Merge tag 'pull-lu-20231018' of https://gitlab.com/rth7680/qemu into staging
linux-user/mips: fix abort on integer overflow
linux-user/sh4: Fix crashes on signal delivery
linux-user/loongarch: Enable LSX/LASX in HWCAP
linux-user: Fixes for zero_bss
linux-user: Propagate failure in mmap_reserve_or_unmap back to target_munmap
linux-user: Detect and report host crashes
linux-user: Remap guest SIGABRT
# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmUwapYdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV92UAf/RSsFWwCBAqt1WKIK
# 7/7F8AF7WW1Hhjy3bHLjNnzgsDeWYfdIVxMGfF9IYKrYMeEqFeBeQ+vcOe9LTAvW
# fEZkA//V+LosiYCwtVGBXyCbeXYxoONMp/taRv6lVHoqVU7aSlbXsYqwePcUtPWq
# r/V+Ru5vssqMueBdE9+E53JPewGPVw8xQE+xGgd1TZIeHWgegZHBzKWVap/3noey
# dKjTig3yxXXg1gQJLCRw+a6bl8oCl4vEluGsLzh5P8aV1imjvFPXkR2w1vQOC3ws
# 8DmyMcPEcsY4D2WLeTAGMheURLRzs5141nT0fQCOB4yzO/I8zYFIG12xCxgWoQkg
# kW9XZw==
# =5oFh
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 18 Oct 2023 16:30:30 PDT
# gpg: using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg: issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A 05C0 64DF 38E8 AF7E 215F
* tag 'pull-lu-20231018' of https://gitlab.com/rth7680/qemu:
linux-user: Remap guest SIGABRT
linux-user: Detect and report host SIGILL, SIGFPE, SIGTRAP
linux-user: Split out host_sig{segv,bus}_handler
linux-user: Simplify signal_init
linux-user: Map unsupported signals to an out-of-bounds value
linux-user: Only register handlers for core_dump_signal by default
linux-user: Detect and report host crashes
linux-user: Exit not abort in die_with_backtrace
linux-user: Split out die_with_signal
linux-user: Propagate failure in mmap_reserve_or_unmap back to target_munmap
linux-user/elfload: Enable LSX/LASX in HWCAP for LoongArch
linux-user/sh4: Fix crashes on signal delivery
linux-user/mips: fix abort on integer overflow
linux-user: Fixes for zero_bss
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/configs/meson/windows.txt b/configs/meson/windows.txt
new file mode 100644
index 0000000..55b192e
--- /dev/null
+++ b/configs/meson/windows.txt
@@ -0,0 +1,9 @@
+# target-specific defaults, can still be overridden on
+# the command line
+
+[built-in options]
+bindir = ''
+prefix = '/qemu'
+
+[project options]
+qemu_suffix = ''
diff --git a/configure b/configure
index 96d0dd5..b4ea78c 100755
--- a/configure
+++ b/configure
@@ -94,7 +94,7 @@
printf "%s" "$1" | sed "s,','\\\\'',g; s,.*,'&',"
}
-print_error() {
+error_exit() {
(echo
echo "ERROR: $1"
while test -n "$2"; do
@@ -102,10 +102,6 @@
shift
done
echo) >&2
-}
-
-error_exit() {
- print_error "$@"
exit 1
}
@@ -248,11 +244,8 @@
default_cflags='-O2 -g'
git_submodules_action="update"
-git="git"
docs="auto"
EXESUF=""
-prefix="/usr/local"
-qemu_suffix="qemu"
system="yes"
linux_user=""
bsd_user=""
@@ -261,12 +254,10 @@
ninja=""
python=
download="enabled"
-bindir="bin"
skip_meson=no
use_containers="yes"
gdb_bin=$(command -v "gdb-multiarch" || command -v "gdb")
gdb_arches=""
-werror=""
# Don't accept a target_list environment variable.
unset target_list
@@ -322,7 +313,6 @@
ld="${LD-${cross_prefix}ld}"
ranlib="${RANLIB-${cross_prefix}ranlib}"
nm="${NM-${cross_prefix}nm}"
-smbd="$SMBD"
strip="${STRIP-${cross_prefix}strip}"
widl="${WIDL-${cross_prefix}widl}"
windres="${WINDRES-${cross_prefix}windres}"
@@ -373,18 +363,6 @@
targetos=bogus
fi
-# OS specific
-
-case $targetos in
-windows)
- plugins="no"
- pie="no"
-;;
-haiku)
- pie="no"
-;;
-esac
-
if test ! -z "$cpu" ; then
# command line argument
:
@@ -600,9 +578,6 @@
if test "$targetos" = "windows" ; then
EXESUF=".exe"
- prefix="/qemu"
- bindir=""
- qemu_suffix=""
fi
meson_option_build_array() {
@@ -625,7 +600,10 @@
meson_options=
meson_option_add() {
- meson_options="$meson_options $(quote_sh "$1")"
+ local arg
+ for arg; do
+ meson_options="$meson_options $(quote_sh "$arg")"
+ done
}
meson_option_parse() {
meson_options="$meson_options $(_meson_option_parse "$@")"
@@ -636,6 +614,14 @@
fi
}
+meson_add_machine_file() {
+ if test "$cross_compile" = "yes"; then
+ meson_option_add --cross-file "$1"
+ else
+ meson_option_add --native-file "$1"
+ fi
+}
+
for opt do
optarg=$(expr "x$opt" : 'x[^=]*=\(.*\)')
case "$opt" in
@@ -643,8 +629,6 @@
;;
--version|-V) exec cat "$source_path/VERSION"
;;
- --prefix=*) prefix="$optarg"
- ;;
--cross-prefix=*)
;;
--cc=*)
@@ -665,8 +649,6 @@
;;
--ninja=*) ninja="$optarg"
;;
- --smbd=*) smbd="$optarg"
- ;;
--extra-cflags=*)
;;
--extra-cxxflags=*)
@@ -715,10 +697,6 @@
;;
--static) static="yes"
;;
- --bindir=*) bindir="$optarg"
- ;;
- --with-suffix=*) qemu_suffix="$optarg"
- ;;
--host=*|--build=*|\
--disable-dependency-tracking|\
--sbindir=*|--sharedstatedir=*|\
@@ -738,7 +716,6 @@
default_cflags='-O0 -g'
;;
--disable-tcg) tcg="disabled"
- plugins="no"
;;
--enable-tcg) tcg="enabled"
;;
@@ -763,25 +740,15 @@
;;
--disable-pie) pie="no"
;;
- --enable-werror) werror="yes"
+ --enable-cfi) cfi=true
;;
- --disable-werror) werror="no"
- ;;
- --enable-cfi)
- cfi="true";
- meson_option_add -Db_lto=true
- ;;
- --disable-cfi) cfi="false"
+ --disable-cfi) cfi=false
;;
--disable-download) download="disabled"; git_submodules_action=validate;
;;
--enable-download) download="enabled"; git_submodules_action=update;
;;
- --enable-plugins) if test "$targetos" = "windows"; then
- error_exit "TCG plugins not currently supported on Windows platforms"
- else
- plugins="yes"
- fi
+ --enable-plugins) plugins="yes"
;;
--disable-plugins) plugins="no"
;;
@@ -807,11 +774,6 @@
git_submodules_action="validate"
fi
-# test for any invalid configuration combinations
-if test "$plugins" = "yes" -a "$tcg" = "disabled"; then
- error_exit "Can't enable plugins on non-TCG builds"
-fi
-
if ! test -f "$source_path/subprojects/keycodemapdb/README" \
&& test "$download" = disabled
then
@@ -887,7 +849,6 @@
Standard options:
--help print this message
- --prefix=PREFIX install in PREFIX [$prefix]
--target-list=LIST set target list (default: build all)
$(echo Available targets: $default_target_list | \
fold -s -w 53 | sed -e 's/^/ /')
@@ -910,20 +871,14 @@
--cross-prefix-ARCH=PREFIX cross compiler prefix when building ARCH guest test cases
--python=PYTHON use specified python [$python]
--ninja=NINJA use specified ninja [$ninja]
- --smbd=SMBD use specified smbd [$smbd]
--static enable static build [$static]
- --bindir=PATH install binaries in PATH
- --with-suffix=SUFFIX suffix for QEMU data inside datadir/libdir/sysconfdir/docdir [$qemu_suffix]
--without-default-features default all --enable-* options to "disabled"
--without-default-devices do not include any device that is not needed to
start the emulator (only use if you are including
desired devices in configs/devices/)
--with-devices-ARCH=NAME override default configs/devices
--enable-debug enable common debug build options
- --disable-werror disable compilation abort on warning
--cpu=CPU Build for host CPU [$cpu]
- --enable-plugins
- enable plugins via shared library loading
--disable-containers don't use containers for cross-building
--container-engine=TYPE which container engine to use [$container_engine]
--gdb=GDB-path gdb to use for gdbstub tests [$gdb_bin]
@@ -1046,17 +1001,6 @@
fi
fi
-# Consult white-list to determine whether to enable werror
-# by default. Only enable by default for git builds
-if test -z "$werror" ; then
- if test -e "$source_path/.git" && \
- { test "$targetos" = linux || test "$targetos" = "windows"; }; then
- werror="yes"
- else
- werror="no"
- fi
-fi
-
if test "$targetos" = "bogus"; then
# Now that we know that we're not printing the help and that
# the compiler works (so the results of the check_defines we used
@@ -1065,15 +1009,27 @@
error_exit "Unrecognized host OS (uname -s reports '$(uname -s)')"
fi
+# test for any invalid configuration combinations
+if test "$targetos" = "windows"; then
+ if test "$plugins" = "yes"; then
+ error_exit "TCG plugins not currently supported on Windows platforms"
+ fi
+ plugins="no"
+fi
+if test "$tcg" = "disabled" ; then
+ if test "$plugins" = "yes"; then
+ error_exit "Can't enable plugins on non-TCG builds"
+ fi
+ plugins="no"
+fi
if test "$static" = "yes" ; then
if test "$plugins" = "yes"; then
error_exit "static and plugins are mutually incompatible"
- else
- plugins="no"
fi
+ plugins="no"
fi
-test "$plugins" = "" && plugins=yes
-if test "$plugins" = "yes"; then
+if test "$plugins" != "no"; then
+ plugins=yes
subdirs="$subdirs contrib/plugins"
fi
@@ -1088,20 +1044,24 @@
int main(void) { return tls_var; }
EOF
-if test "$static" = "yes"; then
- if test "$pie" != "no" && compile_prog "-Werror -fPIE -DPIE" "-static-pie"; then
+if test "$targetos" = windows || test "$targetos" = haiku; then
+ if test "$pie" = "yes"; then
+ error_exit "PIE not available due to missing OS support"
+ fi
+ pie=no
+fi
+
+if test "$pie" != "no"; then
+ if test "$static" = "yes"; then
+ pie_ldflags=-static-pie
+ else
+ pie_ldflags=-pie
+ fi
+ if compile_prog "-Werror -fPIE -DPIE" "$pie_ldflags"; then
pie="yes"
elif test "$pie" = "yes"; then
error_exit "-static-pie not available due to missing toolchain support"
else
- pie="no"
- fi
-elif test "$pie" != "no"; then
- if compile_prog "-Werror -fPIE -DPIE" "-pie"; then
- pie="yes"
- elif test "$pie" = "yes"; then
- error_exit "PIE not available due to missing toolchain support"
- else
echo "Disabling PIE due to missing toolchain support"
pie="no"
fi
@@ -1139,6 +1099,18 @@
fi
fi
+#########################################
+# gdb test
+
+if test -n "$gdb_bin"; then
+ gdb_version=$($gdb_bin --version | head -n 1)
+ if version_ge ${gdb_version##* } 9.1; then
+ gdb_arches=$($python "$source_path/scripts/probe-gdb-support.py" $gdb_bin)
+ else
+ gdb_bin=""
+ fi
+fi
+
##########################################
# big/little endian test
cat > $TMPC << EOF
@@ -1166,34 +1138,6 @@
fi
fi
-########################################
-# check if ccache is interfering with
-# semantic analysis of macros
-
-unset CCACHE_CPP2
-ccache_cpp2=no
-cat > $TMPC << EOF
-static const int Z = 1;
-#define fn() ({ Z; })
-#define TAUT(X) ((X) == Z)
-#define PAREN(X, Y) (X == Y)
-#define ID(X) (X)
-int main(void)
-{
- int x = 0, y = 0;
- x = ID(x);
- x = fn();
- fn();
- if (PAREN(x, y)) return 0;
- if (TAUT(Z)) return 0;
- return 0;
-}
-EOF
-
-if ! compile_object "-Werror"; then
- ccache_cpp2=yes
-fi
-
##########################################
# functions to probe cross compilers
@@ -1337,10 +1281,6 @@
container_cross_prefix=aarch64-linux-gnu-
container_cross_cc=${container_cross_prefix}gcc
;;
- alpha)
- container_image=debian-alpha-cross
- container_cross_prefix=alpha-linux-gnu-
- ;;
arm)
# We don't have any bigendian build tools so we only use this for ARM
container_image=debian-armhf-cross
@@ -1355,10 +1295,6 @@
container_cross_prefix=hexagon-unknown-linux-musl-
container_cross_cc=${container_cross_prefix}clang
;;
- hppa)
- container_image=debian-hppa-cross
- container_cross_prefix=hppa-linux-gnu-
- ;;
i386)
container_image=fedora-i386-cross
container_cross_prefix=
@@ -1367,10 +1303,6 @@
container_image=debian-loongarch-cross
container_cross_prefix=loongarch64-unknown-linux-gnu-
;;
- m68k)
- container_image=debian-m68k-cross
- container_cross_prefix=m68k-linux-gnu-
- ;;
microblaze)
container_image=debian-microblaze-cross
container_cross_prefix=microblaze-linux-musl-
@@ -1383,14 +1315,6 @@
container_image=debian-mips64-cross
container_cross_prefix=mips64-linux-gnuabi64-
;;
- mipsel)
- container_image=debian-mipsel-cross
- container_cross_prefix=mipsel-linux-gnu-
- ;;
- mips)
- container_image=debian-mips-cross
- container_cross_prefix=mips-linux-gnu-
- ;;
nios2)
container_image=debian-nios2-cross
container_cross_prefix=nios2-linux-gnu-
@@ -1405,22 +1329,6 @@
container_cross_prefix=powerpc${target_arch#ppc}-linux-gnu-
container_cross_cc=${container_cross_prefix}gcc-10
;;
- riscv64)
- container_image=debian-riscv64-test-cross
- container_cross_prefix=riscv64-linux-gnu-
- ;;
- s390x)
- container_image=debian-s390x-cross
- container_cross_prefix=s390x-linux-gnu-
- ;;
- sh4)
- container_image=debian-sh4-cross
- container_cross_prefix=sh4-linux-gnu-
- ;;
- sparc64)
- container_image=debian-sparc64-cross
- container_cross_prefix=sparc64-linux-gnu-
- ;;
tricore)
container_image=debian-tricore-cross
container_cross_prefix=tricore-
@@ -1435,6 +1343,11 @@
# default to the dc232b cpu
container_cross_prefix=/opt/2020.07/xtensa-dc232b-elf/bin/xtensa-dc232b-elf-
;;
+ *)
+ # Debian and GNU architecture names usually match
+ container_image=debian-$target_arch-cross
+ container_cross_prefix=$target_arch-linux-gnu-
+ ;;
esac
: ${container_cross_cc:=${container_cross_prefix}gcc}
: ${container_cross_ar:=${container_cross_prefix}ar}
@@ -1679,25 +1592,9 @@
echo all: >> $config_host_mak
-if test "$targetos" = "windows"; then
- echo "QEMU_GA_MANUFACTURER=${QEMU_GA_MANUFACTURER-QEMU}" >> $config_host_mak
- echo "QEMU_GA_DISTRO=${QEMU_GA_DISTRO-Linux}" >> $config_host_mak
- echo "QEMU_GA_VERSION=${QEMU_GA_VERSION-$(cat "$source_path"/VERSION)}" >> $config_host_mak
-fi
-
echo "SRC_PATH=$source_path" >> $config_host_mak
echo "TARGET_DIRS=$target_list" >> $config_host_mak
-
-if test -n "$gdb_bin"; then
- gdb_version=$($gdb_bin --version | head -n 1)
- if version_ge ${gdb_version##* } 9.1; then
- echo "HAVE_GDB_BIN=$gdb_bin" >> $config_host_mak
- gdb_arches=$($python "$source_path/scripts/probe-gdb-support.py" $gdb_bin)
- else
- gdb_bin=""
- fi
-fi
-
+echo "GDB=$gdb_bin" >> $config_host_mak
if test "$container" != no; then
echo "RUNC=$runc" >> $config_host_mak
fi
@@ -1726,10 +1623,6 @@
echo "CONFIG_DEFAULT_TARGETS=y" >> $config_host_mak
fi
-if test "$ccache_cpp2" = "yes"; then
- echo "export CCACHE_CPP2=y" >> $config_host_mak
-fi
-
# contrib/plugins configuration
echo "# Automatically generated by configure - do not modify" > contrib/plugins/$config_host_mak
echo "SRC_PATH=$source_path/contrib/plugins" >> contrib/plugins/$config_host_mak
@@ -1746,14 +1639,6 @@
echo "# Automatically generated by configure - do not modify" > $config_host_mak
echo "SRC_PATH=$source_path" >> $config_host_mak
-# versioned checked in the main config_host.mak above
-if test -n "$gdb_bin"; then
- echo "HAVE_GDB_BIN=$gdb_bin" >> $config_host_mak
-fi
-if test "$plugins" = "yes" ; then
- echo "CONFIG_PLUGIN=y" >> $config_host_mak
-fi
-
tcg_tests_targets=
for target in $target_list; do
arch=${target%%-*}
@@ -1786,7 +1671,7 @@
# will GDB work with these binaries?
if test "${gdb_arches#*$arch}" != "$gdb_arches"; then
- echo "HOST_GDB_SUPPORTS_ARCH=y" >> "$config_target_mak"
+ echo "GDB=$gdb_bin" >> $config_target_mak
fi
echo "run-tcg-tests-$target: $qemu\$(EXESUF)" >> Makefile.prereqs
@@ -1821,6 +1706,29 @@
test -n "$objcc" && echo "objc_args = [$(meson_quote $OBJCFLAGS $EXTRA_OBJCFLAGS)]" >> $cross
echo "c_link_args = [$(meson_quote $CFLAGS $LDFLAGS $EXTRA_CFLAGS $EXTRA_LDFLAGS)]" >> $cross
echo "cpp_link_args = [$(meson_quote $CXXFLAGS $LDFLAGS $EXTRA_CXXFLAGS $EXTRA_LDFLAGS)]" >> $cross
+
+ # Only enable by default for git builds and on select OSes
+ echo "# environment defaults, can still be overridden on " >> $cross
+ echo "# the command line" >> $cross
+ if test -e "$source_path/.git" && \
+ { test "$targetos" = linux || test "$targetos" = "windows"; }; then
+ echo 'werror = true' >> $cross
+ fi
+ echo "[project options]" >> $cross
+ if test "$SMBD" != ''; then
+ echo "smbd = $(meson_quote "$SMBD")" >> $cross
+ fi
+ if test "${QEMU_GA_MANUFACTURER}" != ''; then
+ echo "qemu_ga_manufacturer = $(meson_quote "${QEMU_GA_MANUFACTURER}")" >> $cross
+ fi
+ if test "${QEMU_GA_DISTRO}" != ''; then
+ echo "qemu_ga_distro = $(meson_quote "${QEMU_GA_DISTRO}")" >> $cross
+ fi
+ if test "${QEMU_GA_VERSION}" != ''; then
+ echo "qemu_ga_version = $(meson_quote "${QEMU_GA_VERSION}")" >> $cross
+ fi
+
+ echo >> $cross
echo "[binaries]" >> $cross
echo "c = [$(meson_quote $cc $CPU_CFLAGS)]" >> $cross
test -n "$cxx" && echo "cpp = [$(meson_quote $cxx $CPU_CFLAGS)]" >> $cross
@@ -1828,6 +1736,7 @@
echo "ar = [$(meson_quote $ar)]" >> $cross
echo "nm = [$(meson_quote $nm)]" >> $cross
echo "pkgconfig = [$(meson_quote $pkg_config)]" >> $cross
+ echo "pkg-config = [$(meson_quote $pkg_config)]" >> $cross
echo "ranlib = [$(meson_quote $ranlib)]" >> $cross
if has $sdl2_config; then
echo "sdl2-config = [$(meson_quote $sdl2_config)]" >> $cross
@@ -1853,39 +1762,36 @@
else
echo "endian = 'little'" >> $cross
fi
- cross_arg="--cross-file config-meson.cross"
native="config-meson.native.new"
echo "# Automatically generated by configure - do not modify" > $native
echo "[binaries]" >> $native
echo "c = [$(meson_quote $host_cc)]" >> $native
mv $native config-meson.native
- cross_arg="$cross_arg --native-file config-meson.native"
- else
- cross_arg="--native-file config-meson.cross"
+ meson_option_add --native-file
+ meson_option_add config-meson.native
fi
mv $cross config-meson.cross
+ meson_add_machine_file config-meson.cross
+ if test -f "$source_path/configs/meson/$targetos.txt"; then
+ meson_add_machine_file $source_path/configs/meson/$targetos.txt
+ fi
rm -rf meson-private meson-info meson-logs
- # Built-in options
test "$download" = "disabled" && meson_option_add "--wrap-mode=nodownload"
- test "$bindir" != "bin" && meson_option_add "-Dbindir=$bindir"
test "$default_feature" = no && meson_option_add -Dauto_features=disabled
test "$static" = yes && meson_option_add -Dprefer_static=true
test "$pie" = no && meson_option_add -Db_pie=false
- test "$werror" = yes && meson_option_add -Dwerror=true
# QEMU options
- test "$cfi" != false && meson_option_add "-Dcfi=$cfi"
+ test "$cfi" != false && meson_option_add "-Dcfi=$cfi" "-Db_lto=$cfi"
test "$docs" != auto && meson_option_add "-Ddocs=$docs"
test -n "${LIB_FUZZING_ENGINE+xxx}" && meson_option_add "-Dfuzzing_engine=$LIB_FUZZING_ENGINE"
test "$plugins" = yes && meson_option_add "-Dplugins=true"
- test "$qemu_suffix" != qemu && meson_option_add "-Dqemu_suffix=$qemu_suffix"
- test "$smbd" != '' && meson_option_add "-Dsmbd=$smbd"
test "$tcg" != enabled && meson_option_add "-Dtcg=$tcg"
run_meson() {
- NINJA=$ninja $meson setup --prefix "$prefix" "$@" $cross_arg "$PWD" "$source_path"
+ NINJA=$ninja $meson setup "$@" "$PWD" "$source_path"
}
eval run_meson $meson_options
if test "$?" -ne 0 ; then
diff --git a/docs/sphinx/hxtool.py b/docs/sphinx/hxtool.py
index fb0649a..9f6b9d8 100644
--- a/docs/sphinx/hxtool.py
+++ b/docs/sphinx/hxtool.py
@@ -49,7 +49,7 @@ def serror(file, lnum, errtext):
def parse_directive(line):
"""Return first word of line, if any"""
- return re.split('\W', line)[0]
+ return re.split(r'\W', line)[0]
def parse_defheading(file, lnum, line):
"""Handle a DEFHEADING directive"""
diff --git a/hw/arm/meson.build b/hw/arm/meson.build
index 11eb911..a6feaf1 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -64,7 +64,6 @@
arm_ss.add(when: 'CONFIG_FSL_IMX6UL', if_true: files('fsl-imx6ul.c', 'mcimx6ul-evk.c'))
arm_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_soc.c'))
arm_ss.add(when: 'CONFIG_XEN', if_true: files('xen_arm.c'))
-arm_ss.add_all(xen_ss)
system_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c'))
system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4_boards.c'))
diff --git a/hw/core/machine.c b/hw/core/machine.c
index cfd1edf..05aef2c 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -34,6 +34,8 @@
GlobalProperty hw_compat_8_1[] = {
{ TYPE_PCI_BRIDGE, "x-pci-express-writeable-slt-bug", "true" },
+ { "ramfb", "x-migrate", "off" },
+ { "vfio-pci-nohotplug", "x-ramfb-migrate", "off" }
};
const size_t hw_compat_8_1_len = G_N_ELEMENTS(hw_compat_8_1);
diff --git a/hw/display/ramfb-standalone.c b/hw/display/ramfb-standalone.c
index 8c00943..a96e7eb 100644
--- a/hw/display/ramfb-standalone.c
+++ b/hw/display/ramfb-standalone.c
@@ -1,4 +1,5 @@
#include "qemu/osdep.h"
+#include "migration/vmstate.h"
#include "qapi/error.h"
#include "qemu/module.h"
#include "hw/loader.h"
@@ -15,6 +16,7 @@
SysBusDevice parent_obj;
QemuConsole *con;
RAMFBState *state;
+ bool migrate;
};
static void display_update_wrapper(void *dev)
@@ -40,14 +42,39 @@
ramfb->state = ramfb_setup(errp);
}
+static bool migrate_needed(void *opaque)
+{
+ RAMFBStandaloneState *ramfb = RAMFB(opaque);
+
+ return ramfb->migrate;
+}
+
+static const VMStateDescription ramfb_dev_vmstate = {
+ .name = "ramfb-dev",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = migrate_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_STRUCT_POINTER(state, RAMFBStandaloneState, ramfb_vmstate, RAMFBState),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static Property ramfb_properties[] = {
+ DEFINE_PROP_BOOL("x-migrate", RAMFBStandaloneState, migrate, true),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
static void ramfb_class_initfn(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
+ dc->vmsd = &ramfb_dev_vmstate;
dc->realize = ramfb_realizefn;
dc->desc = "ram framebuffer standalone device";
dc->user_creatable = true;
+ device_class_set_props(dc, ramfb_properties);
}
static const TypeInfo ramfb_info = {
diff --git a/hw/display/ramfb.c b/hw/display/ramfb.c
index c2b002d..477ef72 100644
--- a/hw/display/ramfb.c
+++ b/hw/display/ramfb.c
@@ -28,6 +28,8 @@
uint32_t stride;
};
+typedef struct RAMFBCfg RAMFBCfg;
+
struct RAMFBState {
DisplaySurface *ds;
uint32_t width, height;
@@ -116,6 +118,23 @@
dpy_gfx_update_full(con);
}
+static int ramfb_post_load(void *opaque, int version_id)
+{
+ ramfb_fw_cfg_write(opaque, 0, 0);
+ return 0;
+}
+
+const VMStateDescription ramfb_vmstate = {
+ .name = "ramfb",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .post_load = ramfb_post_load,
+ .fields = (VMStateField[]) {
+ VMSTATE_BUFFER_UNSAFE(cfg, RAMFBState, 0, sizeof(RAMFBCfg)),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
RAMFBState *ramfb_setup(Error **errp)
{
FWCfgState *fw_cfg = fw_cfg_find();
diff --git a/hw/i386/meson.build b/hw/i386/meson.build
index ff87906..369c6bf 100644
--- a/hw/i386/meson.build
+++ b/hw/i386/meson.build
@@ -32,6 +32,5 @@
subdir('xen')
i386_ss.add_all(xenpv_ss)
-i386_ss.add_all(xen_ss)
hw_arch += {'i386': i386_ss}
diff --git a/hw/remote/meson.build b/hw/remote/meson.build
index a1e8708..a3aa29a 100644
--- a/hw/remote/meson.build
+++ b/hw/remote/meson.build
@@ -7,9 +7,11 @@
remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c'))
remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iommu.c'))
-remote_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_true: files('vfio-user-obj.c'))
remote_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_true: libvfio_user_dep)
+remote_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_true: files('vfio-user-obj.c'),
+ if_false: files('vfio-user-obj-stub.c'))
+remote_ss.add(when: 'CONFIG_ALL', if_true: files('vfio-user-obj-stub.c'))
specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c'))
diff --git a/stubs/vfio-user-obj.c b/hw/remote/vfio-user-obj-stub.c
similarity index 100%
rename from stubs/vfio-user-obj.c
rename to hw/remote/vfio-user-obj-stub.c
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
index 6e21d1d..5f257bf 100644
--- a/hw/vfio/ap.c
+++ b/hw/vfio/ap.c
@@ -53,40 +53,6 @@
.vfio_compute_needs_reset = vfio_ap_compute_needs_reset,
};
-static void vfio_ap_put_device(VFIOAPDevice *vapdev)
-{
- g_free(vapdev->vdev.name);
- vfio_put_base_device(&vapdev->vdev);
-}
-
-static VFIOGroup *vfio_ap_get_group(VFIOAPDevice *vapdev, Error **errp)
-{
- GError *gerror = NULL;
- char *symlink, *group_path;
- int groupid;
-
- symlink = g_strdup_printf("%s/iommu_group", vapdev->vdev.sysfsdev);
- group_path = g_file_read_link(symlink, &gerror);
- g_free(symlink);
-
- if (!group_path) {
- error_setg(errp, "%s: no iommu_group found for %s: %s",
- TYPE_VFIO_AP_DEVICE, vapdev->vdev.sysfsdev, gerror->message);
- g_error_free(gerror);
- return NULL;
- }
-
- if (sscanf(basename(group_path), "%d", &groupid) != 1) {
- error_setg(errp, "vfio: failed to read %s", group_path);
- g_free(group_path);
- return NULL;
- }
-
- g_free(group_path);
-
- return vfio_get_group(groupid, &address_space_memory, errp);
-}
-
static void vfio_ap_req_notifier_handler(void *opaque)
{
VFIOAPDevice *vapdev = opaque;
@@ -189,22 +155,14 @@
static void vfio_ap_realize(DeviceState *dev, Error **errp)
{
int ret;
- char *mdevid;
Error *err = NULL;
- VFIOGroup *vfio_group;
- APDevice *apdev = AP_DEVICE(dev);
- VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
+ VFIOAPDevice *vapdev = VFIO_AP_DEVICE(dev);
+ VFIODevice *vbasedev = &vapdev->vdev;
- vfio_group = vfio_ap_get_group(vapdev, errp);
- if (!vfio_group) {
- return;
- }
-
- vapdev->vdev.ops = &vfio_ap_ops;
- vapdev->vdev.type = VFIO_DEVICE_TYPE_AP;
- mdevid = basename(vapdev->vdev.sysfsdev);
- vapdev->vdev.name = g_strdup_printf("%s", mdevid);
- vapdev->vdev.dev = dev;
+ vbasedev->name = g_path_get_basename(vbasedev->sysfsdev);
+ vbasedev->ops = &vfio_ap_ops;
+ vbasedev->type = VFIO_DEVICE_TYPE_AP;
+ vbasedev->dev = dev;
/*
* vfio-ap devices operate in a way compatible with discarding of
@@ -214,9 +172,10 @@
*/
vapdev->vdev.ram_block_discard_allowed = true;
- ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp);
+ ret = vfio_attach_device(vbasedev->name, vbasedev,
+ &address_space_memory, errp);
if (ret) {
- goto out_get_dev_err;
+ goto error;
}
vfio_ap_register_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX, &err);
@@ -230,20 +189,18 @@
return;
-out_get_dev_err:
- vfio_ap_put_device(vapdev);
- vfio_put_group(vfio_group);
+error:
+ error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name);
+ g_free(vbasedev->name);
}
static void vfio_ap_unrealize(DeviceState *dev)
{
- APDevice *apdev = AP_DEVICE(dev);
- VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
- VFIOGroup *group = vapdev->vdev.group;
+ VFIOAPDevice *vapdev = VFIO_AP_DEVICE(dev);
vfio_ap_unregister_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX);
- vfio_ap_put_device(vapdev);
- vfio_put_group(group);
+ vfio_detach_device(&vapdev->vdev);
+ g_free(vapdev->vdev.name);
}
static Property vfio_ap_properties[] = {
@@ -254,8 +211,7 @@
static void vfio_ap_reset(DeviceState *dev)
{
int ret;
- APDevice *apdev = AP_DEVICE(dev);
- VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
+ VFIOAPDevice *vapdev = VFIO_AP_DEVICE(dev);
ret = ioctl(vapdev->vdev.fd, VFIO_DEVICE_RESET);
if (ret) {
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index 1e2fce8..6623ae2 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -572,88 +572,14 @@
g_free(vcdev->io_region);
}
-static void vfio_ccw_put_device(VFIOCCWDevice *vcdev)
-{
- g_free(vcdev->vdev.name);
- vfio_put_base_device(&vcdev->vdev);
-}
-
-static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev,
- Error **errp)
-{
- S390CCWDevice *cdev = S390_CCW_DEVICE(vcdev);
- char *name = g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid,
- cdev->hostid.ssid,
- cdev->hostid.devid);
- VFIODevice *vbasedev;
-
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (strcmp(vbasedev->name, name) == 0) {
- error_setg(errp, "vfio: subchannel %s has already been attached",
- name);
- goto out_err;
- }
- }
-
- /*
- * All vfio-ccw devices are believed to operate in a way compatible with
- * discarding of memory in RAM blocks, ie. pages pinned in the host are
- * in the current working set of the guest driver and therefore never
- * overlap e.g., with pages available to the guest balloon driver. This
- * needs to be set before vfio_get_device() for vfio common to handle
- * ram_block_discard_disable().
- */
- vcdev->vdev.ram_block_discard_allowed = true;
-
- if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, errp)) {
- goto out_err;
- }
-
- vcdev->vdev.ops = &vfio_ccw_ops;
- vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW;
- vcdev->vdev.name = name;
- vcdev->vdev.dev = DEVICE(vcdev);
-
- return;
-
-out_err:
- g_free(name);
-}
-
-static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp)
-{
- char *tmp, group_path[PATH_MAX];
- ssize_t len;
- int groupid;
-
- tmp = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/%s/iommu_group",
- cdev->hostid.cssid, cdev->hostid.ssid,
- cdev->hostid.devid, cdev->mdevid);
- len = readlink(tmp, group_path, sizeof(group_path));
- g_free(tmp);
-
- if (len <= 0 || len >= sizeof(group_path)) {
- error_setg(errp, "vfio: no iommu_group found");
- return NULL;
- }
-
- group_path[len] = 0;
-
- if (sscanf(basename(group_path), "%d", &groupid) != 1) {
- error_setg(errp, "vfio: failed to read %s", group_path);
- return NULL;
- }
-
- return vfio_get_group(groupid, &address_space_memory, errp);
-}
-
static void vfio_ccw_realize(DeviceState *dev, Error **errp)
{
- VFIOGroup *group;
S390CCWDevice *cdev = S390_CCW_DEVICE(dev);
VFIOCCWDevice *vcdev = VFIO_CCW(cdev);
S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev);
+ VFIODevice *vbasedev = &vcdev->vdev;
Error *err = NULL;
+ int ret;
/* Call the class init function for subchannel. */
if (cdc->realize) {
@@ -663,14 +589,27 @@
}
}
- group = vfio_ccw_get_group(cdev, &err);
- if (!group) {
- goto out_group_err;
- }
+ vbasedev->ops = &vfio_ccw_ops;
+ vbasedev->type = VFIO_DEVICE_TYPE_CCW;
+ vbasedev->name = g_strdup_printf("%x.%x.%04x", vcdev->cdev.hostid.cssid,
+ vcdev->cdev.hostid.ssid,
+ vcdev->cdev.hostid.devid);
+ vbasedev->dev = dev;
- vfio_ccw_get_device(group, vcdev, &err);
- if (err) {
- goto out_device_err;
+ /*
+ * All vfio-ccw devices are believed to operate in a way compatible with
+ * discarding of memory in RAM blocks, ie. pages pinned in the host are
+ * in the current working set of the guest driver and therefore never
+ * overlap e.g., with pages available to the guest balloon driver. This
+ * needs to be set before vfio_get_device() for vfio common to handle
+ * ram_block_discard_disable().
+ */
+ vbasedev->ram_block_discard_allowed = true;
+
+ ret = vfio_attach_device(cdev->mdevid, vbasedev,
+ &address_space_memory, errp);
+ if (ret) {
+ goto out_attach_dev_err;
}
vfio_ccw_get_region(vcdev, &err);
@@ -708,10 +647,9 @@
out_io_notifier_err:
vfio_ccw_put_region(vcdev);
out_region_err:
- vfio_ccw_put_device(vcdev);
-out_device_err:
- vfio_put_group(group);
-out_group_err:
+ vfio_detach_device(vbasedev);
+out_attach_dev_err:
+ g_free(vbasedev->name);
if (cdc->unrealize) {
cdc->unrealize(cdev);
}
@@ -724,14 +662,13 @@
S390CCWDevice *cdev = S390_CCW_DEVICE(dev);
VFIOCCWDevice *vcdev = VFIO_CCW(cdev);
S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev);
- VFIOGroup *group = vcdev->vdev.group;
vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_REQ_IRQ_INDEX);
vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_CRW_IRQ_INDEX);
vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_IO_IRQ_INDEX);
vfio_ccw_put_region(vcdev);
- vfio_ccw_put_device(vcdev);
- vfio_put_group(group);
+ vfio_detach_device(&vcdev->vdev);
+ g_free(vcdev->vdev.name);
if (cdc->unrealize) {
cdc->unrealize(cdev);
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 1346492..5ff5acf 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -46,8 +46,8 @@
#include "migration/qemu-file.h"
#include "sysemu/tpm.h"
-VFIOGroupList vfio_group_list =
- QLIST_HEAD_INITIALIZER(vfio_group_list);
+VFIODeviceList vfio_device_list =
+ QLIST_HEAD_INITIALIZER(vfio_device_list);
static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces =
QLIST_HEAD_INITIALIZER(vfio_address_spaces);
@@ -59,304 +59,24 @@
* initialized, this file descriptor is only released on QEMU exit and
* we'll re-use it should another vfio device be attached before then.
*/
-static int vfio_kvm_device_fd = -1;
+int vfio_kvm_device_fd = -1;
#endif
/*
- * Common VFIO interrupt disable
- */
-void vfio_disable_irqindex(VFIODevice *vbasedev, int index)
-{
- struct vfio_irq_set irq_set = {
- .argsz = sizeof(irq_set),
- .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
- .index = index,
- .start = 0,
- .count = 0,
- };
-
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
-}
-
-void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
-{
- struct vfio_irq_set irq_set = {
- .argsz = sizeof(irq_set),
- .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
- .index = index,
- .start = 0,
- .count = 1,
- };
-
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
-}
-
-void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
-{
- struct vfio_irq_set irq_set = {
- .argsz = sizeof(irq_set),
- .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
- .index = index,
- .start = 0,
- .count = 1,
- };
-
- ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
-}
-
-static inline const char *action_to_str(int action)
-{
- switch (action) {
- case VFIO_IRQ_SET_ACTION_MASK:
- return "MASK";
- case VFIO_IRQ_SET_ACTION_UNMASK:
- return "UNMASK";
- case VFIO_IRQ_SET_ACTION_TRIGGER:
- return "TRIGGER";
- default:
- return "UNKNOWN ACTION";
- }
-}
-
-static const char *index_to_str(VFIODevice *vbasedev, int index)
-{
- if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) {
- return NULL;
- }
-
- switch (index) {
- case VFIO_PCI_INTX_IRQ_INDEX:
- return "INTX";
- case VFIO_PCI_MSI_IRQ_INDEX:
- return "MSI";
- case VFIO_PCI_MSIX_IRQ_INDEX:
- return "MSIX";
- case VFIO_PCI_ERR_IRQ_INDEX:
- return "ERR";
- case VFIO_PCI_REQ_IRQ_INDEX:
- return "REQ";
- default:
- return NULL;
- }
-}
-
-static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state)
-{
- switch (container->iommu_type) {
- case VFIO_TYPE1v2_IOMMU:
- case VFIO_TYPE1_IOMMU:
- /*
- * We support coordinated discarding of RAM via the RamDiscardManager.
- */
- return ram_block_uncoordinated_discard_disable(state);
- default:
- /*
- * VFIO_SPAPR_TCE_IOMMU most probably works just fine with
- * RamDiscardManager, however, it is completely untested.
- *
- * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does
- * completely the opposite of managing mapping/pinning dynamically as
- * required by RamDiscardManager. We would have to special-case sections
- * with a RamDiscardManager.
- */
- return ram_block_discard_disable(state);
- }
-}
-
-int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
- int action, int fd, Error **errp)
-{
- struct vfio_irq_set *irq_set;
- int argsz, ret = 0;
- const char *name;
- int32_t *pfd;
-
- argsz = sizeof(*irq_set) + sizeof(*pfd);
-
- irq_set = g_malloc0(argsz);
- irq_set->argsz = argsz;
- irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | action;
- irq_set->index = index;
- irq_set->start = subindex;
- irq_set->count = 1;
- pfd = (int32_t *)&irq_set->data;
- *pfd = fd;
-
- if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
- ret = -errno;
- }
- g_free(irq_set);
-
- if (!ret) {
- return 0;
- }
-
- error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure");
-
- name = index_to_str(vbasedev, index);
- if (name) {
- error_prepend(errp, "%s-%d: ", name, subindex);
- } else {
- error_prepend(errp, "index %d-%d: ", index, subindex);
- }
- error_prepend(errp,
- "Failed to %s %s eventfd signaling for interrupt ",
- fd < 0 ? "tear down" : "set up", action_to_str(action));
- return ret;
-}
-
-/*
- * IO Port/MMIO - Beware of the endians, VFIO is always little endian
- */
-void vfio_region_write(void *opaque, hwaddr addr,
- uint64_t data, unsigned size)
-{
- VFIORegion *region = opaque;
- VFIODevice *vbasedev = region->vbasedev;
- union {
- uint8_t byte;
- uint16_t word;
- uint32_t dword;
- uint64_t qword;
- } buf;
-
- switch (size) {
- case 1:
- buf.byte = data;
- break;
- case 2:
- buf.word = cpu_to_le16(data);
- break;
- case 4:
- buf.dword = cpu_to_le32(data);
- break;
- case 8:
- buf.qword = cpu_to_le64(data);
- break;
- default:
- hw_error("vfio: unsupported write size, %u bytes", size);
- break;
- }
-
- if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
- error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
- ",%d) failed: %m",
- __func__, vbasedev->name, region->nr,
- addr, data, size);
- }
-
- trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
-
- /*
- * A read or write to a BAR always signals an INTx EOI. This will
- * do nothing if not pending (including not in INTx mode). We assume
- * that a BAR access is in response to an interrupt and that BAR
- * accesses will service the interrupt. Unfortunately, we don't know
- * which access will service the interrupt, so we're potentially
- * getting quite a few host interrupts per guest interrupt.
- */
- vbasedev->ops->vfio_eoi(vbasedev);
-}
-
-uint64_t vfio_region_read(void *opaque,
- hwaddr addr, unsigned size)
-{
- VFIORegion *region = opaque;
- VFIODevice *vbasedev = region->vbasedev;
- union {
- uint8_t byte;
- uint16_t word;
- uint32_t dword;
- uint64_t qword;
- } buf;
- uint64_t data = 0;
-
- if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
- error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
- __func__, vbasedev->name, region->nr,
- addr, size);
- return (uint64_t)-1;
- }
- switch (size) {
- case 1:
- data = buf.byte;
- break;
- case 2:
- data = le16_to_cpu(buf.word);
- break;
- case 4:
- data = le32_to_cpu(buf.dword);
- break;
- case 8:
- data = le64_to_cpu(buf.qword);
- break;
- default:
- hw_error("vfio: unsupported read size, %u bytes", size);
- break;
- }
-
- trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data);
-
- /* Same as write above */
- vbasedev->ops->vfio_eoi(vbasedev);
-
- return data;
-}
-
-const MemoryRegionOps vfio_region_ops = {
- .read = vfio_region_read,
- .write = vfio_region_write,
- .endianness = DEVICE_LITTLE_ENDIAN,
- .valid = {
- .min_access_size = 1,
- .max_access_size = 8,
- },
- .impl = {
- .min_access_size = 1,
- .max_access_size = 8,
- },
-};
-
-/*
* Device state interfaces
*/
-typedef struct {
- unsigned long *bitmap;
- hwaddr size;
- hwaddr pages;
-} VFIOBitmap;
-
-static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size)
-{
- vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size();
- vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) /
- BITS_PER_BYTE;
- vbmap->bitmap = g_try_malloc0(vbmap->size);
- if (!vbmap->bitmap) {
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
- uint64_t size, ram_addr_t ram_addr);
-
bool vfio_mig_active(void)
{
- VFIOGroup *group;
VFIODevice *vbasedev;
- if (QLIST_EMPTY(&vfio_group_list)) {
+ if (QLIST_EMPTY(&vfio_device_list)) {
return false;
}
- QLIST_FOREACH(group, &vfio_group_list, next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (vbasedev->migration_blocker) {
- return false;
- }
+ QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ if (vbasedev->migration_blocker) {
+ return false;
}
}
return true;
@@ -371,19 +91,16 @@
*/
static bool vfio_multiple_devices_migration_is_supported(void)
{
- VFIOGroup *group;
VFIODevice *vbasedev;
unsigned int device_num = 0;
bool all_support_p2p = true;
- QLIST_FOREACH(group, &vfio_group_list, next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (vbasedev->migration) {
- device_num++;
+ QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ if (vbasedev->migration) {
+ device_num++;
- if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) {
- all_support_p2p = false;
- }
+ if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) {
+ all_support_p2p = false;
}
}
}
@@ -435,7 +152,7 @@
bool vfio_viommu_preset(VFIODevice *vbasedev)
{
- return vbasedev->group->container->space->as != &address_space_memory;
+ return vbasedev->container->space->as != &address_space_memory;
}
static void vfio_set_migration_error(int err)
@@ -469,7 +186,6 @@
static bool vfio_devices_all_dirty_tracking(VFIOContainer *container)
{
- VFIOGroup *group;
VFIODevice *vbasedev;
MigrationState *ms = migrate_get_current();
@@ -478,34 +194,29 @@
return false;
}
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- VFIOMigration *migration = vbasedev->migration;
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ VFIOMigration *migration = vbasedev->migration;
- if (!migration) {
- return false;
- }
+ if (!migration) {
+ return false;
+ }
- if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF &&
- (vfio_device_state_is_running(vbasedev) ||
- vfio_device_state_is_precopy(vbasedev))) {
- return false;
- }
+ if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF &&
+ (vfio_device_state_is_running(vbasedev) ||
+ vfio_device_state_is_precopy(vbasedev))) {
+ return false;
}
}
return true;
}
-static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container)
+bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container)
{
- VFIOGroup *group;
VFIODevice *vbasedev;
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (!vbasedev->dirty_pages_supported) {
- return false;
- }
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ if (!vbasedev->dirty_pages_supported) {
+ return false;
}
}
@@ -516,178 +227,33 @@
* Check if all VFIO devices are running and migration is active, which is
* essentially equivalent to the migration being in pre-copy phase.
*/
-static bool vfio_devices_all_running_and_mig_active(VFIOContainer *container)
+bool vfio_devices_all_running_and_mig_active(VFIOContainer *container)
{
- VFIOGroup *group;
VFIODevice *vbasedev;
if (!migration_is_active(migrate_get_current())) {
return false;
}
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- VFIOMigration *migration = vbasedev->migration;
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ VFIOMigration *migration = vbasedev->migration;
- if (!migration) {
- return false;
- }
+ if (!migration) {
+ return false;
+ }
- if (vfio_device_state_is_running(vbasedev) ||
- vfio_device_state_is_precopy(vbasedev)) {
- continue;
- } else {
- return false;
- }
+ if (vfio_device_state_is_running(vbasedev) ||
+ vfio_device_state_is_precopy(vbasedev)) {
+ continue;
+ } else {
+ return false;
}
}
return true;
}
-static int vfio_dma_unmap_bitmap(VFIOContainer *container,
- hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
-{
- struct vfio_iommu_type1_dma_unmap *unmap;
- struct vfio_bitmap *bitmap;
- VFIOBitmap vbmap;
- int ret;
-
- ret = vfio_bitmap_alloc(&vbmap, size);
- if (ret) {
- return ret;
- }
-
- unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap));
-
- unmap->argsz = sizeof(*unmap) + sizeof(*bitmap);
- unmap->iova = iova;
- unmap->size = size;
- unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP;
- bitmap = (struct vfio_bitmap *)&unmap->data;
-
- /*
- * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
- * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize
- * to qemu_real_host_page_size.
- */
- bitmap->pgsize = qemu_real_host_page_size();
- bitmap->size = vbmap.size;
- bitmap->data = (__u64 *)vbmap.bitmap;
-
- if (vbmap.size > container->max_dirty_bitmap_size) {
- error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size);
- ret = -E2BIG;
- goto unmap_exit;
- }
-
- ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
- if (!ret) {
- cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap,
- iotlb->translated_addr, vbmap.pages);
- } else {
- error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m");
- }
-
-unmap_exit:
- g_free(unmap);
- g_free(vbmap.bitmap);
-
- return ret;
-}
-
-/*
- * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
- */
-static int vfio_dma_unmap(VFIOContainer *container,
- hwaddr iova, ram_addr_t size,
- IOMMUTLBEntry *iotlb)
-{
- struct vfio_iommu_type1_dma_unmap unmap = {
- .argsz = sizeof(unmap),
- .flags = 0,
- .iova = iova,
- .size = size,
- };
- bool need_dirty_sync = false;
- int ret;
-
- if (iotlb && vfio_devices_all_running_and_mig_active(container)) {
- if (!vfio_devices_all_device_dirty_tracking(container) &&
- container->dirty_pages_supported) {
- return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
- }
-
- need_dirty_sync = true;
- }
-
- while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
- /*
- * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
- * v4.15) where an overflow in its wrap-around check prevents us from
- * unmapping the last page of the address space. Test for the error
- * condition and re-try the unmap excluding the last page. The
- * expectation is that we've never mapped the last page anyway and this
- * unmap request comes via vIOMMU support which also makes it unlikely
- * that this page is used. This bug was introduced well after type1 v2
- * support was introduced, so we shouldn't need to test for v1. A fix
- * is queued for kernel v5.0 so this workaround can be removed once
- * affected kernels are sufficiently deprecated.
- */
- if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) &&
- container->iommu_type == VFIO_TYPE1v2_IOMMU) {
- trace_vfio_dma_unmap_overflow_workaround();
- unmap.size -= 1ULL << ctz64(container->pgsizes);
- continue;
- }
- error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno));
- return -errno;
- }
-
- if (need_dirty_sync) {
- ret = vfio_get_dirty_bitmap(container, iova, size,
- iotlb->translated_addr);
- if (ret) {
- return ret;
- }
- }
-
- return 0;
-}
-
-static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
- ram_addr_t size, void *vaddr, bool readonly)
-{
- struct vfio_iommu_type1_dma_map map = {
- .argsz = sizeof(map),
- .flags = VFIO_DMA_MAP_FLAG_READ,
- .vaddr = (__u64)(uintptr_t)vaddr,
- .iova = iova,
- .size = size,
- };
-
- if (!readonly) {
- map.flags |= VFIO_DMA_MAP_FLAG_WRITE;
- }
-
- /*
- * Try the mapping, if it fails with EBUSY, unmap the region and try
- * again. This shouldn't be necessary, but we sometimes see it in
- * the VGA ROM space.
- */
- if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
- (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 &&
- ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
- return 0;
- }
-
- error_report("VFIO_MAP_DMA failed: %s", strerror(errno));
- return -errno;
-}
-
-static void vfio_host_win_add(VFIOContainer *container,
- hwaddr min_iova, hwaddr max_iova,
- uint64_t iova_pgsizes)
+void vfio_host_win_add(VFIOContainer *container, hwaddr min_iova,
+ hwaddr max_iova, uint64_t iova_pgsizes)
{
VFIOHostDMAWindow *hostwin;
@@ -708,8 +274,8 @@
QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next);
}
-static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova,
- hwaddr max_iova)
+int vfio_host_win_del(VFIOContainer *container,
+ hwaddr min_iova, hwaddr max_iova)
{
VFIOHostDMAWindow *hostwin;
@@ -1084,62 +650,8 @@
return;
}
- if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
- hwaddr pgsize = 0;
-
- /* For now intersections are not allowed, we may relax this later */
- QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
- if (ranges_overlap(hostwin->min_iova,
- hostwin->max_iova - hostwin->min_iova + 1,
- section->offset_within_address_space,
- int128_get64(section->size))) {
- error_setg(&err,
- "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing"
- "host DMA window [0x%"PRIx64",0x%"PRIx64"]",
- section->offset_within_address_space,
- section->offset_within_address_space +
- int128_get64(section->size) - 1,
- hostwin->min_iova, hostwin->max_iova);
- goto fail;
- }
- }
-
- ret = vfio_spapr_create_window(container, section, &pgsize);
- if (ret) {
- error_setg_errno(&err, -ret, "Failed to create SPAPR window");
- goto fail;
- }
-
- vfio_host_win_add(container, section->offset_within_address_space,
- section->offset_within_address_space +
- int128_get64(section->size) - 1, pgsize);
-#ifdef CONFIG_KVM
- if (kvm_enabled()) {
- VFIOGroup *group;
- IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
- struct kvm_vfio_spapr_tce param;
- struct kvm_device_attr attr = {
- .group = KVM_DEV_VFIO_GROUP,
- .attr = KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE,
- .addr = (uint64_t)(unsigned long)¶m,
- };
-
- if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_FD,
- ¶m.tablefd)) {
- QLIST_FOREACH(group, &container->group_list, container_next) {
- param.groupfd = group->fd;
- if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
- error_report("vfio: failed to setup fd %d "
- "for a group with fd %d: %s",
- param.tablefd, param.groupfd,
- strerror(errno));
- return;
- }
- trace_vfio_spapr_group_attach(param.groupfd, param.tablefd);
- }
- }
- }
-#endif
+ if (vfio_container_add_section_window(container, section, &err)) {
+ goto fail;
}
hostwin = vfio_find_hostwin(container, iova, end);
@@ -1251,7 +763,7 @@
fail:
if (memory_region_is_ram_device(section->mr)) {
- error_report("failed to vfio_dma_map. pci p2p may not work");
+ error_reportf_err(err, "PCI p2p may not work: ");
return;
}
/*
@@ -1356,44 +868,7 @@
memory_region_unref(section->mr);
- if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
- vfio_spapr_remove_window(container,
- section->offset_within_address_space);
- if (vfio_host_win_del(container,
- section->offset_within_address_space,
- section->offset_within_address_space +
- int128_get64(section->size) - 1) < 0) {
- hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx,
- __func__, section->offset_within_address_space);
- }
- }
-}
-
-static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start)
-{
- int ret;
- struct vfio_iommu_type1_dirty_bitmap dirty = {
- .argsz = sizeof(dirty),
- };
-
- if (!container->dirty_pages_supported) {
- return 0;
- }
-
- if (start) {
- dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_START;
- } else {
- dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP;
- }
-
- ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty);
- if (ret) {
- ret = -errno;
- error_report("Failed to set dirty tracking flag 0x%x errno: %d",
- dirty.flags, errno);
- }
-
- return ret;
+ vfio_container_del_section_window(container, section);
}
typedef struct VFIODirtyRanges {
@@ -1416,20 +891,17 @@
{
VFIOPCIDevice *pcidev;
VFIODevice *vbasedev;
- VFIOGroup *group;
Object *owner;
owner = memory_region_owner(section->mr);
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) {
- continue;
- }
- pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
- if (OBJECT(pcidev) == owner) {
- return true;
- }
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) {
+ continue;
+ }
+ pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev);
+ if (OBJECT(pcidev) == owner) {
+ return true;
}
}
@@ -1525,24 +997,21 @@
sizeof(uint64_t))] = {};
struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
VFIODevice *vbasedev;
- VFIOGroup *group;
feature->argsz = sizeof(buf);
feature->flags = VFIO_DEVICE_FEATURE_SET |
VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP;
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (!vbasedev->dirty_tracking) {
- continue;
- }
-
- if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
- warn_report("%s: Failed to stop DMA logging, err %d (%s)",
- vbasedev->name, -errno, strerror(errno));
- }
- vbasedev->dirty_tracking = false;
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ if (!vbasedev->dirty_tracking) {
+ continue;
}
+
+ if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+ warn_report("%s: Failed to stop DMA logging, err %d (%s)",
+ vbasedev->name, -errno, strerror(errno));
+ }
+ vbasedev->dirty_tracking = false;
}
}
@@ -1625,7 +1094,6 @@
struct vfio_device_feature *feature;
VFIODirtyRanges ranges;
VFIODevice *vbasedev;
- VFIOGroup *group;
int ret = 0;
vfio_dirty_tracking_init(container, &ranges);
@@ -1635,21 +1103,19 @@
return -errno;
}
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (vbasedev->dirty_tracking) {
- continue;
- }
-
- ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
- if (ret) {
- ret = -errno;
- error_report("%s: Failed to start DMA logging, err %d (%s)",
- vbasedev->name, ret, strerror(errno));
- goto out;
- }
- vbasedev->dirty_tracking = true;
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ if (vbasedev->dirty_tracking) {
+ continue;
}
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+ if (ret) {
+ ret = -errno;
+ error_report("%s: Failed to start DMA logging, err %d (%s)",
+ vbasedev->name, ret, strerror(errno));
+ goto out;
+ }
+ vbasedev->dirty_tracking = true;
}
out:
@@ -1724,71 +1190,31 @@
return 0;
}
-static int vfio_devices_query_dirty_bitmap(VFIOContainer *container,
- VFIOBitmap *vbmap, hwaddr iova,
- hwaddr size)
+int vfio_devices_query_dirty_bitmap(VFIOContainer *container,
+ VFIOBitmap *vbmap, hwaddr iova,
+ hwaddr size)
{
VFIODevice *vbasedev;
- VFIOGroup *group;
int ret;
- QLIST_FOREACH(group, &container->group_list, container_next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- ret = vfio_device_dma_logging_report(vbasedev, iova, size,
- vbmap->bitmap);
- if (ret) {
- error_report("%s: Failed to get DMA logging report, iova: "
- "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx
- ", err: %d (%s)",
- vbasedev->name, iova, size, ret, strerror(-ret));
+ QLIST_FOREACH(vbasedev, &container->device_list, container_next) {
+ ret = vfio_device_dma_logging_report(vbasedev, iova, size,
+ vbmap->bitmap);
+ if (ret) {
+ error_report("%s: Failed to get DMA logging report, iova: "
+ "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx
+ ", err: %d (%s)",
+ vbasedev->name, iova, size, ret, strerror(-ret));
- return ret;
- }
+ return ret;
}
}
return 0;
}
-static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap,
- hwaddr iova, hwaddr size)
-{
- struct vfio_iommu_type1_dirty_bitmap *dbitmap;
- struct vfio_iommu_type1_dirty_bitmap_get *range;
- int ret;
-
- dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range));
-
- dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range);
- dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
- range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data;
- range->iova = iova;
- range->size = size;
-
- /*
- * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
- * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pgsize
- * to qemu_real_host_page_size.
- */
- range->bitmap.pgsize = qemu_real_host_page_size();
- range->bitmap.size = vbmap->size;
- range->bitmap.data = (__u64 *)vbmap->bitmap;
-
- ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap);
- if (ret) {
- ret = -errno;
- error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64
- " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova,
- (uint64_t)range->size, errno);
- }
-
- g_free(dbitmap);
-
- return ret;
-}
-
-static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
- uint64_t size, ram_addr_t ram_addr)
+int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
+ uint64_t size, ram_addr_t ram_addr)
{
bool all_device_dirty_tracking =
vfio_devices_all_device_dirty_tracking(container);
@@ -1977,7 +1403,7 @@
}
}
-static const MemoryListener vfio_memory_listener = {
+const MemoryListener vfio_memory_listener = {
.name = "vfio",
.region_add = vfio_listener_region_add,
.region_del = vfio_listener_region_del,
@@ -1986,338 +1412,34 @@
.log_sync = vfio_listener_log_sync,
};
-static void vfio_listener_release(VFIOContainer *container)
-{
- memory_listener_unregister(&container->listener);
- if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
- memory_listener_unregister(&container->prereg_listener);
- }
-}
-
-static struct vfio_info_cap_header *
-vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id)
-{
- struct vfio_info_cap_header *hdr;
-
- for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
- if (hdr->id == id) {
- return hdr;
- }
- }
-
- return NULL;
-}
-
-struct vfio_info_cap_header *
-vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
-{
- if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) {
- return NULL;
- }
-
- return vfio_get_cap((void *)info, info->cap_offset, id);
-}
-
-static struct vfio_info_cap_header *
-vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t id)
-{
- if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) {
- return NULL;
- }
-
- return vfio_get_cap((void *)info, info->cap_offset, id);
-}
-
-struct vfio_info_cap_header *
-vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id)
-{
- if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) {
- return NULL;
- }
-
- return vfio_get_cap((void *)info, info->cap_offset, id);
-}
-
-bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info,
- unsigned int *avail)
-{
- struct vfio_info_cap_header *hdr;
- struct vfio_iommu_type1_info_dma_avail *cap;
-
- /* If the capability cannot be found, assume no DMA limiting */
- hdr = vfio_get_iommu_type1_info_cap(info,
- VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL);
- if (hdr == NULL) {
- return false;
- }
-
- if (avail != NULL) {
- cap = (void *) hdr;
- *avail = cap->avail;
- }
-
- return true;
-}
-
-static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
- struct vfio_region_info *info)
-{
- struct vfio_info_cap_header *hdr;
- struct vfio_region_info_cap_sparse_mmap *sparse;
- int i, j;
-
- hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
- if (!hdr) {
- return -ENODEV;
- }
-
- sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);
-
- trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
- region->nr, sparse->nr_areas);
-
- region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);
-
- for (i = 0, j = 0; i < sparse->nr_areas; i++) {
- if (sparse->areas[i].size) {
- trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
- sparse->areas[i].offset +
- sparse->areas[i].size - 1);
- region->mmaps[j].offset = sparse->areas[i].offset;
- region->mmaps[j].size = sparse->areas[i].size;
- j++;
- }
- }
-
- region->nr_mmaps = j;
- region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));
-
- return 0;
-}
-
-int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
- int index, const char *name)
-{
- struct vfio_region_info *info;
- int ret;
-
- ret = vfio_get_region_info(vbasedev, index, &info);
- if (ret) {
- return ret;
- }
-
- region->vbasedev = vbasedev;
- region->flags = info->flags;
- region->size = info->size;
- region->fd_offset = info->offset;
- region->nr = index;
-
- if (region->size) {
- region->mem = g_new0(MemoryRegion, 1);
- memory_region_init_io(region->mem, obj, &vfio_region_ops,
- region, name, region->size);
-
- if (!vbasedev->no_mmap &&
- region->flags & VFIO_REGION_INFO_FLAG_MMAP) {
-
- ret = vfio_setup_region_sparse_mmaps(region, info);
-
- if (ret) {
- region->nr_mmaps = 1;
- region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
- region->mmaps[0].offset = 0;
- region->mmaps[0].size = region->size;
- }
- }
- }
-
- g_free(info);
-
- trace_vfio_region_setup(vbasedev->name, index, name,
- region->flags, region->fd_offset, region->size);
- return 0;
-}
-
-static void vfio_subregion_unmap(VFIORegion *region, int index)
-{
- trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem),
- region->mmaps[index].offset,
- region->mmaps[index].offset +
- region->mmaps[index].size - 1);
- memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem);
- munmap(region->mmaps[index].mmap, region->mmaps[index].size);
- object_unparent(OBJECT(®ion->mmaps[index].mem));
- region->mmaps[index].mmap = NULL;
-}
-
-int vfio_region_mmap(VFIORegion *region)
-{
- int i, prot = 0;
- char *name;
-
- if (!region->mem) {
- return 0;
- }
-
- prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0;
- prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0;
-
- for (i = 0; i < region->nr_mmaps; i++) {
- region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot,
- MAP_SHARED, region->vbasedev->fd,
- region->fd_offset +
- region->mmaps[i].offset);
- if (region->mmaps[i].mmap == MAP_FAILED) {
- int ret = -errno;
-
- trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
- region->fd_offset +
- region->mmaps[i].offset,
- region->fd_offset +
- region->mmaps[i].offset +
- region->mmaps[i].size - 1, ret);
-
- region->mmaps[i].mmap = NULL;
-
- for (i--; i >= 0; i--) {
- vfio_subregion_unmap(region, i);
- }
-
- return ret;
- }
-
- name = g_strdup_printf("%s mmaps[%d]",
- memory_region_name(region->mem), i);
- memory_region_init_ram_device_ptr(®ion->mmaps[i].mem,
- memory_region_owner(region->mem),
- name, region->mmaps[i].size,
- region->mmaps[i].mmap);
- g_free(name);
- memory_region_add_subregion(region->mem, region->mmaps[i].offset,
- ®ion->mmaps[i].mem);
-
- trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem),
- region->mmaps[i].offset,
- region->mmaps[i].offset +
- region->mmaps[i].size - 1);
- }
-
- return 0;
-}
-
-void vfio_region_unmap(VFIORegion *region)
-{
- int i;
-
- if (!region->mem) {
- return;
- }
-
- for (i = 0; i < region->nr_mmaps; i++) {
- if (region->mmaps[i].mmap) {
- vfio_subregion_unmap(region, i);
- }
- }
-}
-
-void vfio_region_exit(VFIORegion *region)
-{
- int i;
-
- if (!region->mem) {
- return;
- }
-
- for (i = 0; i < region->nr_mmaps; i++) {
- if (region->mmaps[i].mmap) {
- memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem);
- }
- }
-
- trace_vfio_region_exit(region->vbasedev->name, region->nr);
-}
-
-void vfio_region_finalize(VFIORegion *region)
-{
- int i;
-
- if (!region->mem) {
- return;
- }
-
- for (i = 0; i < region->nr_mmaps; i++) {
- if (region->mmaps[i].mmap) {
- munmap(region->mmaps[i].mmap, region->mmaps[i].size);
- object_unparent(OBJECT(®ion->mmaps[i].mem));
- }
- }
-
- object_unparent(OBJECT(region->mem));
-
- g_free(region->mem);
- g_free(region->mmaps);
-
- trace_vfio_region_finalize(region->vbasedev->name, region->nr);
-
- region->mem = NULL;
- region->mmaps = NULL;
- region->nr_mmaps = 0;
- region->size = 0;
- region->flags = 0;
- region->nr = 0;
-}
-
-void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
-{
- int i;
-
- if (!region->mem) {
- return;
- }
-
- for (i = 0; i < region->nr_mmaps; i++) {
- if (region->mmaps[i].mmap) {
- memory_region_set_enabled(®ion->mmaps[i].mem, enabled);
- }
- }
-
- trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
- enabled);
-}
-
void vfio_reset_handler(void *opaque)
{
- VFIOGroup *group;
VFIODevice *vbasedev;
- QLIST_FOREACH(group, &vfio_group_list, next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (vbasedev->dev->realized) {
- vbasedev->ops->vfio_compute_needs_reset(vbasedev);
- }
+ QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ if (vbasedev->dev->realized) {
+ vbasedev->ops->vfio_compute_needs_reset(vbasedev);
}
}
- QLIST_FOREACH(group, &vfio_group_list, next) {
- QLIST_FOREACH(vbasedev, &group->device_list, next) {
- if (vbasedev->dev->realized && vbasedev->needs_reset) {
- vbasedev->ops->vfio_hot_reset_multi(vbasedev);
- }
+ QLIST_FOREACH(vbasedev, &vfio_device_list, next) {
+ if (vbasedev->dev->realized && vbasedev->needs_reset) {
+ vbasedev->ops->vfio_hot_reset_multi(vbasedev);
}
}
}
-static void vfio_kvm_device_add_group(VFIOGroup *group)
+int vfio_kvm_device_add_fd(int fd, Error **errp)
{
#ifdef CONFIG_KVM
struct kvm_device_attr attr = {
- .group = KVM_DEV_VFIO_GROUP,
- .attr = KVM_DEV_VFIO_GROUP_ADD,
- .addr = (uint64_t)(unsigned long)&group->fd,
+ .group = KVM_DEV_VFIO_FILE,
+ .attr = KVM_DEV_VFIO_FILE_ADD,
+ .addr = (uint64_t)(unsigned long)&fd,
};
if (!kvm_enabled()) {
- return;
+ return 0;
}
if (vfio_kvm_device_fd < 0) {
@@ -2326,41 +1448,46 @@
};
if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) {
- error_report("Failed to create KVM VFIO device: %m");
- return;
+ error_setg_errno(errp, errno, "Failed to create KVM VFIO device");
+ return -errno;
}
vfio_kvm_device_fd = cd.fd;
}
if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
- error_report("Failed to add group %d to KVM VFIO device: %m",
- group->groupid);
+ error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO device",
+ fd);
+ return -errno;
}
#endif
+ return 0;
}
-static void vfio_kvm_device_del_group(VFIOGroup *group)
+int vfio_kvm_device_del_fd(int fd, Error **errp)
{
#ifdef CONFIG_KVM
struct kvm_device_attr attr = {
- .group = KVM_DEV_VFIO_GROUP,
- .attr = KVM_DEV_VFIO_GROUP_DEL,
- .addr = (uint64_t)(unsigned long)&group->fd,
+ .group = KVM_DEV_VFIO_FILE,
+ .attr = KVM_DEV_VFIO_FILE_DEL,
+ .addr = (uint64_t)(unsigned long)&fd,
};
if (vfio_kvm_device_fd < 0) {
- return;
+ error_setg(errp, "KVM VFIO device isn't created yet");
+ return -EINVAL;
}
if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
- error_report("Failed to remove group %d from KVM VFIO device: %m",
- group->groupid);
+ error_setg_errno(errp, errno,
+ "Failed to remove fd %d from KVM VFIO device", fd);
+ return -errno;
}
#endif
+ return 0;
}
-static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
+VFIOAddressSpace *vfio_get_address_space(AddressSpace *as)
{
VFIOAddressSpace *space;
@@ -2375,516 +1502,22 @@
space->as = as;
QLIST_INIT(&space->containers);
+ if (QLIST_EMPTY(&vfio_address_spaces)) {
+ qemu_register_reset(vfio_reset_handler, NULL);
+ }
+
QLIST_INSERT_HEAD(&vfio_address_spaces, space, list);
return space;
}
-static void vfio_put_address_space(VFIOAddressSpace *space)
+void vfio_put_address_space(VFIOAddressSpace *space)
{
if (QLIST_EMPTY(&space->containers)) {
QLIST_REMOVE(space, list);
g_free(space);
}
-}
-
-/*
- * vfio_get_iommu_type - selects the richest iommu_type (v2 first)
- */
-static int vfio_get_iommu_type(VFIOContainer *container,
- Error **errp)
-{
- int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU,
- VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU };
- int i;
-
- for (i = 0; i < ARRAY_SIZE(iommu_types); i++) {
- if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) {
- return iommu_types[i];
- }
- }
- error_setg(errp, "No available IOMMU models");
- return -EINVAL;
-}
-
-static int vfio_init_container(VFIOContainer *container, int group_fd,
- Error **errp)
-{
- int iommu_type, ret;
-
- iommu_type = vfio_get_iommu_type(container, errp);
- if (iommu_type < 0) {
- return iommu_type;
- }
-
- ret = ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd);
- if (ret) {
- error_setg_errno(errp, errno, "Failed to set group container");
- return -errno;
- }
-
- while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) {
- if (iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
- /*
- * On sPAPR, despite the IOMMU subdriver always advertises v1 and
- * v2, the running platform may not support v2 and there is no
- * way to guess it until an IOMMU group gets added to the container.
- * So in case it fails with v2, try v1 as a fallback.
- */
- iommu_type = VFIO_SPAPR_TCE_IOMMU;
- continue;
- }
- error_setg_errno(errp, errno, "Failed to set iommu for container");
- return -errno;
- }
-
- container->iommu_type = iommu_type;
- return 0;
-}
-
-static int vfio_get_iommu_info(VFIOContainer *container,
- struct vfio_iommu_type1_info **info)
-{
-
- size_t argsz = sizeof(struct vfio_iommu_type1_info);
-
- *info = g_new0(struct vfio_iommu_type1_info, 1);
-again:
- (*info)->argsz = argsz;
-
- if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) {
- g_free(*info);
- *info = NULL;
- return -errno;
- }
-
- if (((*info)->argsz > argsz)) {
- argsz = (*info)->argsz;
- *info = g_realloc(*info, argsz);
- goto again;
- }
-
- return 0;
-}
-
-static struct vfio_info_cap_header *
-vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id)
-{
- struct vfio_info_cap_header *hdr;
- void *ptr = info;
-
- if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) {
- return NULL;
- }
-
- for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
- if (hdr->id == id) {
- return hdr;
- }
- }
-
- return NULL;
-}
-
-static void vfio_get_iommu_info_migration(VFIOContainer *container,
- struct vfio_iommu_type1_info *info)
-{
- struct vfio_info_cap_header *hdr;
- struct vfio_iommu_type1_info_cap_migration *cap_mig;
-
- hdr = vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION);
- if (!hdr) {
- return;
- }
-
- cap_mig = container_of(hdr, struct vfio_iommu_type1_info_cap_migration,
- header);
-
- /*
- * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
- * qemu_real_host_page_size to mark those dirty.
- */
- if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) {
- container->dirty_pages_supported = true;
- container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size;
- container->dirty_pgsizes = cap_mig->pgsize_bitmap;
- }
-}
-
-static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
- Error **errp)
-{
- VFIOContainer *container;
- int ret, fd;
- VFIOAddressSpace *space;
-
- space = vfio_get_address_space(as);
-
- /*
- * VFIO is currently incompatible with discarding of RAM insofar as the
- * madvise to purge (zap) the page from QEMU's address space does not
- * interact with the memory API and therefore leaves stale virtual to
- * physical mappings in the IOMMU if the page was previously pinned. We
- * therefore set discarding broken for each group added to a container,
- * whether the container is used individually or shared. This provides
- * us with options to allow devices within a group to opt-in and allow
- * discarding, so long as it is done consistently for a group (for instance
- * if the device is an mdev device where it is known that the host vendor
- * driver will never pin pages outside of the working set of the guest
- * driver, which would thus not be discarding candidates).
- *
- * The first opportunity to induce pinning occurs here where we attempt to
- * attach the group to existing containers within the AddressSpace. If any
- * pages are already zapped from the virtual address space, such as from
- * previous discards, new pinning will cause valid mappings to be
- * re-established. Likewise, when the overall MemoryListener for a new
- * container is registered, a replay of mappings within the AddressSpace
- * will occur, re-establishing any previously zapped pages as well.
- *
- * Especially virtio-balloon is currently only prevented from discarding
- * new memory, it will not yet set ram_block_discard_set_required() and
- * therefore, neither stops us here or deals with the sudden memory
- * consumption of inflated memory.
- *
- * We do support discarding of memory coordinated via the RamDiscardManager
- * with some IOMMU types. vfio_ram_block_discard_disable() handles the
- * details once we know which type of IOMMU we are using.
- */
-
- QLIST_FOREACH(container, &space->containers, next) {
- if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
- ret = vfio_ram_block_discard_disable(container, true);
- if (ret) {
- error_setg_errno(errp, -ret,
- "Cannot set discarding of RAM broken");
- if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER,
- &container->fd)) {
- error_report("vfio: error disconnecting group %d from"
- " container", group->groupid);
- }
- return ret;
- }
- group->container = container;
- QLIST_INSERT_HEAD(&container->group_list, group, container_next);
- vfio_kvm_device_add_group(group);
- return 0;
- }
- }
-
- fd = qemu_open_old("/dev/vfio/vfio", O_RDWR);
- if (fd < 0) {
- error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio");
- ret = -errno;
- goto put_space_exit;
- }
-
- ret = ioctl(fd, VFIO_GET_API_VERSION);
- if (ret != VFIO_API_VERSION) {
- error_setg(errp, "supported vfio version: %d, "
- "reported version: %d", VFIO_API_VERSION, ret);
- ret = -EINVAL;
- goto close_fd_exit;
- }
-
- container = g_malloc0(sizeof(*container));
- container->space = space;
- container->fd = fd;
- container->error = NULL;
- container->dirty_pages_supported = false;
- container->dma_max_mappings = 0;
- QLIST_INIT(&container->giommu_list);
- QLIST_INIT(&container->hostwin_list);
- QLIST_INIT(&container->vrdl_list);
-
- ret = vfio_init_container(container, group->fd, errp);
- if (ret) {
- goto free_container_exit;
- }
-
- ret = vfio_ram_block_discard_disable(container, true);
- if (ret) {
- error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
- goto free_container_exit;
- }
-
- switch (container->iommu_type) {
- case VFIO_TYPE1v2_IOMMU:
- case VFIO_TYPE1_IOMMU:
- {
- struct vfio_iommu_type1_info *info;
-
- ret = vfio_get_iommu_info(container, &info);
- if (ret) {
- error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info");
- goto enable_discards_exit;
- }
-
- if (info->flags & VFIO_IOMMU_INFO_PGSIZES) {
- container->pgsizes = info->iova_pgsizes;
- } else {
- container->pgsizes = qemu_real_host_page_size();
- }
-
- if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) {
- container->dma_max_mappings = 65535;
- }
- vfio_get_iommu_info_migration(container, info);
- g_free(info);
-
- /*
- * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE
- * information to get the actual window extent rather than assume
- * a 64-bit IOVA address space.
- */
- vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes);
-
- break;
- }
- case VFIO_SPAPR_TCE_v2_IOMMU:
- case VFIO_SPAPR_TCE_IOMMU:
- {
- struct vfio_iommu_spapr_tce_info info;
- bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU;
-
- /*
- * The host kernel code implementing VFIO_IOMMU_DISABLE is called
- * when container fd is closed so we do not call it explicitly
- * in this file.
- */
- if (!v2) {
- ret = ioctl(fd, VFIO_IOMMU_ENABLE);
- if (ret) {
- error_setg_errno(errp, errno, "failed to enable container");
- ret = -errno;
- goto enable_discards_exit;
- }
- } else {
- container->prereg_listener = vfio_prereg_listener;
-
- memory_listener_register(&container->prereg_listener,
- &address_space_memory);
- if (container->error) {
- memory_listener_unregister(&container->prereg_listener);
- ret = -1;
- error_propagate_prepend(errp, container->error,
- "RAM memory listener initialization failed: ");
- goto enable_discards_exit;
- }
- }
-
- info.argsz = sizeof(info);
- ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
- if (ret) {
- error_setg_errno(errp, errno,
- "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed");
- ret = -errno;
- if (v2) {
- memory_listener_unregister(&container->prereg_listener);
- }
- goto enable_discards_exit;
- }
-
- if (v2) {
- container->pgsizes = info.ddw.pgsizes;
- /*
- * There is a default window in just created container.
- * To make region_add/del simpler, we better remove this
- * window now and let those iommu_listener callbacks
- * create/remove them when needed.
- */
- ret = vfio_spapr_remove_window(container, info.dma32_window_start);
- if (ret) {
- error_setg_errno(errp, -ret,
- "failed to remove existing window");
- goto enable_discards_exit;
- }
- } else {
- /* The default table uses 4K pages */
- container->pgsizes = 0x1000;
- vfio_host_win_add(container, info.dma32_window_start,
- info.dma32_window_start +
- info.dma32_window_size - 1,
- 0x1000);
- }
- }
- }
-
- vfio_kvm_device_add_group(group);
-
- QLIST_INIT(&container->group_list);
- QLIST_INSERT_HEAD(&space->containers, container, next);
-
- group->container = container;
- QLIST_INSERT_HEAD(&container->group_list, group, container_next);
-
- container->listener = vfio_memory_listener;
-
- memory_listener_register(&container->listener, container->space->as);
-
- if (container->error) {
- ret = -1;
- error_propagate_prepend(errp, container->error,
- "memory listener initialization failed: ");
- goto listener_release_exit;
- }
-
- container->initialized = true;
-
- return 0;
-listener_release_exit:
- QLIST_REMOVE(group, container_next);
- QLIST_REMOVE(container, next);
- vfio_kvm_device_del_group(group);
- vfio_listener_release(container);
-
-enable_discards_exit:
- vfio_ram_block_discard_disable(container, false);
-
-free_container_exit:
- g_free(container);
-
-close_fd_exit:
- close(fd);
-
-put_space_exit:
- vfio_put_address_space(space);
-
- return ret;
-}
-
-static void vfio_disconnect_container(VFIOGroup *group)
-{
- VFIOContainer *container = group->container;
-
- QLIST_REMOVE(group, container_next);
- group->container = NULL;
-
- /*
- * Explicitly release the listener first before unset container,
- * since unset may destroy the backend container if it's the last
- * group.
- */
- if (QLIST_EMPTY(&container->group_list)) {
- vfio_listener_release(container);
- }
-
- if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) {
- error_report("vfio: error disconnecting group %d from container",
- group->groupid);
- }
-
- if (QLIST_EMPTY(&container->group_list)) {
- VFIOAddressSpace *space = container->space;
- VFIOGuestIOMMU *giommu, *tmp;
- VFIOHostDMAWindow *hostwin, *next;
-
- QLIST_REMOVE(container, next);
-
- QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
- memory_region_unregister_iommu_notifier(
- MEMORY_REGION(giommu->iommu_mr), &giommu->n);
- QLIST_REMOVE(giommu, giommu_next);
- g_free(giommu);
- }
-
- QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next,
- next) {
- QLIST_REMOVE(hostwin, hostwin_next);
- g_free(hostwin);
- }
-
- trace_vfio_disconnect_container(container->fd);
- close(container->fd);
- g_free(container);
-
- vfio_put_address_space(space);
- }
-}
-
-VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp)
-{
- VFIOGroup *group;
- char path[32];
- struct vfio_group_status status = { .argsz = sizeof(status) };
-
- QLIST_FOREACH(group, &vfio_group_list, next) {
- if (group->groupid == groupid) {
- /* Found it. Now is it already in the right context? */
- if (group->container->space->as == as) {
- return group;
- } else {
- error_setg(errp, "group %d used in multiple address spaces",
- group->groupid);
- return NULL;
- }
- }
- }
-
- group = g_malloc0(sizeof(*group));
-
- snprintf(path, sizeof(path), "/dev/vfio/%d", groupid);
- group->fd = qemu_open_old(path, O_RDWR);
- if (group->fd < 0) {
- error_setg_errno(errp, errno, "failed to open %s", path);
- goto free_group_exit;
- }
-
- if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) {
- error_setg_errno(errp, errno, "failed to get group %d status", groupid);
- goto close_fd_exit;
- }
-
- if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
- error_setg(errp, "group %d is not viable", groupid);
- error_append_hint(errp,
- "Please ensure all devices within the iommu_group "
- "are bound to their vfio bus driver.\n");
- goto close_fd_exit;
- }
-
- group->groupid = groupid;
- QLIST_INIT(&group->device_list);
-
- if (vfio_connect_container(group, as, errp)) {
- error_prepend(errp, "failed to setup container for group %d: ",
- groupid);
- goto close_fd_exit;
- }
-
- if (QLIST_EMPTY(&vfio_group_list)) {
- qemu_register_reset(vfio_reset_handler, NULL);
- }
-
- QLIST_INSERT_HEAD(&vfio_group_list, group, next);
-
- return group;
-
-close_fd_exit:
- close(group->fd);
-
-free_group_exit:
- g_free(group);
-
- return NULL;
-}
-
-void vfio_put_group(VFIOGroup *group)
-{
- if (!group || !QLIST_EMPTY(&group->device_list)) {
- return;
- }
-
- if (!group->ram_block_discard_allowed) {
- vfio_ram_block_discard_disable(group->container, false);
- }
- vfio_kvm_device_del_group(group);
- vfio_disconnect_container(group);
- QLIST_REMOVE(group, next);
- trace_vfio_put_group(group->fd);
- close(group->fd);
- g_free(group);
-
- if (QLIST_EMPTY(&vfio_group_list)) {
+ if (QLIST_EMPTY(&vfio_address_spaces)) {
qemu_unregister_reset(vfio_reset_handler, NULL);
}
}
@@ -2912,245 +1545,3 @@
return info;
}
-
-int vfio_get_device(VFIOGroup *group, const char *name,
- VFIODevice *vbasedev, Error **errp)
-{
- g_autofree struct vfio_device_info *info = NULL;
- int fd;
-
- fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
- if (fd < 0) {
- error_setg_errno(errp, errno, "error getting device from group %d",
- group->groupid);
- error_append_hint(errp,
- "Verify all devices in group %d are bound to vfio-<bus> "
- "or pci-stub and not already in use\n", group->groupid);
- return fd;
- }
-
- info = vfio_get_device_info(fd);
- if (!info) {
- error_setg_errno(errp, errno, "error getting device info");
- close(fd);
- return -1;
- }
-
- /*
- * Set discarding of RAM as not broken for this group if the driver knows
- * the device operates compatibly with discarding. Setting must be
- * consistent per group, but since compatibility is really only possible
- * with mdev currently, we expect singleton groups.
- */
- if (vbasedev->ram_block_discard_allowed !=
- group->ram_block_discard_allowed) {
- if (!QLIST_EMPTY(&group->device_list)) {
- error_setg(errp, "Inconsistent setting of support for discarding "
- "RAM (e.g., balloon) within group");
- close(fd);
- return -1;
- }
-
- if (!group->ram_block_discard_allowed) {
- group->ram_block_discard_allowed = true;
- vfio_ram_block_discard_disable(group->container, false);
- }
- }
-
- vbasedev->fd = fd;
- vbasedev->group = group;
- QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
-
- vbasedev->num_irqs = info->num_irqs;
- vbasedev->num_regions = info->num_regions;
- vbasedev->flags = info->flags;
-
- trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs);
-
- vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
-
- return 0;
-}
-
-void vfio_put_base_device(VFIODevice *vbasedev)
-{
- if (!vbasedev->group) {
- return;
- }
- QLIST_REMOVE(vbasedev, next);
- vbasedev->group = NULL;
- trace_vfio_put_base_device(vbasedev->fd);
- close(vbasedev->fd);
-}
-
-int vfio_get_region_info(VFIODevice *vbasedev, int index,
- struct vfio_region_info **info)
-{
- size_t argsz = sizeof(struct vfio_region_info);
-
- *info = g_malloc0(argsz);
-
- (*info)->index = index;
-retry:
- (*info)->argsz = argsz;
-
- if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
- g_free(*info);
- *info = NULL;
- return -errno;
- }
-
- if ((*info)->argsz > argsz) {
- argsz = (*info)->argsz;
- *info = g_realloc(*info, argsz);
-
- goto retry;
- }
-
- return 0;
-}
-
-int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
- uint32_t subtype, struct vfio_region_info **info)
-{
- int i;
-
- for (i = 0; i < vbasedev->num_regions; i++) {
- struct vfio_info_cap_header *hdr;
- struct vfio_region_info_cap_type *cap_type;
-
- if (vfio_get_region_info(vbasedev, i, info)) {
- continue;
- }
-
- hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
- if (!hdr) {
- g_free(*info);
- continue;
- }
-
- cap_type = container_of(hdr, struct vfio_region_info_cap_type, header);
-
- trace_vfio_get_dev_region(vbasedev->name, i,
- cap_type->type, cap_type->subtype);
-
- if (cap_type->type == type && cap_type->subtype == subtype) {
- return 0;
- }
-
- g_free(*info);
- }
-
- *info = NULL;
- return -ENODEV;
-}
-
-bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
-{
- struct vfio_region_info *info = NULL;
- bool ret = false;
-
- if (!vfio_get_region_info(vbasedev, region, &info)) {
- if (vfio_get_region_info_cap(info, cap_type)) {
- ret = true;
- }
- g_free(info);
- }
-
- return ret;
-}
-
-/*
- * Interfaces for IBM EEH (Enhanced Error Handling)
- */
-static bool vfio_eeh_container_ok(VFIOContainer *container)
-{
- /*
- * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO
- * implementation is broken if there are multiple groups in a
- * container. The hardware works in units of Partitionable
- * Endpoints (== IOMMU groups) and the EEH operations naively
- * iterate across all groups in the container, without any logic
- * to make sure the groups have their state synchronized. For
- * certain operations (ENABLE) that might be ok, until an error
- * occurs, but for others (GET_STATE) it's clearly broken.
- */
-
- /*
- * XXX Once fixed kernels exist, test for them here
- */
-
- if (QLIST_EMPTY(&container->group_list)) {
- return false;
- }
-
- if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) {
- return false;
- }
-
- return true;
-}
-
-static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op)
-{
- struct vfio_eeh_pe_op pe_op = {
- .argsz = sizeof(pe_op),
- .op = op,
- };
- int ret;
-
- if (!vfio_eeh_container_ok(container)) {
- error_report("vfio/eeh: EEH_PE_OP 0x%x: "
- "kernel requires a container with exactly one group", op);
- return -EPERM;
- }
-
- ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op);
- if (ret < 0) {
- error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op);
- return -errno;
- }
-
- return ret;
-}
-
-static VFIOContainer *vfio_eeh_as_container(AddressSpace *as)
-{
- VFIOAddressSpace *space = vfio_get_address_space(as);
- VFIOContainer *container = NULL;
-
- if (QLIST_EMPTY(&space->containers)) {
- /* No containers to act on */
- goto out;
- }
-
- container = QLIST_FIRST(&space->containers);
-
- if (QLIST_NEXT(container, next)) {
- /* We don't yet have logic to synchronize EEH state across
- * multiple containers */
- container = NULL;
- goto out;
- }
-
-out:
- vfio_put_address_space(space);
- return container;
-}
-
-bool vfio_eeh_as_ok(AddressSpace *as)
-{
- VFIOContainer *container = vfio_eeh_as_container(as);
-
- return (container != NULL) && vfio_eeh_container_ok(container);
-}
-
-int vfio_eeh_as_op(AddressSpace *as, uint32_t op)
-{
- VFIOContainer *container = vfio_eeh_as_container(as);
-
- if (!container) {
- return -ENODEV;
- }
- return vfio_eeh_container_op(container, op);
-}
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
new file mode 100644
index 0000000..adc4672
--- /dev/null
+++ b/hw/vfio/container.c
@@ -0,0 +1,1161 @@
+/*
+ * generic functions used by VFIO devices
+ *
+ * Copyright Red Hat, Inc. 2012
+ *
+ * Authors:
+ * Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Based on qemu-kvm device-assignment:
+ * Adapted for KVM by Qumranet.
+ * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
+ * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
+ * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
+ * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
+ * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
+ */
+
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+#ifdef CONFIG_KVM
+#include <linux/kvm.h>
+#endif
+#include <linux/vfio.h>
+
+#include "hw/vfio/vfio-common.h"
+#include "hw/vfio/vfio.h"
+#include "exec/address-spaces.h"
+#include "exec/memory.h"
+#include "exec/ram_addr.h"
+#include "hw/hw.h"
+#include "qemu/error-report.h"
+#include "qemu/range.h"
+#include "sysemu/kvm.h"
+#include "sysemu/reset.h"
+#include "trace.h"
+#include "qapi/error.h"
+#include "migration/migration.h"
+
+VFIOGroupList vfio_group_list =
+ QLIST_HEAD_INITIALIZER(vfio_group_list);
+
+static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state)
+{
+ switch (container->iommu_type) {
+ case VFIO_TYPE1v2_IOMMU:
+ case VFIO_TYPE1_IOMMU:
+ /*
+ * We support coordinated discarding of RAM via the RamDiscardManager.
+ */
+ return ram_block_uncoordinated_discard_disable(state);
+ default:
+ /*
+ * VFIO_SPAPR_TCE_IOMMU most probably works just fine with
+ * RamDiscardManager, however, it is completely untested.
+ *
+ * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does
+ * completely the opposite of managing mapping/pinning dynamically as
+ * required by RamDiscardManager. We would have to special-case sections
+ * with a RamDiscardManager.
+ */
+ return ram_block_discard_disable(state);
+ }
+}
+
+static int vfio_dma_unmap_bitmap(VFIOContainer *container,
+ hwaddr iova, ram_addr_t size,
+ IOMMUTLBEntry *iotlb)
+{
+ struct vfio_iommu_type1_dma_unmap *unmap;
+ struct vfio_bitmap *bitmap;
+ VFIOBitmap vbmap;
+ int ret;
+
+ ret = vfio_bitmap_alloc(&vbmap, size);
+ if (ret) {
+ return ret;
+ }
+
+ unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap));
+
+ unmap->argsz = sizeof(*unmap) + sizeof(*bitmap);
+ unmap->iova = iova;
+ unmap->size = size;
+ unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP;
+ bitmap = (struct vfio_bitmap *)&unmap->data;
+
+ /*
+ * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
+ * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize
+ * to qemu_real_host_page_size.
+ */
+ bitmap->pgsize = qemu_real_host_page_size();
+ bitmap->size = vbmap.size;
+ bitmap->data = (__u64 *)vbmap.bitmap;
+
+ if (vbmap.size > container->max_dirty_bitmap_size) {
+ error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size);
+ ret = -E2BIG;
+ goto unmap_exit;
+ }
+
+ ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+ if (!ret) {
+ cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap,
+ iotlb->translated_addr, vbmap.pages);
+ } else {
+ error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m");
+ }
+
+unmap_exit:
+ g_free(unmap);
+ g_free(vbmap.bitmap);
+
+ return ret;
+}
+
+/*
+ * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
+ */
+int vfio_dma_unmap(VFIOContainer *container, hwaddr iova,
+ ram_addr_t size, IOMMUTLBEntry *iotlb)
+{
+ struct vfio_iommu_type1_dma_unmap unmap = {
+ .argsz = sizeof(unmap),
+ .flags = 0,
+ .iova = iova,
+ .size = size,
+ };
+ bool need_dirty_sync = false;
+ int ret;
+
+ if (iotlb && vfio_devices_all_running_and_mig_active(container)) {
+ if (!vfio_devices_all_device_dirty_tracking(container) &&
+ container->dirty_pages_supported) {
+ return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
+ }
+
+ need_dirty_sync = true;
+ }
+
+ while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
+ /*
+ * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
+ * v4.15) where an overflow in its wrap-around check prevents us from
+ * unmapping the last page of the address space. Test for the error
+ * condition and re-try the unmap excluding the last page. The
+ * expectation is that we've never mapped the last page anyway and this
+ * unmap request comes via vIOMMU support which also makes it unlikely
+ * that this page is used. This bug was introduced well after type1 v2
+ * support was introduced, so we shouldn't need to test for v1. A fix
+ * is queued for kernel v5.0 so this workaround can be removed once
+ * affected kernels are sufficiently deprecated.
+ */
+ if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) &&
+ container->iommu_type == VFIO_TYPE1v2_IOMMU) {
+ trace_vfio_dma_unmap_overflow_workaround();
+ unmap.size -= 1ULL << ctz64(container->pgsizes);
+ continue;
+ }
+ error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno));
+ return -errno;
+ }
+
+ if (need_dirty_sync) {
+ ret = vfio_get_dirty_bitmap(container, iova, size,
+ iotlb->translated_addr);
+ if (ret) {
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+int vfio_dma_map(VFIOContainer *container, hwaddr iova,
+ ram_addr_t size, void *vaddr, bool readonly)
+{
+ struct vfio_iommu_type1_dma_map map = {
+ .argsz = sizeof(map),
+ .flags = VFIO_DMA_MAP_FLAG_READ,
+ .vaddr = (__u64)(uintptr_t)vaddr,
+ .iova = iova,
+ .size = size,
+ };
+
+ if (!readonly) {
+ map.flags |= VFIO_DMA_MAP_FLAG_WRITE;
+ }
+
+ /*
+ * Try the mapping, if it fails with EBUSY, unmap the region and try
+ * again. This shouldn't be necessary, but we sometimes see it in
+ * the VGA ROM space.
+ */
+ if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
+ (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 &&
+ ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
+ return 0;
+ }
+
+ error_report("VFIO_MAP_DMA failed: %s", strerror(errno));
+ return -errno;
+}
+
+int vfio_container_add_section_window(VFIOContainer *container,
+ MemoryRegionSection *section,
+ Error **errp)
+{
+ VFIOHostDMAWindow *hostwin;
+ hwaddr pgsize = 0;
+ int ret;
+
+ if (container->iommu_type != VFIO_SPAPR_TCE_v2_IOMMU) {
+ return 0;
+ }
+
+ /* For now intersections are not allowed, we may relax this later */
+ QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) {
+ if (ranges_overlap(hostwin->min_iova,
+ hostwin->max_iova - hostwin->min_iova + 1,
+ section->offset_within_address_space,
+ int128_get64(section->size))) {
+ error_setg(errp,
+ "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing"
+ "host DMA window [0x%"PRIx64",0x%"PRIx64"]",
+ section->offset_within_address_space,
+ section->offset_within_address_space +
+ int128_get64(section->size) - 1,
+ hostwin->min_iova, hostwin->max_iova);
+ return -EINVAL;
+ }
+ }
+
+ ret = vfio_spapr_create_window(container, section, &pgsize);
+ if (ret) {
+ error_setg_errno(errp, -ret, "Failed to create SPAPR window");
+ return ret;
+ }
+
+ vfio_host_win_add(container, section->offset_within_address_space,
+ section->offset_within_address_space +
+ int128_get64(section->size) - 1, pgsize);
+#ifdef CONFIG_KVM
+ if (kvm_enabled()) {
+ VFIOGroup *group;
+ IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
+ struct kvm_vfio_spapr_tce param;
+ struct kvm_device_attr attr = {
+ .group = KVM_DEV_VFIO_GROUP,
+ .attr = KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE,
+ .addr = (uint64_t)(unsigned long)¶m,
+ };
+
+ if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_FD,
+ ¶m.tablefd)) {
+ QLIST_FOREACH(group, &container->group_list, container_next) {
+ param.groupfd = group->fd;
+ if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) {
+ error_setg_errno(errp, errno,
+ "vfio: failed GROUP_SET_SPAPR_TCE for "
+ "KVM VFIO device %d and group fd %d",
+ param.tablefd, param.groupfd);
+ return -errno;
+ }
+ trace_vfio_spapr_group_attach(param.groupfd, param.tablefd);
+ }
+ }
+ }
+#endif
+ return 0;
+}
+
+void vfio_container_del_section_window(VFIOContainer *container,
+ MemoryRegionSection *section)
+{
+ if (container->iommu_type != VFIO_SPAPR_TCE_v2_IOMMU) {
+ return;
+ }
+
+ vfio_spapr_remove_window(container,
+ section->offset_within_address_space);
+ if (vfio_host_win_del(container,
+ section->offset_within_address_space,
+ section->offset_within_address_space +
+ int128_get64(section->size) - 1) < 0) {
+ hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx,
+ __func__, section->offset_within_address_space);
+ }
+}
+
+int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start)
+{
+ int ret;
+ struct vfio_iommu_type1_dirty_bitmap dirty = {
+ .argsz = sizeof(dirty),
+ };
+
+ if (!container->dirty_pages_supported) {
+ return 0;
+ }
+
+ if (start) {
+ dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_START;
+ } else {
+ dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP;
+ }
+
+ ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty);
+ if (ret) {
+ ret = -errno;
+ error_report("Failed to set dirty tracking flag 0x%x errno: %d",
+ dirty.flags, errno);
+ }
+
+ return ret;
+}
+
+int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap,
+ hwaddr iova, hwaddr size)
+{
+ struct vfio_iommu_type1_dirty_bitmap *dbitmap;
+ struct vfio_iommu_type1_dirty_bitmap_get *range;
+ int ret;
+
+ dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range));
+
+ dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range);
+ dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
+ range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data;
+ range->iova = iova;
+ range->size = size;
+
+ /*
+ * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
+ * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pgsize
+ * to qemu_real_host_page_size.
+ */
+ range->bitmap.pgsize = qemu_real_host_page_size();
+ range->bitmap.size = vbmap->size;
+ range->bitmap.data = (__u64 *)vbmap->bitmap;
+
+ ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap);
+ if (ret) {
+ ret = -errno;
+ error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64
+ " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova,
+ (uint64_t)range->size, errno);
+ }
+
+ g_free(dbitmap);
+
+ return ret;
+}
+
+static void vfio_listener_release(VFIOContainer *container)
+{
+ memory_listener_unregister(&container->listener);
+ if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+ memory_listener_unregister(&container->prereg_listener);
+ }
+}
+
+static struct vfio_info_cap_header *
+vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t id)
+{
+ if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) {
+ return NULL;
+ }
+
+ return vfio_get_cap((void *)info, info->cap_offset, id);
+}
+
+bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info,
+ unsigned int *avail)
+{
+ struct vfio_info_cap_header *hdr;
+ struct vfio_iommu_type1_info_dma_avail *cap;
+
+ /* If the capability cannot be found, assume no DMA limiting */
+ hdr = vfio_get_iommu_type1_info_cap(info,
+ VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL);
+ if (hdr == NULL) {
+ return false;
+ }
+
+ if (avail != NULL) {
+ cap = (void *) hdr;
+ *avail = cap->avail;
+ }
+
+ return true;
+}
+
+static void vfio_kvm_device_add_group(VFIOGroup *group)
+{
+ Error *err = NULL;
+
+ if (vfio_kvm_device_add_fd(group->fd, &err)) {
+ error_reportf_err(err, "group ID %d: ", group->groupid);
+ }
+}
+
+static void vfio_kvm_device_del_group(VFIOGroup *group)
+{
+ Error *err = NULL;
+
+ if (vfio_kvm_device_del_fd(group->fd, &err)) {
+ error_reportf_err(err, "group ID %d: ", group->groupid);
+ }
+}
+
+/*
+ * vfio_get_iommu_type - selects the richest iommu_type (v2 first)
+ */
+static int vfio_get_iommu_type(VFIOContainer *container,
+ Error **errp)
+{
+ int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU,
+ VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(iommu_types); i++) {
+ if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) {
+ return iommu_types[i];
+ }
+ }
+ error_setg(errp, "No available IOMMU models");
+ return -EINVAL;
+}
+
+static int vfio_init_container(VFIOContainer *container, int group_fd,
+ Error **errp)
+{
+ int iommu_type, ret;
+
+ iommu_type = vfio_get_iommu_type(container, errp);
+ if (iommu_type < 0) {
+ return iommu_type;
+ }
+
+ ret = ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd);
+ if (ret) {
+ error_setg_errno(errp, errno, "Failed to set group container");
+ return -errno;
+ }
+
+ while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) {
+ if (iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+ /*
+ * On sPAPR, despite the IOMMU subdriver always advertises v1 and
+ * v2, the running platform may not support v2 and there is no
+ * way to guess it until an IOMMU group gets added to the container.
+ * So in case it fails with v2, try v1 as a fallback.
+ */
+ iommu_type = VFIO_SPAPR_TCE_IOMMU;
+ continue;
+ }
+ error_setg_errno(errp, errno, "Failed to set iommu for container");
+ return -errno;
+ }
+
+ container->iommu_type = iommu_type;
+ return 0;
+}
+
+static int vfio_get_iommu_info(VFIOContainer *container,
+ struct vfio_iommu_type1_info **info)
+{
+
+ size_t argsz = sizeof(struct vfio_iommu_type1_info);
+
+ *info = g_new0(struct vfio_iommu_type1_info, 1);
+again:
+ (*info)->argsz = argsz;
+
+ if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) {
+ g_free(*info);
+ *info = NULL;
+ return -errno;
+ }
+
+ if (((*info)->argsz > argsz)) {
+ argsz = (*info)->argsz;
+ *info = g_realloc(*info, argsz);
+ goto again;
+ }
+
+ return 0;
+}
+
+static struct vfio_info_cap_header *
+vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id)
+{
+ struct vfio_info_cap_header *hdr;
+ void *ptr = info;
+
+ if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) {
+ return NULL;
+ }
+
+ for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
+ if (hdr->id == id) {
+ return hdr;
+ }
+ }
+
+ return NULL;
+}
+
+static void vfio_get_iommu_info_migration(VFIOContainer *container,
+ struct vfio_iommu_type1_info *info)
+{
+ struct vfio_info_cap_header *hdr;
+ struct vfio_iommu_type1_info_cap_migration *cap_mig;
+
+ hdr = vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION);
+ if (!hdr) {
+ return;
+ }
+
+ cap_mig = container_of(hdr, struct vfio_iommu_type1_info_cap_migration,
+ header);
+
+ /*
+ * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of
+ * qemu_real_host_page_size to mark those dirty.
+ */
+ if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) {
+ container->dirty_pages_supported = true;
+ container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size;
+ container->dirty_pgsizes = cap_mig->pgsize_bitmap;
+ }
+}
+
+static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
+ Error **errp)
+{
+ VFIOContainer *container;
+ int ret, fd;
+ VFIOAddressSpace *space;
+
+ space = vfio_get_address_space(as);
+
+ /*
+ * VFIO is currently incompatible with discarding of RAM insofar as the
+ * madvise to purge (zap) the page from QEMU's address space does not
+ * interact with the memory API and therefore leaves stale virtual to
+ * physical mappings in the IOMMU if the page was previously pinned. We
+ * therefore set discarding broken for each group added to a container,
+ * whether the container is used individually or shared. This provides
+ * us with options to allow devices within a group to opt-in and allow
+ * discarding, so long as it is done consistently for a group (for instance
+ * if the device is an mdev device where it is known that the host vendor
+ * driver will never pin pages outside of the working set of the guest
+ * driver, which would thus not be discarding candidates).
+ *
+ * The first opportunity to induce pinning occurs here where we attempt to
+ * attach the group to existing containers within the AddressSpace. If any
+ * pages are already zapped from the virtual address space, such as from
+ * previous discards, new pinning will cause valid mappings to be
+ * re-established. Likewise, when the overall MemoryListener for a new
+ * container is registered, a replay of mappings within the AddressSpace
+ * will occur, re-establishing any previously zapped pages as well.
+ *
+ * Especially virtio-balloon is currently only prevented from discarding
+ * new memory, it will not yet set ram_block_discard_set_required() and
+ * therefore, neither stops us here or deals with the sudden memory
+ * consumption of inflated memory.
+ *
+ * We do support discarding of memory coordinated via the RamDiscardManager
+ * with some IOMMU types. vfio_ram_block_discard_disable() handles the
+ * details once we know which type of IOMMU we are using.
+ */
+
+ QLIST_FOREACH(container, &space->containers, next) {
+ if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
+ ret = vfio_ram_block_discard_disable(container, true);
+ if (ret) {
+ error_setg_errno(errp, -ret,
+ "Cannot set discarding of RAM broken");
+ if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER,
+ &container->fd)) {
+ error_report("vfio: error disconnecting group %d from"
+ " container", group->groupid);
+ }
+ return ret;
+ }
+ group->container = container;
+ QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+ vfio_kvm_device_add_group(group);
+ return 0;
+ }
+ }
+
+ fd = qemu_open_old("/dev/vfio/vfio", O_RDWR);
+ if (fd < 0) {
+ error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio");
+ ret = -errno;
+ goto put_space_exit;
+ }
+
+ ret = ioctl(fd, VFIO_GET_API_VERSION);
+ if (ret != VFIO_API_VERSION) {
+ error_setg(errp, "supported vfio version: %d, "
+ "reported version: %d", VFIO_API_VERSION, ret);
+ ret = -EINVAL;
+ goto close_fd_exit;
+ }
+
+ container = g_malloc0(sizeof(*container));
+ container->space = space;
+ container->fd = fd;
+ container->error = NULL;
+ container->dirty_pages_supported = false;
+ container->dma_max_mappings = 0;
+ QLIST_INIT(&container->giommu_list);
+ QLIST_INIT(&container->hostwin_list);
+ QLIST_INIT(&container->vrdl_list);
+
+ ret = vfio_init_container(container, group->fd, errp);
+ if (ret) {
+ goto free_container_exit;
+ }
+
+ ret = vfio_ram_block_discard_disable(container, true);
+ if (ret) {
+ error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken");
+ goto free_container_exit;
+ }
+
+ switch (container->iommu_type) {
+ case VFIO_TYPE1v2_IOMMU:
+ case VFIO_TYPE1_IOMMU:
+ {
+ struct vfio_iommu_type1_info *info;
+
+ ret = vfio_get_iommu_info(container, &info);
+ if (ret) {
+ error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info");
+ goto enable_discards_exit;
+ }
+
+ if (info->flags & VFIO_IOMMU_INFO_PGSIZES) {
+ container->pgsizes = info->iova_pgsizes;
+ } else {
+ container->pgsizes = qemu_real_host_page_size();
+ }
+
+ if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) {
+ container->dma_max_mappings = 65535;
+ }
+ vfio_get_iommu_info_migration(container, info);
+ g_free(info);
+
+ /*
+ * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE
+ * information to get the actual window extent rather than assume
+ * a 64-bit IOVA address space.
+ */
+ vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes);
+
+ break;
+ }
+ case VFIO_SPAPR_TCE_v2_IOMMU:
+ case VFIO_SPAPR_TCE_IOMMU:
+ {
+ struct vfio_iommu_spapr_tce_info info;
+ bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU;
+
+ /*
+ * The host kernel code implementing VFIO_IOMMU_DISABLE is called
+ * when container fd is closed so we do not call it explicitly
+ * in this file.
+ */
+ if (!v2) {
+ ret = ioctl(fd, VFIO_IOMMU_ENABLE);
+ if (ret) {
+ error_setg_errno(errp, errno, "failed to enable container");
+ ret = -errno;
+ goto enable_discards_exit;
+ }
+ } else {
+ container->prereg_listener = vfio_prereg_listener;
+
+ memory_listener_register(&container->prereg_listener,
+ &address_space_memory);
+ if (container->error) {
+ memory_listener_unregister(&container->prereg_listener);
+ ret = -1;
+ error_propagate_prepend(errp, container->error,
+ "RAM memory listener initialization failed: ");
+ goto enable_discards_exit;
+ }
+ }
+
+ info.argsz = sizeof(info);
+ ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
+ if (ret) {
+ error_setg_errno(errp, errno,
+ "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed");
+ ret = -errno;
+ if (v2) {
+ memory_listener_unregister(&container->prereg_listener);
+ }
+ goto enable_discards_exit;
+ }
+
+ if (v2) {
+ container->pgsizes = info.ddw.pgsizes;
+ /*
+ * There is a default window in just created container.
+ * To make region_add/del simpler, we better remove this
+ * window now and let those iommu_listener callbacks
+ * create/remove them when needed.
+ */
+ ret = vfio_spapr_remove_window(container, info.dma32_window_start);
+ if (ret) {
+ error_setg_errno(errp, -ret,
+ "failed to remove existing window");
+ goto enable_discards_exit;
+ }
+ } else {
+ /* The default table uses 4K pages */
+ container->pgsizes = 0x1000;
+ vfio_host_win_add(container, info.dma32_window_start,
+ info.dma32_window_start +
+ info.dma32_window_size - 1,
+ 0x1000);
+ }
+ }
+ }
+
+ vfio_kvm_device_add_group(group);
+
+ QLIST_INIT(&container->group_list);
+ QLIST_INSERT_HEAD(&space->containers, container, next);
+
+ group->container = container;
+ QLIST_INSERT_HEAD(&container->group_list, group, container_next);
+
+ container->listener = vfio_memory_listener;
+
+ memory_listener_register(&container->listener, container->space->as);
+
+ if (container->error) {
+ ret = -1;
+ error_propagate_prepend(errp, container->error,
+ "memory listener initialization failed: ");
+ goto listener_release_exit;
+ }
+
+ container->initialized = true;
+
+ return 0;
+listener_release_exit:
+ QLIST_REMOVE(group, container_next);
+ QLIST_REMOVE(container, next);
+ vfio_kvm_device_del_group(group);
+ vfio_listener_release(container);
+
+enable_discards_exit:
+ vfio_ram_block_discard_disable(container, false);
+
+free_container_exit:
+ g_free(container);
+
+close_fd_exit:
+ close(fd);
+
+put_space_exit:
+ vfio_put_address_space(space);
+
+ return ret;
+}
+
+static void vfio_disconnect_container(VFIOGroup *group)
+{
+ VFIOContainer *container = group->container;
+
+ QLIST_REMOVE(group, container_next);
+ group->container = NULL;
+
+ /*
+ * Explicitly release the listener first before unset container,
+ * since unset may destroy the backend container if it's the last
+ * group.
+ */
+ if (QLIST_EMPTY(&container->group_list)) {
+ vfio_listener_release(container);
+ }
+
+ if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) {
+ error_report("vfio: error disconnecting group %d from container",
+ group->groupid);
+ }
+
+ if (QLIST_EMPTY(&container->group_list)) {
+ VFIOAddressSpace *space = container->space;
+ VFIOGuestIOMMU *giommu, *tmp;
+ VFIOHostDMAWindow *hostwin, *next;
+
+ QLIST_REMOVE(container, next);
+
+ QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
+ memory_region_unregister_iommu_notifier(
+ MEMORY_REGION(giommu->iommu_mr), &giommu->n);
+ QLIST_REMOVE(giommu, giommu_next);
+ g_free(giommu);
+ }
+
+ QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next,
+ next) {
+ QLIST_REMOVE(hostwin, hostwin_next);
+ g_free(hostwin);
+ }
+
+ trace_vfio_disconnect_container(container->fd);
+ close(container->fd);
+ g_free(container);
+
+ vfio_put_address_space(space);
+ }
+}
+
+static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp)
+{
+ VFIOGroup *group;
+ char path[32];
+ struct vfio_group_status status = { .argsz = sizeof(status) };
+
+ QLIST_FOREACH(group, &vfio_group_list, next) {
+ if (group->groupid == groupid) {
+ /* Found it. Now is it already in the right context? */
+ if (group->container->space->as == as) {
+ return group;
+ } else {
+ error_setg(errp, "group %d used in multiple address spaces",
+ group->groupid);
+ return NULL;
+ }
+ }
+ }
+
+ group = g_malloc0(sizeof(*group));
+
+ snprintf(path, sizeof(path), "/dev/vfio/%d", groupid);
+ group->fd = qemu_open_old(path, O_RDWR);
+ if (group->fd < 0) {
+ error_setg_errno(errp, errno, "failed to open %s", path);
+ goto free_group_exit;
+ }
+
+ if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) {
+ error_setg_errno(errp, errno, "failed to get group %d status", groupid);
+ goto close_fd_exit;
+ }
+
+ if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
+ error_setg(errp, "group %d is not viable", groupid);
+ error_append_hint(errp,
+ "Please ensure all devices within the iommu_group "
+ "are bound to their vfio bus driver.\n");
+ goto close_fd_exit;
+ }
+
+ group->groupid = groupid;
+ QLIST_INIT(&group->device_list);
+
+ if (vfio_connect_container(group, as, errp)) {
+ error_prepend(errp, "failed to setup container for group %d: ",
+ groupid);
+ goto close_fd_exit;
+ }
+
+ QLIST_INSERT_HEAD(&vfio_group_list, group, next);
+
+ return group;
+
+close_fd_exit:
+ close(group->fd);
+
+free_group_exit:
+ g_free(group);
+
+ return NULL;
+}
+
+static void vfio_put_group(VFIOGroup *group)
+{
+ if (!group || !QLIST_EMPTY(&group->device_list)) {
+ return;
+ }
+
+ if (!group->ram_block_discard_allowed) {
+ vfio_ram_block_discard_disable(group->container, false);
+ }
+ vfio_kvm_device_del_group(group);
+ vfio_disconnect_container(group);
+ QLIST_REMOVE(group, next);
+ trace_vfio_put_group(group->fd);
+ close(group->fd);
+ g_free(group);
+}
+
+static int vfio_get_device(VFIOGroup *group, const char *name,
+ VFIODevice *vbasedev, Error **errp)
+{
+ g_autofree struct vfio_device_info *info = NULL;
+ int fd;
+
+ fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
+ if (fd < 0) {
+ error_setg_errno(errp, errno, "error getting device from group %d",
+ group->groupid);
+ error_append_hint(errp,
+ "Verify all devices in group %d are bound to vfio-<bus> "
+ "or pci-stub and not already in use\n", group->groupid);
+ return fd;
+ }
+
+ info = vfio_get_device_info(fd);
+ if (!info) {
+ error_setg_errno(errp, errno, "error getting device info");
+ close(fd);
+ return -1;
+ }
+
+ /*
+ * Set discarding of RAM as not broken for this group if the driver knows
+ * the device operates compatibly with discarding. Setting must be
+ * consistent per group, but since compatibility is really only possible
+ * with mdev currently, we expect singleton groups.
+ */
+ if (vbasedev->ram_block_discard_allowed !=
+ group->ram_block_discard_allowed) {
+ if (!QLIST_EMPTY(&group->device_list)) {
+ error_setg(errp, "Inconsistent setting of support for discarding "
+ "RAM (e.g., balloon) within group");
+ close(fd);
+ return -1;
+ }
+
+ if (!group->ram_block_discard_allowed) {
+ group->ram_block_discard_allowed = true;
+ vfio_ram_block_discard_disable(group->container, false);
+ }
+ }
+
+ vbasedev->fd = fd;
+ vbasedev->group = group;
+ QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
+
+ vbasedev->num_irqs = info->num_irqs;
+ vbasedev->num_regions = info->num_regions;
+ vbasedev->flags = info->flags;
+
+ trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs);
+
+ vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET);
+
+ return 0;
+}
+
+static void vfio_put_base_device(VFIODevice *vbasedev)
+{
+ if (!vbasedev->group) {
+ return;
+ }
+ QLIST_REMOVE(vbasedev, next);
+ vbasedev->group = NULL;
+ trace_vfio_put_base_device(vbasedev->fd);
+ close(vbasedev->fd);
+}
+
+/*
+ * Interfaces for IBM EEH (Enhanced Error Handling)
+ */
+static bool vfio_eeh_container_ok(VFIOContainer *container)
+{
+ /*
+ * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO
+ * implementation is broken if there are multiple groups in a
+ * container. The hardware works in units of Partitionable
+ * Endpoints (== IOMMU groups) and the EEH operations naively
+ * iterate across all groups in the container, without any logic
+ * to make sure the groups have their state synchronized. For
+ * certain operations (ENABLE) that might be ok, until an error
+ * occurs, but for others (GET_STATE) it's clearly broken.
+ */
+
+ /*
+ * XXX Once fixed kernels exist, test for them here
+ */
+
+ if (QLIST_EMPTY(&container->group_list)) {
+ return false;
+ }
+
+ if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) {
+ return false;
+ }
+
+ return true;
+}
+
+static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op)
+{
+ struct vfio_eeh_pe_op pe_op = {
+ .argsz = sizeof(pe_op),
+ .op = op,
+ };
+ int ret;
+
+ if (!vfio_eeh_container_ok(container)) {
+ error_report("vfio/eeh: EEH_PE_OP 0x%x: "
+ "kernel requires a container with exactly one group", op);
+ return -EPERM;
+ }
+
+ ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op);
+ if (ret < 0) {
+ error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op);
+ return -errno;
+ }
+
+ return ret;
+}
+
+static VFIOContainer *vfio_eeh_as_container(AddressSpace *as)
+{
+ VFIOAddressSpace *space = vfio_get_address_space(as);
+ VFIOContainer *container = NULL;
+
+ if (QLIST_EMPTY(&space->containers)) {
+ /* No containers to act on */
+ goto out;
+ }
+
+ container = QLIST_FIRST(&space->containers);
+
+ if (QLIST_NEXT(container, next)) {
+ /*
+ * We don't yet have logic to synchronize EEH state across
+ * multiple containers
+ */
+ container = NULL;
+ goto out;
+ }
+
+out:
+ vfio_put_address_space(space);
+ return container;
+}
+
+bool vfio_eeh_as_ok(AddressSpace *as)
+{
+ VFIOContainer *container = vfio_eeh_as_container(as);
+
+ return (container != NULL) && vfio_eeh_container_ok(container);
+}
+
+int vfio_eeh_as_op(AddressSpace *as, uint32_t op)
+{
+ VFIOContainer *container = vfio_eeh_as_container(as);
+
+ if (!container) {
+ return -ENODEV;
+ }
+ return vfio_eeh_container_op(container, op);
+}
+
+static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp)
+{
+ char *tmp, group_path[PATH_MAX], *group_name;
+ int ret, groupid;
+ ssize_t len;
+
+ tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev);
+ len = readlink(tmp, group_path, sizeof(group_path));
+ g_free(tmp);
+
+ if (len <= 0 || len >= sizeof(group_path)) {
+ ret = len < 0 ? -errno : -ENAMETOOLONG;
+ error_setg_errno(errp, -ret, "no iommu_group found");
+ return ret;
+ }
+
+ group_path[len] = 0;
+
+ group_name = basename(group_path);
+ if (sscanf(group_name, "%d", &groupid) != 1) {
+ error_setg_errno(errp, errno, "failed to read %s", group_path);
+ return -errno;
+ }
+ return groupid;
+}
+
+/*
+ * vfio_attach_device: attach a device to a security context
+ * @name and @vbasedev->name are likely to be different depending
+ * on the type of the device, hence the need for passing @name
+ */
+int vfio_attach_device(char *name, VFIODevice *vbasedev,
+ AddressSpace *as, Error **errp)
+{
+ int groupid = vfio_device_groupid(vbasedev, errp);
+ VFIODevice *vbasedev_iter;
+ VFIOGroup *group;
+ VFIOContainer *container;
+ int ret;
+
+ if (groupid < 0) {
+ return groupid;
+ }
+
+ trace_vfio_attach_device(vbasedev->name, groupid);
+
+ group = vfio_get_group(groupid, as, errp);
+ if (!group) {
+ return -ENOENT;
+ }
+
+ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
+ if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) {
+ error_setg(errp, "device is already attached");
+ vfio_put_group(group);
+ return -EBUSY;
+ }
+ }
+ ret = vfio_get_device(group, name, vbasedev, errp);
+ if (ret) {
+ vfio_put_group(group);
+ return ret;
+ }
+
+ container = group->container;
+ vbasedev->container = container;
+ QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next);
+ QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next);
+
+ return ret;
+}
+
+void vfio_detach_device(VFIODevice *vbasedev)
+{
+ VFIOGroup *group = vbasedev->group;
+
+ if (!vbasedev->container) {
+ return;
+ }
+
+ QLIST_REMOVE(vbasedev, global_next);
+ QLIST_REMOVE(vbasedev, container_next);
+ vbasedev->container = NULL;
+ trace_vfio_detach_device(vbasedev->name, group->groupid);
+ vfio_put_base_device(vbasedev);
+ vfio_put_group(group);
+}
diff --git a/hw/vfio/display.c b/hw/vfio/display.c
index 837d9e6..7a10fa8 100644
--- a/hw/vfio/display.c
+++ b/hw/vfio/display.c
@@ -544,3 +544,24 @@
vfio_display_edid_exit(vdev->dpy);
g_free(vdev->dpy);
}
+
+static bool migrate_needed(void *opaque)
+{
+ VFIODisplay *dpy = opaque;
+ bool ramfb_exists = dpy->ramfb != NULL;
+
+ /* see vfio_display_migration_needed() */
+ assert(ramfb_exists);
+ return ramfb_exists;
+}
+
+const VMStateDescription vfio_display_vmstate = {
+ .name = "VFIODisplay",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = migrate_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_STRUCT_POINTER(ramfb, VFIODisplay, ramfb_vmstate, RAMFBState),
+ VMSTATE_END_OF_LIST(),
+ }
+};
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c
new file mode 100644
index 0000000..7e5da21
--- /dev/null
+++ b/hw/vfio/helpers.c
@@ -0,0 +1,612 @@
+/*
+ * low level and IOMMU backend agnostic helpers used by VFIO devices,
+ * related to regions, interrupts, capabilities
+ *
+ * Copyright Red Hat, Inc. 2012
+ *
+ * Authors:
+ * Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Based on qemu-kvm device-assignment:
+ * Adapted for KVM by Qumranet.
+ * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
+ * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
+ * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
+ * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
+ * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
+ */
+
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+
+#include "hw/vfio/vfio-common.h"
+#include "hw/vfio/vfio.h"
+#include "hw/hw.h"
+#include "trace.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+
+/*
+ * Common VFIO interrupt disable
+ */
+void vfio_disable_irqindex(VFIODevice *vbasedev, int index)
+{
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
+ .index = index,
+ .start = 0,
+ .count = 0,
+ };
+
+ ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+}
+
+void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index)
+{
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK,
+ .index = index,
+ .start = 0,
+ .count = 1,
+ };
+
+ ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+}
+
+void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index)
+{
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK,
+ .index = index,
+ .start = 0,
+ .count = 1,
+ };
+
+ ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+}
+
+static inline const char *action_to_str(int action)
+{
+ switch (action) {
+ case VFIO_IRQ_SET_ACTION_MASK:
+ return "MASK";
+ case VFIO_IRQ_SET_ACTION_UNMASK:
+ return "UNMASK";
+ case VFIO_IRQ_SET_ACTION_TRIGGER:
+ return "TRIGGER";
+ default:
+ return "UNKNOWN ACTION";
+ }
+}
+
+static const char *index_to_str(VFIODevice *vbasedev, int index)
+{
+ if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) {
+ return NULL;
+ }
+
+ switch (index) {
+ case VFIO_PCI_INTX_IRQ_INDEX:
+ return "INTX";
+ case VFIO_PCI_MSI_IRQ_INDEX:
+ return "MSI";
+ case VFIO_PCI_MSIX_IRQ_INDEX:
+ return "MSIX";
+ case VFIO_PCI_ERR_IRQ_INDEX:
+ return "ERR";
+ case VFIO_PCI_REQ_IRQ_INDEX:
+ return "REQ";
+ default:
+ return NULL;
+ }
+}
+
+int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
+ int action, int fd, Error **errp)
+{
+ struct vfio_irq_set *irq_set;
+ int argsz, ret = 0;
+ const char *name;
+ int32_t *pfd;
+
+ argsz = sizeof(*irq_set) + sizeof(*pfd);
+
+ irq_set = g_malloc0(argsz);
+ irq_set->argsz = argsz;
+ irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | action;
+ irq_set->index = index;
+ irq_set->start = subindex;
+ irq_set->count = 1;
+ pfd = (int32_t *)&irq_set->data;
+ *pfd = fd;
+
+ if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) {
+ ret = -errno;
+ }
+ g_free(irq_set);
+
+ if (!ret) {
+ return 0;
+ }
+
+ error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure");
+
+ name = index_to_str(vbasedev, index);
+ if (name) {
+ error_prepend(errp, "%s-%d: ", name, subindex);
+ } else {
+ error_prepend(errp, "index %d-%d: ", index, subindex);
+ }
+ error_prepend(errp,
+ "Failed to %s %s eventfd signaling for interrupt ",
+ fd < 0 ? "tear down" : "set up", action_to_str(action));
+ return ret;
+}
+
+/*
+ * IO Port/MMIO - Beware of the endians, VFIO is always little endian
+ */
+void vfio_region_write(void *opaque, hwaddr addr,
+ uint64_t data, unsigned size)
+{
+ VFIORegion *region = opaque;
+ VFIODevice *vbasedev = region->vbasedev;
+ union {
+ uint8_t byte;
+ uint16_t word;
+ uint32_t dword;
+ uint64_t qword;
+ } buf;
+
+ switch (size) {
+ case 1:
+ buf.byte = data;
+ break;
+ case 2:
+ buf.word = cpu_to_le16(data);
+ break;
+ case 4:
+ buf.dword = cpu_to_le32(data);
+ break;
+ case 8:
+ buf.qword = cpu_to_le64(data);
+ break;
+ default:
+ hw_error("vfio: unsupported write size, %u bytes", size);
+ break;
+ }
+
+ if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
+ error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
+ ",%d) failed: %m",
+ __func__, vbasedev->name, region->nr,
+ addr, data, size);
+ }
+
+ trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
+
+ /*
+ * A read or write to a BAR always signals an INTx EOI. This will
+ * do nothing if not pending (including not in INTx mode). We assume
+ * that a BAR access is in response to an interrupt and that BAR
+ * accesses will service the interrupt. Unfortunately, we don't know
+ * which access will service the interrupt, so we're potentially
+ * getting quite a few host interrupts per guest interrupt.
+ */
+ vbasedev->ops->vfio_eoi(vbasedev);
+}
+
+uint64_t vfio_region_read(void *opaque,
+ hwaddr addr, unsigned size)
+{
+ VFIORegion *region = opaque;
+ VFIODevice *vbasedev = region->vbasedev;
+ union {
+ uint8_t byte;
+ uint16_t word;
+ uint32_t dword;
+ uint64_t qword;
+ } buf;
+ uint64_t data = 0;
+
+ if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) {
+ error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
+ __func__, vbasedev->name, region->nr,
+ addr, size);
+ return (uint64_t)-1;
+ }
+ switch (size) {
+ case 1:
+ data = buf.byte;
+ break;
+ case 2:
+ data = le16_to_cpu(buf.word);
+ break;
+ case 4:
+ data = le32_to_cpu(buf.dword);
+ break;
+ case 8:
+ data = le64_to_cpu(buf.qword);
+ break;
+ default:
+ hw_error("vfio: unsupported read size, %u bytes", size);
+ break;
+ }
+
+ trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data);
+
+ /* Same as write above */
+ vbasedev->ops->vfio_eoi(vbasedev);
+
+ return data;
+}
+
+const MemoryRegionOps vfio_region_ops = {
+ .read = vfio_region_read,
+ .write = vfio_region_write,
+ .endianness = DEVICE_LITTLE_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ },
+ .impl = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ },
+};
+
+int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size)
+{
+ vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size();
+ vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) /
+ BITS_PER_BYTE;
+ vbmap->bitmap = g_try_malloc0(vbmap->size);
+ if (!vbmap->bitmap) {
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+struct vfio_info_cap_header *
+vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id)
+{
+ struct vfio_info_cap_header *hdr;
+
+ for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
+ if (hdr->id == id) {
+ return hdr;
+ }
+ }
+
+ return NULL;
+}
+
+struct vfio_info_cap_header *
+vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)
+{
+ if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) {
+ return NULL;
+ }
+
+ return vfio_get_cap((void *)info, info->cap_offset, id);
+}
+
+struct vfio_info_cap_header *
+vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id)
+{
+ if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) {
+ return NULL;
+ }
+
+ return vfio_get_cap((void *)info, info->cap_offset, id);
+}
+
+static int vfio_setup_region_sparse_mmaps(VFIORegion *region,
+ struct vfio_region_info *info)
+{
+ struct vfio_info_cap_header *hdr;
+ struct vfio_region_info_cap_sparse_mmap *sparse;
+ int i, j;
+
+ hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP);
+ if (!hdr) {
+ return -ENODEV;
+ }
+
+ sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header);
+
+ trace_vfio_region_sparse_mmap_header(region->vbasedev->name,
+ region->nr, sparse->nr_areas);
+
+ region->mmaps = g_new0(VFIOMmap, sparse->nr_areas);
+
+ for (i = 0, j = 0; i < sparse->nr_areas; i++) {
+ if (sparse->areas[i].size) {
+ trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset,
+ sparse->areas[i].offset +
+ sparse->areas[i].size - 1);
+ region->mmaps[j].offset = sparse->areas[i].offset;
+ region->mmaps[j].size = sparse->areas[i].size;
+ j++;
+ }
+ }
+
+ region->nr_mmaps = j;
+ region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap));
+
+ return 0;
+}
+
+int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
+ int index, const char *name)
+{
+ struct vfio_region_info *info;
+ int ret;
+
+ ret = vfio_get_region_info(vbasedev, index, &info);
+ if (ret) {
+ return ret;
+ }
+
+ region->vbasedev = vbasedev;
+ region->flags = info->flags;
+ region->size = info->size;
+ region->fd_offset = info->offset;
+ region->nr = index;
+
+ if (region->size) {
+ region->mem = g_new0(MemoryRegion, 1);
+ memory_region_init_io(region->mem, obj, &vfio_region_ops,
+ region, name, region->size);
+
+ if (!vbasedev->no_mmap &&
+ region->flags & VFIO_REGION_INFO_FLAG_MMAP) {
+
+ ret = vfio_setup_region_sparse_mmaps(region, info);
+
+ if (ret) {
+ region->nr_mmaps = 1;
+ region->mmaps = g_new0(VFIOMmap, region->nr_mmaps);
+ region->mmaps[0].offset = 0;
+ region->mmaps[0].size = region->size;
+ }
+ }
+ }
+
+ g_free(info);
+
+ trace_vfio_region_setup(vbasedev->name, index, name,
+ region->flags, region->fd_offset, region->size);
+ return 0;
+}
+
+static void vfio_subregion_unmap(VFIORegion *region, int index)
+{
+ trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem),
+ region->mmaps[index].offset,
+ region->mmaps[index].offset +
+ region->mmaps[index].size - 1);
+ memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem);
+ munmap(region->mmaps[index].mmap, region->mmaps[index].size);
+ object_unparent(OBJECT(®ion->mmaps[index].mem));
+ region->mmaps[index].mmap = NULL;
+}
+
+int vfio_region_mmap(VFIORegion *region)
+{
+ int i, prot = 0;
+ char *name;
+
+ if (!region->mem) {
+ return 0;
+ }
+
+ prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0;
+ prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0;
+
+ for (i = 0; i < region->nr_mmaps; i++) {
+ region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot,
+ MAP_SHARED, region->vbasedev->fd,
+ region->fd_offset +
+ region->mmaps[i].offset);
+ if (region->mmaps[i].mmap == MAP_FAILED) {
+ int ret = -errno;
+
+ trace_vfio_region_mmap_fault(memory_region_name(region->mem), i,
+ region->fd_offset +
+ region->mmaps[i].offset,
+ region->fd_offset +
+ region->mmaps[i].offset +
+ region->mmaps[i].size - 1, ret);
+
+ region->mmaps[i].mmap = NULL;
+
+ for (i--; i >= 0; i--) {
+ vfio_subregion_unmap(region, i);
+ }
+
+ return ret;
+ }
+
+ name = g_strdup_printf("%s mmaps[%d]",
+ memory_region_name(region->mem), i);
+ memory_region_init_ram_device_ptr(®ion->mmaps[i].mem,
+ memory_region_owner(region->mem),
+ name, region->mmaps[i].size,
+ region->mmaps[i].mmap);
+ g_free(name);
+ memory_region_add_subregion(region->mem, region->mmaps[i].offset,
+ ®ion->mmaps[i].mem);
+
+ trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem),
+ region->mmaps[i].offset,
+ region->mmaps[i].offset +
+ region->mmaps[i].size - 1);
+ }
+
+ return 0;
+}
+
+void vfio_region_unmap(VFIORegion *region)
+{
+ int i;
+
+ if (!region->mem) {
+ return;
+ }
+
+ for (i = 0; i < region->nr_mmaps; i++) {
+ if (region->mmaps[i].mmap) {
+ vfio_subregion_unmap(region, i);
+ }
+ }
+}
+
+void vfio_region_exit(VFIORegion *region)
+{
+ int i;
+
+ if (!region->mem) {
+ return;
+ }
+
+ for (i = 0; i < region->nr_mmaps; i++) {
+ if (region->mmaps[i].mmap) {
+ memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem);
+ }
+ }
+
+ trace_vfio_region_exit(region->vbasedev->name, region->nr);
+}
+
+void vfio_region_finalize(VFIORegion *region)
+{
+ int i;
+
+ if (!region->mem) {
+ return;
+ }
+
+ for (i = 0; i < region->nr_mmaps; i++) {
+ if (region->mmaps[i].mmap) {
+ munmap(region->mmaps[i].mmap, region->mmaps[i].size);
+ object_unparent(OBJECT(®ion->mmaps[i].mem));
+ }
+ }
+
+ object_unparent(OBJECT(region->mem));
+
+ g_free(region->mem);
+ g_free(region->mmaps);
+
+ trace_vfio_region_finalize(region->vbasedev->name, region->nr);
+
+ region->mem = NULL;
+ region->mmaps = NULL;
+ region->nr_mmaps = 0;
+ region->size = 0;
+ region->flags = 0;
+ region->nr = 0;
+}
+
+void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled)
+{
+ int i;
+
+ if (!region->mem) {
+ return;
+ }
+
+ for (i = 0; i < region->nr_mmaps; i++) {
+ if (region->mmaps[i].mmap) {
+ memory_region_set_enabled(®ion->mmaps[i].mem, enabled);
+ }
+ }
+
+ trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem),
+ enabled);
+}
+
+int vfio_get_region_info(VFIODevice *vbasedev, int index,
+ struct vfio_region_info **info)
+{
+ size_t argsz = sizeof(struct vfio_region_info);
+
+ *info = g_malloc0(argsz);
+
+ (*info)->index = index;
+retry:
+ (*info)->argsz = argsz;
+
+ if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
+ g_free(*info);
+ *info = NULL;
+ return -errno;
+ }
+
+ if ((*info)->argsz > argsz) {
+ argsz = (*info)->argsz;
+ *info = g_realloc(*info, argsz);
+
+ goto retry;
+ }
+
+ return 0;
+}
+
+int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
+ uint32_t subtype, struct vfio_region_info **info)
+{
+ int i;
+
+ for (i = 0; i < vbasedev->num_regions; i++) {
+ struct vfio_info_cap_header *hdr;
+ struct vfio_region_info_cap_type *cap_type;
+
+ if (vfio_get_region_info(vbasedev, i, info)) {
+ continue;
+ }
+
+ hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE);
+ if (!hdr) {
+ g_free(*info);
+ continue;
+ }
+
+ cap_type = container_of(hdr, struct vfio_region_info_cap_type, header);
+
+ trace_vfio_get_dev_region(vbasedev->name, i,
+ cap_type->type, cap_type->subtype);
+
+ if (cap_type->type == type && cap_type->subtype == subtype) {
+ return 0;
+ }
+
+ g_free(*info);
+ }
+
+ *info = NULL;
+ return -ENODEV;
+}
+
+bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type)
+{
+ struct vfio_region_info *info = NULL;
+ bool ret = false;
+
+ if (!vfio_get_region_info(vbasedev, region, &info)) {
+ if (vfio_get_region_info_cap(info, cap_type)) {
+ ret = true;
+ }
+ g_free(info);
+ }
+
+ return ret;
+}
diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build
index da9af29..2a6912c 100644
--- a/hw/vfio/meson.build
+++ b/hw/vfio/meson.build
@@ -1,6 +1,8 @@
vfio_ss = ss.source_set()
vfio_ss.add(files(
+ 'helpers.c',
'common.c',
+ 'container.c',
'spapr.c',
'migration.c',
))
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 898296f..b27011c 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2675,6 +2675,33 @@
return msix_present(pdev);
}
+static bool vfio_display_migration_needed(void *opaque)
+{
+ VFIOPCIDevice *vdev = opaque;
+
+ /*
+ * We need to migrate the VFIODisplay object if ramfb *migration* was
+ * explicitly requested (in which case we enforced both ramfb=on and
+ * display=on), or ramfb migration was left at the default "auto"
+ * setting, and *ramfb* was explicitly requested (in which case we
+ * enforced display=on).
+ */
+ return vdev->ramfb_migrate == ON_OFF_AUTO_ON ||
+ (vdev->ramfb_migrate == ON_OFF_AUTO_AUTO && vdev->enable_ramfb);
+}
+
+const VMStateDescription vmstate_vfio_display = {
+ .name = "VFIOPCIDevice/VFIODisplay",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = vfio_display_migration_needed,
+ .fields = (VMStateField[]){
+ VMSTATE_STRUCT_POINTER(dpy, VFIOPCIDevice, vfio_display_vmstate,
+ VFIODisplay),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
const VMStateDescription vmstate_vfio_pci_config = {
.name = "VFIOPCIDevice",
.version_id = 1,
@@ -2683,6 +2710,10 @@
VMSTATE_PCI_DEVICE(pdev, VFIOPCIDevice),
VMSTATE_MSIX_TEST(pdev, VFIOPCIDevice, vfio_msix_present),
VMSTATE_END_OF_LIST()
+ },
+ .subsections = (const VMStateDescription * []) {
+ &vmstate_vfio_display,
+ NULL
}
};
@@ -2895,10 +2926,10 @@
static void vfio_pci_put_device(VFIOPCIDevice *vdev)
{
+ vfio_detach_device(&vdev->vbasedev);
+
g_free(vdev->vbasedev.name);
g_free(vdev->msix);
-
- vfio_put_base_device(&vdev->vbasedev);
}
static void vfio_err_notifier_handler(void *opaque)
@@ -3045,13 +3076,9 @@
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
- VFIODevice *vbasedev_iter;
- VFIOGroup *group;
- char *tmp, *subsys, group_path[PATH_MAX], *group_name;
+ char *tmp, *subsys;
Error *err = NULL;
- ssize_t len;
struct stat st;
- int groupid;
int i, ret;
bool is_mdev;
char uuid[UUID_FMT_LEN];
@@ -3082,39 +3109,6 @@
vbasedev->type = VFIO_DEVICE_TYPE_PCI;
vbasedev->dev = DEVICE(vdev);
- tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev);
- len = readlink(tmp, group_path, sizeof(group_path));
- g_free(tmp);
-
- if (len <= 0 || len >= sizeof(group_path)) {
- error_setg_errno(errp, len < 0 ? errno : ENAMETOOLONG,
- "no iommu_group found");
- goto error;
- }
-
- group_path[len] = 0;
-
- group_name = basename(group_path);
- if (sscanf(group_name, "%d", &groupid) != 1) {
- error_setg_errno(errp, errno, "failed to read %s", group_path);
- goto error;
- }
-
- trace_vfio_realize(vbasedev->name, groupid);
-
- group = vfio_get_group(groupid, pci_device_iommu_address_space(pdev), errp);
- if (!group) {
- goto error;
- }
-
- QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
- if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) {
- error_setg(errp, "device is already attached");
- vfio_put_group(group);
- goto error;
- }
- }
-
/*
* Mediated devices *might* operate compatibly with discarding of RAM, but
* we cannot know for certain, it depends on whether the mdev vendor driver
@@ -3132,7 +3126,6 @@
if (vbasedev->ram_block_discard_allowed && !is_mdev) {
error_setg(errp, "x-balloon-allowed only potentially compatible "
"with mdev devices");
- vfio_put_group(group);
goto error;
}
@@ -3143,10 +3136,10 @@
name = g_strdup(vbasedev->name);
}
- ret = vfio_get_device(group, name, vbasedev, errp);
+ ret = vfio_attach_device(name, vbasedev,
+ pci_device_iommu_address_space(pdev), errp);
g_free(name);
if (ret) {
- vfio_put_group(group);
goto error;
}
@@ -3338,6 +3331,20 @@
}
}
+ if (vdev->ramfb_migrate == ON_OFF_AUTO_ON && !vdev->enable_ramfb) {
+ warn_report("x-ramfb-migrate=on but ramfb=off. "
+ "Forcing x-ramfb-migrate to off.");
+ vdev->ramfb_migrate = ON_OFF_AUTO_OFF;
+ }
+ if (vbasedev->enable_migration == ON_OFF_AUTO_OFF) {
+ if (vdev->ramfb_migrate == ON_OFF_AUTO_AUTO) {
+ vdev->ramfb_migrate = ON_OFF_AUTO_OFF;
+ } else if (vdev->ramfb_migrate == ON_OFF_AUTO_ON) {
+ error_setg(errp, "x-ramfb-migrate requires enable-migration");
+ goto out_deregister;
+ }
+ }
+
if (!pdev->failover_pair_id) {
if (!vfio_migration_realize(vbasedev, errp)) {
goto out_deregister;
@@ -3371,7 +3378,6 @@
static void vfio_instance_finalize(Object *obj)
{
VFIOPCIDevice *vdev = VFIO_PCI(obj);
- VFIOGroup *group = vdev->vbasedev.group;
vfio_display_finalize(vdev);
vfio_bars_finalize(vdev);
@@ -3385,7 +3391,6 @@
* g_free(vdev->igd_opregion);
*/
vfio_pci_put_device(vdev);
- vfio_put_group(group);
}
static void vfio_exitfn(PCIDevice *pdev)
@@ -3551,6 +3556,8 @@
static Property vfio_pci_dev_nohotplug_properties[] = {
DEFINE_PROP_BOOL("ramfb", VFIOPCIDevice, enable_ramfb, false),
+ DEFINE_PROP_ON_OFF_AUTO("x-ramfb-migrate", VFIOPCIDevice, ramfb_migrate,
+ ON_OFF_AUTO_AUTO),
DEFINE_PROP_END_OF_LIST(),
};
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 0d89eb7..fba8737 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -174,6 +174,7 @@
bool no_kvm_ioeventfd;
bool no_vfio_ioeventfd;
bool enable_ramfb;
+ OnOffAuto ramfb_migrate;
bool defer_kvm_irq_routing;
bool clear_parent_atomics_on_exit;
VFIODisplay *dpy;
@@ -227,4 +228,6 @@
int vfio_display_probe(VFIOPCIDevice *vdev, Error **errp);
void vfio_display_finalize(VFIOPCIDevice *vdev);
+extern const VMStateDescription vfio_display_vmstate;
+
#endif /* HW_VFIO_VFIO_PCI_H */
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
index 5af73f9..8e3d4ac 100644
--- a/hw/vfio/platform.c
+++ b/hw/vfio/platform.c
@@ -529,12 +529,7 @@
*/
static int vfio_base_device_init(VFIODevice *vbasedev, Error **errp)
{
- VFIOGroup *group;
- VFIODevice *vbasedev_iter;
- char *tmp, group_path[PATH_MAX], *group_name;
- ssize_t len;
struct stat st;
- int groupid;
int ret;
/* @sysfsdev takes precedence over @host */
@@ -557,47 +552,15 @@
return -errno;
}
- tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev);
- len = readlink(tmp, group_path, sizeof(group_path));
- g_free(tmp);
-
- if (len < 0 || len >= sizeof(group_path)) {
- ret = len < 0 ? -errno : -ENAMETOOLONG;
- error_setg_errno(errp, -ret, "no iommu_group found");
- return ret;
- }
-
- group_path[len] = 0;
-
- group_name = basename(group_path);
- if (sscanf(group_name, "%d", &groupid) != 1) {
- error_setg_errno(errp, errno, "failed to read %s", group_path);
- return -errno;
- }
-
- trace_vfio_platform_base_device_init(vbasedev->name, groupid);
-
- group = vfio_get_group(groupid, &address_space_memory, errp);
- if (!group) {
- return -ENOENT;
- }
-
- QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
- if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) {
- error_setg(errp, "device is already attached");
- vfio_put_group(group);
- return -EBUSY;
- }
- }
- ret = vfio_get_device(group, vbasedev->name, vbasedev, errp);
+ ret = vfio_attach_device(vbasedev->name, vbasedev,
+ &address_space_memory, errp);
if (ret) {
- vfio_put_group(group);
return ret;
}
ret = vfio_populate_device(vbasedev, errp);
if (ret) {
- vfio_put_group(group);
+ vfio_detach_device(vbasedev);
}
return ret;
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 0ba3c5a..0eb2387 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -37,7 +37,8 @@
vfio_pci_hot_reset_result(const char *name, const char *result) "%s hot reset: %s"
vfio_populate_device_config(const char *name, unsigned long size, unsigned long offset, unsigned long flags) "Device %s config:\n size: 0x%lx, offset: 0x%lx, flags: 0x%lx"
vfio_populate_device_get_irq_info_failure(const char *errstr) "VFIO_DEVICE_GET_IRQ_INFO failure: %s"
-vfio_realize(const char *name, int group_id) " (%s) group %d"
+vfio_attach_device(const char *name, int group_id) " (%s) group %d"
+vfio_detach_device(const char *name, int group_id) " (%s) group %d"
vfio_mdev(const char *name, bool is_mdev) " (%s) is_mdev %d"
vfio_add_ext_cap_dropped(const char *name, uint16_t cap, uint16_t offset) "%s 0x%x@0x%x"
vfio_pci_reset(const char *name) " (%s)"
@@ -120,7 +121,6 @@
vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64
# platform.c
-vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d"
vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = %s"
vfio_platform_eoi(int pin, int fd) "EOI IRQ pin %d (fd=%d)"
vfio_platform_intp_mmap_enable(int pin) "IRQ #%d still active, stay in slow path"
diff --git a/hw/xen/meson.build b/hw/xen/meson.build
index 277f9f2..d887fa9 100644
--- a/hw/xen/meson.build
+++ b/hw/xen/meson.build
@@ -12,6 +12,10 @@
))
xen_specific_ss = ss.source_set()
+xen_specific_ss.add(files(
+ 'xen-mapcache.c',
+ 'xen-hvm-common.c',
+))
if have_xen_pci_passthrough
xen_specific_ss.add(files(
'xen-host-pci-device.c',
@@ -26,10 +30,3 @@
endif
specific_ss.add_all(when: ['CONFIG_XEN', xen], if_true: xen_specific_ss)
-
-xen_ss = ss.source_set()
-
-xen_ss.add(when: 'CONFIG_XEN', if_true: files(
- 'xen-mapcache.c',
- 'xen-hvm-common.c',
-))
diff --git a/include/hw/display/ramfb.h b/include/hw/display/ramfb.h
index b33a2c4..a7e0019 100644
--- a/include/hw/display/ramfb.h
+++ b/include/hw/display/ramfb.h
@@ -1,11 +1,15 @@
#ifndef RAMFB_H
#define RAMFB_H
+#include "migration/vmstate.h"
+
/* ramfb.c */
typedef struct RAMFBState RAMFBState;
void ramfb_display_update(QemuConsole *con, RAMFBState *s);
RAMFBState *ramfb_setup(Error **errp);
+extern const VMStateDescription ramfb_vmstate;
+
/* ramfb-standalone.c */
#define TYPE_RAMFB_DEVICE "ramfb"
diff --git a/include/hw/s390x/vfio-ccw.h b/include/hw/s390x/vfio-ccw.h
index 63a909e..4209d27 100644
--- a/include/hw/s390x/vfio-ccw.h
+++ b/include/hw/s390x/vfio-ccw.h
@@ -22,6 +22,4 @@
#define TYPE_VFIO_CCW "vfio-ccw"
OBJECT_DECLARE_SIMPLE_TYPE(VFIOCCWDevice, VFIO_CCW)
-#define TYPE_VFIO_CCW "vfio-ccw"
-
#endif
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index e9b8954..7780b90 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -98,6 +98,7 @@
QLIST_HEAD(, VFIOGroup) group_list;
QLIST_HEAD(, VFIORamDiscardListener) vrdl_list;
QLIST_ENTRY(VFIOContainer) next;
+ QLIST_HEAD(, VFIODevice) device_list;
} VFIOContainer;
typedef struct VFIOGuestIOMMU {
@@ -129,7 +130,10 @@
typedef struct VFIODevice {
QLIST_ENTRY(VFIODevice) next;
+ QLIST_ENTRY(VFIODevice) container_next;
+ QLIST_ENTRY(VFIODevice) global_next;
struct VFIOGroup *group;
+ VFIOContainer *container;
char *sysfsdev;
char *name;
DeviceState *dev;
@@ -196,7 +200,36 @@
} dmabuf;
} VFIODisplay;
-void vfio_put_base_device(VFIODevice *vbasedev);
+typedef struct {
+ unsigned long *bitmap;
+ hwaddr size;
+ hwaddr pages;
+} VFIOBitmap;
+
+void vfio_host_win_add(VFIOContainer *container,
+ hwaddr min_iova, hwaddr max_iova,
+ uint64_t iova_pgsizes);
+int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova,
+ hwaddr max_iova);
+VFIOAddressSpace *vfio_get_address_space(AddressSpace *as);
+void vfio_put_address_space(VFIOAddressSpace *space);
+bool vfio_devices_all_running_and_saving(VFIOContainer *container);
+
+/* container->fd */
+int vfio_dma_unmap(VFIOContainer *container, hwaddr iova,
+ ram_addr_t size, IOMMUTLBEntry *iotlb);
+int vfio_dma_map(VFIOContainer *container, hwaddr iova,
+ ram_addr_t size, void *vaddr, bool readonly);
+int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start);
+int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap,
+ hwaddr iova, hwaddr size);
+
+int vfio_container_add_section_window(VFIOContainer *container,
+ MemoryRegionSection *section,
+ Error **errp);
+void vfio_container_del_section_window(VFIOContainer *container,
+ MemoryRegionSection *section);
+
void vfio_disable_irqindex(VFIODevice *vbasedev, int index);
void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index);
void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index);
@@ -214,15 +247,22 @@
void vfio_region_exit(VFIORegion *region);
void vfio_region_finalize(VFIORegion *region);
void vfio_reset_handler(void *opaque);
-VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);
-void vfio_put_group(VFIOGroup *group);
struct vfio_device_info *vfio_get_device_info(int fd);
-int vfio_get_device(VFIOGroup *group, const char *name,
- VFIODevice *vbasedev, Error **errp);
+int vfio_attach_device(char *name, VFIODevice *vbasedev,
+ AddressSpace *as, Error **errp);
+void vfio_detach_device(VFIODevice *vbasedev);
+
+int vfio_kvm_device_add_fd(int fd, Error **errp);
+int vfio_kvm_device_del_fd(int fd, Error **errp);
extern const MemoryRegionOps vfio_region_ops;
typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
+typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList;
extern VFIOGroupList vfio_group_list;
+extern VFIODeviceList vfio_device_list;
+
+extern const MemoryListener vfio_memory_listener;
+extern int vfio_kvm_device_fd;
bool vfio_mig_active(void);
int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp);
@@ -245,6 +285,8 @@
unsigned int *avail);
struct vfio_info_cap_header *
vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id);
+struct vfio_info_cap_header *
+vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id);
#endif
extern const MemoryListener vfio_prereg_listener;
@@ -257,4 +299,12 @@
bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp);
void vfio_migration_exit(VFIODevice *vbasedev);
+int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size);
+bool vfio_devices_all_running_and_mig_active(VFIOContainer *container);
+bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container);
+int vfio_devices_query_dirty_bitmap(VFIOContainer *container,
+ VFIOBitmap *vbmap, hwaddr iova,
+ hwaddr size);
+int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
+ uint64_t size, ram_addr_t ram_addr);
#endif /* HW_VFIO_VFIO_COMMON_H */
diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h
index 1109482..c797f0d 100644
--- a/include/qemu/compiler.h
+++ b/include/qemu/compiler.h
@@ -212,4 +212,19 @@
# define QEMU_USED
#endif
+/*
+ * Ugly CPP trick that is like "defined FOO", but also works in C
+ * code. Useful to replace #ifdef with "if" statements; assumes
+ * the symbol was defined with Meson's "config.set()", so it is empty
+ * if defined.
+ */
+#define IS_ENABLED(x) IS_EMPTY(x)
+
+#define IS_EMPTY_JUNK_ junk,
+#define IS_EMPTY(value) IS_EMPTY_(IS_EMPTY_JUNK_##value)
+
+/* Expands to either SECOND_ARG(junk, 1, 0) or SECOND_ARG(IS_EMPTY_JUNK_CONFIG_FOO 1, 0) */
+#define SECOND_ARG(first, second, ...) second
+#define IS_EMPTY_(junk_maybecomma) SECOND_ARG(junk_maybecomma 1, 0)
+
#endif /* COMPILER_H */
diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h
new file mode 100644
index 0000000..218bf7a
--- /dev/null
+++ b/linux-headers/linux/iommufd.h
@@ -0,0 +1,444 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES.
+ */
+#ifndef _IOMMUFD_H
+#define _IOMMUFD_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define IOMMUFD_TYPE (';')
+
+/**
+ * DOC: General ioctl format
+ *
+ * The ioctl interface follows a general format to allow for extensibility. Each
+ * ioctl is passed in a structure pointer as the argument providing the size of
+ * the structure in the first u32. The kernel checks that any structure space
+ * beyond what it understands is 0. This allows userspace to use the backward
+ * compatible portion while consistently using the newer, larger, structures.
+ *
+ * ioctls use a standard meaning for common errnos:
+ *
+ * - ENOTTY: The IOCTL number itself is not supported at all
+ * - E2BIG: The IOCTL number is supported, but the provided structure has
+ * non-zero in a part the kernel does not understand.
+ * - EOPNOTSUPP: The IOCTL number is supported, and the structure is
+ * understood, however a known field has a value the kernel does not
+ * understand or support.
+ * - EINVAL: Everything about the IOCTL was understood, but a field is not
+ * correct.
+ * - ENOENT: An ID or IOVA provided does not exist.
+ * - ENOMEM: Out of memory.
+ * - EOVERFLOW: Mathematics overflowed.
+ *
+ * As well as additional errnos, within specific ioctls.
+ */
+enum {
+ IOMMUFD_CMD_BASE = 0x80,
+ IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE,
+ IOMMUFD_CMD_IOAS_ALLOC,
+ IOMMUFD_CMD_IOAS_ALLOW_IOVAS,
+ IOMMUFD_CMD_IOAS_COPY,
+ IOMMUFD_CMD_IOAS_IOVA_RANGES,
+ IOMMUFD_CMD_IOAS_MAP,
+ IOMMUFD_CMD_IOAS_UNMAP,
+ IOMMUFD_CMD_OPTION,
+ IOMMUFD_CMD_VFIO_IOAS,
+ IOMMUFD_CMD_HWPT_ALLOC,
+ IOMMUFD_CMD_GET_HW_INFO,
+};
+
+/**
+ * struct iommu_destroy - ioctl(IOMMU_DESTROY)
+ * @size: sizeof(struct iommu_destroy)
+ * @id: iommufd object ID to destroy. Can be any destroyable object type.
+ *
+ * Destroy any object held within iommufd.
+ */
+struct iommu_destroy {
+ __u32 size;
+ __u32 id;
+};
+#define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY)
+
+/**
+ * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC)
+ * @size: sizeof(struct iommu_ioas_alloc)
+ * @flags: Must be 0
+ * @out_ioas_id: Output IOAS ID for the allocated object
+ *
+ * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (IOVA)
+ * to memory mapping.
+ */
+struct iommu_ioas_alloc {
+ __u32 size;
+ __u32 flags;
+ __u32 out_ioas_id;
+};
+#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC)
+
+/**
+ * struct iommu_iova_range - ioctl(IOMMU_IOVA_RANGE)
+ * @start: First IOVA
+ * @last: Inclusive last IOVA
+ *
+ * An interval in IOVA space.
+ */
+struct iommu_iova_range {
+ __aligned_u64 start;
+ __aligned_u64 last;
+};
+
+/**
+ * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES)
+ * @size: sizeof(struct iommu_ioas_iova_ranges)
+ * @ioas_id: IOAS ID to read ranges from
+ * @num_iovas: Input/Output total number of ranges in the IOAS
+ * @__reserved: Must be 0
+ * @allowed_iovas: Pointer to the output array of struct iommu_iova_range
+ * @out_iova_alignment: Minimum alignment required for mapping IOVA
+ *
+ * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these ranges
+ * is not allowed. num_iovas will be set to the total number of iovas and
+ * the allowed_iovas[] will be filled in as space permits.
+ *
+ * The allowed ranges are dependent on the HW path the DMA operation takes, and
+ * can change during the lifetime of the IOAS. A fresh empty IOAS will have a
+ * full range, and each attached device will narrow the ranges based on that
+ * device's HW restrictions. Detaching a device can widen the ranges. Userspace
+ * should query ranges after every attach/detach to know what IOVAs are valid
+ * for mapping.
+ *
+ * On input num_iovas is the length of the allowed_iovas array. On output it is
+ * the total number of iovas filled in. The ioctl will return -EMSGSIZE and set
+ * num_iovas to the required value if num_iovas is too small. In this case the
+ * caller should allocate a larger output array and re-issue the ioctl.
+ *
+ * out_iova_alignment returns the minimum IOVA alignment that can be given
+ * to IOMMU_IOAS_MAP/COPY. IOVA's must satisfy::
+ *
+ * starting_iova % out_iova_alignment == 0
+ * (starting_iova + length) % out_iova_alignment == 0
+ *
+ * out_iova_alignment can be 1 indicating any IOVA is allowed. It cannot
+ * be higher than the system PAGE_SIZE.
+ */
+struct iommu_ioas_iova_ranges {
+ __u32 size;
+ __u32 ioas_id;
+ __u32 num_iovas;
+ __u32 __reserved;
+ __aligned_u64 allowed_iovas;
+ __aligned_u64 out_iova_alignment;
+};
+#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RANGES)
+
+/**
+ * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS)
+ * @size: sizeof(struct iommu_ioas_allow_iovas)
+ * @ioas_id: IOAS ID to allow IOVAs from
+ * @num_iovas: Input/Output total number of ranges in the IOAS
+ * @__reserved: Must be 0
+ * @allowed_iovas: Pointer to array of struct iommu_iova_range
+ *
+ * Ensure a range of IOVAs are always available for allocation. If this call
+ * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA ranges
+ * that are narrower than the ranges provided here. This call will fail if
+ * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges.
+ *
+ * When an IOAS is first created the IOVA_RANGES will be maximally sized, and as
+ * devices are attached the IOVA will narrow based on the device restrictions.
+ * When an allowed range is specified any narrowing will be refused, ie device
+ * attachment can fail if the device requires limiting within the allowed range.
+ *
+ * Automatic IOVA allocation is also impacted by this call. MAP will only
+ * allocate within the allowed IOVAs if they are present.
+ *
+ * This call replaces the entire allowed list with the given list.
+ */
+struct iommu_ioas_allow_iovas {
+ __u32 size;
+ __u32 ioas_id;
+ __u32 num_iovas;
+ __u32 __reserved;
+ __aligned_u64 allowed_iovas;
+};
+#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IOVAS)
+
+/**
+ * enum iommufd_ioas_map_flags - Flags for map and copy
+ * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropriate
+ * IOVA to place the mapping at
+ * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping
+ * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping
+ */
+enum iommufd_ioas_map_flags {
+ IOMMU_IOAS_MAP_FIXED_IOVA = 1 << 0,
+ IOMMU_IOAS_MAP_WRITEABLE = 1 << 1,
+ IOMMU_IOAS_MAP_READABLE = 1 << 2,
+};
+
+/**
+ * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP)
+ * @size: sizeof(struct iommu_ioas_map)
+ * @flags: Combination of enum iommufd_ioas_map_flags
+ * @ioas_id: IOAS ID to change the mapping of
+ * @__reserved: Must be 0
+ * @user_va: Userspace pointer to start mapping from
+ * @length: Number of bytes to map
+ * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is set
+ * then this must be provided as input.
+ *
+ * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified then the
+ * mapping will be established at iova, otherwise a suitable location based on
+ * the reserved and allowed lists will be automatically selected and returned in
+ * iova.
+ *
+ * If IOMMU_IOAS_MAP_FIXED_IOVA is specified then the iova range must currently
+ * be unused, existing IOVA cannot be replaced.
+ */
+struct iommu_ioas_map {
+ __u32 size;
+ __u32 flags;
+ __u32 ioas_id;
+ __u32 __reserved;
+ __aligned_u64 user_va;
+ __aligned_u64 length;
+ __aligned_u64 iova;
+};
+#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP)
+
+/**
+ * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY)
+ * @size: sizeof(struct iommu_ioas_copy)
+ * @flags: Combination of enum iommufd_ioas_map_flags
+ * @dst_ioas_id: IOAS ID to change the mapping of
+ * @src_ioas_id: IOAS ID to copy from
+ * @length: Number of bytes to copy and map
+ * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is
+ * set then this must be provided as input.
+ * @src_iova: IOVA to start the copy
+ *
+ * Copy an already existing mapping from src_ioas_id and establish it in
+ * dst_ioas_id. The src iova/length must exactly match a range used with
+ * IOMMU_IOAS_MAP.
+ *
+ * This may be used to efficiently clone a subset of an IOAS to another, or as a
+ * kind of 'cache' to speed up mapping. Copy has an efficiency advantage over
+ * establishing equivalent new mappings, as internal resources are shared, and
+ * the kernel will pin the user memory only once.
+ */
+struct iommu_ioas_copy {
+ __u32 size;
+ __u32 flags;
+ __u32 dst_ioas_id;
+ __u32 src_ioas_id;
+ __aligned_u64 length;
+ __aligned_u64 dst_iova;
+ __aligned_u64 src_iova;
+};
+#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY)
+
+/**
+ * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP)
+ * @size: sizeof(struct iommu_ioas_unmap)
+ * @ioas_id: IOAS ID to change the mapping of
+ * @iova: IOVA to start the unmapping at
+ * @length: Number of bytes to unmap, and return back the bytes unmapped
+ *
+ * Unmap an IOVA range. The iova/length must be a superset of a previously
+ * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or
+ * truncating ranges is not allowed. The values 0 to U64_MAX will unmap
+ * everything.
+ */
+struct iommu_ioas_unmap {
+ __u32 size;
+ __u32 ioas_id;
+ __aligned_u64 iova;
+ __aligned_u64 length;
+};
+#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP)
+
+/**
+ * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and
+ * ioctl(IOMMU_OPTION_HUGE_PAGES)
+ * @IOMMU_OPTION_RLIMIT_MODE:
+ * Change how RLIMIT_MEMLOCK accounting works. The caller must have privilege
+ * to invoke this. Value 0 (default) is user based accouting, 1 uses process
+ * based accounting. Global option, object_id must be 0
+ * @IOMMU_OPTION_HUGE_PAGES:
+ * Value 1 (default) allows contiguous pages to be combined when generating
+ * iommu mappings. Value 0 disables combining, everything is mapped to
+ * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS
+ * option, the object_id must be the IOAS ID.
+ */
+enum iommufd_option {
+ IOMMU_OPTION_RLIMIT_MODE = 0,
+ IOMMU_OPTION_HUGE_PAGES = 1,
+};
+
+/**
+ * enum iommufd_option_ops - ioctl(IOMMU_OPTION_OP_SET) and
+ * ioctl(IOMMU_OPTION_OP_GET)
+ * @IOMMU_OPTION_OP_SET: Set the option's value
+ * @IOMMU_OPTION_OP_GET: Get the option's value
+ */
+enum iommufd_option_ops {
+ IOMMU_OPTION_OP_SET = 0,
+ IOMMU_OPTION_OP_GET = 1,
+};
+
+/**
+ * struct iommu_option - iommu option multiplexer
+ * @size: sizeof(struct iommu_option)
+ * @option_id: One of enum iommufd_option
+ * @op: One of enum iommufd_option_ops
+ * @__reserved: Must be 0
+ * @object_id: ID of the object if required
+ * @val64: Option value to set or value returned on get
+ *
+ * Change a simple option value. This multiplexor allows controlling options
+ * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP_GET
+ * will return the current value.
+ */
+struct iommu_option {
+ __u32 size;
+ __u32 option_id;
+ __u16 op;
+ __u16 __reserved;
+ __u32 object_id;
+ __aligned_u64 val64;
+};
+#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION)
+
+/**
+ * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls
+ * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS
+ * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS
+ * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility
+ */
+enum iommufd_vfio_ioas_op {
+ IOMMU_VFIO_IOAS_GET = 0,
+ IOMMU_VFIO_IOAS_SET = 1,
+ IOMMU_VFIO_IOAS_CLEAR = 2,
+};
+
+/**
+ * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS)
+ * @size: sizeof(struct iommu_vfio_ioas)
+ * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set
+ * For IOMMU_VFIO_IOAS_GET will output the IOAS ID
+ * @op: One of enum iommufd_vfio_ioas_op
+ * @__reserved: Must be 0
+ *
+ * The VFIO compatibility support uses a single ioas because VFIO APIs do not
+ * support the ID field. Set or Get the IOAS that VFIO compatibility will use.
+ * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the
+ * compatibility ioas, either by taking what is already set, or auto creating
+ * one. From then on VFIO will continue to use that ioas and is not effected by
+ * this ioctl. SET or CLEAR does not destroy any auto-created IOAS.
+ */
+struct iommu_vfio_ioas {
+ __u32 size;
+ __u32 ioas_id;
+ __u16 op;
+ __u16 __reserved;
+};
+#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS)
+
+/**
+ * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC)
+ * @size: sizeof(struct iommu_hwpt_alloc)
+ * @flags: Must be 0
+ * @dev_id: The device to allocate this HWPT for
+ * @pt_id: The IOAS to connect this HWPT to
+ * @out_hwpt_id: The ID of the new HWPT
+ * @__reserved: Must be 0
+ *
+ * Explicitly allocate a hardware page table object. This is the same object
+ * type that is returned by iommufd_device_attach() and represents the
+ * underlying iommu driver's iommu_domain kernel object.
+ *
+ * A HWPT will be created with the IOVA mappings from the given IOAS.
+ */
+struct iommu_hwpt_alloc {
+ __u32 size;
+ __u32 flags;
+ __u32 dev_id;
+ __u32 pt_id;
+ __u32 out_hwpt_id;
+ __u32 __reserved;
+};
+#define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC)
+
+/**
+ * struct iommu_hw_info_vtd - Intel VT-d hardware information
+ *
+ * @flags: Must be 0
+ * @__reserved: Must be 0
+ *
+ * @cap_reg: Value of Intel VT-d capability register defined in VT-d spec
+ * section 11.4.2 Capability Register.
+ * @ecap_reg: Value of Intel VT-d capability register defined in VT-d spec
+ * section 11.4.3 Extended Capability Register.
+ *
+ * User needs to understand the Intel VT-d specification to decode the
+ * register value.
+ */
+struct iommu_hw_info_vtd {
+ __u32 flags;
+ __u32 __reserved;
+ __aligned_u64 cap_reg;
+ __aligned_u64 ecap_reg;
+};
+
+/**
+ * enum iommu_hw_info_type - IOMMU Hardware Info Types
+ * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardware
+ * info
+ * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type
+ */
+enum iommu_hw_info_type {
+ IOMMU_HW_INFO_TYPE_NONE,
+ IOMMU_HW_INFO_TYPE_INTEL_VTD,
+};
+
+/**
+ * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO)
+ * @size: sizeof(struct iommu_hw_info)
+ * @flags: Must be 0
+ * @dev_id: The device bound to the iommufd
+ * @data_len: Input the length of a user buffer in bytes. Output the length of
+ * data that kernel supports
+ * @data_uptr: User pointer to a user-space buffer used by the kernel to fill
+ * the iommu type specific hardware information data
+ * @out_data_type: Output the iommu hardware info type as defined in the enum
+ * iommu_hw_info_type.
+ * @__reserved: Must be 0
+ *
+ * Query an iommu type specific hardware information data from an iommu behind
+ * a given device that has been bound to iommufd. This hardware info data will
+ * be used to sync capabilities between the virtual iommu and the physical
+ * iommu, e.g. a nested translation setup needs to check the hardware info, so
+ * a guest stage-1 page table can be compatible with the physical iommu.
+ *
+ * To capture an iommu type specific hardware information data, @data_uptr and
+ * its length @data_len must be provided. Trailing bytes will be zeroed if the
+ * user buffer is larger than the data that kernel has. Otherwise, kernel only
+ * fills the buffer using the given length in @data_len. If the ioctl succeeds,
+ * @data_len will be updated to the length that kernel actually supports,
+ * @out_data_type will be filled to decode the data filled in the buffer
+ * pointed by @data_uptr. Input @data_len == zero is allowed.
+ */
+struct iommu_hw_info {
+ __u32 size;
+ __u32 flags;
+ __u32 dev_id;
+ __u32 data_len;
+ __aligned_u64 data_uptr;
+ __u32 out_data_type;
+ __u32 __reserved;
+};
+#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO)
+#endif
diff --git a/meson.build b/meson.build
index e0d1f84..259dc5f 100644
--- a/meson.build
+++ b/meson.build
@@ -2117,6 +2117,7 @@
config_host_data.set('CONFIG_PLUGIN', get_option('plugins'))
config_host_data.set('CONFIG_RBD', rbd.found())
config_host_data.set('CONFIG_RDMA', rdma.found())
+config_host_data.set('CONFIG_RELOCATABLE', get_option('relocatable'))
config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
config_host_data.set('CONFIG_SDL', sdl.found())
config_host_data.set('CONFIG_SDL_IMAGE', sdl_image.found())
@@ -2200,7 +2201,7 @@
message('Disabling coroutine pool to measure stack usage')
have_coroutine_pool = false
endif
-config_host_data.set10('CONFIG_COROUTINE_POOL', have_coroutine_pool)
+config_host_data.set('CONFIG_COROUTINE_POOL', have_coroutine_pool)
config_host_data.set('CONFIG_DEBUG_GRAPH_LOCK', get_option('debug_graph_lock'))
config_host_data.set('CONFIG_DEBUG_MUTEX', get_option('debug_mutex'))
config_host_data.set('CONFIG_DEBUG_STACK_USAGE', get_option('debug_stack_usage'))
@@ -4026,8 +4027,13 @@
summary_info = {}
summary_info += {'python': '@0@ (version: @1@)'.format(python.full_path(), python.language_version())}
summary_info += {'sphinx-build': sphinx_build}
-if config_host.has_key('HAVE_GDB_BIN')
- summary_info += {'gdb': config_host['HAVE_GDB_BIN']}
+
+# FIXME: the [binaries] section of machine files, which can be probed
+# with find_program(), would be great for passing gdb and genisoimage
+# paths from configure to Meson. However, there seems to be no way to
+# hide a program (for example if gdb is too old).
+if config_host.has_key('GDB')
+ summary_info += {'gdb': config_host['GDB']}
endif
summary_info += {'iasl': iasl}
summary_info += {'genisoimage': config_host['GENISOIMAGE']}
@@ -4060,6 +4066,7 @@
endif
summary_info += {'D-Bus display': dbus_display}
summary_info += {'QOM debugging': get_option('qom_cast_debug')}
+summary_info += {'Relocatable install': get_option('relocatable')}
summary_info += {'vhost-kernel support': have_vhost_kernel}
summary_info += {'vhost-net support': have_vhost_net}
summary_info += {'vhost-user support': have_vhost_user}
@@ -4363,3 +4370,21 @@
message('If you want to help supporting QEMU on this platform, please')
message('contact the developers at qemu-devel@nongnu.org.')
endif
+
+actually_reloc = get_option('relocatable')
+# check if get_relocated_path() is actually able to relocate paths
+if get_option('relocatable') and \
+ not (get_option('prefix') / get_option('bindir')).startswith(get_option('prefix') / '')
+ message()
+ warning('bindir not included within prefix, the installation will not be relocatable.')
+ actually_reloc = false
+endif
+if not actually_reloc and (targetos == 'windows' or get_option('relocatable'))
+ if targetos == 'windows'
+ message()
+ warning('Windows installs should usually be relocatable.')
+ endif
+ message()
+ message('QEMU will have to be installed under ' + get_option('prefix') + '.')
+ message('Use --disable-relocatable to remove this warning.')
+endif
diff --git a/meson_options.txt b/meson_options.txt
index e49309d..3c7398f 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -101,6 +101,8 @@
description: 'Verbose errors in case of CFI violation')
option('multiprocess', type: 'feature', value: 'auto',
description: 'Out of process device emulation support')
+option('relocatable', type : 'boolean', value : 'true',
+ description: 'toggle relocatable install')
option('vfio_user_server', type: 'feature', value: 'disabled',
description: 'vfio-user server support')
option('dbus_display', type: 'feature', value: 'auto',
@@ -353,5 +355,12 @@
option('slirp_smbd', type : 'feature', value : 'auto',
description: 'use smbd (at path --smbd=*) in slirp networking')
+option('qemu_ga_manufacturer', type: 'string', value: 'QEMU',
+ description: '"manufacturer" name for qemu-ga registry entries')
+option('qemu_ga_distro', type: 'string', value: 'Linux',
+ description: 'second path element in qemu-ga registry entries')
+option('qemu_ga_version', type: 'string', value: '',
+ description: 'version number for qemu-ga installer')
+
option('hexagon_idef_parser', type : 'boolean', value : true,
description: 'use idef-parser to automatically generate TCG code for the Hexagon frontend')
diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c
index d206700..a82597f 100644
--- a/migration/migration-hmp-cmds.c
+++ b/migration/migration-hmp-cmds.c
@@ -30,6 +30,7 @@
#include "sysemu/runstate.h"
#include "ui/qemu-spice.h"
#include "sysemu/sysemu.h"
+#include "options.h"
#include "migration.h"
static void migration_global_dump(Monitor *mon)
@@ -696,7 +697,6 @@
typedef struct HMPMigrationStatus {
QEMUTimer *timer;
Monitor *mon;
- bool is_block_migration;
} HMPMigrationStatus;
static void hmp_migrate_status_cb(void *opaque)
@@ -722,7 +722,7 @@
timer_mod(status->timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + 1000);
} else {
- if (status->is_block_migration) {
+ if (migrate_block()) {
monitor_printf(status->mon, "\n");
}
if (info->error_desc) {
@@ -762,7 +762,6 @@
status = g_malloc0(sizeof(*status));
status->mon = mon;
- status->is_block_migration = blk || inc;
status->timer = timer_new_ms(QEMU_CLOCK_REALTIME, hmp_migrate_status_cb,
status);
timer_mod(status->timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME));
diff --git a/migration/migration.c b/migration/migration.c
index 6ba5e14..05c0b80 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -447,6 +447,18 @@
socket_start_incoming_migration(p ? p : uri, errp);
#ifdef CONFIG_RDMA
} else if (strstart(uri, "rdma:", &p)) {
+ if (migrate_compress()) {
+ error_setg(errp, "RDMA and compression can't be used together");
+ return;
+ }
+ if (migrate_xbzrle()) {
+ error_setg(errp, "RDMA and XBZRLE can't be used together");
+ return;
+ }
+ if (migrate_multifd()) {
+ error_setg(errp, "RDMA and multifd can't be used together");
+ return;
+ }
rdma_start_incoming_migration(p, errp);
#endif
} else if (strstart(uri, "exec:", &p)) {
@@ -962,16 +974,7 @@
info->xbzrle_cache->overflow = xbzrle_counters.overflow;
}
- if (migrate_compress()) {
- info->compression = g_malloc0(sizeof(*info->compression));
- info->compression->pages = compression_counters.pages;
- info->compression->busy = compression_counters.busy;
- info->compression->busy_rate = compression_counters.busy_rate;
- info->compression->compressed_size =
- compression_counters.compressed_size;
- info->compression->compression_rate =
- compression_counters.compression_rate;
- }
+ populate_compress(info);
if (cpu_throttle_active()) {
info->has_cpu_throttle_percentage = true;
@@ -1454,11 +1457,9 @@
s->switchover_acked = false;
s->rdma_migration = false;
/*
- * set mig_stats compression_counters memory to zero for a
- * new migration
+ * set mig_stats memory to zero for a new migration
*/
memset(&mig_stats, 0, sizeof(mig_stats));
- memset(&compression_counters, 0, sizeof(compression_counters));
migration_reset_vfio_bytes_transferred();
return 0;
diff --git a/migration/ram-compress.c b/migration/ram-compress.c
index 06254d8..d037dfe 100644
--- a/migration/ram-compress.c
+++ b/migration/ram-compress.c
@@ -32,11 +32,14 @@
#include "ram-compress.h"
#include "qemu/error-report.h"
+#include "qemu/stats64.h"
#include "migration.h"
#include "options.h"
#include "io/channel-null.h"
#include "exec/target_page.h"
#include "exec/ramblock.h"
+#include "ram.h"
+#include "migration-stats.h"
CompressionStats compression_counters;
@@ -227,27 +230,25 @@
void flush_compressed_data(int (send_queued_data(CompressParam *)))
{
- int idx, thread_count;
-
- thread_count = migrate_compress_threads();
+ int thread_count = migrate_compress_threads();
qemu_mutex_lock(&comp_done_lock);
- for (idx = 0; idx < thread_count; idx++) {
- while (!comp_param[idx].done) {
+ for (int i = 0; i < thread_count; i++) {
+ while (!comp_param[i].done) {
qemu_cond_wait(&comp_done_cond, &comp_done_lock);
}
}
qemu_mutex_unlock(&comp_done_lock);
- for (idx = 0; idx < thread_count; idx++) {
- qemu_mutex_lock(&comp_param[idx].mutex);
- if (!comp_param[idx].quit) {
- CompressParam *param = &comp_param[idx];
+ for (int i = 0; i < thread_count; i++) {
+ qemu_mutex_lock(&comp_param[i].mutex);
+ if (!comp_param[i].quit) {
+ CompressParam *param = &comp_param[i];
send_queued_data(param);
assert(qemu_file_buffer_empty(param->file));
compress_reset_result(param);
}
- qemu_mutex_unlock(&comp_param[idx].mutex);
+ qemu_mutex_unlock(&comp_param[i].mutex);
}
}
@@ -262,15 +263,15 @@
int compress_page_with_multi_thread(RAMBlock *block, ram_addr_t offset,
int (send_queued_data(CompressParam *)))
{
- int idx, thread_count, pages = -1;
+ int thread_count, pages = -1;
bool wait = migrate_compress_wait_thread();
thread_count = migrate_compress_threads();
qemu_mutex_lock(&comp_done_lock);
retry:
- for (idx = 0; idx < thread_count; idx++) {
- if (comp_param[idx].done) {
- CompressParam *param = &comp_param[idx];
+ for (int i = 0; i < thread_count; i++) {
+ if (comp_param[i].done) {
+ CompressParam *param = &comp_param[i];
qemu_mutex_lock(¶m->mutex);
param->done = false;
send_queued_data(param);
@@ -364,16 +365,14 @@
int wait_for_decompress_done(void)
{
- int idx, thread_count;
-
if (!migrate_compress()) {
return 0;
}
- thread_count = migrate_decompress_threads();
+ int thread_count = migrate_decompress_threads();
qemu_mutex_lock(&decomp_done_lock);
- for (idx = 0; idx < thread_count; idx++) {
- while (!decomp_param[idx].done) {
+ for (int i = 0; i < thread_count; i++) {
+ while (!decomp_param[i].done) {
qemu_cond_wait(&decomp_done_cond, &decomp_done_lock);
}
}
@@ -430,6 +429,11 @@
return 0;
}
+ /*
+ * set compression_counters memory to zero for a new migration
+ */
+ memset(&compression_counters, 0, sizeof(compression_counters));
+
thread_count = migrate_decompress_threads();
decompress_threads = g_new0(QemuThread, thread_count);
decomp_param = g_new0(DecompressParam, thread_count);
@@ -459,27 +463,54 @@
void decompress_data_with_multi_threads(QEMUFile *f, void *host, int len)
{
- int idx, thread_count;
-
- thread_count = migrate_decompress_threads();
+ int thread_count = migrate_decompress_threads();
QEMU_LOCK_GUARD(&decomp_done_lock);
while (true) {
- for (idx = 0; idx < thread_count; idx++) {
- if (decomp_param[idx].done) {
- decomp_param[idx].done = false;
- qemu_mutex_lock(&decomp_param[idx].mutex);
- qemu_get_buffer(f, decomp_param[idx].compbuf, len);
- decomp_param[idx].des = host;
- decomp_param[idx].len = len;
- qemu_cond_signal(&decomp_param[idx].cond);
- qemu_mutex_unlock(&decomp_param[idx].mutex);
- break;
+ for (int i = 0; i < thread_count; i++) {
+ if (decomp_param[i].done) {
+ decomp_param[i].done = false;
+ qemu_mutex_lock(&decomp_param[i].mutex);
+ qemu_get_buffer(f, decomp_param[i].compbuf, len);
+ decomp_param[i].des = host;
+ decomp_param[i].len = len;
+ qemu_cond_signal(&decomp_param[i].cond);
+ qemu_mutex_unlock(&decomp_param[i].mutex);
+ return;
}
}
- if (idx < thread_count) {
- break;
- } else {
- qemu_cond_wait(&decomp_done_cond, &decomp_done_lock);
- }
+ qemu_cond_wait(&decomp_done_cond, &decomp_done_lock);
}
}
+
+void populate_compress(MigrationInfo *info)
+{
+ if (!migrate_compress()) {
+ return;
+ }
+ info->compression = g_malloc0(sizeof(*info->compression));
+ info->compression->pages = compression_counters.pages;
+ info->compression->busy = compression_counters.busy;
+ info->compression->busy_rate = compression_counters.busy_rate;
+ info->compression->compressed_size = compression_counters.compressed_size;
+ info->compression->compression_rate = compression_counters.compression_rate;
+}
+
+uint64_t ram_compressed_pages(void)
+{
+ return compression_counters.pages;
+}
+
+void update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
+{
+ ram_transferred_add(bytes_xmit);
+
+ if (param->result == RES_ZEROPAGE) {
+ stat64_add(&mig_stats.zero_pages, 1);
+ return;
+ }
+
+ /* 8 means a header with RAM_SAVE_FLAG_CONTINUE. */
+ compression_counters.compressed_size += bytes_xmit - 8;
+ compression_counters.pages++;
+}
+
diff --git a/migration/ram-compress.h b/migration/ram-compress.h
index 6f7fe2f..e55d3b5 100644
--- a/migration/ram-compress.h
+++ b/migration/ram-compress.h
@@ -30,6 +30,7 @@
#define QEMU_MIGRATION_COMPRESS_H
#include "qemu-file.h"
+#include "qapi/qapi-types-migration.h"
enum CompressResult {
RES_NONE = 0,
@@ -67,4 +68,8 @@
int compress_threads_load_setup(QEMUFile *f);
void decompress_data_with_multi_threads(QEMUFile *f, void *host, int len);
+void populate_compress(MigrationInfo *info);
+uint64_t ram_compressed_pages(void);
+void update_compress_thread_counts(const CompressParam *param, int bytes_xmit);
+
#endif
diff --git a/migration/ram.c b/migration/ram.c
index c844151..16c30a9 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -939,7 +939,7 @@
{
return stat64_get(&mig_stats.normal_pages) +
stat64_get(&mig_stats.zero_pages) +
- compression_counters.pages + xbzrle_counters.pages;
+ ram_compressed_pages() + xbzrle_counters.pages;
}
static void migration_update_rates(RAMState *rs, int64_t end_time)
@@ -1144,13 +1144,12 @@
*
* @rs: current RAM state
* @pss: current PSS channel
- * @block: block that contains the page we want to send
* @offset: offset inside the block for the page
*/
-static int save_zero_page(RAMState *rs, PageSearchStatus *pss, RAMBlock *block,
+static int save_zero_page(RAMState *rs, PageSearchStatus *pss,
ram_addr_t offset)
{
- uint8_t *p = block->host + offset;
+ uint8_t *p = pss->block->host + offset;
QEMUFile *file = pss->pss_channel;
int len = 0;
@@ -1158,10 +1157,10 @@
return 0;
}
- len += save_page_header(pss, file, block, offset | RAM_SAVE_FLAG_ZERO);
+ len += save_page_header(pss, file, pss->block, offset | RAM_SAVE_FLAG_ZERO);
qemu_put_byte(file, 0);
len += 1;
- ram_release_page(block->idstr, offset);
+ ram_release_page(pss->block->idstr, offset);
stat64_add(&mig_stats.zero_pages, 1);
ram_transferred_add(len);
@@ -1172,7 +1171,7 @@
*/
if (rs->xbzrle_started) {
XBZRLE_cache_lock();
- xbzrle_cache_zero_page(block->offset + offset);
+ xbzrle_cache_zero_page(pss->block->offset + offset);
XBZRLE_cache_unlock();
}
@@ -1186,12 +1185,12 @@
*
* Return true if the pages has been saved, otherwise false is returned.
*/
-static bool control_save_page(PageSearchStatus *pss, RAMBlock *block,
+static bool control_save_page(PageSearchStatus *pss,
ram_addr_t offset, int *pages)
{
int ret;
- ret = rdma_control_save_page(pss->pss_channel, block->offset, offset,
+ ret = rdma_control_save_page(pss->pss_channel, pss->block->offset, offset,
TARGET_PAGE_SIZE);
if (ret == RAM_SAVE_CONTROL_NOT_SUPP) {
return false;
@@ -1292,21 +1291,6 @@
return 1;
}
-static void
-update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
-{
- ram_transferred_add(bytes_xmit);
-
- if (param->result == RES_ZEROPAGE) {
- stat64_add(&mig_stats.zero_pages, 1);
- return;
- }
-
- /* 8 means a header with RAM_SAVE_FLAG_CONTINUE. */
- compression_counters.compressed_size += bytes_xmit - 8;
- compression_counters.pages++;
-}
-
static bool save_page_use_compression(RAMState *rs);
static int send_queued_data(CompressParam *param)
@@ -2082,7 +2066,7 @@
* paths to handle it
*/
static bool save_compress_page(RAMState *rs, PageSearchStatus *pss,
- RAMBlock *block, ram_addr_t offset)
+ ram_addr_t offset)
{
if (!save_page_use_compression(rs)) {
return false;
@@ -2098,12 +2082,13 @@
* We post the fist page as normal page as compression will take
* much CPU resource.
*/
- if (block != pss->last_sent_block) {
+ if (pss->block != pss->last_sent_block) {
ram_flush_compressed_data(rs);
return false;
}
- if (compress_page_with_multi_thread(block, offset, send_queued_data) > 0) {
+ if (compress_page_with_multi_thread(pss->block, offset,
+ send_queued_data) > 0) {
return true;
}
@@ -2125,15 +2110,15 @@
ram_addr_t offset = ((ram_addr_t)pss->page) << TARGET_PAGE_BITS;
int res;
- if (control_save_page(pss, block, offset, &res)) {
+ if (control_save_page(pss, offset, &res)) {
return res;
}
- if (save_compress_page(rs, pss, block, offset)) {
+ if (save_compress_page(rs, pss, offset)) {
return 1;
}
- if (save_zero_page(rs, pss, block, offset)) {
+ if (save_zero_page(rs, pss, offset)) {
return 1;
}
diff --git a/qga/meson.build b/qga/meson.build
index 59cae0c..940a51d 100644
--- a/qga/meson.build
+++ b/qga/meson.build
@@ -145,6 +145,9 @@
else
libpcre = 'libpcre2'
endif
+ qga_msi_version = get_option('qemu_ga_version') == '' \
+ ? project.version() \
+ : get_option('qemu_ga_version')
qga_msi = custom_target('QGA MSI',
input: files('installer/qemu-ga.wxs'),
output: 'qemu-ga-@0@.msi'.format(host_arch),
@@ -155,9 +158,9 @@
qemu_ga_msi_vss,
'-D', 'BUILD_DIR=' + meson.project_build_root(),
'-D', 'BIN_DIR=' + glib_pc.get_variable('bindir'),
- '-D', 'QEMU_GA_VERSION=' + config_host['QEMU_GA_VERSION'],
- '-D', 'QEMU_GA_MANUFACTURER=' + config_host['QEMU_GA_MANUFACTURER'],
- '-D', 'QEMU_GA_DISTRO=' + config_host['QEMU_GA_DISTRO'],
+ '-D', 'QEMU_GA_VERSION=' + qga_msi_version,
+ '-D', 'QEMU_GA_MANUFACTURER=' + get_option('qemu_ga_manufacturer'),
+ '-D', 'QEMU_GA_DISTRO=' + get_option('qemu_ga_distro'),
'-D', 'LIBPCRE=' + libpcre,
])
all_qga += [qga_msi]
diff --git a/scripts/feature_to_c.py b/scripts/feature_to_c.py
old mode 100755
new mode 100644
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 02fa828..00a0870 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -907,6 +907,7 @@
if (length($subsystem) > 20) {
$subsystem = substr($subsystem, 0, 17);
$subsystem =~ s/\s*$//;
+ $subsystem =~ s/[()]//g;
$subsystem = $subsystem . "...";
}
return $subsystem;
diff --git a/scripts/meson-buildoptions.py b/scripts/meson-buildoptions.py
index 8d2e526..4814a8f 100644
--- a/scripts/meson-buildoptions.py
+++ b/scripts/meson-buildoptions.py
@@ -25,13 +25,15 @@
import shlex
import sys
+# Options with nonstandard names (e.g. --with/--without) or OS-dependent
+# defaults. Try not to add any.
SKIP_OPTIONS = {
"default_devices",
"fuzzing_engine",
- "qemu_suffix",
- "smbd",
}
+# Options whose name doesn't match the option for backwards compatibility
+# reasons, because Meson gives them a funny name, or both
OPTION_NAMES = {
"b_coverage": "gcov",
"b_lto": "lto",
@@ -40,13 +42,25 @@
"malloc": "enable-malloc",
"pkgversion": "with-pkgversion",
"qemu_firmwarepath": "firmwarepath",
+ "qemu_suffix": "with-suffix",
"trace_backends": "enable-trace-backends",
"trace_file": "with-trace-file",
}
+# Options that configure autodetects, even though meson defines them as boolean
+AUTO_OPTIONS = {
+ "plugins",
+ "werror",
+}
+
+# Builtin options that should be definable via configure. Some of the others
+# we really do not want (e.g. c_args is defined via the native file, not
+# via -D, because it's a mix of CFLAGS and --extra-cflags); for specific
+# cases "../configure -D" can be used as an escape hatch.
BUILTIN_OPTIONS = {
"b_coverage",
"b_lto",
+ "bindir",
"datadir",
"debug",
"includedir",
@@ -55,8 +69,10 @@
"localedir",
"localstatedir",
"mandir",
+ "prefix",
"strip",
"sysconfdir",
+ "werror",
}
LINE_WIDTH = 76
@@ -168,6 +184,7 @@ def cli_metavar(opt):
def print_help(options):
print("meson_options_help() {")
+ feature_opts = []
for opt in sorted(options, key=cli_help_key):
key = cli_help_key(opt)
# The first section includes options that have an arguments,
@@ -176,7 +193,7 @@ def print_help(options):
metavar = cli_metavar(opt)
left = f"--{key}={metavar}"
help_line(left, opt, 27, True)
- elif opt["type"] == "boolean":
+ elif opt["type"] == "boolean" and opt["name"] not in AUTO_OPTIONS:
left = f"--{key}"
help_line(left, opt, 27, False)
elif allow_arg(opt):
@@ -185,16 +202,17 @@ def print_help(options):
else:
left = f"--{key}=CHOICE"
help_line(left, opt, 27, True)
+ else:
+ feature_opts.append(opt)
sh_print()
sh_print("Optional features, enabled with --enable-FEATURE and")
sh_print("disabled with --disable-FEATURE, default is enabled if available")
sh_print("(unless built with --without-default-features):")
sh_print()
- for opt in options:
- key = opt["name"].replace("_", "-")
- if opt["type"] != "boolean" and not allow_arg(opt):
- help_line(key, opt, 18, False)
+ for opt in sorted(feature_opts, key=cli_option):
+ key = cli_option(opt)
+ help_line(key, opt, 18, False)
print("}")
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index a28ccbc..7ca4b77 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -3,6 +3,7 @@
printf "%s\n" ' --audio-drv-list=CHOICES Set audio driver list [default] (choices: alsa/co'
printf "%s\n" ' reaudio/default/dsound/jack/oss/pa/pipewire/sdl/s'
printf "%s\n" ' ndio)'
+ printf "%s\n" ' --bindir=VALUE Executable directory [bin]'
printf "%s\n" ' --block-drv-ro-whitelist=VALUE'
printf "%s\n" ' set block driver read-only whitelist (by default'
printf "%s\n" ' affects only QEMU, not tools like qemu-img)'
@@ -17,6 +18,7 @@
printf "%s\n" ' code for the Hexagon frontend'
printf "%s\n" ' --disable-install-blobs install provided firmware blobs'
printf "%s\n" ' --disable-qom-cast-debug cast debugging support'
+ printf "%s\n" ' --disable-relocatable toggle relocatable install'
printf "%s\n" ' --docdir=VALUE Base directory for documentation installation'
printf "%s\n" ' (can be empty) [share/doc]'
printf "%s\n" ' --enable-block-drv-whitelist-in-tools'
@@ -39,7 +41,6 @@
printf "%s\n" ' jemalloc/system/tcmalloc)'
printf "%s\n" ' --enable-module-upgrades try to load modules from alternate paths for'
printf "%s\n" ' upgrades'
- printf "%s\n" ' --enable-plugins TCG plugins via shared library loading'
printf "%s\n" ' --enable-rng-none dummy RNG, avoid using /dev/(u)random and'
printf "%s\n" ' getrandom()'
printf "%s\n" ' --enable-safe-stack SafeStack Stack Smash Protection (requires'
@@ -62,6 +63,14 @@
printf "%s\n" ' --localedir=VALUE Locale data directory [share/locale]'
printf "%s\n" ' --localstatedir=VALUE Localstate data directory [/var/local]'
printf "%s\n" ' --mandir=VALUE Manual page directory [share/man]'
+ printf "%s\n" ' --prefix=VALUE Installation prefix [/usr/local]'
+ printf "%s\n" ' --qemu-ga-distro=VALUE second path element in qemu-ga registry entries'
+ printf "%s\n" ' [Linux]'
+ printf "%s\n" ' --qemu-ga-manufacturer=VALUE'
+ printf "%s\n" ' "manufacturer" name for qemu-ga registry entries'
+ printf "%s\n" ' [QEMU]'
+ printf "%s\n" ' --qemu-ga-version=VALUE version number for qemu-ga installer'
+ printf "%s\n" ' --smbd=VALUE Path to smbd for slirp networking'
printf "%s\n" ' --sysconfdir=VALUE Sysconf data directory [etc]'
printf "%s\n" ' --tls-priority=VALUE Default TLS protocol/cipher priority string'
printf "%s\n" ' [NORMAL]'
@@ -69,6 +78,8 @@
printf "%s\n" ' auto/sigaltstack/ucontext/windows)'
printf "%s\n" ' --with-pkgversion=VALUE use specified string as sub-version of the'
printf "%s\n" ' package'
+ printf "%s\n" ' --with-suffix=VALUE Suffix for QEMU data/modules/config directories'
+ printf "%s\n" ' (can be empty) [qemu]'
printf "%s\n" ' --with-trace-file=VALUE Trace file prefix for simple backend [trace]'
printf "%s\n" ''
printf "%s\n" 'Optional features, enabled with --enable-FEATURE and'
@@ -148,6 +159,7 @@
printf "%s\n" ' pa PulseAudio sound support'
printf "%s\n" ' parallels parallels image format support'
printf "%s\n" ' pipewire PipeWire sound support'
+ printf "%s\n" ' plugins TCG plugins via shared library loading'
printf "%s\n" ' png PNG support with libpng'
printf "%s\n" ' pvrdma Enable PVRDMA support'
printf "%s\n" ' qcow1 qcow1 image format support'
@@ -201,6 +213,7 @@
printf "%s\n" ' vpc vpc image format support'
printf "%s\n" ' vte vte support for the gtk UI'
printf "%s\n" ' vvfat vvfat image format support'
+ printf "%s\n" ' werror Treat warnings as errors'
printf "%s\n" ' whpx WHPX acceleration support'
printf "%s\n" ' xen Xen backend support'
printf "%s\n" ' xen-pci-passthrough'
@@ -229,6 +242,7 @@
--disable-gcov) printf "%s" -Db_coverage=false ;;
--enable-lto) printf "%s" -Db_lto=true ;;
--disable-lto) printf "%s" -Db_lto=false ;;
+ --bindir=*) quote_sh "-Dbindir=$2" ;;
--enable-blkio) printf "%s" -Dblkio=enabled ;;
--disable-blkio) printf "%s" -Dblkio=disabled ;;
--block-drv-ro-whitelist=*) quote_sh "-Dblock_drv_ro_whitelist=$2" ;;
@@ -407,6 +421,7 @@
--disable-plugins) printf "%s" -Dplugins=false ;;
--enable-png) printf "%s" -Dpng=enabled ;;
--disable-png) printf "%s" -Dpng=disabled ;;
+ --prefix=*) quote_sh "-Dprefix=$2" ;;
--enable-pvrdma) printf "%s" -Dpvrdma=enabled ;;
--disable-pvrdma) printf "%s" -Dpvrdma=disabled ;;
--enable-qcow1) printf "%s" -Dqcow1=enabled ;;
@@ -414,6 +429,10 @@
--enable-qed) printf "%s" -Dqed=enabled ;;
--disable-qed) printf "%s" -Dqed=disabled ;;
--firmwarepath=*) quote_sh "-Dqemu_firmwarepath=$(meson_option_build_array $2)" ;;
+ --qemu-ga-distro=*) quote_sh "-Dqemu_ga_distro=$2" ;;
+ --qemu-ga-manufacturer=*) quote_sh "-Dqemu_ga_manufacturer=$2" ;;
+ --qemu-ga-version=*) quote_sh "-Dqemu_ga_version=$2" ;;
+ --with-suffix=*) quote_sh "-Dqemu_suffix=$2" ;;
--enable-qga-vss) printf "%s" -Dqga_vss=enabled ;;
--disable-qga-vss) printf "%s" -Dqga_vss=disabled ;;
--enable-qom-cast-debug) printf "%s" -Dqom_cast_debug=true ;;
@@ -422,6 +441,8 @@
--disable-rbd) printf "%s" -Drbd=disabled ;;
--enable-rdma) printf "%s" -Drdma=enabled ;;
--disable-rdma) printf "%s" -Drdma=disabled ;;
+ --enable-relocatable) printf "%s" -Drelocatable=true ;;
+ --disable-relocatable) printf "%s" -Drelocatable=false ;;
--enable-replication) printf "%s" -Dreplication=enabled ;;
--disable-replication) printf "%s" -Dreplication=disabled ;;
--enable-rng-none) printf "%s" -Drng_none=true ;;
@@ -446,6 +467,7 @@
--disable-slirp-smbd) printf "%s" -Dslirp_smbd=disabled ;;
--enable-smartcard) printf "%s" -Dsmartcard=enabled ;;
--disable-smartcard) printf "%s" -Dsmartcard=disabled ;;
+ --smbd=*) quote_sh "-Dsmbd=$2" ;;
--enable-snappy) printf "%s" -Dsnappy=enabled ;;
--disable-snappy) printf "%s" -Dsnappy=disabled ;;
--enable-sndio) printf "%s" -Dsndio=enabled ;;
@@ -522,6 +544,8 @@
--disable-vte) printf "%s" -Dvte=disabled ;;
--enable-vvfat) printf "%s" -Dvvfat=enabled ;;
--disable-vvfat) printf "%s" -Dvvfat=disabled ;;
+ --enable-werror) printf "%s" -Dwerror=true ;;
+ --disable-werror) printf "%s" -Dwerror=false ;;
--enable-whpx) printf "%s" -Dwhpx=enabled ;;
--disable-whpx) printf "%s" -Dwhpx=disabled ;;
--enable-xen) printf "%s" -Dxen=enabled ;;
diff --git a/scripts/tracetool/__init__.py b/scripts/tracetool/__init__.py
index 33cf85e..b29594d 100644
--- a/scripts/tracetool/__init__.py
+++ b/scripts/tracetool/__init__.py
@@ -210,12 +210,12 @@ class Event(object):
"""
- _CRE = re.compile("((?P<props>[\w\s]+)\s+)?"
- "(?P<name>\w+)"
- "\((?P<args>[^)]*)\)"
- "\s*"
- "(?:(?:(?P<fmt_trans>\".+),)?\s*(?P<fmt>\".+))?"
- "\s*")
+ _CRE = re.compile(r"((?P<props>[\w\s]+)\s+)?"
+ r"(?P<name>\w+)"
+ r"\((?P<args>[^)]*)\)"
+ r"\s*"
+ r"(?:(?:(?P<fmt_trans>\".+),)?\s*(?P<fmt>\".+))?"
+ r"\s*")
_VALID_PROPS = set(["disable", "vcpu"])
@@ -326,7 +326,7 @@ def __repr__(self):
fmt)
# Star matching on PRI is dangerous as one might have multiple
# arguments with that format, hence the non-greedy version of it.
- _FMT = re.compile("(%[\d\.]*\w+|%.*?PRI\S+)")
+ _FMT = re.compile(r"(%[\d\.]*\w+|%.*?PRI\S+)")
def formats(self):
"""List conversion specifiers in the argument print format string."""
diff --git a/scripts/tracetool/format/log_stap.py b/scripts/tracetool/format/log_stap.py
index 0b6549d..b49afab 100644
--- a/scripts/tracetool/format/log_stap.py
+++ b/scripts/tracetool/format/log_stap.py
@@ -83,7 +83,7 @@ def c_fmt_to_stap(fmt):
# and "%ll" is not valid at all. Similarly the size_t
# based "%z" size qualifier is not valid. We just
# strip all size qualifiers for sanity.
- fmt = re.sub("%(\d*)(l+|z)(x|u|d)", "%\\1\\3", "".join(bits))
+ fmt = re.sub(r"%(\d*)(l+|z)(x|u|d)", r"%\1\3", "".join(bits))
return fmt
def generate(events, backend, group):
diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh
index 35a64bb..34295c0 100755
--- a/scripts/update-linux-headers.sh
+++ b/scripts/update-linux-headers.sh
@@ -161,7 +161,8 @@
rm -rf "$output/linux-headers/linux"
mkdir -p "$output/linux-headers/linux"
for header in const.h stddef.h kvm.h vfio.h vfio_ccw.h vfio_zdev.h vhost.h \
- psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h vduse.h; do
+ psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h \
+ vduse.h iommufd.h; do
cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux"
done
diff --git a/stubs/meson.build b/stubs/meson.build
index cde4497..0bf25e6 100644
--- a/stubs/meson.build
+++ b/stubs/meson.build
@@ -65,4 +65,3 @@
stub_ss.add(files('qdev.c'))
endif
stub_ss.add(files('semihost-all.c'))
-stub_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_false: files('vfio-user-obj.c'))
diff --git a/stubs/ramfb.c b/stubs/ramfb.c
index 48143f3..cf64733 100644
--- a/stubs/ramfb.c
+++ b/stubs/ramfb.c
@@ -2,6 +2,8 @@
#include "qapi/error.h"
#include "hw/display/ramfb.h"
+const VMStateDescription ramfb_vmstate = {};
+
void ramfb_display_update(QemuConsole *con, RAMFBState *s)
{
}
diff --git a/target/hexagon/hex_common.py b/target/hexagon/hex_common.py
index dce1b85..0da65d6 100755
--- a/target/hexagon/hex_common.py
+++ b/target/hexagon/hex_common.py
@@ -45,7 +45,7 @@ def uniquify(seq):
immre = re.compile(r"[#]([rRsSuUm])(\d+)(?:[:](\d+))?")
reg_or_immre = re.compile(
r"(((?<!DUP)[MNRCOPQXSGVZA])([stuvwxyzdefg]+)"
- + "([.]?[LlHh]?)(\d+S?))|([#]([rRsSuUm])(\d+)[:]?(\d+)?)"
+ r"([.]?[LlHh]?)(\d+S?))|([#]([rRsSuUm])(\d+)[:]?(\d+)?)"
)
relimmre = re.compile(r"[#]([rR])(\d+)(?:[:](\d+))?")
absimmre = re.compile(r"[#]([sSuUm])(\d+)(?:[:](\d+))?")
@@ -337,7 +337,7 @@ def read_attribs_file(name):
def read_overrides_file(name):
- overridere = re.compile("#define fGEN_TCG_([A-Za-z0-9_]+)\(.*")
+ overridere = re.compile(r"#define fGEN_TCG_([A-Za-z0-9_]+)\(.*")
for line in open(name, "rt").readlines():
if not overridere.match(line):
continue
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 3aab05d..bdca901 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -778,6 +778,7 @@
},
.cpuid = {.eax = 1, .reg = R_EDX, },
.tcg_features = TCG_FEATURES,
+ .no_autoenable_flags = CPUID_HT,
},
[FEAT_1_ECX] = {
.type = CPUID_FEATURE_WORD,
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index f6c7f7e..ab72bcd 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -373,6 +373,8 @@
if (function == 1 && reg == R_EDX) {
/* KVM before 2.6.30 misreports the following features */
ret |= CPUID_MTRR | CPUID_PAT | CPUID_MCE | CPUID_MCA;
+ /* KVM never reports CPUID_HT but QEMU can support when vcpus > 1 */
+ ret |= CPUID_HT;
} else if (function == 1 && reg == R_ECX) {
/* We can set the hypervisor flag, even if KVM does not return it on
* GET_SUPPORTED_CPUID
diff --git a/target/i386/svm.h b/target/i386/svm.h
index f9a7854..1bd7844 100644
--- a/target/i386/svm.h
+++ b/target/i386/svm.h
@@ -132,6 +132,7 @@
/* only included in documentation, maybe wrong */
#define SVM_EXIT_MONITOR 0x08a
#define SVM_EXIT_MWAIT 0x08b
+#define SVM_EXIT_XSETBV 0x08d
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_ERR -1
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index d2061ec..4f6f9fa 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -5916,6 +5916,7 @@
| PREFIX_REPZ | PREFIX_REPNZ))) {
goto illegal_op;
}
+ gen_svm_check_intercept(s, SVM_EXIT_XSETBV);
if (!check_cpl0(s)) {
break;
}
diff --git a/tests/avocado/virtio_check_params.py b/tests/avocado/virtio_check_params.py
index f4314ef..5fe370a 100644
--- a/tests/avocado/virtio_check_params.py
+++ b/tests/avocado/virtio_check_params.py
@@ -43,7 +43,7 @@
class VirtioMaxSegSettingsCheck(QemuSystemTest):
@staticmethod
def make_pattern(props):
- pattern_items = ['{0} = \w+'.format(prop) for prop in props]
+ pattern_items = [r'{0} = \w+'.format(prop) for prop in props]
return '|'.join(pattern_items)
def query_virtqueue(self, vm, dev_type_name):
diff --git a/tests/docker/docker.py b/tests/docker/docker.py
index 688ef62..3b8a267 100755
--- a/tests/docker/docker.py
+++ b/tests/docker/docker.py
@@ -186,7 +186,7 @@ def _check_binfmt_misc(executable):
(binary))
return None, True
- m = re.search("interpreter (\S+)\n", entry)
+ m = re.search(r"interpreter (\S+)\n", entry)
interp = m.group(1)
if interp and interp != executable:
print("binfmt_misc for %s does not point to %s, using %s" %
diff --git a/tests/qemu-iotests/linters.py b/tests/qemu-iotests/linters.py
index 65c4c4e..9fb3fd1 100644
--- a/tests/qemu-iotests/linters.py
+++ b/tests/qemu-iotests/linters.py
@@ -68,7 +68,7 @@ def run_linter(
:raise CalledProcessError: If the linter process exits with failure.
"""
subprocess.run(
- ('python3', '-m', tool, *args),
+ (sys.executable, '-m', tool, *args),
env=env,
check=True,
stdout=subprocess.PIPE if suppress_output else None,
diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py
index 9a37ad9..e67ebd2 100644
--- a/tests/qemu-iotests/testenv.py
+++ b/tests/qemu-iotests/testenv.py
@@ -216,7 +216,7 @@ def __init__(self, source_dir: str, build_dir: str,
self.source_iotests = source_dir
self.build_iotests = build_dir
- self.build_root = os.path.join(self.build_iotests, '..', '..')
+ self.build_root = Path(self.build_iotests).parent.parent
self.init_directories()
diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target
index 2efacf9..62b38c7 100644
--- a/tests/tcg/aarch64/Makefile.target
+++ b/tests/tcg/aarch64/Makefile.target
@@ -73,11 +73,6 @@
# System Registers Tests
AARCH64_TESTS += sysregs
-ifneq ($(CROSS_CC_HAS_SVE),)
-# SVE ioctl test
-AARCH64_TESTS += sve-ioctls
-sve-ioctls: CFLAGS+=-march=armv8.1-a+sve
-
AARCH64_TESTS += test-aes
test-aes: CFLAGS += -O -march=armv8-a+aes
test-aes: test-aes-main.c.inc
@@ -100,26 +95,29 @@
TESTS += sha512-vector
ifneq ($(CROSS_CC_HAS_SVE),)
+# SVE ioctl test
+AARCH64_TESTS += sve-ioctls
+sve-ioctls: CFLAGS+=-march=armv8.1-a+sve
+
sha512-sve: CFLAGS=-O3 -march=armv8.1-a+sve
sha512-sve: sha512.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
TESTS += sha512-sve
-endif
-ifeq ($(HOST_GDB_SUPPORTS_ARCH),y)
+ifneq ($(GDB),)
GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
run-gdbstub-sysregs: sysregs
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(AARCH64_SRC)/gdbstub/test-sve.py, \
basic gdbstub SVE support)
run-gdbstub-sve-ioctls: sve-ioctls
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(AARCH64_SRC)/gdbstub/test-sve-ioctl.py, \
basic gdbstub SVE ZLEN support)
diff --git a/tests/tcg/multiarch/Makefile.target b/tests/tcg/multiarch/Makefile.target
index 43bddea..f3bfaf1 100644
--- a/tests/tcg/multiarch/Makefile.target
+++ b/tests/tcg/multiarch/Makefile.target
@@ -63,45 +63,39 @@
run-test-mmap-%: test-mmap
$(call run-test, test-mmap-$*, $(QEMU) -p $* $<, $< ($* byte pages))
-ifneq ($(HAVE_GDB_BIN),)
-ifeq ($(HOST_GDB_SUPPORTS_ARCH),y)
+ifneq ($(GDB),)
GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
run-gdbstub-sha1: sha1
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(MULTIARCH_SRC)/gdbstub/sha1.py, \
basic gdbstub support)
run-gdbstub-qxfer-auxv-read: sha1
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(MULTIARCH_SRC)/gdbstub/test-qxfer-auxv-read.py, \
basic gdbstub qXfer:auxv:read support)
run-gdbstub-proc-mappings: sha1
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(MULTIARCH_SRC)/gdbstub/test-proc-mappings.py, \
proc mappings support)
run-gdbstub-thread-breakpoint: testthread
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(MULTIARCH_SRC)/gdbstub/test-thread-breakpoint.py, \
hitting a breakpoint on non-main thread)
-
else
run-gdbstub-%:
- $(call skip-test, "gdbstub test $*", "no guest arch support")
-endif
-else
-run-gdbstub-%:
- $(call skip-test, "gdbstub test $*", "need working gdb")
+ $(call skip-test, "gdbstub test $*", "need working gdb with $(patsubst -%,,$(TARGET_NAME)) support")
endif
EXTRA_RUNS += run-gdbstub-sha1 run-gdbstub-qxfer-auxv-read \
run-gdbstub-proc-mappings run-gdbstub-thread-breakpoint
diff --git a/tests/tcg/multiarch/system/Makefile.softmmu-target b/tests/tcg/multiarch/system/Makefile.softmmu-target
index 90810a3..dee4f58 100644
--- a/tests/tcg/multiarch/system/Makefile.softmmu-target
+++ b/tests/tcg/multiarch/system/Makefile.softmmu-target
@@ -14,13 +14,12 @@
MULTIARCH_TEST_SRCS=$(wildcard $(MULTIARCH_SYSTEM_SRC)/*.c)
MULTIARCH_TESTS = $(patsubst $(MULTIARCH_SYSTEM_SRC)/%.c, %, $(MULTIARCH_TEST_SRCS))
-ifneq ($(HAVE_GDB_BIN),)
-ifeq ($(HOST_GDB_SUPPORTS_ARCH),y)
+ifneq ($(GDB),)
GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
run-gdbstub-memory: memory
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) \
--output $<.gdb.out \
--qargs \
@@ -29,7 +28,7 @@
softmmu gdbstub support)
run-gdbstub-interrupt: interrupt
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) \
--output $<.gdb.out \
--qargs \
@@ -38,7 +37,7 @@
softmmu gdbstub support)
run-gdbstub-untimely-packet: hello
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--gdb-args "-ex 'set debug remote 1'" \
--output untimely-packet.gdb.out \
--stderr untimely-packet.gdb.err \
@@ -51,11 +50,7 @@
"GREP", file untimely-packet.gdb.err)
else
run-gdbstub-%:
- $(call skip-test, "gdbstub test $*", "no guest arch support")
-endif
-else
-run-gdbstub-%:
- $(call skip-test, "gdbstub test $*", "need working gdb")
+ $(call skip-test, "gdbstub test $*", "need working gdb with $(patsubst -%,,$(TARGET_NAME)) support")
endif
MULTIARCH_RUNS += run-gdbstub-memory run-gdbstub-interrupt run-gdbstub-untimely-packet
diff --git a/tests/tcg/s390x/Makefile.target b/tests/tcg/s390x/Makefile.target
index c650aef..826f0a1 100644
--- a/tests/tcg/s390x/Makefile.target
+++ b/tests/tcg/s390x/Makefile.target
@@ -81,12 +81,12 @@
TESTS+=$(Z15_TESTS)
endif
-ifeq ($(HOST_GDB_SUPPORTS_ARCH),y)
+ifneq ($(GDB),)
GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
run-gdbstub-signals-s390x: signals-s390x
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(S390X_SRC)/gdbstub/test-signals-s390x.py, \
mixing signals and debugging)
@@ -95,7 +95,7 @@
run-gdbstub-svc: hello-s390x-asm
$(call run-test, $@, $(GDB_SCRIPT) \
- --gdb $(HAVE_GDB_BIN) \
+ --gdb $(GDB) \
--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
--bin $< --test $(S390X_SRC)/gdbstub/test-svc.py, \
single-stepping svc)
diff --git a/tests/unit/test-coroutine.c b/tests/unit/test-coroutine.c
index b0d21d6..a256364 100644
--- a/tests/unit/test-coroutine.c
+++ b/tests/unit/test-coroutine.c
@@ -645,7 +645,7 @@
* with a sentinel value. If there is no freelist this would legitimately
* crash, so skip it.
*/
- if (CONFIG_COROUTINE_POOL) {
+ if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
g_test_add_func("/basic/no-dangling-access", test_no_dangling_access);
}
diff --git a/tests/vm/basevm.py b/tests/vm/basevm.py
index 8aef4cf..61725b8 100644
--- a/tests/vm/basevm.py
+++ b/tests/vm/basevm.py
@@ -331,8 +331,8 @@ def console_init(self, timeout = None):
def console_log(self, text):
for line in re.split("[\r\n]", text):
# filter out terminal escape sequences
- line = re.sub("\x1b\[[0-9;?]*[a-zA-Z]", "", line)
- line = re.sub("\x1b\([0-9;?]*[a-zA-Z]", "", line)
+ line = re.sub("\x1b\\[[0-9;?]*[a-zA-Z]", "", line)
+ line = re.sub("\x1b\\([0-9;?]*[a-zA-Z]", "", line)
# replace unprintable chars
line = re.sub("\x1b", "<esc>", line)
line = re.sub("[\x00-\x1f]", ".", line)
@@ -530,7 +530,7 @@ def get_qemu_version(qemu_path):
and return the major number."""
output = subprocess.check_output([qemu_path, '--version'])
version_line = output.decode("utf-8")
- version_num = re.split(' |\(', version_line)[3].split('.')[0]
+ version_num = re.split(r' |\(', version_line)[3].split('.')[0]
return int(version_num)
def parse_config(config, args):
diff --git a/tests/vm/netbsd b/tests/vm/netbsd
index c7e3f1e..40b27a3 100755
--- a/tests/vm/netbsd
+++ b/tests/vm/netbsd
@@ -40,6 +40,9 @@
"gsed",
"gettext-tools",
+ # libs: basic
+ "dtc",
+
# libs: crypto
"gnutls",
@@ -67,7 +70,8 @@
mkdir src build; cd src;
tar -xf /dev/rld1a;
cd ../build
- ../src/configure --disable-opengl {configure_opts};
+ ../src/configure --disable-opengl --extra-ldflags=-L/usr/pkg/lib \
+ --extra-cflags=-I/usr/pkg/include {configure_opts};
gmake --output-sync -j{jobs} {target} {verbose};
"""
poweroff = "/sbin/poweroff"
diff --git a/ui/shader/meson.build b/ui/shader/meson.build
index 592bf59..3137e65 100644
--- a/ui/shader/meson.build
+++ b/ui/shader/meson.build
@@ -10,5 +10,6 @@
output: output,
capture: true,
input: files('@0@.@1@'.format(e[0], e[1])),
+ build_by_default: false,
command: [shaderinclude, '@INPUT0@'])
endforeach
diff --git a/util/cutils.c b/util/cutils.c
index c99d26c..64f817b 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -1178,9 +1178,11 @@
#else
g_string_append(result, dir);
#endif
- } else if (!starts_with_prefix(dir) || !starts_with_prefix(bindir)) {
- g_string_assign(result, dir);
- } else {
+ goto out;
+ }
+
+ if (IS_ENABLED(CONFIG_RELOCATABLE) &&
+ starts_with_prefix(dir) && starts_with_prefix(bindir)) {
g_string_assign(result, exec_dir);
/* Advance over common components. */
@@ -1203,7 +1205,10 @@
assert(G_IS_DIR_SEPARATOR(dir[-1]));
g_string_append(result, dir - 1);
}
+ goto out;
}
+ g_string_assign(result, dir);
+out:
return g_string_free(result, false);
}
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 17a88f6..5fd2dba 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -57,7 +57,7 @@
{
Coroutine *co = NULL;
- if (CONFIG_COROUTINE_POOL) {
+ if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
co = QSLIST_FIRST(alloc_pool);
@@ -99,7 +99,7 @@
{
co->caller = NULL;
- if (CONFIG_COROUTINE_POOL) {
+ if (IS_ENABLED(CONFIG_COROUTINE_POOL)) {
if (release_pool_size < qatomic_read(&pool_max_size) * 2) {
QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
qatomic_inc(&release_pool_size);
