OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

Merge upstream master

This commit is contained in:
Alibek Omarov 2020-12-18 13:44:43 +03:00
parent 3c31d9aa44 75ee62ac60
commit 2308e3519b
1738 changed files with 48406 additions and 20069 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
.cirrus.yml
View File

@ -9,39 +9,41 @@ freebsd_12_task:
install_script:
- ASSUME_ALWAYS_YES=yes pkg bootstrap -f ;
- pkg install -y bash curl cyrus-sasl git glib gmake gnutls gsed
nettle perl5 pixman pkgconf png usbredir
nettle perl5 pixman pkgconf png usbredir ninja
script:
- mkdir build
- cd build
- ../configure --enable-werror || { cat config.log; exit 1; }
- ../configure --enable-werror || { cat config.log meson-logs/meson-log.txt; exit 1; }
- gmake -j$(sysctl -n hw.ncpu)
- gmake -j$(sysctl -n hw.ncpu) check V=1
macos_task:
timeout_in: 90m
osx_instance:
image: catalina-base
install_script:
- brew install pkg-config python gnu-sed glib pixman make sdl2 bash
- brew install pkg-config python gnu-sed glib pixman make sdl2 bash ninja
script:
- mkdir build
- cd build
- ../configure --python=/usr/local/bin/python3 --enable-werror
--extra-cflags='-Wno-error=deprecated-declarations'
|| { cat config.log; exit 1; }
|| { cat config.log meson-logs/meson-log.txt; exit 1; }
- gmake -j$(sysctl -n hw.ncpu)
- gmake check V=1
macos_xcode_task:
timeout_in: 90m
osx_instance:
# this is an alias for the latest Xcode
image: catalina-xcode
install_script:
- brew install pkg-config gnu-sed glib pixman make sdl2 bash
- brew install pkg-config gnu-sed glib pixman make sdl2 bash ninja
script:
- mkdir build
- cd build
- ../configure --extra-cflags='-Wno-error=deprecated-declarations'
--enable-werror --cc=clang || { cat config.log; exit 1; }
- ../configure --extra-cflags='-Wno-error=deprecated-declarations' --enable-modules
--enable-werror --cc=clang || { cat config.log meson-logs/meson-log.txt; exit 1; }
- gmake -j$(sysctl -n hw.ncpu)
- gmake check V=1
@ -76,7 +78,6 @@ windows_msys2_task:
((Get-Content -path C:\tools\msys64\etc\\post-install\\07-pacman-key.post -Raw) -replace '--refresh-keys', '--version') | Set-Content -Path C:\tools\msys64\etc\\post-install\\07-pacman-key.post
C:\tools\msys64\usr\bin\bash.exe -lc "sed -i 's/^CheckSpace/#CheckSpace/g' /etc/pacman.conf"
C:\tools\msys64\usr\bin\bash.exe -lc "export"
C:\tools\msys64\usr\bin\bash.exe -lc "grep -rl 'repo.msys2.org/' /etc/pacman.d/mirrorlist.* | xargs sed -i 's/repo.msys2.org\//mirrors.tuna.tsinghua.edu.cn\/msys2\//g'"
C:\tools\msys64\usr\bin\pacman.exe --noconfirm -Sy
echo Y | C:\tools\msys64\usr\bin\pacman.exe --noconfirm -Suu --overwrite=*
taskkill /F /FI "MODULES eq msys-2.0.dll"
@ -86,7 +87,6 @@ windows_msys2_task:
C:\tools\msys64\usr\bin\bash.exe -lc "pacman --noconfirm -S --needed \
diffutils git grep make pkg-config sed \
mingw-w64-x86_64-python \
mingw-w64-x86_64-python-setuptools \
mingw-w64-x86_64-toolchain \
mingw-w64-x86_64-SDL2 \
mingw-w64-x86_64-SDL2_image \
@ -110,7 +110,13 @@ windows_msys2_task:
mingw-w64-x86_64-cyrus-sasl \
mingw-w64-x86_64-curl \
mingw-w64-x86_64-gnutls \
mingw-w64-x86_64-libnfs \
"
bitsadmin /transfer msys_download /dynamic /download /priority FOREGROUND `
https://repo.msys2.org/mingw/x86_64/mingw-w64-x86_64-python-sphinx-2.3.1-1-any.pkg.tar.xz `
C:\tools\mingw-w64-x86_64-python-sphinx-2.3.1-1-any.pkg.tar.xz
C:\tools\msys64\usr\bin\bash.exe -lc "pacman --noconfirm -U /c/tools/mingw-w64-x86_64-python-sphinx-2.3.1-1-any.pkg.tar.xz"
del C:\tools\mingw-w64-x86_64-python-sphinx-2.3.1-1-any.pkg.tar.xz
C:\tools\msys64\usr\bin\bash.exe -lc "rm -rf /var/cache/pacman/pkg/*"
cd C:\tools\msys64
echo "Start archive"
@ -123,8 +129,7 @@ windows_msys2_task:
script:
- C:\tools\msys64\usr\bin\bash.exe -lc "mkdir build"
- C:\tools\msys64\usr\bin\bash.exe -lc "cd build && ../configure
--python=python3 --ninja=ninja"
- C:\tools\msys64\usr\bin\bash.exe -lc "cd build && ../configure --python=python3"
- C:\tools\msys64\usr\bin\bash.exe -lc "cd build && make -j8"
test_script:
- C:\tools\msys64\usr\bin\bash.exe -lc "cd build && make V=1 check"

2
.gitattributes vendored Normal file
View File

@ -0,0 +1,2 @@
*.c.inc diff=c
*.h.inc diff=c

94
.gitlab-ci.d/check-dco.py Executable file
View File

@ -0,0 +1,94 @@
#!/usr/bin/env python3
#
# check-dco.py: validate all commits are signed off
#
# Copyright (C) 2020 Red Hat, Inc.
#
# SPDX-License-Identifier: GPL-2.0-or-later
import os
import os.path
import sys
import subprocess
namespace = "qemu-project"
if len(sys.argv) >= 2:
namespace = sys.argv[1]
cwd = os.getcwd()
reponame = os.path.basename(cwd)
repourl = "https://gitlab.com/%s/%s.git" % (namespace, reponame)
subprocess.check_call(["git", "remote", "add", "check-dco", repourl])
subprocess.check_call(["git", "fetch", "check-dco", "master"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL)
ancestor = subprocess.check_output(["git", "merge-base",
"check-dco/master", "HEAD"],
universal_newlines=True)
ancestor = ancestor.strip()
subprocess.check_call(["git", "remote", "rm", "check-dco"])
errors = False
print("\nChecking for 'Signed-off-by: NAME <EMAIL>' " +
"on all commits since %s...\n" % ancestor)
log = subprocess.check_output(["git", "log", "--format=%H %s",
ancestor + "..."],
universal_newlines=True)
if log == "":
commits = []
else:
commits = [[c[0:40], c[41:]] for c in log.strip().split("\n")]
for sha, subject in commits:
msg = subprocess.check_output(["git", "show", "-s", sha],
universal_newlines=True)
lines = msg.strip().split("\n")
print("🔍 %s %s" % (sha, subject))
sob = False
for line in lines:
if "Signed-off-by:" in line:
sob = True
if "localhost" in line:
print(" ❌ FAIL: bad email in %s" % line)
errors = True
if not sob:
print(" ❌ FAIL missing Signed-off-by tag")
errors = True
if errors:
print("""
❌ ERROR: One or more commits are missing a valid Signed-off-By tag.
This project requires all contributors to assert that their contributions
are provided in compliance with the terms of the Developer's Certificate
of Origin 1.1 (DCO):
https://developercertificate.org/
To indicate acceptance of the DCO every commit must have a tag
Signed-off-by: REAL NAME <EMAIL>
This can be achieved by passing the "-s" flag to the "git commit" command.
To bulk update all commits on current branch "git rebase" can be used:
git rebase -i master -x 'git commit --amend --no-edit -s'
""")
sys.exit(1)
sys.exit(0)

56
.gitlab-ci.d/check-patch.py Executable file
View File

@ -0,0 +1,56 @@
#!/usr/bin/env python3
#
# check-patch.py: run checkpatch.pl across all commits in a branch
#
# Copyright (C) 2020 Red Hat, Inc.
#
# SPDX-License-Identifier: GPL-2.0-or-later
import os
import os.path
import sys
import subprocess
namespace = "qemu-project"
if len(sys.argv) >= 2:
namespace = sys.argv[1]
cwd = os.getcwd()
reponame = os.path.basename(cwd)
repourl = "https://gitlab.com/%s/%s.git" % (namespace, reponame)
# GitLab CI environment does not give us any direct info about the
# base for the user's branch. We thus need to figure out a common
# ancestor between the user's branch and current git master.
subprocess.check_call(["git", "remote", "add", "check-patch", repourl])
subprocess.check_call(["git", "fetch", "check-patch", "master"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL)
ancestor = subprocess.check_output(["git", "merge-base",
"check-patch/master", "HEAD"],
universal_newlines=True)
ancestor = ancestor.strip()
log = subprocess.check_output(["git", "log", "--format=%H %s",
ancestor + "..."],
universal_newlines=True)
subprocess.check_call(["git", "remote", "rm", "check-patch"])
if log == "":
print("\nNo commits since %s, skipping checks\n" % ancestor)
sys.exit(0)
errors = False
print("\nChecking all commits since %s...\n" % ancestor, flush=True)
ret = subprocess.run(["scripts/checkpatch.pl", "--terse", ancestor + "..."])
if ret.returncode != 0:
print(" ❌ FAIL one or more commits failed scripts/checkpatch.pl")
sys.exit(1)
sys.exit(0)

2
.gitlab-ci.d/containers.yml
View File

@ -8,7 +8,7 @@
- export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/$NAME:latest"
- apk add python3
- docker info
- docker login registry.gitlab.com -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD"
- docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD"
script:
- echo "TAG:$TAG"
- echo "COMMON_TAG:$COMMON_TAG"

78
.gitlab-ci.d/crossbuilds.yml
View File

@ -1,5 +1,4 @@
.cross_system_build_job_template: &cross_system_build_job_definition
.cross_system_build_job:
stage: build
image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
timeout: 80m
@ -13,7 +12,24 @@
xtensa-softmmu"
- make -j$(expr $(nproc) + 1) all check-build
.cross_user_build_job_template: &cross_user_build_job_definition
# Job to cross-build specific accelerators.
#
# Set the $ACCEL variable to select the specific accelerator (default to
# KVM), and set extra options (such disabling other accelerators) via the
# $ACCEL_CONFIGURE_OPTS variable.
.cross_accel_build_job:
stage: build
image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
timeout: 30m
script:
- mkdir build
- cd build
- PKG_CONFIG_PATH=$PKG_CONFIG_PATH
../configure --enable-werror $QEMU_CONFIGURE_OPTS --disable-tools
--enable-${ACCEL:-kvm} $ACCEL_CONFIGURE_OPTS
- make -j$(expr $(nproc) + 1) all check-build
.cross_user_build_job:
stage: build
image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
script:
@ -24,91 +40,111 @@
- make -j$(expr $(nproc) + 1) all check-build
cross-armel-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-armel-cross
cross-armel-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-armel-cross
cross-armhf-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-armhf-cross
cross-armhf-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-armhf-cross
cross-arm64-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-arm64-cross
cross-arm64-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-arm64-cross
cross-mips-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-mips-cross
cross-mips-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-mips-cross
cross-mipsel-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-mipsel-cross
cross-mipsel-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-mipsel-cross
cross-mips64el-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-mips64el-cross
cross-mips64el-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-mips64el-cross
cross-ppc64el-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-ppc64el-cross
cross-ppc64el-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-ppc64el-cross
cross-s390x-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: debian-s390x-cross
cross-s390x-user:
<<: *cross_user_build_job_definition
extends: .cross_user_build_job
variables:
IMAGE: debian-s390x-cross
cross-s390x-kvm-only:
extends: .cross_accel_build_job
variables:
IMAGE: debian-s390x-cross
ACCEL_CONFIGURE_OPTS: --disable-tcg
cross-win32-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: fedora-win32-cross
cross-win64-system:
<<: *cross_system_build_job_definition
extends: .cross_system_build_job
variables:
IMAGE: fedora-win64-cross
cross-amd64-xen-only:
extends: .cross_accel_build_job
variables:
IMAGE: debian-amd64-cross
ACCEL: xen
ACCEL_CONFIGURE_OPTS: --disable-tcg --disable-kvm
cross-arm64-xen-only:
extends: .cross_accel_build_job
variables:
IMAGE: debian-arm64-cross
ACCEL: xen
ACCEL_CONFIGURE_OPTS: --disable-tcg --disable-kvm

225
.gitlab-ci.yml
View File

@ -7,12 +7,6 @@ stages:
- build
- test
# We assume GitLab has it's own caching set up for RPM/APT repositories so we
# just take care of avocado assets here.
cache:
paths:
- $HOME/avocado/data/cache
include:
- local: '/.gitlab-ci.d/edk2.yml'
- local: '/.gitlab-ci.d/opensbi.yml'
@ -24,6 +18,7 @@ include:
image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest
before_script:
- JOBS=$(expr $(nproc) + 1)
- sed -i s,git.qemu.org/git,gitlab.com/qemu-project, .gitmodules
script:
- mkdir build
- cd build
@ -32,7 +27,7 @@ include:
../configure --enable-werror $CONFIGURE_ARGS --target-list="$TARGETS" ;
else
../configure --enable-werror $CONFIGURE_ARGS ;
fi
fi || { cat config.log meson-logs/meson-log.txt && exit 1; }
- make -j"$JOBS"
- if test -n "$MAKE_CHECK_ARGS";
then
@ -53,6 +48,11 @@ include:
paths:
- ${CI_PROJECT_DIR}/avocado-cache
policy: pull-push
artifacts:
paths:
- build/tests/results/latest/results.xml
reports:
junit: build/tests/results/latest/results.xml
before_script:
- mkdir -p ~/.config/avocado
- echo "[datadir.paths]" > ~/.config/avocado/avocado.conf
@ -61,9 +61,10 @@ include:
- if [ -d ${CI_PROJECT_DIR}/avocado-cache ]; then
du -chs ${CI_PROJECT_DIR}/avocado-cache ;
fi
- export AVOCADO_ALLOW_UNTRUSTED_CODE=1
after_script:
- cd build
- python3 -c 'import json; r = json.load(open("tests/results/latest/results.json")); [print(t["logfile"]) for t in r["tests"] if t["status"] not in ("PASS", "SKIP")]' | xargs cat
- python3 -c 'import json; r = json.load(open("tests/results/latest/results.json")); [print(t["logfile"]) for t in r["tests"] if t["status"] not in ("PASS", "SKIP", "CANCEL")]' | xargs cat
- du -chs ${CI_PROJECT_DIR}/avocado-cache
build-system-ubuntu:
@ -73,6 +74,7 @@ build-system-ubuntu:
TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu
moxie-softmmu microblazeel-softmmu mips64el-softmmu
MAKE_CHECK_ARGS: check-build
CONFIGURE_ARGS: --enable-docs
artifacts:
expire_in: 2 days
paths:
@ -104,6 +106,7 @@ build-system-debian:
TARGETS: arm-softmmu avr-softmmu i386-softmmu mipsel-softmmu
riscv64-softmmu sh4eb-softmmu sparc-softmmu xtensaeb-softmmu
MAKE_CHECK_ARGS: check-build
CONFIGURE_ARGS: --enable-docs
artifacts:
expire_in: 2 days
paths:
@ -132,7 +135,7 @@ build-system-fedora:
<<: *native_build_job_definition
variables:
IMAGE: fedora
CONFIGURE_ARGS: --disable-gcrypt --enable-nettle
CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs
TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu
xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu
MAKE_CHECK_ARGS: check-build
@ -196,27 +199,84 @@ build-disabled:
<<: *native_build_job_definition
variables:
IMAGE: fedora
CONFIGURE_ARGS: --disable-attr --disable-avx2 --disable-bochs
--disable-brlapi --disable-bzip2 --disable-cap-ng --disable-capstone
--disable-cloop --disable-coroutine-pool --disable-curl --disable-curses
--disable-dmg --disable-docs --disable-glusterfs --disable-gnutls
--disable-gtk --disable-guest-agent --disable-iconv --disable-kvm
--disable-libiscsi --disable-libpmem --disable-libssh --disable-libusb
--disable-libxml2 --disable-linux-aio --disable-live-block-migration
--disable-lzo --disable-malloc-trim --disable-mpath --disable-nettle
--disable-numa --disable-parallels --disable-pie --disable-qcow1
--disable-qed --disable-qom-cast-debug --disable-rbd --disable-rdma
--disable-replication --disable-sdl --disable-seccomp --disable-sheepdog
--disable-slirp --disable-smartcard --disable-snappy --disable-spice
--disable-strip --disable-tpm --disable-usb-redir --disable-vdi
--disable-vhost-crypto --disable-vhost-net --disable-vhost-scsi
--disable-vhost-user --disable-vhost-vdpa --disable-vhost-vsock
--disable-virglrenderer --disable-vnc --disable-vte --disable-vvfat
--disable-xen --disable-zstd
CONFIGURE_ARGS:
--disable-attr
--disable-auth-pam
--disable-avx2
--disable-bochs
--disable-brlapi
--disable-bzip2
--disable-cap-ng
--disable-capstone
--disable-cloop
--disable-coroutine-pool
--disable-curl
--disable-curses
--disable-dmg
--disable-docs
--disable-gcrypt
--disable-glusterfs
--disable-gnutls
--disable-gtk
--disable-guest-agent
--disable-iconv
--disable-keyring
--disable-kvm
--disable-libiscsi
--disable-libpmem
--disable-libssh
--disable-libudev
--disable-libusb
--disable-libxml2
--disable-linux-aio
--disable-live-block-migration
--disable-lzo
--disable-malloc-trim
--disable-mpath
--disable-nettle
--disable-numa
--disable-opengl
--disable-parallels
--disable-pie
--disable-qcow1
--disable-qed
--disable-qom-cast-debug
--disable-rbd
--disable-rdma
--disable-replication
--disable-sdl
--disable-seccomp
--disable-sheepdog
--disable-slirp
--disable-smartcard
--disable-snappy
--disable-sparse
--disable-spice
--disable-strip
--disable-tpm
--disable-usb-redir
--disable-vdi
--disable-vhost-crypto
--disable-vhost-net
--disable-vhost-scsi
--disable-vhost-user
--disable-vhost-vdpa
--disable-vhost-vsock
--disable-virglrenderer
--disable-vnc
--disable-vte
--disable-vvfat
--disable-xen
--disable-zstd
TARGETS: arm-softmmu i386-softmmu ppc64-softmmu mips64-softmmu
s390x-softmmu i386-linux-user
MAKE_CHECK_ARGS: check-qtest SPEED=slow
# This jobs explicitly disable TCG (--disable-tcg), KVM is detected by
# the configure script. The container doesn't contain Xen headers so
# Xen accelerator is not detected / selected. As result it build the
# i386-softmmu and x86_64-softmmu with KVM being the single accelerator
# available.
build-tcg-disabled:
<<: *native_build_job_definition
variables:
@ -224,7 +284,7 @@ build-tcg-disabled:
script:
- mkdir build
- cd build
- ../configure --disable-tcg --audio-drv-list=""
- ../configure --disable-tcg --audio-drv-list="" || { cat config.log meson-logs/meson-log.txt && exit 1; }
- make -j"$JOBS"
- make check-unit
- make check-qapi-schema
@ -232,7 +292,7 @@ build-tcg-disabled:
- ./check -raw 001 002 003 004 005 008 009 010 011 012 021 025 032 033 048
052 063 077 086 101 104 106 113 148 150 151 152 157 159 160 163
170 171 183 184 192 194 197 208 215 221 222 226 227 236 253 277
- ./check -qcow2 028 051 056 057 058 065 067 068 082 085 091 095 096 102 122
- ./check -qcow2 028 051 056 057 058 065 068 082 085 091 095 096 102 122
124 132 139 142 144 145 151 152 155 157 165 194 196 197 200 202
208 209 215 216 218 222 227 234 246 247 248 250 254 255 257 258
260 261 262 263 264 270 272 273 277 279
@ -244,6 +304,22 @@ build-user:
CONFIGURE_ARGS: --disable-tools --disable-system
MAKE_CHECK_ARGS: check-tcg
build-user-static:
<<: *native_build_job_definition
variables:
IMAGE: debian-all-test-cross
CONFIGURE_ARGS: --disable-tools --disable-system --static
MAKE_CHECK_ARGS: check-tcg
# Only build the softmmu targets we have check-tcg tests for
build-some-softmmu:
<<: *native_build_job_definition
variables:
IMAGE: debian-all-test-cross
CONFIGURE_ARGS: --disable-tools --enable-debug-tcg
TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu
MAKE_CHECK_ARGS: check-tcg
# Run check-tcg against linux-user (with plugins)
# we skip sparc64-linux-user until it has been fixed somewhat
# we skip cris-linux-user as it doesn't use the common run loop
@ -255,6 +331,14 @@ build-user-plugins:
MAKE_CHECK_ARGS: check-tcg
timeout: 1h 30m
build-some-softmmu-plugins:
<<: *native_build_job_definition
variables:
IMAGE: debian-all-test-cross
CONFIGURE_ARGS: --disable-tools --disable-user --enable-plugins --enable-debug-tcg
TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu
MAKE_CHECK_ARGS: check-tcg
build-clang:
<<: *native_build_job_definition
variables:
@ -303,7 +387,7 @@ build-oss-fuzz:
| grep -v slirp); do
grep "LLVMFuzzerTestOneInput" ${fuzzer} > /dev/null 2>&1 || continue ;
echo Testing ${fuzzer} ... ;
"${fuzzer}" -runs=1000 -seed=1 || exit 1 ;
"${fuzzer}" -runs=1 -seed=1 || exit 1 ;
done
# Unrelated to fuzzer: run some tests with -fsanitize=address
- cd build-oss-fuzz && make check-qtest-i386 check-unit
@ -317,7 +401,7 @@ build-tci:
- mkdir build
- cd build
- ../configure --enable-tcg-interpreter
--target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)"
--target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)" || { cat config.log meson-logs/meson-log.txt && exit 1; }
- make -j"$JOBS"
- make run-tcg-tests-x86_64-softmmu
- make tests/qtest/boot-serial-test tests/qtest/cdrom-test tests/qtest/pxe-test
@ -329,6 +413,22 @@ build-tci:
- QTEST_QEMU_BINARY="./qemu-system-x86_64" ./tests/qtest/pxe-test
- QTEST_QEMU_BINARY="./qemu-system-s390x" ./tests/qtest/pxe-test -m slow
# Alternate coroutines implementations are only really of interest to KVM users
# However we can't test against KVM on Gitlab-CI so we can only run unit tests
build-coroutine-ucontext:
<<: *native_build_job_definition
variables:
IMAGE: ubuntu2004
CONFIGURE_ARGS: --with-coroutine=ucontext --disable-tcg
MAKE_CHECK_ARGS: check-unit
build-coroutine-sigaltstack:
<<: *native_build_job_definition
variables:
IMAGE: ubuntu2004
CONFIGURE_ARGS: --with-coroutine=sigaltstack --disable-tcg
MAKE_CHECK_ARGS: check-unit
# Most jobs test latest gcrypt or nettle builds
#
# These jobs test old gcrypt and nettle from RHEL7
@ -394,3 +494,68 @@ check-crypto-only-gnutls:
variables:
IMAGE: centos7
MAKE_CHECK_ARGS: check
# We don't need to exercise every backend with every front-end
build-trace-multi-user:
<<: *native_build_job_definition
variables:
IMAGE: ubuntu2004
CONFIGURE_ARGS: --enable-trace-backends=log,simple,syslog --disable-system
build-trace-ftrace-system:
<<: *native_build_job_definition
variables:
IMAGE: ubuntu2004
CONFIGURE_ARGS: --enable-trace-backends=ftrace --target-list=x86_64-softmmu
build-trace-ust-system:
<<: *native_build_job_definition
variables:
IMAGE: ubuntu2004
CONFIGURE_ARGS: --enable-trace-backends=ust --target-list=x86_64-softmmu
check-patch:
stage: build
image: $CI_REGISTRY_IMAGE/qemu/centos8:latest
script: .gitlab-ci.d/check-patch.py
except:
variables:
- $CI_PROJECT_NAMESPACE == 'qemu-project' && $CI_COMMIT_BRANCH == 'master'
variables:
GIT_DEPTH: 1000
allow_failure: true
check-dco:
stage: build
image: $CI_REGISTRY_IMAGE/qemu/centos8:latest
script: .gitlab-ci.d/check-dco.py
except:
variables:
- $CI_PROJECT_NAMESPACE == 'qemu-project' && $CI_COMMIT_BRANCH == 'master'
variables:
GIT_DEPTH: 1000
build-libvhost-user:
stage: build
image: $CI_REGISTRY_IMAGE/qemu/fedora:latest
before_script:
- dnf install -y meson ninja-build
script:
- mkdir subprojects/libvhost-user/build
- cd subprojects/libvhost-user/build
- meson
- ninja
pages:
image: $CI_REGISTRY_IMAGE/qemu/ubuntu2004:latest
stage: test
needs:
- job: build-system-ubuntu
artifacts: true
script:
- mkdir public
- mv build/docs/index.html public/
- for i in devel interop specs system tools user ; do mv build/docs/$i public/ ; done
artifacts:
paths:
- public

2
.mailmap
View File

@ -49,6 +49,8 @@ Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
Filip Bozuta <filip.bozuta@syrmia.com> <filip.bozuta@rt-rk.com.com>
Frederic Konrad <konrad@adacore.com> <fred.konrad@greensocs.com>
Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com>
Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn>
James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
Leif Lindholm <leif@nuviainc.com> <leif.lindholm@linaro.org>
Radoslaw Biernacki <rad@semihalf.com> <radoslaw.biernacki@linaro.org>

85
.travis.yml
View File

@ -49,6 +49,7 @@ addons:
- libvdeplug-dev
- libvte-2.91-dev
- libzstd-dev
- ninja-build
- sparse
- uuid-dev
- gcovr
@ -94,7 +95,7 @@ before_install:
# Configure step - may be overridden
before_script:
- mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
- ${SRC_DIR}/configure ${BASE_CONFIG} ${CONFIG} || { cat config.log && exit 1; }
- ${SRC_DIR}/configure ${BASE_CONFIG} ${CONFIG} || { cat config.log meson-logs/meson-log.txt && exit 1; }
# Main build & test - rarely overridden - controlled by TEST_CMD
script:
@ -118,11 +119,6 @@ after_script:
jobs:
include:
- name: "GCC static (user)"
env:
- CONFIG="--disable-system --static"
- CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
# Just build tools and run minimal unit and softfloat checks
- name: "GCC check-unit and check-softfloat"
env:
@ -152,20 +148,6 @@ jobs:
- CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-default"
# Alternate coroutines implementations are only really of interest to KVM users
# However we can't test against KVM on Travis so we can only run unit tests
- name: "check-unit coroutine=ucontext"
env:
- CONFIG="--with-coroutine=ucontext --disable-tcg"
- TEST_CMD="make check-unit -j${JOBS} V=1"
- name: "check-unit coroutine=sigaltstack"
env:
- CONFIG="--with-coroutine=sigaltstack --disable-tcg"
- TEST_CMD="make check-unit -j${JOBS} V=1"
# Check we can build docs and tools (out of tree)
- name: "tools and docs (bionic)"
dist: bionic
@ -177,6 +159,7 @@ jobs:
addons:
apt:
packages:
- ninja-build
- python3-sphinx
- perl
@ -197,7 +180,7 @@ jobs:
compiler: clang
before_script:
- mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
- ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-fsanitize=undefined -Werror" || { cat config.log && exit 1; }
- ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-fsanitize=undefined -Werror" || { cat config.log meson-logs/meson-log.txt && exit 1; }
- name: "Clang (other-softmmu)"
@ -211,6 +194,10 @@ jobs:
# gprof/gcov are GCC features
- name: "GCC gprof/gcov"
dist: bionic
addons:
apt:
packages:
- ninja-build
env:
- CONFIG="--enable-gprof --enable-gcov --disable-libssh
--target-list=${MAIN_SOFTMMU_TARGETS}"
@ -226,25 +213,6 @@ jobs:
- TEST_CMD=""
# We don't need to exercise every backend with every front-end
- name: "GCC trace log,simple,syslog (user)"
env:
- CONFIG="--enable-trace-backends=log,simple,syslog --disable-system"
- TEST_CMD=""
- name: "GCC trace ftrace (x86_64-softmmu)"
env:
- CONFIG="--enable-trace-backends=ftrace --target-list=x86_64-softmmu"
- TEST_CMD=""
- name: "GCC trace ust (x86_64-softmmu)"
env:
- CONFIG="--enable-trace-backends=ust --target-list=x86_64-softmmu"
- TEST_CMD=""
# Using newer GCC with sanitizers
- name: "GCC9 with sanitizers (softmmu)"
dist: bionic
@ -281,6 +249,7 @@ jobs:
- liburcu-dev
- libusb-1.0-0-dev
- libvte-2.91-dev
- ninja-build
- sparse
- uuid-dev
language: generic
@ -291,35 +260,9 @@ jobs:
- TEST_CMD=""
before_script:
- mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
- ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-g3 -O0 -fsanitize=thread" || { cat config.log && exit 1; }
- ${SRC_DIR}/configure ${CONFIG} --extra-cflags="-g3 -O0 -fsanitize=thread" || { cat config.log meson-logs/meson-log.txt && exit 1; }
# Run check-tcg against linux-user
- name: "GCC check-tcg (user)"
env:
- CONFIG="--disable-system --enable-debug-tcg"
- TEST_BUILD_CMD="make build-tcg"
- TEST_CMD="make check-tcg"
- CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
# Run check-tcg against softmmu targets
- name: "GCC check-tcg (some-softmmu)"
env:
- CONFIG="--enable-debug-tcg --target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu"
- TEST_BUILD_CMD="make build-tcg"
- TEST_CMD="make check-tcg"
- CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
# Run check-tcg against softmmu targets (with plugins)
- name: "GCC plugins check-tcg (some-softmmu)"
env:
- CONFIG="--enable-plugins --enable-debug-tcg --target-list=xtensa-softmmu,arm-softmmu,aarch64-softmmu,alpha-softmmu"
- TEST_BUILD_CMD="make build-tcg"
- TEST_CMD="make check-tcg"
- CACHE_NAME="${TRAVIS_BRANCH}-linux-gcc-debug-tcg"
- name: "[aarch64] GCC check-tcg"
arch: arm64
dist: focal
@ -346,6 +289,7 @@ jobs:
- libusb-1.0-0-dev
- libvdeplug-dev
- libvte-2.91-dev
- ninja-build
# Tests dependencies
- genisoimage
env:
@ -379,6 +323,7 @@ jobs:
- libusb-1.0-0-dev
- libvdeplug-dev
- libvte-2.91-dev
- ninja-build
# Tests dependencies
- genisoimage
env:
@ -411,6 +356,7 @@ jobs:
- libusb-1.0-0-dev
- libvdeplug-dev
- libvte-2.91-dev
- ninja-build
# Tests dependencies
- genisoimage
env:
@ -450,6 +396,7 @@ jobs:
- libzstd-dev
- nettle-dev
- xfslibs-dev
- ninja-build
# Tests dependencies
- genisoimage
env:
@ -463,6 +410,7 @@ jobs:
apt_packages:
- libgcrypt20-dev
- libgnutls28-dev
- ninja-build
env:
- CONFIG="--disable-containers --disable-system"
@ -493,6 +441,7 @@ jobs:
- libusb-1.0-0-dev
- libvdeplug-dev
- libvte-2.91-dev
- ninja-build
env:
- TEST_CMD="make check-unit"
- CONFIG="--disable-containers --disable-tcg --enable-kvm
@ -517,7 +466,7 @@ jobs:
- ls -l ${SRC_DIR}/qemu-${QEMU_VERSION}.tar.bz2
- tar -xf ${SRC_DIR}/qemu-${QEMU_VERSION}.tar.bz2 && cd qemu-${QEMU_VERSION}
- mkdir -p release-build && cd release-build
- ../configure ${BASE_CONFIG} ${CONFIG} || { cat config.log && exit 1; }
- ../configure ${BASE_CONFIG} ${CONFIG} || { cat config.log meson-logs/meson-log.txt && exit 1; }
- make install
allow_failures:
- env: UNRELIABLE=true

9
CODING_STYLE.rst
View File

@ -85,8 +85,13 @@ Line width
Lines should be 80 characters; try not to make them longer.
Sometimes it is hard to do, especially when dealing with QEMU subsystems
that use long function or symbol names. Even in that case, do not make
lines much longer than 80 characters.
that use long function or symbol names. If wrapping the line at 80 columns
is obviously less readable and more awkward, prefer not to wrap it; better
to have an 85 character line than one which is awkwardly wrapped.
Even in that case, try not to make lines much longer than 80 characters.
(The checkpatch script will warn at 100 characters, but this is intended
as a guard against obviously-overlength lines, not a target.)
Rationale:

580
Changelog
View File

@ -1,580 +0,0 @@
This file documents changes for QEMU releases 0.12 and earlier.
For changelog information for later releases, see
https://wiki.qemu.org/ChangeLog or look at the git history for
more detailed information.
version 0.12.0:
- Update to SeaBIOS 0.5.0
- e1000: fix device link status in Linux (Anthony Liguori)
- monitor: fix QMP for balloon command (Luiz Capitulino)
- QMP: Return an empty dict by default (Luiz Capitulino)
- QMP: Only handle converted commands (Luiz Capitulino)
- pci: support PCI based option rom loading (Gerd Hoffman/Anthony Liguori)
- Fix backcompat for hotplug of SCSI controllers (Daniel P. Berrange)
- fdc: fix migration from 0.11 (Juan Quintela)
- vmware-vga: fix segv on cursor resize. (Dave Airlie)
- vmware-vga: various fixes (Dave Airlie/Anthony Liguori)
- qdev: improve property error reporting. (Gerd Hoffmann)
- fix vga names in default_list (Gerd Hoffmann)
- usb-host: check mon before using it. (Gerd Hoffmann)
- usb-net: use qdev for -usbdevice (Gerd Hoffmann)
- monitor: Catch printing to non-existent monitor (Luiz Capitulino)
- Avoid permanently disabled QEMU monitor when UNIX migration fails (Daniel P. Berrange)
- Fix loading of ELF multiboot kernels (Kevin Wolf)
- qemu-io: Fix memory leak (Kevin Wolf)
- Fix thinko in linuxboot.S (Paolo Bonzini)
- target-i386: Fix evaluation of DR7 register (Jan Kiszka)
- vnc: hextile: do not generate ForegroundSpecified and SubrectsColoured tiles (Anthony Liguori)
- S390: Bail out without KVM (Alexander Graf)
- S390: Don't tell guest we're updating config space (Alexander Graf)
- target-s390: Fail on unknown instructions (Alexander Graf)
- osdep: Fix runtime failure on older Linux kernels (Andre Przywara)
- Fix a make -j race (Juergen Lock)
- target-alpha: Fix generic ctz64. (Richard Henderson)
- s390: Fix buggy assignment (Stefan Weil)
- target-mips: fix user-mode emulation startup (Nathan Froyd)
- target-i386: Update CPUID feature set for TCG (Andre Przywara)
- s390: fix build on 32 bit host (Michael S. Tsirkin)
version 0.12.0-rc2:
- v2: properly save kvm system time msr registers (Glauber Costa)
- convert more monitor commands to qmp (Luiz Capitulino)
- vnc: fix capslock tracking logic. (Gerd Hoffmann)
- QemuOpts: allow larger option values. (Gerd Hoffmann)
- scsi: fix drive hotplug. (Gerd Hoffmann)
- pci: don't hw_error() when no slot is available. (Gerd Hoffmann)
- pci: don't abort() when trying to hotplug with acpi off. (Gerd Hoffmann)
- allow default devices to be implemented in config file (Gerd Hoffman)
- vc: colorize chardev title line with blue background. (Gerd Hoffmann)
- chardev: make chardevs specified in config file work. (Gerd Hoffmann)
- qdev: also match bus name for global properties (Gerd Hoffmann)
- qdev: add command line option to set global defaults for properties. (Gerd Hoffmann)
- kvm: x86: Save/restore exception_index (Jan Kiszka)
- qdev: Replace device names containing whitespace (Markus Armbruster)
- fix rtc-td-hack on host without high-res timers (Gleb Natapov)
- virtio: verify features on load (Michael S. Tsirkin)
- vmware_vga: add rom file so that it boots. (Dave Airlie)
- Do not abort on qemu_malloc(0) in production builds (Anthony Liguori)
- Fix ARM userspace strex implementation. (Paul Brook)
- qemu: delete rule target on error (Michael S. Tsirkin)
- QMP: add human-readable description to error response (Markus Armbruster)
- convert more monitor commands to QError (Markus Armbruster)
- monitor: Fix double-prompt after "change vnc passwd BLA" (Markus Armbruster)
- monitor: do_cont(): Don't ask for passwords (Luiz Capitulino)
- monitor: Introduce 'block_passwd' command (Luiz Capitulino)
- pci: interrupt disable bit support (Michael S. Tsirkin)
- pci: interrupt status bit implementation (Michael S. Tsirkin)
- pci: prepare irq code for interrupt state (Michael S. Tsirkin)
- msix: function mask support (Michael S. Tsirkin)
- msix: macro rename for function mask support (Michael S. Tsirkin)
- cpuid: Fix multicore setup on Intel (Andre Przywara)
- kvm: x86: Fix initial kvm_has_msr_star (Jan Kiszka)
- Update OpenBIOS images to r640 (Aurelien Jarno)
version 0.10.2:
- fix savevm/loadvm (Anthony Liguori)
- live migration: fix dirty tracking windows (Glauber Costa)
- live migration: improve error propagation (Glauber Costa)
- qcow2: fix image creation for > ~2TB images (Chris Wright)
- hotplug: fix error handling for if= parameter (Eduardo Habkost)
- qcow2: fix data corruption (Nolan Leake)
- virtio: fix guest oops with 2.6.25 kernels (Rusty Russell)
- SH4: add support for -kernel (Takashi Yoshii, Aurelien Jarno)
- hotplug: fix closing of char devices (Jan Kiszka)
- hotplug: remove incorrect check for device name (Eduardo Habkost)
- enable -k on win32 (Herve Poussineau)
- configure: use LANG=C for grep (Andreas Faerber)
- fix VGA regression (malc)
version 0.10.1:
- virtio-net: check right return size on sg list (Alex Williamson)
- Make qemu_announce_self handle holes (live migration after hotplug)
(Marcelo Tosatti)
- Revert r6804-r6808 (qcow2 allocation info). This series of changes added
a high cost to startup for large qcow2 images (Anthony Liguori)
- qemu-img: fix help message (Aurelien Jarno)
- Fix build for non-default installs of SDL (Anthony Liguori)
- Fix race condition in env->interrupt_request. When using TCG and a dynticks
host timer, this condition could cause TCG to get stuck in an infinite
loop (Aurelien Jarno)
- Fix reading encrypted hard disk passwords during early startup (Jan Kiszka)
- Fix encrypted disk reporting in 'info block' (Jan Kiszka)
- Fix console size with tiny displays (MusicPal) (Jan Kiszka)
- Improve error handling in bdrv_open2 (Jan Kiszka)
- Avoid leaking data in mux'ed character devices (Jan Kiszka)
- Fix initial character device reset (no banner in monitor) (Jan Kiszka)
- Fix cpuid KVM crash on i386 host (Lubomir Rintel)
- Fix SLES10sp2 installation by adding ISTAT1 register to LSI SCSI emulation
(Ryan Harper)
version 0.10.0:
- TCG support (No longer requires GCC 3.x)
- Kernel Virtual Machine acceleration support
- BSD userspace emulation
- Bluetooth emulation and host passthrough support
- GDB XML register description support
- Intel e1000 emulation
- HPET emulation
- VirtIO paravirtual device support
- Marvell 88w8618 / MusicPal emulation
- Nokia N-series tablet emulation / OMAP2 processor emulation
- PCI hotplug support
- Live migration and new save/restore formats
- Curses display support
- qemu-nbd utility to mount supported block formats
- Altivec support in PPC emulation and new firmware (OpenBIOS)
- Multiple VNC clients are now supported
- TLS encryption is now supported in VNC
- MIPS Magnum R4000 machine (Hervé Poussineau)
- Braille support (Samuel Thibault)
- Freecom MusicPal system emulation (Jan Kiszka)
- OMAP242x and Nokia N800, N810 machines (Andrzej Zaborowski)
- EsounD audio driver (Frederick Reeve)
- Gravis Ultrasound GF1 sound card (Tibor "TS" Schütz)
- Many, many, bug fixes and new features
version 0.9.1:
- TFTP booting from host directory (Anthony Liguori, Erwan Velu)
- Tap device emulation for Solaris (Sittichai Palanisong)
- Monitor multiplexing to several I/O channels (Jason Wessel)
- ds1225y nvram support (Herve Poussineau)
- CPU model selection support (J. Mayer, Paul Brook, Herve Poussineau)
- Several Sparc fixes (Aurelien Jarno, Blue Swirl, Robert Reif)
- MIPS 64-bit FPU support (Thiemo Seufer)
- Xscale PDA emulation (Andrzej Zaborowski)
- ColdFire system emulation (Paul Brook)
- Improved SH4 support (Magnus Damm)
- MIPS64 support (Aurelien Jarno, Thiemo Seufer)
- Preliminary Alpha guest support (J. Mayer)
- Read-only support for Parallels disk images (Alex Beregszaszi)
- SVM (x86 virtualization) support (Alexander Graf)
- CRIS emulation (Edgar E. Iglesias)
- SPARC32PLUS execution support (Blue Swirl)
- MIPS mipssim pseudo machine (Thiemo Seufer)
- Strace for Linux userland emulation (Stuart Anderson, Thayne Harbaugh)
- OMAP310 MPU emulation plus Palm T|E machine (Andrzej Zaborowski)
- ARM v6, v7, NEON SIMD and SMP emulation (Paul Brook/CodeSourcery)
- Gumstix boards: connex and verdex emulation (Thorsten Zitterell)
- Intel mainstone II board emulation (Armin Kuster)
- VMware SVGA II graphics card support (Andrzej Zaborowski)
version 0.9.0:
- Support for relative paths in backing files for disk images
- Async file I/O API
- New qcow2 disk image format
- Support of multiple VM snapshots
- Linux: specific host CDROM and floppy support
- SMM support
- Moved PCI init, MP table init and ACPI table init to Bochs BIOS
- Support for MIPS32 Release 2 instruction set (Thiemo Seufer)
- MIPS Malta system emulation (Aurelien Jarno, Stefan Weil)
- Darwin userspace emulation (Pierre d'Herbemont)
- m68k user support (Paul Brook)
- several x86 and x86_64 emulation fixes
- Mouse relative offset VNC extension (Anthony Liguori)
- PXE boot support (Anthony Liguori)
- '-daemonize' option (Anthony Liguori)
version 0.8.2:
- ACPI support
- PC VGA BIOS fixes
- switch to OpenBios for SPARC targets (Blue Swirl)
- VNC server fixes
- MIPS FPU support (Marius Groeger)
- Solaris/SPARC host support (Juergen Keil)
- PPC breakpoints and single stepping (Jason Wessel)
- USB updates (Paul Brook)
- UDP/TCP/telnet character devices (Jason Wessel)
- Windows sparse file support (Frediano Ziglio)
- RTL8139 NIC TCP segmentation offloading (Igor Kovalenko)
- PCNET NIC support (Antony T Curtis)
- Support for variable frequency host CPUs
- Workaround for win32 SMP hosts
- Support for AMD Flash memories (Jocelyn Mayer)
- Audio capture to WAV files support (malc)
version 0.8.1:
- USB tablet support (Brad Campbell, Anthony Liguori)
- win32 host serial support (Kazu)
- PC speaker support (Joachim Henke)
- IDE LBA48 support (Jens Axboe)
- SSE3 support
- Solaris port (Juergen Keil)
- Preliminary SH4 target (Samuel Tardieu)
- VNC server (Anthony Liguori)
- slirp fixes (Ed Swierk et al.)
- USB fixes
- ARM Versatile Platform Baseboard emulation (Paul Brook)
version 0.8.0:
- ARM system emulation: Arm Integrator/CP board with an arm1026ej-s
cpu (Paul Brook)
- SMP support
- Mac OS X cocoa improvements (Mike Kronenberg)
- Mac OS X CoreAudio driver (Mike Kronenberg)
- DirectSound driver (malc)
- ALSA audio driver (malc)
- new audio options: '-soundhw' and '-audio-help' (malc)
- ES1370 PCI audio device (malc)
- Initial USB support
- Linux host serial port access
- Linux host low level parallel port access
- New network emulation code supporting VLANs.
- MIPS and MIPSel User Linux emulation
- MIPS fixes to boot Linux (Daniel Jacobowitz)
- NX bit support
- Initial SPARC SMP support (Blue Swirl)
- Major overhaul of the virtual FAT driver for read/write support
(Johannes Schindelin)
version 0.7.2:
- x86_64 fixes (Win2000 and Linux 2.6 boot in 32 bit)
- merge self modifying code handling in dirty ram page mechanism.
- MIPS fixes (Ralf Baechle)
- better user net performances
version 0.7.1:
- read-only Virtual FAT support (Johannes Schindelin)
- Windows 2000 install disk full hack (original idea from Vladimir
N. Oleynik)
- VMDK disk image creation (Filip Navara)
- SPARC64 progress (Blue Swirl)
- initial MIPS support (Jocelyn mayer)
- MIPS improvements (Ralf Baechle)
- 64 bit fixes in user networking (initial patch by Gwenole Beauchesne)
- IOAPIC support (Filip Navara)
version 0.7.0:
- better BIOS translation and HDD geometry auto-detection
- user mode networking bug fix
- undocumented FPU ops support
- Cirrus VGA: support for 1280x1024x[8,15,16] modes
- 'pidfile' option
- .dmg disk image format support (Johannes Schindelin)
- keymaps support (initial patch by Johannes Schindelin)
- big endian ARM support (Lennert Buytenhek)
- added generic 64 bit target support
- x86_64 target support
- initial APIC support
- MMX/SSE/SSE2/PNI support
- PC parallel port support (Mark Jonckheere)
- initial SPARC64 support (Blue Swirl)
- SPARC target boots Linux (Blue Swirl)
- armv5te user mode support (Paul Brook)
- ARM VFP support (Paul Brook)
- ARM "Angel" semihosting syscalls (Paul Brook)
- user mode gdb stub support (Paul Brook)
- Samba 3 support
- initial Cocoa support (Pierre d'Herbemont)
- generic FPU emulation code
- Virtual PC read-only disk image support (Alex Beregszaszi)
version 0.6.1:
- Mac OS X port (Pierre d'Herbemont)
- Virtual console support
- Better monitor line edition
- New block device layer
- New 'qcow' growable disk image support with AES encryption and
transparent decompression
- VMware 3 and 4 read-only disk image support (untested)
- Support for up to 4 serial ports
- TFTP server support (Magnus Damm)
- Port redirection support in user mode networking
- Support for not executable data sections
- Compressed loop disk image support (Johannes Schindelin)
- Level triggered IRQ fix (aka NE2000 PCI performance fix) (Steve
Wormley)
- Fixed Fedora Core 2 problems (now you can run qemu without any
LD_ASSUME_KERNEL tricks on FC2)
- DHCP fix for Windows (accept DHCPREQUEST alone)
- SPARC system emulation (Blue Swirl)
- Automatic Samba configuration for host file access from Windows.
- '-loadvm' and '-full-screen' options
- ne2000 savevm support (Johannes Schindelin)
- Ctrl-Alt is now the default grab key. Ctrl-Alt-[0-9] switches to
the virtual consoles.
- BIOS floppy fix for NT4 (Mike Nordell, Derek Fawcus, Volker Ruppert)
- Floppy fixes for NT4 and NT5 (Mike Nordell)
- NT4 IDE fixes (Ben Pfaf, Mike Nordell)
- SDL Audio support and SB16 fixes (malc)
- ENTER instruction bug fix (initial patch by Stefan Kisdaroczi)
- VGA font change fix
- VGA read-only CRTC register fix
version 0.6.0:
- minimalist FPU exception support (NetBSD FPU probe fix)
- cr0.ET fix (Win95 boot)
- *BSD port (Markus Niemisto)
- I/O access fix (signaled by Mark Jonckheere)
- IDE drives serial number fix (Mike Nordell)
- int13 CDROM BIOS fix (aka Solaris x86 install CD fix)
- int15, ah=86 BIOS fix (aka Solaris x86 hardware probe hang up fix)
- BSR/BSF "undefined behaviour" fix
- vmdk2raw: convert VMware disk images to raw images
- PCI support
- NE2K PCI support
- dummy VGA PCI support
- VGA font selection fix (Daniel Serpell)
- PIC reset fix (Hidemi KAWAI)
- PIC spurious irq support (aka Solaris install bug)
- added '-localtime' option
- Cirrus CL-GD54xx VGA support (initial patch by Makoto Suzuki (suzu))
- APM and system shutdown support
- Fixed system reset
- Support for other PC BIOSes
- Initial PowerMac hardware emulation
- PowerMac/PREP OpenFirmware compatible BIOS (Jocelyn Mayer)
- initial IDE BMDMA support (needed for Darwin x86)
- Set the default memory size for PC emulation to 128 MB
version 0.5.5:
- SDL full screen support (initial patch by malc)
- VGA support on PowerPC PREP
- VBE fixes (Matthew Mastracci)
- PIT fixes (aka Win98 hardware probe and "VGA slowness" bug)
- IDE master only fixes (aka Win98 CD-ROM probe bug)
- ARM load/store half word fix (Ulrich Hecht)
- FDC fixes for Win98
version 0.5.4:
- qemu-fast fixes
- BIOS area protection fix (aka EMM386.EXE fix) (Mike Nordell)
- keyboard/mouse fix (Mike Nordell)
- IDE fixes (Linux did not recognized slave drivers)
- VM86 EIP masking fix (aka NT5 install fix) (Mike Nordell)
- QEMU can now boot a PowerPC Linux kernel (Jocelyn Mayer)
- User mode network stack
- imul imm8 fix + 0x82 opcode support (Hidemi KAWAI)
- precise self modifying code (aka BeOS install bug)
version 0.5.3:
- added Bochs VESA VBE support
- VGA memory map mode 3 access fix (OS/2 install fix)
- IDE fixes (Jens Axboe)
- CPU interrupt fixes
- fixed various TLB invalidation cases (NT install)
- fixed cr0.WP semantics (XP install)
- direct chaining support for SPARC and PowerPC (faster)
- ARM NWFPE support (initial patch by Ulrich Hecht)
- added specific x86 to x86 translator (close to native performance
in qemu-i386 and qemu-fast)
- shm syscalls support (Paul McKerras)
- added accurate CR0.MP/ME/TS emulation
- fixed DMA memory write access (Win95 boot floppy fix)
- graphical x86 linux loader
- command line monitor
- generic removable device support
- support of CD-ROM change
- multiple network interface support
- initial x86-64 host support (Gwenole Beauchesne)
- lret to outer privilege fix (OS/2 install fix)
- task switch fixes (SkyOS boot)
- VM save/restore commands
- new timer API
- more precise RTC emulation (periodic timers + time updates)
- Win32 port (initial patch by Kazu)
version 0.5.2:
- improved soft MMU speed (assembly functions and specializing)
- improved multitasking speed by avoiding flushing TBs when
switching tasks
- improved qemu-fast speed
- improved self modifying code handling (big performance gain in
softmmu mode).
- fixed IO checking
- fixed CD-ROM detection (win98 install CD)
- fixed addseg real mode bug (GRUB boot fix)
- added ROM memory support (win98 boot)
- fixed 'call Ev' in case of paging exception
- updated the script 'qemu-binfmt-conf.sh' to use QEMU automagically
when launching executables for the supported target CPUs.
- PowerPC system emulation update (Jocelyn Mayer)
- PC floppy emulation and DMA fixes (Jocelyn Mayer)
- polled mode for PIC (Jocelyn Mayer)
- fixed PTE dirty bit handling
- fixed xadd same reg bug
- fixed cmpxchg exception safeness
- access to virtual memory in gdb stub
- task gate and NT flag fixes
- eflags optimisation fix for string operations
version 0.5.1:
- float access fixes when using soft mmu
- PC emulation support on PowerPC
- A20 support
- IDE CD-ROM emulation
- ARM fixes (Ulrich Hecht)
- SB16 emulation (malc)
- IRET and INT fixes in VM86 mode with IOPL=3
- Port I/Os use TSS io map
- Full task switching/task gate support
- added verr, verw, arpl, fcmovxx
- PowerPC target support (Jocelyn Mayer)
- Major SPARC target fixes (dynamically linked programs begin to work)
version 0.5.0:
- full hardware level VGA emulation
- graphical display with SDL
- added PS/2 mouse and keyboard emulation
- popw (%esp) fix
- mov to/from segment data width fix
- added real mode support
- added Bochs BIOS and LGPL'ed VGA BIOS loader in qemu
- m68k host port (Richard Zidlicky)
- partial soft MMU support for memory mapped I/Os
- multi-target build
- fixed: no error code in hardware interrupts
- fixed: pop ss, mov ss, x and sti disable hardware irqs for the next insn
- correct single stepping through string operations
- preliminary SPARC target support (Thomas M. Ogrisegg)
- tun-fd option (Rusty Russell)
- automatic IDE geometry detection
- renamed 'vl' to qemu[-fast] and user qemu to qemu-{cpu}.
- added man page
- added full soft mmu mode to launch unpatched OSes.
version 0.4.3:
- x86 exception fix in case of nop instruction.
- gcc 3.2.2 bug workaround (RedHat 9 fix)
- sparc and Alpha host fixes
- many ARM target fixes: 'ls' and 'bash' can be launched.
version 0.4.2:
- many exception handling fixes (can compile a Linux kernel inside vl)
- IDE emulation support
- initial GDB stub support
- deferred update support for disk images (Rusty Russell)
- accept User Mode Linux Copy On Write disk images
- SMP kernels can at least be booted
version 0.4.1:
- more accurate timer support in vl.
- more reliable NE2000 probe in vl.
- added 2.5.66 kernel in vl-test.
- added VLTMPDIR environment variable in vl.
version 0.4:
- initial support for ring 0 x86 processor emulation
- fixed signal handling for correct dosemu DPMI emulation
- fast x86 MMU emulation with mmap()
- fixed popl (%esp) case
- Linux kernel can be executed by QEMU with the 'vl' command.
version 0.3:
- initial support for ARM emulation
- added fnsave, frstor, fnstenv, fldenv FPU instructions
- added FPU register save in signal emulation
- initial ARM port
- Sparc and Alpha ports work on the regression test
- generic ioctl number conversion
- fixed ioctl type conversion
version 0.2:
- PowerPC disassembly and ELF symbols output (Rusty Russell)
- flock support (Rusty Russell)
- ugetrlimit support (Rusty Russell)
- fstat64 fix (Rusty Russell)
- initial Alpha port (Falk Hueffner)
- initial IA64 port (Matt Wilson)
- initial Sparc and Sparc64 port (David S. Miller)
- added HLT instruction
- LRET instruction fix.
- added GPF generation for I/Os.
- added INT3 and TF flag support.
- SHL instruction C flag fix.
- mmap emulation for host page size > 4KB
- self-modifying code support
- better VM86 support (dosemu works on non trivial programs)
- precise exception support (EIP is computed correctly in most cases)
- more precise LDT/GDT/IDT emulation
- faster segment load in vm86 mode
- direct chaining of basic blocks (faster emulation)
version 0.1.6:
- automatic library search system. QEMU can now work with unpatched
ELF dynamic loader and libc (Rusty Russell).
- ISO C warning fixes (Alistair Strachan)
- first self-virtualizable version (works only as long as the
translation cache is not flushed)
- RH9 fixes
version 0.1.5:
- ppc64 support + personality() patch (Rusty Russell)
- first Alpha CPU patches (Falk Hueffner)
- removed bfd.h dependency
- fixed shrd, shld, idivl and divl on PowerPC.
- fixed buggy glibc PowerPC rint() function (test-i386 passes now on PowerPC).
version 0.1.4:
- more accurate VM86 emulation (can launch small DOS 16 bit
executables in wine).
- fixed push/pop fs/gs
- added iret instruction.
- added times() syscall and SIOCATMARK ioctl.
version 0.1.3:
- S390 support (Ulrich Weigand)
- glibc 2.3.x compile fix (Ulrich Weigand)
- socketcall endian fix (Ulrich Weigand)
- struct sockaddr endian fix (Ulrich Weigand)
- sendmsg/recvmsg endian fix (Ulrich Weigand)
- execve endian fix (Ulrich Weigand)
- fdset endian fix (Ulrich Weigand)
- partial setsockopt syscall support (Ulrich Weigand)
- more accurate pushf/popf emulation
- first partial vm86() syscall support (can be used with runcom example).
- added bound, cmpxchg8b, cpuid instructions
- added 16 bit addressing support/override for string operations
- poll() fix
version 0.1.2:
- compile fixes
- xlat instruction
- xchg instruction memory lock
- added simple vm86 example (not working with QEMU yet). The 54 byte
DOS executable 'pi_10.com' program was released by Bertram
Felgenhauer (more information at http://www.boo.net/~jasonp/pipage.html).
version 0.1.1:
- glibc 2.2 compilation fixes
- added -s and -L options
- binary distribution of x86 glibc and wine
- big endian fixes in ELF loader and getdents.
version 0.1:
- initial public release.

206
MAINTAINERS
View File

@ -112,12 +112,11 @@ L: qemu-s390x@nongnu.org
Guest CPU cores (TCG)
---------------------
Overall TCG CPUs
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
R: Paolo Bonzini <pbonzini@redhat.com>
S: Maintained
F: softmmu/cpus.c
F: cpus-common.c
F: exec.c
F: accel/tcg/
F: accel/stubs/tcg-stub.c
F: scripts/decodetree.py
@ -139,7 +138,7 @@ F: include/fpu/
F: tests/fp/
Alpha TCG CPUs
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Maintained
F: target/alpha/
F: tests/tcg/alpha/
@ -159,6 +158,7 @@ F: disas/arm.c
F: disas/arm-a64.cc
F: disas/libvixl/
F: docs/system/target-arm.rst
F: docs/system/arm/cpu-features.rst
ARM SMMU
M: Eric Auger <eric.auger@redhat.com>
@ -186,7 +186,7 @@ F: tests/tcg/cris/
F: disas/cris.c
HPPA (PA-RISC) TCG CPUs
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Maintained
F: target/hppa/
F: hw/hppa/
@ -221,14 +221,14 @@ F: hw/microblaze/
F: disas/microblaze.c
MIPS TCG CPUs
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
M: Philippe Mathieu-Daudé <f4bug@amsat.org>
R: Aurelien Jarno <aurelien@aurel32.net>
R: Jiaxun Yang <jiaxun.yang@flygoat.com>
R: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>
S: Maintained
S: Odd Fixes
F: target/mips/
F: default-configs/*mips*
F: disas/*mips*
F: disas/mips.c
F: docs/system/cpu-models-mips.rst.inc
F: hw/intc/mips_gic.c
F: hw/mips/
@ -238,11 +238,13 @@ F: include/hw/intc/mips_gic.h
F: include/hw/mips/
F: include/hw/misc/mips_*
F: include/hw/timer/mips_gictimer.h
F: tests/acceptance/linux_ssh_mips_malta.py
F: tests/acceptance/machine_mips_malta.py
F: tests/tcg/mips/
K: ^Subject:.*(?i)mips
MIPS TCG CPUs (nanoMIPS ISA)
S: Orphan
F: disas/nanomips.*
Moxie TCG CPUs
M: Anthony Green <green@moxielogic.com>
S: Maintained
@ -257,7 +259,6 @@ M: Marek Vasut <marex@denx.de>
S: Maintained
F: target/nios2/
F: hw/nios2/
F: hw/intc/nios2_iic.c
F: disas/nios2.c
F: default-configs/nios2-softmmu.mak
@ -270,6 +271,7 @@ F: tests/tcg/openrisc/
PowerPC TCG CPUs
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Maintained
F: target/ppc/
@ -292,11 +294,11 @@ F: linux-user/host/riscv64/
RENESAS RX CPUs
M: Yoshinori Sato <ysato@users.sourceforge.jp>
S: Maintained
S: Odd Fixes
F: target/rx/
S390 TCG CPUs
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
M: David Hildenbrand <david@redhat.com>
S: Maintained
F: target/s390x/
@ -332,7 +334,7 @@ F: include/hw/unicore32/
X86 TCG CPUs
M: Paolo Bonzini <pbonzini@redhat.com>
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
M: Eduardo Habkost <ehabkost@redhat.com>
S: Maintained
F: target/i386/
@ -341,7 +343,7 @@ F: tests/tcg/x86_64/
F: hw/i386/
F: disas/i386.c
F: docs/system/cpu-models-x86.rst.inc
T: git https://github.com/ehabkost/qemu.git x86-next
T: git https://gitlab.com/ehabkost/qemu.git x86-next
Xtensa TCG CPUs
M: Max Filippov <jcmvbkbc@gmail.com>
@ -386,13 +388,13 @@ S: Maintained
F: target/arm/kvm.c
MIPS KVM CPUs
M: Huacai Chen <chenhc@lemote.com>
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
M: Huacai Chen <chenhuacai@kernel.org>
S: Odd Fixes
F: target/mips/kvm.c
PPC KVM CPUs
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
S: Maintained
F: target/ppc/kvm.c
@ -424,13 +426,13 @@ M: Paolo Bonzini <pbonzini@redhat.com>
M: Marcelo Tosatti <mtosatti@redhat.com>
L: kvm@vger.kernel.org
S: Supported
F: target/i386/kvm.c
F: target/i386/kvm/
F: scripts/kvm/vmxcap
Guest CPU Cores (other accelerators)
------------------------------------
Overall
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
R: Paolo Bonzini <pbonzini@redhat.com>
S: Maintained
F: include/sysemu/accel.h
@ -443,17 +445,13 @@ M: Cameron Esfahani <dirty@apple.com>
M: Roman Bolshakov <r.bolshakov@yadro.com>
W: https://wiki.qemu.org/Features/HVF
S: Maintained
F: accel/stubs/hvf-stub.c
F: target/i386/hvf/
F: include/sysemu/hvf.h
WHPX CPUs
M: Sunil Muthuswamy <sunilmut@microsoft.com>
S: Supported
F: target/i386/whpx-all.c
F: target/i386/whpx-cpus.c
F: target/i386/whp-dispatch.h
F: accel/stubs/whpx-stub.c
F: target/i386/whpx/
F: include/sysemu/whpx.h
Guest CPU Cores (Xen)
@ -493,7 +491,7 @@ W: https://github.com/intel/haxm/issues
S: Maintained
F: accel/stubs/hax-stub.c
F: include/sysemu/hax.h
F: target/i386/hax-*
F: target/i386/hax/
Hosts
-----
@ -534,7 +532,7 @@ F: qemu.nsi
Alpha Machines
--------------
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Maintained
F: hw/alpha/
F: hw/isa/smc37c669-superio.c
@ -558,7 +556,7 @@ S: Maintained
F: hw/*/allwinner-h3*
F: include/hw/*/allwinner-h3*
F: hw/arm/orangepi.c
F: docs/system/orangepi.rst
F: docs/system/arm/orangepi.rst
ARM PrimeCell and CMSDK devices
M: Peter Maydell <peter.maydell@linaro.org>
@ -759,8 +757,10 @@ L: qemu-arm@nongnu.org
S: Supported
F: hw/*/npcm7xx*
F: include/hw/*/npcm7xx*
F: tests/qtest/npcm7xx*
F: pc-bios/npcm7xx_bootrom.bin
F: roms/vbootrom
F: docs/system/arm/nuvoton.rst
nSeries
M: Andrzej Zaborowski <balrogg@gmail.com>
@ -800,6 +800,7 @@ F: hw/arm/raspi_platform.h
F: hw/*/bcm283*
F: include/hw/arm/raspi*
F: include/hw/*/bcm283*
F: docs/system/arm/raspi.rst
Real View
M: Peter Maydell <peter.maydell@linaro.org>
@ -854,6 +855,7 @@ R: Leif Lindholm <leif@nuviainc.com>
L: qemu-arm@nongnu.org
S: Maintained
F: hw/arm/sbsa-ref.c
F: docs/system/arm/sbsa.rst
Sharp SL-5500 (Collie) PDA
M: Peter Maydell <peter.maydell@linaro.org>
@ -998,6 +1000,7 @@ F: include/hw/*/*aspeed*
F: include/hw/misc/pca9552*.h
F: hw/net/ftgmac100.c
F: include/hw/net/ftgmac100.h
F: docs/system/arm/aspeed.rst
NRF51
M: Joel Stanley <joel@jms.id.au>
@ -1043,7 +1046,7 @@ F: hw/*/etraxfs_*.c
HP-PARISC Machines
------------------
HP B160L
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
R: Helge Deller <deller@gmx.de>
S: Odd Fixes
F: default-configs/hppa-softmmu.mak
@ -1124,10 +1127,9 @@ F: hw/display/jazz_led.c
F: hw/dma/rc4030.c
Malta
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
M: Philippe Mathieu-Daudé <f4bug@amsat.org>
R: Aurelien Jarno <aurelien@aurel32.net>
S: Maintained
S: Odd Fixes
F: hw/isa/piix4.c
F: hw/acpi/piix4.c
F: hw/mips/malta.c
@ -1137,23 +1139,14 @@ F: tests/acceptance/linux_ssh_mips_malta.py
F: tests/acceptance/machine_mips_malta.py
Mipssim
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
R: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>
S: Odd Fixes
S: Orphaned
F: hw/mips/mipssim.c
F: hw/net/mipsnet.c
R4000
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
R: Aurelien Jarno <aurelien@aurel32.net>
R: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>
S: Obsolete
F: hw/mips/r4k.c
Fuloong 2E
M: Huacai Chen <chenhc@lemote.com>
M: Huacai Chen <chenhuacai@kernel.org>
M: Philippe Mathieu-Daudé <f4bug@amsat.org>
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
R: Jiaxun Yang <jiaxun.yang@flygoat.com>
S: Odd Fixes
F: hw/mips/fuloong2e.c
@ -1162,15 +1155,15 @@ F: hw/pci-host/bonito.c
F: include/hw/isa/vt82c686.h
Loongson-3 virtual platforms
M: Huacai Chen <chenhc@lemote.com>
M: Huacai Chen <chenhuacai@kernel.org>
R: Jiaxun Yang <jiaxun.yang@flygoat.com>
S: Maintained
F: hw/intc/loongson_liointc.c
Boston
M: Paul Burton <pburton@wavecomp.com>
M: Paul Burton <paulburton@kernel.org>
R: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>
S: Maintained
S: Odd Fixes
F: hw/core/loader-fit.c
F: hw/mips/boston.c
F: hw/pci-host/xilinx-pcie.c
@ -1187,18 +1180,21 @@ PowerPC Machines
----------------
405
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc/ppc405_boards.c
Bamboo
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc/ppc440_bamboo.c
e500
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc/e500*
@ -1212,6 +1208,7 @@ F: pc-bios/u-boot.e500
mpc8544ds
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc/mpc8544ds.c
@ -1220,6 +1217,7 @@ F: hw/ppc/mpc8544_guts.c
New World (mac99)
M: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
R: David Gibson <david@gibson.dropbear.id.au>
R: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc/mac_newworld.c
@ -1239,6 +1237,7 @@ F: pc-bios/qemu_vga.ndrv
Old World (g3beige)
M: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
R: David Gibson <david@gibson.dropbear.id.au>
R: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc/mac_oldworld.c
@ -1252,6 +1251,8 @@ F: pc-bios/qemu_vga.ndrv
PReP
M: Hervé Poussineau <hpoussin@reactos.org>
R: David Gibson <david@gibson.dropbear.id.au>
R: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Maintained
F: hw/ppc/prep.c
@ -1268,6 +1269,7 @@ F: tests/acceptance/ppc_prep_40p.py
sPAPR
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Supported
F: hw/*/spapr*
@ -1285,6 +1287,7 @@ F: tests/qtest/libqos/rtas*
PowerNV (Non-Virtualized)
M: Cédric Le Goater <clg@kaod.org>
M: David Gibson <david@gibson.dropbear.id.au>
M: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Maintained
F: hw/ppc/pnv*
@ -1304,6 +1307,8 @@ F: hw/ppc/virtex_ml507.c
sam460ex
M: BALATON Zoltan <balaton@eik.bme.hu>
R: David Gibson <david@gibson.dropbear.id.au>
R: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Maintained
F: hw/ppc/sam460ex.c
@ -1334,14 +1339,20 @@ L: qemu-riscv@nongnu.org
S: Supported
F: hw/riscv/microchip_pfsoc.c
F: hw/char/mchp_pfsoc_mmuart.c
F: hw/misc/mchp_pfsoc_dmc.c
F: hw/misc/mchp_pfsoc_ioscb.c
F: hw/misc/mchp_pfsoc_sysreg.c
F: include/hw/riscv/microchip_pfsoc.h
F: include/hw/char/mchp_pfsoc_mmuart.h
F: include/hw/misc/mchp_pfsoc_dmc.h
F: include/hw/misc/mchp_pfsoc_ioscb.h
F: include/hw/misc/mchp_pfsoc_sysreg.h
RX Machines
-----------
rx-gdbsim
M: Yoshinori Sato <ysato@users.sourceforge.jp>
S: Maintained
S: Odd Fixes
F: docs/system/target-rx.rst
F: hw/rx/rx-gdbsim.c
F: tests/acceptance/machine_rx_gdbsim.py
@ -1351,7 +1362,7 @@ SH4 Machines
R2D
M: Yoshinori Sato <ysato@users.sourceforge.jp>
R: Magnus Damm <magnus.damm@gmail.com>
S: Maintained
S: Odd Fixes
F: hw/sh4/r2d.c
F: hw/intc/sh_intc.c
F: include/hw/sh4/sh_intc.h
@ -1424,6 +1435,7 @@ F: include/hw/s390x/
F: hw/watchdog/wdt_diag288.c
F: include/hw/watchdog/wdt_diag288.h
F: default-configs/s390x-softmmu.mak
F: tests/acceptance/machine_s390_ccw_virtio.py
T: git https://github.com/cohuck/qemu.git s390-next
T: git https://github.com/borntraeger/qemu.git s390-next
L: qemu-s390x@nongnu.org
@ -1443,6 +1455,7 @@ S390 PCI
M: Matthew Rosato <mjrosato@linux.ibm.com>
S: Supported
F: hw/s390x/s390-pci*
F: include/hw/s390x/s390-pci*
L: qemu-s390x@nongnu.org
UniCore32 Machines
@ -1525,6 +1538,7 @@ Machine core
M: Eduardo Habkost <ehabkost@redhat.com>
M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
S: Supported
F: cpu.c
F: hw/core/cpu.c
F: hw/core/machine-qmp-cmds.c
F: hw/core/machine.c
@ -1537,7 +1551,7 @@ F: include/hw/boards.h
F: include/hw/core/cpu.h
F: include/hw/cpu/cluster.h
F: include/sysemu/numa.h
T: git https://github.com/ehabkost/qemu.git machine-next
T: git https://gitlab.com/ehabkost/qemu.git machine-next
Xtensa Machines
---------------
@ -1559,6 +1573,14 @@ F: hw/net/opencores_eth.c
Devices
-------
Xilinx CAN
M: Vikram Garhwal <fnu.vikram@xilinx.com>
M: Francisco Iglesias <francisco.iglesias@xilinx.com>
S: Maintained
F: hw/net/can/xlnx-*
F: include/hw/net/xlnx-*
F: tests/qtest/xlnx-can-test*
EDU
M: Jiri Slaby <jslaby@suse.cz>
S: Maintained
@ -1604,6 +1626,7 @@ L: qemu-arm@nongnu.org
S: Maintained
F: hw/*/omap*
F: include/hw/arm/omap.h
F: docs/system/arm/sx1.rst
IPack
M: Alberto Garcia <berto@igalia.com>
@ -1883,7 +1906,9 @@ M: Klaus Jensen <its@irrelevant.dk>
L: qemu-block@nongnu.org
S: Supported
F: hw/block/nvme*
F: include/block/nvme.h
F: tests/qtest/nvme-test.c
F: docs/specs/nvme.txt
T: git git://git.infradead.org/qemu-nvme.git nvme-next
megasas
@ -1913,6 +1938,7 @@ Rocker
M: Jiri Pirko <jiri@resnulli.us>
S: Maintained
F: hw/net/rocker/
F: qapi/rocker.json
F: tests/rocker/
F: docs/specs/rocker.txt
@ -1974,6 +2000,12 @@ F: docs/specs/vmgenid.txt
F: tests/qtest/vmgenid-test.c
F: stubs/vmgenid.c
LED
M: Philippe Mathieu-Daudé <f4bug@amsat.org>
S: Maintained
F: include/hw/misc/led.h
F: hw/misc/led.c
Unimplemented device
M: Peter Maydell <peter.maydell@linaro.org>
R: Philippe Mathieu-Daudé <f4bug@amsat.org>
@ -2055,7 +2087,7 @@ R: Laszlo Ersek <lersek@redhat.com>
R: Gerd Hoffmann <kraxel@redhat.com>
S: Supported
F: docs/specs/fw_cfg.txt
F: hw/nvram/fw_cfg.c
F: hw/nvram/fw_cfg*.c
F: stubs/fw_cfg.c
F: include/hw/nvram/fw_cfg.h
F: include/standard-headers/linux/qemu_fw_cfg.h
@ -2064,8 +2096,9 @@ F: tests/qtest/fw_cfg-test.c
T: git https://github.com/philmd/qemu.git fw_cfg-next
XIVE
M: David Gibson <david@gibson.dropbear.id.au>
M: Cédric Le Goater <clg@kaod.org>
R: David Gibson <david@gibson.dropbear.id.au>
R: Greg Kurz <groug@kaod.org>
L: qemu-ppc@nongnu.org
S: Supported
F: hw/*/*xive*
@ -2075,7 +2108,7 @@ F: docs/*/*xive*
Renesas peripherals
M: Yoshinori Sato <ysato@users.sourceforge.jp>
R: Magnus Damm <magnus.damm@gmail.com>
S: Maintained
S: Odd Fixes
F: hw/char/renesas_sci.c
F: hw/char/sh_serial.c
F: hw/timer/renesas_*.c
@ -2086,7 +2119,7 @@ F: include/hw/timer/renesas_*.h
Renesas RX peripherals
M: Yoshinori Sato <ysato@users.sourceforge.jp>
S: Maintained
S: Odd Fixes
F: hw/intc/rx_icu.c
F: hw/rx/
F: include/hw/intc/rx_icu.h
@ -2109,6 +2142,7 @@ S: Maintained
F: audio/
F: hw/audio/
F: include/hw/audio/
F: qapi/audio.json
F: tests/qtest/ac97-test.c
F: tests/qtest/es1370-test.c
F: tests/qtest/intel-hda-test.c
@ -2235,7 +2269,7 @@ Device Tree
M: Alistair Francis <alistair.francis@wdc.com>
R: David Gibson <david@gibson.dropbear.id.au>
S: Maintained
F: device_tree.c
F: softmmu/device_tree.c
F: include/sysemu/device_tree.h
Dump
@ -2281,10 +2315,11 @@ F: include/exec/memop.h
F: include/exec/memory.h
F: include/exec/ram_addr.h
F: include/exec/ramblock.h
F: softmmu/dma-helpers.c
F: softmmu/ioport.c
F: softmmu/memory.c
F: softmmu/physmem.c
F: include/exec/memory-internal.h
F: exec.c
F: scripts/coccinelle/memory-region-housekeeping.cocci
SPICE
@ -2316,6 +2351,7 @@ M: Paolo Bonzini <pbonzini@redhat.com>
S: Maintained
F: include/qemu/main-loop.h
F: include/sysemu/runstate.h
F: include/sysemu/runstate-action.h
F: util/main-loop.c
F: util/qemu-timer.c
F: softmmu/vl.c
@ -2324,6 +2360,7 @@ F: softmmu/cpus.c
F: softmmu/cpu-throttle.c
F: softmmu/cpu-timers.c
F: softmmu/icount.c
F: softmmu/runstate-action.c
F: qapi/run-state.json
Read, Copy, Update (RCU)
@ -2371,7 +2408,7 @@ M: Igor Mammedov <imammedo@redhat.com>
S: Maintained
F: backends/hostmem*.c
F: include/sysemu/hostmem.h
T: git https://github.com/ehabkost/qemu.git machine-next
T: git https://gitlab.com/ehabkost/qemu.git machine-next
Cryptodev Backends
M: Gonglei <arei.gonglei@huawei.com>
@ -2379,11 +2416,18 @@ S: Maintained
F: include/sysemu/cryptodev*.h
F: backends/cryptodev*.c
Python library
M: John Snow <jsnow@redhat.com>
M: Cleber Rosa <crosa@redhat.com>
R: Eduardo Habkost <ehabkost@redhat.com>
S: Maintained
F: python/
T: git https://gitlab.com/jsnow/qemu.git python
Python scripts
M: Eduardo Habkost <ehabkost@redhat.com>
M: Cleber Rosa <crosa@redhat.com>
S: Odd fixes
F: python/qemu/*py
F: scripts/*.py
F: tests/*.py
@ -2394,7 +2438,7 @@ F: scripts/simplebench/
QAPI
M: Markus Armbruster <armbru@redhat.com>
M: Michael Roth <mdroth@linux.vnet.ibm.com>
M: Michael Roth <michael.roth@amd.com>
S: Supported
F: qapi/
X: qapi/*.json
@ -2438,7 +2482,7 @@ F: tests/data/qobject/qdict.txt
T: git https://repo.or.cz/qemu/armbru.git qapi-next
QEMU Guest Agent
M: Michael Roth <mdroth@linux.vnet.ibm.com>
M: Michael Roth <michael.roth@amd.com>
S: Maintained
F: qga/
F: docs/interop/qemu-ga.rst
@ -2461,7 +2505,8 @@ F: include/monitor/qdev.h
F: include/qom/
F: qapi/qom.json
F: qapi/qdev.json
F: qdev-monitor.c
F: scripts/coccinelle/qom-parent-type.cocci
F: softmmu/qdev-monitor.c
F: qom/
F: tests/check-qom-interface.c
F: tests/check-qom-proplist.c
@ -2479,7 +2524,9 @@ F: monitor/monitor-internal.h
F: monitor/qmp*
F: monitor/misc.c
F: monitor/monitor.c
F: qapi/control.json
F: qapi/error.json
F: qapi/introspect.json
F: docs/devel/*qmp-*
F: docs/interop/*qmp-*
F: scripts/qmp/
@ -2495,7 +2542,7 @@ S: Maintained
F: softmmu/qtest.c
F: accel/qtest/
F: tests/qtest/
X: tests/qtest/bios-tables-test-allowed-diff.h
X: tests/qtest/bios-tables-test*
Device Fuzzing
M: Alexander Bulekov <alxndr@bu.edu>
@ -2506,7 +2553,7 @@ R: Thomas Huth <thuth@redhat.com>
S: Maintained
F: tests/qtest/fuzz/
F: scripts/oss-fuzz/
F: docs/devel/fuzzing.txt
F: docs/devel/fuzzing.rst
Register API
M: Alistair Francis <alistair@alistair23.me>
@ -2540,6 +2587,7 @@ S: Maintained
F: trace/
F: trace-events
F: docs/qemu-option-trace.rst.inc
F: qapi/trace.json
F: scripts/tracetool.py
F: scripts/tracetool/
F: scripts/qemu-trace-stap*
@ -2591,7 +2639,7 @@ F: docs/interop/dbus-vmstate.rst
Seccomp
M: Eduardo Otubo <otubo@redhat.com>
S: Supported
F: qemu-seccomp.c
F: softmmu/qemu-seccomp.c
F: include/sysemu/seccomp.h
Cryptography
@ -2599,6 +2647,7 @@ M: Daniel P. Berrange <berrange@redhat.com>
S: Maintained
F: crypto/
F: include/crypto/
F: qapi/crypto.json
F: tests/test-crypto-*
F: tests/benchmark-crypto-*
F: tests/crypto-tls-*
@ -2786,7 +2835,7 @@ F: scripts/gensyscalls.sh
Tiny Code Generator (TCG)
-------------------------
Common TCG code
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Maintained
F: tcg/
F: include/tcg/
@ -2815,22 +2864,22 @@ F: tcg/arm/
F: disas/arm.c
i386 TCG target
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Maintained
F: tcg/i386/
F: disas/i386.c
MIPS TCG target
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
M: Philippe Mathieu-Daudé <f4bug@amsat.org>
R: Aurelien Jarno <aurelien@aurel32.net>
R: Huacai Chen <chenhc@lemote.com>
R: Huacai Chen <chenhuacai@kernel.org>
R: Jiaxun Yang <jiaxun.yang@flygoat.com>
R: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>
S: Maintained
S: Odd Fixes
F: tcg/mips/
PPC TCG target
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Odd Fixes
F: tcg/ppc/
F: disas/ppc.c
@ -2844,7 +2893,7 @@ F: tcg/riscv/
F: disas/riscv.c
S390 TCG target
M: Richard Henderson <rth@twiddle.net>
M: Richard Henderson <richard.henderson@linaro.org>
S: Maintained
F: tcg/s390/
F: disas/s390.c
@ -2879,7 +2928,6 @@ F: block/rbd.c
Sheepdog
M: Liu Yuan <namei.unix@gmail.com>
L: qemu-block@nongnu.org
L: sheepdog@lists.wpkg.org
S: Odd Fixes
F: block/sheepdog.c
@ -2952,12 +3000,13 @@ R: Fam Zheng <fam@euphon.net>
L: qemu-block@nongnu.org
S: Supported
F: block/nvme*
F: include/block/nvme.h
T: git https://github.com/stefanha/qemu.git block
Bootdevice
M: Gonglei <arei.gonglei@huawei.com>
S: Maintained
F: bootdevice.c
F: softmmu/bootdevice.c
Quorum
M: Alberto Garcia <berto@igalia.com>
@ -3068,6 +3117,21 @@ L: qemu-block@nongnu.org
S: Supported
F: tests/image-fuzzer/
Vhost-user block device backend server
M: Coiby Xu <Coiby.Xu@gmail.com>
S: Maintained
F: block/export/vhost-user-blk-server.c
F: block/export/vhost-user-blk-server.h
F: include/qemu/vhost-user-server.h
F: tests/qtest/libqos/vhost-user-blk.c
F: util/vhost-user-server.c
FUSE block device exports
M: Max Reitz <mreitz@redhat.com>
L: qemu-block@nongnu.org
S: Supported
F: block/export/fuse.c
Replication
M: Wen Congyang <wencongyang2@huawei.com>
M: Xie Changlong <xiechanglong.d@gmail.com>
@ -3126,6 +3190,8 @@ R: Wainer dos Santos Moschetta <wainersm@redhat.com>
S: Maintained
F: .gitlab-ci.yml
F: .gitlab-ci.d/crossbuilds.yml
F: .gitlab-ci.d/*py
F: scripts/ci/gitlab-pipeline-status
Guest Test Compilation Support
M: Alex Bennée <alex.bennee@linaro.org>
@ -3167,7 +3233,7 @@ S: Odd Fixes
F: scripts/git-submodule.sh
UI translations
M: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
S: Orphaned
F: po/*.po
Sphinx documentation configuration and build machinery

169
Makefile
View File

@ -14,6 +14,8 @@ SRC_PATH=.
# we have explicit rules for everything
MAKEFLAGS += -rR
SHELL = /usr/bin/env bash -o pipefail
# Usage: $(call quiet-command,command and args,"NAME","args to print")
# This will run "command and args", and either:
# if V=1 just print the whole command and args
@ -28,13 +30,21 @@ UNCHECKED_GOALS := %clean TAGS cscope ctags dist \
help check-help print-% \
docker docker-% vm-help vm-test vm-build-%
all:
.PHONY: all clean distclean recurse-all dist msi FORCE
# Don't try to regenerate Makefile or configure
# We don't generate any of them
Makefile: ;
configure: ;
# All following code might depend on configuration variables
ifneq ($(wildcard config-host.mak),)
# Put the all: rule here so that config-host.mak can contain dependencies.
all:
include config-host.mak
git-submodule-update:
.git-submodule-status: git-submodule-update config-host.mak
Makefile: .git-submodule-status
.PHONY: git-submodule-update
@ -62,28 +72,7 @@ git-submodule-update:
endif
endif
export NINJA=./ninjatool
# Running meson regenerates both build.ninja and ninjatool, and that is
# enough to prime the rest of the build.
ninjatool: build.ninja
Makefile.ninja: build.ninja ninjatool
./ninjatool -t ninja2make --omit clean dist uninstall cscope TAGS ctags < $< > $@
-include Makefile.ninja
${ninja-targets-c_COMPILER} ${ninja-targets-cpp_COMPILER}: .var.command += -MP
# If MESON is empty, the rule will be re-evaluated after Makefiles are
# reread (and MESON won't be empty anymore).
ifneq ($(MESON),)
Makefile.mtest: build.ninja scripts/mtest2make.py
$(MESON) introspect --targets --tests --benchmarks | $(PYTHON) scripts/mtest2make.py > $@
-include Makefile.mtest
endif
Makefile: .git-submodule-status
.git-submodule-status: git-submodule-update config-host.mak
# 0. ensure the build tree is okay
# Check that we're not trying to do an out-of-tree build from
# a tree that's been used for an in-tree build.
@ -95,14 +84,95 @@ seems to have been used for an in-tree build. You can fix this by running \
endif
endif
# force a rerun of configure if config-host.mak is too old or corrupted
ifeq ($(MESON),)
.PHONY: config-host.mak
x := $(shell rm -rf meson-private meson-info meson-logs)
endif
ifeq ($(NINJA),)
.PHONY: config-host.mak
x := $(shell rm -rf meson-private meson-info meson-logs)
else
export NINJA
endif
ifeq ($(wildcard build.ninja),)
.PHONY: config-host.mak
x := $(shell rm -rf meson-private meson-info meson-logs)
endif
ifeq ($(origin prefix),file)
.PHONY: config-host.mak
x := $(shell rm -rf meson-private meson-info meson-logs)
endif
# 1. ensure config-host.mak is up-to-date
config-host.mak: $(SRC_PATH)/configure $(SRC_PATH)/pc-bios $(SRC_PATH)/VERSION
@echo $@ is out-of-date, running configure
@echo config-host.mak is out-of-date, running configure
@if test -f meson-private/coredata.dat; then \
./config.status --skip-meson; \
else \
./config.status; \
./config.status && touch build.ninja.stamp; \
fi
# 2. meson.stamp exists if meson has run at least once (so ninja reconfigure
# works), but otherwise never needs to be updated
meson-private/coredata.dat: meson.stamp
meson.stamp: config-host.mak
@touch meson.stamp
# 3. ensure generated build files are up-to-date
ifneq ($(NINJA),)
Makefile.ninja: build.ninja
$(quiet-@){ \
echo 'ninja-targets = \'; \
$(NINJA) -t targets all | sed 's/:.*//; $$!s/$$/ \\/'; \
echo 'build-files = \'; \
$(NINJA) -t query build.ninja | sed -n '1,/^ input:/d; /^ outputs:/q; s/$$/ \\/p'; \
} > $@.tmp && mv $@.tmp $@
-include Makefile.ninja
# A separate rule is needed for Makefile dependencies to avoid -n
build.ninja: build.ninja.stamp
build.ninja.stamp: meson.stamp $(build-files)
$(NINJA) $(if $V,-v,) build.ninja && touch $@
endif
ifneq ($(MESON),)
Makefile.mtest: build.ninja scripts/mtest2make.py
$(MESON) introspect --targets --tests --benchmarks | $(PYTHON) scripts/mtest2make.py > $@
-include Makefile.mtest
endif
# 4. Rules to bridge to other makefiles
ifneq ($(NINJA),)
MAKE.n = $(findstring n,$(firstword $(MAKEFLAGS)))
MAKE.k = $(findstring k,$(firstword $(MAKEFLAGS)))
MAKE.q = $(findstring q,$(firstword $(MAKEFLAGS)))
MAKE.nq = $(if $(word 2, $(MAKE.n) $(MAKE.q)),nq)
NINJAFLAGS = $(if $V,-v) $(if $(MAKE.n), -n) $(if $(MAKE.k), -k0) \
$(filter-out -j, $(lastword -j1 $(filter -l% -j%, $(MAKEFLAGS)))) \
ninja-cmd-goals = $(or $(MAKECMDGOALS), all)
ninja-cmd-goals += $(foreach t, $(.tests), $(.test.deps.$t))
makefile-targets := build.ninja ctags TAGS cscope dist clean uninstall
# "ninja -t targets" also lists all prerequisites. If build system
# files are marked as PHONY, however, Make will always try to execute
# "ninja build.ninja".
ninja-targets := $(filter-out $(build-files) $(makefile-targets), $(ninja-targets))
.PHONY: $(ninja-targets) run-ninja
$(ninja-targets): run-ninja
# Use "| cat" to give Ninja a more "make-y" output. Use "+" to bypass the
# --output-sync line.
run-ninja: config-host.mak
ifneq ($(filter $(ninja-targets), $(ninja-cmd-goals)),)
+$(quiet-@)$(if $(MAKE.nq),@:, $(NINJA) \
$(NINJAFLAGS) $(sort $(filter $(ninja-targets), $(ninja-cmd-goals))) | cat)
endif
endif
# Force configure to re-run if the API symbols are updated
ifeq ($(CONFIG_PLUGIN),y)
config-host.mak: $(SRC_PATH)/plugins/qemu-plugins.symbols
@ -112,37 +182,21 @@ plugins:
$(call quiet-command,\
$(MAKE) $(SUBDIR_MAKEFLAGS) -C contrib/plugins V="$(V)", \
"BUILD", "example plugins")
endif
endif # $(CONFIG_PLUGIN)
else
else # config-host.mak does not exist
config-host.mak:
ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
@echo "Please call configure before running make!"
@exit 1
endif
endif
# Only needed in case Makefile.ninja does not exist.
.PHONY: ninja-clean ninja-distclean clean-ctlist
clean-ctlist:
ninja-clean::
ninja-distclean::
build.ninja: config-host.mak
# Don't try to regenerate Makefile or configure
# We don't generate any of them
Makefile: ;
configure: ;
.PHONY: all clean distclean install \
recurse-all dist msi FORCE
endif # config-host.mak does not exist
SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory --quiet)
include $(SRC_PATH)/tests/Makefile.include
all: recurse-all
Makefile:
ROM_DIRS = $(addprefix pc-bios/, $(ROMS))
ROM_DIRS_RULES=$(foreach t, all clean, $(addsuffix /$(t), $(ROM_DIRS)))
@ -157,8 +211,9 @@ recurse-clean: $(addsuffix /clean, $(ROM_DIRS))
######################################################################
clean: recurse-clean ninja-clean clean-ctlist
if test -f ninjatool; then ./ninjatool $(if $(V),-v,) -t clean; fi
clean: recurse-clean
-$(quiet-@)test -f build.ninja && $(NINJA) $(NINJAFLAGS) -t clean || :
-$(quiet-@)test -f build.ninja && $(NINJA) $(NINJAFLAGS) clean-ctlist || :
# avoid old build problems by removing potentially incorrect old files
rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
find . \( -name '*.so' -o -name '*.dll' -o -name '*.[oda]' \) -type f \
@ -175,8 +230,8 @@ dist: qemu-$(VERSION).tar.bz2
qemu-%.tar.bz2:
$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"
distclean: clean ninja-distclean
-test -f ninjatool && ./ninjatool $(if $(V),-v,) -t clean -g
distclean: clean
-$(quiet-@)test -f build.ninja && $(NINJA) $(NINJAFLAGS) -t clean -g || :
rm -f config-host.mak config-host.h*
rm -f tests/tcg/config-*.mak
rm -f config-all-disas.mak config.status
@ -185,28 +240,28 @@ distclean: clean ninja-distclean
rm -f qemu-plugins-ld.symbols qemu-plugins-ld64.symbols
rm -f *-config-target.h *-config-devices.mak *-config-devices.h
rm -rf meson-private meson-logs meson-info compile_commands.json
rm -f Makefile.ninja ninjatool ninjatool.stamp Makefile.mtest
rm -f Makefile.ninja Makefile.mtest build.ninja.stamp meson.stamp
rm -f config.log
rm -f linux-headers/asm
rm -Rf .sdk
find-src-path = find "$(SRC_PATH)/" -path "$(SRC_PATH)/meson" -prune -o -name "*.[chsS]"
find-src-path = find "$(SRC_PATH)/" -path "$(SRC_PATH)/meson" -prune -o \( -name "*.[chsS]" -o -name "*.[ch].inc" \)
.PHONY: ctags
ctags:
rm -f tags
$(find-src-path) -exec ctags --append {} +
rm -f "$(SRC_PATH)/"tags
$(find-src-path) -exec ctags -f "$(SRC_PATH)/"tags --append {} +
.PHONY: TAGS
TAGS:
rm -f TAGS
$(find-src-path) -exec etags --append {} +
rm -f "$(SRC_PATH)/"TAGS
$(find-src-path) -exec etags -f "$(SRC_PATH)/"TAGS --append {} +
.PHONY: cscope
cscope:
rm -f "$(SRC_PATH)"/cscope.*
$(find-src-path) -print | sed -e 's,^\./,,' > "$(SRC_PATH)/cscope.files"
cscope -b -i"$(SRC_PATH)/cscope.files"
cscope -b -i"$(SRC_PATH)/cscope.files" -f"$(SRC_PATH)"/cscope.out
# Needed by "meson install"
export DESTDIR
@ -215,7 +270,7 @@ include $(SRC_PATH)/tests/docker/Makefile.include
include $(SRC_PATH)/tests/vm/Makefile.include
print-help-run = printf " %-30s - %s\\n" "$1" "$2"
print-help = $(quiet-@)$(call print-help-run,$1,$2)
print-help = @$(call print-help-run,$1,$2)
.PHONY: help
help:

8
README.rst
View File

@ -134,6 +134,14 @@ For additional information on bug reporting consult:
* `<https://qemu.org/Contribute/ReportABug>`_
ChangeLog
=========
For version history and release notes, please visit
`<https://wiki.qemu.org/ChangeLog/>`_ or look at the git history for
more detailed information.
Contact
=======

2
VERSION
View File

@ -1 +1 @@
5.1.50
5.2.50

27
accel/qtest/qtest-cpus.c → accel/dummy-cpus.c
View File

@ -1,5 +1,5 @@
/*
* QTest accelerator code
* Dummy cpu thread code
*
* Copyright IBM, Corp. 2011
*
@ -13,26 +13,13 @@
#include "qemu/osdep.h"
#include "qemu/rcu.h"
#include "qapi/error.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/config-file.h"
#include "sysemu/accel.h"
#include "sysemu/qtest.h"
#include "sysemu/cpus.h"
#include "sysemu/cpu-timers.h"
#include "qemu/guest-random.h"
#include "qemu/main-loop.h"
#include "hw/core/cpu.h"
#include "qtest-cpus.h"
static void *qtest_cpu_thread_fn(void *arg)
static void *dummy_cpu_thread_fn(void *arg)
{
#ifdef _WIN32
error_report("qtest is not supported under Windows");
exit(1);
#else
CPUState *cpu = arg;
sigset_t waitset;
int r;
@ -69,10 +56,9 @@ static void *qtest_cpu_thread_fn(void *arg)
qemu_mutex_unlock_iothread();
rcu_unregister_thread();
return NULL;
#endif
}
static void qtest_start_vcpu_thread(CPUState *cpu)
void dummy_start_vcpu_thread(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
@ -81,11 +67,6 @@ static void qtest_start_vcpu_thread(CPUState *cpu)
qemu_cond_init(cpu->halt_cond);
snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/DUMMY",
cpu->cpu_index);
qemu_thread_create(cpu->thread, thread_name, qtest_cpu_thread_fn, cpu,
qemu_thread_create(cpu->thread, thread_name, dummy_cpu_thread_fn, cpu,
QEMU_THREAD_JOINABLE);
}
const CpusAccel qtest_cpus = {
.create_vcpu_thread = qtest_start_vcpu_thread,
.get_virtual_clock = qtest_get_virtual_clock,
};

24
accel/kvm/kvm-all.c
View File

@ -745,7 +745,7 @@ static int kvm_log_clear_one_slot(KVMSlot *mem, int as_id, uint64_t start,
assert(bmap_start % BITS_PER_LONG == 0);
/* We should never do log_clear before log_sync */
assert(mem->dirty_bmap);
if (start_delta) {
if (start_delta || bmap_npages - size / psize) {
/* Slow path - we need to manipulate a temp bitmap */
bmap_clear = bitmap_new(bmap_npages);
bitmap_copy_with_src_offset(bmap_clear, mem->dirty_bmap,
@ -758,7 +758,10 @@ static int kvm_log_clear_one_slot(KVMSlot *mem, int as_id, uint64_t start,
bitmap_clear(bmap_clear, 0, start_delta);
d.dirty_bitmap = bmap_clear;
} else {
/* Fast path - start address aligns well with BITS_PER_LONG */
/*
* Fast path - both start and size align well with BITS_PER_LONG
* (or the end of memory slot)
*/
d.dirty_bitmap = mem->dirty_bmap + BIT_WORD(bmap_start);
}
@ -2013,7 +2016,6 @@ static int kvm_init(MachineState *ms)
const KVMCapabilityInfo *missing_cap;
int ret;
int type = 0;
const char *kvm_type;
uint64_t dirty_log_manual_caps;
s = KVM_STATE(ms->accelerator);
@ -2069,13 +2071,11 @@ static int kvm_init(MachineState *ms)
}
s->as = g_new0(struct KVMAs, s->nr_as);
kvm_type = qemu_opt_get(qemu_get_machine_opts(), "kvm-type");
if (mc->kvm_type) {
if (object_property_find(OBJECT(current_machine), "kvm-type")) {
g_autofree char *kvm_type = object_property_get_str(OBJECT(current_machine),
"kvm-type",
&error_abort);
type = mc->kvm_type(ms, kvm_type);
} else if (kvm_type) {
ret = -EINVAL;
fprintf(stderr, "Invalid argument kvm-type=%s\n", kvm_type);
goto err;
}
do {
@ -2239,8 +2239,10 @@ static int kvm_init(MachineState *ms)
kvm_memory_listener_register(s, &s->memory_listener,
&address_space_memory, 0);
memory_listener_register(&kvm_io_listener,
&address_space_io);
if (kvm_eventfds_allowed) {
memory_listener_register(&kvm_io_listener,
&address_space_io);
}
memory_listener_register(&kvm_coalesced_pio_listener,
&address_space_io);

8
accel/meson.build
View File

@ -5,3 +5,11 @@ subdir('kvm')
subdir('tcg')
subdir('xen')
subdir('stubs')
dummy_ss = ss.source_set()
dummy_ss.add(files(
'dummy-cpus.c',
))
specific_ss.add_all(when: ['CONFIG_SOFTMMU', 'CONFIG_POSIX'], if_true: dummy_ss)
specific_ss.add_all(when: ['CONFIG_XEN'], if_true: dummy_ss)

1
accel/qtest/meson.build
View File

@ -1,7 +1,6 @@
qtest_ss = ss.source_set()
qtest_ss.add(files(
'qtest.c',
'qtest-cpus.c',
))
specific_ss.add_all(when: ['CONFIG_SOFTMMU', 'CONFIG_POSIX'], if_true: qtest_ss)

5
accel/qtest/qtest.c
View File

@ -25,7 +25,10 @@
#include "qemu/main-loop.h"
#include "hw/core/cpu.h"
#include "qtest-cpus.h"
const CpusAccel qtest_cpus = {
.create_vcpu_thread = dummy_start_vcpu_thread,
.get_virtual_clock = qtest_get_virtual_clock,
};
static int qtest_init_accel(MachineState *ms)
{

1
accel/stubs/hax-stub.c
View File

@ -14,7 +14,6 @@
*/
#include "qemu/osdep.h"
#include "cpu.h"
#include "sysemu/hax.h"
int hax_sync_vcpus(void)

2
accel/stubs/xen-stub.c
View File

@ -7,7 +7,7 @@
#include "qemu/osdep.h"
#include "sysemu/xen.h"
#include "qapi/qapi-commands-misc.h"
#include "qapi/qapi-commands-migration.h"
bool xen_allowed;

38
accel/tcg/cpu-exec.c
View File

@ -236,9 +236,26 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
}
#endif
void cpu_exec_step_atomic(CPUState *cpu)
static void cpu_exec_enter(CPUState *cpu)
{
CPUClass *cc = CPU_GET_CLASS(cpu);
if (cc->cpu_exec_enter) {
cc->cpu_exec_enter(cpu);
}
}
static void cpu_exec_exit(CPUState *cpu)
{
CPUClass *cc = CPU_GET_CLASS(cpu);
if (cc->cpu_exec_exit) {
cc->cpu_exec_exit(cpu);
}
}
void cpu_exec_step_atomic(CPUState *cpu)
{
TranslationBlock *tb;
target_ulong cs_base, pc;
uint32_t flags;
@ -257,11 +274,11 @@ void cpu_exec_step_atomic(CPUState *cpu)
/* Since we got here, we know that parallel_cpus must be true. */
parallel_cpus = false;
cc->cpu_exec_enter(cpu);
cpu_exec_enter(cpu);
/* execute the generated code */
trace_exec_tb(tb, pc);
cpu_tb_exec(cpu, tb);
cc->cpu_exec_exit(cpu);
cpu_exec_exit(cpu);
} else {
/*
* The mmap_lock is dropped by tb_gen_code if it runs out of
@ -465,7 +482,9 @@ static inline void cpu_handle_debug_exception(CPUState *cpu)
}
}
cc->debug_excp_handler(cpu);
if (cc->debug_excp_handler) {
cc->debug_excp_handler(cpu);
}
}
static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
@ -606,7 +625,8 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
True when it is, and we should restart on a new TB,
and via longjmp via cpu_loop_exit. */
else {
if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
if (cc->cpu_exec_interrupt &&
cc->cpu_exec_interrupt(cpu, interrupt_request)) {
if (need_replay_interrupt(interrupt_request)) {
replay_interrupt();
}
@ -685,7 +705,7 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
insns_left = MIN(0xffff, cpu->icount_budget);
cpu_neg(cpu)->icount_decr.u16.low = insns_left;
cpu->icount_extra = cpu->icount_budget - insns_left;
if (!cpu->icount_extra) {
if (!cpu->icount_extra && insns_left < tb->icount) {
/* Execute any remaining instructions, then let the main loop
* handle the next event.
*/
@ -713,7 +733,7 @@ int cpu_exec(CPUState *cpu)
rcu_read_lock();
cc->cpu_exec_enter(cpu);
cpu_exec_enter(cpu);
/* Calculate difference between guest clock and host clock.
* This delay includes the delay of the last cycle, so
@ -724,7 +744,7 @@ int cpu_exec(CPUState *cpu)
/* prepare setjmp context for exception handling */
if (sigsetjmp(cpu->jmp_env, 0) != 0) {
#if defined(__clang__) || !QEMU_GNUC_PREREQ(4, 6)
#if defined(__clang__)
/* Some compilers wrongly smash all local variables after
* siglongjmp. There were bug reports for gcc 4.5.0 and clang.
* Reload essential local variables here for those compilers.
@ -775,7 +795,7 @@ int cpu_exec(CPUState *cpu)
}
}
cc->cpu_exec_exit(cpu);
cpu_exec_exit(cpu);
rcu_read_unlock();
return ret;

275
accel/tcg/cputlb.c
View File

@ -409,12 +409,21 @@ void tlb_flush_all_cpus_synced(CPUState *src_cpu)
tlb_flush_by_mmuidx_all_cpus_synced(src_cpu, ALL_MMUIDX_BITS);
}
static bool tlb_hit_page_mask_anyprot(CPUTLBEntry *tlb_entry,
target_ulong page, target_ulong mask)
{
page &= mask;
mask &= TARGET_PAGE_MASK | TLB_INVALID_MASK;
return (page == (tlb_entry->addr_read & mask) ||
page == (tlb_addr_write(tlb_entry) & mask) ||
page == (tlb_entry->addr_code & mask));
}
static inline bool tlb_hit_page_anyprot(CPUTLBEntry *tlb_entry,
target_ulong page)
{
return tlb_hit_page(tlb_entry->addr_read, page) ||
tlb_hit_page(tlb_addr_write(tlb_entry), page) ||
tlb_hit_page(tlb_entry->addr_code, page);
return tlb_hit_page_mask_anyprot(tlb_entry, page, -1);
}
/**
@ -427,31 +436,45 @@ static inline bool tlb_entry_is_empty(const CPUTLBEntry *te)
}
/* Called with tlb_c.lock held */
static inline bool tlb_flush_entry_locked(CPUTLBEntry *tlb_entry,
target_ulong page)
static bool tlb_flush_entry_mask_locked(CPUTLBEntry *tlb_entry,
target_ulong page,
target_ulong mask)
{
if (tlb_hit_page_anyprot(tlb_entry, page)) {
if (tlb_hit_page_mask_anyprot(tlb_entry, page, mask)) {
memset(tlb_entry, -1, sizeof(*tlb_entry));
return true;
}
return false;
}
static inline bool tlb_flush_entry_locked(CPUTLBEntry *tlb_entry,
target_ulong page)
{
return tlb_flush_entry_mask_locked(tlb_entry, page, -1);
}
/* Called with tlb_c.lock held */
static inline void tlb_flush_vtlb_page_locked(CPUArchState *env, int mmu_idx,
target_ulong page)
static void tlb_flush_vtlb_page_mask_locked(CPUArchState *env, int mmu_idx,
target_ulong page,
target_ulong mask)
{
CPUTLBDesc *d = &env_tlb(env)->d[mmu_idx];
int k;
assert_cpu_is_self(env_cpu(env));
for (k = 0; k < CPU_VTLB_SIZE; k++) {
if (tlb_flush_entry_locked(&d->vtable[k], page)) {
if (tlb_flush_entry_mask_locked(&d->vtable[k], page, mask)) {
tlb_n_used_entries_dec(env, mmu_idx);
}
}
}
static inline void tlb_flush_vtlb_page_locked(CPUArchState *env, int mmu_idx,
target_ulong page)
{
tlb_flush_vtlb_page_mask_locked(env, mmu_idx, page, -1);
}
static void tlb_flush_page_locked(CPUArchState *env, int midx,
target_ulong page)
{
@ -666,6 +689,240 @@ void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr)
tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS);
}
static void tlb_flush_page_bits_locked(CPUArchState *env, int midx,
target_ulong page, unsigned bits)
{
CPUTLBDesc *d = &env_tlb(env)->d[midx];
CPUTLBDescFast *f = &env_tlb(env)->f[midx];
target_ulong mask = MAKE_64BIT_MASK(0, bits);
/*
* If @bits is smaller than the tlb size, there may be multiple entries
* within the TLB; otherwise all addresses that match under @mask hit
* the same TLB entry.
*
* TODO: Perhaps allow bits to be a few bits less than the size.
* For now, just flush the entire TLB.
*/
if (mask < f->mask) {
tlb_debug("forcing full flush midx %d ("
TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
midx, page, mask);
tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
return;
}
/* Check if we need to flush due to large pages. */
if ((page & d->large_page_mask) == d->large_page_addr) {
tlb_debug("forcing full flush midx %d ("
TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
midx, d->large_page_addr, d->large_page_mask);
tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
return;
}
if (tlb_flush_entry_mask_locked(tlb_entry(env, midx, page), page, mask)) {
tlb_n_used_entries_dec(env, midx);
}
tlb_flush_vtlb_page_mask_locked(env, midx, page, mask);
}
typedef struct {
target_ulong addr;
uint16_t idxmap;
uint16_t bits;
} TLBFlushPageBitsByMMUIdxData;
static void
tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
TLBFlushPageBitsByMMUIdxData d)
{
CPUArchState *env = cpu->env_ptr;
int mmu_idx;
assert_cpu_is_self(cpu);
tlb_debug("page addr:" TARGET_FMT_lx "/%u mmu_map:0x%x\n",
d.addr, d.bits, d.idxmap);
qemu_spin_lock(&env_tlb(env)->c.lock);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
if ((d.idxmap >> mmu_idx) & 1) {
tlb_flush_page_bits_locked(env, mmu_idx, d.addr, d.bits);
}
}
qemu_spin_unlock(&env_tlb(env)->c.lock);
tb_flush_jmp_cache(cpu, d.addr);
}
static bool encode_pbm_to_runon(run_on_cpu_data *out,
TLBFlushPageBitsByMMUIdxData d)
{
/* We need 6 bits to hold to hold @bits up to 63. */
if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) {
*out = RUN_ON_CPU_TARGET_PTR(d.addr | (d.idxmap << 6) | d.bits);
return true;
}
return false;
}
static TLBFlushPageBitsByMMUIdxData
decode_runon_to_pbm(run_on_cpu_data data)
{
target_ulong addr_map_bits = (target_ulong) data.target_ptr;
return (TLBFlushPageBitsByMMUIdxData){
.addr = addr_map_bits & TARGET_PAGE_MASK,
.idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6,
.bits = addr_map_bits & 0x3f
};
}
static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu,
run_on_cpu_data runon)
{
tlb_flush_page_bits_by_mmuidx_async_0(cpu, decode_runon_to_pbm(runon));
}
static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
run_on_cpu_data data)
{
TLBFlushPageBitsByMMUIdxData *d = data.host_ptr;
tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d);
g_free(d);
}
void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
uint16_t idxmap, unsigned bits)
{
TLBFlushPageBitsByMMUIdxData d;
run_on_cpu_data runon;
/* If all bits are significant, this devolves to tlb_flush_page. */
if (bits >= TARGET_LONG_BITS) {
tlb_flush_page_by_mmuidx(cpu, addr, idxmap);
return;
}
/* If no page bits are significant, this devolves to tlb_flush. */
if (bits < TARGET_PAGE_BITS) {
tlb_flush_by_mmuidx(cpu, idxmap);
return;
}
/* This should already be page aligned */
d.addr = addr & TARGET_PAGE_MASK;
d.idxmap = idxmap;
d.bits = bits;
if (qemu_cpu_is_self(cpu)) {
tlb_flush_page_bits_by_mmuidx_async_0(cpu, d);
} else if (encode_pbm_to_runon(&runon, d)) {
async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
} else {
TLBFlushPageBitsByMMUIdxData *p
= g_new(TLBFlushPageBitsByMMUIdxData, 1);
/* Otherwise allocate a structure, freed by the worker. */
*p = d;
async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2,
RUN_ON_CPU_HOST_PTR(p));
}
}
void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
target_ulong addr,
uint16_t idxmap,
unsigned bits)
{
TLBFlushPageBitsByMMUIdxData d;
run_on_cpu_data runon;
/* If all bits are significant, this devolves to tlb_flush_page. */
if (bits >= TARGET_LONG_BITS) {
tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap);
return;
}
/* If no page bits are significant, this devolves to tlb_flush. */
if (bits < TARGET_PAGE_BITS) {
tlb_flush_by_mmuidx_all_cpus(src_cpu, idxmap);
return;
}
/* This should already be page aligned */
d.addr = addr & TARGET_PAGE_MASK;
d.idxmap = idxmap;
d.bits = bits;
if (encode_pbm_to_runon(&runon, d)) {
flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
} else {
CPUState *dst_cpu;
TLBFlushPageBitsByMMUIdxData *p;
/* Allocate a separate data block for each destination cpu. */
CPU_FOREACH(dst_cpu) {
if (dst_cpu != src_cpu) {
p = g_new(TLBFlushPageBitsByMMUIdxData, 1);
*p = d;
async_run_on_cpu(dst_cpu,
tlb_flush_page_bits_by_mmuidx_async_2,
RUN_ON_CPU_HOST_PTR(p));
}
}
}
tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d);
}
void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
target_ulong addr,
uint16_t idxmap,
unsigned bits)
{
TLBFlushPageBitsByMMUIdxData d;
run_on_cpu_data runon;
/* If all bits are significant, this devolves to tlb_flush_page. */
if (bits >= TARGET_LONG_BITS) {
tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap);
return;
}
/* If no page bits are significant, this devolves to tlb_flush. */
if (bits < TARGET_PAGE_BITS) {
tlb_flush_by_mmuidx_all_cpus_synced(src_cpu, idxmap);
return;
}
/* This should already be page aligned */
d.addr = addr & TARGET_PAGE_MASK;
d.idxmap = idxmap;
d.bits = bits;
if (encode_pbm_to_runon(&runon, d)) {
flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1,
runon);
} else {
CPUState *dst_cpu;
TLBFlushPageBitsByMMUIdxData *p;
/* Allocate a separate data block for each destination cpu. */
CPU_FOREACH(dst_cpu) {
if (dst_cpu != src_cpu) {
p = g_new(TLBFlushPageBitsByMMUIdxData, 1);
*p = d;
async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
RUN_ON_CPU_HOST_PTR(p));
}
}
p = g_new(TLBFlushPageBitsByMMUIdxData, 1);
*p = d;
async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
RUN_ON_CPU_HOST_PTR(p));
}
}
/* update the TLBs so that writes to code in the virtual page 'addr'
can be detected */
void tlb_protect_code(ram_addr_t ram_addr)

9
accel/tcg/meson.build
View File

@ -12,4 +12,11 @@ tcg_ss.add(when: 'CONFIG_SOFTMMU', if_false: files('user-exec-stub.c'))
tcg_ss.add(when: 'CONFIG_PLUGIN', if_true: [files('plugin-gen.c'), libdl])
specific_ss.add_all(when: 'CONFIG_TCG', if_true: tcg_ss)
specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files('tcg-all.c', 'cputlb.c', 'tcg-cpus.c'))
specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files(
'tcg-all.c',
'cputlb.c',
'tcg-cpus.c',
'tcg-cpus-mttcg.c',
'tcg-cpus-icount.c',
'tcg-cpus-rr.c'
))

13
accel/tcg/tcg-all.c
View File

@ -104,8 +104,19 @@ static int tcg_init(MachineState *ms)
tcg_exec_init(s->tb_size * 1024 * 1024);
mttcg_enabled = s->mttcg_enabled;
cpus_register_accel(&tcg_cpus);
/*
* Initialize TCG regions
*/
tcg_region_init();
if (mttcg_enabled) {
cpus_register_accel(&tcg_cpus_mttcg);
} else if (icount_enabled()) {
cpus_register_accel(&tcg_cpus_icount);
} else {
cpus_register_accel(&tcg_cpus_rr);
}
return 0;
}

147
accel/tcg/tcg-cpus-icount.c Normal file
View File

@ -0,0 +1,147 @@
/*
* QEMU TCG Single Threaded vCPUs implementation using instruction counting
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2014 Red Hat Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/tcg.h"
#include "sysemu/replay.h"
#include "qemu/main-loop.h"
#include "qemu/guest-random.h"
#include "exec/exec-all.h"
#include "hw/boards.h"
#include "tcg-cpus.h"
#include "tcg-cpus-icount.h"
#include "tcg-cpus-rr.h"
static int64_t icount_get_limit(void)
{
int64_t deadline;
if (replay_mode != REPLAY_MODE_PLAY) {
/*
* Include all the timers, because they may need an attention.
* Too long CPU execution may create unnecessary delay in UI.
*/
deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL,
QEMU_TIMER_ATTR_ALL);
/* Check realtime timers, because they help with input processing */
deadline = qemu_soonest_timeout(deadline,
qemu_clock_deadline_ns_all(QEMU_CLOCK_REALTIME,
QEMU_TIMER_ATTR_ALL));
/*
* Maintain prior (possibly buggy) behaviour where if no deadline
* was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than
* INT32_MAX nanoseconds ahead, we still use INT32_MAX
* nanoseconds.
*/
if ((deadline < 0) || (deadline > INT32_MAX)) {
deadline = INT32_MAX;
}
return icount_round(deadline);
} else {
return replay_get_instructions();
}
}
static void icount_notify_aio_contexts(void)
{
/* Wake up other AioContexts. */
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
}
void icount_handle_deadline(void)
{
assert(qemu_in_vcpu_thread());
int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL,
QEMU_TIMER_ATTR_ALL);
if (deadline == 0) {
icount_notify_aio_contexts();
}
}
void icount_prepare_for_run(CPUState *cpu)
{
int insns_left;
/*
* These should always be cleared by icount_process_data after
* each vCPU execution. However u16.high can be raised
* asynchronously by cpu_exit/cpu_interrupt/tcg_cpus_handle_interrupt
*/
g_assert(cpu_neg(cpu)->icount_decr.u16.low == 0);
g_assert(cpu->icount_extra == 0);
cpu->icount_budget = icount_get_limit();
insns_left = MIN(0xffff, cpu->icount_budget);
cpu_neg(cpu)->icount_decr.u16.low = insns_left;
cpu->icount_extra = cpu->icount_budget - insns_left;
replay_mutex_lock();
if (cpu->icount_budget == 0 && replay_has_checkpoint()) {
icount_notify_aio_contexts();
}
}
void icount_process_data(CPUState *cpu)
{
/* Account for executed instructions */
icount_update(cpu);
/* Reset the counters */
cpu_neg(cpu)->icount_decr.u16.low = 0;
cpu->icount_extra = 0;
cpu->icount_budget = 0;
replay_account_executed_instructions();
replay_mutex_unlock();
}
static void icount_handle_interrupt(CPUState *cpu, int mask)
{
int old_mask = cpu->interrupt_request;
tcg_cpus_handle_interrupt(cpu, mask);
if (qemu_cpu_is_self(cpu) &&
!cpu->can_do_io
&& (mask & ~old_mask) != 0) {
cpu_abort(cpu, "Raised interrupt while not in I/O function");
}
}
const CpusAccel tcg_cpus_icount = {
.create_vcpu_thread = rr_start_vcpu_thread,
.kick_vcpu_thread = rr_kick_vcpu_thread,
.handle_interrupt = icount_handle_interrupt,
.get_virtual_clock = icount_get,
.get_elapsed_ticks = icount_get,
};

17
accel/tcg/tcg-cpus-icount.h Normal file
View File

@ -0,0 +1,17 @@
/*
* QEMU TCG Single Threaded vCPUs implementation using instruction counting
*
* Copyright 2020 SUSE LLC
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef TCG_CPUS_ICOUNT_H
#define TCG_CPUS_ICOUNT_H
void icount_handle_deadline(void);
void icount_prepare_for_run(CPUState *cpu);
void icount_process_data(CPUState *cpu);
#endif /* TCG_CPUS_ICOUNT_H */

140
accel/tcg/tcg-cpus-mttcg.c Normal file
View File

@ -0,0 +1,140 @@
/*
* QEMU TCG Multi Threaded vCPUs implementation
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2014 Red Hat Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/tcg.h"
#include "sysemu/replay.h"
#include "qemu/main-loop.h"
#include "qemu/guest-random.h"
#include "exec/exec-all.h"
#include "hw/boards.h"
#include "tcg-cpus.h"
/*
* In the multi-threaded case each vCPU has its own thread. The TLS
* variable current_cpu can be used deep in the code to find the
* current CPUState for a given thread.
*/
static void *mttcg_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
assert(tcg_enabled());
g_assert(!icount_enabled());
rcu_register_thread();
tcg_register_thread();
qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
current_cpu = cpu;
cpu_thread_signal_created(cpu);
qemu_guest_random_seed_thread_part2(cpu->random_seed);
/* process any pending work */
cpu->exit_request = 1;
do {
if (cpu_can_run(cpu)) {
int r;
qemu_mutex_unlock_iothread();
r = tcg_cpus_exec(cpu);
qemu_mutex_lock_iothread();
switch (r) {
case EXCP_DEBUG:
cpu_handle_guest_debug(cpu);
break;
case EXCP_HALTED:
/*
* during start-up the vCPU is reset and the thread is
* kicked several times. If we don't ensure we go back
* to sleep in the halted state we won't cleanly
* start-up when the vCPU is enabled.
*
* cpu->halted should ensure we sleep in wait_io_event
*/
g_assert(cpu->halted);
break;
case EXCP_ATOMIC:
qemu_mutex_unlock_iothread();
cpu_exec_step_atomic(cpu);
qemu_mutex_lock_iothread();
default:
/* Ignore everything else? */
break;
}
}
qatomic_mb_set(&cpu->exit_request, 0);
qemu_wait_io_event(cpu);
} while (!cpu->unplug || cpu_can_run(cpu));
tcg_cpus_destroy(cpu);
qemu_mutex_unlock_iothread();
rcu_unregister_thread();
return NULL;
}
static void mttcg_kick_vcpu_thread(CPUState *cpu)
{
cpu_exit(cpu);
}
static void mttcg_start_vcpu_thread(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
g_assert(tcg_enabled());
parallel_cpus = (current_machine->smp.max_cpus > 1);
cpu->thread = g_malloc0(sizeof(QemuThread));
cpu->halt_cond = g_malloc0(sizeof(QemuCond));
qemu_cond_init(cpu->halt_cond);
/* create a thread per vCPU with TCG (MTTCG) */
snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/TCG",
cpu->cpu_index);
qemu_thread_create(cpu->thread, thread_name, mttcg_cpu_thread_fn,
cpu, QEMU_THREAD_JOINABLE);
#ifdef _WIN32
cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
}
const CpusAccel tcg_cpus_mttcg = {
.create_vcpu_thread = mttcg_start_vcpu_thread,
.kick_vcpu_thread = mttcg_kick_vcpu_thread,
.handle_interrupt = tcg_cpus_handle_interrupt,
};

305
accel/tcg/tcg-cpus-rr.c Normal file
View File

@ -0,0 +1,305 @@
/*
* QEMU TCG Single Threaded vCPUs implementation
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2014 Red Hat Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/tcg.h"
#include "sysemu/replay.h"
#include "qemu/main-loop.h"
#include "qemu/guest-random.h"
#include "exec/exec-all.h"
#include "hw/boards.h"
#include "tcg-cpus.h"
#include "tcg-cpus-rr.h"
#include "tcg-cpus-icount.h"
/* Kick all RR vCPUs */
void rr_kick_vcpu_thread(CPUState *unused)
{
CPUState *cpu;
CPU_FOREACH(cpu) {
cpu_exit(cpu);
};
}
/*
* TCG vCPU kick timer
*
* The kick timer is responsible for moving single threaded vCPU
* emulation on to the next vCPU. If more than one vCPU is running a
* timer event with force a cpu->exit so the next vCPU can get
* scheduled.
*
* The timer is removed if all vCPUs are idle and restarted again once
* idleness is complete.
*/
static QEMUTimer *rr_kick_vcpu_timer;
static CPUState *rr_current_cpu;
#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)
static inline int64_t rr_next_kick_time(void)
{
return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD;
}
/* Kick the currently round-robin scheduled vCPU to next */
static void rr_kick_next_cpu(void)
{
CPUState *cpu;
do {
cpu = qatomic_mb_read(&rr_current_cpu);
if (cpu) {
cpu_exit(cpu);
}
} while (cpu != qatomic_mb_read(&rr_current_cpu));
}
static void rr_kick_thread(void *opaque)
{
timer_mod(rr_kick_vcpu_timer, rr_next_kick_time());
rr_kick_next_cpu();
}
static void rr_start_kick_timer(void)
{
if (!rr_kick_vcpu_timer && CPU_NEXT(first_cpu)) {
rr_kick_vcpu_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
rr_kick_thread, NULL);
}
if (rr_kick_vcpu_timer && !timer_pending(rr_kick_vcpu_timer)) {
timer_mod(rr_kick_vcpu_timer, rr_next_kick_time());
}
}
static void rr_stop_kick_timer(void)
{
if (rr_kick_vcpu_timer && timer_pending(rr_kick_vcpu_timer)) {
timer_del(rr_kick_vcpu_timer);
}
}
static void rr_wait_io_event(void)
{
CPUState *cpu;
while (all_cpu_threads_idle()) {
rr_stop_kick_timer();
qemu_cond_wait_iothread(first_cpu->halt_cond);
}
rr_start_kick_timer();
CPU_FOREACH(cpu) {
qemu_wait_io_event_common(cpu);
}
}
/*
* Destroy any remaining vCPUs which have been unplugged and have
* finished running
*/
static void rr_deal_with_unplugged_cpus(void)
{
CPUState *cpu;
CPU_FOREACH(cpu) {
if (cpu->unplug && !cpu_can_run(cpu)) {
tcg_cpus_destroy(cpu);
break;
}
}
}
/*
* In the single-threaded case each vCPU is simulated in turn. If
* there is more than a single vCPU we create a simple timer to kick
* the vCPU and ensure we don't get stuck in a tight loop in one vCPU.
* This is done explicitly rather than relying on side-effects
* elsewhere.
*/
static void *rr_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
assert(tcg_enabled());
rcu_register_thread();
tcg_register_thread();
qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
cpu_thread_signal_created(cpu);
qemu_guest_random_seed_thread_part2(cpu->random_seed);
/* wait for initial kick-off after machine start */
while (first_cpu->stopped) {
qemu_cond_wait_iothread(first_cpu->halt_cond);
/* process any pending work */
CPU_FOREACH(cpu) {
current_cpu = cpu;
qemu_wait_io_event_common(cpu);
}
}
rr_start_kick_timer();
cpu = first_cpu;
/* process any pending work */
cpu->exit_request = 1;
while (1) {
qemu_mutex_unlock_iothread();
replay_mutex_lock();
qemu_mutex_lock_iothread();
if (icount_enabled()) {
/* Account partial waits to QEMU_CLOCK_VIRTUAL. */
icount_account_warp_timer();
/*
* Run the timers here. This is much more efficient than
* waking up the I/O thread and waiting for completion.
*/
icount_handle_deadline();
}
replay_mutex_unlock();
if (!cpu) {
cpu = first_cpu;
}
while (cpu && cpu_work_list_empty(cpu) && !cpu->exit_request) {
qatomic_mb_set(&rr_current_cpu, cpu);
current_cpu = cpu;
qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
(cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
if (cpu_can_run(cpu)) {
int r;
qemu_mutex_unlock_iothread();
if (icount_enabled()) {
icount_prepare_for_run(cpu);
}
r = tcg_cpus_exec(cpu);
if (icount_enabled()) {
icount_process_data(cpu);
}
qemu_mutex_lock_iothread();
if (r == EXCP_DEBUG) {
cpu_handle_guest_debug(cpu);
break;
} else if (r == EXCP_ATOMIC) {
qemu_mutex_unlock_iothread();
cpu_exec_step_atomic(cpu);
qemu_mutex_lock_iothread();
break;
}
} else if (cpu->stop) {
if (cpu->unplug) {
cpu = CPU_NEXT(cpu);
}
break;
}
cpu = CPU_NEXT(cpu);
} /* while (cpu && !cpu->exit_request).. */
/* Does not need qatomic_mb_set because a spurious wakeup is okay. */
qatomic_set(&rr_current_cpu, NULL);
if (cpu && cpu->exit_request) {
qatomic_mb_set(&cpu->exit_request, 0);
}
if (icount_enabled() && all_cpu_threads_idle()) {
/*
* When all cpus are sleeping (e.g in WFI), to avoid a deadlock
* in the main_loop, wake it up in order to start the warp timer.
*/
qemu_notify_event();
}
rr_wait_io_event();
rr_deal_with_unplugged_cpus();
}
rcu_unregister_thread();
return NULL;
}
void rr_start_vcpu_thread(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
static QemuCond *single_tcg_halt_cond;
static QemuThread *single_tcg_cpu_thread;
g_assert(tcg_enabled());
parallel_cpus = false;
if (!single_tcg_cpu_thread) {
cpu->thread = g_malloc0(sizeof(QemuThread));
cpu->halt_cond = g_malloc0(sizeof(QemuCond));
qemu_cond_init(cpu->halt_cond);
/* share a single thread for all cpus with TCG */
snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "ALL CPUs/TCG");
qemu_thread_create(cpu->thread, thread_name,
rr_cpu_thread_fn,
cpu, QEMU_THREAD_JOINABLE);
single_tcg_halt_cond = cpu->halt_cond;
single_tcg_cpu_thread = cpu->thread;
#ifdef _WIN32
cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
} else {
/* we share the thread */
cpu->thread = single_tcg_cpu_thread;
cpu->halt_cond = single_tcg_halt_cond;
cpu->thread_id = first_cpu->thread_id;
cpu->can_do_io = 1;
cpu->created = true;
}
}
const CpusAccel tcg_cpus_rr = {
.create_vcpu_thread = rr_start_vcpu_thread,
.kick_vcpu_thread = rr_kick_vcpu_thread,
.handle_interrupt = tcg_cpus_handle_interrupt,
};

21
accel/tcg/tcg-cpus-rr.h Normal file
View File

@ -0,0 +1,21 @@
/*
* QEMU TCG Single Threaded vCPUs implementation
*
* Copyright 2020 SUSE LLC
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef TCG_CPUS_RR_H
#define TCG_CPUS_RR_H
#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)
/* Kick all RR vCPUs. */
void rr_kick_vcpu_thread(CPUState *unused);
/* start the round robin vcpu thread */
void rr_start_vcpu_thread(CPUState *cpu);
#endif /* TCG_CPUS_RR_H */

506
accel/tcg/tcg-cpus.c
View File

@ -1,5 +1,7 @@
/*
* QEMU System Emulator
* QEMU TCG vCPU common functionality
*
* Functionality common to all TCG vCPU variants: mttcg, rr and icount.
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2014 Red Hat Inc.
@ -34,207 +36,19 @@
#include "tcg-cpus.h"
/* Kick all RR vCPUs */
static void qemu_cpu_kick_rr_cpus(void)
{
CPUState *cpu;
/* common functionality among all TCG variants */
CPU_FOREACH(cpu) {
cpu_exit(cpu);
};
void tcg_cpus_destroy(CPUState *cpu)
{
cpu_thread_signal_destroyed(cpu);
}
static void tcg_kick_vcpu_thread(CPUState *cpu)
{
if (qemu_tcg_mttcg_enabled()) {
cpu_exit(cpu);
} else {
qemu_cpu_kick_rr_cpus();
}
}
/*
* TCG vCPU kick timer
*
* The kick timer is responsible for moving single threaded vCPU
* emulation on to the next vCPU. If more than one vCPU is running a
* timer event with force a cpu->exit so the next vCPU can get
* scheduled.
*
* The timer is removed if all vCPUs are idle and restarted again once
* idleness is complete.
*/
static QEMUTimer *tcg_kick_vcpu_timer;
static CPUState *tcg_current_rr_cpu;
#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)
static inline int64_t qemu_tcg_next_kick(void)
{
return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD;
}
/* Kick the currently round-robin scheduled vCPU to next */
static void qemu_cpu_kick_rr_next_cpu(void)
{
CPUState *cpu;
do {
cpu = qatomic_mb_read(&tcg_current_rr_cpu);
if (cpu) {
cpu_exit(cpu);
}
} while (cpu != qatomic_mb_read(&tcg_current_rr_cpu));
}
static void kick_tcg_thread(void *opaque)
{
timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
qemu_cpu_kick_rr_next_cpu();
}
static void start_tcg_kick_timer(void)
{
assert(!mttcg_enabled);
if (!tcg_kick_vcpu_timer && CPU_NEXT(first_cpu)) {
tcg_kick_vcpu_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
kick_tcg_thread, NULL);
}
if (tcg_kick_vcpu_timer && !timer_pending(tcg_kick_vcpu_timer)) {
timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
}
}
static void stop_tcg_kick_timer(void)
{
assert(!mttcg_enabled);
if (tcg_kick_vcpu_timer && timer_pending(tcg_kick_vcpu_timer)) {
timer_del(tcg_kick_vcpu_timer);
}
}
static void qemu_tcg_destroy_vcpu(CPUState *cpu)
{
}
static void qemu_tcg_rr_wait_io_event(void)
{
CPUState *cpu;
while (all_cpu_threads_idle()) {
stop_tcg_kick_timer();
qemu_cond_wait_iothread(first_cpu->halt_cond);
}
start_tcg_kick_timer();
CPU_FOREACH(cpu) {
qemu_wait_io_event_common(cpu);
}
}
static int64_t tcg_get_icount_limit(void)
{
int64_t deadline;
if (replay_mode != REPLAY_MODE_PLAY) {
/*
* Include all the timers, because they may need an attention.
* Too long CPU execution may create unnecessary delay in UI.
*/
deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL,
QEMU_TIMER_ATTR_ALL);
/* Check realtime timers, because they help with input processing */
deadline = qemu_soonest_timeout(deadline,
qemu_clock_deadline_ns_all(QEMU_CLOCK_REALTIME,
QEMU_TIMER_ATTR_ALL));
/*
* Maintain prior (possibly buggy) behaviour where if no deadline
* was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than
* INT32_MAX nanoseconds ahead, we still use INT32_MAX
* nanoseconds.
*/
if ((deadline < 0) || (deadline > INT32_MAX)) {
deadline = INT32_MAX;
}
return icount_round(deadline);
} else {
return replay_get_instructions();
}
}
static void notify_aio_contexts(void)
{
/* Wake up other AioContexts. */
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
qemu_clock_run_timers(QEMU_CLOCK_VIRTUAL);
}
static void handle_icount_deadline(void)
{
assert(qemu_in_vcpu_thread());
if (icount_enabled()) {
int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL,
QEMU_TIMER_ATTR_ALL);
if (deadline == 0) {
notify_aio_contexts();
}
}
}
static void prepare_icount_for_run(CPUState *cpu)
{
if (icount_enabled()) {
int insns_left;
/*
* These should always be cleared by process_icount_data after
* each vCPU execution. However u16.high can be raised
* asynchronously by cpu_exit/cpu_interrupt/tcg_handle_interrupt
*/
g_assert(cpu_neg(cpu)->icount_decr.u16.low == 0);
g_assert(cpu->icount_extra == 0);
cpu->icount_budget = tcg_get_icount_limit();
insns_left = MIN(0xffff, cpu->icount_budget);
cpu_neg(cpu)->icount_decr.u16.low = insns_left;
cpu->icount_extra = cpu->icount_budget - insns_left;
replay_mutex_lock();
if (cpu->icount_budget == 0 && replay_has_checkpoint()) {
notify_aio_contexts();
}
}
}
static void process_icount_data(CPUState *cpu)
{
if (icount_enabled()) {
/* Account for executed instructions */
icount_update(cpu);
/* Reset the counters */
cpu_neg(cpu)->icount_decr.u16.low = 0;
cpu->icount_extra = 0;
cpu->icount_budget = 0;
replay_account_executed_instructions();
replay_mutex_unlock();
}
}
static int tcg_cpu_exec(CPUState *cpu)
int tcg_cpus_exec(CPUState *cpu)
{
int ret;
#ifdef CONFIG_PROFILER
int64_t ti;
#endif
assert(tcg_enabled());
#ifdef CONFIG_PROFILER
ti = profile_getclock();
@ -249,298 +63,11 @@ static int tcg_cpu_exec(CPUState *cpu)
return ret;
}
/*
* Destroy any remaining vCPUs which have been unplugged and have
* finished running
*/
static void deal_with_unplugged_cpus(void)
{
CPUState *cpu;
CPU_FOREACH(cpu) {
if (cpu->unplug && !cpu_can_run(cpu)) {
qemu_tcg_destroy_vcpu(cpu);
cpu_thread_signal_destroyed(cpu);
break;
}
}
}
/*
* Single-threaded TCG
*
* In the single-threaded case each vCPU is simulated in turn. If
* there is more than a single vCPU we create a simple timer to kick
* the vCPU and ensure we don't get stuck in a tight loop in one vCPU.
* This is done explicitly rather than relying on side-effects
* elsewhere.
*/
static void *tcg_rr_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
assert(tcg_enabled());
rcu_register_thread();
tcg_register_thread();
qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
cpu_thread_signal_created(cpu);
qemu_guest_random_seed_thread_part2(cpu->random_seed);
/* wait for initial kick-off after machine start */
while (first_cpu->stopped) {
qemu_cond_wait_iothread(first_cpu->halt_cond);
/* process any pending work */
CPU_FOREACH(cpu) {
current_cpu = cpu;
qemu_wait_io_event_common(cpu);
}
}
start_tcg_kick_timer();
cpu = first_cpu;
/* process any pending work */
cpu->exit_request = 1;
while (1) {
qemu_mutex_unlock_iothread();
replay_mutex_lock();
qemu_mutex_lock_iothread();
/* Account partial waits to QEMU_CLOCK_VIRTUAL. */
icount_account_warp_timer();
/*
* Run the timers here. This is much more efficient than
* waking up the I/O thread and waiting for completion.
*/
handle_icount_deadline();
replay_mutex_unlock();
if (!cpu) {
cpu = first_cpu;
}
while (cpu && cpu_work_list_empty(cpu) && !cpu->exit_request) {
qatomic_mb_set(&tcg_current_rr_cpu, cpu);
current_cpu = cpu;
qemu_clock_enable(QEMU_CLOCK_VIRTUAL,
(cpu->singlestep_enabled & SSTEP_NOTIMER) == 0);
if (cpu_can_run(cpu)) {
int r;
qemu_mutex_unlock_iothread();
prepare_icount_for_run(cpu);
r = tcg_cpu_exec(cpu);
process_icount_data(cpu);
qemu_mutex_lock_iothread();
if (r == EXCP_DEBUG) {
cpu_handle_guest_debug(cpu);
break;
} else if (r == EXCP_ATOMIC) {
qemu_mutex_unlock_iothread();
cpu_exec_step_atomic(cpu);
qemu_mutex_lock_iothread();
break;
}
} else if (cpu->stop) {
if (cpu->unplug) {
cpu = CPU_NEXT(cpu);
}
break;
}
cpu = CPU_NEXT(cpu);
} /* while (cpu && !cpu->exit_request).. */
/* Does not need qatomic_mb_set because a spurious wakeup is okay. */
qatomic_set(&tcg_current_rr_cpu, NULL);
if (cpu && cpu->exit_request) {
qatomic_mb_set(&cpu->exit_request, 0);
}
if (icount_enabled() && all_cpu_threads_idle()) {
/*
* When all cpus are sleeping (e.g in WFI), to avoid a deadlock
* in the main_loop, wake it up in order to start the warp timer.
*/
qemu_notify_event();
}
qemu_tcg_rr_wait_io_event();
deal_with_unplugged_cpus();
}
rcu_unregister_thread();
return NULL;
}
/*
* Multi-threaded TCG
*
* In the multi-threaded case each vCPU has its own thread. The TLS
* variable current_cpu can be used deep in the code to find the
* current CPUState for a given thread.
*/
static void *tcg_cpu_thread_fn(void *arg)
{
CPUState *cpu = arg;
assert(tcg_enabled());
g_assert(!icount_enabled());
rcu_register_thread();
tcg_register_thread();
qemu_mutex_lock_iothread();
qemu_thread_get_self(cpu->thread);
cpu->thread_id = qemu_get_thread_id();
cpu->can_do_io = 1;
current_cpu = cpu;
cpu_thread_signal_created(cpu);
qemu_guest_random_seed_thread_part2(cpu->random_seed);
/* process any pending work */
cpu->exit_request = 1;
do {
if (cpu_can_run(cpu)) {
int r;
qemu_mutex_unlock_iothread();
r = tcg_cpu_exec(cpu);
qemu_mutex_lock_iothread();
switch (r) {
case EXCP_DEBUG:
cpu_handle_guest_debug(cpu);
break;
case EXCP_HALTED:
/*
* during start-up the vCPU is reset and the thread is
* kicked several times. If we don't ensure we go back
* to sleep in the halted state we won't cleanly
* start-up when the vCPU is enabled.
*
* cpu->halted should ensure we sleep in wait_io_event
*/
g_assert(cpu->halted);
break;
case EXCP_ATOMIC:
qemu_mutex_unlock_iothread();
cpu_exec_step_atomic(cpu);
qemu_mutex_lock_iothread();
default:
/* Ignore everything else? */
break;
}
}
qatomic_mb_set(&cpu->exit_request, 0);
qemu_wait_io_event(cpu);
} while (!cpu->unplug || cpu_can_run(cpu));
qemu_tcg_destroy_vcpu(cpu);
cpu_thread_signal_destroyed(cpu);
qemu_mutex_unlock_iothread();
rcu_unregister_thread();
return NULL;
}
static void tcg_start_vcpu_thread(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
static QemuCond *single_tcg_halt_cond;
static QemuThread *single_tcg_cpu_thread;
static int tcg_region_inited;
assert(tcg_enabled());
/*
* Initialize TCG regions--once. Now is a good time, because:
* (1) TCG's init context, prologue and target globals have been set up.
* (2) qemu_tcg_mttcg_enabled() works now (TCG init code runs before the
* -accel flag is processed, so the check doesn't work then).
*/
if (!tcg_region_inited) {
tcg_region_inited = 1;
tcg_region_init();
parallel_cpus = qemu_tcg_mttcg_enabled() && current_machine->smp.max_cpus > 1;
}
if (qemu_tcg_mttcg_enabled() || !single_tcg_cpu_thread) {
cpu->thread = g_malloc0(sizeof(QemuThread));
cpu->halt_cond = g_malloc0(sizeof(QemuCond));
qemu_cond_init(cpu->halt_cond);
if (qemu_tcg_mttcg_enabled()) {
/* create a thread per vCPU with TCG (MTTCG) */
snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/TCG",
cpu->cpu_index);
qemu_thread_create(cpu->thread, thread_name, tcg_cpu_thread_fn,
cpu, QEMU_THREAD_JOINABLE);
} else {
/* share a single thread for all cpus with TCG */
snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "ALL CPUs/TCG");
qemu_thread_create(cpu->thread, thread_name,
tcg_rr_cpu_thread_fn,
cpu, QEMU_THREAD_JOINABLE);
single_tcg_halt_cond = cpu->halt_cond;
single_tcg_cpu_thread = cpu->thread;
}
#ifdef _WIN32
cpu->hThread = qemu_thread_get_handle(cpu->thread);
#endif
} else {
/* For non-MTTCG cases we share the thread */
cpu->thread = single_tcg_cpu_thread;
cpu->halt_cond = single_tcg_halt_cond;
cpu->thread_id = first_cpu->thread_id;
cpu->can_do_io = 1;
cpu->created = true;
}
}
static int64_t tcg_get_virtual_clock(void)
{
if (icount_enabled()) {
return icount_get();
}
return cpu_get_clock();
}
static int64_t tcg_get_elapsed_ticks(void)
{
if (icount_enabled()) {
return icount_get();
}
return cpu_get_ticks();
}
/* mask must never be zero, except for A20 change call */
static void tcg_handle_interrupt(CPUState *cpu, int mask)
void tcg_cpus_handle_interrupt(CPUState *cpu, int mask)
{
int old_mask;
g_assert(qemu_mutex_iothread_locked());
old_mask = cpu->interrupt_request;
cpu->interrupt_request |= mask;
/*
@ -551,20 +78,5 @@ static void tcg_handle_interrupt(CPUState *cpu, int mask)
qemu_cpu_kick(cpu);
} else {
qatomic_set(&cpu_neg(cpu)->icount_decr.u16.high, -1);
if (icount_enabled() &&
!cpu->can_do_io
&& (mask & ~old_mask) != 0) {
cpu_abort(cpu, "Raised interrupt while not in I/O function");
}
}
}
const CpusAccel tcg_cpus = {
.create_vcpu_thread = tcg_start_vcpu_thread,
.kick_vcpu_thread = tcg_kick_vcpu_thread,
.handle_interrupt = tcg_handle_interrupt,
.get_virtual_clock = tcg_get_virtual_clock,
.get_elapsed_ticks = tcg_get_elapsed_ticks,
};

12
accel/tcg/tcg-cpus.h
View File

@ -1,5 +1,7 @@
/*
* Accelerator CPUS Interface
* QEMU TCG vCPU common functionality
*
* Functionality common to all TCG vcpu variants: mttcg, rr and icount.
*
* Copyright 2020 SUSE LLC
*
@ -12,6 +14,12 @@
#include "sysemu/cpus.h"
extern const CpusAccel tcg_cpus;
extern const CpusAccel tcg_cpus_mttcg;
extern const CpusAccel tcg_cpus_icount;
extern const CpusAccel tcg_cpus_rr;
void tcg_cpus_destroy(CPUState *cpu);
int tcg_cpus_exec(CPUState *cpu);
void tcg_cpus_handle_interrupt(CPUState *cpu, int mask);
#endif /* TCG_CPUS_H */

6
accel/tcg/translate-all.c
View File

@ -2267,6 +2267,10 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
tb_destroy(tb);
}
qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc,
"cpu_io_recompile: rewound execution of TB to "
TARGET_FMT_lx "\n", tb->pc);
/* TODO: If env->pc != tb->pc (i.e. the faulting instruction was not
* the first in the TB) then we end up generating a whole new TB and
* repeating the fault, which is horribly inefficient.
@ -2375,7 +2379,7 @@ void dump_exec_info(void)
qemu_printf("Translation buffer state:\n");
/*
* Report total code size including the padding and TB structs;
* otherwise users might think "-tb-size" is not honoured.
* otherwise users might think "-accel tcg,tb-size" is not honoured.
* For avg host size we use the precise numbers from tb_tree_stats though.
*/
qemu_printf("gen code size %zu/%zu\n",

4
accel/tcg/user-exec-stub.c
View File

@ -9,6 +9,10 @@ void cpu_resume(CPUState *cpu)
{
}
void cpu_remove_sync(CPUState *cpu)
{
}
void qemu_init_vcpu(CPUState *cpu)
{
}

8
accel/xen/xen-all.c
View File

@ -16,6 +16,7 @@
#include "hw/xen/xen_pt.h"
#include "chardev/char.h"
#include "sysemu/accel.h"
#include "sysemu/cpus.h"
#include "sysemu/xen.h"
#include "sysemu/runstate.h"
#include "migration/misc.h"
@ -153,6 +154,10 @@ static void xen_setup_post(MachineState *ms, AccelState *accel)
}
}
const CpusAccel xen_cpus = {
.create_vcpu_thread = dummy_start_vcpu_thread,
};
static int xen_init(MachineState *ms)
{
MachineClass *mc = MACHINE_GET_CLASS(ms);
@ -180,6 +185,9 @@ static int xen_init(MachineState *ms)
* opt out of system RAM being allocated by generic code
*/
mc->default_ram_id = NULL;
cpus_register_accel(&xen_cpus);
return 0;
}

31
audio/audio.c
View File

@ -104,9 +104,6 @@ const struct mixeng_volume nominal_volume = {
static bool legacy_config = true;
#ifdef AUDIO_IS_FLAWLESS_AND_NO_CHECKS_ARE_REQURIED
#error No its not
#else
int audio_bug (const char *funcname, int cond)
{
if (cond) {
@ -119,25 +116,11 @@ int audio_bug (const char *funcname, int cond)
AUD_log (NULL, "I am sorry\n");
}
AUD_log (NULL, "Context:\n");
#if defined AUDIO_BREAKPOINT_ON_BUG
# if defined HOST_I386
# if defined __GNUC__
__asm__ ("int3");
# elif defined _MSC_VER
_asm _emit 0xcc;
# else
abort ();
# endif
# else
abort ();
# endif
#endif
abort();
}
return cond;
}
#endif
static inline int audio_bits_to_index (int bits)
{
@ -1588,13 +1571,6 @@ static void audio_vm_change_state_handler (void *opaque, int running,
audio_reset_timer (s);
}
static bool is_cleaning_up;
bool audio_is_cleaning_up(void)
{
return is_cleaning_up;
}
static void free_audio_state(AudioState *s)
{
HWVoiceOut *hwo, *hwon;
@ -1647,7 +1623,6 @@ static void free_audio_state(AudioState *s)
void audio_cleanup(void)
{
is_cleaning_up = true;
while (!QTAILQ_EMPTY(&audio_states)) {
AudioState *s = QTAILQ_FIRST(&audio_states);
QTAILQ_REMOVE(&audio_states, s, list);
@ -1709,7 +1684,9 @@ static AudioState *audio_init(Audiodev *dev, const char *name)
* backend and this can go away.
*/
driver = audio_driver_lookup("spice");
driver->can_be_default = 1;
if (driver) {
driver->can_be_default = 1;
}
}
if (dev) {

1
audio/audio.h
View File

@ -160,7 +160,6 @@ static inline void *advance (void *p, int incr)
int wav_start_capture(AudioState *state, CaptureState *s, const char *path,
int freq, int bits, int nchannels);
bool audio_is_cleaning_up(void);
void audio_cleanup(void);
void audio_sample_to_uint64(const void *samples, int pos,

53
audio/coreaudio.c
View File

@ -482,7 +482,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
Audiodev *dev = drv_opaque;
AudiodevCoreaudioPerDirectionOptions *cpdo = dev->u.coreaudio.out;
int frames;
struct audsettings fake_as;
struct audsettings obt_as;
/* create mutex */
err = pthread_mutex_init(&core->mutex, NULL);
@ -491,8 +491,8 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
return -1;
}
fake_as = *as;
as = &fake_as;
obt_as = *as;
as = &obt_as;
as->fmt = AUDIO_FORMAT_F32;
audio_pcm_init_info (&hw->info, as);
@ -584,17 +584,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
return -1;
}
/* start Playback */
if (!isPlaying(core->outputDeviceID)) {
status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ, "Could not start playback\n");
AudioDeviceDestroyIOProcID(core->outputDeviceID, core->ioprocid);
core->outputDeviceID = kAudioDeviceUnknown;
return -1;
}
}
return 0;
}
@ -604,22 +593,20 @@ static void coreaudio_fini_out (HWVoiceOut *hw)
int err;
coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
if (!audio_is_cleaning_up()) {
/* stop playback */
if (isPlaying(core->outputDeviceID)) {
status = AudioDeviceStop(core->outputDeviceID, core->ioprocid);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not stop playback\n");
}
}
/* remove callback */
status = AudioDeviceDestroyIOProcID(core->outputDeviceID,
core->ioprocid);
/* stop playback */
if (isPlaying(core->outputDeviceID)) {
status = AudioDeviceStop(core->outputDeviceID, core->ioprocid);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not remove IOProc\n");
coreaudio_logerr(status, "Could not stop playback\n");
}
}
/* remove callback */
status = AudioDeviceDestroyIOProcID(core->outputDeviceID,
core->ioprocid);
if (status != kAudioHardwareNoError) {
coreaudio_logerr(status, "Could not remove IOProc\n");
}
core->outputDeviceID = kAudioDeviceUnknown;
/* destroy mutex */
@ -644,13 +631,11 @@ static void coreaudio_enable_out(HWVoiceOut *hw, bool enable)
}
} else {
/* stop playback */
if (!audio_is_cleaning_up()) {
if (isPlaying(core->outputDeviceID)) {
status = AudioDeviceStop(core->outputDeviceID,
core->ioprocid);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not pause playback\n");
}
if (isPlaying(core->outputDeviceID)) {
status = AudioDeviceStop(core->outputDeviceID,
core->ioprocid);
if (status != kAudioHardwareNoError) {
coreaudio_logerr(status, "Could not pause playback\n");
}
}
}

50
audio/jackaudio.c
View File

@ -25,6 +25,7 @@
#include "qemu/osdep.h"
#include "qemu/module.h"
#include "qemu/atomic.h"
#include "qemu/main-loop.h"
#include "qemu-common.h"
#include "audio.h"
@ -63,6 +64,7 @@ typedef struct QJackClient {
QJackState state;
jack_client_t *client;
jack_nframes_t freq;
QEMUBH *shutdown_bh;
struct QJack *j;
int nchannels;
@ -87,6 +89,7 @@ QJackIn;
static int qjack_client_init(QJackClient *c);
static void qjack_client_connect_ports(QJackClient *c);
static void qjack_client_fini(QJackClient *c);
static QemuMutex qjack_shutdown_lock;
static void qjack_buffer_create(QJackBuffer *buffer, int channels, int frames)
{
@ -306,21 +309,27 @@ static int qjack_xrun(void *arg)
return 0;
}
static void qjack_shutdown_bh(void *opaque)
{
QJackClient *c = (QJackClient *)opaque;
qjack_client_fini(c);
}
static void qjack_shutdown(void *arg)
{
QJackClient *c = (QJackClient *)arg;
c->state = QJACK_STATE_SHUTDOWN;
qemu_bh_schedule(c->shutdown_bh);
}
static void qjack_client_recover(QJackClient *c)
{
if (c->state == QJACK_STATE_SHUTDOWN) {
qjack_client_fini(c);
if (c->state != QJACK_STATE_DISCONNECTED) {
return;
}
/* packets is used simply to throttle this */
if (c->state == QJACK_STATE_DISCONNECTED &&
c->packets % 100 == 0) {
if (c->packets % 100 == 0) {
/* if enabled then attempt to recover */
if (c->enabled) {
@ -489,15 +498,16 @@ static int qjack_init_out(HWVoiceOut *hw, struct audsettings *as,
QJackOut *jo = (QJackOut *)hw;
Audiodev *dev = (Audiodev *)drv_opaque;
qjack_client_fini(&jo->c);
jo->c.out = true;
jo->c.enabled = false;
jo->c.nchannels = as->nchannels;
jo->c.opt = dev->u.jack.out;
jo->c.shutdown_bh = qemu_bh_new(qjack_shutdown_bh, &jo->c);
int ret = qjack_client_init(&jo->c);
if (ret != 0) {
qemu_bh_delete(jo->c.shutdown_bh);
return ret;
}
@ -525,15 +535,16 @@ static int qjack_init_in(HWVoiceIn *hw, struct audsettings *as,
QJackIn *ji = (QJackIn *)hw;
Audiodev *dev = (Audiodev *)drv_opaque;
qjack_client_fini(&ji->c);
ji->c.out = false;
ji->c.enabled = false;
ji->c.nchannels = as->nchannels;
ji->c.opt = dev->u.jack.in;
ji->c.shutdown_bh = qemu_bh_new(qjack_shutdown_bh, &ji->c);
int ret = qjack_client_init(&ji->c);
if (ret != 0) {
qemu_bh_delete(ji->c.shutdown_bh);
return ret;
}
@ -555,7 +566,7 @@ static int qjack_init_in(HWVoiceIn *hw, struct audsettings *as,
return 0;
}
static void qjack_client_fini(QJackClient *c)
static void qjack_client_fini_locked(QJackClient *c)
{
switch (c->state) {
case QJACK_STATE_RUNNING:
@ -564,28 +575,40 @@ static void qjack_client_fini(QJackClient *c)
case QJACK_STATE_SHUTDOWN:
jack_client_close(c->client);
c->client = NULL;
qjack_buffer_free(&c->fifo);
g_free(c->port);
c->state = QJACK_STATE_DISCONNECTED;
/* fallthrough */
case QJACK_STATE_DISCONNECTED:
break;
}
}
qjack_buffer_free(&c->fifo);
g_free(c->port);
c->state = QJACK_STATE_DISCONNECTED;
static void qjack_client_fini(QJackClient *c)
{
qemu_mutex_lock(&qjack_shutdown_lock);
qjack_client_fini_locked(c);
qemu_mutex_unlock(&qjack_shutdown_lock);
}
static void qjack_fini_out(HWVoiceOut *hw)
{
QJackOut *jo = (QJackOut *)hw;
qjack_client_fini(&jo->c);
qemu_bh_delete(jo->c.shutdown_bh);
}
static void qjack_fini_in(HWVoiceIn *hw)
{
QJackIn *ji = (QJackIn *)hw;
qjack_client_fini(&ji->c);
qemu_bh_delete(ji->c.shutdown_bh);
}
static void qjack_enable_out(HWVoiceOut *hw, bool enable)
@ -662,6 +685,7 @@ static void qjack_info(const char *msg)
static void register_audio_jack(void)
{
qemu_mutex_init(&qjack_shutdown_lock);
audio_driver_register(&jack_driver);
jack_set_thread_creator(qjack_thread_creator);
jack_set_error_function(qjack_error);

2
audio/meson.build
View File

@ -1,5 +1,5 @@
softmmu_ss.add([spice_headers, files('audio.c')])
softmmu_ss.add(files(
'audio.c',
'audio_legacy.c',
'mixeng.c',
'noaudio.c',

4
audio/spiceaudio.c
View File

@ -106,7 +106,7 @@ static int line_out_init(HWVoiceOut *hw, struct audsettings *as,
out->active = 0;
out->sin.base.sif = &playback_sif.base;
qemu_spice_add_interface (&out->sin.base);
qemu_spice.add_interface(&out->sin.base);
#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
spice_server_set_playback_rate(&out->sin, settings.freq);
#endif
@ -215,7 +215,7 @@ static int line_in_init(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
in->active = 0;
in->sin.base.sif = &record_sif.base;
qemu_spice_add_interface (&in->sin.base);
qemu_spice.add_interface(&in->sin.base);
#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
spice_server_set_record_rate(&in->sin, settings.freq);
#endif

2
authz/base.c
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

2
authz/list.c
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

13
authz/listfile.c
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
@ -73,7 +73,8 @@ qauthz_list_file_load(QAuthZListFile *fauthz, Error **errp)
pdict = qobject_to(QDict, obj);
if (!pdict) {
error_setg(errp, QERR_INVALID_PARAMETER_TYPE, "obj", "dict");
error_setg(errp, "File '%s' must contain a JSON object",
fauthz->filename);
goto cleanup;
}
@ -122,7 +123,15 @@ qauthz_list_file_complete(UserCreatable *uc, Error **errp)
QAuthZListFile *fauthz = QAUTHZ_LIST_FILE(uc);
gchar *dir = NULL, *file = NULL;
if (!fauthz->filename) {
error_setg(errp, "filename not provided");
return;
}
fauthz->list = qauthz_list_file_load(fauthz, errp);
if (!fauthz->list) {
return;
}
if (!fauthz->refresh) {
return;

10
authz/meson.build
View File

@ -1,4 +1,3 @@
authz_ss = ss.source_set()
authz_ss.add(genh)
authz_ss.add(files(
'base.c',
@ -8,12 +7,3 @@ authz_ss.add(files(
))
authz_ss.add(when: ['CONFIG_AUTH_PAM', pam], if_true: files('pamacct.c'))
authz_ss = authz_ss.apply(config_host, strict: false)
libauthz = static_library('authz', authz_ss.sources() + genh,
dependencies: [authz_ss.dependencies()],
name_suffix: 'fa',
build_by_default: false)
authz = declare_dependency(link_whole: libauthz,
dependencies: qom)

8
authz/pamacct.c
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
@ -84,6 +84,12 @@ qauthz_pam_prop_get_service(Object *obj,
static void
qauthz_pam_complete(UserCreatable *uc, Error **errp)
{
QAuthZPAM *pauthz = QAUTHZ_PAM(uc);
if (!pauthz->service) {
error_setg(errp, "The 'service' property must be set");
return;
}
}

16
authz/simple.c
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
@ -65,11 +65,25 @@ qauthz_simple_finalize(Object *obj)
}
static void
qauthz_simple_complete(UserCreatable *uc, Error **errp)
{
QAuthZSimple *sauthz = QAUTHZ_SIMPLE(uc);
if (!sauthz->identity) {
error_setg(errp, "The 'identity' property must be set");
return;
}
}
static void
qauthz_simple_class_init(ObjectClass *oc, void *data)
{
QAuthZClass *authz = QAUTHZ_CLASS(oc);
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
ucc->complete = qauthz_simple_complete;
authz->is_allowed = qauthz_simple_is_allowed;
object_class_property_add_str(oc, "identity",

2
backends/cryptodev-builtin.c
View File

@ -9,7 +9,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

2
backends/cryptodev-vhost-user.c
View File

@ -9,7 +9,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

2
backends/cryptodev-vhost.c
View File

@ -10,7 +10,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

2
backends/cryptodev.c
View File

@ -9,7 +9,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

9
backends/rng-egd.c
View File

@ -135,12 +135,6 @@ static char *rng_egd_get_chardev(Object *obj, Error **errp)
return NULL;
}
static void rng_egd_init(Object *obj)
{
object_property_add_str(obj, "chardev",
rng_egd_get_chardev, rng_egd_set_chardev);
}
static void rng_egd_finalize(Object *obj)
{
RngEgd *s = RNG_EGD(obj);
@ -155,6 +149,8 @@ static void rng_egd_class_init(ObjectClass *klass, void *data)
rbc->request_entropy = rng_egd_request_entropy;
rbc->opened = rng_egd_opened;
object_class_property_add_str(klass, "chardev",
rng_egd_get_chardev, rng_egd_set_chardev);
}
static const TypeInfo rng_egd_info = {
@ -162,7 +158,6 @@ static const TypeInfo rng_egd_info = {
.parent = TYPE_RNG_BACKEND,
.instance_size = sizeof(RngEgd),
.class_init = rng_egd_class_init,
.instance_init = rng_egd_init,
.instance_finalize = rng_egd_finalize,
};

8
backends/rng-random.c
View File

@ -108,10 +108,6 @@ static void rng_random_init(Object *obj)
{
RngRandom *s = RNG_RANDOM(obj);
object_property_add_str(obj, "filename",
rng_random_get_filename,
rng_random_set_filename);
s->filename = g_strdup("/dev/urandom");
s->fd = -1;
}
@ -134,6 +130,10 @@ static void rng_random_class_init(ObjectClass *klass, void *data)
rbc->request_entropy = rng_random_request_entropy;
rbc->opened = rng_random_opened;
object_class_property_add_str(klass, "filename",
rng_random_get_filename,
rng_random_set_filename);
}
static const TypeInfo rng_random_info = {

8
backends/rng.c
View File

@ -105,10 +105,6 @@ static void rng_backend_init(Object *obj)
RngBackend *s = RNG_BACKEND(obj);
QSIMPLEQ_INIT(&s->requests);
object_property_add_bool(obj, "opened",
rng_backend_prop_get_opened,
rng_backend_prop_set_opened);
}
static void rng_backend_finalize(Object *obj)
@ -123,6 +119,10 @@ static void rng_backend_class_init(ObjectClass *oc, void *data)
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
ucc->complete = rng_backend_complete;
object_class_property_add_bool(oc, "opened",
rng_backend_prop_get_opened,
rng_backend_prop_set_opened);
}
static const TypeInfo rng_backend_info = {

2
backends/tpm/tpm_emulator.c
View File

@ -14,7 +14,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

4
backends/tpm/tpm_ioctl.h
View File

@ -12,6 +12,10 @@
#include <sys/uio.h>
#include <sys/ioctl.h>
#ifdef HAVE_SYS_IOCCOM_H
#include <sys/ioccom.h>
#endif
/*
* Every response from a command involving a TPM command execution must hold
* the ptm_res as the first element.

2
backends/tpm/tpm_passthrough.c
View File

@ -11,7 +11,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

10
backends/tpm/tpm_util.c
View File

@ -8,7 +8,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
@ -35,8 +35,7 @@
static void get_tpm(Object *obj, Visitor *v, const char *name, void *opaque,
Error **errp)
{
DeviceState *dev = DEVICE(obj);
TPMBackend **be = qdev_get_prop_ptr(dev, opaque);
TPMBackend **be = qdev_get_prop_ptr(obj, opaque);
char *p;
p = g_strdup(*be ? (*be)->id : "");
@ -49,7 +48,7 @@ static void set_tpm(Object *obj, Visitor *v, const char *name, void *opaque,
{
DeviceState *dev = DEVICE(obj);
Property *prop = opaque;
TPMBackend *s, **be = qdev_get_prop_ptr(dev, prop);
TPMBackend *s, **be = qdev_get_prop_ptr(obj, prop);
char *str;
if (dev->realized) {
@ -73,9 +72,8 @@ static void set_tpm(Object *obj, Visitor *v, const char *name, void *opaque,
static void release_tpm(Object *obj, const char *name, void *opaque)
{
DeviceState *dev = DEVICE(obj);
Property *prop = opaque;
TPMBackend **be = qdev_get_prop_ptr(dev, prop);
TPMBackend **be = qdev_get_prop_ptr(obj, prop);
if (*be) {
tpm_backend_reset(*be);

6
backends/vhost-user.c
View File

@ -175,9 +175,9 @@ static char *get_chardev(Object *obj, Error **errp)
return NULL;
}
static void vhost_user_backend_init(Object *obj)
static void vhost_user_backend_class_init(ObjectClass *oc, void *data)
{
object_property_add_str(obj, "chardev", get_chardev, set_chardev);
object_class_property_add_str(oc, "chardev", get_chardev, set_chardev);
}
static void vhost_user_backend_finalize(Object *obj)
@ -195,7 +195,7 @@ static const TypeInfo vhost_user_backend_info = {
.name = TYPE_VHOST_USER_BACKEND,
.parent = TYPE_OBJECT,
.instance_size = sizeof(VhostUserBackend),
.instance_init = vhost_user_backend_init,
.class_init = vhost_user_backend_class_init,
.instance_finalize = vhost_user_backend_finalize,
};

138
block.c
View File

@ -26,6 +26,7 @@
#include "block/trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/fuse.h"
#include "block/nbd.h"
#include "block/qdict.h"
#include "qemu/error-report.h"
@ -961,6 +962,11 @@ int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
}
bs->total_sectors = hint;
if (bs->total_sectors * BDRV_SECTOR_SIZE > BDRV_MAX_LENGTH) {
return -EFBIG;
}
return 0;
}
@ -4458,6 +4464,15 @@ static void bdrv_close(BlockDriverState *bs)
}
QLIST_INIT(&bs->aio_notifiers);
bdrv_drained_end(bs);
/*
* If we're still inside some bdrv_drain_all_begin()/end() sections, end
* them now since this BDS won't exist anymore when bdrv_drain_all_end()
* gets called.
*/
if (bs->quiesce_counter) {
bdrv_drain_all_end_quiesce(bs);
}
}
void bdrv_close_all(void)
@ -4554,8 +4569,16 @@ static bool should_update_child(BdrvChild *c, BlockDriverState *to)
return ret;
}
void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
Error **errp)
/*
* With auto_skip=true bdrv_replace_node_common skips updating from parents
* if it creates a parent-child relation loop or if parent is block-job.
*
* With auto_skip=false the error is returned if from has a parent which should
* not be updated.
*/
static void bdrv_replace_node_common(BlockDriverState *from,
BlockDriverState *to,
bool auto_skip, Error **errp)
{
BdrvChild *c, *next;
GSList *list = NULL, *p;
@ -4574,7 +4597,12 @@ void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
assert(c->bs == from);
if (!should_update_child(c, to)) {
continue;
if (auto_skip) {
continue;
}
error_setg(errp, "Should not change '%s' link to '%s'",
c->name, from->node_name);
goto out;
}
if (c->frozen) {
error_setg(errp, "Cannot change '%s' link to '%s'",
@ -4614,6 +4642,12 @@ out:
bdrv_unref(from);
}
void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
Error **errp)
{
return bdrv_replace_node_common(from, to, true, errp);
}
/*
* Add new bs contents at the top of an image chain while the chain is
* live, while keeping required fields on the top layer.
@ -4882,9 +4916,11 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
{
BlockDriverState *explicit_top = top;
bool update_inherits_from;
BdrvChild *c, *next;
BdrvChild *c;
Error *local_err = NULL;
int ret = -EIO;
g_autoptr(GSList) updated_children = NULL;
GSList *p;
bdrv_ref(top);
bdrv_subtree_drained_begin(top);
@ -4898,14 +4934,6 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
goto exit;
}
/* This function changes all links that point to top and makes
* them point to base. Check that none of them is frozen. */
QLIST_FOREACH(c, &top->parents, next_parent) {
if (c->frozen) {
goto exit;
}
}
/* If 'base' recursively inherits from 'top' then we should set
* base->inherits_from to top->inherits_from after 'top' and all
* other intermediate nodes have been dropped.
@ -4922,36 +4950,36 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
backing_file_str = base->filename;
}
QLIST_FOREACH_SAFE(c, &top->parents, next_parent, next) {
/* Check whether we are allowed to switch c from top to base */
GSList *ignore_children = g_slist_prepend(NULL, c);
ret = bdrv_check_update_perm(base, NULL, c->perm, c->shared_perm,
ignore_children, NULL, &local_err);
g_slist_free(ignore_children);
if (ret < 0) {
error_report_err(local_err);
goto exit;
}
QLIST_FOREACH(c, &top->parents, next_parent) {
updated_children = g_slist_prepend(updated_children, c);
}
bdrv_replace_node_common(top, base, false, &local_err);
if (local_err) {
error_report_err(local_err);
goto exit;
}
for (p = updated_children; p; p = p->next) {
c = p->data;
/* If so, update the backing file path in the image file */
if (c->klass->update_filename) {
ret = c->klass->update_filename(c, base, backing_file_str,
&local_err);
if (ret < 0) {
bdrv_abort_perm_update(base);
/*
* TODO: Actually, we want to rollback all previous iterations
* of this loop, and (which is almost impossible) previous
* bdrv_replace_node()...
*
* Note, that c->klass->update_filename may lead to permission
* update, so it's a bad idea to call it inside permission
* update transaction of bdrv_replace_node.
*/
error_report_err(local_err);
goto exit;
}
}
/*
* Do the actual switch in the in-memory graph.
* Completes bdrv_check_update_perm() transaction internally.
* c->frozen is false, we have checked that above.
*/
bdrv_ref(base);
bdrv_replace_child(c, base);
bdrv_unref(top);
}
if (update_inherits_from) {
@ -5082,8 +5110,13 @@ int64_t bdrv_getlength(BlockDriverState *bs)
{
int64_t ret = bdrv_nb_sectors(bs);
ret = ret > INT64_MAX / BDRV_SECTOR_SIZE ? -EFBIG : ret;
return ret < 0 ? ret : ret * BDRV_SECTOR_SIZE;
if (ret < 0) {
return ret;
}
if (ret > INT64_MAX / BDRV_SECTOR_SIZE) {
return -EFBIG;
}
return ret * BDRV_SECTOR_SIZE;
}
/* return 0 as number of sectors if no device present or error */
@ -5211,7 +5244,7 @@ BlockDriverState *bdrv_find_node(const char *node_name)
BlockDeviceInfoList *bdrv_named_nodes_list(bool flat,
Error **errp)
{
BlockDeviceInfoList *list, *entry;
BlockDeviceInfoList *list;
BlockDriverState *bs;
list = NULL;
@ -5221,22 +5254,12 @@ BlockDeviceInfoList *bdrv_named_nodes_list(bool flat,
qapi_free_BlockDeviceInfoList(list);
return NULL;
}
entry = g_malloc0(sizeof(*entry));
entry->value = info;
entry->next = list;
list = entry;
QAPI_LIST_PREPEND(list, info);
}
return list;
}
#define QAPI_LIST_ADD(list, element) do { \
typeof(list) _tmp = g_new(typeof(*(list)), 1); \
_tmp->value = (element); \
_tmp->next = (list); \
(list) = _tmp; \
} while (0)
typedef struct XDbgBlockGraphConstructor {
XDbgBlockGraph *graph;
GHashTable *graph_nodes;
@ -5291,7 +5314,7 @@ static void xdbg_graph_add_node(XDbgBlockGraphConstructor *gr, void *node,
n->type = type;
n->name = g_strdup(name);
QAPI_LIST_ADD(gr->graph->nodes, n);
QAPI_LIST_PREPEND(gr->graph->nodes, n);
}
static void xdbg_graph_add_edge(XDbgBlockGraphConstructor *gr, void *parent,
@ -5310,14 +5333,14 @@ static void xdbg_graph_add_edge(XDbgBlockGraphConstructor *gr, void *parent,
uint64_t flag = bdrv_qapi_perm_to_blk_perm(qapi_perm);
if (flag & child->perm) {
QAPI_LIST_ADD(edge->perm, qapi_perm);
QAPI_LIST_PREPEND(edge->perm, qapi_perm);
}
if (flag & child->shared_perm) {
QAPI_LIST_ADD(edge->shared_perm, qapi_perm);
QAPI_LIST_PREPEND(edge->shared_perm, qapi_perm);
}
}
QAPI_LIST_ADD(gr->graph->edges, edge);
QAPI_LIST_PREPEND(gr->graph->edges, edge);
}
@ -5517,6 +5540,7 @@ void bdrv_get_backing_filename(BlockDriverState *bs,
int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
int ret;
BlockDriver *drv = bs->drv;
/* if bs->drv == NULL, bs is closed, so there's nothing to do here */
if (!drv) {
@ -5530,7 +5554,16 @@ int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
return -ENOTSUP;
}
memset(bdi, 0, sizeof(*bdi));
return drv->bdrv_get_info(bs, bdi);
ret = drv->bdrv_get_info(bs, bdi);
if (ret < 0) {
return ret;
}
if (bdi->cluster_size > BDRV_MAX_ALIGNMENT) {
return -EINVAL;
}
return 0;
}
ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs,
@ -5783,6 +5816,7 @@ int coroutine_fn bdrv_co_invalidate_cache(BlockDriverState *bs, Error **errp)
bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, NULL, errp);
if (ret < 0) {
bdrv_abort_perm_update(bs);
bs->open_flags |= BDRV_O_INACTIVE;
return ret;
}

32
block/accounting.c
View File

@ -199,29 +199,27 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
return;
}
qemu_mutex_lock(&stats->lock);
WITH_QEMU_LOCK_GUARD(&stats->lock) {
if (failed) {
stats->failed_ops[cookie->type]++;
} else {
stats->nr_bytes[cookie->type] += cookie->bytes;
stats->nr_ops[cookie->type]++;
}
if (failed) {
stats->failed_ops[cookie->type]++;
} else {
stats->nr_bytes[cookie->type] += cookie->bytes;
stats->nr_ops[cookie->type]++;
}
block_latency_histogram_account(&stats->latency_histogram[cookie->type],
latency_ns);
block_latency_histogram_account(&stats->latency_histogram[cookie->type],
latency_ns);
if (!failed || stats->account_failed) {
stats->total_time_ns[cookie->type] += latency_ns;
stats->last_access_time_ns = time_ns;
if (!failed || stats->account_failed) {
stats->total_time_ns[cookie->type] += latency_ns;
stats->last_access_time_ns = time_ns;
QSLIST_FOREACH(s, &stats->intervals, entries) {
timed_average_account(&s->latency[cookie->type], latency_ns);
QSLIST_FOREACH(s, &stats->intervals, entries) {
timed_average_account(&s->latency[cookie->type], latency_ns);
}
}
}
qemu_mutex_unlock(&stats->lock);
cookie->type = BLOCK_ACCT_NONE;
}

3
block/blkdebug.c
View File

@ -173,7 +173,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
{
struct add_rule_data *d = opaque;
BDRVBlkdebugState *s = d->s;
const char* event_name;
const char *event_name;
int event;
struct BlkdebugRule *rule;
int64_t sector;
@ -215,6 +215,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
BLKDEBUG_IO_TYPE__MAX, &local_error);
if (local_error) {
error_propagate(errp, local_error);
g_free(rule);
return -1;
}
if (iotype != BLKDEBUG_IO_TYPE__MAX) {

2
block/commit.c
View File

@ -156,7 +156,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp)
/* Copy if allocated above the base */
ret = bdrv_is_allocated_above(blk_bs(s->top), s->base_overlay, true,
offset, COMMIT_BUFFER_SIZE, &n);
copy = (ret == 1);
copy = (ret > 0);
trace_commit_one_iteration(s, offset, n, ret);
if (copy) {
assert(n < SIZE_MAX);

8
block/coroutines.h
View File

@ -41,21 +41,25 @@ bdrv_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes,
int coroutine_fn
bdrv_co_common_block_status_above(BlockDriverState *bs,
BlockDriverState *base,
bool include_base,
bool want_zero,
int64_t offset,
int64_t bytes,
int64_t *pnum,
int64_t *map,
BlockDriverState **file);
BlockDriverState **file,
int *depth);
int generated_co_wrapper
bdrv_common_block_status_above(BlockDriverState *bs,
BlockDriverState *base,
bool include_base,
bool want_zero,
int64_t offset,
int64_t bytes,
int64_t *pnum,
int64_t *map,
BlockDriverState **file);
BlockDriverState **file,
int *depth);
int coroutine_fn bdrv_co_readv_vmstate(BlockDriverState *bs,
QEMUIOVector *qiov, int64_t pos);

2
block/crypto.c
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

2
block/crypto.h
View File

@ -6,7 +6,7 @@
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of

28
block/curl.c
View File

@ -564,23 +564,23 @@ static void curl_detach_aio_context(BlockDriverState *bs)
BDRVCURLState *s = bs->opaque;
int i;
qemu_mutex_lock(&s->mutex);
for (i = 0; i < CURL_NUM_STATES; i++) {
if (s->states[i].in_use) {
curl_clean_state(&s->states[i]);
WITH_QEMU_LOCK_GUARD(&s->mutex) {
for (i = 0; i < CURL_NUM_STATES; i++) {
if (s->states[i].in_use) {
curl_clean_state(&s->states[i]);
}
if (s->states[i].curl) {
curl_easy_cleanup(s->states[i].curl);
s->states[i].curl = NULL;
}
g_free(s->states[i].orig_buf);
s->states[i].orig_buf = NULL;
}
if (s->states[i].curl) {
curl_easy_cleanup(s->states[i].curl);
s->states[i].curl = NULL;
if (s->multi) {
curl_multi_cleanup(s->multi);
s->multi = NULL;
}
g_free(s->states[i].orig_buf);
s->states[i].orig_buf = NULL;
}
if (s->multi) {
curl_multi_cleanup(s->multi);
s->multi = NULL;
}
qemu_mutex_unlock(&s->mutex);
timer_del(&s->timer);
}

1
block/dmg-lzfse.c
View File

@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "dmg.h"
#include <lzfse.h>

2
block/dmg.c
View File

@ -559,7 +559,7 @@ static void dmg_refresh_limits(BlockDriverState *bs, Error **errp)
bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */
}
static inline int is_sector_in_chunk(BDRVDMGState* s,
static inline int is_sector_in_chunk(BDRVDMGState *s,
uint32_t chunk_num, uint64_t sector_num)
{
if (chunk_num >= s->n_chunks || s->sectors[chunk_num] > sector_num ||

41
block/export/export.c
View File

@ -15,15 +15,26 @@
#include "block/block.h"
#include "sysemu/block-backend.h"
#include "sysemu/iothread.h"
#include "block/export.h"
#include "block/fuse.h"
#include "block/nbd.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-block-export.h"
#include "qapi/qapi-events-block-export.h"
#include "qemu/id.h"
#ifdef CONFIG_VHOST_USER_BLK_SERVER
#include "vhost-user-blk-server.h"
#endif
static const BlockExportDriver *blk_exp_drivers[] = {
&blk_exp_nbd,
#ifdef CONFIG_VHOST_USER_BLK_SERVER
&blk_exp_vhost_user_blk,
#endif
#ifdef CONFIG_FUSE
&blk_exp_fuse,
#endif
};
/* Only accessed from the main thread */
@ -57,10 +68,11 @@ static const BlockExportDriver *blk_exp_find_driver(BlockExportType type)
BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp)
{
bool fixed_iothread = export->has_fixed_iothread && export->fixed_iothread;
const BlockExportDriver *drv;
BlockExport *exp = NULL;
BlockDriverState *bs;
BlockBackend *blk;
BlockBackend *blk = NULL;
AioContext *ctx;
uint64_t perm;
int ret;
@ -96,6 +108,28 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp)
ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
if (export->has_iothread) {
IOThread *iothread;
AioContext *new_ctx;
iothread = iothread_by_id(export->iothread);
if (!iothread) {
error_setg(errp, "iothread \"%s\" not found", export->iothread);
goto fail;
}
new_ctx = iothread_get_aio_context(iothread);
ret = bdrv_try_set_aio_context(bs, new_ctx, errp);
if (ret == 0) {
aio_context_release(ctx);
aio_context_acquire(new_ctx);
ctx = new_ctx;
} else if (fixed_iothread) {
goto fail;
}
}
/*
* Block exports are used for non-shared storage migration. Make sure
* that BDRV_O_INACTIVE is cleared and the image is ready for write
@ -110,6 +144,11 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp)
}
blk = blk_new(ctx, perm, BLK_PERM_ALL);
if (!fixed_iothread) {
blk_set_allow_aio_context_change(blk, true);
}
ret = blk_insert_bs(blk, bs, errp);
if (ret < 0) {
goto fail;

726
block/export/fuse.c Normal file
View File

@ -0,0 +1,726 @@
/*
* Present a block device as a raw image through FUSE
*
* Copyright (c) 2020 Max Reitz <mreitz@redhat.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; under version 2 or later of the License.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#define FUSE_USE_VERSION 31
#include "qemu/osdep.h"
#include "block/aio.h"
#include "block/block.h"
#include "block/export.h"
#include "block/fuse.h"
#include "block/qapi.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-block.h"
#include "sysemu/block-backend.h"
#include <fuse.h>
#include <fuse_lowlevel.h>
/* Prevent overly long bounce buffer allocations */
#define FUSE_MAX_BOUNCE_BYTES (MIN(BDRV_REQUEST_MAX_BYTES, 64 * 1024 * 1024))
typedef struct FuseExport {
BlockExport common;
struct fuse_session *fuse_session;
struct fuse_buf fuse_buf;
bool mounted, fd_handler_set_up;
char *mountpoint;
bool writable;
bool growable;
} FuseExport;
static GHashTable *exports;
static const struct fuse_lowlevel_ops fuse_ops;
static void fuse_export_shutdown(BlockExport *exp);
static void fuse_export_delete(BlockExport *exp);
static void init_exports_table(void);
static int setup_fuse_export(FuseExport *exp, const char *mountpoint,
Error **errp);
static void read_from_fuse_export(void *opaque);
static bool is_regular_file(const char *path, Error **errp);
static int fuse_export_create(BlockExport *blk_exp,
BlockExportOptions *blk_exp_args,
Error **errp)
{
FuseExport *exp = container_of(blk_exp, FuseExport, common);
BlockExportOptionsFuse *args = &blk_exp_args->u.fuse;
int ret;
assert(blk_exp_args->type == BLOCK_EXPORT_TYPE_FUSE);
/* For growable exports, take the RESIZE permission */
if (args->growable) {
uint64_t blk_perm, blk_shared_perm;
blk_get_perm(exp->common.blk, &blk_perm, &blk_shared_perm);
ret = blk_set_perm(exp->common.blk, blk_perm | BLK_PERM_RESIZE,
blk_shared_perm, errp);
if (ret < 0) {
return ret;
}
}
init_exports_table();
/*
* It is important to do this check before calling is_regular_file() --
* that function will do a stat(), which we would have to handle if we
* already exported something on @mountpoint. But we cannot, because
* we are currently caught up here.
* (Note that ideally we would want to resolve relative paths here,
* but bdrv_make_absolute_filename() might do the wrong thing for
* paths that contain colons, and realpath() would resolve symlinks,
* which we do not want: The mount point is not going to be the
* symlink's destination, but the link itself.)
* So this will not catch all potential clashes, but hopefully at
* least the most common one of specifying exactly the same path
* string twice.
*/
if (g_hash_table_contains(exports, args->mountpoint)) {
error_setg(errp, "There already is a FUSE export on '%s'",
args->mountpoint);
ret = -EEXIST;
goto fail;
}
if (!is_regular_file(args->mountpoint, errp)) {
ret = -EINVAL;
goto fail;
}
exp->mountpoint = g_strdup(args->mountpoint);
exp->writable = blk_exp_args->writable;
exp->growable = args->growable;
ret = setup_fuse_export(exp, args->mountpoint, errp);
if (ret < 0) {
goto fail;
}
return 0;
fail:
fuse_export_delete(blk_exp);
return ret;
}
/**
* Allocates the global @exports hash table.
*/
static void init_exports_table(void)
{
if (exports) {
return;
}
exports = g_hash_table_new_full(g_str_hash, g_str_equal, g_free, NULL);
}
/**
* Create exp->fuse_session and mount it.
*/
static int setup_fuse_export(FuseExport *exp, const char *mountpoint,
Error **errp)
{
const char *fuse_argv[4];
char *mount_opts;
struct fuse_args fuse_args;
int ret;
/* Needs to match what fuse_init() sets. Only max_read must be supplied. */
mount_opts = g_strdup_printf("max_read=%zu", FUSE_MAX_BOUNCE_BYTES);
fuse_argv[0] = ""; /* Dummy program name */
fuse_argv[1] = "-o";
fuse_argv[2] = mount_opts;
fuse_argv[3] = NULL;
fuse_args = (struct fuse_args)FUSE_ARGS_INIT(3, (char **)fuse_argv);
exp->fuse_session = fuse_session_new(&fuse_args, &fuse_ops,
sizeof(fuse_ops), exp);
g_free(mount_opts);
if (!exp->fuse_session) {
error_setg(errp, "Failed to set up FUSE session");
ret = -EIO;
goto fail;
}
ret = fuse_session_mount(exp->fuse_session, mountpoint);
if (ret < 0) {
error_setg(errp, "Failed to mount FUSE session to export");
ret = -EIO;
goto fail;
}
exp->mounted = true;
g_hash_table_insert(exports, g_strdup(mountpoint), NULL);
aio_set_fd_handler(exp->common.ctx,
fuse_session_fd(exp->fuse_session), true,
read_from_fuse_export, NULL, NULL, exp);
exp->fd_handler_set_up = true;
return 0;
fail:
fuse_export_shutdown(&exp->common);
return ret;
}
/**
* Callback to be invoked when the FUSE session FD can be read from.
* (This is basically the FUSE event loop.)
*/
static void read_from_fuse_export(void *opaque)
{
FuseExport *exp = opaque;
int ret;
blk_exp_ref(&exp->common);
do {
ret = fuse_session_receive_buf(exp->fuse_session, &exp->fuse_buf);
} while (ret == -EINTR);
if (ret < 0) {
goto out;
}
fuse_session_process_buf(exp->fuse_session, &exp->fuse_buf);
out:
blk_exp_unref(&exp->common);
}
static void fuse_export_shutdown(BlockExport *blk_exp)
{
FuseExport *exp = container_of(blk_exp, FuseExport, common);
if (exp->fuse_session) {
fuse_session_exit(exp->fuse_session);
if (exp->fd_handler_set_up) {
aio_set_fd_handler(exp->common.ctx,
fuse_session_fd(exp->fuse_session), true,
NULL, NULL, NULL, NULL);
exp->fd_handler_set_up = false;
}
}
if (exp->mountpoint) {
/*
* Safe to drop now, because we will not handle any requests
* for this export anymore anyway.
*/
g_hash_table_remove(exports, exp->mountpoint);
}
}
static void fuse_export_delete(BlockExport *blk_exp)
{
FuseExport *exp = container_of(blk_exp, FuseExport, common);
if (exp->fuse_session) {
if (exp->mounted) {
fuse_session_unmount(exp->fuse_session);
}
fuse_session_destroy(exp->fuse_session);
}
free(exp->fuse_buf.mem);
g_free(exp->mountpoint);
}
/**
* Check whether @path points to a regular file. If not, put an
* appropriate message into *errp.
*/
static bool is_regular_file(const char *path, Error **errp)
{
struct stat statbuf;
int ret;
ret = stat(path, &statbuf);
if (ret < 0) {
error_setg_errno(errp, errno, "Failed to stat '%s'", path);
return false;
}
if (!S_ISREG(statbuf.st_mode)) {
error_setg(errp, "'%s' is not a regular file", path);
return false;
}
return true;
}
/**
* A chance to set change some parameters supplied to FUSE_INIT.
*/
static void fuse_init(void *userdata, struct fuse_conn_info *conn)
{
/*
* MIN_NON_ZERO() would not be wrong here, but what we set here
* must equal what has been passed to fuse_session_new().
* Therefore, as long as max_read must be passed as a mount option
* (which libfuse claims will be changed at some point), we have
* to set max_read to a fixed value here.
*/
conn->max_read = FUSE_MAX_BOUNCE_BYTES;
conn->max_write = MIN_NON_ZERO(BDRV_REQUEST_MAX_BYTES, conn->max_write);
}
/**
* Let clients look up files. Always return ENOENT because we only
* care about the mountpoint itself.
*/
static void fuse_lookup(fuse_req_t req, fuse_ino_t parent, const char *name)
{
fuse_reply_err(req, ENOENT);
}
/**
* Let clients get file attributes (i.e., stat() the file).
*/
static void fuse_getattr(fuse_req_t req, fuse_ino_t inode,
struct fuse_file_info *fi)
{
struct stat statbuf;
int64_t length, allocated_blocks;
time_t now = time(NULL);
FuseExport *exp = fuse_req_userdata(req);
mode_t mode;
length = blk_getlength(exp->common.blk);
if (length < 0) {
fuse_reply_err(req, -length);
return;
}
allocated_blocks = bdrv_get_allocated_file_size(blk_bs(exp->common.blk));
if (allocated_blocks <= 0) {
allocated_blocks = DIV_ROUND_UP(length, 512);
} else {
allocated_blocks = DIV_ROUND_UP(allocated_blocks, 512);
}
mode = S_IFREG | S_IRUSR;
if (exp->writable) {
mode |= S_IWUSR;
}
statbuf = (struct stat) {
.st_ino = inode,
.st_mode = mode,
.st_nlink = 1,
.st_uid = getuid(),
.st_gid = getgid(),
.st_size = length,
.st_blksize = blk_bs(exp->common.blk)->bl.request_alignment,
.st_blocks = allocated_blocks,
.st_atime = now,
.st_mtime = now,
.st_ctime = now,
};
fuse_reply_attr(req, &statbuf, 1.);
}
static int fuse_do_truncate(const FuseExport *exp, int64_t size,
bool req_zero_write, PreallocMode prealloc)
{
uint64_t blk_perm, blk_shared_perm;
BdrvRequestFlags truncate_flags = 0;
int ret;
if (req_zero_write) {
truncate_flags |= BDRV_REQ_ZERO_WRITE;
}
/* Growable exports have a permanent RESIZE permission */
if (!exp->growable) {
blk_get_perm(exp->common.blk, &blk_perm, &blk_shared_perm);
ret = blk_set_perm(exp->common.blk, blk_perm | BLK_PERM_RESIZE,
blk_shared_perm, NULL);
if (ret < 0) {
return ret;
}
}
ret = blk_truncate(exp->common.blk, size, true, prealloc,
truncate_flags, NULL);
if (!exp->growable) {
/* Must succeed, because we are only giving up the RESIZE permission */
blk_set_perm(exp->common.blk, blk_perm, blk_shared_perm, &error_abort);
}
return ret;
}
/**
* Let clients set file attributes. Only resizing is supported.
*/
static void fuse_setattr(fuse_req_t req, fuse_ino_t inode, struct stat *statbuf,
int to_set, struct fuse_file_info *fi)
{
FuseExport *exp = fuse_req_userdata(req);
int ret;
if (!exp->writable) {
fuse_reply_err(req, EACCES);
return;
}
if (to_set & ~FUSE_SET_ATTR_SIZE) {
fuse_reply_err(req, ENOTSUP);
return;
}
ret = fuse_do_truncate(exp, statbuf->st_size, true, PREALLOC_MODE_OFF);
if (ret < 0) {
fuse_reply_err(req, -ret);
return;
}
fuse_getattr(req, inode, fi);
}
/**
* Let clients open a file (i.e., the exported image).
*/
static void fuse_open(fuse_req_t req, fuse_ino_t inode,
struct fuse_file_info *fi)
{
fuse_reply_open(req, fi);
}
/**
* Handle client reads from the exported image.
*/
static void fuse_read(fuse_req_t req, fuse_ino_t inode,
size_t size, off_t offset, struct fuse_file_info *fi)
{
FuseExport *exp = fuse_req_userdata(req);
int64_t length;
void *buf;
int ret;
/* Limited by max_read, should not happen */
if (size > FUSE_MAX_BOUNCE_BYTES) {
fuse_reply_err(req, EINVAL);
return;
}
/**
* Clients will expect short reads at EOF, so we have to limit
* offset+size to the image length.
*/
length = blk_getlength(exp->common.blk);
if (length < 0) {
fuse_reply_err(req, -length);
return;
}
if (offset + size > length) {
size = length - offset;
}
buf = qemu_try_blockalign(blk_bs(exp->common.blk), size);
if (!buf) {
fuse_reply_err(req, ENOMEM);
return;
}
ret = blk_pread(exp->common.blk, offset, buf, size);
if (ret >= 0) {
fuse_reply_buf(req, buf, size);
} else {
fuse_reply_err(req, -ret);
}
qemu_vfree(buf);
}
/**
* Handle client writes to the exported image.
*/
static void fuse_write(fuse_req_t req, fuse_ino_t inode, const char *buf,
size_t size, off_t offset, struct fuse_file_info *fi)
{
FuseExport *exp = fuse_req_userdata(req);
int64_t length;
int ret;
/* Limited by max_write, should not happen */
if (size > BDRV_REQUEST_MAX_BYTES) {
fuse_reply_err(req, EINVAL);
return;
}
if (!exp->writable) {
fuse_reply_err(req, EACCES);
return;
}
/**
* Clients will expect short writes at EOF, so we have to limit
* offset+size to the image length.
*/
length = blk_getlength(exp->common.blk);
if (length < 0) {
fuse_reply_err(req, -length);
return;
}
if (offset + size > length) {
if (exp->growable) {
ret = fuse_do_truncate(exp, offset + size, true, PREALLOC_MODE_OFF);
if (ret < 0) {
fuse_reply_err(req, -ret);
return;
}
} else {
size = length - offset;
}
}
ret = blk_pwrite(exp->common.blk, offset, buf, size, 0);
if (ret >= 0) {
fuse_reply_write(req, size);
} else {
fuse_reply_err(req, -ret);
}
}
/**
* Let clients perform various fallocate() operations.
*/
static void fuse_fallocate(fuse_req_t req, fuse_ino_t inode, int mode,
off_t offset, off_t length,
struct fuse_file_info *fi)
{
FuseExport *exp = fuse_req_userdata(req);
int64_t blk_len;
int ret;
if (!exp->writable) {
fuse_reply_err(req, EACCES);
return;
}
blk_len = blk_getlength(exp->common.blk);
if (blk_len < 0) {
fuse_reply_err(req, -blk_len);
return;
}
if (mode & FALLOC_FL_KEEP_SIZE) {
length = MIN(length, blk_len - offset);
}
if (mode & FALLOC_FL_PUNCH_HOLE) {
if (!(mode & FALLOC_FL_KEEP_SIZE)) {
fuse_reply_err(req, EINVAL);
return;
}
do {
int size = MIN(length, BDRV_REQUEST_MAX_BYTES);
ret = blk_pdiscard(exp->common.blk, offset, size);
offset += size;
length -= size;
} while (ret == 0 && length > 0);
} else if (mode & FALLOC_FL_ZERO_RANGE) {
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + length > blk_len) {
/* No need for zeroes, we are going to write them ourselves */
ret = fuse_do_truncate(exp, offset + length, false,
PREALLOC_MODE_OFF);
if (ret < 0) {
fuse_reply_err(req, -ret);
return;
}
}
do {
int size = MIN(length, BDRV_REQUEST_MAX_BYTES);
ret = blk_pwrite_zeroes(exp->common.blk,
offset, size, 0);
offset += size;
length -= size;
} while (ret == 0 && length > 0);
} else if (!mode) {
/* We can only fallocate at the EOF with a truncate */
if (offset < blk_len) {
fuse_reply_err(req, EOPNOTSUPP);
return;
}
if (offset > blk_len) {
/* No preallocation needed here */
ret = fuse_do_truncate(exp, offset, true, PREALLOC_MODE_OFF);
if (ret < 0) {
fuse_reply_err(req, -ret);
return;
}
}
ret = fuse_do_truncate(exp, offset + length, true,
PREALLOC_MODE_FALLOC);
} else {
ret = -EOPNOTSUPP;
}
fuse_reply_err(req, ret < 0 ? -ret : 0);
}
/**
* Let clients fsync the exported image.
*/
static void fuse_fsync(fuse_req_t req, fuse_ino_t inode, int datasync,
struct fuse_file_info *fi)
{
FuseExport *exp = fuse_req_userdata(req);
int ret;
ret = blk_flush(exp->common.blk);
fuse_reply_err(req, ret < 0 ? -ret : 0);
}
/**
* Called before an FD to the exported image is closed. (libfuse
* notes this to be a way to return last-minute errors.)
*/
static void fuse_flush(fuse_req_t req, fuse_ino_t inode,
struct fuse_file_info *fi)
{
fuse_fsync(req, inode, 1, fi);
}
#ifdef CONFIG_FUSE_LSEEK
/**
* Let clients inquire allocation status.
*/
static void fuse_lseek(fuse_req_t req, fuse_ino_t inode, off_t offset,
int whence, struct fuse_file_info *fi)
{
FuseExport *exp = fuse_req_userdata(req);
if (whence != SEEK_HOLE && whence != SEEK_DATA) {
fuse_reply_err(req, EINVAL);
return;
}
while (true) {
int64_t pnum;
int ret;
ret = bdrv_block_status_above(blk_bs(exp->common.blk), NULL,
offset, INT64_MAX, &pnum, NULL, NULL);
if (ret < 0) {
fuse_reply_err(req, -ret);
return;
}
if (!pnum && (ret & BDRV_BLOCK_EOF)) {
int64_t blk_len;
/*
* If blk_getlength() rounds (e.g. by sectors), then the
* export length will be rounded, too. However,
* bdrv_block_status_above() may return EOF at unaligned
* offsets. We must not let this become visible and thus
* always simulate a hole between @offset (the real EOF)
* and @blk_len (the client-visible EOF).
*/
blk_len = blk_getlength(exp->common.blk);
if (blk_len < 0) {
fuse_reply_err(req, -blk_len);
return;
}
if (offset > blk_len || whence == SEEK_DATA) {
fuse_reply_err(req, ENXIO);
} else {
fuse_reply_lseek(req, offset);
}
return;
}
if (ret & BDRV_BLOCK_DATA) {
if (whence == SEEK_DATA) {
fuse_reply_lseek(req, offset);
return;
}
} else {
if (whence == SEEK_HOLE) {
fuse_reply_lseek(req, offset);
return;
}
}
/* Safety check against infinite loops */
if (!pnum) {
fuse_reply_err(req, ENXIO);
return;
}
offset += pnum;
}
}
#endif
static const struct fuse_lowlevel_ops fuse_ops = {
.init = fuse_init,
.lookup = fuse_lookup,
.getattr = fuse_getattr,
.setattr = fuse_setattr,
.open = fuse_open,
.read = fuse_read,
.write = fuse_write,
.fallocate = fuse_fallocate,
.flush = fuse_flush,
.fsync = fuse_fsync,
#ifdef CONFIG_FUSE_LSEEK
.lseek = fuse_lseek,
#endif
};
const BlockExportDriver blk_exp_fuse = {
.type = BLOCK_EXPORT_TYPE_FUSE,
.instance_size = sizeof(FuseExport),
.create = fuse_export_create,
.delete = fuse_export_delete,
.request_shutdown = fuse_export_shutdown,
};

8
block/export/meson.build
View File

@ -1 +1,7 @@
block_ss.add(files('export.c'))
blockdev_ss.add(files('export.c'))
if have_vhost_user_blk_server
blockdev_ss.add(files('vhost-user-blk-server.c'))
endif
blockdev_ss.add(when: fuse, if_true: files('fuse.c'))

435
block/export/vhost-user-blk-server.c Normal file
View File

@ -0,0 +1,435 @@
/*
* Sharing QEMU block devices via vhost-user protocal
*
* Parts of the code based on nbd/server.c.
*
* Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
* Copyright (c) 2020 Red Hat, Inc.
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "block/block.h"
#include "subprojects/libvhost-user/libvhost-user.h" /* only for the type definitions */
#include "standard-headers/linux/virtio_blk.h"
#include "qemu/vhost-user-server.h"
#include "vhost-user-blk-server.h"
#include "qapi/error.h"
#include "qom/object_interfaces.h"
#include "sysemu/block-backend.h"
#include "util/block-helpers.h"
enum {
VHOST_USER_BLK_NUM_QUEUES_DEFAULT = 1,
};
struct virtio_blk_inhdr {
unsigned char status;
};
typedef struct VuBlkReq {
VuVirtqElement elem;
int64_t sector_num;
size_t size;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr out;
VuServer *server;
struct VuVirtq *vq;
} VuBlkReq;
/* vhost user block device */
typedef struct {
BlockExport export;
VuServer vu_server;
uint32_t blk_size;
QIOChannelSocket *sioc;
struct virtio_blk_config blkcfg;
bool writable;
} VuBlkExport;
static void vu_blk_req_complete(VuBlkReq *req)
{
VuDev *vu_dev = &req->server->vu_dev;
/* IO size with 1 extra status byte */
vu_queue_push(vu_dev, req->vq, &req->elem, req->size + 1);
vu_queue_notify(vu_dev, req->vq);
free(req);
}
static int coroutine_fn
vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov,
uint32_t iovcnt, uint32_t type)
{
struct virtio_blk_discard_write_zeroes desc;
ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc));
if (unlikely(size != sizeof(desc))) {
error_report("Invalid size %zd, expect %zu", size, sizeof(desc));
return -EINVAL;
}
uint64_t range[2] = { le64_to_cpu(desc.sector) << 9,
le32_to_cpu(desc.num_sectors) << 9 };
if (type == VIRTIO_BLK_T_DISCARD) {
if (blk_co_pdiscard(blk, range[0], range[1]) == 0) {
return 0;
}
} else if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) {
return 0;
}
}
return -EINVAL;
}
static void coroutine_fn vu_blk_virtio_process_req(void *opaque)
{
VuBlkReq *req = opaque;
VuServer *server = req->server;
VuVirtqElement *elem = &req->elem;
uint32_t type;
VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server);
BlockBackend *blk = vexp->export.blk;
struct iovec *in_iov = elem->in_sg;
struct iovec *out_iov = elem->out_sg;
unsigned in_num = elem->in_num;
unsigned out_num = elem->out_num;
/* refer to hw/block/virtio_blk.c */
if (elem->out_num < 1 || elem->in_num < 1) {
error_report("virtio-blk request missing headers");
goto err;
}
if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out,
sizeof(req->out)) != sizeof(req->out))) {
error_report("virtio-blk request outhdr too short");
goto err;
}
iov_discard_front(&out_iov, &out_num, sizeof(req->out));
if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
error_report("virtio-blk request inhdr too short");
goto err;
}
/* We always touch the last byte, so just see how big in_iov is. */
req->in = (void *)in_iov[in_num - 1].iov_base
+ in_iov[in_num - 1].iov_len
- sizeof(struct virtio_blk_inhdr);
iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
type = le32_to_cpu(req->out.type);
switch (type & ~VIRTIO_BLK_T_BARRIER) {
case VIRTIO_BLK_T_IN:
case VIRTIO_BLK_T_OUT: {
ssize_t ret = 0;
bool is_write = type & VIRTIO_BLK_T_OUT;
req->sector_num = le64_to_cpu(req->out.sector);
if (is_write && !vexp->writable) {
req->in->status = VIRTIO_BLK_S_IOERR;
break;
}
int64_t offset = req->sector_num * vexp->blk_size;
QEMUIOVector qiov;
if (is_write) {
qemu_iovec_init_external(&qiov, out_iov, out_num);
ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0);
} else {
qemu_iovec_init_external(&qiov, in_iov, in_num);
ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0);
}
if (ret >= 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
case VIRTIO_BLK_T_FLUSH:
if (blk_co_flush(blk) == 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
case VIRTIO_BLK_T_GET_ID: {
size_t size = MIN(iov_size(&elem->in_sg[0], in_num),
VIRTIO_BLK_ID_BYTES);
snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
req->in->status = VIRTIO_BLK_S_OK;
req->size = elem->in_sg[0].iov_len;
break;
}
case VIRTIO_BLK_T_DISCARD:
case VIRTIO_BLK_T_WRITE_ZEROES: {
int rc;
if (!vexp->writable) {
req->in->status = VIRTIO_BLK_S_IOERR;
break;
}
rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type);
if (rc == 0) {
req->in->status = VIRTIO_BLK_S_OK;
} else {
req->in->status = VIRTIO_BLK_S_IOERR;
}
break;
}
default:
req->in->status = VIRTIO_BLK_S_UNSUPP;
break;
}
vu_blk_req_complete(req);
return;
err:
free(req);
}
static void vu_blk_process_vq(VuDev *vu_dev, int idx)
{
VuServer *server = container_of(vu_dev, VuServer, vu_dev);
VuVirtq *vq = vu_get_queue(vu_dev, idx);
while (1) {
VuBlkReq *req;
req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq));
if (!req) {
break;
}
req->server = server;
req->vq = vq;
Coroutine *co =
qemu_coroutine_create(vu_blk_virtio_process_req, req);
qemu_coroutine_enter(co);
}
}
static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started)
{
VuVirtq *vq;
assert(vu_dev);
vq = vu_get_queue(vu_dev, idx);
vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL);
}
static uint64_t vu_blk_get_features(VuDev *dev)
{
uint64_t features;
VuServer *server = container_of(dev, VuServer, vu_dev);
VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server);
features = 1ull << VIRTIO_BLK_F_SIZE_MAX |
1ull << VIRTIO_BLK_F_SEG_MAX |
1ull << VIRTIO_BLK_F_TOPOLOGY |
1ull << VIRTIO_BLK_F_BLK_SIZE |
1ull << VIRTIO_BLK_F_FLUSH |
1ull << VIRTIO_BLK_F_DISCARD |
1ull << VIRTIO_BLK_F_WRITE_ZEROES |
1ull << VIRTIO_BLK_F_CONFIG_WCE |
1ull << VIRTIO_BLK_F_MQ |
1ull << VIRTIO_F_VERSION_1 |
1ull << VIRTIO_RING_F_INDIRECT_DESC |
1ull << VIRTIO_RING_F_EVENT_IDX |
1ull << VHOST_USER_F_PROTOCOL_FEATURES;
if (!vexp->writable) {
features |= 1ull << VIRTIO_BLK_F_RO;
}
return features;
}
static uint64_t vu_blk_get_protocol_features(VuDev *dev)
{
return 1ull << VHOST_USER_PROTOCOL_F_CONFIG |
1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD;
}
static int
vu_blk_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len)
{
VuServer *server = container_of(vu_dev, VuServer, vu_dev);
VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server);
if (len > sizeof(struct virtio_blk_config)) {
return -1;
}
memcpy(config, &vexp->blkcfg, len);
return 0;
}
static int
vu_blk_set_config(VuDev *vu_dev, const uint8_t *data,
uint32_t offset, uint32_t size, uint32_t flags)
{
VuServer *server = container_of(vu_dev, VuServer, vu_dev);
VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server);
uint8_t wce;
/* don't support live migration */
if (flags != VHOST_SET_CONFIG_TYPE_MASTER) {
return -EINVAL;
}
if (offset != offsetof(struct virtio_blk_config, wce) ||
size != 1) {
return -EINVAL;
}
wce = *data;
vexp->blkcfg.wce = wce;
blk_set_enable_write_cache(vexp->export.blk, wce);
return 0;
}
/*
* When the client disconnects, it sends a VHOST_USER_NONE request
* and vu_process_message will simple call exit which cause the VM
* to exit abruptly.
* To avoid this issue, process VHOST_USER_NONE request ahead
* of vu_process_message.
*
*/
static int vu_blk_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply)
{
if (vmsg->request == VHOST_USER_NONE) {
dev->panic(dev, "disconnect");
return true;
}
return false;
}
static const VuDevIface vu_blk_iface = {
.get_features = vu_blk_get_features,
.queue_set_started = vu_blk_queue_set_started,
.get_protocol_features = vu_blk_get_protocol_features,
.get_config = vu_blk_get_config,
.set_config = vu_blk_set_config,
.process_msg = vu_blk_process_msg,
};
static void blk_aio_attached(AioContext *ctx, void *opaque)
{
VuBlkExport *vexp = opaque;
vexp->export.ctx = ctx;
vhost_user_server_attach_aio_context(&vexp->vu_server, ctx);
}
static void blk_aio_detach(void *opaque)
{
VuBlkExport *vexp = opaque;
vhost_user_server_detach_aio_context(&vexp->vu_server);
vexp->export.ctx = NULL;
}
static void
vu_blk_initialize_config(BlockDriverState *bs,
struct virtio_blk_config *config,
uint32_t blk_size,
uint16_t num_queues)
{
config->capacity = cpu_to_le64(bdrv_getlength(bs) >> BDRV_SECTOR_BITS);
config->blk_size = cpu_to_le32(blk_size);
config->size_max = cpu_to_le32(0);
config->seg_max = cpu_to_le32(128 - 2);
config->min_io_size = cpu_to_le16(1);
config->opt_io_size = cpu_to_le32(1);
config->num_queues = cpu_to_le16(num_queues);
config->max_discard_sectors = cpu_to_le32(32768);
config->max_discard_seg = cpu_to_le32(1);
config->discard_sector_alignment = cpu_to_le32(config->blk_size >> 9);
config->max_write_zeroes_sectors = cpu_to_le32(32768);
config->max_write_zeroes_seg = cpu_to_le32(1);
}
static void vu_blk_exp_request_shutdown(BlockExport *exp)
{
VuBlkExport *vexp = container_of(exp, VuBlkExport, export);
vhost_user_server_stop(&vexp->vu_server);
}
static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts,
Error **errp)
{
VuBlkExport *vexp = container_of(exp, VuBlkExport, export);
BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk;
Error *local_err = NULL;
uint64_t logical_block_size;
uint16_t num_queues = VHOST_USER_BLK_NUM_QUEUES_DEFAULT;
vexp->writable = opts->writable;
vexp->blkcfg.wce = 0;
if (vu_opts->has_logical_block_size) {
logical_block_size = vu_opts->logical_block_size;
} else {
logical_block_size = BDRV_SECTOR_SIZE;
}
check_block_size(exp->id, "logical-block-size", logical_block_size,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
vexp->blk_size = logical_block_size;
blk_set_guest_block_size(exp->blk, logical_block_size);
if (vu_opts->has_num_queues) {
num_queues = vu_opts->num_queues;
}
if (num_queues == 0) {
error_setg(errp, "num-queues must be greater than 0");
return -EINVAL;
}
vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg,
logical_block_size, num_queues);
blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach,
vexp);
if (!vhost_user_server_start(&vexp->vu_server, vu_opts->addr, exp->ctx,
num_queues, &vu_blk_iface, errp)) {
blk_remove_aio_context_notifier(exp->blk, blk_aio_attached,
blk_aio_detach, vexp);
return -EADDRNOTAVAIL;
}
return 0;
}
static void vu_blk_exp_delete(BlockExport *exp)
{
VuBlkExport *vexp = container_of(exp, VuBlkExport, export);
blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach,
vexp);
}
const BlockExportDriver blk_exp_vhost_user_blk = {
.type = BLOCK_EXPORT_TYPE_VHOST_USER_BLK,
.instance_size = sizeof(VuBlkExport),
.create = vu_blk_exp_create,
.delete = vu_blk_exp_delete,
.request_shutdown = vu_blk_exp_request_shutdown,
};

19
block/export/vhost-user-blk-server.h Normal file
View File

@ -0,0 +1,19 @@
/*
* Sharing QEMU block devices via vhost-user protocal
*
* Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
* Copyright (c) 2020 Red Hat, Inc.
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#ifndef VHOST_USER_BLK_SERVER_H
#define VHOST_USER_BLK_SERVER_H
#include "block/export.h"
/* For block/export/export.c */
extern const BlockExportDriver blk_exp_vhost_user_blk;
#endif /* VHOST_USER_BLK_SERVER_H */

12
block/file-posix.c
View File

@ -1698,6 +1698,7 @@ static int handle_aiocb_write_zeroes_unmap(void *opaque)
switch (ret) {
case -ENOTSUP:
case -EINVAL:
case -EBUSY:
break;
default:
return ret;
@ -2110,7 +2111,7 @@ static void raw_aio_attach_aio_context(BlockDriverState *bs,
#endif
#ifdef CONFIG_LINUX_IO_URING
if (s->use_linux_io_uring) {
Error *local_err;
Error *local_err = NULL;
if (!aio_setup_linux_io_uring(new_context, &local_err)) {
error_reportf_err(local_err, "Unable to use linux io_uring, "
"falling back to thread pool: ");
@ -2925,7 +2926,6 @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
#ifdef CONFIG_FALLOCATE
if (offset + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) {
BdrvTrackedRequest *req;
uint64_t end;
/*
* This is a workaround for a bug in the Linux XFS driver,
@ -2949,9 +2949,9 @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
assert(req->offset <= offset);
assert(req->offset + req->bytes >= offset + bytes);
end = INT64_MAX & -(uint64_t)bs->bl.request_alignment;
req->bytes = end - req->offset;
req->overlap_bytes = req->bytes;
req->bytes = BDRV_MAX_LENGTH - req->offset;
assert(bdrv_check_request(req->offset, req->bytes) == 0);
bdrv_mark_request_serialising(req, bs->bl.request_alignment);
}
@ -3103,7 +3103,7 @@ static int raw_check_perm(BlockDriverState *bs, uint64_t perm, uint64_t shared,
}
/* Copy locks to the new fd */
if (s->perm_change_fd) {
if (s->perm_change_fd && s->use_lock) {
ret = raw_apply_lock_bytes(NULL, s->perm_change_fd, perm, ~shared,
false, errp);
if (ret < 0) {

311
block/io.c
View File

@ -135,10 +135,10 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
{
ERRP_GUARD();
BlockDriver *drv = bs->drv;
BdrvChild *c;
bool have_limits;
Error *local_err = NULL;
memset(&bs->bl, 0, sizeof(bs->bl));
@ -156,9 +156,8 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
QLIST_FOREACH(c, &bs->children, next) {
if (c->role & (BDRV_CHILD_DATA | BDRV_CHILD_FILTERED | BDRV_CHILD_COW))
{
bdrv_refresh_limits(c->bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
bdrv_refresh_limits(c->bs, errp);
if (*errp) {
return;
}
bdrv_merge_limits(&bs->bl, &c->bs->bl);
@ -177,6 +176,13 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
/* Then let the driver override it */
if (drv->bdrv_refresh_limits) {
drv->bdrv_refresh_limits(bs, errp);
if (*errp) {
return;
}
}
if (bs->bl.request_alignment > BDRV_MAX_ALIGNMENT) {
error_setg(errp, "Driver requires too large request alignment");
}
}
@ -306,17 +312,7 @@ static void bdrv_co_drain_bh_cb(void *opaque)
if (bs) {
AioContext *ctx = bdrv_get_aio_context(bs);
AioContext *co_ctx = qemu_coroutine_get_aio_context(co);
/*
* When the coroutine yielded, the lock for its home context was
* released, so we need to re-acquire it here. If it explicitly
* acquired a different context, the lock is still held and we don't
* want to lock it a second time (or AIO_WAIT_WHILE() would hang).
*/
if (ctx == co_ctx) {
aio_context_acquire(ctx);
}
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
assert(!data->drained_end_counter);
@ -328,9 +324,7 @@ static void bdrv_co_drain_bh_cb(void *opaque)
data->ignore_bds_parents,
data->drained_end_counter);
}
if (ctx == co_ctx) {
aio_context_release(ctx);
}
aio_context_release(ctx);
} else {
assert(data->begin);
bdrv_drain_all_begin();
@ -348,13 +342,16 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
int *drained_end_counter)
{
BdrvCoDrainData data;
Coroutine *self = qemu_coroutine_self();
AioContext *ctx = bdrv_get_aio_context(bs);
AioContext *co_ctx = qemu_coroutine_get_aio_context(self);
/* Calling bdrv_drain() from a BH ensures the current coroutine yields and
* other coroutines run if they were queued by aio_co_enter(). */
assert(qemu_in_coroutine());
data = (BdrvCoDrainData) {
.co = qemu_coroutine_self(),
.co = self,
.bs = bs,
.done = false,
.begin = begin,
@ -368,13 +365,29 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
if (bs) {
bdrv_inc_in_flight(bs);
}
replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
bdrv_co_drain_bh_cb, &data);
/*
* Temporarily drop the lock across yield or we would get deadlocks.
* bdrv_co_drain_bh_cb() reaquires the lock as needed.
*
* When we yield below, the lock for the current context will be
* released, so if this is actually the lock that protects bs, don't drop
* it a second time.
*/
if (ctx != co_ctx) {
aio_context_release(ctx);
}
replay_bh_schedule_oneshot_event(ctx, bdrv_co_drain_bh_cb, &data);
qemu_coroutine_yield();
/* If we are resumed from some other event (such as an aio completion or a
* timer callback), it is a bug in the caller that should be fixed. */
assert(data.done);
/* Reaquire the AioContext of bs if we dropped it */
if (ctx != co_ctx) {
aio_context_acquire(ctx);
}
}
void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
@ -633,6 +646,19 @@ void bdrv_drain_all_begin(void)
}
}
void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
{
int drained_end_counter = 0;
g_assert(bs->quiesce_counter > 0);
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
bdrv_do_drained_end(bs, false, NULL, true, &drained_end_counter);
}
BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
}
void bdrv_drain_all_end(void)
{
BlockDriverState *bs = NULL;
@ -872,18 +898,31 @@ static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self
return waited;
}
static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
size_t size)
int bdrv_check_request(int64_t offset, int64_t bytes)
{
if (size > BDRV_REQUEST_MAX_BYTES) {
if (offset < 0 || bytes < 0) {
return -EIO;
}
if (!bdrv_is_inserted(bs)) {
return -ENOMEDIUM;
if (bytes > BDRV_MAX_LENGTH) {
return -EIO;
}
if (offset < 0) {
if (offset > BDRV_MAX_LENGTH - bytes) {
return -EIO;
}
return 0;
}
static int bdrv_check_request32(int64_t offset, int64_t bytes)
{
int ret = bdrv_check_request(offset, bytes);
if (ret < 0) {
return ret;
}
if (bytes > BDRV_REQUEST_MAX_BYTES) {
return -EIO;
}
@ -1630,7 +1669,11 @@ int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
trace_bdrv_co_preadv(bs, offset, bytes, flags);
ret = bdrv_check_byte_request(bs, offset, bytes);
if (!bdrv_is_inserted(bs)) {
return -ENOMEDIUM;
}
ret = bdrv_check_request32(offset, bytes);
if (ret < 0) {
return ret;
}
@ -2042,11 +2085,11 @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child,
trace_bdrv_co_pwritev(child->bs, offset, bytes, flags);
if (!bs->drv) {
if (!bdrv_is_inserted(bs)) {
return -ENOMEDIUM;
}
ret = bdrv_check_byte_request(bs, offset, bytes);
ret = bdrv_check_request32(offset, bytes);
if (ret < 0) {
return ret;
}
@ -2282,17 +2325,17 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
ret |= BDRV_BLOCK_ALLOCATED;
} else if (want_zero && bs->drv->supports_backing) {
} else if (bs->drv->supports_backing) {
BlockDriverState *cow_bs = bdrv_cow_bs(bs);
if (cow_bs) {
if (!cow_bs) {
ret |= BDRV_BLOCK_ZERO;
} else if (want_zero) {
int64_t size2 = bdrv_getlength(cow_bs);
if (size2 >= 0 && offset >= size2) {
ret |= BDRV_BLOCK_ZERO;
}
} else {
ret |= BDRV_BLOCK_ZERO;
}
}
@ -2343,41 +2386,101 @@ early_out:
int coroutine_fn
bdrv_co_common_block_status_above(BlockDriverState *bs,
BlockDriverState *base,
bool include_base,
bool want_zero,
int64_t offset,
int64_t bytes,
int64_t *pnum,
int64_t *map,
BlockDriverState **file)
BlockDriverState **file,
int *depth)
{
int ret;
BlockDriverState *p;
int ret = 0;
bool first = true;
int64_t eof = 0;
int dummy;
assert(bs != base);
for (p = bs; p != base; p = bdrv_filter_or_cow_bs(p)) {
assert(!include_base || base); /* Can't include NULL base */
if (!depth) {
depth = &dummy;
}
*depth = 0;
if (!include_base && bs == base) {
*pnum = bytes;
return 0;
}
ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file);
++*depth;
if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) {
return ret;
}
if (ret & BDRV_BLOCK_EOF) {
eof = offset + *pnum;
}
assert(*pnum <= bytes);
bytes = *pnum;
for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base;
p = bdrv_filter_or_cow_bs(p))
{
ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map,
file);
++*depth;
if (ret < 0) {
break;
return ret;
}
if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) {
if (*pnum == 0) {
/*
* Reading beyond the end of the file continues to read
* zeroes, but we can only widen the result to the
* unallocated length we learned from an earlier
* iteration.
* The top layer deferred to this layer, and because this layer is
* short, any zeroes that we synthesize beyond EOF behave as if they
* were allocated at this layer.
*
* We don't include BDRV_BLOCK_EOF into ret, as upper layer may be
* larger. We'll add BDRV_BLOCK_EOF if needed at function end, see
* below.
*/
assert(ret & BDRV_BLOCK_EOF);
*pnum = bytes;
}
if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) {
if (file) {
*file = p;
}
ret = BDRV_BLOCK_ZERO | BDRV_BLOCK_ALLOCATED;
break;
}
/* [offset, pnum] unallocated on this layer, which could be only
* the first part of [offset, bytes]. */
bytes = MIN(bytes, *pnum);
first = false;
if (ret & BDRV_BLOCK_ALLOCATED) {
/*
* We've found the node and the status, we must break.
*
* Drop BDRV_BLOCK_EOF, as it's not for upper layer, which may be
* larger. We'll add BDRV_BLOCK_EOF if needed at function end, see
* below.
*/
ret &= ~BDRV_BLOCK_EOF;
break;
}
if (p == base) {
assert(include_base);
break;
}
/*
* OK, [offset, offset + *pnum) region is unallocated on this layer,
* let's continue the diving.
*/
assert(*pnum <= bytes);
bytes = *pnum;
}
if (offset + *pnum == eof) {
ret |= BDRV_BLOCK_EOF;
}
return ret;
}
@ -2385,8 +2488,8 @@ int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
int64_t offset, int64_t bytes, int64_t *pnum,
int64_t *map, BlockDriverState **file)
{
return bdrv_common_block_status_above(bs, base, true, offset, bytes,
pnum, map, file);
return bdrv_common_block_status_above(bs, base, false, true, offset, bytes,
pnum, map, file, NULL);
}
int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes,
@ -2396,14 +2499,41 @@ int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes,
offset, bytes, pnum, map, file);
}
/*
* Check @bs (and its backing chain) to see if the range defined
* by @offset and @bytes is known to read as zeroes.
* Return 1 if that is the case, 0 otherwise and -errno on error.
* This test is meant to be fast rather than accurate so returning 0
* does not guarantee non-zero data.
*/
int coroutine_fn bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset,
int64_t bytes)
{
int ret;
int64_t pnum = bytes;
if (!bytes) {
return 1;
}
ret = bdrv_common_block_status_above(bs, NULL, false, false, offset,
bytes, &pnum, NULL, NULL, NULL);
if (ret < 0) {
return ret;
}
return (pnum == bytes) && (ret & BDRV_BLOCK_ZERO);
}
int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset,
int64_t bytes, int64_t *pnum)
{
int ret;
int64_t dummy;
ret = bdrv_common_block_status_above(bs, bdrv_filter_or_cow_bs(bs), false,
offset, bytes, pnum ? pnum : &dummy,
ret = bdrv_common_block_status_above(bs, bs, true, false, offset,
bytes, pnum ? pnum : &dummy, NULL,
NULL, NULL);
if (ret < 0) {
return ret;
@ -2414,8 +2544,9 @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset,
/*
* Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP]
*
* Return 1 if (a prefix of) the given range is allocated in any image
* between BASE and TOP (BASE is only included if include_base is set).
* Return a positive depth if (a prefix of) the given range is allocated
* in any image between BASE and TOP (BASE is only included if include_base
* is set). Depth 1 is TOP, 2 is the first backing layer, and so forth.
* BASE can be NULL to check if the given offset is allocated in any
* image of the chain. Return 0 otherwise, or negative errno on
* failure.
@ -2426,51 +2557,23 @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset,
* at 'offset + *pnum' may return the same allocation status (in other
* words, the result is not necessarily the maximum possible range);
* but 'pnum' will only be 0 when end of file is reached.
*
*/
int bdrv_is_allocated_above(BlockDriverState *top,
BlockDriverState *base,
bool include_base, int64_t offset,
int64_t bytes, int64_t *pnum)
{
BlockDriverState *intermediate;
int ret;
int64_t n = bytes;
assert(base || !include_base);
intermediate = top;
while (include_base || intermediate != base) {
int64_t pnum_inter;
int64_t size_inter;
assert(intermediate);
ret = bdrv_is_allocated(intermediate, offset, bytes, &pnum_inter);
if (ret < 0) {
return ret;
}
if (ret) {
*pnum = pnum_inter;
return 1;
}
size_inter = bdrv_getlength(intermediate);
if (size_inter < 0) {
return size_inter;
}
if (n > pnum_inter &&
(intermediate == top || offset + pnum_inter < size_inter)) {
n = pnum_inter;
}
if (intermediate == base) {
break;
}
intermediate = bdrv_filter_or_cow_bs(intermediate);
int depth;
int ret = bdrv_common_block_status_above(top, base, include_base, false,
offset, bytes, pnum, NULL, NULL,
&depth);
if (ret < 0) {
return ret;
}
*pnum = n;
if (ret & BDRV_BLOCK_ALLOCATED) {
return depth;
}
return 0;
}
@ -2716,8 +2819,9 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset,
return -EPERM;
}
if (offset < 0 || bytes < 0 || bytes > INT64_MAX - offset) {
return -EIO;
ret = bdrv_check_request(offset, bytes);
if (ret < 0) {
return ret;
}
/* Do nothing if disabled. */
@ -2973,10 +3077,10 @@ static int coroutine_fn bdrv_co_copy_range_internal(
assert(!(read_flags & BDRV_REQ_NO_FALLBACK));
assert(!(write_flags & BDRV_REQ_NO_FALLBACK));
if (!dst || !dst->bs) {
if (!dst || !dst->bs || !bdrv_is_inserted(dst->bs)) {
return -ENOMEDIUM;
}
ret = bdrv_check_byte_request(dst->bs, dst_offset, bytes);
ret = bdrv_check_request32(dst_offset, bytes);
if (ret) {
return ret;
}
@ -2984,10 +3088,10 @@ static int coroutine_fn bdrv_co_copy_range_internal(
return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, write_flags);
}
if (!src || !src->bs) {
if (!src || !src->bs || !bdrv_is_inserted(src->bs)) {
return -ENOMEDIUM;
}
ret = bdrv_check_byte_request(src->bs, src_offset, bytes);
ret = bdrv_check_request32(src_offset, bytes);
if (ret) {
return ret;
}
@ -3117,6 +3221,13 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact,
return -EINVAL;
}
ret = bdrv_check_request(offset, 0);
if (ret < 0) {
error_setg(errp, "Required too big image size, it must be not greater "
"than %" PRId64, BDRV_MAX_LENGTH);
return ret;
}
old_size = bdrv_getlength(bs);
if (old_size < 0) {
error_setg_errno(errp, -old_size, "Failed to get old image size");

2
block/io_uring.c
View File

@ -425,6 +425,6 @@ LuringState *luring_init(Error **errp)
void luring_cleanup(LuringState *s)
{
io_uring_queue_exit(&s->ring);
g_free(s);
trace_luring_cleanup_state(s);
g_free(s);
}

56
block/iscsi.c
View File

@ -322,25 +322,23 @@ iscsi_aio_cancel(BlockAIOCB *blockacb)
IscsiAIOCB *acb = (IscsiAIOCB *)blockacb;
IscsiLun *iscsilun = acb->iscsilun;
qemu_mutex_lock(&iscsilun->mutex);
WITH_QEMU_LOCK_GUARD(&iscsilun->mutex) {
/* If it was cancelled or completed already, our work is done here */
if (acb->cancelled || acb->status != -EINPROGRESS) {
qemu_mutex_unlock(&iscsilun->mutex);
return;
/* If it was cancelled or completed already, our work is done here */
if (acb->cancelled || acb->status != -EINPROGRESS) {
return;
}
acb->cancelled = true;
qemu_aio_ref(acb); /* released in iscsi_abort_task_cb() */
/* send a task mgmt call to the target to cancel the task on the target */
if (iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
iscsi_abort_task_cb, acb) < 0) {
qemu_aio_unref(acb); /* since iscsi_abort_task_cb() won't be called */
}
}
acb->cancelled = true;
qemu_aio_ref(acb); /* released in iscsi_abort_task_cb() */
/* send a task mgmt call to the target to cancel the task on the target */
if (iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
iscsi_abort_task_cb, acb) < 0) {
qemu_aio_unref(acb); /* since iscsi_abort_task_cb() won't be called */
}
qemu_mutex_unlock(&iscsilun->mutex);
}
static const AIOCBInfo iscsi_aiocb_info = {
@ -375,22 +373,22 @@ static void iscsi_timed_check_events(void *opaque)
{
IscsiLun *iscsilun = opaque;
qemu_mutex_lock(&iscsilun->mutex);
WITH_QEMU_LOCK_GUARD(&iscsilun->mutex) {
/* check for timed out requests */
iscsi_service(iscsilun->iscsi, 0);
/* check for timed out requests */
iscsi_service(iscsilun->iscsi, 0);
if (iscsilun->request_timed_out) {
iscsilun->request_timed_out = false;
iscsi_reconnect(iscsilun->iscsi);
}
if (iscsilun->request_timed_out) {
iscsilun->request_timed_out = false;
iscsi_reconnect(iscsilun->iscsi);
/*
* newer versions of libiscsi may return zero events. Ensure we are
* able to return to service once this situation changes.
*/
iscsi_set_events(iscsilun);
}
/* newer versions of libiscsi may return zero events. Ensure we are able
* to return to service once this situation changes. */
iscsi_set_events(iscsilun);
qemu_mutex_unlock(&iscsilun->mutex);
timer_mod(iscsilun->event_timer,
qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
}

3
block/meson.build
View File

@ -7,7 +7,6 @@ block_ss.add(files(
'backup-top.c',
'blkdebug.c',
'blklogwrites.c',
'blkreplay.c',
'blkverify.c',
'block-backend.c',
'block-copy.c',
@ -42,6 +41,8 @@ block_ss.add(files(
'write-threshold.c',
), zstd, zlib)
softmmu_ss.add(when: 'CONFIG_TCG', if_true: files('blkreplay.c'))
block_ss.add(when: 'CONFIG_QCOW1', if_true: files('qcow.c'))
block_ss.add(when: 'CONFIG_VDI', if_true: files('vdi.c'))
block_ss.add(when: 'CONFIG_CLOOP', if_true: files('cloop.c'))

2
block/mirror.c
View File

@ -846,7 +846,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
}
assert(count);
if (ret == 1) {
if (ret > 0) {
bdrv_set_dirty_bitmap(s->dirty_bitmap, offset, count);
}
offset += count;

26
block/nbd.c
View File

@ -135,6 +135,7 @@ typedef struct BDRVNBDState {
QCryptoTLSCreds *tlscreds;
const char *hostname;
char *x_dirty_bitmap;
bool alloc_depth;
bool wait_connect;
NBDConnectThread *connect_thread;
@ -961,6 +962,16 @@ static int nbd_parse_blockstatus_payload(BDRVNBDState *s,
trace_nbd_parse_blockstatus_compliance("extent length too large");
}
/*
* HACK: if we are using x-dirty-bitmaps to access
* qemu:allocation-depth, treat all depths > 2 the same as 2,
* since nbd_client_co_block_status is only expecting the low two
* bits to be set.
*/
if (s->alloc_depth && extent->flags > 2) {
extent->flags = 2;
}
return 0;
}
@ -1795,11 +1806,16 @@ static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
s->sioc = NULL;
return ret;
}
if (s->x_dirty_bitmap && !s->info.base_allocation) {
error_setg(errp, "requested x-dirty-bitmap %s not found",
s->x_dirty_bitmap);
ret = -EINVAL;
goto fail;
if (s->x_dirty_bitmap) {
if (!s->info.base_allocation) {
error_setg(errp, "requested x-dirty-bitmap %s not found",
s->x_dirty_bitmap);
ret = -EINVAL;
goto fail;
}
if (strcmp(s->x_dirty_bitmap, "qemu:allocation-depth") == 0) {
s->alloc_depth = true;
}
}
if (s->info.flags & NBD_FLAG_READ_ONLY) {
ret = bdrv_apply_auto_read_only(bs, "NBD export is read-only", errp);

13
block/nfs.c
View File

@ -24,7 +24,9 @@
#include "qemu/osdep.h"
#if !defined(_WIN32)
#include <poll.h>
#endif
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qapi/error.h"
@ -58,7 +60,7 @@ typedef struct NFSClient {
bool has_zero_init;
AioContext *aio_context;
QemuMutex mutex;
blkcnt_t st_blocks;
uint64_t st_blocks;
bool cache_used;
NFSServer *server;
char *path;
@ -545,7 +547,9 @@ static int64_t nfs_client_open(NFSClient *client, BlockdevOptionsNfs *opts,
}
ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
#if !defined(_WIN32)
client->st_blocks = st.st_blocks;
#endif
client->has_zero_init = S_ISREG(st.st_mode);
*strp = '/';
goto out;
@ -706,6 +710,7 @@ static int nfs_has_zero_init(BlockDriverState *bs)
return client->has_zero_init;
}
#if !defined(_WIN32)
/* Called (via nfs_service) with QemuMutex held. */
static void
nfs_get_allocated_file_size_cb(int ret, struct nfs_context *nfs, void *data,
@ -748,6 +753,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
return (task.ret < 0 ? task.ret : st.st_blocks * 512);
}
#endif
static int coroutine_fn
nfs_file_co_truncate(BlockDriverState *bs, int64_t offset, bool exact,
@ -800,7 +806,9 @@ static int nfs_reopen_prepare(BDRVReopenState *state,
nfs_get_error(client->context));
return ret;
}
#if !defined(_WIN32)
client->st_blocks = st.st_blocks;
#endif
}
return 0;
@ -869,7 +877,10 @@ static BlockDriver bdrv_nfs = {
.create_opts = &nfs_create_opts,
.bdrv_has_zero_init = nfs_has_zero_init,
/* libnfs does not provide the allocated filesize of a file on win32. */
#if !defined(_WIN32)
.bdrv_get_allocated_file_size = nfs_get_allocated_file_size,
#endif
.bdrv_co_truncate = nfs_file_co_truncate,
.bdrv_file_open = nfs_file_open,

236
block/nvme.c
View File

@ -41,6 +41,16 @@
typedef struct BDRVNVMeState BDRVNVMeState;
/* Same index is used for queues and IRQs */
#define INDEX_ADMIN 0
#define INDEX_IO(n) (1 + n)
/* This driver shares a single MSIX IRQ for the admin and I/O queues */
enum {
MSIX_SHARED_IRQ_IDX = 0,
MSIX_IRQ_COUNT = 1
};
typedef struct {
int32_t head, tail;
uint8_t *queue;
@ -81,18 +91,10 @@ typedef struct {
QEMUBH *completion_bh;
} NVMeQueuePair;
#define INDEX_ADMIN 0
#define INDEX_IO(n) (1 + n)
/* This driver shares a single MSIX IRQ for the admin and I/O queues */
enum {
MSIX_SHARED_IRQ_IDX = 0,
MSIX_IRQ_COUNT = 1
};
struct BDRVNVMeState {
AioContext *aio_context;
QEMUVFIOState *vfio;
void *bar0_wo_map;
/* Memory mapped registers */
volatile struct {
uint32_t sq_tail;
@ -103,7 +105,7 @@ struct BDRVNVMeState {
* [1..]: io queues.
*/
NVMeQueuePair **queues;
int nr_queues;
unsigned queue_count;
size_t page_size;
/* How many uint32_t elements does each doorbell entry take. */
size_t doorbell_scale;
@ -128,6 +130,12 @@ struct BDRVNVMeState {
/* PCI address (required for nvme_refresh_filename()) */
char *device;
struct {
uint64_t completion_errors;
uint64_t aligned_accesses;
uint64_t unaligned_accesses;
} stats;
};
#define NVME_BLOCK_OPT_DEVICE "device"
@ -153,28 +161,32 @@ static QemuOptsList runtime_opts = {
},
};
static void nvme_init_queue(BDRVNVMeState *s, NVMeQueue *q,
int nentries, int entry_bytes, Error **errp)
/* Returns true on success, false on failure. */
static bool nvme_init_queue(BDRVNVMeState *s, NVMeQueue *q,
unsigned nentries, size_t entry_bytes, Error **errp)
{
size_t bytes;
int r;
bytes = ROUND_UP(nentries * entry_bytes, s->page_size);
bytes = ROUND_UP(nentries * entry_bytes, qemu_real_host_page_size);
q->head = q->tail = 0;
q->queue = qemu_try_memalign(s->page_size, bytes);
q->queue = qemu_try_memalign(qemu_real_host_page_size, bytes);
if (!q->queue) {
error_setg(errp, "Cannot allocate queue");
return;
return false;
}
memset(q->queue, 0, bytes);
r = qemu_vfio_dma_map(s->vfio, q->queue, bytes, false, &q->iova);
if (r) {
error_setg(errp, "Cannot map queue");
return false;
}
return true;
}
static void nvme_free_queue_pair(NVMeQueuePair *q)
{
trace_nvme_free_queue_pair(q->index, q);
if (q->completion_bh) {
qemu_bh_delete(q->completion_bh);
}
@ -198,31 +210,33 @@ static void nvme_free_req_queue_cb(void *opaque)
static NVMeQueuePair *nvme_create_queue_pair(BDRVNVMeState *s,
AioContext *aio_context,
int idx, int size,
unsigned idx, size_t size,
Error **errp)
{
int i, r;
Error *local_err = NULL;
NVMeQueuePair *q;
uint64_t prp_list_iova;
size_t bytes;
q = g_try_new0(NVMeQueuePair, 1);
if (!q) {
return NULL;
}
q->prp_list_pages = qemu_try_memalign(s->page_size,
s->page_size * NVME_NUM_REQS);
trace_nvme_create_queue_pair(idx, q, size, aio_context,
event_notifier_get_fd(s->irq_notifier));
bytes = QEMU_ALIGN_UP(s->page_size * NVME_NUM_REQS,
qemu_real_host_page_size);
q->prp_list_pages = qemu_try_memalign(qemu_real_host_page_size, bytes);
if (!q->prp_list_pages) {
goto fail;
}
memset(q->prp_list_pages, 0, s->page_size * NVME_NUM_REQS);
memset(q->prp_list_pages, 0, bytes);
qemu_mutex_init(&q->lock);
q->s = s;
q->index = idx;
qemu_co_queue_init(&q->free_req_queue);
q->completion_bh = aio_bh_new(aio_context, nvme_process_completion_bh, q);
r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages,
s->page_size * NVME_NUM_REQS,
r = qemu_vfio_dma_map(s->vfio, q->prp_list_pages, bytes,
false, &prp_list_iova);
if (r) {
goto fail;
@ -237,16 +251,12 @@ static NVMeQueuePair *nvme_create_queue_pair(BDRVNVMeState *s,
req->prp_list_iova = prp_list_iova + i * s->page_size;
}
nvme_init_queue(s, &q->sq, size, NVME_SQ_ENTRY_BYTES, &local_err);
if (local_err) {
error_propagate(errp, local_err);
if (!nvme_init_queue(s, &q->sq, size, NVME_SQ_ENTRY_BYTES, errp)) {
goto fail;
}
q->sq.doorbell = &s->doorbells[idx * s->doorbell_scale].sq_tail;
nvme_init_queue(s, &q->cq, size, NVME_CQ_ENTRY_BYTES, &local_err);
if (local_err) {
error_propagate(errp, local_err);
if (!nvme_init_queue(s, &q->cq, size, NVME_CQ_ENTRY_BYTES, errp)) {
goto fail;
}
q->cq.doorbell = &s->doorbells[idx * s->doorbell_scale].cq_head;
@ -286,7 +296,7 @@ static NVMeRequest *nvme_get_free_req(NVMeQueuePair *q)
while (q->free_req_head == -1) {
if (qemu_in_coroutine()) {
trace_nvme_free_req_queue_wait(q);
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);
@ -384,14 +394,17 @@ static bool nvme_process_completion(NVMeQueuePair *q)
break;
}
ret = nvme_translate_error(c);
if (ret) {
s->stats.completion_errors++;
}
q->cq.head = (q->cq.head + 1) % NVME_QUEUE_SIZE;
if (!q->cq.head) {
q->cq_phase = !q->cq_phase;
}
cid = le16_to_cpu(c->cid);
if (cid == 0 || cid > NVME_QUEUE_SIZE) {
fprintf(stderr, "Unexpected CID in completion queue: %" PRIu32 "\n",
cid);
warn_report("NVMe: Unexpected CID in completion queue: %"PRIu32", "
"queue size: %u", cid, NVME_QUEUE_SIZE);
continue;
}
trace_nvme_complete_command(s, q->index, cid);
@ -456,7 +469,7 @@ static void nvme_submit_command(NVMeQueuePair *q, NVMeRequest *req,
assert(!req->cb);
req->cb = cb;
req->opaque = opaque;
cmd->cid = cpu_to_le32(req->cid);
cmd->cid = cpu_to_le16(req->cid);
trace_nvme_submit_command(q->s, q->index, req->cid);
nvme_trace_command(cmd);
@ -470,16 +483,17 @@ static void nvme_submit_command(NVMeQueuePair *q, NVMeRequest *req,
qemu_mutex_unlock(&q->lock);
}
static void nvme_cmd_sync_cb(void *opaque, int ret)
static void nvme_admin_cmd_sync_cb(void *opaque, int ret)
{
int *pret = opaque;
*pret = ret;
aio_wait_kick();
}
static int nvme_cmd_sync(BlockDriverState *bs, NVMeQueuePair *q,
NvmeCmd *cmd)
static int nvme_admin_cmd_sync(BlockDriverState *bs, NvmeCmd *cmd)
{
BDRVNVMeState *s = bs->opaque;
NVMeQueuePair *q = s->queues[INDEX_ADMIN];
AioContext *aio_context = bdrv_get_aio_context(bs);
NVMeRequest *req;
int ret = -EINPROGRESS;
@ -487,15 +501,17 @@ static int nvme_cmd_sync(BlockDriverState *bs, NVMeQueuePair *q,
if (!req) {
return -EBUSY;
}
nvme_submit_command(q, req, cmd, nvme_cmd_sync_cb, &ret);
nvme_submit_command(q, req, cmd, nvme_admin_cmd_sync_cb, &ret);
AIO_WAIT_WHILE(aio_context, ret == -EINPROGRESS);
return ret;
}
static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
/* Returns true on success, false on failure. */
static bool nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
{
BDRVNVMeState *s = bs->opaque;
bool ret = false;
union {
NvmeIdCtrl ctrl;
NvmeIdNs ns;
@ -508,21 +524,22 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
.opcode = NVME_ADM_CMD_IDENTIFY,
.cdw10 = cpu_to_le32(0x1),
};
size_t id_size = QEMU_ALIGN_UP(sizeof(*id), qemu_real_host_page_size);
id = qemu_try_memalign(s->page_size, sizeof(*id));
id = qemu_try_memalign(qemu_real_host_page_size, id_size);
if (!id) {
error_setg(errp, "Cannot allocate buffer for identify response");
goto out;
}
r = qemu_vfio_dma_map(s->vfio, id, sizeof(*id), true, &iova);
r = qemu_vfio_dma_map(s->vfio, id, id_size, true, &iova);
if (r) {
error_setg(errp, "Cannot map buffer for DMA");
goto out;
}
memset(id, 0, sizeof(*id));
memset(id, 0, id_size);
cmd.dptr.prp1 = cpu_to_le64(iova);
if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
if (nvme_admin_cmd_sync(bs, &cmd)) {
error_setg(errp, "Failed to identify controller");
goto out;
}
@ -542,10 +559,10 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROES);
s->supports_discard = !!(oncs & NVME_ONCS_DSM);
memset(id, 0, sizeof(*id));
memset(id, 0, id_size);
cmd.cdw10 = 0;
cmd.nsid = cpu_to_le32(namespace);
if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
if (nvme_admin_cmd_sync(bs, &cmd)) {
error_setg(errp, "Failed to identify namespace");
goto out;
}
@ -572,10 +589,13 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
goto out;
}
ret = true;
s->blkshift = lbaf->ds;
out:
qemu_vfio_dma_unmap(s->vfio, id);
qemu_vfree(id);
return ret;
}
static bool nvme_poll_queue(NVMeQueuePair *q)
@ -585,6 +605,7 @@ static bool nvme_poll_queue(NVMeQueuePair *q)
const size_t cqe_offset = q->cq.head * NVME_CQ_ENTRY_BYTES;
NvmeCqe *cqe = (NvmeCqe *)&q->cq.queue[cqe_offset];
trace_nvme_poll_queue(q->s, q->index);
/*
* Do an early check for completions. q->lock isn't needed because
* nvme_process_completion() only runs in the event loop thread and
@ -609,7 +630,7 @@ static bool nvme_poll_queues(BDRVNVMeState *s)
bool progress = false;
int i;
for (i = 0; i < s->nr_queues; i++) {
for (i = 0; i < s->queue_count; i++) {
if (nvme_poll_queue(s->queues[i])) {
progress = true;
}
@ -630,11 +651,12 @@ static void nvme_handle_event(EventNotifier *n)
static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
{
BDRVNVMeState *s = bs->opaque;
int n = s->nr_queues;
unsigned n = s->queue_count;
NVMeQueuePair *q;
NvmeCmd cmd;
int queue_size = NVME_QUEUE_SIZE;
unsigned queue_size = NVME_QUEUE_SIZE;
assert(n <= UINT16_MAX);
q = nvme_create_queue_pair(s, bdrv_get_aio_context(bs),
n, queue_size, errp);
if (!q) {
@ -643,26 +665,26 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
cmd = (NvmeCmd) {
.opcode = NVME_ADM_CMD_CREATE_CQ,
.dptr.prp1 = cpu_to_le64(q->cq.iova),
.cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
.cdw11 = cpu_to_le32(0x3),
.cdw10 = cpu_to_le32(((queue_size - 1) << 16) | n),
.cdw11 = cpu_to_le32(NVME_CQ_IEN | NVME_CQ_PC),
};
if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
error_setg(errp, "Failed to create CQ io queue [%d]", n);
if (nvme_admin_cmd_sync(bs, &cmd)) {
error_setg(errp, "Failed to create CQ io queue [%u]", n);
goto out_error;
}
cmd = (NvmeCmd) {
.opcode = NVME_ADM_CMD_CREATE_SQ,
.dptr.prp1 = cpu_to_le64(q->sq.iova),
.cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
.cdw11 = cpu_to_le32(0x1 | (n << 16)),
.cdw10 = cpu_to_le32(((queue_size - 1) << 16) | n),
.cdw11 = cpu_to_le32(NVME_SQ_PC | (n << 16)),
};
if (nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd)) {
error_setg(errp, "Failed to create SQ io queue [%d]", n);
if (nvme_admin_cmd_sync(bs, &cmd)) {
error_setg(errp, "Failed to create SQ io queue [%u]", n);
goto out_error;
}
s->queues = g_renew(NVMeQueuePair *, s->queues, n + 1);
s->queues[n] = q;
s->nr_queues++;
s->queue_count++;
return true;
out_error:
nvme_free_queue_pair(q);
@ -675,7 +697,6 @@ static bool nvme_poll_cb(void *opaque)
BDRVNVMeState *s = container_of(e, BDRVNVMeState,
irq_notifier[MSIX_SHARED_IRQ_IDX]);
trace_nvme_poll_cb(s);
return nvme_poll_queues(s);
}
@ -683,12 +704,12 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
Error **errp)
{
BDRVNVMeState *s = bs->opaque;
NVMeQueuePair *q;
AioContext *aio_context = bdrv_get_aio_context(bs);
int ret;
uint64_t cap;
uint64_t timeout_ms;
uint64_t deadline, now;
Error *local_err = NULL;
volatile NvmeBar *regs = NULL;
qemu_co_mutex_init(&s->dma_map_lock);
@ -718,15 +739,29 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
* Initialization". */
cap = le64_to_cpu(regs->cap);
trace_nvme_controller_capability_raw(cap);
trace_nvme_controller_capability("Maximum Queue Entries Supported",
1 + NVME_CAP_MQES(cap));
trace_nvme_controller_capability("Contiguous Queues Required",
NVME_CAP_CQR(cap));
trace_nvme_controller_capability("Doorbell Stride",
2 << (2 + NVME_CAP_DSTRD(cap)));
trace_nvme_controller_capability("Subsystem Reset Supported",
NVME_CAP_NSSRS(cap));
trace_nvme_controller_capability("Memory Page Size Minimum",
1 << (12 + NVME_CAP_MPSMIN(cap)));
trace_nvme_controller_capability("Memory Page Size Maximum",
1 << (12 + NVME_CAP_MPSMAX(cap)));
if (!NVME_CAP_CSS(cap)) {
error_setg(errp, "Device doesn't support NVMe command set");
ret = -EINVAL;
goto out;
}
s->page_size = MAX(4096, 1 << NVME_CAP_MPSMIN(cap));
s->page_size = 1u << (12 + NVME_CAP_MPSMIN(cap));
s->doorbell_scale = (4 << NVME_CAP_DSTRD(cap)) / sizeof(uint32_t);
bs->bl.opt_mem_alignment = s->page_size;
bs->bl.request_alignment = s->page_size;
timeout_ms = MIN(500 * NVME_CAP_TO(cap), 30000);
/* Reset device to get a clean state. */
@ -743,8 +778,10 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
}
}
s->doorbells = qemu_vfio_pci_map_bar(s->vfio, 0, sizeof(NvmeBar),
NVME_DOORBELL_SIZE, PROT_WRITE, errp);
s->bar0_wo_map = qemu_vfio_pci_map_bar(s->vfio, 0, 0,
sizeof(NvmeBar) + NVME_DOORBELL_SIZE,
PROT_WRITE, errp);
s->doorbells = (void *)((uintptr_t)s->bar0_wo_map + sizeof(NvmeBar));
if (!s->doorbells) {
ret = -EINVAL;
goto out;
@ -752,19 +789,18 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
/* Set up admin queue. */
s->queues = g_new(NVMeQueuePair *, 1);
s->queues[INDEX_ADMIN] = nvme_create_queue_pair(s, aio_context, 0,
NVME_QUEUE_SIZE,
errp);
if (!s->queues[INDEX_ADMIN]) {
q = nvme_create_queue_pair(s, aio_context, 0, NVME_QUEUE_SIZE, errp);
if (!q) {
ret = -EINVAL;
goto out;
}
s->nr_queues = 1;
QEMU_BUILD_BUG_ON(NVME_QUEUE_SIZE & 0xF000);
regs->aqa = cpu_to_le32((NVME_QUEUE_SIZE << AQA_ACQS_SHIFT) |
(NVME_QUEUE_SIZE << AQA_ASQS_SHIFT));
regs->asq = cpu_to_le64(s->queues[INDEX_ADMIN]->sq.iova);
regs->acq = cpu_to_le64(s->queues[INDEX_ADMIN]->cq.iova);
s->queues[INDEX_ADMIN] = q;
s->queue_count = 1;
QEMU_BUILD_BUG_ON((NVME_QUEUE_SIZE - 1) & 0xF000);
regs->aqa = cpu_to_le32(((NVME_QUEUE_SIZE - 1) << AQA_ACQS_SHIFT) |
((NVME_QUEUE_SIZE - 1) << AQA_ASQS_SHIFT));
regs->asq = cpu_to_le64(q->sq.iova);
regs->acq = cpu_to_le64(q->cq.iova);
/* After setting up all control registers we can enable device now. */
regs->cc = cpu_to_le32((ctz32(NVME_CQ_ENTRY_BYTES) << CC_IOCQES_SHIFT) |
@ -792,9 +828,7 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
&s->irq_notifier[MSIX_SHARED_IRQ_IDX],
false, nvme_handle_event, nvme_poll_cb);
nvme_identify(bs, namespace, &local_err);
if (local_err) {
error_propagate(errp, local_err);
if (!nvme_identify(bs, namespace, errp)) {
ret = -EIO;
goto out;
}
@ -860,7 +894,7 @@ static int nvme_enable_disable_write_cache(BlockDriverState *bs, bool enable,
.cdw11 = cpu_to_le32(enable ? 0x01 : 0x00),
};
ret = nvme_cmd_sync(bs, s->queues[INDEX_ADMIN], &cmd);
ret = nvme_admin_cmd_sync(bs, &cmd);
if (ret) {
error_setg(errp, "Failed to configure NVMe write cache");
}
@ -869,10 +903,9 @@ static int nvme_enable_disable_write_cache(BlockDriverState *bs, bool enable,
static void nvme_close(BlockDriverState *bs)
{
int i;
BDRVNVMeState *s = bs->opaque;
for (i = 0; i < s->nr_queues; ++i) {
for (unsigned i = 0; i < s->queue_count; ++i) {
nvme_free_queue_pair(s->queues[i]);
}
g_free(s->queues);
@ -880,8 +913,8 @@ static void nvme_close(BlockDriverState *bs)
&s->irq_notifier[MSIX_SHARED_IRQ_IDX],
false, NULL, NULL);
event_notifier_cleanup(&s->irq_notifier[MSIX_SHARED_IRQ_IDX]);
qemu_vfio_pci_unmap_bar(s->vfio, 0, (void *)s->doorbells,
sizeof(NvmeBar), NVME_DOORBELL_SIZE);
qemu_vfio_pci_unmap_bar(s->vfio, 0, s->bar0_wo_map,
0, sizeof(NvmeBar) + NVME_DOORBELL_SIZE);
qemu_vfio_close(s->vfio);
g_free(s->device);
@ -985,11 +1018,12 @@ static coroutine_fn int nvme_cmd_map_qiov(BlockDriverState *bs, NvmeCmd *cmd,
for (i = 0; i < qiov->niov; ++i) {
bool retry = true;
uint64_t iova;
size_t len = QEMU_ALIGN_UP(qiov->iov[i].iov_len,
qemu_real_host_page_size);
try_map:
r = qemu_vfio_dma_map(s->vfio,
qiov->iov[i].iov_base,
qiov->iov[i].iov_len,
true, &iova);
len, true, &iova);
if (r == -ENOMEM && retry) {
retry = false;
trace_nvme_dma_flush_queue_wait(s);
@ -1097,7 +1131,7 @@ static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs,
};
trace_nvme_prw_aligned(s, is_write, offset, bytes, flags, qiov->niov);
assert(s->nr_queues > 1);
assert(s->queue_count > 1);
req = nvme_get_free_req(ioq);
assert(req);
@ -1133,8 +1167,9 @@ static inline bool nvme_qiov_aligned(BlockDriverState *bs,
BDRVNVMeState *s = bs->opaque;
for (i = 0; i < qiov->niov; ++i) {
if (!QEMU_PTR_IS_ALIGNED(qiov->iov[i].iov_base, s->page_size) ||
!QEMU_IS_ALIGNED(qiov->iov[i].iov_len, s->page_size)) {
if (!QEMU_PTR_IS_ALIGNED(qiov->iov[i].iov_base,
qemu_real_host_page_size) ||
!QEMU_IS_ALIGNED(qiov->iov[i].iov_len, qemu_real_host_page_size)) {
trace_nvme_qiov_unaligned(qiov, i, qiov->iov[i].iov_base,
qiov->iov[i].iov_len, s->page_size);
return false;
@ -1150,15 +1185,17 @@ static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
int r;
uint8_t *buf = NULL;
QEMUIOVector local_qiov;
size_t len = QEMU_ALIGN_UP(bytes, qemu_real_host_page_size);
assert(QEMU_IS_ALIGNED(offset, s->page_size));
assert(QEMU_IS_ALIGNED(bytes, s->page_size));
assert(bytes <= s->max_transfer);
if (nvme_qiov_aligned(bs, qiov)) {
s->stats.aligned_accesses++;
return nvme_co_prw_aligned(bs, offset, bytes, qiov, is_write, flags);
}
s->stats.unaligned_accesses++;
trace_nvme_prw_buffered(s, offset, bytes, qiov->niov, is_write);
buf = qemu_try_memalign(s->page_size, bytes);
buf = qemu_try_memalign(qemu_real_host_page_size, len);
if (!buf) {
return -ENOMEM;
@ -1205,7 +1242,7 @@ static coroutine_fn int nvme_co_flush(BlockDriverState *bs)
.ret = -EINPROGRESS,
};
assert(s->nr_queues > 1);
assert(s->queue_count > 1);
req = nvme_get_free_req(ioq);
assert(req);
nvme_submit_command(ioq, req, &cmd, nvme_rw_cb, &data);
@ -1257,7 +1294,7 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs,
cmd.cdw12 = cpu_to_le32(cdw12);
trace_nvme_write_zeroes(s, offset, bytes, flags);
assert(s->nr_queues > 1);
assert(s->queue_count > 1);
req = nvme_get_free_req(ioq);
assert(req);
@ -1300,7 +1337,7 @@ static int coroutine_fn nvme_co_pdiscard(BlockDriverState *bs,
return -ENOTSUP;
}
assert(s->nr_queues > 1);
assert(s->queue_count > 1);
buf = qemu_try_memalign(s->page_size, s->page_size);
if (!buf) {
@ -1380,7 +1417,7 @@ static void nvme_detach_aio_context(BlockDriverState *bs)
{
BDRVNVMeState *s = bs->opaque;
for (int i = 0; i < s->nr_queues; i++) {
for (unsigned i = 0; i < s->queue_count; i++) {
NVMeQueuePair *q = s->queues[i];
qemu_bh_delete(q->completion_bh);
@ -1401,7 +1438,7 @@ static void nvme_attach_aio_context(BlockDriverState *bs,
aio_set_event_notifier(new_context, &s->irq_notifier[MSIX_SHARED_IRQ_IDX],
false, nvme_handle_event, nvme_poll_cb);
for (int i = 0; i < s->nr_queues; i++) {
for (unsigned i = 0; i < s->queue_count; i++) {
NVMeQueuePair *q = s->queues[i];
q->completion_bh =
@ -1418,11 +1455,10 @@ static void nvme_aio_plug(BlockDriverState *bs)
static void nvme_aio_unplug(BlockDriverState *bs)
{
int i;
BDRVNVMeState *s = bs->opaque;
assert(s->plugged);
s->plugged = false;
for (i = INDEX_IO(0); i < s->nr_queues; i++) {
for (unsigned i = INDEX_IO(0); i < s->queue_count; i++) {
NVMeQueuePair *q = s->queues[i];
qemu_mutex_lock(&q->lock);
nvme_kick(q);
@ -1452,6 +1488,21 @@ static void nvme_unregister_buf(BlockDriverState *bs, void *host)
qemu_vfio_dma_unmap(s->vfio, host);
}
static BlockStatsSpecific *nvme_get_specific_stats(BlockDriverState *bs)
{
BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1);
BDRVNVMeState *s = bs->opaque;
stats->driver = BLOCKDEV_DRIVER_NVME;
stats->u.nvme = (BlockStatsSpecificNvme) {
.completion_errors = s->stats.completion_errors,
.aligned_accesses = s->stats.aligned_accesses,
.unaligned_accesses = s->stats.unaligned_accesses,
};
return stats;
}
static const char *const nvme_strong_runtime_opts[] = {
NVME_BLOCK_OPT_DEVICE,
NVME_BLOCK_OPT_NAMESPACE,
@ -1485,6 +1536,7 @@ static BlockDriver bdrv_nvme = {
.bdrv_refresh_filename = nvme_refresh_filename,
.bdrv_refresh_limits = nvme_refresh_limits,
.strong_runtime_opts = nvme_strong_runtime_opts,
.bdrv_get_specific_stats = nvme_get_specific_stats,
.bdrv_detach_aio_context = nvme_detach_aio_context,
.bdrv_attach_aio_context = nvme_attach_aio_context,

14
block/qcow2-cluster.c
View File

@ -1049,6 +1049,8 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice);
assert(l2_index + m->nb_clusters <= s->l2_slice_size);
assert(m->cow_end.offset + m->cow_end.nb_bytes <=
m->nb_clusters << s->cluster_bits);
for (i = 0; i < m->nb_clusters; i++) {
uint64_t offset = cluster_offset + ((uint64_t)i << s->cluster_bits);
/* if two concurrent writes happen to the same unallocated cluster
@ -1070,8 +1072,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
if (has_subclusters(s) && !m->prealloc) {
uint64_t l2_bitmap = get_l2_bitmap(s, l2_slice, l2_index + i);
unsigned written_from = m->cow_start.offset;
unsigned written_to = m->cow_end.offset + m->cow_end.nb_bytes ?:
m->nb_clusters << s->cluster_bits;
unsigned written_to = m->cow_end.offset + m->cow_end.nb_bytes;
int first_sc, last_sc;
/* Narrow written_from and written_to down to the current cluster */
written_from = MAX(written_from, i << s->cluster_bits);
@ -2009,14 +2010,17 @@ static int zero_in_l2_slice(BlockDriverState *bs, uint64_t offset,
continue;
}
/* First update L2 entries */
qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_slice);
if (unmap) {
qcow2_free_any_cluster(bs, old_l2_entry, QCOW2_DISCARD_REQUEST);
}
set_l2_entry(s, l2_slice, l2_index + i, new_l2_entry);
if (has_subclusters(s)) {
set_l2_bitmap(s, l2_slice, l2_index + i, new_l2_bitmap);
}
/* Then decrease the refcount */
if (unmap) {
qcow2_free_any_cluster(bs, old_l2_entry, QCOW2_DISCARD_REQUEST);
}
}
qcow2_cache_put(s->l2_table_cache, (void **) &l2_slice);

74
block/qcow2.c
View File

@ -269,7 +269,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
case QCOW2_EXT_MAGIC_FEATURE_TABLE:
if (p_feature_table != NULL) {
void* feature_table = g_malloc0(ext.len + 2 * sizeof(Qcow2Feature));
void *feature_table = g_malloc0(ext.len + 2 * sizeof(Qcow2Feature));
ret = bdrv_pread(bs->file, offset , feature_table, ext.len);
if (ret < 0) {
error_setg_errno(errp, -ret, "ERROR: ext_feature_table: "
@ -2361,15 +2361,26 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
continue;
}
/* The data (middle) region must be immediately after the
* start region */
/*
* The write request should start immediately after the first
* COW region. This does not always happen because the area
* touched by the request can be larger than the one defined
* by @m (a single request can span an area consisting of a
* mix of previously unallocated and allocated clusters, that
* is why @l2meta is a list).
*/
if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) {
/* In this case the request starts before this region */
assert(offset < l2meta_cow_start(m));
assert(m->cow_start.nb_bytes == 0);
continue;
}
/* The end region must be immediately after the data (middle)
* region */
/* The write request should end immediately before the second
* COW region (see above for why it does not always happen) */
if (m->offset + m->cow_end.offset != offset + bytes) {
assert(offset + bytes > m->offset + m->cow_end.offset);
assert(m->cow_end.nb_bytes == 0);
continue;
}
@ -2387,26 +2398,26 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
return false;
}
static bool is_unallocated(BlockDriverState *bs, int64_t offset, int64_t bytes)
{
int64_t nr;
return !bytes ||
(!bdrv_is_allocated_above(bs, NULL, false, offset, bytes, &nr) &&
nr == bytes);
}
static bool is_zero_cow(BlockDriverState *bs, QCowL2Meta *m)
/*
* 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)
{
/*
* This check is designed for optimization shortcut so it must be
* efficient.
* Instead of is_zero(), use is_unallocated() as it is faster (but not
* as accurate and can result in false negatives).
* Instead of is_zero(), use bdrv_co_is_zero_fast() as it is
* faster (but not as accurate and can result in false negatives).
*/
return is_unallocated(bs, m->offset + m->cow_start.offset,
m->cow_start.nb_bytes) &&
is_unallocated(bs, m->offset + m->cow_end.offset,
m->cow_end.nb_bytes);
int ret = bdrv_co_is_zero_fast(bs, m->offset + m->cow_start.offset,
m->cow_start.nb_bytes);
if (ret <= 0) {
return ret;
}
return bdrv_co_is_zero_fast(bs, m->offset + m->cow_end.offset,
m->cow_end.nb_bytes);
}
static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta)
@ -2432,7 +2443,10 @@ static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta)
continue;
}
if (!is_zero_cow(bs, m)) {
ret = is_zero_cow(bs, m);
if (ret < 0) {
return ret;
} else if (ret == 0) {
continue;
}
@ -3374,7 +3388,7 @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp)
size_t cluster_size;
int version;
int refcount_order;
uint64_t* refcount_table;
uint64_t *refcount_table;
int ret;
uint8_t compression_type = QCOW2_COMPRESSION_TYPE_ZLIB;
@ -3860,8 +3874,20 @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes)
if (!bytes) {
return true;
}
res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL);
return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes;
/*
* bdrv_block_status_above doesn't merge different types of zeros, for
* example, zeros which come from the region which is unallocated in
* the whole backing chain, and zeros which come because of a short
* backing file. So, we need a loop.
*/
do {
res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL);
offset += nr;
bytes -= nr;
} while (res >= 0 && (res & BDRV_BLOCK_ZERO) && nr && bytes);
return res >= 0 && (res & BDRV_BLOCK_ZERO) && bytes == 0;
}
static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,

25
block/qcow2.h
View File

@ -343,8 +343,8 @@ typedef struct BDRVQcow2State {
uint64_t l1_table_offset;
uint64_t *l1_table;
Qcow2Cache* l2_table_cache;
Qcow2Cache* refcount_block_cache;
Qcow2Cache *l2_table_cache;
Qcow2Cache *refcount_block_cache;
QEMUTimer *cache_clean_timer;
unsigned cache_clean_interval;
@ -394,7 +394,7 @@ typedef struct BDRVQcow2State {
uint64_t autoclear_features;
size_t unknown_header_fields_size;
void* unknown_header_fields;
void *unknown_header_fields;
QLIST_HEAD(, Qcow2UnknownHeaderExtension) unknown_header_ext;
QTAILQ_HEAD (, Qcow2DiscardRegion) discards;
bool cache_discards;
@ -435,17 +435,18 @@ typedef struct Qcow2COWRegion {
/**
* Describes an in-flight (part of a) write request that writes to clusters
* that are not referenced in their L2 table yet.
* that need to have their L2 table entries updated (because they are
* newly allocated or need changes in their L2 bitmaps)
*/
typedef struct QCowL2Meta
{
/** Guest offset of the first newly allocated cluster */
/** Guest offset of the first updated cluster */
uint64_t offset;
/** Host offset of the first newly allocated cluster */
/** Host offset of the first updated cluster */
uint64_t alloc_offset;
/** Number of newly allocated clusters */
/** Number of updated clusters */
int nb_clusters;
/** Do not free the old clusters */
@ -458,14 +459,16 @@ typedef struct QCowL2Meta
CoQueue dependent_requests;
/**
* The COW Region between the start of the first allocated cluster and the
* area the guest actually writes to.
* The COW Region immediately before the area the guest actually
* writes to. This (part of the) write request starts at
* cow_start.offset + cow_start.nb_bytes.
*/
Qcow2COWRegion cow_start;
/**
* The COW Region between the area the guest actually writes to and the
* end of the last allocated cluster.
* The COW Region immediately after the area the guest actually
* writes to. This (part of the) write request ends at cow_end.offset
* (which must always be set even when cow_end.nb_bytes is 0).
*/
Qcow2COWRegion cow_end;

7
block/quorum.c
View File

@ -856,7 +856,7 @@ static int quorum_valid_threshold(int threshold, int num_children, Error **errp)
if (threshold < 1) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
"vote-threshold", "value >= 1");
"vote-threshold", "a value >= 1");
return -ERANGE;
}
@ -1163,7 +1163,12 @@ static void quorum_child_perm(BlockDriverState *bs, BdrvChild *c,
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
{
BDRVQuorumState *s = bs->opaque;
*nperm = perm & DEFAULT_PERM_PASSTHROUGH;
if (s->rewrite_corrupted) {
*nperm |= BLK_PERM_WRITE;
}
/*
* We cannot share RESIZE or WRITE, as this would make the

14
block/sheepdog.c
View File

@ -242,6 +242,16 @@ typedef struct SheepdogInode {
*/
#define FNV1A_64_INIT ((uint64_t)0xcbf29ce484222325ULL)
static void deprecation_warning(void)
{
static bool warned;
if (!warned) {
warn_report("the sheepdog block driver is deprecated");
warned = true;
}
}
/*
* 64 bit Fowler/Noll/Vo FNV-1a hash code
*/
@ -1548,6 +1558,8 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
char *buf = NULL;
QemuOpts *opts;
deprecation_warning();
s->bs = bs;
s->aio_context = bdrv_get_aio_context(bs);
@ -2007,6 +2019,8 @@ static int sd_co_create(BlockdevCreateOptions *options, Error **errp)
assert(options->driver == BLOCKDEV_DRIVER_SHEEPDOG);
deprecation_warning();
s = g_new0(BDRVSheepdogState, 1);
/* Steal SocketAddress from QAPI, set NULL to prevent double free */

2
block/stream.c
View File

@ -167,7 +167,7 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
n = len - offset;
}
copy = (ret == 1);
copy = (ret > 0);
}
trace_stream_one_iteration(s, offset, n, ret);
if (copy) {

48
block/throttle-groups.c
View File

@ -546,7 +546,7 @@ void throttle_group_register_tgm(ThrottleGroupMember *tgm,
tgm->aio_context = ctx;
qatomic_set(&tgm->restart_pending, 0);
qemu_mutex_lock(&tg->lock);
QEMU_LOCK_GUARD(&tg->lock);
/* If the ThrottleGroup is new set this ThrottleGroupMember as the token */
for (i = 0; i < 2; i++) {
if (!tg->tokens[i]) {
@ -565,8 +565,6 @@ void throttle_group_register_tgm(ThrottleGroupMember *tgm,
qemu_co_mutex_init(&tgm->throttled_reqs_lock);
qemu_co_queue_init(&tgm->throttled_reqs[0]);
qemu_co_queue_init(&tgm->throttled_reqs[1]);
qemu_mutex_unlock(&tg->lock);
}
/* Unregister a ThrottleGroupMember from its group, removing it from the list,
@ -594,25 +592,25 @@ void throttle_group_unregister_tgm(ThrottleGroupMember *tgm)
/* Wait for throttle_group_restart_queue_entry() coroutines to finish */
AIO_WAIT_WHILE(tgm->aio_context, qatomic_read(&tgm->restart_pending) > 0);
qemu_mutex_lock(&tg->lock);
for (i = 0; i < 2; i++) {
assert(tgm->pending_reqs[i] == 0);
assert(qemu_co_queue_empty(&tgm->throttled_reqs[i]));
assert(!timer_pending(tgm->throttle_timers.timers[i]));
if (tg->tokens[i] == tgm) {
token = throttle_group_next_tgm(tgm);
/* Take care of the case where this is the last tgm in the group */
if (token == tgm) {
token = NULL;
WITH_QEMU_LOCK_GUARD(&tg->lock) {
for (i = 0; i < 2; i++) {
assert(tgm->pending_reqs[i] == 0);
assert(qemu_co_queue_empty(&tgm->throttled_reqs[i]));
assert(!timer_pending(tgm->throttle_timers.timers[i]));
if (tg->tokens[i] == tgm) {
token = throttle_group_next_tgm(tgm);
/* Take care of the case where this is the last tgm in the group */
if (token == tgm) {
token = NULL;
}
tg->tokens[i] = token;
}
tg->tokens[i] = token;
}
}
/* remove the current tgm from the list */
QLIST_REMOVE(tgm, round_robin);
throttle_timers_destroy(&tgm->throttle_timers);
qemu_mutex_unlock(&tg->lock);
/* remove the current tgm from the list */
QLIST_REMOVE(tgm, round_robin);
throttle_timers_destroy(&tgm->throttle_timers);
}
throttle_group_unref(&tg->ts);
tgm->throttle_state = NULL;
@ -638,14 +636,14 @@ void throttle_group_detach_aio_context(ThrottleGroupMember *tgm)
assert(qemu_co_queue_empty(&tgm->throttled_reqs[1]));
/* Kick off next ThrottleGroupMember, if necessary */
qemu_mutex_lock(&tg->lock);
for (i = 0; i < 2; i++) {
if (timer_pending(tt->timers[i])) {
tg->any_timer_armed[i] = false;
schedule_next_request(tgm, i);
WITH_QEMU_LOCK_GUARD(&tg->lock) {
for (i = 0; i < 2; i++) {
if (timer_pending(tt->timers[i])) {
tg->any_timer_armed[i] = false;
schedule_next_request(tgm, i);
}
}
}
qemu_mutex_unlock(&tg->lock);
throttle_timers_detach_aio_context(tt);
tgm->aio_context = NULL;

30
block/trace-events
View File

@ -134,25 +134,29 @@ qed_aio_write_postfill(void *s, void *acb, uint64_t start, size_t len, uint64_t
qed_aio_write_main(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"
# nvme.c
nvme_kick(void *s, int queue) "s %p queue %d"
nvme_controller_capability_raw(uint64_t value) "0x%08"PRIx64
nvme_controller_capability(const char *desc, uint64_t value) "%s: %"PRIu64
nvme_kick(void *s, unsigned q_index) "s %p q #%u"
nvme_dma_flush_queue_wait(void *s) "s %p"
nvme_error(int cmd_specific, int sq_head, int sqid, int cid, int status) "cmd_specific %d sq_head %d sqid %d cid %d status 0x%x"
nvme_process_completion(void *s, int index, int inflight) "s %p queue %d inflight %d"
nvme_process_completion_queue_plugged(void *s, int index) "s %p queue %d"
nvme_complete_command(void *s, int index, int cid) "s %p queue %d cid %d"
nvme_submit_command(void *s, int index, int cid) "s %p queue %d cid %d"
nvme_process_completion(void *s, unsigned q_index, int inflight) "s %p q #%u inflight %d"
nvme_process_completion_queue_plugged(void *s, unsigned q_index) "s %p q #%u"
nvme_complete_command(void *s, unsigned q_index, int cid) "s %p q #%u cid %d"
nvme_submit_command(void *s, unsigned q_index, int cid) "s %p q #%u cid %d"
nvme_submit_command_raw(int c0, int c1, int c2, int c3, int c4, int c5, int c6, int c7) "%02x %02x %02x %02x %02x %02x %02x %02x"
nvme_handle_event(void *s) "s %p"
nvme_poll_cb(void *s) "s %p"
nvme_prw_aligned(void *s, int is_write, uint64_t offset, uint64_t bytes, int flags, int niov) "s %p is_write %d offset %"PRId64" bytes %"PRId64" flags %d niov %d"
nvme_write_zeroes(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p offset %"PRId64" bytes %"PRId64" flags %d"
nvme_poll_queue(void *s, unsigned q_index) "s %p q #%u"
nvme_prw_aligned(void *s, int is_write, uint64_t offset, uint64_t bytes, int flags, int niov) "s %p is_write %d offset 0x%"PRIx64" bytes %"PRId64" flags %d niov %d"
nvme_write_zeroes(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p offset 0x%"PRIx64" bytes %"PRId64" flags %d"
nvme_qiov_unaligned(const void *qiov, int n, void *base, size_t size, int align) "qiov %p n %d base %p size 0x%zx align 0x%x"
nvme_prw_buffered(void *s, uint64_t offset, uint64_t bytes, int niov, int is_write) "s %p offset %"PRId64" bytes %"PRId64" niov %d is_write %d"
nvme_rw_done(void *s, int is_write, uint64_t offset, uint64_t bytes, int ret) "s %p is_write %d offset %"PRId64" bytes %"PRId64" ret %d"
nvme_dsm(void *s, uint64_t offset, uint64_t bytes) "s %p offset %"PRId64" bytes %"PRId64""
nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset %"PRId64" bytes %"PRId64" ret %d"
nvme_prw_buffered(void *s, uint64_t offset, uint64_t bytes, int niov, int is_write) "s %p offset 0x%"PRIx64" bytes %"PRId64" niov %d is_write %d"
nvme_rw_done(void *s, int is_write, uint64_t offset, uint64_t bytes, int ret) "s %p is_write %d offset 0x%"PRIx64" bytes %"PRId64" ret %d"
nvme_dsm(void *s, uint64_t offset, uint64_t bytes) "s %p offset 0x%"PRIx64" bytes %"PRId64""
nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset 0x%"PRIx64" bytes %"PRId64" ret %d"
nvme_dma_map_flush(void *s) "s %p"
nvme_free_req_queue_wait(void *q) "q %p"
nvme_free_req_queue_wait(void *s, unsigned q_index) "s %p q #%u"
nvme_create_queue_pair(unsigned q_index, void *q, unsigned size, void *aio_context, int fd) "index %u q %p size %u aioctx %p fd %d"
nvme_free_queue_pair(unsigned q_index, void *q) "index %u q %p"
nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d"
nvme_cmd_map_qiov_pages(void *s, int i, uint64_t page) "s %p page[%d] 0x%"PRIx64
nvme_cmd_map_qiov_iov(void *s, int i, void *page, int pages) "s %p iov[%d] %p pages %d"

8
block/vmdk.c
View File

@ -595,7 +595,7 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
int ret;
uint32_t magic;
VMDK3Header header;
VmdkExtent *extent;
VmdkExtent *extent = NULL;
ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));
if (ret < 0) {
@ -751,7 +751,7 @@ static int vmdk_open_se_sparse(BlockDriverState *bs,
int ret;
VMDKSESparseConstHeader const_header;
VMDKSESparseVolatileHeader volatile_header;
VmdkExtent *extent;
VmdkExtent *extent = NULL;
ret = bdrv_apply_auto_read_only(bs,
"No write support for seSparse images available", errp);
@ -869,7 +869,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
uint32_t magic;
uint32_t l1_size, l1_entry_sectors;
VMDK4Header header;
VmdkExtent *extent;
VmdkExtent *extent = NULL;
BDRVVmdkState *s = bs->opaque;
int64_t l1_backup_offset = 0;
bool compressed;
@ -1088,7 +1088,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
BdrvChild *extent_file;
BdrvChildRole extent_role;
BDRVVmdkState *s = bs->opaque;
VmdkExtent *extent;
VmdkExtent *extent = NULL;
char extent_opt_prefix[32];
Error *local_err = NULL;

10
block/vpc.c
View File

@ -172,7 +172,7 @@ static QemuOptsList vpc_runtime_opts = {
static QemuOptsList vpc_create_opts;
static uint32_t vpc_checksum(uint8_t* buf, size_t size)
static uint32_t vpc_checksum(uint8_t *buf, size_t size)
{
uint32_t res = 0;
int i;
@ -528,7 +528,7 @@ static inline int64_t get_image_offset(BlockDriverState *bs, uint64_t offset,
*
* Returns 0 on success and < 0 on error
*/
static int rewrite_footer(BlockDriverState* bs)
static int rewrite_footer(BlockDriverState *bs)
{
int ret;
BDRVVPCState *s = bs->opaque;
@ -548,7 +548,7 @@ static int rewrite_footer(BlockDriverState* bs)
*
* Returns the sectors' offset in the image file on success and < 0 on error
*/
static int64_t alloc_block(BlockDriverState* bs, int64_t offset)
static int64_t alloc_block(BlockDriverState *bs, int64_t offset)
{
BDRVVPCState *s = bs->opaque;
int64_t bat_offset;
@ -781,8 +781,8 @@ static int coroutine_fn vpc_co_block_status(BlockDriverState *bs,
* the hardware EIDE and ATA-2 limit of 16 heads (max disk size of 127 GB)
* and instead allow up to 255 heads.
*/
static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
uint8_t* heads, uint8_t* secs_per_cyl)
static int calculate_geometry(int64_t total_sectors, uint16_t *cyls,
uint8_t *heads, uint8_t *secs_per_cyl)
{
uint32_t cyls_times_heads;

12
block/vvfat.c
View File

@ -1437,7 +1437,7 @@ static void print_direntry(const direntry_t* direntry)
for(i=0;i<11;i++)
ADD_CHAR(direntry->name[i]);
buffer[j] = 0;
fprintf(stderr,"%s attributes=0x%02x begin=%d size=%d\n",
fprintf(stderr, "%s attributes=0x%02x begin=%u size=%u\n",
buffer,
direntry->attributes,
begin_of_direntry(direntry),le32_to_cpu(direntry->size));
@ -1446,7 +1446,7 @@ static void print_direntry(const direntry_t* direntry)
static void print_mapping(const mapping_t* mapping)
{
fprintf(stderr, "mapping (%p): begin, end = %d, %d, dir_index = %d, "
fprintf(stderr, "mapping (%p): begin, end = %u, %u, dir_index = %u, "
"first_mapping_index = %d, name = %s, mode = 0x%x, " ,
mapping, mapping->begin, mapping->end, mapping->dir_index,
mapping->first_mapping_index, mapping->path, mapping->mode);
@ -1454,7 +1454,7 @@ static void print_mapping(const mapping_t* mapping)
if (mapping->mode & MODE_DIRECTORY)
fprintf(stderr, "parent_mapping_index = %d, first_dir_index = %d\n", mapping->info.dir.parent_mapping_index, mapping->info.dir.first_dir_index);
else
fprintf(stderr, "offset = %d\n", mapping->info.file.offset);
fprintf(stderr, "offset = %u\n", mapping->info.file.offset);
}
#endif
@ -1588,7 +1588,7 @@ typedef struct commit_t {
static void clear_commits(BDRVVVFATState* s)
{
int i;
DLOG(fprintf(stderr, "clear_commits (%d commits)\n", s->commits.next));
DLOG(fprintf(stderr, "clear_commits (%u commits)\n", s->commits.next));
for (i = 0; i < s->commits.next; i++) {
commit_t* commit = array_get(&(s->commits), i);
assert(commit->path || commit->action == ACTION_WRITEOUT);
@ -2648,7 +2648,9 @@ static int handle_renames_and_mkdirs(BDRVVVFATState* s)
fprintf(stderr, "handle_renames\n");
for (i = 0; i < s->commits.next; i++) {
commit_t* commit = array_get(&(s->commits), i);
fprintf(stderr, "%d, %s (%d, %d)\n", i, commit->path ? commit->path : "(null)", commit->param.rename.cluster, commit->action);
fprintf(stderr, "%d, %s (%u, %d)\n", i,
commit->path ? commit->path : "(null)",
commit->param.rename.cluster, commit->action);
}
#endif

19
blockdev-nbd.c
View File

@ -14,6 +14,8 @@
#include "sysemu/block-backend.h"
#include "hw/block/block.h"
#include "qapi/error.h"
#include "qapi/clone-visitor.h"
#include "qapi/qapi-visit-block-export.h"
#include "qapi/qapi-commands-block-export.h"
#include "block/nbd.h"
#include "io/channel-socket.h"
@ -195,7 +197,8 @@ void qmp_nbd_server_add(NbdServerAddOptions *arg, Error **errp)
* the device name as a default here for compatibility.
*/
if (!arg->has_name) {
arg->name = arg->device;
arg->has_name = true;
arg->name = g_strdup(arg->device);
}
export_opts = g_new(BlockExportOptions, 1);
@ -205,15 +208,13 @@ void qmp_nbd_server_add(NbdServerAddOptions *arg, Error **errp)
.node_name = g_strdup(bdrv_get_node_name(bs)),
.has_writable = arg->has_writable,
.writable = arg->writable,
.u.nbd = {
.has_name = true,
.name = g_strdup(arg->name),
.has_description = arg->has_description,
.description = g_strdup(arg->description),
.has_bitmap = arg->has_bitmap,
.bitmap = g_strdup(arg->bitmap),
},
};
QAPI_CLONE_MEMBERS(BlockExportOptionsNbdBase, &export_opts->u.nbd,
qapi_NbdServerAddOptions_base(arg));
if (arg->has_bitmap) {
export_opts->u.nbd.has_bitmaps = true;
QAPI_LIST_PREPEND(export_opts->u.nbd.bitmaps, g_strdup(arg->bitmap));
}
/*
* nbd-server-add doesn't complain when a read-only device should be

32
blockdev.c
View File

@ -1827,6 +1827,7 @@ static void drive_backup_prepare(BlkActionState *common, Error **errp)
if (set_backing_hd) {
bdrv_set_backing_hd(target_bs, source, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto unref;
}
}
@ -2454,7 +2455,7 @@ void coroutine_fn qmp_block_resize(bool has_device, const char *device,
int64_t size, Error **errp)
{
Error *local_err = NULL;
BlockBackend *blk = NULL;
BlockBackend *blk;
BlockDriverState *bs;
AioContext *old_ctx;
@ -2468,27 +2469,29 @@ void coroutine_fn qmp_block_resize(bool has_device, const char *device,
if (size < 0) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "size", "a >0 size");
goto out;
return;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_RESIZE, NULL)) {
error_setg(errp, QERR_DEVICE_IN_USE, device);
goto out;
return;
}
blk = blk_new_with_bs(bs, BLK_PERM_RESIZE, BLK_PERM_ALL, errp);
if (!blk) {
goto out;
return;
}
bdrv_co_lock(bs);
bdrv_drained_begin(bs);
bdrv_co_unlock(bs);
old_ctx = bdrv_co_enter(bs);
blk_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp);
bdrv_co_leave(bs, old_ctx);
bdrv_drained_end(bs);
out:
bdrv_co_lock(bs);
bdrv_drained_end(bs);
blk_unref(blk);
bdrv_co_unlock(bs);
}
@ -2531,7 +2534,7 @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
if (has_base) {
base_bs = bdrv_find_backing_image(bs, base);
if (base_bs == NULL) {
error_setg(errp, QERR_BASE_NOT_FOUND, base);
error_setg(errp, "Can't find '%s' in the backing chain", base);
goto out;
}
assert(bdrv_get_aio_context(base_bs) == aio_context);
@ -2703,13 +2706,16 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
}
} else if (has_base && base) {
base_bs = bdrv_find_backing_image(top_bs, base);
if (base_bs == NULL) {
error_setg(errp, "Can't find '%s' in the backing chain", base);
goto out;
}
} else {
base_bs = bdrv_find_base(top_bs);
}
if (base_bs == NULL) {
error_setg(errp, QERR_BASE_NOT_FOUND, base ? base : "NULL");
goto out;
if (base_bs == NULL) {
error_setg(errp, "There is no backimg image");
goto out;
}
}
assert(bdrv_get_aio_context(base_bs) == aio_context);
@ -2988,7 +2994,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
}
if (granularity & (granularity - 1)) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "granularity",
"power of 2");
"a power of 2");
return;
}

6
bsd-user/main.c
View File

@ -745,7 +745,6 @@ int main(int argc, char **argv)
const char *gdbstub = NULL;
char **target_environ, **wrk;
envlist_t *envlist = NULL;
char *trace_file = NULL;
bsd_type = target_openbsd;
if (argc <= 1)
@ -851,8 +850,7 @@ int main(int argc, char **argv)
} else if (!strcmp(r, "strace")) {
do_strace = 1;
} else if (!strcmp(r, "trace")) {
g_free(trace_file);
trace_file = trace_opt_parse(optarg);
trace_opt_parse(optarg);
} else {
usage();
}
@ -880,7 +878,7 @@ int main(int argc, char **argv)
if (!trace_init_backends()) {
exit(1);
}
trace_init_file(trace_file);
trace_init_file();
/* Zero out regs */
memset(regs, 0, sizeof(struct target_pt_regs));

38
chardev/char-mux.c
View File

@ -33,6 +33,13 @@
/* MUX driver for serial I/O splitting */
/*
* Set to false by suspend_mux_open. Open events are delayed until
* resume_mux_open. Usually suspend_mux_open is called before
* command line processing and resume_mux_open afterwards.
*/
static bool muxes_opened = true;
/* Called with chr_write_lock held. */
static int mux_chr_write(Chardev *chr, const uint8_t *buf, int len)
{
@ -237,7 +244,7 @@ void mux_chr_send_all_event(Chardev *chr, QEMUChrEvent event)
MuxChardev *d = MUX_CHARDEV(chr);
int i;
if (!machine_init_done) {
if (!muxes_opened) {
return;
}
@ -328,7 +335,7 @@ static void qemu_chr_open_mux(Chardev *chr,
/* only default to opened state if we've realized the initial
* set of muxes
*/
*be_opened = machine_init_done;
*be_opened = muxes_opened;
qemu_chr_fe_init(&d->chr, drv, errp);
}
@ -360,19 +367,42 @@ static void qemu_chr_parse_mux(QemuOpts *opts, ChardevBackend *backend,
* mux will receive CHR_EVENT_OPENED notifications for the BE
* immediately.
*/
static int open_muxes(Chardev *chr)
static void open_muxes(Chardev *chr)
{
/* send OPENED to all already-attached FEs */
mux_chr_send_all_event(chr, CHR_EVENT_OPENED);
/*
* mark mux as OPENED so any new FEs will immediately receive
* OPENED event
*/
chr->be_open = 1;
}
void suspend_mux_open(void)
{
muxes_opened = false;
}
static int chardev_options_parsed_cb(Object *child, void *opaque)
{
Chardev *chr = (Chardev *)child;
ChardevClass *class = CHARDEV_GET_CLASS(chr);
if (!chr->be_open && class->chr_options_parsed) {
class->chr_options_parsed(chr);
}
return 0;
}
void resume_mux_open(void)
{
muxes_opened = true;
object_child_foreach(get_chardevs_root(),
chardev_options_parsed_cb, NULL);
}
static void char_mux_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
@ -383,7 +413,7 @@ static void char_mux_class_init(ObjectClass *oc, void *data)
cc->chr_accept_input = mux_chr_accept_input;
cc->chr_add_watch = mux_chr_add_watch;
cc->chr_be_event = mux_chr_be_event;
cc->chr_machine_done = open_muxes;
cc->chr_options_parsed = open_muxes;
cc->chr_update_read_handler = mux_chr_update_read_handlers;
}

24
chardev/char-socket.c
View File

@ -443,10 +443,24 @@ static char *qemu_chr_socket_address(SocketChardev *s, const char *prefix)
s->is_listen ? ",server" : "");
break;
case SOCKET_ADDRESS_TYPE_UNIX:
return g_strdup_printf("%sunix:%s%s", prefix,
s->addr->u.q_unix.path,
{
const char *tight = "", *abstract = "";
UnixSocketAddress *sa = &s->addr->u.q_unix;
#ifdef CONFIG_LINUX
if (sa->has_abstract && sa->abstract) {
abstract = ",abstract";
if (sa->has_tight && sa->tight) {
tight = ",tight";
}
}
#endif
return g_strdup_printf("%sunix:%s%s%s%s", prefix, sa->path,
abstract, tight,
s->is_listen ? ",server" : "");
break;
}
case SOCKET_ADDRESS_TYPE_FD:
return g_strdup_printf("%sfd:%s%s", prefix, s->addr->u.fd.str,
s->is_listen ? ",server" : "");
@ -1386,8 +1400,10 @@ static void qemu_chr_parse_socket(QemuOpts *opts, ChardevBackend *backend,
const char *host = qemu_opt_get(opts, "host");
const char *port = qemu_opt_get(opts, "port");
const char *fd = qemu_opt_get(opts, "fd");
#ifdef CONFIG_LINUX
bool tight = qemu_opt_get_bool(opts, "tight", true);
bool abstract = qemu_opt_get_bool(opts, "abstract", false);
#endif
SocketAddressLegacy *addr;
ChardevSocket *sock;
@ -1439,8 +1455,12 @@ static void qemu_chr_parse_socket(QemuOpts *opts, ChardevBackend *backend,
addr->type = SOCKET_ADDRESS_LEGACY_KIND_UNIX;
q_unix = addr->u.q_unix.data = g_new0(UnixSocketAddress, 1);
q_unix->path = g_strdup(path);
#ifdef CONFIG_LINUX
q_unix->has_tight = true;
q_unix->tight = tight;
q_unix->has_abstract = true;
q_unix->abstract = abstract;
#endif
} else if (host) {
addr->type = SOCKET_ADDRESS_LEGACY_KIND_INET;
addr->u.inet.data = g_new(InetSocketAddress, 1);

Some files were not shown because too many files have changed in this diff Show More