDB_BREAKPOINT_SW:
+    case GDB_BREAKPOINT_HW:
+        CPU_FOREACH(cpu) {
+            err = cpu_breakpoint_remove(cpu, addr, BP_GDB);
+            if (err) {
+                break;
+            }
+        }
+        return err;
+    case GDB_WATCHPOINT_WRITE:
+    case GDB_WATCHPOINT_READ:
+    case GDB_WATCHPOINT_ACCESS:
+        CPU_FOREACH(cpu) {
+            err = cpu_watchpoint_remove(cpu, addr, len,
+                                        xlat_gdb_type(cpu, type));
+            if (err) {
+                break;
+            }
+        }
+        return err;
+    default:
+        return -ENOSYS;
+    }
+}
+
+static inline void tcg_remove_all_breakpoints(CPUState *cpu)
+{
+    cpu_breakpoint_remove_all(cpu, BP_GDB);
+    cpu_watchpoint_remove_all(cpu, BP_GDB);
+}
+
 static void tcg_accel_ops_init(AccelOpsClass *ops)
 {
     if (qemu_tcg_mttcg_enabled()) {
@@ -109,6 +202,11 @@ static void tcg_accel_ops_init(AccelOpsClass *ops)
             ops->handle_interrupt = tcg_handle_interrupt;
         }
     }
+
+    ops->supports_guest_debug = tcg_supports_guest_debug;
+    ops->insert_breakpoint = tcg_insert_breakpoint;
+    ops->remove_breakpoint = tcg_remove_breakpoint;
+    ops->remove_all_breakpoints = tcg_remove_all_breakpoints;
 }
 
 static void tcg_accel_ops_class_init(ObjectClass *oc, void *data)

accel/tcg/tcg-all.c

@@ -25,6 +25,7 @@
 
 #include "qemu/osdep.h"
 #include "sysemu/tcg.h"
+#include "sysemu/replay.h"
 #include "sysemu/cpu-timers.h"
 #include "tcg/tcg.h"
 #include "qapi/error.h"
@@ -215,12 +216,28 @@ static void tcg_set_splitwx(Object *obj, bool value, Error **errp)
     s->splitwx_enabled = value;
 }
 
+static int tcg_gdbstub_supported_sstep_flags(void)
+{
+    /*
+     * In replay mode all events will come from the log and can't be
+     * suppressed otherwise we would break determinism. However as those
+     * events are tied to the number of executed instructions we won't see
+     * them occurring every time we single step.
+     */
+    if (replay_mode != REPLAY_MODE_NONE) {
+        return SSTEP_ENABLE;
+    } else {
+        return SSTEP_ENABLE | SSTEP_NOIRQ | SSTEP_NOTIMER;
+    }
+}
+
 static void tcg_accel_class_init(ObjectClass *oc, void *data)
 {
     AccelClass *ac = ACCEL_CLASS(oc);
     ac->name = "tcg";
     ac->init_machine = tcg_init_machine;
     ac->allowed = &tcg_allowed;
+    ac->gdbstub_supported_sstep_flags = tcg_gdbstub_supported_sstep_flags;
 
     object_class_property_add_str(oc, "thread",
                                   tcg_get_thread,

accel/tcg/translate-all.c

@@ -46,6 +46,7 @@
 
 #include "exec/cputlb.h"
 #include "exec/translate-all.h"
+#include "exec/translator.h"
 #include "qemu/bitmap.h"
 #include "qemu/qemu-print.h"
 #include "qemu/timer.h"
@@ -57,6 +58,7 @@
 #include "sysemu/tcg.h"
 #include "qapi/error.h"
 #include "hw/core/tcg-cpu-ops.h"
+#include "tb-jmp-cache.h"
 #include "tb-hash.h"
 #include "tb-context.h"
 #include "internal.h"
@@ -730,21 +732,14 @@ void libafl_add_backdoor_hook(void (*exec)(target_ulong id, uint64_t data),
 #define assert_memory_lock() tcg_debug_assert(have_mmap_lock())
 #endif
 
-#define SMC_BITMAP_USE_THRESHOLD 10
-
 typedef struct PageDesc {
     /* list of TBs intersecting this ram page */
     uintptr_t first_tb;
-#ifdef CONFIG_SOFTMMU
+#ifdef CONFIG_USER_ONLY
-    /* in order to optimize self modifying code, we count the number
-       of lookups we do to a given page to use a bitmap */
-    unsigned long *code_bitmap;
-    unsigned int code_write_count;
-#else
     unsigned long flags;
     void *target_data;
 #endif
-#ifndef CONFIG_USER_ONLY
+#ifdef CONFIG_SOFTMMU
     QemuSpin lock;
 #endif
 } PageDesc;
@@ -933,7 +928,7 @@ static int encode_search(TranslationBlock *tb, uint8_t *block)
 
         for (j = 0; j < TARGET_INSN_START_WORDS; ++j) {
             if (i == 0) {
-                prev = (j == 0 ? tb->pc : 0);
+                prev = (!TARGET_TB_PCREL && j == 0 ? tb_pc(tb) : 0);
             } else {
                 prev = tcg_ctx->gen_insn_data[i - 1][j];
             }
@@ -961,7 +956,7 @@ static int encode_search(TranslationBlock *tb, uint8_t *block)
 static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
                                      uintptr_t searched_pc, bool reset_icount)
 {
-    target_ulong data[TARGET_INSN_START_WORDS] = { tb->pc };
+    target_ulong data[TARGET_INSN_START_WORDS];
     uintptr_t host_pc = (uintptr_t)tb->tc.ptr;
     CPUArchState *env = cpu->env_ptr;
     const uint8_t *p = tb->tc.ptr + tb->tc.size;
@@ -977,6 +972,11 @@ static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
         return -1;
     }
 
+    memset(data, 0, sizeof(data));
+    if (!TARGET_TB_PCREL) {
+        data[0] = tb_pc(tb);
+    }
+
     /* Reconstruct the stored insn data while looking for the point at
        which the end of the insn exceeds the searched_pc.  */
     for (i = 0; i < num_insns; ++i) {
@@ -1100,7 +1100,7 @@ void page_init(void)
 #endif
 }
 
-static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc)
+static PageDesc *page_find_alloc(tb_page_addr_t index, bool alloc)
 {
     PageDesc *pd;
     void **lp;
@@ -1168,11 +1168,11 @@ static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc)
 
 static inline PageDesc *page_find(tb_page_addr_t index)
 {
-    return page_find_alloc(index, 0);
+    return page_find_alloc(index, false);
 }
 
 static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1,
-                           PageDesc **ret_p2, tb_page_addr_t phys2, int alloc);
+                           PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc);
 
 /* In user-mode page locks aren't used; mmap_lock is enough */
 #ifdef CONFIG_USER_ONLY
@@ -1286,7 +1286,7 @@ static inline void page_unlock(PageDesc *pd)
 /* lock the page(s) of a TB in the correct acquisition order */
 static inline void page_lock_tb(const TranslationBlock *tb)
 {
-    page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], 0);
+    page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], false);
 }
 
 static inline void page_unlock_tb(const TranslationBlock *tb)
@@ -1475,7 +1475,7 @@ void page_collection_unlock(struct page_collection *set)
 #endif /* !CONFIG_USER_ONLY */
 
 static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1,
-                           PageDesc **ret_p2, tb_page_addr_t phys2, int alloc)
+                           PageDesc **ret_p2, tb_page_addr_t phys2, bool alloc)
 {
     PageDesc *p1, *p2;
     tb_page_addr_t page1;
@@ -1519,13 +1519,13 @@ static bool tb_cmp(const void *ap, const void *bp)
     const TranslationBlock *a = ap;
     const TranslationBlock *b = bp;
 
-    return a->pc == b->pc &&
+    return ((TARGET_TB_PCREL || tb_pc(a) == tb_pc(b)) &&
-        a->cs_base == b->cs_base &&
+            a->cs_base == b->cs_base &&
-        a->flags == b->flags &&
+            a->flags == b->flags &&
-        (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) &&
+            (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) &&
-        a->trace_vcpu_dstate == b->trace_vcpu_dstate &&
+            a->trace_vcpu_dstate == b->trace_vcpu_dstate &&
-        a->page_addr[0] == b->page_addr[0] &&
+            a->page_addr[0] == b->page_addr[0] &&
-        a->page_addr[1] == b->page_addr[1];
+            a->page_addr[1] == b->page_addr[1]);
 }
 
 void tb_htable_init(void)
@@ -1535,17 +1535,6 @@ void tb_htable_init(void)
     qht_init(&tb_ctx.htable, tb_cmp, CODE_GEN_HTABLE_SIZE, mode);
 }
 
-/* call with @p->lock held */
-static inline void invalidate_page_bitmap(PageDesc *p)
-{
-    assert_page_locked(p);
-#ifdef CONFIG_SOFTMMU
-    g_free(p->code_bitmap);
-    p->code_bitmap = NULL;
-    p->code_write_count = 0;
-#endif
-}
-
 /* Set to NULL all the 'first_tb' fields in all PageDescs. */
 static void page_flush_tb_1(int level, void **lp)
 {
@@ -1560,7 +1549,6 @@ static void page_flush_tb_1(int level, void **lp)
         for (i = 0; i < V_L2_SIZE; ++i) {
             page_lock(&pd[i]);
             pd[i].first_tb = (uintptr_t)NULL;
-            invalidate_page_bitmap(pd + i);
             page_unlock(&pd[i]);
         }
     } else {
@@ -1614,7 +1602,7 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)
     }
 
     CPU_FOREACH(cpu) {
-        cpu_tb_jmp_cache_clear(cpu);
+        tcg_flush_jmp_cache(cpu);
     }
 
     qht_reset_size(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE);
@@ -1659,9 +1647,10 @@ static void do_tb_invalidate_check(void *p, uint32_t hash, void *userp)
     TranslationBlock *tb = p;
     target_ulong addr = *(target_ulong *)userp;
 
-    if (!(addr + TARGET_PAGE_SIZE <= tb->pc || addr >= tb->pc + tb->size)) {
+    if (!(addr + TARGET_PAGE_SIZE <= tb_pc(tb) ||
+          addr >= tb_pc(tb) + tb->size)) {
         printf("ERROR invalidate: address=" TARGET_FMT_lx
-               " PC=%08lx size=%04x\n", addr, (long)tb->pc, tb->size);
+               " PC=%08lx size=%04x\n", addr, (long)tb_pc(tb), tb->size);
     }
 }
 
@@ -1680,11 +1669,11 @@ static void do_tb_page_check(void *p, uint32_t hash, void *userp)
     TranslationBlock *tb = p;
     int flags1, flags2;
 
-    flags1 = page_get_flags(tb->pc);
+    flags1 = page_get_flags(tb_pc(tb));
-    flags2 = page_get_flags(tb->pc + tb->size - 1);
+    flags2 = page_get_flags(tb_pc(tb) + tb->size - 1);
     if ((flags1 & PAGE_WRITE) || (flags2 & PAGE_WRITE)) {
         printf("ERROR page flags: PC=%08lx size=%04x f1=%x f2=%x\n",
-               (long)tb->pc, tb->size, flags1, flags2);
+               (long)tb_pc(tb), tb->size, flags1, flags2);
     }
 }
 
@@ -1793,6 +1782,28 @@ static inline void tb_jmp_unlink(TranslationBlock *dest)
     qemu_spin_unlock(&dest->jmp_lock);
 }
 
+static void tb_jmp_cache_inval_tb(TranslationBlock *tb)
+{
+    CPUState *cpu;
+
+    if (TARGET_TB_PCREL) {
+        /* A TB may be at any virtual address */
+        CPU_FOREACH(cpu) {
+            tcg_flush_jmp_cache(cpu);
+        }
+    } else {
+        uint32_t h = tb_jmp_cache_hash_func(tb_pc(tb));
+
+        CPU_FOREACH(cpu) {
+            CPUJumpCache *jc = cpu->tb_jmp_cache;
+
+            if (qatomic_read(&jc->array[h].tb) == tb) {
+                qatomic_set(&jc->array[h].tb, NULL);
+            }
+        }
+    }
+}
+
 /*
  * In user-mode, call with mmap_lock held.
  * In !user-mode, if @rm_from_page_list is set, call with the TB's pages'
@@ -1800,7 +1811,6 @@ static inline void tb_jmp_unlink(TranslationBlock *dest)
  */
 static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)
 {
-    CPUState *cpu;
     PageDesc *p;
     uint32_t h;
     tb_page_addr_t phys_pc;
@@ -1814,9 +1824,9 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)
     qemu_spin_unlock(&tb->jmp_lock);
 
     /* remove the TB from the hash list */
-    phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
+    phys_pc = tb->page_addr[0];
-    h = tb_hash_func(phys_pc, tb->pc, tb->flags, orig_cflags,
+    h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)),
-                     tb->trace_vcpu_dstate);
+                     tb->flags, orig_cflags, tb->trace_vcpu_dstate);
     if (!qht_remove(&tb_ctx.htable, tb, h)) {
         return;
     }
@@ -1825,21 +1835,14 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)
     if (rm_from_page_list) {
         p = page_find(tb->page_addr[0] >> TARGET_PAGE_BITS);
         tb_page_remove(p, tb);
-        invalidate_page_bitmap(p);
         if (tb->page_addr[1] != -1) {
             p = page_find(tb->page_addr[1] >> TARGET_PAGE_BITS);
             tb_page_remove(p, tb);
-            invalidate_page_bitmap(p);
         }
     }
 
     /* remove the TB from the hash list */
-    h = tb_jmp_cache_hash_func(tb->pc);
+    tb_jmp_cache_inval_tb(tb);
-    CPU_FOREACH(cpu) {
-        if (qatomic_read(&cpu->tb_jmp_cache[h]) == tb) {
-            qatomic_set(&cpu->tb_jmp_cache[h], NULL);
-        }
-    }
 
     /* suppress this TB from the two jump lists */
     tb_remove_from_jmp_list(tb, 0);
@@ -1874,35 +1877,6 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
     }
 }
 
-#ifdef CONFIG_SOFTMMU
-/* call with @p->lock held */
-static void build_page_bitmap(PageDesc *p)
-{
-    int n, tb_start, tb_end;
-    TranslationBlock *tb;
-
-    assert_page_locked(p);
-    p->code_bitmap = bitmap_new(TARGET_PAGE_SIZE);
-
-    PAGE_FOR_EACH_TB(p, tb, n) {
-        /* NOTE: this is subtle as a TB may span two physical pages */
-        if (n == 0) {
-            /* NOTE: tb_end may be after the end of the page, but
-               it is not a problem */
-            tb_start = tb->pc & ~TARGET_PAGE_MASK;
-            tb_end = tb_start + tb->size;
-            if (tb_end > TARGET_PAGE_SIZE) {
-                tb_end = TARGET_PAGE_SIZE;
-             }
-        } else {
-            tb_start = 0;
-            tb_end = ((tb->pc + tb->size) & ~TARGET_PAGE_MASK);
-        }
-        bitmap_set(p->code_bitmap, tb_start, tb_end - tb_start);
-    }
-}
-#endif
-
 /* add the tb in the target page and protect it if necessary
  *
  * Called with mmap_lock held for user-mode emulation.
@@ -1923,7 +1897,6 @@ static inline void tb_page_add(PageDesc *p, TranslationBlock *tb,
     page_already_protected = p->first_tb != (uintptr_t)NULL;
 #endif
     p->first_tb = (uintptr_t)tb | n;
-    invalidate_page_bitmap(p);
 
 #if defined(CONFIG_USER_ONLY)
     /* translator_loop() must have made all TB pages non-writable */
@@ -1969,8 +1942,8 @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
      * Note that inserting into the hash table first isn't an option, since
      * we can only insert TBs that are fully initialized.
      */
-    page_lock_pair(&p, phys_pc, &p2, phys_page2, 1);
+    page_lock_pair(&p, phys_pc, &p2, phys_page2, true);
-    tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK);
+    tb_page_add(p, tb, 0, phys_pc);
     if (p2) {
         tb_page_add(p2, tb, 1, phys_page2);
     } else {
@@ -1978,17 +1951,15 @@ tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
     }
 
     /* add in the hash table */
-    h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags,
+    h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)),
-                     tb->trace_vcpu_dstate);
+                     tb->flags, tb->cflags, tb->trace_vcpu_dstate);
     qht_insert(&tb_ctx.htable, tb, h, &existing_tb);
 
     /* remove TB from the page(s) if we couldn't insert it */
     if (unlikely(existing_tb)) {
         tb_page_remove(p, tb);
-        invalidate_page_bitmap(p);
         if (p2) {
             tb_page_remove(p2, tb);
-            invalidate_page_bitmap(p2);
         }
         tb = existing_tb;
     }
@@ -2202,19 +2173,19 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 {
     CPUArchState *env = cpu->env_ptr;
     TranslationBlock *tb, *existing_tb;
-    tb_page_addr_t phys_pc, phys_page2;
+    tb_page_addr_t phys_pc;
-    target_ulong virt_page2;
     tcg_insn_unit *gen_code_buf;
     int gen_code_size, search_size, max_insns;
 #ifdef CONFIG_PROFILER
     TCGProfile *prof = &tcg_ctx->prof;
     int64_t ti;
 #endif
+    void *host_pc;
 
     assert_memory_lock();
     qemu_thread_jit_write();
 
-    phys_pc = get_page_addr_code(env, pc);
+    phys_pc = get_page_addr_code_hostp(env, pc, &host_pc);
 
     if (phys_pc == -1) {
         /* Generate a one-shot TB with 1 insn in it */
@@ -2240,11 +2211,15 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 
     gen_code_buf = tcg_ctx->code_gen_ptr;
     tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf);
+#if !TARGET_TB_PCREL
     tb->pc = pc;
+#endif
     tb->cs_base = cs_base;
     tb->flags = flags;
     tb->cflags = cflags;
     tb->trace_vcpu_dstate = *cpu->trace_dstate;
+    tb->page_addr[0] = phys_pc;
+    tb->page_addr[1] = -1;
     tcg_ctx->tb_cflags = cflags;
  tb_overflow:
 
@@ -2283,12 +2258,12 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     
     //// --- End LibAFL code ---
 
-    gen_intermediate_code(cpu, tb, max_insns);
+    gen_intermediate_code(cpu, tb, max_insns, pc, host_pc);
     assert(tb->size != 0);
     tcg_ctx->cpu = NULL;
     max_insns = tb->icount;
 
-    trace_translate_block(tb, tb->pc, tb->tc.ptr);
+    trace_translate_block(tb, pc, tb->tc.ptr);
 
     /* generate machine code */
     tb->jmp_reset_offset[0] = TB_JMP_RESET_OFFSET_INVALID;
@@ -2309,7 +2284,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     ti = profile_getclock();
 #endif
 
-    gen_code_size = tcg_gen_code(tcg_ctx, tb);
+    gen_code_size = tcg_gen_code(tcg_ctx, tb, pc);
     if (unlikely(gen_code_size < 0)) {
  error_return:
         switch (gen_code_size) {
@@ -2365,7 +2340,7 @@ 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)) {
+        qemu_log_in_addr_range(pc)) {
         FILE *logfile = qemu_log_trylock();
         if (logfile) {
             int code_size, data_size;
@@ -2459,13 +2434,11 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     }
 
     /*
-     * If the TB is not associated with a physical RAM page then
+     * If the TB is not associated with a physical RAM page then it must be
-     * it must be a temporary one-insn TB, and we have nothing to do
+     * a temporary one-insn TB, and we have nothing left to do. Return early
-     * except fill in the page_addr[] fields. Return early before
+     * before attempting to link to other TBs or add to the lookup table.
-     * attempting to link to other TBs or add to the lookup table.
      */
-    if (phys_pc == -1) {
+    if (tb->page_addr[0] == -1) {
-        tb->page_addr[0] = tb->page_addr[1] = -1;
         return tb;
     }
 
@@ -2476,17 +2449,11 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
      */
     tcg_tb_insert(tb);
 
-    /* check next page if needed */
-    virt_page2 = (pc + tb->size - 1) & TARGET_PAGE_MASK;
-    phys_page2 = -1;
-    if ((pc & TARGET_PAGE_MASK) != virt_page2) {
-        phys_page2 = get_page_addr_code(env, virt_page2);
-    }
     /*
      * No explicit memory barrier is required -- tb_link_page() makes the
      * TB visible in a consistent state.
      */
-    existing_tb = tb_link_page(tb, phys_pc, phys_page2);
+    existing_tb = tb_link_page(tb, tb->page_addr[0], tb->page_addr[1]);
     /* if the TB already exists, discard what we just translated */
     if (unlikely(existing_tb != tb)) {
         uintptr_t orig_aligned = (uintptr_t)gen_code_buf;
@@ -2541,11 +2508,12 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
         if (n == 0) {
             /* NOTE: tb_end may be after the end of the page, but
                it is not a problem */
-            tb_start = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
+            tb_start = tb->page_addr[0];
             tb_end = tb_start + tb->size;
         } else {
             tb_start = tb->page_addr[1];
-            tb_end = tb_start + ((tb->pc + tb->size) & ~TARGET_PAGE_MASK);
+            tb_end = tb_start + ((tb->page_addr[0] + tb->size)
+                                 & ~TARGET_PAGE_MASK);
         }
         if (!(tb_end <= start || tb_start >= end)) {
 #ifdef TARGET_HAS_PRECISE_SMC
@@ -2575,7 +2543,6 @@ tb_invalidate_phys_page_range__locked(struct page_collection *pages,
 #if !defined(CONFIG_USER_ONLY)
     /* if no code remaining, no need to continue to use slow writes */
     if (!p->first_tb) {
-        invalidate_page_bitmap(p);
         tlb_unprotect_code(start);
     }
 #endif
@@ -2671,24 +2638,8 @@ void tb_invalidate_phys_page_fast(struct page_collection *pages,
     }
 
     assert_page_locked(p);
-    if (!p->code_bitmap &&
+    tb_invalidate_phys_page_range__locked(pages, p, start, start + len,
-        ++p->code_write_count >= SMC_BITMAP_USE_THRESHOLD) {
+                                          retaddr);
-        build_page_bitmap(p);
-    }
-    if (p->code_bitmap) {
-        unsigned int nr;
-        unsigned long b;
-
-        nr = start & ~TARGET_PAGE_MASK;
-        b = p->code_bitmap[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG - 1));
-        if (b & ((1 << len) - 1)) {
-            goto do_invalidate;
-        }
-    } else {
-    do_invalidate:
-        tb_invalidate_phys_page_range__locked(pages, p, start, start + len,
-                                              retaddr);
-    }
 }
 #else
 /* Called with mmap_lock held. If pc is not 0 then it indicates the
@@ -2829,9 +2780,13 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
      */
     cpu->cflags_next_tb = curr_cflags(cpu) | CF_MEMI_ONLY | CF_LAST_IO | n;
 
-    qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc,
+    if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
-                           "cpu_io_recompile: rewound execution of TB to "
+        target_ulong pc = log_pc(cpu, tb);
-                           TARGET_FMT_lx "\n", tb->pc);
+        if (qemu_log_in_addr_range(pc)) {
+            qemu_log("cpu_io_recompile: rewound execution of TB to "
+                     TARGET_FMT_lx "\n", pc);
+        }
+    }
 
     cpu_loop_exit_noexc(cpu);
 }
@@ -3102,7 +3057,7 @@ int page_get_flags(target_ulong address)
 #ifndef PAGE_TARGET_STICKY
 #define PAGE_TARGET_STICKY  0
 #endif
-#define PAGE_STICKY  (PAGE_ANON | PAGE_TARGET_STICKY)
+#define PAGE_STICKY  (PAGE_ANON | PAGE_PASSTHROUGH | PAGE_TARGET_STICKY)
 
 /* Modify the flags of a page and invalidate the code if necessary.
    The flag PAGE_WRITE_ORG is positioned automatically depending
@@ -3133,7 +3088,7 @@ void page_set_flags(target_ulong start, target_ulong end, int flags)
     for (addr = start, len = end - start;
          len != 0;
          len -= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
-        PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, 1);
+        PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, true);
 
         /* If the write protection bit is set, then we invalidate
            the code inside.  */
@@ -3153,6 +3108,32 @@ void page_set_flags(target_ulong start, target_ulong end, int flags)
     }
 }
 
+void page_reset_target_data(target_ulong start, target_ulong end)
+{
+    target_ulong addr, len;
+
+    /*
+     * This function should never be called with addresses outside the
+     * guest address space.  If this assert fires, it probably indicates
+     * a missing call to h2g_valid.
+     */
+    assert(end - 1 <= GUEST_ADDR_MAX);
+    assert(start < end);
+    assert_memory_lock();
+
+    start = start & TARGET_PAGE_MASK;
+    end = TARGET_PAGE_ALIGN(end);
+
+    for (addr = start, len = end - start;
+         len != 0;
+         len -= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
+        PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, 1);
+
+        g_free(p->target_data);
+        p->target_data = NULL;
+    }
+}
+
 void *page_get_target_data(target_ulong address)
 {
     PageDesc *p = page_find(address >> TARGET_PAGE_BITS);
@@ -3330,6 +3311,26 @@ int page_unprotect(target_ulong address, uintptr_t pc)
 }
 #endif /* CONFIG_USER_ONLY */
 
+/*
+ * Called by generic code at e.g. cpu reset after cpu creation,
+ * therefore we must be prepared to allocate the jump cache.
+ */
+void tcg_flush_jmp_cache(CPUState *cpu)
+{
+    CPUJumpCache *jc = cpu->tb_jmp_cache;
+
+    if (likely(jc)) {
+        for (int i = 0; i < TB_JMP_CACHE_SIZE; i++) {
+            qatomic_set(&jc->array[i].tb, NULL);
+        }
+    } else {
+        /* This should happen once during realize, and thus never race. */
+        jc = g_new0(CPUJumpCache, 1);
+        jc = qatomic_xchg(&cpu->tb_jmp_cache, jc);
+        assert(jc == NULL);
+    }
+}
+
 /* This is a wrapper for common code that can not use CONFIG_SOFTMMU */
 void tcg_flush_softmmu_tlb(CPUState *cs)
 {

accel/tcg/translator.c

@@ -78,30 +78,27 @@ bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest)
     return ((db->pc_first ^ dest) & TARGET_PAGE_MASK) == 0;
 }
 
-static inline void translator_page_protect(DisasContextBase *dcbase,
+void translator_loop(CPUState *cpu, TranslationBlock *tb, int max_insns,
-                                           target_ulong pc)
+                     target_ulong pc, void *host_pc,
-{
+                     const TranslatorOps *ops, DisasContextBase *db)
-#ifdef CONFIG_USER_ONLY
-    dcbase->page_protect_end = pc | ~TARGET_PAGE_MASK;
-    page_protect(pc);
-#endif
-}
-
-void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
-                     CPUState *cpu, TranslationBlock *tb, int max_insns)
 {
     uint32_t cflags = tb_cflags(tb);
     bool plugin_enabled;
 
     /* Initialize DisasContext */
     db->tb = tb;
-    db->pc_first = tb->pc;
+    db->pc_first = pc;
-    db->pc_next = db->pc_first;
+    db->pc_next = pc;
     db->is_jmp = DISAS_NEXT;
     db->num_insns = 0;
     db->max_insns = max_insns;
     db->singlestep_enabled = cflags & CF_SINGLE_STEP;
-    translator_page_protect(db, db->pc_next);
+    db->host_addr[0] = host_pc;
+    db->host_addr[1] = NULL;
+
+#ifdef CONFIG_USER_ONLY
+    page_protect(pc);
+#endif
 
     ops->init_disas_context(db, cpu);
     tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
@@ -114,7 +111,7 @@ 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, cflags & CF_MEMI_ONLY);
+    plugin_enabled = plugin_gen_tb_start(cpu, db, cflags & CF_MEMI_ONLY);
 
     while (true) {
         db->num_insns++;
@@ -255,31 +252,103 @@ post_translate_insn:
 #endif
 }
 
-static inline void translator_maybe_page_protect(DisasContextBase *dcbase,
+static void *translator_access(CPUArchState *env, DisasContextBase *db,
-                                                 target_ulong pc, size_t len)
+                               target_ulong pc, size_t len)
 {
-#ifdef CONFIG_USER_ONLY
+    void *host;
-    target_ulong end = pc + len - 1;
+    target_ulong base, end;
+    TranslationBlock *tb;
 
-    if (end > dcbase->page_protect_end) {
+    tb = db->tb;
-        translator_page_protect(dcbase, end);
+
+    /* Use slow path if first page is MMIO. */
+    if (unlikely(tb->page_addr[0] == -1)) {
+        return NULL;
     }
+
+    end = pc + len - 1;
+    if (likely(is_same_page(db, end))) {
+        host = db->host_addr[0];
+        base = db->pc_first;
+    } else {
+        host = db->host_addr[1];
+        base = TARGET_PAGE_ALIGN(db->pc_first);
+        if (host == NULL) {
+            tb->page_addr[1] =
+                get_page_addr_code_hostp(env, base, &db->host_addr[1]);
+#ifdef CONFIG_USER_ONLY
+            page_protect(end);
 #endif
+            /* We cannot handle MMIO as second page. */
+            assert(tb->page_addr[1] != -1);
+            host = db->host_addr[1];
+        }
+
+        /* Use slow path when crossing pages. */
+        if (is_same_page(db, pc)) {
+            return NULL;
+        }
+    }
+
+    tcg_debug_assert(pc >= base);
+    return host + (pc - base);
 }
 
-#define GEN_TRANSLATOR_LD(fullname, type, load_fn, swap_fn)             \
+uint8_t translator_ldub(CPUArchState *env, DisasContextBase *db, abi_ptr pc)
-    type fullname ## _swap(CPUArchState *env, DisasContextBase *dcbase, \
+{
-                           abi_ptr pc, bool do_swap)                    \
+    uint8_t ret;
-    {                                                                   \
+    void *p = translator_access(env, db, pc, sizeof(ret));
-        translator_maybe_page_protect(dcbase, pc, sizeof(type));        \
+
-        type ret = load_fn(env, pc);                                    \
+    if (p) {
-        if (do_swap) {                                                  \
+        plugin_insn_append(pc, p, sizeof(ret));
-            ret = swap_fn(ret);                                         \
+        return ldub_p(p);
-        }                                                               \
-        plugin_insn_append(pc, &ret, sizeof(ret));                      \
-        return ret;                                                     \
     }
+    ret = cpu_ldub_code(env, pc);
+    plugin_insn_append(pc, &ret, sizeof(ret));
+    return ret;
+}
 
-FOR_EACH_TRANSLATOR_LD(GEN_TRANSLATOR_LD)
+uint16_t translator_lduw(CPUArchState *env, DisasContextBase *db, abi_ptr pc)
+{
+    uint16_t ret, plug;
+    void *p = translator_access(env, db, pc, sizeof(ret));
 
-#undef GEN_TRANSLATOR_LD
+    if (p) {
+        plugin_insn_append(pc, p, sizeof(ret));
+        return lduw_p(p);
+    }
+    ret = cpu_lduw_code(env, pc);
+    plug = tswap16(ret);
+    plugin_insn_append(pc, &plug, sizeof(ret));
+    return ret;
+}
+
+uint32_t translator_ldl(CPUArchState *env, DisasContextBase *db, abi_ptr pc)
+{
+    uint32_t ret, plug;
+    void *p = translator_access(env, db, pc, sizeof(ret));
+
+    if (p) {
+        plugin_insn_append(pc, p, sizeof(ret));
+        return ldl_p(p);
+    }
+    ret = cpu_ldl_code(env, pc);
+    plug = tswap32(ret);
+    plugin_insn_append(pc, &plug, sizeof(ret));
+    return ret;
+}
+
+uint64_t translator_ldq(CPUArchState *env, DisasContextBase *db, abi_ptr pc)
+{
+    uint64_t ret, plug;
+    void *p = translator_access(env, db, pc, sizeof(ret));
+
+    if (p) {
+        plugin_insn_append(pc, p, sizeof(ret));
+        return ldq_p(p);
+    }
+    ret = cpu_ldq_code(env, pc);
+    plug = tswap64(ret);
+    plugin_insn_append(pc, &plug, sizeof(ret));
+    return ret;
+}

accel/tcg/user-exec.c

@@ -80,10 +80,7 @@ MMUAccessType adjust_signal_pc(uintptr_t *pc, bool is_write)
          * (and if the translator doesn't handle page boundaries correctly
          * there's little we can do about that here).  Therefore, do not
          * trigger the unwinder.
-         *
-         * Like tb_gen_code, release the memory lock before cpu_loop_exit.
          */
-        mmap_unlock();
         *pc = 0;
         return MMU_INST_FETCH;
     }
@@ -199,6 +196,20 @@ void *probe_access(CPUArchState *env, target_ulong addr, int size,
     return size ? g2h(env_cpu(env), addr) : NULL;
 }
 
+tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr,
+                                        void **hostp)
+{
+    int flags;
+
+    flags = probe_access_internal(env, addr, 1, MMU_INST_FETCH, false, 0);
+    g_assert(flags == 0);
+
+    if (hostp) {
+        *hostp = g2h_untagged(addr);
+    }
+    return addr;
+}
+
 /* The softmmu versions of these helpers are in cputlb.c.  */
 
 /*

audio/audio.c

@@ -32,6 +32,7 @@
 #include "qapi/qapi-visit-audio.h"
 #include "qemu/cutils.h"
 #include "qemu/module.h"
+#include "qemu/help_option.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/replay.h"
 #include "sysemu/runstate.h"
@@ -137,7 +138,7 @@ static inline int audio_bits_to_index (int bits)
     default:
         audio_bug ("bits_to_index", 1);
         AUD_log (NULL, "invalid bits %d\n", bits);
-        abort();
+        return 0;
     }
 }
 
@@ -155,7 +156,7 @@ void *audio_calloc (const char *funcname, int nmemb, size_t size)
         AUD_log (NULL, "%s passed invalid arguments to audio_calloc\n",
                  funcname);
         AUD_log (NULL, "nmemb=%d size=%zu (len=%zu)\n", nmemb, size, len);
-        abort();
+        return NULL;
     }
 
     return g_malloc0 (len);
@@ -542,7 +543,7 @@ static size_t audio_pcm_hw_get_live_in(HWVoiceIn *hw)
     size_t live = hw->total_samples_captured - audio_pcm_hw_find_min_in (hw);
     if (audio_bug(__func__, live > hw->conv_buf->size)) {
         dolog("live=%zu hw->conv_buf->size=%zu\n", live, hw->conv_buf->size);
-        abort();
+        return 0;
     }
     return live;
 }
@@ -580,7 +581,7 @@ static size_t audio_pcm_sw_read(SWVoiceIn *sw, void *buf, size_t size)
     }
     if (audio_bug(__func__, live > hw->conv_buf->size)) {
         dolog("live_in=%zu hw->conv_buf->size=%zu\n", live, hw->conv_buf->size);
-        abort();
+        return 0;
     }
 
     rpos = audio_ring_posb(hw->conv_buf->pos, live, hw->conv_buf->size);
@@ -655,7 +656,7 @@ static size_t audio_pcm_hw_get_live_out (HWVoiceOut *hw, int *nb_live)
 
         if (audio_bug(__func__, live > hw->mix_buf->size)) {
             dolog("live=%zu hw->mix_buf->size=%zu\n", live, hw->mix_buf->size);
-            abort();
+            return 0;
         }
         return live;
     }
@@ -705,7 +706,7 @@ static size_t audio_pcm_sw_write(SWVoiceOut *sw, void *buf, size_t size)
     live = sw->total_hw_samples_mixed;
     if (audio_bug(__func__, live > hwsamples)) {
         dolog("live=%zu hw->mix_buf->size=%zu\n", live, hwsamples);
-        abort();
+        return 0;
     }
 
     if (live == hwsamples) {
@@ -997,7 +998,7 @@ static size_t audio_get_avail (SWVoiceIn *sw)
     if (audio_bug(__func__, live > sw->hw->conv_buf->size)) {
         dolog("live=%zu sw->hw->conv_buf->size=%zu\n", live,
               sw->hw->conv_buf->size);
-        abort();
+        return 0;
     }
 
     ldebug (
@@ -1027,7 +1028,7 @@ static size_t audio_get_free(SWVoiceOut *sw)
     if (audio_bug(__func__, live > sw->hw->mix_buf->size)) {
         dolog("live=%zu sw->hw->mix_buf->size=%zu\n", live,
               sw->hw->mix_buf->size);
-        abort();
+        return 0;
     }
 
     dead = sw->hw->mix_buf->size - live;
@@ -1169,7 +1170,7 @@ static void audio_run_out (AudioState *s)
 
         if (audio_bug(__func__, live > hw->mix_buf->size)) {
             dolog("live=%zu hw->mix_buf->size=%zu\n", live, hw->mix_buf->size);
-            abort();
+            continue;
         }
 
         if (hw->pending_disable && !nb_live) {
@@ -1202,7 +1203,7 @@ static void audio_run_out (AudioState *s)
         if (audio_bug(__func__, hw->mix_buf->pos >= hw->mix_buf->size)) {
             dolog("hw->mix_buf->pos=%zu hw->mix_buf->size=%zu played=%zu\n",
                   hw->mix_buf->pos, hw->mix_buf->size, played);
-            abort();
+            hw->mix_buf->pos = 0;
         }
 
 #ifdef DEBUG_OUT
@@ -1222,7 +1223,7 @@ static void audio_run_out (AudioState *s)
             if (audio_bug(__func__, played > sw->total_hw_samples_mixed)) {
                 dolog("played=%zu sw->total_hw_samples_mixed=%zu\n",
                       played, sw->total_hw_samples_mixed);
-                abort();
+                played = sw->total_hw_samples_mixed;
             }
 
             sw->total_hw_samples_mixed -= played;
@@ -1345,7 +1346,7 @@ static void audio_run_capture (AudioState *s)
             if (audio_bug(__func__, captured > sw->total_hw_samples_mixed)) {
                 dolog("captured=%zu sw->total_hw_samples_mixed=%zu\n",
                       captured, sw->total_hw_samples_mixed);
-                abort();
+                captured = sw->total_hw_samples_mixed;
             }
 
             sw->total_hw_samples_mixed -= captured;
@@ -1743,7 +1744,6 @@ static AudioState *audio_init(Audiodev *dev, const char *name)
         atexit(audio_cleanup);
         atexit_registered = true;
     }
-    QTAILQ_INSERT_TAIL(&audio_states, s, list);
 
     s->ts = timer_new_ns(QEMU_CLOCK_VIRTUAL, audio_timer, s);
 
@@ -1769,6 +1769,10 @@ static AudioState *audio_init(Audiodev *dev, const char *name)
         } else {
             dolog ("Unknown audio driver `%s'\n", drvname);
         }
+        if (!done) {
+            free_audio_state(s);
+            return NULL;
+        }
     } else {
         for (i = 0; audio_prio_list[i]; i++) {
             AudiodevListEntry *e = audiodev_find(&head, audio_prio_list[i]);
@@ -1806,6 +1810,7 @@ static AudioState *audio_init(Audiodev *dev, const char *name)
                "(Audio can continue looping even after stopping the VM)\n");
     }
 
+    QTAILQ_INSERT_TAIL(&audio_states, s, list);
     QLIST_INIT (&s->card_head);
     vmstate_register (NULL, 0, &vmstate_audio, s);
     return s;
@@ -2025,6 +2030,7 @@ void audio_create_pdos(Audiodev *dev)
         CASE(OSS, oss, Oss);
         CASE(PA, pa, Pa);
         CASE(SDL, sdl, Sdl);
+        CASE(SNDIO, sndio, );
         CASE(SPICE, spice, );
         CASE(WAV, wav, );
 
@@ -2097,10 +2103,28 @@ static void audio_validate_opts(Audiodev *dev, Error **errp)
     }
 }
 
+void audio_help(void)
+{
+    int i;
+
+    printf("Available audio drivers:\n");
+
+    for (i = 0; i < AUDIODEV_DRIVER__MAX; i++) {
+        audio_driver *driver = audio_driver_lookup(AudiodevDriver_str(i));
+        if (driver) {
+            printf("%s\n", driver->name);
+        }
+    }
+}
+
 void audio_parse_option(const char *opt)
 {
     Audiodev *dev = NULL;
 
+    if (is_help_option(opt)) {
+        audio_help();
+        exit(EXIT_SUCCESS);
+    }
     Visitor *v = qobject_input_visitor_new_str(opt, "driver", &error_fatal);
     visit_type_Audiodev(v, NULL, &dev, &error_fatal);
     visit_free(v);
@@ -2119,13 +2143,17 @@ void audio_define(Audiodev *dev)
     QSIMPLEQ_INSERT_TAIL(&audiodevs, e, next);
 }
 
-void audio_init_audiodevs(void)
+bool audio_init_audiodevs(void)
 {
     AudiodevListEntry *e;
 
     QSIMPLEQ_FOREACH(e, &audiodevs, next) {
-        audio_init(e->dev, NULL);
+        if (!audio_init(e->dev, NULL)) {
+            return false;
+        }
     }
+
+    return true;
 }
 
 audsettings audiodev_to_audsettings(AudiodevPerDirectionOptions *pdo)

audio/audio.h

@@ -170,7 +170,8 @@ void audio_sample_from_uint64(void *samples, int pos,
 
 void audio_define(Audiodev *audio);
 void audio_parse_option(const char *opt);
-void audio_init_audiodevs(void);
+bool audio_init_audiodevs(void);
+void audio_help(void);
 void audio_legacy_help(void);
 
 AudioState *audio_state_by_name(const char *name);

audio/audio_template.h

@@ -59,13 +59,12 @@ static void glue(audio_init_nb_voices_, TYPE)(AudioState *s,
     if (audio_bug(__func__, !voice_size && max_voices)) {
         dolog ("drv=`%s' voice_size=0 max_voices=%d\n",
                drv->name, max_voices);
-        abort();
+        glue (s->nb_hw_voices_, TYPE) = 0;
     }
 
     if (audio_bug(__func__, voice_size && !max_voices)) {
         dolog ("drv=`%s' voice_size=%d max_voices=0\n",
                drv->name, voice_size);
-        abort();
     }
 }
 
@@ -82,7 +81,6 @@ static void glue(audio_pcm_hw_alloc_resources_, TYPE)(HW *hw)
         size_t samples = hw->samples;
         if (audio_bug(__func__, samples == 0)) {
             dolog("Attempted to allocate empty buffer\n");
-            abort();
         }
 
         HWBUF = g_malloc0(sizeof(STSampleBuffer) + sizeof(st_sample) * samples);
@@ -254,12 +252,12 @@ static HW *glue(audio_pcm_hw_add_new_, TYPE)(AudioState *s,
 
     if (audio_bug(__func__, !drv)) {
         dolog ("No host audio driver\n");
-        abort();
+        return NULL;
     }
 
     if (audio_bug(__func__, !drv->pcm_ops)) {
         dolog ("Host audio driver without pcm_ops\n");
-        abort();
+        return NULL;
     }
 
     hw = audio_calloc(__func__, 1, glue(drv->voice_size_, TYPE));
@@ -277,13 +275,12 @@ static HW *glue(audio_pcm_hw_add_new_, TYPE)(AudioState *s,
     QLIST_INIT (&hw->cap_head);
 #endif
     if (glue (hw->pcm_ops->init_, TYPE) (hw, as, s->drv_opaque)) {
-        g_free(hw);
+        goto err0;
-        return NULL;
     }
 
     if (audio_bug(__func__, hw->samples <= 0)) {
         dolog("hw->samples=%zd\n", hw->samples);
-        abort();
+        goto err1;
     }
 
     if (hw->info.is_float) {
@@ -312,6 +309,12 @@ static HW *glue(audio_pcm_hw_add_new_, TYPE)(AudioState *s,
     audio_attach_capture (hw);
 #endif
     return hw;
+
+ err1:
+    glue (hw->pcm_ops->fini_, TYPE) (hw);
+ err0:
+    g_free (hw);
+    return NULL;
 }
 
 AudiodevPerDirectionOptions *glue(audio_get_pdo_, TYPE)(Audiodev *dev)
@@ -336,6 +339,8 @@ AudiodevPerDirectionOptions *glue(audio_get_pdo_, TYPE)(Audiodev *dev)
         return qapi_AudiodevPaPerDirectionOptions_base(dev->u.pa.TYPE);
     case AUDIODEV_DRIVER_SDL:
         return qapi_AudiodevSdlPerDirectionOptions_base(dev->u.sdl.TYPE);
+    case AUDIODEV_DRIVER_SNDIO:
+        return dev->u.sndio.TYPE;
     case AUDIODEV_DRIVER_SPICE:
         return dev->u.spice.TYPE;
     case AUDIODEV_DRIVER_WAV:
@@ -432,7 +437,7 @@ void glue (AUD_close_, TYPE) (QEMUSoundCard *card, SW *sw)
     if (sw) {
         if (audio_bug(__func__, !card)) {
             dolog ("card=%p\n", card);
-            abort();
+            return;
         }
 
         glue (audio_close_, TYPE) (sw);
@@ -454,7 +459,7 @@ SW *glue (AUD_open_, TYPE) (
     if (audio_bug(__func__, !card || !name || !callback_fn || !as)) {
         dolog ("card=%p name=%p callback_fn=%p as=%p\n",
                card, name, callback_fn, as);
-        abort();
+        goto fail;
     }
 
     s = card->state;
@@ -465,12 +470,12 @@ SW *glue (AUD_open_, TYPE) (
 
     if (audio_bug(__func__, audio_validate_settings(as))) {
         audio_print_settings (as);
-        abort();
+        goto fail;
     }
 
     if (audio_bug(__func__, !s->drv)) {
         dolog ("Can not open `%s' (no host audio driver)\n", name);
-        abort();
+        goto fail;
     }
 
     if (sw && audio_pcm_info_eq (&sw->info, as)) {

audio/meson.build

@@ -17,6 +17,7 @@ foreach m : [
   ['pa', pulse, files('paaudio.c')],
   ['sdl', sdl, files('sdlaudio.c')],
   ['jack', jack, files('jackaudio.c')],
+  ['sndio', sndio, files('sndioaudio.c')],
   ['spice', spice, files('spiceaudio.c')]
 ]
   if m[1].found()

audio/sndioaudio.c

@@ -0,0 +1,565 @@
+/*
+ * SPDX-License-Identifier: ISC
+ *
+ * Copyright (c) 2019 Alexandre Ratchov <alex@caoua.org>
+ */
+
+/*
+ * TODO :
+ *
+ * Use a single device and open it in full-duplex rather than
+ * opening it twice (once for playback once for recording).
+ *
+ * This is the only way to ensure that playback doesn't drift with respect
+ * to recording, which is what guest systems expect.
+ */
+
+#include <poll.h>
+#include <sndio.h>
+#include "qemu/osdep.h"
+#include "qemu/main-loop.h"
+#include "audio.h"
+#include "trace.h"
+
+#define AUDIO_CAP "sndio"
+#include "audio_int.h"
+
+/* default latency in microseconds if no option is set */
+#define SNDIO_LATENCY_US   50000
+
+typedef struct SndioVoice {
+    union {
+        HWVoiceOut out;
+        HWVoiceIn in;
+    } hw;
+    struct sio_par par;
+    struct sio_hdl *hdl;
+    struct pollfd *pfds;
+    struct pollindex {
+        struct SndioVoice *self;
+        int index;
+    } *pindexes;
+    unsigned char *buf;
+    size_t buf_size;
+    size_t sndio_pos;
+    size_t qemu_pos;
+    unsigned int mode;
+    unsigned int nfds;
+    bool enabled;
+} SndioVoice;
+
+typedef struct SndioConf {
+    const char *devname;
+    unsigned int latency;
+} SndioConf;
+
+/* needed for forward reference */
+static void sndio_poll_in(void *arg);
+static void sndio_poll_out(void *arg);
+
+/*
+ * stop polling descriptors
+ */
+static void sndio_poll_clear(SndioVoice *self)
+{
+    struct pollfd *pfd;
+    int i;
+
+    for (i = 0; i < self->nfds; i++) {
+        pfd = &self->pfds[i];
+        qemu_set_fd_handler(pfd->fd, NULL, NULL, NULL);
+    }
+
+    self->nfds = 0;
+}
+
+/*
+ * write data to the device until it blocks or
+ * all of our buffered data is written
+ */
+static void sndio_write(SndioVoice *self)
+{
+    size_t todo, n;
+
+    todo = self->qemu_pos - self->sndio_pos;
+
+    /*
+     * transfer data to device, until it blocks
+     */
+    while (todo > 0) {
+        n = sio_write(self->hdl, self->buf + self->sndio_pos, todo);
+        if (n == 0) {
+            break;
+        }
+        self->sndio_pos += n;
+        todo -= n;
+    }
+
+    if (self->sndio_pos == self->buf_size) {
+        /*
+         * we complete the block
+         */
+        self->sndio_pos = 0;
+        self->qemu_pos = 0;
+    }
+}
+
+/*
+ * read data from the device until it blocks or
+ * there no room any longer
+ */
+static void sndio_read(SndioVoice *self)
+{
+    size_t todo, n;
+
+    todo = self->buf_size - self->sndio_pos;
+
+    /*
+     * transfer data from the device, until it blocks
+     */
+    while (todo > 0) {
+        n = sio_read(self->hdl, self->buf + self->sndio_pos, todo);
+        if (n == 0) {
+            break;
+        }
+        self->sndio_pos += n;
+        todo -= n;
+    }
+}
+
+/*
+ * Set handlers for all descriptors libsndio needs to
+ * poll
+ */
+static void sndio_poll_wait(SndioVoice *self)
+{
+    struct pollfd *pfd;
+    int events, i;
+
+    events = 0;
+    if (self->mode == SIO_PLAY) {
+        if (self->sndio_pos < self->qemu_pos) {
+            events |= POLLOUT;
+        }
+    } else {
+        if (self->sndio_pos < self->buf_size) {
+            events |= POLLIN;
+        }
+    }
+
+    /*
+     * fill the given array of descriptors with the events sndio
+     * wants, they are different from our 'event' variable because
+     * sndio may use descriptors internally.
+     */
+    self->nfds = sio_pollfd(self->hdl, self->pfds, events);
+
+    for (i = 0; i < self->nfds; i++) {
+        pfd = &self->pfds[i];
+        if (pfd->fd < 0) {
+            continue;
+        }
+        qemu_set_fd_handler(pfd->fd,
+            (pfd->events & POLLIN) ? sndio_poll_in : NULL,
+            (pfd->events & POLLOUT) ? sndio_poll_out : NULL,
+            &self->pindexes[i]);
+        pfd->revents = 0;
+    }
+}
+
+/*
+ * call-back called when one of the descriptors
+ * became readable or writable
+ */
+static void sndio_poll_event(SndioVoice *self, int index, int event)
+{
+    int revents;
+
+    /*
+     * ensure we're not called twice this cycle
+     */
+    sndio_poll_clear(self);
+
+    /*
+     * make self->pfds[] look as we're returning from poll syscal,
+     * this is how sio_revents expects events to be.
+     */
+    self->pfds[index].revents = event;
+
+    /*
+     * tell sndio to handle events and return whether we can read or
+     * write without blocking.
+     */
+    revents = sio_revents(self->hdl, self->pfds);
+    if (self->mode == SIO_PLAY) {
+        if (revents & POLLOUT) {
+            sndio_write(self);
+        }
+
+        if (self->qemu_pos < self->buf_size) {
+            audio_run(self->hw.out.s, "sndio_out");
+        }
+    } else {
+        if (revents & POLLIN) {
+            sndio_read(self);
+        }
+
+        if (self->qemu_pos < self->sndio_pos) {
+            audio_run(self->hw.in.s, "sndio_in");
+        }
+    }
+
+    /*
+     * audio_run() may have changed state
+     */
+    if (self->enabled) {
+        sndio_poll_wait(self);
+    }
+}
+
+/*
+ * return the upper limit of the amount of free play buffer space
+ */
+static size_t sndio_buffer_get_free(HWVoiceOut *hw)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    return self->buf_size - self->qemu_pos;
+}
+
+/*
+ * return a buffer where data to play can be stored,
+ * its size is stored in the location pointed by the size argument.
+ */
+static void *sndio_get_buffer_out(HWVoiceOut *hw, size_t *size)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    *size = self->buf_size - self->qemu_pos;
+    return self->buf + self->qemu_pos;
+}
+
+/*
+ * put back to sndio back-end a buffer returned by sndio_get_buffer_out()
+ */
+static size_t sndio_put_buffer_out(HWVoiceOut *hw, void *buf, size_t size)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    self->qemu_pos += size;
+    sndio_poll_wait(self);
+    return size;
+}
+
+/*
+ * return a buffer from where recorded data is available,
+ * its size is stored in the location pointed by the size argument.
+ * it may not exceed the initial value of "*size".
+ */
+static void *sndio_get_buffer_in(HWVoiceIn *hw, size_t *size)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+    size_t todo, max_todo;
+
+    /*
+     * unlike the get_buffer_out() method, get_buffer_in()
+     * must return a buffer of at most the given size, see audio.c
+     */
+    max_todo = *size;
+
+    todo = self->sndio_pos - self->qemu_pos;
+    if (todo > max_todo) {
+        todo = max_todo;
+    }
+
+    *size = todo;
+    return self->buf + self->qemu_pos;
+}
+
+/*
+ * discard the given amount of recorded data
+ */
+static void sndio_put_buffer_in(HWVoiceIn *hw, void *buf, size_t size)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    self->qemu_pos += size;
+    if (self->qemu_pos == self->buf_size) {
+        self->qemu_pos = 0;
+        self->sndio_pos = 0;
+    }
+    sndio_poll_wait(self);
+}
+
+/*
+ * call-back called when one of our descriptors becomes writable
+ */
+static void sndio_poll_out(void *arg)
+{
+    struct pollindex *pindex = (struct pollindex *) arg;
+
+    sndio_poll_event(pindex->self, pindex->index, POLLOUT);
+}
+
+/*
+ * call-back called when one of our descriptors becomes readable
+ */
+static void sndio_poll_in(void *arg)
+{
+    struct pollindex *pindex = (struct pollindex *) arg;
+
+    sndio_poll_event(pindex->self, pindex->index, POLLIN);
+}
+
+static void sndio_fini(SndioVoice *self)
+{
+    if (self->hdl) {
+        sio_close(self->hdl);
+        self->hdl = NULL;
+    }
+
+    g_free(self->pfds);
+    g_free(self->pindexes);
+    g_free(self->buf);
+}
+
+static int sndio_init(SndioVoice *self,
+                      struct audsettings *as, int mode, Audiodev *dev)
+{
+    AudiodevSndioOptions *opts = &dev->u.sndio;
+    unsigned long long latency;
+    const char *dev_name;
+    struct sio_par req;
+    unsigned int nch;
+    int i, nfds;
+
+    dev_name = opts->has_dev ? opts->dev : SIO_DEVANY;
+    latency = opts->has_latency ? opts->latency : SNDIO_LATENCY_US;
+
+    /* open the device in non-blocking mode */
+    self->hdl = sio_open(dev_name, mode, 1);
+    if (self->hdl == NULL) {
+        dolog("failed to open device\n");
+        return -1;
+    }
+
+    self->mode = mode;
+
+    sio_initpar(&req);
+
+    switch (as->fmt) {
+    case AUDIO_FORMAT_S8:
+        req.bits = 8;
+        req.sig = 1;
+        break;
+    case AUDIO_FORMAT_U8:
+        req.bits = 8;
+        req.sig = 0;
+        break;
+    case AUDIO_FORMAT_S16:
+        req.bits = 16;
+        req.sig = 1;
+        break;
+    case AUDIO_FORMAT_U16:
+        req.bits = 16;
+        req.sig = 0;
+        break;
+    case AUDIO_FORMAT_S32:
+        req.bits = 32;
+        req.sig = 1;
+        break;
+    case AUDIO_FORMAT_U32:
+        req.bits = 32;
+        req.sig = 0;
+        break;
+    default:
+        dolog("unknown audio sample format\n");
+        return -1;
+    }
+
+    if (req.bits > 8) {
+        req.le = as->endianness ? 0 : 1;
+    }
+
+    req.rate = as->freq;
+    if (mode == SIO_PLAY) {
+        req.pchan = as->nchannels;
+    } else {
+        req.rchan = as->nchannels;
+    }
+
+    /* set on-device buffer size */
+    req.appbufsz = req.rate * latency / 1000000;
+
+    if (!sio_setpar(self->hdl, &req)) {
+        dolog("failed set audio params\n");
+        goto fail;
+    }
+
+    if (!sio_getpar(self->hdl, &self->par)) {
+        dolog("failed get audio params\n");
+        goto fail;
+    }
+
+    nch = (mode == SIO_PLAY) ? self->par.pchan : self->par.rchan;
+
+    /*
+     * With the default setup, sndio supports any combination of parameters
+     * so these checks are mostly to catch configuration errors.
+     */
+    if (self->par.bits != req.bits || self->par.bps != req.bits / 8 ||
+        self->par.sig != req.sig || (req.bits > 8 && self->par.le != req.le) ||
+        self->par.rate != as->freq || nch != as->nchannels) {
+        dolog("unsupported audio params\n");
+        goto fail;
+    }
+
+    /*
+     * we use one block as buffer size; this is how
+     * transfers get well aligned
+     */
+    self->buf_size = self->par.round * self->par.bps * nch;
+
+    self->buf = g_malloc(self->buf_size);
+    if (self->buf == NULL) {
+        dolog("failed to allocate audio buffer\n");
+        goto fail;
+    }
+
+    nfds = sio_nfds(self->hdl);
+
+    self->pfds = g_malloc_n(nfds, sizeof(struct pollfd));
+    if (self->pfds == NULL) {
+        dolog("failed to allocate pollfd structures\n");
+        goto fail;
+    }
+
+    self->pindexes = g_malloc_n(nfds, sizeof(struct pollindex));
+    if (self->pindexes == NULL) {
+        dolog("failed to allocate pollindex structures\n");
+        goto fail;
+    }
+
+    for (i = 0; i < nfds; i++) {
+        self->pindexes[i].self = self;
+        self->pindexes[i].index = i;
+    }
+
+    return 0;
+fail:
+    sndio_fini(self);
+    return -1;
+}
+
+static void sndio_enable(SndioVoice *self, bool enable)
+{
+    if (enable) {
+        sio_start(self->hdl);
+        self->enabled = true;
+        sndio_poll_wait(self);
+    } else {
+        self->enabled = false;
+        sndio_poll_clear(self);
+        sio_stop(self->hdl);
+    }
+}
+
+static void sndio_enable_out(HWVoiceOut *hw, bool enable)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    sndio_enable(self, enable);
+}
+
+static void sndio_enable_in(HWVoiceIn *hw, bool enable)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    sndio_enable(self, enable);
+}
+
+static int sndio_init_out(HWVoiceOut *hw, struct audsettings *as, void *opaque)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    if (sndio_init(self, as, SIO_PLAY, opaque) == -1) {
+        return -1;
+    }
+
+    audio_pcm_init_info(&hw->info, as);
+    hw->samples = self->par.round;
+    return 0;
+}
+
+static int sndio_init_in(HWVoiceIn *hw, struct audsettings *as, void *opaque)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    if (sndio_init(self, as, SIO_REC, opaque) == -1) {
+        return -1;
+    }
+
+    audio_pcm_init_info(&hw->info, as);
+    hw->samples = self->par.round;
+    return 0;
+}
+
+static void sndio_fini_out(HWVoiceOut *hw)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    sndio_fini(self);
+}
+
+static void sndio_fini_in(HWVoiceIn *hw)
+{
+    SndioVoice *self = (SndioVoice *) hw;
+
+    sndio_fini(self);
+}
+
+static void *sndio_audio_init(Audiodev *dev)
+{
+    assert(dev->driver == AUDIODEV_DRIVER_SNDIO);
+    return dev;
+}
+
+static void sndio_audio_fini(void *opaque)
+{
+}
+
+static struct audio_pcm_ops sndio_pcm_ops = {
+    .init_out        = sndio_init_out,
+    .fini_out        = sndio_fini_out,
+    .enable_out      = sndio_enable_out,
+    .write           = audio_generic_write,
+    .buffer_get_free = sndio_buffer_get_free,
+    .get_buffer_out  = sndio_get_buffer_out,
+    .put_buffer_out  = sndio_put_buffer_out,
+    .init_in         = sndio_init_in,
+    .fini_in         = sndio_fini_in,
+    .read            = audio_generic_read,
+    .enable_in       = sndio_enable_in,
+    .get_buffer_in   = sndio_get_buffer_in,
+    .put_buffer_in   = sndio_put_buffer_in,
+};
+
+static struct audio_driver sndio_audio_driver = {
+    .name           = "sndio",
+    .descr          = "sndio https://sndio.org",
+    .init           = sndio_audio_init,
+    .fini           = sndio_audio_fini,
+    .pcm_ops        = &sndio_pcm_ops,
+    .can_be_default = 1,
+    .max_voices_out = INT_MAX,
+    .max_voices_in  = INT_MAX,
+    .voice_size_out = sizeof(SndioVoice),
+    .voice_size_in  = sizeof(SndioVoice)
+};
+
+static void register_audio_sndio(void)
+{
+    audio_driver_register(&sndio_audio_driver);
+}
+
+type_init(register_audio_sndio);

backends/dbus-vmstate.c

@@ -114,14 +114,19 @@ dbus_get_proxies(DBusVMState *self, GError **err)
                     "org.qemu.VMState1",
                     NULL, err);
         if (!proxy) {
-            return NULL;
+            if (err != NULL && *err != NULL) {
+                warn_report("%s: Failed to create proxy: %s",
+                            __func__, (*err)->message);
+                g_clear_error(err);
+            }
+            continue;
         }
 
         result = g_dbus_proxy_get_cached_property(proxy, "Id");
         if (!result) {
-            g_set_error_literal(err, G_IO_ERROR, G_IO_ERROR_FAILED,
+            warn_report("%s: VMState Id property is missing.", __func__);
-                                "VMState Id property is missing.");
+            g_clear_object(&proxy);
-            return NULL;
+            continue;
         }
 
         id = g_variant_dup_string(result, &size);

backends/hostmem.c

@@ -306,22 +306,12 @@ bool host_memory_backend_is_mapped(HostMemoryBackend *backend)
     return backend->is_mapped;
 }
 
-#ifdef __linux__
 size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
 {
-    Object *obj = OBJECT(memdev);
+    size_t pagesize = qemu_ram_pagesize(memdev->mr.ram_block);
-    char *path = object_property_get_str(obj, "mem-path", NULL);
+    g_assert(pagesize >= qemu_real_host_page_size());
-    size_t pagesize = qemu_mempath_getpagesize(path);
-
-    g_free(path);
     return pagesize;
 }
-#else
-size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
-{
-    return qemu_real_host_page_size();
-}
-#endif
 
 static void
 host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)

backends/tpm/tpm_emulator.c

@@ -32,8 +32,10 @@
 #include "qemu/sockets.h"
 #include "qemu/lockable.h"
 #include "io/channel-socket.h"
+#include "sysemu/runstate.h"
 #include "sysemu/tpm_backend.h"
 #include "sysemu/tpm_util.h"
+#include "sysemu/runstate.h"
 #include "tpm_int.h"
 #include "tpm_ioctl.h"
 #include "migration/blocker.h"
@@ -81,6 +83,9 @@ struct TPMEmulator {
     unsigned int established_flag_cached:1;
 
     TPMBlobBuffers state_blobs;
+
+    bool relock_storage;
+    VMChangeStateEntry *vmstate;
 };
 
 struct tpm_error {
@@ -302,6 +307,35 @@ static int tpm_emulator_stop_tpm(TPMBackend *tb)
     return 0;
 }
 
+static int tpm_emulator_lock_storage(TPMEmulator *tpm_emu)
+{
+    ptm_lockstorage pls;
+
+    if (!TPM_EMULATOR_IMPLEMENTS_ALL_CAPS(tpm_emu, PTM_CAP_LOCK_STORAGE)) {
+        trace_tpm_emulator_lock_storage_cmd_not_supt();
+        return 0;
+    }
+
+    /* give failing side 300 * 10ms time to release lock */
+    pls.u.req.retries = cpu_to_be32(300);
+    if (tpm_emulator_ctrlcmd(tpm_emu, CMD_LOCK_STORAGE, &pls,
+                             sizeof(pls.u.req), sizeof(pls.u.resp)) < 0) {
+        error_report("tpm-emulator: Could not lock storage within 3 seconds: "
+                     "%s", strerror(errno));
+        return -1;
+    }
+
+    pls.u.resp.tpm_result = be32_to_cpu(pls.u.resp.tpm_result);
+    if (pls.u.resp.tpm_result != 0) {
+        error_report("tpm-emulator: TPM result for CMD_LOCK_STORAGE: 0x%x %s",
+                     pls.u.resp.tpm_result,
+                     tpm_emulator_strerror(pls.u.resp.tpm_result));
+        return -1;
+    }
+
+    return 0;
+}
+
 static int tpm_emulator_set_buffer_size(TPMBackend *tb,
                                         size_t wanted_size,
                                         size_t *actual_size)
@@ -383,6 +417,15 @@ err_exit:
 
 static int tpm_emulator_startup_tpm(TPMBackend *tb, size_t buffersize)
 {
+    /* TPM startup will be done from post_load hook */
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        if (buffersize != 0) {
+            return tpm_emulator_set_buffer_size(tb, buffersize, NULL);
+        }
+
+        return 0;
+    }
+
     return tpm_emulator_startup_tpm_resume(tb, buffersize, false);
 }
 
@@ -843,13 +886,34 @@ static int tpm_emulator_pre_save(void *opaque)
 {
     TPMBackend *tb = opaque;
     TPMEmulator *tpm_emu = TPM_EMULATOR(tb);
+    int ret;
 
     trace_tpm_emulator_pre_save();
 
     tpm_backend_finish_sync(tb);
 
     /* get the state blobs from the TPM */
-    return tpm_emulator_get_state_blobs(tpm_emu);
+    ret = tpm_emulator_get_state_blobs(tpm_emu);
+
+    tpm_emu->relock_storage = ret == 0;
+
+    return ret;
+}
+
+static void tpm_emulator_vm_state_change(void *opaque, bool running,
+                                         RunState state)
+{
+    TPMBackend *tb = opaque;
+    TPMEmulator *tpm_emu = TPM_EMULATOR(tb);
+
+    trace_tpm_emulator_vm_state_change(running, state);
+
+    if (!running || state != RUN_STATE_RUNNING || !tpm_emu->relock_storage) {
+        return;
+    }
+
+    /* lock storage after migration fall-back */
+    tpm_emulator_lock_storage(tpm_emu);
 }
 
 /*
@@ -911,6 +975,9 @@ static void tpm_emulator_inst_init(Object *obj)
     tpm_emu->options = g_new0(TPMEmulatorOptions, 1);
     tpm_emu->cur_locty_number = ~0;
     qemu_mutex_init(&tpm_emu->mutex);
+    tpm_emu->vmstate =
+        qemu_add_vm_change_state_handler(tpm_emulator_vm_state_change,
+                                         tpm_emu);
 
     vmstate_register(NULL, VMSTATE_INSTANCE_ID_ANY,
                      &vmstate_tpm_emulator, obj);
@@ -960,6 +1027,7 @@ static void tpm_emulator_inst_finalize(Object *obj)
     tpm_sized_buffer_reset(&state_blobs->savestate);
 
     qemu_mutex_destroy(&tpm_emu->mutex);
+    qemu_del_vm_change_state_handler(tpm_emu->vmstate);
 
     vmstate_unregister(NULL, &vmstate_tpm_emulator, obj);
 }

backends/tpm/tpm_ioctl.h

@@ -5,12 +5,19 @@
  *
  * This file is licensed under the terms of the 3-clause BSD license
  */
+#ifndef _TPM_IOCTL_H_
+#define _TPM_IOCTL_H_
 
-#ifndef TPM_IOCTL_H
+#if defined(__CYGWIN__)
-#define TPM_IOCTL_H
+# define __USE_LINUX_IOCTL_DEFS
+#endif
 
+#include <stdint.h>
+#include <sys/types.h>
+#ifndef _WIN32
 #include <sys/uio.h>
 #include <sys/ioctl.h>
+#endif
 
 #ifdef HAVE_SYS_IOCCOM_H
 #include <sys/ioccom.h>
@@ -194,6 +201,48 @@ struct ptm_setbuffersize {
     } u;
 };
 
+#define PTM_GETINFO_SIZE (3 * 1024)
+/*
+ * PTM_GET_INFO: Get info about the TPM implementation (from libtpms)
+ *
+ * This request allows to indirectly call TPMLIB_GetInfo(flags) and
+ * retrieve information from libtpms.
+ * Only one transaction is currently necessary for returning results
+ * to a client. Therefore, totlength and length will be the same if
+ * offset is 0.
+ */
+struct ptm_getinfo {
+    union {
+        struct {
+            uint64_t flags;
+            uint32_t offset;      /* offset from where to read */
+            uint32_t pad;         /* 32 bit arch */
+        } req; /* request */
+        struct {
+            ptm_res tpm_result;
+            uint32_t totlength;
+            uint32_t length;
+            char buffer[PTM_GETINFO_SIZE];
+        } resp; /* response */
+    } u;
+};
+
+#define SWTPM_INFO_TPMSPECIFICATION ((uint64_t)1 << 0)
+#define SWTPM_INFO_TPMATTRIBUTES    ((uint64_t)1 << 1)
+
+/*
+ * PTM_LOCK_STORAGE: Lock the storage and retry n times
+ */
+struct ptm_lockstorage {
+    union {
+        struct {
+            uint32_t retries; /* number of retries */
+        } req; /* request */
+        struct {
+            ptm_res tpm_result;
+        } resp; /* reponse */
+    } u;
+};
 
 typedef uint64_t ptm_cap;
 typedef struct ptm_est ptm_est;
@@ -205,6 +254,8 @@ typedef struct ptm_getstate ptm_getstate;
 typedef struct ptm_setstate ptm_setstate;
 typedef struct ptm_getconfig ptm_getconfig;
 typedef struct ptm_setbuffersize ptm_setbuffersize;
+typedef struct ptm_getinfo ptm_getinfo;
+typedef struct ptm_lockstorage ptm_lockstorage;
 
 /* capability flags returned by PTM_GET_CAPABILITY */
 #define PTM_CAP_INIT               (1)
@@ -221,7 +272,11 @@ typedef struct ptm_setbuffersize ptm_setbuffersize;
 #define PTM_CAP_GET_CONFIG         (1 << 11)
 #define PTM_CAP_SET_DATAFD         (1 << 12)
 #define PTM_CAP_SET_BUFFERSIZE     (1 << 13)
+#define PTM_CAP_GET_INFO           (1 << 14)
+#define PTM_CAP_SEND_COMMAND_HEADER (1 << 15)
+#define PTM_CAP_LOCK_STORAGE       (1 << 16)
 
+#ifndef _WIN32
 enum {
     PTM_GET_CAPABILITY     = _IOR('P', 0, ptm_cap),
     PTM_INIT               = _IOWR('P', 1, ptm_init),
@@ -240,7 +295,10 @@ enum {
     PTM_GET_CONFIG         = _IOR('P', 14, ptm_getconfig),
     PTM_SET_DATAFD         = _IOR('P', 15, ptm_res),
     PTM_SET_BUFFERSIZE     = _IOWR('P', 16, ptm_setbuffersize),
+    PTM_GET_INFO           = _IOWR('P', 17, ptm_getinfo),
+    PTM_LOCK_STORAGE       = _IOWR('P', 18, ptm_lockstorage),
 };
+#endif
 
 /*
  * Commands used by the non-CUSE TPMs
@@ -253,23 +311,25 @@ enum {
  * and ptm_set_state:u.req.data) are 0xffffffff.
  */
 enum {
-    CMD_GET_CAPABILITY = 1,
+    CMD_GET_CAPABILITY = 1,   /* 0x01 */
-    CMD_INIT,
+    CMD_INIT,                 /* 0x02 */
-    CMD_SHUTDOWN,
+    CMD_SHUTDOWN,             /* 0x03 */
-    CMD_GET_TPMESTABLISHED,
+    CMD_GET_TPMESTABLISHED,   /* 0x04 */
-    CMD_SET_LOCALITY,
+    CMD_SET_LOCALITY,         /* 0x05 */
-    CMD_HASH_START,
+    CMD_HASH_START,           /* 0x06 */
-    CMD_HASH_DATA,
+    CMD_HASH_DATA,            /* 0x07 */
-    CMD_HASH_END,
+    CMD_HASH_END,             /* 0x08 */
-    CMD_CANCEL_TPM_CMD,
+    CMD_CANCEL_TPM_CMD,       /* 0x09 */
-    CMD_STORE_VOLATILE,
+    CMD_STORE_VOLATILE,       /* 0x0a */
-    CMD_RESET_TPMESTABLISHED,
+    CMD_RESET_TPMESTABLISHED, /* 0x0b */
-    CMD_GET_STATEBLOB,
+    CMD_GET_STATEBLOB,        /* 0x0c */
-    CMD_SET_STATEBLOB,
+    CMD_SET_STATEBLOB,        /* 0x0d */
-    CMD_STOP,
+    CMD_STOP,                 /* 0x0e */
-    CMD_GET_CONFIG,
+    CMD_GET_CONFIG,           /* 0x0f */
-    CMD_SET_DATAFD,
+    CMD_SET_DATAFD,           /* 0x10 */
-    CMD_SET_BUFFERSIZE,
+    CMD_SET_BUFFERSIZE,       /* 0x11 */
+    CMD_GET_INFO,             /* 0x12 */
+    CMD_LOCK_STORAGE,         /* 0x13 */
 };
 
-#endif /* TPM_IOCTL_H */
+#endif /* _TPM_IOCTL_H_ */

backends/tpm/trace-events

@@ -20,6 +20,8 @@ tpm_emulator_set_buffer_size(uint32_t buffersize, uint32_t minsize, uint32_t max
 tpm_emulator_startup_tpm_resume(bool is_resume, size_t buffersize) "is_resume: %d, buffer size: %zu"
 tpm_emulator_get_tpm_established_flag(uint8_t flag) "got established flag: %d"
 tpm_emulator_cancel_cmd_not_supt(void) "Backend does not support CANCEL_TPM_CMD"
+tpm_emulator_lock_storage_cmd_not_supt(void) "Backend does not support LOCK_STORAGE"
+tpm_emulator_vm_state_change(int running, int state) "state change to running %d state %d"
 tpm_emulator_handle_device_opts_tpm12(void) "TPM Version 1.2"
 tpm_emulator_handle_device_opts_tpm2(void) "TPM Version 2"
 tpm_emulator_handle_device_opts_unspec(void) "TPM Version Unspecified"

block.c

@@ -631,9 +631,10 @@ static int64_t create_file_fallback_truncate(BlockBackend *blk,
  * Helper function for bdrv_create_file_fallback(): Zero the first
  * sector to remove any potentially pre-existing image header.
  */
-static int create_file_fallback_zero_first_sector(BlockBackend *blk,
+static int coroutine_fn
-                                                  int64_t current_size,
+create_file_fallback_zero_first_sector(BlockBackend *blk,
-                                                  Error **errp)
+                                       int64_t current_size,
+                                       Error **errp)
 {
     int64_t bytes_to_clear;
     int ret;
@@ -4980,8 +4981,8 @@ static void bdrv_close(BlockDriverState *bs)
 
 void bdrv_close_all(void)
 {
-    assert(job_next(NULL) == NULL);
     GLOBAL_STATE_CODE();
+    assert(job_next(NULL) == NULL);
 
     /* Drop references from requests still in flight, such as canceled block
      * jobs whose AIO context has not been polled yet */
@@ -6167,13 +6168,16 @@ XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp)
         }
     }
 
-    for (job = block_job_next(NULL); job; job = block_job_next(job)) {
+    WITH_JOB_LOCK_GUARD() {
-        GSList *el;
+        for (job = block_job_next_locked(NULL); job;
+             job = block_job_next_locked(job)) {
+            GSList *el;
 
-        xdbg_graph_add_node(gr, job, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_JOB,
+            xdbg_graph_add_node(gr, job, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_JOB,
-                           job->job.id);
+                                job->job.id);
-        for (el = job->nodes; el; el = el->next) {
+            for (el = job->nodes; el; el = el->next) {
-            xdbg_graph_add_edge(gr, job, (BdrvChild *)el->data);
+                xdbg_graph_add_edge(gr, job, (BdrvChild *)el->data);
+            }
         }
     }
 

block/accounting.c

@@ -38,13 +38,31 @@ void block_acct_init(BlockAcctStats *stats)
     if (qtest_enabled()) {
         clock_type = QEMU_CLOCK_VIRTUAL;
     }
+    stats->account_invalid = true;
+    stats->account_failed = true;
 }
 
-void block_acct_setup(BlockAcctStats *stats, bool account_invalid,
+static bool bool_from_onoffauto(OnOffAuto val, bool def)
-                      bool account_failed)
 {
-    stats->account_invalid = account_invalid;
+    switch (val) {
-    stats->account_failed = account_failed;
+    case ON_OFF_AUTO_AUTO:
+        return def;
+    case ON_OFF_AUTO_ON:
+        return true;
+    case ON_OFF_AUTO_OFF:
+        return false;
+    default:
+        abort();
+    }
+}
+
+void block_acct_setup(BlockAcctStats *stats, enum OnOffAuto account_invalid,
+                      enum OnOffAuto account_failed)
+{
+    stats->account_invalid = bool_from_onoffauto(account_invalid,
+                                                 stats->account_invalid);
+    stats->account_failed = bool_from_onoffauto(account_failed,
+                                                stats->account_failed);
 }
 
 void block_acct_cleanup(BlockAcctStats *stats)

block/blkverify.c

@@ -258,7 +258,7 @@ blkverify_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
     return blkverify_co_prwv(bs, &r, offset, bytes, qiov, qiov, flags, true);
 }
 
-static int blkverify_co_flush(BlockDriverState *bs)
+static int coroutine_fn blkverify_co_flush(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 

block/block-backend.c

@@ -1546,7 +1546,7 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset,
     return &acb->common;
 }
 
-static void blk_aio_read_entry(void *opaque)
+static void coroutine_fn blk_aio_read_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
@@ -1558,7 +1558,7 @@ static void blk_aio_read_entry(void *opaque)
     blk_aio_complete(acb);
 }
 
-static void blk_aio_write_entry(void *opaque)
+static void coroutine_fn blk_aio_write_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
@@ -1669,7 +1669,7 @@ int coroutine_fn blk_co_ioctl(BlockBackend *blk, unsigned long int req,
     return ret;
 }
 
-static void blk_aio_ioctl_entry(void *opaque)
+static void coroutine_fn blk_aio_ioctl_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
@@ -1703,7 +1703,7 @@ blk_co_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes)
     return bdrv_co_pdiscard(blk->root, offset, bytes);
 }
 
-static void blk_aio_pdiscard_entry(void *opaque)
+static void coroutine_fn blk_aio_pdiscard_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
@@ -1747,7 +1747,7 @@ static int coroutine_fn blk_co_do_flush(BlockBackend *blk)
     return bdrv_co_flush(blk_bs(blk));
 }
 
-static void blk_aio_flush_entry(void *opaque)
+static void coroutine_fn blk_aio_flush_entry(void *opaque)
 {
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;

block/copy-before-write.c

@@ -203,9 +203,9 @@ static int coroutine_fn cbw_co_flush(BlockDriverState *bs)
  * It's guaranteed that guest writes will not interact in the region until
  * cbw_snapshot_read_unlock() called.
  */
-static BlockReq *cbw_snapshot_read_lock(BlockDriverState *bs,
+static coroutine_fn BlockReq *
-                                        int64_t offset, int64_t bytes,
+cbw_snapshot_read_lock(BlockDriverState *bs, int64_t offset, int64_t bytes,
-                                        int64_t *pnum, BdrvChild **file)
+                       int64_t *pnum, BdrvChild **file)
 {
     BDRVCopyBeforeWriteState *s = bs->opaque;
     BlockReq *req = g_new(BlockReq, 1);
@@ -240,7 +240,8 @@ static BlockReq *cbw_snapshot_read_lock(BlockDriverState *bs,
     return req;
 }
 
-static void cbw_snapshot_read_unlock(BlockDriverState *bs, BlockReq *req)
+static coroutine_fn void
+cbw_snapshot_read_unlock(BlockDriverState *bs, BlockReq *req)
 {
     BDRVCopyBeforeWriteState *s = bs->opaque;
 

block/curl.c

@@ -855,7 +855,7 @@ out_noclean:
     return -EINVAL;
 }
 
-static void curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
+static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
 {
     CURLState *state;
     int running;

block/file-posix.c

@@ -154,7 +154,6 @@ typedef struct BDRVRawState {
 
     bool has_discard:1;
     bool has_write_zeroes:1;
-    bool discard_zeroes:1;
     bool use_linux_aio:1;
     bool use_linux_io_uring:1;
     int page_cache_inconsistent; /* errno from fdatasync failure */
@@ -755,7 +754,6 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
             ret = -EINVAL;
             goto fail;
         } else {
-            s->discard_zeroes = true;
             s->has_fallocate = true;
         }
     } else {
@@ -769,19 +767,12 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     }
 
     if (S_ISBLK(st.st_mode)) {
-#ifdef BLKDISCARDZEROES
-        unsigned int arg;
-        if (ioctl(s->fd, BLKDISCARDZEROES, &arg) == 0 && arg) {
-            s->discard_zeroes = true;
-        }
-#endif
 #ifdef __linux__
         /* On Linux 3.10, BLKDISCARD leaves stale data in the page cache.  Do
          * not rely on the contents of discarded blocks unless using O_DIRECT.
          * Same for BLKZEROOUT.
          */
         if (!(bs->open_flags & BDRV_O_NOCACHE)) {
-            s->discard_zeroes = false;
             s->has_write_zeroes = false;
         }
 #endif
@@ -1295,7 +1286,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
     }
 #endif
 
-    if (bs->sg || S_ISBLK(st.st_mode)) {
+    if (bdrv_is_sg(bs) || S_ISBLK(st.st_mode)) {
         int ret = hdev_get_max_hw_transfer(s->fd, &st);
 
         if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) {
@@ -2061,6 +2052,28 @@ static int coroutine_fn raw_thread_pool_submit(BlockDriverState *bs,
     return thread_pool_submit_co(pool, func, arg);
 }
 
+/*
+ * Check if all memory in this vector is sector aligned.
+ */
+static bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
+{
+    int i;
+    size_t alignment = bdrv_min_mem_align(bs);
+    size_t len = bs->bl.request_alignment;
+    IO_CODE();
+
+    for (i = 0; i < qiov->niov; i++) {
+        if ((uintptr_t) qiov->iov[i].iov_base % alignment) {
+            return false;
+        }
+        if (qiov->iov[i].iov_len % len) {
+            return false;
+        }
+    }
+
+    return true;
+}
+
 static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
                                    uint64_t bytes, QEMUIOVector *qiov, int type)
 {
@@ -2158,7 +2171,7 @@ static void raw_aio_unplug(BlockDriverState *bs)
 #endif
 }
 
-static int raw_co_flush_to_disk(BlockDriverState *bs)
+static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
     RawPosixAIOData acb;

block/gluster.c

@@ -1555,7 +1555,6 @@ static BlockDriver bdrv_gluster = {
     .format_name                  = "gluster",
     .protocol_name                = "gluster",
     .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = false,
     .bdrv_file_open               = qemu_gluster_open,
     .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
@@ -1585,7 +1584,6 @@ static BlockDriver bdrv_gluster_tcp = {
     .format_name                  = "gluster",
     .protocol_name                = "gluster+tcp",
     .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = false,
     .bdrv_file_open               = qemu_gluster_open,
     .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
@@ -1615,7 +1613,6 @@ static BlockDriver bdrv_gluster_unix = {
     .format_name                  = "gluster",
     .protocol_name                = "gluster+unix",
     .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
     .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
@@ -1651,7 +1648,6 @@ static BlockDriver bdrv_gluster_rdma = {
     .format_name                  = "gluster",
     .protocol_name                = "gluster+rdma",
     .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
     .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
     .bdrv_reopen_commit           = qemu_gluster_reopen_commit,

block/io.c

@@ -751,11 +751,11 @@ static void coroutine_fn tracked_request_end(BdrvTrackedRequest *req)
 /**
  * Add an active request to the tracked requests list
  */
-static void tracked_request_begin(BdrvTrackedRequest *req,
+static void coroutine_fn tracked_request_begin(BdrvTrackedRequest *req,
-                                  BlockDriverState *bs,
+                                               BlockDriverState *bs,
-                                  int64_t offset,
+                                               int64_t offset,
-                                  int64_t bytes,
+                                               int64_t bytes,
-                                  enum BdrvTrackedRequestType type)
+                                               enum BdrvTrackedRequestType type)
 {
     bdrv_check_request(offset, bytes, &error_abort);
 
@@ -794,7 +794,7 @@ static bool tracked_request_overlaps(BdrvTrackedRequest *req,
 }
 
 /* Called with self->bs->reqs_lock held */
-static BdrvTrackedRequest *
+static coroutine_fn BdrvTrackedRequest *
 bdrv_find_conflicting_request(BdrvTrackedRequest *self)
 {
     BdrvTrackedRequest *req;
@@ -828,20 +828,16 @@ bdrv_find_conflicting_request(BdrvTrackedRequest *self)
 }
 
 /* Called with self->bs->reqs_lock held */
-static bool coroutine_fn
+static void coroutine_fn
 bdrv_wait_serialising_requests_locked(BdrvTrackedRequest *self)
 {
     BdrvTrackedRequest *req;
-    bool waited = false;
 
     while ((req = bdrv_find_conflicting_request(self))) {
         self->waiting_for = req;
         qemu_co_queue_wait(&req->wait_queue, &self->bs->reqs_lock);
         self->waiting_for = NULL;
-        waited = true;
     }
-
-    return waited;
 }
 
 /* Called with req->bs->reqs_lock held */
@@ -934,36 +930,31 @@ void bdrv_dec_in_flight(BlockDriverState *bs)
     bdrv_wakeup(bs);
 }
 
-static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self)
+static void coroutine_fn
+bdrv_wait_serialising_requests(BdrvTrackedRequest *self)
 {
     BlockDriverState *bs = self->bs;
-    bool waited = false;
 
     if (!qatomic_read(&bs->serialising_in_flight)) {
-        return false;
+        return;
     }
 
     qemu_co_mutex_lock(&bs->reqs_lock);
-    waited = bdrv_wait_serialising_requests_locked(self);
+    bdrv_wait_serialising_requests_locked(self);
     qemu_co_mutex_unlock(&bs->reqs_lock);
-
-    return waited;
 }
 
-bool coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req,
+void coroutine_fn bdrv_make_request_serialising(BdrvTrackedRequest *req,
                                                 uint64_t align)
 {
-    bool waited;
     IO_CODE();
 
     qemu_co_mutex_lock(&req->bs->reqs_lock);
 
     tracked_request_set_serialising(req, align);
-    waited = bdrv_wait_serialising_requests_locked(req);
+    bdrv_wait_serialising_requests_locked(req);
 
     qemu_co_mutex_unlock(&req->bs->reqs_lock);
-
-    return waited;
 }
 
 int bdrv_check_qiov_request(int64_t offset, int64_t bytes,
@@ -1644,10 +1635,10 @@ static bool bdrv_init_padding(BlockDriverState *bs,
     return true;
 }
 
-static int bdrv_padding_rmw_read(BdrvChild *child,
+static coroutine_fn int bdrv_padding_rmw_read(BdrvChild *child,
-                                 BdrvTrackedRequest *req,
+                                              BdrvTrackedRequest *req,
-                                 BdrvRequestPadding *pad,
+                                              BdrvRequestPadding *pad,
-                                 bool zero_middle)
+                                              bool zero_middle)
 {
     QEMUIOVector local_qiov;
     BlockDriverState *bs = child->bs;
@@ -3168,7 +3159,7 @@ out:
     return ret;
 }
 
-int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf)
+int coroutine_fn bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf)
 {
     BlockDriver *drv = bs->drv;
     CoroutineIOCompletion co = {
@@ -3236,27 +3227,6 @@ void *qemu_try_blockalign0(BlockDriverState *bs, size_t size)
     return mem;
 }
 
-/*
- * Check if all memory in this vector is sector aligned.
- */
-bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
-{
-    int i;
-    size_t alignment = bdrv_min_mem_align(bs);
-    IO_CODE();
-
-    for (i = 0; i < qiov->niov; i++) {
-        if ((uintptr_t) qiov->iov[i].iov_base % alignment) {
-            return false;
-        }
-        if (qiov->iov[i].iov_len % alignment) {
-            return false;
-        }
-    }
-
-    return true;
-}
-
 void bdrv_io_plug(BlockDriverState *bs)
 {
     BdrvChild *child;

block/io_uring.c

@@ -11,6 +11,7 @@
 #include "qemu/osdep.h"
 #include <liburing.h>
 #include "block/aio.h"
+#include "qemu/error-report.h"
 #include "qemu/queue.h"
 #include "block/block.h"
 #include "block/raw-aio.h"

block/iscsi.c

@@ -290,7 +290,8 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
     }
 }
 
-static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
+static void coroutine_fn
+iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
 {
     *iTask = (struct IscsiTask) {
         .co         = qemu_coroutine_self(),
@@ -2065,7 +2066,7 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
     uint64_t max_xfer_len = iscsilun->use_16_for_rw ? 0xffffffff : 0xffff;
     unsigned int block_size = MAX(BDRV_SECTOR_SIZE, iscsilun->block_size);
 
-    assert(iscsilun->block_size >= BDRV_SECTOR_SIZE || bs->sg);
+    assert(iscsilun->block_size >= BDRV_SECTOR_SIZE || bdrv_is_sg(bs));
 
     bs->bl.request_alignment = block_size;
 

block/linux-aio.c

@@ -461,7 +461,7 @@ LinuxAioState *laio_init(Error **errp)
     s = g_malloc0(sizeof(*s));
     rc = event_notifier_init(&s->e, false);
     if (rc < 0) {
-        error_setg_errno(errp, -rc, "failed to to initialize event notifier");
+        error_setg_errno(errp, -rc, "failed to initialize event notifier");
         goto out_free_state;
     }
 

block/mirror.c

@@ -894,6 +894,7 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
     BlockDriverState *bs = s->mirror_top_bs->backing->bs;
     BlockDriverState *target_bs = blk_bs(s->target);
     bool need_drain = true;
+    BlockDeviceIoStatus iostatus;
     int64_t length;
     int64_t target_length;
     BlockDriverInfo bdi;
@@ -1016,8 +1017,11 @@ static int coroutine_fn mirror_run(Job *job, Error **errp)
          * We do so every BLKOCK_JOB_SLICE_TIME nanoseconds, or when there is
          * an error, or when the source is clean, whichever comes first. */
         delta = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - s->last_pause_ns;
+        WITH_JOB_LOCK_GUARD() {
+            iostatus = s->common.iostatus;
+        }
         if (delta < BLOCK_JOB_SLICE_TIME &&
-            s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
+            iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
             if (s->in_flight >= MAX_IN_FLIGHT || s->buf_free_count == 0 ||
                 (cnt == 0 && s->in_flight > 0)) {
                 trace_mirror_yield(s, cnt, s->buf_free_count, s->in_flight);
@@ -1152,8 +1156,10 @@ static void mirror_complete(Job *job, Error **errp)
     s->should_complete = true;
 
     /* If the job is paused, it will be re-entered when it is resumed */
-    if (!job->paused) {
+    WITH_JOB_LOCK_GUARD() {
-        job_enter(job);
+        if (!job->paused) {
+            job_enter_cond_locked(job, NULL);
+        }
     }
 }
 
@@ -1173,8 +1179,11 @@ static bool mirror_drained_poll(BlockJob *job)
      * from one of our own drain sections, to avoid a deadlock waiting for
      * ourselves.
      */
-    if (!s->common.job.paused && !job_is_cancelled(&job->job) && !s->in_drain) {
+    WITH_JOB_LOCK_GUARD() {
-        return true;
+        if (!s->common.job.paused && !job_is_cancelled_locked(&job->job)
+            && !s->in_drain) {
+            return true;
+        }
     }
 
     return !!s->in_flight;

block/monitor/block-hmp-cmds.c

@@ -638,16 +638,16 @@ static void print_block_info(Monitor *mon, BlockInfo *info,
     assert(!info || !info->has_inserted || info->inserted == inserted);
 
     if (info && *info->device) {
-        monitor_printf(mon, "%s", info->device);
+        monitor_puts(mon, info->device);
         if (inserted && inserted->has_node_name) {
             monitor_printf(mon, " (%s)", inserted->node_name);
         }
     } else {
         assert(info || inserted);
-        monitor_printf(mon, "%s",
+        monitor_puts(mon,
-                       inserted && inserted->has_node_name ? inserted->node_name
+                     inserted && inserted->has_node_name ? inserted->node_name
-                       : info && info->has_qdev ? info->qdev
+                     : info && info->has_qdev ? info->qdev
-                       : "<anonymous>");
+                     : "<anonymous>");
     }
 
     if (inserted) {

block/nbd.c

@@ -983,11 +983,12 @@ static void nbd_iter_request_error(NBDReplyChunkIter *iter, int ret)
  * nbd_reply_chunk_iter_receive
  * The pointer stored in @payload requires g_free() to free it.
  */
-static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s,
+static bool coroutine_fn nbd_reply_chunk_iter_receive(BDRVNBDState *s,
-                                         NBDReplyChunkIter *iter,
+                                                      NBDReplyChunkIter *iter,
-                                         uint64_t handle,
+                                                      uint64_t handle,
-                                         QEMUIOVector *qiov, NBDReply *reply,
+                                                      QEMUIOVector *qiov,
-                                         void **payload)
+                                                      NBDReply *reply,
+                                                      void **payload)
 {
     int ret, request_ret;
     NBDReply local_reply;

block/nfs.c

@@ -223,7 +223,7 @@ static void nfs_process_write(void *arg)
     qemu_mutex_unlock(&client->mutex);
 }
 
-static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
+static void coroutine_fn nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
 {
     *task = (NFSRPC) {
         .co             = qemu_coroutine_self(),

block/nvme.c

@@ -293,34 +293,42 @@ static void nvme_kick(NVMeQueuePair *q)
     q->need_kick = 0;
 }
 
-/* Find a free request element if any, otherwise:
+static NVMeRequest *nvme_get_free_req_nofail_locked(NVMeQueuePair *q)
- * a) if in coroutine context, try to wait for one to become available;
- * b) if not in coroutine, return NULL;
- */
-static NVMeRequest *nvme_get_free_req(NVMeQueuePair *q)
 {
     NVMeRequest *req;
 
-    qemu_mutex_lock(&q->lock);
-
-    while (q->free_req_head == -1) {
-        if (qemu_in_coroutine()) {
-            trace_nvme_free_req_queue_wait(q->s, q->index);
-            qemu_co_queue_wait(&q->free_req_queue, &q->lock);
-        } else {
-            qemu_mutex_unlock(&q->lock);
-            return NULL;
-        }
-    }
-
     req = &q->reqs[q->free_req_head];
     q->free_req_head = req->free_req_next;
     req->free_req_next = -1;
-
-    qemu_mutex_unlock(&q->lock);
     return req;
 }
 
+/* Return a free request element if any, otherwise return NULL.  */
+static NVMeRequest *nvme_get_free_req_nowait(NVMeQueuePair *q)
+{
+    QEMU_LOCK_GUARD(&q->lock);
+    if (q->free_req_head == -1) {
+        return NULL;
+    }
+    return nvme_get_free_req_nofail_locked(q);
+}
+
+/*
+ * Wait for a free request to become available if necessary, then
+ * return it.
+ */
+static coroutine_fn NVMeRequest *nvme_get_free_req(NVMeQueuePair *q)
+{
+    QEMU_LOCK_GUARD(&q->lock);
+
+    while (q->free_req_head == -1) {
+        trace_nvme_free_req_queue_wait(q->s, q->index);
+        qemu_co_queue_wait(&q->free_req_queue, &q->lock);
+    }
+
+    return nvme_get_free_req_nofail_locked(q);
+}
+
 /* With q->lock */
 static void nvme_put_free_req_locked(NVMeQueuePair *q, NVMeRequest *req)
 {
@@ -506,7 +514,7 @@ static int nvme_admin_cmd_sync(BlockDriverState *bs, NvmeCmd *cmd)
     AioContext *aio_context = bdrv_get_aio_context(bs);
     NVMeRequest *req;
     int ret = -EINPROGRESS;
-    req = nvme_get_free_req(q);
+    req = nvme_get_free_req_nowait(q);
     if (!req) {
         return -EBUSY;
     }
@@ -1234,8 +1242,10 @@ static inline bool nvme_qiov_aligned(BlockDriverState *bs,
     return true;
 }
 
-static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
+static coroutine_fn int nvme_co_prw(BlockDriverState *bs,
-                       QEMUIOVector *qiov, bool is_write, int flags)
+                                    uint64_t offset, uint64_t bytes,
+                                    QEMUIOVector *qiov, bool is_write,
+                                    int flags)
 {
     BDRVNVMeState *s = bs->opaque;
     int r;

block/parallels.c

@@ -165,8 +165,9 @@ static int64_t block_status(BDRVParallelsState *s, int64_t sector_num,
     return start_off;
 }
 
-static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
+static coroutine_fn int64_t allocate_clusters(BlockDriverState *bs,
-                                 int nb_sectors, int *pnum)
+                                              int64_t sector_num,
+                                              int nb_sectors, int *pnum)
 {
     int ret = 0;
     BDRVParallelsState *s = bs->opaque;
@@ -241,8 +242,8 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
             return ret;
         }
 
-        ret = bdrv_co_pwritev(bs->file, s->data_end * BDRV_SECTOR_SIZE,
+        ret = bdrv_co_pwrite(bs->file, s->data_end * BDRV_SECTOR_SIZE,
-                              nb_cow_bytes, buf, 0);
+                             nb_cow_bytes, buf, 0);
         qemu_vfree(buf);
         if (ret < 0) {
             return ret;

block/qcow2-bitmap.c

@@ -787,10 +787,10 @@ static int bitmap_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list,
         }
     }
 
-    /* Actually, even in in-place case ignoring QCOW2_OL_BITMAP_DIRECTORY is not
+    /* Actually, even in the in-place case ignoring QCOW2_OL_BITMAP_DIRECTORY
-     * necessary, because we drop QCOW2_AUTOCLEAR_BITMAPS when updating bitmap
+     * is not necessary, because we drop QCOW2_AUTOCLEAR_BITMAPS when updating
-     * directory in-place (actually, turn-off the extension), which is checked
+     * bitmap directory in-place (actually, turn-off the extension), which is
-     * in qcow2_check_metadata_overlap() */
+     * checked in qcow2_check_metadata_overlap() */
     ret = qcow2_pre_write_overlap_check(
             bs, in_place ? QCOW2_OL_BITMAP_DIRECTORY : 0, dir_offset, dir_size,
             false);
@@ -1208,7 +1208,7 @@ int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp)
         }
     }
 
-    g_slist_foreach(ro_dirty_bitmaps, set_readonly_helper, false);
+    g_slist_foreach(ro_dirty_bitmaps, set_readonly_helper, (gpointer)false);
     ret = 0;
 
 out:

block/qcow2-cluster.c

@@ -884,7 +884,7 @@ int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
     return 0;
 }
 
-static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
+static int coroutine_fn perform_cow(BlockDriverState *bs, QCowL2Meta *m)
 {
     BDRVQcow2State *s = bs->opaque;
     Qcow2COWRegion *start = &m->cow_start;
@@ -1024,7 +1024,8 @@ fail:
     return ret;
 }
 
-int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
+int coroutine_fn qcow2_alloc_cluster_link_l2(BlockDriverState *bs,
+                                             QCowL2Meta *m)
 {
     BDRVQcow2State *s = bs->opaque;
     int i, j = 0, l2_index, ret;
@@ -1397,8 +1398,9 @@ static int count_single_write_clusters(BlockDriverState *bs, int nb_clusters,
  *           information on cluster allocation may be invalid now. The caller
  *           must start over anyway, so consider *cur_bytes undefined.
  */
-static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
+static int coroutine_fn handle_dependencies(BlockDriverState *bs,
-    uint64_t *cur_bytes, QCowL2Meta **m)
+                                            uint64_t guest_offset,
+                                            uint64_t *cur_bytes, QCowL2Meta **m)
 {
     BDRVQcow2State *s = bs->opaque;
     QCowL2Meta *old_alloc;
@@ -1772,9 +1774,10 @@ out:
  *
  * Return 0 on success and -errno in error cases
  */
-int qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset,
+int coroutine_fn qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset,
-                            unsigned int *bytes, uint64_t *host_offset,
+                                         unsigned int *bytes,
-                            QCowL2Meta **m)
+                                         uint64_t *host_offset,
+                                         QCowL2Meta **m)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t start, remaining;
@@ -2105,8 +2108,8 @@ out:
     return ret;
 }
 
-int qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset,
+int coroutine_fn qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset,
-                             uint64_t bytes, int flags)
+                                          uint64_t bytes, int flags)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t end_offset = offset + bytes;

block/qcow2-refcount.c

@@ -1206,7 +1206,7 @@ void qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry,
     }
 }
 
-int coroutine_fn qcow2_write_caches(BlockDriverState *bs)
+int qcow2_write_caches(BlockDriverState *bs)
 {
     BDRVQcow2State *s = bs->opaque;
     int ret;
@@ -1226,7 +1226,7 @@ int coroutine_fn qcow2_write_caches(BlockDriverState *bs)
     return 0;
 }
 
-int coroutine_fn qcow2_flush_caches(BlockDriverState *bs)
+int qcow2_flush_caches(BlockDriverState *bs)
 {
     int ret = qcow2_write_caches(bs);
     if (ret < 0) {
@@ -3706,7 +3706,7 @@ int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size)
     return -EIO;
 }
 
-int qcow2_detect_metadata_preallocation(BlockDriverState *bs)
+int coroutine_fn qcow2_detect_metadata_preallocation(BlockDriverState *bs)
 {
     BDRVQcow2State *s = bs->opaque;
     int64_t i, end_cluster, cluster_count = 0, threshold;

block/qcow2.c

@@ -275,6 +275,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
                 if (ret < 0) {
                     error_setg_errno(errp, -ret, "ERROR: ext_feature_table: "
                                      "Could not read table");
+                    g_free(feature_table);
                     return ret;
                 }
 
@@ -1696,16 +1697,27 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
             ret = -EINVAL;
             goto fail;
         }
+
+        s->image_backing_file = g_malloc(len + 1);
         ret = bdrv_pread(bs->file, header.backing_file_offset, len,
-                         bs->auto_backing_file, 0);
+                         s->image_backing_file, 0);
         if (ret < 0) {
             error_setg_errno(errp, -ret, "Could not read backing file name");
             goto fail;
         }
-        bs->auto_backing_file[len] = '\0';
+        s->image_backing_file[len] = '\0';
-        pstrcpy(bs->backing_file, sizeof(bs->backing_file),
+
-                bs->auto_backing_file);
+        /*
-        s->image_backing_file = g_strdup(bs->auto_backing_file);
+         * Update only when something has changed.  This function is called by
+         * qcow2_co_invalidate_cache(), and we do not want to reset
+         * auto_backing_file unless necessary.
+         */
+        if (!g_str_equal(s->image_backing_file, bs->backing_file)) {
+            pstrcpy(bs->backing_file, sizeof(bs->backing_file),
+                    s->image_backing_file);
+            pstrcpy(bs->auto_backing_file, sizeof(bs->auto_backing_file),
+                    s->image_backing_file);
+        }
     }
 
     /*
@@ -2436,7 +2448,7 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
  * Return 1 if the COW regions read as zeroes, 0 if not, < 0 on error.
  * Note that returning 0 does not guarantee non-zero data.
  */
-static int is_zero_cow(BlockDriverState *bs, QCowL2Meta *m)
+static int coroutine_fn is_zero_cow(BlockDriverState *bs, QCowL2Meta *m)
 {
     /*
      * This check is designed for optimization shortcut so it must be
@@ -2454,7 +2466,8 @@ static int is_zero_cow(BlockDriverState *bs, QCowL2Meta *m)
                                 m->cow_end.nb_bytes);
 }
 
-static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta)
+static int coroutine_fn handle_alloc_space(BlockDriverState *bs,
+                                           QCowL2Meta *l2meta)
 {
     BDRVQcow2State *s = bs->opaque;
     QCowL2Meta *m;

block/qcow2.h

@@ -874,8 +874,8 @@ void qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry,
 int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t l1_table_offset, int l1_size, int addend);
 
-int coroutine_fn qcow2_flush_caches(BlockDriverState *bs);
+int qcow2_flush_caches(BlockDriverState *bs);
-int coroutine_fn qcow2_write_caches(BlockDriverState *bs);
+int qcow2_write_caches(BlockDriverState *bs);
 int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
                           BdrvCheckMode fix);
 
@@ -895,7 +895,7 @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
                                 void *cb_opaque, Error **errp);
 int qcow2_shrink_reftable(BlockDriverState *bs);
 int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size);
-int qcow2_detect_metadata_preallocation(BlockDriverState *bs);
+int coroutine_fn qcow2_detect_metadata_preallocation(BlockDriverState *bs);
 
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
@@ -908,9 +908,9 @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
 int qcow2_get_host_offset(BlockDriverState *bs, uint64_t offset,
                           unsigned int *bytes, uint64_t *host_offset,
                           QCow2SubclusterType *subcluster_type);
-int qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset,
+int coroutine_fn qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset,
-                            unsigned int *bytes, uint64_t *host_offset,
+                                         unsigned int *bytes,
-                            QCowL2Meta **m);
+                                         uint64_t *host_offset, QCowL2Meta **m);
 int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                           uint64_t offset,
                                           int compressed_size,
@@ -918,13 +918,14 @@ int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
 void qcow2_parse_compressed_l2_entry(BlockDriverState *bs, uint64_t l2_entry,
                                      uint64_t *coffset, int *csize);
 
-int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
+int coroutine_fn qcow2_alloc_cluster_link_l2(BlockDriverState *bs,
+                                             QCowL2Meta *m);
 void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset,
                           uint64_t bytes, enum qcow2_discard_type type,
                           bool full_discard);
-int qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset,
+int coroutine_fn qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset,
-                             uint64_t bytes, int flags);
+                                          uint64_t bytes, int flags);
 
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
                                BlockDriverAmendStatusCB *status_cb,

block/qed.c

@@ -254,7 +254,7 @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s)
     return l2_table;
 }
 
-static bool qed_plug_allocating_write_reqs(BDRVQEDState *s)
+static bool coroutine_fn qed_plug_allocating_write_reqs(BDRVQEDState *s)
 {
     qemu_co_mutex_lock(&s->table_lock);
 
@@ -273,7 +273,7 @@ static bool qed_plug_allocating_write_reqs(BDRVQEDState *s)
     return true;
 }
 
-static void qed_unplug_allocating_write_reqs(BDRVQEDState *s)
+static void coroutine_fn qed_unplug_allocating_write_reqs(BDRVQEDState *s)
 {
     qemu_co_mutex_lock(&s->table_lock);
     assert(s->allocating_write_reqs_plugged);
@@ -445,6 +445,8 @@ static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options,
     }
 
     if ((s->header.features & QED_F_BACKING_FILE)) {
+        g_autofree char *backing_file_str = NULL;
+
         if ((uint64_t)s->header.backing_filename_offset +
             s->header.backing_filename_size >
             s->header.cluster_size * s->header.header_size) {
@@ -452,16 +454,21 @@ static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options,
             return -EINVAL;
         }
 
+        backing_file_str = g_malloc(sizeof(bs->backing_file));
         ret = qed_read_string(bs->file, s->header.backing_filename_offset,
                               s->header.backing_filename_size,
-                              bs->auto_backing_file,
+                              backing_file_str, sizeof(bs->backing_file));
-                              sizeof(bs->auto_backing_file));
         if (ret < 0) {
             error_setg(errp, "Failed to read backing filename");
             return ret;
         }
-        pstrcpy(bs->backing_file, sizeof(bs->backing_file),
+
-                bs->auto_backing_file);
+        if (!g_str_equal(backing_file_str, bs->backing_file)) {
+            pstrcpy(bs->backing_file, sizeof(bs->backing_file),
+                    backing_file_str);
+            pstrcpy(bs->auto_backing_file, sizeof(bs->auto_backing_file),
+                    backing_file_str);
+        }
 
         if (s->header.features & QED_F_BACKING_FORMAT_NO_PROBE) {
             pstrcpy(bs->backing_format, sizeof(bs->backing_format), "raw");

block/quorum.c

@@ -161,11 +161,10 @@ static bool quorum_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b)
     return a->l == b->l;
 }
 
-static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs,
+static QuorumAIOCB *coroutine_fn quorum_aio_get(BlockDriverState *bs,
-                                   QEMUIOVector *qiov,
+                                                QEMUIOVector *qiov,
-                                   uint64_t offset,
+                                                uint64_t offset, uint64_t bytes,
-                                   uint64_t bytes,
+                                                int flags)
-                                   int flags)
 {
     BDRVQuorumState *s = bs->opaque;
     QuorumAIOCB *acb = g_new(QuorumAIOCB, 1);
@@ -233,8 +232,6 @@ static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
     return false;
 }
 
-static int read_fifo_child(QuorumAIOCB *acb);
-
 static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
 {
     int i;
@@ -273,7 +270,7 @@ static void quorum_report_bad_versions(BDRVQuorumState *s,
     }
 }
 
-static void quorum_rewrite_entry(void *opaque)
+static void coroutine_fn quorum_rewrite_entry(void *opaque)
 {
     QuorumCo *co = opaque;
     QuorumAIOCB *acb = co->acb;
@@ -574,7 +571,7 @@ free_exit:
     quorum_free_vote_list(&acb->votes);
 }
 
-static void read_quorum_children_entry(void *opaque)
+static void coroutine_fn read_quorum_children_entry(void *opaque)
 {
     QuorumCo *co = opaque;
     QuorumAIOCB *acb = co->acb;
@@ -602,7 +599,7 @@ static void read_quorum_children_entry(void *opaque)
     }
 }
 
-static int read_quorum_children(QuorumAIOCB *acb)
+static int coroutine_fn read_quorum_children(QuorumAIOCB *acb)
 {
     BDRVQuorumState *s = acb->bs->opaque;
     int i;
@@ -643,7 +640,7 @@ static int read_quorum_children(QuorumAIOCB *acb)
     return acb->vote_ret;
 }
 
-static int read_fifo_child(QuorumAIOCB *acb)
+static int coroutine_fn read_fifo_child(QuorumAIOCB *acb)
 {
     BDRVQuorumState *s = acb->bs->opaque;
     int n, ret;
@@ -664,8 +661,10 @@ static int read_fifo_child(QuorumAIOCB *acb)
     return ret;
 }
 
-static int quorum_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
+static int coroutine_fn quorum_co_preadv(BlockDriverState *bs,
-                            QEMUIOVector *qiov, BdrvRequestFlags flags)
+                                         int64_t offset, int64_t bytes,
+                                         QEMUIOVector *qiov,
+                                         BdrvRequestFlags flags)
 {
     BDRVQuorumState *s = bs->opaque;
     QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes, flags);
@@ -684,7 +683,7 @@ static int quorum_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
     return ret;
 }
 
-static void write_quorum_entry(void *opaque)
+static void coroutine_fn write_quorum_entry(void *opaque)
 {
     QuorumCo *co = opaque;
     QuorumAIOCB *acb = co->acb;
@@ -715,9 +714,9 @@ static void write_quorum_entry(void *opaque)
     }
 }
 
-static int quorum_co_pwritev(BlockDriverState *bs, int64_t offset,
+static int coroutine_fn quorum_co_pwritev(BlockDriverState *bs, int64_t offset,
-                             int64_t bytes, QEMUIOVector *qiov,
+                                          int64_t bytes, QEMUIOVector *qiov,
-                             BdrvRequestFlags flags)
+                                          BdrvRequestFlags flags)
 {
     BDRVQuorumState *s = bs->opaque;
     QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes, flags);
@@ -746,8 +745,9 @@ static int quorum_co_pwritev(BlockDriverState *bs, int64_t offset,
     return ret;
 }
 
-static int quorum_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
+static int coroutine_fn quorum_co_pwrite_zeroes(BlockDriverState *bs,
-                                   int64_t bytes, BdrvRequestFlags flags)
+                                                int64_t offset, int64_t bytes,
+                                                BdrvRequestFlags flags)
 
 {
     return quorum_co_pwritev(bs, offset, bytes, NULL,

block/raw-format.c

@@ -411,7 +411,8 @@ static void raw_lock_medium(BlockDriverState *bs, bool locked)
     bdrv_lock_medium(bs->file->bs, locked);
 }
 
-static int raw_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+static int coroutine_fn raw_co_ioctl(BlockDriverState *bs,
+                                     unsigned long int req, void *buf)
 {
     BDRVRawState *s = bs->opaque;
     if (s->offset || s->has_size) {
@@ -463,7 +464,7 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    bs->sg = bs->file->bs->sg;
+    bs->sg = bdrv_is_sg(bs->file->bs);
     bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
         (BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
     bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
@@ -489,7 +490,7 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
 
-    if (bs->sg && (s->offset || s->has_size)) {
+    if (bdrv_is_sg(bs) && (s->offset || s->has_size)) {
         error_setg(errp, "Cannot use offset/size with SCSI generic devices");
         return -EINVAL;
     }

block/replication.c

@@ -142,6 +142,7 @@ static void replication_close(BlockDriverState *bs)
 {
     BDRVReplicationState *s = bs->opaque;
     Job *commit_job;
+    GLOBAL_STATE_CODE();
 
     if (s->stage == BLOCK_REPLICATION_RUNNING) {
         replication_stop(s->rs, false, NULL);
@@ -726,7 +727,9 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
          * disk, secondary disk in backup_job_completed().
          */
         if (s->backup_job) {
+            aio_context_release(aio_context);
             job_cancel_sync(&s->backup_job->job, true);
+            aio_context_acquire(aio_context);
         }
 
         if (!failover) {

block/throttle.c

@@ -162,7 +162,7 @@ static int coroutine_fn throttle_co_pwritev_compressed(BlockDriverState *bs,
                                BDRV_REQ_WRITE_COMPRESSED);
 }
 
-static int throttle_co_flush(BlockDriverState *bs)
+static int coroutine_fn throttle_co_flush(BlockDriverState *bs)
 {
     return bdrv_co_flush(bs->file->bs);
 }

block/vmdk.c

@@ -1787,10 +1787,11 @@ static int coroutine_fn vmdk_co_block_status(BlockDriverState *bs,
     return ret;
 }
 
-static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
+static int coroutine_fn
-                            int64_t offset_in_cluster, QEMUIOVector *qiov,
+vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
-                            uint64_t qiov_offset, uint64_t n_bytes,
+                  int64_t offset_in_cluster, QEMUIOVector *qiov,
-                            uint64_t offset)
+                  uint64_t qiov_offset, uint64_t n_bytes,
+                  uint64_t offset)
 {
     int ret;
     VmdkGrainMarker *data = NULL;
@@ -1868,9 +1869,10 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
     return ret;
 }
 
-static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset,
+static int coroutine_fn
-                            int64_t offset_in_cluster, QEMUIOVector *qiov,
+vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset,
-                            int bytes)
+                 int64_t offset_in_cluster, QEMUIOVector *qiov,
+                 int bytes)
 {
     int ret;
     int cluster_bytes, buf_bytes;
@@ -2015,9 +2017,9 @@ fail:
  *
  * Returns: error code with 0 for success.
  */
-static int vmdk_pwritev(BlockDriverState *bs, uint64_t offset,
+static int coroutine_fn vmdk_pwritev(BlockDriverState *bs, uint64_t offset,
-                       uint64_t bytes, QEMUIOVector *qiov,
+                                     uint64_t bytes, QEMUIOVector *qiov,
-                       bool zeroed, bool zero_dry_run)
+                                     bool zeroed, bool zero_dry_run)
 {
     BDRVVmdkState *s = bs->opaque;
     VmdkExtent *extent = NULL;

blockdev.c

@@ -150,14 +150,12 @@ void blockdev_mark_auto_del(BlockBackend *blk)
         return;
     }
 
-    for (job = block_job_next(NULL); job; job = block_job_next(job)) {
+    JOB_LOCK_GUARD();
+
+    for (job = block_job_next_locked(NULL); job;
+         job = block_job_next_locked(job)) {
         if (block_job_has_bdrv(job, blk_bs(blk))) {
-            AioContext *aio_context = job->job.aio_context;
+            job_cancel_locked(&job->job, false);
-            aio_context_acquire(aio_context);
-
-            job_cancel(&job->job, false);
-
-            aio_context_release(aio_context);
         }
     }
 
@@ -455,6 +453,17 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
     }
 }
 
+static OnOffAuto account_get_opt(QemuOpts *opts, const char *name)
+{
+    if (!qemu_opt_find(opts, name)) {
+        return ON_OFF_AUTO_AUTO;
+    }
+    if (qemu_opt_get_bool(opts, name, true)) {
+        return ON_OFF_AUTO_ON;
+    }
+    return ON_OFF_AUTO_OFF;
+}
+
 /* Takes the ownership of bs_opts */
 static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
                                    Error **errp)
@@ -462,7 +471,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     const char *buf;
     int bdrv_flags = 0;
     int on_read_error, on_write_error;
-    bool account_invalid, account_failed;
+    OnOffAuto account_invalid, account_failed;
     bool writethrough, read_only;
     BlockBackend *blk;
     BlockDriverState *bs;
@@ -496,8 +505,8 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     /* extract parameters */
     snapshot = qemu_opt_get_bool(opts, "snapshot", 0);
 
-    account_invalid = qemu_opt_get_bool(opts, "stats-account-invalid", true);
+    account_invalid = account_get_opt(opts, "stats-account-invalid");
-    account_failed = qemu_opt_get_bool(opts, "stats-account-failed", true);
+    account_failed = account_get_opt(opts, "stats-account-failed");
 
     writethrough = !qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, true);
 
@@ -1833,14 +1842,7 @@ static void drive_backup_abort(BlkActionState *common)
     DriveBackupState *state = DO_UPCAST(DriveBackupState, common, common);
 
     if (state->job) {
-        AioContext *aio_context;
-
-        aio_context = bdrv_get_aio_context(state->bs);
-        aio_context_acquire(aio_context);
-
         job_cancel_sync(&state->job->job, true);
-
-        aio_context_release(aio_context);
     }
 }
 
@@ -1934,14 +1936,7 @@ static void blockdev_backup_abort(BlkActionState *common)
     BlockdevBackupState *state = DO_UPCAST(BlockdevBackupState, common, common);
 
     if (state->job) {
-        AioContext *aio_context;
-
-        aio_context = bdrv_get_aio_context(state->bs);
-        aio_context_acquire(aio_context);
-
         job_cancel_sync(&state->job->job, true);
-
-        aio_context_release(aio_context);
     }
 }
 
@@ -3302,17 +3297,16 @@ out:
     aio_context_release(aio_context);
 }
 
-/* Get a block job using its ID and acquire its AioContext */
+/*
-static BlockJob *find_block_job(const char *id, AioContext **aio_context,
+ * Get a block job using its ID. Called with job_mutex held.
-                                Error **errp)
+ */
+static BlockJob *find_block_job_locked(const char *id, Error **errp)
 {
     BlockJob *job;
 
     assert(id != NULL);
 
-    *aio_context = NULL;
+    job = block_job_get_locked(id);
-
-    job = block_job_get(id);
 
     if (!job) {
         error_set(errp, ERROR_CLASS_DEVICE_NOT_ACTIVE,
@@ -3320,30 +3314,30 @@ static BlockJob *find_block_job(const char *id, AioContext **aio_context,
         return NULL;
     }
 
-    *aio_context = block_job_get_aio_context(job);
-    aio_context_acquire(*aio_context);
-
     return job;
 }
 
 void qmp_block_job_set_speed(const char *device, int64_t speed, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *job;
-    BlockJob *job = find_block_job(device, &aio_context, errp);
+
+    JOB_LOCK_GUARD();
+    job = find_block_job_locked(device, errp);
 
     if (!job) {
         return;
     }
 
-    block_job_set_speed(job, speed, errp);
+    block_job_set_speed_locked(job, speed, errp);
-    aio_context_release(aio_context);
 }
 
 void qmp_block_job_cancel(const char *device,
                           bool has_force, bool force, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *job;
-    BlockJob *job = find_block_job(device, &aio_context, errp);
+
+    JOB_LOCK_GUARD();
+    job = find_block_job_locked(device, errp);
 
     if (!job) {
         return;
@@ -3353,97 +3347,94 @@ void qmp_block_job_cancel(const char *device,
         force = false;
     }
 
-    if (job_user_paused(&job->job) && !force) {
+    if (job_user_paused_locked(&job->job) && !force) {
         error_setg(errp, "The block job for device '%s' is currently paused",
                    device);
-        goto out;
+        return;
     }
 
     trace_qmp_block_job_cancel(job);
-    job_user_cancel(&job->job, force, errp);
+    job_user_cancel_locked(&job->job, force, errp);
-out:
-    aio_context_release(aio_context);
 }
 
 void qmp_block_job_pause(const char *device, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *job;
-    BlockJob *job = find_block_job(device, &aio_context, errp);
+
+    JOB_LOCK_GUARD();
+    job = find_block_job_locked(device, errp);
 
     if (!job) {
         return;
     }
 
     trace_qmp_block_job_pause(job);
-    job_user_pause(&job->job, errp);
+    job_user_pause_locked(&job->job, errp);
-    aio_context_release(aio_context);
 }
 
 void qmp_block_job_resume(const char *device, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *job;
-    BlockJob *job = find_block_job(device, &aio_context, errp);
+
+    JOB_LOCK_GUARD();
+    job = find_block_job_locked(device, errp);
 
     if (!job) {
         return;
     }
 
     trace_qmp_block_job_resume(job);
-    job_user_resume(&job->job, errp);
+    job_user_resume_locked(&job->job, errp);
-    aio_context_release(aio_context);
 }
 
 void qmp_block_job_complete(const char *device, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *job;
-    BlockJob *job = find_block_job(device, &aio_context, errp);
+
+    JOB_LOCK_GUARD();
+    job = find_block_job_locked(device, errp);
 
     if (!job) {
         return;
     }
 
     trace_qmp_block_job_complete(job);
-    job_complete(&job->job, errp);
+    job_complete_locked(&job->job, errp);
-    aio_context_release(aio_context);
 }
 
 void qmp_block_job_finalize(const char *id, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *job;
-    BlockJob *job = find_block_job(id, &aio_context, errp);
+
+    JOB_LOCK_GUARD();
+    job = find_block_job_locked(id, errp);
 
     if (!job) {
         return;
     }
 
     trace_qmp_block_job_finalize(job);
-    job_ref(&job->job);
+    job_ref_locked(&job->job);
-    job_finalize(&job->job, errp);
+    job_finalize_locked(&job->job, errp);
 
-    /*
+    job_unref_locked(&job->job);
-     * Job's context might have changed via job_finalize (and job_txn_apply
-     * automatically acquires the new one), so make sure we release the correct
-     * one.
-     */
-    aio_context = block_job_get_aio_context(job);
-    job_unref(&job->job);
-    aio_context_release(aio_context);
 }
 
 void qmp_block_job_dismiss(const char *id, Error **errp)
 {
-    AioContext *aio_context;
+    BlockJob *bjob;
-    BlockJob *bjob = find_block_job(id, &aio_context, errp);
     Job *job;
 
+    JOB_LOCK_GUARD();
+    bjob = find_block_job_locked(id, errp);
+
     if (!bjob) {
         return;
     }
 
     trace_qmp_block_job_dismiss(bjob);
     job = &bjob->job;
-    job_dismiss(&job, errp);
+    job_dismiss_locked(&job, errp);
-    aio_context_release(aio_context);
 }
 
 void qmp_change_backing_file(const char *device,
@@ -3720,17 +3711,16 @@ BlockJobInfoList *qmp_query_block_jobs(Error **errp)
     BlockJobInfoList *head = NULL, **tail = &head;
     BlockJob *job;
 
-    for (job = block_job_next(NULL); job; job = block_job_next(job)) {
+    JOB_LOCK_GUARD();
+
+    for (job = block_job_next_locked(NULL); job;
+         job = block_job_next_locked(job)) {
         BlockJobInfo *value;
-        AioContext *aio_context;
 
         if (block_job_is_internal(job)) {
             continue;
         }
-        aio_context = block_job_get_aio_context(job);
+        value = block_job_query_locked(job, errp);
-        aio_context_acquire(aio_context);
-        value = block_job_query(job, errp);
-        aio_context_release(aio_context);
         if (!value) {
             qapi_free_BlockJobInfoList(head);
             return NULL;

blockjob.c

@@ -36,21 +36,6 @@
 #include "qemu/main-loop.h"
 #include "qemu/timer.h"
 
-/*
- * The block job API is composed of two categories of functions.
- *
- * The first includes functions used by the monitor.  The monitor is
- * peculiar in that it accesses the block job list with block_job_get, and
- * therefore needs consistency across block_job_get and the actual operation
- * (e.g. block_job_set_speed).  The consistency is achieved with
- * aio_context_acquire/release.  These functions are declared in blockjob.h.
- *
- * The second includes functions used by the block job drivers and sometimes
- * by the core block layer.  These do not care about locking, because the
- * whole coroutine runs under the AioContext lock, and are declared in
- * blockjob_int.h.
- */
-
 static bool is_block_job(Job *job)
 {
     return job_type(job) == JOB_TYPE_BACKUP ||
@@ -59,21 +44,21 @@ static bool is_block_job(Job *job)
            job_type(job) == JOB_TYPE_STREAM;
 }
 
-BlockJob *block_job_next(BlockJob *bjob)
+BlockJob *block_job_next_locked(BlockJob *bjob)
 {
     Job *job = bjob ? &bjob->job : NULL;
     GLOBAL_STATE_CODE();
 
     do {
-        job = job_next(job);
+        job = job_next_locked(job);
     } while (job && !is_block_job(job));
 
     return job ? container_of(job, BlockJob, job) : NULL;
 }
 
-BlockJob *block_job_get(const char *id)
+BlockJob *block_job_get_locked(const char *id)
 {
-    Job *job = job_get(id);
+    Job *job = job_get_locked(id);
     GLOBAL_STATE_CODE();
 
     if (job && is_block_job(job)) {
@@ -83,6 +68,12 @@ BlockJob *block_job_get(const char *id)
     }
 }
 
+BlockJob *block_job_get(const char *id)
+{
+    JOB_LOCK_GUARD();
+    return block_job_get_locked(id);
+}
+
 void block_job_free(Job *job)
 {
     BlockJob *bjob = container_of(job, BlockJob, job);
@@ -114,8 +105,10 @@ static bool child_job_drained_poll(BdrvChild *c)
     /* An inactive or completed job doesn't have any pending requests. Jobs
      * with !job->busy are either already paused or have a pause point after
      * being reentered, so no job driver code will run before they pause. */
-    if (!job->busy || job_is_completed(job)) {
+    WITH_JOB_LOCK_GUARD() {
-        return false;
+        if (!job->busy || job_is_completed_locked(job)) {
+            return false;
+        }
     }
 
     /* Otherwise, assume that it isn't fully stopped yet, but allow the job to
@@ -163,12 +156,13 @@ static void child_job_set_aio_ctx(BdrvChild *c, AioContext *ctx,
         bdrv_set_aio_context_ignore(sibling->bs, ctx, ignore);
     }
 
-    job->job.aio_context = ctx;
+    job_set_aio_context(&job->job, ctx);
 }
 
 static AioContext *child_job_get_parent_aio_context(BdrvChild *c)
 {
     BlockJob *job = c->opaque;
+    GLOBAL_STATE_CODE();
 
     return job->job.aio_context;
 }
@@ -250,7 +244,8 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs,
     return 0;
 }
 
-static void block_job_on_idle(Notifier *n, void *opaque)
+/* Called with job_mutex lock held. */
+static void block_job_on_idle_locked(Notifier *n, void *opaque)
 {
     aio_wait_kick();
 }
@@ -271,14 +266,14 @@ static bool job_timer_pending(Job *job)
     return timer_pending(&job->sleep_timer);
 }
 
-bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
+bool block_job_set_speed_locked(BlockJob *job, int64_t speed, Error **errp)
 {
     const BlockJobDriver *drv = block_job_driver(job);
     int64_t old_speed = job->speed;
 
     GLOBAL_STATE_CODE();
 
-    if (job_apply_verb(&job->job, JOB_VERB_SET_SPEED, errp) < 0) {
+    if (job_apply_verb_locked(&job->job, JOB_VERB_SET_SPEED, errp) < 0) {
         return false;
     }
     if (speed < 0) {
@@ -292,7 +287,9 @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
     job->speed = speed;
 
     if (drv->set_speed) {
+        job_unlock();
         drv->set_speed(job, speed);
+        job_lock();
     }
 
     if (speed && speed <= old_speed) {
@@ -300,18 +297,24 @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
     }
 
     /* kick only if a timer is pending */
-    job_enter_cond(&job->job, job_timer_pending);
+    job_enter_cond_locked(&job->job, job_timer_pending);
 
     return true;
 }
 
+static bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
+{
+    JOB_LOCK_GUARD();
+    return block_job_set_speed_locked(job, speed, errp);
+}
+
 int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n)
 {
     IO_CODE();
     return ratelimit_calculate_delay(&job->limit, n);
 }
 
-BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
+BlockJobInfo *block_job_query_locked(BlockJob *job, Error **errp)
 {
     BlockJobInfo *info;
     uint64_t progress_current, progress_total;
@@ -329,13 +332,13 @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
     info = g_new0(BlockJobInfo, 1);
     info->type      = g_strdup(job_type_str(&job->job));
     info->device    = g_strdup(job->job.id);
-    info->busy      = qatomic_read(&job->job.busy);
+    info->busy      = job->job.busy;
     info->paused    = job->job.pause_count > 0;
     info->offset    = progress_current;
     info->len       = progress_total;
     info->speed     = job->speed;
     info->io_status = job->iostatus;
-    info->ready     = job_is_ready(&job->job),
+    info->ready     = job_is_ready_locked(&job->job),
     info->status    = job->job.status;
     info->auto_finalize = job->job.auto_finalize;
     info->auto_dismiss  = job->job.auto_dismiss;
@@ -348,7 +351,8 @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
     return info;
 }
 
-static void block_job_iostatus_set_err(BlockJob *job, int error)
+/* Called with job lock held */
+static void block_job_iostatus_set_err_locked(BlockJob *job, int error)
 {
     if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
         job->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
@@ -356,7 +360,8 @@ static void block_job_iostatus_set_err(BlockJob *job, int error)
     }
 }
 
-static void block_job_event_cancelled(Notifier *n, void *opaque)
+/* Called with job_mutex lock held. */
+static void block_job_event_cancelled_locked(Notifier *n, void *opaque)
 {
     BlockJob *job = opaque;
     uint64_t progress_current, progress_total;
@@ -375,7 +380,8 @@ static void block_job_event_cancelled(Notifier *n, void *opaque)
                                         job->speed);
 }
 
-static void block_job_event_completed(Notifier *n, void *opaque)
+/* Called with job_mutex lock held. */
+static void block_job_event_completed_locked(Notifier *n, void *opaque)
 {
     BlockJob *job = opaque;
     const char *msg = NULL;
@@ -401,7 +407,8 @@ static void block_job_event_completed(Notifier *n, void *opaque)
                                         msg);
 }
 
-static void block_job_event_pending(Notifier *n, void *opaque)
+/* Called with job_mutex lock held. */
+static void block_job_event_pending_locked(Notifier *n, void *opaque)
 {
     BlockJob *job = opaque;
 
@@ -413,7 +420,8 @@ static void block_job_event_pending(Notifier *n, void *opaque)
                                       job->job.id);
 }
 
-static void block_job_event_ready(Notifier *n, void *opaque)
+/* Called with job_mutex lock held. */
+static void block_job_event_ready_locked(Notifier *n, void *opaque)
 {
     BlockJob *job = opaque;
     uint64_t progress_current, progress_total;
@@ -433,11 +441,6 @@ static void block_job_event_ready(Notifier *n, void *opaque)
 }
 
 
-/*
- * API for block job drivers and the block layer.  These functions are
- * declared in blockjob_int.h.
- */
-
 void *block_job_create(const char *job_id, const BlockJobDriver *driver,
                        JobTxn *txn, BlockDriverState *bs, uint64_t perm,
                        uint64_t shared_perm, int64_t speed, int flags,
@@ -463,19 +466,21 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
 
     ratelimit_init(&job->limit);
 
-    job->finalize_cancelled_notifier.notify = block_job_event_cancelled;
+    job->finalize_cancelled_notifier.notify = block_job_event_cancelled_locked;
-    job->finalize_completed_notifier.notify = block_job_event_completed;
+    job->finalize_completed_notifier.notify = block_job_event_completed_locked;
-    job->pending_notifier.notify = block_job_event_pending;
+    job->pending_notifier.notify = block_job_event_pending_locked;
-    job->ready_notifier.notify = block_job_event_ready;
+    job->ready_notifier.notify = block_job_event_ready_locked;
-    job->idle_notifier.notify = block_job_on_idle;
+    job->idle_notifier.notify = block_job_on_idle_locked;
 
-    notifier_list_add(&job->job.on_finalize_cancelled,
+    WITH_JOB_LOCK_GUARD() {
-                      &job->finalize_cancelled_notifier);
+        notifier_list_add(&job->job.on_finalize_cancelled,
-    notifier_list_add(&job->job.on_finalize_completed,
+                          &job->finalize_cancelled_notifier);
-                      &job->finalize_completed_notifier);
+        notifier_list_add(&job->job.on_finalize_completed,
-    notifier_list_add(&job->job.on_pending, &job->pending_notifier);
+                          &job->finalize_completed_notifier);
-    notifier_list_add(&job->job.on_ready, &job->ready_notifier);
+        notifier_list_add(&job->job.on_pending, &job->pending_notifier);
-    notifier_list_add(&job->job.on_idle, &job->idle_notifier);
+        notifier_list_add(&job->job.on_ready, &job->ready_notifier);
+        notifier_list_add(&job->job.on_idle, &job->idle_notifier);
+    }
 
     error_setg(&job->blocker, "block device is in use by block job: %s",
                job_type_str(&job->job));
@@ -498,7 +503,7 @@ fail:
     return NULL;
 }
 
-void block_job_iostatus_reset(BlockJob *job)
+void block_job_iostatus_reset_locked(BlockJob *job)
 {
     GLOBAL_STATE_CODE();
     if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
@@ -508,6 +513,12 @@ void block_job_iostatus_reset(BlockJob *job)
     job->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
 }
 
+static void block_job_iostatus_reset(BlockJob *job)
+{
+    JOB_LOCK_GUARD();
+    block_job_iostatus_reset_locked(job);
+}
+
 void block_job_user_resume(Job *job)
 {
     BlockJob *bjob = container_of(job, BlockJob, job);
@@ -546,12 +557,17 @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err,
                                         action);
     }
     if (action == BLOCK_ERROR_ACTION_STOP) {
-        if (!job->job.user_paused) {
+        WITH_JOB_LOCK_GUARD() {
-            job_pause(&job->job);
+            if (!job->job.user_paused) {
-            /* make the pause user visible, which will be resumed from QMP. */
+                job_pause_locked(&job->job);
-            job->job.user_paused = true;
+                /*
+                 * make the pause user visible, which will be
+                 * resumed from QMP.
+                 */
+                job->job.user_paused = true;
+            }
+            block_job_iostatus_set_err_locked(job, error);
         }
-        block_job_iostatus_set_err(job, error);
     }
     return action;
 }

chardev/baum.c

@@ -87,6 +87,9 @@
 
 #define BUF_SIZE 256
 
+#define X_MAX   84
+#define Y_MAX   1
+
 struct BaumChardev {
     Chardev parent;
 
@@ -244,11 +247,11 @@ static int baum_deferred_init(BaumChardev *baum)
         brlapi_perror("baum: brlapi__getDisplaySize");
         return 0;
     }
-    if (baum->y > 1) {
+    if (baum->y > Y_MAX) {
-        baum->y = 1;
+        baum->y = Y_MAX;
     }
-    if (baum->x > 84) {
+    if (baum->x > X_MAX) {
-        baum->x = 84;
+        baum->x = X_MAX;
     }
 
     con = qemu_console_lookup_by_index(0);
@@ -296,7 +299,8 @@ static void baum_chr_accept_input(struct Chardev *chr)
 static void baum_write_packet(BaumChardev *baum, const uint8_t *buf, int len)
 {
     Chardev *chr = CHARDEV(baum);
-    uint8_t io_buf[1 + 2 * len], *cur = io_buf;
+    g_autofree uint8_t *io_buf = g_malloc(1 + 2 * len);
+    uint8_t *cur = io_buf;
     int room;
     *cur++ = ESC;
     while (len--)
@@ -380,9 +384,9 @@ static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
     switch (req) {
     case BAUM_REQ_DisplayData:
     {
-        uint8_t cells[baum->x * baum->y], c;
+        uint8_t cells[X_MAX * Y_MAX], c;
-        uint8_t text[baum->x * baum->y];
+        uint8_t text[X_MAX * Y_MAX];
-        uint8_t zero[baum->x * baum->y];
+        uint8_t zero[X_MAX * Y_MAX];
         int cursor = BRLAPI_CURSOR_OFF;
         int i;
 
@@ -405,7 +409,7 @@ static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
         }
         timer_del(baum->cellCount_timer);
 
-        memset(zero, 0, sizeof(zero));
+        memset(zero, 0, baum->x * baum->y);
 
         brlapi_writeArguments_t wa = {
             .displayNumber = BRLAPI_DISPLAY_DEFAULT,

chardev/char-socket.c

@@ -557,12 +557,10 @@ static char *qemu_chr_compute_filename(SocketChardev *s)
     const char *left = "", *right = "";
 
     switch (ss->ss_family) {
-#ifndef _WIN32
     case AF_UNIX:
         return g_strdup_printf("unix:%s%s",
                                ((struct sockaddr_un *)(ss))->sun_path,
                                s->is_listen ? ",server=on" : "");
-#endif
     case AF_INET6:
         left  = "[";
         right = "]";
@@ -1372,10 +1370,12 @@ static void qmp_chardev_open_socket(Chardev *chr,
     }
 
     qemu_chr_set_feature(chr, QEMU_CHAR_FEATURE_RECONNECTABLE);
+#ifndef _WIN32
     /* TODO SOCKET_ADDRESS_FD where fd has AF_UNIX */
     if (addr->type == SOCKET_ADDRESS_TYPE_UNIX) {
         qemu_chr_set_feature(chr, QEMU_CHAR_FEATURE_FD_PASS);
     }
+#endif
 
     /*
      * In the chardev-change special-case, we shouldn't register a new yank

chardev/char.c

@@ -193,7 +193,7 @@ int qemu_chr_be_can_write(Chardev *s)
     return be->chr_can_read(be->opaque);
 }
 
-void qemu_chr_be_write_impl(Chardev *s, uint8_t *buf, int len)
+void qemu_chr_be_write_impl(Chardev *s, const uint8_t *buf, int len)
 {
     CharBackend *be = s->be;
 
@@ -202,7 +202,7 @@ void qemu_chr_be_write_impl(Chardev *s, uint8_t *buf, int len)
     }
 }
 
-void qemu_chr_be_write(Chardev *s, uint8_t *buf, int len)
+void qemu_chr_be_write(Chardev *s, const uint8_t *buf, int len)
 {
     if (qemu_chr_replay(s)) {
         if (replay_mode == REPLAY_MODE_PLAY) {

chardev/msmouse.c

@@ -24,23 +24,45 @@
 
 #include "qemu/osdep.h"
 #include "qemu/module.h"
+#include "qemu/fifo8.h"
 #include "chardev/char.h"
+#include "chardev/char-serial.h"
 #include "ui/console.h"
 #include "ui/input.h"
 #include "qom/object.h"
 
-#define MSMOUSE_LO6(n) ((n) & 0x3f)
+#define MSMOUSE_LO6(n)  ((n) & 0x3f)
-#define MSMOUSE_HI2(n) (((n) & 0xc0) >> 6)
+#define MSMOUSE_HI2(n)  (((n) & 0xc0) >> 6)
+#define MSMOUSE_PWR(cm) (cm & (CHR_TIOCM_RTS | CHR_TIOCM_DTR))
+
+/* Serial PnP for 6 bit devices/mice sends all ASCII chars - 0x20 */
+#define M(c) (c - 0x20)
+/* Serial fifo size. */
+#define MSMOUSE_BUF_SZ 64
+
+/* Mouse ID: Send "M3" cause we behave like a 3 button logitech mouse. */
+const uint8_t mouse_id[] = {'M', '3'};
+/*
+ * PnP start "(", PnP version (1.0), vendor ID, product ID, '\\',
+ * serial ID (omitted), '\\', MS class name, '\\', driver ID (omitted), '\\',
+ * product description, checksum, ")"
+ * Missing parts are inserted later.
+ */
+const uint8_t pnp_data[] = {M('('), 1, '$', M('Q'), M('M'), M('U'),
+                         M('0'), M('0'), M('0'), M('1'),
+                         M('\\'), M('\\'),
+                         M('M'), M('O'), M('U'), M('S'), M('E'),
+                         M('\\'), M('\\')};
 
 struct MouseChardev {
     Chardev parent;
 
     QemuInputHandlerState *hs;
+    int tiocm;
     int axis[INPUT_AXIS__MAX];
     bool btns[INPUT_BUTTON__MAX];
     bool btnc[INPUT_BUTTON__MAX];
-    uint8_t outbuf[32];
+    Fifo8 outbuf;
-    int outlen;
 };
 typedef struct MouseChardev MouseChardev;
 
@@ -51,20 +73,18 @@ DECLARE_INSTANCE_CHECKER(MouseChardev, MOUSE_CHARDEV,
 static void msmouse_chr_accept_input(Chardev *chr)
 {
     MouseChardev *mouse = MOUSE_CHARDEV(chr);
-    int len;
+    uint32_t len, avail;
 
     len = qemu_chr_be_can_write(chr);
-    if (len > mouse->outlen) {
+    avail = fifo8_num_used(&mouse->outbuf);
-        len = mouse->outlen;
+    while (len > 0 && avail > 0) {
-    }
+        const uint8_t *buf;
-    if (!len) {
+        uint32_t size;
-        return;
-    }
 
-    qemu_chr_be_write(chr, mouse->outbuf, len);
+        buf = fifo8_pop_buf(&mouse->outbuf, MIN(len, avail), &size);
-    mouse->outlen -= len;
+        qemu_chr_be_write(chr, buf, size);
-    if (mouse->outlen) {
+        len = qemu_chr_be_can_write(chr);
-        memmove(mouse->outbuf, mouse->outbuf + len, mouse->outlen);
+        avail -= size;
     }
 }
 
@@ -91,12 +111,11 @@ static void msmouse_queue_event(MouseChardev *mouse)
         mouse->btnc[INPUT_BUTTON_MIDDLE]) {
         bytes[3] |= (mouse->btns[INPUT_BUTTON_MIDDLE] ? 0x20 : 0x00);
         mouse->btnc[INPUT_BUTTON_MIDDLE] = false;
-        count = 4;
+        count++;
     }
 
-    if (mouse->outlen <= sizeof(mouse->outbuf) - count) {
+    if (fifo8_num_free(&mouse->outbuf) >= count) {
-        memcpy(mouse->outbuf + mouse->outlen, bytes, count);
+        fifo8_push_all(&mouse->outbuf, bytes, count);
-        mouse->outlen += count;
     } else {
         /* queue full -> drop event */
     }
@@ -109,6 +128,11 @@ static void msmouse_input_event(DeviceState *dev, QemuConsole *src,
     InputMoveEvent *move;
     InputBtnEvent *btn;
 
+    /* Ignore events if serial mouse powered down. */
+    if (!MSMOUSE_PWR(mouse->tiocm)) {
+        return;
+    }
+
     switch (evt->type) {
     case INPUT_EVENT_KIND_REL:
         move = evt->u.rel.data;
@@ -132,6 +156,11 @@ static void msmouse_input_sync(DeviceState *dev)
     MouseChardev *mouse = MOUSE_CHARDEV(dev);
     Chardev *chr = CHARDEV(dev);
 
+    /* Ignore events if serial mouse powered down. */
+    if (!MSMOUSE_PWR(mouse->tiocm)) {
+        return;
+    }
+
     msmouse_queue_event(mouse);
     msmouse_chr_accept_input(chr);
 }
@@ -142,13 +171,6 @@ static int msmouse_chr_write(struct Chardev *s, const uint8_t *buf, int len)
     return len;
 }
 
-static void char_msmouse_finalize(Object *obj)
-{
-    MouseChardev *mouse = MOUSE_CHARDEV(obj);
-
-    qemu_input_handler_unregister(mouse->hs);
-}
-
 static QemuInputHandler msmouse_handler = {
     .name  = "QEMU Microsoft Mouse",
     .mask  = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_REL,
@@ -156,6 +178,81 @@ static QemuInputHandler msmouse_handler = {
     .sync  = msmouse_input_sync,
 };
 
+static int msmouse_ioctl(Chardev *chr, int cmd, void *arg)
+{
+    MouseChardev *mouse = MOUSE_CHARDEV(chr);
+    int c, i, j;
+    uint8_t bytes[MSMOUSE_BUF_SZ / 2];
+    int *targ = (int *)arg;
+    const uint8_t hexchr[16] = {M('0'), M('1'), M('2'), M('3'), M('4'), M('5'),
+                             M('6'), M('7'), M('8'), M('9'), M('A'), M('B'),
+                             M('C'), M('D'), M('E'), M('F')};
+
+    switch (cmd) {
+    case CHR_IOCTL_SERIAL_SET_TIOCM:
+        c = mouse->tiocm;
+        mouse->tiocm = *(int *)arg;
+        if (MSMOUSE_PWR(mouse->tiocm)) {
+            if (!MSMOUSE_PWR(c)) {
+                /*
+                 * Power on after reset: Send ID and PnP data
+                 * No need to check fifo space as it is empty at this point.
+                 */
+                fifo8_push_all(&mouse->outbuf, mouse_id, sizeof(mouse_id));
+                /* Add PnP data: */
+                fifo8_push_all(&mouse->outbuf, pnp_data, sizeof(pnp_data));
+                /*
+                 * Add device description from qemu handler name.
+                 * Make sure this all fits into the queue beforehand!
+                 */
+                c = M(')');
+                for (i = 0; msmouse_handler.name[i]; i++) {
+                    bytes[i] = M(msmouse_handler.name[i]);
+                    c += bytes[i];
+                }
+                /* Calc more of checksum */
+                for (j = 0; j < sizeof(pnp_data); j++) {
+                    c += pnp_data[j];
+                }
+                c &= 0xff;
+                bytes[i++] = hexchr[c >> 4];
+                bytes[i++] = hexchr[c & 0x0f];
+                bytes[i++] = M(')');
+                fifo8_push_all(&mouse->outbuf, bytes, i);
+                /* Start sending data to serial. */
+                msmouse_chr_accept_input(chr);
+            }
+            break;
+        }
+        /*
+         * Reset mouse buffers on power down.
+         * Mouse won't send anything without power.
+         */
+        fifo8_reset(&mouse->outbuf);
+        memset(mouse->axis, 0, sizeof(mouse->axis));
+        memset(mouse->btns, false, sizeof(mouse->btns));
+        memset(mouse->btnc, false, sizeof(mouse->btns));
+        break;
+    case CHR_IOCTL_SERIAL_GET_TIOCM:
+        /* Remember line control status. */
+        *targ = mouse->tiocm;
+        break;
+    default:
+        return -ENOTSUP;
+    }
+    return 0;
+}
+
+static void char_msmouse_finalize(Object *obj)
+{
+    MouseChardev *mouse = MOUSE_CHARDEV(obj);
+
+    if (mouse->hs) {
+        qemu_input_handler_unregister(mouse->hs);
+    }
+    fifo8_destroy(&mouse->outbuf);
+}
+
 static void msmouse_chr_open(Chardev *chr,
                              ChardevBackend *backend,
                              bool *be_opened,
@@ -166,6 +263,8 @@ static void msmouse_chr_open(Chardev *chr,
     *be_opened = false;
     mouse->hs = qemu_input_handler_register((DeviceState *)mouse,
                                             &msmouse_handler);
+    mouse->tiocm = 0;
+    fifo8_create(&mouse->outbuf, MSMOUSE_BUF_SZ);
 }
 
 static void char_msmouse_class_init(ObjectClass *oc, void *data)
@@ -175,6 +274,7 @@ static void char_msmouse_class_init(ObjectClass *oc, void *data)
     cc->open = msmouse_chr_open;
     cc->chr_write = msmouse_chr_write;
     cc->chr_accept_input = msmouse_chr_accept_input;
+    cc->chr_ioctl = msmouse_ioctl;
 }
 
 static const TypeInfo char_msmouse_type_info = {

chardev/wctablet.c

@@ -319,7 +319,9 @@ static void wctablet_chr_finalize(Object *obj)
 {
     TabletChardev *tablet = WCTABLET_CHARDEV(obj);
 
-    qemu_input_handler_unregister(tablet->hs);
+    if (tablet->hs) {
+        qemu_input_handler_unregister(tablet->hs);
+    }
 }
 
 static void wctablet_chr_open(Chardev *chr,

configs/devices/or1k-softmmu/default.mak

@@ -3,3 +3,4 @@
 # Boards:
 #
 CONFIG_OR1K_SIM=y
+CONFIG_OR1K_VIRT=y

configs/targets/loongarch64-softmmu.mak

@@ -1,5 +1,5 @@
 TARGET_ARCH=loongarch64
 TARGET_BASE_ARCH=loongarch
 TARGET_SUPPORTS_MTTCG=y
-TARGET_XML_FILES= gdb-xml/loongarch-base64.xml gdb-xml/loongarch-fpu64.xml
+TARGET_XML_FILES= gdb-xml/loongarch-base64.xml gdb-xml/loongarch-fpu.xml
 TARGET_NEED_FDT=y

configs/targets/or1k-softmmu.mak

@@ -1,3 +1,4 @@
 TARGET_ARCH=openrisc
+TARGET_SUPPORTS_MTTCG=y
 TARGET_BIG_ENDIAN=y
 TARGET_NEED_FDT=y

configure

@@ -57,7 +57,7 @@ GNUmakefile: ;
 
 EOF
     cd build
-    exec $source_path/configure "$@"
+    exec "$source_path/configure" "$@"
 fi
 
 # Temporary directory used for files created while
@@ -67,8 +67,7 @@ fi
 # it when configure exits.)
 TMPDIR1="config-temp"
 rm -rf "${TMPDIR1}"
-mkdir -p "${TMPDIR1}"
+if ! mkdir -p "${TMPDIR1}"; then
-if [ $? -ne 0 ]; then
     echo "ERROR: failed to create temporary directory"
     exit 1
 fi
@@ -76,7 +75,6 @@ fi
 TMPB="qemu-conf"
 TMPC="${TMPDIR1}/${TMPB}.c"
 TMPO="${TMPDIR1}/${TMPB}.o"
-TMPCXX="${TMPDIR1}/${TMPB}.cxx"
 TMPM="${TMPDIR1}/${TMPB}.m"
 TMPE="${TMPDIR1}/${TMPB}.exe"
 
@@ -111,7 +109,7 @@ error_exit() {
 do_compiler() {
   # Run the compiler, capturing its output to the log. First argument
   # is compiler binary to execute.
-  local compiler="$1"
+  compiler="$1"
   shift
   if test -n "$BASH_VERSION"; then eval '
       echo >>config.log "
@@ -159,10 +157,6 @@ do_cc() {
     do_compiler_werror "$cc" $CPU_CFLAGS "$@"
 }
 
-do_cxx() {
-    do_compiler_werror "$cxx" $CPU_CFLAGS "$@"
-}
-
 do_objc() {
     do_compiler_werror "$objcc" $CPU_CFLAGS "$@"
 }
@@ -172,24 +166,6 @@ add_to() {
     eval $1=\${$1:+\"\$$1 \"}\$2
 }
 
-update_cxxflags() {
-    # Set QEMU_CXXFLAGS from QEMU_CFLAGS by filtering out those
-    # options which some versions of GCC's C++ compiler complain about
-    # because they only make sense for C programs.
-    QEMU_CXXFLAGS="-D__STDC_LIMIT_MACROS -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS"
-    CONFIGURE_CXXFLAGS=$(echo "$CONFIGURE_CFLAGS" | sed s/-std=gnu11/-std=gnu++11/)
-    for arg in $QEMU_CFLAGS; do
-        case $arg in
-            -Wstrict-prototypes|-Wmissing-prototypes|-Wnested-externs|\
-            -Wold-style-declaration|-Wold-style-definition|-Wredundant-decls)
-                ;;
-            *)
-                QEMU_CXXFLAGS=${QEMU_CXXFLAGS:+$QEMU_CXXFLAGS }$arg
-                ;;
-        esac
-    done
-}
-
 compile_object() {
   local_cflags="$1"
   do_cc $CFLAGS $EXTRA_CFLAGS $CONFIGURE_CFLAGS $QEMU_CFLAGS $local_cflags -c -o $TMPO $TMPC
@@ -311,7 +287,6 @@ pie=""
 coroutine=""
 plugins="$default_feature"
 meson=""
-meson_args=""
 ninja=""
 bindir="bin"
 skip_meson=no
@@ -321,11 +296,6 @@ vfio_user_server="disabled"
 # are included in the automatically generated help message)
 
 # 1. Track which submodules are needed
-if test "$default_feature" = no ; then
-  slirp="disabled"
-else
-  slirp="auto"
-fi
 fdt="auto"
 
 # 2. Automatically enable/disable other options
@@ -695,20 +665,21 @@ meson_option_build_array() {
 
 meson_option_build_array() {
   printf '['
-  (if test "$targetos" == windows; then
+  (if test "$targetos" = windows; then
     IFS=\;
   else
     IFS=:
   fi
   for e in $1; do
-    e=${e/'\'/'\\'}
+    printf '"""'
-    e=${e/\"/'\"'}
+    # backslash escape any '\' and '"' characters
-    printf '"""%s""",' "$e"
+    printf "%s" "$e" | sed -e 's/\([\"]\)/\\\1/g'
+    printf '""",'
   done)
   printf ']\n'
 }
 
-. $source_path/scripts/meson-buildoptions.sh
+. "$source_path/scripts/meson-buildoptions.sh"
 
 meson_options=
 meson_option_add() {
@@ -728,7 +699,7 @@ for opt do
   case "$opt" in
   --help|-h) show_help=yes
   ;;
-  --version|-V) exec cat $source_path/VERSION
+  --version|-V) exec cat "$source_path/VERSION"
   ;;
   --prefix=*) prefix="$optarg"
   ;;
@@ -845,14 +816,6 @@ for opt do
   ;;
   --disable-tsan) tsan="no"
   ;;
-  --disable-slirp) slirp="disabled"
-  ;;
-  --enable-slirp) slirp="enabled"
-  ;;
-  --enable-slirp=git) slirp="internal"
-  ;;
-  --enable-slirp=*) slirp="$optarg"
-  ;;
   --disable-tcg) tcg="disabled"
                  plugins="no"
   ;;
@@ -1017,7 +980,7 @@ default_target_list=""
 mak_wilds=""
 
 if [ "$linux_user" != no ]; then
-    if [ "$targetos" = linux ] && [ -d $source_path/linux-user/include/host/$cpu ]; then
+    if [ "$targetos" = linux ] && [ -d "$source_path/linux-user/include/host/$cpu" ]; then
         linux_user=yes
     elif [ "$linux_user" = yes ]; then
         error_exit "linux-user not supported on this architecture"
@@ -1027,7 +990,7 @@ if [ "$bsd_user" != no ]; then
     if [ "$bsd_user" = "" ]; then
         test $targetos = freebsd && bsd_user=yes
     fi
-    if [ "$bsd_user" = yes ] && ! [ -d $source_path/bsd-user/$targetos ]; then
+    if [ "$bsd_user" = yes ] && ! [ -d "$source_path/bsd-user/$targetos" ]; then
         error_exit "bsd-user not supported on this host OS"
     fi
 fi
@@ -1125,7 +1088,7 @@ exit 0
 fi
 
 # Remove old dependency files to make sure that they get properly regenerated
-rm -f */config-devices.mak.d
+rm -f ./*/config-devices.mak.d
 
 if test -z "$python"
 then
@@ -1143,16 +1106,13 @@ if ! $python -c 'import sys; sys.exit(sys.version_info < (3,6))'; then
       "Use --python=/path/to/python to specify a supported Python."
 fi
 
-# Preserve python version since some functionality is dependent on it
-python_version=$($python -c 'import sys; print("%d.%d.%d" % (sys.version_info[0], sys.version_info[1], sys.version_info[2]))' 2>/dev/null)
-
 # Suppress writing compiled files
 python="$python -B"
 
 if test -z "$meson"; then
-    if test "$explicit_python" = no && has meson && version_ge "$(meson --version)" 0.59.3; then
+    if test "$explicit_python" = no && has meson && version_ge "$(meson --version)" 0.61.5; then
         meson=meson
-    elif test $git_submodules_action != 'ignore' ; then
+    elif test "$git_submodules_action" != 'ignore' ; then
         meson=git
     elif test -e "${source_path}/meson/meson.py" ; then
         meson=internal
@@ -1289,6 +1249,7 @@ add_to nowarn_flags -Wno-string-plus-int
 add_to nowarn_flags -Wno-typedef-redefinition
 add_to nowarn_flags -Wno-tautological-type-limit-compare
 add_to nowarn_flags -Wno-psabi
+add_to nowarn_flags -Wno-gnu-variable-sized-type-not-at-end
 
 gcc_flags="$warn_flags $nowarn_flags"
 
@@ -1401,18 +1362,19 @@ EOF
 if test "$static" = "yes"; then
   if test "$pie" != "no" && compile_prog "-Werror -fPIE -DPIE" "-static-pie"; then
     CONFIGURE_CFLAGS="-fPIE -DPIE $CONFIGURE_CFLAGS"
-    QEMU_LDFLAGS="-static-pie $QEMU_LDFLAGS"
     pie="yes"
   elif test "$pie" = "yes"; then
     error_exit "-static-pie not available due to missing toolchain support"
   else
-    QEMU_LDFLAGS="-static $QEMU_LDFLAGS"
     pie="no"
   fi
 elif test "$pie" = "no"; then
   if compile_prog "-Werror -fno-pie" "-no-pie"; then
     CONFIGURE_CFLAGS="-fno-pie $CONFIGURE_CFLAGS"
     CONFIGURE_LDFLAGS="-no-pie $CONFIGURE_LDFLAGS"
+    # Meson currently only handles pie as a boolean for now so if we have
+    # explicitly disabled PIE we need to extend our cflags because it wont.
+    QEMU_CFLAGS="-fno-pie -no-pie $QEMU_CFLAGS"
   fi
 elif compile_prog "-Werror -fPIE -DPIE" "-pie"; then
   CONFIGURE_CFLAGS="-fPIE -DPIE $CONFIGURE_CFLAGS"
@@ -1425,12 +1387,6 @@ else
   pie="no"
 fi
 
-# Detect support for PT_GNU_RELRO + DT_BIND_NOW.
-# The combination is known as "full relro", because .got.plt is read-only too.
-if compile_prog "" "-Wl,-z,relro -Wl,-z,now" ; then
-  QEMU_LDFLAGS="-Wl,-z,relro -Wl,-z,now $QEMU_LDFLAGS"
-fi
-
 ##########################################
 # __sync_fetch_and_and requires at least -march=i486. Many toolchains
 # use i686 as default anyway, but for those that don't, an explicit
@@ -1499,15 +1455,6 @@ if test "$tcg" = "enabled"; then
     git_submodules="$git_submodules tests/fp/berkeley-softfloat-3"
 fi
 
-feature_not_found() {
-  feature=$1
-  remedy=$2
-
-  error_exit "User requested feature $feature" \
-      "configure was not able to find it." \
-      "$remedy"
-}
-
 # ---
 # big/little endian test
 cat > $TMPC << EOF
@@ -1670,7 +1617,7 @@ else
     ;;
   ucontext)
     if test "$ucontext_works" != "yes"; then
-      feature_not_found "ucontext"
+      error_exit "'ucontext' backend requested but makecontext not available"
     fi
     ;;
   sigaltstack)
@@ -1859,23 +1806,18 @@ EOF
   fi
 fi
 
-##########################################
-# check for slirp
-
-case "$slirp" in
-  auto | enabled | internal)
-    # Simpler to always update submodule, even if not needed.
-    git_submodules="${git_submodules} slirp"
-    ;;
-esac
-
 ##########################################
 # functions to probe cross compilers
 
 container="no"
 if test $use_containers = "yes"; then
-    if has "docker" || has "podman"; then
+    case $($python "$source_path"/tests/docker/docker.py probe) in
-        container=$($python $source_path/tests/docker/docker.py probe)
+        *docker) container=docker ;;
+        podman) container=podman ;;
+        no) container=no ;;
+    esac
+    if test "$container" != "no"; then
+        docker_py="$python $source_path/tests/docker/docker.py --engine $container"
     fi
 fi
 
@@ -2059,7 +2001,7 @@ probe_target_compiler() {
         ;;
       ppc64|ppc64le)
         container_image=debian-powerpc-test-cross
-        container_cross_prefix=powerpc${1#ppc}-linux-gnu-
+        container_cross_prefix=powerpc${target_arch#ppc}-linux-gnu-
         container_cross_cc=${container_cross_prefix}gcc-10
         ;;
       riscv64)
@@ -2107,7 +2049,6 @@ probe_target_compiler() {
     : ${container_cross_strip:=${container_cross_prefix}strip}
   done
 
-  local t try
   try=cross
   case "$target_arch:$cpu" in
     aarch64_be:aarch64 | \
@@ -2120,8 +2061,8 @@ probe_target_compiler() {
       try='native cross' ;;
   esac
   eval "target_cflags=\${cross_cc_cflags_$target_arch}"
-  for t in $try; do
+  for thistry in $try; do
-    case $t in
+    case $thistry in
     native)
       target_cc=$cc
       target_ccas=$ccas
@@ -2204,7 +2145,6 @@ probe_target_compiler() {
     build_static=
     target_cc=
     target_ccas=
-    target_cflags=
     target_ar=
     target_as=
     target_ld=
@@ -2213,54 +2153,54 @@ probe_target_compiler() {
     target_ranlib=
     target_strip=
   fi
+  test -n "$target_cc"
 }
 
 write_target_makefile() {
   echo "EXTRA_CFLAGS=$target_cflags"
-  if test -n "$target_cc"; then
+  if test -z "$target_cc" && test -z "$target_as"; then
-    echo "CC=$target_cc"
+    test -z "$container_image" && error_exit "Internal error: could not find cross compiler for $1?"
-    echo "CCAS=$target_ccas"
+    echo "$1: docker-image-$container_image" >> Makefile.prereqs
-  fi
+    if test -n "$container_cross_cc"; then
-  if test -n "$target_ar"; then
+      echo "CC=$docker_py cc --cc $container_cross_cc -i qemu/$container_image -s $source_path --"
-    echo "AR=$target_ar"
+      echo "CCAS=$docker_py cc --cc $container_cross_cc -i qemu/$container_image -s $source_path --"
-  fi
+    fi
-  if test -n "$target_as"; then
+    echo "AR=$docker_py cc --cc $container_cross_ar -i qemu/$container_image -s $source_path --"
-    echo "AS=$target_as"
+    echo "AS=$docker_py cc --cc $container_cross_as -i qemu/$container_image -s $source_path --"
-  fi
+    echo "LD=$docker_py cc --cc $container_cross_ld -i qemu/$container_image -s $source_path --"
-  if test -n "$target_ld"; then
+    echo "NM=$docker_py cc --cc $container_cross_nm -i qemu/$container_image -s $source_path --"
-    echo "LD=$target_ld"
+    echo "OBJCOPY=$docker_py cc --cc $container_cross_objcopy -i qemu/$container_image -s $source_path --"
-  fi
+    echo "RANLIB=$docker_py cc --cc $container_cross_ranlib -i qemu/$container_image -s $source_path --"
-  if test -n "$target_nm"; then
+    echo "STRIP=$docker_py cc --cc $container_cross_strip -i qemu/$container_image -s $source_path --"
-    echo "NM=$target_nm"
+  else
-  fi
+    if test -n "$target_cc"; then
-  if test -n "$target_objcopy"; then
+      echo "CC=$target_cc"
-    echo "OBJCOPY=$target_objcopy"
+      echo "CCAS=$target_ccas"
-  fi
+    fi
-  if test -n "$target_ranlib"; then
+    if test -n "$target_ar"; then
-    echo "RANLIB=$target_ranlib"
+      echo "AR=$target_ar"
-  fi
+    fi
-  if test -n "$target_strip"; then
+    if test -n "$target_as"; then
-    echo "STRIP=$target_strip"
+      echo "AS=$target_as"
+    fi
+    if test -n "$target_ld"; then
+      echo "LD=$target_ld"
+    fi
+    if test -n "$target_nm"; then
+      echo "NM=$target_nm"
+    fi
+    if test -n "$target_objcopy"; then
+      echo "OBJCOPY=$target_objcopy"
+    fi
+    if test -n "$target_ranlib"; then
+      echo "RANLIB=$target_ranlib"
+    fi
+    if test -n "$target_strip"; then
+      echo "STRIP=$target_strip"
+    fi
   fi
 }
 
-write_container_target_makefile() {
-  echo "EXTRA_CFLAGS=$target_cflags"
-  if test -n "$container_cross_cc"; then
-    echo "CC=\$(DOCKER_SCRIPT) cc --cc $container_cross_cc -i qemu/$container_image -s $source_path --"
-    echo "CCAS=\$(DOCKER_SCRIPT) cc --cc $container_cross_cc -i qemu/$container_image -s $source_path --"
-  fi
-  echo "AR=\$(DOCKER_SCRIPT) cc --cc $container_cross_ar -i qemu/$container_image -s $source_path --"
-  echo "AS=\$(DOCKER_SCRIPT) cc --cc $container_cross_as -i qemu/$container_image -s $source_path --"
-  echo "LD=\$(DOCKER_SCRIPT) cc --cc $container_cross_ld -i qemu/$container_image -s $source_path --"
-  echo "NM=\$(DOCKER_SCRIPT) cc --cc $container_cross_nm -i qemu/$container_image -s $source_path --"
-  echo "OBJCOPY=\$(DOCKER_SCRIPT) cc --cc $container_cross_objcopy -i qemu/$container_image -s $source_path --"
-  echo "RANLIB=\$(DOCKER_SCRIPT) cc --cc $container_cross_ranlib -i qemu/$container_image -s $source_path --"
-  echo "STRIP=\$(DOCKER_SCRIPT) cc --cc $container_cross_strip -i qemu/$container_image -s $source_path --"
-}
-
-
-
 ##########################################
 # check for vfio_user_server
 
@@ -2282,13 +2222,6 @@ if test "$fortify_source" = "yes" ; then
   QEMU_CFLAGS="-U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 $QEMU_CFLAGS"
 fi
 
-case "$ARCH" in
-alpha)
-  # Ensure there's only a single GP
-  QEMU_CFLAGS="-msmall-data $QEMU_CFLAGS"
-;;
-esac
-
 if test "$have_asan" = "yes"; then
   QEMU_CFLAGS="-fsanitize=address $QEMU_CFLAGS"
   QEMU_LDFLAGS="-fsanitize=address $QEMU_LDFLAGS"
@@ -2316,14 +2249,6 @@ if test "$have_ubsan" = "yes"; then
 fi
 
 ##########################################
-
-# Exclude --warn-common with TSan to suppress warnings from the TSan libraries.
-if test "$solaris" = "no" && test "$tsan" = "no"; then
-    if $ld --version 2>/dev/null | grep "GNU ld" >/dev/null 2>/dev/null ; then
-        QEMU_LDFLAGS="-Wl,--warn-common $QEMU_LDFLAGS"
-    fi
-fi
-
 # Guest agent Windows MSI package
 
 if test "$QEMU_GA_MANUFACTURER" = ""; then
@@ -2333,7 +2258,7 @@ if test "$QEMU_GA_DISTRO" = ""; then
   QEMU_GA_DISTRO=Linux
 fi
 if test "$QEMU_GA_VERSION" = ""; then
-    QEMU_GA_VERSION=$(cat $source_path/VERSION)
+    QEMU_GA_VERSION=$(cat "$source_path"/VERSION)
 fi
 
 
@@ -2349,7 +2274,6 @@ fi
 # tests might fail. Prefer to keep the relevant files in their own
 # directory and symlink the directory instead.
 LINKS="Makefile"
-LINKS="$LINKS tests/tcg/Makefile.target"
 LINKS="$LINKS pc-bios/optionrom/Makefile"
 LINKS="$LINKS pc-bios/s390-ccw/Makefile"
 LINKS="$LINKS pc-bios/vof/Makefile"
@@ -2360,38 +2284,26 @@ LINKS="$LINKS python"
 LINKS="$LINKS contrib/plugins/Makefile "
 for f in $LINKS ; do
     if [ -e "$source_path/$f" ]; then
-        mkdir -p `dirname ./$f`
+        mkdir -p "$(dirname ./"$f")"
         symlink "$source_path/$f" "$f"
     fi
 done
 
+echo "# Automatically generated by configure - do not modify" > Makefile.prereqs
+
 # Mac OS X ships with a broken assembler
 roms=
-probe_target_compiler i386-softmmu
+if test "$targetos" != "darwin" && test "$targetos" != "sunos" && \
-if test -n "$target_cc" &&
+        test "$targetos" != "haiku" && test "$softmmu" = yes && \
-        test "$targetos" != "darwin" && test "$targetos" != "sunos" && \
+        probe_target_compiler i386-softmmu; then
-        test "$targetos" != "haiku" && test "$softmmu" = yes ; then
+    roms="pc-bios/optionrom"
-    # Different host OS linkers have different ideas about the name of the ELF
+    config_mak=pc-bios/optionrom/config.mak
-    # emulation. Linux and OpenBSD/amd64 use 'elf_i386'; FreeBSD uses the _fbsd
+    echo "# Automatically generated by configure - do not modify" > $config_mak
-    # variant; OpenBSD/i386 uses the _obsd variant; and Windows uses i386pe.
+    echo "TOPSRC_DIR=$source_path" >> $config_mak
-    for emu in elf_i386 elf_i386_fbsd elf_i386_obsd i386pe; do
+    write_target_makefile >> $config_mak
-        if "$target_ld" -verbose 2>&1 | grep -q "^[[:space:]]*$emu[[:space:]]*$"; then
-            ld_i386_emulation="$emu"
-            break
-        fi
-    done
-    if test -n "$ld_i386_emulation"; then
-        roms="pc-bios/optionrom"
-        config_mak=pc-bios/optionrom/config.mak
-        echo "# Automatically generated by configure - do not modify" > $config_mak
-        echo "TOPSRC_DIR=$source_path" >> $config_mak
-        echo "LD_I386_EMULATION=$ld_i386_emulation" >> $config_mak
-        write_target_makefile >> $config_mak
-    fi
 fi
 
-probe_target_compiler ppc-softmmu
+if test "$softmmu" = yes && probe_target_compiler ppc-softmmu; then
-if test -n "$target_cc" && test "$softmmu" = yes; then
     roms="$roms pc-bios/vof"
     config_mak=pc-bios/vof/config.mak
     echo "# Automatically generated by configure - do not modify" > $config_mak
@@ -2401,8 +2313,7 @@ fi
 
 # Only build s390-ccw bios if the compiler has -march=z900 or -march=z10
 # (which is the lowest architecture level that Clang supports)
-probe_target_compiler s390x-softmmu
+if test "$softmmu" = yes && probe_target_compiler s390x-softmmu; then
-if test -n "$target_cc" && test "$softmmu" = yes; then
   write_c_skeleton
   do_compiler "$target_cc" $target_cc_cflags -march=z900 -o $TMPO -c $TMPC
   has_z900=$?
@@ -2425,39 +2336,7 @@ fi
 #######################################
 # generate config-host.mak
 
-# Check that the C++ compiler exists and works with the C compiler.
+if ! (GIT="$git" "$source_path/scripts/git-submodule.sh" "$git_submodules_action" "$git_submodules"); then
-# All the QEMU_CXXFLAGS are based on QEMU_CFLAGS. Keep this at the end to don't miss any other that could be added.
-if has $cxx; then
-    cat > $TMPC <<EOF
-int c_function(void);
-int main(void) { return c_function(); }
-EOF
-
-    compile_object
-
-    cat > $TMPCXX <<EOF
-extern "C" {
-   int c_function(void);
-}
-int c_function(void) { return 42; }
-EOF
-
-    update_cxxflags
-
-    if do_cxx $CXXFLAGS $EXTRA_CXXFLAGS $CONFIGURE_CXXFLAGS $QEMU_CXXFLAGS -o $TMPE $TMPCXX $TMPO $QEMU_LDFLAGS; then
-        # C++ compiler $cxx works ok with C compiler $cc
-        :
-    else
-        echo "C++ compiler $cxx does not work with C compiler $cc"
-        echo "Disabling C++ specific optional code"
-        cxx=
-    fi
-else
-    echo "No C++ compiler available; disabling C++ specific optional code"
-    cxx=
-fi
-
-if !(GIT="$git" "$source_path/scripts/git-submodule.sh" "$git_submodules_action" "$git_submodules"); then
     exit 1
 fi
 
@@ -2526,9 +2405,15 @@ if test -n "$gdb_bin"; then
     gdb_version=$($gdb_bin --version | head -n 1)
     if version_ge ${gdb_version##* } 9.1; then
         echo "HAVE_GDB_BIN=$gdb_bin" >> $config_host_mak
+    else
+        gdb_bin=""
     fi
 fi
 
+if test "$container" != no; then
+    echo "ENGINE=$container" >> $config_host_mak
+fi
+
 if test "$as_shared_lib" = "yes" ; then
   echo "AS_SHARED_LIB=y" >> $config_host_mak
 fi
@@ -2544,7 +2429,6 @@ echo "MESON=$meson" >> $config_host_mak
 echo "NINJA=$ninja" >> $config_host_mak
 echo "CC=$cc" >> $config_host_mak
 echo "QEMU_CFLAGS=$QEMU_CFLAGS" >> $config_host_mak
-echo "QEMU_CXXFLAGS=$QEMU_CXXFLAGS" >> $config_host_mak
 echo "QEMU_OBJCFLAGS=$QEMU_OBJCFLAGS" >> $config_host_mak
 echo "GLIB_CFLAGS=$glib_cflags" >> $config_host_mak
 echo "GLIB_LIBS=$glib_libs" >> $config_host_mak
@@ -2589,7 +2473,7 @@ fi
 for target in $target_list; do
     target_dir="$target"
     target_name=$(echo $target | cut -d '-' -f 1)$EXESUF
-    mkdir -p $target_dir
+    mkdir -p "$target_dir"
     case $target in
         *-user) symlink "../qemu-$target_name" "$target_dir/qemu-$target_name" ;;
         *) symlink "../qemu-system-$target_name" "$target_dir/qemu-system-$target_name" ;;
@@ -2609,29 +2493,28 @@ if test "$safe_stack" = "yes"; then
 fi
 
 # tests/tcg configuration
-(makefile=tests/tcg/Makefile.prereqs
+(config_host_mak=tests/tcg/config-host.mak
-echo "# Automatically generated by configure - do not modify" > $makefile
+mkdir -p tests/tcg
-
-config_host_mak=tests/tcg/config-host.mak
 echo "# Automatically generated by configure - do not modify" > $config_host_mak
 echo "SRC_PATH=$source_path" >> $config_host_mak
 echo "HOST_CC=$host_cc" >> $config_host_mak
 
+# versioned checked in the main config_host.mak above
+if test -n "$gdb_bin"; then
+    echo "HAVE_GDB_BIN=$gdb_bin" >> $config_host_mak
+fi
+
 tcg_tests_targets=
 for target in $target_list; do
   arch=${target%%-*}
 
-  config_target_mak=tests/tcg/config-$target.mak
-
-  echo "# Automatically generated by configure - do not modify" > $config_target_mak
-  echo "TARGET_NAME=$arch" >> $config_target_mak
   case $target in
     xtensa*-linux-user)
       # the toolchain is not complete with headers, only build softmmu tests
       continue
       ;;
     *-softmmu)
-      test -f $source_path/tests/tcg/$arch/Makefile.softmmu-target || continue
+      test -f "$source_path/tests/tcg/$arch/Makefile.softmmu-target" || continue
       qemu="qemu-system-$arch"
       ;;
     *-linux-user|*-bsd-user)
@@ -2639,85 +2522,22 @@ for target in $target_list; do
       ;;
   esac
 
-  probe_target_compiler $target
+  if probe_target_compiler $target || test -n "$container_image"; then
-  if test $got_cross_cc = yes; then
+      test -n "$container_image" && build_static=y
-      # Test for compiler features for optional tests. We only do this
+      mkdir -p "tests/tcg/$target"
-      # for cross compilers because ensuring the docker containers based
+      config_target_mak=tests/tcg/$target/config-target.mak
-      # compilers is a requirememt for adding a new test that needs a
+      ln -sf "$source_path/tests/tcg/Makefile.target" "tests/tcg/$target/Makefile"
-      # compiler feature.
+      echo "# Automatically generated by configure - do not modify" > "$config_target_mak"
-
+      echo "TARGET_NAME=$arch" >> "$config_target_mak"
-      echo "BUILD_STATIC=$build_static" >> $config_target_mak
+      echo "TARGET=$target" >> "$config_target_mak"
-      write_target_makefile >> $config_target_mak
+      write_target_makefile "build-tcg-tests-$target" >> "$config_target_mak"
-      case $target in
+      echo "BUILD_STATIC=$build_static" >> "$config_target_mak"
-          aarch64-*)
+      echo "QEMU=$PWD/$qemu" >> "$config_target_mak"
-              if do_compiler "$target_cc" $target_cflags \
+      echo "run-tcg-tests-$target: $qemu\$(EXESUF)" >> Makefile.prereqs
-                             -march=armv8.1-a+sve -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_SVE=y" >> $config_target_mak
-              fi
-              if do_compiler "$target_cc" $target_cflags \
-                             -march=armv8.1-a+sve2 -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_SVE2=y" >> $config_target_mak
-              fi
-              if do_compiler "$target_cc" $target_cflags \
-                             -march=armv8.3-a -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_ARMV8_3=y" >> $config_target_mak
-              fi
-              if do_compiler "$target_cc" $target_cflags \
-                             -mbranch-protection=standard -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_ARMV8_BTI=y" >> $config_target_mak
-              fi
-              if do_compiler "$target_cc" $target_cflags \
-                             -march=armv8.5-a+memtag -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_ARMV8_MTE=y" >> $config_target_mak
-              fi
-              ;;
-          ppc*)
-              if do_compiler "$target_cc" $target_cflags \
-                             -mpower8-vector -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_POWER8_VECTOR=y" >> $config_target_mak
-              fi
-              if do_compiler "$target_cc" $target_cflags \
-                             -mpower10 -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_POWER10=y" >> $config_target_mak
-              fi
-              ;;
-          i386-linux-user)
-              if do_compiler "$target_cc" $target_cflags \
-                             -Werror -fno-pie -o $TMPE $TMPC; then
-                  echo "CROSS_CC_HAS_I386_NOPIE=y" >> $config_target_mak
-              fi
-              ;;
-      esac
-  elif test -n "$container_image"; then
-      echo "build-tcg-tests-$target: docker-image-$container_image" >> $makefile
-      echo "BUILD_STATIC=y" >> $config_target_mak
-      write_container_target_makefile >> $config_target_mak
-      case $target in
-          aarch64-*)
-              echo "CROSS_CC_HAS_SVE=y" >> $config_target_mak
-              echo "CROSS_CC_HAS_SVE2=y" >> $config_target_mak
-              echo "CROSS_CC_HAS_ARMV8_3=y" >> $config_target_mak
-              echo "CROSS_CC_HAS_ARMV8_BTI=y" >> $config_target_mak
-              echo "CROSS_CC_HAS_ARMV8_MTE=y" >> $config_target_mak
-              ;;
-          ppc*)
-              echo "CROSS_CC_HAS_POWER8_VECTOR=y" >> $config_target_mak
-              echo "CROSS_CC_HAS_POWER10=y" >> $config_target_mak
-              ;;
-          i386-linux-user)
-              echo "CROSS_CC_HAS_I386_NOPIE=y" >> $config_target_mak
-              ;;
-      esac
-      got_cross_cc=yes
-  fi
-  if test $got_cross_cc = yes; then
-      mkdir -p tests/tcg/$target
-      echo "QEMU=$PWD/$qemu" >> $config_target_mak
-      echo "run-tcg-tests-$target: $qemu\$(EXESUF)" >> $makefile
       tcg_tests_targets="$tcg_tests_targets $target"
   fi
 done
-echo "TCG_TESTS_TARGETS=$tcg_tests_targets" >> $makefile)
+echo "TCG_TESTS_TARGETS=$tcg_tests_targets" >> config-host.mak)
 
 if test "$skip_meson" = no; then
   cross="config-meson.cross.new"
@@ -2735,7 +2555,6 @@ if test "$skip_meson" = no; then
       echo "${a}-softmmu = '$c'" >> $cross
   done
 
-  test -z "$cxx" && echo "link_language = 'c'" >> $cross
   echo "[built-in options]" >> $cross
   echo "c_args = [$(meson_quote $CFLAGS $EXTRA_CFLAGS)]" >> $cross
   echo "cpp_args = [$(meson_quote $CXXFLAGS $EXTRA_CXXFLAGS)]" >> $cross
@@ -2792,7 +2611,6 @@ if test "$skip_meson" = no; then
   test "$fdt" != auto && meson_option_add "-Dfdt=$fdt"
   test -n "${LIB_FUZZING_ENGINE+xxx}" && meson_option_add "-Dfuzzing_engine=$LIB_FUZZING_ENGINE"
   test "$qemu_suffix" != qemu && meson_option_add "-Dqemu_suffix=$qemu_suffix"
-  test "$slirp" != auto && meson_option_add "-Dslirp=$slirp"
   test "$smbd" != '' && meson_option_add "-Dsmbd=$smbd"
   test "$tcg" != enabled && meson_option_add "-Dtcg=$tcg"
   test "$vfio_user_server" != auto && meson_option_add "-Dvfio_user_server=$vfio_user_server"

contrib/gitdm/domain-map

@@ -10,6 +10,7 @@ bytedance.com   ByteDance
 cmss.chinamobile.com China Mobile
 citrix.com      Citrix
 crudebyte.com   Crudebyte
+chinatelecom.cn China Telecom
 eldorado.org.br Instituto de Pesquisas Eldorado
 fujitsu.com     Fujitsu
 google.com      Google
@@ -19,6 +20,7 @@ ibm.com         IBM
 igalia.com      Igalia
 intel.com       Intel
 linaro.org      Linaro
+loongson.cn     Loongson Technology
 lwn.net         LWN
 microsoft.com   Microsoft
 mvista.com      MontaVista

contrib/gitdm/group-map-academics

@@ -19,3 +19,9 @@ edu.cn
 
 # Boston University
 bu.edu
+
+# Institute of Software Chinese Academy of Sciences
+iscas.ac.cn
+
+# Université Grenoble Alpes
+univ-grenoble-alpes.fr

contrib/gitdm/group-map-individuals

@@ -34,3 +34,6 @@ bmeng.cn@gmail.com
 liq3ea@gmail.com
 chetan4windows@gmail.com
 akihiko.odaki@gmail.com
+paul@nowt.org
+git@xen0n.name
+simon@simonsafar.com

contrib/plugins/cache.c

@@ -38,7 +38,7 @@ enum EvictionPolicy policy;
  * put in any of the blocks inside the set. The number of block per set is
  * called the associativity (assoc).
  *
- * Each block contains the the stored tag and a valid bit. Since this is not
+ * Each block contains the stored tag and a valid bit. Since this is not
  * a functional simulator, the data itself is not stored. We only identify
  * whether a block is in the cache or not by searching for its tag.
  *

contrib/plugins/execlog.c

@@ -20,6 +20,9 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
 /* Store last executed instruction on each vCPU as a GString */
 GArray *last_exec;
 
+static GPtrArray *imatches;
+static GArray *amatches;
+
 /**
  * Add memory read or write information to current instruction log
  */
@@ -85,12 +88,13 @@ static void vcpu_insn_exec(unsigned int cpu_index, void *udata)
 static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
 {
     struct qemu_plugin_insn *insn;
-    uint64_t insn_vaddr;
+    bool skip = (imatches || amatches);
-    uint32_t insn_opcode;
-    char *insn_disas;
 
     size_t n = qemu_plugin_tb_n_insns(tb);
     for (size_t i = 0; i < n; i++) {
+        char *insn_disas;
+        uint64_t insn_vaddr;
+
         /*
          * `insn` is shared between translations in QEMU, copy needed data here.
          * `output` is never freed as it might be used multiple times during
@@ -99,20 +103,55 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
          * a limitation for CISC architectures.
          */
         insn = qemu_plugin_tb_get_insn(tb, i);
-        insn_vaddr = qemu_plugin_insn_vaddr(insn);
-        insn_opcode = *((uint32_t *)qemu_plugin_insn_data(insn));
         insn_disas = qemu_plugin_insn_disas(insn);
-        char *output = g_strdup_printf("0x%"PRIx64", 0x%"PRIx32", \"%s\"",
+        insn_vaddr = qemu_plugin_insn_vaddr(insn);
-                                       insn_vaddr, insn_opcode, insn_disas);
 
-        /* Register callback on memory read or write */
+        /*
-        qemu_plugin_register_vcpu_mem_cb(insn, vcpu_mem,
+         * If we are filtering we better check out if we have any
-                                         QEMU_PLUGIN_CB_NO_REGS,
+         * hits. The skip "latches" so we can track memory accesses
-                                         QEMU_PLUGIN_MEM_RW, NULL);
+         * after the instruction we care about.
+         */
+        if (skip && imatches) {
+            int j;
+            for (j = 0; j < imatches->len && skip; j++) {
+                char *m = g_ptr_array_index(imatches, j);
+                if (g_str_has_prefix(insn_disas, m)) {
+                    skip = false;
+                }
+            }
+        }
+
+        if (skip && amatches) {
+            int j;
+            for (j = 0; j < amatches->len && skip; j++) {
+                uint64_t v = g_array_index(amatches, uint64_t, j);
+                if (v == insn_vaddr) {
+                    skip = false;
+                }
+            }
+        }
+
+        if (skip) {
+            g_free(insn_disas);
+        } else {
+            uint32_t insn_opcode;
+            insn_opcode = *((uint32_t *)qemu_plugin_insn_data(insn));
+            char *output = g_strdup_printf("0x%"PRIx64", 0x%"PRIx32", \"%s\"",
+                                           insn_vaddr, insn_opcode, insn_disas);
+
+            /* Register callback on memory read or write */
+            qemu_plugin_register_vcpu_mem_cb(insn, vcpu_mem,
+                                             QEMU_PLUGIN_CB_NO_REGS,
+                                             QEMU_PLUGIN_MEM_RW, NULL);
+
+            /* Register callback on instruction */
+            qemu_plugin_register_vcpu_insn_exec_cb(insn, vcpu_insn_exec,
+                                                   QEMU_PLUGIN_CB_NO_REGS, output);
+
+            /* reset skip */
+            skip = (imatches || amatches);
+        }
 
-        /* Register callback on instruction */
-        qemu_plugin_register_vcpu_insn_exec_cb(insn, vcpu_insn_exec,
-                                               QEMU_PLUGIN_CB_NO_REGS, output);
     }
 }
 
@@ -132,6 +171,25 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
     }
 }
 
+/* Add a match to the array of matches */
+static void parse_insn_match(char *match)
+{
+    if (!imatches) {
+        imatches = g_ptr_array_new();
+    }
+    g_ptr_array_add(imatches, match);
+}
+
+static void parse_vaddr_match(char *match)
+{
+    uint64_t v = g_ascii_strtoull(match, NULL, 16);
+
+    if (!amatches) {
+        amatches = g_array_new(false, true, sizeof(uint64_t));
+    }
+    g_array_append_val(amatches, v);
+}
+
 /**
  * Install the plugin
  */
@@ -145,6 +203,19 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
      */
     last_exec = g_array_new(FALSE, FALSE, sizeof(GString *));
 
+    for (int i = 0; i < argc; i++) {
+        char *opt = argv[i];
+        g_autofree char **tokens = g_strsplit(opt, "=", 2);
+        if (g_strcmp0(tokens[0], "ifilter") == 0) {
+            parse_insn_match(tokens[1]);
+        } else if (g_strcmp0(tokens[0], "afilter") == 0) {
+            parse_vaddr_match(tokens[1]);
+        } else {
+            fprintf(stderr, "option parsing failed: %s\n", opt);
+            return -1;
+        }
+    }
+
     /* Register translation block and exit callbacks */
     qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
     qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);

contrib/vhost-user-blk/vhost-user-blk.c

@@ -106,10 +106,7 @@ static void vub_req_complete(VubReq *req)
                   req->size + 1);
     vu_queue_notify(vu_dev, req->vq);
 
-    if (req->elem) {
+    g_free(req->elem);
-        free(req->elem);
-    }
-
     g_free(req);
 }
 
@@ -243,7 +240,7 @@ static int vub_virtio_process_req(VubDev *vdev_blk,
     /* refer to hw/block/virtio_blk.c */
     if (elem->out_num < 1 || elem->in_num < 1) {
         fprintf(stderr, "virtio-blk request missing headers\n");
-        free(elem);
+        g_free(elem);
         return -1;
     }
 
@@ -325,7 +322,7 @@ static int vub_virtio_process_req(VubDev *vdev_blk,
     return 0;
 
 err:
-    free(elem);
+    g_free(elem);
     g_free(req);
     return -1;
 }