rpms/qemu-kvm
7
0
Fork 0
Code Issues Pull Requests Releases Activity

* Mon Sep 05 2022 Miroslav Rezanina <mrezanin@redhat.com> - 7.1.0-1

Browse Source 
- Rebase to QEMU 7.1.0 [bz#2111769]
- Resolves: bz#2111769
  (Rebase to QEMU 7.1.0)
This commit is contained in:
Miroslav Rezanina 2022-09-05 04:13:56 -04:00
parent 716a3942b3
commit 91ddd1ed64
171 changed files with 1352 additions and 18546 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -22,3 +22,5 @@
/qemu-6.1.0.tar.xz
/qemu-6.2.0.tar.xz
/qemu-7.0.0.tar.xz
/capstone.tar.gz
/qemu-7.1.0.tar.xz

38
0004-Initial-redhat-build.patch
View File

@ -1,4 +1,4 @@
From fc113ecd7c99646a7ced0b99570b5927ae6d595f Mon Sep 17 00:00:00 2001
From 476f040f14a9287efb6f0bf5b3ca97844bf9fdc3 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 26 May 2021 10:56:02 +0200
Subject: Initial redhat build
@ -13,7 +13,7 @@ several issues are fixed in QEMU tree:
We disable make check due to issues with some of the tests.
This rebase is based on qemu-kvm-6.2.0-13.el9
This rebase is based on qemu-kvm-7.0.0-11.el9
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
@ -50,6 +50,12 @@ Rebase changes (7.0.0):
- Change permissions on installing tests/Makefile.include
- Remove ssh block driver
Rebase changes (7.1.0 rc0):
- --disable-vnc-png renamed to --disable-png (upstream)
- removed --disable-vhost-vsock and --disable-vhost-scsi
- capstone submodule removed
- Temporary include capstone build
Merged patches (6.0.0):
- 605758c902 Limit build on Power to qemu-img and qemu-ga only
@ -146,7 +152,7 @@ Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
.distro/85-kvm.preset | 5 -
.distro/Makefile | 100 +
.distro/Makefile.common | 40 +
.distro/Makefile.common | 41 +
.distro/README.tests | 39 +
.distro/ksm.service | 13 -
.distro/ksm.sysconfig | 4 -
@ -158,18 +164,17 @@ Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
.distro/kvm-setup.service | 14 -
.distro/modules-load.conf | 4 +
.distro/qemu-guest-agent.service | 1 -
.distro/qemu-kvm.spec.template | 4034 +++++++++++++++++++++++
.distro/qemu-kvm.spec.template | 4256 +++++++++++++++++++++++
.distro/rpminspect.yaml | 6 +-
.distro/scripts/extract_build_cmd.py | 12 +
.gitignore | 1 +
README.systemtap | 43 +
meson.build | 4 +-
scripts/qemu-guest-agent/fsfreeze-hook | 2 +-
scripts/systemtap/conf.d/qemu_kvm.conf | 4 +
scripts/systemtap/script.d/qemu_kvm.stp | 1 +
tests/check-block.sh | 2 +
ui/vnc-auth-sasl.c | 2 +-
25 files changed, 4290 insertions(+), 339 deletions(-)
24 files changed, 4510 insertions(+), 338 deletions(-)
delete mode 100644 .distro/85-kvm.preset
create mode 100644 .distro/Makefile
create mode 100644 .distro/Makefile.common
@ -237,21 +242,6 @@ index 0000000000..ad913fc990
+
+3. Translate the trace record to readable format.
+ # /usr/share/qemu-kvm/simpletrace.py --no-header /usr/share/qemu-kvm/trace-events /tmp/trace.log
diff --git a/meson.build b/meson.build
index 861de93c4f..6f7e430f0f 100644
--- a/meson.build
+++ b/meson.build
@@ -2394,7 +2394,9 @@ if capstone_opt == 'internal'
# Include all configuration defines via a header file, which will wind up
# as a dependency on the object file, and thus changes here will result
# in a rebuild.
- '-include', 'capstone-defs.h'
+ '-include', 'capstone-defs.h',
+
+ '-Wp,-D_GLIBCXX_ASSERTIONS',
]
libcapstone = static_library('capstone',
diff --git a/scripts/qemu-guest-agent/fsfreeze-hook b/scripts/qemu-guest-agent/fsfreeze-hook
index 13aafd4845..e9b84ec028 100755
--- a/scripts/qemu-guest-agent/fsfreeze-hook
@ -283,11 +273,11 @@ index 0000000000..c04abf9449
@@ -0,0 +1 @@
+probe qemu.kvm.simpletrace.handle_qmp_command,qemu.kvm.simpletrace.monitor_protocol_*,qemu.kvm.simpletrace.migrate_set_state {}
diff --git a/tests/check-block.sh b/tests/check-block.sh
index f59496396c..d900d8b35e 100755
index 5de2c1ba0b..6af743f441 100755
--- a/tests/check-block.sh
+++ b/tests/check-block.sh
@@ -48,6 +48,8 @@ if LANG=C bash --version | grep -q 'GNU bash, version [123]' ; then
skip "bash version too old ==> Not running the qemu-iotests."
@@ -22,6 +22,8 @@ if [ -z "$(find . -name 'qemu-system-*' -print)" ]; then
skip "No qemu-system binary available ==> Not running the qemu-iotests."
fi
+exit 0

251
0005-Re-enable-capstone-internal-build.patch Normal file
View File

@ -0,0 +1,251 @@
From 963cd2a0d78f6cec0ee5203ca2d2de77094bf047 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 1 Jun 2022 05:45:58 -0400
Subject: Re-enable capstone internal build
Until capstone component is added to RHEL 9 we revert changes removing
internal capstone usage.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
.distro/Makefile.common | 3 +-
.distro/capstone.tar.gz | Bin 0 -> 5765837 bytes
.distro/qemu-kvm.spec.template | 5 +-
configure | 12 ++++
meson.build | 116 +++++++++++++++++++++++++++++++--
meson_options.txt | 3 +-
scripts/meson-buildoptions.sh | 5 +-
7 files changed, 135 insertions(+), 9 deletions(-)
create mode 100644 .distro/capstone.tar.gz
diff --git a/configure b/configure
index 72ab03f11a..448b0c82cb 100755
--- a/configure
+++ b/configure
@@ -322,8 +322,10 @@ vfio_user_server="disabled"
# 1. Track which submodules are needed
if test "$default_feature" = no ; then
+ capstone="disabled"
slirp="disabled"
else
+ capstone="auto"
slirp="auto"
fi
fdt="auto"
@@ -902,6 +904,15 @@ for opt do
--enable-uuid|--disable-uuid)
echo "$0: $opt is obsolete, UUID support is always built" >&2
;;
+ --disable-capstone) capstone="disabled"
+ ;;
+ --enable-capstone) capstone="enabled"
+ ;;
+ --enable-capstone=git) capstone="internal"
+ ;;
+ --enable-capstone=*) capstone="$optarg"
+ ;;
+
--with-git=*) git="$optarg"
;;
--with-git-submodules=*)
@@ -2742,6 +2753,7 @@ if test "$skip_meson" = no; then
test "$werror" = yes && meson_option_add -Dwerror=true
# QEMU options
+ test "$capstone" != auto && meson_option_add "-Dcapstone=$capstone"
test "$cfi" != false && meson_option_add "-Dcfi=$cfi"
test "$fdt" != auto && meson_option_add "-Dfdt=$fdt"
test -n "${LIB_FUZZING_ENGINE+xxx}" && meson_option_add "-Dfuzzing_engine=$LIB_FUZZING_ENGINE"
diff --git a/meson.build b/meson.build
index 20fddbd707..9e6a979c13 100644
--- a/meson.build
+++ b/meson.build
@@ -2596,10 +2596,13 @@ genh += custom_target('config-poison.h',
##############
capstone = not_found
-if not get_option('capstone').auto() or have_system or have_user
+capstone_opt = get_option('capstone')
+if capstone_opt in ['enabled', 'auto', 'system']
+ have_internal = fs.exists(meson.current_source_dir() / 'capstone/Makefile')
capstone = dependency('capstone', version: '>=3.0.5',
kwargs: static_kwargs, method: 'pkg-config',
- required: get_option('capstone'))
+ required: capstone_opt == 'system' or
+ capstone_opt == 'enabled' and not have_internal)
# Some versions of capstone have broken pkg-config file
# that reports a wrong -I path, causing the #include to
@@ -2608,10 +2611,113 @@ if not get_option('capstone').auto() or have_system or have_user
if capstone.found() and not cc.compiles('#include <capstone.h>',
dependencies: [capstone])
capstone = not_found
- if get_option('capstone').enabled()
- error('capstone requested, but it does not appear to work')
+ if capstone_opt == 'system'
+ error('system capstone requested, it does not appear to work')
endif
endif
+
+ if capstone.found()
+ capstone_opt = 'system'
+ elif have_internal
+ capstone_opt = 'internal'
+ else
+ capstone_opt = 'disabled'
+ endif
+endif
+if capstone_opt == 'internal'
+ capstone_data = configuration_data()
+ capstone_data.set('CAPSTONE_USE_SYS_DYN_MEM', '1')
+
+ capstone_files = files(
+ 'capstone/cs.c',
+ 'capstone/MCInst.c',
+ 'capstone/MCInstrDesc.c',
+ 'capstone/MCRegisterInfo.c',
+ 'capstone/SStream.c',
+ 'capstone/utils.c'
+ )
+
+ if 'CONFIG_ARM_DIS' in config_all_disas
+ capstone_data.set('CAPSTONE_HAS_ARM', '1')
+ capstone_files += files(
+ 'capstone/arch/ARM/ARMDisassembler.c',
+ 'capstone/arch/ARM/ARMInstPrinter.c',
+ 'capstone/arch/ARM/ARMMapping.c',
+ 'capstone/arch/ARM/ARMModule.c'
+ )
+ endif
+
+ # FIXME: This config entry currently depends on a c++ compiler.
+ # Which is needed for building libvixl, but not for capstone.
+ if 'CONFIG_ARM_A64_DIS' in config_all_disas
+ capstone_data.set('CAPSTONE_HAS_ARM64', '1')
+ capstone_files += files(
+ 'capstone/arch/AArch64/AArch64BaseInfo.c',
+ 'capstone/arch/AArch64/AArch64Disassembler.c',
+ 'capstone/arch/AArch64/AArch64InstPrinter.c',
+ 'capstone/arch/AArch64/AArch64Mapping.c',
+ 'capstone/arch/AArch64/AArch64Module.c'
+ )
+ endif
+
+ if 'CONFIG_PPC_DIS' in config_all_disas
+ capstone_data.set('CAPSTONE_HAS_POWERPC', '1')
+ capstone_files += files(
+ 'capstone/arch/PowerPC/PPCDisassembler.c',
+ 'capstone/arch/PowerPC/PPCInstPrinter.c',
+ 'capstone/arch/PowerPC/PPCMapping.c',
+ 'capstone/arch/PowerPC/PPCModule.c'
+ )
+ endif
+
+ if 'CONFIG_S390_DIS' in config_all_disas
+ capstone_data.set('CAPSTONE_HAS_SYSZ', '1')
+ capstone_files += files(
+ 'capstone/arch/SystemZ/SystemZDisassembler.c',
+ 'capstone/arch/SystemZ/SystemZInstPrinter.c',
+ 'capstone/arch/SystemZ/SystemZMapping.c',
+ 'capstone/arch/SystemZ/SystemZModule.c',
+ 'capstone/arch/SystemZ/SystemZMCTargetDesc.c'
+ )
+ endif
+
+ if 'CONFIG_I386_DIS' in config_all_disas
+ capstone_data.set('CAPSTONE_HAS_X86', 1)
+ capstone_files += files(
+ 'capstone/arch/X86/X86Disassembler.c',
+ 'capstone/arch/X86/X86DisassemblerDecoder.c',
+ 'capstone/arch/X86/X86ATTInstPrinter.c',
+ 'capstone/arch/X86/X86IntelInstPrinter.c',
+ 'capstone/arch/X86/X86InstPrinterCommon.c',
+ 'capstone/arch/X86/X86Mapping.c',
+ 'capstone/arch/X86/X86Module.c'
+ )
+ endif
+
+ configure_file(output: 'capstone-defs.h', configuration: capstone_data)
+
+ capstone_cargs = [
+ # FIXME: There does not seem to be a way to completely replace the c_args
+ # that come from add_project_arguments() -- we can only add to them.
+ # So: disable all warnings with a big hammer.
+ '-Wno-error', '-w',
+
+ # Include all configuration defines via a header file, which will wind up
+ # as a dependency on the object file, and thus changes here will result
+ # in a rebuild.
+ '-include', 'capstone-defs.h',
+
+ '-Wp,-D_GLIBCXX_ASSERTIONS',
+
+ ]
+
+ libcapstone = static_library('capstone',
+ build_by_default: false,
+ sources: capstone_files,
+ c_args: capstone_cargs,
+ include_directories: 'capstone/include')
+ capstone = declare_dependency(link_with: libcapstone,
+ include_directories: 'capstone/include/capstone')
endif
slirp = not_found
@@ -3977,7 +4083,7 @@ summary_info += {'bzip2 support': libbzip2}
summary_info += {'lzfse support': liblzfse}
summary_info += {'zstd support': zstd}
summary_info += {'NUMA host support': numa}
-summary_info += {'capstone': capstone}
+summary_info += {'capstone': capstone_opt == 'internal' ? capstone_opt : capstone}
summary_info += {'libpmem support': libpmem}
summary_info += {'libdaxctl support': libdaxctl}
summary_info += {'libudev': libudev}
diff --git a/meson_options.txt b/meson_options.txt
index e58e158396..7cd920fcd6 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -262,7 +262,8 @@ option('libvduse', type: 'feature', value: 'auto',
option('vduse_blk_export', type: 'feature', value: 'auto',
description: 'VDUSE block export support')
-option('capstone', type: 'feature', value: 'auto',
+option('capstone', type: 'combo', value: 'auto',
+ choices: ['disabled', 'enabled', 'auto', 'system', 'internal'],
description: 'Whether and how to find the capstone library')
option('slirp', type: 'combo', value: 'auto',
choices: ['disabled', 'enabled', 'auto', 'system', 'internal'],
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index 359b04e0e6..b1001aa1db 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -16,6 +16,9 @@ meson_options_help() {
printf "%s\n" ' --enable-block-drv-whitelist-in-tools'
printf "%s\n" ' use block whitelist also in tools instead of only'
printf "%s\n" ' QEMU'
+ printf "%s\n" ' --enable-capstone[=CHOICE]'
+ printf "%s\n" ' Whether and how to find the capstone library'
+ printf "%s\n" ' (choices: auto/disabled/enabled/internal/system)'
printf "%s\n" ' --enable-cfi Control-Flow Integrity (CFI)'
printf "%s\n" ' --enable-cfi-debug Verbose errors in case of CFI violation'
printf "%s\n" ' --enable-debug-mutex mutex debugging support'
@@ -75,7 +78,6 @@ meson_options_help() {
printf "%s\n" ' bzip2 bzip2 support for DMG images'
printf "%s\n" ' canokey CanoKey support'
printf "%s\n" ' cap-ng cap_ng support'
- printf "%s\n" ' capstone Whether and how to find the capstone library'
printf "%s\n" ' cloop cloop image format support'
printf "%s\n" ' cocoa Cocoa user interface (macOS only)'
printf "%s\n" ' coreaudio CoreAudio sound support'
@@ -216,6 +218,7 @@ _meson_option_parse() {
--disable-cap-ng) printf "%s" -Dcap_ng=disabled ;;
--enable-capstone) printf "%s" -Dcapstone=enabled ;;
--disable-capstone) printf "%s" -Dcapstone=disabled ;;
+ --enable-capstone=*) quote_sh "-Dcapstone=$2" ;;
--enable-cfi) printf "%s" -Dcfi=true ;;
--disable-cfi) printf "%s" -Dcfi=false ;;
--enable-cfi-debug) printf "%s" -Dcfi_debug=true ;;
--
2.31.1

147
0005-Enable-disable-devices-for-RHEL.patch → 0006-Enable-disable-devices-for-RHEL.patch
View File

@ -1,4 +1,4 @@
From 51ec7495d69fe4b4d0b61642ca6c0e7fd7a1032d Mon Sep 17 00:00:00 2001
From ae20ca5826cd237e727cff1663177f7f863fab21 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 15 Jul 2021 03:22:36 -0400
Subject: Enable/disable devices for RHEL
@ -22,6 +22,13 @@ Rebase notes (7.0.0):
- Renamed CONFIG_ARM_GIC_TCG to CONFIG_ARM_GICV3_TCG
- Removed upstream devices
Rebase notes (7.1.0 rc0):
- Added CONFIG_VHOST_VSOCK and CONFIG_VHOST_USER_VSOCK configs
- Added CONFIG_CXL and CONFIG_CXL_MEM_DEVICE for aarch64 and x86_64
Rebase notes (7.1.0 rc3):
- Added CONFIG_VHOST_USER_FS option (all archs)
Merged patches (6.1.0):
- c51bf45304 Remove SPICE and QXL from x86_64-rh-devices.mak
- 02fc745601 aarch64-rh-devices: add CONFIG_PVPANIC_PCI
@ -37,14 +44,19 @@ Merged patches (6.2.0):
Merged patches (7.0.0):
- fd7c45a5a8 redhat: Enable virtio-mem as tech-preview on x86-64
- c9e68ea451 Enable SGX -- RH Only
Merged patches (7.1.0 rc0):
- 38b89dc245 pc: Move s3/s4 suspend disabling to compat (only hw/acpi/ich9.c chunk)
- 8f663466c6 configs/devices/aarch64-softmmu: Enable CONFIG_VIRTIO_MEM
- 1bf372717a Enable virtio-iommu-pci on aarch64
- ae3f269458 Enable virtio-iommu-pci on x86_64
---
.distro/qemu-kvm.spec.template | 18 +--
.../aarch64-softmmu/aarch64-rh-devices.mak | 34 ++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 35 ++++++
.../aarch64-softmmu/aarch64-rh-devices.mak | 41 +++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 37 ++++++
configs/devices/rh-virtio.mak | 10 ++
.../s390x-softmmu/s390x-rh-devices.mak | 15 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 103 ++++++++++++++++++
hw/acpi/ich9.c | 4 +-
.../s390x-softmmu/s390x-rh-devices.mak | 18 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 109 ++++++++++++++++++
hw/arm/meson.build | 2 +-
hw/block/fdc.c | 10 ++
hw/cpu/meson.build | 5 +-
@ -58,7 +70,7 @@ Merged patches (7.0.0):
target/ppc/cpu-models.c | 9 ++
target/s390x/cpu_models_sysemu.c | 3 +
target/s390x/kvm/kvm.c | 8 ++
20 files changed, 269 insertions(+), 15 deletions(-)
19 files changed, 285 insertions(+), 13 deletions(-)
create mode 100644 configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
create mode 100644 configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
create mode 100644 configs/devices/rh-virtio.mak
@ -67,10 +79,10 @@ Merged patches (7.0.0):
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
new file mode 100644
index 0000000000..5f6ee1de5b
index 0000000000..720ec0cb57
--- /dev/null
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -0,0 +1,34 @@
@@ -0,0 +1,41 @@
+include ../rh-virtio.mak
+
+CONFIG_ARM_GIC_KVM=y
@ -79,6 +91,8 @@ index 0000000000..5f6ee1de5b
+CONFIG_ARM_SMMUV3=y
+CONFIG_ARM_V7M=y
+CONFIG_ARM_VIRT=y
+CONFIG_CXL=y
+CONFIG_CXL_MEM_DEVICE=y
+CONFIG_EDID=y
+CONFIG_PCIE_PORT=y
+CONFIG_PCI_DEVICES=y
@ -95,6 +109,8 @@ index 0000000000..5f6ee1de5b
+CONFIG_VFIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MEM=y
+CONFIG_VIRTIO_IOMMU=y
+CONFIG_XIO3130=y
+CONFIG_NVDIMM=y
+CONFIG_ACPI_APEI=y
@ -105,12 +121,15 @@ index 0000000000..5f6ee1de5b
+CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y
+CONFIG_PVPANIC_PCI=y
+CONFIG_PXB=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
diff --git a/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
new file mode 100644
index 0000000000..6a3e3f0227
index 0000000000..dbb7d30829
--- /dev/null
+++ b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
@@ -0,0 +1,35 @@
@@ -0,0 +1,37 @@
+include ../rh-virtio.mak
+
+CONFIG_DIMM=y
@ -146,6 +165,8 @@ index 0000000000..6a3e3f0227
+CONFIG_TPM=y
+CONFIG_TPM_SPAPR=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
diff --git a/configs/devices/rh-virtio.mak b/configs/devices/rh-virtio.mak
new file mode 100644
index 0000000000..94ede1b5f6
@ -164,10 +185,10 @@ index 0000000000..94ede1b5f6
+CONFIG_VIRTIO_SERIAL=y
diff --git a/configs/devices/s390x-softmmu/s390x-rh-devices.mak b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
new file mode 100644
index 0000000000..d3b38312e1
index 0000000000..69a799adbd
--- /dev/null
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -0,0 +1,15 @@
@@ -0,0 +1,18 @@
+include ../rh-virtio.mak
+
+CONFIG_PCI=y
@ -183,12 +204,15 @@ index 0000000000..d3b38312e1
+CONFIG_VHOST_USER=y
+CONFIG_VIRTIO_CCW=y
+CONFIG_WDT_DIAG288=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
new file mode 100644
index 0000000000..d0c9e66641
index 0000000000..10cb0a14e0
--- /dev/null
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -0,0 +1,103 @@
@@ -0,0 +1,109 @@
+include ../rh-virtio.mak
+
+CONFIG_ACPI=y
@ -204,6 +228,8 @@ index 0000000000..d0c9e66641
+CONFIG_APIC=y
+CONFIG_APM=y
+CONFIG_BOCHS_DISPLAY=y
+CONFIG_CXL=y
+CONFIG_CXL_MEM_DEVICE=y
+CONFIG_DIMM=y
+CONFIG_E1000E_PCI_EXPRESS=y
+CONFIG_E1000_PCI=y
@ -281,6 +307,7 @@ index 0000000000..d0c9e66641
+CONFIG_VIRTIO_MEM=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VGA=y
+CONFIG_VIRTIO_IOMMU=y
+CONFIG_VMMOUSE=y
+CONFIG_VMPORT=y
+CONFIG_VTD=y
@ -292,26 +319,14 @@ index 0000000000..d0c9e66641
+CONFIG_TPM_TIS_ISA=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_SGX=y
diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c
index bd9bbade70..de1e401cdf 100644
--- a/hw/acpi/ich9.c
+++ b/hw/acpi/ich9.c
@@ -435,8 +435,8 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm)
static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
pm->acpi_memory_hotplug.is_enabled = true;
pm->cpu_hotplug_legacy = true;
- pm->disable_s3 = 0;
- pm->disable_s4 = 0;
+ pm->disable_s3 = 1;
+ pm->disable_s4 = 1;
pm->s4_val = 2;
pm->use_acpi_hotplug_bridge = true;
pm->keep_pci_slot_hpc = true;
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
diff --git a/hw/arm/meson.build b/hw/arm/meson.build
index 721a8eb8be..87ed4dd914 100644
index 92f9f6e000..c5e94c997c 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -31,7 +31,7 @@ arm_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c'))
@@ -30,7 +30,7 @@ arm_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c'))
arm_ss.add(when: 'CONFIG_ZYNQ', if_true: files('xilinx_zynq.c'))
arm_ss.add(when: 'CONFIG_SABRELITE', if_true: files('sabrelite.c'))
@ -321,7 +336,7 @@ index 721a8eb8be..87ed4dd914 100644
arm_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx.c', 'pxa2xx_gpio.c', 'pxa2xx_pic.c'))
arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic.c'))
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index 347875a0cd..ca1776121f 100644
index 64ae4a6899..9b8e782c19 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -49,6 +49,8 @@
@ -333,7 +348,7 @@ index 347875a0cd..ca1776121f 100644
/********************************************************/
/* debug Floppy devices */
@@ -2338,6 +2340,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp)
@@ -2346,6 +2348,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp)
FDrive *drive;
static int command_tables_inited = 0;
@ -379,10 +394,10 @@ index 3bb6a58698..6447fdb02e 100644
* Also accept 8 MB/16 MB for backward compatibility.
*/
diff --git a/hw/ide/piix.c b/hw/ide/piix.c
index ce89fd0aa3..fbcf802b13 100644
index 9a9b28078e..f3ce3fbcee 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -232,7 +232,8 @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
@@ -197,7 +197,8 @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
k->device_id = PCI_DEVICE_ID_INTEL_82371SB_1;
k->class_id = PCI_CLASS_STORAGE_IDE;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
@ -392,7 +407,7 @@ index ce89fd0aa3..fbcf802b13 100644
}
static const TypeInfo piix3_ide_info = {
@@ -261,6 +262,8 @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
@@ -220,6 +221,8 @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
k->class_id = PCI_CLASS_STORAGE_IDE;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
dc->hotpluggable = false;
@ -402,12 +417,12 @@ index ce89fd0aa3..fbcf802b13 100644
static const TypeInfo piix4_ide_info = {
diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c
index 4efdf75620..5143ebaa27 100644
index b92b63bedc..3b6235dde6 100644
--- a/hw/input/pckbd.c
+++ b/hw/input/pckbd.c
@@ -814,6 +814,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
@@ -957,6 +957,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
dc->vmsd = &vmstate_kbd_isa;
isa->build_aml = i8042_build_aml;
adevc->build_dev_aml = i8042_build_aml;
set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
+ /* Disabled for Red Hat Enterprise Linux: */
+ dc->user_creatable = false;
@ -415,10 +430,10 @@ index 4efdf75620..5143ebaa27 100644
static const TypeInfo i8042_info = {
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index f5bc81296d..282d01e374 100644
index e26e0a64c1..41492fae79 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -1821,6 +1821,7 @@ static const E1000Info e1000_devices[] = {
@@ -1824,6 +1824,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
@ -426,7 +441,7 @@ index f5bc81296d..282d01e374 100644
{
.name = "e1000-82544gc",
.device_id = E1000_DEV_ID_82544GC_COPPER,
@@ -1833,6 +1834,7 @@ static const E1000Info e1000_devices[] = {
@@ -1836,6 +1837,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
@ -452,7 +467,7 @@ index 8a4861f45a..fcb5dfe792 100644
DEFINE_SPAPR_CPU_CORE_TYPE("power7+_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"),
diff --git a/hw/usb/meson.build b/hw/usb/meson.build
index de853d780d..0776ae6a20 100644
index 793df42e21..cd3c305471 100644
--- a/hw/usb/meson.build
+++ b/hw/usb/meson.build
@@ -52,7 +52,7 @@ softmmu_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reade
@ -465,10 +480,10 @@ index de853d780d..0776ae6a20 100644
endif
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 13d0e9b195..3826fa5122 100644
index 3099b38e32..10d91c4ef0 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -22,6 +22,7 @@
@@ -147,6 +147,7 @@ void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu)
/* CPU models. These are not needed for the AArch64 linux-user build. */
#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
@ -476,31 +491,31 @@ index 13d0e9b195..3826fa5122 100644
#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -375,6 +376,7 @@ static void cortex_a9_initfn(Object *obj)
cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */
@@ -500,6 +501,7 @@ static void cortex_a9_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41093000;
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
}
+#endif /* disabled for RHEL */
#ifndef CONFIG_USER_ONLY
static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
@@ -400,6 +402,7 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
REGINFO_SENTINEL
@@ -524,6 +526,7 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
.access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 },
};
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_a7_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -445,6 +448,7 @@ static void cortex_a7_initfn(Object *obj)
cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
@@ -572,6 +575,7 @@ static void cortex_a7_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41072000;
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
}
+#endif /* disabled for RHEL */
static void cortex_a15_initfn(Object *obj)
{
@@ -488,6 +492,7 @@ static void cortex_a15_initfn(Object *obj)
@@ -618,6 +622,7 @@ static void cortex_a15_initfn(Object *obj)
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
}
@ -508,7 +523,7 @@ index 13d0e9b195..3826fa5122 100644
static void cortex_m0_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -928,6 +933,7 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
@@ -1058,6 +1063,7 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
cc->gdb_core_xml_file = "arm-m-profile.xml";
}
@ -516,7 +531,7 @@ index 13d0e9b195..3826fa5122 100644
#ifndef TARGET_AARCH64
/*
@@ -1007,6 +1013,7 @@ static void arm_max_initfn(Object *obj)
@@ -1125,6 +1131,7 @@ static void arm_max_initfn(Object *obj)
#endif /* !TARGET_AARCH64 */
static const ARMCPUInfo arm_tcg_cpus[] = {
@ -524,7 +539,7 @@ index 13d0e9b195..3826fa5122 100644
{ .name = "arm926", .initfn = arm926_initfn },
{ .name = "arm946", .initfn = arm946_initfn },
{ .name = "arm1026", .initfn = arm1026_initfn },
@@ -1022,7 +1029,9 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
@@ -1140,7 +1147,9 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "cortex-a7", .initfn = cortex_a7_initfn },
{ .name = "cortex-a8", .initfn = cortex_a8_initfn },
{ .name = "cortex-a9", .initfn = cortex_a9_initfn },
@ -534,7 +549,7 @@ index 13d0e9b195..3826fa5122 100644
{ .name = "cortex-m0", .initfn = cortex_m0_initfn,
.class_init = arm_v7m_class_init },
{ .name = "cortex-m3", .initfn = cortex_m3_initfn,
@@ -1053,6 +1062,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
@@ -1171,6 +1180,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
@ -543,7 +558,7 @@ index 13d0e9b195..3826fa5122 100644
{ .name = "max", .initfn = arm_max_initfn },
#endif
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index 976be5e0d1..dd78883410 100644
index 912b037c63..cd3ff700ac 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -66,6 +66,7 @@
@ -573,7 +588,7 @@ index 976be5e0d1..dd78883410 100644
POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7,
"POWER7 v2.3")
POWERPC_DEF("power7+_v2.1", CPU_POWERPC_POWER7P_v21, POWER7,
@@ -897,12 +901,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
@@ -896,12 +900,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "7447a", "7447a_v1.2" },
{ "7457a", "7457a_v1.2" },
{ "apollo7pm", "7457a_v1.0" },
@ -589,7 +604,7 @@ index 976be5e0d1..dd78883410 100644
{ "power7", "power7_v2.3" },
{ "power7+", "power7+_v2.1" },
{ "power8e", "power8e_v2.1" },
@@ -912,6 +919,7 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
@@ -911,12 +918,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power10", "power10_v2.0" },
#endif
@ -597,18 +612,18 @@ index 976be5e0d1..dd78883410 100644
/* Generic PowerPCs */
#if defined(TARGET_PPC64)
{ "ppc64", "970fx_v3.1" },
@@ -919,5 +927,6 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
#endif
{ "ppc32", "604" },
{ "ppc", "604" },
{ "default", "604" },
+#endif
{ NULL, NULL }
};
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 05c3ccaaff..6a04ccab1b 100644
index d8a141a023..d086b1c39c 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -36,6 +36,9 @@ static void check_unavailable_features(const S390CPUModel *max_model,
@@ -35,6 +35,9 @@ static void check_unavailable_features(const S390CPUModel *max_model,
(max_model->def->gen == model->def->gen &&
max_model->def->ec_ga < model->def->ec_ga)) {
list_add_feat("type", unavailable);
@ -619,10 +634,10 @@ index 05c3ccaaff..6a04ccab1b 100644
/* detect missing features if any to properly report them */
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index 6acf14d5ec..74f089d87f 100644
index 7bd8db0e7b..81cb489694 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -2512,6 +2512,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
@@ -2520,6 +2520,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
error_setg(errp, "KVM doesn't support CPU models");
return;
}

101
0006-Machine-type-related-general-changes.patch → 0007-Machine-type-related-general-changes.patch
View File

@ -1,4 +1,4 @@
From a525db3951dc68c469d1f51bdc69ab6e75e72c37 Mon Sep 17 00:00:00 2001
From 8ee73de7f30f39293388932bbb0d69b6c9435ab1 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 11 Jan 2019 09:54:45 +0100
Subject: Machine type related general changes
@ -19,6 +19,10 @@ Rebase notes (7.0.0):
- Remove downstream changes leftovers in hw/rtc/mc146818rtc.c
- Remove unnecessary change in hw/usb/hcd-uhci.c
Rebase notes (7.1.0 rc0):
- Moved adding rhel_old_machine_deprecation variable from s390x to general machine types commit
- Moved adding hw_compat_rhel_8_6 struct from x86_64 to general machine types commit
Merged patches (6.1.0):
- f2fb42a3c6 redhat: add missing entries in hw_compat_rhel_8_4
- 1949ec258e hw/arm/virt: Disable PL011 clock migration through hw_compat_rhel_8_3
@ -35,28 +39,32 @@ Merged patches (6.2.0):
Merged patches (7.0.0):
- ef5afcc86d Fix virtio-net-pci* "vectors" compat
- 168f0d56e3 compat: Update hw_compat_rhel_8_5 with 6.2.0 RC2 changes
Merged patches (7.1.0 rc0):
- 38b89dc245 pc: Move s3/s4 suspend disabling to compat (only hw/acpi/piix4.c chunk)
- 1d6439527a WRB: Introduce RHEL 9.0.0 hw compat structure (only hw/core/machine.c and include/hw/boards.h chunk)
---
hw/acpi/piix4.c | 6 +-
hw/acpi/piix4.c | 2 +-
hw/arm/virt.c | 2 +-
hw/core/machine.c | 186 +++++++++++++++++++++++++++++++++++
hw/core/machine.c | 211 +++++++++++++++++++++++++++++++++++
hw/display/vga-isa.c | 2 +-
hw/i386/pc_piix.c | 2 +
hw/i386/pc_q35.c | 2 +
hw/net/rtl8139.c | 4 +-
hw/smbios/smbios.c | 46 ++++++++-
hw/smbios/smbios.c | 46 +++++++-
hw/timer/i8254_common.c | 2 +-
hw/usb/hcd-xhci-pci.c | 59 ++++++++---
hw/usb/hcd-xhci-pci.c | 59 +++++++---
hw/usb/hcd-xhci-pci.h | 1 +
include/hw/boards.h | 21 ++++
include/hw/boards.h | 28 +++++
include/hw/firmware/smbios.h | 5 +-
include/hw/i386/pc.h | 3 +
14 files changed, 316 insertions(+), 25 deletions(-)
14 files changed, 346 insertions(+), 23 deletions(-)
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index fe5625d07a..28544e78c3 100644
index 0a81f1ad93..dbfb362a8f 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -287,7 +287,7 @@ static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
@@ -248,7 +248,7 @@ static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
static const VMStateDescription vmstate_acpi = {
.name = "piix4_pm",
.version_id = 3,
@ -65,22 +73,11 @@ index fe5625d07a..28544e78c3 100644
.post_load = vmstate_acpi_post_load,
.fields = (VMStateField[]) {
VMSTATE_PCI_DEVICE(parent_obj, PIIX4PMState),
@@ -653,8 +653,8 @@ static void piix4_send_gpe(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static Property piix4_pm_properties[] = {
DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 1),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 1),
DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
DEFINE_PROP_BOOL(ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, PIIX4PMState,
use_acpi_hotplug_bridge, true),
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index d2e5ecd234..6a84031fd7 100644
index 9633f822f3..389d6882dd 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1596,7 +1596,7 @@ static void virt_build_smbios(VirtMachineState *vms)
@@ -1617,7 +1617,7 @@ static void virt_build_smbios(VirtMachineState *vms)
smbios_set_defaults("QEMU", product,
vmc->smbios_old_sys_ver ? "1.0" : mc->name, false,
@ -90,13 +87,38 @@ index d2e5ecd234..6a84031fd7 100644
smbios_get_tables(MACHINE(vms), NULL, 0,
&smbios_tables, &smbios_tables_len,
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 1e23fdc14b..ea430d844e 100644
index a673302cce..909f75770b 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -37,6 +37,192 @@
#include "hw/virtio/virtio.h"
@@ -40,6 +40,217 @@
#include "hw/virtio/virtio-pci.h"
#include "qom/object_interfaces.h"
+/*
+ * RHEL only: machine types for previous major releases are deprecated
+ */
+const char *rhel_old_machine_deprecation =
+ "machine types for previous major releases are deprecated";
+
+/*
+ * Mostly the same as hw_compat_6_2
+ */
+GlobalProperty hw_compat_rhel_9_0[] = {
+ /* hw_compat_rhel_9_0 from hw_compat_6_2 */
+ { "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
+};
+const size_t hw_compat_rhel_9_0_len = G_N_ELEMENTS(hw_compat_rhel_9_0);
+
+GlobalProperty hw_compat_rhel_8_6[] = {
+ /* hw_compat_rhel_8_6 bz 2065589 */
+ /*
+ * vhost-vsock device in RHEL 8 kernels doesn't support seqpacket, so
+ * we need do disable it downstream on the latest hw_compat_rhel_8.
+ */
+ { "vhost-vsock-device", "seqpacket", "off" },
+};
+const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+
+/*
+ * Mostly the same as hw_compat_6_0 and hw_compat_6_1
+ */
@ -283,9 +305,9 @@ index 1e23fdc14b..ea430d844e 100644
+};
+const size_t hw_compat_rhel_7_6_len = G_N_ELEMENTS(hw_compat_rhel_7_6);
+
GlobalProperty hw_compat_6_2[] = {
{ "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
};
GlobalProperty hw_compat_7_0[] = {
{ "arm-gicv3-common", "force-8-bit-prio", "on" },
{ "nvme-ns", "eui64-default", "on"},
diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c
index 46abbc5653..505467059b 100644
--- a/hw/display/vga-isa.c
@ -300,10 +322,10 @@ index 46abbc5653..505467059b 100644
};
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index b72c03d0a6..c797e98312 100644
index 20962c34e7..1ec5d6a4f8 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -177,6 +177,8 @@ static void pc_init1(MachineState *machine,
@@ -185,6 +185,8 @@ static void pc_init1(MachineState *machine,
smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)",
mc->name, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
@ -313,10 +335,10 @@ index b72c03d0a6..c797e98312 100644
}
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 1780f79bc1..b695f88c45 100644
index 2e5dae9a89..ef471f6664 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -200,6 +200,8 @@ static void pc_q35_init(MachineState *machine)
@@ -201,6 +201,8 @@ static void pc_q35_init(MachineState *machine)
smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)",
mc->name, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
@ -555,13 +577,19 @@ index c193f79443..086a1feb1e 100644
#endif
diff --git a/include/hw/boards.h b/include/hw/boards.h
index c92ac8815c..c90a19b4d1 100644
index 7b416c9787..bfd757c561 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -449,4 +449,25 @@ extern const size_t hw_compat_2_2_len;
@@ -451,4 +451,32 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
+extern GlobalProperty hw_compat_rhel_9_0[];
+extern const size_t hw_compat_rhel_9_0_len;
+
+extern GlobalProperty hw_compat_rhel_8_6[];
+extern const size_t hw_compat_rhel_8_6_len;
+
+extern GlobalProperty hw_compat_rhel_8_5[];
+extern const size_t hw_compat_rhel_8_5_len;
+
@ -583,6 +611,7 @@ index c92ac8815c..c90a19b4d1 100644
+extern GlobalProperty hw_compat_rhel_7_6[];
+extern const size_t hw_compat_rhel_7_6_len;
+
+extern const char *rhel_old_machine_deprecation;
#endif
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 4b7ad77a44..9acff96a86 100644
@ -601,10 +630,10 @@ index 4b7ad77a44..9acff96a86 100644
void smbios_get_tables(MachineState *ms,
const struct smbios_phys_mem_area *mem_array,
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 1a27de9c8b..91331059d9 100644
index 8435733bd6..4d9e95a091 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -113,6 +113,9 @@ struct PCMachineClass {
@@ -112,6 +112,9 @@ struct PCMachineClass {
bool smbios_defaults;
bool smbios_legacy_mode;
bool smbios_uuid_encoded;

351
0007-Add-aarch64-machine-types.patch → 0008-Add-aarch64-machine-types.patch
View File

@ -1,4 +1,4 @@
From 697aaa43e3c0f20fc312f06be6c1093f1ba907e1 Mon Sep 17 00:00:00 2001
From dfe5c09a8cca1dcbff5798951fa88b7f540ea4ed Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 12:53:31 +0200
Subject: Add aarch64 machine types
@ -17,6 +17,12 @@ Rebase notes (7.0.0):
- Added dtb-kaslr-seed option
- Set no_tcg_lpa2 to true
Rebase notes (7.1.0 rc0):
- replace dtb_kaslr_seed by dtb_randomness
Rebase notes (7.1.0 rc3):
- Updated dtb_randomness comment
Merged patches (6.2.0):
- 9a3d4fde0e hw/arm/virt: Remove 9.0 machine type
- f7d04d6695 hw: arm: virt: Add hw_compat_rhel_8_5 to 8.5 machine type
@ -29,13 +35,28 @@ Merged patches (7.0.0):
- a1d1b6eeb6 hw/arm/virt: Expose the 'RAS' option
- 47f8fe1b82 hw/arm/virt: Add 9.0 machine type and remove 8.5 one
- ed2346788f hw/arm/virt: Check no_tcg_its and minor style changes
Merged patches (7.0.0):
- f79b31bdef hw/arm/virt: Remove the dtb-kaslr-seed machine option
- b6fca85f4a hw/arm/virt: Fix missing initialization in instance/class_init()
Merged patches (7.1.0 rc0):
- ac97dd4f9f RHEL-only: AArch64: Drop unsupported CPU types
- e9c0a70664 target/arm: deprecate named CPU models
---
hw/arm/virt.c | 234 +++++++++++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 8 ++
2 files changed, 241 insertions(+), 1 deletion(-)
hw/arm/virt.c | 236 ++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 8 ++
target/arm/cpu-qom.h | 1 +
target/arm/cpu.c | 5 +
target/arm/cpu.h | 2 +
target/arm/cpu64.c | 14 +-
target/arm/cpu_tcg.c | 12 +-
target/arm/helper.c | 2 +
tests/qtest/arm-cpu-features.c | 6 +
9 files changed, 274 insertions(+), 12 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6a84031fd7..e06862d22a 100644
index 389d6882dd..9737b77eca 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -80,6 +80,7 @@
@ -96,7 +117,26 @@ index 6a84031fd7..e06862d22a 100644
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -2250,6 +2292,7 @@ static void machvirt_init(MachineState *machine)
@@ -197,14 +239,18 @@ static const int a15irqmap[] = {
};
static const char *valid_cpus[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
ARM_CPU_TYPE_NAME("cortex-a53"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("cortex-a57"),
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a72"),
ARM_CPU_TYPE_NAME("cortex-a76"),
ARM_CPU_TYPE_NAME("a64fx"),
ARM_CPU_TYPE_NAME("neoverse-n1"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("host"),
ARM_CPU_TYPE_NAME("max"),
};
@@ -2288,6 +2334,7 @@ static void machvirt_init(MachineState *machine)
qemu_add_machine_init_done_notifier(&vms->machine_done);
}
@ -104,7 +144,7 @@ index 6a84031fd7..e06862d22a 100644
static bool virt_get_secure(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2277,6 +2320,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
@@ -2315,6 +2362,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
vms->virt = value;
}
@ -112,7 +152,23 @@ index 6a84031fd7..e06862d22a 100644
static bool virt_get_highmem(Object *obj, Error **errp)
{
@@ -2402,6 +2446,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
@@ -2344,6 +2392,7 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
vms->its = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static bool virt_get_dtb_randomness(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2357,6 +2406,7 @@ static void virt_set_dtb_randomness(Object *obj, bool value, Error **errp)
vms->dtb_randomness = value;
}
+#endif /* disabled for RHEL */
static char *virt_get_oem_id(Object *obj, Error **errp)
{
@@ -2440,6 +2490,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
vms->ras = value;
}
@ -120,7 +176,7 @@ index 6a84031fd7..e06862d22a 100644
static bool virt_get_mte(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2415,6 +2460,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
@@ -2453,6 +2504,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
vms->mte = value;
}
@ -128,7 +184,7 @@ index 6a84031fd7..e06862d22a 100644
static char *virt_get_gic_version(Object *obj, Error **errp)
{
@@ -2818,6 +2864,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
@@ -2884,6 +2936,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
return fixed_ipa ? 0 : requested_pa_size;
}
@ -136,7 +192,7 @@ index 6a84031fd7..e06862d22a 100644
static void virt_machine_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
@@ -3206,3 +3253,188 @@ static void virt_machine_2_6_options(MachineClass *mc)
@@ -3285,3 +3338,184 @@ static void virt_machine_2_6_options(MachineClass *mc)
vmc->no_pmu = true;
}
DEFINE_VIRT_MACHINE(2, 6)
@ -171,6 +227,7 @@ index 6a84031fd7..e06862d22a 100644
+ hc->unplug_request = virt_machine_device_unplug_request_cb;
+ hc->unplug = virt_machine_device_unplug_cb;
+ mc->nvdimm_supported = true;
+ mc->smp_props.clusters_supported = true;
+ mc->auto_enable_numa_with_memhp = true;
+ mc->auto_enable_numa_with_memdev = true;
+ mc->default_ram_id = "mach-virt.ram";
@ -233,13 +290,6 @@ index 6a84031fd7..e06862d22a 100644
+ "Override the default value of field OEM Table ID "
+ "in ACPI table header."
+ "The string may be up to 8 bytes in size");
+
+ object_class_property_add_bool(oc, "dtb-kaslr-seed",
+ virt_get_dtb_kaslr_seed,
+ virt_set_dtb_kaslr_seed);
+ object_class_property_set_description(oc, "dtb-kaslr-seed",
+ "Set off to disable passing of kaslr-seed "
+ "dtb node to guest");
+}
+
+static void rhel_virt_instance_init(Object *obj)
@ -258,6 +308,8 @@ index 6a84031fd7..e06862d22a 100644
+ vms->gic_version = VIRT_GIC_VERSION_NOSEL;
+
+ vms->highmem_ecam = !vmc->no_highmem_ecam;
+ vms->highmem_mmio = true;
+ vms->highmem_redists = true;
+
+ if (vmc->no_its) {
+ vms->its = false;
@ -284,8 +336,8 @@ index 6a84031fd7..e06862d22a 100644
+ /* MTE is disabled by default and non-configurable for RHEL */
+ vms->mte = false;
+
+ /* Supply a kaslr-seed by default */
+ vms->dtb_kaslr_seed = true;
+ /* Supply kaslr-seed and rng-seed by default, non-configurable for RHEL */
+ vms->dtb_randomness = true;
+
+ vms->irqmap = a15irqmap;
+
@ -326,10 +378,10 @@ index 6a84031fd7..e06862d22a 100644
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 0, 0)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 7e76ee2619..9b1efe8f0e 100644
index 6ec479ca2b..22b54ec510 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -179,9 +179,17 @@ struct VirtMachineState {
@@ -180,9 +180,17 @@ struct VirtMachineState {
#define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM)
@ -347,6 +399,261 @@ index 7e76ee2619..9b1efe8f0e 100644
void virt_acpi_setup(VirtMachineState *vms);
bool virt_is_acpi_enabled(VirtMachineState *vms);
diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h
index 64c44cef2d..82e97249bc 100644
--- a/target/arm/cpu-qom.h
+++ b/target/arm/cpu-qom.h
@@ -35,6 +35,7 @@ typedef struct ARMCPUInfo {
const char *name;
void (*initfn)(Object *obj);
void (*class_init)(ObjectClass *oc, void *data);
+ const char *deprecation_note;
} ARMCPUInfo;
void arm_cpu_register(const ARMCPUInfo *info);
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 7ec3281da9..86174077f1 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2200,8 +2200,13 @@ static void arm_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
acc->info = data;
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
}
void arm_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 5168e3d837..876ca7cebb 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -34,6 +34,8 @@
#define KVM_HAVE_MCE_INJECTION 1
#endif
+#define RHEL_CPU_DEPRECATION "use 'host' / 'max'"
+
#define EXCP_UDEF 1 /* undefined instruction */
#define EXCP_SWI 2 /* software interrupt */
#define EXCP_PREFETCH_ABORT 3
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 78e27f778a..1a16c9dccc 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -94,6 +94,7 @@ static void aarch64_a57_initfn(Object *obj)
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a53_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -343,6 +344,7 @@ static void aarch64_neoverse_n1_initfn(Object *obj)
/* From D5.1 AArch64 PMU register summary */
cpu->isar.reset_pmcr_el0 = 0x410c3000;
}
+#endif /* disabled for RHEL */
void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
{
@@ -1108,6 +1110,7 @@ static void aarch64_max_initfn(Object *obj)
qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a64fx_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -1156,14 +1159,18 @@ static void aarch64_a64fx_initfn(Object *obj)
/* TODO: Add A64FX specific HPC extension registers */
}
+#endif /* disabled for RHEL */
static const ARMCPUInfo aarch64_cpus[] = {
- { .name = "cortex-a57", .initfn = aarch64_a57_initfn },
+ { .name = "cortex-a57", .initfn = aarch64_a57_initfn,
+ .deprecation_note = RHEL_CPU_DEPRECATION },
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a53", .initfn = aarch64_a53_initfn },
{ .name = "cortex-a72", .initfn = aarch64_a72_initfn },
{ .name = "cortex-a76", .initfn = aarch64_a76_initfn },
{ .name = "a64fx", .initfn = aarch64_a64fx_initfn },
{ .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn },
+#endif /* disabled for RHEL */
{ .name = "max", .initfn = aarch64_max_initfn },
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
{ .name = "host", .initfn = aarch64_host_initfn },
@@ -1235,8 +1242,13 @@ static void aarch64_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
acc->info = data;
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
}
void aarch64_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 10d91c4ef0..33cbc2cfe8 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -144,10 +144,10 @@ void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu)
}
#endif /* !CONFIG_USER_ONLY */
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/* CPU models. These are not needed for the AArch64 linux-user build. */
#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
-#if 0 /* Disabled for Red Hat Enterprise Linux */
#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -501,7 +501,6 @@ static void cortex_a9_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41093000;
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
}
-#endif /* disabled for RHEL */
#ifndef CONFIG_USER_ONLY
static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
@@ -526,7 +525,6 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
.access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 },
};
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_a7_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -575,7 +573,6 @@ static void cortex_a7_initfn(Object *obj)
cpu->isar.reset_pmcr_el0 = 0x41072000;
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
}
-#endif /* disabled for RHEL */
static void cortex_a15_initfn(Object *obj)
{
@@ -622,7 +619,6 @@ static void cortex_a15_initfn(Object *obj)
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
}
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_m0_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -1063,7 +1059,6 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
cc->gdb_core_xml_file = "arm-m-profile.xml";
}
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
/*
@@ -1131,7 +1126,6 @@ static void arm_max_initfn(Object *obj)
#endif /* !TARGET_AARCH64 */
static const ARMCPUInfo arm_tcg_cpus[] = {
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "arm926", .initfn = arm926_initfn },
{ .name = "arm946", .initfn = arm946_initfn },
{ .name = "arm1026", .initfn = arm1026_initfn },
@@ -1147,9 +1141,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "cortex-a7", .initfn = cortex_a7_initfn },
{ .name = "cortex-a8", .initfn = cortex_a8_initfn },
{ .name = "cortex-a9", .initfn = cortex_a9_initfn },
-#endif /* disabled for RHEL */
{ .name = "cortex-a15", .initfn = cortex_a15_initfn },
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-m0", .initfn = cortex_m0_initfn,
.class_init = arm_v7m_class_init },
{ .name = "cortex-m3", .initfn = cortex_m3_initfn,
@@ -1180,7 +1172,6 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
{ .name = "max", .initfn = arm_max_initfn },
#endif
@@ -1208,3 +1199,4 @@ static void arm_tcg_cpu_register_types(void)
type_init(arm_tcg_cpu_register_types)
#endif /* !CONFIG_USER_ONLY || !TARGET_AARCH64 */
+#endif /* disabled for RHEL */
diff --git a/target/arm/helper.c b/target/arm/helper.c
index d7bc467a2a..a91494b7d3 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -8213,6 +8213,7 @@ void arm_cpu_list(void)
static void arm_cpu_add_definition(gpointer data, gpointer user_data)
{
ObjectClass *oc = data;
+ CPUClass *cc = CPU_CLASS(oc);
CpuDefinitionInfoList **cpu_list = user_data;
CpuDefinitionInfo *info;
const char *typename;
@@ -8222,6 +8223,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
info->name = g_strndup(typename,
strlen(typename) - strlen("-" TYPE_ARM_CPU));
info->q_typename = g_strdup(typename);
+ info->deprecated = !!cc->deprecation_note;
QAPI_LIST_PREPEND(*cpu_list, info);
}
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index 5a14527386..a3579fc303 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -440,8 +440,10 @@ static void test_query_cpu_model_expansion(const void *data)
assert_error(qts, "host", "The CPU type 'host' requires KVM", NULL);
/* Test expected feature presence/absence for some cpu types */
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "cortex-a15", "pmu");
assert_has_not_feature(qts, "cortex-a15", "aarch64");
+#endif /* disabled for RHEL */
/* Enabling and disabling pmu should always work. */
assert_has_feature_enabled(qts, "max", "pmu");
@@ -458,6 +460,7 @@ static void test_query_cpu_model_expansion(const void *data)
assert_has_feature_enabled(qts, "cortex-a57", "pmu");
assert_has_feature_enabled(qts, "cortex-a57", "aarch64");
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "a64fx", "pmu");
assert_has_feature_enabled(qts, "a64fx", "aarch64");
/*
@@ -470,6 +473,7 @@ static void test_query_cpu_model_expansion(const void *data)
"{ 'sve384': true }");
assert_error(qts, "a64fx", "cannot enable sve640",
"{ 'sve640': true }");
+#endif /* disabled for RHEL */
sve_tests_default(qts, "max");
pauth_tests_default(qts, "max");
@@ -505,9 +509,11 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
QDict *resp;
char *error;
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_error(qts, "cortex-a15",
"We cannot guarantee the CPU type 'cortex-a15' works "
"with KVM on this host", NULL);
+#endif /* disabled for RHEL */
assert_has_feature_enabled(qts, "host", "aarch64");
--
2.31.1

58
0008-Add-ppc64-machine-types.patch → 0009-Add-ppc64-machine-types.patch
View File

@ -1,4 +1,4 @@
From f61b3d7dc000886e23943457ee9baf1d4cae43b4 Mon Sep 17 00:00:00 2001
From 77a23381d2a445ee499c4335816f3df08d545aed Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 13:27:13 +0200
Subject: Add ppc64 machine types
@ -19,21 +19,25 @@ Merged patches (6.1.0):
- 0215eb3356 Remove RHEL 7.3.0 machine types (only ppc64 changes)
- af69d1ca6e Remove RHEL 7.4.0 machine types (only ppc64 changes)
- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only ppc64 changes)
Merged patches (7.1.0 rc0):
- baa6790171 target/ppc/cpu-models: Fix ppc_cpu_aliases list for RHEL
---
hw/ppc/spapr.c | 243 ++++++++++++++++++++++++++++++++++++++++
hw/ppc/spapr_cpu_core.c | 13 +++
include/hw/ppc/spapr.h | 4 +
target/ppc/compat.c | 13 ++-
target/ppc/cpu-models.c | 1 +
target/ppc/cpu.h | 1 +
target/ppc/kvm.c | 27 +++++
target/ppc/kvm_ppc.h | 13 +++
7 files changed, 313 insertions(+), 1 deletion(-)
8 files changed, 314 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index a4372ba189..5fdf8b506d 100644
index bc9ba6e6dc..5d0989f87a 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1622,6 +1622,9 @@ static void spapr_machine_reset(MachineState *machine)
@@ -1633,6 +1633,9 @@ static void spapr_machine_reset(MachineState *machine)
pef_kvm_reset(machine->cgs, &error_fatal);
spapr_caps_apply(spapr);
@ -43,7 +47,7 @@ index a4372ba189..5fdf8b506d 100644
first_ppc_cpu = POWERPC_CPU(first_cpu);
if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
@@ -3317,6 +3320,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
@@ -3344,6 +3347,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
spapr->host_serial = g_strdup(value);
}
@ -64,7 +68,7 @@ index a4372ba189..5fdf8b506d 100644
static void spapr_instance_init(Object *obj)
{
SpaprMachineState *spapr = SPAPR_MACHINE(obj);
@@ -3395,6 +3412,12 @@ static void spapr_instance_init(Object *obj)
@@ -3422,6 +3439,12 @@ static void spapr_instance_init(Object *obj)
spapr_get_host_serial, spapr_set_host_serial);
object_property_set_description(obj, "host-serial",
"Host serial number to advertise in guest device tree");
@ -77,7 +81,7 @@ index a4372ba189..5fdf8b506d 100644
}
static void spapr_machine_finalizefn(Object *obj)
@@ -4652,6 +4675,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
@@ -4679,6 +4702,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
vmc->client_architecture_support = spapr_vof_client_architecture_support;
vmc->quiesce = spapr_vof_quiesce;
vmc->setprop = spapr_vof_setprop;
@ -85,15 +89,15 @@ index a4372ba189..5fdf8b506d 100644
}
static const TypeInfo spapr_machine_info = {
@@ -4703,6 +4727,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
@@ -4730,6 +4754,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
} \
type_init(spapr_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* pseries-7.0
* pseries-7.1
*/
@@ -4830,6 +4855,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
@@ -4868,6 +4893,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
}
DEFINE_SPAPR_MACHINE(4_1, "4.1", false);
@ -101,7 +105,7 @@ index a4372ba189..5fdf8b506d 100644
/*
* pseries-4.0
@@ -4849,6 +4875,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
@@ -4887,6 +4913,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
*nv2atsd = 0;
return true;
}
@ -110,7 +114,7 @@ index a4372ba189..5fdf8b506d 100644
static void spapr_machine_4_0_class_options(MachineClass *mc)
{
SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
@@ -5176,6 +5204,221 @@ static void spapr_machine_2_1_class_options(MachineClass *mc)
@@ -5214,6 +5242,221 @@ static void spapr_machine_2_1_class_options(MachineClass *mc)
compat_props_add(mc->compat_props, hw_compat_2_1, hw_compat_2_1_len);
}
DEFINE_SPAPR_MACHINE(2_1, "2.1", false);
@ -371,7 +375,7 @@ index fcb5dfe792..ab8fb5bf62 100644
qdev_unrealize(DEVICE(cpu));
return false;
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index f5c33dcc86..4a68e0a901 100644
index 530d739b1d..6f96972392 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -154,6 +154,7 @@ struct SpaprMachineClass {
@ -382,7 +386,7 @@ index f5c33dcc86..4a68e0a901 100644
bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index,
uint64_t *buid, hwaddr *pio,
hwaddr *mmio32, hwaddr *mmio64,
@@ -241,6 +242,9 @@ struct SpaprMachineState {
@@ -256,6 +257,9 @@ struct SpaprMachineState {
/* Set by -boot */
char *boot_device;
@ -417,11 +421,23 @@ index 7949a24f5a..f207a9ba01 100644
{
const CompatInfo *compat = compat_by_pvr(compat_pvr);
const CompatInfo *min = compat_by_pvr(min_compat_pvr);
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index cd3ff700ac..1cb49c8087 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -746,6 +746,7 @@
/* PowerPC CPU aliases */
PowerPCCPUAlias ppc_cpu_aliases[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ "405", "405d4" },
{ "405cr", "405crc" },
{ "405gp", "405gpd" },
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 047b24ba50..79c5ac50b9 100644
index a4c893cfad..c6575493b7 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1462,6 +1462,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch)
@@ -1464,6 +1464,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch)
/* Compatibility modes */
#if defined(TARGET_PPC64)
@ -430,10 +446,10 @@ index 047b24ba50..79c5ac50b9 100644
uint32_t min_compat_pvr, uint32_t max_compat_pvr);
bool ppc_type_check_compat(const char *cputype, uint32_t compat_pvr,
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index dc93b99189..154888cce5 100644
index 466d0d2f4c..22c100e227 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -90,6 +90,7 @@ static int cap_ppc_nested_kvm_hv;
@@ -89,6 +89,7 @@ static int cap_ppc_nested_kvm_hv;
static int cap_large_decr;
static int cap_fwnmi;
static int cap_rpt_invalidate;
@ -441,7 +457,7 @@ index dc93b99189..154888cce5 100644
static uint32_t debug_inst_opcode;
@@ -137,6 +138,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
@@ -136,6 +137,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
cap_resize_hpt = kvm_vm_check_extension(s, KVM_CAP_SPAPR_RESIZE_HPT);
kvmppc_get_cpu_characteristics(s);
cap_ppc_nested_kvm_hv = kvm_vm_check_extension(s, KVM_CAP_PPC_NESTED_HV);
@ -449,7 +465,7 @@ index dc93b99189..154888cce5 100644
cap_large_decr = kvmppc_get_dec_bits();
cap_fwnmi = kvm_vm_check_extension(s, KVM_CAP_PPC_FWNMI);
/*
@@ -2563,6 +2565,16 @@ int kvmppc_has_cap_rpt_invalidate(void)
@@ -2570,6 +2572,16 @@ int kvmppc_has_cap_rpt_invalidate(void)
return cap_rpt_invalidate;
}
@ -466,7 +482,7 @@ index dc93b99189..154888cce5 100644
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void)
{
uint32_t host_pvr = mfpvr();
@@ -2959,3 +2971,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
@@ -2966,3 +2978,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
{
return true;
}

148
0009-Add-s390x-machine-types.patch → 0010-Add-s390x-machine-types.patch
View File

@ -1,4 +1,4 @@
From 680f343e58a50a99d17bc7dedd3ee90980912023 Mon Sep 17 00:00:00 2001
From 6a14fc5e35a8cec7f049c203d6dc2390fac175f1 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 13:47:32 +0200
Subject: Add s390x machine types
@ -7,6 +7,10 @@ Adding changes to add RHEL machine types for s390x architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
Rebase changes (7.1.0 rc0):
- Moved adding rhel_old_machine_deprecation variable to general machine types commit
Merged patches (6.1.0):
- 64a9a5c971 hw/s390x: Remove the RHEL7-only machine type
- 395516d62b redhat: s390x: add rhel-8.5.0 compat machine
@ -18,62 +22,47 @@ Merged patches (7.0.0):
- e6ff4de4f7 redhat: Add s390x machine type compatibility handling for the rebase to v6.2
- 4b0efa7e21 redhat: Add rhel8.6.0 and rhel9.0.0 machine types for s390x
- dcc64971bf RHEL: mark old machine types as deprecated (partialy)
---
hw/core/machine.c | 6 +++
hw/s390x/s390-virtio-ccw.c | 104 ++++++++++++++++++++++++++++++++++++-
include/hw/boards.h | 2 +
3 files changed, 111 insertions(+), 1 deletion(-)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index ea430d844e..77202a3570 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -37,6 +37,12 @@
#include "hw/virtio/virtio.h"
#include "hw/virtio/virtio-pci.h"
+/*
+ * RHEL only: machine types for previous major releases are deprecated
+ */
+const char *rhel_old_machine_deprecation =
+ "machine types for previous major releases are deprecated";
+
/*
* Mostly the same as hw_compat_6_0 and hw_compat_6_1
*/
Merged patches (7.1.0 rc0):
- 1d6439527a WRB: Introduce RHEL 9.0.0 hw compat structure (only hw/s390x/s390-virtio-ccw.c chunk)
- c8ad21ca31 redhat: Update s390x machine type compatibility for rebase to QEMU 7.0.0
- 5bcf8d874c target/s390x: deprecate CPUs older than z14
---
hw/s390x/s390-virtio-ccw.c | 107 +++++++++++++++++++++++++++++++
target/s390x/cpu_models.c | 11 ++++
target/s390x/cpu_models.h | 2 +
target/s390x/cpu_models_sysemu.c | 2 +
4 files changed, 122 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 90480e7cf9..ec4176a1e0 100644
index cc3097bfee..4c68d72000 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -767,7 +767,7 @@ bool css_migration_enabled(void)
{ \
MachineClass *mc = MACHINE_CLASS(oc); \
ccw_machine_##suffix##_class_options(mc); \
- mc->desc = "VirtIO-ccw based S390 machine v" verstr; \
+ mc->desc = "VirtIO-ccw based S390 machine " verstr; \
if (latest) { \
mc->alias = "s390-ccw-virtio"; \
mc->is_default = true; \
@@ -791,6 +791,7 @@ bool css_migration_enabled(void)
@@ -792,6 +792,7 @@ bool css_migration_enabled(void)
} \
type_init(ccw_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void ccw_machine_7_0_instance_options(MachineState *machine)
static void ccw_machine_7_1_instance_options(MachineState *machine)
{
}
@@ -1115,6 +1116,107 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
@@ -1131,6 +1132,112 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
}
DEFINE_CCW_MACHINE(2_4, "2.4", false);
+#endif
+
+
+static void ccw_machine_rhel900_instance_options(MachineState *machine)
+{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+
+ s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
+}
+
+static void ccw_machine_rhel900_class_options(MachineClass *mc)
+{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_0, hw_compat_rhel_9_0_len);
+}
+DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
+
@ -170,17 +159,84 @@ index 90480e7cf9..ec4176a1e0 100644
static void ccw_machine_register_types(void)
{
diff --git a/include/hw/boards.h b/include/hw/boards.h
index c90a19b4d1..bf59275f18 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -470,4 +470,6 @@ extern const size_t hw_compat_rhel_8_0_len;
extern GlobalProperty hw_compat_rhel_7_6[];
extern const size_t hw_compat_rhel_7_6_len;
+extern const char *rhel_old_machine_deprecation;
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index c3a4f80633..739770dc15 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -45,6 +45,9 @@
* of a following release have been a superset of the previous release. With
* generation 15 one base feature and one optional feature have been deprecated.
*/
+
#endif
+#define RHEL_CPU_DEPRECATION "use at least 'z14', or 'host' / 'qemu' / 'max'"
+
static S390CPUDef s390_cpu_defs[] = {
CPUDEF_INIT(0x2064, 7, 1, 38, 0x00000000U, "z900", "IBM zSeries 900 GA1"),
CPUDEF_INIT(0x2064, 7, 2, 38, 0x00000000U, "z900.2", "IBM zSeries 900 GA2"),
@@ -854,22 +857,30 @@ static void s390_host_cpu_model_class_init(ObjectClass *oc, void *data)
static void s390_base_cpu_model_class_init(ObjectClass *oc, void *data)
{
S390CPUClass *xcc = S390_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
/* all base models are migration safe */
xcc->cpu_def = (const S390CPUDef *) data;
xcc->is_migration_safe = true;
xcc->is_static = true;
xcc->desc = xcc->cpu_def->desc;
+ if (xcc->cpu_def->gen < 14) {
+ cc->deprecation_note = RHEL_CPU_DEPRECATION;
+ }
}
static void s390_cpu_model_class_init(ObjectClass *oc, void *data)
{
S390CPUClass *xcc = S390_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
/* model that can change between QEMU versions */
xcc->cpu_def = (const S390CPUDef *) data;
xcc->is_migration_safe = true;
xcc->desc = xcc->cpu_def->desc;
+ if (xcc->cpu_def->gen < 14) {
+ cc->deprecation_note = RHEL_CPU_DEPRECATION;
+ }
}
static void s390_qemu_cpu_model_class_init(ObjectClass *oc, void *data)
diff --git a/target/s390x/cpu_models.h b/target/s390x/cpu_models.h
index 74d1f87e4f..372160bcd7 100644
--- a/target/s390x/cpu_models.h
+++ b/target/s390x/cpu_models.h
@@ -38,6 +38,8 @@ struct S390CPUDef {
S390FeatBitmap full_feat;
/* used to init full_feat from generated data */
S390FeatInit full_init;
+ /* if deprecated, provides a suggestion */
+ const char *deprecation_note;
};
/* CPU model based on a CPU definition */
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index d086b1c39c..1b9cc66405 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -60,6 +60,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
CpuDefinitionInfo *info;
char *name = g_strdup(object_class_get_name(klass));
S390CPUClass *scc = S390_CPU_CLASS(klass);
+ CPUClass *cc = CPU_CLASS(klass);
/* strip off the -s390x-cpu */
g_strrstr(name, "-" TYPE_S390_CPU)[0] = 0;
@@ -69,6 +70,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
info->migration_safe = scc->is_migration_safe;
info->q_static = scc->is_static;
info->q_typename = g_strdup(object_class_get_name(klass));
+ info->deprecated = !!cc->deprecation_note;
/* check for unavailable features */
if (cpu_list_data->model) {
Object *obj;
--
2.31.1

279
0010-Add-x86_64-machine-types.patch → 0011-Add-x86_64-machine-types.patch
View File

@ -1,4 +1,4 @@
From 427a575ca57966bc72e1ebf218081da530d435d7 Mon Sep 17 00:00:00 2001
From 68c1bbec1fae27b527f85f2666c54fff3d499eaf Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 19 Oct 2018 13:10:31 +0200
Subject: Add x86_64 machine types
@ -31,45 +31,29 @@ Merged patches (7.0.0):
- 6110d865e5 x86: Add q35 RHEL 9.0.0 machine type
- dcc64971bf RHEL: mark old machine types as deprecated (partialy)
- 6b396f182b RHEL: disable "seqpacket" for "vhost-vsock-device" in rhel8.6.0
Merged patches (7.1.0 rc0):
- 38b89dc245 pc: Move s3/s4 suspend disabling to compat (only hw/i386/pc.c chunk)
- 1d6439527a WRB: Introduce RHEL 9.0.0 hw compat structure (x86_64 specific changes)
- 35b5c8554f target/i386: deprecate CPUs older than x86_64-v2 ABI
---
hw/core/machine.c | 10 ++
hw/i386/pc.c | 135 +++++++++++++++++++++-
hw/i386/pc_piix.c | 79 ++++++++++++-
hw/i386/pc_q35.c | 227 ++++++++++++++++++++++++++++++++++++-
hw/i386/pc.c | 147 ++++++++++++++++++++++-
hw/i386/pc_piix.c | 83 ++++++++++++-
hw/i386/pc_q35.c | 231 ++++++++++++++++++++++++++++++++++++-
hw/s390x/s390-virtio-ccw.c | 1 +
include/hw/boards.h | 5 +
include/hw/i386/pc.h | 24 ++++
include/hw/boards.h | 2 +
include/hw/i386/pc.h | 27 +++++
target/i386/cpu.c | 21 ++++
target/i386/kvm/kvm-cpu.c | 1 +
target/i386/kvm/kvm.c | 4 +
tests/qtest/pvpanic-test.c | 5 +-
10 files changed, 484 insertions(+), 7 deletions(-)
10 files changed, 515 insertions(+), 7 deletions(-)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 77202a3570..28989b6e7b 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -43,6 +43,16 @@
const char *rhel_old_machine_deprecation =
"machine types for previous major releases are deprecated";
+GlobalProperty hw_compat_rhel_8_6[] = {
+ /* hw_compat_rhel_8_6 bz 2065589 */
+ /*
+ * vhost-vsock device in RHEL 8 kernels doesn't support seqpacket, so
+ * we need do disable it downstream on the latest hw_compat_rhel_8.
+ */
+ { "vhost-vsock-device", "seqpacket", "off" },
+};
+const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+
/*
* Mostly the same as hw_compat_6_0 and hw_compat_6_1
*/
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index fd55fc725c..263d882af6 100644
index 7280c02ce3..09b62db9e9 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -375,6 +375,137 @@ GlobalProperty pc_compat_1_4[] = {
@@ -390,6 +390,149 @@ GlobalProperty pc_compat_1_4[] = {
};
const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4);
@ -78,6 +62,12 @@ index fd55fc725c..263d882af6 100644
+ * machine type.
+ */
+GlobalProperty pc_rhel_compat[] = {
+ /* we don't support s3/s4 suspend */
+ { "PIIX4_PM", "disable_s3", "1" },
+ { "PIIX4_PM", "disable_s4", "1" },
+ { "ICH9-LPC", "disable_s3", "1" },
+ { "ICH9-LPC", "disable_s4", "1" },
+
+ { TYPE_X86_CPU, "host-phys-bits", "on" },
+ { TYPE_X86_CPU, "host-phys-bits-limit", "48" },
+ { TYPE_X86_CPU, "vmx-entry-load-perf-global-ctrl", "off" },
@ -89,6 +79,12 @@ index fd55fc725c..263d882af6 100644
+};
+const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat);
+
+GlobalProperty pc_rhel_9_0_compat[] = {
+ /* pc_rhel_9_0_compat from pc_compat_6_2 */
+ { "virtio-mem", "unplugged-inaccessible", "off" },
+};
+const size_t pc_rhel_9_0_compat_len = G_N_ELEMENTS(pc_rhel_9_0_compat);
+
+GlobalProperty pc_rhel_8_5_compat[] = {
+ /* pc_rhel_8_5_compat from pc_compat_6_0 */
+ { "qemu64" "-" TYPE_X86_CPU, "family", "6" },
@ -207,7 +203,7 @@ index fd55fc725c..263d882af6 100644
GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled)
{
GSIState *s;
@@ -1738,6 +1869,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
@@ -1910,6 +2053,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
pcmc->pvh_enabled = true;
pcmc->kvmclock_create_always = true;
assert(!mc->get_hotplug_handler);
@ -215,7 +211,7 @@ index fd55fc725c..263d882af6 100644
mc->get_hotplug_handler = pc_get_hotplug_handler;
mc->hotplug_allowed = pc_hotplug_allowed;
mc->cpu_index_to_instance_props = x86_cpu_index_to_props;
@@ -1748,7 +1880,8 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
@@ -1920,7 +2064,8 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
mc->has_hotpluggable_cpus = true;
mc->default_boot_order = "cad";
mc->block_default_type = IF_IDE;
@ -226,10 +222,10 @@ index fd55fc725c..263d882af6 100644
mc->wakeup = pc_machine_wakeup;
hc->pre_plug = pc_machine_device_pre_plug_cb;
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index c797e98312..0cacc0d623 100644
index 1ec5d6a4f8..52111697cb 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -50,6 +50,7 @@
@@ -51,6 +51,7 @@
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "sysemu/xen.h"
@ -237,7 +233,7 @@ index c797e98312..0cacc0d623 100644
#ifdef CONFIG_XEN
#include <xen/hvm/hvm_info_table.h>
#include "hw/xen/xen_pt.h"
@@ -174,8 +175,8 @@ static void pc_init1(MachineState *machine,
@@ -182,8 +183,8 @@ static void pc_init1(MachineState *machine,
if (pcmc->smbios_defaults) {
MachineClass *mc = MACHINE_GET_CLASS(machine);
/* These values are guest ABI, do not change */
@ -248,7 +244,7 @@ index c797e98312..0cacc0d623 100644
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -314,6 +315,7 @@ static void pc_init1(MachineState *machine,
@@ -331,6 +332,7 @@ static void pc_init1(MachineState *machine,
* hw_compat_*, pc_compat_*, or * pc_*_machine_options().
*/
@ -256,7 +252,7 @@ index c797e98312..0cacc0d623 100644
static void pc_compat_2_3_fn(MachineState *machine)
{
X86MachineState *x86ms = X86_MACHINE(machine);
@@ -967,3 +969,76 @@ static void xenfv_3_1_machine_options(MachineClass *m)
@@ -880,3 +882,80 @@ static void xenfv_3_1_machine_options(MachineClass *m)
DEFINE_PC_MACHINE(xenfv, "xenfv-3.1", pc_xen_hvm_init,
xenfv_3_1_machine_options);
#endif
@ -305,6 +301,10 @@ index c797e98312..0cacc0d623 100644
+ pcmc->kvmclock_create_always = false;
+ /* From pc_i440fx_5_1_machine_options() */
+ pcmc->pci_root_uid = 1;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_6,
+ hw_compat_rhel_8_6_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_5,
@ -334,10 +334,10 @@ index c797e98312..0cacc0d623 100644
+DEFINE_PC_MACHINE(rhel760, "pc-i440fx-rhel7.6.0", pc_init_rhel760,
+ pc_machine_rhel760_options);
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index b695f88c45..157160e069 100644
index ef471f6664..4e7f1a707c 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -197,8 +197,8 @@ static void pc_q35_init(MachineState *machine)
@@ -198,8 +198,8 @@ static void pc_q35_init(MachineState *machine)
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
@ -348,7 +348,7 @@ index b695f88c45..157160e069 100644
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -342,6 +342,7 @@ static void pc_q35_init(MachineState *machine)
@@ -352,6 +352,7 @@ static void pc_q35_init(MachineState *machine)
DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn)
@ -356,7 +356,7 @@ index b695f88c45..157160e069 100644
static void pc_q35_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
@@ -631,3 +632,225 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
@@ -654,3 +655,229 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL,
pc_q35_2_4_machine_options);
@ -397,6 +397,10 @@ index b695f88c45..157160e069 100644
+ m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.0.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900,
@ -583,10 +587,10 @@ index b695f88c45..157160e069 100644
+DEFINE_PC_MACHINE(q35_rhel760, "pc-q35-rhel7.6.0", pc_q35_init_rhel760,
+ pc_q35_machine_rhel760_options);
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index ec4176a1e0..465a2a09d2 100644
index 4c68d72000..e1e6b6b5a7 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1136,6 +1136,7 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine)
@@ -1157,6 +1157,7 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine)
static void ccw_machine_rhel860_class_options(MachineClass *mc)
{
ccw_machine_rhel900_class_options(mc);
@ -595,7 +599,7 @@ index ec4176a1e0..465a2a09d2 100644
/* All RHEL machines for prior major releases are deprecated */
mc->deprecation_reason = rhel_old_machine_deprecation;
diff --git a/include/hw/boards.h b/include/hw/boards.h
index bf59275f18..d1555665df 100644
index bfd757c561..0d22c19f4a 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -266,6 +266,8 @@ struct MachineClass {
@ -607,27 +611,20 @@ index bf59275f18..d1555665df 100644
bool ignore_boot_device_suffixes;
bool smbus_no_migration_support;
bool nvdimm_supported;
@@ -449,6 +451,9 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
+extern GlobalProperty hw_compat_rhel_8_6[];
+extern const size_t hw_compat_rhel_8_6_len;
+
extern GlobalProperty hw_compat_rhel_8_5[];
extern const size_t hw_compat_rhel_8_5_len;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 91331059d9..419a6ec24b 100644
index 4d9e95a091..f96bf85df1 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -289,6 +289,30 @@ extern const size_t pc_compat_1_5_len;
@@ -290,6 +290,33 @@ extern const size_t pc_compat_1_5_len;
extern GlobalProperty pc_compat_1_4[];
extern const size_t pc_compat_1_4_len;
+extern GlobalProperty pc_rhel_compat[];
+extern const size_t pc_rhel_compat_len;
+
+extern GlobalProperty pc_rhel_9_0_compat[];
+extern const size_t pc_rhel_9_0_compat_len;
+
+extern GlobalProperty pc_rhel_8_5_compat[];
+extern const size_t pc_rhel_8_5_compat_len;
+
@ -649,11 +646,165 @@ index 91331059d9..419a6ec24b 100644
+extern GlobalProperty pc_rhel_7_6_compat[];
+extern const size_t pc_rhel_7_6_compat_len;
+
/* Helper for setting model-id for CPU models that changed model-id
* depending on QEMU versions up to QEMU 2.4.
#define DEFINE_PC_MACHINE(suffix, namestr, initfn, optsfn) \
static void pc_machine_##suffix##_class_init(ObjectClass *oc, void *data) \
{ \
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 1db1278a59..db97eeb8b0 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -1832,9 +1832,13 @@ static const CPUCaches epyc_milan_cache_info = {
* PT in VMX operation
*/
+#define RHEL_CPU_DEPRECATION \
+ "use at least 'Nehalem' / 'Opteron_G4', or 'host' / 'max'"
+
static const X86CPUDefinition builtin_x86_defs[] = {
{
.name = "qemu64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -1855,6 +1859,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "phenom",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
@@ -1887,6 +1892,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "core2duo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1929,6 +1935,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -1970,6 +1977,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "qemu32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 4,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1984,6 +1992,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -2014,6 +2023,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "coreduo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2047,6 +2057,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "486",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 4,
@@ -2059,6 +2070,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 5,
@@ -2071,6 +2083,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2083,6 +2096,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 3,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2095,6 +2109,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "athlon",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_AMD,
.family = 6,
@@ -2110,6 +2125,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "n270",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2135,6 +2151,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Conroe",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2175,6 +2192,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Penryn",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -3762,6 +3780,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G1",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3782,6 +3801,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3804,6 +3824,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c
index 5eb955ce9a..74c1396a93 100644
index 7237378a7d..7b8a3d5af0 100644
--- a/target/i386/kvm/kvm-cpu.c
+++ b/target/i386/kvm/kvm-cpu.c
@@ -137,6 +137,7 @@ static PropValue kvm_default_props[] = {
@ -665,10 +816,10 @@ index 5eb955ce9a..74c1396a93 100644
};
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 9cf8e03669..6d1e009443 100644
index f148a6d52f..4e5d4bafc4 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3488,6 +3488,7 @@ static int kvm_get_msrs(X86CPU *cpu)
@@ -3626,6 +3626,7 @@ static int kvm_get_msrs(X86CPU *cpu)
struct kvm_msr_entry *msrs = cpu->kvm_msr_buf->entries;
int ret, i;
uint64_t mtrr_top_bits;
@ -676,7 +827,7 @@ index 9cf8e03669..6d1e009443 100644
kvm_msr_buf_reset(cpu);
@@ -3822,6 +3823,9 @@ static int kvm_get_msrs(X86CPU *cpu)
@@ -3981,6 +3982,9 @@ static int kvm_get_msrs(X86CPU *cpu)
break;
case MSR_KVM_ASYNC_PF_EN:
env->async_pf_en_msr = msrs[i].data;
@ -687,7 +838,7 @@ index 9cf8e03669..6d1e009443 100644
case MSR_KVM_ASYNC_PF_INT:
env->async_pf_int_msr = msrs[i].data;
diff --git a/tests/qtest/pvpanic-test.c b/tests/qtest/pvpanic-test.c
index 6dcad2db49..580c2c43d2 100644
index bc7b7dfc39..96e6dee3a1 100644
--- a/tests/qtest/pvpanic-test.c
+++ b/tests/qtest/pvpanic-test.c
@@ -17,7 +17,7 @@ static void test_panic_nopause(void)

107
0011-Enable-make-check.patch → 0012-Enable-make-check.patch
View File

@ -1,4 +1,4 @@
From 5e419e5e0a721bdbbfa6d9b82c8be5c5b3d26a01 Mon Sep 17 00:00:00 2001
From 0833b7e925c98253c90c9de18758517f2778f77d Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 2 Sep 2020 09:39:41 +0200
Subject: Enable make check
@ -24,22 +24,88 @@ Rebase changes (7.0.0):
- Remove unnecessary changes in iotest 051
- Remove changes in bios-tables-test.c and prom-env-test.c qtests
Rebase changes (7.1.0 rc0):
- Disable bcm2835-dma-test (added upstream)
Merged patches (6.1.0):
- 2f129df7d3 redhat: Enable the 'test-block-iothread' test again
Merged patches (7.1.0 rc0):
- 64d736640e RHEL-only: tests/avocado: Switch aarch64 tests from a53 to a57
---
.distro/qemu-kvm.spec.template | 5 ++---
tests/avocado/replay_kernel.py | 2 +-
tests/avocado/reverse_debugging.py | 2 +-
tests/avocado/tcg_plugins.py | 6 +++---
tests/qtest/fuzz-e1000e-test.c | 2 +-
tests/qtest/fuzz-virtio-scsi-test.c | 2 +-
tests/qtest/intel-hda-test.c | 2 +-
tests/qtest/libqos/meson.build | 2 +-
tests/qtest/lpc-ich9-test.c | 2 +-
tests/qtest/meson.build | 4 ----
tests/qtest/meson.build | 7 +------
tests/qtest/usb-hcd-xhci-test.c | 4 ++++
tests/qtest/virtio-net-failover.c | 1 +
9 files changed, 12 insertions(+), 12 deletions(-)
12 files changed, 18 insertions(+), 19 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index 0b2b0dc692..3a7b5f0748 100644
--- a/tests/avocado/replay_kernel.py
+++ b/tests/avocado/replay_kernel.py
@@ -147,7 +147,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/reverse_debugging.py b/tests/avocado/reverse_debugging.py
index d2921e70c3..66d185ed42 100644
--- a/tests/avocado/reverse_debugging.py
+++ b/tests/avocado/reverse_debugging.py
@@ -198,7 +198,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/tcg_plugins.py b/tests/avocado/tcg_plugins.py
index 642d2e49e3..93b3afd823 100644
--- a/tests/avocado/tcg_plugins.py
+++ b/tests/avocado/tcg_plugins.py
@@ -68,7 +68,7 @@ def test_aarch64_virt_insn(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -94,7 +94,7 @@ def test_aarch64_virt_insn_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -120,7 +120,7 @@ def test_aarch64_virt_mem_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
diff --git a/tests/qtest/fuzz-e1000e-test.c b/tests/qtest/fuzz-e1000e-test.c
index 66229e6096..947fba73b7 100644
index 5052883fb6..b5286f4b12 100644
--- a/tests/qtest/fuzz-e1000e-test.c
+++ b/tests/qtest/fuzz-e1000e-test.c
@@ -17,7 +17,7 @@ static void test_lp1879531_eth_get_rss_ex_dst_addr(void)
@ -52,7 +118,7 @@ index 66229e6096..947fba73b7 100644
qtest_outl(s, 0xcf8, 0x80001010);
qtest_outl(s, 0xcfc, 0xe1020000);
diff --git a/tests/qtest/fuzz-virtio-scsi-test.c b/tests/qtest/fuzz-virtio-scsi-test.c
index aaf6d10e18..43727d62ac 100644
index 71c91b0356..dae4139c17 100644
--- a/tests/qtest/fuzz-virtio-scsi-test.c
+++ b/tests/qtest/fuzz-virtio-scsi-test.c
@@ -19,7 +19,7 @@ static void test_mmio_oob_from_memory_region_cache(void)
@ -78,20 +144,20 @@ index a58c98e4d1..c8387e39ce 100644
qtest_outl(s, 0xcf8, 0x80000804);
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index e988d15791..46f7dcb81a 100644
index fd5d6e5ae1..d9409560cd 100644
--- a/tests/qtest/libqos/meson.build
+++ b/tests/qtest/libqos/meson.build
@@ -41,7 +41,7 @@ libqos_srcs = files('../libqtest.c',
@@ -44,7 +44,7 @@ libqos_srcs = files(
'virtio-rng.c',
'virtio-scsi.c',
'virtio-serial.c',
- 'virtio-iommu.c',
+# 'virtio-iommu.c',
'generic-pcihost.c',
# qgraph machines:
'aarch64-xlnx-zcu102-machine.c',
diff --git a/tests/qtest/lpc-ich9-test.c b/tests/qtest/lpc-ich9-test.c
index fe0bef9980..7a9d51579b 100644
index 8ac95b89f7..cd2102555c 100644
--- a/tests/qtest/lpc-ich9-test.c
+++ b/tests/qtest/lpc-ich9-test.c
@@ -15,7 +15,7 @@ static void test_lp1878642_pci_bus_get_irq_level_assert(void)
@ -104,18 +170,18 @@ index fe0bef9980..7a9d51579b 100644
qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index d25f82bb5a..67cd32def1 100644
index be4b30dea2..2c3d62a9fe 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -73,7 +73,6 @@ qtests_i386 = \
@@ -76,7 +76,6 @@ qtests_i386 = \
config_all_devices.has_key('CONFIG_Q35') and \
config_all_devices.has_key('CONFIG_VIRTIO_PCI') and \
slirp.found() ? ['virtio-net-failover'] : []) + \
- (unpack_edk2_blobs ? ['bios-tables-test'] : []) + \
qtests_pci + \
qtests_cxl + \
['fdc-test',
'ide-test',
@@ -86,7 +85,6 @@ qtests_i386 = \
@@ -90,7 +89,6 @@ qtests_i386 = \
'drive_del-test',
'tco-test',
'cpu-plug-test',
@ -123,7 +189,7 @@ index d25f82bb5a..67cd32def1 100644
'vmgenid-test',
'migration-test',
'test-x86-cpuid-compat',
@@ -216,7 +214,6 @@ qtests_arm = \
@@ -212,15 +210,13 @@ qtests_arm = \
# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional
qtests_aarch64 = \
@ -131,7 +197,16 @@ index d25f82bb5a..67cd32def1 100644
(config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-test'] : []) + \
(config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-swtpm-test'] : []) + \
(config_all_devices.has_key('CONFIG_XLNX_ZYNQMP_ARM') ? ['xlnx-can-test', 'fuzz-xlnx-dp-test'] : []) + \
@@ -231,7 +228,6 @@ qtests_s390x = \
['arm-cpu-features',
'numa-test',
'boot-serial-test',
- 'migration-test',
- 'bcm2835-dma-test']
+ 'migration-test']
qtests_s390x = \
(slirp.found() ? ['pxe-test', 'test-netfilter'] : []) + \
@@ -228,7 +224,6 @@ qtests_s390x = \
(config_host.has_key('CONFIG_POSIX') ? ['test-filter-redirector'] : []) + \
['boot-serial-test',
'drive_del-test',
@ -170,7 +245,7 @@ index 10ef9d2a91..3855873050 100644
qtest_start("-device nec-usb-xhci,id=xhci"
diff --git a/tests/qtest/virtio-net-failover.c b/tests/qtest/virtio-net-failover.c
index 78811f1c92..44de8af00c 100644
index 443ee56de9..1bccb3bab9 100644
--- a/tests/qtest/virtio-net-failover.c
+++ b/tests/qtest/virtio-net-failover.c
@@ -25,6 +25,7 @@

22
0012-vfio-cap-number-of-devices-that-can-be-assigned.patch → 0013-vfio-cap-number-of-devices-that-can-be-assigned.patch
View File

@ -1,4 +1,4 @@
From c358fd4c224a9c3f64b4a8fff34cc6b1dc201fa0 Mon Sep 17 00:00:00 2001
From 2092b90c5d7791bedbdb4ba067c90ae44d355e66 Mon Sep 17 00:00:00 2001
From: Bandan Das <bsd@redhat.com>
Date: Tue, 3 Dec 2013 20:05:13 +0100
Subject: vfio: cap number of devices that can be assigned
@ -32,20 +32,20 @@ Signed-off-by: Bandan Das <bsd@redhat.com>
2 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 67a183f17b..1e20f9fd59 100644
index 939dcc3d4a..acbc6673ce 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -45,6 +45,9 @@
#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
@@ -48,6 +48,9 @@
/* Protected by BQL */
static KVMRouteChange vfio_route_change;
+/* RHEL only: Set once for the first assigned dev */
+static uint16_t device_limit;
+
static void vfio_disable_interrupts(VFIOPCIDevice *vdev);
static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
@@ -2810,9 +2813,30 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
static void vfio_msi_disable_common(VFIOPCIDevice *vdev);
@@ -2854,9 +2857,30 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
ssize_t len;
struct stat st;
int groupid;
@ -74,10 +74,10 @@ index 67a183f17b..1e20f9fd59 100644
+ return;
+ }
+
if (!vdev->vbasedev.sysfsdev) {
if (!vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
~vdev->host.slot || ~vdev->host.function)) {
@@ -3249,6 +3273,9 @@ static Property vfio_pci_dev_properties[] = {
@@ -3293,6 +3317,9 @@ static Property vfio_pci_dev_properties[] = {
DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),
DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
no_geforce_quirks, false),
@ -88,10 +88,10 @@ index 67a183f17b..1e20f9fd59 100644
false),
DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd,
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 64777516d1..e0fe6ca97e 100644
index 7c236a52f4..7b7d036a8f 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -139,6 +139,7 @@ struct VFIOPCIDevice {
@@ -140,6 +140,7 @@ struct VFIOPCIDevice {
EventNotifier err_notifier;
EventNotifier req_notifier;
int (*resetfn)(struct VFIOPCIDevice *);

8
0013-Add-support-statement-to-help-output.patch → 0014-Add-support-statement-to-help-output.patch
View File

@ -1,4 +1,4 @@
From ba0c7a5f6b9a1f75666db6b3b795ddf03695dc26 Mon Sep 17 00:00:00 2001
From 793720efdf835b13246f02191f6c07a60a726841 Mon Sep 17 00:00:00 2001
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Wed, 4 Dec 2013 18:53:17 +0100
Subject: Add support statement to -help output
@ -21,10 +21,10 @@ Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
1 file changed, 9 insertions(+)
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 6f646531a0..9d5dab43d2 100644
index 706bd7cff7..e08ef71108 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -831,9 +831,17 @@ static void version(void)
@@ -836,9 +836,17 @@ static void version(void)
QEMU_COPYRIGHT "\n");
}
@ -42,7 +42,7 @@ index 6f646531a0..9d5dab43d2 100644
printf("usage: %s [options] [disk_image]\n\n"
"'disk_image' is a raw hard disk image for IDE hard disk 0\n\n",
g_get_prgname());
@@ -859,6 +867,7 @@ static void help(int exitcode)
@@ -864,6 +872,7 @@ static void help(int exitcode)
"\n"
QEMU_HELP_BOTTOM "\n");

45
0014-globally-limit-the-maximum-number-of-CPUs.patch
View File

@ -1,45 +0,0 @@
From 9ebfd2f6cfa8e79c92e58fd169f90cc768fb865a Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 21 Jan 2014 10:46:52 +0100
Subject: globally limit the maximum number of CPUs
We now globally limit the number of VCPUs.
Especially, there is no way one can specify more than
max_cpus VCPUs for a VM.
This allows us the restore the ppc max_cpus limitation to the upstream
default and minimize the ppc hack in kvm-all.c.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Signed-off-by: Danilo Cesar Lemes de Paula <ddepaula@redhat.com>
---
accel/kvm/kvm-all.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 5f1377ca04..fdf0e4d429 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2430,6 +2430,18 @@ static int kvm_init(MachineState *ms)
soft_vcpus_limit = kvm_recommended_vcpus(s);
hard_vcpus_limit = kvm_max_vcpus(s);
+#ifdef HOST_PPC64
+ /*
+ * On POWER, the kernel advertises a soft limit based on the
+ * number of CPU threads on the host. We want to allow exceeding
+ * this for testing purposes, so we don't want to set hard limit
+ * to soft limit as on x86.
+ */
+#else
+ /* RHEL doesn't support nr_vcpus > soft_vcpus_limit */
+ hard_vcpus_limit = soft_vcpus_limit;
+#endif
+
while (nc->name) {
if (nc->num > soft_vcpus_limit) {
warn_report("Number of %s cpus requested (%d) exceeds "
--
2.31.1

6
0015-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch
View File

@ -1,4 +1,4 @@
From 4b6c8cdc52fdf94d4098d278defb3833dce1d189 Mon Sep 17 00:00:00 2001
From 62589d41546b4200fe5cff7504514bbe3aa72e45 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 8 Jul 2020 08:35:50 +0200
Subject: Use qemu-kvm in documentation instead of qemu-system-<arch>
@ -36,10 +36,10 @@ index 52d6454b93..d74dbdeca9 100644
.. |I2C| replace:: I\ :sup:`2`\ C
.. |I2S| replace:: I\ :sup:`2`\ S
diff --git a/qemu-options.hx b/qemu-options.hx
index 34e9b32a5c..924f61ab6d 100644
index 31c04f7eea..1290fab5ba 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3233,11 +3233,11 @@ SRST
@@ -3250,11 +3250,11 @@ SRST
::

4
0017-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch → 0016-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch
View File

@ -1,4 +1,4 @@
From 64a06662cdea0ff62efb122be4eab506b2a842d9 Mon Sep 17 00:00:00 2001
From e0b9e638d4145e576409c754f525b83f630d7bb0 Mon Sep 17 00:00:00 2001
From: David Gibson <dgibson@redhat.com>
Date: Wed, 6 Feb 2019 03:58:56 +0000
Subject: BZ1653590: Require at least 64kiB pages for downstream guests & hosts
@ -32,7 +32,7 @@ Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
1 file changed, 7 insertions(+)
diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c
index 655ab856a0..6aa7f93df9 100644
index b4283055c1..59b88aadff 100644
--- a/hw/ppc/spapr_caps.c
+++ b/hw/ppc/spapr_caps.c
@@ -329,12 +329,19 @@ bool spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,

66
0016-virtio-scsi-Reject-scsi-cd-if-data-plane-enabled-RHE.patch
View File

@ -1,66 +0,0 @@
From b72e04cb7e417d9e1c973223747ab3a27abda8b4 Mon Sep 17 00:00:00 2001
From: Fam Zheng <famz@redhat.com>
Date: Wed, 14 Jun 2017 15:37:01 +0200
Subject: virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]
RH-Author: Fam Zheng <famz@redhat.com>
Message-id: <20170614153701.14757-1-famz@redhat.com>
Patchwork-id: 75613
O-Subject: [RHV-7.4 qemu-kvm-rhev PATCH v3] virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]
Bugzilla: 1378816
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Max Reitz <mreitz@redhat.com>
We need a fix for RHEL 7.4 and 7.3.z, but unfortunately upstream isn't
ready. If it were, the changes will be too invasive. To have an idea:
https://lists.gnu.org/archive/html/qemu-devel/2017-05/msg05400.html
is an incomplete attempt to fix part of the issue, and the remaining
work unfortunately involve even more complex changes.
As a band-aid, this partially reverts the effect of ef8875b
(virtio-scsi: Remove op blocker for dataplane, since v2.7). We cannot
simply revert that commit as a whole because we already shipped it in
qemu-kvm-rhev 7.3, since when, block jobs has been possible. We should
only block what has been broken. Also, faithfully reverting the above
commit means adding back the removed op blocker, but that is not enough,
because it still crashes when inserting media into an initially empty
scsi-cd.
All in all, scsi-cd on virtio-scsi-dataplane has basically been unusable
unless the scsi-cd never enters an empty state, so, disable it
altogether. Otherwise it would be much more difficult to avoid
crashing.
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
hw/scsi/virtio-scsi.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 34a968ecfb..7f6da33a8a 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -896,6 +896,15 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
AioContext *old_context;
int ret;
+ /* XXX: Remove this check once block backend is capable of handling
+ * AioContext change upon eject/insert.
+ * s->ctx is NULL if ioeventfd is off, s->ctx is qemu_get_aio_context() if
+ * data plane is not used, both cases are safe for scsi-cd. */
+ if (s->ctx && s->ctx != qemu_get_aio_context() &&
+ object_dynamic_cast(OBJECT(dev), "scsi-cd")) {
+ error_setg(errp, "scsi-cd is not supported by data plane");
+ return;
+ }
if (s->ctx && !s->dataplane_fenced) {
if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
return;
--
2.31.1

6
0018-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch → 0017-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch
View File

@ -1,4 +1,4 @@
From 54f9157a918e1404f2f17ce89a9c8b9088c1bc06 Mon Sep 17 00:00:00 2001
From e87482425c6d8dafe0bd447a1e68710ea6969906 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 20 Aug 2021 18:25:12 +0200
Subject: qcow2: Deprecation warning when opening v2 images rw
@ -44,10 +44,10 @@ Rebase notes (6.1.0):
2 files changed, 7 insertions(+)
diff --git a/block/qcow2.c b/block/qcow2.c
index b5c47931ef..a795e457ac 100644
index c6c6692fb7..bccfbc0024 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1337,6 +1337,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
@@ -1335,6 +1335,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
ret = -ENOTSUP;
goto fail;
}

116
0018-Introduce-upstream-7.0-compat-changes.patch Normal file
View File

@ -0,0 +1,116 @@
From 0be2889fa221ba98bd436fa4b4542e57f623d31b Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 1 Jun 2022 08:09:04 -0400
Subject: Introduce upstream 7.0 compat changes
Addding upstream compat changes to 9.1 structure
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (weekly-220608):
- Added new 7.0 compat added upstream
Rebase notes (QEMU 7.1.0 RC3):
- Setting legacy_no_rng_seed to true for RHEL machine types
---
hw/arm/virt.c | 1 +
hw/core/machine.c | 11 +++++++++++
hw/i386/pc_piix.c | 3 +++
hw/i386/pc_q35.c | 3 +++
hw/s390x/s390-virtio-ccw.c | 1 +
include/hw/boards.h | 3 +++
6 files changed, 22 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 9737b77eca..e80c5b7d8b 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3514,6 +3514,7 @@ static void rhel900_virt_options(MachineClass *mc)
VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_1, hw_compat_rhel_9_1_len);
/* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
vmc->no_tcg_lpa2 = true;
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 909f75770b..5a3867692d 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -46,6 +46,17 @@
const char *rhel_old_machine_deprecation =
"machine types for previous major releases are deprecated";
+/*
+ * Mostly the same as hw_compat_7_0
+ */
+GlobalProperty hw_compat_rhel_9_1[] = {
+ /* hw_compat_rhel_9_1 from hw_compat_7_0 */
+ { "arm-gicv3-common", "force-8-bit-prio", "on" },
+ /* hw_compat_rhel_9_1 from hw_compat_7_0 */
+ { "nvme-ns", "eui64-default", "on"},
+};
+const size_t hw_compat_rhel_9_1_len = G_N_ELEMENTS(hw_compat_rhel_9_1);
+
/*
* Mostly the same as hw_compat_6_2
*/
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 52111697cb..7f56ef4e81 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -927,6 +927,9 @@ static void pc_machine_rhel760_options(MachineClass *m)
pcmc->kvmclock_create_always = false;
/* From pc_i440fx_5_1_machine_options() */
pcmc->pci_root_uid = 1;
+ pcmc->legacy_no_rng_seed = true;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_1,
+ hw_compat_rhel_9_1_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_0,
hw_compat_rhel_9_0_len);
compat_props_add(m->compat_props, pc_rhel_9_0_compat,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 4e7f1a707c..f16dc3bff5 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -692,6 +692,9 @@ static void pc_q35_machine_rhel900_options(MachineClass *m)
m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.0.0";
+ pcmc->legacy_no_rng_seed = true;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_1,
+ hw_compat_rhel_9_1_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_0,
hw_compat_rhel_9_0_len);
compat_props_add(m->compat_props, pc_rhel_9_0_compat,
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index e1e6b6b5a7..de748a0a57 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1144,6 +1144,7 @@ static void ccw_machine_rhel900_instance_options(MachineState *machine)
static void ccw_machine_rhel900_class_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_1, hw_compat_rhel_9_1_len);
compat_props_add(mc->compat_props, hw_compat_rhel_9_0, hw_compat_rhel_9_0_len);
}
DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 0d22c19f4a..130f1c3424 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -453,6 +453,9 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
+extern GlobalProperty hw_compat_rhel_9_1[];
+extern const size_t hw_compat_rhel_9_1_len;
+
extern GlobalProperty hw_compat_rhel_9_0[];
extern const size_t hw_compat_rhel_9_0_len;
--
2.31.1

135
0019-WRB-Introduce-RHEL-9.0.0-hw-compat-structure.patch
View File

@ -1,135 +0,0 @@
From 1d6439527aa6ccabb58208c94417778ccc19de39 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 9 Feb 2022 04:16:25 -0500
Subject: WRB: Introduce RHEL 9.0.0 hw compat structure
General compatibility structure for post RHEL 9.0.0 rebase.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/core/machine.c | 9 +++++++++
hw/i386/pc.c | 6 ++++++
hw/i386/pc_piix.c | 4 ++++
hw/i386/pc_q35.c | 4 ++++
hw/s390x/s390-virtio-ccw.c | 2 ++
include/hw/boards.h | 3 +++
include/hw/i386/pc.h | 3 +++
7 files changed, 31 insertions(+)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 28989b6e7b..dffc3ef4ab 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -53,6 +53,15 @@ GlobalProperty hw_compat_rhel_8_6[] = {
};
const size_t hw_compat_rhel_8_6_len = G_N_ELEMENTS(hw_compat_rhel_8_6);
+/*
+ * Mostly the same as hw_compat_6_2
+ */
+GlobalProperty hw_compat_rhel_9_0[] = {
+ /* hw_compat_rhel_9_0 from hw_compat_6_2 */
+ { "PIIX4_PM", "x-not-migrate-acpi-index", "on"},
+};
+const size_t hw_compat_rhel_9_0_len = G_N_ELEMENTS(hw_compat_rhel_9_0);
+
/*
* Mostly the same as hw_compat_6_0 and hw_compat_6_1
*/
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 263d882af6..0886cfe3fe 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -391,6 +391,12 @@ GlobalProperty pc_rhel_compat[] = {
};
const size_t pc_rhel_compat_len = G_N_ELEMENTS(pc_rhel_compat);
+GlobalProperty pc_rhel_9_0_compat[] = {
+ /* pc_rhel_9_0_compat from pc_compat_6_2 */
+ { "virtio-mem", "unplugged-inaccessible", "off" },
+};
+const size_t pc_rhel_9_0_compat_len = G_N_ELEMENTS(pc_rhel_9_0_compat);
+
GlobalProperty pc_rhel_8_5_compat[] = {
/* pc_rhel_8_5_compat from pc_compat_6_0 */
{ "qemu64" "-" TYPE_X86_CPU, "family", "6" },
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 0cacc0d623..dc987fe93b 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -1014,6 +1014,10 @@ static void pc_machine_rhel760_options(MachineClass *m)
pcmc->kvmclock_create_always = false;
/* From pc_i440fx_5_1_machine_options() */
pcmc->pci_root_uid = 1;
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
compat_props_add(m->compat_props, hw_compat_rhel_8_6,
hw_compat_rhel_8_6_len);
compat_props_add(m->compat_props, hw_compat_rhel_8_5,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 157160e069..52c253c570 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -669,6 +669,10 @@ static void pc_q35_machine_rhel900_options(MachineClass *m)
m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.0.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
}
DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900,
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 465a2a09d2..08e0f6a79b 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1118,12 +1118,14 @@ static void ccw_machine_2_4_class_options(MachineClass *mc)
DEFINE_CCW_MACHINE(2_4, "2.4", false);
#endif
+
static void ccw_machine_rhel900_instance_options(MachineState *machine)
{
}
static void ccw_machine_rhel900_class_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_0, hw_compat_rhel_9_0_len);
}
DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index d1555665df..635e45dd71 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -451,6 +451,9 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
+extern GlobalProperty hw_compat_rhel_9_0[];
+extern const size_t hw_compat_rhel_9_0_len;
+
extern GlobalProperty hw_compat_rhel_8_6[];
extern const size_t hw_compat_rhel_8_6_len;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 419a6ec24b..a492c420b5 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -292,6 +292,9 @@ extern const size_t pc_compat_1_4_len;
extern GlobalProperty pc_rhel_compat[];
extern const size_t pc_rhel_compat_len;
+extern GlobalProperty pc_rhel_9_0_compat[];
+extern const size_t pc_rhel_9_0_compat_len;
+
extern GlobalProperty pc_rhel_8_5_compat[];
extern const size_t pc_rhel_8_5_compat_len;
--
2.31.1

38
0020-redhat-Update-s390x-machine-type-compatibility-for-r.patch
View File

@ -1,38 +0,0 @@
From c8ad21ca31892f8798cf82508c2b2c61bf3b9895 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Mon, 4 Apr 2022 12:15:50 +0200
Subject: redhat: Update s390x machine type compatibility for rebase to QEMU
7.0.0
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 143: Update machine type compatibility for QEMU 7.0.0 update [s390x]
RH-Commit: [23/23] 0ecf97d7bdddc50565b5779c64744b353f715cbd
RH-Bugzilla: 2064782
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
No s390x-specific machine class property updates required this time,
only an update to the default qemu cpu model.
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 08e0f6a79b..4a491d4988 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1121,6 +1121,9 @@ DEFINE_CCW_MACHINE(2_4, "2.4", false);
static void ccw_machine_rhel900_instance_options(MachineState *machine)
{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+
+ s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
}
static void ccw_machine_rhel900_class_options(MachineClass *mc)
--
2.31.1

70
0021-pc-Move-s3-s4-suspend-disabling-to-compat.patch
View File

@ -1,70 +0,0 @@
From 38b89dc24551258b630f09d1c654b6c72b265c79 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Thu, 14 Apr 2022 14:58:43 +0100
Subject: pc: Move s3/s4 suspend disabling to compat
RH-Author: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-MergeRequest: 155: 7.0 machine type fixes (x86)
RH-Commit: [26/26] 7d666032d5f5dab1444ebba085f92f2de4e86699
RH-Bugzilla: 2064771
Our downstream patches currently have tweaks in the C code to disable
s3/s4; Thomas pointed out we can just set the property.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
hw/acpi/ich9.c | 4 ++--
hw/acpi/piix4.c | 4 ++--
hw/i386/pc.c | 6 ++++++
3 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c
index de1e401cdf..bd9bbade70 100644
--- a/hw/acpi/ich9.c
+++ b/hw/acpi/ich9.c
@@ -435,8 +435,8 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm)
static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
pm->acpi_memory_hotplug.is_enabled = true;
pm->cpu_hotplug_legacy = true;
- pm->disable_s3 = 1;
- pm->disable_s4 = 1;
+ pm->disable_s3 = 0;
+ pm->disable_s4 = 0;
pm->s4_val = 2;
pm->use_acpi_hotplug_bridge = true;
pm->keep_pci_slot_hpc = true;
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index 28544e78c3..2fb2b43248 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -653,8 +653,8 @@ static void piix4_send_gpe(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
static Property piix4_pm_properties[] = {
DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 1),
- DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 1),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
+ DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
DEFINE_PROP_BOOL(ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, PIIX4PMState,
use_acpi_hotplug_bridge, true),
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 0886cfe3fe..f98f842f80 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -380,6 +380,12 @@ const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4);
* machine type.
*/
GlobalProperty pc_rhel_compat[] = {
+ /* we don't support s3/s4 suspend */
+ { "PIIX4_PM", "disable_s3", "1" },
+ { "PIIX4_PM", "disable_s4", "1" },
+ { "ICH9-LPC", "disable_s3", "1" },
+ { "ICH9-LPC", "disable_s4", "1" },
+
{ TYPE_X86_CPU, "host-phys-bits", "on" },
{ TYPE_X86_CPU, "host-phys-bits-limit", "48" },
{ TYPE_X86_CPU, "vmx-entry-load-perf-global-ctrl", "off" },
--
2.31.1

87
kvm-Add-dirty-sync-missed-zero-copy-migration-stat.patch
View File

@ -1,87 +0,0 @@
From ac346634c5731407baa9de709dbd4d5cc6f45301 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 11 Jul 2022 18:11:12 -0300
Subject: [PATCH 02/11] Add dirty-sync-missed-zero-copy migration stat
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [2/6] 115035fd0a4e4b9439c91fb0f5d1a2f9244ba369 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20220711211112.18951-3-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit cf20c897338067ab4b70a4596fdccaf90c7e29a1)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 2 ++
monitor/hmp-cmds.c | 5 +++++
qapi/migration.json | 7 ++++++-
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/migration/migration.c b/migration/migration.c
index 8fb3eae910..3a3a7a4a50 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1017,6 +1017,8 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
info->ram->normal_bytes = ram_counters.normal * page_size;
info->ram->mbps = s->mbps;
info->ram->dirty_sync_count = ram_counters.dirty_sync_count;
+ info->ram->dirty_sync_missed_zero_copy =
+ ram_counters.dirty_sync_missed_zero_copy;
info->ram->postcopy_requests = ram_counters.postcopy_requests;
info->ram->page_size = page_size;
info->ram->multifd_bytes = ram_counters.multifd_bytes;
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index 634968498b..9cec01de38 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -305,6 +305,11 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
monitor_printf(mon, "postcopy ram: %" PRIu64 " kbytes\n",
info->ram->postcopy_bytes >> 10);
}
+ if (info->ram->dirty_sync_missed_zero_copy) {
+ monitor_printf(mon,
+ "Zero-copy-send fallbacks happened: %" PRIu64 " times\n",
+ info->ram->dirty_sync_missed_zero_copy);
+ }
}
if (info->has_disk) {
diff --git a/qapi/migration.json b/qapi/migration.json
index 5105790cd0..9b38b3c21c 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -55,6 +55,10 @@
# @postcopy-bytes: The number of bytes sent during the post-copy phase
# (since 7.0).
#
+# @dirty-sync-missed-zero-copy: Number of times dirty RAM synchronization could
+# not avoid copying dirty pages. This is between
+# 0 and @dirty-sync-count * @multifd-channels.
+# (since 7.1)
# Since: 0.14
##
{ 'struct': 'MigrationStats',
@@ -65,7 +69,8 @@
'postcopy-requests' : 'int', 'page-size' : 'int',
'multifd-bytes' : 'uint64', 'pages-per-second' : 'uint64',
'precopy-bytes' : 'uint64', 'downtime-bytes' : 'uint64',
- 'postcopy-bytes' : 'uint64' } }
+ 'postcopy-bytes' : 'uint64',
+ 'dirty-sync-missed-zero-copy' : 'uint64' } }
##
# @XBZRLECacheStats:
--
2.31.1

41
kvm-Enable-virtio-iommu-pci-on-aarch64.patch
View File

@ -1,41 +0,0 @@
From 85781b8745fa1581a66f64011d61a4f0c4e103dc Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Fri, 6 May 2022 17:03:11 +0200
Subject: [PATCH 3/5] Enable virtio-iommu-pci on aarch64
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 83: Enable virtio-iommu-pci on aarch64
RH-Commit: [1/1] 23e5c0832e52c66adf5fd6daccdc3edddc7ecb8b (eauger1/centos-qemu-kvm)
RH-Bugzilla: 1477099
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1477099
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45128798
Upstream Status: RHEL-only
Tested: With virtio-net-pci and virtio-block-pci
let's enable the virtio-iommu-pci device on aarch64 by
turning CONFIG_VIRTIO_IOMMU on.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
configs/devices/aarch64-softmmu/aarch64-rh-devices.mak | 1 +
1 file changed, 1 insertion(+)
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
index 187938573f..1618d31b89 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -23,6 +23,7 @@ CONFIG_VFIO_PCI=y
CONFIG_VIRTIO_MMIO=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_MEM=y
+CONFIG_VIRTIO_IOMMU=y
CONFIG_XIO3130=y
CONFIG_NVDIMM=y
CONFIG_ACPI_APEI=y
--
2.31.1

41
kvm-Enable-virtio-iommu-pci-on-x86_64.patch
View File

@ -1,41 +0,0 @@
From c531a39171201f8a1d063e6af752e5d629c1b4bf Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Thu, 9 Jun 2022 11:35:18 +0200
Subject: [PATCH 4/6] Enable virtio-iommu-pci on x86_64
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 100: Enable virtio-iommu-pci on x86_64
RH-Commit: [1/1] a164af477efc7cb9d3d76a0e644f198f7c9fb2b5 (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2094252
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2094252
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45871185
Upstream Status: RHEL-only
Tested: With virtio-net-pci and virtio-block-pci
let's enable the virtio-iommu-pci device on x86_64 by
turning CONFIG_VIRTIO_IOMMU on.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
configs/devices/x86_64-softmmu/x86_64-rh-devices.mak | 1 +
1 file changed, 1 insertion(+)
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
index d0c9e66641..3850b9de72 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -90,6 +90,7 @@ CONFIG_VHOST_USER_BLK=y
CONFIG_VIRTIO_MEM=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_VGA=y
+CONFIG_VIRTIO_IOMMU=y
CONFIG_VMMOUSE=y
CONFIG_VMPORT=y
CONFIG_VTD=y
--
2.31.1

503
kvm-Introduce-event-loop-base-abstract-class.patch
View File

@ -1,503 +0,0 @@
From 1163da281c178359dd7e1cf1ced5c98caa600f8e Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Date: Mon, 25 Apr 2022 09:57:21 +0200
Subject: [PATCH 01/16] Introduce event-loop-base abstract class
RH-Author: Nicolas Saenz Julienne <nsaenzju@redhat.com>
RH-MergeRequest: 93: util/thread-pool: Expose minimum and maximum size
RH-Commit: [1/3] 5817205d8f56cc4aa98bd5963ecac54a59bad990
RH-Bugzilla: 2031024
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Introduce the 'event-loop-base' abstract class, it'll hold the
properties common to all event loops and provide the necessary hooks for
their creation and maintenance. Then have iothread inherit from it.
EventLoopBaseClass is defined as user creatable and provides a hook for
its children to attach themselves to the user creatable class 'complete'
function. It also provides an update_params() callback to propagate
property changes onto its children.
The new 'event-loop-base' class will live in the root directory. It is
built on its own using the 'link_whole' option (there are no direct
function dependencies between the class and its children, it all happens
trough 'constructor' magic). And also imposes new compilation
dependencies:
qom <- event-loop-base <- blockdev (iothread.c)
And in subsequent patches:
qom <- event-loop-base <- qemuutil (util/main-loop.c)
All this forced some amount of reordering in meson.build:
- Moved qom build definition before qemuutil. Doing it the other way
around (i.e. moving qemuutil after qom) isn't possible as a lot of
core libraries that live in between the two depend on it.
- Process the 'hw' subdir earlier, as it introduces files into the
'qom' source set.
No functional changes intended.
Signed-off-by: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-id: 20220425075723.20019-2-nsaenzju@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 7d5983e3c8c40b1d0668faba31d79905c4fadd7d)
---
event-loop-base.c | 104 +++++++++++++++++++++++++++++++
include/sysemu/event-loop-base.h | 36 +++++++++++
include/sysemu/iothread.h | 6 +-
iothread.c | 65 ++++++-------------
meson.build | 23 ++++---
qapi/qom.json | 22 +++++--
6 files changed, 192 insertions(+), 64 deletions(-)
create mode 100644 event-loop-base.c
create mode 100644 include/sysemu/event-loop-base.h
diff --git a/event-loop-base.c b/event-loop-base.c
new file mode 100644
index 0000000000..a924c73a7c
--- /dev/null
+++ b/event-loop-base.c
@@ -0,0 +1,104 @@
+/*
+ * QEMU event-loop base
+ *
+ * Copyright (C) 2022 Red Hat Inc
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@redhat.com>
+ * Nicolas Saenz Julienne <nsaenzju@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qom/object_interfaces.h"
+#include "qapi/error.h"
+#include "sysemu/event-loop-base.h"
+
+typedef struct {
+ const char *name;
+ ptrdiff_t offset; /* field's byte offset in EventLoopBase struct */
+} EventLoopBaseParamInfo;
+
+static EventLoopBaseParamInfo aio_max_batch_info = {
+ "aio-max-batch", offsetof(EventLoopBase, aio_max_batch),
+};
+
+static void event_loop_base_get_param(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ EventLoopBase *event_loop_base = EVENT_LOOP_BASE(obj);
+ EventLoopBaseParamInfo *info = opaque;
+ int64_t *field = (void *)event_loop_base + info->offset;
+
+ visit_type_int64(v, name, field, errp);
+}
+
+static void event_loop_base_set_param(Object *obj, Visitor *v,
+ const char *name, void *opaque, Error **errp)
+{
+ EventLoopBaseClass *bc = EVENT_LOOP_BASE_GET_CLASS(obj);
+ EventLoopBase *base = EVENT_LOOP_BASE(obj);
+ EventLoopBaseParamInfo *info = opaque;
+ int64_t *field = (void *)base + info->offset;
+ int64_t value;
+
+ if (!visit_type_int64(v, name, &value, errp)) {
+ return;
+ }
+
+ if (value < 0) {
+ error_setg(errp, "%s value must be in range [0, %" PRId64 "]",
+ info->name, INT64_MAX);
+ return;
+ }
+
+ *field = value;
+
+ if (bc->update_params) {
+ bc->update_params(base, errp);
+ }
+
+ return;
+}
+
+static void event_loop_base_complete(UserCreatable *uc, Error **errp)
+{
+ EventLoopBaseClass *bc = EVENT_LOOP_BASE_GET_CLASS(uc);
+ EventLoopBase *base = EVENT_LOOP_BASE(uc);
+
+ if (bc->init) {
+ bc->init(base, errp);
+ }
+}
+
+static void event_loop_base_class_init(ObjectClass *klass, void *class_data)
+{
+ UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass);
+ ucc->complete = event_loop_base_complete;
+
+ object_class_property_add(klass, "aio-max-batch", "int",
+ event_loop_base_get_param,
+ event_loop_base_set_param,
+ NULL, &aio_max_batch_info);
+}
+
+static const TypeInfo event_loop_base_info = {
+ .name = TYPE_EVENT_LOOP_BASE,
+ .parent = TYPE_OBJECT,
+ .instance_size = sizeof(EventLoopBase),
+ .class_size = sizeof(EventLoopBaseClass),
+ .class_init = event_loop_base_class_init,
+ .abstract = true,
+ .interfaces = (InterfaceInfo[]) {
+ { TYPE_USER_CREATABLE },
+ { }
+ }
+};
+
+static void register_types(void)
+{
+ type_register_static(&event_loop_base_info);
+}
+type_init(register_types);
diff --git a/include/sysemu/event-loop-base.h b/include/sysemu/event-loop-base.h
new file mode 100644
index 0000000000..8e77d8b69f
--- /dev/null
+++ b/include/sysemu/event-loop-base.h
@@ -0,0 +1,36 @@
+/*
+ * QEMU event-loop backend
+ *
+ * Copyright (C) 2022 Red Hat Inc
+ *
+ * Authors:
+ * Nicolas Saenz Julienne <nsaenzju@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#ifndef QEMU_EVENT_LOOP_BASE_H
+#define QEMU_EVENT_LOOP_BASE_H
+
+#include "qom/object.h"
+#include "block/aio.h"
+#include "qemu/typedefs.h"
+
+#define TYPE_EVENT_LOOP_BASE "event-loop-base"
+OBJECT_DECLARE_TYPE(EventLoopBase, EventLoopBaseClass,
+ EVENT_LOOP_BASE)
+
+struct EventLoopBaseClass {
+ ObjectClass parent_class;
+
+ void (*init)(EventLoopBase *base, Error **errp);
+ void (*update_params)(EventLoopBase *base, Error **errp);
+};
+
+struct EventLoopBase {
+ Object parent;
+
+ /* AioContext AIO engine parameters */
+ int64_t aio_max_batch;
+};
+#endif
diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h
index 7f714bd136..8f8601d6ab 100644
--- a/include/sysemu/iothread.h
+++ b/include/sysemu/iothread.h
@@ -17,11 +17,12 @@
#include "block/aio.h"
#include "qemu/thread.h"
#include "qom/object.h"
+#include "sysemu/event-loop-base.h"
#define TYPE_IOTHREAD "iothread"
struct IOThread {
- Object parent_obj;
+ EventLoopBase parent_obj;
QemuThread thread;
AioContext *ctx;
@@ -37,9 +38,6 @@ struct IOThread {
int64_t poll_max_ns;
int64_t poll_grow;
int64_t poll_shrink;
-
- /* AioContext AIO engine parameters */
- int64_t aio_max_batch;
};
typedef struct IOThread IOThread;
diff --git a/iothread.c b/iothread.c
index 0f98af0f2a..8fa2f3bfb8 100644
--- a/iothread.c
+++ b/iothread.c
@@ -17,6 +17,7 @@
#include "qemu/module.h"
#include "block/aio.h"
#include "block/block.h"
+#include "sysemu/event-loop-base.h"
#include "sysemu/iothread.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-misc.h"
@@ -152,10 +153,15 @@ static void iothread_init_gcontext(IOThread *iothread)
iothread->main_loop = g_main_loop_new(iothread->worker_context, TRUE);
}
-static void iothread_set_aio_context_params(IOThread *iothread, Error **errp)
+static void iothread_set_aio_context_params(EventLoopBase *base, Error **errp)
{
+ IOThread *iothread = IOTHREAD(base);
ERRP_GUARD();
+ if (!iothread->ctx) {
+ return;
+ }
+
aio_context_set_poll_params(iothread->ctx,
iothread->poll_max_ns,
iothread->poll_grow,
@@ -166,14 +172,15 @@ static void iothread_set_aio_context_params(IOThread *iothread, Error **errp)
}
aio_context_set_aio_params(iothread->ctx,
- iothread->aio_max_batch,
+ iothread->parent_obj.aio_max_batch,
errp);
}
-static void iothread_complete(UserCreatable *obj, Error **errp)
+
+static void iothread_init(EventLoopBase *base, Error **errp)
{
Error *local_error = NULL;
- IOThread *iothread = IOTHREAD(obj);
+ IOThread *iothread = IOTHREAD(base);
char *thread_name;
iothread->stopping = false;
@@ -189,7 +196,7 @@ static void iothread_complete(UserCreatable *obj, Error **errp)
*/
iothread_init_gcontext(iothread);
- iothread_set_aio_context_params(iothread, &local_error);
+ iothread_set_aio_context_params(base, &local_error);
if (local_error) {
error_propagate(errp, local_error);
aio_context_unref(iothread->ctx);
@@ -201,7 +208,7 @@ static void iothread_complete(UserCreatable *obj, Error **errp)
* to inherit.
*/
thread_name = g_strdup_printf("IO %s",
- object_get_canonical_path_component(OBJECT(obj)));
+ object_get_canonical_path_component(OBJECT(base)));
qemu_thread_create(&iothread->thread, thread_name, iothread_run,
iothread, QEMU_THREAD_JOINABLE);
g_free(thread_name);
@@ -226,9 +233,6 @@ static IOThreadParamInfo poll_grow_info = {
static IOThreadParamInfo poll_shrink_info = {
"poll-shrink", offsetof(IOThread, poll_shrink),
};
-static IOThreadParamInfo aio_max_batch_info = {
- "aio-max-batch", offsetof(IOThread, aio_max_batch),
-};
static void iothread_get_param(Object *obj, Visitor *v,
const char *name, IOThreadParamInfo *info, Error **errp)
@@ -288,35 +292,12 @@ static void iothread_set_poll_param(Object *obj, Visitor *v,
}
}
-static void iothread_get_aio_param(Object *obj, Visitor *v,
- const char *name, void *opaque, Error **errp)
-{
- IOThreadParamInfo *info = opaque;
-
- iothread_get_param(obj, v, name, info, errp);
-}
-
-static void iothread_set_aio_param(Object *obj, Visitor *v,
- const char *name, void *opaque, Error **errp)
-{
- IOThread *iothread = IOTHREAD(obj);
- IOThreadParamInfo *info = opaque;
-
- if (!iothread_set_param(obj, v, name, info, errp)) {
- return;
- }
-
- if (iothread->ctx) {
- aio_context_set_aio_params(iothread->ctx,
- iothread->aio_max_batch,
- errp);
- }
-}
-
static void iothread_class_init(ObjectClass *klass, void *class_data)
{
- UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass);
- ucc->complete = iothread_complete;
+ EventLoopBaseClass *bc = EVENT_LOOP_BASE_CLASS(klass);
+
+ bc->init = iothread_init;
+ bc->update_params = iothread_set_aio_context_params;
object_class_property_add(klass, "poll-max-ns", "int",
iothread_get_poll_param,
@@ -330,23 +311,15 @@ static void iothread_class_init(ObjectClass *klass, void *class_data)
iothread_get_poll_param,
iothread_set_poll_param,
NULL, &poll_shrink_info);
- object_class_property_add(klass, "aio-max-batch", "int",
- iothread_get_aio_param,
- iothread_set_aio_param,
- NULL, &aio_max_batch_info);
}
static const TypeInfo iothread_info = {
.name = TYPE_IOTHREAD,
- .parent = TYPE_OBJECT,
+ .parent = TYPE_EVENT_LOOP_BASE,
.class_init = iothread_class_init,
.instance_size = sizeof(IOThread),
.instance_init = iothread_instance_init,
.instance_finalize = iothread_instance_finalize,
- .interfaces = (InterfaceInfo[]) {
- {TYPE_USER_CREATABLE},
- {}
- },
};
static void iothread_register_types(void)
@@ -383,7 +356,7 @@ static int query_one_iothread(Object *object, void *opaque)
info->poll_max_ns = iothread->poll_max_ns;
info->poll_grow = iothread->poll_grow;
info->poll_shrink = iothread->poll_shrink;
- info->aio_max_batch = iothread->aio_max_batch;
+ info->aio_max_batch = iothread->parent_obj.aio_max_batch;
QAPI_LIST_APPEND(*tail, info);
return 0;
diff --git a/meson.build b/meson.build
index 6f7e430f0f..b9c919a55e 100644
--- a/meson.build
+++ b/meson.build
@@ -2804,6 +2804,7 @@ subdir('qom')
subdir('authz')
subdir('crypto')
subdir('ui')
+subdir('hw')
if enable_modules
@@ -2811,6 +2812,18 @@ if enable_modules
modulecommon = declare_dependency(link_whole: libmodulecommon, compile_args: '-DBUILD_DSO')
endif
+qom_ss = qom_ss.apply(config_host, strict: false)
+libqom = static_library('qom', qom_ss.sources() + genh,
+ dependencies: [qom_ss.dependencies()],
+ name_suffix: 'fa')
+qom = declare_dependency(link_whole: libqom)
+
+event_loop_base = files('event-loop-base.c')
+event_loop_base = static_library('event-loop-base', sources: event_loop_base + genh,
+ build_by_default: true)
+event_loop_base = declare_dependency(link_whole: event_loop_base,
+ dependencies: [qom])
+
stub_ss = stub_ss.apply(config_all, strict: false)
util_ss.add_all(trace_ss)
@@ -2897,7 +2910,6 @@ subdir('monitor')
subdir('net')
subdir('replay')
subdir('semihosting')
-subdir('hw')
subdir('tcg')
subdir('fpu')
subdir('accel')
@@ -3022,13 +3034,6 @@ qemu_syms = custom_target('qemu.syms', output: 'qemu.syms',
capture: true,
command: [undefsym, nm, '@INPUT@'])
-qom_ss = qom_ss.apply(config_host, strict: false)
-libqom = static_library('qom', qom_ss.sources() + genh,
- dependencies: [qom_ss.dependencies()],
- name_suffix: 'fa')
-
-qom = declare_dependency(link_whole: libqom)
-
authz_ss = authz_ss.apply(config_host, strict: false)
libauthz = static_library('authz', authz_ss.sources() + genh,
dependencies: [authz_ss.dependencies()],
@@ -3081,7 +3086,7 @@ libblockdev = static_library('blockdev', blockdev_ss.sources() + genh,
build_by_default: false)
blockdev = declare_dependency(link_whole: [libblockdev],
- dependencies: [block])
+ dependencies: [block, event_loop_base])
qmp_ss = qmp_ss.apply(config_host, strict: false)
libqmp = static_library('qmp', qmp_ss.sources() + genh,
diff --git a/qapi/qom.json b/qapi/qom.json
index eeb5395ff3..a2439533c5 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -499,6 +499,20 @@
'*repeat': 'bool',
'*grab-toggle': 'GrabToggleKeys' } }
+##
+# @EventLoopBaseProperties:
+#
+# Common properties for event loops
+#
+# @aio-max-batch: maximum number of requests in a batch for the AIO engine,
+# 0 means that the engine will use its default.
+# (default: 0)
+#
+# Since: 7.1
+##
+{ 'struct': 'EventLoopBaseProperties',
+ 'data': { '*aio-max-batch': 'int' } }
+
##
# @IothreadProperties:
#
@@ -516,17 +530,15 @@
# algorithm detects it is spending too long polling without
# encountering events. 0 selects a default behaviour (default: 0)
#
-# @aio-max-batch: maximum number of requests in a batch for the AIO engine,
-# 0 means that the engine will use its default
-# (default:0, since 6.1)
+# The @aio-max-batch option is available since 6.1.
#
# Since: 2.0
##
{ 'struct': 'IothreadProperties',
+ 'base': 'EventLoopBaseProperties',
'data': { '*poll-max-ns': 'int',
'*poll-grow': 'int',
- '*poll-shrink': 'int',
- '*aio-max-batch': 'int' } }
+ '*poll-shrink': 'int' } }
##
# @MemoryBackendProperties:
--
2.31.1

420
kvm-QIOChannel-Add-flags-on-io_writev-and-introduce-io_f.patch
View File

@ -1,420 +0,0 @@
From cda3fcf14f2883fea633e25256f6c14a71271adf Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:31 -0300
Subject: [PATCH 08/18] QIOChannel: Add flags on io_writev and introduce
io_flush callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [2/11] 06acfb6b0cb2c25733c2eb198011f7623b5a7024 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Add flags to io_writev and introduce io_flush as optional callback to
QIOChannelClass, allowing the implementation of zero copy writes by
subclasses.
How to use them:
- Write data using qio_channel_writev*(...,QIO_CHANNEL_WRITE_FLAG_ZERO_COPY),
- Wait write completion with qio_channel_flush().
Notes:
As some zero copy write implementations work asynchronously, it's
recommended to keep the write buffer untouched until the return of
qio_channel_flush(), to avoid the risk of sending an updated buffer
instead of the buffer state during write.
As io_flush callback is optional, if a subclass does not implement it, then:
- io_flush will return 0 without changing anything.
Also, some functions like qio_channel_writev_full_all() were adapted to
receive a flag parameter. That allows shared code between zero copy and
non-zero copy writev, and also an easier implementation on new flags.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20220513062836.965425-3-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit b88651cb4d4fa416fdbb6afaf5b26ec8c035eaad)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
chardev/char-io.c | 2 +-
hw/remote/mpqemu-link.c | 2 +-
include/io/channel.h | 38 +++++++++++++++++++++-
io/channel-buffer.c | 1 +
io/channel-command.c | 1 +
io/channel-file.c | 1 +
io/channel-socket.c | 2 ++
io/channel-tls.c | 1 +
io/channel-websock.c | 1 +
io/channel.c | 49 +++++++++++++++++++++++------
migration/rdma.c | 1 +
scsi/pr-manager-helper.c | 2 +-
tests/unit/test-io-channel-socket.c | 1 +
13 files changed, 88 insertions(+), 14 deletions(-)
diff --git a/chardev/char-io.c b/chardev/char-io.c
index 8ced184160..4451128cba 100644
--- a/chardev/char-io.c
+++ b/chardev/char-io.c
@@ -122,7 +122,7 @@ int io_channel_send_full(QIOChannel *ioc,
ret = qio_channel_writev_full(
ioc, &iov, 1,
- fds, nfds, NULL);
+ fds, nfds, 0, NULL);
if (ret == QIO_CHANNEL_ERR_BLOCK) {
if (offset) {
return offset;
diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c
index 7e841820e5..e8f556bd27 100644
--- a/hw/remote/mpqemu-link.c
+++ b/hw/remote/mpqemu-link.c
@@ -69,7 +69,7 @@ bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp)
}
if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send),
- fds, nfds, errp)) {
+ fds, nfds, 0, errp)) {
ret = true;
} else {
trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds);
diff --git a/include/io/channel.h b/include/io/channel.h
index 88988979f8..c680ee7480 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -32,12 +32,15 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
#define QIO_CHANNEL_ERR_BLOCK -2
+#define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+
typedef enum QIOChannelFeature QIOChannelFeature;
enum QIOChannelFeature {
QIO_CHANNEL_FEATURE_FD_PASS,
QIO_CHANNEL_FEATURE_SHUTDOWN,
QIO_CHANNEL_FEATURE_LISTEN,
+ QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
};
@@ -104,6 +107,7 @@ struct QIOChannelClass {
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp);
ssize_t (*io_readv)(QIOChannel *ioc,
const struct iovec *iov,
@@ -136,6 +140,8 @@ struct QIOChannelClass {
IOHandler *io_read,
IOHandler *io_write,
void *opaque);
+ int (*io_flush)(QIOChannel *ioc,
+ Error **errp);
};
/* General I/O handling functions */
@@ -228,6 +234,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
* @niov: the length of the @iov array
* @fds: an array of file handles to send
* @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
* @errp: pointer to a NULL-initialized error object
*
* Write data to the IO channel, reading it from the
@@ -260,6 +267,7 @@ ssize_t qio_channel_writev_full(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp);
/**
@@ -837,6 +845,7 @@ int qio_channel_readv_full_all(QIOChannel *ioc,
* @niov: the length of the @iov array
* @fds: an array of file handles to send
* @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
* @errp: pointer to a NULL-initialized error object
*
*
@@ -846,6 +855,14 @@ int qio_channel_readv_full_all(QIOChannel *ioc,
* to be written, yielding from the current coroutine
* if required.
*
+ * If QIO_CHANNEL_WRITE_FLAG_ZERO_COPY is passed in flags,
+ * instead of waiting for all requested data to be written,
+ * this function will wait until it's all queued for writing.
+ * In this case, if the buffer gets changed between queueing and
+ * sending, the updated buffer will be sent. If this is not a
+ * desired behavior, it's suggested to call qio_channel_flush()
+ * before reusing the buffer.
+ *
* Returns: 0 if all bytes were written, or -1 on error
*/
@@ -853,6 +870,25 @@ int qio_channel_writev_full_all(QIOChannel *ioc,
const struct iovec *iov,
size_t niov,
int *fds, size_t nfds,
- Error **errp);
+ int flags, Error **errp);
+
+/**
+ * qio_channel_flush:
+ * @ioc: the channel object
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Will block until every packet queued with
+ * qio_channel_writev_full() + QIO_CHANNEL_WRITE_FLAG_ZERO_COPY
+ * is sent, or return in case of any error.
+ *
+ * If not implemented, acts as a no-op, and returns 0.
+ *
+ * Returns -1 if any error is found,
+ * 1 if every send failed to use zero copy.
+ * 0 otherwise.
+ */
+
+int qio_channel_flush(QIOChannel *ioc,
+ Error **errp);
#endif /* QIO_CHANNEL_H */
diff --git a/io/channel-buffer.c b/io/channel-buffer.c
index baa4e2b089..bf52011be2 100644
--- a/io/channel-buffer.c
+++ b/io/channel-buffer.c
@@ -81,6 +81,7 @@ static ssize_t qio_channel_buffer_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelBuffer *bioc = QIO_CHANNEL_BUFFER(ioc);
diff --git a/io/channel-command.c b/io/channel-command.c
index 338da73ade..54560464ae 100644
--- a/io/channel-command.c
+++ b/io/channel-command.c
@@ -258,6 +258,7 @@ static ssize_t qio_channel_command_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelCommand *cioc = QIO_CHANNEL_COMMAND(ioc);
diff --git a/io/channel-file.c b/io/channel-file.c
index d7cf6d278f..ef6807a6be 100644
--- a/io/channel-file.c
+++ b/io/channel-file.c
@@ -114,6 +114,7 @@ static ssize_t qio_channel_file_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 7a8d9f69c9..a1be2197ca 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -525,6 +525,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -620,6 +621,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 2ae1b92fc0..4ce890a538 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -301,6 +301,7 @@ static ssize_t qio_channel_tls_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelTLS *tioc = QIO_CHANNEL_TLS(ioc);
diff --git a/io/channel-websock.c b/io/channel-websock.c
index 55145a6a8c..9619906ac3 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -1127,6 +1127,7 @@ static ssize_t qio_channel_websock_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);
diff --git a/io/channel.c b/io/channel.c
index e8b019dc36..0640941ac5 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -72,18 +72,32 @@ ssize_t qio_channel_writev_full(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
- if ((fds || nfds) &&
- !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
+ if (fds || nfds) {
+ if (!qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
+ error_setg_errno(errp, EINVAL,
+ "Channel does not support file descriptor passing");
+ return -1;
+ }
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+ error_setg_errno(errp, EINVAL,
+ "Zero Copy does not support file descriptor passing");
+ return -1;
+ }
+ }
+
+ if ((flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) &&
+ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
error_setg_errno(errp, EINVAL,
- "Channel does not support file descriptor passing");
+ "Requested Zero Copy feature is not available");
return -1;
}
- return klass->io_writev(ioc, iov, niov, fds, nfds, errp);
+ return klass->io_writev(ioc, iov, niov, fds, nfds, flags, errp);
}
@@ -217,14 +231,14 @@ int qio_channel_writev_all(QIOChannel *ioc,
size_t niov,
Error **errp)
{
- return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, errp);
+ return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, 0, errp);
}
int qio_channel_writev_full_all(QIOChannel *ioc,
const struct iovec *iov,
size_t niov,
int *fds, size_t nfds,
- Error **errp)
+ int flags, Error **errp)
{
int ret = -1;
struct iovec *local_iov = g_new(struct iovec, niov);
@@ -237,8 +251,10 @@ int qio_channel_writev_full_all(QIOChannel *ioc,
while (nlocal_iov > 0) {
ssize_t len;
- len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds, nfds,
- errp);
+
+ len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds,
+ nfds, flags, errp);
+
if (len == QIO_CHANNEL_ERR_BLOCK) {
if (qemu_in_coroutine()) {
qio_channel_yield(ioc, G_IO_OUT);
@@ -277,7 +293,7 @@ ssize_t qio_channel_writev(QIOChannel *ioc,
size_t niov,
Error **errp)
{
- return qio_channel_writev_full(ioc, iov, niov, NULL, 0, errp);
+ return qio_channel_writev_full(ioc, iov, niov, NULL, 0, 0, errp);
}
@@ -297,7 +313,7 @@ ssize_t qio_channel_write(QIOChannel *ioc,
Error **errp)
{
struct iovec iov = { .iov_base = (char *)buf, .iov_len = buflen };
- return qio_channel_writev_full(ioc, &iov, 1, NULL, 0, errp);
+ return qio_channel_writev_full(ioc, &iov, 1, NULL, 0, 0, errp);
}
@@ -473,6 +489,19 @@ off_t qio_channel_io_seek(QIOChannel *ioc,
return klass->io_seek(ioc, offset, whence, errp);
}
+int qio_channel_flush(QIOChannel *ioc,
+ Error **errp)
+{
+ QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
+
+ if (!klass->io_flush ||
+ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
+ return 0;
+ }
+
+ return klass->io_flush(ioc, errp);
+}
+
static void qio_channel_restart_read(void *opaque)
{
diff --git a/migration/rdma.c b/migration/rdma.c
index ef1e65ec36..672d1958a9 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2840,6 +2840,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
diff --git a/scsi/pr-manager-helper.c b/scsi/pr-manager-helper.c
index 451c7631b7..3be52a98d5 100644
--- a/scsi/pr-manager-helper.c
+++ b/scsi/pr-manager-helper.c
@@ -77,7 +77,7 @@ static int pr_manager_helper_write(PRManagerHelper *pr_mgr,
iov.iov_base = (void *)buf;
iov.iov_len = sz;
n_written = qio_channel_writev_full(QIO_CHANNEL(pr_mgr->ioc), &iov, 1,
- nfds ? &fd : NULL, nfds, errp);
+ nfds ? &fd : NULL, nfds, 0, errp);
if (n_written <= 0) {
assert(n_written != QIO_CHANNEL_ERR_BLOCK);
diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c
index c49eec1f03..6713886d02 100644
--- a/tests/unit/test-io-channel-socket.c
+++ b/tests/unit/test-io-channel-socket.c
@@ -444,6 +444,7 @@ static void test_io_channel_unix_fd_pass(void)
G_N_ELEMENTS(iosend),
fdsend,
G_N_ELEMENTS(fdsend),
+ 0,
&error_abort);
qio_channel_readv_full(dst,
--
2.35.3

56
kvm-QIOChannelSocket-Add-support-for-MSG_ZEROCOPY-IPV6.patch
View File

@ -1,56 +0,0 @@
From cb6dc39a5e5d2d981b4b1e983042b3fbb529d5d1 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Thu, 4 Aug 2022 04:10:43 -0300
Subject: [PATCH 06/11] QIOChannelSocket: Add support for MSG_ZEROCOPY + IPV6
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [6/6] 2eb1aba8ebf267a6f67cfba2e489dc88619c7fd4 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
For using MSG_ZEROCOPY, there are two steps:
1 - io_writev() the packet, which enqueues the packet for sending, and
2 - io_flush(), which gets confirmation that all packets got correctly sent
Currently, if MSG_ZEROCOPY is used to send packets over IPV6, no error will
be reported in (1), but it will fail in the first time (2) happens.
This happens because (2) currently checks for cmsg_level & cmsg_type
associated with IPV4 only, before reporting any error.
Add checks for cmsg_level & cmsg_type associated with IPV6, and thus enable
support for MSG_ZEROCOPY + IPV6
Fixes: 2bc58ffc29 ("QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit 5258a7e2c0677d16e9e1d06845f60171adf0b290)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index eb7baa2184..efd5f60808 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -747,8 +747,8 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
}
cm = CMSG_FIRSTHDR(&msg);
- if (cm->cmsg_level != SOL_IP &&
- cm->cmsg_type != IP_RECVERR) {
+ if (cm->cmsg_level != SOL_IP && cm->cmsg_type != IP_RECVERR &&
+ cm->cmsg_level != SOL_IPV6 && cm->cmsg_type != IPV6_RECVERR) {
error_setg_errno(errp, EPROTOTYPE,
"Wrong cmsg in errqueue");
return -1;
--
2.31.1

65
kvm-QIOChannelSocket-Fix-zero-copy-flush-returning-code-.patch
View File

@ -1,65 +0,0 @@
From 678981c6bb7c964e1591f6f8aba49e9602f64852 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 11 Jul 2022 18:11:11 -0300
Subject: [PATCH 01/11] QIOChannelSocket: Fix zero-copy flush returning code 1
when nothing sent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [1/6] cebc887cb61de1572d8ae3232cde45e80c339404 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
If flush is called when no buffer was sent with MSG_ZEROCOPY, it currently
returns 1. This return code should be used only when Linux fails to use
MSG_ZEROCOPY on a lot of sendmsg().
Fix this by returning early from flush if no sendmsg(...,MSG_ZEROCOPY)
was attempted.
Fixes: 2bc58ffc2926 ("QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Acked-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Message-Id: <20220711211112.18951-2-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 927f93e099c4f9184e60a1bc61624ac2d04d0223)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 8ae8b212cf..eb7baa2184 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -717,12 +717,18 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
struct cmsghdr *cm;
char control[CMSG_SPACE(sizeof(*serr))];
int received;
- int ret = 1;
+ int ret;
+
+ if (sioc->zero_copy_queued == sioc->zero_copy_sent) {
+ return 0;
+ }
msg.msg_control = control;
msg.msg_controllen = sizeof(control);
memset(control, 0, sizeof(control));
+ ret = 1;
+
while (sioc->zero_copy_sent < sioc->zero_copy_queued) {
received = recvmsg(sioc->fd, &msg, MSG_ERRQUEUE);
if (received < 0) {
--
2.31.1

58
kvm-QIOChannelSocket-Fix-zero-copy-send-so-socket-flush-.patch
View File

@ -1,58 +0,0 @@
From e70f01749addd7d0b7aa7fa4fdedb664f98e6b9b Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 20 Jun 2022 02:39:43 -0300
Subject: [PATCH 16/18] QIOChannelSocket: Fix zero-copy send so socket flush
works
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [10/11] a2dfac987e24026b1a78e90b86234ca206b6401f (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Somewhere between v6 and v7 the of the zero-copy-send patchset a crucial
part of the flushing mechanism got missing: incrementing zero_copy_queued.
Without that, the flushing interface becomes a no-op, and there is no
guarantee the buffer is really sent.
This can go as bad as causing a corruption in RAM during migration.
Fixes: 2bc58ffc2926 ("QIOChannelSocket: Implement io_writev zero copy flag & io_flush for CONFIG_LINUX")
Reported-by: 徐闯 <xuchuangxclwt@bytedance.com>
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 4f5a09714c983a3471fd12e3c7f3196e95c650c1)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 7490e5943d..8ae8b212cf 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -612,6 +612,11 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
"Unable to write to socket");
return -1;
}
+
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+ sioc->zero_copy_queued++;
+ }
+
return ret;
}
#else /* WIN32 */
--
2.35.3

249
kvm-QIOChannelSocket-Implement-io_writev-zero-copy-flag-.patch
View File

@ -1,249 +0,0 @@
From 4aeba0365d30dabe2e70dc172683f0878a4a9621 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:32 -0300
Subject: [PATCH 09/18] QIOChannelSocket: Implement io_writev zero copy flag &
io_flush for CONFIG_LINUX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [3/11] 9afeac1f5ac7675624660a0281726c09c8321180 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
For CONFIG_LINUX, implement the new zero copy flag and the optional callback
io_flush on QIOChannelSocket, but enables it only when MSG_ZEROCOPY
feature is available in the host kernel, which is checked on
qio_channel_socket_connect_sync()
qio_channel_socket_flush() was implemented by counting how many times
sendmsg(...,MSG_ZEROCOPY) was successfully called, and then reading the
socket's error queue, in order to find how many of them finished sending.
Flush will loop until those counters are the same, or until some error occurs.
Notes on using writev() with QIO_CHANNEL_WRITE_FLAG_ZERO_COPY:
1: Buffer
- As MSG_ZEROCOPY tells the kernel to use the same user buffer to avoid copying,
some caution is necessary to avoid overwriting any buffer before it's sent.
If something like this happen, a newer version of the buffer may be sent instead.
- If this is a problem, it's recommended to call qio_channel_flush() before freeing
or re-using the buffer.
2: Locked memory
- When using MSG_ZERCOCOPY, the buffer memory will be locked after queued, and
unlocked after it's sent.
- Depending on the size of each buffer, and how often it's sent, it may require
a larger amount of locked memory than usually available to non-root user.
- If the required amount of locked memory is not available, writev_zero_copy
will return an error, which can abort an operation like migration,
- Because of this, when an user code wants to add zero copy as a feature, it
requires a mechanism to disable it, so it can still be accessible to less
privileged users.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20220513062836.965425-4-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 2bc58ffc2926a4efdd03edfb5909861fefc68c3d)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
include/io/channel-socket.h | 2 +
io/channel-socket.c | 116 ++++++++++++++++++++++++++++++++++--
2 files changed, 114 insertions(+), 4 deletions(-)
diff --git a/include/io/channel-socket.h b/include/io/channel-socket.h
index e747e63514..513c428fe4 100644
--- a/include/io/channel-socket.h
+++ b/include/io/channel-socket.h
@@ -47,6 +47,8 @@ struct QIOChannelSocket {
socklen_t localAddrLen;
struct sockaddr_storage remoteAddr;
socklen_t remoteAddrLen;
+ ssize_t zero_copy_queued;
+ ssize_t zero_copy_sent;
};
diff --git a/io/channel-socket.c b/io/channel-socket.c
index a1be2197ca..fbd2214d20 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -26,6 +26,14 @@
#include "io/channel-watch.h"
#include "trace.h"
#include "qapi/clone-visitor.h"
+#ifdef CONFIG_LINUX
+#include <linux/errqueue.h>
+#include <sys/socket.h>
+
+#if (defined(MSG_ZEROCOPY) && defined(SO_ZEROCOPY))
+#define QEMU_MSG_ZEROCOPY
+#endif
+#endif
#define SOCKET_MAX_FDS 16
@@ -55,6 +63,8 @@ qio_channel_socket_new(void)
sioc = QIO_CHANNEL_SOCKET(object_new(TYPE_QIO_CHANNEL_SOCKET));
sioc->fd = -1;
+ sioc->zero_copy_queued = 0;
+ sioc->zero_copy_sent = 0;
ioc = QIO_CHANNEL(sioc);
qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
@@ -154,6 +164,16 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
return -1;
}
+#ifdef QEMU_MSG_ZEROCOPY
+ int ret, v = 1;
+ ret = setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &v, sizeof(v));
+ if (ret == 0) {
+ /* Zero copy available on host */
+ qio_channel_set_feature(QIO_CHANNEL(ioc),
+ QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY);
+ }
+#endif
+
return 0;
}
@@ -534,6 +554,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
char control[CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS)];
size_t fdsize = sizeof(int) * nfds;
struct cmsghdr *cmsg;
+ int sflags = 0;
memset(control, 0, CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS));
@@ -558,15 +579,31 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
memcpy(CMSG_DATA(cmsg), fds, fdsize);
}
+#ifdef QEMU_MSG_ZEROCOPY
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+ sflags = MSG_ZEROCOPY;
+ }
+#endif
+
retry:
- ret = sendmsg(sioc->fd, &msg, 0);
+ ret = sendmsg(sioc->fd, &msg, sflags);
if (ret <= 0) {
- if (errno == EAGAIN) {
+ switch (errno) {
+ case EAGAIN:
return QIO_CHANNEL_ERR_BLOCK;
- }
- if (errno == EINTR) {
+ case EINTR:
goto retry;
+#ifdef QEMU_MSG_ZEROCOPY
+ case ENOBUFS:
+ if (sflags & MSG_ZEROCOPY) {
+ error_setg_errno(errp, errno,
+ "Process can't lock enough memory for using MSG_ZEROCOPY");
+ return -1;
+ }
+ break;
+#endif
}
+
error_setg_errno(errp, errno,
"Unable to write to socket");
return -1;
@@ -660,6 +697,74 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
}
#endif /* WIN32 */
+
+#ifdef QEMU_MSG_ZEROCOPY
+static int qio_channel_socket_flush(QIOChannel *ioc,
+ Error **errp)
+{
+ QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
+ struct msghdr msg = {};
+ struct sock_extended_err *serr;
+ struct cmsghdr *cm;
+ char control[CMSG_SPACE(sizeof(*serr))];
+ int received;
+ int ret = 1;
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+ memset(control, 0, sizeof(control));
+
+ while (sioc->zero_copy_sent < sioc->zero_copy_queued) {
+ received = recvmsg(sioc->fd, &msg, MSG_ERRQUEUE);
+ if (received < 0) {
+ switch (errno) {
+ case EAGAIN:
+ /* Nothing on errqueue, wait until something is available */
+ qio_channel_wait(ioc, G_IO_ERR);
+ continue;
+ case EINTR:
+ continue;
+ default:
+ error_setg_errno(errp, errno,
+ "Unable to read errqueue");
+ return -1;
+ }
+ }
+
+ cm = CMSG_FIRSTHDR(&msg);
+ if (cm->cmsg_level != SOL_IP &&
+ cm->cmsg_type != IP_RECVERR) {
+ error_setg_errno(errp, EPROTOTYPE,
+ "Wrong cmsg in errqueue");
+ return -1;
+ }
+
+ serr = (void *) CMSG_DATA(cm);
+ if (serr->ee_errno != SO_EE_ORIGIN_NONE) {
+ error_setg_errno(errp, serr->ee_errno,
+ "Error on socket");
+ return -1;
+ }
+ if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+ error_setg_errno(errp, serr->ee_origin,
+ "Error not from zero copy");
+ return -1;
+ }
+
+ /* No errors, count successfully finished sendmsg()*/
+ sioc->zero_copy_sent += serr->ee_data - serr->ee_info + 1;
+
+ /* If any sendmsg() succeeded using zero copy, return 0 at the end */
+ if (serr->ee_code != SO_EE_CODE_ZEROCOPY_COPIED) {
+ ret = 0;
+ }
+ }
+
+ return ret;
+}
+
+#endif /* QEMU_MSG_ZEROCOPY */
+
static int
qio_channel_socket_set_blocking(QIOChannel *ioc,
bool enabled,
@@ -790,6 +895,9 @@ static void qio_channel_socket_class_init(ObjectClass *klass,
ioc_klass->io_set_delay = qio_channel_socket_set_delay;
ioc_klass->io_create_watch = qio_channel_socket_create_watch;
ioc_klass->io_set_aio_fd_handler = qio_channel_socket_set_aio_fd_handler;
+#ifdef QEMU_MSG_ZEROCOPY
+ ioc_klass->io_flush = qio_channel_socket_flush;
+#endif
}
static const TypeInfo qio_channel_socket_info = {
--
2.35.3

82
kvm-QIOChannelSocket-Introduce-assert-and-reduce-ifdefs-.patch
View File

@ -1,82 +0,0 @@
From 60bf942a58db12c821f2a6a49e2e0b04b99bec30 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 20 Jun 2022 02:39:42 -0300
Subject: [PATCH 15/18] QIOChannelSocket: Introduce assert and reduce ifdefs to
improve readability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [9/11] eaa02d68301852ccc98bdacc7387d8d03be1cb05 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
During implementation of MSG_ZEROCOPY feature, a lot of #ifdefs were
introduced, particularly at qio_channel_socket_writev().
Rewrite some of those changes so it's easier to read.
Also, introduce an assert to help detect incorrect zero-copy usage is when
it's disabled on build.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
dgilbert: Fixed up thinko'd g_assert_unreachable->g_assert_not_reached
(cherry picked from commit 803ca43e4c7fcf32f9f68c118301ccd0c83ece3f)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
io/channel-socket.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/io/channel-socket.c b/io/channel-socket.c
index fbd2214d20..7490e5943d 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -579,11 +579,17 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
memcpy(CMSG_DATA(cmsg), fds, fdsize);
}
-#ifdef QEMU_MSG_ZEROCOPY
if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
+#ifdef QEMU_MSG_ZEROCOPY
sflags = MSG_ZEROCOPY;
- }
+#else
+ /*
+ * We expect QIOChannel class entry point to have
+ * blocked this code path already
+ */
+ g_assert_not_reached();
#endif
+ }
retry:
ret = sendmsg(sioc->fd, &msg, sflags);
@@ -593,15 +599,13 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
return QIO_CHANNEL_ERR_BLOCK;
case EINTR:
goto retry;
-#ifdef QEMU_MSG_ZEROCOPY
case ENOBUFS:
- if (sflags & MSG_ZEROCOPY) {
+ if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
error_setg_errno(errp, errno,
"Process can't lock enough memory for using MSG_ZEROCOPY");
return -1;
}
break;
-#endif
}
error_setg_errno(errp, errno,
--
2.35.3

237
kvm-RHEL-only-AArch64-Drop-unsupported-CPU-types.patch
View File

@ -1,237 +0,0 @@
From 055edf068196622a3e1868c9e4c991d410272a6d Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 15 Jun 2022 15:28:27 +0200
Subject: [PATCH 03/18] RHEL-only: AArch64: Drop unsupported CPU types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [3/6] 21f54c86dc87e5e75a64459b5a385686bc09640c (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2066824
Upstream Status: RHEL only
We only need to support AArch64 cpu types and we only need three
types:
1) A base type to use with TCG, i.e. a cpu type with only base
features. 'cortex-a57' serves this role and is currently used
by libguestfs.
2) The 'max' type, which is for both KVM and TCG and is good for
tests that just specify 'max' but run under both. 'max' with
TCG also provides the VM with all the CPU features TCG
supports, which is good for VMs that need features not
provided by the basic cortex-a57.
3) The host type which is used with KVM.
Signed-off-by: Andrew Jones <drjones@redhat.com>
---
hw/arm/virt.c | 4 ++++
target/arm/cpu64.c | 6 ++++++
target/arm/cpu_tcg.c | 12 ++----------
tests/qtest/arm-cpu-features.c | 6 ++++++
4 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 95d012d6eb..74119976d3 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -239,12 +239,16 @@ static const int a15irqmap[] = {
};
static const char *valid_cpus[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
ARM_CPU_TYPE_NAME("cortex-a53"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("cortex-a57"),
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a72"),
ARM_CPU_TYPE_NAME("a64fx"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("host"),
ARM_CPU_TYPE_NAME("max"),
};
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index eb44c05822..e80b831073 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -146,6 +146,7 @@ static void aarch64_a57_initfn(Object *obj)
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a53_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -249,6 +250,7 @@ static void aarch64_a72_initfn(Object *obj)
cpu->gic_vprebits = 5;
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
}
+#endif /* disabled for RHEL */
void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
{
@@ -923,6 +925,7 @@ static void aarch64_max_initfn(Object *obj)
qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a64fx_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -969,12 +972,15 @@ static void aarch64_a64fx_initfn(Object *obj)
/* TODO: Add A64FX specific HPC extension registers */
}
+#endif /* disabled for RHEL */
static const ARMCPUInfo aarch64_cpus[] = {
{ .name = "cortex-a57", .initfn = aarch64_a57_initfn },
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a53", .initfn = aarch64_a53_initfn },
{ .name = "cortex-a72", .initfn = aarch64_a72_initfn },
{ .name = "a64fx", .initfn = aarch64_a64fx_initfn },
+#endif /* disabled for RHEL */
{ .name = "max", .initfn = aarch64_max_initfn },
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
{ .name = "host", .initfn = aarch64_host_initfn },
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 3826fa5122..74727fc92c 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -19,10 +19,10 @@
#include "hw/boards.h"
#endif
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/* CPU models. These are not needed for the AArch64 linux-user build. */
#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
-#if 0 /* Disabled for Red Hat Enterprise Linux */
#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG)
static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
{
@@ -376,7 +376,6 @@ static void cortex_a9_initfn(Object *obj)
cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
}
-#endif /* disabled for RHEL */
#ifndef CONFIG_USER_ONLY
static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
@@ -402,7 +401,6 @@ static const ARMCPRegInfo cortexa15_cp_reginfo[] = {
REGINFO_SENTINEL
};
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_a7_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -448,7 +446,6 @@ static void cortex_a7_initfn(Object *obj)
cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
}
-#endif /* disabled for RHEL */
static void cortex_a15_initfn(Object *obj)
{
@@ -492,7 +489,6 @@ static void cortex_a15_initfn(Object *obj)
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
}
-#if 0 /* Disabled for Red Hat Enterprise Linux */
static void cortex_m0_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -933,7 +929,6 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
cc->gdb_core_xml_file = "arm-m-profile.xml";
}
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
/*
@@ -1013,7 +1008,6 @@ static void arm_max_initfn(Object *obj)
#endif /* !TARGET_AARCH64 */
static const ARMCPUInfo arm_tcg_cpus[] = {
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "arm926", .initfn = arm926_initfn },
{ .name = "arm946", .initfn = arm946_initfn },
{ .name = "arm1026", .initfn = arm1026_initfn },
@@ -1029,9 +1023,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "cortex-a7", .initfn = cortex_a7_initfn },
{ .name = "cortex-a8", .initfn = cortex_a8_initfn },
{ .name = "cortex-a9", .initfn = cortex_a9_initfn },
-#endif /* disabled for RHEL */
{ .name = "cortex-a15", .initfn = cortex_a15_initfn },
-#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-m0", .initfn = cortex_m0_initfn,
.class_init = arm_v7m_class_init },
{ .name = "cortex-m3", .initfn = cortex_m3_initfn,
@@ -1062,7 +1054,6 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
-#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
{ .name = "max", .initfn = arm_max_initfn },
#endif
@@ -1090,3 +1081,4 @@ static void arm_tcg_cpu_register_types(void)
type_init(arm_tcg_cpu_register_types)
#endif /* !CONFIG_USER_ONLY || !TARGET_AARCH64 */
+#endif /* disabled for RHEL */
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index f76652143a..fe2a0a070d 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -440,8 +440,10 @@ static void test_query_cpu_model_expansion(const void *data)
assert_error(qts, "host", "The CPU type 'host' requires KVM", NULL);
/* Test expected feature presence/absence for some cpu types */
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "cortex-a15", "pmu");
assert_has_not_feature(qts, "cortex-a15", "aarch64");
+#endif /* disabled for RHEL */
/* Enabling and disabling pmu should always work. */
assert_has_feature_enabled(qts, "max", "pmu");
@@ -458,6 +460,7 @@ static void test_query_cpu_model_expansion(const void *data)
assert_has_feature_enabled(qts, "cortex-a57", "pmu");
assert_has_feature_enabled(qts, "cortex-a57", "aarch64");
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_has_feature_enabled(qts, "a64fx", "pmu");
assert_has_feature_enabled(qts, "a64fx", "aarch64");
/*
@@ -470,6 +473,7 @@ static void test_query_cpu_model_expansion(const void *data)
"{ 'sve384': true }");
assert_error(qts, "a64fx", "cannot enable sve640",
"{ 'sve640': true }");
+#endif /* disabled for RHEL */
sve_tests_default(qts, "max");
pauth_tests_default(qts, "max");
@@ -505,9 +509,11 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
QDict *resp;
char *error;
+#if 0 /* Disabled for Red Hat Enterprise Linux */
assert_error(qts, "cortex-a15",
"We cannot guarantee the CPU type 'cortex-a15' works "
"with KVM on this host", NULL);
+#endif /* disabled for RHEL */
assert_has_feature_enabled(qts, "host", "aarch64");
--
2.35.3

95
kvm-RHEL-only-tests-avocado-Switch-aarch64-tests-from-a5.patch
View File

@ -1,95 +0,0 @@
From d710394f68eb0b6116dd8ac76f619c192e0d5972 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 15 Jun 2022 15:28:27 +0200
Subject: [PATCH 02/18] RHEL-only: tests/avocado: Switch aarch64 tests from a53
to a57
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [2/6] e85ef69b42c411a6997e4da10ba05176368769b3 (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2066824
Upstream Status: RHEL only
We plan to remove the cortex-a53 from the supported cpu types. Switch
all avocado tests that use it to the cortex-a57, which will work the
same and we intend to keep. We don't want to try and upstream this
change since the better upstream change would be to switch from the
a53 to 'max', but the upstream tests also need to use later guest
kernels to use 'max' (see qemu upstream commit 0942820408dc
("hw/arm/virt: Disable LPA2 for -machine virt-6.2")
Signed-off-by: Andrew Jones <drjones@redhat.com>
---
tests/avocado/replay_kernel.py | 2 +-
tests/avocado/reverse_debugging.py | 2 +-
tests/avocado/tcg_plugins.py | 6 +++---
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index 0b2b0dc692..3a7b5f0748 100644
--- a/tests/avocado/replay_kernel.py
+++ b/tests/avocado/replay_kernel.py
@@ -147,7 +147,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/reverse_debugging.py b/tests/avocado/reverse_debugging.py
index d2921e70c3..66d185ed42 100644
--- a/tests/avocado/reverse_debugging.py
+++ b/tests/avocado/reverse_debugging.py
@@ -198,7 +198,7 @@ def test_aarch64_virt(self):
"""
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
'/linux/releases/29/Everything/aarch64/os/images/pxeboot'
diff --git a/tests/avocado/tcg_plugins.py b/tests/avocado/tcg_plugins.py
index 642d2e49e3..93b3afd823 100644
--- a/tests/avocado/tcg_plugins.py
+++ b/tests/avocado/tcg_plugins.py
@@ -68,7 +68,7 @@ def test_aarch64_virt_insn(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -94,7 +94,7 @@ def test_aarch64_virt_insn_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
@@ -120,7 +120,7 @@ def test_aarch64_virt_mem_icount(self):
:avocado: tags=accel:tcg
:avocado: tags=arch:aarch64
:avocado: tags=machine:virt
- :avocado: tags=cpu:cortex-a53
+ :avocado: tags=cpu:cortex-a57
"""
kernel_path = self._grab_aarch64_kernel()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
--
2.35.3

58
kvm-Revert-globally-limit-the-maximum-number-of-CPUs.patch
View File

@ -1,58 +0,0 @@
From 5ab8613582fd56b847fe75750acb5b7255900b35 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Thu, 9 Jun 2022 11:55:15 +0200
Subject: [PATCH 15/16] Revert "globally limit the maximum number of CPUs"
RH-Author: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-MergeRequest: 99: Revert "globally limit the maximum number of CPUs"
RH-Commit: [1/1] 13100d4a2209b2190a3654c1f9cf4ebade1e8d24 (vkuznets/qemu-kvm-c9s)
RH-Bugzilla: 2094270
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2094270
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45871149
Upstream Status: RHEL-only
Tested: with upstream kernel
Downstream QEMU carries a patch that sets the hard limit of possible vCPUs
to the value that the KVM code of the kernel recommends as soft limit.
Upstream KVM code has been changed recently to not use an arbitrary soft
limit anymore, but to cap the value on the amount of available physical
CPUs of the host. This defeats the purpose of the downstream change in
QEMU completely. Drop the downstream-only patch to allow CPU overcommit.
This reverts commit 6669f6fa677d43144f39d6ad59725b7ba622f1c2.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
accel/kvm/kvm-all.c | 12 ------------
1 file changed, 12 deletions(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index fdf0e4d429..5f1377ca04 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2430,18 +2430,6 @@ static int kvm_init(MachineState *ms)
soft_vcpus_limit = kvm_recommended_vcpus(s);
hard_vcpus_limit = kvm_max_vcpus(s);
-#ifdef HOST_PPC64
- /*
- * On POWER, the kernel advertises a soft limit based on the
- * number of CPU threads on the host. We want to allow exceeding
- * this for testing purposes, so we don't want to set hard limit
- * to soft limit as on x86.
- */
-#else
- /* RHEL doesn't support nr_vcpus > soft_vcpus_limit */
- hard_vcpus_limit = soft_vcpus_limit;
-#endif
-
while (nc->name) {
if (nc->num > soft_vcpus_limit) {
warn_report("Number of %s cpus requested (%d) exceeds "
--
2.31.1

134
kvm-Revert-migration-Simplify-unqueue_page.patch
View File

@ -1,134 +0,0 @@
From 5ea59b17866add54e5ae8c76d3cb472c67e1fa91 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Tue, 2 Aug 2022 08:19:49 +0200
Subject: [PATCH 32/32] Revert "migration: Simplify unqueue_page()"
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 112: Fix postcopy migration on s390x
RH-Commit: [2/2] 3913c9ed3f27f4b66245913da29d0c46db0c6567 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2099934
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
This reverts commit cfd66f30fb0f735df06ff4220e5000290a43dad3.
The simplification of unqueue_page() introduced a bug that sometimes
breaks migration on s390x hosts.
The problem is not fully understood yet, but since we are already in
the freeze for QEMU 7.1 and we need something working there, let's
revert this patch for the upcoming release. The optimization can be
redone later again in a proper way if necessary.
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2099934
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20220802061949.331576-1-thuth@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 777f53c75983dd10756f5dbfc8af50fe11da81c1)
Conflicts:
migration/trace-events
(trivial contextual conflict)
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
migration/ram.c | 37 ++++++++++++++++++++++++++-----------
migration/trace-events | 3 ++-
2 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/migration/ram.c b/migration/ram.c
index fb6db54642..ee40e4a718 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1548,7 +1548,6 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
{
struct RAMSrcPageRequest *entry;
RAMBlock *block = NULL;
- size_t page_size;
if (!postcopy_has_request(rs)) {
return NULL;
@@ -1565,13 +1564,10 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
entry = QSIMPLEQ_FIRST(&rs->src_page_requests);
block = entry->rb;
*offset = entry->offset;
- page_size = qemu_ram_pagesize(block);
- /* Each page request should only be multiple page size of the ramblock */
- assert((entry->len % page_size) == 0);
- if (entry->len > page_size) {
- entry->len -= page_size;
- entry->offset += page_size;
+ if (entry->len > TARGET_PAGE_SIZE) {
+ entry->len -= TARGET_PAGE_SIZE;
+ entry->offset += TARGET_PAGE_SIZE;
} else {
memory_region_unref(block->mr);
QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
@@ -1579,9 +1575,6 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
migration_consume_urgent_request();
}
- trace_unqueue_page(block->idstr, *offset,
- test_bit((*offset >> TARGET_PAGE_BITS), block->bmap));
-
return block;
}
@@ -1956,8 +1949,30 @@ static bool get_queued_page(RAMState *rs, PageSearchStatus *pss)
{
RAMBlock *block;
ram_addr_t offset;
+ bool dirty;
+
+ do {
+ block = unqueue_page(rs, &offset);
+ /*
+ * We're sending this page, and since it's postcopy nothing else
+ * will dirty it, and we must make sure it doesn't get sent again
+ * even if this queue request was received after the background
+ * search already sent it.
+ */
+ if (block) {
+ unsigned long page;
+
+ page = offset >> TARGET_PAGE_BITS;
+ dirty = test_bit(page, block->bmap);
+ if (!dirty) {
+ trace_get_queued_page_not_dirty(block->idstr, (uint64_t)offset,
+ page);
+ } else {
+ trace_get_queued_page(block->idstr, (uint64_t)offset, page);
+ }
+ }
- block = unqueue_page(rs, &offset);
+ } while (block && !dirty);
if (!block) {
/*
diff --git a/migration/trace-events b/migration/trace-events
index 1aec580e92..09d61ed1f4 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -85,6 +85,8 @@ put_qlist_end(const char *field_name, const char *vmsd_name) "%s(%s)"
qemu_file_fclose(void) ""
# ram.c
+get_queued_page(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"
+get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"
migration_bitmap_sync_start(void) ""
migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
migration_bitmap_clear_dirty(char *str, uint64_t start, uint64_t size, unsigned long page) "rb %s start 0x%"PRIx64" size 0x%"PRIx64" page 0x%lx"
@@ -110,7 +112,6 @@ ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRI
ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" PRIu64
ram_write_tracking_ramblock_start(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
ram_write_tracking_ramblock_stop(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
-unqueue_page(char *block, uint64_t offset, bool dirty) "ramblock '%s' offset 0x%"PRIx64" dirty %d"
# multifd.c
multifd_new_send_channel_async(uint8_t id) "channel %u"
--
2.31.1

51
kvm-Revert-virtio-scsi-Reject-scsi-cd-if-data-plane-enab.patch
View File

@ -1,51 +0,0 @@
From 733acef2caea0758edd74fb634b095ce09bf5914 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 9 May 2022 03:46:23 -0400
Subject: [PATCH 15/16] Revert "virtio-scsi: Reject scsi-cd if data plane
enabled [RHEL only]"
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 91: Revert "virtio-scsi: Reject scsi-cd if data plane enabled [RHEL only]"
RH-Commit: [1/1] 1af55d792bc9166e5c86272afe8093c76ab41bb4 (eesposit/qemu-kvm)
RH-Bugzilla: 1995710
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
This reverts commit 4e17b1126e.
Over time AioContext usage and coverage has increased, and now block
backend is capable of handling AioContext change upon eject and insert.
Therefore the above downstream-only commit is not necessary anymore,
and can be safely reverted.
X-downstream-only: true
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
hw/scsi/virtio-scsi.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 2450c9438c..db54d104be 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -937,15 +937,6 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
AioContext *old_context;
int ret;
- /* XXX: Remove this check once block backend is capable of handling
- * AioContext change upon eject/insert.
- * s->ctx is NULL if ioeventfd is off, s->ctx is qemu_get_aio_context() if
- * data plane is not used, both cases are safe for scsi-cd. */
- if (s->ctx && s->ctx != qemu_get_aio_context() &&
- object_dynamic_cast(OBJECT(dev), "scsi-cd")) {
- error_setg(errp, "scsi-cd is not supported by data plane");
- return;
- }
if (s->ctx && !s->dataplane_fenced) {
if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
return;
--
2.31.1

41
kvm-configs-devices-aarch64-softmmu-Enable-CONFIG_VIRTIO.patch
View File

@ -1,41 +0,0 @@
From 3a0e9bb88e82cc76ca5efc0595ce94b5dc34749e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Mon, 25 Apr 2022 13:42:46 +0800
Subject: [PATCH 1/2] configs/devices/aarch64-softmmu: Enable CONFIG_VIRTIO_MEM
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 80: Enable virtio-mem for aarch64
RH-Commit: [1/1] 1afbd08da6d7c860da8d617a0a932d3660514878 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2044162
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2044162
This enables virtio-mem device on aarch64 since all needed commits
are ready.
b1b87327a9 hw/arm/virt: Support for virtio-mem-pci
1263615efe virtio-mem: Correct default THP size for ARM64
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
configs/devices/aarch64-softmmu/aarch64-rh-devices.mak | 1 +
1 file changed, 1 insertion(+)
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
index 5f6ee1de5b..187938573f 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -22,6 +22,7 @@ CONFIG_VFIO=y
CONFIG_VFIO_PCI=y
CONFIG_VIRTIO_MMIO=y
CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_MEM=y
CONFIG_XIO3130=y
CONFIG_NVDIMM=y
CONFIG_ACPI_APEI=y
--
2.35.1

101
kvm-coroutine-Rename-qemu_coroutine_inc-dec_pool_size.patch
View File

@ -1,101 +0,0 @@
From e3cb8849862a9f0dd20f2913d540336a037d43c7 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Tue, 10 May 2022 17:10:19 +0200
Subject: [PATCH 07/16] coroutine: Rename qemu_coroutine_inc/dec_pool_size()
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 87: coroutine: Fix crashes due to too large pool batch size
RH-Commit: [1/2] 6389b11f70225f221784c270d9b90c1ea43ca8fb (kmwolf/centos-qemu-kvm)
RH-Bugzilla: 2079938
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
It's true that these functions currently affect the batch size in which
coroutines are reused (i.e. moved from the global release pool to the
allocation pool of a specific thread), but this is a bug and will be
fixed in a separate patch.
In fact, the comment in the header file already just promises that it
influences the pool size, so reflect this in the name of the functions.
As a nice side effect, the shorter function name makes some line
wrapping unnecessary.
Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20220510151020.105528-2-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 98e3ab35054b946f7c2aba5408822532b0920b53)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/block/virtio-blk.c | 6 ++----
include/qemu/coroutine.h | 6 +++---
util/qemu-coroutine.c | 4 ++--
3 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 540c38f829..6a1cc41877 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -1215,8 +1215,7 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
for (i = 0; i < conf->num_queues; i++) {
virtio_add_queue(vdev, conf->queue_size, virtio_blk_handle_output);
}
- qemu_coroutine_increase_pool_batch_size(conf->num_queues * conf->queue_size
- / 2);
+ qemu_coroutine_inc_pool_size(conf->num_queues * conf->queue_size / 2);
virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
if (err != NULL) {
error_propagate(errp, err);
@@ -1253,8 +1252,7 @@ static void virtio_blk_device_unrealize(DeviceState *dev)
for (i = 0; i < conf->num_queues; i++) {
virtio_del_queue(vdev, i);
}
- qemu_coroutine_decrease_pool_batch_size(conf->num_queues * conf->queue_size
- / 2);
+ qemu_coroutine_dec_pool_size(conf->num_queues * conf->queue_size / 2);
qemu_del_vm_change_state_handler(s->change);
blockdev_mark_auto_del(s->blk);
virtio_cleanup(vdev);
diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index c828a95ee0..5b621d1295 100644
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -334,12 +334,12 @@ void coroutine_fn yield_until_fd_readable(int fd);
/**
* Increase coroutine pool size
*/
-void qemu_coroutine_increase_pool_batch_size(unsigned int additional_pool_size);
+void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size);
/**
- * Devcrease coroutine pool size
+ * Decrease coroutine pool size
*/
-void qemu_coroutine_decrease_pool_batch_size(unsigned int additional_pool_size);
+void qemu_coroutine_dec_pool_size(unsigned int additional_pool_size);
#include "qemu/lockable.h"
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index c03b2422ff..faca0ca97c 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -205,12 +205,12 @@ AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co)
return co->ctx;
}
-void qemu_coroutine_increase_pool_batch_size(unsigned int additional_pool_size)
+void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
qatomic_add(&pool_batch_size, additional_pool_size);
}
-void qemu_coroutine_decrease_pool_batch_size(unsigned int removing_pool_size)
+void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
qatomic_sub(&pool_batch_size, removing_pool_size);
}
--
2.31.1

138
kvm-coroutine-Revert-to-constant-batch-size.patch
View File

@ -1,138 +0,0 @@
From 345107bfd5537b51f34aaeb97d6161858bb6feee Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Tue, 10 May 2022 17:10:20 +0200
Subject: [PATCH 08/16] coroutine: Revert to constant batch size
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 87: coroutine: Fix crashes due to too large pool batch size
RH-Commit: [2/2] 8a8a39af873854cdc8333d1a70f3479a97c3ec7a (kmwolf/centos-qemu-kvm)
RH-Bugzilla: 2079938
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Commit 4c41c69e changed the way the coroutine pool is sized because for
virtio-blk devices with a large queue size and heavy I/O, it was just
too small and caused coroutines to be deleted and reallocated soon
afterwards. The change made the size dynamic based on the number of
queues and the queue size of virtio-blk devices.
There are two important numbers here: Slightly simplified, when a
coroutine terminates, it is generally stored in the global release pool
up to a certain pool size, and if the pool is full, it is freed.
Conversely, when allocating a new coroutine, the coroutines in the
release pool are reused if the pool already has reached a certain
minimum size (the batch size), otherwise we allocate new coroutines.
The problem after commit 4c41c69e is that it not only increases the
maximum pool size (which is the intended effect), but also the batch
size for reusing coroutines (which is a bug). It means that in cases
with many devices and/or a large queue size (which defaults to the
number of vcpus for virtio-blk-pci), many thousand coroutines could be
sitting in the release pool without being reused.
This is not only a waste of memory and allocations, but it actually
makes the QEMU process likely to hit the vm.max_map_count limit on Linux
because each coroutine requires two mappings (its stack and the guard
page for the stack), causing it to abort() in qemu_alloc_stack() because
when the limit is hit, mprotect() starts to fail with ENOMEM.
In order to fix the problem, change the batch size back to 64 to avoid
uselessly accumulating coroutines in the release pool, but keep the
dynamic maximum pool size so that coroutines aren't freed too early
in heavy I/O scenarios.
Note that this fix doesn't strictly make it impossible to hit the limit,
but this would only happen if most of the coroutines are actually in use
at the same time, not just sitting in a pool. This is the same behaviour
as we already had before commit 4c41c69e. Fully preventing this would
require allowing qemu_coroutine_create() to return an error, but it
doesn't seem to be a scenario that people hit in practice.
Cc: qemu-stable@nongnu.org
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=2079938
Fixes: 4c41c69e05fe28c0f95f8abd2ebf407e95a4f04b
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20220510151020.105528-3-kwolf@redhat.com>
Tested-by: Hiroki Narukawa <hnarukaw@yahoo-corp.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 9ec7a59b5aad4b736871c378d30f5ef5ec51cb52)
Conflicts:
util/qemu-coroutine.c
Trivial merge conflict because we don't have commit ac387a08 downstream.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
util/qemu-coroutine.c | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index faca0ca97c..804f672e0a 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -20,14 +20,20 @@
#include "qemu/coroutine_int.h"
#include "block/aio.h"
-/** Initial batch size is 64, and is increased on demand */
+/**
+ * The minimal batch size is always 64, coroutines from the release_pool are
+ * reused as soon as there are 64 coroutines in it. The maximum pool size starts
+ * with 64 and is increased on demand so that coroutines are not deleted even if
+ * they are not immediately reused.
+ */
enum {
- POOL_INITIAL_BATCH_SIZE = 64,
+ POOL_MIN_BATCH_SIZE = 64,
+ POOL_INITIAL_MAX_SIZE = 64,
};
/** Free list to speed up creation */
static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_batch_size = POOL_INITIAL_BATCH_SIZE;
+static unsigned int pool_max_size = POOL_INITIAL_MAX_SIZE;
static unsigned int release_pool_size;
static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
static __thread unsigned int alloc_pool_size;
@@ -51,7 +57,7 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
if (CONFIG_COROUTINE_POOL) {
co = QSLIST_FIRST(&alloc_pool);
if (!co) {
- if (release_pool_size > qatomic_read(&pool_batch_size)) {
+ if (release_pool_size > POOL_MIN_BATCH_SIZE) {
/* Slow path; a good place to register the destructor, too. */
if (!coroutine_pool_cleanup_notifier.notify) {
coroutine_pool_cleanup_notifier.notify = coroutine_pool_cleanup;
@@ -88,12 +94,12 @@ static void coroutine_delete(Coroutine *co)
co->caller = NULL;
if (CONFIG_COROUTINE_POOL) {
- if (release_pool_size < qatomic_read(&pool_batch_size) * 2) {
+ if (release_pool_size < qatomic_read(&pool_max_size) * 2) {
QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
qatomic_inc(&release_pool_size);
return;
}
- if (alloc_pool_size < qatomic_read(&pool_batch_size)) {
+ if (alloc_pool_size < qatomic_read(&pool_max_size)) {
QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
alloc_pool_size++;
return;
@@ -207,10 +213,10 @@ AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co)
void qemu_coroutine_inc_pool_size(unsigned int additional_pool_size)
{
- qatomic_add(&pool_batch_size, additional_pool_size);
+ qatomic_add(&pool_max_size, additional_pool_size);
}
void qemu_coroutine_dec_pool_size(unsigned int removing_pool_size)
{
- qatomic_sub(&pool_batch_size, removing_pool_size);
+ qatomic_sub(&pool_max_size, removing_pool_size);
}
--
2.31.1

132
kvm-coroutine-ucontext-use-QEMU_DEFINE_STATIC_CO_TLS.patch
View File

@ -1,132 +0,0 @@
From ffbd90e5f4eba620c7cd631b04f0ed31beb22ffa Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 May 2022 12:07:56 +0100
Subject: [PATCH 1/6] coroutine-ucontext: use QEMU_DEFINE_STATIC_CO_TLS()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 89: coroutine: use coroutine TLS macros to protect thread-local variables
RH-Commit: [1/3] a9782fe8e919c4bd317b7e8744c7ff57d898add3 (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 1952483
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
Thread-Local Storage variables cannot be used directly from coroutine
code because the compiler may optimize TLS variable accesses across
qemu_coroutine_yield() calls. When the coroutine is re-entered from
another thread the TLS variables from the old thread must no longer be
used.
Use QEMU_DEFINE_STATIC_CO_TLS() for the current and leader variables.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20220307153853.602859-2-stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 34145a307d849d0b6734d0222a7aa0bb9eef7407)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/coroutine-ucontext.c | 38 ++++++++++++++++++++++++--------------
1 file changed, 24 insertions(+), 14 deletions(-)
diff --git a/util/coroutine-ucontext.c b/util/coroutine-ucontext.c
index 904b375192..127d5a13c8 100644
--- a/util/coroutine-ucontext.c
+++ b/util/coroutine-ucontext.c
@@ -25,6 +25,7 @@
#include "qemu/osdep.h"
#include <ucontext.h>
#include "qemu/coroutine_int.h"
+#include "qemu/coroutine-tls.h"
#ifdef CONFIG_VALGRIND_H
#include <valgrind/valgrind.h>
@@ -66,8 +67,8 @@ typedef struct {
/**
* Per-thread coroutine bookkeeping
*/
-static __thread CoroutineUContext leader;
-static __thread Coroutine *current;
+QEMU_DEFINE_STATIC_CO_TLS(Coroutine *, current);
+QEMU_DEFINE_STATIC_CO_TLS(CoroutineUContext, leader);
/*
* va_args to makecontext() must be type 'int', so passing
@@ -97,14 +98,15 @@ static inline __attribute__((always_inline))
void finish_switch_fiber(void *fake_stack_save)
{
#ifdef CONFIG_ASAN
+ CoroutineUContext *leaderp = get_ptr_leader();
const void *bottom_old;
size_t size_old;
__sanitizer_finish_switch_fiber(fake_stack_save, &bottom_old, &size_old);
- if (!leader.stack) {
- leader.stack = (void *)bottom_old;
- leader.stack_size = size_old;
+ if (!leaderp->stack) {
+ leaderp->stack = (void *)bottom_old;
+ leaderp->stack_size = size_old;
}
#endif
#ifdef CONFIG_TSAN
@@ -161,8 +163,10 @@ static void coroutine_trampoline(int i0, int i1)
/* Initialize longjmp environment and switch back the caller */
if (!sigsetjmp(self->env, 0)) {
- start_switch_fiber_asan(COROUTINE_YIELD, &fake_stack_save, leader.stack,
- leader.stack_size);
+ CoroutineUContext *leaderp = get_ptr_leader();
+
+ start_switch_fiber_asan(COROUTINE_YIELD, &fake_stack_save,
+ leaderp->stack, leaderp->stack_size);
start_switch_fiber_tsan(&fake_stack_save, self, true); /* true=caller */
siglongjmp(*(sigjmp_buf *)co->entry_arg, 1);
}
@@ -297,7 +301,7 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
int ret;
void *fake_stack_save = NULL;
- current = to_;
+ set_current(to_);
ret = sigsetjmp(from->env, 0);
if (ret == 0) {
@@ -315,18 +319,24 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
Coroutine *qemu_coroutine_self(void)
{
- if (!current) {
- current = &leader.base;
+ Coroutine *self = get_current();
+ CoroutineUContext *leaderp = get_ptr_leader();
+
+ if (!self) {
+ self = &leaderp->base;
+ set_current(self);
}
#ifdef CONFIG_TSAN
- if (!leader.tsan_co_fiber) {
- leader.tsan_co_fiber = __tsan_get_current_fiber();
+ if (!leaderp->tsan_co_fiber) {
+ leaderp->tsan_co_fiber = __tsan_get_current_fiber();
}
#endif
- return current;
+ return self;
}
bool qemu_in_coroutine(void)
{
- return current && current->caller;
+ Coroutine *self = get_current();
+
+ return self && self->caller;
}
--
2.31.1

139
kvm-coroutine-use-QEMU_DEFINE_STATIC_CO_TLS.patch
View File

@ -1,139 +0,0 @@
From 9c2e55d25fec6ffb21e344513b7dbeed7e21f641 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 May 2022 12:08:04 +0100
Subject: [PATCH 2/6] coroutine: use QEMU_DEFINE_STATIC_CO_TLS()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 89: coroutine: use coroutine TLS macros to protect thread-local variables
RH-Commit: [2/3] 68a8847e406e2eace6ddc31b0c5676a60600d606 (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 1952483
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
Thread-Local Storage variables cannot be used directly from coroutine
code because the compiler may optimize TLS variable accesses across
qemu_coroutine_yield() calls. When the coroutine is re-entered from
another thread the TLS variables from the old thread must no longer be
used.
Use QEMU_DEFINE_STATIC_CO_TLS() for the current and leader variables.
The alloc_pool QSLIST needs a typedef so the return value of
get_ptr_alloc_pool() can be stored in a local variable.
One example of why this code is necessary: a coroutine that yields
before calling qemu_coroutine_create() to create another coroutine is
affected by the TLS issue.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20220307153853.602859-3-stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ac387a08a9c9f6b36757da912f0339c25f421f90)
Conflicts:
- Context conflicts due to commit 5411171c3ef4 ("coroutine: Revert to
constant batch size").
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/qemu-coroutine.c | 41 ++++++++++++++++++++++++-----------------
1 file changed, 24 insertions(+), 17 deletions(-)
diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 804f672e0a..4a8bd63ef0 100644
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -18,6 +18,7 @@
#include "qemu/atomic.h"
#include "qemu/coroutine.h"
#include "qemu/coroutine_int.h"
+#include "qemu/coroutine-tls.h"
#include "block/aio.h"
/**
@@ -35,17 +36,20 @@ enum {
static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
static unsigned int pool_max_size = POOL_INITIAL_MAX_SIZE;
static unsigned int release_pool_size;
-static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
-static __thread unsigned int alloc_pool_size;
-static __thread Notifier coroutine_pool_cleanup_notifier;
+
+typedef QSLIST_HEAD(, Coroutine) CoroutineQSList;
+QEMU_DEFINE_STATIC_CO_TLS(CoroutineQSList, alloc_pool);
+QEMU_DEFINE_STATIC_CO_TLS(unsigned int, alloc_pool_size);
+QEMU_DEFINE_STATIC_CO_TLS(Notifier, coroutine_pool_cleanup_notifier);
static void coroutine_pool_cleanup(Notifier *n, void *value)
{
Coroutine *co;
Coroutine *tmp;
+ CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
- QSLIST_FOREACH_SAFE(co, &alloc_pool, pool_next, tmp) {
- QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
+ QSLIST_FOREACH_SAFE(co, alloc_pool, pool_next, tmp) {
+ QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
qemu_coroutine_delete(co);
}
}
@@ -55,27 +59,30 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
Coroutine *co = NULL;
if (CONFIG_COROUTINE_POOL) {
- co = QSLIST_FIRST(&alloc_pool);
+ CoroutineQSList *alloc_pool = get_ptr_alloc_pool();
+
+ co = QSLIST_FIRST(alloc_pool);
if (!co) {
if (release_pool_size > POOL_MIN_BATCH_SIZE) {
/* Slow path; a good place to register the destructor, too. */
- if (!coroutine_pool_cleanup_notifier.notify) {
- coroutine_pool_cleanup_notifier.notify = coroutine_pool_cleanup;
- qemu_thread_atexit_add(&coroutine_pool_cleanup_notifier);
+ Notifier *notifier = get_ptr_coroutine_pool_cleanup_notifier();
+ if (!notifier->notify) {
+ notifier->notify = coroutine_pool_cleanup;
+ qemu_thread_atexit_add(notifier);
}
/* This is not exact; there could be a little skew between
* release_pool_size and the actual size of release_pool. But
* it is just a heuristic, it does not need to be perfect.
*/
- alloc_pool_size = qatomic_xchg(&release_pool_size, 0);
- QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
- co = QSLIST_FIRST(&alloc_pool);
+ set_alloc_pool_size(qatomic_xchg(&release_pool_size, 0));
+ QSLIST_MOVE_ATOMIC(alloc_pool, &release_pool);
+ co = QSLIST_FIRST(alloc_pool);
}
}
if (co) {
- QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
- alloc_pool_size--;
+ QSLIST_REMOVE_HEAD(alloc_pool, pool_next);
+ set_alloc_pool_size(get_alloc_pool_size() - 1);
}
}
@@ -99,9 +106,9 @@ static void coroutine_delete(Coroutine *co)
qatomic_inc(&release_pool_size);
return;
}
- if (alloc_pool_size < qatomic_read(&pool_max_size)) {
- QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
- alloc_pool_size++;
+ if (get_alloc_pool_size() < qatomic_read(&pool_max_size)) {
+ QSLIST_INSERT_HEAD(get_ptr_alloc_pool(), co, pool_next);
+ set_alloc_pool_size(get_alloc_pool_size() + 1);
return;
}
}
--
2.31.1

99
kvm-coroutine-win32-use-QEMU_DEFINE_STATIC_CO_TLS.patch
View File

@ -1,99 +0,0 @@
From 336581e6e9ace3f1ddd24ad0a258db9785f9b0ed Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 May 2022 12:08:12 +0100
Subject: [PATCH 3/6] coroutine-win32: use QEMU_DEFINE_STATIC_CO_TLS()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 89: coroutine: use coroutine TLS macros to protect thread-local variables
RH-Commit: [3/3] 55b35dfdae1bc7d6f614ac9f81a92f5c6431f713 (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 1952483
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
Thread-Local Storage variables cannot be used directly from coroutine
code because the compiler may optimize TLS variable accesses across
qemu_coroutine_yield() calls. When the coroutine is re-entered from
another thread the TLS variables from the old thread must no longer be
used.
Use QEMU_DEFINE_STATIC_CO_TLS() for the current and leader variables.
I think coroutine-win32.c could get away with __thread because the
variables are only used in situations where either the stale value is
correct (current) or outside coroutine context (loading leader when
current is NULL). Due to the difficulty of being sure that this is
really safe in all scenarios it seems worth converting it anyway.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20220307153853.602859-4-stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c1fe694357a328c807ae3cc6961c19e923448fcc)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
util/coroutine-win32.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/util/coroutine-win32.c b/util/coroutine-win32.c
index de6bd4fd3e..c02a62c896 100644
--- a/util/coroutine-win32.c
+++ b/util/coroutine-win32.c
@@ -25,6 +25,7 @@
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/coroutine_int.h"
+#include "qemu/coroutine-tls.h"
typedef struct
{
@@ -34,8 +35,8 @@ typedef struct
CoroutineAction action;
} CoroutineWin32;
-static __thread CoroutineWin32 leader;
-static __thread Coroutine *current;
+QEMU_DEFINE_STATIC_CO_TLS(CoroutineWin32, leader);
+QEMU_DEFINE_STATIC_CO_TLS(Coroutine *, current);
/* This function is marked noinline to prevent GCC from inlining it
* into coroutine_trampoline(). If we allow it to do that then it
@@ -52,7 +53,7 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
CoroutineWin32 *from = DO_UPCAST(CoroutineWin32, base, from_);
CoroutineWin32 *to = DO_UPCAST(CoroutineWin32, base, to_);
- current = to_;
+ set_current(to_);
to->action = action;
SwitchToFiber(to->fiber);
@@ -89,14 +90,21 @@ void qemu_coroutine_delete(Coroutine *co_)
Coroutine *qemu_coroutine_self(void)
{
+ Coroutine *current = get_current();
+
if (!current) {
- current = &leader.base;
- leader.fiber = ConvertThreadToFiber(NULL);
+ CoroutineWin32 *leader = get_ptr_leader();
+
+ current = &leader->base;
+ set_current(current);
+ leader->fiber = ConvertThreadToFiber(NULL);
}
return current;
}
bool qemu_in_coroutine(void)
{
+ Coroutine *current = get_current();
+
return current && current->caller;
}
--
2.31.1

179
kvm-hw-acpi-aml-build-Use-existing-CPU-topology-to-build.patch
View File

@ -1,179 +0,0 @@
From 8a12049e97149056f61f7748d9869606d282d16e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 06/16] hw/acpi/aml-build: Use existing CPU topology to build
PPTT table
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [6/6] 53fa376531c204cf706cc1a7a0499019756106cb (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
When the PPTT table is built, the CPU topology is re-calculated, but
it's unecessary because the CPU topology has been populated in
virt_possible_cpu_arch_ids() on arm/virt machine.
This reworks build_pptt() to avoid by reusing the existing IDs in
ms->possible_cpus. Currently, the only user of build_pptt() is
arm/virt machine.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Tested-by: Yanan Wang <wangyanan55@huawei.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Acked-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-id: 20220503140304.855514-7-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit ae9141d4a3265553503bf07d3574b40f84615a34)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/acpi/aml-build.c | 111 +++++++++++++++++++-------------------------
1 file changed, 48 insertions(+), 63 deletions(-)
diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c
index 4086879ebf..e6bfac95c7 100644
--- a/hw/acpi/aml-build.c
+++ b/hw/acpi/aml-build.c
@@ -2002,86 +2002,71 @@ void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms,
const char *oem_id, const char *oem_table_id)
{
MachineClass *mc = MACHINE_GET_CLASS(ms);
- GQueue *list = g_queue_new();
- guint pptt_start = table_data->len;
- guint parent_offset;
- guint length, i;
- int uid = 0;
- int socket;
+ CPUArchIdList *cpus = ms->possible_cpus;
+ int64_t socket_id = -1, cluster_id = -1, core_id = -1;
+ uint32_t socket_offset = 0, cluster_offset = 0, core_offset = 0;
+ uint32_t pptt_start = table_data->len;
+ int n;
AcpiTable table = { .sig = "PPTT", .rev = 2,
.oem_id = oem_id, .oem_table_id = oem_table_id };
acpi_table_begin(&table, table_data);
- for (socket = 0; socket < ms->smp.sockets; socket++) {
- g_queue_push_tail(list,
- GUINT_TO_POINTER(table_data->len - pptt_start));
- build_processor_hierarchy_node(
- table_data,
- /*
- * Physical package - represents the boundary
- * of a physical package
- */
- (1 << 0),
- 0, socket, NULL, 0);
- }
-
- if (mc->smp_props.clusters_supported) {
- length = g_queue_get_length(list);
- for (i = 0; i < length; i++) {
- int cluster;
-
- parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
- for (cluster = 0; cluster < ms->smp.clusters; cluster++) {
- g_queue_push_tail(list,
- GUINT_TO_POINTER(table_data->len - pptt_start));
- build_processor_hierarchy_node(
- table_data,
- (0 << 0), /* not a physical package */
- parent_offset, cluster, NULL, 0);
- }
+ /*
+ * This works with the assumption that cpus[n].props.*_id has been
+ * sorted from top to down levels in mc->possible_cpu_arch_ids().
+ * Otherwise, the unexpected and duplicated containers will be
+ * created.
+ */
+ for (n = 0; n < cpus->len; n++) {
+ if (cpus->cpus[n].props.socket_id != socket_id) {
+ assert(cpus->cpus[n].props.socket_id > socket_id);
+ socket_id = cpus->cpus[n].props.socket_id;
+ cluster_id = -1;
+ core_id = -1;
+ socket_offset = table_data->len - pptt_start;
+ build_processor_hierarchy_node(table_data,
+ (1 << 0), /* Physical package */
+ 0, socket_id, NULL, 0);
}
- }
- length = g_queue_get_length(list);
- for (i = 0; i < length; i++) {
- int core;
-
- parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
- for (core = 0; core < ms->smp.cores; core++) {
- if (ms->smp.threads > 1) {
- g_queue_push_tail(list,
- GUINT_TO_POINTER(table_data->len - pptt_start));
- build_processor_hierarchy_node(
- table_data,
- (0 << 0), /* not a physical package */
- parent_offset, core, NULL, 0);
- } else {
- build_processor_hierarchy_node(
- table_data,
- (1 << 1) | /* ACPI Processor ID valid */
- (1 << 3), /* Node is a Leaf */
- parent_offset, uid++, NULL, 0);
+ if (mc->smp_props.clusters_supported) {
+ if (cpus->cpus[n].props.cluster_id != cluster_id) {
+ assert(cpus->cpus[n].props.cluster_id > cluster_id);
+ cluster_id = cpus->cpus[n].props.cluster_id;
+ core_id = -1;
+ cluster_offset = table_data->len - pptt_start;
+ build_processor_hierarchy_node(table_data,
+ (0 << 0), /* Not a physical package */
+ socket_offset, cluster_id, NULL, 0);
}
+ } else {
+ cluster_offset = socket_offset;
}
- }
- length = g_queue_get_length(list);
- for (i = 0; i < length; i++) {
- int thread;
+ if (ms->smp.threads == 1) {
+ build_processor_hierarchy_node(table_data,
+ (1 << 1) | /* ACPI Processor ID valid */
+ (1 << 3), /* Node is a Leaf */
+ cluster_offset, n, NULL, 0);
+ } else {
+ if (cpus->cpus[n].props.core_id != core_id) {
+ assert(cpus->cpus[n].props.core_id > core_id);
+ core_id = cpus->cpus[n].props.core_id;
+ core_offset = table_data->len - pptt_start;
+ build_processor_hierarchy_node(table_data,
+ (0 << 0), /* Not a physical package */
+ cluster_offset, core_id, NULL, 0);
+ }
- parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list));
- for (thread = 0; thread < ms->smp.threads; thread++) {
- build_processor_hierarchy_node(
- table_data,
+ build_processor_hierarchy_node(table_data,
(1 << 1) | /* ACPI Processor ID valid */
(1 << 2) | /* Processor is a Thread */
(1 << 3), /* Node is a Leaf */
- parent_offset, uid++, NULL, 0);
+ core_offset, n, NULL, 0);
}
}
- g_queue_free(list);
acpi_table_end(linker, &table);
}
--
2.31.1

74
kvm-hw-arm-virt-Consider-SMP-configuration-in-CPU-topolo.patch
View File

@ -1,74 +0,0 @@
From 3b05d3464945295112b5d02d142422f524a52054 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 03/16] hw/arm/virt: Consider SMP configuration in CPU topology
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [3/6] 7125b41f038c2b1cb33377d0ef1222f1ea42b648 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
Currently, the SMP configuration isn't considered when the CPU
topology is populated. In this case, it's impossible to provide
the default CPU-to-NUMA mapping or association based on the socket
ID of the given CPU.
This takes account of SMP configuration when the CPU topology
is populated. The die ID for the given CPU isn't assigned since
it's not supported on arm/virt machine. Besides, the used SMP
configuration in qtest/numa-test/aarch64_numa_cpu() is corrcted
to avoid testing failure
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Acked-by: Igor Mammedov <imammedo@redhat.com>
Message-id: 20220503140304.855514-4-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit c9ec4cb5e4936f980889e717524e73896b0200ed)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 8be12e121d..a87c8d396a 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2553,6 +2553,7 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
int n;
unsigned int max_cpus = ms->smp.max_cpus;
VirtMachineState *vms = VIRT_MACHINE(ms);
+ MachineClass *mc = MACHINE_GET_CLASS(vms);
if (ms->possible_cpus) {
assert(ms->possible_cpus->len == max_cpus);
@@ -2566,8 +2567,20 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
ms->possible_cpus->cpus[n].type = ms->cpu_type;
ms->possible_cpus->cpus[n].arch_id =
virt_cpu_mp_affinity(vms, n);
+
+ assert(!mc->smp_props.dies_supported);
+ ms->possible_cpus->cpus[n].props.has_socket_id = true;
+ ms->possible_cpus->cpus[n].props.socket_id =
+ n / (ms->smp.clusters * ms->smp.cores * ms->smp.threads);
+ ms->possible_cpus->cpus[n].props.has_cluster_id = true;
+ ms->possible_cpus->cpus[n].props.cluster_id =
+ (n / (ms->smp.cores * ms->smp.threads)) % ms->smp.clusters;
+ ms->possible_cpus->cpus[n].props.has_core_id = true;
+ ms->possible_cpus->cpus[n].props.core_id =
+ (n / ms->smp.threads) % ms->smp.cores;
ms->possible_cpus->cpus[n].props.has_thread_id = true;
- ms->possible_cpus->cpus[n].props.thread_id = n;
+ ms->possible_cpus->cpus[n].props.thread_id =
+ n % ms->smp.threads;
}
return ms->possible_cpus;
}
--
2.31.1

88
kvm-hw-arm-virt-Fix-CPU-s-default-NUMA-node-ID.patch
View File

@ -1,88 +0,0 @@
From 14e49ad3b98f01c1ad6fe456469d40a96a43dc3c Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 05/16] hw/arm/virt: Fix CPU's default NUMA node ID
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [5/6] 5336f62bc0c53c0417db1d71ef89544907bc28c0 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
When CPU-to-NUMA association isn't explicitly provided by users,
the default one is given by mc->get_default_cpu_node_id(). However,
the CPU topology isn't fully considered in the default association
and this causes CPU topology broken warnings on booting Linux guest.
For example, the following warning messages are observed when the
Linux guest is booted with the following command lines.
/home/gavin/sandbox/qemu.main/build/qemu-system-aarch64 \
-accel kvm -machine virt,gic-version=host \
-cpu host \
-smp 6,sockets=2,cores=3,threads=1 \
-m 1024M,slots=16,maxmem=64G \
-object memory-backend-ram,id=mem0,size=128M \
-object memory-backend-ram,id=mem1,size=128M \
-object memory-backend-ram,id=mem2,size=128M \
-object memory-backend-ram,id=mem3,size=128M \
-object memory-backend-ram,id=mem4,size=128M \
-object memory-backend-ram,id=mem4,size=384M \
-numa node,nodeid=0,memdev=mem0 \
-numa node,nodeid=1,memdev=mem1 \
-numa node,nodeid=2,memdev=mem2 \
-numa node,nodeid=3,memdev=mem3 \
-numa node,nodeid=4,memdev=mem4 \
-numa node,nodeid=5,memdev=mem5
:
alternatives: patching kernel code
BUG: arch topology borken
the CLS domain not a subset of the MC domain
<the above error log repeats>
BUG: arch topology borken
the DIE domain not a subset of the NODE domain
With current implementation of mc->get_default_cpu_node_id(),
CPU#0 to CPU#5 are associated with NODE#0 to NODE#5 separately.
That's incorrect because CPU#0/1/2 should be associated with same
NUMA node because they're seated in same socket.
This fixes the issue by considering the socket ID when the default
CPU-to-NUMA association is provided in virt_possible_cpu_arch_ids().
With this applied, no more CPU topology broken warnings are seen
from the Linux guest. The 6 CPUs are associated with NODE#0/1, but
there are no CPUs associated with NODE#2/3/4/5.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Message-id: 20220503140304.855514-6-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 4c18bc192386dfbca530e7f550e0992df657818a)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index a87c8d396a..95d012d6eb 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2545,7 +2545,9 @@ virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
static int64_t virt_get_default_cpu_node_id(const MachineState *ms, int idx)
{
- return idx % ms->numa_state->num_nodes;
+ int64_t socket_id = ms->possible_cpus->cpus[idx].props.socket_id;
+
+ return socket_id % ms->numa_state->num_nodes;
}
static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
--
2.31.1

56
kvm-hw-arm-virt-Fix-missing-initialization-in-instance-c.patch
View File

@ -1,56 +0,0 @@
From e25c40735d2f022c07481b548d20476222006657 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 4 May 2022 11:11:54 +0200
Subject: [PATCH 2/5] hw/arm/virt: Fix missing initialization in
instance/class_init()
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 82: hw/arm/virt: Remove the dtb-kaslr-seed machine option
RH-Commit: [2/2] 22cbbfc30cf57a09b8acfb25d8a4dff2754c630c (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2046029
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2046029
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45133161
Upstream Status: RHEL-only
Tested: Boot RHEL guest and check migration from 8.6 to 9.1
(with custom additions)
During the 7.0 rebase, the initialization of highmem_mmio and
highmem_redists was forgotten in rhel_virt_instance_init().
Fix it to match virt_instance_init() code.
Also mc->smp_props.clusters_supported was missing in
rhel_machine_class_init().
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index bde4f77994..8be12e121d 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3286,6 +3286,7 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data)
hc->unplug_request = virt_machine_device_unplug_request_cb;
hc->unplug = virt_machine_device_unplug_cb;
mc->nvdimm_supported = true;
+ mc->smp_props.clusters_supported = true;
mc->auto_enable_numa_with_memhp = true;
mc->auto_enable_numa_with_memdev = true;
mc->default_ram_id = "mach-virt.ram";
@@ -3366,6 +3367,8 @@ static void rhel_virt_instance_init(Object *obj)
vms->gic_version = VIRT_GIC_VERSION_NOSEL;
vms->highmem_ecam = !vmc->no_highmem_ecam;
+ vms->highmem_mmio = true;
+ vms->highmem_redists = true;
if (vmc->no_its) {
vms->its = false;
--
2.31.1

76
kvm-hw-arm-virt-Remove-the-dtb-kaslr-seed-machine-option.patch
View File

@ -1,76 +0,0 @@
From 69f771c3dc641431f3e98497cbd3832edb69284f Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Tue, 3 May 2022 08:56:52 +0200
Subject: [PATCH 1/5] hw/arm/virt: Remove the dtb-kaslr-seed machine option
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 82: hw/arm/virt: Remove the dtb-kaslr-seed machine option
RH-Commit: [1/2] a89dcd7f22e04ae39de99795d3f34cdd0b831bc0 (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2046029
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2046029
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45133161
Upstream Status: RHEL-only
Tested: Boot RHEL guest and check the option is not available
In RHEL we do not want to expose the dtb-kaslr-seed virt machine
option. Indeed the default 'on' value matches our need as
random data in the DTB does not cause any boot failure and we
want to support KASLR for the guest.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
---
hw/arm/virt.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e06862d22a..bde4f77994 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2350,6 +2350,7 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
vms->its = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static bool virt_get_dtb_kaslr_seed(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2363,6 +2364,7 @@ static void virt_set_dtb_kaslr_seed(Object *obj, bool value, Error **errp)
vms->dtb_kaslr_seed = value;
}
+#endif /* disabled for RHEL */
static char *virt_get_oem_id(Object *obj, Error **errp)
{
@@ -3346,13 +3348,6 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data)
"Override the default value of field OEM Table ID "
"in ACPI table header."
"The string may be up to 8 bytes in size");
-
- object_class_property_add_bool(oc, "dtb-kaslr-seed",
- virt_get_dtb_kaslr_seed,
- virt_set_dtb_kaslr_seed);
- object_class_property_set_description(oc, "dtb-kaslr-seed",
- "Set off to disable passing of kaslr-seed "
- "dtb node to guest");
}
static void rhel_virt_instance_init(Object *obj)
@@ -3397,7 +3392,7 @@ static void rhel_virt_instance_init(Object *obj)
/* MTE is disabled by default and non-configurable for RHEL */
vms->mte = false;
- /* Supply a kaslr-seed by default */
+ /* Supply a kaslr-seed by default and non-configurable for RHEL */
vms->dtb_kaslr_seed = true;
vms->irqmap = a15irqmap;
--
2.31.1

96
kvm-hw-block-fdc-Prevent-end-of-track-overrun-CVE-2021-3.patch
View File

@ -1,96 +0,0 @@
From 6ee4a8718dcce2d6da43ee200534b75baf1d7bbe Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= <philmd@redhat.com>
Date: Thu, 18 Nov 2021 12:57:32 +0100
Subject: [PATCH 16/17] hw/block/fdc: Prevent end-of-track overrun
(CVE-2021-3507)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 107: hw/block/fdc: Prevent end-of-track overrun (CVE-2021-3507)
RH-Commit: [1/2] 9ffc5290348884d20b894fa79f4d0c8089247f8b (mrezanin/centos-src-qemu-kvm)
RH-Bugzilla: 1951522
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
Per the 82078 datasheet, if the end-of-track (EOT byte in
the FIFO) is more than the number of sectors per side, the
command is terminated unsuccessfully:
* 5.2.5 DATA TRANSFER TERMINATION
The 82078 supports terminal count explicitly through
the TC pin and implicitly through the underrun/over-
run and end-of-track (EOT) functions. For full sector
transfers, the EOT parameter can define the last
sector to be transferred in a single or multisector
transfer. If the last sector to be transferred is a par-
tial sector, the host can stop transferring the data in
mid-sector, and the 82078 will continue to complete
the sector as if a hardware TC was received. The
only difference between these implicit functions and
TC is that they return "abnormal termination" result
status. Such status indications can be ignored if they
were expected.
* 6.1.3 READ TRACK
This command terminates when the EOT specified
number of sectors have been read. If the 82078
does not find an I D Address Mark on the diskette
after the second· occurrence of a pulse on the
INDX# pin, then it sets the IC code in Status Regis-
ter 0 to "01" (Abnormal termination), sets the MA bit
in Status Register 1 to "1", and terminates the com-
mand.
* 6.1.6 VERIFY
Refer to Table 6-6 and Table 6-7 for information
concerning the values of MT and EC versus SC and
EOT value.
* Table 6·6. Result Phase Table
* Table 6-7. Verify Command Result Phase Table
Fix by aborting the transfer when EOT > # Sectors Per Side.
Cc: qemu-stable@nongnu.org
Cc: Hervé Poussineau <hpoussin@reactos.org>
Fixes: baca51faff0 ("floppy driver: disk geometry auto detect")
Reported-by: Alexander Bulekov <alxndr@bu.edu>
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/339
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20211118115733.4038610-2-philmd@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit defac5e2fbddf8423a354ff0454283a2115e1367)
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
hw/block/fdc.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index ca1776121f..6481ec0cfb 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -1532,6 +1532,14 @@ static void fdctrl_start_transfer(FDCtrl *fdctrl, int direction)
int tmp;
fdctrl->data_len = 128 << (fdctrl->fifo[5] > 7 ? 7 : fdctrl->fifo[5]);
tmp = (fdctrl->fifo[6] - ks + 1);
+ if (tmp < 0) {
+ FLOPPY_DPRINTF("invalid EOT: %d\n", tmp);
+ fdctrl_stop_transfer(fdctrl, FD_SR0_ABNTERM, FD_SR1_MA, 0x00);
+ fdctrl->fifo[3] = kt;
+ fdctrl->fifo[4] = kh;
+ fdctrl->fifo[5] = ks;
+ return;
+ }
if (fdctrl->fifo[0] & 0x80)
tmp += fdctrl->fifo[6];
fdctrl->data_len *= tmp;
--
2.31.1

95
kvm-hw-virtio-Replace-g_memdup-by-g_memdup2.patch
View File

@ -1,95 +0,0 @@
From 4dad0e9abbc843fba4e5fee6e7aa1b0db13f5898 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 21 Jul 2022 15:27:35 +0200
Subject: [PATCH 03/32] hw/virtio: Replace g_memdup() by g_memdup2()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 108: Net Control Virtqueue shadow Support
RH-Commit: [3/27] ae196903eb1a7aebbf999100e997cf82e5024cb6 (eperezmartin/qemu-kvm)
RH-Bugzilla: 1939363
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
Bugzilla: https://bugzilla.redhat.com/1939363
Upstream Status: git://git.qemu.org/qemu.git
commit d792199de55ca5cb5334016884039c740290b5c7
Author: Philippe Mathieu-Daudé <f4bug@amsat.org>
Date: Thu May 12 19:57:46 2022 +0200
hw/virtio: Replace g_memdup() by g_memdup2()
Per https://discourse.gnome.org/t/port-your-module-from-g-memdup-to-g-memdup2-now/5538
The old API took the size of the memory to duplicate as a guint,
whereas most memory functions take memory sizes as a gsize. This
made it easy to accidentally pass a gsize to g_memdup(). For large
values, that would lead to a silent truncation of the size from 64
to 32 bits, and result in a heap area being returned which is
significantly smaller than what the caller expects. This can likely
be exploited in various modules to cause a heap buffer overflow.
Replace g_memdup() by the safer g_memdup2() wrapper.
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20220512175747.142058-6-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
hw/net/virtio-net.c | 3 ++-
hw/virtio/virtio-crypto.c | 6 +++---
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 099e65036d..633de61513 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -1458,7 +1458,8 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
}
iov_cnt = elem->out_num;
- iov2 = iov = g_memdup(elem->out_sg, sizeof(struct iovec) * elem->out_num);
+ iov2 = iov = g_memdup2(elem->out_sg,
+ sizeof(struct iovec) * elem->out_num);
s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));
iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));
if (s != sizeof(ctrl)) {
diff --git a/hw/virtio/virtio-crypto.c b/hw/virtio/virtio-crypto.c
index dcd80b904d..0e31e3cc04 100644
--- a/hw/virtio/virtio-crypto.c
+++ b/hw/virtio/virtio-crypto.c
@@ -242,7 +242,7 @@ static void virtio_crypto_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
}
out_num = elem->out_num;
- out_iov_copy = g_memdup(elem->out_sg, sizeof(out_iov[0]) * out_num);
+ out_iov_copy = g_memdup2(elem->out_sg, sizeof(out_iov[0]) * out_num);
out_iov = out_iov_copy;
in_num = elem->in_num;
@@ -605,11 +605,11 @@ virtio_crypto_handle_request(VirtIOCryptoReq *request)
}
out_num = elem->out_num;
- out_iov_copy = g_memdup(elem->out_sg, sizeof(out_iov[0]) * out_num);
+ out_iov_copy = g_memdup2(elem->out_sg, sizeof(out_iov[0]) * out_num);
out_iov = out_iov_copy;
in_num = elem->in_num;
- in_iov_copy = g_memdup(elem->in_sg, sizeof(in_iov[0]) * in_num);
+ in_iov_copy = g_memdup2(elem->in_sg, sizeof(in_iov[0]) * in_num);
in_iov = in_iov_copy;
if (unlikely(iov_to_buf(out_iov, out_num, 0, &req, sizeof(req))
--
2.31.1

52
kvm-iotests-108-Fix-when-missing-user_allow_other.patch
View File

@ -1,52 +0,0 @@
From 447bca651c9156d7aba6b7495c75f19b5e4ed53f Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Thu, 21 Apr 2022 16:24:35 +0200
Subject: [PATCH 07/16] iotests/108: Fix when missing user_allow_other
RH-Author: Hanna Reitz <hreitz@redhat.com>
RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding
RH-Commit: [4/4] a51ab8606fc9d8dea2b6539f4e795d5813892a5c (hreitz/qemu-kvm-c-9-s)
RH-Bugzilla: 2072379
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
FUSE exports' allow-other option defaults to "auto", which means that it
will try passing allow_other as a mount option, and fall back to not
using it when an error occurs. We make no effort to hide fusermount's
error message (because it would be difficult, and because users might
want to know about the fallback occurring), and so when allow_other does
not work (primarily when /etc/fuse.conf does not contain
user_allow_other), this error message will appear and break the
reference output.
We do not need allow_other here, though, so we can just pass
allow-other=off to fix that.
Reported-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220421142435.569600-1-hreitz@redhat.com>
Tested-by: Markus Armbruster <armbru@redhat.com>
Tested-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 348a0740afc5b313599533eb69bbb2b95d2f1bba)
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
---
tests/qemu-iotests/108 | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index a3090e2875..4681c7c769 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -326,7 +326,7 @@ else
$QSD \
--blockdev file,node-name=export-node,filename="$TEST_IMG" \
- --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off \
+ --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off,allow-other=off \
--pidfile "$TEST_DIR/qsd.pid" \
&
--
2.31.1

445
kvm-iotests-108-Test-new-refcount-rebuild-algorithm.patch
View File

@ -1,445 +0,0 @@
From ed69e01352b5e9a06173daab53bfa373c8535732 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Tue, 5 Apr 2022 15:46:51 +0200
Subject: [PATCH 05/16] iotests/108: Test new refcount rebuild algorithm
RH-Author: Hanna Reitz <hreitz@redhat.com>
RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding
RH-Commit: [2/4] b68310a9fee8465dd3f568c8e867e1b7ae52bdaf (hreitz/qemu-kvm-c-9-s)
RH-Bugzilla: 2072379
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
One clear problem with how qcow2's refcount structure rebuild algorithm
used to be before "qcow2: Improve refcount structure rebuilding" was
that it is prone to failure for qcow2 images on block devices: There is
generally unused space after the actual image, and if that exceeds what
one refblock covers, the old algorithm would invariably write the
reftable past the block device's end, which cannot work. The new
algorithm does not have this problem.
Test it with three tests:
(1) Create an image with more empty space at the end than what one
refblock covers, see whether rebuilding the refcount structures
results in a change in the image file length. (It should not.)
(2) Leave precisely enough space somewhere at the beginning of the image
for the new reftable (and the refblock for that place), see whether
the new algorithm puts the reftable there. (It should.)
(3) Test the original problem: Create (something like) a block device
with a fixed size, then create a qcow2 image in there, write some
data, and then have qemu-img check rebuild the refcount structures.
Before HEAD^, the reftable would have been written past the image
file end, i.e. outside of what the block device provides, which
cannot work. HEAD^ should have fixed that.
("Something like a block device" means a loop device if we can use
one ("sudo -n losetup" works), or a FUSE block export with
growable=false otherwise.)
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220405134652.19278-3-hreitz@redhat.com>
(cherry picked from commit 9ffd6d646d1d5ee9087a8cbf0b7d2f96c5656162)
Conflicts:
- 108: The downstream qemu-storage-daemon does not support --daemonize,
so this switch has been replaced by a loop waiting for the PID file to
appear
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
---
tests/qemu-iotests/108 | 263 ++++++++++++++++++++++++++++++++++++-
tests/qemu-iotests/108.out | 81 ++++++++++++
2 files changed, 343 insertions(+), 1 deletion(-)
diff --git a/tests/qemu-iotests/108 b/tests/qemu-iotests/108
index 56339ab2c5..a3090e2875 100755
--- a/tests/qemu-iotests/108
+++ b/tests/qemu-iotests/108
@@ -30,13 +30,20 @@ status=1 # failure is the default!
_cleanup()
{
- _cleanup_test_img
+ _cleanup_test_img
+ if [ -f "$TEST_DIR/qsd.pid" ]; then
+ qsd_pid=$(cat "$TEST_DIR/qsd.pid")
+ kill -KILL "$qsd_pid"
+ fusermount -u "$TEST_DIR/fuse-export" &>/dev/null
+ fi
+ rm -f "$TEST_DIR/fuse-export"
}
trap "_cleanup; exit \$status" 0 1 2 3 15
# get standard environment, filters and checks
. ./common.rc
. ./common.filter
+. ./common.qemu
# This tests qcow2-specific low-level functionality
_supported_fmt qcow2
@@ -47,6 +54,22 @@ _supported_os Linux
# files
_unsupported_imgopts 'refcount_bits=\([^1]\|.\([^6]\|$\)\)' data_file
+# This test either needs sudo -n losetup or FUSE exports to work
+if sudo -n losetup &>/dev/null; then
+ loopdev=true
+else
+ loopdev=false
+
+ # QSD --export fuse will either yield "Parameter 'id' is missing"
+ # or "Invalid parameter 'fuse'", depending on whether there is
+ # FUSE support or not.
+ error=$($QSD --export fuse 2>&1)
+ if [[ $error = *"'fuse'"* ]]; then
+ _notrun 'Passwordless sudo for losetup or FUSE support required, but' \
+ 'neither is available'
+ fi
+fi
+
echo
echo '=== Repairing an image without any refcount table ==='
echo
@@ -138,6 +161,244 @@ _make_test_img 64M
poke_file "$TEST_IMG" $((0x10008)) "\xff\xff\xff\xff\xff\xff\x00\x00"
_check_test_img -r all
+echo
+echo '=== Check rebuilt reftable location ==='
+
+# In an earlier version of the refcount rebuild algorithm, the
+# reftable was generally placed at the image end (unless something was
+# allocated in the area covered by the refblock right before the image
+# file end, then we would try to place the reftable in that refblock).
+# This was later changed so the reftable would be placed in the
+# earliest possible location. Test this.
+
+echo
+echo '--- Does the image size increase? ---'
+echo
+
+# First test: Just create some image, write some data to it, and
+# resize it so there is free space at the end of the image (enough
+# that it spans at least one full refblock, which for cluster_size=512
+# images, spans 128k). With the old algorithm, the reftable would
+# have then been placed at the end of the image file, but with the new
+# one, it will be put in that free space.
+# We want to check whether the size of the image file increases due to
+# rebuilding the refcount structures (it should not).
+
+_make_test_img -o 'cluster_size=512' 1M
+# Write something
+$QEMU_IO -c 'write 0 64k' "$TEST_IMG" | _filter_qemu_io
+
+# Add free space
+file_len=$(stat -c '%s' "$TEST_IMG")
+truncate -s $((file_len + 256 * 1024)) "$TEST_IMG"
+
+# Corrupt the image by saying the image header was not allocated
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
+rb_offset=$(peek_file_be "$TEST_IMG" $rt_offset 8)
+poke_file "$TEST_IMG" $rb_offset "\x00\x00"
+
+# Check whether rebuilding the refcount structures increases the image
+# file size
+file_len=$(stat -c '%s' "$TEST_IMG")
+echo
+# The only leaks there can be are the old refcount structures that are
+# leaked during rebuilding, no need to clutter the output with them
+_check_test_img -r all | grep -v '^Repairing cluster.*refcount=1 reference=0'
+echo
+post_repair_file_len=$(stat -c '%s' "$TEST_IMG")
+
+if [[ $file_len -eq $post_repair_file_len ]]; then
+ echo 'OK: Image size did not change'
+else
+ echo 'ERROR: Image size differs' \
+ "($file_len before, $post_repair_file_len after)"
+fi
+
+echo
+echo '--- Will the reftable occupy a hole specifically left for it? ---'
+echo
+
+# Note: With cluster_size=512, every refblock covers 128k.
+# The reftable covers 8M per reftable cluster.
+
+# Create an image that requires two reftable clusters (just because
+# this is more interesting than a single-clustered reftable).
+_make_test_img -o 'cluster_size=512' 9M
+$QEMU_IO -c 'write 0 8M' "$TEST_IMG" | _filter_qemu_io
+
+# Writing 8M will have resized the reftable. Unfortunately, doing so
+# will leave holes in the file, so we need to fill them up so we can
+# be sure the whole file is allocated. Do that by writing
+# consecutively smaller chunks starting from 8 MB, until the file
+# length increases even with a chunk size of 512. Then we must have
+# filled all holes.
+ofs=$((8 * 1024 * 1024))
+block_len=$((16 * 1024))
+while [[ $block_len -ge 512 ]]; do
+ file_len=$(stat -c '%s' "$TEST_IMG")
+ while [[ $(stat -c '%s' "$TEST_IMG") -eq $file_len ]]; do
+ # Do not include this in the reference output, it does not
+ # really matter which qemu-io calls we do here exactly
+ $QEMU_IO -c "write $ofs $block_len" "$TEST_IMG" >/dev/null
+ ofs=$((ofs + block_len))
+ done
+ block_len=$((block_len / 2))
+done
+
+# Fill up to 9M (do not include this in the reference output either,
+# $ofs is random for all we know)
+$QEMU_IO -c "write $ofs $((9 * 1024 * 1024 - ofs))" "$TEST_IMG" >/dev/null
+
+# Make space as follows:
+# - For the first refblock: Right at the beginning of the image (this
+# refblock is placed in the first place possible),
+# - For the reftable somewhere soon afterwards, still near the
+# beginning of the image (i.e. covered by the first refblock); the
+# reftable too is placed in the first place possible, but only after
+# all refblocks have been placed)
+# No space is needed for the other refblocks, because no refblock is
+# put before the space it covers. In this test case, we do not mind
+# if they are placed at the image file's end.
+
+# Before we make that space, we have to find out the host offset of
+# the area that belonged to the two data clusters at guest offset 4k,
+# because we expect the reftable to be placed there, and we will have
+# to verify that it is.
+
+l1_offset=$(peek_file_be "$TEST_IMG" 40 8)
+l2_offset=$(peek_file_be "$TEST_IMG" $l1_offset 8)
+l2_offset=$((l2_offset & 0x00fffffffffffe00))
+data_4k_offset=$(peek_file_be "$TEST_IMG" \
+ $((l2_offset + 4096 / 512 * 8)) 8)
+data_4k_offset=$((data_4k_offset & 0x00fffffffffffe00))
+
+$QEMU_IO -c "discard 0 512" -c "discard 4k 1k" "$TEST_IMG" | _filter_qemu_io
+
+# Corrupt the image by saying the image header was not allocated
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
+rb_offset=$(peek_file_be "$TEST_IMG" $rt_offset 8)
+poke_file "$TEST_IMG" $rb_offset "\x00\x00"
+
+echo
+# The only leaks there can be are the old refcount structures that are
+# leaked during rebuilding, no need to clutter the output with them
+_check_test_img -r all | grep -v '^Repairing cluster.*refcount=1 reference=0'
+echo
+
+# Check whether the reftable was put where we expected
+rt_offset=$(peek_file_be "$TEST_IMG" 48 8)
+if [[ $rt_offset -eq $data_4k_offset ]]; then
+ echo 'OK: Reftable is where we expect it'
+else
+ echo "ERROR: Reftable is at $rt_offset, but was expected at $data_4k_offset"
+fi
+
+echo
+echo '--- Rebuilding refcount structures on block devices ---'
+echo
+
+# A block device cannot really grow, at least not during qemu-img
+# check. As mentioned in the above cases, rebuilding the refcount
+# structure may lead to new refcount structures being written after
+# the end of the image, and in the past that happened even if there
+# was more than sufficient space in the image. Such post-EOF writes
+# will not work on block devices, so test that the new algorithm
+# avoids it.
+
+# If we have passwordless sudo and losetup, we can use those to create
+# a block device. Otherwise, we can resort to qemu's FUSE export to
+# create a file that isn't growable, which effectively tests the same
+# thing.
+
+_cleanup_test_img
+truncate -s $((64 * 1024 * 1024)) "$TEST_IMG"
+
+if $loopdev; then
+ export_mp=$(sudo -n losetup --show -f "$TEST_IMG")
+ export_mp_driver=host_device
+ sudo -n chmod go+rw "$export_mp"
+else
+ # Create non-growable FUSE export that is a bit like an empty
+ # block device
+ export_mp="$TEST_DIR/fuse-export"
+ export_mp_driver=file
+ touch "$export_mp"
+
+ $QSD \
+ --blockdev file,node-name=export-node,filename="$TEST_IMG" \
+ --export fuse,id=fuse-export,node-name=export-node,mountpoint="$export_mp",writable=on,growable=off \
+ --pidfile "$TEST_DIR/qsd.pid" \
+ &
+
+ while [ ! -f "$TEST_DIR/qsd.pid" ]; do
+ sleep 0.1
+ done
+fi
+
+# Now create a qcow2 image on the device -- unfortunately, qemu-img
+# create force-creates the file, so we have to resort to the
+# blockdev-create job.
+_launch_qemu \
+ --blockdev $export_mp_driver,node-name=file,filename="$export_mp"
+
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "qmp_capabilities" }' \
+ 'return'
+
+# Small cluster size again, so the image needs multiple refblocks
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "blockdev-create",
+ "arguments": {
+ "job-id": "create",
+ "options": {
+ "driver": "qcow2",
+ "file": "file",
+ "size": '$((64 * 1024 * 1024))',
+ "cluster-size": 512
+ } } }' \
+ '"concluded"'
+
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "job-dismiss", "arguments": { "id": "create" } }' \
+ 'return'
+
+_send_qemu_cmd \
+ $QEMU_HANDLE \
+ '{ "execute": "quit" }' \
+ 'return'
+
+wait=y _cleanup_qemu
+echo
+
+# Write some data
+$QEMU_IO -c 'write 0 64k' "$export_mp" | _filter_qemu_io
+
+# Corrupt the image by saying the image header was not allocated
+rt_offset=$(peek_file_be "$export_mp" 48 8)
+rb_offset=$(peek_file_be "$export_mp" $rt_offset 8)
+poke_file "$export_mp" $rb_offset "\x00\x00"
+
+# Repairing such a simple case should just work
+# (We used to put the reftable at the end of the image file, which can
+# never work for non-growable devices.)
+echo
+TEST_IMG="$export_mp" _check_test_img -r all \
+ | grep -v '^Repairing cluster.*refcount=1 reference=0'
+
+if $loopdev; then
+ sudo -n losetup -d "$export_mp"
+else
+ qsd_pid=$(cat "$TEST_DIR/qsd.pid")
+ kill -TERM "$qsd_pid"
+ # Wait for process to exit (cannot `wait` because the QSD is daemonized)
+ while [ -f "$TEST_DIR/qsd.pid" ]; do
+ true
+ done
+fi
+
# success, all done
echo '*** done'
rm -f $seq.full
diff --git a/tests/qemu-iotests/108.out b/tests/qemu-iotests/108.out
index 75bab8dc84..b5401d788d 100644
--- a/tests/qemu-iotests/108.out
+++ b/tests/qemu-iotests/108.out
@@ -105,6 +105,87 @@ The following inconsistencies were found and repaired:
0 leaked clusters
1 corruptions
+Double checking the fixed image now...
+No errors were found on the image.
+
+=== Check rebuilt reftable location ===
+
+--- Does the image size increase? ---
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+ERROR cluster 0 refcount=0 reference=1
+Rebuilding refcount structure
+The following inconsistencies were found and repaired:
+
+ 0 leaked clusters
+ 1 corruptions
+
+Double checking the fixed image now...
+No errors were found on the image.
+
+OK: Image size did not change
+
+--- Will the reftable occupy a hole specifically left for it? ---
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=9437184
+wrote 8388608/8388608 bytes at offset 0
+8 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+discard 512/512 bytes at offset 0
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+discard 1024/1024 bytes at offset 4096
+1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+ERROR cluster 0 refcount=0 reference=1
+Rebuilding refcount structure
+The following inconsistencies were found and repaired:
+
+ 0 leaked clusters
+ 1 corruptions
+
+Double checking the fixed image now...
+No errors were found on the image.
+
+OK: Reftable is where we expect it
+
+--- Rebuilding refcount structures on block devices ---
+
+{ "execute": "qmp_capabilities" }
+{"return": {}}
+{ "execute": "blockdev-create",
+ "arguments": {
+ "job-id": "create",
+ "options": {
+ "driver": "IMGFMT",
+ "file": "file",
+ "size": 67108864,
+ "cluster-size": 512
+ } } }
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "create"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "create"}}
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "waiting", "id": "create"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "pending", "id": "create"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "concluded", "id": "create"}}
+{ "execute": "job-dismiss", "arguments": { "id": "create" } }
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "null", "id": "create"}}
+{"return": {}}
+{ "execute": "quit" }
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false, "reason": "host-qmp-quit"}}
+
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+ERROR cluster 0 refcount=0 reference=1
+Rebuilding refcount structure
+The following inconsistencies were found and repaired:
+
+ 0 leaked clusters
+ 1 corruptions
+
Double checking the fixed image now...
No errors were found on the image.
*** done
--
2.31.1

62
kvm-kvm-don-t-use-perror-without-useful-errno.patch
View File

@ -1,62 +0,0 @@
From 9ddefaedf423ec03eadaf17496c14e0d7b2381c8 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Thu, 28 Jul 2022 16:24:46 +0200
Subject: [PATCH 30/32] kvm: don't use perror() without useful errno
RH-Author: Cornelia Huck <cohuck@redhat.com>
RH-MergeRequest: 110: kvm: don't use perror() without useful errno
RH-Commit: [1/1] 20e51aac6767c1f89f74c7d692d1fb7689eff5f0 (cohuck/qemu-kvm-c9s)
RH-Bugzilla: 2095608
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
perror() is designed to append the decoded errno value to a
string. This, however, only makes sense if we called something that
actually sets errno prior to that.
For the callers that check for split irqchip support that is not the
case, and we end up with confusing error messages that end in
"success". Use error_report() instead.
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Message-Id: <20220728142446.438177-1-cohuck@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
https://bugzilla.redhat.com/show_bug.cgi?id=2095608
(cherry picked from commit 47c182fe8b03c0c40059fb95840923e65c9bdb4f)
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
accel/kvm/kvm-all.c | 2 +-
target/arm/kvm.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 5f1377ca04..e9c7947640 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2254,7 +2254,7 @@ static void kvm_irqchip_create(KVMState *s)
ret = kvm_arch_irqchip_create(s);
if (ret == 0) {
if (s->kernel_irqchip_split == ON_OFF_AUTO_ON) {
- perror("Split IRQ chip mode not supported.");
+ error_report("Split IRQ chip mode not supported.");
exit(1);
} else {
ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP);
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index bbf1ce7ba3..0a2ba1f8e3 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -960,7 +960,7 @@ void kvm_arch_init_irq_routing(KVMState *s)
int kvm_arch_irqchip_create(KVMState *s)
{
if (kvm_kernel_irqchip_split()) {
- perror("-machine kernel_irqchip=split is not supported on ARM.");
+ error_report("-machine kernel_irqchip=split is not supported on ARM.");
exit(1);
}
--
2.31.1

49
kvm-linux-aio-explain-why-max-batch-is-checked-in-laio_i.patch
View File

@ -1,49 +0,0 @@
From 49d9c9dced7278517105e9cfec34ea4af716432d Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 9 Jun 2022 17:47:12 +0100
Subject: [PATCH 6/6] linux-aio: explain why max batch is checked in
laio_io_unplug()
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 102: linux-aio: fix unbalanced plugged counter in laio_io_unplug()
RH-Commit: [2/2] b3d6421086bde50d4baad2343b2df89c5f66950e (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 2092788
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
It may not be obvious why laio_io_unplug() checks max batch. I discussed
this with Stefano and have added a comment summarizing the reason.
Cc: Stefano Garzarella <sgarzare@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Message-id: 20220609164712.1539045-3-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 99b969fbe105117f5af6060d3afef40ca39cc9c1)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
block/linux-aio.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 6078da7e42..9c2393a2f7 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -365,6 +365,12 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s,
assert(s->io_q.plugged);
s->io_q.plugged--;
+ /*
+ * Why max batch checking is performed here:
+ * Another BDS may have queued requests with a higher dev_max_batch and
+ * therefore in_queue could now exceed our dev_max_batch. Re-check the max
+ * batch so we can honor our device's dev_max_batch.
+ */
if (s->io_q.in_queue >= laio_max_batch(s, dev_max_batch) ||
(!s->io_q.plugged &&
!s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending))) {
--
2.31.1

56
kvm-linux-aio-fix-unbalanced-plugged-counter-in-laio_io_.patch
View File

@ -1,56 +0,0 @@
From e7326c3a7e0fc022aa5c0ae07bc1e19ad1b6f2ed Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 9 Jun 2022 17:47:11 +0100
Subject: [PATCH 5/6] linux-aio: fix unbalanced plugged counter in
laio_io_unplug()
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 102: linux-aio: fix unbalanced plugged counter in laio_io_unplug()
RH-Commit: [1/2] 8a71da371c72521f1d70b8767ee564575e0d522b (stefanha/centos-stream-qemu-kvm)
RH-Bugzilla: 2092788
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Every laio_io_plug() call has a matching laio_io_unplug() call. There is
a plugged counter that tracks the number of levels of plugging and
allows for nesting.
The plugged counter must reflect the balance between laio_io_plug() and
laio_io_unplug() calls accurately. Otherwise I/O stalls occur since
io_submit(2) calls are skipped while plugged.
Reported-by: Nikolay Tenev <nt@storpool.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Message-id: 20220609164712.1539045-2-stefanha@redhat.com
Cc: Stefano Garzarella <sgarzare@redhat.com>
Fixes: 68d7946648 ("linux-aio: add `dev_max_batch` parameter to laio_io_unplug()")
[Stefano Garzarella suggested adding a Fixes tag.
--Stefan]
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit f387cac5af030a58ac5a0dacf64cab5e5a4fe5c7)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
block/linux-aio.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 4c423fcccf..6078da7e42 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -363,8 +363,10 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s,
uint64_t dev_max_batch)
{
assert(s->io_q.plugged);
+ s->io_q.plugged--;
+
if (s->io_q.in_queue >= laio_max_batch(s, dev_max_batch) ||
- (--s->io_q.plugged == 0 &&
+ (!s->io_q.plugged &&
!s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending))) {
ioq_submit(s);
}
--
2.31.1

154
kvm-meson-create-have_vhost_-variables.patch
View File

@ -1,154 +0,0 @@
From 51c310097832724bafac26aed81399da40128400 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 21 Jul 2022 15:50:43 +0200
Subject: [PATCH 05/32] meson: create have_vhost_* variables
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 108: Net Control Virtqueue shadow Support
RH-Commit: [5/27] 3b30f89e6d639923dc9d9a92a4261bb4509e5c83 (eperezmartin/qemu-kvm)
RH-Bugzilla: 1939363
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
Bugzilla: https://bugzilla.redhat.com/1939363
Upstream Status: git://git.qemu.org/qemu.git
commit 2a3129a37652e5e81d12f6e16dd3c447f09831f9
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed Apr 20 17:34:05 2022 +0200
meson: create have_vhost_* variables
When using Meson options rather than config-host.h, the "when" clauses
have to be changed to if statements (which is not necessarily great,
though at least it highlights which parts of the build are per-target
and which are not).
Do that before moving vhost logic to meson.build, though for now
the variables are just based on config-host.mak data.
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
meson.build | 30 ++++++++++++++++++++----------
tests/meson.build | 2 +-
tools/meson.build | 2 +-
3 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/meson.build b/meson.build
index 13e3323380..735f538497 100644
--- a/meson.build
+++ b/meson.build
@@ -298,6 +298,15 @@ have_tpm = get_option('tpm') \
.require(targetos != 'windows', error_message: 'TPM emulation only available on POSIX systems') \
.allowed()
+# vhost
+have_vhost_user = 'CONFIG_VHOST_USER' in config_host
+have_vhost_vdpa = 'CONFIG_VHOST_VDPA' in config_host
+have_vhost_kernel = 'CONFIG_VHOST_KERNEL' in config_host
+have_vhost_net_user = 'CONFIG_VHOST_NET_USER' in config_host
+have_vhost_net_vdpa = 'CONFIG_VHOST_NET_VDPA' in config_host
+have_vhost_net = 'CONFIG_VHOST_NET' in config_host
+have_vhost_user_crypto = 'CONFIG_VHOST_CRYPTO' in config_host
+
# Target-specific libraries and flags
libm = cc.find_library('m', required: false)
threads = dependency('threads')
@@ -1335,7 +1344,7 @@ has_statx_mnt_id = cc.links(statx_mnt_id_test)
have_vhost_user_blk_server = get_option('vhost_user_blk_server') \
.require(targetos == 'linux',
error_message: 'vhost_user_blk_server requires linux') \
- .require('CONFIG_VHOST_USER' in config_host,
+ .require(have_vhost_user,
error_message: 'vhost_user_blk_server requires vhost-user support') \
.disable_auto_if(not have_system) \
.allowed()
@@ -2116,9 +2125,9 @@ host_kconfig = \
(have_ivshmem ? ['CONFIG_IVSHMEM=y'] : []) + \
('CONFIG_OPENGL' in config_host ? ['CONFIG_OPENGL=y'] : []) + \
(x11.found() ? ['CONFIG_X11=y'] : []) + \
- ('CONFIG_VHOST_USER' in config_host ? ['CONFIG_VHOST_USER=y'] : []) + \
- ('CONFIG_VHOST_VDPA' in config_host ? ['CONFIG_VHOST_VDPA=y'] : []) + \
- ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \
+ (have_vhost_user ? ['CONFIG_VHOST_USER=y'] : []) + \
+ (have_vhost_vdpa ? ['CONFIG_VHOST_VDPA=y'] : []) + \
+ (have_vhost_kernel ? ['CONFIG_VHOST_KERNEL=y'] : []) + \
(have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \
('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \
('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \
@@ -2799,7 +2808,7 @@ if have_system or have_user
endif
vhost_user = not_found
-if targetos == 'linux' and 'CONFIG_VHOST_USER' in config_host
+if targetos == 'linux' and have_vhost_user
libvhost_user = subproject('libvhost-user')
vhost_user = libvhost_user.get_variable('vhost_user_dep')
endif
@@ -3386,7 +3395,7 @@ if have_tools
dependencies: qemuutil,
install: true)
- if 'CONFIG_VHOST_USER' in config_host
+ if have_vhost_user
subdir('contrib/vhost-user-blk')
subdir('contrib/vhost-user-gpu')
subdir('contrib/vhost-user-input')
@@ -3516,15 +3525,16 @@ if 'simple' in get_option('trace_backends')
endif
summary_info += {'D-Bus display': dbus_display}
summary_info += {'QOM debugging': get_option('qom_cast_debug')}
-summary_info += {'vhost-kernel support': config_host.has_key('CONFIG_VHOST_KERNEL')}
-summary_info += {'vhost-net support': config_host.has_key('CONFIG_VHOST_NET')}
-summary_info += {'vhost-crypto support': config_host.has_key('CONFIG_VHOST_CRYPTO')}
+summary_info += {'vhost-kernel support': have_vhost_kernel}
+summary_info += {'vhost-net support': have_vhost_net}
+summary_info += {'vhost-user support': have_vhost_user}
+summary_info += {'vhost-user-crypto support': have_vhost_user_crypto}
summary_info += {'vhost-scsi support': config_host.has_key('CONFIG_VHOST_SCSI')}
summary_info += {'vhost-vsock support': config_host.has_key('CONFIG_VHOST_VSOCK')}
-summary_info += {'vhost-user support': config_host.has_key('CONFIG_VHOST_USER')}
summary_info += {'vhost-user-blk server support': have_vhost_user_blk_server}
summary_info += {'vhost-user-fs support': config_host.has_key('CONFIG_VHOST_USER_FS')}
summary_info += {'vhost-vdpa support': config_host.has_key('CONFIG_VHOST_VDPA')}
+summary_info += {'vhost-vdpa support': have_vhost_vdpa}
summary_info += {'build guest agent': have_ga}
summary(summary_info, bool_yn: true, section: 'Configurable features')
diff --git a/tests/meson.build b/tests/meson.build
index 1d05109eb4..bbe41c8559 100644
--- a/tests/meson.build
+++ b/tests/meson.build
@@ -70,7 +70,7 @@ test_deps = {
'test-qht-par': qht_bench,
}
-if have_tools and 'CONFIG_VHOST_USER' in config_host and 'CONFIG_LINUX' in config_host
+if have_tools and have_vhost_user and 'CONFIG_LINUX' in config_host
executable('vhost-user-bridge',
sources: files('vhost-user-bridge.c'),
dependencies: [qemuutil, vhost_user])
diff --git a/tools/meson.build b/tools/meson.build
index 46977af84f..10eb3a043f 100644
--- a/tools/meson.build
+++ b/tools/meson.build
@@ -3,7 +3,7 @@ have_virtiofsd = get_option('virtiofsd') \
error_message: 'virtiofsd requires Linux') \
.require(seccomp.found() and libcap_ng.found(),
error_message: 'virtiofsd requires libcap-ng-devel and seccomp-devel') \
- .require('CONFIG_VHOST_USER' in config_host,
+ .require(have_vhost_user,
error_message: 'virtiofsd needs vhost-user-support') \
.disable_auto_if(not have_tools and not have_system) \
.allowed()
--
2.31.1

213
kvm-meson-use-have_vhost_-variables-to-pick-sources.patch
View File

@ -1,213 +0,0 @@
From a7d57a09e33275d5e6649273b5c9da1bc3c92491 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 21 Jul 2022 15:51:53 +0200
Subject: [PATCH 06/32] meson: use have_vhost_* variables to pick sources
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 108: Net Control Virtqueue shadow Support
RH-Commit: [6/27] bc3db1efb759c0bc97fde2f4fbb3d6dc404c8d3d (eperezmartin/qemu-kvm)
RH-Bugzilla: 1939363
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
Bugzilla: https://bugzilla.redhat.com/1939363
Upstream Status: git://git.qemu.org/qemu.git
commit 43b6d7ee1fbc5b5fb7c85d8131fdac1863214ad6
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed Apr 20 17:34:06 2022 +0200
meson: use have_vhost_* variables to pick sources
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
Kconfig.host | 3 ---
backends/meson.build | 8 ++++++--
hw/net/meson.build | 8 ++++++--
hw/virtio/Kconfig | 3 ---
hw/virtio/meson.build | 25 ++++++++++++++++---------
meson.build | 1 +
net/meson.build | 12 +++++++-----
tests/qtest/meson.build | 4 +++-
8 files changed, 39 insertions(+), 25 deletions(-)
diff --git a/Kconfig.host b/Kconfig.host
index 60b9c07b5e..1165c4eacd 100644
--- a/Kconfig.host
+++ b/Kconfig.host
@@ -22,15 +22,12 @@ config TPM
config VHOST_USER
bool
- select VHOST
config VHOST_VDPA
bool
- select VHOST
config VHOST_KERNEL
bool
- select VHOST
config VIRTFS
bool
diff --git a/backends/meson.build b/backends/meson.build
index 6e68945528..cb92f639ca 100644
--- a/backends/meson.build
+++ b/backends/meson.build
@@ -12,9 +12,13 @@ softmmu_ss.add([files(
softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files('rng-random.c'))
softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files('hostmem-file.c'))
softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files('hostmem-memfd.c'))
-softmmu_ss.add(when: ['CONFIG_VHOST_USER', 'CONFIG_VIRTIO'], if_true: files('vhost-user.c'))
+if have_vhost_user
+ softmmu_ss.add(when: 'CONFIG_VIRTIO', if_true: files('vhost-user.c'))
+endif
softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost.c'))
-softmmu_ss.add(when: ['CONFIG_VIRTIO_CRYPTO', 'CONFIG_VHOST_CRYPTO'], if_true: files('cryptodev-vhost-user.c'))
+if have_vhost_user_crypto
+ softmmu_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('cryptodev-vhost-user.c'))
+endif
softmmu_ss.add(when: 'CONFIG_GIO', if_true: [files('dbus-vmstate.c'), gio])
softmmu_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c'))
diff --git a/hw/net/meson.build b/hw/net/meson.build
index 685b75badb..ebac261542 100644
--- a/hw/net/meson.build
+++ b/hw/net/meson.build
@@ -46,8 +46,12 @@ specific_ss.add(when: 'CONFIG_XILINX_ETHLITE', if_true: files('xilinx_ethlite.c'
softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('net_rx_pkt.c'))
specific_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('virtio-net.c'))
-softmmu_ss.add(when: ['CONFIG_VIRTIO_NET', 'CONFIG_VHOST_NET'], if_true: files('vhost_net.c'), if_false: files('vhost_net-stub.c'))
-softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost_net-stub.c'))
+if have_vhost_net
+ softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost_net.c'), if_false: files('vhost_net-stub.c'))
+ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost_net-stub.c'))
+else
+ softmmu_ss.add(files('vhost_net-stub.c'))
+endif
softmmu_ss.add(when: 'CONFIG_ETSEC', if_true: files(
'fsl_etsec/etsec.c',
diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig
index c144d42f9b..8ca7b3d9d6 100644
--- a/hw/virtio/Kconfig
+++ b/hw/virtio/Kconfig
@@ -1,6 +1,3 @@
-config VHOST
- bool
-
config VIRTIO
bool
diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
index 67dc77e00f..30a832eb4a 100644
--- a/hw/virtio/meson.build
+++ b/hw/virtio/meson.build
@@ -2,18 +2,22 @@ softmmu_virtio_ss = ss.source_set()
softmmu_virtio_ss.add(files('virtio-bus.c'))
softmmu_virtio_ss.add(when: 'CONFIG_VIRTIO_PCI', if_true: files('virtio-pci.c'))
softmmu_virtio_ss.add(when: 'CONFIG_VIRTIO_MMIO', if_true: files('virtio-mmio.c'))
-softmmu_virtio_ss.add(when: 'CONFIG_VHOST', if_false: files('vhost-stub.c'))
-
-softmmu_ss.add_all(when: 'CONFIG_VIRTIO', if_true: softmmu_virtio_ss)
-softmmu_ss.add(when: 'CONFIG_VIRTIO', if_false: files('vhost-stub.c'))
-
-softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-stub.c'))
virtio_ss = ss.source_set()
virtio_ss.add(files('virtio.c'))
-virtio_ss.add(when: 'CONFIG_VHOST', if_true: files('vhost.c', 'vhost-backend.c', 'vhost-iova-tree.c'))
-virtio_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user.c'))
-virtio_ss.add(when: 'CONFIG_VHOST_VDPA', if_true: files('vhost-shadow-virtqueue.c', 'vhost-vdpa.c'))
+
+if have_vhost
+ virtio_ss.add(files('vhost.c', 'vhost-backend.c', 'vhost-iova-tree.c'))
+ if have_vhost_user
+ virtio_ss.add(files('vhost-user.c'))
+ endif
+ if have_vhost_vdpa
+ virtio_ss.add(files('vhost-vdpa.c', 'vhost-shadow-virtqueue.c'))
+ endif
+else
+ softmmu_virtio_ss.add(files('vhost-stub.c'))
+endif
+
virtio_ss.add(when: 'CONFIG_VIRTIO_BALLOON', if_true: files('virtio-balloon.c'))
virtio_ss.add(when: 'CONFIG_VIRTIO_CRYPTO', if_true: files('virtio-crypto.c'))
virtio_ss.add(when: ['CONFIG_VIRTIO_CRYPTO', 'CONFIG_VIRTIO_PCI'], if_true: files('virtio-crypto-pci.c'))
@@ -53,3 +57,6 @@ virtio_pci_ss.add(when: 'CONFIG_VIRTIO_MEM', if_true: files('virtio-mem-pci.c'))
virtio_ss.add_all(when: 'CONFIG_VIRTIO_PCI', if_true: virtio_pci_ss)
specific_ss.add_all(when: 'CONFIG_VIRTIO', if_true: virtio_ss)
+softmmu_ss.add_all(when: 'CONFIG_VIRTIO', if_true: softmmu_virtio_ss)
+softmmu_ss.add(when: 'CONFIG_VIRTIO', if_false: files('vhost-stub.c'))
+softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-stub.c'))
diff --git a/meson.build b/meson.build
index 735f538497..9ba675f098 100644
--- a/meson.build
+++ b/meson.build
@@ -305,6 +305,7 @@ have_vhost_kernel = 'CONFIG_VHOST_KERNEL' in config_host
have_vhost_net_user = 'CONFIG_VHOST_NET_USER' in config_host
have_vhost_net_vdpa = 'CONFIG_VHOST_NET_VDPA' in config_host
have_vhost_net = 'CONFIG_VHOST_NET' in config_host
+have_vhost = have_vhost_user or have_vhost_vdpa or have_vhost_kernel
have_vhost_user_crypto = 'CONFIG_VHOST_CRYPTO' in config_host
# Target-specific libraries and flags
diff --git a/net/meson.build b/net/meson.build
index 847bc2ac85..c965e83b26 100644
--- a/net/meson.build
+++ b/net/meson.build
@@ -26,10 +26,10 @@ softmmu_ss.add(when: vde, if_true: files('vde.c'))
if have_netmap
softmmu_ss.add(files('netmap.c'))
endif
-vhost_user_ss = ss.source_set()
-vhost_user_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-user.c'), if_false: files('vhost-user-stub.c'))
-softmmu_ss.add_all(when: 'CONFIG_VHOST_NET_USER', if_true: vhost_user_ss)
-softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-user-stub.c'))
+if have_vhost_net_user
+ softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-user.c'), if_false: files('vhost-user-stub.c'))
+ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-user-stub.c'))
+endif
softmmu_ss.add(when: 'CONFIG_LINUX', if_true: files('tap-linux.c'))
softmmu_ss.add(when: 'CONFIG_BSD', if_true: files('tap-bsd.c'))
@@ -40,6 +40,8 @@ if not config_host.has_key('CONFIG_LINUX') and not config_host.has_key('CONFIG_B
endif
softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix))
softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c'))
-softmmu_ss.add(when: 'CONFIG_VHOST_NET_VDPA', if_true: files('vhost-vdpa.c'))
+if have_vhost_net_vdpa
+ softmmu_ss.add(files('vhost-vdpa.c'))
+endif
subdir('can')
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index 67cd32def1..9f550df900 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -269,7 +269,9 @@ qos_test_ss.add(
if have_virtfs
qos_test_ss.add(files('virtio-9p-test.c'))
endif
-qos_test_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-test.c'))
+if have_vhost_user
+ qos_test_ss.add(files('vhost-user-test.c'))
+endif
if have_tools and have_vhost_user_blk_server
qos_test_ss.add(files('vhost-user-blk-test.c'))
endif
--
2.31.1

87
kvm-meson.build-Fix-docker-test-build-alpine-when-includ.patch
View File

@ -1,87 +0,0 @@
From 7c489b54b0bb33445113fbf16e88feb23be68013 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:30 -0300
Subject: [PATCH 07/18] meson.build: Fix docker-test-build@alpine when
including linux/errqueue.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [1/11] f058eb846fcf611d527a1dd3b0cc399cdc17e3ee (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
A build error happens in alpine CI when linux/errqueue.h is included
in io/channel-socket.c, due to redefining of 'struct __kernel_timespec':
===
ninja: job failed: [...]
In file included from /usr/include/linux/errqueue.h:6,
from ../io/channel-socket.c:29:
/usr/include/linux/time_types.h:7:8: error: redefinition of 'struct __kernel_timespec'
7 | struct __kernel_timespec {
| ^~~~~~~~~~~~~~~~~
In file included from /usr/include/liburing.h:19,
from /builds/user/qemu/include/block/aio.h:18,
from /builds/user/qemu/include/io/channel.h:26,
from /builds/user/qemu/include/io/channel-socket.h:24,
from ../io/channel-socket.c:24:
/usr/include/liburing/compat.h:9:8: note: originally defined here
9 | struct __kernel_timespec {
| ^~~~~~~~~~~~~~~~~
ninja: subcommand failed
===
As above error message suggests, 'struct __kernel_timespec' was already
defined by liburing/compat.h.
Fix alpine CI by adding test to disable liburing in configure step if a
redefinition happens between linux/errqueue.h and liburing/compat.h.
[dgilbert: This has been fixed in Alpine issue 13813 and liburing]
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Message-Id: <20220513062836.965425-2-leobras@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 354081d43de44ebd3497fe08f7f0121a5517d528)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
meson.build | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/meson.build b/meson.build
index 5a7c10e639..13e3323380 100644
--- a/meson.build
+++ b/meson.build
@@ -471,12 +471,23 @@ if not get_option('linux_aio').auto() or have_block
required: get_option('linux_aio'),
kwargs: static_kwargs)
endif
+
+linux_io_uring_test = '''
+ #include <liburing.h>
+ #include <linux/errqueue.h>
+
+ int main(void) { return 0; }'''
+
linux_io_uring = not_found
if not get_option('linux_io_uring').auto() or have_block
linux_io_uring = dependency('liburing', version: '>=0.3',
required: get_option('linux_io_uring'),
method: 'pkg-config', kwargs: static_kwargs)
+ if not cc.links(linux_io_uring_test)
+ linux_io_uring = not_found
+ endif
endif
+
libnfs = not_found
if not get_option('libnfs').auto() or have_block
libnfs = dependency('libnfs', version: '>=1.9.3',
--
2.35.3

106
kvm-migration-Add-migrate_use_tls-helper.patch
View File

@ -1,106 +0,0 @@
From 828f6c106eedcb7a48e551ffda15af56ff92a899 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:34 -0300
Subject: [PATCH 11/18] migration: Add migrate_use_tls() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [5/11] 06e945297c3b9c0ce5864885aafcdba1e5746bc2 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
A lot of places check parameters.tls_creds in order to evaluate if TLS is
in use, and sometimes call migrate_get_current() just for that test.
Add new helper function migrate_use_tls() in order to simplify testing
for TLS usage.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20220513062836.965425-6-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit d2fafb6a6814a8998607d0baf691265032996a0f)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/channel.c | 3 +--
migration/migration.c | 9 +++++++++
migration/migration.h | 1 +
migration/multifd.c | 5 +----
4 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/migration/channel.c b/migration/channel.c
index c4fc000a1a..086b5c0d8b 100644
--- a/migration/channel.c
+++ b/migration/channel.c
@@ -38,8 +38,7 @@ void migration_channel_process_incoming(QIOChannel *ioc)
trace_migration_set_incoming_channel(
ioc, object_get_typename(OBJECT(ioc)));
- if (s->parameters.tls_creds &&
- *s->parameters.tls_creds &&
+ if (migrate_use_tls() &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
migration_tls_channel_process_incoming(s, ioc, &local_err);
diff --git a/migration/migration.c b/migration/migration.c
index 0a6b3b9f4d..d91efb66fe 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2582,6 +2582,15 @@ bool migrate_use_zero_copy_send(void)
}
#endif
+int migrate_use_tls(void)
+{
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->parameters.tls_creds && *s->parameters.tls_creds;
+}
+
int migrate_use_xbzrle(void)
{
MigrationState *s;
diff --git a/migration/migration.h b/migration/migration.h
index 5bcb7628ef..c2cabb8a14 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -381,6 +381,7 @@ bool migrate_use_zero_copy_send(void);
#else
#define migrate_use_zero_copy_send() (false)
#endif
+int migrate_use_tls(void);
int migrate_use_xbzrle(void);
uint64_t migrate_xbzrle_cache_size(void);
bool migrate_colo_enabled(void);
diff --git a/migration/multifd.c b/migration/multifd.c
index 76b57a7177..43998ad117 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -784,14 +784,11 @@ static bool multifd_channel_connect(MultiFDSendParams *p,
QIOChannel *ioc,
Error *error)
{
- MigrationState *s = migrate_get_current();
-
trace_multifd_set_outgoing_channel(
ioc, object_get_typename(OBJECT(ioc)), p->tls_hostname, error);
if (!error) {
- if (s->parameters.tls_creds &&
- *s->parameters.tls_creds &&
+ if (migrate_use_tls() &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
multifd_tls_channel_connect(p, ioc, &error);
--
2.35.3

250
kvm-migration-Add-zero-copy-send-parameter-for-QMP-HMP-f.patch
View File

@ -1,250 +0,0 @@
From d6500340dc3c1152b5efe04ef3daa50c17a55e30 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:33 -0300
Subject: [PATCH 10/18] migration: Add zero-copy-send parameter for QMP/HMP for
Linux
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [4/11] 514d98d595992c53ff98de750035e080ded8972e (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Add property that allows zero-copy migration of memory pages
on the sending side, and also includes a helper function
migrate_use_zero_copy_send() to check if it's enabled.
No code is introduced to actually do the migration, but it allow
future implementations to enable/disable this feature.
On non-Linux builds this parameter is compiled-out.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20220513062836.965425-5-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit abb6295b3ace5d17c3a65936913fc346616dbf14)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 32 ++++++++++++++++++++++++++++++++
migration/migration.h | 5 +++++
migration/socket.c | 11 +++++++++--
monitor/hmp-cmds.c | 6 ++++++
qapi/migration.json | 24 ++++++++++++++++++++++++
5 files changed, 76 insertions(+), 2 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index 695f0f2900..0a6b3b9f4d 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -899,6 +899,10 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
params->multifd_zlib_level = s->parameters.multifd_zlib_level;
params->has_multifd_zstd_level = true;
params->multifd_zstd_level = s->parameters.multifd_zstd_level;
+#ifdef CONFIG_LINUX
+ params->has_zero_copy_send = true;
+ params->zero_copy_send = s->parameters.zero_copy_send;
+#endif
params->has_xbzrle_cache_size = true;
params->xbzrle_cache_size = s->parameters.xbzrle_cache_size;
params->has_max_postcopy_bandwidth = true;
@@ -1555,6 +1559,11 @@ static void migrate_params_test_apply(MigrateSetParameters *params,
if (params->has_multifd_compression) {
dest->multifd_compression = params->multifd_compression;
}
+#ifdef CONFIG_LINUX
+ if (params->has_zero_copy_send) {
+ dest->zero_copy_send = params->zero_copy_send;
+ }
+#endif
if (params->has_xbzrle_cache_size) {
dest->xbzrle_cache_size = params->xbzrle_cache_size;
}
@@ -1667,6 +1676,11 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
if (params->has_multifd_compression) {
s->parameters.multifd_compression = params->multifd_compression;
}
+#ifdef CONFIG_LINUX
+ if (params->has_zero_copy_send) {
+ s->parameters.zero_copy_send = params->zero_copy_send;
+ }
+#endif
if (params->has_xbzrle_cache_size) {
s->parameters.xbzrle_cache_size = params->xbzrle_cache_size;
xbzrle_cache_resize(params->xbzrle_cache_size, errp);
@@ -2557,6 +2571,17 @@ int migrate_multifd_zstd_level(void)
return s->parameters.multifd_zstd_level;
}
+#ifdef CONFIG_LINUX
+bool migrate_use_zero_copy_send(void)
+{
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->parameters.zero_copy_send;
+}
+#endif
+
int migrate_use_xbzrle(void)
{
MigrationState *s;
@@ -4200,6 +4225,10 @@ static Property migration_properties[] = {
DEFINE_PROP_UINT8("multifd-zstd-level", MigrationState,
parameters.multifd_zstd_level,
DEFAULT_MIGRATE_MULTIFD_ZSTD_LEVEL),
+#ifdef CONFIG_LINUX
+ DEFINE_PROP_BOOL("zero_copy_send", MigrationState,
+ parameters.zero_copy_send, false),
+#endif
DEFINE_PROP_SIZE("xbzrle-cache-size", MigrationState,
parameters.xbzrle_cache_size,
DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE),
@@ -4297,6 +4326,9 @@ static void migration_instance_init(Object *obj)
params->has_multifd_compression = true;
params->has_multifd_zlib_level = true;
params->has_multifd_zstd_level = true;
+#ifdef CONFIG_LINUX
+ params->has_zero_copy_send = true;
+#endif
params->has_xbzrle_cache_size = true;
params->has_max_postcopy_bandwidth = true;
params->has_max_cpu_throttle = true;
diff --git a/migration/migration.h b/migration/migration.h
index 2de861df01..5bcb7628ef 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -376,6 +376,11 @@ MultiFDCompression migrate_multifd_compression(void);
int migrate_multifd_zlib_level(void);
int migrate_multifd_zstd_level(void);
+#ifdef CONFIG_LINUX
+bool migrate_use_zero_copy_send(void);
+#else
+#define migrate_use_zero_copy_send() (false)
+#endif
int migrate_use_xbzrle(void);
uint64_t migrate_xbzrle_cache_size(void);
bool migrate_colo_enabled(void);
diff --git a/migration/socket.c b/migration/socket.c
index 05705a32d8..3754d8f72c 100644
--- a/migration/socket.c
+++ b/migration/socket.c
@@ -74,9 +74,16 @@ static void socket_outgoing_migration(QIOTask *task,
if (qio_task_propagate_error(task, &err)) {
trace_migration_socket_outgoing_error(error_get_pretty(err));
- } else {
- trace_migration_socket_outgoing_connected(data->hostname);
+ goto out;
}
+
+ trace_migration_socket_outgoing_connected(data->hostname);
+
+ if (migrate_use_zero_copy_send()) {
+ error_setg(&err, "Zero copy send not available in migration");
+ }
+
+out:
migration_channel_connect(data->s, sioc, data->hostname, err);
object_unref(OBJECT(sioc));
}
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index 634968498b..55b48d3733 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -1309,6 +1309,12 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
p->has_multifd_zstd_level = true;
visit_type_uint8(v, param, &p->multifd_zstd_level, &err);
break;
+#ifdef CONFIG_LINUX
+ case MIGRATION_PARAMETER_ZERO_COPY_SEND:
+ p->has_zero_copy_send = true;
+ visit_type_bool(v, param, &p->zero_copy_send, &err);
+ break;
+#endif
case MIGRATION_PARAMETER_XBZRLE_CACHE_SIZE:
p->has_xbzrle_cache_size = true;
if (!visit_type_size(v, param, &cache_size, &err)) {
diff --git a/qapi/migration.json b/qapi/migration.json
index 27d7b28158..4d833ecdd6 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -741,6 +741,13 @@
# will consume more CPU.
# Defaults to 1. (Since 5.0)
#
+# @zero-copy-send: Controls behavior on sending memory pages on migration.
+# When true, enables a zero-copy mechanism for sending
+# memory pages, if host supports it.
+# Requires that QEMU be permitted to use locked memory
+# for guest RAM pages.
+# Defaults to false. (Since 7.1)
+#
# @block-bitmap-mapping: Maps block nodes and bitmaps on them to
# aliases for the purpose of dirty bitmap migration. Such
# aliases may for example be the corresponding names on the
@@ -780,6 +787,7 @@
'xbzrle-cache-size', 'max-postcopy-bandwidth',
'max-cpu-throttle', 'multifd-compression',
'multifd-zlib-level' ,'multifd-zstd-level',
+ { 'name': 'zero-copy-send', 'if' : 'CONFIG_LINUX'},
'block-bitmap-mapping' ] }
##
@@ -906,6 +914,13 @@
# will consume more CPU.
# Defaults to 1. (Since 5.0)
#
+# @zero-copy-send: Controls behavior on sending memory pages on migration.
+# When true, enables a zero-copy mechanism for sending
+# memory pages, if host supports it.
+# Requires that QEMU be permitted to use locked memory
+# for guest RAM pages.
+# Defaults to false. (Since 7.1)
+#
# @block-bitmap-mapping: Maps block nodes and bitmaps on them to
# aliases for the purpose of dirty bitmap migration. Such
# aliases may for example be the corresponding names on the
@@ -960,6 +975,7 @@
'*multifd-compression': 'MultiFDCompression',
'*multifd-zlib-level': 'uint8',
'*multifd-zstd-level': 'uint8',
+ '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' },
'*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } }
##
@@ -1106,6 +1122,13 @@
# will consume more CPU.
# Defaults to 1. (Since 5.0)
#
+# @zero-copy-send: Controls behavior on sending memory pages on migration.
+# When true, enables a zero-copy mechanism for sending
+# memory pages, if host supports it.
+# Requires that QEMU be permitted to use locked memory
+# for guest RAM pages.
+# Defaults to false. (Since 7.1)
+#
# @block-bitmap-mapping: Maps block nodes and bitmaps on them to
# aliases for the purpose of dirty bitmap migration. Such
# aliases may for example be the corresponding names on the
@@ -1158,6 +1181,7 @@
'*multifd-compression': 'MultiFDCompression',
'*multifd-zlib-level': 'uint8',
'*multifd-zstd-level': 'uint8',
+ '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' },
'*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } }
##
--
2.35.3

98
kvm-migration-Allow-migrate-recover-to-run-multiple-time.patch
View File

@ -1,98 +0,0 @@
From fd6f516a94e635bc42e58448f314db575814a834 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Thu, 31 Mar 2022 11:08:45 -0400
Subject: [PATCH 18/18] migration: Allow migrate-recover to run multiple times
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 104: migration: Allow migrate-recover to run multiple times
RH-Commit: [1/1] afd726e54c069ae800e2d01f34e768d6bac7dcb9 (peterx/qemu-kvm)
RH-Bugzilla: 2096143
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Previously migration didn't have an easy way to cleanup the listening
transport, migrate recovery only allows to execute once. That's done with a
trick flag in postcopy_recover_triggered.
Now the facility is already there.
Drop postcopy_recover_triggered and instead allows a new migrate-recover to
release the previous listener transport.
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20220331150857.74406-8-peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 08401c0426bc1a5ce4609afd1cda5dd39abbf9fa)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
migration/migration.c | 13 ++-----------
migration/migration.h | 1 -
migration/savevm.c | 3 ---
3 files changed, 2 insertions(+), 15 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index 2a141bfaf3..8fb3eae910 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2166,11 +2166,8 @@ void qmp_migrate_recover(const char *uri, Error **errp)
return;
}
- if (qatomic_cmpxchg(&mis->postcopy_recover_triggered,
- false, true) == true) {
- error_setg(errp, "Migrate recovery is triggered already");
- return;
- }
+ /* If there's an existing transport, release it */
+ migration_incoming_transport_cleanup(mis);
/*
* Note that this call will never start a real migration; it will
@@ -2178,12 +2175,6 @@ void qmp_migrate_recover(const char *uri, Error **errp)
* to continue using that newly established channel.
*/
qemu_start_incoming_migration(uri, errp);
-
- /* Safe to dereference with the assert above */
- if (*errp) {
- /* Reset the flag so user could still retry */
- qatomic_set(&mis->postcopy_recover_triggered, false);
- }
}
void qmp_migrate_pause(Error **errp)
diff --git a/migration/migration.h b/migration/migration.h
index c2cabb8a14..fbc8690ec8 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -139,7 +139,6 @@ struct MigrationIncomingState {
struct PostcopyBlocktimeContext *blocktime_ctx;
/* notify PAUSED postcopy incoming migrations to try to continue */
- bool postcopy_recover_triggered;
QemuSemaphore postcopy_pause_sem_dst;
QemuSemaphore postcopy_pause_sem_fault;
diff --git a/migration/savevm.c b/migration/savevm.c
index 02ed94c180..d9076897b8 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2589,9 +2589,6 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis)
assert(migrate_postcopy_ram());
- /* Clear the triggered bit to allow one recovery */
- mis->postcopy_recover_triggered = false;
-
/*
* Unregister yank with either from/to src would work, since ioc behind it
* is the same
--
2.35.3

93
kvm-migration-Avoid-false-positive-on-non-supported-scen.patch
View File

@ -1,93 +0,0 @@
From 0753565af588dfa78b3529e359b1590e15fcbdb3 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Tue, 19 Jul 2022 09:23:45 -0300
Subject: [PATCH 04/11] migration: Avoid false-positive on non-supported
scenarios for zero-copy-send
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [4/6] f5c7ed6710d92668acb81d0118a71fab0b4e3d43 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Migration with zero-copy-send currently has it's limitations, as it can't
be used with TLS nor any kind of compression. In such scenarios, it should
output errors during parameter / capability setting.
But currently there are some ways of setting this not-supported scenarios
without printing the error message:
!) For 'compression' capability, it works by enabling it together with
zero-copy-send. This happens because the validity test for zero-copy uses
the helper unction migrate_use_compression(), which check for compression
presence in s->enabled_capabilities[MIGRATION_CAPABILITY_COMPRESS].
The point here is: the validity test happens before the capability gets
enabled. If all of them get enabled together, this test will not return
error.
In order to fix that, replace migrate_use_compression() by directly testing
the cap_list parameter migrate_caps_check().
2) For features enabled by parameters such as TLS & 'multifd_compression',
there was also a possibility of setting non-supported scenarios: setting
zero-copy-send first, then setting the unsupported parameter.
In order to fix that, also add a check for parameters conflicting with
zero-copy-send on migrate_params_check().
3) XBZRLE is also a compression capability, so it makes sense to also add
it to the list of capabilities which are not supported with zero-copy-send.
Fixes: 1abaec9a1b2c ("migration: Change zero_copy_send from migration parameter to migration capability")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Message-Id: <20220719122345.253713-1-leobras@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 90eb69e4f1a16b388d0483543bf6bfc69a9966e4)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/migration/migration.c b/migration/migration.c
index 3a3a7a4a50..343629d59c 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1265,7 +1265,9 @@ static bool migrate_caps_check(bool *cap_list,
#ifdef CONFIG_LINUX
if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND] &&
(!cap_list[MIGRATION_CAPABILITY_MULTIFD] ||
- migrate_use_compression() ||
+ cap_list[MIGRATION_CAPABILITY_COMPRESS] ||
+ cap_list[MIGRATION_CAPABILITY_XBZRLE] ||
+ migrate_multifd_compression() ||
migrate_use_tls())) {
error_setg(errp,
"Zero copy only available for non-compressed non-TLS multifd migration");
@@ -1502,6 +1504,17 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp)
error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: ");
return false;
}
+
+#ifdef CONFIG_LINUX
+ if (migrate_use_zero_copy_send() &&
+ ((params->has_multifd_compression && params->multifd_compression) ||
+ (params->has_tls_creds && params->tls_creds && *params->tls_creds))) {
+ error_setg(errp,
+ "Zero copy only available for non-compressed non-TLS multifd migration");
+ return false;
+ }
+#endif
+
return true;
}
--
2.31.1

289
kvm-migration-Change-zero_copy_send-from-migration-param.patch
View File

@ -1,289 +0,0 @@
From 7e2a037f3f349c21201152cecce32d8c8ff0bea0 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 20 Jun 2022 02:39:45 -0300
Subject: [PATCH 17/18] migration: Change zero_copy_send from migration
parameter to migration capability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [11/11] e4a955607947896a49398ac8400241a0adac51a1 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
When originally implemented, zero_copy_send was designed as a Migration
paramenter.
But taking into account how is that supposed to work, and how
the difference between a capability and a parameter, it only makes sense
that zero-copy-send would work better as a capability.
Taking into account how recently the change got merged, it was decided
that it's still time to make it right, and convert zero_copy_send into
a Migration capability.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
dgilbert: always define the capability, even on non-Linux but error if
set; avoids build problems with the capability
(cherry picked from commit 1abaec9a1b2c23f7aa94709a422128d9e42c3e0b)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 58 +++++++++++++++++++------------------------
monitor/hmp-cmds.c | 6 -----
qapi/migration.json | 33 +++++++-----------------
3 files changed, 34 insertions(+), 63 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index 102236fba0..2a141bfaf3 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -163,7 +163,8 @@ INITIALIZE_MIGRATE_CAPS_SET(check_caps_background_snapshot,
MIGRATION_CAPABILITY_COMPRESS,
MIGRATION_CAPABILITY_XBZRLE,
MIGRATION_CAPABILITY_X_COLO,
- MIGRATION_CAPABILITY_VALIDATE_UUID);
+ MIGRATION_CAPABILITY_VALIDATE_UUID,
+ MIGRATION_CAPABILITY_ZERO_COPY_SEND);
/* When we add fault tolerance, we could have several
migrations at once. For now we don't need to add
@@ -899,10 +900,6 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
params->multifd_zlib_level = s->parameters.multifd_zlib_level;
params->has_multifd_zstd_level = true;
params->multifd_zstd_level = s->parameters.multifd_zstd_level;
-#ifdef CONFIG_LINUX
- params->has_zero_copy_send = true;
- params->zero_copy_send = s->parameters.zero_copy_send;
-#endif
params->has_xbzrle_cache_size = true;
params->xbzrle_cache_size = s->parameters.xbzrle_cache_size;
params->has_max_postcopy_bandwidth = true;
@@ -1263,6 +1260,24 @@ static bool migrate_caps_check(bool *cap_list,
}
}
+#ifdef CONFIG_LINUX
+ if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND] &&
+ (!cap_list[MIGRATION_CAPABILITY_MULTIFD] ||
+ migrate_use_compression() ||
+ migrate_use_tls())) {
+ error_setg(errp,
+ "Zero copy only available for non-compressed non-TLS multifd migration");
+ return false;
+ }
+#else
+ if (cap_list[MIGRATION_CAPABILITY_ZERO_COPY_SEND]) {
+ error_setg(errp,
+ "Zero copy currently only available on Linux");
+ return false;
+ }
+#endif
+
+
/* incoming side only */
if (runstate_check(RUN_STATE_INMIGRATE) &&
!migrate_multifd_is_allowed() &&
@@ -1485,16 +1500,6 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp)
error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: ");
return false;
}
-#ifdef CONFIG_LINUX
- if (params->zero_copy_send &&
- (!migrate_use_multifd() ||
- params->multifd_compression != MULTIFD_COMPRESSION_NONE ||
- (params->tls_creds && *params->tls_creds))) {
- error_setg(errp,
- "Zero copy only available for non-compressed non-TLS multifd migration");
- return false;
- }
-#endif
return true;
}
@@ -1568,11 +1573,6 @@ static void migrate_params_test_apply(MigrateSetParameters *params,
if (params->has_multifd_compression) {
dest->multifd_compression = params->multifd_compression;
}
-#ifdef CONFIG_LINUX
- if (params->has_zero_copy_send) {
- dest->zero_copy_send = params->zero_copy_send;
- }
-#endif
if (params->has_xbzrle_cache_size) {
dest->xbzrle_cache_size = params->xbzrle_cache_size;
}
@@ -1685,11 +1685,6 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
if (params->has_multifd_compression) {
s->parameters.multifd_compression = params->multifd_compression;
}
-#ifdef CONFIG_LINUX
- if (params->has_zero_copy_send) {
- s->parameters.zero_copy_send = params->zero_copy_send;
- }
-#endif
if (params->has_xbzrle_cache_size) {
s->parameters.xbzrle_cache_size = params->xbzrle_cache_size;
xbzrle_cache_resize(params->xbzrle_cache_size, errp);
@@ -2587,7 +2582,7 @@ bool migrate_use_zero_copy_send(void)
s = migrate_get_current();
- return s->parameters.zero_copy_send;
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_COPY_SEND];
}
#endif
@@ -4243,10 +4238,6 @@ static Property migration_properties[] = {
DEFINE_PROP_UINT8("multifd-zstd-level", MigrationState,
parameters.multifd_zstd_level,
DEFAULT_MIGRATE_MULTIFD_ZSTD_LEVEL),
-#ifdef CONFIG_LINUX
- DEFINE_PROP_BOOL("zero_copy_send", MigrationState,
- parameters.zero_copy_send, false),
-#endif
DEFINE_PROP_SIZE("xbzrle-cache-size", MigrationState,
parameters.xbzrle_cache_size,
DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE),
@@ -4284,6 +4275,10 @@ static Property migration_properties[] = {
DEFINE_PROP_MIG_CAP("x-multifd", MIGRATION_CAPABILITY_MULTIFD),
DEFINE_PROP_MIG_CAP("x-background-snapshot",
MIGRATION_CAPABILITY_BACKGROUND_SNAPSHOT),
+#ifdef CONFIG_LINUX
+ DEFINE_PROP_MIG_CAP("x-zero-copy-send",
+ MIGRATION_CAPABILITY_ZERO_COPY_SEND),
+#endif
DEFINE_PROP_END_OF_LIST(),
};
@@ -4344,9 +4339,6 @@ static void migration_instance_init(Object *obj)
params->has_multifd_compression = true;
params->has_multifd_zlib_level = true;
params->has_multifd_zstd_level = true;
-#ifdef CONFIG_LINUX
- params->has_zero_copy_send = true;
-#endif
params->has_xbzrle_cache_size = true;
params->has_max_postcopy_bandwidth = true;
params->has_max_cpu_throttle = true;
diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c
index 55b48d3733..634968498b 100644
--- a/monitor/hmp-cmds.c
+++ b/monitor/hmp-cmds.c
@@ -1309,12 +1309,6 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
p->has_multifd_zstd_level = true;
visit_type_uint8(v, param, &p->multifd_zstd_level, &err);
break;
-#ifdef CONFIG_LINUX
- case MIGRATION_PARAMETER_ZERO_COPY_SEND:
- p->has_zero_copy_send = true;
- visit_type_bool(v, param, &p->zero_copy_send, &err);
- break;
-#endif
case MIGRATION_PARAMETER_XBZRLE_CACHE_SIZE:
p->has_xbzrle_cache_size = true;
if (!visit_type_size(v, param, &cache_size, &err)) {
diff --git a/qapi/migration.json b/qapi/migration.json
index 4d833ecdd6..5105790cd0 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -463,6 +463,13 @@
# procedure starts. The VM RAM is saved with running VM.
# (since 6.0)
#
+# @zero-copy-send: Controls behavior on sending memory pages on migration.
+# When true, enables a zero-copy mechanism for sending
+# memory pages, if host supports it.
+# Requires that QEMU be permitted to use locked memory
+# for guest RAM pages.
+# (since 7.1)
+#
# Features:
# @unstable: Members @x-colo and @x-ignore-shared are experimental.
#
@@ -476,7 +483,8 @@
'block', 'return-path', 'pause-before-switchover', 'multifd',
'dirty-bitmaps', 'postcopy-blocktime', 'late-block-activate',
{ 'name': 'x-ignore-shared', 'features': [ 'unstable' ] },
- 'validate-uuid', 'background-snapshot'] }
+ 'validate-uuid', 'background-snapshot',
+ 'zero-copy-send'] }
##
# @MigrationCapabilityStatus:
@@ -741,12 +749,6 @@
# will consume more CPU.
# Defaults to 1. (Since 5.0)
#
-# @zero-copy-send: Controls behavior on sending memory pages on migration.
-# When true, enables a zero-copy mechanism for sending
-# memory pages, if host supports it.
-# Requires that QEMU be permitted to use locked memory
-# for guest RAM pages.
-# Defaults to false. (Since 7.1)
#
# @block-bitmap-mapping: Maps block nodes and bitmaps on them to
# aliases for the purpose of dirty bitmap migration. Such
@@ -787,7 +789,6 @@
'xbzrle-cache-size', 'max-postcopy-bandwidth',
'max-cpu-throttle', 'multifd-compression',
'multifd-zlib-level' ,'multifd-zstd-level',
- { 'name': 'zero-copy-send', 'if' : 'CONFIG_LINUX'},
'block-bitmap-mapping' ] }
##
@@ -914,13 +915,6 @@
# will consume more CPU.
# Defaults to 1. (Since 5.0)
#
-# @zero-copy-send: Controls behavior on sending memory pages on migration.
-# When true, enables a zero-copy mechanism for sending
-# memory pages, if host supports it.
-# Requires that QEMU be permitted to use locked memory
-# for guest RAM pages.
-# Defaults to false. (Since 7.1)
-#
# @block-bitmap-mapping: Maps block nodes and bitmaps on them to
# aliases for the purpose of dirty bitmap migration. Such
# aliases may for example be the corresponding names on the
@@ -975,7 +969,6 @@
'*multifd-compression': 'MultiFDCompression',
'*multifd-zlib-level': 'uint8',
'*multifd-zstd-level': 'uint8',
- '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' },
'*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } }
##
@@ -1122,13 +1115,6 @@
# will consume more CPU.
# Defaults to 1. (Since 5.0)
#
-# @zero-copy-send: Controls behavior on sending memory pages on migration.
-# When true, enables a zero-copy mechanism for sending
-# memory pages, if host supports it.
-# Requires that QEMU be permitted to use locked memory
-# for guest RAM pages.
-# Defaults to false. (Since 7.1)
-#
# @block-bitmap-mapping: Maps block nodes and bitmaps on them to
# aliases for the purpose of dirty bitmap migration. Such
# aliases may for example be the corresponding names on the
@@ -1181,7 +1167,6 @@
'*multifd-compression': 'MultiFDCompression',
'*multifd-zlib-level': 'uint8',
'*multifd-zstd-level': 'uint8',
- '*zero-copy-send': { 'type': 'bool', 'if': 'CONFIG_LINUX' },
'*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } }
##
--
2.35.3

47
kvm-migration-Fix-operator-type.patch
View File

@ -1,47 +0,0 @@
From 4bd48e784ae0c38c89f1a944b06c997fd28c4d37 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Thu, 19 May 2022 04:15:33 -0400
Subject: [PATCH 16/16] migration: Fix operator type
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Miroslav Rezanina <mrezanin@redhat.com>
RH-MergeRequest: 92: Fix build using clang 14
RH-Commit: [1/1] ad9980e64cf2e39085d68f1ff601444bf2afe228 (mrezanin/centos-src-qemu-kvm)
RH-Bugzilla: 2064530
RH-Acked-by: Daniel P. Berrangé <berrange@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Clang spotted an & that should have been an &&; fix it.
Reported by: David Binderman / https://gitlab.com/dcb
Fixes: 65dacaa04fa ("migration: introduce save_normal_page()")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/963
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20220406102515.96320-1-dgilbert@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit f912ec5b2d65644116ff496b58d7c9145c19e4c0)
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
migration/ram.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/migration/ram.c b/migration/ram.c
index 3532f64ecb..0ef4bd63eb 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1289,7 +1289,7 @@ static int save_normal_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
offset | RAM_SAVE_FLAG_PAGE));
if (async) {
qemu_put_buffer_async(rs->f, buf, TARGET_PAGE_SIZE,
- migrate_release_ram() &
+ migrate_release_ram() &&
migration_in_postcopy());
} else {
qemu_put_buffer(rs->f, buf, TARGET_PAGE_SIZE);
--
2.31.1

62
kvm-migration-add-remaining-params-has_-true-in-migratio.patch
View File

@ -1,62 +0,0 @@
From 9698c0e8dd9b4f5dbc237a3f98ac46297dac85fb Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 25 Jul 2022 22:02:35 -0300
Subject: [PATCH 05/11] migration: add remaining params->has_* = true in
migration_instance_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [5/6] 50bbad254e2356b3ae16f6e00a3db8fd0b22dde9 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Some of params->has_* = true are missing in migration_instance_init, this
causes migrate_params_check() to skip some tests, allowing some
unsupported scenarios.
Fix this by adding all missing params->has_* = true in
migration_instance_init().
Fixes: 69ef1f36b0 ("migration: define 'tls-creds' and 'tls-hostname' migration parameters")
Fixes: 1d58872a91 ("migration: do not wait for free thread")
Fixes: d2f1d29b95 ("migration: add support for a "tls-authz" migration parameter")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Message-Id: <20220726010235.342927-1-leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit df67aa3e61e2c83459da7d815962d9706f1528fc)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/migration/migration.c b/migration/migration.c
index 343629d59c..5e78028df4 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -4332,6 +4332,7 @@ static void migration_instance_init(Object *obj)
/* Set has_* up only for parameter checks */
params->has_compress_level = true;
params->has_compress_threads = true;
+ params->has_compress_wait_thread = true;
params->has_decompress_threads = true;
params->has_throttle_trigger_threshold = true;
params->has_cpu_throttle_initial = true;
@@ -4352,6 +4353,9 @@ static void migration_instance_init(Object *obj)
params->has_announce_max = true;
params->has_announce_rounds = true;
params->has_announce_step = true;
+ params->has_tls_creds = true;
+ params->has_tls_hostname = true;
+ params->has_tls_authz = true;
qemu_sem_init(&ms->postcopy_pause_sem, 0);
qemu_sem_init(&ms->postcopy_pause_rp_sem, 0);
--
2.31.1

83
kvm-migration-multifd-Report-to-user-when-zerocopy-not-w.patch
View File

@ -1,83 +0,0 @@
From 78bbe28d5f5691330239041448cccfb339eed779 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 11 Jul 2022 18:11:13 -0300
Subject: [PATCH 03/11] migration/multifd: Report to user when zerocopy not
working
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 111: zero-copy-send fixes & improvements
RH-Commit: [3/6] 4f9165325b3cb8ff16d8b3b7649ff780fae0e2ad (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 2107466
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Some errors, like the lack of Scatter-Gather support by the network
interface(NETIF_F_SG) may cause sendmsg(...,MSG_ZEROCOPY) to fail on using
zero-copy, which causes it to fall back to the default copying mechanism.
After each full dirty-bitmap scan there should be a zero-copy flush
happening, which checks for errors each of the previous calls to
sendmsg(...,MSG_ZEROCOPY). If all of them failed to use zero-copy, then
increment dirty_sync_missed_zero_copy migration stat to let the user know
about it.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Message-Id: <20220711211112.18951-4-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit d59c40cc483729f2e67c80e58df769ad19976fe9)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/multifd.c | 2 ++
migration/ram.c | 5 +++++
migration/ram.h | 2 ++
3 files changed, 9 insertions(+)
diff --git a/migration/multifd.c b/migration/multifd.c
index 0b5b41c53f..96e5f0a058 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -626,6 +626,8 @@ int multifd_send_sync_main(QEMUFile *f)
if (ret < 0) {
error_report_err(err);
return -1;
+ } else if (ret == 1) {
+ dirty_sync_missed_zero_copy();
}
}
}
diff --git a/migration/ram.c b/migration/ram.c
index ee40e4a718..c437ff1b1f 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -406,6 +406,11 @@ static void ram_transferred_add(uint64_t bytes)
ram_counters.transferred += bytes;
}
+void dirty_sync_missed_zero_copy(void)
+{
+ ram_counters.dirty_sync_missed_zero_copy++;
+}
+
/* used by the search for pages to send */
struct PageSearchStatus {
/* Current block being searched */
diff --git a/migration/ram.h b/migration/ram.h
index 2c6dc3675d..34adf5cb92 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -86,4 +86,6 @@ void ram_write_tracking_prepare(void);
int ram_write_tracking_start(void);
void ram_write_tracking_stop(void);
+void dirty_sync_missed_zero_copy(void);
+
#endif
--
2.31.1

142
kvm-multifd-Copy-pages-before-compressing-them-with-zlib.patch
View File

@ -1,142 +0,0 @@
From 1d280070748b604c60a7be4d4c3c3a28e3964f37 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Tue, 2 Aug 2022 10:11:21 +0200
Subject: [PATCH 31/32] multifd: Copy pages before compressing them with zlib
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 112: Fix postcopy migration on s390x
RH-Commit: [1/2] fd5a0221e22b4563bd1cb7f8a8b95f0bfe8f5fc9 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2099934
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2099934
zlib_send_prepare() compresses pages of a running VM. zlib does not
make any thread-safety guarantees with respect to changing deflate()
input concurrently with deflate() [1].
One can observe problems due to this with the IBM zEnterprise Data
Compression accelerator capable zlib [2]. When the hardware
acceleration is enabled, migration/multifd/tcp/plain/zlib test fails
intermittently [3] due to sliding window corruption. The accelerator's
architecture explicitly discourages concurrent accesses [4]:
Page 26-57, "Other Conditions":
As observed by this CPU, other CPUs, and channel
programs, references to the parameter block, first,
second, and third operands may be multiple-access
references, accesses to these storage locations are
not necessarily block-concurrent, and the sequence
of these accesses or references is undefined.
Mark Adler pointed out that vanilla zlib performs double fetches under
certain circumstances as well [5], therefore we need to copy data
before passing it to deflate().
[1] https://zlib.net/manual.html
[2] https://github.com/madler/zlib/pull/410
[3] https://lists.nongnu.org/archive/html/qemu-devel/2022-03/msg03988.html
[4] http://publibfp.dhe.ibm.com/epubs/pdf/a227832c.pdf
[5] https://lists.gnu.org/archive/html/qemu-devel/2022-07/msg00889.html
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-Id: <20220705203559.2960949-1-iii@linux.ibm.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 007e179ef0e97eafda4c9ff2a9d665a1947c7c6d)
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
migration/multifd-zlib.c | 38 ++++++++++++++++++++++++++++++--------
1 file changed, 30 insertions(+), 8 deletions(-)
diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c
index 3a7ae44485..18213a9513 100644
--- a/migration/multifd-zlib.c
+++ b/migration/multifd-zlib.c
@@ -27,6 +27,8 @@ struct zlib_data {
uint8_t *zbuff;
/* size of compressed buffer */
uint32_t zbuff_len;
+ /* uncompressed buffer of size qemu_target_page_size() */
+ uint8_t *buf;
};
/* Multifd zlib compression */
@@ -45,26 +47,38 @@ static int zlib_send_setup(MultiFDSendParams *p, Error **errp)
{
struct zlib_data *z = g_new0(struct zlib_data, 1);
z_stream *zs = &z->zs;
+ const char *err_msg;
zs->zalloc = Z_NULL;
zs->zfree = Z_NULL;
zs->opaque = Z_NULL;
if (deflateInit(zs, migrate_multifd_zlib_level()) != Z_OK) {
- g_free(z);
- error_setg(errp, "multifd %u: deflate init failed", p->id);
- return -1;
+ err_msg = "deflate init failed";
+ goto err_free_z;
}
/* This is the maxium size of the compressed buffer */
z->zbuff_len = compressBound(MULTIFD_PACKET_SIZE);
z->zbuff = g_try_malloc(z->zbuff_len);
if (!z->zbuff) {
- deflateEnd(&z->zs);
- g_free(z);
- error_setg(errp, "multifd %u: out of memory for zbuff", p->id);
- return -1;
+ err_msg = "out of memory for zbuff";
+ goto err_deflate_end;
+ }
+ z->buf = g_try_malloc(qemu_target_page_size());
+ if (!z->buf) {
+ err_msg = "out of memory for buf";
+ goto err_free_zbuff;
}
p->data = z;
return 0;
+
+err_free_zbuff:
+ g_free(z->zbuff);
+err_deflate_end:
+ deflateEnd(&z->zs);
+err_free_z:
+ g_free(z);
+ error_setg(errp, "multifd %u: %s", p->id, err_msg);
+ return -1;
}
/**
@@ -82,6 +96,8 @@ static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp)
deflateEnd(&z->zs);
g_free(z->zbuff);
z->zbuff = NULL;
+ g_free(z->buf);
+ z->buf = NULL;
g_free(p->data);
p->data = NULL;
}
@@ -114,8 +130,14 @@ static int zlib_send_prepare(MultiFDSendParams *p, Error **errp)
flush = Z_SYNC_FLUSH;
}
+ /*
+ * Since the VM might be running, the page may be changing concurrently
+ * with compression. zlib does not guarantee that this is safe,
+ * therefore copy the page before calling deflate().
+ */
+ memcpy(z->buf, p->pages->block->host + p->normal[i], page_size);
zs->avail_in = page_size;
- zs->next_in = p->pages->block->host + p->normal[i];
+ zs->next_in = z->buf;
zs->avail_out = available;
zs->next_out = z->zbuff + out_size;
--
2.31.1

182
kvm-multifd-Implement-zero-copy-write-in-multifd-migrati.patch
View File

@ -1,182 +0,0 @@
From c1a2866d158ac67179fa0d17f1710302eb9a3866 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:37 -0300
Subject: [PATCH 14/18] multifd: Implement zero copy write in multifd migration
(multifd-zero-copy)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [8/11] b93009cc94b2cc4b464b4f68ebfb37b870dd6f7d (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Implement zero copy send on nocomp_send_write(), by making use of QIOChannel
writev + flags & flush interface.
Change multifd_send_sync_main() so flush_zero_copy() can be called
after each iteration in order to make sure all dirty pages are sent before
a new iteration is started. It will also flush at the beginning and at the
end of migration.
Also make it return -1 if flush_zero_copy() fails, in order to cancel
the migration process, and avoid resuming the guest in the target host
without receiving all current RAM.
This will work fine on RAM migration because the RAM pages are not usually freed,
and there is no problem on changing the pages content between writev_zero_copy() and
the actual sending of the buffer, because this change will dirty the page and
cause it to be re-sent on a next iteration anyway.
A lot of locked memory may be needed in order to use multifd migration
with zero-copy enabled, so disabling the feature should be necessary for
low-privileged users trying to perform multifd migrations.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20220513062836.965425-9-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 5b1d9bab2da4fca3a3caee97c430e5709cb32b7b)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/migration.c | 11 ++++++++++-
migration/multifd.c | 37 +++++++++++++++++++++++++++++++++++--
migration/multifd.h | 2 ++
migration/socket.c | 5 +++--
4 files changed, 50 insertions(+), 5 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index d91efb66fe..102236fba0 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1485,7 +1485,16 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp)
error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: ");
return false;
}
-
+#ifdef CONFIG_LINUX
+ if (params->zero_copy_send &&
+ (!migrate_use_multifd() ||
+ params->multifd_compression != MULTIFD_COMPRESSION_NONE ||
+ (params->tls_creds && *params->tls_creds))) {
+ error_setg(errp,
+ "Zero copy only available for non-compressed non-TLS multifd migration");
+ return false;
+ }
+#endif
return true;
}
diff --git a/migration/multifd.c b/migration/multifd.c
index 8fca6c970e..0b5b41c53f 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -571,6 +571,7 @@ void multifd_save_cleanup(void)
int multifd_send_sync_main(QEMUFile *f)
{
int i;
+ bool flush_zero_copy;
if (!migrate_use_multifd()) {
return 0;
@@ -581,6 +582,20 @@ int multifd_send_sync_main(QEMUFile *f)
return -1;
}
}
+
+ /*
+ * When using zero-copy, it's necessary to flush the pages before any of
+ * the pages can be sent again, so we'll make sure the new version of the
+ * pages will always arrive _later_ than the old pages.
+ *
+ * Currently we achieve this by flushing the zero-page requested writes
+ * per ram iteration, but in the future we could potentially optimize it
+ * to be less frequent, e.g. only after we finished one whole scanning of
+ * all the dirty bitmaps.
+ */
+
+ flush_zero_copy = migrate_use_zero_copy_send();
+
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
@@ -602,6 +617,17 @@ int multifd_send_sync_main(QEMUFile *f)
ram_counters.transferred += p->packet_len;
qemu_mutex_unlock(&p->mutex);
qemu_sem_post(&p->sem);
+
+ if (flush_zero_copy && p->c) {
+ int ret;
+ Error *err = NULL;
+
+ ret = qio_channel_flush(p->c, &err);
+ if (ret < 0) {
+ error_report_err(err);
+ return -1;
+ }
+ }
}
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
@@ -686,8 +712,8 @@ static void *multifd_send_thread(void *opaque)
p->iov[0].iov_base = p->packet;
}
- ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num,
- &local_err);
+ ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL,
+ 0, p->write_flags, &local_err);
if (ret != 0) {
break;
}
@@ -928,6 +954,13 @@ int multifd_save_setup(Error **errp)
/* We need one extra place for the packet header */
p->iov = g_new0(struct iovec, page_count + 1);
p->normal = g_new0(ram_addr_t, page_count);
+
+ if (migrate_use_zero_copy_send()) {
+ p->write_flags = QIO_CHANNEL_WRITE_FLAG_ZERO_COPY;
+ } else {
+ p->write_flags = 0;
+ }
+
socket_send_channel_create(multifd_new_send_channel_async, p);
}
diff --git a/migration/multifd.h b/migration/multifd.h
index cd495195ce..7ec688fb4f 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -96,6 +96,8 @@ typedef struct {
uint32_t packet_len;
/* pointer to the packet */
MultiFDPacket_t *packet;
+ /* multifd flags for sending ram */
+ int write_flags;
/* multifd flags for each packet */
uint32_t flags;
/* size of the next packet that contains pages */
diff --git a/migration/socket.c b/migration/socket.c
index 3754d8f72c..4fd5e85f50 100644
--- a/migration/socket.c
+++ b/migration/socket.c
@@ -79,8 +79,9 @@ static void socket_outgoing_migration(QIOTask *task,
trace_migration_socket_outgoing_connected(data->hostname);
- if (migrate_use_zero_copy_send()) {
- error_setg(&err, "Zero copy send not available in migration");
+ if (migrate_use_zero_copy_send() &&
+ !qio_channel_has_feature(sioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
+ error_setg(&err, "Zero copy send feature not detected in host kernel");
}
out:
--
2.35.3

102
kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch
View File

@ -1,102 +0,0 @@
From 63255c13492f42a3236d96e706e5f8e70bb4e219 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:36 -0300
Subject: [PATCH 13/18] multifd: Send header packet without flags if
zero-copy-send is enabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [7/11] 137eea685e387d3d6aff187ec3fcac05bc16b6e3 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Since d48c3a0445 ("multifd: Use a single writev on the send side"),
sending the header packet and the memory pages happens in the same
writev, which can potentially make the migration faster.
Using channel-socket as example, this works well with the default copying
mechanism of sendmsg(), but with zero-copy-send=true, it will cause
the migration to often break.
This happens because the header packet buffer gets reused quite often,
and there is a high chance that by the time the MSG_ZEROCOPY mechanism get
to send the buffer, it has already changed, sending the wrong data and
causing the migration to abort.
It means that, as it is, the buffer for the header packet is not suitable
for sending with MSG_ZEROCOPY.
In order to enable zero copy for multifd, send the header packet on an
individual write(), without any flags, and the remanining pages with a
writev(), as it was happening before. This only changes how a migration
with zero-copy-send=true works, not changing any current behavior for
migrations with zero-copy-send=false.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20220513062836.965425-8-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit b7dbdd8e76cd03453c234dbb9578d20969859d74)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/multifd.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/migration/multifd.c b/migration/multifd.c
index cdb57439a7..8fca6c970e 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -619,6 +619,7 @@ static void *multifd_send_thread(void *opaque)
MultiFDSendParams *p = opaque;
Error *local_err = NULL;
int ret = 0;
+ bool use_zero_copy_send = migrate_use_zero_copy_send();
trace_multifd_send_thread_start(p->id);
rcu_register_thread();
@@ -641,9 +642,14 @@ static void *multifd_send_thread(void *opaque)
if (p->pending_job) {
uint64_t packet_num = p->packet_num;
uint32_t flags = p->flags;
- p->iovs_num = 1;
p->normal_num = 0;
+ if (use_zero_copy_send) {
+ p->iovs_num = 0;
+ } else {
+ p->iovs_num = 1;
+ }
+
for (int i = 0; i < p->pages->num; i++) {
p->normal[p->normal_num] = p->pages->offset[i];
p->normal_num++;
@@ -667,8 +673,18 @@ static void *multifd_send_thread(void *opaque)
trace_multifd_send(p->id, packet_num, p->normal_num, flags,
p->next_packet_size);
- p->iov[0].iov_len = p->packet_len;
- p->iov[0].iov_base = p->packet;
+ if (use_zero_copy_send) {
+ /* Send header first, without zerocopy */
+ ret = qio_channel_write_all(p->c, (void *)p->packet,
+ p->packet_len, &local_err);
+ if (ret != 0) {
+ break;
+ }
+ } else {
+ /* Send header using the same writev call */
+ p->iov[0].iov_len = p->packet_len;
+ p->iov[0].iov_base = p->packet;
+ }
ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num,
&local_err);
--
2.35.3

163
kvm-multifd-multifd_send_sync_main-now-returns-negative-.patch
View File

@ -1,163 +0,0 @@
From 4ca5375a936bc87829c6e2b4620f56c73a5efc70 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:35 -0300
Subject: [PATCH 12/18] multifd: multifd_send_sync_main now returns negative on
error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [6/11] c8ebdee4327d463c74f4b2eeb42d3c964f314c94 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
Even though multifd_send_sync_main() currently emits error_reports, it's
callers don't really check it before continuing.
Change multifd_send_sync_main() to return -1 on error and 0 on success.
Also change all it's callers to make use of this change and possibly fail
earlier.
(This change is important to next patch on multifd zero copy
implementation, to make it sure an error in zero-copy flush does not go
unnoticed.
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Message-Id: <20220513062836.965425-7-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 33d70973a3a6e8c6b62bcbc64d9e488961981007)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
migration/multifd.c | 10 ++++++----
migration/multifd.h | 2 +-
migration/ram.c | 29 ++++++++++++++++++++++-------
3 files changed, 29 insertions(+), 12 deletions(-)
diff --git a/migration/multifd.c b/migration/multifd.c
index 43998ad117..cdb57439a7 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -568,17 +568,17 @@ void multifd_save_cleanup(void)
multifd_send_state = NULL;
}
-void multifd_send_sync_main(QEMUFile *f)
+int multifd_send_sync_main(QEMUFile *f)
{
int i;
if (!migrate_use_multifd()) {
- return;
+ return 0;
}
if (multifd_send_state->pages->num) {
if (multifd_send_pages(f) < 0) {
error_report("%s: multifd_send_pages fail", __func__);
- return;
+ return -1;
}
}
for (i = 0; i < migrate_multifd_channels(); i++) {
@@ -591,7 +591,7 @@ void multifd_send_sync_main(QEMUFile *f)
if (p->quit) {
error_report("%s: channel %d has already quit", __func__, i);
qemu_mutex_unlock(&p->mutex);
- return;
+ return -1;
}
p->packet_num = multifd_send_state->packet_num++;
@@ -610,6 +610,8 @@ void multifd_send_sync_main(QEMUFile *f)
qemu_sem_wait(&p->sem_sync);
}
trace_multifd_send_sync_main(multifd_send_state->packet_num);
+
+ return 0;
}
static void *multifd_send_thread(void *opaque)
diff --git a/migration/multifd.h b/migration/multifd.h
index 4dda900a0b..cd495195ce 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -22,7 +22,7 @@ int multifd_load_cleanup(Error **errp);
bool multifd_recv_all_channels_created(void);
bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
void multifd_recv_sync_main(void);
-void multifd_send_sync_main(QEMUFile *f);
+int multifd_send_sync_main(QEMUFile *f);
int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
/* Multifd Compression flags */
diff --git a/migration/ram.c b/migration/ram.c
index 0ef4bd63eb..fb6db54642 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2903,6 +2903,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
{
RAMState **rsp = opaque;
RAMBlock *block;
+ int ret;
if (compress_threads_save_setup()) {
return -1;
@@ -2937,7 +2938,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
ram_control_before_iterate(f, RAM_CONTROL_SETUP);
ram_control_after_iterate(f, RAM_CONTROL_SETUP);
- multifd_send_sync_main(f);
+ ret = multifd_send_sync_main(f);
+ if (ret < 0) {
+ return ret;
+ }
+
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
qemu_fflush(f);
@@ -3046,7 +3051,11 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
out:
if (ret >= 0
&& migration_is_setup_or_active(migrate_get_current()->state)) {
- multifd_send_sync_main(rs->f);
+ ret = multifd_send_sync_main(rs->f);
+ if (ret < 0) {
+ return ret;
+ }
+
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
qemu_fflush(f);
ram_transferred_add(8);
@@ -3106,13 +3115,19 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
ram_control_after_iterate(f, RAM_CONTROL_FINISH);
}
- if (ret >= 0) {
- multifd_send_sync_main(rs->f);
- qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
- qemu_fflush(f);
+ if (ret < 0) {
+ return ret;
}
- return ret;
+ ret = multifd_send_sync_main(rs->f);
+ if (ret < 0) {
+ return ret;
+ }
+
+ qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+ qemu_fflush(f);
+
+ return 0;
}
static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
--
2.35.3

381
kvm-nbd-server-Allow-MULTI_CONN-for-shared-writable-expo.patch
View File

@ -1,381 +0,0 @@
From 4a9ddf42788d3f924bdad7746f7aca615f03d7c1 Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Wed, 11 May 2022 19:49:24 -0500
Subject: [PATCH 2/2] nbd/server: Allow MULTI_CONN for shared writable exports
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 90: Advertise MULTI_CONN on writeable NBD servers
RH-Commit: [2/2] 53f0e885a5ed7f6e4bb14e74fe8e7957e6afe90f (ebblake/centos-qemu-kvm)
RH-Bugzilla: 1708300
RH-Acked-by: Nir Soffer <nsoffer@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Daniel P. Berrangé <berrange@redhat.com>
According to the NBD spec, a server that advertises
NBD_FLAG_CAN_MULTI_CONN promises that multiple client connections will
not see any cache inconsistencies: when properly separated by a single
flush, actions performed by one client will be visible to another
client, regardless of which client did the flush.
We always satisfy these conditions in qemu - even when we support
multiple clients, ALL clients go through a single point of reference
into the block layer, with no local caching. The effect of one client
is instantly visible to the next client. Even if our backend were a
network device, we argue that any multi-path caching effects that
would cause inconsistencies in back-to-back actions not seeing the
effect of previous actions would be a bug in that backend, and not the
fault of caching in qemu. As such, it is safe to unconditionally
advertise CAN_MULTI_CONN for any qemu NBD server situation that
supports parallel clients.
Note, however, that we don't want to advertise CAN_MULTI_CONN when we
know that a second client cannot connect (for historical reasons,
qemu-nbd defaults to a single connection while nbd-server-add and QMP
commands default to unlimited connections; but we already have
existing means to let either style of NBD server creation alter those
defaults). This is visible by no longer advertising MULTI_CONN for
'qemu-nbd -r' without -e, as in the iotest nbd-qemu-allocation.
The harder part of this patch is setting up an iotest to demonstrate
behavior of multiple NBD clients to a single server. It might be
possible with parallel qemu-io processes, but I found it easier to do
in python with the help of libnbd, and help from Nir and Vladimir in
writing the test.
Signed-off-by: Eric Blake <eblake@redhat.com>
Suggested-by: Nir Soffer <nsoffer@redhat.com>
Suggested-by: Vladimir Sementsov-Ogievskiy <v.sementsov-og@mail.ru>
Message-Id: <20220512004924.417153-3-eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 58a6fdcc9efb2a7c1ef4893dca4aa5e8020ca3dc)
Conflicts:
nbd/server.c - context, e5fb29d5 not backported
Signed-off-by: Eric Blake <eblake@redhat.com>
---
MAINTAINERS | 1 +
blockdev-nbd.c | 5 +
docs/interop/nbd.txt | 1 +
docs/tools/qemu-nbd.rst | 3 +-
include/block/nbd.h | 3 +-
nbd/server.c | 10 +-
qapi/block-export.json | 8 +-
tests/qemu-iotests/tests/nbd-multiconn | 145 ++++++++++++++++++
tests/qemu-iotests/tests/nbd-multiconn.out | 5 +
.../tests/nbd-qemu-allocation.out | 2 +-
10 files changed, 172 insertions(+), 11 deletions(-)
create mode 100755 tests/qemu-iotests/tests/nbd-multiconn
create mode 100644 tests/qemu-iotests/tests/nbd-multiconn.out
diff --git a/MAINTAINERS b/MAINTAINERS
index 4ad2451e03..2fe20a49ab 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3370,6 +3370,7 @@ F: qemu-nbd.*
F: blockdev-nbd.c
F: docs/interop/nbd.txt
F: docs/tools/qemu-nbd.rst
+F: tests/qemu-iotests/tests/*nbd*
T: git https://repo.or.cz/qemu/ericb.git nbd
T: git https://src.openvz.org/scm/~vsementsov/qemu.git nbd
diff --git a/blockdev-nbd.c b/blockdev-nbd.c
index add41a23af..c6d9b0324c 100644
--- a/blockdev-nbd.c
+++ b/blockdev-nbd.c
@@ -44,6 +44,11 @@ bool nbd_server_is_running(void)
return nbd_server || qemu_nbd_connections >= 0;
}
+int nbd_server_max_connections(void)
+{
+ return nbd_server ? nbd_server->max_connections : qemu_nbd_connections;
+}
+
static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
{
nbd_client_put(client);
diff --git a/docs/interop/nbd.txt b/docs/interop/nbd.txt
index bdb0f2a41a..f5ca25174a 100644
--- a/docs/interop/nbd.txt
+++ b/docs/interop/nbd.txt
@@ -68,3 +68,4 @@ NBD_CMD_BLOCK_STATUS for "qemu:dirty-bitmap:", NBD_CMD_CACHE
* 4.2: NBD_FLAG_CAN_MULTI_CONN for shareable read-only exports,
NBD_CMD_FLAG_FAST_ZERO
* 5.2: NBD_CMD_BLOCK_STATUS for "qemu:allocation-depth"
+* 7.1: NBD_FLAG_CAN_MULTI_CONN for shareable writable exports
diff --git a/docs/tools/qemu-nbd.rst b/docs/tools/qemu-nbd.rst
index 4c950f6199..8e08a29e89 100644
--- a/docs/tools/qemu-nbd.rst
+++ b/docs/tools/qemu-nbd.rst
@@ -139,8 +139,7 @@ driver options if :option:`--image-opts` is specified.
.. option:: -e, --shared=NUM
Allow up to *NUM* clients to share the device (default
- ``1``), 0 for unlimited. Safe for readers, but for now,
- consistency is not guaranteed between multiple writers.
+ ``1``), 0 for unlimited.
.. option:: -t, --persistent
diff --git a/include/block/nbd.h b/include/block/nbd.h
index c5a29ce1c6..c74b7a9d2e 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2016-2020 Red Hat, Inc.
+ * Copyright (C) 2016-2022 Red Hat, Inc.
* Copyright (C) 2005 Anthony Liguori <anthony@codemonkey.ws>
*
* Network Block Device
@@ -346,6 +346,7 @@ void nbd_client_put(NBDClient *client);
void nbd_server_is_qemu_nbd(int max_connections);
bool nbd_server_is_running(void);
+int nbd_server_max_connections(void);
void nbd_server_start(SocketAddress *addr, const char *tls_creds,
const char *tls_authz, uint32_t max_connections,
Error **errp);
diff --git a/nbd/server.c b/nbd/server.c
index c5644fd3f6..6e2157acfa 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2016-2021 Red Hat, Inc.
+ * Copyright (C) 2016-2022 Red Hat, Inc.
* Copyright (C) 2005 Anthony Liguori <anthony@codemonkey.ws>
*
* Network Block Device Server Side
@@ -1642,7 +1642,6 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args,
int64_t size;
uint64_t perm, shared_perm;
bool readonly = !exp_args->writable;
- bool shared = !exp_args->writable;
strList *bitmaps;
size_t i;
int ret;
@@ -1693,11 +1692,12 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args,
exp->description = g_strdup(arg->description);
exp->nbdflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_FLUSH |
NBD_FLAG_SEND_FUA | NBD_FLAG_SEND_CACHE);
+
+ if (nbd_server_max_connections() != 1) {
+ exp->nbdflags |= NBD_FLAG_CAN_MULTI_CONN;
+ }
if (readonly) {
exp->nbdflags |= NBD_FLAG_READ_ONLY;
- if (shared) {
- exp->nbdflags |= NBD_FLAG_CAN_MULTI_CONN;
- }
} else {
exp->nbdflags |= (NBD_FLAG_SEND_TRIM | NBD_FLAG_SEND_WRITE_ZEROES |
NBD_FLAG_SEND_FAST_ZERO);
diff --git a/qapi/block-export.json b/qapi/block-export.json
index 1e34927f85..755ccc89b1 100644
--- a/qapi/block-export.json
+++ b/qapi/block-export.json
@@ -21,7 +21,9 @@
# recreated on the fly while the NBD server is active.
# If missing, it will default to denying access (since 4.0).
# @max-connections: The maximum number of connections to allow at the same
-# time, 0 for unlimited. (since 5.2; default: 0)
+# time, 0 for unlimited. Setting this to 1 also stops
+# the server from advertising multiple client support
+# (since 5.2; default: 0)
#
# Since: 4.2
##
@@ -50,7 +52,9 @@
# recreated on the fly while the NBD server is active.
# If missing, it will default to denying access (since 4.0).
# @max-connections: The maximum number of connections to allow at the same
-# time, 0 for unlimited. (since 5.2; default: 0)
+# time, 0 for unlimited. Setting this to 1 also stops
+# the server from advertising multiple client support
+# (since 5.2; default: 0).
#
# Returns: error if the server is already running.
#
diff --git a/tests/qemu-iotests/tests/nbd-multiconn b/tests/qemu-iotests/tests/nbd-multiconn
new file mode 100755
index 0000000000..b121f2e363
--- /dev/null
+++ b/tests/qemu-iotests/tests/nbd-multiconn
@@ -0,0 +1,145 @@
+#!/usr/bin/env python3
+# group: rw auto quick
+#
+# Test cases for NBD multi-conn advertisement
+#
+# Copyright (C) 2022 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+import os
+from contextlib import contextmanager
+import iotests
+from iotests import qemu_img_create, qemu_io
+
+
+disk = os.path.join(iotests.test_dir, 'disk')
+size = '4M'
+nbd_sock = os.path.join(iotests.sock_dir, 'nbd_sock')
+nbd_uri = 'nbd+unix:///{}?socket=' + nbd_sock
+
+
+@contextmanager
+def open_nbd(export_name):
+ h = nbd.NBD()
+ try:
+ h.connect_uri(nbd_uri.format(export_name))
+ yield h
+ finally:
+ h.shutdown()
+
+class TestNbdMulticonn(iotests.QMPTestCase):
+ def setUp(self):
+ qemu_img_create('-f', iotests.imgfmt, disk, size)
+ qemu_io('-c', 'w -P 1 0 2M', '-c', 'w -P 2 2M 2M', disk)
+
+ self.vm = iotests.VM()
+ self.vm.launch()
+ result = self.vm.qmp('blockdev-add', {
+ 'driver': 'qcow2',
+ 'node-name': 'n',
+ 'file': {'driver': 'file', 'filename': disk}
+ })
+ self.assert_qmp(result, 'return', {})
+
+ def tearDown(self):
+ self.vm.shutdown()
+ os.remove(disk)
+ try:
+ os.remove(nbd_sock)
+ except OSError:
+ pass
+
+ @contextmanager
+ def run_server(self, max_connections=None):
+ args = {
+ 'addr': {
+ 'type': 'unix',
+ 'data': {'path': nbd_sock}
+ }
+ }
+ if max_connections is not None:
+ args['max-connections'] = max_connections
+
+ result = self.vm.qmp('nbd-server-start', args)
+ self.assert_qmp(result, 'return', {})
+ yield
+
+ result = self.vm.qmp('nbd-server-stop')
+ self.assert_qmp(result, 'return', {})
+
+ def add_export(self, name, writable=None):
+ args = {
+ 'type': 'nbd',
+ 'id': name,
+ 'node-name': 'n',
+ 'name': name,
+ }
+ if writable is not None:
+ args['writable'] = writable
+
+ result = self.vm.qmp('block-export-add', args)
+ self.assert_qmp(result, 'return', {})
+
+ def test_default_settings(self):
+ with self.run_server():
+ self.add_export('r')
+ self.add_export('w', writable=True)
+ with open_nbd('r') as h:
+ self.assertTrue(h.can_multi_conn())
+ with open_nbd('w') as h:
+ self.assertTrue(h.can_multi_conn())
+
+ def test_limited_connections(self):
+ with self.run_server(max_connections=1):
+ self.add_export('r')
+ self.add_export('w', writable=True)
+ with open_nbd('r') as h:
+ self.assertFalse(h.can_multi_conn())
+ with open_nbd('w') as h:
+ self.assertFalse(h.can_multi_conn())
+
+ def test_parallel_writes(self):
+ with self.run_server():
+ self.add_export('w', writable=True)
+
+ clients = [nbd.NBD() for _ in range(3)]
+ for c in clients:
+ c.connect_uri(nbd_uri.format('w'))
+ self.assertTrue(c.can_multi_conn())
+
+ initial_data = clients[0].pread(1024 * 1024, 0)
+ self.assertEqual(initial_data, b'\x01' * 1024 * 1024)
+
+ updated_data = b'\x03' * 1024 * 1024
+ clients[1].pwrite(updated_data, 0)
+ clients[2].flush()
+ current_data = clients[0].pread(1024 * 1024, 0)
+
+ self.assertEqual(updated_data, current_data)
+
+ for i in range(3):
+ clients[i].shutdown()
+
+
+if __name__ == '__main__':
+ try:
+ # Easier to use libnbd than to try and set up parallel
+ # 'qemu-nbd --list' or 'qemu-io' processes, but not all systems
+ # have libnbd installed.
+ import nbd # type: ignore
+
+ iotests.main(supported_fmts=['qcow2'])
+ except ImportError:
+ iotests.notrun('libnbd not installed')
diff --git a/tests/qemu-iotests/tests/nbd-multiconn.out b/tests/qemu-iotests/tests/nbd-multiconn.out
new file mode 100644
index 0000000000..8d7e996700
--- /dev/null
+++ b/tests/qemu-iotests/tests/nbd-multiconn.out
@@ -0,0 +1,5 @@
+...
+----------------------------------------------------------------------
+Ran 3 tests
+
+OK
diff --git a/tests/qemu-iotests/tests/nbd-qemu-allocation.out b/tests/qemu-iotests/tests/nbd-qemu-allocation.out
index 0bf1abb063..9d938db24e 100644
--- a/tests/qemu-iotests/tests/nbd-qemu-allocation.out
+++ b/tests/qemu-iotests/tests/nbd-qemu-allocation.out
@@ -17,7 +17,7 @@ wrote 2097152/2097152 bytes at offset 1048576
exports available: 1
export: ''
size: 4194304
- flags: 0x58f ( readonly flush fua df multi cache )
+ flags: 0x48f ( readonly flush fua df cache )
min block: 1
opt block: 4096
max block: 33554432
--
2.31.1

63
kvm-pc-bios-s390-ccw-Fix-booting-with-logical-block-size.patch
View File

@ -1,63 +0,0 @@
From 03996a8a826c9186e4a16e1b4757f1ef5947a503 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 5 Aug 2022 11:42:14 +0200
Subject: [PATCH 07/11] pc-bios/s390-ccw: Fix booting with logical block size <
physical block size
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 113: pc-bios/s390-ccw: Fix booting with logical block size < physical block size
RH-Commit: [1/1] a45ff477bc7d7011ea6c4d42a1aade213d1e4690 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2112303
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Claudio Imbrenda <None>
For accessing single blocks during boot, it's the logical block size that
matters. (Physical block sizes are rather interesting e.g. for creating
file systems with the correct alignment for speed reasons etc.).
So the s390-ccw bios has to use the logical block size for calculating
sector numbers during the boot phase, the "physical_block_exp" shift
value must not be taken into account. This change fixes the boot process
when the guest hast been installed on a disk where the logical block size
differs from the physical one, e.g. if the guest has been installed
like this:
qemu-system-s390x -nographic -accel kvm -m 2G \
-drive if=none,id=d1,file=fedora.iso,format=raw,media=cdrom \
-device virtio-scsi -device scsi-cd,drive=d1 \
-drive if=none,id=d2,file=test.qcow2,format=qcow2
-device virtio-blk,drive=d2,physical_block_size=4096,logical_block_size=512
Linux correctly uses the logical block size of 512 for the installation,
but the s390-ccw bios tries to boot from a disk with 4096 block size so
far, as long as this patch has not been applied yet (well, it used to work
by accident in the past due to the virtio_assume_scsi() hack that used to
enforce 512 byte sectors on all virtio-block disks, but that hack has been
well removed in commit 5447de2619050a0a4d to fix other scenarios).
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2112303
Message-Id: <20220805094214.285223-1-thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit 393296de19650e1400ca265914cfdeb313725363)
---
pc-bios/s390-ccw/virtio-blkdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c
index 8271c47296..794f99b42c 100644
--- a/pc-bios/s390-ccw/virtio-blkdev.c
+++ b/pc-bios/s390-ccw/virtio-blkdev.c
@@ -173,7 +173,7 @@ int virtio_get_block_size(void)
switch (vdev->senseid.cu_model) {
case VIRTIO_ID_BLOCK:
- return vdev->config.blk.blk_size << vdev->config.blk.physical_block_exp;
+ return vdev->config.blk.blk_size;
case VIRTIO_ID_SCSI:
return vdev->scsi_block_size;
}
--
2.31.1

180
kvm-pc-bios-s390-ccw-Split-virtio-scsi-code-from-virtio_.patch
View File

@ -1,180 +0,0 @@
From 2e38b4ec5c53b2b98539a70105d3046e1c452ab8 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 13/17] pc-bios/s390-ccw: Split virtio-scsi code from
virtio_blk_setup_device()
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [8/10] f49c5fb77e05c9dc09ed9f037e37f6a461e4bba6 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit cf30b7c4a9b2c64518be8037c2e6670aacdb00b9
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:19:00 2022 +0200
pc-bios/s390-ccw: Split virtio-scsi code from virtio_blk_setup_device()
The next patch is going to add more virtio-block specific code to
virtio_blk_setup_device(), and if the virtio-scsi code is also in
there, this is more cumbersome. And the calling function virtio_setup()
in main.c looks at the device type already anyway, so it's more
logical to separate the virtio-scsi stuff into a new function in
virtio-scsi.c instead.
Message-Id: <20220704111903.62400-10-thuth@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/main.c | 24 +++++++++++++++++-------
pc-bios/s390-ccw/virtio-blkdev.c | 20 ++------------------
pc-bios/s390-ccw/virtio-scsi.c | 19 ++++++++++++++++++-
pc-bios/s390-ccw/virtio-scsi.h | 2 +-
4 files changed, 38 insertions(+), 27 deletions(-)
diff --git a/pc-bios/s390-ccw/main.c b/pc-bios/s390-ccw/main.c
index 5d2b7ba94d..13e1d8fdf7 100644
--- a/pc-bios/s390-ccw/main.c
+++ b/pc-bios/s390-ccw/main.c
@@ -14,6 +14,7 @@
#include "s390-ccw.h"
#include "cio.h"
#include "virtio.h"
+#include "virtio-scsi.h"
#include "dasd-ipl.h"
char stack[PAGE_SIZE * 8] __attribute__((__aligned__(PAGE_SIZE)));
@@ -218,6 +219,7 @@ static int virtio_setup(void)
{
VDev *vdev = virtio_get_device();
QemuIplParameters *early_qipl = (QemuIplParameters *)QIPL_ADDRESS;
+ int ret;
memcpy(&qipl, early_qipl, sizeof(QemuIplParameters));
@@ -225,18 +227,26 @@ static int virtio_setup(void)
menu_setup();
}
- if (virtio_get_device_type() == VIRTIO_ID_NET) {
+ switch (vdev->senseid.cu_model) {
+ case VIRTIO_ID_NET:
sclp_print("Network boot device detected\n");
vdev->netboot_start_addr = qipl.netboot_start_addr;
- } else {
- int ret = virtio_blk_setup_device(blk_schid);
- if (ret) {
- return ret;
- }
+ return 0;
+ case VIRTIO_ID_BLOCK:
+ ret = virtio_blk_setup_device(blk_schid);
+ break;
+ case VIRTIO_ID_SCSI:
+ ret = virtio_scsi_setup_device(blk_schid);
+ break;
+ default:
+ panic("\n! No IPL device available !\n");
+ }
+
+ if (!ret) {
IPL_assert(virtio_ipl_disk_is_valid(), "No valid IPL device detected");
}
- return 0;
+ return ret;
}
static void ipl_boot_device(void)
diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c
index db1f7f44aa..c175b66a47 100644
--- a/pc-bios/s390-ccw/virtio-blkdev.c
+++ b/pc-bios/s390-ccw/virtio-blkdev.c
@@ -222,27 +222,11 @@ uint64_t virtio_get_blocks(void)
int virtio_blk_setup_device(SubChannelId schid)
{
VDev *vdev = virtio_get_device();
- int ret = 0;
vdev->schid = schid;
virtio_setup_ccw(vdev);
- switch (vdev->senseid.cu_model) {
- case VIRTIO_ID_BLOCK:
- sclp_print("Using virtio-blk.\n");
- break;
- case VIRTIO_ID_SCSI:
- IPL_assert(vdev->config.scsi.sense_size == VIRTIO_SCSI_SENSE_SIZE,
- "Config: sense size mismatch");
- IPL_assert(vdev->config.scsi.cdb_size == VIRTIO_SCSI_CDB_SIZE,
- "Config: CDB size mismatch");
+ sclp_print("Using virtio-blk.\n");
- sclp_print("Using virtio-scsi.\n");
- ret = virtio_scsi_setup(vdev);
- break;
- default:
- panic("\n! No IPL device available !\n");
- }
-
- return ret;
+ return 0;
}
diff --git a/pc-bios/s390-ccw/virtio-scsi.c b/pc-bios/s390-ccw/virtio-scsi.c
index 2c8d0f3097..3b7069270c 100644
--- a/pc-bios/s390-ccw/virtio-scsi.c
+++ b/pc-bios/s390-ccw/virtio-scsi.c
@@ -329,7 +329,7 @@ static void scsi_parse_capacity_report(void *data,
}
}
-int virtio_scsi_setup(VDev *vdev)
+static int virtio_scsi_setup(VDev *vdev)
{
int retry_test_unit_ready = 3;
uint8_t data[256];
@@ -430,3 +430,20 @@ int virtio_scsi_setup(VDev *vdev)
return 0;
}
+
+int virtio_scsi_setup_device(SubChannelId schid)
+{
+ VDev *vdev = virtio_get_device();
+
+ vdev->schid = schid;
+ virtio_setup_ccw(vdev);
+
+ IPL_assert(vdev->config.scsi.sense_size == VIRTIO_SCSI_SENSE_SIZE,
+ "Config: sense size mismatch");
+ IPL_assert(vdev->config.scsi.cdb_size == VIRTIO_SCSI_CDB_SIZE,
+ "Config: CDB size mismatch");
+
+ sclp_print("Using virtio-scsi.\n");
+
+ return virtio_scsi_setup(vdev);
+}
diff --git a/pc-bios/s390-ccw/virtio-scsi.h b/pc-bios/s390-ccw/virtio-scsi.h
index 4b14c2c2f9..e6b6cd4815 100644
--- a/pc-bios/s390-ccw/virtio-scsi.h
+++ b/pc-bios/s390-ccw/virtio-scsi.h
@@ -67,8 +67,8 @@ static inline bool virtio_scsi_response_ok(const VirtioScsiCmdResp *r)
return r->response == VIRTIO_SCSI_S_OK && r->status == CDB_STATUS_GOOD;
}
-int virtio_scsi_setup(VDev *vdev);
int virtio_scsi_read_many(VDev *vdev,
ulong sector, void *load_addr, int sec_num);
+int virtio_scsi_setup_device(SubChannelId schid);
#endif /* VIRTIO_SCSI_H */
--
2.31.1

102
kvm-pc-bios-s390-ccw-bootmap-Improve-the-guessing-logic-.patch
View File

@ -1,102 +0,0 @@
From 64fa56e0520215e3909e442f09d8073c1870648a Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 07/17] pc-bios/s390-ccw/bootmap: Improve the guessing logic in
zipl_load_vblk()
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [2/10] ca8f5e847617cf4ac2fd6c38edb2982f32fa3eba (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit 422865f6672ee1482b98d18321b55c1ecfb06c82
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:54 2022 +0200
pc-bios/s390-ccw/bootmap: Improve the guessing logic in zipl_load_vblk()
The logic of trying an final ISO or ECKD boot on virtio-block devices is
very weird: Since the geometry hardly ever matches in virtio_disk_is_scsi(),
virtio_blk_setup_device() always sets a "guessed" disk geometry via
virtio_assume_scsi() (which is certainly also wrong in a lot of cases).
zipl_load_vblk() then sees that there's been a "virtio_guessed_disk_nature"
and tries to fix up the geometry again via virtio_assume_iso9660() before
always trying to do ipl_iso_el_torito(). That's a very brain-twisting
way of attempting to boot from ISO images, which won't work anymore after
the following patches that will clean up the virtio_assume_scsi() mess
(and thus get rid of the "virtio_guessed_disk_nature" here).
Let's try a better approach instead: ISO files always have a magic
string "CD001" at offset 0x8001 (see e.g. the ECMA-119 specification)
which we can use to decide whether we should try to boot in ISO 9660
mode (which we should also try if we see a sector size of 2048).
And if we were not able to boot in ISO mode here, the final boot attempt
before panicking is to boot in ECKD mode. Since this is our last boot
attempt anyway, simply always assume the ECKD geometry here (if the sector
size was not 4096 yet), so that we also do not depend on the guessed disk
geometry from virtio_blk_setup_device() here anymore.
Message-Id: <20220704111903.62400-4-thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/bootmap.c | 27 +++++++++++++++++++++++----
1 file changed, 23 insertions(+), 4 deletions(-)
diff --git a/pc-bios/s390-ccw/bootmap.c b/pc-bios/s390-ccw/bootmap.c
index 56411ab3b6..994e59c0b0 100644
--- a/pc-bios/s390-ccw/bootmap.c
+++ b/pc-bios/s390-ccw/bootmap.c
@@ -780,18 +780,37 @@ static void ipl_iso_el_torito(void)
}
}
+/**
+ * Detect whether we're trying to boot from an .ISO image.
+ * These always have a signature string "CD001" at offset 0x8001.
+ */
+static bool has_iso_signature(void)
+{
+ int blksize = virtio_get_block_size();
+
+ if (!blksize || virtio_read(0x8000 / blksize, sec)) {
+ return false;
+ }
+
+ return !memcmp("CD001", &sec[1], 5);
+}
+
/***********************************************************************
* Bus specific IPL sequences
*/
static void zipl_load_vblk(void)
{
- if (virtio_guessed_disk_nature()) {
- virtio_assume_iso9660();
+ int blksize = virtio_get_block_size();
+
+ if (blksize == VIRTIO_ISO_BLOCK_SIZE || has_iso_signature()) {
+ if (blksize != VIRTIO_ISO_BLOCK_SIZE) {
+ virtio_assume_iso9660();
+ }
+ ipl_iso_el_torito();
}
- ipl_iso_el_torito();
- if (virtio_guessed_disk_nature()) {
+ if (blksize != VIRTIO_DASD_DEFAULT_BLOCK_SIZE) {
sclp_print("Using guessed DASD geometry.\n");
virtio_assume_eckd();
}
--
2.31.1

78
kvm-pc-bios-s390-ccw-netboot.mak-Ignore-Clang-s-warnings.patch
View File

@ -1,78 +0,0 @@
From 56674ee1f25f12978a6a8a1390e11b55b3e0fabe Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 15/17] pc-bios/s390-ccw/netboot.mak: Ignore Clang's warnings
about GNU extensions
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [10/10] 037dab4df23ebb2b42871bca8c842a53a7204b50 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit e2269220acb03e6c6a460c3090d804835e202239
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:19:03 2022 +0200
pc-bios/s390-ccw/netboot.mak: Ignore Clang's warnings about GNU extensions
When compiling the s390-ccw bios with Clang (v14.0), there is currently
an unuseful warning like this:
CC pc-bios/s390-ccw/ipv6.o
../../roms/SLOF/lib/libnet/ipv6.c:447:18: warning: variable length array
folded to constant array as an extension [-Wgnu-folding-constant]
unsigned short raw[ip6size];
^
SLOF is currently GCC-only and cannot be compiled with Clang yet, so
it is expected that such extensions sneak in there - and as long as
we don't want to compile the code with a compiler that is neither GCC
or Clang, it is also not necessary to avoid such extensions.
Thus these GNU-extension related warnings are completely useless in
the s390-ccw bios, especially in the code that is coming from SLOF,
so we should simply disable the related warnings here now.
Message-Id: <20220704111903.62400-13-thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/netboot.mak | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/pc-bios/s390-ccw/netboot.mak b/pc-bios/s390-ccw/netboot.mak
index 68b4d7edcb..ad41898cb6 100644
--- a/pc-bios/s390-ccw/netboot.mak
+++ b/pc-bios/s390-ccw/netboot.mak
@@ -16,9 +16,12 @@ s390-netboot.elf: $(NETOBJS) libnet.a libc.a
s390-netboot.img: s390-netboot.elf
$(call quiet-command,$(STRIP) --strip-unneeded $< -o $@,"STRIP","$(TARGET_DIR)$@")
+# SLOF is GCC-only, so ignore warnings about GNU extensions with Clang here
+NO_GNU_WARN := $(call cc-option,-Werror $(QEMU_CFLAGS),-Wno-gnu)
+
# libc files:
-LIBC_CFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(LIBC_INC) $(LIBNET_INC) \
+LIBC_CFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(NO_GNU_WARN) $(LIBC_INC) $(LIBNET_INC) \
-MMD -MP -MT $@ -MF $(@:%.o=%.d)
CTYPE_OBJS = isdigit.o isxdigit.o toupper.o
@@ -52,7 +55,7 @@ libc.a: $(LIBCOBJS)
LIBNETOBJS := args.o dhcp.o dns.o icmpv6.o ipv6.o tcp.o udp.o bootp.o \
dhcpv6.o ethernet.o ipv4.o ndp.o tftp.o pxelinux.o
-LIBNETCFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(LIBC_INC) $(LIBNET_INC) \
+LIBNETCFLAGS = $(QEMU_CFLAGS) $(CFLAGS) $(NO_GNU_WARN) $(LIBC_INC) $(LIBNET_INC) \
-DDHCPARCH=0x1F -MMD -MP -MT $@ -MF $(@:%.o=%.d)
%.o : $(SLOF_DIR)/lib/libnet/%.c
--
2.31.1

56
kvm-pc-bios-s390-ccw-virtio-Beautify-the-code-for-readin.patch
View File

@ -1,56 +0,0 @@
From 430e76fd964390db86c8486f76b916a1cf7f74c2 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 12/17] pc-bios/s390-ccw/virtio: Beautify the code for reading
virtqueue configuration
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [7/10] b15c06b4c5431837672b6cb5d57d09da20718441 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit 070824885741f5d2a66626d3c4ecb2773c8e0552
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:59 2022 +0200
pc-bios/s390-ccw/virtio: Beautify the code for reading virtqueue configuration
It looks nicer if we separate the run_ccw() from the IPL_assert()
statement, and the error message should talk about "virtio device"
instead of "block device", since this code is nowadays used for
non-block (i.e. network) devices, too.
Message-Id: <20220704111903.62400-9-thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/pc-bios/s390-ccw/virtio.c b/pc-bios/s390-ccw/virtio.c
index d8c2b52710..f37510f312 100644
--- a/pc-bios/s390-ccw/virtio.c
+++ b/pc-bios/s390-ccw/virtio.c
@@ -289,9 +289,8 @@ void virtio_setup_ccw(VDev *vdev)
.num = 0,
};
- IPL_assert(
- run_ccw(vdev, CCW_CMD_READ_VQ_CONF, &config, sizeof(config), false) == 0,
- "Could not get block device VQ configuration");
+ rc = run_ccw(vdev, CCW_CMD_READ_VQ_CONF, &config, sizeof(config), false);
+ IPL_assert(rc == 0, "Could not get virtio device VQ configuration");
info.num = config.num;
vring_init(&vdev->vrings[i], &info);
vdev->vrings[i].schid = vdev->schid;
--
2.31.1

63
kvm-pc-bios-s390-ccw-virtio-Introduce-a-macro-for-the-DA.patch
View File

@ -1,63 +0,0 @@
From 7d4f2454f95bfc087ad3f2fe3bc4625dcea3568e Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 06/17] pc-bios/s390-ccw/virtio: Introduce a macro for the DASD
block size
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [1/10] 71033934e1e9988bcf71362e02665ceb7449009d (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit 1f2c2ee48e87ea743f8e23cc7569dd26c4cf9623
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:53 2022 +0200
pc-bios/s390-ccw/virtio: Introduce a macro for the DASD block size
Use VIRTIO_DASD_DEFAULT_BLOCK_SIZE instead of the magic value 4096.
Message-Id: <20220704111903.62400-3-thuth@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio-blkdev.c | 2 +-
pc-bios/s390-ccw/virtio.h | 1 +
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c
index 7d35050292..6483307630 100644
--- a/pc-bios/s390-ccw/virtio-blkdev.c
+++ b/pc-bios/s390-ccw/virtio-blkdev.c
@@ -155,7 +155,7 @@ void virtio_assume_eckd(void)
vdev->config.blk.physical_block_exp = 0;
switch (vdev->senseid.cu_model) {
case VIRTIO_ID_BLOCK:
- vdev->config.blk.blk_size = 4096;
+ vdev->config.blk.blk_size = VIRTIO_DASD_DEFAULT_BLOCK_SIZE;
break;
case VIRTIO_ID_SCSI:
vdev->config.blk.blk_size = vdev->scsi_block_size;
diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h
index 19fceb6495..9e410bde6f 100644
--- a/pc-bios/s390-ccw/virtio.h
+++ b/pc-bios/s390-ccw/virtio.h
@@ -198,6 +198,7 @@ extern int virtio_read_many(ulong sector, void *load_addr, int sec_num);
#define VIRTIO_SECTOR_SIZE 512
#define VIRTIO_ISO_BLOCK_SIZE 2048
#define VIRTIO_SCSI_BLOCK_SIZE 512
+#define VIRTIO_DASD_DEFAULT_BLOCK_SIZE 4096
static inline ulong virtio_sector_adjust(ulong sector)
{
--
2.31.1

67
kvm-pc-bios-s390-ccw-virtio-Read-device-config-after-fea.patch
View File

@ -1,67 +0,0 @@
From 20f8724d0837acbe642c8c7698a4b256f34c1209 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 11/17] pc-bios/s390-ccw/virtio: Read device config after
feature negotiation
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [6/10] 54d21e430b2dfba9e0a0823d6bb8ec7e7f8ff2ff (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit aa5c69ce99411c4886bcd051f288afc02b6d968d
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:58 2022 +0200
pc-bios/s390-ccw/virtio: Read device config after feature negotiation
Feature negotiation should be done first, since some fields in the
config area can depend on the negotiated features and thus should
rather be read afterwards.
While we're at it, also adjust the error message here a little bit
(the code is nowadays used for non-block virtio devices, too).
Message-Id: <20220704111903.62400-8-thuth@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/pc-bios/s390-ccw/virtio.c b/pc-bios/s390-ccw/virtio.c
index 4e85a2eb82..d8c2b52710 100644
--- a/pc-bios/s390-ccw/virtio.c
+++ b/pc-bios/s390-ccw/virtio.c
@@ -262,10 +262,6 @@ void virtio_setup_ccw(VDev *vdev)
rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false);
IPL_assert(rc == 0, "Could not write DRIVER status to host");
- IPL_assert(
- run_ccw(vdev, CCW_CMD_READ_CONF, &vdev->config, cfg_size, false) == 0,
- "Could not get block device configuration");
-
/* Feature negotiation */
for (i = 0; i < ARRAY_SIZE(vdev->guest_features); i++) {
feats.features = 0;
@@ -278,6 +274,9 @@ void virtio_setup_ccw(VDev *vdev)
IPL_assert(rc == 0, "Could not set features bits");
}
+ rc = run_ccw(vdev, CCW_CMD_READ_CONF, &vdev->config, cfg_size, false);
+ IPL_assert(rc == 0, "Could not get virtio device configuration");
+
for (i = 0; i < vdev->nr_vqs; i++) {
VqInfo info = {
.queue = (unsigned long long) ring_area + (i * VIRTIO_RING_SIZE),
--
2.31.1

93
kvm-pc-bios-s390-ccw-virtio-Set-missing-status-bits-whil.patch
View File

@ -1,93 +0,0 @@
From 303fb3ddcdbbd1373c5b1aa28e03f90507e217f3 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 10/17] pc-bios/s390-ccw/virtio: Set missing status bits while
initializing
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [5/10] 4bc44d9adae055fb60b79d04a2f08535b4d38d2b (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit 175aa06a152ef6b58ba9b2e47a1296b024dea70c
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:57 2022 +0200
pc-bios/s390-ccw/virtio: Set missing status bits while initializing
According chapter "3.1.1 Driver Requirements: Device Initialization"
of the Virtio specification (v1.1), a driver for a device has to set
the ACKNOWLEDGE and DRIVER bits in the status field after resetting
the device. The s390-ccw bios skipped these steps so far and seems
like QEMU never cared. Anyway, it's better to follow the spec, so
let's set these bits now in the right spots, too.
Message-Id: <20220704111903.62400-7-thuth@redhat.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/pc-bios/s390-ccw/virtio.c b/pc-bios/s390-ccw/virtio.c
index 5d2c6e3381..4e85a2eb82 100644
--- a/pc-bios/s390-ccw/virtio.c
+++ b/pc-bios/s390-ccw/virtio.c
@@ -220,7 +220,7 @@ int virtio_run(VDev *vdev, int vqid, VirtioCmd *cmd)
void virtio_setup_ccw(VDev *vdev)
{
int i, rc, cfg_size = 0;
- unsigned char status = VIRTIO_CONFIG_S_DRIVER_OK;
+ uint8_t status;
struct VirtioFeatureDesc {
uint32_t features;
uint8_t index;
@@ -234,6 +234,10 @@ void virtio_setup_ccw(VDev *vdev)
run_ccw(vdev, CCW_CMD_VDEV_RESET, NULL, 0, false);
+ status = VIRTIO_CONFIG_S_ACKNOWLEDGE;
+ rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false);
+ IPL_assert(rc == 0, "Could not write ACKNOWLEDGE status to host");
+
switch (vdev->senseid.cu_model) {
case VIRTIO_ID_NET:
vdev->nr_vqs = 2;
@@ -253,6 +257,11 @@ void virtio_setup_ccw(VDev *vdev)
default:
panic("Unsupported virtio device\n");
}
+
+ status |= VIRTIO_CONFIG_S_DRIVER;
+ rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false);
+ IPL_assert(rc == 0, "Could not write DRIVER status to host");
+
IPL_assert(
run_ccw(vdev, CCW_CMD_READ_CONF, &vdev->config, cfg_size, false) == 0,
"Could not get block device configuration");
@@ -291,9 +300,10 @@ void virtio_setup_ccw(VDev *vdev)
run_ccw(vdev, CCW_CMD_SET_VQ, &info, sizeof(info), false) == 0,
"Cannot set VQ info");
}
- IPL_assert(
- run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false) == 0,
- "Could not write status to host");
+
+ status |= VIRTIO_CONFIG_S_DRIVER_OK;
+ rc = run_ccw(vdev, CCW_CMD_WRITE_STATUS, &status, sizeof(status), false);
+ IPL_assert(rc == 0, "Could not write DRIVER_OK status to host");
}
bool virtio_is_supported(SubChannelId schid)
--
2.31.1

101
kvm-pc-bios-s390-ccw-virtio-blkdev-Remove-virtio_assume_.patch
View File

@ -1,101 +0,0 @@
From d3335a98a7b6e084aadf4907968536a67cf8e64c Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 09/17] pc-bios/s390-ccw/virtio-blkdev: Remove
virtio_assume_scsi()
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [4/10] bf27f75344f220a03475a2918ed49ec9cd5ba317 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit 5447de2619050a0a4dd480b97f88a9b58da360d1
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:56 2022 +0200
pc-bios/s390-ccw/virtio-blkdev: Remove virtio_assume_scsi()
The virtio_assume_scsi() function is very questionable: First, it
is only called for virtio-blk, and not for virtio-scsi, so the naming
is already quite confusing. Second, it is called if we detected a
"invalid" IPL disk, trying to fix it by blindly setting a sector
size of 512. This of course won't work in most cases since disks
might have a different sector size for a reason.
Thus let's remove this strange function now. The calling code can
also be removed completely, since there is another spot in main.c
that does "IPL_assert(virtio_ipl_disk_is_valid(), ...)" to make
sure that we do not try to IPL from an invalid device.
Message-Id: <20220704111903.62400-6-thuth@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio-blkdev.c | 24 ------------------------
pc-bios/s390-ccw/virtio.h | 1 -
2 files changed, 25 deletions(-)
diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c
index 7e13155589..db1f7f44aa 100644
--- a/pc-bios/s390-ccw/virtio-blkdev.c
+++ b/pc-bios/s390-ccw/virtio-blkdev.c
@@ -112,23 +112,6 @@ VirtioGDN virtio_guessed_disk_nature(void)
return virtio_get_device()->guessed_disk_nature;
}
-void virtio_assume_scsi(void)
-{
- VDev *vdev = virtio_get_device();
-
- switch (vdev->senseid.cu_model) {
- case VIRTIO_ID_BLOCK:
- vdev->guessed_disk_nature = VIRTIO_GDN_SCSI;
- vdev->config.blk.blk_size = VIRTIO_SCSI_BLOCK_SIZE;
- vdev->config.blk.physical_block_exp = 0;
- vdev->blk_factor = 1;
- break;
- case VIRTIO_ID_SCSI:
- vdev->scsi_block_size = VIRTIO_SCSI_BLOCK_SIZE;
- break;
- }
-}
-
void virtio_assume_iso9660(void)
{
VDev *vdev = virtio_get_device();
@@ -247,13 +230,6 @@ int virtio_blk_setup_device(SubChannelId schid)
switch (vdev->senseid.cu_model) {
case VIRTIO_ID_BLOCK:
sclp_print("Using virtio-blk.\n");
- if (!virtio_ipl_disk_is_valid()) {
- /* make sure all getters but blocksize return 0 for
- * invalid IPL disk
- */
- memset(&vdev->config.blk, 0, sizeof(vdev->config.blk));
- virtio_assume_scsi();
- }
break;
case VIRTIO_ID_SCSI:
IPL_assert(vdev->config.scsi.sense_size == VIRTIO_SCSI_SENSE_SIZE,
diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h
index 241730effe..600ba5052b 100644
--- a/pc-bios/s390-ccw/virtio.h
+++ b/pc-bios/s390-ccw/virtio.h
@@ -182,7 +182,6 @@ enum guessed_disk_nature_type {
typedef enum guessed_disk_nature_type VirtioGDN;
VirtioGDN virtio_guessed_disk_nature(void);
-void virtio_assume_scsi(void);
void virtio_assume_eckd(void);
void virtio_assume_iso9660(void);
--
2.31.1

63
kvm-pc-bios-s390-ccw-virtio-blkdev-Request-the-right-fea.patch
View File

@ -1,63 +0,0 @@
From db58915fcaf3d24b64fe2c34cc15b5596b9a81bb Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 14/17] pc-bios/s390-ccw/virtio-blkdev: Request the right
feature bits
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [9/10] 9dcd8c2f659f366f9487ab6473d1f0d7778b40a7 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit 9125a314cca4a1838b09305a87d8efb98f80ab67
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:19:01 2022 +0200
pc-bios/s390-ccw/virtio-blkdev: Request the right feature bits
The virtio-blk code uses the block size and geometry fields in the
config area. According to the virtio-spec, these have to be negotiated
with the right feature bits during initialization, otherwise they
might not be available. QEMU is so far very forgiving and always
provides them, but we should not rely on this behavior, so let's
better request them properly via the VIRTIO_BLK_F_GEOMETRY and
VIRTIO_BLK_F_BLK_SIZE feature bits.
Message-Id: <20220704111903.62400-11-thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio-blkdev.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c
index c175b66a47..8271c47296 100644
--- a/pc-bios/s390-ccw/virtio-blkdev.c
+++ b/pc-bios/s390-ccw/virtio-blkdev.c
@@ -13,6 +13,9 @@
#include "virtio.h"
#include "virtio-scsi.h"
+#define VIRTIO_BLK_F_GEOMETRY (1 << 4)
+#define VIRTIO_BLK_F_BLK_SIZE (1 << 6)
+
static int virtio_blk_read_many(VDev *vdev, ulong sector, void *load_addr,
int sec_num)
{
@@ -223,6 +226,7 @@ int virtio_blk_setup_device(SubChannelId schid)
{
VDev *vdev = virtio_get_device();
+ vdev->guest_features[0] = VIRTIO_BLK_F_GEOMETRY | VIRTIO_BLK_F_BLK_SIZE;
vdev->schid = schid;
virtio_setup_ccw(vdev);
--
2.31.1

124
kvm-pc-bios-s390-ccw-virtio-blkdev-Simplify-fix-virtio_i.patch
View File

@ -1,124 +0,0 @@
From f07e4629a7c58407f903810a038660c88c6a6315 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 8 Jul 2022 20:49:01 +0200
Subject: [PATCH 08/17] pc-bios/s390-ccw/virtio-blkdev: Simplify/fix
virtio_ipl_disk_is_valid()
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 106: pc-bios/s390-ccw: Fix boot from disks with 4k sectors that do not have the typical DASD geometry
RH-Commit: [3/10] fb06830a3e50d9da3d84913b50bb227865cc44b3 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2098077
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: http://bugzilla.redhat.com/2098077
commit bbf615f7b707f009ef8e757d170902ad33b90644
Author: Thomas Huth <thuth@redhat.com>
Date: Mon Jul 4 13:18:55 2022 +0200
pc-bios/s390-ccw/virtio-blkdev: Simplify/fix virtio_ipl_disk_is_valid()
The s390-ccw bios fails to boot if the boot disk is a virtio-blk
disk with a sector size of 4096. For example:
dasdfmt -b 4096 -d cdl -y -p -M quick /dev/dasdX
fdasd -a /dev/dasdX
install a guest onto /dev/dasdX1 using virtio-blk
qemu-system-s390x -nographic -hda /dev/dasdX1
The bios then bails out with:
! Cannot read block 0 !
Looking at virtio_ipl_disk_is_valid() and especially the function
virtio_disk_is_scsi(), it does not really make sense that we expect
only such a limited disk geometry (like a block size of 512) for
our boot disks. Let's relax the check and allow everything that
remotely looks like a sane disk.
Message-Id: <20220704111903.62400-5-thuth@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
pc-bios/s390-ccw/virtio-blkdev.c | 41 ++++++--------------------------
pc-bios/s390-ccw/virtio.h | 2 --
2 files changed, 7 insertions(+), 36 deletions(-)
diff --git a/pc-bios/s390-ccw/virtio-blkdev.c b/pc-bios/s390-ccw/virtio-blkdev.c
index 6483307630..7e13155589 100644
--- a/pc-bios/s390-ccw/virtio-blkdev.c
+++ b/pc-bios/s390-ccw/virtio-blkdev.c
@@ -166,46 +166,19 @@ void virtio_assume_eckd(void)
virtio_eckd_sectors_for_block_size(vdev->config.blk.blk_size);
}
-bool virtio_disk_is_scsi(void)
-{
- VDev *vdev = virtio_get_device();
-
- if (vdev->guessed_disk_nature == VIRTIO_GDN_SCSI) {
- return true;
- }
- switch (vdev->senseid.cu_model) {
- case VIRTIO_ID_BLOCK:
- return (vdev->config.blk.geometry.heads == 255)
- && (vdev->config.blk.geometry.sectors == 63)
- && (virtio_get_block_size() == VIRTIO_SCSI_BLOCK_SIZE);
- case VIRTIO_ID_SCSI:
- return true;
- }
- return false;
-}
-
-bool virtio_disk_is_eckd(void)
+bool virtio_ipl_disk_is_valid(void)
{
+ int blksize = virtio_get_block_size();
VDev *vdev = virtio_get_device();
- const int block_size = virtio_get_block_size();
- if (vdev->guessed_disk_nature == VIRTIO_GDN_DASD) {
+ if (vdev->guessed_disk_nature == VIRTIO_GDN_SCSI ||
+ vdev->guessed_disk_nature == VIRTIO_GDN_DASD) {
return true;
}
- switch (vdev->senseid.cu_model) {
- case VIRTIO_ID_BLOCK:
- return (vdev->config.blk.geometry.heads == 15)
- && (vdev->config.blk.geometry.sectors ==
- virtio_eckd_sectors_for_block_size(block_size));
- case VIRTIO_ID_SCSI:
- return false;
- }
- return false;
-}
-bool virtio_ipl_disk_is_valid(void)
-{
- return virtio_disk_is_scsi() || virtio_disk_is_eckd();
+ return (vdev->senseid.cu_model == VIRTIO_ID_BLOCK ||
+ vdev->senseid.cu_model == VIRTIO_ID_SCSI) &&
+ blksize >= 512 && blksize <= 4096;
}
int virtio_get_block_size(void)
diff --git a/pc-bios/s390-ccw/virtio.h b/pc-bios/s390-ccw/virtio.h
index 9e410bde6f..241730effe 100644
--- a/pc-bios/s390-ccw/virtio.h
+++ b/pc-bios/s390-ccw/virtio.h
@@ -186,8 +186,6 @@ void virtio_assume_scsi(void);
void virtio_assume_eckd(void);
void virtio_assume_iso9660(void);
-extern bool virtio_disk_is_scsi(void);
-extern bool virtio_disk_is_eckd(void);
extern bool virtio_ipl_disk_is_valid(void);
extern int virtio_get_block_size(void);
extern uint8_t virtio_get_heads(void);
--
2.31.1

126
kvm-qapi-machine.json-Add-cluster-id.patch
View File

@ -1,126 +0,0 @@
From e97c563f7146098119839aa146a6f25070eb7148 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:02 +0800
Subject: [PATCH 01/16] qapi/machine.json: Add cluster-id
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [1/6] 44d7d83008c6d28485ae44f7cced792f4987b919 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
This adds cluster-id in CPU instance properties, which will be used
by arm/virt machine. Besides, the cluster-id is also verified or
dumped in various spots:
* hw/core/machine.c::machine_set_cpu_numa_node() to associate
CPU with its NUMA node.
* hw/core/machine.c::machine_numa_finish_cpu_init() to record
CPU slots with no NUMA mapping set.
* hw/core/machine-hmp-cmds.c::hmp_hotpluggable_cpus() to dump
cluster-id.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Acked-by: Igor Mammedov <imammedo@redhat.com>
Message-id: 20220503140304.855514-2-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 1dcf7001d4bae651129d46d5628b29e93a411d0b)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/core/machine-hmp-cmds.c | 4 ++++
hw/core/machine.c | 16 ++++++++++++++++
qapi/machine.json | 6 ++++--
3 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c
index 4e2f319aeb..5cb5eecbfc 100644
--- a/hw/core/machine-hmp-cmds.c
+++ b/hw/core/machine-hmp-cmds.c
@@ -77,6 +77,10 @@ void hmp_hotpluggable_cpus(Monitor *mon, const QDict *qdict)
if (c->has_die_id) {
monitor_printf(mon, " die-id: \"%" PRIu64 "\"\n", c->die_id);
}
+ if (c->has_cluster_id) {
+ monitor_printf(mon, " cluster-id: \"%" PRIu64 "\"\n",
+ c->cluster_id);
+ }
if (c->has_core_id) {
monitor_printf(mon, " core-id: \"%" PRIu64 "\"\n", c->core_id);
}
diff --git a/hw/core/machine.c b/hw/core/machine.c
index dffc3ef4ab..168f4de910 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -890,6 +890,11 @@ void machine_set_cpu_numa_node(MachineState *machine,
return;
}
+ if (props->has_cluster_id && !slot->props.has_cluster_id) {
+ error_setg(errp, "cluster-id is not supported");
+ return;
+ }
+
if (props->has_socket_id && !slot->props.has_socket_id) {
error_setg(errp, "socket-id is not supported");
return;
@@ -909,6 +914,11 @@ void machine_set_cpu_numa_node(MachineState *machine,
continue;
}
+ if (props->has_cluster_id &&
+ props->cluster_id != slot->props.cluster_id) {
+ continue;
+ }
+
if (props->has_die_id && props->die_id != slot->props.die_id) {
continue;
}
@@ -1203,6 +1213,12 @@ static char *cpu_slot_to_string(const CPUArchId *cpu)
}
g_string_append_printf(s, "die-id: %"PRId64, cpu->props.die_id);
}
+ if (cpu->props.has_cluster_id) {
+ if (s->len) {
+ g_string_append_printf(s, ", ");
+ }
+ g_string_append_printf(s, "cluster-id: %"PRId64, cpu->props.cluster_id);
+ }
if (cpu->props.has_core_id) {
if (s->len) {
g_string_append_printf(s, ", ");
diff --git a/qapi/machine.json b/qapi/machine.json
index d25a481ce4..4c417e32a5 100644
--- a/qapi/machine.json
+++ b/qapi/machine.json
@@ -868,10 +868,11 @@
# @node-id: NUMA node ID the CPU belongs to
# @socket-id: socket number within node/board the CPU belongs to
# @die-id: die number within socket the CPU belongs to (since 4.1)
-# @core-id: core number within die the CPU belongs to
+# @cluster-id: cluster number within die the CPU belongs to (since 7.1)
+# @core-id: core number within cluster the CPU belongs to
# @thread-id: thread number within core the CPU belongs to
#
-# Note: currently there are 5 properties that could be present
+# Note: currently there are 6 properties that could be present
# but management should be prepared to pass through other
# properties with device_add command to allow for future
# interface extension. This also requires the filed names to be kept in
@@ -883,6 +884,7 @@
'data': { '*node-id': 'int',
'*socket-id': 'int',
'*die-id': 'int',
+ '*cluster-id': 'int',
'*core-id': 'int',
'*thread-id': 'int'
}
--
2.31.1

162
kvm-qcow2-Add-errp-to-rebuild_refcount_structure.patch
View File

@ -1,162 +0,0 @@
From 5e385a0e49a520550a83299632be175857b63f19 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Tue, 5 Apr 2022 15:46:52 +0200
Subject: [PATCH 06/16] qcow2: Add errp to rebuild_refcount_structure()
RH-Author: Hanna Reitz <hreitz@redhat.com>
RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding
RH-Commit: [3/4] 937b89a7eab6ec6b18618d59bc1526976ad03290 (hreitz/qemu-kvm-c-9-s)
RH-Bugzilla: 2072379
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Instead of fprint()-ing error messages in rebuild_refcount_structure()
and its rebuild_refcounts_write_refblocks() helper, pass them through an
Error object to qcow2_check_refcounts() (which will then print it).
Suggested-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220405134652.19278-4-hreitz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 0423f75351ab83b844a31349218b0eadd830e07a)
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
---
block/qcow2-refcount.c | 33 +++++++++++++++++++--------------
1 file changed, 19 insertions(+), 14 deletions(-)
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index c5669eaa51..ed0ecfaa89 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -2465,7 +2465,8 @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs,
static int rebuild_refcounts_write_refblocks(
BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters,
int64_t first_cluster, int64_t end_cluster,
- uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr
+ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr,
+ Error **errp
)
{
BDRVQcow2State *s = bs->opaque;
@@ -2516,8 +2517,8 @@ static int rebuild_refcounts_write_refblocks(
nb_clusters,
&first_free_cluster);
if (refblock_offset < 0) {
- fprintf(stderr, "ERROR allocating refblock: %s\n",
- strerror(-refblock_offset));
+ error_setg_errno(errp, -refblock_offset,
+ "ERROR allocating refblock");
return refblock_offset;
}
@@ -2539,6 +2540,7 @@ static int rebuild_refcounts_write_refblocks(
on_disk_reftable_entries *
REFTABLE_ENTRY_SIZE);
if (!on_disk_reftable) {
+ error_setg(errp, "ERROR allocating reftable memory");
return -ENOMEM;
}
@@ -2562,7 +2564,7 @@ static int rebuild_refcounts_write_refblocks(
ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset,
s->cluster_size, false);
if (ret < 0) {
- fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
+ error_setg_errno(errp, -ret, "ERROR writing refblock");
return ret;
}
@@ -2578,7 +2580,7 @@ static int rebuild_refcounts_write_refblocks(
ret = bdrv_pwrite(bs->file, refblock_offset, on_disk_refblock,
s->cluster_size);
if (ret < 0) {
- fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
+ error_setg_errno(errp, -ret, "ERROR writing refblock");
return ret;
}
@@ -2601,7 +2603,8 @@ static int rebuild_refcounts_write_refblocks(
static int rebuild_refcount_structure(BlockDriverState *bs,
BdrvCheckResult *res,
void **refcount_table,
- int64_t *nb_clusters)
+ int64_t *nb_clusters,
+ Error **errp)
{
BDRVQcow2State *s = bs->opaque;
int64_t reftable_offset = -1;
@@ -2652,7 +2655,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs,
rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,
0, *nb_clusters,
&on_disk_reftable,
- &on_disk_reftable_entries);
+ &on_disk_reftable_entries, errp);
if (reftable_size_changed < 0) {
res->check_errors++;
ret = reftable_size_changed;
@@ -2676,8 +2679,8 @@ static int rebuild_refcount_structure(BlockDriverState *bs,
refcount_table, nb_clusters,
&first_free_cluster);
if (reftable_offset < 0) {
- fprintf(stderr, "ERROR allocating reftable: %s\n",
- strerror(-reftable_offset));
+ error_setg_errno(errp, -reftable_offset,
+ "ERROR allocating reftable");
res->check_errors++;
ret = reftable_offset;
goto fail;
@@ -2695,7 +2698,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs,
reftable_start_cluster,
reftable_end_cluster,
&on_disk_reftable,
- &on_disk_reftable_entries);
+ &on_disk_reftable_entries, errp);
if (reftable_size_changed < 0) {
res->check_errors++;
ret = reftable_size_changed;
@@ -2725,7 +2728,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs,
ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length,
false);
if (ret < 0) {
- fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
+ error_setg_errno(errp, -ret, "ERROR writing reftable");
goto fail;
}
@@ -2733,7 +2736,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs,
ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,
reftable_length);
if (ret < 0) {
- fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
+ error_setg_errno(errp, -ret, "ERROR writing reftable");
goto fail;
}
@@ -2746,7 +2749,7 @@ static int rebuild_refcount_structure(BlockDriverState *bs,
&reftable_offset_and_clusters,
sizeof(reftable_offset_and_clusters));
if (ret < 0) {
- fprintf(stderr, "ERROR setting reftable: %s\n", strerror(-ret));
+ error_setg_errno(errp, -ret, "ERROR setting reftable");
goto fail;
}
@@ -2814,11 +2817,13 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
if (rebuild && (fix & BDRV_FIX_ERRORS)) {
BdrvCheckResult old_res = *res;
int fresh_leaks = 0;
+ Error *local_err = NULL;
fprintf(stderr, "Rebuilding refcount structure\n");
ret = rebuild_refcount_structure(bs, res, &refcount_table,
- &nb_clusters);
+ &nb_clusters, &local_err);
if (ret < 0) {
+ error_report_err(local_err);
goto fail;
}
--
2.31.1

465
kvm-qcow2-Improve-refcount-structure-rebuilding.patch
View File

@ -1,465 +0,0 @@
From b453cf6be8429f4438d51eb24fcf49e7d9f14db6 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Tue, 5 Apr 2022 15:46:50 +0200
Subject: [PATCH 04/16] qcow2: Improve refcount structure rebuilding
RH-Author: Hanna Reitz <hreitz@redhat.com>
RH-MergeRequest: 96: qcow2: Improve refcount structure rebuilding
RH-Commit: [1/4] a3606b7abcaebb4930b566e95b1090aead62dfae (hreitz/qemu-kvm-c-9-s)
RH-Bugzilla: 2072379
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
When rebuilding the refcount structures (when qemu-img check -r found
errors with refcount = 0, but reference count > 0), the new refcount
table defaults to being put at the image file end[1]. There is no good
reason for that except that it means we will not have to rewrite any
refblocks we already wrote to disk.
Changing the code to rewrite those refblocks is not too difficult,
though, so let us do that. That is beneficial for images on block
devices, where we cannot really write beyond the end of the image file.
Use this opportunity to add extensive comments to the code, and refactor
it a bit, getting rid of the backwards-jumping goto.
[1] Unless there is something allocated in the area pointed to by the
last refblock, so we have to write that refblock. In that case, we
try to put the reftable in there.
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1519071
Closes: https://gitlab.com/qemu-project/qemu/-/issues/941
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220405134652.19278-2-hreitz@redhat.com>
(cherry picked from commit a8c07ec287554dcefd33733f0e5888a281ddc95e)
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
---
block/qcow2-refcount.c | 332 +++++++++++++++++++++++++++++------------
1 file changed, 235 insertions(+), 97 deletions(-)
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index b91499410c..c5669eaa51 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -2438,111 +2438,140 @@ static int64_t alloc_clusters_imrt(BlockDriverState *bs,
}
/*
- * Creates a new refcount structure based solely on the in-memory information
- * given through *refcount_table. All necessary allocations will be reflected
- * in that array.
+ * Helper function for rebuild_refcount_structure().
*
- * On success, the old refcount structure is leaked (it will be covered by the
- * new refcount structure).
+ * Scan the range of clusters [first_cluster, end_cluster) for allocated
+ * clusters and write all corresponding refblocks to disk. The refblock
+ * and allocation data is taken from the in-memory refcount table
+ * *refcount_table[] (of size *nb_clusters), which is basically one big
+ * (unlimited size) refblock for the whole image.
+ *
+ * For these refblocks, clusters are allocated using said in-memory
+ * refcount table. Care is taken that these allocations are reflected
+ * in the refblocks written to disk.
+ *
+ * The refblocks' offsets are written into a reftable, which is
+ * *on_disk_reftable_ptr[] (of size *on_disk_reftable_entries_ptr). If
+ * that reftable is of insufficient size, it will be resized to fit.
+ * This reftable is not written to disk.
+ *
+ * (If *on_disk_reftable_ptr is not NULL, the entries within are assumed
+ * to point to existing valid refblocks that do not need to be allocated
+ * again.)
+ *
+ * Return whether the on-disk reftable array was resized (true/false),
+ * or -errno on error.
*/
-static int rebuild_refcount_structure(BlockDriverState *bs,
- BdrvCheckResult *res,
- void **refcount_table,
- int64_t *nb_clusters)
+static int rebuild_refcounts_write_refblocks(
+ BlockDriverState *bs, void **refcount_table, int64_t *nb_clusters,
+ int64_t first_cluster, int64_t end_cluster,
+ uint64_t **on_disk_reftable_ptr, uint32_t *on_disk_reftable_entries_ptr
+ )
{
BDRVQcow2State *s = bs->opaque;
- int64_t first_free_cluster = 0, reftable_offset = -1, cluster = 0;
+ int64_t cluster;
int64_t refblock_offset, refblock_start, refblock_index;
- uint32_t reftable_size = 0;
- uint64_t *on_disk_reftable = NULL;
+ int64_t first_free_cluster = 0;
+ uint64_t *on_disk_reftable = *on_disk_reftable_ptr;
+ uint32_t on_disk_reftable_entries = *on_disk_reftable_entries_ptr;
void *on_disk_refblock;
- int ret = 0;
- struct {
- uint64_t reftable_offset;
- uint32_t reftable_clusters;
- } QEMU_PACKED reftable_offset_and_clusters;
-
- qcow2_cache_empty(bs, s->refcount_block_cache);
+ bool reftable_grown = false;
+ int ret;
-write_refblocks:
- for (; cluster < *nb_clusters; cluster++) {
+ for (cluster = first_cluster; cluster < end_cluster; cluster++) {
+ /* Check all clusters to find refblocks that contain non-zero entries */
if (!s->get_refcount(*refcount_table, cluster)) {
continue;
}
+ /*
+ * This cluster is allocated, so we need to create a refblock
+ * for it. The data we will write to disk is just the
+ * respective slice from *refcount_table, so it will contain
+ * accurate refcounts for all clusters belonging to this
+ * refblock. After we have written it, we will therefore skip
+ * all remaining clusters in this refblock.
+ */
+
refblock_index = cluster >> s->refcount_block_bits;
refblock_start = refblock_index << s->refcount_block_bits;
- /* Don't allocate a cluster in a refblock already written to disk */
- if (first_free_cluster < refblock_start) {
- first_free_cluster = refblock_start;
- }
- refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table,
- nb_clusters, &first_free_cluster);
- if (refblock_offset < 0) {
- fprintf(stderr, "ERROR allocating refblock: %s\n",
- strerror(-refblock_offset));
- res->check_errors++;
- ret = refblock_offset;
- goto fail;
- }
+ if (on_disk_reftable_entries > refblock_index &&
+ on_disk_reftable[refblock_index])
+ {
+ /*
+ * We can get here after a `goto write_refblocks`: We have a
+ * reftable from a previous run, and the refblock is already
+ * allocated. No need to allocate it again.
+ */
+ refblock_offset = on_disk_reftable[refblock_index];
+ } else {
+ int64_t refblock_cluster_index;
- if (reftable_size <= refblock_index) {
- uint32_t old_reftable_size = reftable_size;
- uint64_t *new_on_disk_reftable;
+ /* Don't allocate a cluster in a refblock already written to disk */
+ if (first_free_cluster < refblock_start) {
+ first_free_cluster = refblock_start;
+ }
+ refblock_offset = alloc_clusters_imrt(bs, 1, refcount_table,
+ nb_clusters,
+ &first_free_cluster);
+ if (refblock_offset < 0) {
+ fprintf(stderr, "ERROR allocating refblock: %s\n",
+ strerror(-refblock_offset));
+ return refblock_offset;
+ }
- reftable_size = ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE,
- s->cluster_size) / REFTABLE_ENTRY_SIZE;
- new_on_disk_reftable = g_try_realloc(on_disk_reftable,
- reftable_size *
- REFTABLE_ENTRY_SIZE);
- if (!new_on_disk_reftable) {
- res->check_errors++;
- ret = -ENOMEM;
- goto fail;
+ refblock_cluster_index = refblock_offset / s->cluster_size;
+ if (refblock_cluster_index >= end_cluster) {
+ /*
+ * We must write the refblock that holds this refblock's
+ * refcount
+ */
+ end_cluster = refblock_cluster_index + 1;
}
- on_disk_reftable = new_on_disk_reftable;
- memset(on_disk_reftable + old_reftable_size, 0,
- (reftable_size - old_reftable_size) * REFTABLE_ENTRY_SIZE);
+ if (on_disk_reftable_entries <= refblock_index) {
+ on_disk_reftable_entries =
+ ROUND_UP((refblock_index + 1) * REFTABLE_ENTRY_SIZE,
+ s->cluster_size) / REFTABLE_ENTRY_SIZE;
+ on_disk_reftable =
+ g_try_realloc(on_disk_reftable,
+ on_disk_reftable_entries *
+ REFTABLE_ENTRY_SIZE);
+ if (!on_disk_reftable) {
+ return -ENOMEM;
+ }
- /* The offset we have for the reftable is now no longer valid;
- * this will leak that range, but we can easily fix that by running
- * a leak-fixing check after this rebuild operation */
- reftable_offset = -1;
- } else {
- assert(on_disk_reftable);
- }
- on_disk_reftable[refblock_index] = refblock_offset;
+ memset(on_disk_reftable + *on_disk_reftable_entries_ptr, 0,
+ (on_disk_reftable_entries -
+ *on_disk_reftable_entries_ptr) *
+ REFTABLE_ENTRY_SIZE);
- /* If this is apparently the last refblock (for now), try to squeeze the
- * reftable in */
- if (refblock_index == (*nb_clusters - 1) >> s->refcount_block_bits &&
- reftable_offset < 0)
- {
- uint64_t reftable_clusters = size_to_clusters(s, reftable_size *
- REFTABLE_ENTRY_SIZE);
- reftable_offset = alloc_clusters_imrt(bs, reftable_clusters,
- refcount_table, nb_clusters,
- &first_free_cluster);
- if (reftable_offset < 0) {
- fprintf(stderr, "ERROR allocating reftable: %s\n",
- strerror(-reftable_offset));
- res->check_errors++;
- ret = reftable_offset;
- goto fail;
+ *on_disk_reftable_ptr = on_disk_reftable;
+ *on_disk_reftable_entries_ptr = on_disk_reftable_entries;
+
+ reftable_grown = true;
+ } else {
+ assert(on_disk_reftable);
}
+ on_disk_reftable[refblock_index] = refblock_offset;
}
+ /* Refblock is allocated, write it to disk */
+
ret = qcow2_pre_write_overlap_check(bs, 0, refblock_offset,
s->cluster_size, false);
if (ret < 0) {
fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
- goto fail;
+ return ret;
}
- /* The size of *refcount_table is always cluster-aligned, therefore the
- * write operation will not overflow */
+ /*
+ * The refblock is simply a slice of *refcount_table.
+ * Note that the size of *refcount_table is always aligned to
+ * whole clusters, so the write operation will not result in
+ * out-of-bounds accesses.
+ */
on_disk_refblock = (void *)((char *) *refcount_table +
refblock_index * s->cluster_size);
@@ -2550,23 +2579,99 @@ write_refblocks:
s->cluster_size);
if (ret < 0) {
fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
- goto fail;
+ return ret;
}
- /* Go to the end of this refblock */
+ /* This refblock is done, skip to its end */
cluster = refblock_start + s->refcount_block_size - 1;
}
- if (reftable_offset < 0) {
- uint64_t post_refblock_start, reftable_clusters;
+ return reftable_grown;
+}
+
+/*
+ * Creates a new refcount structure based solely on the in-memory information
+ * given through *refcount_table (this in-memory information is basically just
+ * the concatenation of all refblocks). All necessary allocations will be
+ * reflected in that array.
+ *
+ * On success, the old refcount structure is leaked (it will be covered by the
+ * new refcount structure).
+ */
+static int rebuild_refcount_structure(BlockDriverState *bs,
+ BdrvCheckResult *res,
+ void **refcount_table,
+ int64_t *nb_clusters)
+{
+ BDRVQcow2State *s = bs->opaque;
+ int64_t reftable_offset = -1;
+ int64_t reftable_length = 0;
+ int64_t reftable_clusters;
+ int64_t refblock_index;
+ uint32_t on_disk_reftable_entries = 0;
+ uint64_t *on_disk_reftable = NULL;
+ int ret = 0;
+ int reftable_size_changed = 0;
+ struct {
+ uint64_t reftable_offset;
+ uint32_t reftable_clusters;
+ } QEMU_PACKED reftable_offset_and_clusters;
+
+ qcow2_cache_empty(bs, s->refcount_block_cache);
+
+ /*
+ * For each refblock containing entries, we try to allocate a
+ * cluster (in the in-memory refcount table) and write its offset
+ * into on_disk_reftable[]. We then write the whole refblock to
+ * disk (as a slice of the in-memory refcount table).
+ * This is done by rebuild_refcounts_write_refblocks().
+ *
+ * Once we have scanned all clusters, we try to find space for the
+ * reftable. This will dirty the in-memory refcount table (i.e.
+ * make it differ from the refblocks we have already written), so we
+ * need to run rebuild_refcounts_write_refblocks() again for the
+ * range of clusters where the reftable has been allocated.
+ *
+ * This second run might make the reftable grow again, in which case
+ * we will need to allocate another space for it, which is why we
+ * repeat all this until the reftable stops growing.
+ *
+ * (This loop will terminate, because with every cluster the
+ * reftable grows, it can accomodate a multitude of more refcounts,
+ * so that at some point this must be able to cover the reftable
+ * and all refblocks describing it.)
+ *
+ * We then convert the reftable to big-endian and write it to disk.
+ *
+ * Note that we never free any reftable allocations. Doing so would
+ * needlessly complicate the algorithm: The eventual second check
+ * run we do will clean up all leaks we have caused.
+ */
+
+ reftable_size_changed =
+ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,
+ 0, *nb_clusters,
+ &on_disk_reftable,
+ &on_disk_reftable_entries);
+ if (reftable_size_changed < 0) {
+ res->check_errors++;
+ ret = reftable_size_changed;
+ goto fail;
+ }
+
+ /*
+ * There was no reftable before, so rebuild_refcounts_write_refblocks()
+ * must have increased its size (from 0 to something).
+ */
+ assert(reftable_size_changed);
+
+ do {
+ int64_t reftable_start_cluster, reftable_end_cluster;
+ int64_t first_free_cluster = 0;
+
+ reftable_length = on_disk_reftable_entries * REFTABLE_ENTRY_SIZE;
+ reftable_clusters = size_to_clusters(s, reftable_length);
- post_refblock_start = ROUND_UP(*nb_clusters, s->refcount_block_size);
- reftable_clusters =
- size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE);
- /* Not pretty but simple */
- if (first_free_cluster < post_refblock_start) {
- first_free_cluster = post_refblock_start;
- }
reftable_offset = alloc_clusters_imrt(bs, reftable_clusters,
refcount_table, nb_clusters,
&first_free_cluster);
@@ -2578,24 +2683,55 @@ write_refblocks:
goto fail;
}
- goto write_refblocks;
- }
+ /*
+ * We need to update the affected refblocks, so re-run the
+ * write_refblocks loop for the reftable's range of clusters.
+ */
+ assert(offset_into_cluster(s, reftable_offset) == 0);
+ reftable_start_cluster = reftable_offset / s->cluster_size;
+ reftable_end_cluster = reftable_start_cluster + reftable_clusters;
+ reftable_size_changed =
+ rebuild_refcounts_write_refblocks(bs, refcount_table, nb_clusters,
+ reftable_start_cluster,
+ reftable_end_cluster,
+ &on_disk_reftable,
+ &on_disk_reftable_entries);
+ if (reftable_size_changed < 0) {
+ res->check_errors++;
+ ret = reftable_size_changed;
+ goto fail;
+ }
+
+ /*
+ * If the reftable size has changed, we will need to find a new
+ * allocation, repeating the loop.
+ */
+ } while (reftable_size_changed);
- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {
+ /* The above loop must have run at least once */
+ assert(reftable_offset >= 0);
+
+ /*
+ * All allocations are done, all refblocks are written, convert the
+ * reftable to big-endian and write it to disk.
+ */
+
+ for (refblock_index = 0; refblock_index < on_disk_reftable_entries;
+ refblock_index++)
+ {
cpu_to_be64s(&on_disk_reftable[refblock_index]);
}
- ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset,
- reftable_size * REFTABLE_ENTRY_SIZE,
+ ret = qcow2_pre_write_overlap_check(bs, 0, reftable_offset, reftable_length,
false);
if (ret < 0) {
fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
goto fail;
}
- assert(reftable_size < INT_MAX / REFTABLE_ENTRY_SIZE);
+ assert(reftable_length < INT_MAX);
ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,
- reftable_size * REFTABLE_ENTRY_SIZE);
+ reftable_length);
if (ret < 0) {
fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
goto fail;
@@ -2604,7 +2740,7 @@ write_refblocks:
/* Enter new reftable into the image header */
reftable_offset_and_clusters.reftable_offset = cpu_to_be64(reftable_offset);
reftable_offset_and_clusters.reftable_clusters =
- cpu_to_be32(size_to_clusters(s, reftable_size * REFTABLE_ENTRY_SIZE));
+ cpu_to_be32(reftable_clusters);
ret = bdrv_pwrite_sync(bs->file,
offsetof(QCowHeader, refcount_table_offset),
&reftable_offset_and_clusters,
@@ -2614,12 +2750,14 @@ write_refblocks:
goto fail;
}
- for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {
+ for (refblock_index = 0; refblock_index < on_disk_reftable_entries;
+ refblock_index++)
+ {
be64_to_cpus(&on_disk_reftable[refblock_index]);
}
s->refcount_table = on_disk_reftable;
s->refcount_table_offset = reftable_offset;
- s->refcount_table_size = reftable_size;
+ s->refcount_table_size = on_disk_reftable_entries;
update_max_refcount_table_index(s);
return 0;
--
2.31.1

92
kvm-qemu-nbd-Pass-max-connections-to-blockdev-layer.patch
View File

@ -1,92 +0,0 @@
From e6aae1d0368a152924c38775e517f4e83c1d898b Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Wed, 11 May 2022 19:49:23 -0500
Subject: [PATCH 1/2] qemu-nbd: Pass max connections to blockdev layer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 90: Advertise MULTI_CONN on writeable NBD servers
RH-Commit: [1/2] b0e33fd125bf3523b8b9a4dead3c8bb2342bfd4e (ebblake/centos-qemu-kvm)
RH-Bugzilla: 1708300
RH-Acked-by: Nir Soffer <None>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Daniel P. Berrangé <berrange@redhat.com>
The next patch wants to adjust whether the NBD server code advertises
MULTI_CONN based on whether it is known if the server limits to
exactly one client. For a server started by QMP, this information is
obtained through nbd_server_start (which can support more than one
export); but for qemu-nbd (which supports exactly one export), it is
controlled only by the command-line option -e/--shared. Since we
already have a hook function used by qemu-nbd, it's easiest to just
alter its signature to fit our needs.
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-Id: <20220512004924.417153-2-eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a5fced40212ed73c715ca298a2929dd4d99c9999)
Signed-off-by: Eric Blake <eblake@redhat.com>
---
blockdev-nbd.c | 8 ++++----
include/block/nbd.h | 2 +-
qemu-nbd.c | 2 +-
3 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/blockdev-nbd.c b/blockdev-nbd.c
index 9840d25a82..add41a23af 100644
--- a/blockdev-nbd.c
+++ b/blockdev-nbd.c
@@ -30,18 +30,18 @@ typedef struct NBDServerData {
} NBDServerData;
static NBDServerData *nbd_server;
-static bool is_qemu_nbd;
+static int qemu_nbd_connections = -1; /* Non-negative if this is qemu-nbd */
static void nbd_update_server_watch(NBDServerData *s);
-void nbd_server_is_qemu_nbd(bool value)
+void nbd_server_is_qemu_nbd(int max_connections)
{
- is_qemu_nbd = value;
+ qemu_nbd_connections = max_connections;
}
bool nbd_server_is_running(void)
{
- return nbd_server || is_qemu_nbd;
+ return nbd_server || qemu_nbd_connections >= 0;
}
static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
diff --git a/include/block/nbd.h b/include/block/nbd.h
index a98eb665da..c5a29ce1c6 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -344,7 +344,7 @@ void nbd_client_new(QIOChannelSocket *sioc,
void nbd_client_get(NBDClient *client);
void nbd_client_put(NBDClient *client);
-void nbd_server_is_qemu_nbd(bool value);
+void nbd_server_is_qemu_nbd(int max_connections);
bool nbd_server_is_running(void);
void nbd_server_start(SocketAddress *addr, const char *tls_creds,
const char *tls_authz, uint32_t max_connections,
diff --git a/qemu-nbd.c b/qemu-nbd.c
index 713e7557a9..8c25ae93df 100644
--- a/qemu-nbd.c
+++ b/qemu-nbd.c
@@ -1087,7 +1087,7 @@ int main(int argc, char **argv)
bs->detect_zeroes = detect_zeroes;
- nbd_server_is_qemu_nbd(true);
+ nbd_server_is_qemu_nbd(shared);
export_opts = g_new(BlockExportOptions, 1);
*export_opts = (BlockExportOptions) {
--
2.31.1

100
kvm-qtest-numa-test-Correct-CPU-and-NUMA-association-in-.patch
View File

@ -1,100 +0,0 @@
From a039ed652e6d2f5edcef9d5d1d3baec17ce7f929 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 04/16] qtest/numa-test: Correct CPU and NUMA association in
aarch64_numa_cpu()
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [4/6] 64e9908a179eb4fb586d662f70f275a81808e50c (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
In aarch64_numa_cpu(), the CPU and NUMA association is something
like below. Two threads in the same core/cluster/socket are
associated with two individual NUMA nodes, which is unreal as
Igor Mammedov mentioned. We don't expect the association to break
NUMA-to-socket boundary, which matches with the real world.
NUMA-node socket cluster core thread
------------------------------------------
0 0 0 0 0
1 0 0 0 1
This corrects the topology for CPUs and their association with
NUMA nodes. After this patch is applied, the CPU and NUMA
association becomes something like below, which looks real.
Besides, socket/cluster/core/thread IDs are all checked when
the NUMA node IDs are verified. It helps to check if the CPU
topology is properly populated or not.
NUMA-node socket cluster core thread
------------------------------------------
0 1 0 0 0
1 0 0 0 0
Suggested-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Acked-by: Igor Mammedov <imammedo@redhat.com>
Message-id: 20220503140304.855514-5-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit e280ecb39bc1629f74ea5479d464fd1608dc8f76)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
tests/qtest/numa-test.c | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c
index aeda8c774c..32e35daaae 100644
--- a/tests/qtest/numa-test.c
+++ b/tests/qtest/numa-test.c
@@ -224,17 +224,17 @@ static void aarch64_numa_cpu(const void *data)
g_autofree char *cli = NULL;
cli = make_cli(data, "-machine "
- "smp.cpus=2,smp.sockets=1,smp.clusters=1,smp.cores=1,smp.threads=2 "
+ "smp.cpus=2,smp.sockets=2,smp.clusters=1,smp.cores=1,smp.threads=1 "
"-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 "
- "-numa cpu,node-id=1,thread-id=0 "
- "-numa cpu,node-id=0,thread-id=1");
+ "-numa cpu,node-id=0,socket-id=1,cluster-id=0,core-id=0,thread-id=0 "
+ "-numa cpu,node-id=1,socket-id=0,cluster-id=0,core-id=0,thread-id=0");
qts = qtest_init(cli);
cpus = get_cpus(qts, &resp);
g_assert(cpus);
while ((e = qlist_pop(cpus))) {
QDict *cpu, *props;
- int64_t thread, node;
+ int64_t socket, cluster, core, thread, node;
cpu = qobject_to(QDict, e);
g_assert(qdict_haskey(cpu, "props"));
@@ -242,12 +242,18 @@ static void aarch64_numa_cpu(const void *data)
g_assert(qdict_haskey(props, "node-id"));
node = qdict_get_int(props, "node-id");
+ g_assert(qdict_haskey(props, "socket-id"));
+ socket = qdict_get_int(props, "socket-id");
+ g_assert(qdict_haskey(props, "cluster-id"));
+ cluster = qdict_get_int(props, "cluster-id");
+ g_assert(qdict_haskey(props, "core-id"));
+ core = qdict_get_int(props, "core-id");
g_assert(qdict_haskey(props, "thread-id"));
thread = qdict_get_int(props, "thread-id");
- if (thread == 0) {
+ if (socket == 0 && cluster == 0 && core == 0 && thread == 0) {
g_assert_cmpint(node, ==, 1);
- } else if (thread == 1) {
+ } else if (socket == 1 && cluster == 0 && core == 0 && thread == 0) {
g_assert_cmpint(node, ==, 0);
} else {
g_assert(false);
--
2.31.1

68
kvm-qtest-numa-test-Specify-CPU-topology-in-aarch64_numa.patch
View File

@ -1,68 +0,0 @@
From 66f3928b40991d8467a3da086688f73d061886c8 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 11 May 2022 18:01:35 +0800
Subject: [PATCH 02/16] qtest/numa-test: Specify CPU topology in
aarch64_numa_cpu()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 86: hw/arm/virt: Fix the default CPU topology
RH-Commit: [2/6] b851e7ad59e057825392ddf75e9040cc102a0385 (gwshan/qemu-rhel-9)
RH-Bugzilla: 2041823
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2041823
The CPU topology isn't enabled on arm/virt machine yet, but we're
going to do it in next patch. After the CPU topology is enabled by
next patch, "thread-id=1" becomes invalid because the CPU core is
preferred on arm/virt machine. It means these two CPUs have 0/1
as their core IDs, but their thread IDs are all 0. It will trigger
test failure as the following message indicates:
[14/21 qemu:qtest+qtest-aarch64 / qtest-aarch64/numa-test ERROR
1.48s killed by signal 6 SIGABRT
>>> G_TEST_DBUS_DAEMON=/home/gavin/sandbox/qemu.main/tests/dbus-vmstate-daemon.sh \
QTEST_QEMU_STORAGE_DAEMON_BINARY=./storage-daemon/qemu-storage-daemon \
QTEST_QEMU_BINARY=./qemu-system-aarch64 \
QTEST_QEMU_IMG=./qemu-img MALLOC_PERTURB_=83 \
/home/gavin/sandbox/qemu.main/build/tests/qtest/numa-test --tap -k
――――――――――――――――――――――――――――――――――――――――――――――
stderr:
qemu-system-aarch64: -numa cpu,node-id=0,thread-id=1: no match found
This fixes the issue by providing comprehensive SMP configurations
in aarch64_numa_cpu(). The SMP configurations aren't used before
the CPU topology is enabled in next patch.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Message-id: 20220503140304.855514-3-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit ac7199a2523ce2ccf8e685087a5d177eeca89b09)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
tests/qtest/numa-test.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c
index 90bf68a5b3..aeda8c774c 100644
--- a/tests/qtest/numa-test.c
+++ b/tests/qtest/numa-test.c
@@ -223,7 +223,8 @@ static void aarch64_numa_cpu(const void *data)
QTestState *qts;
g_autofree char *cli = NULL;
- cli = make_cli(data, "-machine smp.cpus=2 "
+ cli = make_cli(data, "-machine "
+ "smp.cpus=2,smp.sockets=1,smp.clusters=1,smp.cores=1,smp.threads=2 "
"-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 "
"-numa cpu,node-id=1,thread-id=0 "
"-numa cpu,node-id=0,thread-id=1");
--
2.31.1

106
kvm-redhat-Update-linux-headers-linux-kvm.h-to-v5.18-rc6.patch
View File

@ -1,106 +0,0 @@
From 236f216309261bc924e49014267998fdc2ef7f46 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 29 Jul 2022 16:55:34 +0200
Subject: [PATCH 28/32] redhat: Update linux-headers/linux/kvm.h to v5.18-rc6
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 109: Honor storage keys during emulation of I/O instructions
RH-Commit: [1/2] f306d7ff8efa64b14158388b95815ac556a25d8a (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2111994
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Claudio Imbrenda <None>
Upstream Status: RHEL-only
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2111994
Based on upstream commit e4082063e47e9731dbeb1c26174c17f6038f577f
("linux-headers: Update to v5.18-rc6"), but this is focusing on
the file linux-headers/linux/kvm.h only (since the other changes
related to the VFIO renaming might break some stuff).
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
linux-headers/linux/kvm.h | 27 +++++++++++++++++++++------
1 file changed, 21 insertions(+), 6 deletions(-)
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index d232feaae9..0d05d02ee4 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -445,7 +445,11 @@ struct kvm_run {
#define KVM_SYSTEM_EVENT_RESET 2
#define KVM_SYSTEM_EVENT_CRASH 3
__u32 type;
- __u64 flags;
+ __u32 ndata;
+ union {
+ __u64 flags;
+ __u64 data[16];
+ };
} system_event;
/* KVM_EXIT_S390_STSI */
struct {
@@ -562,9 +566,12 @@ struct kvm_s390_mem_op {
__u32 op; /* type of operation */
__u64 buf; /* buffer in userspace */
union {
- __u8 ar; /* the access register number */
+ struct {
+ __u8 ar; /* the access register number */
+ __u8 key; /* access key, ignored if flag unset */
+ };
__u32 sida_offset; /* offset into the sida */
- __u8 reserved[32]; /* should be set to 0 */
+ __u8 reserved[32]; /* ignored */
};
};
/* types for kvm_s390_mem_op->op */
@@ -572,9 +579,12 @@ struct kvm_s390_mem_op {
#define KVM_S390_MEMOP_LOGICAL_WRITE 1
#define KVM_S390_MEMOP_SIDA_READ 2
#define KVM_S390_MEMOP_SIDA_WRITE 3
+#define KVM_S390_MEMOP_ABSOLUTE_READ 4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
/* flags for kvm_s390_mem_op->flags */
#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
+#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
/* for KVM_INTERRUPT */
struct kvm_interrupt {
@@ -1134,6 +1144,12 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_GPA_BITS 207
#define KVM_CAP_XSAVE2 208
#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
+#define KVM_CAP_S390_MEM_OP_EXTENSION 211
+#define KVM_CAP_PMU_CAPABILITY 212
+#define KVM_CAP_DISABLE_QUIRKS2 213
+/* #define KVM_CAP_VM_TSC_CONTROL 214 */
+#define KVM_CAP_SYSTEM_EVENT_DATA 215
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1624,9 +1640,6 @@ struct kvm_enc_region {
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
-/* Available with KVM_CAP_XSAVE2 */
-#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
-
struct kvm_s390_pv_sec_parm {
__u64 origin;
__u64 length;
@@ -1973,6 +1986,8 @@ struct kvm_dirty_gfn {
#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
+#define KVM_PMU_CAP_DISABLE (1 << 0)
+
/**
* struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
* @flags: Some extra information for header, always 0 for now.
--
2.31.1

96
kvm-scsi-generic-Fix-emulated-block-limits-VPD-page.patch
View File

@ -1,96 +0,0 @@
From e5360c1e76fee8b8dcbcba7efbb1e36f0b48ac40 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Mon, 22 Aug 2022 14:53:20 +0200
Subject: [PATCH 01/23] scsi-generic: Fix emulated block limits VPD page
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 115: scsi-generic: Fix emulated block limits VPD page
RH-Bugzilla: 2120275
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/1] 336ba583311a80beeadd1900336056404f63211a (kmwolf/centos-qemu-kvm)
Commits 01ef8185b80 amd 24b36e9813e updated the way that the maximum
transfer length is calculated for patching block limits VPD page in an
INQUIRY response.
The same updates also need to be made for the case where the host device
does not support the block limits VPD page at all and we emulate the
whole page.
Without this fix, on host block devices a maximum transfer length of
(INT_MAX - sector_size) bytes is advertised to the guest, resulting in
I/O errors when a request that exceeds the host limits is made by the
guest. (Prior to commit 24b36e9813e, this code path would use the
max_transfer value from the host instead of INT_MAX, but still miss the
fix from 01ef8185b80 where max_transfer is also capped to max_iov
host pages, so it would be less wrong, but still wrong.)
Cc: qemu-stable@nongnu.org
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2096251
Fixes: 01ef8185b809af9d287e1a03a3f9d8ea8231118a
Fixes: 24b36e9813ec15da7db62e3b3621730710c5f020
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20220822125320.48257-1-kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 51e15194b0a091e5c40aab2eb234a1d36c5c58ee)
Resolved conflict: qemu_real_host_page_size() is a getter function in
current upstream, but still just a public global variable downstream.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
hw/scsi/scsi-generic.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index 0306ccc7b1..3742899839 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -147,6 +147,18 @@ static int execute_command(BlockBackend *blk,
return 0;
}
+static uint64_t calculate_max_transfer(SCSIDevice *s)
+{
+ uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
+ uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
+
+ assert(max_transfer);
+ max_transfer = MIN_NON_ZERO(max_transfer,
+ max_iov * qemu_real_host_page_size);
+
+ return max_transfer / s->blocksize;
+}
+
static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
{
uint8_t page, page_idx;
@@ -179,12 +191,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
(r->req.cmd.buf[1] & 0x01)) {
page = r->req.cmd.buf[2];
if (page == 0xb0) {
- uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
- uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
-
- assert(max_transfer);
- max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
- / s->blocksize;
+ uint64_t max_transfer = calculate_max_transfer(s);
stl_be_p(&r->buf[8], max_transfer);
/* Also take care of the opt xfer len. */
stl_be_p(&r->buf[12],
@@ -230,7 +237,7 @@ static int scsi_generic_emulate_block_limits(SCSIGenericReq *r, SCSIDevice *s)
uint8_t buf[64];
SCSIBlockLimits bl = {
- .max_io_sectors = blk_get_max_transfer(s->conf.blk) / s->blocksize
+ .max_io_sectors = calculate_max_transfer(s),
};
memset(r->buf, 0, r->buflen);
--
2.31.1

54
kvm-sysemu-tpm-Add-a-stub-function-for-TPM_IS_CRB.patch
View File

@ -1,54 +0,0 @@
From 74b3e92dcb9e343e135a681259514b4fd28086ea Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Fri, 6 May 2022 15:25:09 +0200
Subject: [PATCH 4/5] sysemu: tpm: Add a stub function for TPM_IS_CRB
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 84: vfio/common: Remove spurious tpm-crb-cmd misalignment warning
RH-Commit: [1/2] 0ab55ca1aa12a3a7cbdef5a378928f75e030e536 (eauger1/centos-qemu-kvm)
RH-Bugzilla: 2037612
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Andrew Jones <drjones@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2037612
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=45166961
Upstream Status: YES
Tested: With TPM-CRB and VFIO
In a subsequent patch, VFIO will need to recognize if
a memory region owner is a TPM CRB device. Hence VFIO
needs to use TPM_IS_CRB() even if CONFIG_TPM is unset. So
let's add a stub function.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Suggested-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Stefan Berger <stefanb@linnux.ibm.com>
Link: https://lore.kernel.org/r/20220506132510.1847942-2-eric.auger@redhat.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
(cherry picked from commit 4168cdad398843ed53d650a27651868b4d3e21c9)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
include/sysemu/tpm.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/include/sysemu/tpm.h b/include/sysemu/tpm.h
index 68b2206463..fb40e30ff6 100644
--- a/include/sysemu/tpm.h
+++ b/include/sysemu/tpm.h
@@ -80,6 +80,12 @@ static inline TPMVersion tpm_get_version(TPMIf *ti)
#define tpm_init() (0)
#define tpm_cleanup()
+/* needed for an alignment check in non-tpm code */
+static inline Object *TPM_IS_CRB(Object *obj)
+{
+ return NULL;
+}
+
#endif /* CONFIG_TPM */
#endif /* QEMU_TPM_H */
--
2.31.1

129
kvm-target-arm-deprecate-named-CPU-models.patch
View File

@ -1,129 +0,0 @@
From 1f8528b71d96c01dd6106f11681f4a4e2776ef5f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Mon, 21 Mar 2022 12:05:42 +0000
Subject: [PATCH 06/18] target/arm: deprecate named CPU models
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [6/6] afddeb9e898206fd04499f01c48caf7dc1a8b8ef (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
KVM requires use of the 'host' CPU model, so named CPU models are only
needed for TCG. Since we don't consider TCG to be supported we can
deprecate all the named CPU models. TCG users can rely on 'max' model.
Note: this has the effect of deprecating the default built-in CPU
model 'cortex-a57'. Applications using QEMU are expected to make an
explicit choice about which CPU model they want, since no builtin
default can suit all purposes.
https://bugzilla.redhat.com/show_bug.cgi?id=2060839
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
---
target/arm/cpu-qom.h | 1 +
target/arm/cpu.c | 5 +++++
target/arm/cpu.h | 2 ++
target/arm/cpu64.c | 8 +++++++-
target/arm/helper.c | 2 ++
5 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h
index 64c44cef2d..82e97249bc 100644
--- a/target/arm/cpu-qom.h
+++ b/target/arm/cpu-qom.h
@@ -35,6 +35,7 @@ typedef struct ARMCPUInfo {
const char *name;
void (*initfn)(Object *obj);
void (*class_init)(ObjectClass *oc, void *data);
+ const char *deprecation_note;
} ARMCPUInfo;
void arm_cpu_register(const ARMCPUInfo *info);
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 5d4ca7a227..c74b0fb462 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2105,8 +2105,13 @@ static void arm_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
acc->info = data;
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
}
void arm_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 23879de5fa..c0c9f680e5 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -33,6 +33,8 @@
#define KVM_HAVE_MCE_INJECTION 1
#endif
+#define RHEL_CPU_DEPRECATION "use 'host' / 'max'"
+
#define EXCP_UDEF 1 /* undefined instruction */
#define EXCP_SWI 2 /* software interrupt */
#define EXCP_PREFETCH_ABORT 3
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index e80b831073..c8f152891c 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -975,7 +975,8 @@ static void aarch64_a64fx_initfn(Object *obj)
#endif /* disabled for RHEL */
static const ARMCPUInfo aarch64_cpus[] = {
- { .name = "cortex-a57", .initfn = aarch64_a57_initfn },
+ { .name = "cortex-a57", .initfn = aarch64_a57_initfn,
+ .deprecation_note = RHEL_CPU_DEPRECATION },
#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a53", .initfn = aarch64_a53_initfn },
{ .name = "cortex-a72", .initfn = aarch64_a72_initfn },
@@ -1052,8 +1053,13 @@ static void aarch64_cpu_instance_init(Object *obj)
static void cpu_register_class_init(ObjectClass *oc, void *data)
{
ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
acc->info = data;
+
+ if (acc->info->deprecation_note) {
+ cc->deprecation_note = acc->info->deprecation_note;
+ }
}
void aarch64_cpu_register(const ARMCPUInfo *info)
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 7d14650615..3d34f63e49 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -8560,6 +8560,7 @@ void arm_cpu_list(void)
static void arm_cpu_add_definition(gpointer data, gpointer user_data)
{
ObjectClass *oc = data;
+ CPUClass *cc = CPU_CLASS(oc);
CpuDefinitionInfoList **cpu_list = user_data;
CpuDefinitionInfo *info;
const char *typename;
@@ -8569,6 +8570,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
info->name = g_strndup(typename,
strlen(typename) - strlen("-" TYPE_ARM_CPU));
info->q_typename = g_strdup(typename);
+ info->deprecated = !!cc->deprecation_note;
QAPI_LIST_PREPEND(*cpu_list, info);
}
--
2.35.3

273
kvm-target-i386-deprecate-CPUs-older-than-x86_64-v2-ABI.patch
View File

@ -1,273 +0,0 @@
From 577b04770e47aed0f88acb4a415ed04ddbe087f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Thu, 17 Mar 2022 17:59:22 +0000
Subject: [PATCH 04/18] target/i386: deprecate CPUs older than x86_64-v2 ABI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [4/6] 71f6043f11b31ffa841a2e14d24972e571c18a9e (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RHEL-9 is compiled with the x86_64-v2 ABI. We use this as a baseline to
select which CPUs we want to support, such that there is at least one
supported guest CPU that can be launched for every physical machine
capable of running RHEL-9 KVM.
Supported CPUs:
* QEMU models
base (QEMU internal)
host (host passthrough)
max (host passthrough for KVM,
all emulated features for TCG)
* Intel models
Icelake-Server
Icelake-Server-noTSX
Cascadelake-Server (2019)
Cascadelake-Server-noTSX (2019)
Skylake-Server (2016)
Skylake-Server-IBRS (2016)
Skylake-Server-noTSX-IBRS (2016)
Skylake-Client (2015)
Skylake-Client-IBRS (2015)
Skylake-Client-noTSX-IBRS (2015)
Broadwell (2014)
Broadwell-IBRS (2014)
Broadwell-noTSX (2014)
Broadwell-noTSX-IBRS (2014)
Haswell (2013)
Haswell-IBRS (2013)
Haswell-noTSX (2013)
Haswell-noTSX-IBRS (2013)
IvyBridge (2012)
IvyBridge-IBRS (2012)
SandyBridge (2011)
SandyBridge-IBRS (2011)
Westmere (2010)
Westmere-IBRS (2010)
Nehalem (2008)
Nehalem-IBRS (2008)
Cooperlake (2020)
Snowridge (2019)
KnightsMill (2017)
Denverton (2016)
* AMD models
EPYC-Milan (2021)
EPYC-Rome (2019)
EPYC (2017)
EPYC-IBPB (2017)
Opteron_G5 (2012)
Opteron_G4 (2011)
* Other
Dhyana (2018)
(I've omitted the many -vNNN versions for brevity)
Deprecated CPUs:
486
athlon
Conroe
core2duo
coreduo
Icelake-Client (already deprecated upstream)
Icelake-Client-noTSX (already deprecated upstream)
kvm32
kvm64
n270
Opteron_G1
Opteron_G2
Opteron_G3
Penryn
pentium2
pentium3
pentium
phenom
qemu32
qemu64
The deprecated CPU models are subject to removal in a future
major version of RHEL.
Note: this has the effect of deprecating the default built-in CPU
model 'qemu64'. Applications using QEMU are expected to make an
explicit choice about which CPU model they want, since no builtin
default can suit all purposes.
https://bugzilla.redhat.com/show_bug.cgi?id=2060839
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
---
target/i386/cpu.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index cb6b5467d0..87cb641b5f 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -1780,9 +1780,13 @@ static const CPUCaches epyc_milan_cache_info = {
* PT in VMX operation
*/
+#define RHEL_CPU_DEPRECATION \
+ "use at least 'Nehalem' / 'Opteron_G4', or 'host' / 'max'"
+
static const X86CPUDefinition builtin_x86_defs[] = {
{
.name = "qemu64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -1803,6 +1807,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "phenom",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
@@ -1835,6 +1840,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "core2duo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1877,6 +1883,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -1918,6 +1925,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "qemu32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 4,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1932,6 +1940,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -1962,6 +1971,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "coreduo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -1995,6 +2005,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "486",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 4,
@@ -2007,6 +2018,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 5,
@@ -2019,6 +2031,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2031,6 +2044,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 3,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2043,6 +2057,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "athlon",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_AMD,
.family = 6,
@@ -2058,6 +2073,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "n270",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2083,6 +2099,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Conroe",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2123,6 +2140,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Penryn",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -3832,6 +3850,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G1",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3852,6 +3871,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3874,6 +3894,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
--
2.35.3

48
kvm-target-ppc-cpu-models-Fix-ppc_cpu_aliases-list-for-R.patch
View File

@ -1,48 +0,0 @@
From 39642d0d37e2ef61ce7fde0bc284d37a365e4482 Mon Sep 17 00:00:00 2001
From: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Date: Mon, 2 May 2022 17:59:11 -0300
Subject: [PATCH 2/2] target/ppc/cpu-models: Fix ppc_cpu_aliases list for RHEL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Murilo Opsfelder Araújo <muriloo@linux.ibm.com>
RH-MergeRequest: 81: target/ppc/cpu-models: remove extraneous "#endif"
RH-Commit: [1/1] 5fff003ad3deb84c6a8e69ab90552a31edb3b058 (mopsfelder/centos-stream-src-qemu-kvm)
RH-Bugzilla: 2081022
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
The commit b9d28ecdedaf ("Enable/disable devices for RHEL") removed the
"#if 0" from the beginning of the ppc_cpu_aliases list, which broke the
build on ppc64le:
../target/ppc/cpu-models.c:904:2: error: #endif without #if
#endif
^
1 error generated.
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2081022
Fixes: b9d28ecdedaf (Enable/disable devices for RHEL)
Signed-off-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
---
target/ppc/cpu-models.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index dd78883410..528467eac1 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -746,6 +746,7 @@
/* PowerPC CPU aliases */
PowerPCCPUAlias ppc_cpu_aliases[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ "405", "405d4" },
{ "405cr", "405crc" },
{ "405gp", "405gpd" },
--
2.35.1

194
kvm-target-s390x-deprecate-CPUs-older-than-z14.patch
View File

@ -1,194 +0,0 @@
From 8459c305914e2a7a19dcd1662d54a89def7acfa6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Thu, 17 Mar 2022 17:59:22 +0000
Subject: [PATCH 05/18] target/s390x: deprecate CPUs older than z14
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [5/6] 2da9e06cf452287673f94f880a7eb8b2b37b7278 (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RHEL-9 is compiled with the z14 ABI. We use this as a baseline to
select which CPUs we want to support, such that there is at least one
supported guest CPU that can be launched for every physical
machine capable of running RHEL-9 KVM.
Supported CPUs:
gen15a-base
gen15a
gen15b-base
gen15b
gen16a-base
gen16a
gen16b-base
gen16b
max
qemu
z14.2-base
z14.2
z14-base
z14
z14ZR1-base
z14ZR1
Deprecated CPUs:
z10BC.2-base
z10BC.2
z10BC-base
z10BC
z10EC.2-base
z10EC.2
z10EC.3-base
z10EC.3
z10EC-base
z10EC
z114-base
z114
z13.2-base
z13.2
z13-base
z13s-base
z13s
z13
z196.2-base
z196.2
z196-base
z196
z800-base
z800
z890.2-base
z890.2
z890.3-base
z890.3
z890-base
z890
z900.2-base
z900.2
z900.3-base
z900.3
z900-base
z900
z990.2-base
z990.2
z990.3-base
z990.3
z990.4-base
z990.4
z990.5-base
z990.5
z990-base
z990
z9BC.2-base
z9BC.2
z9BC-base
z9BC
z9EC.2-base
z9EC.2
z9EC.3-base
z9EC.3
z9EC-base
z9EC
zBC12-base
zBC12
zEC12.2-base
zEC12.2
zEC12-base
zEC12
https://bugzilla.redhat.com/show_bug.cgi?id=2060839
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
---
target/s390x/cpu_models.c | 11 +++++++++++
target/s390x/cpu_models.h | 2 ++
target/s390x/cpu_models_sysemu.c | 2 ++
3 files changed, 15 insertions(+)
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index 6d71428056..9b9fc41676 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -45,6 +45,9 @@
* of a following release have been a superset of the previous release. With
* generation 15 one base feature and one optional feature have been deprecated.
*/
+
+#define RHEL_CPU_DEPRECATION "use at least 'z14', or 'host' / 'qemu' / 'max'"
+
static S390CPUDef s390_cpu_defs[] = {
CPUDEF_INIT(0x2064, 7, 1, 38, 0x00000000U, "z900", "IBM zSeries 900 GA1"),
CPUDEF_INIT(0x2064, 7, 2, 38, 0x00000000U, "z900.2", "IBM zSeries 900 GA2"),
@@ -852,22 +855,30 @@ static void s390_host_cpu_model_class_init(ObjectClass *oc, void *data)
static void s390_base_cpu_model_class_init(ObjectClass *oc, void *data)
{
S390CPUClass *xcc = S390_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
/* all base models are migration safe */
xcc->cpu_def = (const S390CPUDef *) data;
xcc->is_migration_safe = true;
xcc->is_static = true;
xcc->desc = xcc->cpu_def->desc;
+ if (xcc->cpu_def->gen < 14) {
+ cc->deprecation_note = RHEL_CPU_DEPRECATION;
+ }
}
static void s390_cpu_model_class_init(ObjectClass *oc, void *data)
{
S390CPUClass *xcc = S390_CPU_CLASS(oc);
+ CPUClass *cc = CPU_CLASS(oc);
/* model that can change between QEMU versions */
xcc->cpu_def = (const S390CPUDef *) data;
xcc->is_migration_safe = true;
xcc->desc = xcc->cpu_def->desc;
+ if (xcc->cpu_def->gen < 14) {
+ cc->deprecation_note = RHEL_CPU_DEPRECATION;
+ }
}
static void s390_qemu_cpu_model_class_init(ObjectClass *oc, void *data)
diff --git a/target/s390x/cpu_models.h b/target/s390x/cpu_models.h
index 74d1f87e4f..372160bcd7 100644
--- a/target/s390x/cpu_models.h
+++ b/target/s390x/cpu_models.h
@@ -38,6 +38,8 @@ struct S390CPUDef {
S390FeatBitmap full_feat;
/* used to init full_feat from generated data */
S390FeatInit full_init;
+ /* if deprecated, provides a suggestion */
+ const char *deprecation_note;
};
/* CPU model based on a CPU definition */
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 6a04ccab1b..f3b7c304ec 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -61,6 +61,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
CpuDefinitionInfo *info;
char *name = g_strdup(object_class_get_name(klass));
S390CPUClass *scc = S390_CPU_CLASS(klass);
+ CPUClass *cc = CPU_CLASS(klass);
/* strip off the -s390x-cpu */
g_strrstr(name, "-" TYPE_S390_CPU)[0] = 0;
@@ -70,6 +71,7 @@ static void create_cpu_model_list(ObjectClass *klass, void *opaque)
info->migration_safe = scc->is_migration_safe;
info->q_static = scc->is_static;
info->q_typename = g_strdup(object_class_get_name(klass));
+ info->deprecated = !!cc->deprecation_note;
/* check for unavailable features */
if (cpu_list_data->model) {
Object *obj;
--
2.35.3

103
kvm-target-s390x-kvm-Honor-storage-keys-during-emulation.patch
View File

@ -1,103 +0,0 @@
From 27c1d979a994f5afc59c3520af58d15aa5aae723 Mon Sep 17 00:00:00 2001
From: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Date: Fri, 6 May 2022 17:39:56 +0200
Subject: [PATCH 29/32] target/s390x: kvm: Honor storage keys during emulation
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 109: Honor storage keys during emulation of I/O instructions
RH-Commit: [2/2] 346dee1e13bfe1c074e4c6a4417091711d852f9c (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2111994
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Claudio Imbrenda <None>
Storage key controlled protection is currently not honored when
emulating instructions.
If available, enable key protection for the MEM_OP ioctl, thereby
enabling it for the s390_cpu_virt_mem_* functions, when using kvm.
As a result, the emulation of the following instructions honors storage
keys:
* CLP
The Synch I/O CLP command would need special handling in order
to support storage keys, but is currently not supported.
* CHSC
Performing commands asynchronously would require special
handling, but commands are currently always synchronous.
* STSI
* TSCH
Must (and does) not change channel if terminated due to
protection.
* MSCH
Suppressed on protection, works because fetching instruction.
* SSCH
Suppressed on protection, works because fetching instruction.
* STSCH
* STCRW
Suppressed on protection, this works because no partial store is
possible, because the operand cannot span multiple pages.
* PCISTB
* MPCIFC
* STPCIFC
Signed-off-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Message-Id: <20220506153956.2217601-3-scgl@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit 54354861d21b69ec0781f43e67b8d4f6edad7e3f)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2111994
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
target/s390x/kvm/kvm.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index 74f089d87f..1f1d1a33b8 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -152,12 +152,15 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
static int cap_sync_regs;
static int cap_async_pf;
static int cap_mem_op;
+static int cap_mem_op_extension;
static int cap_s390_irq;
static int cap_ri;
static int cap_hpage_1m;
static int cap_vcpu_resets;
static int cap_protected;
+static bool mem_op_storage_key_support;
+
static int active_cmma;
static int kvm_s390_query_mem_limit(uint64_t *memory_limit)
@@ -355,6 +358,8 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS);
cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF);
cap_mem_op = kvm_check_extension(s, KVM_CAP_S390_MEM_OP);
+ cap_mem_op_extension = kvm_check_extension(s, KVM_CAP_S390_MEM_OP_EXTENSION);
+ mem_op_storage_key_support = cap_mem_op_extension > 0;
cap_s390_irq = kvm_check_extension(s, KVM_CAP_S390_INJECT_IRQ);
cap_vcpu_resets = kvm_check_extension(s, KVM_CAP_S390_VCPU_RESETS);
cap_protected = kvm_check_extension(s, KVM_CAP_S390_PROTECTED);
@@ -843,6 +848,7 @@ int kvm_s390_mem_op(S390CPU *cpu, vaddr addr, uint8_t ar, void *hostbuf,
: KVM_S390_MEMOP_LOGICAL_READ,
.buf = (uint64_t)hostbuf,
.ar = ar,
+ .key = (cpu->env.psw.mask & PSW_MASK_KEY) >> PSW_SHIFT_KEY,
};
int ret;
@@ -852,6 +858,9 @@ int kvm_s390_mem_op(S390CPU *cpu, vaddr addr, uint8_t ar, void *hostbuf,
if (!hostbuf) {
mem_op.flags |= KVM_S390_MEMOP_F_CHECK_ONLY;
}
+ if (mem_op_storage_key_support) {
+ mem_op.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION;
+ }
ret = kvm_vcpu_ioctl(CPU(cpu), KVM_S390_MEM_OP, &mem_op);
if (ret < 0) {
--
2.31.1

157
kvm-tests-avocado-update-aarch64_virt-test-to-exercise-c.patch
View File

@ -1,157 +0,0 @@
From f52aa60217634c96fef59ce76b803a94610bf5c8 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 15 Jun 2022 15:28:27 +0200
Subject: [PATCH 01/18] tests/avocado: update aarch64_virt test to exercise
-cpu max
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Daniel P. Berrangé <berrange@redhat.com>
RH-MergeRequest: 94: i386, aarch64, s390x: deprecate many named CPU models
RH-Commit: [1/6] df6839e567180a4c32afd98852f68b2279e00f7c (berrange/centos-src-qemu)
RH-Bugzilla: 2060839
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2066824
commit 11593544df6f8febb3ce87015c22b429bf43c4c7
Author: Alex Bennée <alex.bennee@linaro.org>
Date: Tue Apr 19 10:09:56 2022 +0100
tests/avocado: update aarch64_virt test to exercise -cpu max
The Fedora 29 kernel is quite old and importantly fails when running
in LPA2 scenarios. As it's not really exercising much of the CPU space
replace it with a custom 5.16.12 kernel with all the architecture
options turned on. There is a minimal buildroot initramfs included in
the kernel which has a few tools for stress testing the memory
subsystem. The userspace also targets the Neoverse N1 processor so
would fail with a v8.0 cpu like cortex-a53.
While we are at it move the test into its own file so it can have an
assigned maintainer.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Acked-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220419091020.3008144-2-alex.bennee@linaro.org>
Signed-off-by: Andrew Jones <drjones@redhat.com>
---
MAINTAINERS | 1 +
tests/avocado/boot_linux_console.py | 25 -------------
tests/avocado/machine_aarch64_virt.py | 51 +++++++++++++++++++++++++++
3 files changed, 52 insertions(+), 25 deletions(-)
create mode 100644 tests/avocado/machine_aarch64_virt.py
diff --git a/MAINTAINERS b/MAINTAINERS
index 2fe20a49ab..bfe8806f60 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -942,6 +942,7 @@ S: Maintained
F: hw/arm/virt*
F: include/hw/arm/virt.h
F: docs/system/arm/virt.rst
+F: tests/avocado/machine_aarch64_virt.py
Xilinx Zynq
M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py
index b40a3abc81..45a2ceda22 100644
--- a/tests/avocado/boot_linux_console.py
+++ b/tests/avocado/boot_linux_console.py
@@ -325,31 +325,6 @@ def test_mips_malta32el_nanomips_64k_dbg(self):
kernel_hash = '18d1c68f2e23429e266ca39ba5349ccd0aeb7180'
self.do_test_mips_malta32el_nanomips(kernel_url, kernel_hash)
- def test_aarch64_virt(self):
- """
- :avocado: tags=arch:aarch64
- :avocado: tags=machine:virt
- :avocado: tags=accel:tcg
- :avocado: tags=cpu:cortex-a53
- """
- kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
- '/linux/releases/29/Everything/aarch64/os/images/pxeboot'
- '/vmlinuz')
- kernel_hash = '8c73e469fc6ea06a58dc83a628fc695b693b8493'
- kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash)
-
- self.vm.set_console()
- kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
- 'console=ttyAMA0')
- self.require_accelerator("tcg")
- self.vm.add_args('-cpu', 'cortex-a53',
- '-accel', 'tcg',
- '-kernel', kernel_path,
- '-append', kernel_command_line)
- self.vm.launch()
- console_pattern = 'Kernel command line: %s' % kernel_command_line
- self.wait_for_console_pattern(console_pattern)
-
def test_aarch64_xlnx_versal_virt(self):
"""
:avocado: tags=arch:aarch64
diff --git a/tests/avocado/machine_aarch64_virt.py b/tests/avocado/machine_aarch64_virt.py
new file mode 100644
index 0000000000..21848cba70
--- /dev/null
+++ b/tests/avocado/machine_aarch64_virt.py
@@ -0,0 +1,51 @@
+# Functional test that boots a Linux kernel and checks the console
+#
+# Copyright (c) 2022 Linaro Ltd.
+#
+# Author:
+# Alex Bennée <alex.bennee@linaro.org>
+#
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+import time
+
+from avocado_qemu import QemuSystemTest
+from avocado_qemu import wait_for_console_pattern
+from avocado_qemu import exec_command
+
+class Aarch64VirtMachine(QemuSystemTest):
+ KERNEL_COMMON_COMMAND_LINE = 'printk.time=0 '
+
+ def wait_for_console_pattern(self, success_message, vm=None):
+ wait_for_console_pattern(self, success_message,
+ failure_message='Kernel panic - not syncing',
+ vm=vm)
+
+ def test_aarch64_virt(self):
+ """
+ :avocado: tags=arch:aarch64
+ :avocado: tags=machine:virt
+ :avocado: tags=accel:tcg
+ :avocado: tags=cpu:max
+ """
+ kernel_url = ('https://fileserver.linaro.org/s/'
+ 'z6B2ARM7DQT3HWN/download')
+
+ kernel_hash = 'ed11daab50c151dde0e1e9c9cb8b2d9bd3215347'
+ kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash)
+
+ self.vm.set_console()
+ kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
+ 'console=ttyAMA0')
+ self.require_accelerator("tcg")
+ self.vm.add_args('-cpu', 'max,pauth-impdef=on',
+ '-accel', 'tcg',
+ '-kernel', kernel_path,
+ '-append', kernel_command_line)
+ self.vm.launch()
+ self.wait_for_console_pattern('Welcome to Buildroot')
+ time.sleep(0.1)
+ exec_command(self, 'root')
+ time.sleep(0.1)
+ exec_command(self, 'cat /proc/self/maps')
+ time.sleep(0.1)
--
2.35.3

119
kvm-tests-qtest-fdc-test-Add-a-regression-test-for-CVE-2.patch
View File

@ -1,119 +0,0 @@
From cea7b15c613a11ea15a1458d6990be7044df6643 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= <philmd@redhat.com>
Date: Thu, 18 Nov 2021 12:57:33 +0100
Subject: [PATCH 17/17] tests/qtest/fdc-test: Add a regression test for
CVE-2021-3507
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 107: hw/block/fdc: Prevent end-of-track overrun (CVE-2021-3507)
RH-Commit: [2/2] 067c052df790959c28c1fcc16547676d36523bd9 (mrezanin/centos-src-qemu-kvm)
RH-Bugzilla: 1951522
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
Add the reproducer from https://gitlab.com/qemu-project/qemu/-/issues/339
Without the previous commit, when running 'make check-qtest-i386'
with QEMU configured with '--enable-sanitizers' we get:
==4028352==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x619000062a00 at pc 0x5626d03c491a bp 0x7ffdb4199410 sp 0x7ffdb4198bc0
READ of size 786432 at 0x619000062a00 thread T0
#0 0x5626d03c4919 in __asan_memcpy (qemu-system-i386+0x1e65919)
#1 0x5626d1c023cc in flatview_write_continue softmmu/physmem.c:2787:13
#2 0x5626d1bf0c0f in flatview_write softmmu/physmem.c:2822:14
#3 0x5626d1bf0798 in address_space_write softmmu/physmem.c:2914:18
#4 0x5626d1bf0f37 in address_space_rw softmmu/physmem.c:2924:16
#5 0x5626d1bf14c8 in cpu_physical_memory_rw softmmu/physmem.c:2933:5
#6 0x5626d0bd5649 in cpu_physical_memory_write include/exec/cpu-common.h:82:5
#7 0x5626d0bd0a07 in i8257_dma_write_memory hw/dma/i8257.c:452:9
#8 0x5626d09f825d in fdctrl_transfer_handler hw/block/fdc.c:1616:13
#9 0x5626d0a048b4 in fdctrl_start_transfer hw/block/fdc.c:1539:13
#10 0x5626d09f4c3e in fdctrl_write_data hw/block/fdc.c:2266:13
#11 0x5626d09f22f7 in fdctrl_write hw/block/fdc.c:829:9
#12 0x5626d1c20bc5 in portio_write softmmu/ioport.c:207:17
0x619000062a00 is located 0 bytes to the right of 512-byte region [0x619000062800,0x619000062a00)
allocated by thread T0 here:
#0 0x5626d03c66ec in posix_memalign (qemu-system-i386+0x1e676ec)
#1 0x5626d2b988d4 in qemu_try_memalign util/oslib-posix.c:210:11
#2 0x5626d2b98b0c in qemu_memalign util/oslib-posix.c:226:27
#3 0x5626d09fbaf0 in fdctrl_realize_common hw/block/fdc.c:2341:20
#4 0x5626d0a150ed in isabus_fdc_realize hw/block/fdc-isa.c:113:5
#5 0x5626d2367935 in device_set_realized hw/core/qdev.c:531:13
SUMMARY: AddressSanitizer: heap-buffer-overflow (qemu-system-i386+0x1e65919) in __asan_memcpy
Shadow bytes around the buggy address:
0x0c32800044f0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c3280004500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0c3280004510: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0c3280004520: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0c3280004530: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
=>0x0c3280004540:[fa]fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c3280004550: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c3280004560: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c3280004570: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c3280004580: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
0x0c3280004590: fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd fd
Shadow byte legend (one shadow byte represents 8 application bytes):
Addressable: 00
Heap left redzone: fa
Freed heap region: fd
==4028352==ABORTING
[ kwolf: Added snapshot=on to prevent write file lock failure ]
Reported-by: Alexander Bulekov <alxndr@bu.edu>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Alexander Bulekov <alxndr@bu.edu>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 46609b90d9e3a6304def11038a76b58ff43f77bc)
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
tests/qtest/fdc-test.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/tests/qtest/fdc-test.c b/tests/qtest/fdc-test.c
index b0d40012e6..1d4f852128 100644
--- a/tests/qtest/fdc-test.c
+++ b/tests/qtest/fdc-test.c
@@ -583,6 +583,26 @@ static void test_cve_2021_20196(void)
qtest_quit(s);
}
+static void test_cve_2021_3507(void)
+{
+ QTestState *s;
+
+ s = qtest_initf("-nographic -m 32M -nodefaults "
+ "-drive file=%s,format=raw,if=floppy,snapshot=on",
+ test_image);
+ qtest_outl(s, 0x9, 0x0a0206);
+ qtest_outw(s, 0x3f4, 0x1600);
+ qtest_outw(s, 0x3f4, 0x0000);
+ qtest_outw(s, 0x3f4, 0x0000);
+ qtest_outw(s, 0x3f4, 0x0000);
+ qtest_outw(s, 0x3f4, 0x0200);
+ qtest_outw(s, 0x3f4, 0x0200);
+ qtest_outw(s, 0x3f4, 0x0000);
+ qtest_outw(s, 0x3f4, 0x0000);
+ qtest_outw(s, 0x3f4, 0x0000);
+ qtest_quit(s);
+}
+
int main(int argc, char **argv)
{
int fd;
@@ -614,6 +634,7 @@ int main(int argc, char **argv)
qtest_add_func("/fdc/read_no_dma_19", test_read_no_dma_19);
qtest_add_func("/fdc/fuzz-registers", fuzz_registers);
qtest_add_func("/fdc/fuzz/cve_2021_20196", test_cve_2021_20196);
+ qtest_add_func("/fdc/fuzz/cve_2021_3507", test_cve_2021_3507);
ret = g_test_run();
--
2.31.1

70
kvm-util-Return-void-on-iova_tree_remove.patch
View File

@ -1,70 +0,0 @@
From 74c829f82eafa8e42ae94f7ace55c8aaed3bb5f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Wed, 27 Apr 2022 17:49:31 +0200
Subject: [PATCH 05/23] util: Return void on iova_tree_remove
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 116: vdpa: Restore device state on destination
RH-Bugzilla: 2114060
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/21] 252287acca896eba7b5d2b62fc6247cfc565ba57 (eperezmartin/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060
Upstream status: Merged
It always returns IOVA_OK so nobody uses it.
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20220427154931.3166388-1-eperezma@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
(cherry picked from commit 832fef7cc14d65f99d523f883ef384014e6476a7)
---
include/qemu/iova-tree.h | 4 +---
util/iova-tree.c | 4 +---
2 files changed, 2 insertions(+), 6 deletions(-)
diff --git a/include/qemu/iova-tree.h b/include/qemu/iova-tree.h
index c938fb0793..16bbfdf5f8 100644
--- a/include/qemu/iova-tree.h
+++ b/include/qemu/iova-tree.h
@@ -72,10 +72,8 @@ int iova_tree_insert(IOVATree *tree, const DMAMap *map);
* provided. The range does not need to be exactly what has inserted,
* all the mappings that are included in the provided range will be
* removed from the tree. Here map->translated_addr is meaningless.
- *
- * Return: 0 if succeeded, or <0 if error.
*/
-int iova_tree_remove(IOVATree *tree, const DMAMap *map);
+void iova_tree_remove(IOVATree *tree, const DMAMap *map);
/**
* iova_tree_find:
diff --git a/util/iova-tree.c b/util/iova-tree.c
index 6dff29c1f6..fee530a579 100644
--- a/util/iova-tree.c
+++ b/util/iova-tree.c
@@ -164,15 +164,13 @@ void iova_tree_foreach(IOVATree *tree, iova_tree_iterator iterator)
g_tree_foreach(tree->tree, iova_tree_traverse, iterator);
}
-int iova_tree_remove(IOVATree *tree, const DMAMap *map)
+void iova_tree_remove(IOVATree *tree, const DMAMap *map)
{
const DMAMap *overlap;
while ((overlap = iova_tree_find(tree, map))) {
g_tree_remove(tree->tree, overlap);
}
-
- return IOVA_OK;
}
/**
--
2.31.1

182
kvm-util-accept-iova_tree_remove_parameter-by-value.patch
View File

@ -1,182 +0,0 @@
From 90697579eaf598614293d75f684d6e8c55f8ab9b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Tue, 23 Aug 2022 20:20:04 +0200
Subject: [PATCH 06/23] util: accept iova_tree_remove_parameter by value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 116: vdpa: Restore device state on destination
RH-Bugzilla: 2114060
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [5/21] ddaf052789e7ab3c67a77c038347113301587ffb (eperezmartin/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2114060
Upstream status: git@github.com:jasowang/qemu.git net-next
It's convenient to call iova_tree_remove from a map returned from
iova_tree_find or iova_tree_find_iova. With the current code this is not
possible, since we will free it, and then we will try to search for it
again.
Fix it making accepting the map by value, forcing a copy of the
argument. Not applying a fixes tag, since there is no use like that at
the moment.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit d69ba6677405de86b3b617fc7688b549f84cf013)
---
hw/i386/intel_iommu.c | 6 +++---
hw/virtio/vhost-iova-tree.c | 2 +-
hw/virtio/vhost-iova-tree.h | 2 +-
hw/virtio/vhost-vdpa.c | 6 +++---
include/qemu/iova-tree.h | 2 +-
net/vhost-vdpa.c | 4 ++--
util/iova-tree.c | 4 ++--
7 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index c64aa81a83..6738cf0929 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -1157,7 +1157,7 @@ static int vtd_page_walk_one(IOMMUTLBEvent *event, vtd_page_walk_info *info)
return ret;
}
/* Drop any existing mapping */
- iova_tree_remove(as->iova_tree, &target);
+ iova_tree_remove(as->iova_tree, target);
/* Recover the correct type */
event->type = IOMMU_NOTIFIER_MAP;
entry->perm = cache_perm;
@@ -1170,7 +1170,7 @@ static int vtd_page_walk_one(IOMMUTLBEvent *event, vtd_page_walk_info *info)
trace_vtd_page_walk_one_skip_unmap(entry->iova, entry->addr_mask);
return 0;
}
- iova_tree_remove(as->iova_tree, &target);
+ iova_tree_remove(as->iova_tree, target);
}
trace_vtd_page_walk_one(info->domain_id, entry->iova,
@@ -3532,7 +3532,7 @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
map.iova = n->start;
map.size = size;
- iova_tree_remove(as->iova_tree, &map);
+ iova_tree_remove(as->iova_tree, map);
}
static void vtd_address_space_unmap_all(IntelIOMMUState *s)
diff --git a/hw/virtio/vhost-iova-tree.c b/hw/virtio/vhost-iova-tree.c
index 55fed1fefb..1339a4de8b 100644
--- a/hw/virtio/vhost-iova-tree.c
+++ b/hw/virtio/vhost-iova-tree.c
@@ -104,7 +104,7 @@ int vhost_iova_tree_map_alloc(VhostIOVATree *tree, DMAMap *map)
* @iova_tree: The vhost iova tree
* @map: The map to remove
*/
-void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map)
+void vhost_iova_tree_remove(VhostIOVATree *iova_tree, DMAMap map)
{
iova_tree_remove(iova_tree->iova_taddr_map, map);
}
diff --git a/hw/virtio/vhost-iova-tree.h b/hw/virtio/vhost-iova-tree.h
index 6a4f24e0f9..4adfd79ff0 100644
--- a/hw/virtio/vhost-iova-tree.h
+++ b/hw/virtio/vhost-iova-tree.h
@@ -22,6 +22,6 @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostIOVATree, vhost_iova_tree_delete);
const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *iova_tree,
const DMAMap *map);
int vhost_iova_tree_map_alloc(VhostIOVATree *iova_tree, DMAMap *map);
-void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map);
+void vhost_iova_tree_remove(VhostIOVATree *iova_tree, DMAMap map);
#endif
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index cc15b7d8ee..39aa70f52d 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -238,7 +238,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
fail_map:
if (v->shadow_vqs_enabled) {
- vhost_iova_tree_remove(v->iova_tree, &mem_region);
+ vhost_iova_tree_remove(v->iova_tree, mem_region);
}
fail:
@@ -298,7 +298,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
return;
}
iova = result->iova;
- vhost_iova_tree_remove(v->iova_tree, result);
+ vhost_iova_tree_remove(v->iova_tree, *result);
}
vhost_vdpa_iotlb_batch_begin_once(v);
ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize));
@@ -942,7 +942,7 @@ static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle,
needle->perm == IOMMU_RO);
if (unlikely(r != 0)) {
error_setg_errno(errp, -r, "Cannot map region to device");
- vhost_iova_tree_remove(v->iova_tree, needle);
+ vhost_iova_tree_remove(v->iova_tree, *needle);
}
return r == 0;
diff --git a/include/qemu/iova-tree.h b/include/qemu/iova-tree.h
index 16bbfdf5f8..8528e5c98f 100644
--- a/include/qemu/iova-tree.h
+++ b/include/qemu/iova-tree.h
@@ -73,7 +73,7 @@ int iova_tree_insert(IOVATree *tree, const DMAMap *map);
* all the mappings that are included in the provided range will be
* removed from the tree. Here map->translated_addr is meaningless.
*/
-void iova_tree_remove(IOVATree *tree, const DMAMap *map);
+void iova_tree_remove(IOVATree *tree, DMAMap map);
/**
* iova_tree_find:
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 411e71e6c2..ba65736f83 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -244,7 +244,7 @@ static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
}
- vhost_iova_tree_remove(tree, map);
+ vhost_iova_tree_remove(tree, *map);
}
static size_t vhost_vdpa_net_cvq_cmd_len(void)
@@ -297,7 +297,7 @@ static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
return true;
dma_map_err:
- vhost_iova_tree_remove(v->iova_tree, &map);
+ vhost_iova_tree_remove(v->iova_tree, map);
return false;
}
diff --git a/util/iova-tree.c b/util/iova-tree.c
index fee530a579..536789797e 100644
--- a/util/iova-tree.c
+++ b/util/iova-tree.c
@@ -164,11 +164,11 @@ void iova_tree_foreach(IOVATree *tree, iova_tree_iterator iterator)
g_tree_foreach(tree->tree, iova_tree_traverse, iterator);
}
-void iova_tree_remove(IOVATree *tree, const DMAMap *map)
+void iova_tree_remove(IOVATree *tree, DMAMap map)
{
const DMAMap *overlap;
- while ((overlap = iova_tree_find(tree, map))) {
+ while ((overlap = iova_tree_find(tree, &map))) {
g_tree_remove(tree->tree, overlap);
}
}
--
2.31.1

385
kvm-util-event-loop-base-Introduce-options-to-set-the-th.patch
View File

@ -1,385 +0,0 @@
From 7a6fa42d4a4263c94b9bf18290f9e7680ea9e7f4 Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Date: Mon, 25 Apr 2022 09:57:23 +0200
Subject: [PATCH 03/16] util/event-loop-base: Introduce options to set the
thread pool size
RH-Author: Nicolas Saenz Julienne <nsaenzju@redhat.com>
RH-MergeRequest: 93: util/thread-pool: Expose minimum and maximum size
RH-Commit: [3/3] af78a88ff3c69701cbb5f9e980c3d6ebbd13ff98
RH-Bugzilla: 2031024
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
The thread pool regulates itself: when idle, it kills threads until
empty, when in demand, it creates new threads until full. This behaviour
doesn't play well with latency sensitive workloads where the price of
creating a new thread is too high. For example, when paired with qemu's
'-mlock', or using safety features like SafeStack, creating a new thread
has been measured take multiple milliseconds.
In order to mitigate this let's introduce a new 'EventLoopBase'
property to set the thread pool size. The threads will be created during
the pool's initialization or upon updating the property's value, remain
available during its lifetime regardless of demand, and destroyed upon
freeing it. A properly characterized workload will then be able to
configure the pool to avoid any latency spikes.
Signed-off-by: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-id: 20220425075723.20019-4-nsaenzju@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 71ad4713cc1d7fca24388b828ef31ae6cb38a31c)
---
event-loop-base.c | 23 +++++++++++++
include/block/aio.h | 10 ++++++
include/block/thread-pool.h | 3 ++
include/sysemu/event-loop-base.h | 4 +++
iothread.c | 3 ++
qapi/qom.json | 10 +++++-
util/aio-posix.c | 1 +
util/async.c | 20 ++++++++++++
util/main-loop.c | 9 ++++++
util/thread-pool.c | 55 +++++++++++++++++++++++++++++---
10 files changed, 133 insertions(+), 5 deletions(-)
diff --git a/event-loop-base.c b/event-loop-base.c
index e7f99a6ec8..d5be4dc6fc 100644
--- a/event-loop-base.c
+++ b/event-loop-base.c
@@ -14,6 +14,7 @@
#include "qemu/osdep.h"
#include "qom/object_interfaces.h"
#include "qapi/error.h"
+#include "block/thread-pool.h"
#include "sysemu/event-loop-base.h"
typedef struct {
@@ -21,9 +22,22 @@ typedef struct {
ptrdiff_t offset; /* field's byte offset in EventLoopBase struct */
} EventLoopBaseParamInfo;
+static void event_loop_base_instance_init(Object *obj)
+{
+ EventLoopBase *base = EVENT_LOOP_BASE(obj);
+
+ base->thread_pool_max = THREAD_POOL_MAX_THREADS_DEFAULT;
+}
+
static EventLoopBaseParamInfo aio_max_batch_info = {
"aio-max-batch", offsetof(EventLoopBase, aio_max_batch),
};
+static EventLoopBaseParamInfo thread_pool_min_info = {
+ "thread-pool-min", offsetof(EventLoopBase, thread_pool_min),
+};
+static EventLoopBaseParamInfo thread_pool_max_info = {
+ "thread-pool-max", offsetof(EventLoopBase, thread_pool_max),
+};
static void event_loop_base_get_param(Object *obj, Visitor *v,
const char *name, void *opaque, Error **errp)
@@ -95,12 +109,21 @@ static void event_loop_base_class_init(ObjectClass *klass, void *class_data)
event_loop_base_get_param,
event_loop_base_set_param,
NULL, &aio_max_batch_info);
+ object_class_property_add(klass, "thread-pool-min", "int",
+ event_loop_base_get_param,
+ event_loop_base_set_param,
+ NULL, &thread_pool_min_info);
+ object_class_property_add(klass, "thread-pool-max", "int",
+ event_loop_base_get_param,
+ event_loop_base_set_param,
+ NULL, &thread_pool_max_info);
}
static const TypeInfo event_loop_base_info = {
.name = TYPE_EVENT_LOOP_BASE,
.parent = TYPE_OBJECT,
.instance_size = sizeof(EventLoopBase),
+ .instance_init = event_loop_base_instance_init,
.class_size = sizeof(EventLoopBaseClass),
.class_init = event_loop_base_class_init,
.abstract = true,
diff --git a/include/block/aio.h b/include/block/aio.h
index 5634173b12..d128558f1d 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -192,6 +192,8 @@ struct AioContext {
QSLIST_HEAD(, Coroutine) scheduled_coroutines;
QEMUBH *co_schedule_bh;
+ int thread_pool_min;
+ int thread_pool_max;
/* Thread pool for performing work and receiving completion callbacks.
* Has its own locking.
*/
@@ -769,4 +771,12 @@ void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
void aio_context_set_aio_params(AioContext *ctx, int64_t max_batch,
Error **errp);
+/**
+ * aio_context_set_thread_pool_params:
+ * @ctx: the aio context
+ * @min: min number of threads to have readily available in the thread pool
+ * @min: max number of threads the thread pool can contain
+ */
+void aio_context_set_thread_pool_params(AioContext *ctx, int64_t min,
+ int64_t max, Error **errp);
#endif
diff --git a/include/block/thread-pool.h b/include/block/thread-pool.h
index 7dd7d730a0..2020bcc92d 100644
--- a/include/block/thread-pool.h
+++ b/include/block/thread-pool.h
@@ -20,6 +20,8 @@
#include "block/block.h"
+#define THREAD_POOL_MAX_THREADS_DEFAULT 64
+
typedef int ThreadPoolFunc(void *opaque);
typedef struct ThreadPool ThreadPool;
@@ -33,5 +35,6 @@ BlockAIOCB *thread_pool_submit_aio(ThreadPool *pool,
int coroutine_fn thread_pool_submit_co(ThreadPool *pool,
ThreadPoolFunc *func, void *arg);
void thread_pool_submit(ThreadPool *pool, ThreadPoolFunc *func, void *arg);
+void thread_pool_update_params(ThreadPool *pool, struct AioContext *ctx);
#endif
diff --git a/include/sysemu/event-loop-base.h b/include/sysemu/event-loop-base.h
index fced4c9fea..2748bf6ae1 100644
--- a/include/sysemu/event-loop-base.h
+++ b/include/sysemu/event-loop-base.h
@@ -33,5 +33,9 @@ struct EventLoopBase {
/* AioContext AIO engine parameters */
int64_t aio_max_batch;
+
+ /* AioContext thread pool parameters */
+ int64_t thread_pool_min;
+ int64_t thread_pool_max;
};
#endif
diff --git a/iothread.c b/iothread.c
index 8fa2f3bfb8..529194a566 100644
--- a/iothread.c
+++ b/iothread.c
@@ -174,6 +174,9 @@ static void iothread_set_aio_context_params(EventLoopBase *base, Error **errp)
aio_context_set_aio_params(iothread->ctx,
iothread->parent_obj.aio_max_batch,
errp);
+
+ aio_context_set_thread_pool_params(iothread->ctx, base->thread_pool_min,
+ base->thread_pool_max, errp);
}
diff --git a/qapi/qom.json b/qapi/qom.json
index 7d4a2ac1b9..6a653c6636 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -508,10 +508,18 @@
# 0 means that the engine will use its default.
# (default: 0)
#
+# @thread-pool-min: minimum number of threads reserved in the thread pool
+# (default:0)
+#
+# @thread-pool-max: maximum number of threads the thread pool can contain
+# (default:64)
+#
# Since: 7.1
##
{ 'struct': 'EventLoopBaseProperties',
- 'data': { '*aio-max-batch': 'int' } }
+ 'data': { '*aio-max-batch': 'int',
+ '*thread-pool-min': 'int',
+ '*thread-pool-max': 'int' } }
##
# @IothreadProperties:
diff --git a/util/aio-posix.c b/util/aio-posix.c
index be0182a3c6..731f3826c0 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -15,6 +15,7 @@
#include "qemu/osdep.h"
#include "block/block.h"
+#include "block/thread-pool.h"
#include "qemu/main-loop.h"
#include "qemu/rcu.h"
#include "qemu/rcu_queue.h"
diff --git a/util/async.c b/util/async.c
index 2ea1172f3e..554ba70cca 100644
--- a/util/async.c
+++ b/util/async.c
@@ -563,6 +563,9 @@ AioContext *aio_context_new(Error **errp)
ctx->aio_max_batch = 0;
+ ctx->thread_pool_min = 0;
+ ctx->thread_pool_max = THREAD_POOL_MAX_THREADS_DEFAULT;
+
return ctx;
fail:
g_source_destroy(&ctx->source);
@@ -696,3 +699,20 @@ void qemu_set_current_aio_context(AioContext *ctx)
assert(!get_my_aiocontext());
set_my_aiocontext(ctx);
}
+
+void aio_context_set_thread_pool_params(AioContext *ctx, int64_t min,
+ int64_t max, Error **errp)
+{
+
+ if (min > max || !max || min > INT_MAX || max > INT_MAX) {
+ error_setg(errp, "bad thread-pool-min/thread-pool-max values");
+ return;
+ }
+
+ ctx->thread_pool_min = min;
+ ctx->thread_pool_max = max;
+
+ if (ctx->thread_pool) {
+ thread_pool_update_params(ctx->thread_pool, ctx);
+ }
+}
diff --git a/util/main-loop.c b/util/main-loop.c
index 5b13f456fa..a0f48186ab 100644
--- a/util/main-loop.c
+++ b/util/main-loop.c
@@ -30,6 +30,7 @@
#include "sysemu/replay.h"
#include "qemu/main-loop.h"
#include "block/aio.h"
+#include "block/thread-pool.h"
#include "qemu/error-report.h"
#include "qemu/queue.h"
#include "qemu/compiler.h"
@@ -187,12 +188,20 @@ int qemu_init_main_loop(Error **errp)
static void main_loop_update_params(EventLoopBase *base, Error **errp)
{
+ ERRP_GUARD();
+
if (!qemu_aio_context) {
error_setg(errp, "qemu aio context not ready");
return;
}
aio_context_set_aio_params(qemu_aio_context, base->aio_max_batch, errp);
+ if (*errp) {
+ return;
+ }
+
+ aio_context_set_thread_pool_params(qemu_aio_context, base->thread_pool_min,
+ base->thread_pool_max, errp);
}
MainLoop *mloop;
diff --git a/util/thread-pool.c b/util/thread-pool.c
index d763cea505..196835b4d3 100644
--- a/util/thread-pool.c
+++ b/util/thread-pool.c
@@ -58,7 +58,6 @@ struct ThreadPool {
QemuMutex lock;
QemuCond worker_stopped;
QemuSemaphore sem;
- int max_threads;
QEMUBH *new_thread_bh;
/* The following variables are only accessed from one AioContext. */
@@ -71,8 +70,27 @@ struct ThreadPool {
int new_threads; /* backlog of threads we need to create */
int pending_threads; /* threads created but not running yet */
bool stopping;
+ int min_threads;
+ int max_threads;
};
+static inline bool back_to_sleep(ThreadPool *pool, int ret)
+{
+ /*
+ * The semaphore timed out, we should exit the loop except when:
+ * - There is work to do, we raced with the signal.
+ * - The max threads threshold just changed, we raced with the signal.
+ * - The thread pool forces a minimum number of readily available threads.
+ */
+ if (ret == -1 && (!QTAILQ_EMPTY(&pool->request_list) ||
+ pool->cur_threads > pool->max_threads ||
+ pool->cur_threads <= pool->min_threads)) {
+ return true;
+ }
+
+ return false;
+}
+
static void *worker_thread(void *opaque)
{
ThreadPool *pool = opaque;
@@ -91,8 +109,9 @@ static void *worker_thread(void *opaque)
ret = qemu_sem_timedwait(&pool->sem, 10000);
qemu_mutex_lock(&pool->lock);
pool->idle_threads--;
- } while (ret == -1 && !QTAILQ_EMPTY(&pool->request_list));
- if (ret == -1 || pool->stopping) {
+ } while (back_to_sleep(pool, ret));
+ if (ret == -1 || pool->stopping ||
+ pool->cur_threads > pool->max_threads) {
break;
}
@@ -294,6 +313,33 @@ void thread_pool_submit(ThreadPool *pool, ThreadPoolFunc *func, void *arg)
thread_pool_submit_aio(pool, func, arg, NULL, NULL);
}
+void thread_pool_update_params(ThreadPool *pool, AioContext *ctx)
+{
+ qemu_mutex_lock(&pool->lock);
+
+ pool->min_threads = ctx->thread_pool_min;
+ pool->max_threads = ctx->thread_pool_max;
+
+ /*
+ * We either have to:
+ * - Increase the number available of threads until over the min_threads
+ * threshold.
+ * - Decrease the number of available threads until under the max_threads
+ * threshold.
+ * - Do nothing. The current number of threads fall in between the min and
+ * max thresholds. We'll let the pool manage itself.
+ */
+ for (int i = pool->cur_threads; i < pool->min_threads; i++) {
+ spawn_thread(pool);
+ }
+
+ for (int i = pool->cur_threads; i > pool->max_threads; i--) {
+ qemu_sem_post(&pool->sem);
+ }
+
+ qemu_mutex_unlock(&pool->lock);
+}
+
static void thread_pool_init_one(ThreadPool *pool, AioContext *ctx)
{
if (!ctx) {
@@ -306,11 +352,12 @@ static void thread_pool_init_one(ThreadPool *pool, AioContext *ctx)
qemu_mutex_init(&pool->lock);
qemu_cond_init(&pool->worker_stopped);
qemu_sem_init(&pool->sem, 0);
- pool->max_threads = 64;
pool->new_thread_bh = aio_bh_new(ctx, spawn_thread_bh_fn, pool);
QLIST_INIT(&pool->head);
QTAILQ_INIT(&pool->request_list);
+
+ thread_pool_update_params(pool, ctx);
}
ThreadPool *thread_pool_new(AioContext *ctx)
--
2.31.1

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