rpms
/
qemu-kvm
21
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

import qemu-kvm-7.2.0-10.el9

Browse Source
c9-beta imports/c9-beta/qemu-kvm-7.2.0-10.el9
CentOS Sources 2 years ago committed by MSVSphere Packaging Team
commit c65da14c2b
124 changed files with 24383 additions and 0 deletions
Show Stats Download Patch File Download Diff File

1
.gitignore vendored
Unescape View File

@ -0,0 +1 @@
SOURCES/qemu-7.2.0.tar.xz

1
.qemu-kvm.metadata
Unescape View File

@ -0,0 +1 @@
634a3e4b381cbf13085eb1568accb85cbd9d89c4 SOURCES/qemu-7.2.0.tar.xz

302
SOURCES/0004-Initial-redhat-build.patch
Unescape View File

@ -0,0 +1,302 @@
From ccc4a5bdc8c2f27678312364a7c12aeafd009bb6 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
This patch introduces redhat build structure in redhat subdirectory. In addition,
several issues are fixed in QEMU tree:
- Change of app name for sasl_server_init in VNC code from qemu to qemu-kvm
- As we use qemu-kvm as name in all places, this is updated to be consistent
- Man page renamed from qemu to qemu-kvm
- man page is installed using make install so we have to fix it in qemu tree
We disable make check due to issues with some of the tests.
This rebase is based on qemu-kvm-7.1.0-7.el9
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
Rebase changes (6.1.0):
- Move build to .distro
- Move changes for support file to related commit
- Added dependency for python3-sphinx-rtd_theme
- Removed --disable-sheepdog configure option
- Added new hw-display modules
- SASL initialization moved to ui/vnc-auth-sasl.c
- Add accel-qtest-<arch> and accel-tcg-x86_64 libraries
- Added hw-usb-host module
- Disable new configure options (bpf, nvmm, slirp-smbd)
- Use -pie for ksmctl build (annocheck complain fix)
Rebase changes (6.2.0):
- removed --disable-jemalloc and --disable-tcmalloc configure options
- added audio-oss.so
- added fdt requirement for x86_64
- tests/acceptance renamed to tests/avocado
- added multiboot_dma.bin
- Add -Wno-string-plus-int to extra flags
- Updated configure options
Rebase changes (7.0.0):
- Do not use -mlittle CFLAG on ppc64le
- Used upstream handling issue with ui/clipboard.c
- Use -mlittle-endian on ppc64le instead of deleteing it in configure
- Drop --disable-libxml2 option for configure (upstream)
- Remove vof roms
- Disable AVX2 support
- Use internal meson
- Disable new configure options (dbus-display and qga-vss)
- 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
Rebase changes (7.2.0 rc0):
- Switch --enable-slirp=system to --enable-slirp
Rebaes changes (7.2.0 rc2):
- Added new configure options (blkio and sndio, both disabled)
Rebase changes (7.2.0):
- Fix SRPM name generation to work on Fedora 37
- Switch back to system meson
Merged patches (6.0.0):
- 605758c902 Limit build on Power to qemu-img and qemu-ga only
Merged patches (6.1.0):
- f04f91751f Use cached tarballs
- 6581165c65 Remove message with running VM count
- 03c3cac9fc spec-file: build qemu-kvm without SPICE and QXL
- e0ae6c1f6c spec-file: Obsolete qemu-kvm-ui-spice
- 9d2e9f9ecf spec: Do not build qemu-kvm-block-gluster
- cf470b4234 spec: Do not link pcnet and ne2k_pci roms
- e981284a6b redhat: Install the s390-netboot.img that we've built
- 24ef557f33 spec: Remove usage of Group: tag
- c40d69b4f4 spec: Drop %defattr usage
- f8e98798ce spec: Clean up BuildRequires
- 47246b43ee spec: Remove iasl BuildRequires
- 170dc1cbe0 spec: Remove redundant 0 in conditionals
- 8718f6fa11 spec: Add more have_XXX conditionals
- a001269ce9 spec: Remove binutils versioned Requires
- 34545ee641 spec: Remove diffutils BuildRequires
- c2c82beac9 spec: Remove redundant Requires:
- 9314c231f4 spec: Add XXX_version macros
- c43db0bf0f spec: Add have_block_rbd
- 3ecb0c0319 qga: drop StandardError=syslog
- 018049dc80 Remove iscsi support
- a2edf18777 redhat: Replace the kvm-setup.service with a /etc/modules-load.d config file
- 387b5fbcfe redhat: Move qemu-kvm-docs dependency to qemu-kvm
- 4ead693178 redhat: introducting qemu-kvm-hw-usbredir
- 4dc6fc3035 redhat: use the standard vhost-user JSON path
- 84757178b4 Fix local build
- 8c394227dd spec: Restrict block drivers in tools
- b6aa7c1fae Move tools to separate package
- eafd82e509 Split qemu-pr-helper to separate package
- 2c0182e2aa spec: RPM_BUILD_ROOT -> %{buildroot}
- 91bd55ca13 spec: More use of %{name} instead of 'qemu-kvm'
- 50ba299c61 spec: Use qemu-pr-helper.service from qemu.git (partial)
- ee08d4e0a3 spec: Use %{_sourcedir} for referencing sources
- 039e7f7d02 spec: Add tools_only
- 884ba71617 spec: %build: Add run_configure helper
- 8ebd864d65 spec: %build: Disable more bits with %{disable_everything} (partial)
- f23fdb53f5 spec: %build: Add macros for some 'configure' parameters
- fe951a8bd8 spec: %files: Move qemu-guest-agent and qemu-img earlier
- 353b632e37 spec: %install: Remove redundant bits
- 9d2015b752 spec: %install: Add %{modprobe_kvm_conf} macro
- 6d05134e8c spec: %install: Remove qemu-guest-agent /etc/qemu-kvm usage
- 985b226467 spec: %install: clean up qemu-ga section
- dfaf9c600d spec: %install: Use a single %{tools_only} section
- f6978ddb46 spec: Make tools_only not cross spec sections
- 071c211098 spec: %install: Limit time spent in %{qemu_kvm_build}
- 1b65c674be spec: misc syntactic merges with Fedora
- 4da16294cf spec: Use Fedora's pattern for specifying rc version
- d7ee259a79 spec: %files: don't use fine grained -docs file list
- 64cad0c60f spec: %files: Add licenses to qemu-common too
- c3de4f080a spec: %install: Drop python3 shebang fixup
- 46fc216115 Update local build to work with spec file improvements
- bab9531548 spec: Remove buildldflags
- c8360ab6a9 spec: Use %make_build macro
- f6966c66e9 spec: Drop make install sharedir and datadir usage
- 86982421bc spec: use %make_install macro
- 191c405d22 spec: parallelize `make check`
- 251a1fb958 spec: Drop explicit --build-id
- 44c7dda6c3 spec: use %{build_ldflags}
- 0009a34354 Move virtiofsd to separate package
- 34d1b200b3 Utilize --firmware configure option
- 2800e1dd03 spec: Switch toolchain to Clang/LLVM (except process-patches.sh)
- e8a70f500f spec: Use safe-stack for x86_64
- e29445d50d spec: Reenable write support for VMDK etc. in tools
- a4fe2a3e16 redhat: Disable LTO on non-x86 architectures
Merged patches (6.2.0):
- 333452440b remove sgabios dependency
- 7d3633f184 enable pulseaudio
- bd898709b0 spec: disable use of gcrypt for crypto backends in favour of gnutls
- e4f0c6dee6 spec: Remove block-curl and block-ssh dependency
- 4dc13bfe63 spec: Build the VDI block driver
- d2f2ff3c74 spec: Explicitly include compress filter
- a7d047f9c2 Move ksmtuned files to separate package
Merged patches (7.0.0):
- 098d4d08d0 spec: Rename qemu-kvm-hw-usbredir to qemu-kvm-device-usb-redirect
- c2bd0d6834 spec: Split qemu-kvm-ui-opengl
- 2c9cda805d spec: Introduce packages for virtio-gpu-* modules (changed as rhel device tree not set)
- d0414a3e0b spec: Introduce device-display-virtio-vga* packages
- 3534ec46d4 spec: Move usb-host module to separate package
- ddc14d4737 spec: Move qtest accel module to tests package
- 6f2c4befa6 spec: Extend qemu-kvm-core description
- 6f11866e4e (rhel/rhel-9.0.0) Update to qemu-kvm-6.2.0-6.el9
- da0a28758f ui/clipboard: fix use-after-free regression
- 895d4d52eb spec: Remove qemu-virtiofsd
- c8c8c8bd84 spec: Fix obsolete for spice subpackages
- d46d2710b2 spec: Obsolete old usb redir subpackage
- 6f52a50b68 spec: Obsolete ssh driver
Merged patches (7.2.0 rc4):
- 8c6834feb6 Remove opengl display device subpackages (C9S MR 124)
- 0ecc97f29e spec: Add requires for packages with additional virtio-gpu variants (C9S MR 124)
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
fix
---
.distro/Makefile | 100 +
.distro/Makefile.common | 41 +
.distro/README.tests | 39 +
.distro/modules-load.conf | 4 +
.distro/qemu-guest-agent.service | 1 -
.distro/qemu-kvm.spec.template | 4315 +++++++++++++++++++++++
.distro/rpminspect.yaml | 6 +-
.distro/scripts/extract_build_cmd.py | 12 +
.distro/scripts/process-patches.sh | 4 +
.gitignore | 1 +
README.systemtap | 43 +
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 +-
16 files changed, 4573 insertions(+), 4 deletions(-)
create mode 100644 .distro/Makefile
create mode 100644 .distro/Makefile.common
create mode 100644 .distro/README.tests
create mode 100644 .distro/modules-load.conf
create mode 100644 .distro/qemu-kvm.spec.template
create mode 100644 README.systemtap
create mode 100644 scripts/systemtap/conf.d/qemu_kvm.conf
create mode 100644 scripts/systemtap/script.d/qemu_kvm.stp
diff --git a/README.systemtap b/README.systemtap
new file mode 100644
index 0000000000..ad913fc990
--- /dev/null
+++ b/README.systemtap
@@ -0,0 +1,43 @@
+QEMU tracing using systemtap-initscript
+---------------------------------------
+
+You can capture QEMU trace data all the time using systemtap-initscript. This
+uses SystemTap's flight recorder mode to trace all running guests to a
+fixed-size buffer on the host. Old trace entries are overwritten by new
+entries when the buffer size wraps.
+
+1. Install the systemtap-initscript package:
+ # yum install systemtap-initscript
+
+2. Install the systemtap scripts and the conf file:
+ # cp /usr/share/qemu-kvm/systemtap/script.d/qemu_kvm.stp /etc/systemtap/script.d/
+ # cp /usr/share/qemu-kvm/systemtap/conf.d/qemu_kvm.conf /etc/systemtap/conf.d/
+
+The set of trace events to enable is given in qemu_kvm.stp. This SystemTap
+script can be customized to add or remove trace events provided in
+/usr/share/systemtap/tapset/qemu-kvm-simpletrace.stp.
+
+SystemTap customizations can be made to qemu_kvm.conf to control the flight
+recorder buffer size and whether to store traces in memory only or disk too.
+See stap(1) for option documentation.
+
+3. Start the systemtap service.
+　# service systemtap start qemu_kvm
+
+4. Make the service start at boot time.
+　# chkconfig systemtap on
+
+5. Confirm that the service works.
+ # service systemtap status qemu_kvm
+ qemu_kvm is running...
+
+When you want to inspect the trace buffer, perform the following steps:
+
+1. Dump the trace buffer.
+ # staprun -A qemu_kvm >/tmp/trace.log
+
+2. Start the systemtap service because the preceding step stops the service.
+ # service systemtap start qemu_kvm
+
+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/scripts/qemu-guest-agent/fsfreeze-hook b/scripts/qemu-guest-agent/fsfreeze-hook
index 13aafd4845..e9b84ec028 100755
--- a/scripts/qemu-guest-agent/fsfreeze-hook
+++ b/scripts/qemu-guest-agent/fsfreeze-hook
@@ -8,7 +8,7 @@
# request, it is issued with "thaw" argument after filesystem is thawed.
LOGFILE=/var/log/qga-fsfreeze-hook.log
-FSFREEZE_D=$(dirname -- "$0")/fsfreeze-hook.d
+FSFREEZE_D=$(dirname -- "$(realpath $0)")/fsfreeze-hook.d
# Check whether file $1 is a backup or rpm-generated file and should be ignored
is_ignored_file() {
diff --git a/scripts/systemtap/conf.d/qemu_kvm.conf b/scripts/systemtap/conf.d/qemu_kvm.conf
new file mode 100644
index 0000000000..372d8160a4
--- /dev/null
+++ b/scripts/systemtap/conf.d/qemu_kvm.conf
@@ -0,0 +1,4 @@
+# Force load uprobes (see BZ#1118352)
+stap -e 'probe process("/usr/libexec/qemu-kvm").function("main") { printf("") }' -c true
+
+qemu_kvm_OPT="-s4" # per-CPU buffer size, in megabytes
diff --git a/scripts/systemtap/script.d/qemu_kvm.stp b/scripts/systemtap/script.d/qemu_kvm.stp
new file mode 100644
index 0000000000..c04abf9449
--- /dev/null
+++ b/scripts/systemtap/script.d/qemu_kvm.stp
@@ -0,0 +1 @@
+probe qemu.kvm.simpletrace.handle_qmp_command,qemu.kvm.simpletrace.monitor_protocol_*,qemu.kvm.simpletrace.migrate_set_state {}
diff --git a/tests/check-block.sh b/tests/check-block.sh
index 5de2c1ba0b..6af743f441 100755
--- a/tests/check-block.sh
+++ b/tests/check-block.sh
@@ -22,6 +22,8 @@ if [ -z "$(find . -name 'qemu-system-*' -print)" ]; then
skip "No qemu-system binary available ==> Not running the qemu-iotests."
fi
+exit 0
+
cd tests/qemu-iotests
# QEMU_CHECK_BLOCK_AUTO is used to disable some unstable sub-tests
diff --git a/ui/vnc-auth-sasl.c b/ui/vnc-auth-sasl.c
index 47fdae5b21..2a950caa2a 100644
--- a/ui/vnc-auth-sasl.c
+++ b/ui/vnc-auth-sasl.c
@@ -42,7 +42,7 @@
bool vnc_sasl_server_init(Error **errp)
{
- int saslErr = sasl_server_init(NULL, "qemu");
+ int saslErr = sasl_server_init(NULL, "qemu-kvm");
if (saslErr != SASL_OK) {
error_setg(errp, "Failed to initialize SASL auth: %s",
--
2.31.1

657
SOURCES/0005-Enable-disable-devices-for-RHEL.patch
Unescape View File

@ -0,0 +1,657 @@
From 90366cd2ead5a5301aaceed56477d2e6d9f1b3cd Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 7 Dec 2022 03:05:48 -0500
Subject: Enable/disable devices for RHEL
This commit adds all changes related to changes in supported devices.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
Rebase notes (6.1.0):
- Added CONFIG_TPM (except s390x)
- default-configs moved to configs
- Use --with-device-<ARCH> configure option to use rhel configs
Rebase notes (6.2.0):
- Add CONFIG_ISA_FDC
- Do not remove -no-hpet documentation
Rebase notes (7.0.0):
- Added CONFIG_ARM_GIC_TCG option for aarch64
- Fixes necessary for layout change fixes
- 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)
Rebase notes (7.2.0 rc20):
- Removed disabling a15mpcore.c as no longer needed
Merged patches (6.1.0):
- c51bf45304 Remove SPICE and QXL from x86_64-rh-devices.mak
- 02fc745601 aarch64-rh-devices: add CONFIG_PVPANIC_PCI
- f2fe835153 aarch64-rh-devices: add CONFIG_PXB
- b5431733ad disable CONFIG_USB_STORAGE_BOT
- 478ba0cdf6 Disable TPM passthrough
- 2504d68a7c aarch64: Add USB storage devices
- 51c2a3253c disable ac97 audio
Merged patches (6.2.0):
- 9f2f9fa2ba disable sga device
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 | 41 +++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 37 ++++++
configs/devices/rh-virtio.mak | 10 ++
.../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 | 3 +-
hw/display/cirrus_vga.c | 5 +-
hw/ide/piix.c | 5 +-
hw/input/pckbd.c | 2 +
hw/net/e1000.c | 2 +
hw/ppc/spapr_cpu_core.c | 2 +
hw/usb/meson.build | 2 +-
target/arm/cpu_tcg.c | 10 ++
target/ppc/cpu-models.c | 9 ++
target/s390x/cpu_models_sysemu.c | 3 +
target/s390x/kvm/kvm.c | 8 ++
19 files changed, 283 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
create mode 100644 configs/devices/s390x-softmmu/s390x-rh-devices.mak
create mode 100644 configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
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..720ec0cb57
--- /dev/null
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -0,0 +1,41 @@
+include ../rh-virtio.mak
+
+CONFIG_ARM_GIC_KVM=y
+CONFIG_ARM_GICV3_TCG=y
+CONFIG_ARM_GIC=y
+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
+CONFIG_PCI_TESTDEV=y
+CONFIG_PFLASH_CFI01=y
+CONFIG_SCSI=y
+CONFIG_SEMIHOSTING=y
+CONFIG_USB=y
+CONFIG_USB_XHCI=y
+CONFIG_USB_XHCI_PCI=y
+CONFIG_USB_STORAGE_CORE=y
+CONFIG_USB_STORAGE_CLASSIC=y
+CONFIG_VFIO=y
+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
+CONFIG_TPM=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_TPM_TIS_SYSBUS=y
+CONFIG_PTIMER=y
+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..dbb7d30829
--- /dev/null
+++ b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
@@ -0,0 +1,37 @@
+include ../rh-virtio.mak
+
+CONFIG_DIMM=y
+CONFIG_MEM_DEVICE=y
+CONFIG_NVDIMM=y
+CONFIG_PCI=y
+CONFIG_PCI_DEVICES=y
+CONFIG_PCI_TESTDEV=y
+CONFIG_PCI_EXPRESS=y
+CONFIG_PSERIES=y
+CONFIG_SCSI=y
+CONFIG_SPAPR_VSCSI=y
+CONFIG_TEST_DEVICES=y
+CONFIG_USB=y
+CONFIG_USB_OHCI=y
+CONFIG_USB_OHCI_PCI=y
+CONFIG_USB_SMARTCARD=y
+CONFIG_USB_STORAGE_CORE=y
+CONFIG_USB_STORAGE_CLASSIC=y
+CONFIG_USB_XHCI=y
+CONFIG_USB_XHCI_NEC=y
+CONFIG_USB_XHCI_PCI=y
+CONFIG_VFIO=y
+CONFIG_VFIO_PCI=y
+CONFIG_VGA=y
+CONFIG_VGA_PCI=y
+CONFIG_VHOST_USER=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VGA=y
+CONFIG_WDT_IB6300ESB=y
+CONFIG_XICS=y
+CONFIG_XIVE=y
+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
--- /dev/null
+++ b/configs/devices/rh-virtio.mak
@@ -0,0 +1,10 @@
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_GPU=y
+CONFIG_VIRTIO_INPUT=y
+CONFIG_VIRTIO_INPUT_HOST=y
+CONFIG_VIRTIO_NET=y
+CONFIG_VIRTIO_RNG=y
+CONFIG_VIRTIO_SCSI=y
+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..69a799adbd
--- /dev/null
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -0,0 +1,18 @@
+include ../rh-virtio.mak
+
+CONFIG_PCI=y
+CONFIG_S390_CCW_VIRTIO=y
+CONFIG_S390_FLIC=y
+CONFIG_S390_FLIC_KVM=y
+CONFIG_SCLPCONSOLE=y
+CONFIG_SCSI=y
+CONFIG_VFIO=y
+CONFIG_VFIO_AP=y
+CONFIG_VFIO_CCW=y
+CONFIG_VFIO_PCI=y
+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..10cb0a14e0
--- /dev/null
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -0,0 +1,109 @@
+include ../rh-virtio.mak
+
+CONFIG_ACPI=y
+CONFIG_ACPI_PCI=y
+CONFIG_ACPI_CPU_HOTPLUG=y
+CONFIG_ACPI_MEMORY_HOTPLUG=y
+CONFIG_ACPI_NVDIMM=y
+CONFIG_ACPI_SMBUS=y
+CONFIG_ACPI_VMGENID=y
+CONFIG_ACPI_X86=y
+CONFIG_ACPI_X86_ICH=y
+CONFIG_AHCI=y
+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
+CONFIG_EDU=y
+CONFIG_FDC=y
+CONFIG_FDC_SYSBUS=y
+CONFIG_FDC_ISA=y
+CONFIG_FW_CFG_DMA=y
+CONFIG_HDA=y
+CONFIG_HYPERV=y
+CONFIG_HYPERV_TESTDEV=y
+CONFIG_I2C=y
+CONFIG_I440FX=y
+CONFIG_I8254=y
+CONFIG_I8257=y
+CONFIG_I8259=y
+CONFIG_I82801B11=y
+CONFIG_IDE_CORE=y
+CONFIG_IDE_PCI=y
+CONFIG_IDE_PIIX=y
+CONFIG_IDE_QDEV=y
+CONFIG_IOAPIC=y
+CONFIG_IOH3420=y
+CONFIG_ISA_BUS=y
+CONFIG_ISA_DEBUG=y
+CONFIG_ISA_TESTDEV=y
+CONFIG_LPC_ICH9=y
+CONFIG_MC146818RTC=y
+CONFIG_MEM_DEVICE=y
+CONFIG_NVDIMM=y
+CONFIG_OPENGL=y
+CONFIG_PAM=y
+CONFIG_PC=y
+CONFIG_PCI=y
+CONFIG_PCIE_PORT=y
+CONFIG_PCI_DEVICES=y
+CONFIG_PCI_EXPRESS=y
+CONFIG_PCI_EXPRESS_Q35=y
+CONFIG_PCI_I440FX=y
+CONFIG_PCI_TESTDEV=y
+CONFIG_PCKBD=y
+CONFIG_PCSPK=y
+CONFIG_PC_ACPI=y
+CONFIG_PC_PCI=y
+CONFIG_PFLASH_CFI01=y
+CONFIG_PVPANIC_ISA=y
+CONFIG_PXB=y
+CONFIG_Q35=y
+CONFIG_RTL8139_PCI=y
+CONFIG_SCSI=y
+CONFIG_SERIAL=y
+CONFIG_SERIAL_ISA=y
+CONFIG_SERIAL_PCI=y
+CONFIG_SEV=y
+CONFIG_SMBIOS=y
+CONFIG_SMBUS_EEPROM=y
+CONFIG_TEST_DEVICES=y
+CONFIG_USB=y
+CONFIG_USB_EHCI=y
+CONFIG_USB_EHCI_PCI=y
+CONFIG_USB_SMARTCARD=y
+CONFIG_USB_STORAGE_CORE=y
+CONFIG_USB_STORAGE_CLASSIC=y
+CONFIG_USB_UHCI=y
+CONFIG_USB_XHCI=y
+CONFIG_USB_XHCI_NEC=y
+CONFIG_USB_XHCI_PCI=y
+CONFIG_VFIO=y
+CONFIG_VFIO_PCI=y
+CONFIG_VGA=y
+CONFIG_VGA_CIRRUS=y
+CONFIG_VGA_PCI=y
+CONFIG_VHOST_USER=y
+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
+CONFIG_WDT_IB6300ESB=y
+CONFIG_WDT_IB700=y
+CONFIG_XIO3130=y
+CONFIG_TPM=y
+CONFIG_TPM_CRB=y
+CONFIG_TPM_TIS_ISA=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_SGX=y
+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 92f9f6e000..c5e94c997c 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -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'))
-arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c'))
+#arm_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m.c'))
arm_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210.c'))
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 64ae4a6899..9b8e782c19 100644
--- a/hw/block/fdc.c
+++ b/hw/block/fdc.c
@@ -49,6 +49,8 @@
#include "qom/object.h"
#include "fdc-internal.h"
+#include "hw/boards.h"
+
/********************************************************/
/* debug Floppy devices */
@@ -2346,6 +2348,14 @@ void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp)
FDrive *drive;
static int command_tables_inited = 0;
+ /* Restricted for Red Hat Enterprise Linux: */
+ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
+ if (!strstr(mc->name, "-rhel7.")) {
+ error_setg(errp, "Device %s is not supported with machine type %s",
+ object_get_typename(OBJECT(dev)), mc->name);
+ return;
+ }
+
if (fdctrl->fallback == FLOPPY_DRIVE_TYPE_AUTO) {
error_setg(errp, "Cannot choose a fallback FDrive type of 'auto'");
return;
diff --git a/hw/cpu/meson.build b/hw/cpu/meson.build
index 9e52fee9e7..87c209a754 100644
--- a/hw/cpu/meson.build
+++ b/hw/cpu/meson.build
@@ -1,4 +1,5 @@
-softmmu_ss.add(files('core.c', 'cluster.c'))
+#softmmu_ss.add(files('core.c', 'cluster.c'))
+softmmu_ss.add(files('core.c'))
specific_ss.add(when: 'CONFIG_ARM11MPCORE', if_true: files('arm11mpcore.c'))
specific_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview_mpcore.c'))
diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c
index 6e8c747c46..1948ebee8e 100644
--- a/hw/display/cirrus_vga.c
+++ b/hw/display/cirrus_vga.c
@@ -2946,7 +2946,10 @@ static void pci_cirrus_vga_realize(PCIDevice *dev, Error **errp)
PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
int16_t device_id = pc->device_id;
- /*
+ warn_report("'cirrus-vga' is deprecated, "
+ "please use a different VGA card instead");
+
+ /*
* Follow real hardware, cirrus card emulated has 4 MB video memory.
* Also accept 8 MB/16 MB for backward compatibility.
*/
diff --git a/hw/ide/piix.c b/hw/ide/piix.c
index 267dbf37db..87fcda4062 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -199,7 +199,8 @@ 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);
- dc->hotpluggable = false;
+ /* Disabled for Red Hat Enterprise Linux: */
+ dc->user_creatable = false;
}
static const TypeInfo piix3_ide_info = {
@@ -222,6 +223,8 @@ 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;
+ /* Disabled for Red Hat Enterprise Linux: */
+ dc->user_creatable = false;
}
static const TypeInfo piix4_ide_info = {
diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c
index b92b63bedc..3b6235dde6 100644
--- a/hw/input/pckbd.c
+++ b/hw/input/pckbd.c
@@ -957,6 +957,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
dc->vmsd = &vmstate_kbd_isa;
adevc->build_dev_aml = i8042_build_aml;
set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
+ /* Disabled for Red Hat Enterprise Linux: */
+ dc->user_creatable = false;
}
static const TypeInfo i8042_info = {
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index e26e0a64c1..41492fae79 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -1824,6 +1824,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
+#if 0 /* Disabled for Red Hat Enterprise Linux 7 */
{
.name = "e1000-82544gc",
.device_id = E1000_DEV_ID_82544GC_COPPER,
@@ -1836,6 +1837,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
+#endif
};
static void e1000_register_types(void)
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index 8a4861f45a..fcb5dfe792 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -379,10 +379,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = {
.instance_size = sizeof(SpaprCpuCore),
.class_size = sizeof(SpaprCpuCoreClass),
},
+#if 0 /* Disabled for Red Hat Enterprise Linux */
DEFINE_SPAPR_CPU_CORE_TYPE("970_v2.2"),
DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.0"),
DEFINE_SPAPR_CPU_CORE_TYPE("970mp_v1.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power5+_v2.1"),
+#endif
DEFINE_SPAPR_CPU_CORE_TYPE("power7_v2.3"),
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 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
if cacard.found()
usbsmartcard_ss = ss.source_set()
usbsmartcard_ss.add(when: 'CONFIG_USB_SMARTCARD',
- if_true: [cacard, files('ccid-card-emulated.c', 'ccid-card-passthru.c')])
+ if_true: [cacard, files('ccid-card-passthru.c')])
hw_usb_modules += {'smartcard': usbsmartcard_ss}
endif
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 9a2cef7d05..a528ff9a3d 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -151,6 +151,7 @@ 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)
+#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)
{
@@ -504,6 +505,7 @@ 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)
@@ -528,6 +530,7 @@ 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);
@@ -576,6 +579,7 @@ 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)
{
@@ -624,6 +628,7 @@ 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);
@@ -1065,6 +1070,7 @@ 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
/*
@@ -1132,6 +1138,7 @@ 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 },
@@ -1147,7 +1154,9 @@ 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 },
+#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,
@@ -1178,6 +1187,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
{ .name = "pxa270-b1", .initfn = pxa270b1_initfn },
{ .name = "pxa270-c0", .initfn = pxa270c0_initfn },
{ .name = "pxa270-c5", .initfn = pxa270c5_initfn },
+#endif /* disabled for RHEL */
#ifndef TARGET_AARCH64
{ .name = "max", .initfn = arm_max_initfn },
#endif
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index 912b037c63..cd3ff700ac 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -66,6 +66,7 @@
#define POWERPC_DEF(_name, _pvr, _type, _desc) \
POWERPC_DEF_SVR(_name, _desc, _pvr, POWERPC_SVR_NONE, _type)
+#if 0 /* Embedded and 32-bit CPUs disabled for Red Hat Enterprise Linux */
/* Embedded PowerPC */
/* PowerPC 405 family */
/* PowerPC 405 cores */
@@ -698,8 +699,10 @@
"PowerPC 7447A v1.2 (G4)")
POWERPC_DEF("7457a_v1.2", CPU_POWERPC_74x7A_v12, 7455,
"PowerPC 7457A v1.2 (G4)")
+#endif
/* 64 bits PowerPC */
#if defined(TARGET_PPC64)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
POWERPC_DEF("970_v2.2", CPU_POWERPC_970_v22, 970,
"PowerPC 970 v2.2")
POWERPC_DEF("970fx_v1.0", CPU_POWERPC_970FX_v10, 970,
@@ -718,6 +721,7 @@
"PowerPC 970MP v1.1")
POWERPC_DEF("power5+_v2.1", CPU_POWERPC_POWER5P_v21, POWER5P,
"POWER5+ v2.1")
+#endif
POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7,
"POWER7 v2.3")
POWERPC_DEF("power7+_v2.1", CPU_POWERPC_POWER7P_v21, POWER7,
@@ -896,12 +900,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "7447a", "7447a_v1.2" },
{ "7457a", "7457a_v1.2" },
{ "apollo7pm", "7457a_v1.0" },
+#endif
#if defined(TARGET_PPC64)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ "970", "970_v2.2" },
{ "970fx", "970fx_v3.1" },
{ "970mp", "970mp_v1.1" },
{ "power5+", "power5+_v2.1" },
{ "power5gs", "power5+_v2.1" },
+#endif
{ "power7", "power7_v2.3" },
{ "power7+", "power7+_v2.1" },
{ "power8e", "power8e_v2.1" },
@@ -911,12 +918,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power10", "power10_v2.0" },
#endif
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/* Generic PowerPCs */
#if defined(TARGET_PPC64)
{ "ppc64", "970fx_v3.1" },
#endif
{ "ppc32", "604" },
{ "ppc", "604" },
+#endif
{ NULL, NULL }
};
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index d8a141a023..d086b1c39c 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -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);
+ } else if (model->def->gen < 11 && kvm_enabled()) {
+ /* Older CPU models are not supported on Red Hat Enterprise Linux */
+ list_add_feat("type", unavailable);
}
/* detect missing features if any to properly report them */
diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c
index 3ac7ec9acf..97da1a6424 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -2529,6 +2529,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
error_setg(errp, "KVM doesn't support CPU models");
return;
}
+
+ /* Older CPU models are not supported on Red Hat Enterprise Linux */
+ if (model->def->gen < 11) {
+ error_setg(errp, "KVM: Unsupported CPU type specified: %s",
+ MACHINE(qdev_get_machine())->cpu_type);
+ return;
+ }
+
prop.cpuid = s390_cpuid_from_cpu_model(model);
prop.ibc = s390_ibc_from_cpu_model(model);
/* configure cpu features indicated via STFL(e) */
--
2.31.1

665
SOURCES/0006-Machine-type-related-general-changes.patch
Unescape View File

@ -0,0 +1,665 @@
From 0208f38671b9de4036c0d56142a7f22e5091bae0 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
This patch is first part of original "Add RHEL machine types" patch we
split to allow easier review. It contains changes not related to any
architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
Rebase notes (6.2.0):
- Do not duplicate minimal_version_id for piix4_pm
- Remove empty line chunks in serial.c
- Remove migration.h include in serial.c
- Update hw_compat_rhel_8_5 (from MR 66)
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
- a3995e2eff Remove RHEL 7.0.0 machine type (only generic changes)
- ad3190a79b Remove RHEL 7.1.0 machine type (only generic changes)
- 84bbe15d4e Remove RHEL 7.2.0 machine type (only generic changes)
- 0215eb3356 Remove RHEL 7.3.0 machine types (only generic changes)
- af69d1ca6e Remove RHEL 7.4.0 machine types (only generic changes)
- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only generic changes)
Merged patches (6.2.0):
- d687ac13d2 redhat: Define hw_compat_rhel_8_5
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)
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/acpi/piix4.c | 2 +-
hw/arm/virt.c | 2 +-
hw/core/machine.c | 222 +++++++++++++++++++++++++++++++++++
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/timer/i8254_common.c | 2 +-
hw/usb/hcd-xhci-pci.c | 59 +++++++---
hw/usb/hcd-xhci-pci.h | 1 +
include/hw/boards.h | 31 +++++
include/hw/firmware/smbios.h | 5 +-
include/hw/i386/pc.h | 3 +
14 files changed, 360 insertions(+), 23 deletions(-)
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index 0a81f1ad93..dbfb362a8f 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -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,
- .minimum_version_id = 3,
+ .minimum_version_id = 2,
.post_load = vmstate_acpi_post_load,
.fields = (VMStateField[]) {
VMSTATE_PCI_DEVICE(parent_obj, PIIX4PMState),
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index b871350856..d633300fdc 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1619,7 +1619,7 @@ static void virt_build_smbios(VirtMachineState *vms)
smbios_set_defaults("QEMU", product,
vmc->smbios_old_sys_ver ? "1.0" : mc->name, false,
- true, SMBIOS_ENTRY_POINT_TYPE_64);
+ true, NULL, NULL, SMBIOS_ENTRY_POINT_TYPE_64);
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 8d34caa31d..9edec1ca05 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -40,6 +40,228 @@
#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_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
+ */
+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
+ */
+GlobalProperty hw_compat_rhel_8_5[] = {
+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */
+ { "gpex-pcihost", "allow-unmapped-accesses", "false" },
+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */
+ { "i8042", "extended-state", "false"},
+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */
+ { "nvme-ns", "eui64-default", "off"},
+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */
+ { "e1000", "init-vet", "off" },
+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */
+ { "e1000e", "init-vet", "off" },
+ /* hw_compat_rhel_8_5 from hw_compat_6_0 */
+ { "vhost-vsock-device", "seqpacket", "off" },
+ /* hw_compat_rhel_8_5 from hw_compat_6_1 */
+ { "vhost-user-vsock-device", "seqpacket", "off" },
+ /* hw_compat_rhel_8_5 from hw_compat_6_1 */
+ { "nvme-ns", "shared", "off" },
+};
+const size_t hw_compat_rhel_8_5_len = G_N_ELEMENTS(hw_compat_rhel_8_5);
+
+/*
+ * Mostly the same as hw_compat_5_2
+ */
+GlobalProperty hw_compat_rhel_8_4[] = {
+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */
+ { "ICH9-LPC", "smm-compat", "on"},
+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */
+ { "PIIX4_PM", "smm-compat", "on"},
+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */
+ { "virtio-blk-device", "report-discard-granularity", "off" },
+ /* hw_compat_rhel_8_4 from hw_compat_5_2 */
+ /*
+ * Upstream incorrectly had "virtio-net-pci" instead of "virtio-net-pci-base",
+ * (https://bugzilla.redhat.com/show_bug.cgi?id=1999141)
+ */
+ { "virtio-net-pci-base", "vectors", "3"},
+};
+const size_t hw_compat_rhel_8_4_len = G_N_ELEMENTS(hw_compat_rhel_8_4);
+
+/*
+ * Mostly the same as hw_compat_5_1
+ */
+GlobalProperty hw_compat_rhel_8_3[] = {
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "vhost-scsi", "num_queues", "1"},
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "vhost-user-blk", "num-queues", "1"},
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "vhost-user-scsi", "num_queues", "1"},
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "virtio-blk-device", "num-queues", "1"},
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "virtio-scsi-device", "num_queues", "1"},
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "nvme", "use-intel-id", "on"},
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "pvpanic", "events", "1"}, /* PVPANIC_PANICKED */
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "pl011", "migrate-clk", "off" },
+ /* hw_compat_rhel_8_3 bz 1912846 */
+ { "pci-xhci", "x-rh-late-msi-cap", "off" },
+ /* hw_compat_rhel_8_3 from hw_compat_5_1 */
+ { "virtio-pci", "x-ats-page-aligned", "off"},
+};
+const size_t hw_compat_rhel_8_3_len = G_N_ELEMENTS(hw_compat_rhel_8_3);
+
+/*
+ * The same as hw_compat_4_2 + hw_compat_5_0
+ */
+GlobalProperty hw_compat_rhel_8_2[] = {
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "virtio-blk-device", "queue-size", "128"},
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "virtio-scsi-device", "virtqueue_size", "128"},
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "virtio-blk-device", "x-enable-wce-if-config-wce", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "virtio-blk-device", "seg-max-adjust", "off"},
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "virtio-scsi-device", "seg_max_adjust", "off"},
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "vhost-blk-device", "seg_max_adjust", "off"},
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "usb-host", "suppress-remote-wake", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "usb-redir", "suppress-remote-wake", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "qxl", "revision", "4" },
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "qxl-vga", "revision", "4" },
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "fw_cfg", "acpi-mr-restore", "false" },
+ /* hw_compat_rhel_8_2 from hw_compat_4_2 */
+ { "virtio-device", "use-disabled-flag", "false" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "pci-host-bridge", "x-config-reg-migration-enabled", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "virtio-balloon-device", "page-poison", "false" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "vmport", "x-read-set-eax", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "vmport", "x-signal-unsupported-cmd", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "vmport", "x-report-vmx-type", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "vmport", "x-cmds-v2", "off" },
+ /* hw_compat_rhel_8_2 from hw_compat_5_0 */
+ { "virtio-device", "x-disable-legacy-check", "true" },
+};
+const size_t hw_compat_rhel_8_2_len = G_N_ELEMENTS(hw_compat_rhel_8_2);
+
+/*
+ * The same as hw_compat_4_1
+ */
+GlobalProperty hw_compat_rhel_8_1[] = {
+ /* hw_compat_rhel_8_1 from hw_compat_4_1 */
+ { "virtio-pci", "x-pcie-flr-init", "off" },
+};
+const size_t hw_compat_rhel_8_1_len = G_N_ELEMENTS(hw_compat_rhel_8_1);
+
+/* The same as hw_compat_3_1
+ * format of array has been changed by:
+ * 6c36bddf5340 ("machine: Use shorter format for GlobalProperty arrays")
+ */
+GlobalProperty hw_compat_rhel_8_0[] = {
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "pcie-root-port", "x-speed", "2_5" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "pcie-root-port", "x-width", "1" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "memory-backend-file", "x-use-canonical-path-for-ramblock-id", "true" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "memory-backend-memfd", "x-use-canonical-path-for-ramblock-id", "true" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "tpm-crb", "ppi", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "tpm-tis", "ppi", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "usb-kbd", "serial", "42" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "usb-mouse", "serial", "42" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "usb-tablet", "serial", "42" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "virtio-blk-device", "discard", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 */
+ { "virtio-blk-device", "write-zeroes", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */
+ { "VGA", "edid", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */
+ { "secondary-vga", "edid", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */
+ { "bochs-display", "edid", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */
+ { "virtio-vga", "edid", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */
+ { "virtio-gpu-device", "edid", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_4_0 */
+ { "virtio-device", "use-started", "false" },
+ /* hw_compat_rhel_8_0 from hw_compat_3_1 - that was added in 4.1 */
+ { "pcie-root-port-base", "disable-acs", "true" },
+};
+const size_t hw_compat_rhel_8_0_len = G_N_ELEMENTS(hw_compat_rhel_8_0);
+
+/* The same as hw_compat_3_0 + hw_compat_2_12
+ * except that
+ * there's nothing in 3_0
+ * migration.decompress-error-check=off was in 7.5 from bz 1584139
+ */
+GlobalProperty hw_compat_rhel_7_6[] = {
+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */
+ { "hda-audio", "use-timer", "false" },
+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */
+ { "cirrus-vga", "global-vmstate", "true" },
+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */
+ { "VGA", "global-vmstate", "true" },
+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */
+ { "vmware-svga", "global-vmstate", "true" },
+ /* hw_compat_rhel_7_6 from hw_compat_2_12 */
+ { "qxl-vga", "global-vmstate", "true" },
+};
+const size_t hw_compat_rhel_7_6_len = G_N_ELEMENTS(hw_compat_rhel_7_6);
+
GlobalProperty hw_compat_7_1[] = {
{ "virtio-device", "queue_reset", "false" },
};
diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c
index 2a5437d803..0db2c2b2a1 100644
--- a/hw/display/vga-isa.c
+++ b/hw/display/vga-isa.c
@@ -89,7 +89,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp)
}
static Property vga_isa_properties[] = {
- DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 8),
+ DEFINE_PROP_UINT32("vgamem_mb", ISAVGAState, state.vram_size_mb, 16),
DEFINE_PROP_END_OF_LIST(),
};
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 0ad0ed1603..0985ff67d2 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -187,6 +187,8 @@ 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,
+ pcmc->smbios_stream_product,
+ pcmc->smbios_stream_version,
pcms->smbios_entry_point_type);
}
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index a496bd6e74..ea582254e3 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -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,
+ pcmc->smbios_stream_product,
+ pcmc->smbios_stream_version,
pcms->smbios_entry_point_type);
}
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 700b1b66b6..13693aeb4f 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -3178,7 +3178,7 @@ static int rtl8139_pre_save(void *opaque)
static const VMStateDescription vmstate_rtl8139 = {
.name = "rtl8139",
- .version_id = 5,
+ .version_id = 4,
.minimum_version_id = 3,
.post_load = rtl8139_post_load,
.pre_save = rtl8139_pre_save,
@@ -3259,7 +3259,9 @@ static const VMStateDescription vmstate_rtl8139 = {
VMSTATE_UINT32(tally_counters.TxMCol, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkPhy, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkBrd, RTL8139State),
+#if 0 /* Disabled for Red Hat Enterprise Linux bz 1420195 */
VMSTATE_UINT32_V(tally_counters.RxOkMul, RTL8139State, 5),
+#endif
VMSTATE_UINT16(tally_counters.TxAbt, RTL8139State),
VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State),
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index b4243de735..c5ad69237e 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -57,6 +57,9 @@ static bool smbios_legacy = true;
static bool smbios_uuid_encoded = true;
/* end: legacy structures & constants for <= 2.0 machines */
+/* Set to true for modern Windows 10 HardwareID-6 compat */
+static bool smbios_type2_required;
+
uint8_t *smbios_tables;
size_t smbios_tables_len;
@@ -669,7 +672,7 @@ static void smbios_build_type_1_table(void)
static void smbios_build_type_2_table(void)
{
- SMBIOS_BUILD_TABLE_PRE(2, T2_BASE, false); /* optional */
+ SMBIOS_BUILD_TABLE_PRE(2, T2_BASE, smbios_type2_required);
SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer);
SMBIOS_TABLE_SET_STR(2, product_str, type2.product);
@@ -977,7 +980,10 @@ void smbios_set_cpuid(uint32_t version, uint32_t features)
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version, bool legacy_mode,
- bool uuid_encoded, SmbiosEntryPointType ep_type)
+ bool uuid_encoded,
+ const char *stream_product,
+ const char *stream_version,
+ SmbiosEntryPointType ep_type)
{
smbios_have_defaults = true;
smbios_legacy = legacy_mode;
@@ -998,11 +1004,45 @@ void smbios_set_defaults(const char *manufacturer, const char *product,
g_free(smbios_entries);
}
+ /*
+ * If @stream_product & @stream_version are non-NULL, then
+ * we're following rules for new Windows driver support.
+ * The data we have to report is defined in this doc:
+ *
+ * https://docs.microsoft.com/en-us/windows-hardware/drivers/install/specifying-hardware-ids-for-a-computer
+ *
+ * The Windows drivers are written to expect use of the
+ * scheme documented as "HardwareID-6" against Windows 10,
+ * which uses SMBIOS System (Type 1) and Base Board (Type 2)
+ * tables and will match on
+ *
+ * System Manufacturer = Red Hat (@manufacturer)
+ * System SKU Number = 8.2.0 (@stream_version)
+ * Baseboard Manufacturer = Red Hat (@manufacturer)
+ * Baseboard Product = RHEL-AV (@stream_product)
+ *
+ * NB, SKU must be changed with each RHEL-AV release
+ *
+ * Other fields can be freely used by applications using
+ * QEMU. For example apps can use the "System product"
+ * and "System version" to identify themselves.
+ *
+ * We get 'System Manufacturer' and 'Baseboard Manufacturer'
+ */
SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type1.product, product);
SMBIOS_SET_DEFAULT(type1.version, version);
+ SMBIOS_SET_DEFAULT(type1.family, "Red Hat Enterprise Linux");
+ if (stream_version != NULL) {
+ SMBIOS_SET_DEFAULT(type1.sku, stream_version);
+ }
SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer);
- SMBIOS_SET_DEFAULT(type2.product, product);
+ if (stream_product != NULL) {
+ SMBIOS_SET_DEFAULT(type2.product, stream_product);
+ smbios_type2_required = true;
+ } else {
+ SMBIOS_SET_DEFAULT(type2.product, product);
+ }
SMBIOS_SET_DEFAULT(type2.version, version);
SMBIOS_SET_DEFAULT(type3.manufacturer, manufacturer);
SMBIOS_SET_DEFAULT(type3.version, version);
diff --git a/hw/timer/i8254_common.c b/hw/timer/i8254_common.c
index 050875b497..32935da46c 100644
--- a/hw/timer/i8254_common.c
+++ b/hw/timer/i8254_common.c
@@ -231,7 +231,7 @@ static const VMStateDescription vmstate_pit_common = {
.pre_save = pit_dispatch_pre_save,
.post_load = pit_dispatch_post_load,
.fields = (VMStateField[]) {
- VMSTATE_UINT32_V(channels[0].irq_disabled, PITCommonState, 3),
+ VMSTATE_UINT32(channels[0].irq_disabled, PITCommonState), /* qemu-kvm's v2 had 'flags' here */
VMSTATE_STRUCT_ARRAY(channels, PITCommonState, 3, 2,
vmstate_pit_channel, PITChannelState),
VMSTATE_INT64(channels[0].next_transition_time,
diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c
index 643d4643e4..529bad9366 100644
--- a/hw/usb/hcd-xhci-pci.c
+++ b/hw/usb/hcd-xhci-pci.c
@@ -104,6 +104,33 @@ static int xhci_pci_vmstate_post_load(void *opaque, int version_id)
return 0;
}
+/* RH bz 1912846 */
+static bool usb_xhci_pci_add_msi(struct PCIDevice *dev, Error **errp)
+{
+ int ret;
+ Error *err = NULL;
+ XHCIPciState *s = XHCI_PCI(dev);
+
+ ret = msi_init(dev, 0x70, s->xhci.numintrs, true, false, &err);
+ /*
+ * Any error other than -ENOTSUP(board's MSI support is broken)
+ * is a programming error
+ */
+ assert(!ret || ret == -ENOTSUP);
+ if (ret && s->msi == ON_OFF_AUTO_ON) {
+ /* Can't satisfy user's explicit msi=on request, fail */
+ error_append_hint(&err, "You have to use msi=auto (default) or "
+ "msi=off with this machine type.\n");
+ error_propagate(errp, err);
+ return true;
+ }
+ assert(!err || s->msi == ON_OFF_AUTO_AUTO);
+ /* With msi=auto, we fall back to MSI off silently */
+ error_free(err);
+
+ return false;
+}
+
static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp)
{
int ret;
@@ -125,23 +152,12 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp)
s->xhci.nec_quirks = true;
}
- if (s->msi != ON_OFF_AUTO_OFF) {
- ret = msi_init(dev, 0x70, s->xhci.numintrs, true, false, &err);
- /*
- * Any error other than -ENOTSUP(board's MSI support is broken)
- * is a programming error
- */
- assert(!ret || ret == -ENOTSUP);
- if (ret && s->msi == ON_OFF_AUTO_ON) {
- /* Can't satisfy user's explicit msi=on request, fail */
- error_append_hint(&err, "You have to use msi=auto (default) or "
- "msi=off with this machine type.\n");
+ if (s->msi != ON_OFF_AUTO_OFF && s->rh_late_msi_cap) {
+ /* This gives the behaviour from 5.2.0 onwards, lspci shows 90,a0,70 */
+ if (usb_xhci_pci_add_msi(dev, &err)) {
error_propagate(errp, err);
return;
}
- assert(!err || s->msi == ON_OFF_AUTO_AUTO);
- /* With msi=auto, we fall back to MSI off silently */
- error_free(err);
}
pci_register_bar(dev, 0,
PCI_BASE_ADDRESS_SPACE_MEMORY |
@@ -154,6 +170,14 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp)
assert(ret > 0);
}
+ /* RH bz 1912846 */
+ if (s->msi != ON_OFF_AUTO_OFF && !s->rh_late_msi_cap) {
+ /* This gives the older RH machine behaviour, lspci shows 90,70,a0 */
+ if (usb_xhci_pci_add_msi(dev, &err)) {
+ error_propagate(errp, err);
+ return;
+ }
+ }
if (s->msix != ON_OFF_AUTO_OFF) {
/* TODO check for errors, and should fail when msix=on */
msix_init(dev, s->xhci.numintrs,
@@ -198,11 +222,18 @@ static void xhci_instance_init(Object *obj)
qdev_alias_all_properties(DEVICE(&s->xhci), obj);
}
+static Property xhci_pci_properties[] = {
+ /* RH bz 1912846 */
+ DEFINE_PROP_BOOL("x-rh-late-msi-cap", XHCIPciState, rh_late_msi_cap, true),
+ DEFINE_PROP_END_OF_LIST()
+};
+
static void xhci_class_init(ObjectClass *klass, void *data)
{
PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
DeviceClass *dc = DEVICE_CLASS(klass);
+ device_class_set_props(dc, xhci_pci_properties);
dc->reset = xhci_pci_reset;
dc->vmsd = &vmstate_xhci_pci;
set_bit(DEVICE_CATEGORY_USB, dc->categories);
diff --git a/hw/usb/hcd-xhci-pci.h b/hw/usb/hcd-xhci-pci.h
index c193f79443..086a1feb1e 100644
--- a/hw/usb/hcd-xhci-pci.h
+++ b/hw/usb/hcd-xhci-pci.h
@@ -39,6 +39,7 @@ typedef struct XHCIPciState {
XHCIState xhci;
OnOffAuto msi;
OnOffAuto msix;
+ bool rh_late_msi_cap; /* bz 1912846 */
} XHCIPciState;
#endif
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 90f1dd3aeb..2209d4e416 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -454,4 +454,35 @@ 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;
+
+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;
+
+extern GlobalProperty hw_compat_rhel_8_4[];
+extern const size_t hw_compat_rhel_8_4_len;
+
+extern GlobalProperty hw_compat_rhel_8_3[];
+extern const size_t hw_compat_rhel_8_3_len;
+
+extern GlobalProperty hw_compat_rhel_8_2[];
+extern const size_t hw_compat_rhel_8_2_len;
+
+extern GlobalProperty hw_compat_rhel_8_1[];
+extern const size_t hw_compat_rhel_8_1_len;
+
+extern GlobalProperty hw_compat_rhel_8_0[];
+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;
#endif
diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h
index 7f3259a630..d24b3ccd32 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -294,7 +294,10 @@ void smbios_entry_add(QemuOpts *opts, Error **errp);
void smbios_set_cpuid(uint32_t version, uint32_t features);
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version, bool legacy_mode,
- bool uuid_encoded, SmbiosEntryPointType ep_type);
+ bool uuid_encoded,
+ const char *stream_product,
+ const char *stream_version,
+ SmbiosEntryPointType ep_type);
uint8_t *smbios_get_table_legacy(MachineState *ms, size_t *length);
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 c95333514e..3754eaa97d 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -112,6 +112,9 @@ struct PCMachineClass {
bool smbios_defaults;
bool smbios_legacy_mode;
bool smbios_uuid_encoded;
+ /* New fields needed for Windows HardwareID-6 matching */
+ const char *smbios_stream_product;
+ const char *smbios_stream_version;
/* RAM / address space compat: */
bool gigabyte_align;
--
2.31.1

675
SOURCES/0007-Add-aarch64-machine-types.patch
Unescape View File

@ -0,0 +1,675 @@
From 8501581c99760ed8a800d0c98eeb17a4bf450366 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
Adding changes to add RHEL machine types for aarch64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (6.1.0):
- Use CONFIG_TPM check when using TPM structures
- Add support for default_bus_bypass_iommu
- ea4c0b32d9 arm/virt: Register highmem and gic-version as class properties
- 895e1fa86a hw/arm/virt: Add 8.5 and 9.0 machine types and remove older ones
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
Rebase notes (7.2.0 rc0):
- Disabled cortex-a35
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
Merged patches (7.0.0):
- 3b82be3dd3 redhat: virt-rhel8.5.0: Update machine type compatibility for QEMU 6.2.0 update
- c354a86c9b hw/arm/virt: Register "iommu" as a class property
- c1a2630dc9 hw/arm/virt: Register "its" as a class property
- 9d8c61dc93 hw/arm/virt: Rename default_bus_bypass_iommu
- 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
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/arm/virt.c | 237 ++++++++++++++++++++++++++++++++-
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 | 16 ++-
target/arm/cpu_tcg.c | 12 +-
target/arm/helper.c | 2 +
tests/qtest/arm-cpu-features.c | 6 +
9 files changed, 277 insertions(+), 12 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index d633300fdc..dfcab40a73 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -80,6 +80,7 @@
#include "hw/char/pl011.h"
#include "qemu/guest-random.h"
+#if 0 /* Disabled for Red Hat Enterprise Linux */
#define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \
static void virt_##major##_##minor##_class_init(ObjectClass *oc, \
void *data) \
@@ -106,7 +107,48 @@
DEFINE_VIRT_MACHINE_LATEST(major, minor, true)
#define DEFINE_VIRT_MACHINE(major, minor) \
DEFINE_VIRT_MACHINE_LATEST(major, minor, false)
-
+#endif /* disabled for RHEL */
+
+#define DEFINE_RHEL_MACHINE_LATEST(m, n, s, latest) \
+ static void rhel##m##n##s##_virt_class_init(ObjectClass *oc, \
+ void *data) \
+ { \
+ MachineClass *mc = MACHINE_CLASS(oc); \
+ rhel##m##n##s##_virt_options(mc); \
+ mc->desc = "RHEL " # m "." # n "." # s " ARM Virtual Machine"; \
+ if (latest) { \
+ mc->alias = "virt"; \
+ mc->is_default = 1; \
+ } \
+ } \
+ static const TypeInfo rhel##m##n##s##_machvirt_info = { \
+ .name = MACHINE_TYPE_NAME("virt-rhel" # m "." # n "." # s), \
+ .parent = TYPE_RHEL_MACHINE, \
+ .class_init = rhel##m##n##s##_virt_class_init, \
+ }; \
+ static void rhel##m##n##s##_machvirt_init(void) \
+ { \
+ type_register_static(&rhel##m##n##s##_machvirt_info); \
+ } \
+ type_init(rhel##m##n##s##_machvirt_init);
+
+#define DEFINE_RHEL_MACHINE_AS_LATEST(major, minor, subminor) \
+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, true)
+#define DEFINE_RHEL_MACHINE(major, minor, subminor) \
+ DEFINE_RHEL_MACHINE_LATEST(major, minor, subminor, false)
+
+/* This variable is for changes to properties that are RHEL specific,
+ * different to the current upstream and to be applied to the latest
+ * machine type.
+ */
+GlobalProperty arm_rhel_compat[] = {
+ {
+ .driver = "virtio-net-pci",
+ .property = "romfile",
+ .value = "",
+ },
+};
+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -197,15 +239,19 @@ 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-a35"),
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"),
};
@@ -2290,6 +2336,7 @@ static void machvirt_init(MachineState *machine)
qemu_add_machine_init_done_notifier(&vms->machine_done);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static bool virt_get_secure(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2317,6 +2364,7 @@ static void virt_set_virt(Object *obj, bool value, Error **errp)
vms->virt = value;
}
+#endif /* disabled for RHEL */
static bool virt_get_highmem(Object *obj, Error **errp)
{
@@ -2346,6 +2394,7 @@ 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);
@@ -2359,6 +2408,7 @@ 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)
{
@@ -2442,6 +2492,7 @@ static void virt_set_ras(Object *obj, bool value, Error **errp)
vms->ras = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static bool virt_get_mte(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2455,6 +2506,7 @@ static void virt_set_mte(Object *obj, bool value, Error **errp)
vms->mte = value;
}
+#endif /* disabled for RHEL */
static char *virt_get_gic_version(Object *obj, Error **errp)
{
@@ -2886,6 +2938,7 @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
return fixed_ipa ? 0 : requested_pa_size;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void virt_machine_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
@@ -3294,3 +3347,185 @@ static void virt_machine_2_6_options(MachineClass *mc)
vmc->no_pmu = true;
}
DEFINE_VIRT_MACHINE(2, 6)
+#endif /* disabled for RHEL */
+
+static void rhel_machine_class_init(ObjectClass *oc, void *data)
+{
+ MachineClass *mc = MACHINE_CLASS(oc);
+ HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
+
+ mc->family = "virt-rhel-Z";
+ mc->init = machvirt_init;
+ /* Maximum supported VCPU count for all virt-rhel* machines */
+ mc->max_cpus = 384;
+#ifdef CONFIG_TPM
+ machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS);
+#endif
+ mc->block_default_type = IF_VIRTIO;
+ mc->no_cdrom = 1;
+ mc->pci_allow_0_address = true;
+ /* We know we will never create a pre-ARMv7 CPU which needs 1K pages */
+ mc->minimum_page_bits = 12;
+ mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids;
+ mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
+ mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a57");
+ mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
+ mc->kvm_type = virt_kvm_type;
+ assert(!mc->get_hotplug_handler);
+ mc->get_hotplug_handler = virt_machine_get_hotplug_handler;
+ hc->pre_plug = virt_machine_device_pre_plug_cb;
+ hc->plug = virt_machine_device_plug_cb;
+ 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";
+
+ object_class_property_add(oc, "acpi", "OnOffAuto",
+ virt_get_acpi, virt_set_acpi,
+ NULL, NULL);
+ object_class_property_set_description(oc, "acpi",
+ "Enable ACPI");
+
+ object_class_property_add_bool(oc, "highmem", virt_get_highmem,
+ virt_set_highmem);
+ object_class_property_set_description(oc, "highmem",
+ "Set on/off to enable/disable using "
+ "physical address space above 32 bits");
+
+ object_class_property_add_str(oc, "gic-version", virt_get_gic_version,
+ virt_set_gic_version);
+ object_class_property_set_description(oc, "gic-version",
+ "Set GIC version. "
+ "Valid values are 2, 3, host and max");
+
+ object_class_property_add_str(oc, "iommu", virt_get_iommu, virt_set_iommu);
+ object_class_property_set_description(oc, "iommu",
+ "Set the IOMMU type. "
+ "Valid values are none and smmuv3");
+
+ object_class_property_add_bool(oc, "default-bus-bypass-iommu",
+ virt_get_default_bus_bypass_iommu,
+ virt_set_default_bus_bypass_iommu);
+ object_class_property_set_description(oc, "default-bus-bypass-iommu",
+ "Set on/off to enable/disable "
+ "bypass_iommu for default root bus");
+
+ object_class_property_add_bool(oc, "ras", virt_get_ras,
+ virt_set_ras);
+ object_class_property_set_description(oc, "ras",
+ "Set on/off to enable/disable reporting host memory errors "
+ "to a KVM guest using ACPI and guest external abort exceptions");
+
+ object_class_property_add_bool(oc, "its", virt_get_its,
+ virt_set_its);
+ object_class_property_set_description(oc, "its",
+ "Set on/off to enable/disable "
+ "ITS instantiation");
+
+ object_class_property_add_str(oc, "x-oem-id",
+ virt_get_oem_id,
+ virt_set_oem_id);
+ object_class_property_set_description(oc, "x-oem-id",
+ "Override the default value of field OEMID "
+ "in ACPI table header."
+ "The string may be up to 6 bytes in size");
+
+
+ object_class_property_add_str(oc, "x-oem-table-id",
+ virt_get_oem_table_id,
+ virt_set_oem_table_id);
+ object_class_property_set_description(oc, "x-oem-table-id",
+ "Override the default value of field OEM Table ID "
+ "in ACPI table header."
+ "The string may be up to 8 bytes in size");
+}
+
+static void rhel_virt_instance_init(Object *obj)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+ VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
+
+ /* EL3 is disabled by default and non-configurable for RHEL */
+ vms->secure = false;
+
+ /* EL2 is disabled by default and non-configurable for RHEL */
+ vms->virt = false;
+
+ /* High memory is enabled by default */
+ vms->highmem = true;
+ 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;
+ } else {
+ /* Default allows ITS instantiation */
+ vms->its = true;
+
+ if (vmc->no_tcg_its) {
+ vms->tcg_its = false;
+ } else {
+ vms->tcg_its = true;
+ }
+ }
+
+ /* Default disallows iommu instantiation */
+ vms->iommu = VIRT_IOMMU_NONE;
+
+ /* The default root bus is attached to iommu by default */
+ vms->default_bus_bypass_iommu = false;
+
+ /* Default disallows RAS instantiation and is non-configurable for RHEL */
+ vms->ras = false;
+
+ /* MTE is disabled by default and non-configurable for RHEL */
+ vms->mte = false;
+
+ /* Supply kaslr-seed and rng-seed by default, non-configurable for RHEL */
+ vms->dtb_randomness = true;
+
+ vms->irqmap = a15irqmap;
+
+ virt_flash_create(vms);
+
+ vms->oem_id = g_strndup(ACPI_BUILD_APPNAME6, 6);
+ vms->oem_table_id = g_strndup(ACPI_BUILD_APPNAME8, 8);
+}
+
+static const TypeInfo rhel_machine_info = {
+ .name = TYPE_RHEL_MACHINE,
+ .parent = TYPE_MACHINE,
+ .abstract = true,
+ .instance_size = sizeof(VirtMachineState),
+ .class_size = sizeof(VirtMachineClass),
+ .class_init = rhel_machine_class_init,
+ .instance_init = rhel_virt_instance_init,
+ .interfaces = (InterfaceInfo[]) {
+ { TYPE_HOTPLUG_HANDLER },
+ { }
+ },
+};
+
+static void rhel_machine_init(void)
+{
+ type_register_static(&rhel_machine_info);
+}
+type_init(rhel_machine_init);
+
+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;
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 0, 0)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 6ec479ca2b..22b54ec510 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -180,9 +180,17 @@ struct VirtMachineState {
#define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM)
+#if 0 /* disabled for Red Hat Enterprise Linux */
#define TYPE_VIRT_MACHINE MACHINE_TYPE_NAME("virt")
OBJECT_DECLARE_TYPE(VirtMachineState, VirtMachineClass, VIRT_MACHINE)
+#else
+#define TYPE_RHEL_MACHINE MACHINE_TYPE_NAME("virt-rhel")
+typedef struct VirtMachineClass VirtMachineClass;
+typedef struct VirtMachineState VirtMachineState;
+DECLARE_OBJ_CHECKERS(VirtMachineState, VirtMachineClass, VIRT_MACHINE, TYPE_RHEL_MACHINE)
+#endif
+
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 38d066c294..a845814bfb 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2250,8 +2250,13 @@ 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 9aeed3c848..f9f504d89e 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 3d74f134f5..4b330a52b5 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -36,6 +36,7 @@
#include "hw/qdev-properties.h"
#include "internals.h"
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a35_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -115,6 +116,7 @@ static void aarch64_a35_initfn(Object *obj)
/* These values are the same with A53/A57/A72. */
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
+#endif /* disabled for RHEL */
void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
{
@@ -735,6 +737,7 @@ 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);
@@ -1033,6 +1036,7 @@ 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 */
static void aarch64_host_initfn(Object *obj)
{
@@ -1240,13 +1244,18 @@ static void aarch64_max_initfn(Object *obj)
}
static const ARMCPUInfo aarch64_cpus[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
{ .name = "cortex-a35", .initfn = aarch64_a35_initfn },
- { .name = "cortex-a57", .initfn = aarch64_a57_initfn },
+#endif /* disabled for RHEL */
+ { .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 },
@@ -1318,8 +1327,13 @@ 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 a528ff9a3d..053f70e399 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -148,10 +148,10 @@ 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)
{
@@ -505,7 +505,6 @@ 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)
@@ -530,7 +529,6 @@ 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);
@@ -579,7 +577,6 @@ 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)
{
@@ -628,7 +625,6 @@ 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);
@@ -1070,7 +1066,6 @@ 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
/*
@@ -1138,7 +1133,6 @@ 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 },
@@ -1154,9 +1148,7 @@ 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,
@@ -1187,7 +1179,6 @@ 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
@@ -1215,3 +1206,4 @@ 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 d8c8223ec3..ad9d235773 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -8476,6 +8476,7 @@ 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;
@@ -8485,6 +8486,7 @@ 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

544
SOURCES/0008-Add-ppc64-machine-types.patch
Unescape View File

@ -0,0 +1,544 @@
From 2c523f1b6c9470e1cd517ba99e414cde02727e16 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
Adding changes to add RHEL machine types for ppc64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Rebase notes (6.2.0):
- Fixed rebase conflict relicts
- Update machine type compat for 6.2 (from MR 66)
Merged patches (6.1.0):
- c438c25ac3 redhat: Define pseries-rhel8.5.0 machine type
- a3995e2eff Remove RHEL 7.0.0 machine type (only ppc64 changes)
- ad3190a79b Remove RHEL 7.1.0 machine type (only ppc64 changes)
- 84bbe15d4e Remove RHEL 7.2.0 machine type (only ppc64 changes)
- 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 +++
8 files changed, 314 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 66b414d2e9..499eb49253 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1633,6 +1633,9 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
pef_kvm_reset(machine->cgs, &error_fatal);
spapr_caps_apply(spapr);
+ if (spapr->svm_allowed) {
+ kvmppc_svm_allow(&error_fatal);
+ }
first_ppc_cpu = POWERPC_CPU(first_cpu);
if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
@@ -3347,6 +3350,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
spapr->host_serial = g_strdup(value);
}
+static bool spapr_get_svm_allowed(Object *obj, Error **errp)
+{
+ SpaprMachineState *spapr = SPAPR_MACHINE(obj);
+
+ return spapr->svm_allowed;
+}
+
+static void spapr_set_svm_allowed(Object *obj, bool value, Error **errp)
+{
+ SpaprMachineState *spapr = SPAPR_MACHINE(obj);
+
+ spapr->svm_allowed = value;
+}
+
static void spapr_instance_init(Object *obj)
{
SpaprMachineState *spapr = SPAPR_MACHINE(obj);
@@ -3425,6 +3442,12 @@ 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");
+ object_property_add_bool(obj, "x-svm-allowed",
+ spapr_get_svm_allowed,
+ spapr_set_svm_allowed);
+ object_property_set_description(obj, "x-svm-allowed",
+ "Allow the guest to become a Secure Guest"
+ " (experimental only)");
}
static void spapr_machine_finalizefn(Object *obj)
@@ -4682,6 +4705,7 @@ 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;
+ smc->has_power9_support = true;
}
static const TypeInfo spapr_machine_info = {
@@ -4733,6 +4757,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
} \
type_init(spapr_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* pseries-7.2
*/
@@ -4882,6 +4907,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc)
}
DEFINE_SPAPR_MACHINE(4_1, "4.1", false);
+#endif
/*
* pseries-4.0
@@ -4901,6 +4927,8 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
*nv2atsd = 0;
return true;
}
+
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void spapr_machine_4_0_class_options(MachineClass *mc)
{
SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
@@ -5228,6 +5256,221 @@ 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);
+#endif
+
+static void spapr_machine_rhel_default_class_options(MachineClass *mc)
+{
+ /*
+ * Defaults for the latest behaviour inherited from the base class
+ * can be overriden here for all pseries-rhel* machines.
+ */
+
+ /* Maximum supported VCPU count */
+ mc->max_cpus = 384;
+}
+
+/*
+ * pseries-rhel8.5.0
+ * like pseries-6.0
+ */
+
+static void spapr_machine_rhel850_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ /* The default machine type must apply the RHEL specific defaults */
+ spapr_machine_rhel_default_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_5,
+ hw_compat_rhel_8_5_len);
+ smc->pre_6_2_numa_affinity = true;
+ mc->smp_props.prefer_sockets = true;
+}
+
+DEFINE_SPAPR_MACHINE(rhel850, "rhel8.5.0", true);
+
+/*
+ * pseries-rhel8.4.0
+ * like pseries-5.2
+ */
+
+static void spapr_machine_rhel840_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel850_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_4,
+ hw_compat_rhel_8_4_len);
+}
+
+DEFINE_SPAPR_MACHINE(rhel840, "rhel8.4.0", false);
+
+/*
+ * pseries-rhel8.3.0
+ * like pseries-5.1
+ */
+
+static void spapr_machine_rhel830_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel840_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_3,
+ hw_compat_rhel_8_3_len);
+
+ /* from pseries-5.1 */
+ smc->pre_5_2_numa_associativity = true;
+}
+
+DEFINE_SPAPR_MACHINE(rhel830, "rhel8.3.0", false);
+
+/*
+ * pseries-rhel8.2.0
+ * like pseries-4.2 + pseries-5.0
+ * except SPAPR_CAP_CCF_ASSIST that has been backported to pseries-rhel8.1.0
+ */
+
+static void spapr_machine_rhel820_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+ /* from pseries-5.0 */
+ static GlobalProperty compat[] = {
+ { TYPE_SPAPR_PCI_HOST_BRIDGE, "pre-5.1-associativity", "on" },
+ };
+
+ spapr_machine_rhel830_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_2,
+ hw_compat_rhel_8_2_len);
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
+
+ /* from pseries-4.2 */
+ smc->default_caps.caps[SPAPR_CAP_FWNMI] = SPAPR_CAP_OFF;
+ smc->rma_limit = 16 * GiB;
+ mc->nvdimm_supported = false;
+
+ /* from pseries-5.0 */
+ mc->numa_mem_supported = true;
+ smc->pre_5_1_assoc_refpoints = true;
+}
+
+DEFINE_SPAPR_MACHINE(rhel820, "rhel8.2.0", false);
+
+/*
+ * pseries-rhel8.1.0
+ * like pseries-4.1
+ */
+
+static void spapr_machine_rhel810_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+ static GlobalProperty compat[] = {
+ /* Only allow 4kiB and 64kiB IOMMU pagesizes */
+ { TYPE_SPAPR_PCI_HOST_BRIDGE, "pgsz", "0x11000" },
+ };
+
+ spapr_machine_rhel820_class_options(mc);
+
+ /* from pseries-4.1 */
+ smc->linux_pci_probe = false;
+ smc->smp_threads_vsmt = false;
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_1,
+ hw_compat_rhel_8_1_len);
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
+
+ /* from pseries-4.2 */
+ smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_OFF;
+}
+
+DEFINE_SPAPR_MACHINE(rhel810, "rhel8.1.0", false);
+
+/*
+ * pseries-rhel8.0.0
+ * like pseries-3.1 and pseries-4.0
+ * except SPAPR_CAP_CFPC, SPAPR_CAP_SBBC and SPAPR_CAP_IBS
+ * that have been backported to pseries-rhel8.0.0
+ */
+
+static void spapr_machine_rhel800_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel810_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_0,
+ hw_compat_rhel_8_0_len);
+
+ /* pseries-4.0 */
+ smc->phb_placement = phb_placement_4_0;
+ smc->irq = &spapr_irq_xics;
+ smc->pre_4_1_migration = true;
+
+ /* pseries-3.1 */
+ mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power8_v2.0");
+ smc->update_dt_enabled = false;
+ smc->dr_phb_enabled = false;
+ smc->broken_host_serial_model = true;
+ smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_OFF;
+}
+
+DEFINE_SPAPR_MACHINE(rhel800, "rhel8.0.0", false);
+
+/*
+ * pseries-rhel7.6.0
+ * like spapr_compat_2_12 and spapr_compat_3_0
+ * spapr_compat_0 is empty
+ */
+GlobalProperty spapr_compat_rhel7_6[] = {
+ { TYPE_POWERPC_CPU, "pre-3.0-migration", "on" },
+ { TYPE_SPAPR_CPU_CORE, "pre-3.0-migration", "on" },
+};
+const size_t spapr_compat_rhel7_6_len = G_N_ELEMENTS(spapr_compat_rhel7_6);
+
+
+static void spapr_machine_rhel760_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel800_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len);
+ compat_props_add(mc->compat_props, spapr_compat_rhel7_6, spapr_compat_rhel7_6_len);
+
+ /* from spapr_machine_3_0_class_options() */
+ smc->legacy_irq_allocation = true;
+ smc->nr_xirqs = 0x400;
+ smc->irq = &spapr_irq_xics_legacy;
+
+ /* from spapr_machine_2_12_class_options() */
+ /* We depend on kvm_enabled() to choose a default value for the
+ * hpt-max-page-size capability. Of course we can't do it here
+ * because this is too early and the HW accelerator isn't initialzed
+ * yet. Postpone this to machine init (see default_caps_with_cpu()).
+ */
+ smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 0;
+
+ /* SPAPR_CAP_WORKAROUND enabled in pseries-rhel800 by
+ * f21757edc554
+ * "Enable mitigations by default for pseries-4.0 machine type")
+ */
+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_BROKEN;
+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_BROKEN;
+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_BROKEN;
+}
+
+DEFINE_SPAPR_MACHINE(rhel760, "rhel7.6.0", false);
+
+/*
+ * pseries-rhel7.6.0-sxxm
+ *
+ * pseries-rhel7.6.0 with speculative execution exploit mitigations enabled by default
+ */
+
+static void spapr_machine_rhel760sxxm_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ spapr_machine_rhel760_class_options(mc);
+ smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND;
+ smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD;
+}
+
+DEFINE_SPAPR_MACHINE(rhel760sxxm, "rhel7.6.0-sxxm", false);
static void spapr_machine_register_types(void)
{
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index fcb5dfe792..ab8fb5bf62 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -25,6 +25,7 @@
#include "sysemu/reset.h"
#include "sysemu/hw_accel.h"
#include "qemu/error-report.h"
+#include "cpu-models.h"
static void spapr_reset_vcpu(PowerPCCPU *cpu)
{
@@ -259,6 +260,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
{
CPUPPCState *env = &cpu->env;
CPUState *cs = CPU(cpu);
+ SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
if (!qdev_realize(DEVICE(cpu), NULL, errp)) {
return false;
@@ -270,6 +272,17 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
/* Set time-base frequency to 512 MHz. vhyp must be set first. */
cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ);
+ if (!smc->has_power9_support &&
+ (((spapr->max_compat_pvr &&
+ ppc_compat_cmp(spapr->max_compat_pvr,
+ CPU_POWERPC_LOGICAL_3_00) >= 0)) ||
+ (!spapr->max_compat_pvr &&
+ ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, 0)))) {
+ error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
+ "POWER9 CPU is not supported by this machine class");
+ return false;
+ }
+
if (spapr_irq_cpu_intc_create(spapr, cpu, errp) < 0) {
qdev_unrealize(DEVICE(cpu));
return false;
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 04a95669ab..d5f4cf5e03 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -154,6 +154,7 @@ struct SpaprMachineClass {
bool pre_5_2_numa_associativity;
bool pre_6_2_numa_affinity;
+ bool has_power9_support;
bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index,
uint64_t *buid, hwaddr *pio,
hwaddr *mmio32, hwaddr *mmio64,
@@ -256,6 +257,9 @@ struct SpaprMachineState {
/* Set by -boot */
char *boot_device;
+ /* Secure Guest support via x-svm-allowed */
+ bool svm_allowed;
+
/*< public >*/
char *kvm_type;
char *host_model;
diff --git a/target/ppc/compat.c b/target/ppc/compat.c
index 7949a24f5a..f207a9ba01 100644
--- a/target/ppc/compat.c
+++ b/target/ppc/compat.c
@@ -114,8 +114,19 @@ static const CompatInfo *compat_by_pvr(uint32_t pvr)
return NULL;
}
+long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2)
+{
+ const CompatInfo *compat1 = compat_by_pvr(pvr1);
+ const CompatInfo *compat2 = compat_by_pvr(pvr2);
+
+ g_assert(compat1);
+ g_assert(compat2);
+
+ return compat1 - compat2;
+}
+
static bool pcc_compat(PowerPCCPUClass *pcc, uint32_t compat_pvr,
- uint32_t min_compat_pvr, uint32_t max_compat_pvr)
+ uint32_t min_compat_pvr, uint32_t max_compat_pvr)
{
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 81d4263a07..508fbed90b 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1467,6 +1467,7 @@ static inline int cpu_mmu_index(CPUPPCState *env, bool ifetch)
/* Compatibility modes */
#if defined(TARGET_PPC64)
+long ppc_compat_cmp(uint32_t pvr1, uint32_t pvr2);
bool ppc_check_compat(PowerPCCPU *cpu, uint32_t compat_pvr,
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 7c25348b7b..83671c955f 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -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;
+static int cap_ppc_secure_guest;
static uint32_t debug_inst_opcode;
@@ -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);
+ cap_ppc_secure_guest = kvm_vm_check_extension(s, KVM_CAP_PPC_SECURE_GUEST);
cap_large_decr = kvmppc_get_dec_bits();
cap_fwnmi = kvm_vm_check_extension(s, KVM_CAP_PPC_FWNMI);
/*
@@ -2570,6 +2572,16 @@ int kvmppc_has_cap_rpt_invalidate(void)
return cap_rpt_invalidate;
}
+bool kvmppc_has_cap_secure_guest(void)
+{
+ return !!cap_ppc_secure_guest;
+}
+
+int kvmppc_enable_cap_secure_guest(void)
+{
+ return kvm_vm_enable_cap(kvm_state, KVM_CAP_PPC_SECURE_GUEST, 0, 1);
+}
+
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void)
{
uint32_t host_pvr = mfpvr();
@@ -2970,3 +2982,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
void kvm_arch_accel_class_init(ObjectClass *oc)
{
}
+
+void kvmppc_svm_allow(Error **errp)
+{
+ if (!kvm_enabled()) {
+ error_setg(errp, "No PEF support in tcg, try x-svm-allowed=off");
+ return;
+ }
+
+ if (!kvmppc_has_cap_secure_guest()) {
+ error_setg(errp, "KVM implementation does not support secure guests, "
+ "try x-svm-allowed=off");
+ } else if (kvmppc_enable_cap_secure_guest() < 0) {
+ error_setg(errp, "Error enabling x-svm-allowed, try x-svm-allowed=off");
+ }
+}
diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index ee9325bf9a..20dbb95989 100644
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -40,6 +40,7 @@ int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu);
target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu,
bool radix, bool gtse,
uint64_t proc_tbl);
+void kvmppc_svm_allow(Error **errp);
#ifndef CONFIG_USER_ONLY
bool kvmppc_spapr_use_multitce(void);
int kvmppc_spapr_enable_inkernel_multitce(void);
@@ -74,6 +75,8 @@ int kvmppc_get_cap_large_decr(void);
int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable);
int kvmppc_has_cap_rpt_invalidate(void);
int kvmppc_enable_hwrng(void);
+bool kvmppc_has_cap_secure_guest(void);
+int kvmppc_enable_cap_secure_guest(void);
int kvmppc_put_books_sregs(PowerPCCPU *cpu);
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void);
void kvmppc_check_papr_resize_hpt(Error **errp);
@@ -393,6 +396,16 @@ static inline int kvmppc_has_cap_rpt_invalidate(void)
return false;
}
+static inline bool kvmppc_has_cap_secure_guest(void)
+{
+ return false;
+}
+
+static inline int kvmppc_enable_cap_secure_guest(void)
+{
+ return -1;
+}
+
static inline int kvmppc_enable_hwrng(void)
{
return -1;
--
2.31.1

246
SOURCES/0009-Add-s390x-machine-types.patch
Unescape View File

@ -0,0 +1,246 @@
From 1973257ed781a93943f27f1518933e8c09c50f88 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
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
Merged patches (6.2.0):
- 3bf66f4520 redhat: Add s390x machine type compatibility update for 6.1 rebase
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)
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
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/s390x/s390-virtio-ccw.c | 108 +++++++++++++++++++++++++++++++
target/s390x/cpu_models.c | 11 ++++
target/s390x/cpu_models.h | 2 +
target/s390x/cpu_models_sysemu.c | 2 +
4 files changed, 123 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 2e64ffab45..8d5221fbb1 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -823,6 +823,7 @@ bool css_migration_enabled(void)
} \
type_init(ccw_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void ccw_machine_7_2_instance_options(MachineState *machine)
{
}
@@ -1186,6 +1187,113 @@ 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_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);
+
+static void ccw_machine_rhel860_instance_options(MachineState *machine)
+{
+ /* Note: The -rhel8.6.0 and -rhel9.0.0 machines are technically identical */
+ ccw_machine_rhel900_instance_options(machine);
+}
+
+static void ccw_machine_rhel860_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel900_class_options(mc);
+
+ /* All RHEL machines for prior major releases are deprecated */
+ mc->deprecation_reason = rhel_old_machine_deprecation;
+}
+DEFINE_CCW_MACHINE(rhel860, "rhel8.6.0", false);
+
+static void ccw_machine_rhel850_instance_options(MachineState *machine)
+{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 };
+
+ ccw_machine_rhel860_instance_options(machine);
+
+ s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat);
+
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_NNPA);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_VECTOR_PACKED_DECIMAL_ENH2);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_BEAR_ENH);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_RDP);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAI);
+}
+
+static void ccw_machine_rhel850_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel860_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len);
+ mc->smp_props.prefer_sockets = true;
+}
+DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", false);
+
+static void ccw_machine_rhel840_instance_options(MachineState *machine)
+{
+ ccw_machine_rhel850_instance_options(machine);
+}
+
+static void ccw_machine_rhel840_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel850_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_4, hw_compat_rhel_8_4_len);
+}
+DEFINE_CCW_MACHINE(rhel840, "rhel8.4.0", false);
+
+static void ccw_machine_rhel820_instance_options(MachineState *machine)
+{
+ ccw_machine_rhel840_instance_options(machine);
+}
+
+static void ccw_machine_rhel820_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel840_class_options(mc);
+ mc->fixup_ram_size = s390_fixup_ram_size;
+ /* we did not publish a rhel8.3.0 machine */
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_3, hw_compat_rhel_8_3_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_2, hw_compat_rhel_8_2_len);
+}
+DEFINE_CCW_MACHINE(rhel820, "rhel8.2.0", false);
+
+static void ccw_machine_rhel760_instance_options(MachineState *machine)
+{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V3_1 };
+
+ ccw_machine_rhel820_instance_options(machine);
+
+ s390_set_qemu_cpu_model(0x2827, 12, 2, qemu_cpu_feat);
+
+ /* The multiple-epoch facility was not available with rhel7.6.0 on z14GA1 */
+ s390_cpudef_featoff(14, 1, S390_FEAT_MULTIPLE_EPOCH);
+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_QSIE);
+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_QTOUE);
+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_STOE);
+ s390_cpudef_featoff(14, 1, S390_FEAT_PTFF_STOUE);
+}
+
+static void ccw_machine_rhel760_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel820_class_options(mc);
+ /* We never published the s390x version of RHEL-AV 8.0 and 8.1, so add this here */
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len);
+}
+DEFINE_CCW_MACHINE(rhel760, "rhel7.6.0", false);
static void ccw_machine_register_types(void)
{
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.
*/
+
+#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 fb1adc8b21..d76745afa9 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

874
SOURCES/0010-Add-x86_64-machine-types.patch
Unescape View File

@ -0,0 +1,874 @@
From 0935624ccdddc286d6eeeb0c1b70d78983c21aa2 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
Adding changes to add RHEL machine types for x86_64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Rebase notes (6.1.0):
- Update qemu64 cpu spec
Rebase notes (7.0.0):
- Reset alias for all machine-types except latest one
Merged patches (6.1.0):
- 59c284ad3b x86: Add x86 rhel8.5 machine types
- a8868b42fe redhat: x86: Enable 'kvm-asyncpf-int' by default
- a3995e2eff Remove RHEL 7.0.0 machine type (only x86_64 changes)
- ad3190a79b Remove RHEL 7.1.0 machine type (only x86_64 changes)
- 84bbe15d4e Remove RHEL 7.2.0 machine type (only x86_64 changes)
- 0215eb3356 Remove RHEL 7.3.0 machine types (only x86_64 changes)
- af69d1ca6e Remove RHEL 7.4.0 machine types (only x86_64 changes)
- 8f7a74ab78 Remove RHEL 7.5.0 machine types (only x86_64 changes)
Merged patches (7.0.0):
- eae7d8dd3c x86/rhel machine types: Add pc_rhel_8_5_compat
- 6762f56469 x86/rhel machine types: Wire compat into q35 and i440fx
- 5762101438 rhel machine types/x86: set prefer_sockets
- 9ba9ddc632 x86: Add q35 RHEL 8.6.0 machine type
- 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
Merged patches (7.2.0 rc0):
- 0be2889fa2 Introduce upstream 7.0 compat changes (only applicable parts)
---
hw/i386/pc.c | 147 ++++++++++++++++++++++-
hw/i386/pc_piix.c | 86 +++++++++++++-
hw/i386/pc_q35.c | 234 ++++++++++++++++++++++++++++++++++++-
hw/s390x/s390-virtio-ccw.c | 1 +
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, 521 insertions(+), 7 deletions(-)
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 546b703cb4..c7b1350e64 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -393,6 +393,149 @@ GlobalProperty pc_compat_1_4[] = {
};
const size_t pc_compat_1_4_len = G_N_ELEMENTS(pc_compat_1_4);
+/* This macro is for changes to properties that are RHEL specific,
+ * different to the current upstream and to be applied to the latest
+ * 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" },
+ { TYPE_X86_CPU, "vmx-exit-load-perf-global-ctrl", "off" },
+ /* bz 1508330 */
+ { "vfio-pci", "x-no-geforce-quirks", "on" },
+ /* bz 1941397 */
+ { TYPE_X86_CPU, "kvm-asyncpf-int", "on" },
+};
+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" },
+ /* pc_rhel_8_5_compat from pc_compat_6_0 */
+ { "qemu64" "-" TYPE_X86_CPU, "model", "6" },
+ /* pc_rhel_8_5_compat from pc_compat_6_0 */
+ { "qemu64" "-" TYPE_X86_CPU, "stepping", "3" },
+ /* pc_rhel_8_5_compat from pc_compat_6_0 */
+ { TYPE_X86_CPU, "x-vendor-cpuid-only", "off" },
+ /* pc_rhel_8_5_compat from pc_compat_6_0 */
+ { "ICH9-LPC", ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, "off" },
+
+ /* pc_rhel_8_5_compat from pc_compat_6_1 */
+ { TYPE_X86_CPU, "hv-version-id-build", "0x1bbc" },
+ /* pc_rhel_8_5_compat from pc_compat_6_1 */
+ { TYPE_X86_CPU, "hv-version-id-major", "0x0006" },
+ /* pc_rhel_8_5_compat from pc_compat_6_1 */
+ { TYPE_X86_CPU, "hv-version-id-minor", "0x0001" },
+};
+const size_t pc_rhel_8_5_compat_len = G_N_ELEMENTS(pc_rhel_8_5_compat);
+
+GlobalProperty pc_rhel_8_4_compat[] = {
+ /* pc_rhel_8_4_compat from pc_compat_5_2 */
+ { "ICH9-LPC", "x-smi-cpu-hotunplug", "off" },
+ { TYPE_X86_CPU, "kvm-asyncpf-int", "off" },
+};
+const size_t pc_rhel_8_4_compat_len = G_N_ELEMENTS(pc_rhel_8_4_compat);
+
+GlobalProperty pc_rhel_8_3_compat[] = {
+ /* pc_rhel_8_3_compat from pc_compat_5_1 */
+ { "ICH9-LPC", "x-smi-cpu-hotplug", "off" },
+};
+const size_t pc_rhel_8_3_compat_len = G_N_ELEMENTS(pc_rhel_8_3_compat);
+
+GlobalProperty pc_rhel_8_2_compat[] = {
+ /* pc_rhel_8_2_compat from pc_compat_4_2 */
+ { "mch", "smbase-smram", "off" },
+};
+const size_t pc_rhel_8_2_compat_len = G_N_ELEMENTS(pc_rhel_8_2_compat);
+
+/* pc_rhel_8_1_compat is empty since pc_4_1_compat is */
+GlobalProperty pc_rhel_8_1_compat[] = { };
+const size_t pc_rhel_8_1_compat_len = G_N_ELEMENTS(pc_rhel_8_1_compat);
+
+GlobalProperty pc_rhel_8_0_compat[] = {
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "intel-iommu", "dma-drain", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G3" "-" TYPE_X86_CPU, "rdtscp", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G4" "-" TYPE_X86_CPU, "rdtscp", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G4" "-" TYPE_X86_CPU, "npt", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G4" "-" TYPE_X86_CPU, "nrip-save", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G5" "-" TYPE_X86_CPU, "rdtscp", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G5" "-" TYPE_X86_CPU, "npt", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Opteron_G5" "-" TYPE_X86_CPU, "nrip-save", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "EPYC" "-" TYPE_X86_CPU, "npt", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "EPYC" "-" TYPE_X86_CPU, "nrip-save", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "EPYC-IBPB" "-" TYPE_X86_CPU, "npt", "off" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "EPYC-IBPB" "-" TYPE_X86_CPU, "nrip-save", "off" },
+ /** The mpx=on entries from pc_compat_3_1 are in pc_rhel_7_6_compat **/
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { "Cascadelake-Server" "-" TYPE_X86_CPU, "stepping", "5" },
+ /* pc_rhel_8_0_compat from pc_compat_3_1 */
+ { TYPE_X86_CPU, "x-intel-pt-auto-level", "off" },
+};
+const size_t pc_rhel_8_0_compat_len = G_N_ELEMENTS(pc_rhel_8_0_compat);
+
+/* Similar to PC_COMPAT_3_0 + PC_COMPAT_2_12, but:
+ * all of the 2_12 stuff was already in 7.6 from bz 1481253
+ * x-migrate-smi-count comes from PC_COMPAT_2_11 but
+ * is really tied to kernel version so keep it off on 7.x
+ * machine types irrespective of host.
+ */
+GlobalProperty pc_rhel_7_6_compat[] = {
+ /* pc_rhel_7_6_compat from pc_compat_3_0 */
+ { TYPE_X86_CPU, "x-hv-synic-kvm-only", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_3_0 */
+ { "Skylake-Server" "-" TYPE_X86_CPU, "pku", "off" },
+ /* pc_rhel_7_6_compat from pc_compat_3_0 */
+ { "Skylake-Server-IBRS" "-" TYPE_X86_CPU, "pku", "off" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { TYPE_X86_CPU, "x-migrate-smi-count", "off" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Skylake-Client" "-" TYPE_X86_CPU, "mpx", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Skylake-Client-IBRS" "-" TYPE_X86_CPU, "mpx", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Skylake-Server" "-" TYPE_X86_CPU, "mpx", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Skylake-Server-IBRS" "-" TYPE_X86_CPU, "mpx", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Cascadelake-Server" "-" TYPE_X86_CPU, "mpx", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Icelake-Client" "-" TYPE_X86_CPU, "mpx", "on" },
+ /* pc_rhel_7_6_compat from pc_compat_2_11 */
+ { "Icelake-Server" "-" TYPE_X86_CPU, "mpx", "on" },
+};
+const size_t pc_rhel_7_6_compat_len = G_N_ELEMENTS(pc_rhel_7_6_compat);
+
+/*
+ * The PC_RHEL_*_COMPAT serve the same purpose for RHEL-7 machine
+ * types as the PC_COMPAT_* do for upstream types.
+ * PC_RHEL_7_*_COMPAT apply both to i440fx and q35 types.
+ */
+
GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled)
{
GSIState *s;
@@ -1907,6 +2050,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
pcmc->pvh_enabled = true;
pcmc->kvmclock_create_always = true;
assert(!mc->get_hotplug_handler);
+ mc->async_pf_vmexit_disable = false;
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;
@@ -1917,7 +2061,8 @@ 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;
- mc->max_cpus = 255;
+ /* 240: max CPU count for RHEL */
+ mc->max_cpus = 240;
mc->reset = pc_machine_reset;
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 0985ff67d2..173a1fd10b 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -53,6 +53,7 @@
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "sysemu/xen.h"
+#include "migration/migration.h"
#ifdef CONFIG_XEN
#include <xen/hvm/hvm_info_table.h>
#include "hw/xen/xen_pt.h"
@@ -184,8 +185,8 @@ static void pc_init1(MachineState *machine,
if (pcmc->smbios_defaults) {
MachineClass *mc = MACHINE_GET_CLASS(machine);
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)",
- mc->name, pcmc->smbios_legacy_mode,
+ smbios_set_defaults("Red Hat", "KVM",
+ mc->desc, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -334,6 +335,7 @@ static void pc_init1(MachineState *machine,
* hw_compat_*, pc_compat_*, or * pc_*_machine_options().
*/
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void pc_compat_2_3_fn(MachineState *machine)
{
X86MachineState *x86ms = X86_MACHINE(machine);
@@ -896,3 +898,83 @@ 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
+#endif /* Disabled for Red Hat Enterprise Linux */
+
+/* Red Hat Enterprise Linux machine types */
+
+/* Options for the latest rhel7 machine type */
+static void pc_machine_rhel7_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ m->family = "pc_piix_Y";
+ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off";
+ pcmc->default_nic_model = "e1000";
+ pcmc->pci_root_uid = 0;
+ m->default_display = "std";
+ m->no_parallel = 1;
+ m->numa_mem_supported = true;
+ m->auto_enable_numa_with_memdev = false;
+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE);
+ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
+ m->alias = "pc";
+ m->is_default = 1;
+ m->smp_props.prefer_sockets = true;
+}
+
+static void pc_init_rhel760(MachineState *machine)
+{
+ pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, \
+ TYPE_I440FX_PCI_DEVICE);
+}
+
+static void pc_machine_rhel760_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_machine_rhel7_options(m);
+ m->desc = "RHEL 7.6.0 PC (i440FX + PIIX, 1996)";
+ m->async_pf_vmexit_disable = true;
+ m->smbus_no_migration_support = true;
+
+ /* All RHEL machines for prior major releases are deprecated */
+ m->deprecation_reason = rhel_old_machine_deprecation;
+
+ pcmc->pvh_enabled = false;
+ pcmc->default_cpu_version = CPU_VERSION_LEGACY;
+ 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,
+ 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,
+ hw_compat_rhel_8_5_len);
+ compat_props_add(m->compat_props, pc_rhel_8_5_compat,
+ pc_rhel_8_5_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_4,
+ hw_compat_rhel_8_4_len);
+ compat_props_add(m->compat_props, pc_rhel_8_4_compat,
+ pc_rhel_8_4_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_3,
+ hw_compat_rhel_8_3_len);
+ compat_props_add(m->compat_props, pc_rhel_8_3_compat,
+ pc_rhel_8_3_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_2,
+ hw_compat_rhel_8_2_len);
+ compat_props_add(m->compat_props, pc_rhel_8_2_compat,
+ pc_rhel_8_2_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len);
+ compat_props_add(m->compat_props, pc_rhel_8_1_compat, pc_rhel_8_1_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len);
+ compat_props_add(m->compat_props, pc_rhel_8_0_compat, pc_rhel_8_0_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len);
+ compat_props_add(m->compat_props, pc_rhel_7_6_compat, pc_rhel_7_6_compat_len);
+}
+
+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 ea582254e3..97c3630021 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -198,8 +198,8 @@ static void pc_q35_init(MachineState *machine)
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)",
- mc->name, pcmc->smbios_legacy_mode,
+ smbios_set_defaults("Red Hat", "KVM",
+ mc->desc, pcmc->smbios_legacy_mode,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product,
pcmc->smbios_stream_version,
@@ -352,6 +352,7 @@ static void pc_q35_init(MachineState *machine)
DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void pc_q35_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
@@ -666,3 +667,232 @@ 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);
+#endif /* Disabled for Red Hat Enterprise Linux */
+
+/* Red Hat Enterprise Linux machine types */
+
+/* Options for the latest rhel q35 machine type */
+static void pc_q35_machine_rhel_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pcmc->default_nic_model = "e1000e";
+ pcmc->pci_root_uid = 0;
+ m->family = "pc_q35_Z";
+ m->units_per_default_bus = 1;
+ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off";
+ m->default_display = "std";
+ m->no_floppy = 1;
+ m->no_parallel = 1;
+ pcmc->default_cpu_version = 1;
+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_AMD_IOMMU_DEVICE);
+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_INTEL_IOMMU_DEVICE);
+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE);
+ m->alias = "q35";
+ m->max_cpus = 710;
+ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
+}
+
+static void pc_q35_init_rhel900(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel900_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel_options(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,
+ pc_rhel_9_0_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel900, "pc-q35-rhel9.0.0", pc_q35_init_rhel900,
+ pc_q35_machine_rhel900_options);
+
+static void pc_q35_init_rhel860(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel860_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel900_options(m);
+ m->desc = "RHEL-8.6.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+
+ /* All RHEL machines for prior major releases are deprecated */
+ m->deprecation_reason = rhel_old_machine_deprecation;
+
+ pcmc->smbios_stream_product = "RHEL-AV";
+ pcmc->smbios_stream_version = "8.6.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_8_6,
+ hw_compat_rhel_8_6_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel860, "pc-q35-rhel8.6.0", pc_q35_init_rhel860,
+ pc_q35_machine_rhel860_options);
+
+
+static void pc_q35_init_rhel850(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel850_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel860_options(m);
+ m->desc = "RHEL-8.5.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+ pcmc->smbios_stream_product = "RHEL-AV";
+ pcmc->smbios_stream_version = "8.5.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_8_5,
+ hw_compat_rhel_8_5_len);
+ compat_props_add(m->compat_props, pc_rhel_8_5_compat,
+ pc_rhel_8_5_compat_len);
+ m->smp_props.prefer_sockets = true;
+}
+
+DEFINE_PC_MACHINE(q35_rhel850, "pc-q35-rhel8.5.0", pc_q35_init_rhel850,
+ pc_q35_machine_rhel850_options);
+
+
+static void pc_q35_init_rhel840(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel840_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel850_options(m);
+ m->desc = "RHEL-8.4.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+ pcmc->smbios_stream_product = "RHEL-AV";
+ pcmc->smbios_stream_version = "8.4.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_8_4,
+ hw_compat_rhel_8_4_len);
+ compat_props_add(m->compat_props, pc_rhel_8_4_compat,
+ pc_rhel_8_4_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel840, "pc-q35-rhel8.4.0", pc_q35_init_rhel840,
+ pc_q35_machine_rhel840_options);
+
+
+static void pc_q35_init_rhel830(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel830_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel840_options(m);
+ m->desc = "RHEL-8.3.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+ pcmc->smbios_stream_product = "RHEL-AV";
+ pcmc->smbios_stream_version = "8.3.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_8_3,
+ hw_compat_rhel_8_3_len);
+ compat_props_add(m->compat_props, pc_rhel_8_3_compat,
+ pc_rhel_8_3_compat_len);
+ /* From pc_q35_5_1_machine_options() */
+ pcmc->kvmclock_create_always = false;
+ /* From pc_q35_5_1_machine_options() */
+ pcmc->pci_root_uid = 1;
+}
+
+DEFINE_PC_MACHINE(q35_rhel830, "pc-q35-rhel8.3.0", pc_q35_init_rhel830,
+ pc_q35_machine_rhel830_options);
+
+static void pc_q35_init_rhel820(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel820_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel830_options(m);
+ m->desc = "RHEL-8.2.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+ m->numa_mem_supported = true;
+ m->auto_enable_numa_with_memdev = false;
+ pcmc->smbios_stream_product = "RHEL-AV";
+ pcmc->smbios_stream_version = "8.2.0";
+ compat_props_add(m->compat_props, hw_compat_rhel_8_2,
+ hw_compat_rhel_8_2_len);
+ compat_props_add(m->compat_props, pc_rhel_8_2_compat,
+ pc_rhel_8_2_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel820, "pc-q35-rhel8.2.0", pc_q35_init_rhel820,
+ pc_q35_machine_rhel820_options);
+
+static void pc_q35_init_rhel810(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel810_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel820_options(m);
+ m->desc = "RHEL-8.1.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+ pcmc->smbios_stream_product = NULL;
+ pcmc->smbios_stream_version = NULL;
+ compat_props_add(m->compat_props, hw_compat_rhel_8_1, hw_compat_rhel_8_1_len);
+ compat_props_add(m->compat_props, pc_rhel_8_1_compat, pc_rhel_8_1_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel810, "pc-q35-rhel8.1.0", pc_q35_init_rhel810,
+ pc_q35_machine_rhel810_options);
+
+static void pc_q35_init_rhel800(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel800_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel810_options(m);
+ m->desc = "RHEL-8.0.0 PC (Q35 + ICH9, 2009)";
+ m->smbus_no_migration_support = true;
+ m->alias = NULL;
+ pcmc->pvh_enabled = false;
+ pcmc->default_cpu_version = CPU_VERSION_LEGACY;
+ compat_props_add(m->compat_props, hw_compat_rhel_8_0, hw_compat_rhel_8_0_len);
+ compat_props_add(m->compat_props, pc_rhel_8_0_compat, pc_rhel_8_0_compat_len);
+}
+
+DEFINE_PC_MACHINE(q35_rhel800, "pc-q35-rhel8.0.0", pc_q35_init_rhel800,
+ pc_q35_machine_rhel800_options);
+
+static void pc_q35_init_rhel760(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel760_options(MachineClass *m)
+{
+ pc_q35_machine_rhel800_options(m);
+ m->alias = NULL;
+ m->desc = "RHEL-7.6.0 PC (Q35 + ICH9, 2009)";
+ m->async_pf_vmexit_disable = true;
+ compat_props_add(m->compat_props, hw_compat_rhel_7_6, hw_compat_rhel_7_6_len);
+ compat_props_add(m->compat_props, pc_rhel_7_6_compat, pc_rhel_7_6_compat_len);
+}
+
+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 8d5221fbb1..ba640e3d9e 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1213,6 +1213,7 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine)
static void ccw_machine_rhel860_class_options(MachineClass *mc)
{
ccw_machine_rhel900_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_8_6, hw_compat_rhel_8_6_len);
/* 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 2209d4e416..fd75f551b1 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -266,6 +266,8 @@ struct MachineClass {
strList *allowed_dynamic_sysbus_devices;
bool auto_enable_numa_with_memhp;
bool auto_enable_numa_with_memdev;
+ /* RHEL only */
+ bool async_pf_vmexit_disable;
bool ignore_boot_device_suffixes;
bool smbus_no_migration_support;
bool nvdimm_supported;
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 3754eaa97d..4266fe2fdb 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -293,6 +293,33 @@ 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;
+
+extern GlobalProperty pc_rhel_8_4_compat[];
+extern const size_t pc_rhel_8_4_compat_len;
+
+extern GlobalProperty pc_rhel_8_3_compat[];
+extern const size_t pc_rhel_8_3_compat_len;
+
+extern GlobalProperty pc_rhel_8_2_compat[];
+extern const size_t pc_rhel_8_2_compat_len;
+
+extern GlobalProperty pc_rhel_8_1_compat[];
+extern const size_t pc_rhel_8_1_compat_len;
+
+extern GlobalProperty pc_rhel_8_0_compat[];
+extern const size_t pc_rhel_8_0_compat_len;
+
+extern GlobalProperty pc_rhel_7_6_compat[];
+extern const size_t pc_rhel_7_6_compat_len;
+
#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 22b681ca37..f7c526cbe6 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 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[] = {
{ "acpi", "off" },
{ "monitor", "off" },
{ "svm", "off" },
+ { "kvm-pv-unhalt", "on" },
{ NULL, NULL },
};
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index a213209379..81526a1575 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3707,6 +3707,7 @@ 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;
+ MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
kvm_msr_buf_reset(cpu);
@@ -4062,6 +4063,9 @@ static int kvm_get_msrs(X86CPU *cpu)
break;
case MSR_KVM_ASYNC_PF_EN:
env->async_pf_en_msr = msrs[i].data;
+ if (mc->async_pf_vmexit_disable) {
+ env->async_pf_en_msr &= ~(1ULL << 2);
+ }
break;
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 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)
QDict *response, *data;
QTestState *qts;
- qts = qtest_init("-device pvpanic -action panic=none");
+ qts = qtest_init("-M q35 -device pvpanic -action panic=none");
val = qtest_inb(qts, 0x505);
g_assert_cmpuint(val, ==, 3);
@@ -40,7 +40,8 @@ static void test_panic(void)
QDict *response, *data;
QTestState *qts;
- qts = qtest_init("-device pvpanic -action panic=pause");
+ /* RHEL: Use q35 */
+ qts = qtest_init("-M q35 -device pvpanic -action panic=pause");
val = qtest_inb(qts, 0x505);
g_assert_cmpuint(val, ==, 3);
--
2.31.1

261
SOURCES/0011-Enable-make-check.patch
Unescape View File

@ -0,0 +1,261 @@
From badfb1290c8eea8a2e1769b2392c7899d5077698 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
Fixing tests after device disabling and machine types changes and enabling
make check run during build.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase changes (6.1.0):
- removed unnecessary test changes
Rebase changes (6.2.0):
- new way of disabling bios-table-test
Rebase changes (7.0.0):
- Disable testing virtio-iommu-pci
- Rename default_bus_bypass_iommu property to default-bus-bypass-iommu
- Disable qtest-bios-table for aarch64
- Removed redhat chunks for boot-serial-test.c, cdrom-test.c and cpu-plug-test.c qtests
- Do not disable boot-order-test, prom-env-test and boot-serial-test qtests
- Use rhel machine type for new intel hda qtest
- 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 | 7 +------
tests/qtest/usb-hcd-xhci-test.c | 4 ++++
tests/qtest/virtio-net-failover.c | 1 +
12 files changed, 18 insertions(+), 19 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index 00a26e4a0c..fe5ecf238a 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 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)
{
QTestState *s;
- s = qtest_init("-nographic -monitor none -serial none -M pc-q35-5.0");
+ s = qtest_init("-nographic -monitor none -serial none -M pc-q35-rhel8.4.0");
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 e37b48b2cc..88647da054 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)
{
QTestState *s;
- s = qtest_init("-M pc-q35-5.2 -m 512M "
+ s = qtest_init("-M pc-q35-rhel8.4.0 -m 512M "
"-device virtio-scsi,num_queues=8,addr=03.0 ");
qtest_outl(s, 0xcf8, 0x80001811);
diff --git a/tests/qtest/intel-hda-test.c b/tests/qtest/intel-hda-test.c
index d4a8db6fd6..1a796ec15a 100644
--- a/tests/qtest/intel-hda-test.c
+++ b/tests/qtest/intel-hda-test.c
@@ -38,7 +38,7 @@ static void test_issue542_ich6(void)
{
QTestState *s;
- s = qtest_init("-nographic -nodefaults -M pc-q35-6.2 "
+ s = qtest_init("-nographic -nodefaults -M pc-q35-rhel9.0.0 "
"-device intel-hda,id=" HDA_ID CODEC_DEVICES);
qtest_outl(s, 0xcf8, 0x80000804);
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index 32f028872c..1e78a1a055 100644
--- a/tests/qtest/libqos/meson.build
+++ b/tests/qtest/libqos/meson.build
@@ -43,7 +43,7 @@ libqos_srcs = files(
'virtio-rng.c',
'virtio-scsi.c',
'virtio-serial.c',
- 'virtio-iommu.c',
+# 'virtio-iommu.c',
'virtio-gpio.c',
'generic-pcihost.c',
diff --git a/tests/qtest/lpc-ich9-test.c b/tests/qtest/lpc-ich9-test.c
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)
{
QTestState *s;
- s = qtest_init("-M pc-q35-5.0 "
+ s = qtest_init("-M pc-q35-rhel8.4.0 "
"-nographic -monitor none -serial none");
qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index c07a5b1a5f..9df3f9f8b9 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -82,7 +82,6 @@ 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',
@@ -96,7 +95,6 @@ qtests_i386 = \
'drive_del-test',
'tco-test',
'cpu-plug-test',
- 'q35-test',
'vmgenid-test',
'migration-test',
'test-x86-cpuid-compat',
@@ -209,15 +207,13 @@ qtests_arm = \
# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional
qtests_aarch64 = \
- (cpu != 'arm' and unpack_edk2_blobs ? ['bios-tables-test'] : []) + \
(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'] : []) + \
['arm-cpu-features',
'numa-test',
'boot-serial-test',
- 'migration-test',
- 'bcm2835-dma-test']
+ 'migration-test']
qtests_s390x = \
(slirp.found() ? ['pxe-test', 'test-netfilter'] : []) + \
@@ -225,7 +221,6 @@ qtests_s390x = \
(config_host.has_key('CONFIG_POSIX') ? ['test-filter-redirector'] : []) + \
['boot-serial-test',
'drive_del-test',
- 'device-plug-test',
'virtio-ccw-test',
'cpu-plug-test',
'migration-test']
diff --git a/tests/qtest/usb-hcd-xhci-test.c b/tests/qtest/usb-hcd-xhci-test.c
index 10ef9d2a91..3855873050 100644
--- a/tests/qtest/usb-hcd-xhci-test.c
+++ b/tests/qtest/usb-hcd-xhci-test.c
@@ -21,6 +21,7 @@ static void test_xhci_hotplug(void)
usb_test_hotplug(global_qtest, "xhci", "1", NULL);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void test_usb_uas_hotplug(void)
{
QTestState *qts = global_qtest;
@@ -36,6 +37,7 @@ static void test_usb_uas_hotplug(void)
qtest_qmp_device_del(qts, "scsihd");
qtest_qmp_device_del(qts, "uas");
}
+#endif
static void test_usb_ccid_hotplug(void)
{
@@ -56,7 +58,9 @@ int main(int argc, char **argv)
qtest_add_func("/xhci/pci/init", test_xhci_init);
qtest_add_func("/xhci/pci/hotplug", test_xhci_hotplug);
+#if 0 /* Disabled for Red Hat Enterprise Linux */
qtest_add_func("/xhci/pci/hotplug/usb-uas", test_usb_uas_hotplug);
+#endif
qtest_add_func("/xhci/pci/hotplug/usb-ccid", test_usb_ccid_hotplug);
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 4a809590bf..1bf3fa641c 100644
--- a/tests/qtest/virtio-net-failover.c
+++ b/tests/qtest/virtio-net-failover.c
@@ -25,6 +25,7 @@
#define PCI_SEL_BASE 0x0010
#define BASE_MACHINE "-M q35 -nodefaults " \
+ "-global ICH9-LPC.acpi-pci-hotplug-with-bridge-support=on " \
"-device pcie-root-port,id=root0,addr=0x1,bus=pcie.0,chassis=1 " \
"-device pcie-root-port,id=root1,addr=0x2,bus=pcie.0,chassis=2 "
--
2.31.1

104
SOURCES/0012-vfio-cap-number-of-devices-that-can-be-assigned.patch
Unescape View File

@ -0,0 +1,104 @@
From 0804844e4755377be6d2ebad578794ad9f4f3f31 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
RH-Author: Bandan Das <bsd@redhat.com>
Message-id: <1386101113-31560-3-git-send-email-bsd@redhat.com>
Patchwork-id: 55984
O-Subject: [PATCH RHEL7 qemu-kvm v2 2/2] vfio: cap number of devices that can be assigned
Bugzilla: 678368
RH-Acked-by: Alex Williamson <alex.williamson@redhat.com>
RH-Acked-by: Marcelo Tosatti <mtosatti@redhat.com>
RH-Acked-by: Michael S. Tsirkin <mst@redhat.com>
Go through all groups to get count of total number of devices
active to enforce limit
Reasoning from Alex for the limit(32) - Assuming 3 slots per
device, with 125 slots (number of memory slots for RHEL 7),
we can support almost 40 devices and still have few slots left
for other uses. Stepping down a bit, the number 32 arbitrarily
matches the number of slots on a PCI bus and is also a nice power
of two.
Count of slots increased to 509 later so we could increase limit
to 64 as some usecases require more than 32 devices.
Signed-off-by: Bandan Das <bsd@redhat.com>
---
hw/vfio/pci.c | 29 ++++++++++++++++++++++++++++-
hw/vfio/pci.h | 1 +
2 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 939dcc3d4a..acbc6673ce 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -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);
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;
- int i, ret;
+ int ret, i = 0;
bool is_mdev;
+ if (device_limit && device_limit != vdev->assigned_device_limit) {
+ error_setg(errp, "Assigned device limit has been redefined. "
+ "Old:%d, New:%d",
+ device_limit, vdev->assigned_device_limit);
+ return;
+ } else {
+ device_limit = vdev->assigned_device_limit;
+ }
+
+ QLIST_FOREACH(group, &vfio_group_list, next) {
+ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
+ i++;
+ }
+ }
+
+ if (i >= vdev->assigned_device_limit) {
+ error_setg(errp, "Maximum supported vfio devices (%d) "
+ "already attached", vdev->assigned_device_limit);
+ return;
+ }
+
if (!vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
~vdev->host.slot || ~vdev->host.function)) {
@@ -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),
+ /* RHEL only */
+ DEFINE_PROP_UINT16("x-assigned-device-limit", VFIOPCIDevice,
+ assigned_device_limit, 64),
DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd,
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 7c236a52f4..7b7d036a8f 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -140,6 +140,7 @@ struct VFIOPCIDevice {
EventNotifier err_notifier;
EventNotifier req_notifier;
int (*resetfn)(struct VFIOPCIDevice *);
+ uint16_t assigned_device_limit;
uint32_t vendor_id;
uint32_t device_id;
uint32_t sub_vendor_id;
--
2.31.1

55
SOURCES/0013-Add-support-statement-to-help-output.patch
Unescape View File

@ -0,0 +1,55 @@
From 283a0e258dc2f3b83c58e6f948bafe430cd2c1d5 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
RH-Author: Eduardo Habkost <ehabkost@redhat.com>
Message-id: <1386183197-27761-1-git-send-email-ehabkost@redhat.com>
Patchwork-id: 55994
O-Subject: [qemu-kvm RHEL7 PATCH] Add support statement to -help output
Bugzilla: 972773
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: knoel@redhat.com
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Add support statement to -help output, reporting direct qemu-kvm usage
as unsupported by Red Hat, and advising users to use libvirt instead.
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
softmmu/vl.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 5115221efe..17188df528 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -834,9 +834,17 @@ static void version(void)
QEMU_COPYRIGHT "\n");
}
+static void print_rh_warning(void)
+{
+ printf("\nWARNING: Direct use of qemu-kvm from the command line is not supported by Red Hat.\n"
+ "WARNING: Use libvirt as the stable management interface.\n"
+ "WARNING: Some command line options listed here may not be available in future releases.\n\n");
+}
+
static void help(int exitcode)
{
version();
+ print_rh_warning();
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());
@@ -862,6 +870,7 @@ static void help(int exitcode)
"\n"
QEMU_HELP_BOTTOM "\n");
+ print_rh_warning();
exit(exitcode);
}
--
2.31.1

61
SOURCES/0014-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch
Unescape View File

@ -0,0 +1,61 @@
From d8ded821aa698b3b03bd9089fbd6c2b33da87b9e 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>
Patchwork-id: 62380
O-Subject: [RHEV-7.1 qemu-kvm-rhev PATCHv4] Use qemu-kvm in documentation instead of qemu-system-i386
Bugzilla: 1140620
RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
RH-Acked-by: Markus Armbruster <armbru@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
From: Miroslav Rezanina <mrezanin@redhat.com>
We change the name and location of qemu-kvm binaries. Update documentation
to reflect this change. Only architectures available in RHEL are updated.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
docs/defs.rst.inc | 4 ++--
qemu-options.hx | 10 +++++-----
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/docs/defs.rst.inc b/docs/defs.rst.inc
index 52d6454b93..d74dbdeca9 100644
--- a/docs/defs.rst.inc
+++ b/docs/defs.rst.inc
@@ -9,7 +9,7 @@
but the manpages will end up misrendered with following normal text
incorrectly in boldface.
-.. |qemu_system| replace:: qemu-system-x86_64
-.. |qemu_system_x86| replace:: qemu-system-x86_64
+.. |qemu_system| replace:: qemu-kvm
+.. |qemu_system_x86| replace:: qemu-kvm
.. |I2C| replace:: I\ :sup:`2`\ C
.. |I2S| replace:: I\ :sup:`2`\ S
diff --git a/qemu-options.hx b/qemu-options.hx
index 7f99d15b23..ea02ca3a45 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3300,11 +3300,11 @@ SRST
::
- qemu -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,share=on \
- -numa node,memdev=mem \
- -chardev socket,id=chr0,path=/path/to/socket \
- -netdev type=vhost-user,id=net0,chardev=chr0 \
- -device virtio-net-pci,netdev=net0
+ qemu-kvm -m 512 -object memory-backend-file,id=mem,size=512M,mem-path=/hugetlbfs,share=on \
+ -numa node,memdev=mem \
+ -chardev socket,id=chr0,path=/path/to/socket \
+ -netdev type=vhost-user,id=net0,chardev=chr0 \
+ -device virtio-net-pci,netdev=net0
``-netdev vhost-vdpa[,vhostdev=/path/to/dev][,vhostfd=h]``
Establish a vhost-vdpa netdev.
--
2.31.1

60
SOURCES/0015-BZ1653590-Require-at-least-64kiB-pages-for-downstrea.patch
Unescape View File

@ -0,0 +1,60 @@
From 9c6acadb444c9300d7c18b6939ce4f96484aeacc 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
RH-Author: David Gibson <dgibson@redhat.com>
Message-id: <20190206035856.19058-1-dgibson@redhat.com>
Patchwork-id: 84246
O-Subject: [RHELAV-8.0/rhel qemu-kvm PATCH] BZ1653590: Require at least 64kiB pages for downstream guests & hosts
Bugzilla: 1653590
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Serhii Popovych <spopovyc@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
Most current POWER guests require 64kiB page support, so that's the default
for the cap-hpt-max-pagesize option in qemu which limits available guest
page sizes. We warn if the value is set smaller than that, but don't
outright fail upstream, because we need to allow for the possibility of
guest (and/or host) kernels configured for 4kiB page sizes.
Downstream, however, we simply don't support 4kiB pagesize configured
kernels in guest or host, so we can have qemu simply error out in this
situation.
Testing: Attempted to start a guest with cap-hpt-max-page-size=4k and verified
it failed immediately with a qemu error
Signed-off-by: David Gibson <dgibson@redhat.com>
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
---
hw/ppc/spapr_caps.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c
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,
static void cap_hpt_maxpagesize_apply(SpaprMachineState *spapr,
uint8_t val, Error **errp)
{
+#if 0 /* disabled for RHEL */
if (val < 12) {
error_setg(errp, "Require at least 4kiB hpt-max-page-size");
return;
} else if (val < 16) {
warn_report("Many guests require at least 64kiB hpt-max-page-size");
}
+#else /* Only page sizes >=64kiB supported for RHEL */
+ if (val < 16) {
+ error_setg(errp, "Require at least 64kiB hpt-max-page-size");
+ return;
+ }
+#endif
spapr_check_pagesize(spapr, qemu_minrampagesize(), errp);
}
--
2.31.1

77
SOURCES/0016-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch
Unescape View File

@ -0,0 +1,77 @@
From 02fde2a0cbd679ebd4104fe5522572c31ec23abd 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
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 37: qcow2: Deprecation warning when opening v2 images rw
RH-Commit: [1/1] f450d0ae32d35063b28c72c4f2d2ebb9e6d8db3e (kmwolf/centos-qemu-kvm)
RH-Bugzilla: 1951814
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Hanna Reitz <hreitz@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Philippe Mathieu-Daudé <philmd@redhat.com>
qcow2 v3 has been around for a long time (since QEMU 1.1/RHEL 7), so
there is no real reason any more to use it. People still using it might
do so unintentionally. Warn about it and suggest upgrading during the
RHEL 9 timeframe so that the code can possibly be disabled in RHEL 10.
The warning is restricted to read-write mode and the system emulator.
The primary motivation for not having it in qemu-img is that 'qemu-img
amend' for upgrades would warn otherwise. It also avoids having to make
too many changes to the test suite.
bdrv_uses_whitelist() is used as a proxy for deciding whether we are
running in a tool or the system emulator. This is not entirely clean,
but it's what is available and the same function qcow2_do_open() already
uses it this way for another warning.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
patch_name: kvm-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch
present_in_specfile: true
location_in_specfile: 116
---
Rebase notes (6.1.0):
- Replace bs->read_only with bdrv_is_read_only
---
block/qcow2.c | 6 ++++++
tests/qemu-iotests/common.filter | 1 +
2 files changed, 7 insertions(+)
diff --git a/block/qcow2.c b/block/qcow2.c
index 4d6666d3ff..d2ba263e9d 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1336,6 +1336,12 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options,
ret = -ENOTSUP;
goto fail;
}
+ if (header.version < 3 && !bdrv_is_read_only(bs) && bdrv_uses_whitelist()) {
+ warn_report_once("qcow2 v2 images are deprecated and may not be "
+ "supported in future versions. Please consider "
+ "upgrading the image with 'qemu-img amend "
+ "-o compat=v3'.");
+ }
s->qcow_version = header.version;
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index cc9f1a5891..6a13757177 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -83,6 +83,7 @@ _filter_qemu()
{
gsed -e "s#\\(^\\|(qemu) \\)$(basename $QEMU_PROG):#\1QEMU_PROG:#" \
-e 's#^QEMU [0-9]\+\.[0-9]\+\.[0-9]\+ monitor#QEMU X.Y.Z monitor#' \
+ -e "/qcow2 v2 images are deprecated/d" \
-e $'s#\r##' # QEMU monitor uses \r\n line endings
}
--
2.31.1

26
SOURCES/0018-Addd-7.2-compat-bits-for-RHEL-9.1-machine-type.patch
Unescape View File

@ -0,0 +1,26 @@
From 21ed34787b9492c2cfe3d8fc12a32748bcf02307 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 9 Nov 2022 07:08:32 -0500
Subject: Addd 7.2 compat bits for RHEL 9.1 machine type
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
hw/core/machine.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 9edec1ca05..3d851d34da 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -54,6 +54,8 @@ GlobalProperty hw_compat_rhel_9_1[] = {
{ "arm-gicv3-common", "force-8-bit-prio", "on" },
/* hw_compat_rhel_9_1 from hw_compat_7_0 */
{ "nvme-ns", "eui64-default", "on"},
+ /* hw_compat_rhel_9_1 from hw_compat_7_1 */
+ { "virtio-device", "queue_reset", "false" },
};
const size_t hw_compat_rhel_9_1_len = G_N_ELEMENTS(hw_compat_rhel_9_1);
--
2.31.1

47
SOURCES/0019-redhat-Update-s390x-machine-type-compatibility-for-Q.patch
Unescape View File

@ -0,0 +1,47 @@
From 27c188c6a4cbd908269cf06affd24025708ecb5c Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 17 Nov 2022 16:47:16 +0100
Subject: redhat: Update s390x machine type compatibility for QEMU 7.2.0 update
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2143585
Upstream Status: n/a (rhel-only)
Add the compatibility handling for the rebase from QEMU 7.1 to 7.2,
i.e. the settings from ccw_machine_7_1_class_options() and
ccw_machine_7_1_instance_options() to the rhel9.1.0 machine type
(earlier settings have been added by previous rebases already).
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index ba640e3d9e..97e868ada0 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1195,12 +1195,21 @@ 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);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAIE);
}
static void ccw_machine_rhel900_class_options(MachineClass *mc)
{
+ S390CcwMachineClass *s390mc = S390_CCW_MACHINE_CLASS(mc);
+ static GlobalProperty compat[] = {
+ { TYPE_S390_PCI_DEVICE, "interpret", "off", },
+ { TYPE_S390_PCI_DEVICE, "forwarding-assist", "off", },
+ };
+
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
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);
+ s390mc->max_threads = S390_MAX_CPUS;
}
DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
--
2.31.1

43
SOURCES/0020-redhat-aarch64-add-rhel9.2.0-virt-machine-type.patch
Unescape View File

@ -0,0 +1,43 @@
From c1a21266d8bed27f1ef1f705818fde5f9350b73f Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Wed, 23 Nov 2022 14:15:37 +0100
Subject: redhat: aarch64: add rhel9.2.0 virt machine type
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2131982
Upstream: RHEL only
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
hw/arm/virt.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index dfcab40a73..0a94f31dd1 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3518,14 +3518,21 @@ static void rhel_machine_init(void)
}
type_init(rhel_machine_init);
+static void rhel920_virt_options(MachineClass *mc)
+{
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 2, 0)
+
static void rhel900_virt_options(MachineClass *mc)
{
VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+ rhel920_virt_options(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;
}
-DEFINE_RHEL_MACHINE_AS_LATEST(9, 0, 0)
+DEFINE_RHEL_MACHINE(9, 0, 0)
--
2.31.1

62
SOURCES/0021-redhat-Add-new-rhel-9.2.0-s390x-machine-type.patch
Unescape View File

@ -0,0 +1,62 @@
From a932b8d4296066be01613ada84241b501488f99f Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 17 Nov 2022 17:03:24 +0100
Subject: redhat: Add new rhel-9.2.0 s390x machine type
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2136473
Upstream Status: n/a (rhel-only)
RHEL 9.2 will be an EUS release - we want to have a new machine
type here to make sure that we have a spot where we can wire up
fixes later.
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 97e868ada0..aa142a1a4e 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1190,10 +1190,21 @@ DEFINE_CCW_MACHINE(2_4, "2.4", false);
#endif
+static void ccw_machine_rhel920_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_machine_rhel920_class_options(MachineClass *mc)
+{
+}
+DEFINE_CCW_MACHINE(rhel920, "rhel9.2.0", true);
+
static void ccw_machine_rhel900_instance_options(MachineState *machine)
{
static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+ ccw_machine_rhel920_instance_options(machine);
+
s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAIE);
}
@@ -1206,12 +1217,14 @@ static void ccw_machine_rhel900_class_options(MachineClass *mc)
{ TYPE_S390_PCI_DEVICE, "forwarding-assist", "off", },
};
+ ccw_machine_rhel920_class_options(mc);
+
compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
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);
s390mc->max_threads = S390_MAX_CPUS;
}
-DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", true);
+DEFINE_CCW_MACHINE(rhel900, "rhel9.0.0", false);
static void ccw_machine_rhel860_instance_options(MachineState *machine)
{
--
2.31.1

75
SOURCES/0022-x86-rhel-9.2.0-machine-type.patch
Unescape View File

@ -0,0 +1,75 @@
From f33ca8aed4744238230f1f2cc47df77aa4c9e0ac Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Date: Thu, 17 Nov 2022 12:36:30 +0000
Subject: x86: rhel 9.2.0 machine type
Add a 9.2.0 x86 machine type, and fix up the compatibility
for 9.0.0 and older.
pc_compat_7_1 and pc_compat_7_0 are both empty upstream so there's
nothing to do there.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
hw/i386/pc_piix.c | 1 +
hw/i386/pc_q35.c | 21 ++++++++++++++++++++-
2 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 173a1fd10b..fc06877344 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -944,6 +944,7 @@ static void pc_machine_rhel760_options(MachineClass *m)
/* From pc_i440fx_5_1_machine_options() */
pcmc->pci_root_uid = 1;
pcmc->legacy_no_rng_seed = true;
+ pcmc->enforce_amd_1tb_hole = false;
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,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 97c3630021..52cfe3bf45 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -692,6 +692,23 @@ static void pc_q35_machine_rhel_options(MachineClass *m)
compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
}
+static void pc_q35_init_rhel920(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel920_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel_options(m);
+ m->desc = "RHEL-9.2.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.2.0";
+}
+
+DEFINE_PC_MACHINE(q35_rhel920, "pc-q35-rhel9.2.0", pc_q35_init_rhel920,
+ pc_q35_machine_rhel920_options);
+
static void pc_q35_init_rhel900(MachineState *machine)
{
pc_q35_init(machine);
@@ -700,11 +717,13 @@ static void pc_q35_init_rhel900(MachineState *machine)
static void pc_q35_machine_rhel900_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
- pc_q35_machine_rhel_options(m);
+ pc_q35_machine_rhel920_options(m);
m->desc = "RHEL-9.0.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.0.0";
pcmc->legacy_no_rng_seed = true;
+ pcmc->enforce_amd_1tb_hole = false;
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,
--
2.31.1

10
SOURCES/95-kvm-memlock.conf
Unescape View File

@ -0,0 +1,10 @@
# The KVM HV implementation on Power can require a significant amount
# of unswappable memory (about half of which also needs to be host
# physically contiguous) to hold the guest's Hash Page Table (HPT) -
# roughly 1/64th of the guest's RAM size, minimum 16MiB.
#
# These limits allow unprivileged users to start smallish VMs, such as
# those used by libguestfs.
#
* hard memlock 65536
* soft memlock 65536

2
SOURCES/99-qemu-guest-agent.rules
Unescape View File

@ -0,0 +1,2 @@
SUBSYSTEM=="virtio-ports", ATTR{name}=="org.qemu.guest_agent.0", \
TAG+="systemd" ENV{SYSTEMD_WANTS}="qemu-guest-agent.service"

39
SOURCES/README.tests
Unescape View File

@ -0,0 +1,39 @@
qemu-kvm-tests README
=====================
The qemu-kvm-tests rpm contains tests that can be used to verify the
functionality of the installed qemu-kvm package
When installed, the files from this rpm will be arranged in the following
directory structure
tests-src/
├── README
├── scripts
│   ├── qemu.py
│   └── qmp
└── tests
├── acceptance
├── Makefile.include
└── qemu-iotests
The tests/ directory within the tests-src/ directory is setup to remain a copy
of a subset of the tests/ directory from the QEMU source tree
The avocado_qemu tests and qemu-iotests, along with files required for the
execution of the avocado_qemu tests (scripts/qemu.py and scripts/qmp/) will be
installed in a new location - /usr/lib64/qemu-kvm/tests-src/
avocado_qemu tests:
The avocado_qemu tests can be executed by running the following avocado command:
avocado run -p qemu_bin=/usr/libexec/qemu-kvm /usr/lib64/qemu-kvm/tests/acceptance/
Avocado needs to be installed separately using either pip or from source as
Avocado is not being packaged for RHEL-8.
qemu-iotests:
symlinks to corresponding binaries need to be created for QEMU_PROG,
QEMU_IO_PROG, QEMU_IMG_PROG, and QEMU_NBD_PROG before the iotests can be
executed.
The primary purpose of this package is to make these tests available to be
executed as gating tests for the virt module in the RHEL-8 OSCI environment.

1
SOURCES/bridge.conf
Unescape View File

@ -0,0 +1 @@
allow virbr0

82
SOURCES/kvm-KVM-keep-track-of-running-ioctls.patch
Unescape View File

@ -0,0 +1,82 @@
From 6aebc271d95f9c59cb63c923b6ce35f16fce10e4 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 16 Jan 2023 07:17:23 -0500
Subject: [PATCH 30/31] KVM: keep track of running ioctls
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 138: accel: introduce accelerator blocker API
RH-Bugzilla: 1979276
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/3] f566f81dda26ae733008f32261ecd1253ec1796d (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1979276
commit a27dd2de68f37ba96fe164a42121daa5f0750afc
Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Fri Nov 11 10:47:57 2022 -0500
KVM: keep track of running ioctls
Using the new accel-blocker API, mark where ioctls are being called
in KVM. Next, we will implement the critical section that will take
care of performing memslots modifications atomically, therefore
preventing any new ioctl from running and allowing the running ones
to finish.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20221111154758.1372674-3-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
accel/kvm/kvm-all.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f99b0becd8..ff660fd469 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2310,6 +2310,7 @@ static int kvm_init(MachineState *ms)
assert(TARGET_PAGE_SIZE <= qemu_real_host_page_size());
s->sigmask_len = 8;
+ accel_blocker_init();
#ifdef KVM_CAP_SET_GUEST_DEBUG
QTAILQ_INIT(&s->kvm_sw_breakpoints);
@@ -3014,7 +3015,9 @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
va_end(ap);
trace_kvm_vm_ioctl(type, arg);
+ accel_ioctl_begin();
ret = ioctl(s->vmfd, type, arg);
+ accel_ioctl_end();
if (ret == -1) {
ret = -errno;
}
@@ -3032,7 +3035,9 @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
va_end(ap);
trace_kvm_vcpu_ioctl(cpu->cpu_index, type, arg);
+ accel_cpu_ioctl_begin(cpu);
ret = ioctl(cpu->kvm_fd, type, arg);
+ accel_cpu_ioctl_end(cpu);
if (ret == -1) {
ret = -errno;
}
@@ -3050,7 +3055,9 @@ int kvm_device_ioctl(int fd, int type, ...)
va_end(ap);
trace_kvm_device_ioctl(fd, type, arg);
+ accel_ioctl_begin();
ret = ioctl(fd, type, arg);
+ accel_ioctl_end();
if (ret == -1) {
ret = -errno;
}
--
2.31.1

140
SOURCES/kvm-Revert-vhost-user-Introduce-nested-event-loop-in-vho.patch
Unescape View File

@ -0,0 +1,140 @@
From 0c19fb7c4a22a30830152b224b2e66963f829a7a Mon Sep 17 00:00:00 2001
From: Greg Kurz <groug@kaod.org>
Date: Thu, 19 Jan 2023 18:24:24 +0100
Subject: [PATCH 19/20] Revert "vhost-user: Introduce nested event loop in
vhost_user_read()"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 146: Fix vhost-user with dpdk
RH-Bugzilla: 2155173
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Greg Kurz (RH) <gkurz@redhat.com>
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Commit: [2/2] 9b67041f92f29f70b7ccb41d8087801e4e4e38af (lvivier/qemu-kvm-centos)
This reverts commit a7f523c7d114d445c5d83aecdba3efc038e5a692.
The nested event loop is broken by design. It's only user was removed.
Drop the code as well so that nobody ever tries to use it again.
I had to fix a couple of trivial conflicts around return values because
of 025faa872bcf ("vhost-user: stick to -errno error return convention").
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20230119172424.478268-3-groug@kaod.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
(cherry picked from commit 4382138f642f69fdbc79ebf4e93d84be8061191f)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/virtio/vhost-user.c | 65 ++++--------------------------------------
1 file changed, 5 insertions(+), 60 deletions(-)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 0ac00eb901..7cb49c50f9 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -305,19 +305,8 @@ static int vhost_user_read_header(struct vhost_dev *dev, VhostUserMsg *msg)
return 0;
}
-struct vhost_user_read_cb_data {
- struct vhost_dev *dev;
- VhostUserMsg *msg;
- GMainLoop *loop;
- int ret;
-};
-
-static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
- gpointer opaque)
+static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
- struct vhost_user_read_cb_data *data = opaque;
- struct vhost_dev *dev = data->dev;
- VhostUserMsg *msg = data->msg;
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
uint8_t *p = (uint8_t *) msg;
@@ -325,8 +314,7 @@ static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
r = vhost_user_read_header(dev, msg);
if (r < 0) {
- data->ret = r;
- goto end;
+ return r;
}
/* validate message size is sane */
@@ -334,8 +322,7 @@ static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
error_report("Failed to read msg header."
" Size %d exceeds the maximum %zu.", msg->hdr.size,
VHOST_USER_PAYLOAD_SIZE);
- data->ret = -EPROTO;
- goto end;
+ return -EPROTO;
}
if (msg->hdr.size) {
@@ -346,53 +333,11 @@ static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition,
int saved_errno = errno;
error_report("Failed to read msg payload."
" Read %d instead of %d.", r, msg->hdr.size);
- data->ret = r < 0 ? -saved_errno : -EIO;
- goto end;
+ return r < 0 ? -saved_errno : -EIO;
}
}
-end:
- g_main_loop_quit(data->loop);
- return G_SOURCE_REMOVE;
-}
-
-static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
-{
- struct vhost_user *u = dev->opaque;
- CharBackend *chr = u->user->chr;
- GMainContext *prev_ctxt = chr->chr->gcontext;
- GMainContext *ctxt = g_main_context_new();
- GMainLoop *loop = g_main_loop_new(ctxt, FALSE);
- struct vhost_user_read_cb_data data = {
- .dev = dev,
- .loop = loop,
- .msg = msg,
- .ret = 0
- };
-
- /*
- * We want to be able to monitor the slave channel fd while waiting
- * for chr I/O. This requires an event loop, but we can't nest the
- * one to which chr is currently attached : its fd handlers might not
- * be prepared for re-entrancy. So we create a new one and switch chr
- * to use it.
- */
- qemu_chr_be_update_read_handlers(chr->chr, ctxt);
- qemu_chr_fe_add_watch(chr, G_IO_IN | G_IO_HUP, vhost_user_read_cb, &data);
-
- g_main_loop_run(loop);
-
- /*
- * Restore the previous event loop context. This also destroys/recreates
- * event sources : this guarantees that all pending events in the original
- * context that have been processed by the nested loop are purged.
- */
- qemu_chr_be_update_read_handlers(chr->chr, prev_ctxt);
-
- g_main_loop_unref(loop);
- g_main_context_unref(ctxt);
-
- return data.ret;
+ return 0;
}
static int process_message_reply(struct vhost_dev *dev,
--
2.31.1

143
SOURCES/kvm-Revert-vhost-user-Monitor-slave-channel-in-vhost_use.patch
Unescape View File

@ -0,0 +1,143 @@
From 9fb47ad317ad8cdda9960190d499ad6c3a9817f0 Mon Sep 17 00:00:00 2001
From: Greg Kurz <groug@kaod.org>
Date: Thu, 19 Jan 2023 18:24:23 +0100
Subject: [PATCH 18/20] Revert "vhost-user: Monitor slave channel in
vhost_user_read()"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 146: Fix vhost-user with dpdk
RH-Bugzilla: 2155173
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Greg Kurz (RH) <gkurz@redhat.com>
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Commit: [1/2] c583a7f121ca9c93c9a2ad17bf0ccf5c1241dc99 (lvivier/qemu-kvm-centos)
This reverts commit db8a3772e300c1a656331a92da0785d81667dc81.
Motivation : this is breaking vhost-user with DPDK as reported in [0].
Received unexpected msg type. Expected 22 received 40
Fail to update device iotlb
Received unexpected msg type. Expected 40 received 22
Received unexpected msg type. Expected 22 received 11
Fail to update device iotlb
Received unexpected msg type. Expected 11 received 22
vhost VQ 1 ring restore failed: -71: Protocol error (71)
Received unexpected msg type. Expected 22 received 11
Fail to update device iotlb
Received unexpected msg type. Expected 11 received 22
vhost VQ 0 ring restore failed: -71: Protocol error (71)
unable to start vhost net: 71: falling back on userspace virtio
The failing sequence that leads to the first error is :
- QEMU sends a VHOST_USER_GET_STATUS (40) request to DPDK on the master
socket
- QEMU starts a nested event loop in order to wait for the
VHOST_USER_GET_STATUS response and to be able to process messages from
the slave channel
- DPDK sends a couple of legitimate IOTLB miss messages on the slave
channel
- QEMU processes each IOTLB request and sends VHOST_USER_IOTLB_MSG (22)
updates on the master socket
- QEMU assumes to receive a response for the latest VHOST_USER_IOTLB_MSG
but it gets the response for the VHOST_USER_GET_STATUS instead
The subsequent errors have the same root cause : the nested event loop
breaks the order by design. It lures QEMU to expect responses to the
latest message sent on the master socket to arrive first.
Since this was only needed for DAX enablement which is still not merged
upstream, just drop the code for now. A working solution will have to
be merged later on. Likely protect the master socket with a mutex
and service the slave channel with a separate thread, as discussed with
Maxime in the mail thread below.
[0] https://lore.kernel.org/qemu-devel/43145ede-89dc-280e-b953-6a2b436de395@redhat.com/
Reported-by: Yanghang Liu <yanghliu@redhat.com>
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2155173
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20230119172424.478268-2-groug@kaod.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
(cherry picked from commit f340a59d5a852d75ae34555723694c7e8eafbd0c)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/virtio/vhost-user.c | 35 +++--------------------------------
1 file changed, 3 insertions(+), 32 deletions(-)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 8f635844af..0ac00eb901 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -356,35 +356,6 @@ end:
return G_SOURCE_REMOVE;
}
-static gboolean slave_read(QIOChannel *ioc, GIOCondition condition,
- gpointer opaque);
-
-/*
- * This updates the read handler to use a new event loop context.
- * Event sources are removed from the previous context : this ensures
- * that events detected in the previous context are purged. They will
- * be re-detected and processed in the new context.
- */
-static void slave_update_read_handler(struct vhost_dev *dev,
- GMainContext *ctxt)
-{
- struct vhost_user *u = dev->opaque;
-
- if (!u->slave_ioc) {
- return;
- }
-
- if (u->slave_src) {
- g_source_destroy(u->slave_src);
- g_source_unref(u->slave_src);
- }
-
- u->slave_src = qio_channel_add_watch_source(u->slave_ioc,
- G_IO_IN | G_IO_HUP,
- slave_read, dev, NULL,
- ctxt);
-}
-
static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
struct vhost_user *u = dev->opaque;
@@ -406,7 +377,6 @@ static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
* be prepared for re-entrancy. So we create a new one and switch chr
* to use it.
*/
- slave_update_read_handler(dev, ctxt);
qemu_chr_be_update_read_handlers(chr->chr, ctxt);
qemu_chr_fe_add_watch(chr, G_IO_IN | G_IO_HUP, vhost_user_read_cb, &data);
@@ -418,7 +388,6 @@ static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
* context that have been processed by the nested loop are purged.
*/
qemu_chr_be_update_read_handlers(chr->chr, prev_ctxt);
- slave_update_read_handler(dev, NULL);
g_main_loop_unref(loop);
g_main_context_unref(ctxt);
@@ -1802,7 +1771,9 @@ static int vhost_setup_slave_channel(struct vhost_dev *dev)
return -ECONNREFUSED;
}
u->slave_ioc = ioc;
- slave_update_read_handler(dev, NULL);
+ u->slave_src = qio_channel_add_watch_source(u->slave_ioc,
+ G_IO_IN | G_IO_HUP,
+ slave_read, dev, NULL, NULL);
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
--
2.31.1

348
SOURCES/kvm-accel-introduce-accelerator-blocker-API.patch
Unescape View File

@ -0,0 +1,348 @@
From ae2077fd5d351a68c313c64f07fb225dff694a8f Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 16 Jan 2023 07:16:41 -0500
Subject: [PATCH 29/31] accel: introduce accelerator blocker API
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 138: accel: introduce accelerator blocker API
RH-Bugzilla: 1979276
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/3] 56b07cd7db516c5066e6d66b4695064fdf73abbf (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1979276
commit bd688fc93120fb3e28aa70e3dfdf567ccc1e0bc1
Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Fri Nov 11 10:47:56 2022 -0500
accel: introduce accelerator blocker API
This API allows the accelerators to prevent vcpus from issuing
new ioctls while execting a critical section marked with the
accel_ioctl_inhibit_begin/end functions.
Note that all functions submitting ioctls must mark where the
ioctl is being called with accel_{cpu_}ioctl_begin/end().
This API requires the caller to always hold the BQL.
API documentation is in sysemu/accel-blocker.h
Internally, it uses a QemuLockCnt together with a per-CPU QemuLockCnt
(to minimize cache line bouncing) to keep avoid that new ioctls
run when the critical section starts, and a QemuEvent to wait
that all running ioctls finish.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20221111154758.1372674-2-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Conflicts:
util/meson.build: "interval-tree.c" does not exist
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
accel/accel-blocker.c | 154 +++++++++++++++++++++++++++++++++
accel/meson.build | 2 +-
hw/core/cpu-common.c | 2 +
include/hw/core/cpu.h | 3 +
include/sysemu/accel-blocker.h | 56 ++++++++++++
util/meson.build | 2 +-
6 files changed, 217 insertions(+), 2 deletions(-)
create mode 100644 accel/accel-blocker.c
create mode 100644 include/sysemu/accel-blocker.h
diff --git a/accel/accel-blocker.c b/accel/accel-blocker.c
new file mode 100644
index 0000000000..1e7f423462
--- /dev/null
+++ b/accel/accel-blocker.c
@@ -0,0 +1,154 @@
+/*
+ * Lock to inhibit accelerator ioctls
+ *
+ * Copyright (c) 2022 Red Hat Inc.
+ *
+ * Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/thread.h"
+#include "qemu/main-loop.h"
+#include "hw/core/cpu.h"
+#include "sysemu/accel-blocker.h"
+
+static QemuLockCnt accel_in_ioctl_lock;
+static QemuEvent accel_in_ioctl_event;
+
+void accel_blocker_init(void)
+{
+ qemu_lockcnt_init(&accel_in_ioctl_lock);
+ qemu_event_init(&accel_in_ioctl_event, false);
+}
+
+void accel_ioctl_begin(void)
+{
+ if (likely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ /* block if lock is taken in kvm_ioctl_inhibit_begin() */
+ qemu_lockcnt_inc(&accel_in_ioctl_lock);
+}
+
+void accel_ioctl_end(void)
+{
+ if (likely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ qemu_lockcnt_dec(&accel_in_ioctl_lock);
+ /* change event to SET. If event was BUSY, wake up all waiters */
+ qemu_event_set(&accel_in_ioctl_event);
+}
+
+void accel_cpu_ioctl_begin(CPUState *cpu)
+{
+ if (unlikely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ /* block if lock is taken in kvm_ioctl_inhibit_begin() */
+ qemu_lockcnt_inc(&cpu->in_ioctl_lock);
+}
+
+void accel_cpu_ioctl_end(CPUState *cpu)
+{
+ if (unlikely(qemu_mutex_iothread_locked())) {
+ return;
+ }
+
+ qemu_lockcnt_dec(&cpu->in_ioctl_lock);
+ /* change event to SET. If event was BUSY, wake up all waiters */
+ qemu_event_set(&accel_in_ioctl_event);
+}
+
+static bool accel_has_to_wait(void)
+{
+ CPUState *cpu;
+ bool needs_to_wait = false;
+
+ CPU_FOREACH(cpu) {
+ if (qemu_lockcnt_count(&cpu->in_ioctl_lock)) {
+ /* exit the ioctl, if vcpu is running it */
+ qemu_cpu_kick(cpu);
+ needs_to_wait = true;
+ }
+ }
+
+ return needs_to_wait || qemu_lockcnt_count(&accel_in_ioctl_lock);
+}
+
+void accel_ioctl_inhibit_begin(void)
+{
+ CPUState *cpu;
+
+ /*
+ * We allow to inhibit only when holding the BQL, so we can identify
+ * when an inhibitor wants to issue an ioctl easily.
+ */
+ g_assert(qemu_mutex_iothread_locked());
+
+ /* Block further invocations of the ioctls outside the BQL. */
+ CPU_FOREACH(cpu) {
+ qemu_lockcnt_lock(&cpu->in_ioctl_lock);
+ }
+ qemu_lockcnt_lock(&accel_in_ioctl_lock);
+
+ /* Keep waiting until there are running ioctls */
+ while (true) {
+
+ /* Reset event to FREE. */
+ qemu_event_reset(&accel_in_ioctl_event);
+
+ if (accel_has_to_wait()) {
+ /*
+ * If event is still FREE, and there are ioctls still in progress,
+ * wait.
+ *
+ * If an ioctl finishes before qemu_event_wait(), it will change
+ * the event state to SET. This will prevent qemu_event_wait() from
+ * blocking, but it's not a problem because if other ioctls are
+ * still running the loop will iterate once more and reset the event
+ * status to FREE so that it can wait properly.
+ *
+ * If an ioctls finishes while qemu_event_wait() is blocking, then
+ * it will be waken up, but also here the while loop makes sure
+ * to re-enter the wait if there are other running ioctls.
+ */
+ qemu_event_wait(&accel_in_ioctl_event);
+ } else {
+ /* No ioctl is running */
+ return;
+ }
+ }
+}
+
+void accel_ioctl_inhibit_end(void)
+{
+ CPUState *cpu;
+
+ qemu_lockcnt_unlock(&accel_in_ioctl_lock);
+ CPU_FOREACH(cpu) {
+ qemu_lockcnt_unlock(&cpu->in_ioctl_lock);
+ }
+}
+
diff --git a/accel/meson.build b/accel/meson.build
index 259c35c4c8..061332610f 100644
--- a/accel/meson.build
+++ b/accel/meson.build
@@ -1,4 +1,4 @@
-specific_ss.add(files('accel-common.c'))
+specific_ss.add(files('accel-common.c', 'accel-blocker.c'))
softmmu_ss.add(files('accel-softmmu.c'))
user_ss.add(files('accel-user.c'))
diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c
index f9fdd46b9d..8d6a4b1b65 100644
--- a/hw/core/cpu-common.c
+++ b/hw/core/cpu-common.c
@@ -237,6 +237,7 @@ static void cpu_common_initfn(Object *obj)
cpu->nr_threads = 1;
qemu_mutex_init(&cpu->work_mutex);
+ qemu_lockcnt_init(&cpu->in_ioctl_lock);
QSIMPLEQ_INIT(&cpu->work_list);
QTAILQ_INIT(&cpu->breakpoints);
QTAILQ_INIT(&cpu->watchpoints);
@@ -248,6 +249,7 @@ static void cpu_common_finalize(Object *obj)
{
CPUState *cpu = CPU(obj);
+ qemu_lockcnt_destroy(&cpu->in_ioctl_lock);
qemu_mutex_destroy(&cpu->work_mutex);
}
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 8830546121..2417597236 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -398,6 +398,9 @@ struct CPUState {
uint32_t kvm_fetch_index;
uint64_t dirty_pages;
+ /* Use by accel-block: CPU is executing an ioctl() */
+ QemuLockCnt in_ioctl_lock;
+
/* Used for events with 'vcpu' and *without* the 'disabled' properties */
DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS);
DECLARE_BITMAP(trace_dstate, CPU_TRACE_DSTATE_MAX_EVENTS);
diff --git a/include/sysemu/accel-blocker.h b/include/sysemu/accel-blocker.h
new file mode 100644
index 0000000000..72020529ef
--- /dev/null
+++ b/include/sysemu/accel-blocker.h
@@ -0,0 +1,56 @@
+/*
+ * Accelerator blocking API, to prevent new ioctls from starting and wait the
+ * running ones finish.
+ * This mechanism differs from pause/resume_all_vcpus() in that it does not
+ * release the BQL.
+ *
+ * Copyright (c) 2022 Red Hat Inc.
+ *
+ * Author: Emanuele Giuseppe Esposito <eesposit@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 ACCEL_BLOCKER_H
+#define ACCEL_BLOCKER_H
+
+#include "qemu/osdep.h"
+#include "sysemu/cpus.h"
+
+extern void accel_blocker_init(void);
+
+/*
+ * accel_{cpu_}ioctl_begin/end:
+ * Mark when ioctl is about to run or just finished.
+ *
+ * accel_{cpu_}ioctl_begin will block after accel_ioctl_inhibit_begin() is
+ * called, preventing new ioctls to run. They will continue only after
+ * accel_ioctl_inibith_end().
+ */
+extern void accel_ioctl_begin(void);
+extern void accel_ioctl_end(void);
+extern void accel_cpu_ioctl_begin(CPUState *cpu);
+extern void accel_cpu_ioctl_end(CPUState *cpu);
+
+/*
+ * accel_ioctl_inhibit_begin: start critical section
+ *
+ * This function makes sure that:
+ * 1) incoming accel_{cpu_}ioctl_begin() calls block
+ * 2) wait that all ioctls that were already running reach
+ * accel_{cpu_}ioctl_end(), kicking vcpus if necessary.
+ *
+ * This allows the caller to access shared data or perform operations without
+ * worrying of concurrent vcpus accesses.
+ */
+extern void accel_ioctl_inhibit_begin(void);
+
+/*
+ * accel_ioctl_inhibit_end: end critical section started by
+ * accel_ioctl_inhibit_begin()
+ *
+ * This function allows blocked accel_{cpu_}ioctl_begin() to continue.
+ */
+extern void accel_ioctl_inhibit_end(void);
+
+#endif /* ACCEL_BLOCKER_H */
diff --git a/util/meson.build b/util/meson.build
index 25b9b61f98..85a5504c4d 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -57,6 +57,7 @@ util_ss.add(files('guest-random.c'))
util_ss.add(files('yank.c'))
util_ss.add(files('int128.c'))
util_ss.add(files('memalign.c'))
+util_ss.add(files('lockcnt.c'))
if have_user
util_ss.add(files('selfmap.c'))
@@ -71,7 +72,6 @@ endif
if have_block or have_ga
util_ss.add(files('aiocb.c', 'async.c'))
util_ss.add(files('base64.c'))
- util_ss.add(files('lockcnt.c'))
util_ss.add(files('main-loop.c'))
util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c'))
util_ss.add(files('coroutine-@0@.c'.format(config_host['CONFIG_COROUTINE_BACKEND'])))
--
2.31.1

58
SOURCES/kvm-accel-tcg-Test-CPUJumpCache-in-tb_jmp_cache_clear_pa.patch
Unescape View File

@ -0,0 +1,58 @@
From ab68e13b7628f2348d41a4518a92508542af712f Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Fri, 3 Feb 2023 18:15:10 +0100
Subject: [PATCH 05/20] accel/tcg: Test CPUJumpCache in tb_jmp_cache_clear_page
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 144: accel/tcg: Test CPUJumpCache in tb_jmp_cache_clear_page
RH-Bugzilla: 2165280
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Shaoqin Huang <None>
RH-Commit: [1/1] 5b0863c34ba06c01c4e343d1ecd72402779c7de3 (eauger1/centos-qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/2165280
Upstream: yes
Brew: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=50530041
Test: 'kvm unit test ./run_tests.sh -g debug' does not SIGSEV anymore
After commit 4e4fa6c12d ("accel/tcg: Complete cpu initialization
before registration"), it looks the CPUJumpCache pointer can be NULL.
This causes a SIGSEV when running debug-wp-migration kvm unit test.
At the first place it should be clarified why this TCG code is called
with KVM acceleration. This may hide another bug.
Fixes: 4e4fa6c12d ("accel/tcg: Complete cpu initialization before registration")
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20230203171510.2867451-1-eric.auger@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
(cherry picked from commit 99ab4d500af638ba3ebb20e8aa89d72201b70860)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
accel/tcg/cputlb.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index 6f1c00682b..4244b0e4e3 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -100,9 +100,14 @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,
static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr)
{
- int i, i0 = tb_jmp_cache_hash_page(page_addr);
CPUJumpCache *jc = cpu->tb_jmp_cache;
+ int i, i0;
+ if (unlikely(!jc)) {
+ return;
+ }
+
+ i0 = tb_jmp_cache_hash_page(page_addr);
for (i = 0; i < TB_JMP_PAGE_SIZE; i++) {
qatomic_set(&jc->array[i0 + i].tb, NULL);
}
--
2.31.1

250
SOURCES/kvm-block-Call-drain-callbacks-only-once.patch
Unescape View File

@ -0,0 +1,250 @@
From 9bb9cafd736057fd2a8ebfa6f5769668f125fbe6 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:06 +0100
Subject: [PATCH 24/31] block: Call drain callbacks only once
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [12/16] ea9a433dc01d1b8539a2d4ea12887f2a3ce830ea (sgarzarella/qemu-kvm-c-9-s)
We only need to call both the BlockDriver's callback and the parent
callbacks when going from undrained to drained or vice versa. A second
drain section doesn't make a difference for the driver or the parent,
they weren't supposed to send new requests before and after the second
drain.
One thing that gets in the way is the 'ignore_bds_parents' parameter in
bdrv_do_drained_begin_quiesce() and bdrv_do_drained_end(): It means that
bdrv_drain_all_begin() increases bs->quiesce_counter, but does not
quiesce the parent through BdrvChildClass callbacks. If an additional
drain section is started now, bs->quiesce_counter will be non-zero, but
we would still need to quiesce the parent through BdrvChildClass in
order to keep things consistent (and unquiesce it on the matching
bdrv_drained_end(), even though the counter would not reach 0 yet as
long as the bdrv_drain_all() section is still active).
Instead of keeping track of this, let's just get rid of the parameter.
It was introduced in commit 6cd5c9d7b2d as an optimisation so that
during bdrv_drain_all(), we wouldn't recursively drain all parents up to
the root for each node, resulting in quadratic complexity. As it happens,
calling the callbacks only once solves the same problem, so as of this
patch, we'll still have O(n) complexity and ignore_bds_parents is not
needed any more.
This patch only ignores the 'ignore_bds_parents' parameter. It will be
removed in a separate patch.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-12-kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 57e05be343f33f4e5899a8d8946a8596d68424a1)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 25 +++++++------------------
block/io.c | 30 ++++++++++++++++++------------
include/block/block_int-common.h | 8 ++++----
tests/unit/test-bdrv-drain.c | 16 ++++++++++------
4 files changed, 39 insertions(+), 40 deletions(-)
diff --git a/block.c b/block.c
index e0e3b21790..5a583e260d 100644
--- a/block.c
+++ b/block.c
@@ -2824,7 +2824,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
{
BlockDriverState *old_bs = child->bs;
int new_bs_quiesce_counter;
- int drain_saldo;
assert(!child->frozen);
assert(old_bs != new_bs);
@@ -2834,16 +2833,13 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
}
- new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
- drain_saldo = new_bs_quiesce_counter - child->parent_quiesce_counter;
-
/*
* If the new child node is drained but the old one was not, flush
* all outstanding requests to the old child node.
*/
- while (drain_saldo > 0 && child->klass->drained_begin) {
+ new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
+ if (new_bs_quiesce_counter && !child->quiesced_parent) {
bdrv_parent_drained_begin_single(child, true);
- drain_saldo--;
}
if (old_bs) {
@@ -2859,16 +2855,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
if (new_bs) {
assert_bdrv_graph_writable(new_bs);
QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
-
- /*
- * Polling in bdrv_parent_drained_begin_single() may have led to the new
- * node's quiesce_counter having been decreased. Not a problem, we just
- * need to recognize this here and then invoke drained_end appropriately
- * more often.
- */
- assert(new_bs->quiesce_counter <= new_bs_quiesce_counter);
- drain_saldo += new_bs->quiesce_counter - new_bs_quiesce_counter;
-
if (child->klass->attach) {
child->klass->attach(child);
}
@@ -2877,10 +2863,13 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
/*
* If the old child node was drained but the new one is not, allow
* requests to come in only after the new node has been attached.
+ *
+ * Update new_bs_quiesce_counter because bdrv_parent_drained_begin_single()
+ * polls, which could have changed the value.
*/
- while (drain_saldo < 0 && child->klass->drained_end) {
+ new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
+ if (!new_bs_quiesce_counter && child->quiesced_parent) {
bdrv_parent_drained_end_single(child);
- drain_saldo++;
}
}
diff --git a/block/io.c b/block/io.c
index 75224480d0..87d6f22ec4 100644
--- a/block/io.c
+++ b/block/io.c
@@ -62,8 +62,9 @@ void bdrv_parent_drained_end_single(BdrvChild *c)
{
IO_OR_GS_CODE();
- assert(c->parent_quiesce_counter > 0);
- c->parent_quiesce_counter--;
+ assert(c->quiesced_parent);
+ c->quiesced_parent = false;
+
if (c->klass->drained_end) {
c->klass->drained_end(c);
}
@@ -110,7 +111,10 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
{
AioContext *ctx = bdrv_child_get_parent_aio_context(c);
IO_OR_GS_CODE();
- c->parent_quiesce_counter++;
+
+ assert(!c->quiesced_parent);
+ c->quiesced_parent = true;
+
if (c->klass->drained_begin) {
c->klass->drained_begin(c);
}
@@ -358,11 +362,12 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
/* Stop things in parent-to-child order */
if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) {
aio_disable_external(bdrv_get_aio_context(bs));
- }
- bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
- if (bs->drv && bs->drv->bdrv_drain_begin) {
- bs->drv->bdrv_drain_begin(bs);
+ /* TODO Remove ignore_bds_parents, we don't consider it any more */
+ bdrv_parent_drained_begin(bs, parent, false);
+ if (bs->drv && bs->drv->bdrv_drain_begin) {
+ bs->drv->bdrv_drain_begin(bs);
+ }
}
}
@@ -413,13 +418,14 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
assert(bs->quiesce_counter > 0);
/* Re-enable things in child-to-parent order */
- if (bs->drv && bs->drv->bdrv_drain_end) {
- bs->drv->bdrv_drain_end(bs);
- }
- bdrv_parent_drained_end(bs, parent, ignore_bds_parents);
-
old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter);
if (old_quiesce_counter == 1) {
+ if (bs->drv && bs->drv->bdrv_drain_end) {
+ bs->drv->bdrv_drain_end(bs);
+ }
+ /* TODO Remove ignore_bds_parents, we don't consider it any more */
+ bdrv_parent_drained_end(bs, parent, false);
+
aio_enable_external(bdrv_get_aio_context(bs));
}
}
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 791dddfd7d..a6bc6b7fe9 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -980,13 +980,13 @@ struct BdrvChild {
bool frozen;
/*
- * How many times the parent of this child has been drained
+ * True if the parent of this child has been drained by this BdrvChild
* (through klass->drained_*).
- * Usually, this is equal to bs->quiesce_counter (potentially
- * reduced by bdrv_drain_all_count). It may differ while the
+ *
+ * It is generally true if bs->quiesce_counter > 0. It may differ while the
* child is entering or leaving a drained section.
*/
- int parent_quiesce_counter;
+ bool quiesced_parent;
QLIST_ENTRY(BdrvChild) next;
QLIST_ENTRY(BdrvChild) next_parent;
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index dda08de8db..172bc6debc 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -296,7 +296,11 @@ static void test_quiesce_common(enum drain_type drain_type, bool recursive)
do_drain_begin(drain_type, bs);
- g_assert_cmpint(bs->quiesce_counter, ==, 1);
+ if (drain_type == BDRV_DRAIN_ALL) {
+ g_assert_cmpint(bs->quiesce_counter, ==, 2);
+ } else {
+ g_assert_cmpint(bs->quiesce_counter, ==, 1);
+ }
g_assert_cmpint(backing->quiesce_counter, ==, !!recursive);
do_drain_end(drain_type, bs);
@@ -348,8 +352,8 @@ static void test_nested(void)
for (outer = 0; outer < DRAIN_TYPE_MAX; outer++) {
for (inner = 0; inner < DRAIN_TYPE_MAX; inner++) {
- int backing_quiesce = (outer != BDRV_DRAIN) +
- (inner != BDRV_DRAIN);
+ int backing_quiesce = (outer == BDRV_DRAIN_ALL) +
+ (inner == BDRV_DRAIN_ALL);
g_assert_cmpint(bs->quiesce_counter, ==, 0);
g_assert_cmpint(backing->quiesce_counter, ==, 0);
@@ -359,10 +363,10 @@ static void test_nested(void)
do_drain_begin(outer, bs);
do_drain_begin(inner, bs);
- g_assert_cmpint(bs->quiesce_counter, ==, 2);
+ g_assert_cmpint(bs->quiesce_counter, ==, 2 + !!backing_quiesce);
g_assert_cmpint(backing->quiesce_counter, ==, backing_quiesce);
- g_assert_cmpint(s->drain_count, ==, 2);
- g_assert_cmpint(backing_s->drain_count, ==, backing_quiesce);
+ g_assert_cmpint(s->drain_count, ==, 1);
+ g_assert_cmpint(backing_s->drain_count, ==, !!backing_quiesce);
do_drain_end(inner, bs);
do_drain_end(outer, bs);
--
2.31.1

298
SOURCES/kvm-block-Don-t-poll-in-bdrv_replace_child_noperm.patch
Unescape View File

@ -0,0 +1,298 @@
From 150ef3356cc6732fede7ca059168fc0565ed0b76 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:09 +0100
Subject: [PATCH 27/31] block: Don't poll in bdrv_replace_child_noperm()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [15/16] 5fc7d6b703a2d6c1118d875056f0afbd6ba5cca9 (sgarzarella/qemu-kvm-c-9-s)
In order to make sure that bdrv_replace_child_noperm() doesn't have to
poll any more, get rid of the bdrv_parent_drained_begin_single() call.
This is possible now because we can require that the parent is already
drained through the child in question when the function is called and we
don't call the parent drain callbacks more than once.
The additional drain calls needed in callers cause the test case to run
its code in the drain handler too early (bdrv_attach_child() drains
now), so modify it to only enable the code after the test setup has
completed.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-15-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 23987471285a26397e3152a9244b652445fd36c4)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 103 ++++++++++++++++++++++++++++++-----
block/io.c | 2 +-
include/block/block-io.h | 8 +++
tests/unit/test-bdrv-drain.c | 10 ++++
4 files changed, 108 insertions(+), 15 deletions(-)
diff --git a/block.c b/block.c
index af31a94863..65588d313a 100644
--- a/block.c
+++ b/block.c
@@ -2407,6 +2407,20 @@ static void bdrv_replace_child_abort(void *opaque)
GLOBAL_STATE_CODE();
/* old_bs reference is transparently moved from @s to @s->child */
+ if (!s->child->bs) {
+ /*
+ * The parents were undrained when removing old_bs from the child. New
+ * requests can't have been made, though, because the child was empty.
+ *
+ * TODO Make bdrv_replace_child_noperm() transactionable to avoid
+ * undraining the parent in the first place. Once this is done, having
+ * new_bs drained when calling bdrv_replace_child_tran() is not a
+ * requirement any more.
+ */
+ bdrv_parent_drained_begin_single(s->child, false);
+ assert(!bdrv_parent_drained_poll_single(s->child));
+ }
+ assert(s->child->quiesced_parent);
bdrv_replace_child_noperm(s->child, s->old_bs);
bdrv_unref(new_bs);
}
@@ -2422,12 +2436,19 @@ static TransactionActionDrv bdrv_replace_child_drv = {
*
* Note: real unref of old_bs is done only on commit.
*
+ * Both @child->bs and @new_bs (if non-NULL) must be drained. @new_bs must be
+ * kept drained until the transaction is completed.
+ *
* The function doesn't update permissions, caller is responsible for this.
*/
static void bdrv_replace_child_tran(BdrvChild *child, BlockDriverState *new_bs,
Transaction *tran)
{
BdrvReplaceChildState *s = g_new(BdrvReplaceChildState, 1);
+
+ assert(child->quiesced_parent);
+ assert(!new_bs || new_bs->quiesce_counter);
+
*s = (BdrvReplaceChildState) {
.child = child,
.old_bs = child->bs,
@@ -2819,6 +2840,14 @@ uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm)
return permissions[qapi_perm];
}
+/*
+ * Replaces the node that a BdrvChild points to without updating permissions.
+ *
+ * If @new_bs is non-NULL, the parent of @child must already be drained through
+ * @child.
+ *
+ * This function does not poll.
+ */
static void bdrv_replace_child_noperm(BdrvChild *child,
BlockDriverState *new_bs)
{
@@ -2826,6 +2855,28 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
int new_bs_quiesce_counter;
assert(!child->frozen);
+
+ /*
+ * If we want to change the BdrvChild to point to a drained node as its new
+ * child->bs, we need to make sure that its new parent is drained, too. In
+ * other words, either child->quiesce_parent must already be true or we must
+ * be able to set it and keep the parent's quiesce_counter consistent with
+ * that, but without polling or starting new requests (this function
+ * guarantees that it doesn't poll, and starting new requests would be
+ * against the invariants of drain sections).
+ *
+ * To keep things simple, we pick the first option (child->quiesce_parent
+ * must already be true). We also generalise the rule a bit to make it
+ * easier to verify in callers and more likely to be covered in test cases:
+ * The parent must be quiesced through this child even if new_bs isn't
+ * currently drained.
+ *
+ * The only exception is for callers that always pass new_bs == NULL. In
+ * this case, we obviously never need to consider the case of a drained
+ * new_bs, so we can keep the callers simpler by allowing them not to drain
+ * the parent.
+ */
+ assert(!new_bs || child->quiesced_parent);
assert(old_bs != new_bs);
GLOBAL_STATE_CODE();
@@ -2833,15 +2884,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
}
- /*
- * If the new child node is drained but the old one was not, flush
- * all outstanding requests to the old child node.
- */
- new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
- if (new_bs_quiesce_counter && !child->quiesced_parent) {
- bdrv_parent_drained_begin_single(child, true);
- }
-
if (old_bs) {
if (child->klass->detach) {
child->klass->detach(child);
@@ -2861,11 +2903,9 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
}
/*
- * If the old child node was drained but the new one is not, allow
- * requests to come in only after the new node has been attached.
- *
- * Update new_bs_quiesce_counter because bdrv_parent_drained_begin_single()
- * polls, which could have changed the value.
+ * If the parent was drained through this BdrvChild previously, but new_bs
+ * is not drained, allow requests to come in only after the new node has
+ * been attached.
*/
new_bs_quiesce_counter = (new_bs ? new_bs->quiesce_counter : 0);
if (!new_bs_quiesce_counter && child->quiesced_parent) {
@@ -3002,6 +3042,24 @@ static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs,
}
bdrv_ref(child_bs);
+ /*
+ * Let every new BdrvChild start with a drained parent. Inserting the child
+ * in the graph with bdrv_replace_child_noperm() will undrain it if
+ * @child_bs is not drained.
+ *
+ * The child was only just created and is not yet visible in global state
+ * until bdrv_replace_child_noperm() inserts it into the graph, so nobody
+ * could have sent requests and polling is not necessary.
+ *
+ * Note that this means that the parent isn't fully drained yet, we only
+ * stop new requests from coming in. This is fine, we don't care about the
+ * old requests here, they are not for this child. If another place enters a
+ * drain section for the same parent, but wants it to be fully quiesced, it
+ * will not run most of the the code in .drained_begin() again (which is not
+ * a problem, we already did this), but it will still poll until the parent
+ * is fully quiesced, so it will not be negatively affected either.
+ */
+ bdrv_parent_drained_begin_single(new_child, false);
bdrv_replace_child_noperm(new_child, child_bs);
BdrvAttachChildCommonState *s = g_new(BdrvAttachChildCommonState, 1);
@@ -5059,12 +5117,24 @@ static void bdrv_remove_child(BdrvChild *child, Transaction *tran)
}
if (child->bs) {
+ BlockDriverState *bs = child->bs;
+ bdrv_drained_begin(bs);
bdrv_replace_child_tran(child, NULL, tran);
+ bdrv_drained_end(bs);
}
tran_add(tran, &bdrv_remove_child_drv, child);
}
+static void undrain_on_clean_cb(void *opaque)
+{
+ bdrv_drained_end(opaque);
+}
+
+static TransactionActionDrv undrain_on_clean = {
+ .clean = undrain_on_clean_cb,
+};
+
static int bdrv_replace_node_noperm(BlockDriverState *from,
BlockDriverState *to,
bool auto_skip, Transaction *tran,
@@ -5074,6 +5144,11 @@ static int bdrv_replace_node_noperm(BlockDriverState *from,
GLOBAL_STATE_CODE();
+ bdrv_drained_begin(from);
+ bdrv_drained_begin(to);
+ tran_add(tran, &undrain_on_clean, from);
+ tran_add(tran, &undrain_on_clean, to);
+
QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
assert(c->bs == from);
if (!should_update_child(c, to)) {
diff --git a/block/io.c b/block/io.c
index 5e9150d92c..ae64830eac 100644
--- a/block/io.c
+++ b/block/io.c
@@ -81,7 +81,7 @@ static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore)
}
}
-static bool bdrv_parent_drained_poll_single(BdrvChild *c)
+bool bdrv_parent_drained_poll_single(BdrvChild *c)
{
if (c->klass->drained_poll) {
return c->klass->drained_poll(c);
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 8f5e75756a..65e6d2569b 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -292,6 +292,14 @@ bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
*/
void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
+/**
+ * bdrv_parent_drained_poll_single:
+ *
+ * Returns true if there is any pending activity to cease before @c can be
+ * called quiesced, false otherwise.
+ */
+bool bdrv_parent_drained_poll_single(BdrvChild *c);
+
/**
* bdrv_parent_drained_end_single:
*
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 172bc6debc..2686a8acee 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -1654,6 +1654,7 @@ static void test_drop_intermediate_poll(void)
typedef struct BDRVReplaceTestState {
+ bool setup_completed;
bool was_drained;
bool was_undrained;
bool has_read;
@@ -1738,6 +1739,10 @@ static void bdrv_replace_test_drain_begin(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
+ if (!s->setup_completed) {
+ return;
+ }
+
if (!s->drain_count) {
s->drain_co = qemu_coroutine_create(bdrv_replace_test_drain_co, bs);
bdrv_inc_in_flight(bs);
@@ -1769,6 +1774,10 @@ static void bdrv_replace_test_drain_end(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
+ if (!s->setup_completed) {
+ return;
+ }
+
g_assert(s->drain_count > 0);
if (!--s->drain_count) {
s->was_undrained = true;
@@ -1867,6 +1876,7 @@ static void do_test_replace_child_mid_drain(int old_drain_count,
bdrv_ref(old_child_bs);
bdrv_attach_child(parent_bs, old_child_bs, "child", &child_of_bds,
BDRV_CHILD_COW, &error_abort);
+ parent_s->setup_completed = true;
for (i = 0; i < old_drain_count; i++) {
bdrv_drained_begin(old_child_bs);
--
2.31.1

54
SOURCES/kvm-block-Don-t-use-subtree-drains-in-bdrv_drop_intermed.patch
Unescape View File

@ -0,0 +1,54 @@
From 6af6de77dace29aa8548b3649dc9c6163740ac86 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:03 +0100
Subject: [PATCH 21/31] block: Don't use subtree drains in
bdrv_drop_intermediate()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [9/16] 3c06fa826f262558f57d38b0155500c2e8e23a53 (sgarzarella/qemu-kvm-c-9-s)
Instead of using a subtree drain from the top node (which also drains
child nodes of base that we're not even interested in), use a normal
drain for base, which automatically drains all of the parents, too.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-9-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 631086deefc32690ee56efed1c5b891dec31ae37)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/block.c b/block.c
index cb5e96b1cf..b3449a312e 100644
--- a/block.c
+++ b/block.c
@@ -5586,7 +5586,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
GLOBAL_STATE_CODE();
bdrv_ref(top);
- bdrv_subtree_drained_begin(top);
+ bdrv_drained_begin(base);
if (!top->drv || !base->drv) {
goto exit;
@@ -5659,7 +5659,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
ret = 0;
exit:
- bdrv_subtree_drained_end(top);
+ bdrv_drained_end(base);
bdrv_unref(top);
return ret;
}
--
2.31.1

157
SOURCES/kvm-block-Drain-individual-nodes-during-reopen.patch
Unescape View File

@ -0,0 +1,157 @@
From ad52cb621daad45d3c2a0e2e670d6ca2e16690bd Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:02 +0100
Subject: [PATCH 20/31] block: Drain individual nodes during reopen
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [8/16] 5441b6f0ae9102ef40d1093e1db3084eea81e3b0 (sgarzarella/qemu-kvm-c-9-s)
bdrv_reopen() and friends use subtree drains as a lazy way of covering
all the nodes they touch. Turns out that this lazy way is a lot more
complicated than just draining the nodes individually, even not
accounting for the additional complexity in the drain mechanism itself.
Simplify the code by switching to draining the individual nodes that are
already managed in the BlockReopenQueue anyway.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-8-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit d22933acd2f470eeef779e4d444e848f76dcfaf8)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 16 +++++++++-------
block/replication.c | 6 ------
blockdev.c | 13 -------------
3 files changed, 9 insertions(+), 26 deletions(-)
diff --git a/block.c b/block.c
index 46df410b07..cb5e96b1cf 100644
--- a/block.c
+++ b/block.c
@@ -4150,7 +4150,7 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs,
* returns a pointer to bs_queue, which is either the newly allocated
* bs_queue, or the existing bs_queue being used.
*
- * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple().
+ * bs is drained here and undrained by bdrv_reopen_queue_free().
*
* To be called with bs->aio_context locked.
*/
@@ -4172,12 +4172,10 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
int flags;
QemuOpts *opts;
- /* Make sure that the caller remembered to use a drained section. This is
- * important to avoid graph changes between the recursive queuing here and
- * bdrv_reopen_multiple(). */
- assert(bs->quiesce_counter > 0);
GLOBAL_STATE_CODE();
+ bdrv_drained_begin(bs);
+
if (bs_queue == NULL) {
bs_queue = g_new0(BlockReopenQueue, 1);
QTAILQ_INIT(bs_queue);
@@ -4328,6 +4326,12 @@ void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue)
if (bs_queue) {
BlockReopenQueueEntry *bs_entry, *next;
QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
+ AioContext *ctx = bdrv_get_aio_context(bs_entry->state.bs);
+
+ aio_context_acquire(ctx);
+ bdrv_drained_end(bs_entry->state.bs);
+ aio_context_release(ctx);
+
qobject_unref(bs_entry->state.explicit_options);
qobject_unref(bs_entry->state.options);
g_free(bs_entry);
@@ -4475,7 +4479,6 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
GLOBAL_STATE_CODE();
- bdrv_subtree_drained_begin(bs);
queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
if (ctx != qemu_get_aio_context()) {
@@ -4486,7 +4489,6 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
if (ctx != qemu_get_aio_context()) {
aio_context_acquire(ctx);
}
- bdrv_subtree_drained_end(bs);
return ret;
}
diff --git a/block/replication.c b/block/replication.c
index f1eed25e43..c62f48a874 100644
--- a/block/replication.c
+++ b/block/replication.c
@@ -374,9 +374,6 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable,
s->orig_secondary_read_only = bdrv_is_read_only(secondary_disk->bs);
}
- bdrv_subtree_drained_begin(hidden_disk->bs);
- bdrv_subtree_drained_begin(secondary_disk->bs);
-
if (s->orig_hidden_read_only) {
QDict *opts = qdict_new();
qdict_put_bool(opts, BDRV_OPT_READ_ONLY, !writable);
@@ -401,9 +398,6 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable,
aio_context_acquire(ctx);
}
}
-
- bdrv_subtree_drained_end(hidden_disk->bs);
- bdrv_subtree_drained_end(secondary_disk->bs);
}
static void backup_job_cleanup(BlockDriverState *bs)
diff --git a/blockdev.c b/blockdev.c
index 3f1dec6242..8ffb3d9537 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -3547,8 +3547,6 @@ fail:
void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp)
{
BlockReopenQueue *queue = NULL;
- GSList *drained = NULL;
- GSList *p;
/* Add each one of the BDS that we want to reopen to the queue */
for (; reopen_list != NULL; reopen_list = reopen_list->next) {
@@ -3585,9 +3583,7 @@ void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp)
ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
- bdrv_subtree_drained_begin(bs);
queue = bdrv_reopen_queue(queue, bs, qdict, false);
- drained = g_slist_prepend(drained, bs);
aio_context_release(ctx);
}
@@ -3598,15 +3594,6 @@ void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp)
fail:
bdrv_reopen_queue_free(queue);
- for (p = drained; p; p = p->next) {
- BlockDriverState *bs = p->data;
- AioContext *ctx = bdrv_get_aio_context(bs);
-
- aio_context_acquire(ctx);
- bdrv_subtree_drained_end(bs);
- aio_context_release(ctx);
- }
- g_slist_free(drained);
}
void qmp_blockdev_del(const char *node_name, Error **errp)
--
2.31.1

96
SOURCES/kvm-block-Drop-out-of-coroutine-in-bdrv_do_drained_begin.patch
Unescape View File

@ -0,0 +1,96 @@
From 9a789d104a4a69031ad95d7fad6380ab21e82503 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:08 +0100
Subject: [PATCH 26/31] block: Drop out of coroutine in
bdrv_do_drained_begin_quiesce()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [14/16] c9266663b822f703e55b6a07de98ceb56e69e924 (sgarzarella/qemu-kvm-c-9-s)
The next patch adds a parent drain to bdrv_attach_child_common(), which
shouldn't be, but is currently called from coroutines in some cases (e.g.
.bdrv_co_create implementations generally open new nodes). Therefore,
the assertion that we're not in a coroutine doesn't hold true any more.
We could just remove the assertion because there is nothing in the
function that should be in conflict with running in a coroutine, but
just to be on the safe side, we can reverse the caller relationship
between bdrv_do_drained_begin() and bdrv_do_drained_begin_quiesce() so
that the latter also just drops out of coroutine context and we can
still be certain in the future that any drain code doesn't run in
coroutines.
As a nice side effect, the structure of bdrv_do_drained_begin() is now
symmetrical with bdrv_do_drained_end().
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-14-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 05c272ff0cf1b16cc3606f746182dd99b774f553)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block/io.c | 25 ++++++++++++-------------
1 file changed, 12 insertions(+), 13 deletions(-)
diff --git a/block/io.c b/block/io.c
index 2e9503df6a..5e9150d92c 100644
--- a/block/io.c
+++ b/block/io.c
@@ -346,10 +346,15 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
}
}
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
+static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
+ bool poll)
{
IO_OR_GS_CODE();
- assert(!qemu_in_coroutine());
+
+ if (qemu_in_coroutine()) {
+ bdrv_co_yield_to_drain(bs, true, parent, poll);
+ return;
+ }
/* Stop things in parent-to-child order */
if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) {
@@ -359,17 +364,6 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
bs->drv->bdrv_drain_begin(bs);
}
}
-}
-
-static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
- bool poll)
-{
- if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, true, parent, poll);
- return;
- }
-
- bdrv_do_drained_begin_quiesce(bs, parent);
/*
* Wait for drained requests to finish.
@@ -385,6 +379,11 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
}
}
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
+{
+ bdrv_do_drained_begin(bs, parent, false);
+}
+
void bdrv_drained_begin(BlockDriverState *bs)
{
IO_OR_GS_CODE();
--
2.31.1

67
SOURCES/kvm-block-Fix-locking-for-bdrv_reopen_queue_child.patch
Unescape View File

@ -0,0 +1,67 @@
From e790b4c20a5124239fe93e91fbc87745e5f2cea6 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:01 +0100
Subject: [PATCH 19/31] block: Fix locking for bdrv_reopen_queue_child()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [7/16] 46bb54506c4400b9a1bf66b6bd7987ff67260003 (sgarzarella/qemu-kvm-c-9-s)
Callers don't agree whether bdrv_reopen_queue_child() should be called
with the AioContext lock held or not. Standardise on holding the lock
(as done by QMP blockdev-reopen and the replication block driver) and
fix bdrv_reopen() to do the same.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-7-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 2e117866d7c96cc17e84cd2946fee1bf3292d814)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/block.c b/block.c
index 7999fd08c5..46df410b07 100644
--- a/block.c
+++ b/block.c
@@ -4151,6 +4151,8 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs,
* bs_queue, or the existing bs_queue being used.
*
* bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple().
+ *
+ * To be called with bs->aio_context locked.
*/
static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
BlockDriverState *bs,
@@ -4309,6 +4311,7 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
return bs_queue;
}
+/* To be called with bs->aio_context locked */
BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
BlockDriverState *bs,
QDict *options, bool keep_old_opts)
@@ -4473,11 +4476,11 @@ int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts,
GLOBAL_STATE_CODE();
bdrv_subtree_drained_begin(bs);
+ queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
+
if (ctx != qemu_get_aio_context()) {
aio_context_release(ctx);
}
-
- queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts);
ret = bdrv_reopen_multiple(queue, errp);
if (ctx != qemu_get_aio_context()) {
--
2.31.1

132
SOURCES/kvm-block-Improve-empty-format-specific-info-dump.patch
Unescape View File

@ -0,0 +1,132 @@
From 074c89b05dae971c7118cb769fd34e22135c8f4c Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:53 +0200
Subject: [PATCH 06/20] block: Improve empty format-specific info dump
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [1/12] be551e83f426e620e673302198b51368bfd324ce (hreitz/qemu-kvm-c-9-s)
When a block driver supports obtaining format-specific information, but
that object only contains optional fields, it is possible that none of
them are present, so that dump_qobject() (called by
bdrv_image_info_specific_dump()) will not print anything.
The callers of bdrv_image_info_specific_dump() put a header above this
information ("Format specific information:\n"), which will look strange
when there is nothing below. Modify bdrv_image_info_specific_dump() to
print this header instead of its callers, and only if there is indeed
something to be printed.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-2-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 3716470b24f0f63090d59bcf28ad8fe6fb7835bd)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 41 +++++++++++++++++++++++++++++++++++++----
include/block/qapi.h | 3 ++-
qemu-io-cmds.c | 4 ++--
3 files changed, 41 insertions(+), 7 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index cf557e3aea..51202b470a 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -777,7 +777,35 @@ static void dump_qdict(int indentation, QDict *dict)
}
}
-void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec)
+/*
+ * Return whether dumping the given QObject with dump_qobject() would
+ * yield an empty dump, i.e. not print anything.
+ */
+static bool qobject_is_empty_dump(const QObject *obj)
+{
+ switch (qobject_type(obj)) {
+ case QTYPE_QNUM:
+ case QTYPE_QSTRING:
+ case QTYPE_QBOOL:
+ return false;
+
+ case QTYPE_QDICT:
+ return qdict_size(qobject_to(QDict, obj)) == 0;
+
+ case QTYPE_QLIST:
+ return qlist_empty(qobject_to(QList, obj));
+
+ default:
+ abort();
+ }
+}
+
+/**
+ * Dumps the given ImageInfoSpecific object in a human-readable form,
+ * prepending an optional prefix if the dump is not empty.
+ */
+void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
+ const char *prefix)
{
QObject *obj, *data;
Visitor *v = qobject_output_visitor_new(&obj);
@@ -785,7 +813,12 @@ void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec)
visit_type_ImageInfoSpecific(v, NULL, &info_spec, &error_abort);
visit_complete(v, &obj);
data = qdict_get(qobject_to(QDict, obj), "data");
- dump_qobject(1, data);
+ if (!qobject_is_empty_dump(data)) {
+ if (prefix) {
+ qemu_printf("%s", prefix);
+ }
+ dump_qobject(1, data);
+ }
qobject_unref(obj);
visit_free(v);
}
@@ -866,7 +899,7 @@ void bdrv_image_info_dump(ImageInfo *info)
}
if (info->has_format_specific) {
- qemu_printf("Format specific information:\n");
- bdrv_image_info_specific_dump(info->format_specific);
+ bdrv_image_info_specific_dump(info->format_specific,
+ "Format specific information:\n");
}
}
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 22c7807c89..c09859ea78 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -40,6 +40,7 @@ void bdrv_query_image_info(BlockDriverState *bs,
Error **errp);
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
-void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec);
+void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
+ const char *prefix);
void bdrv_image_info_dump(ImageInfo *info);
#endif
diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index 952dc940f1..f4a374528e 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -1825,8 +1825,8 @@ static int info_f(BlockBackend *blk, int argc, char **argv)
return -EIO;
}
if (spec_info) {
- printf("Format specific information:\n");
- bdrv_image_info_specific_dump(spec_info);
+ bdrv_image_info_specific_dump(spec_info,
+ "Format specific information:\n");
qapi_free_ImageInfoSpecific(spec_info);
}
--
2.31.1

81
SOURCES/kvm-block-Inline-bdrv_drain_invoke.patch
Unescape View File

@ -0,0 +1,81 @@
From 1808e560396872173f787f8e338e9837a4c3d626 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:00 +0100
Subject: [PATCH 18/31] block: Inline bdrv_drain_invoke()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [6/16] 2c7473a36360eb43d94b967deb12308cb5ea0d3b (sgarzarella/qemu-kvm-c-9-s)
bdrv_drain_invoke() has now two entirely separate cases that share no
code any more and are selected depending on a bool parameter. Each case
has only one caller. Just inline the function.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-6-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c7bc05f78ab31fb02fc9635f60b9bd22efc8d121)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block/io.c | 23 ++++++-----------------
1 file changed, 6 insertions(+), 17 deletions(-)
diff --git a/block/io.c b/block/io.c
index f4ca62b034..a25103be6f 100644
--- a/block/io.c
+++ b/block/io.c
@@ -242,21 +242,6 @@ typedef struct {
bool ignore_bds_parents;
} BdrvCoDrainData;
-/* Recursively call BlockDriver.bdrv_drain_begin/end callbacks */
-static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
-{
- if (!bs->drv || (begin && !bs->drv->bdrv_drain_begin) ||
- (!begin && !bs->drv->bdrv_drain_end)) {
- return;
- }
-
- if (begin) {
- bs->drv->bdrv_drain_begin(bs);
- } else {
- bs->drv->bdrv_drain_end(bs);
- }
-}
-
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
BdrvChild *ignore_parent, bool ignore_bds_parents)
@@ -390,7 +375,9 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
- bdrv_drain_invoke(bs, true);
+ if (bs->drv && bs->drv->bdrv_drain_begin) {
+ bs->drv->bdrv_drain_begin(bs);
+ }
}
static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
@@ -461,7 +448,9 @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
assert(bs->quiesce_counter > 0);
/* Re-enable things in child-to-parent order */
- bdrv_drain_invoke(bs, false);
+ if (bs->drv && bs->drv->bdrv_drain_end) {
+ bs->drv->bdrv_drain_end(bs);
+ }
bdrv_parent_drained_end(bs, parent, ignore_bds_parents);
old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter);
--
2.31.1

433
SOURCES/kvm-block-Remove-drained_end_counter.patch
Unescape View File

@ -0,0 +1,433 @@
From 3009e49f242ab371ffad35bb29c2c26ddfac75d4 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:40:59 +0100
Subject: [PATCH 17/31] block: Remove drained_end_counter
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [5/16] 5589e3f05dece5394a05641f7f42096e8dc62bdb (sgarzarella/qemu-kvm-c-9-s)
drained_end_counter is unused now, nobody changes its value any more. It
can be removed.
In cases where we had two almost identical functions that only differed
in whether the caller passes drained_end_counter, or whether they would
poll for a local drained_end_counter to reach 0, these become a single
function.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20221118174110.55183-5-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 2f65df6e16dea2d6e7212fa675f4779d9281e26f)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 5 +-
block/block-backend.c | 4 +-
block/io.c | 98 ++++++++------------------------
blockjob.c | 2 +-
include/block/block-io.h | 24 --------
include/block/block_int-common.h | 6 +-
6 files changed, 30 insertions(+), 109 deletions(-)
diff --git a/block.c b/block.c
index 16a62a329c..7999fd08c5 100644
--- a/block.c
+++ b/block.c
@@ -1235,11 +1235,10 @@ static bool bdrv_child_cb_drained_poll(BdrvChild *child)
return bdrv_drain_poll(bs, false, NULL, false);
}
-static void bdrv_child_cb_drained_end(BdrvChild *child,
- int *drained_end_counter)
+static void bdrv_child_cb_drained_end(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
- bdrv_drained_end_no_poll(bs, drained_end_counter);
+ bdrv_drained_end(bs);
}
static int bdrv_child_cb_inactivate(BdrvChild *child)
diff --git a/block/block-backend.c b/block/block-backend.c
index d98a96ff37..feaf2181fa 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -129,7 +129,7 @@ static void blk_root_inherit_options(BdrvChildRole role, bool parent_is_format,
}
static void blk_root_drained_begin(BdrvChild *child);
static bool blk_root_drained_poll(BdrvChild *child);
-static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter);
+static void blk_root_drained_end(BdrvChild *child);
static void blk_root_change_media(BdrvChild *child, bool load);
static void blk_root_resize(BdrvChild *child);
@@ -2556,7 +2556,7 @@ static bool blk_root_drained_poll(BdrvChild *child)
return busy || !!blk->in_flight;
}
-static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter)
+static void blk_root_drained_end(BdrvChild *child)
{
BlockBackend *blk = child->opaque;
assert(blk->quiesce_counter);
diff --git a/block/io.c b/block/io.c
index c2ed4b2af9..f4ca62b034 100644
--- a/block/io.c
+++ b/block/io.c
@@ -58,28 +58,19 @@ static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore,
}
}
-static void bdrv_parent_drained_end_single_no_poll(BdrvChild *c,
- int *drained_end_counter)
+void bdrv_parent_drained_end_single(BdrvChild *c)
{
+ IO_OR_GS_CODE();
+
assert(c->parent_quiesce_counter > 0);
c->parent_quiesce_counter--;
if (c->klass->drained_end) {
- c->klass->drained_end(c, drained_end_counter);
+ c->klass->drained_end(c);
}
}
-void bdrv_parent_drained_end_single(BdrvChild *c)
-{
- int drained_end_counter = 0;
- AioContext *ctx = bdrv_child_get_parent_aio_context(c);
- IO_OR_GS_CODE();
- bdrv_parent_drained_end_single_no_poll(c, &drained_end_counter);
- AIO_WAIT_WHILE(ctx, qatomic_read(&drained_end_counter) > 0);
-}
-
static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
- bool ignore_bds_parents,
- int *drained_end_counter)
+ bool ignore_bds_parents)
{
BdrvChild *c;
@@ -87,7 +78,7 @@ static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) {
continue;
}
- bdrv_parent_drained_end_single_no_poll(c, drained_end_counter);
+ bdrv_parent_drained_end_single(c);
}
}
@@ -249,12 +240,10 @@ typedef struct {
bool poll;
BdrvChild *parent;
bool ignore_bds_parents;
- int *drained_end_counter;
} BdrvCoDrainData;
/* Recursively call BlockDriver.bdrv_drain_begin/end callbacks */
-static void bdrv_drain_invoke(BlockDriverState *bs, bool begin,
- int *drained_end_counter)
+static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
{
if (!bs->drv || (begin && !bs->drv->bdrv_drain_begin) ||
(!begin && !bs->drv->bdrv_drain_end)) {
@@ -305,8 +294,7 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
BdrvChild *parent, bool ignore_bds_parents,
bool poll);
static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- int *drained_end_counter);
+ BdrvChild *parent, bool ignore_bds_parents);
static void bdrv_co_drain_bh_cb(void *opaque)
{
@@ -319,14 +307,12 @@ static void bdrv_co_drain_bh_cb(void *opaque)
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
- assert(!data->drained_end_counter);
bdrv_do_drained_begin(bs, data->recursive, data->parent,
data->ignore_bds_parents, data->poll);
} else {
assert(!data->poll);
bdrv_do_drained_end(bs, data->recursive, data->parent,
- data->ignore_bds_parents,
- data->drained_end_counter);
+ data->ignore_bds_parents);
}
aio_context_release(ctx);
} else {
@@ -342,8 +328,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
bool begin, bool recursive,
BdrvChild *parent,
bool ignore_bds_parents,
- bool poll,
- int *drained_end_counter)
+ bool poll)
{
BdrvCoDrainData data;
Coroutine *self = qemu_coroutine_self();
@@ -363,7 +348,6 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
.parent = parent,
.ignore_bds_parents = ignore_bds_parents,
.poll = poll,
- .drained_end_counter = drained_end_counter,
};
if (bs) {
@@ -406,7 +390,7 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
bdrv_parent_drained_begin(bs, parent, ignore_bds_parents);
- bdrv_drain_invoke(bs, true, NULL);
+ bdrv_drain_invoke(bs, true);
}
static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
@@ -417,7 +401,7 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
if (qemu_in_coroutine()) {
bdrv_co_yield_to_drain(bs, true, recursive, parent, ignore_bds_parents,
- poll, NULL);
+ poll);
return;
}
@@ -461,38 +445,24 @@ void bdrv_subtree_drained_begin(BlockDriverState *bs)
/**
* This function does not poll, nor must any of its recursively called
- * functions. The *drained_end_counter pointee will be incremented
- * once for every background operation scheduled, and decremented once
- * the operation settles. Therefore, the pointer must remain valid
- * until the pointee reaches 0. That implies that whoever sets up the
- * pointee has to poll until it is 0.
- *
- * We use atomic operations to access *drained_end_counter, because
- * (1) when called from bdrv_set_aio_context_ignore(), the subgraph of
- * @bs may contain nodes in different AioContexts,
- * (2) bdrv_drain_all_end() uses the same counter for all nodes,
- * regardless of which AioContext they are in.
+ * functions.
*/
static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- int *drained_end_counter)
+ BdrvChild *parent, bool ignore_bds_parents)
{
BdrvChild *child;
int old_quiesce_counter;
- assert(drained_end_counter != NULL);
-
if (qemu_in_coroutine()) {
bdrv_co_yield_to_drain(bs, false, recursive, parent, ignore_bds_parents,
- false, drained_end_counter);
+ false);
return;
}
assert(bs->quiesce_counter > 0);
/* Re-enable things in child-to-parent order */
- bdrv_drain_invoke(bs, false, drained_end_counter);
- bdrv_parent_drained_end(bs, parent, ignore_bds_parents,
- drained_end_counter);
+ bdrv_drain_invoke(bs, false);
+ bdrv_parent_drained_end(bs, parent, ignore_bds_parents);
old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter);
if (old_quiesce_counter == 1) {
@@ -503,32 +473,21 @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
assert(!ignore_bds_parents);
bs->recursive_quiesce_counter--;
QLIST_FOREACH(child, &bs->children, next) {
- bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents,
- drained_end_counter);
+ bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents);
}
}
}
void bdrv_drained_end(BlockDriverState *bs)
{
- int drained_end_counter = 0;
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, false, NULL, false, &drained_end_counter);
- BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
-}
-
-void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter)
-{
- IO_CODE();
- bdrv_do_drained_end(bs, false, NULL, false, drained_end_counter);
+ bdrv_do_drained_end(bs, false, NULL, false);
}
void bdrv_subtree_drained_end(BlockDriverState *bs)
{
- int drained_end_counter = 0;
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, true, NULL, false, &drained_end_counter);
- BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
+ bdrv_do_drained_end(bs, true, NULL, false);
}
void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
@@ -543,16 +502,12 @@ void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
{
- int drained_end_counter = 0;
int i;
IO_OR_GS_CODE();
for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
- bdrv_do_drained_end(child->bs, true, child, false,
- &drained_end_counter);
+ bdrv_do_drained_end(child->bs, true, child, false);
}
-
- BDRV_POLL_WHILE(child->bs, qatomic_read(&drained_end_counter) > 0);
}
void bdrv_drain(BlockDriverState *bs)
@@ -610,7 +565,7 @@ void bdrv_drain_all_begin(void)
GLOBAL_STATE_CODE();
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true, NULL);
+ bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true);
return;
}
@@ -649,22 +604,19 @@ void bdrv_drain_all_begin(void)
void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
{
- int drained_end_counter = 0;
GLOBAL_STATE_CODE();
g_assert(bs->quiesce_counter > 0);
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
- bdrv_do_drained_end(bs, false, NULL, true, &drained_end_counter);
+ bdrv_do_drained_end(bs, false, NULL, true);
}
- BDRV_POLL_WHILE(bs, qatomic_read(&drained_end_counter) > 0);
}
void bdrv_drain_all_end(void)
{
BlockDriverState *bs = NULL;
- int drained_end_counter = 0;
GLOBAL_STATE_CODE();
/*
@@ -680,13 +632,11 @@ void bdrv_drain_all_end(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_end(bs, false, NULL, true, &drained_end_counter);
+ bdrv_do_drained_end(bs, false, NULL, true);
aio_context_release(aio_context);
}
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
- AIO_WAIT_WHILE(NULL, qatomic_read(&drained_end_counter) > 0);
-
assert(bdrv_drain_all_count > 0);
bdrv_drain_all_count--;
}
diff --git a/blockjob.c b/blockjob.c
index f51d4e18f3..0ab721e139 100644
--- a/blockjob.c
+++ b/blockjob.c
@@ -120,7 +120,7 @@ static bool child_job_drained_poll(BdrvChild *c)
}
}
-static void child_job_drained_end(BdrvChild *c, int *drained_end_counter)
+static void child_job_drained_end(BdrvChild *c)
{
BlockJob *job = c->opaque;
job_resume(&job->job);
diff --git a/include/block/block-io.h b/include/block/block-io.h
index b099d7db45..054e964c9b 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -237,21 +237,6 @@ int coroutine_fn bdrv_co_copy_range(BdrvChild *src, int64_t src_offset,
int64_t bytes, BdrvRequestFlags read_flags,
BdrvRequestFlags write_flags);
-/**
- * bdrv_drained_end_no_poll:
- *
- * Same as bdrv_drained_end(), but do not poll for the subgraph to
- * actually become unquiesced. Therefore, no graph changes will occur
- * with this function.
- *
- * *drained_end_counter is incremented for every background operation
- * that is scheduled, and will be decremented for every operation once
- * it settles. The caller must poll until it reaches 0. The counter
- * should be accessed using atomic operations only.
- */
-void bdrv_drained_end_no_poll(BlockDriverState *bs, int *drained_end_counter);
-
-
/*
* "I/O or GS" API functions. These functions can run without
* the BQL, but only in one specific iothread/main loop.
@@ -311,9 +296,6 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
* bdrv_parent_drained_end_single:
*
* End a quiesced section for the parent of @c.
- *
- * This polls @bs's AioContext until all scheduled sub-drained_ends
- * have settled, which may result in graph changes.
*/
void bdrv_parent_drained_end_single(BdrvChild *c);
@@ -361,12 +343,6 @@ void bdrv_subtree_drained_begin(BlockDriverState *bs);
* bdrv_drained_end:
*
* End a quiescent section started by bdrv_drained_begin().
- *
- * This polls @bs's AioContext until all scheduled sub-drained_ends
- * have settled. On one hand, that may result in graph changes. On
- * the other, this requires that the caller either runs in the main
- * loop; or that all involved nodes (@bs and all of its parents) are
- * in the caller's AioContext.
*/
void bdrv_drained_end(BlockDriverState *bs);
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 40d646d1ed..2b97576f6d 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -939,15 +939,11 @@ struct BdrvChildClass {
* These functions must not change the graph (and therefore also must not
* call aio_poll(), which could change the graph indirectly).
*
- * If drained_end() schedules background operations, it must atomically
- * increment *drained_end_counter for each such operation and atomically
- * decrement it once the operation has settled.
- *
* Note that this can be nested. If drained_begin() was called twice, new
* I/O is allowed only after drained_end() was called twice, too.
*/
void (*drained_begin)(BdrvChild *child);
- void (*drained_end)(BdrvChild *child, int *drained_end_counter);
+ void (*drained_end)(BdrvChild *child);
/*
* Returns whether the parent has pending requests for the child. This
--
2.31.1

274
SOURCES/kvm-block-Remove-ignore_bds_parents-parameter-from-drain.patch
Unescape View File

@ -0,0 +1,274 @@
From 0dc7990533cef41e58579ee96315aca1fdc44ea1 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:07 +0100
Subject: [PATCH 25/31] block: Remove ignore_bds_parents parameter from
drain_begin/end.
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [13/16] 1ed88d975a9569bffeb33ad847874417780ce408 (sgarzarella/qemu-kvm-c-9-s)
ignore_bds_parents is now ignored during drain_begin and drain_end, so
we can just remove it there. It is still a valid optimisation for
drain_all in bdrv_drained_poll(), so leave it around there.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-13-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a82a3bd135078d14f1bb4b5e50f51e77d3748270)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 2 +-
block/io.c | 58 +++++++++++++++-------------------------
include/block/block-io.h | 3 +--
3 files changed, 24 insertions(+), 39 deletions(-)
diff --git a/block.c b/block.c
index 5a583e260d..af31a94863 100644
--- a/block.c
+++ b/block.c
@@ -1226,7 +1226,7 @@ static char *bdrv_child_get_parent_desc(BdrvChild *c)
static void bdrv_child_cb_drained_begin(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
- bdrv_do_drained_begin_quiesce(bs, NULL, false);
+ bdrv_do_drained_begin_quiesce(bs, NULL);
}
static bool bdrv_child_cb_drained_poll(BdrvChild *child)
diff --git a/block/io.c b/block/io.c
index 87d6f22ec4..2e9503df6a 100644
--- a/block/io.c
+++ b/block/io.c
@@ -45,13 +45,12 @@ static void bdrv_parent_cb_resize(BlockDriverState *bs);
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int64_t bytes, BdrvRequestFlags flags);
-static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore,
- bool ignore_bds_parents)
+static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore)
{
BdrvChild *c, *next;
QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
- if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) {
+ if (c == ignore) {
continue;
}
bdrv_parent_drained_begin_single(c, false);
@@ -70,13 +69,12 @@ void bdrv_parent_drained_end_single(BdrvChild *c)
}
}
-static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore,
- bool ignore_bds_parents)
+static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore)
{
BdrvChild *c;
QLIST_FOREACH(c, &bs->parents, next_parent) {
- if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) {
+ if (c == ignore) {
continue;
}
bdrv_parent_drained_end_single(c);
@@ -242,7 +240,6 @@ typedef struct {
bool begin;
bool poll;
BdrvChild *parent;
- bool ignore_bds_parents;
} BdrvCoDrainData;
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
@@ -269,9 +266,8 @@ static bool bdrv_drain_poll_top_level(BlockDriverState *bs,
}
static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents, bool poll);
-static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents);
+ bool poll);
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent);
static void bdrv_co_drain_bh_cb(void *opaque)
{
@@ -284,11 +280,10 @@ static void bdrv_co_drain_bh_cb(void *opaque)
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
- bdrv_do_drained_begin(bs, data->parent, data->ignore_bds_parents,
- data->poll);
+ bdrv_do_drained_begin(bs, data->parent, data->poll);
} else {
assert(!data->poll);
- bdrv_do_drained_end(bs, data->parent, data->ignore_bds_parents);
+ bdrv_do_drained_end(bs, data->parent);
}
aio_context_release(ctx);
} else {
@@ -303,7 +298,6 @@ static void bdrv_co_drain_bh_cb(void *opaque)
static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
bool begin,
BdrvChild *parent,
- bool ignore_bds_parents,
bool poll)
{
BdrvCoDrainData data;
@@ -321,7 +315,6 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
.done = false,
.begin = begin,
.parent = parent,
- .ignore_bds_parents = ignore_bds_parents,
.poll = poll,
};
@@ -353,8 +346,7 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
}
}
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
- BdrvChild *parent, bool ignore_bds_parents)
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent)
{
IO_OR_GS_CODE();
assert(!qemu_in_coroutine());
@@ -362,9 +354,7 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
/* Stop things in parent-to-child order */
if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) {
aio_disable_external(bdrv_get_aio_context(bs));
-
- /* TODO Remove ignore_bds_parents, we don't consider it any more */
- bdrv_parent_drained_begin(bs, parent, false);
+ bdrv_parent_drained_begin(bs, parent);
if (bs->drv && bs->drv->bdrv_drain_begin) {
bs->drv->bdrv_drain_begin(bs);
}
@@ -372,14 +362,14 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents, bool poll)
+ bool poll)
{
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, true, parent, ignore_bds_parents, poll);
+ bdrv_co_yield_to_drain(bs, true, parent, poll);
return;
}
- bdrv_do_drained_begin_quiesce(bs, parent, ignore_bds_parents);
+ bdrv_do_drained_begin_quiesce(bs, parent);
/*
* Wait for drained requests to finish.
@@ -391,7 +381,6 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
* nodes.
*/
if (poll) {
- assert(!ignore_bds_parents);
BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, parent));
}
}
@@ -399,20 +388,19 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
void bdrv_drained_begin(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_begin(bs, NULL, false, true);
+ bdrv_do_drained_begin(bs, NULL, true);
}
/**
* This function does not poll, nor must any of its recursively called
* functions.
*/
-static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
- bool ignore_bds_parents)
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent)
{
int old_quiesce_counter;
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, false, parent, ignore_bds_parents, false);
+ bdrv_co_yield_to_drain(bs, false, parent, false);
return;
}
assert(bs->quiesce_counter > 0);
@@ -423,9 +411,7 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
if (bs->drv && bs->drv->bdrv_drain_end) {
bs->drv->bdrv_drain_end(bs);
}
- /* TODO Remove ignore_bds_parents, we don't consider it any more */
- bdrv_parent_drained_end(bs, parent, false);
-
+ bdrv_parent_drained_end(bs, parent);
aio_enable_external(bdrv_get_aio_context(bs));
}
}
@@ -433,7 +419,7 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
void bdrv_drained_end(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, NULL, false);
+ bdrv_do_drained_end(bs, NULL);
}
void bdrv_drain(BlockDriverState *bs)
@@ -491,7 +477,7 @@ void bdrv_drain_all_begin(void)
GLOBAL_STATE_CODE();
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(NULL, true, NULL, true, true);
+ bdrv_co_yield_to_drain(NULL, true, NULL, true);
return;
}
@@ -516,7 +502,7 @@ void bdrv_drain_all_begin(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_begin(bs, NULL, true, false);
+ bdrv_do_drained_begin(bs, NULL, false);
aio_context_release(aio_context);
}
@@ -536,7 +522,7 @@ void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
- bdrv_do_drained_end(bs, NULL, true);
+ bdrv_do_drained_end(bs, NULL);
}
}
@@ -558,7 +544,7 @@ void bdrv_drain_all_end(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_end(bs, NULL, true);
+ bdrv_do_drained_end(bs, NULL);
aio_context_release(aio_context);
}
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 9c36a16a1f..8f5e75756a 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -329,8 +329,7 @@ void bdrv_drained_begin(BlockDriverState *bs);
* Quiesces a BDS like bdrv_drained_begin(), but does not wait for already
* running requests to complete.
*/
-void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
- BdrvChild *parent, bool ignore_bds_parents);
+void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent);
/**
* bdrv_drained_end:
--
2.31.1

106
SOURCES/kvm-block-Remove-poll-parameter-from-bdrv_parent_drained.patch
Unescape View File

@ -0,0 +1,106 @@
From 60b66881fb972e1cdff1cd7b4c865e5e21c141b0 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:10 +0100
Subject: [PATCH 28/31] block: Remove poll parameter from
bdrv_parent_drained_begin_single()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [16/16] fd526cc9e5bebeb256cfa56d23ec596f26caa37a (sgarzarella/qemu-kvm-c-9-s)
All callers of bdrv_parent_drained_begin_single() pass poll=false now,
so we don't need the parameter any more.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20221118174110.55183-16-kwolf@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 606ed756c1d69cba4822be8923248d2fd714f069)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 4 ++--
block/io.c | 8 ++------
include/block/block-io.h | 5 ++---
3 files changed, 6 insertions(+), 11 deletions(-)
diff --git a/block.c b/block.c
index 65588d313a..0d78711416 100644
--- a/block.c
+++ b/block.c
@@ -2417,7 +2417,7 @@ static void bdrv_replace_child_abort(void *opaque)
* new_bs drained when calling bdrv_replace_child_tran() is not a
* requirement any more.
*/
- bdrv_parent_drained_begin_single(s->child, false);
+ bdrv_parent_drained_begin_single(s->child);
assert(!bdrv_parent_drained_poll_single(s->child));
}
assert(s->child->quiesced_parent);
@@ -3059,7 +3059,7 @@ static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs,
* a problem, we already did this), but it will still poll until the parent
* is fully quiesced, so it will not be negatively affected either.
*/
- bdrv_parent_drained_begin_single(new_child, false);
+ bdrv_parent_drained_begin_single(new_child);
bdrv_replace_child_noperm(new_child, child_bs);
BdrvAttachChildCommonState *s = g_new(BdrvAttachChildCommonState, 1);
diff --git a/block/io.c b/block/io.c
index ae64830eac..38e57d1f67 100644
--- a/block/io.c
+++ b/block/io.c
@@ -53,7 +53,7 @@ static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore)
if (c == ignore) {
continue;
}
- bdrv_parent_drained_begin_single(c, false);
+ bdrv_parent_drained_begin_single(c);
}
}
@@ -105,9 +105,8 @@ static bool bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore,
return busy;
}
-void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
+void bdrv_parent_drained_begin_single(BdrvChild *c)
{
- AioContext *ctx = bdrv_child_get_parent_aio_context(c);
IO_OR_GS_CODE();
assert(!c->quiesced_parent);
@@ -116,9 +115,6 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
if (c->klass->drained_begin) {
c->klass->drained_begin(c);
}
- if (poll) {
- AIO_WAIT_WHILE(ctx, bdrv_parent_drained_poll_single(c));
- }
}
static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 65e6d2569b..92aaa7c1e9 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -287,10 +287,9 @@ bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
/**
* bdrv_parent_drained_begin_single:
*
- * Begin a quiesced section for the parent of @c. If @poll is true, wait for
- * any pending activity to cease.
+ * Begin a quiesced section for the parent of @c.
*/
-void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll);
+void bdrv_parent_drained_begin_single(BdrvChild *c);
/**
* bdrv_parent_drained_poll_single:
--
2.31.1

896
SOURCES/kvm-block-Remove-subtree-drains.patch
Unescape View File

@ -0,0 +1,896 @@
From 79063522861cb2baf921b204bcdf4c3bfb5697f4 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:05 +0100
Subject: [PATCH 23/31] block: Remove subtree drains
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [11/16] d92f5041cceeeec49a65441b22d20f692c0f1c77 (sgarzarella/qemu-kvm-c-9-s)
Subtree drains are not used any more. Remove them.
After this, BdrvChildClass.attach/detach() don't poll any more.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-11-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 299403aedaeb7f08d8e98aa8614b29d4e5546066)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 20 +--
block/io.c | 121 +++-----------
include/block/block-io.h | 18 +--
include/block/block_int-common.h | 1 -
include/block/block_int-io.h | 12 --
tests/unit/test-bdrv-drain.c | 261 ++-----------------------------
6 files changed, 44 insertions(+), 389 deletions(-)
diff --git a/block.c b/block.c
index 5330e89903..e0e3b21790 100644
--- a/block.c
+++ b/block.c
@@ -1232,7 +1232,7 @@ static void bdrv_child_cb_drained_begin(BdrvChild *child)
static bool bdrv_child_cb_drained_poll(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
- return bdrv_drain_poll(bs, false, NULL, false);
+ return bdrv_drain_poll(bs, NULL, false);
}
static void bdrv_child_cb_drained_end(BdrvChild *child)
@@ -1482,8 +1482,6 @@ static void bdrv_child_cb_attach(BdrvChild *child)
assert(!bs->file);
bs->file = child;
}
-
- bdrv_apply_subtree_drain(child, bs);
}
static void bdrv_child_cb_detach(BdrvChild *child)
@@ -1494,8 +1492,6 @@ static void bdrv_child_cb_detach(BdrvChild *child)
bdrv_backing_detach(child);
}
- bdrv_unapply_subtree_drain(child, bs);
-
assert_bdrv_graph_writable(bs);
QLIST_REMOVE(child, next);
if (child == bs->backing) {
@@ -2851,9 +2847,6 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
}
if (old_bs) {
- /* Detach first so that the recursive drain sections coming from @child
- * are already gone and we only end the drain sections that came from
- * elsewhere. */
if (child->klass->detach) {
child->klass->detach(child);
}
@@ -2868,17 +2861,14 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
/*
- * Detaching the old node may have led to the new node's
- * quiesce_counter having been decreased. Not a problem, we
- * just need to recognize this here and then invoke
- * drained_end appropriately more often.
+ * Polling in bdrv_parent_drained_begin_single() may have led to the new
+ * node's quiesce_counter having been decreased. Not a problem, we just
+ * need to recognize this here and then invoke drained_end appropriately
+ * more often.
*/
assert(new_bs->quiesce_counter <= new_bs_quiesce_counter);
drain_saldo += new_bs->quiesce_counter - new_bs_quiesce_counter;
- /* Attach only after starting new drained sections, so that recursive
- * drain sections coming from @child don't get an extra .drained_begin
- * callback. */
if (child->klass->attach) {
child->klass->attach(child);
}
diff --git a/block/io.c b/block/io.c
index a25103be6f..75224480d0 100644
--- a/block/io.c
+++ b/block/io.c
@@ -236,17 +236,15 @@ typedef struct {
BlockDriverState *bs;
bool done;
bool begin;
- bool recursive;
bool poll;
BdrvChild *parent;
bool ignore_bds_parents;
} BdrvCoDrainData;
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
-bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
- BdrvChild *ignore_parent, bool ignore_bds_parents)
+bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent,
+ bool ignore_bds_parents)
{
- BdrvChild *child, *next;
IO_OR_GS_CODE();
if (bdrv_parent_drained_poll(bs, ignore_parent, ignore_bds_parents)) {
@@ -257,29 +255,19 @@ bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
return true;
}
- if (recursive) {
- assert(!ignore_bds_parents);
- QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
- if (bdrv_drain_poll(child->bs, recursive, child, false)) {
- return true;
- }
- }
- }
-
return false;
}
-static bool bdrv_drain_poll_top_level(BlockDriverState *bs, bool recursive,
+static bool bdrv_drain_poll_top_level(BlockDriverState *bs,
BdrvChild *ignore_parent)
{
- return bdrv_drain_poll(bs, recursive, ignore_parent, false);
+ return bdrv_drain_poll(bs, ignore_parent, false);
}
-static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- bool poll);
-static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents);
+static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents, bool poll);
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents);
static void bdrv_co_drain_bh_cb(void *opaque)
{
@@ -292,12 +280,11 @@ static void bdrv_co_drain_bh_cb(void *opaque)
aio_context_acquire(ctx);
bdrv_dec_in_flight(bs);
if (data->begin) {
- bdrv_do_drained_begin(bs, data->recursive, data->parent,
- data->ignore_bds_parents, data->poll);
+ bdrv_do_drained_begin(bs, data->parent, data->ignore_bds_parents,
+ data->poll);
} else {
assert(!data->poll);
- bdrv_do_drained_end(bs, data->recursive, data->parent,
- data->ignore_bds_parents);
+ bdrv_do_drained_end(bs, data->parent, data->ignore_bds_parents);
}
aio_context_release(ctx);
} else {
@@ -310,7 +297,7 @@ static void bdrv_co_drain_bh_cb(void *opaque)
}
static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
- bool begin, bool recursive,
+ bool begin,
BdrvChild *parent,
bool ignore_bds_parents,
bool poll)
@@ -329,7 +316,6 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
.bs = bs,
.done = false,
.begin = begin,
- .recursive = recursive,
.parent = parent,
.ignore_bds_parents = ignore_bds_parents,
.poll = poll,
@@ -380,29 +366,16 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
}
}
-static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents,
- bool poll)
+static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents, bool poll)
{
- BdrvChild *child, *next;
-
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, true, recursive, parent, ignore_bds_parents,
- poll);
+ bdrv_co_yield_to_drain(bs, true, parent, ignore_bds_parents, poll);
return;
}
bdrv_do_drained_begin_quiesce(bs, parent, ignore_bds_parents);
- if (recursive) {
- assert(!ignore_bds_parents);
- bs->recursive_quiesce_counter++;
- QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
- bdrv_do_drained_begin(child->bs, true, child, ignore_bds_parents,
- false);
- }
- }
-
/*
* Wait for drained requests to finish.
*
@@ -414,35 +387,27 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
*/
if (poll) {
assert(!ignore_bds_parents);
- BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, recursive, parent));
+ BDRV_POLL_WHILE(bs, bdrv_drain_poll_top_level(bs, parent));
}
}
void bdrv_drained_begin(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_begin(bs, false, NULL, false, true);
-}
-
-void bdrv_subtree_drained_begin(BlockDriverState *bs)
-{
- IO_OR_GS_CODE();
- bdrv_do_drained_begin(bs, true, NULL, false, true);
+ bdrv_do_drained_begin(bs, NULL, false, true);
}
/**
* This function does not poll, nor must any of its recursively called
* functions.
*/
-static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
- BdrvChild *parent, bool ignore_bds_parents)
+static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent,
+ bool ignore_bds_parents)
{
- BdrvChild *child;
int old_quiesce_counter;
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs, false, recursive, parent, ignore_bds_parents,
- false);
+ bdrv_co_yield_to_drain(bs, false, parent, ignore_bds_parents, false);
return;
}
assert(bs->quiesce_counter > 0);
@@ -457,46 +422,12 @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
if (old_quiesce_counter == 1) {
aio_enable_external(bdrv_get_aio_context(bs));
}
-
- if (recursive) {
- assert(!ignore_bds_parents);
- bs->recursive_quiesce_counter--;
- QLIST_FOREACH(child, &bs->children, next) {
- bdrv_do_drained_end(child->bs, true, child, ignore_bds_parents);
- }
- }
}
void bdrv_drained_end(BlockDriverState *bs)
{
IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, false, NULL, false);
-}
-
-void bdrv_subtree_drained_end(BlockDriverState *bs)
-{
- IO_OR_GS_CODE();
- bdrv_do_drained_end(bs, true, NULL, false);
-}
-
-void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
-{
- int i;
- IO_OR_GS_CODE();
-
- for (i = 0; i < new_parent->recursive_quiesce_counter; i++) {
- bdrv_do_drained_begin(child->bs, true, child, false, true);
- }
-}
-
-void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
-{
- int i;
- IO_OR_GS_CODE();
-
- for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
- bdrv_do_drained_end(child->bs, true, child, false);
- }
+ bdrv_do_drained_end(bs, NULL, false);
}
void bdrv_drain(BlockDriverState *bs)
@@ -529,7 +460,7 @@ static bool bdrv_drain_all_poll(void)
while ((bs = bdrv_next_all_states(bs))) {
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- result |= bdrv_drain_poll(bs, false, NULL, true);
+ result |= bdrv_drain_poll(bs, NULL, true);
aio_context_release(aio_context);
}
@@ -554,7 +485,7 @@ void bdrv_drain_all_begin(void)
GLOBAL_STATE_CODE();
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(NULL, true, false, NULL, true, true);
+ bdrv_co_yield_to_drain(NULL, true, NULL, true, true);
return;
}
@@ -579,7 +510,7 @@ void bdrv_drain_all_begin(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_begin(bs, false, NULL, true, false);
+ bdrv_do_drained_begin(bs, NULL, true, false);
aio_context_release(aio_context);
}
@@ -599,7 +530,7 @@ void bdrv_drain_all_end_quiesce(BlockDriverState *bs)
g_assert(!bs->refcnt);
while (bs->quiesce_counter) {
- bdrv_do_drained_end(bs, false, NULL, true);
+ bdrv_do_drained_end(bs, NULL, true);
}
}
@@ -621,7 +552,7 @@ void bdrv_drain_all_end(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- bdrv_do_drained_end(bs, false, NULL, true);
+ bdrv_do_drained_end(bs, NULL, true);
aio_context_release(aio_context);
}
diff --git a/include/block/block-io.h b/include/block/block-io.h
index 054e964c9b..9c36a16a1f 100644
--- a/include/block/block-io.h
+++ b/include/block/block-io.h
@@ -302,8 +302,7 @@ void bdrv_parent_drained_end_single(BdrvChild *c);
/**
* bdrv_drain_poll:
*
- * Poll for pending requests in @bs, its parents (except for @ignore_parent),
- * and if @recursive is true its children as well (used for subtree drain).
+ * Poll for pending requests in @bs and its parents (except for @ignore_parent).
*
* If @ignore_bds_parents is true, parents that are BlockDriverStates must
* ignore the drain request because they will be drained separately (used for
@@ -311,8 +310,8 @@ void bdrv_parent_drained_end_single(BdrvChild *c);
*
* This is part of bdrv_drained_begin.
*/
-bool bdrv_drain_poll(BlockDriverState *bs, bool recursive,
- BdrvChild *ignore_parent, bool ignore_bds_parents);
+bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent,
+ bool ignore_bds_parents);
/**
* bdrv_drained_begin:
@@ -333,12 +332,6 @@ void bdrv_drained_begin(BlockDriverState *bs);
void bdrv_do_drained_begin_quiesce(BlockDriverState *bs,
BdrvChild *parent, bool ignore_bds_parents);
-/**
- * Like bdrv_drained_begin, but recursively begins a quiesced section for
- * exclusive access to all child nodes as well.
- */
-void bdrv_subtree_drained_begin(BlockDriverState *bs);
-
/**
* bdrv_drained_end:
*
@@ -346,9 +339,4 @@ void bdrv_subtree_drained_begin(BlockDriverState *bs);
*/
void bdrv_drained_end(BlockDriverState *bs);
-/**
- * End a quiescent section started by bdrv_subtree_drained_begin().
- */
-void bdrv_subtree_drained_end(BlockDriverState *bs);
-
#endif /* BLOCK_IO_H */
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 2b97576f6d..791dddfd7d 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -1184,7 +1184,6 @@ struct BlockDriverState {
/* Accessed with atomic ops. */
int quiesce_counter;
- int recursive_quiesce_counter;
unsigned int write_gen; /* Current data generation */
diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h
index 4b0b3e17ef..8bc061ebb8 100644
--- a/include/block/block_int-io.h
+++ b/include/block/block_int-io.h
@@ -179,16 +179,4 @@ void bdrv_bsc_invalidate_range(BlockDriverState *bs,
*/
void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes);
-
-/*
- * "I/O or GS" API functions. These functions can run without
- * the BQL, but only in one specific iothread/main loop.
- *
- * See include/block/block-io.h for more information about
- * the "I/O or GS" API.
- */
-
-void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
-void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
-
#endif /* BLOCK_INT_IO_H */
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 695519ee02..dda08de8db 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -156,7 +156,6 @@ static void call_in_coroutine(void (*entry)(void))
enum drain_type {
BDRV_DRAIN_ALL,
BDRV_DRAIN,
- BDRV_SUBTREE_DRAIN,
DRAIN_TYPE_MAX,
};
@@ -165,7 +164,6 @@ static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs)
switch (drain_type) {
case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break;
case BDRV_DRAIN: bdrv_drained_begin(bs); break;
- case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_begin(bs); break;
default: g_assert_not_reached();
}
}
@@ -175,7 +173,6 @@ static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs)
switch (drain_type) {
case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break;
case BDRV_DRAIN: bdrv_drained_end(bs); break;
- case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_end(bs); break;
default: g_assert_not_reached();
}
}
@@ -271,11 +268,6 @@ static void test_drv_cb_drain(void)
test_drv_cb_common(BDRV_DRAIN, false);
}
-static void test_drv_cb_drain_subtree(void)
-{
- test_drv_cb_common(BDRV_SUBTREE_DRAIN, true);
-}
-
static void test_drv_cb_co_drain_all(void)
{
call_in_coroutine(test_drv_cb_drain_all);
@@ -286,11 +278,6 @@ static void test_drv_cb_co_drain(void)
call_in_coroutine(test_drv_cb_drain);
}
-static void test_drv_cb_co_drain_subtree(void)
-{
- call_in_coroutine(test_drv_cb_drain_subtree);
-}
-
static void test_quiesce_common(enum drain_type drain_type, bool recursive)
{
BlockBackend *blk;
@@ -332,11 +319,6 @@ static void test_quiesce_drain(void)
test_quiesce_common(BDRV_DRAIN, false);
}
-static void test_quiesce_drain_subtree(void)
-{
- test_quiesce_common(BDRV_SUBTREE_DRAIN, true);
-}
-
static void test_quiesce_co_drain_all(void)
{
call_in_coroutine(test_quiesce_drain_all);
@@ -347,11 +329,6 @@ static void test_quiesce_co_drain(void)
call_in_coroutine(test_quiesce_drain);
}
-static void test_quiesce_co_drain_subtree(void)
-{
- call_in_coroutine(test_quiesce_drain_subtree);
-}
-
static void test_nested(void)
{
BlockBackend *blk;
@@ -402,158 +379,6 @@ static void test_nested(void)
blk_unref(blk);
}
-static void test_multiparent(void)
-{
- BlockBackend *blk_a, *blk_b;
- BlockDriverState *bs_a, *bs_b, *backing;
- BDRVTestState *a_s, *b_s, *backing_s;
-
- blk_a = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR,
- &error_abort);
- a_s = bs_a->opaque;
- blk_insert_bs(blk_a, bs_a, &error_abort);
-
- blk_b = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR,
- &error_abort);
- b_s = bs_b->opaque;
- blk_insert_bs(blk_b, bs_b, &error_abort);
-
- backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort);
- backing_s = backing->opaque;
- bdrv_set_backing_hd(bs_a, backing, &error_abort);
- bdrv_set_backing_hd(bs_b, backing, &error_abort);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 1);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 1);
- g_assert_cmpint(backing->quiesce_counter, ==, 1);
- g_assert_cmpint(a_s->drain_count, ==, 1);
- g_assert_cmpint(b_s->drain_count, ==, 1);
- g_assert_cmpint(backing_s->drain_count, ==, 1);
-
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 2);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 2);
- g_assert_cmpint(backing->quiesce_counter, ==, 2);
- g_assert_cmpint(a_s->drain_count, ==, 2);
- g_assert_cmpint(b_s->drain_count, ==, 2);
- g_assert_cmpint(backing_s->drain_count, ==, 2);
-
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_b);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 1);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 1);
- g_assert_cmpint(backing->quiesce_counter, ==, 1);
- g_assert_cmpint(a_s->drain_count, ==, 1);
- g_assert_cmpint(b_s->drain_count, ==, 1);
- g_assert_cmpint(backing_s->drain_count, ==, 1);
-
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- bdrv_unref(backing);
- bdrv_unref(bs_a);
- bdrv_unref(bs_b);
- blk_unref(blk_a);
- blk_unref(blk_b);
-}
-
-static void test_graph_change_drain_subtree(void)
-{
- BlockBackend *blk_a, *blk_b;
- BlockDriverState *bs_a, *bs_b, *backing;
- BDRVTestState *a_s, *b_s, *backing_s;
-
- blk_a = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR,
- &error_abort);
- a_s = bs_a->opaque;
- blk_insert_bs(blk_a, bs_a, &error_abort);
-
- blk_b = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL);
- bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR,
- &error_abort);
- b_s = bs_b->opaque;
- blk_insert_bs(blk_b, bs_b, &error_abort);
-
- backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort);
- backing_s = backing->opaque;
- bdrv_set_backing_hd(bs_a, backing, &error_abort);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b);
- do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b);
-
- bdrv_set_backing_hd(bs_b, backing, &error_abort);
- g_assert_cmpint(bs_a->quiesce_counter, ==, 5);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 5);
- g_assert_cmpint(backing->quiesce_counter, ==, 5);
- g_assert_cmpint(a_s->drain_count, ==, 5);
- g_assert_cmpint(b_s->drain_count, ==, 5);
- g_assert_cmpint(backing_s->drain_count, ==, 5);
-
- bdrv_set_backing_hd(bs_b, NULL, &error_abort);
- g_assert_cmpint(bs_a->quiesce_counter, ==, 3);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 2);
- g_assert_cmpint(backing->quiesce_counter, ==, 3);
- g_assert_cmpint(a_s->drain_count, ==, 3);
- g_assert_cmpint(b_s->drain_count, ==, 2);
- g_assert_cmpint(backing_s->drain_count, ==, 3);
-
- bdrv_set_backing_hd(bs_b, backing, &error_abort);
- g_assert_cmpint(bs_a->quiesce_counter, ==, 5);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 5);
- g_assert_cmpint(backing->quiesce_counter, ==, 5);
- g_assert_cmpint(a_s->drain_count, ==, 5);
- g_assert_cmpint(b_s->drain_count, ==, 5);
- g_assert_cmpint(backing_s->drain_count, ==, 5);
-
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_b);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_b);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
- do_drain_end(BDRV_SUBTREE_DRAIN, bs_a);
-
- g_assert_cmpint(bs_a->quiesce_counter, ==, 0);
- g_assert_cmpint(bs_b->quiesce_counter, ==, 0);
- g_assert_cmpint(backing->quiesce_counter, ==, 0);
- g_assert_cmpint(a_s->drain_count, ==, 0);
- g_assert_cmpint(b_s->drain_count, ==, 0);
- g_assert_cmpint(backing_s->drain_count, ==, 0);
-
- bdrv_unref(backing);
- bdrv_unref(bs_a);
- bdrv_unref(bs_b);
- blk_unref(blk_a);
- blk_unref(blk_b);
-}
-
static void test_graph_change_drain_all(void)
{
BlockBackend *blk_a, *blk_b;
@@ -773,12 +598,6 @@ static void test_iothread_drain(void)
test_iothread_common(BDRV_DRAIN, 1);
}
-static void test_iothread_drain_subtree(void)
-{
- test_iothread_common(BDRV_SUBTREE_DRAIN, 0);
- test_iothread_common(BDRV_SUBTREE_DRAIN, 1);
-}
-
typedef struct TestBlockJob {
BlockJob common;
@@ -863,7 +682,6 @@ enum test_job_result {
enum test_job_drain_node {
TEST_JOB_DRAIN_SRC,
TEST_JOB_DRAIN_SRC_CHILD,
- TEST_JOB_DRAIN_SRC_PARENT,
};
static void test_blockjob_common_drain_node(enum drain_type drain_type,
@@ -901,9 +719,6 @@ static void test_blockjob_common_drain_node(enum drain_type drain_type,
case TEST_JOB_DRAIN_SRC_CHILD:
drain_bs = src_backing;
break;
- case TEST_JOB_DRAIN_SRC_PARENT:
- drain_bs = src_overlay;
- break;
default:
g_assert_not_reached();
}
@@ -1055,10 +870,6 @@ static void test_blockjob_common(enum drain_type drain_type, bool use_iothread,
TEST_JOB_DRAIN_SRC);
test_blockjob_common_drain_node(drain_type, use_iothread, result,
TEST_JOB_DRAIN_SRC_CHILD);
- if (drain_type == BDRV_SUBTREE_DRAIN) {
- test_blockjob_common_drain_node(drain_type, use_iothread, result,
- TEST_JOB_DRAIN_SRC_PARENT);
- }
}
static void test_blockjob_drain_all(void)
@@ -1071,11 +882,6 @@ static void test_blockjob_drain(void)
test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_SUCCESS);
}
-static void test_blockjob_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_SUCCESS);
-}
-
static void test_blockjob_error_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, false, TEST_JOB_FAIL_RUN);
@@ -1088,12 +894,6 @@ static void test_blockjob_error_drain(void)
test_blockjob_common(BDRV_DRAIN, false, TEST_JOB_FAIL_PREPARE);
}
-static void test_blockjob_error_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_FAIL_RUN);
- test_blockjob_common(BDRV_SUBTREE_DRAIN, false, TEST_JOB_FAIL_PREPARE);
-}
-
static void test_blockjob_iothread_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_SUCCESS);
@@ -1104,11 +904,6 @@ static void test_blockjob_iothread_drain(void)
test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_SUCCESS);
}
-static void test_blockjob_iothread_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_SUCCESS);
-}
-
static void test_blockjob_iothread_error_drain_all(void)
{
test_blockjob_common(BDRV_DRAIN_ALL, true, TEST_JOB_FAIL_RUN);
@@ -1121,12 +916,6 @@ static void test_blockjob_iothread_error_drain(void)
test_blockjob_common(BDRV_DRAIN, true, TEST_JOB_FAIL_PREPARE);
}
-static void test_blockjob_iothread_error_drain_subtree(void)
-{
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_FAIL_RUN);
- test_blockjob_common(BDRV_SUBTREE_DRAIN, true, TEST_JOB_FAIL_PREPARE);
-}
-
typedef struct BDRVTestTopState {
BdrvChild *wait_child;
@@ -1273,14 +1062,6 @@ static void do_test_delete_by_drain(bool detach_instead_of_delete,
bdrv_drain(child_bs);
bdrv_unref(child_bs);
break;
- case BDRV_SUBTREE_DRAIN:
- /* Would have to ref/unref bs here for !detach_instead_of_delete, but
- * then the whole test becomes pointless because the graph changes
- * don't occur during the drain any more. */
- assert(detach_instead_of_delete);
- bdrv_subtree_drained_begin(bs);
- bdrv_subtree_drained_end(bs);
- break;
case BDRV_DRAIN_ALL:
bdrv_drain_all_begin();
bdrv_drain_all_end();
@@ -1315,11 +1096,6 @@ static void test_detach_by_drain(void)
do_test_delete_by_drain(true, BDRV_DRAIN);
}
-static void test_detach_by_drain_subtree(void)
-{
- do_test_delete_by_drain(true, BDRV_SUBTREE_DRAIN);
-}
-
struct detach_by_parent_data {
BlockDriverState *parent_b;
@@ -1452,7 +1228,10 @@ static void test_detach_indirect(bool by_parent_cb)
g_assert(acb != NULL);
/* Drain and check the expected result */
- bdrv_subtree_drained_begin(parent_b);
+ bdrv_drained_begin(parent_b);
+ bdrv_drained_begin(a);
+ bdrv_drained_begin(b);
+ bdrv_drained_begin(c);
g_assert(detach_by_parent_data.child_c != NULL);
@@ -1467,12 +1246,15 @@ static void test_detach_indirect(bool by_parent_cb)
g_assert(QLIST_NEXT(child_a, next) == NULL);
g_assert_cmpint(parent_a->quiesce_counter, ==, 1);
- g_assert_cmpint(parent_b->quiesce_counter, ==, 1);
+ g_assert_cmpint(parent_b->quiesce_counter, ==, 3);
g_assert_cmpint(a->quiesce_counter, ==, 1);
- g_assert_cmpint(b->quiesce_counter, ==, 0);
+ g_assert_cmpint(b->quiesce_counter, ==, 1);
g_assert_cmpint(c->quiesce_counter, ==, 1);
- bdrv_subtree_drained_end(parent_b);
+ bdrv_drained_end(parent_b);
+ bdrv_drained_end(a);
+ bdrv_drained_end(b);
+ bdrv_drained_end(c);
bdrv_unref(parent_b);
blk_unref(blk);
@@ -2202,70 +1984,47 @@ int main(int argc, char **argv)
g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all);
g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain);
- g_test_add_func("/bdrv-drain/driver-cb/drain_subtree",
- test_drv_cb_drain_subtree);
g_test_add_func("/bdrv-drain/driver-cb/co/drain_all",
test_drv_cb_co_drain_all);
g_test_add_func("/bdrv-drain/driver-cb/co/drain", test_drv_cb_co_drain);
- g_test_add_func("/bdrv-drain/driver-cb/co/drain_subtree",
- test_drv_cb_co_drain_subtree);
-
g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all);
g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain);
- g_test_add_func("/bdrv-drain/quiesce/drain_subtree",
- test_quiesce_drain_subtree);
g_test_add_func("/bdrv-drain/quiesce/co/drain_all",
test_quiesce_co_drain_all);
g_test_add_func("/bdrv-drain/quiesce/co/drain", test_quiesce_co_drain);
- g_test_add_func("/bdrv-drain/quiesce/co/drain_subtree",
- test_quiesce_co_drain_subtree);
g_test_add_func("/bdrv-drain/nested", test_nested);
- g_test_add_func("/bdrv-drain/multiparent", test_multiparent);
- g_test_add_func("/bdrv-drain/graph-change/drain_subtree",
- test_graph_change_drain_subtree);
g_test_add_func("/bdrv-drain/graph-change/drain_all",
test_graph_change_drain_all);
g_test_add_func("/bdrv-drain/iothread/drain_all", test_iothread_drain_all);
g_test_add_func("/bdrv-drain/iothread/drain", test_iothread_drain);
- g_test_add_func("/bdrv-drain/iothread/drain_subtree",
- test_iothread_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all);
g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain);
- g_test_add_func("/bdrv-drain/blockjob/drain_subtree",
- test_blockjob_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/error/drain_all",
test_blockjob_error_drain_all);
g_test_add_func("/bdrv-drain/blockjob/error/drain",
test_blockjob_error_drain);
- g_test_add_func("/bdrv-drain/blockjob/error/drain_subtree",
- test_blockjob_error_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/iothread/drain_all",
test_blockjob_iothread_drain_all);
g_test_add_func("/bdrv-drain/blockjob/iothread/drain",
test_blockjob_iothread_drain);
- g_test_add_func("/bdrv-drain/blockjob/iothread/drain_subtree",
- test_blockjob_iothread_drain_subtree);
g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain_all",
test_blockjob_iothread_error_drain_all);
g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain",
test_blockjob_iothread_error_drain);
- g_test_add_func("/bdrv-drain/blockjob/iothread/error/drain_subtree",
- test_blockjob_iothread_error_drain_subtree);
g_test_add_func("/bdrv-drain/deletion/drain", test_delete_by_drain);
g_test_add_func("/bdrv-drain/detach/drain_all", test_detach_by_drain_all);
g_test_add_func("/bdrv-drain/detach/drain", test_detach_by_drain);
- g_test_add_func("/bdrv-drain/detach/drain_subtree", test_detach_by_drain_subtree);
g_test_add_func("/bdrv-drain/detach/parent_cb", test_detach_by_parent_cb);
g_test_add_func("/bdrv-drain/detach/driver_cb", test_detach_by_driver_cb);
--
2.31.1

302
SOURCES/kvm-block-Revert-.bdrv_drained_begin-end-to-non-coroutin.patch
Unescape View File

@ -0,0 +1,302 @@
From 0e894c93cae97bb792dc483be8e295d097ebd7a1 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:40:58 +0100
Subject: [PATCH 16/31] block: Revert .bdrv_drained_begin/end to
non-coroutine_fn
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [4/16] 86d6049e40a99604e414c2572b67f74b85868832 (sgarzarella/qemu-kvm-c-9-s)
Polling during bdrv_drained_end() can be problematic (and in the future,
we may get cases for bdrv_drained_begin() where polling is forbidden,
and we don't care about already in-flight requests, but just want to
prevent new requests from arriving).
The .bdrv_drained_begin/end callbacks running in a coroutine is the only
reason why we have to do this polling, so make them non-coroutine
callbacks again. None of the callers actually yield any more.
This means that bdrv_drained_end() effectively doesn't poll any more,
even if AIO_WAIT_WHILE() loops are still there (their condition is false
from the beginning). This is generally not a problem, but in
test-bdrv-drain, some additional explicit aio_poll() calls need to be
added because the test case wants to verify the final state after BHs
have executed.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-4-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 5e8ac21717373cbe96ef7a91e216bf5788815d63)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 4 +--
block/io.c | 49 +++++---------------------------
block/qed.c | 6 ++--
block/throttle.c | 8 +++---
include/block/block_int-common.h | 10 ++++---
tests/unit/test-bdrv-drain.c | 18 ++++++------
6 files changed, 32 insertions(+), 63 deletions(-)
diff --git a/block.c b/block.c
index ec184150a2..16a62a329c 100644
--- a/block.c
+++ b/block.c
@@ -1713,8 +1713,8 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
assert(is_power_of_2(bs->bl.request_alignment));
for (i = 0; i < bs->quiesce_counter; i++) {
- if (drv->bdrv_co_drain_begin) {
- drv->bdrv_co_drain_begin(bs);
+ if (drv->bdrv_drain_begin) {
+ drv->bdrv_drain_begin(bs);
}
}
diff --git a/block/io.c b/block/io.c
index b9424024f9..c2ed4b2af9 100644
--- a/block/io.c
+++ b/block/io.c
@@ -252,55 +252,20 @@ typedef struct {
int *drained_end_counter;
} BdrvCoDrainData;
-static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
-{
- BdrvCoDrainData *data = opaque;
- BlockDriverState *bs = data->bs;
-
- if (data->begin) {
- bs->drv->bdrv_co_drain_begin(bs);
- } else {
- bs->drv->bdrv_co_drain_end(bs);
- }
-
- /* Set data->done and decrement drained_end_counter before bdrv_wakeup() */
- qatomic_mb_set(&data->done, true);
- if (!data->begin) {
- qatomic_dec(data->drained_end_counter);
- }
- bdrv_dec_in_flight(bs);
-
- g_free(data);
-}
-
-/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */
+/* Recursively call BlockDriver.bdrv_drain_begin/end callbacks */
static void bdrv_drain_invoke(BlockDriverState *bs, bool begin,
int *drained_end_counter)
{
- BdrvCoDrainData *data;
-
- if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) ||
- (!begin && !bs->drv->bdrv_co_drain_end)) {
+ if (!bs->drv || (begin && !bs->drv->bdrv_drain_begin) ||
+ (!begin && !bs->drv->bdrv_drain_end)) {
return;
}
- data = g_new(BdrvCoDrainData, 1);
- *data = (BdrvCoDrainData) {
- .bs = bs,
- .done = false,
- .begin = begin,
- .drained_end_counter = drained_end_counter,
- };
-
- if (!begin) {
- qatomic_inc(drained_end_counter);
+ if (begin) {
+ bs->drv->bdrv_drain_begin(bs);
+ } else {
+ bs->drv->bdrv_drain_end(bs);
}
-
- /* Make sure the driver callback completes during the polling phase for
- * drain_begin. */
- bdrv_inc_in_flight(bs);
- data->co = qemu_coroutine_create(bdrv_drain_invoke_entry, data);
- aio_co_schedule(bdrv_get_aio_context(bs), data->co);
}
/* Returns true if BDRV_POLL_WHILE() should go into a blocking aio_poll() */
diff --git a/block/qed.c b/block/qed.c
index 013f826c44..c2691a85b1 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -262,7 +262,7 @@ static bool coroutine_fn qed_plug_allocating_write_reqs(BDRVQEDState *s)
assert(!s->allocating_write_reqs_plugged);
if (s->allocating_acb != NULL) {
/* Another allocating write came concurrently. This cannot happen
- * from bdrv_qed_co_drain_begin, but it can happen when the timer runs.
+ * from bdrv_qed_drain_begin, but it can happen when the timer runs.
*/
qemu_co_mutex_unlock(&s->table_lock);
return false;
@@ -365,7 +365,7 @@ static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
}
}
-static void coroutine_fn bdrv_qed_co_drain_begin(BlockDriverState *bs)
+static void bdrv_qed_drain_begin(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
@@ -1661,7 +1661,7 @@ static BlockDriver bdrv_qed = {
.bdrv_co_check = bdrv_qed_co_check,
.bdrv_detach_aio_context = bdrv_qed_detach_aio_context,
.bdrv_attach_aio_context = bdrv_qed_attach_aio_context,
- .bdrv_co_drain_begin = bdrv_qed_co_drain_begin,
+ .bdrv_drain_begin = bdrv_qed_drain_begin,
};
static void bdrv_qed_init(void)
diff --git a/block/throttle.c b/block/throttle.c
index 131eba3ab4..88851c84f4 100644
--- a/block/throttle.c
+++ b/block/throttle.c
@@ -214,7 +214,7 @@ static void throttle_reopen_abort(BDRVReopenState *reopen_state)
reopen_state->opaque = NULL;
}
-static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs)
+static void throttle_drain_begin(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
if (qatomic_fetch_inc(&tgm->io_limits_disabled) == 0) {
@@ -222,7 +222,7 @@ static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs)
}
}
-static void coroutine_fn throttle_co_drain_end(BlockDriverState *bs)
+static void throttle_drain_end(BlockDriverState *bs)
{
ThrottleGroupMember *tgm = bs->opaque;
assert(tgm->io_limits_disabled);
@@ -261,8 +261,8 @@ static BlockDriver bdrv_throttle = {
.bdrv_reopen_commit = throttle_reopen_commit,
.bdrv_reopen_abort = throttle_reopen_abort,
- .bdrv_co_drain_begin = throttle_co_drain_begin,
- .bdrv_co_drain_end = throttle_co_drain_end,
+ .bdrv_drain_begin = throttle_drain_begin,
+ .bdrv_drain_end = throttle_drain_end,
.is_filter = true,
.strong_runtime_opts = throttle_strong_runtime_opts,
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 31ae91e56e..40d646d1ed 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -735,17 +735,19 @@ struct BlockDriver {
void (*bdrv_io_unplug)(BlockDriverState *bs);
/**
- * bdrv_co_drain_begin is called if implemented in the beginning of a
+ * bdrv_drain_begin is called if implemented in the beginning of a
* drain operation to drain and stop any internal sources of requests in
* the driver.
- * bdrv_co_drain_end is called if implemented at the end of the drain.
+ * bdrv_drain_end is called if implemented at the end of the drain.
*
* They should be used by the driver to e.g. manage scheduled I/O
* requests, or toggle an internal state. After the end of the drain new
* requests will continue normally.
+ *
+ * Implementations of both functions must not call aio_poll().
*/
- void coroutine_fn (*bdrv_co_drain_begin)(BlockDriverState *bs);
- void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs);
+ void (*bdrv_drain_begin)(BlockDriverState *bs);
+ void (*bdrv_drain_end)(BlockDriverState *bs);
bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);
bool coroutine_fn (*bdrv_co_can_store_new_dirty_bitmap)(
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 24f34e24ad..695519ee02 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -46,7 +46,7 @@ static void coroutine_fn sleep_in_drain_begin(void *opaque)
bdrv_dec_in_flight(bs);
}
-static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs)
+static void bdrv_test_drain_begin(BlockDriverState *bs)
{
BDRVTestState *s = bs->opaque;
s->drain_count++;
@@ -57,7 +57,7 @@ static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs)
}
}
-static void coroutine_fn bdrv_test_co_drain_end(BlockDriverState *bs)
+static void bdrv_test_drain_end(BlockDriverState *bs)
{
BDRVTestState *s = bs->opaque;
s->drain_count--;
@@ -111,8 +111,8 @@ static BlockDriver bdrv_test = {
.bdrv_close = bdrv_test_close,
.bdrv_co_preadv = bdrv_test_co_preadv,
- .bdrv_co_drain_begin = bdrv_test_co_drain_begin,
- .bdrv_co_drain_end = bdrv_test_co_drain_end,
+ .bdrv_drain_begin = bdrv_test_drain_begin,
+ .bdrv_drain_end = bdrv_test_drain_end,
.bdrv_child_perm = bdrv_default_perms,
@@ -1703,6 +1703,7 @@ static void test_blockjob_commit_by_drained_end(void)
bdrv_drained_begin(bs_child);
g_assert(!job_has_completed);
bdrv_drained_end(bs_child);
+ aio_poll(qemu_get_aio_context(), false);
g_assert(job_has_completed);
bdrv_unref(bs_parents[0]);
@@ -1858,6 +1859,7 @@ static void test_drop_intermediate_poll(void)
g_assert(!job_has_completed);
ret = bdrv_drop_intermediate(chain[1], chain[0], NULL);
+ aio_poll(qemu_get_aio_context(), false);
g_assert(ret == 0);
g_assert(job_has_completed);
@@ -1946,7 +1948,7 @@ static void coroutine_fn bdrv_replace_test_drain_co(void *opaque)
* .was_drained.
* Increment .drain_count.
*/
-static void coroutine_fn bdrv_replace_test_co_drain_begin(BlockDriverState *bs)
+static void bdrv_replace_test_drain_begin(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
@@ -1977,7 +1979,7 @@ static void coroutine_fn bdrv_replace_test_read_entry(void *opaque)
* If .drain_count reaches 0 and the node has a backing file, issue a
* read request.
*/
-static void coroutine_fn bdrv_replace_test_co_drain_end(BlockDriverState *bs)
+static void bdrv_replace_test_drain_end(BlockDriverState *bs)
{
BDRVReplaceTestState *s = bs->opaque;
@@ -2002,8 +2004,8 @@ static BlockDriver bdrv_replace_test = {
.bdrv_close = bdrv_replace_test_close,
.bdrv_co_preadv = bdrv_replace_test_co_preadv,
- .bdrv_co_drain_begin = bdrv_replace_test_co_drain_begin,
- .bdrv_co_drain_end = bdrv_replace_test_co_drain_end,
+ .bdrv_drain_begin = bdrv_replace_test_drain_begin,
+ .bdrv_drain_end = bdrv_replace_test_drain_end,
.bdrv_child_perm = bdrv_default_perms,
};
--
2.31.1

246
SOURCES/kvm-block-Split-BlockNodeInfo-off-of-ImageInfo.patch
Unescape View File

@ -0,0 +1,246 @@
From 54e290df4bc1c9e83be7357caed6a2b1ba4f21f0 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:56 +0200
Subject: [PATCH 09/20] block: Split BlockNodeInfo off of ImageInfo
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [4/12] fc8d69d549bb9a929db218b91697ee3ae95c1ff6 (hreitz/qemu-kvm-c-9-s)
ImageInfo sometimes contains flat information, and sometimes it does
not. Split off a BlockNodeInfo struct, which only contains information
about a single node and has no link to the backing image.
We do this so we can extend BlockNodeInfo to a BlockGraphInfo struct,
which has links to all child nodes, not just the backing node. It would
be strange to base BlockGraphInfo on ImageInfo, because then this
extended struct would have two links to the backing node (one in
BlockGraphInfo as one of all the child links, and one in ImageInfo).
Furthermore, it is quite common to ignore the backing-image field
altogether: bdrv_query_image_info() does not set it, and
bdrv_image_info_dump() does not evaluate it. That signals that we
should have different structs for describing a single node and one that
has a link to the backing image.
Still, bdrv_query_image_info() and bdrv_image_info_dump() are not
changed too much in this patch. Follow-up patches will handle them.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-5-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a2085f8909377b6df738f6c3f7ee6db4d16da8f7)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 86 ++++++++++++++++++++++++++++++++------------
include/block/qapi.h | 3 ++
qapi/block-core.json | 24 +++++++++----
3 files changed, 85 insertions(+), 28 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index 51202b470a..e5022b4481 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -241,30 +241,18 @@ int bdrv_query_snapshot_info_list(BlockDriverState *bs,
}
/**
- * bdrv_query_image_info:
- * @bs: block device to examine
- * @p_info: location to store image information
- * @errp: location to store error information
- *
- * Store "flat" image information in @p_info.
- *
- * "Flat" means it does *not* query backing image information,
- * i.e. (*pinfo)->has_backing_image will be set to false and
- * (*pinfo)->backing_image to NULL even when the image does in fact have
- * a backing image.
- *
- * @p_info will be set only on success. On error, store error in @errp.
+ * Helper function for other query info functions. Store information about @bs
+ * in @info, setting @errp on error.
*/
-void bdrv_query_image_info(BlockDriverState *bs,
- ImageInfo **p_info,
- Error **errp)
+static void bdrv_do_query_node_info(BlockDriverState *bs,
+ BlockNodeInfo *info,
+ Error **errp)
{
int64_t size;
const char *backing_filename;
BlockDriverInfo bdi;
int ret;
Error *err = NULL;
- ImageInfo *info;
aio_context_acquire(bdrv_get_aio_context(bs));
@@ -277,7 +265,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
bdrv_refresh_filename(bs);
- info = g_new0(ImageInfo, 1);
info->filename = g_strdup(bs->filename);
info->format = g_strdup(bdrv_get_format_name(bs));
info->virtual_size = size;
@@ -298,7 +285,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
info->format_specific = bdrv_get_specific_info(bs, &err);
if (err) {
error_propagate(errp, err);
- qapi_free_ImageInfo(info);
goto out;
}
info->has_format_specific = info->format_specific != NULL;
@@ -339,16 +325,72 @@ void bdrv_query_image_info(BlockDriverState *bs,
break;
default:
error_propagate(errp, err);
- qapi_free_ImageInfo(info);
goto out;
}
- *p_info = info;
-
out:
aio_context_release(bdrv_get_aio_context(bs));
}
+/**
+ * bdrv_query_block_node_info:
+ * @bs: block node to examine
+ * @p_info: location to store node information
+ * @errp: location to store error information
+ *
+ * Store image information about @bs in @p_info.
+ *
+ * @p_info will be set only on success. On error, store error in @errp.
+ */
+void bdrv_query_block_node_info(BlockDriverState *bs,
+ BlockNodeInfo **p_info,
+ Error **errp)
+{
+ BlockNodeInfo *info;
+ ERRP_GUARD();
+
+ info = g_new0(BlockNodeInfo, 1);
+ bdrv_do_query_node_info(bs, info, errp);
+ if (*errp) {
+ qapi_free_BlockNodeInfo(info);
+ return;
+ }
+
+ *p_info = info;
+}
+
+/**
+ * bdrv_query_image_info:
+ * @bs: block node to examine
+ * @p_info: location to store image information
+ * @errp: location to store error information
+ *
+ * Store "flat" image information in @p_info.
+ *
+ * "Flat" means it does *not* query backing image information,
+ * i.e. (*pinfo)->has_backing_image will be set to false and
+ * (*pinfo)->backing_image to NULL even when the image does in fact have
+ * a backing image.
+ *
+ * @p_info will be set only on success. On error, store error in @errp.
+ */
+void bdrv_query_image_info(BlockDriverState *bs,
+ ImageInfo **p_info,
+ Error **errp)
+{
+ ImageInfo *info;
+ ERRP_GUARD();
+
+ info = g_new0(ImageInfo, 1);
+ bdrv_do_query_node_info(bs, qapi_ImageInfo_base(info), errp);
+ if (*errp) {
+ qapi_free_ImageInfo(info);
+ return;
+ }
+
+ *p_info = info;
+}
+
/* @p_info will be set only on success. */
static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
Error **errp)
diff --git a/include/block/qapi.h b/include/block/qapi.h
index c09859ea78..c7de4e3fa9 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -35,6 +35,9 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
int bdrv_query_snapshot_info_list(BlockDriverState *bs,
SnapshotInfoList **p_list,
Error **errp);
+void bdrv_query_block_node_info(BlockDriverState *bs,
+ BlockNodeInfo **p_info,
+ Error **errp);
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
Error **errp);
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 4b9365167f..7720da0498 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -251,7 +251,7 @@
} }
##
-# @ImageInfo:
+# @BlockNodeInfo:
#
# Information about a QEMU image file
#
@@ -279,22 +279,34 @@
#
# @snapshots: list of VM snapshots
#
-# @backing-image: info of the backing image (since 1.6)
-#
# @format-specific: structure supplying additional format-specific
# information (since 1.7)
#
-# Since: 1.3
+# Since: 8.0
##
-{ 'struct': 'ImageInfo',
+{ 'struct': 'BlockNodeInfo',
'data': {'filename': 'str', 'format': 'str', '*dirty-flag': 'bool',
'*actual-size': 'int', 'virtual-size': 'int',
'*cluster-size': 'int', '*encrypted': 'bool', '*compressed': 'bool',
'*backing-filename': 'str', '*full-backing-filename': 'str',
'*backing-filename-format': 'str', '*snapshots': ['SnapshotInfo'],
- '*backing-image': 'ImageInfo',
'*format-specific': 'ImageInfoSpecific' } }
+##
+# @ImageInfo:
+#
+# Information about a QEMU image file, and potentially its backing image
+#
+# @backing-image: info of the backing image
+#
+# Since: 1.3
+##
+{ 'struct': 'ImageInfo',
+ 'base': 'BlockNodeInfo',
+ 'data': {
+ '*backing-image': 'ImageInfo'
+ } }
+
##
# @ImageCheck:
#
--
2.31.1

70
SOURCES/kvm-block-drop-bdrv_remove_filter_or_cow_child.patch
Unescape View File

@ -0,0 +1,70 @@
From defd6b325264d94ffb1355a8b19f9a77bd694a2f Mon Sep 17 00:00:00 2001
From: Vladimir Sementsov-Ogievskiy <vladimir.sementsov-ogievskiy@openvz.org>
Date: Mon, 7 Nov 2022 19:35:56 +0300
Subject: [PATCH 13/31] block: drop bdrv_remove_filter_or_cow_child
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [1/16] 6339edd738c3b79f8ecb6c1e012e52b6afb1a622 (sgarzarella/qemu-kvm-c-9-s)
Drop this simple wrapper used only in one place. We have too many graph
modifying functions even without it.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@openvz.org>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221107163558.618889-3-vsementsov@yandex-team.ru>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit f38eaec4c3618dfc4a23e20435cefb5bf8325264)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 15 +--------------
1 file changed, 1 insertion(+), 14 deletions(-)
diff --git a/block.c b/block.c
index a18f052374..ec184150a2 100644
--- a/block.c
+++ b/block.c
@@ -93,8 +93,6 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs,
static void bdrv_replace_child_noperm(BdrvChild *child,
BlockDriverState *new_bs);
static void bdrv_remove_child(BdrvChild *child, Transaction *tran);
-static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs,
- Transaction *tran);
static int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
BlockReopenQueue *queue,
@@ -5073,17 +5071,6 @@ static void bdrv_remove_child(BdrvChild *child, Transaction *tran)
tran_add(tran, &bdrv_remove_child_drv, child);
}
-/*
- * A function to remove backing-chain child of @bs if exists: cow child for
- * format nodes (always .backing) and filter child for filters (may be .file or
- * .backing)
- */
-static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs,
- Transaction *tran)
-{
- bdrv_remove_child(bdrv_filter_or_cow_child(bs), tran);
-}
-
static int bdrv_replace_node_noperm(BlockDriverState *from,
BlockDriverState *to,
bool auto_skip, Transaction *tran,
@@ -5168,7 +5155,7 @@ static int bdrv_replace_node_common(BlockDriverState *from,
}
if (detach_subchain) {
- bdrv_remove_filter_or_cow_child(to_cow_parent, tran);
+ bdrv_remove_child(bdrv_filter_or_cow_child(to_cow_parent), tran);
}
found = g_hash_table_new(NULL, NULL);
--
2.31.1

145
SOURCES/kvm-block-file-Add-file-specific-image-info.patch
Unescape View File

@ -0,0 +1,145 @@
From 4af86458d6bea2a6e15fd57d4d4bbe88e35f7e72 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:54 +0200
Subject: [PATCH 07/20] block/file: Add file-specific image info
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [2/12] d8cc351d6c16c41b2000e41dc555f13093a9edce (hreitz/qemu-kvm-c-9-s)
Add some (optional) information that the file driver can provide for
image files, namely the extent size hint.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-3-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 7f36a50ab4e7d39369cac67be4ba9d6ee4081dc0)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/file-posix.c | 30 ++++++++++++++++++++++++++++++
qapi/block-core.json | 26 ++++++++++++++++++++++++--
2 files changed, 54 insertions(+), 2 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index b9647c5ffc..df3da79aed 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -3095,6 +3095,34 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
return 0;
}
+static ImageInfoSpecific *raw_get_specific_info(BlockDriverState *bs,
+ Error **errp)
+{
+ ImageInfoSpecificFile *file_info = g_new0(ImageInfoSpecificFile, 1);
+ ImageInfoSpecific *spec_info = g_new(ImageInfoSpecific, 1);
+
+ *spec_info = (ImageInfoSpecific){
+ .type = IMAGE_INFO_SPECIFIC_KIND_FILE,
+ .u.file.data = file_info,
+ };
+
+#ifdef FS_IOC_FSGETXATTR
+ {
+ BDRVRawState *s = bs->opaque;
+ struct fsxattr attr;
+ int ret;
+
+ ret = ioctl(s->fd, FS_IOC_FSGETXATTR, &attr);
+ if (!ret && attr.fsx_extsize != 0) {
+ file_info->has_extent_size_hint = true;
+ file_info->extent_size_hint = attr.fsx_extsize;
+ }
+ }
+#endif
+
+ return spec_info;
+}
+
static BlockStatsSpecificFile get_blockstats_specific_file(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
@@ -3328,6 +3356,7 @@ BlockDriver bdrv_file = {
.bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_info = raw_get_info,
+ .bdrv_get_specific_info = raw_get_specific_info,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
.bdrv_get_specific_stats = raw_get_specific_stats,
@@ -3700,6 +3729,7 @@ static BlockDriver bdrv_host_device = {
.bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_info = raw_get_info,
+ .bdrv_get_specific_info = raw_get_specific_info,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
.bdrv_get_specific_stats = hdev_get_specific_stats,
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 95ac4fa634..f5d822cbd6 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -139,16 +139,29 @@
'*encryption-format': 'RbdImageEncryptionFormat'
} }
+##
+# @ImageInfoSpecificFile:
+#
+# @extent-size-hint: Extent size hint (if available)
+#
+# Since: 8.0
+##
+{ 'struct': 'ImageInfoSpecificFile',
+ 'data': {
+ '*extent-size-hint': 'size'
+ } }
+
##
# @ImageInfoSpecificKind:
#
# @luks: Since 2.7
# @rbd: Since 6.1
+# @file: Since 8.0
#
# Since: 1.7
##
{ 'enum': 'ImageInfoSpecificKind',
- 'data': [ 'qcow2', 'vmdk', 'luks', 'rbd' ] }
+ 'data': [ 'qcow2', 'vmdk', 'luks', 'rbd', 'file' ] }
##
# @ImageInfoSpecificQCow2Wrapper:
@@ -185,6 +198,14 @@
{ 'struct': 'ImageInfoSpecificRbdWrapper',
'data': { 'data': 'ImageInfoSpecificRbd' } }
+##
+# @ImageInfoSpecificFileWrapper:
+#
+# Since: 8.0
+##
+{ 'struct': 'ImageInfoSpecificFileWrapper',
+ 'data': { 'data': 'ImageInfoSpecificFile' } }
+
##
# @ImageInfoSpecific:
#
@@ -199,7 +220,8 @@
'qcow2': 'ImageInfoSpecificQCow2Wrapper',
'vmdk': 'ImageInfoSpecificVmdkWrapper',
'luks': 'ImageInfoSpecificLUKSWrapper',
- 'rbd': 'ImageInfoSpecificRbdWrapper'
+ 'rbd': 'ImageInfoSpecificRbdWrapper',
+ 'file': 'ImageInfoSpecificFileWrapper'
} }
##
--
2.31.1

206
SOURCES/kvm-block-qapi-Add-indentation-to-bdrv_node_info_dump.patch
Unescape View File

@ -0,0 +1,206 @@
From c8c282c2e1d74cfc5de6527f7e20dfc3e76b67ac Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:00 +0200
Subject: [PATCH 13/20] block/qapi: Add indentation to bdrv_node_info_dump()
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [8/12] d3a697e81ab9828457198075e5815a592363c725 (hreitz/qemu-kvm-c-9-s)
In order to let qemu-img info present a block graph, add a parameter to
bdrv_node_info_dump() and bdrv_image_info_specific_dump() so that the
information of nodes below the root level can be given an indentation.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-9-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 76c9e9750d1bd580e8ed4465f6be3a986434e7c3)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/monitor/block-hmp-cmds.c | 2 +-
block/qapi.c | 47 +++++++++++++++++++---------------
include/block/qapi.h | 5 ++--
qemu-img.c | 2 +-
qemu-io-cmds.c | 3 ++-
5 files changed, 34 insertions(+), 25 deletions(-)
diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index aa37faa601..72824d4e2e 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -734,7 +734,7 @@ static void print_block_info(Monitor *mon, BlockInfo *info,
monitor_printf(mon, "\nImages:\n");
image_info = inserted->image;
while (1) {
- bdrv_node_info_dump(qapi_ImageInfo_base(image_info));
+ bdrv_node_info_dump(qapi_ImageInfo_base(image_info), 0);
if (image_info->has_backing_image) {
image_info = image_info->backing_image;
} else {
diff --git a/block/qapi.c b/block/qapi.c
index f208c21ccf..3e35603f0c 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -915,7 +915,8 @@ static bool qobject_is_empty_dump(const QObject *obj)
* prepending an optional prefix if the dump is not empty.
*/
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
- const char *prefix)
+ const char *prefix,
+ int indentation)
{
QObject *obj, *data;
Visitor *v = qobject_output_visitor_new(&obj);
@@ -925,48 +926,51 @@ void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
data = qdict_get(qobject_to(QDict, obj), "data");
if (!qobject_is_empty_dump(data)) {
if (prefix) {
- qemu_printf("%s", prefix);
+ qemu_printf("%*s%s", indentation * 4, "", prefix);
}
- dump_qobject(1, data);
+ dump_qobject(indentation + 1, data);
}
qobject_unref(obj);
visit_free(v);
}
-void bdrv_node_info_dump(BlockNodeInfo *info)
+void bdrv_node_info_dump(BlockNodeInfo *info, int indentation)
{
char *size_buf, *dsize_buf;
+ g_autofree char *ind_s = g_strdup_printf("%*s", indentation * 4, "");
+
if (!info->has_actual_size) {
dsize_buf = g_strdup("unavailable");
} else {
dsize_buf = size_to_str(info->actual_size);
}
size_buf = size_to_str(info->virtual_size);
- qemu_printf("image: %s\n"
- "file format: %s\n"
- "virtual size: %s (%" PRId64 " bytes)\n"
- "disk size: %s\n",
- info->filename, info->format, size_buf,
- info->virtual_size,
- dsize_buf);
+ qemu_printf("%simage: %s\n"
+ "%sfile format: %s\n"
+ "%svirtual size: %s (%" PRId64 " bytes)\n"
+ "%sdisk size: %s\n",
+ ind_s, info->filename,
+ ind_s, info->format,
+ ind_s, size_buf, info->virtual_size,
+ ind_s, dsize_buf);
g_free(size_buf);
g_free(dsize_buf);
if (info->has_encrypted && info->encrypted) {
- qemu_printf("encrypted: yes\n");
+ qemu_printf("%sencrypted: yes\n", ind_s);
}
if (info->has_cluster_size) {
- qemu_printf("cluster_size: %" PRId64 "\n",
- info->cluster_size);
+ qemu_printf("%scluster_size: %" PRId64 "\n",
+ ind_s, info->cluster_size);
}
if (info->has_dirty_flag && info->dirty_flag) {
- qemu_printf("cleanly shut down: no\n");
+ qemu_printf("%scleanly shut down: no\n", ind_s);
}
if (info->has_backing_filename) {
- qemu_printf("backing file: %s", info->backing_filename);
+ qemu_printf("%sbacking file: %s", ind_s, info->backing_filename);
if (!info->has_full_backing_filename) {
qemu_printf(" (cannot determine actual path)");
} else if (strcmp(info->backing_filename,
@@ -975,15 +979,16 @@ void bdrv_node_info_dump(BlockNodeInfo *info)
}
qemu_printf("\n");
if (info->has_backing_filename_format) {
- qemu_printf("backing file format: %s\n",
- info->backing_filename_format);
+ qemu_printf("%sbacking file format: %s\n",
+ ind_s, info->backing_filename_format);
}
}
if (info->has_snapshots) {
SnapshotInfoList *elem;
- qemu_printf("Snapshot list:\n");
+ qemu_printf("%sSnapshot list:\n", ind_s);
+ qemu_printf("%s", ind_s);
bdrv_snapshot_dump(NULL);
qemu_printf("\n");
@@ -1003,6 +1008,7 @@ void bdrv_node_info_dump(BlockNodeInfo *info)
pstrcpy(sn.id_str, sizeof(sn.id_str), elem->value->id);
pstrcpy(sn.name, sizeof(sn.name), elem->value->name);
+ qemu_printf("%s", ind_s);
bdrv_snapshot_dump(&sn);
qemu_printf("\n");
}
@@ -1010,6 +1016,7 @@ void bdrv_node_info_dump(BlockNodeInfo *info)
if (info->has_format_specific) {
bdrv_image_info_specific_dump(info->format_specific,
- "Format specific information:\n");
+ "Format specific information:\n",
+ indentation);
}
}
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 196436020e..38855f2ae9 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -49,6 +49,7 @@ void bdrv_query_block_graph_info(BlockDriverState *bs,
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
- const char *prefix);
-void bdrv_node_info_dump(BlockNodeInfo *info);
+ const char *prefix,
+ int indentation);
+void bdrv_node_info_dump(BlockNodeInfo *info, int indentation);
#endif
diff --git a/qemu-img.c b/qemu-img.c
index 3b2ca3bbcb..30b4ea58bb 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -2859,7 +2859,7 @@ static void dump_human_image_info_list(BlockNodeInfoList *list)
}
delim = true;
- bdrv_node_info_dump(elem->value);
+ bdrv_node_info_dump(elem->value, 0);
}
}
diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c
index f4a374528e..fdcb89211b 100644
--- a/qemu-io-cmds.c
+++ b/qemu-io-cmds.c
@@ -1826,7 +1826,8 @@ static int info_f(BlockBackend *blk, int argc, char **argv)
}
if (spec_info) {
bdrv_image_info_specific_dump(spec_info,
- "Format specific information:\n");
+ "Format specific information:\n",
+ 0);
qapi_free_ImageInfoSpecific(spec_info);
}
--
2.31.1

155
SOURCES/kvm-block-qapi-Introduce-BlockGraphInfo.patch
Unescape View File

@ -0,0 +1,155 @@
From 0044e3848b02ef6edba5961d1f4b6297d137d207 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:59 +0200
Subject: [PATCH 12/20] block/qapi: Introduce BlockGraphInfo
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [7/12] de47bac372cd552b812c774a2f35f95923af74ff (hreitz/qemu-kvm-c-9-s)
Introduce a new QAPI type BlockGraphInfo and an associated
bdrv_query_block_graph_info() function that recursively gathers
BlockNodeInfo objects through a block graph.
A follow-up patch is going to make "qemu-img info" use this to print
information about all nodes that are (usually implicitly) opened for a
given image file.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-8-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6cab33997b91eb86e82a6a2ae58a24f835249d4a)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
include/block/qapi.h | 3 +++
qapi/block-core.json | 35 ++++++++++++++++++++++++++++++++
3 files changed, 86 insertions(+)
diff --git a/block/qapi.c b/block/qapi.c
index 5d0a8d2ce3..f208c21ccf 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -411,6 +411,54 @@ fail:
qapi_free_ImageInfo(info);
}
+/**
+ * bdrv_query_block_graph_info:
+ * @bs: root node to start from
+ * @p_info: location to store image information
+ * @errp: location to store error information
+ *
+ * Store image information about the graph starting from @bs in @p_info.
+ *
+ * @p_info will be set only on success. On error, store error in @errp.
+ */
+void bdrv_query_block_graph_info(BlockDriverState *bs,
+ BlockGraphInfo **p_info,
+ Error **errp)
+{
+ BlockGraphInfo *info;
+ BlockChildInfoList **children_list_tail;
+ BdrvChild *c;
+ ERRP_GUARD();
+
+ info = g_new0(BlockGraphInfo, 1);
+ bdrv_do_query_node_info(bs, qapi_BlockGraphInfo_base(info), errp);
+ if (*errp) {
+ goto fail;
+ }
+
+ children_list_tail = &info->children;
+
+ QLIST_FOREACH(c, &bs->children, next) {
+ BlockChildInfo *c_info;
+
+ c_info = g_new0(BlockChildInfo, 1);
+ QAPI_LIST_APPEND(children_list_tail, c_info);
+
+ c_info->name = g_strdup(c->name);
+ bdrv_query_block_graph_info(c->bs, &c_info->info, errp);
+ if (*errp) {
+ goto fail;
+ }
+ }
+
+ *p_info = info;
+ return;
+
+fail:
+ assert(*errp != NULL);
+ qapi_free_BlockGraphInfo(info);
+}
+
/* @p_info will be set only on success. */
static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
Error **errp)
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 2174bf8fa2..196436020e 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -43,6 +43,9 @@ void bdrv_query_image_info(BlockDriverState *bs,
bool flat,
bool skip_implicit_filters,
Error **errp);
+void bdrv_query_block_graph_info(BlockDriverState *bs,
+ BlockGraphInfo **p_info,
+ Error **errp);
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 4cf2deeb6c..d703e0fb16 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -307,6 +307,41 @@
'*backing-image': 'ImageInfo'
} }
+##
+# @BlockChildInfo:
+#
+# Information about all nodes in the block graph starting at some node,
+# annotated with information about that node in relation to its parent.
+#
+# @name: Child name of the root node in the BlockGraphInfo struct, in its role
+# as the child of some undescribed parent node
+#
+# @info: Block graph information starting at this node
+#
+# Since: 8.0
+##
+{ 'struct': 'BlockChildInfo',
+ 'data': {
+ 'name': 'str',
+ 'info': 'BlockGraphInfo'
+ } }
+
+##
+# @BlockGraphInfo:
+#
+# Information about all nodes in a block (sub)graph in the form of BlockNodeInfo
+# data.
+# The base BlockNodeInfo struct contains the information for the (sub)graph's
+# root node.
+#
+# @children: Array of links to this node's child nodes' information
+#
+# Since: 8.0
+##
+{ 'struct': 'BlockGraphInfo',
+ 'base': 'BlockNodeInfo',
+ 'data': { 'children': ['BlockChildInfo'] } }
+
##
# @ImageCheck:
#
--
2.31.1

197
SOURCES/kvm-block-qapi-Let-bdrv_query_image_info-recurse.patch
Unescape View File

@ -0,0 +1,197 @@
From ae2c3df00d673d436fe4d8ec9103a3b76d7e6233 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:58 +0200
Subject: [PATCH 11/20] block/qapi: Let bdrv_query_image_info() recurse
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [6/12] 451a83fd682cd6dd6026c22974d18c2f12ee06e3 (hreitz/qemu-kvm-c-9-s)
There is no real reason why bdrv_query_image_info() should generally not
recurse. The ImageInfo struct has a pointer to the backing image, so it
should generally be filled, unless the caller explicitly opts out.
This moves the recursing code from bdrv_block_device_info() into
bdrv_query_image_info().
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-7-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 5d8813593f3f673fc96eed199beb35690cc46f58)
Conflicts:
block/qapi.c: Conflicts with
54fde4ff0621c22b15cbaaa3c74301cc0dbd1c9e ("qapi block: Elide
redundant has_FOO in generated C"), which dropped
`has_backing_image`. Without that commit (and 44ea9d9be before it),
we still need to set `has_backing_image` in
`bdrv_query_image_info()`.
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/qapi.c | 94 +++++++++++++++++++++++++++-----------------
include/block/qapi.h | 2 +
2 files changed, 59 insertions(+), 37 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index ad88bf9b38..5d0a8d2ce3 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -47,8 +47,10 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
Error **errp)
{
ImageInfo **p_image_info;
+ ImageInfo *backing_info;
BlockDriverState *bs0, *backing;
BlockDeviceInfo *info;
+ ERRP_GUARD();
if (!bs->drv) {
error_setg(errp, "Block device %s is ejected", bs->node_name);
@@ -149,38 +151,21 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
bs0 = bs;
p_image_info = &info->image;
info->backing_file_depth = 0;
- while (1) {
- Error *local_err = NULL;
- bdrv_query_image_info(bs0, p_image_info, &local_err);
- if (local_err) {
- error_propagate(errp, local_err);
- qapi_free_BlockDeviceInfo(info);
- return NULL;
- }
-
- /* stop gathering data for flat output */
- if (flat) {
- break;
- }
- if (bs0->drv && bdrv_filter_or_cow_child(bs0)) {
- /*
- * Put any filtered child here (for backwards compatibility to when
- * we put bs0->backing here, which might be any filtered child).
- */
- info->backing_file_depth++;
- bs0 = bdrv_filter_or_cow_bs(bs0);
- (*p_image_info)->has_backing_image = true;
- p_image_info = &((*p_image_info)->backing_image);
- } else {
- break;
- }
+ /*
+ * Skip automatically inserted nodes that the user isn't aware of for
+ * query-block (blk != NULL), but not for query-named-block-nodes
+ */
+ bdrv_query_image_info(bs0, p_image_info, flat, blk != NULL, errp);
+ if (*errp) {
+ qapi_free_BlockDeviceInfo(info);
+ return NULL;
+ }
- /* Skip automatically inserted nodes that the user isn't aware of for
- * query-block (blk != NULL), but not for query-named-block-nodes */
- if (blk) {
- bs0 = bdrv_skip_implicit_filters(bs0);
- }
+ backing_info = info->image->backing_image;
+ while (backing_info) {
+ info->backing_file_depth++;
+ backing_info = backing_info->backing_image;
}
return info;
@@ -363,19 +348,28 @@ void bdrv_query_block_node_info(BlockDriverState *bs,
* bdrv_query_image_info:
* @bs: block node to examine
* @p_info: location to store image information
+ * @flat: skip backing node information
+ * @skip_implicit_filters: skip implicit filters in the backing chain
* @errp: location to store error information
*
- * Store "flat" image information in @p_info.
+ * Store image information in @p_info, potentially recursively covering the
+ * backing chain.
*
- * "Flat" means it does *not* query backing image information,
- * i.e. (*pinfo)->has_backing_image will be set to false and
- * (*pinfo)->backing_image to NULL even when the image does in fact have
- * a backing image.
+ * If @flat is true, do not query backing image information, i.e.
+ * (*p_info)->has_backing_image will be set to false and
+ * (*p_info)->backing_image to NULL even when the image does in fact have a
+ * backing image.
+ *
+ * If @skip_implicit_filters is true, implicit filter nodes in the backing chain
+ * will be skipped when querying backing image information.
+ * (@skip_implicit_filters is ignored when @flat is true.)
*
* @p_info will be set only on success. On error, store error in @errp.
*/
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
+ bool flat,
+ bool skip_implicit_filters,
Error **errp)
{
ImageInfo *info;
@@ -384,11 +378,37 @@ void bdrv_query_image_info(BlockDriverState *bs,
info = g_new0(ImageInfo, 1);
bdrv_do_query_node_info(bs, qapi_ImageInfo_base(info), errp);
if (*errp) {
- qapi_free_ImageInfo(info);
- return;
+ goto fail;
+ }
+
+ if (!flat) {
+ BlockDriverState *backing;
+
+ /*
+ * Use any filtered child here (for backwards compatibility to when
+ * we always took bs->backing, which might be any filtered child).
+ */
+ backing = bdrv_filter_or_cow_bs(bs);
+ if (skip_implicit_filters) {
+ backing = bdrv_skip_implicit_filters(backing);
+ }
+
+ if (backing) {
+ bdrv_query_image_info(backing, &info->backing_image, false,
+ skip_implicit_filters, errp);
+ if (*errp) {
+ goto fail;
+ }
+ info->has_backing_image = true;
+ }
}
*p_info = info;
+ return;
+
+fail:
+ assert(*errp);
+ qapi_free_ImageInfo(info);
}
/* @p_info will be set only on success. */
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 22198dcd0c..2174bf8fa2 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -40,6 +40,8 @@ void bdrv_query_block_node_info(BlockDriverState *bs,
Error **errp);
void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
+ bool flat,
+ bool skip_implicit_filters,
Error **errp);
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
--
2.31.1

99
SOURCES/kvm-block-temporarily-hold-the-new-AioContext-of-bs_top-.patch
Unescape View File

@ -0,0 +1,99 @@
From b952c8f1da6f8597736c0e040565830139369359 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Tue, 14 Feb 2023 18:16:21 +0100
Subject: [PATCH] block: temporarily hold the new AioContext of bs_top in
bdrv_append()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 153: block: temporarily hold the new AioContext of bs_top in bdrv_append()
RH-Bugzilla: 2168209
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [1/1] 5b190426d996e8c9f7a781bd97aee8d25756dbd3 (sgarzarella/qemu-kvm-c-9-s)
bdrv_append() is called with bs_top AioContext held, but
bdrv_attach_child_noperm() could change the AioContext of bs_top.
bdrv_replace_node_noperm() calls bdrv_drained_begin() starting from
commit 2398747128 ("block: Don't poll in bdrv_replace_child_noperm()").
bdrv_drained_begin() can call BDRV_POLL_WHILE that assumes the new lock
is taken, so let's temporarily hold the new AioContext to prevent QEMU
from failing in BDRV_POLL_WHILE when it tries to release the wrong
AioContext.
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2168209
Reported-by: Aihua Liang <aliang@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20230214171621.11574-1-sgarzare@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 60d90bf43c169b9d1dbcb17ed794b7b02c6862b1)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/block.c b/block.c
index 0d78711416..9e1dcb9e47 100644
--- a/block.c
+++ b/block.c
@@ -5275,6 +5275,8 @@ int bdrv_drop_filter(BlockDriverState *bs, Error **errp)
* child.
*
* This function does not create any image files.
+ *
+ * The caller must hold the AioContext lock for @bs_top.
*/
int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
Error **errp)
@@ -5282,11 +5284,14 @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
int ret;
BdrvChild *child;
Transaction *tran = tran_new();
+ AioContext *old_context, *new_context = NULL;
GLOBAL_STATE_CODE();
assert(!bs_new->backing);
+ old_context = bdrv_get_aio_context(bs_top);
+
child = bdrv_attach_child_noperm(bs_new, bs_top, "backing",
&child_of_bds, bdrv_backing_role(bs_new),
tran, errp);
@@ -5295,6 +5300,19 @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top,
goto out;
}
+ /*
+ * bdrv_attach_child_noperm could change the AioContext of bs_top.
+ * bdrv_replace_node_noperm calls bdrv_drained_begin, so let's temporarily
+ * hold the new AioContext, since bdrv_drained_begin calls BDRV_POLL_WHILE
+ * that assumes the new lock is taken.
+ */
+ new_context = bdrv_get_aio_context(bs_top);
+
+ if (old_context != new_context) {
+ aio_context_release(old_context);
+ aio_context_acquire(new_context);
+ }
+
ret = bdrv_replace_node_noperm(bs_top, bs_new, true, tran, errp);
if (ret < 0) {
goto out;
@@ -5306,6 +5324,11 @@ out:
bdrv_refresh_limits(bs_top, NULL, NULL);
+ if (new_context && old_context != new_context) {
+ aio_context_release(new_context);
+ aio_context_acquire(old_context);
+ }
+
return ret;
}
--
2.31.1

140
SOURCES/kvm-block-vmdk-Change-extent-info-type.patch
Unescape View File

@ -0,0 +1,140 @@
From d8caed018afb0f60f449e971398d2a8d6c2992e7 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:55 +0200
Subject: [PATCH 08/20] block/vmdk: Change extent info type
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [3/12] efe50a2797c679ce6bb5faa423047461a34e6792 (hreitz/qemu-kvm-c-9-s)
VMDK's implementation of .bdrv_get_specific_info() returns information
about its extent files, ostensibly in the form of ImageInfo objects.
However, it does not get this information through
bdrv_query_image_info(), but fills only a select few fields with custom
information that does not always match the fields' purposes.
For example, @format, which is supposed to be a block driver name, is
filled with the extent type, e.g. SPARSE or FLAT.
In ImageInfo, @compressed shows whether the data that can be seen in the
image is stored in compressed form or not. For example, a compressed
qcow2 image will store compressed data in its data file, but when
accessing the qcow2 node, you will see normal data. This is not how
VMDK uses the @compressed field for its extent files: Instead, it
signifies whether accessing the extent file will yield compressed data
(which the VMDK driver then (de-)compresses).
Create a new structure to represent the extent information. This allows
us to clarify the fields' meanings, and it clearly shows that these are
not complete ImageInfo objects. (That is, if a user wants an extent
file's ImageInfo object, they will need to query it separately, and will
not get it from ImageInfoSpecificVmdk.extents.)
Note that this removes the last use of ['ImageInfo'] (i.e. an array of
ImageInfo objects), so the QAPI generator will no longer generate
ImageInfoList by default. However, we use it in qemu-img.c, so we need
to create a dummy object to force the generate to create that type,
similarly to DummyForceArrays in machine.json (introduced in commit
9f08c8ec73878122ad4b061ed334f0437afaaa32 ("qapi: Lazy creation of array
types")).
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-4-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 456e75171a85c19a5bfa202eefcbdc4ef1692f05)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/vmdk.c | 8 ++++----
qapi/block-core.json | 38 +++++++++++++++++++++++++++++++++++++-
2 files changed, 41 insertions(+), 5 deletions(-)
diff --git a/block/vmdk.c b/block/vmdk.c
index 26376352b9..4435b9880b 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -2901,12 +2901,12 @@ static int vmdk_has_zero_init(BlockDriverState *bs)
return 1;
}
-static ImageInfo *vmdk_get_extent_info(VmdkExtent *extent)
+static VmdkExtentInfo *vmdk_get_extent_info(VmdkExtent *extent)
{
- ImageInfo *info = g_new0(ImageInfo, 1);
+ VmdkExtentInfo *info = g_new0(VmdkExtentInfo, 1);
bdrv_refresh_filename(extent->file->bs);
- *info = (ImageInfo){
+ *info = (VmdkExtentInfo){
.filename = g_strdup(extent->file->bs->filename),
.format = g_strdup(extent->type),
.virtual_size = extent->sectors * BDRV_SECTOR_SIZE,
@@ -2985,7 +2985,7 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs,
int i;
BDRVVmdkState *s = bs->opaque;
ImageInfoSpecific *spec_info = g_new0(ImageInfoSpecific, 1);
- ImageInfoList **tail;
+ VmdkExtentInfoList **tail;
*spec_info = (ImageInfoSpecific){
.type = IMAGE_INFO_SPECIFIC_KIND_VMDK,
diff --git a/qapi/block-core.json b/qapi/block-core.json
index f5d822cbd6..4b9365167f 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -124,7 +124,33 @@
'create-type': 'str',
'cid': 'int',
'parent-cid': 'int',
- 'extents': ['ImageInfo']
+ 'extents': ['VmdkExtentInfo']
+ } }
+
+##
+# @VmdkExtentInfo:
+#
+# Information about a VMDK extent file
+#
+# @filename: Name of the extent file
+#
+# @format: Extent type (e.g. FLAT or SPARSE)
+#
+# @virtual-size: Number of bytes covered by this extent
+#
+# @cluster-size: Cluster size in bytes (for non-flat extents)
+#
+# @compressed: Whether this extent contains compressed data
+#
+# Since: 8.0
+##
+{ 'struct': 'VmdkExtentInfo',
+ 'data': {
+ 'filename': 'str',
+ 'format': 'str',
+ 'virtual-size': 'int',
+ '*cluster-size': 'int',
+ '*compressed': 'bool'
} }
##
@@ -5754,3 +5780,13 @@
'data': { 'device': 'str', '*id': 'str', '*name': 'str'},
'returns': 'SnapshotInfo',
'allow-preconfig': true }
+
+##
+# @DummyBlockCoreForceArrays:
+#
+# Not used by QMP; hack to let us use ImageInfoList internally
+#
+# Since: 8.0
+##
+{ 'struct': 'DummyBlockCoreForceArrays',
+ 'data': { 'unused-image-info': ['ImageInfo'] } }
--
2.31.1

169
SOURCES/kvm-hw-arm-virt-Add-compact-highmem-property.patch
Unescape View File

@ -0,0 +1,169 @@
From 4ab2aff624908e49b099f00609875f4d03e9e1ec Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 6/8] hw/arm/virt: Add 'compact-highmem' property
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [6/8] 781506f3445493f05b511547370b6d88ef092457
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
After the improvement to high memory region address assignment is
applied, the memory layout can be changed, introducing possible
migration breakage. For example, VIRT_HIGH_PCIE_MMIO memory region
is disabled or enabled when the optimization is applied or not, with
the following configuration. The configuration is only achievable by
modifying the source code until more properties are added to allow
users selectively disable those high memory regions.
pa_bits = 40;
vms->highmem_redists = false;
vms->highmem_ecam = false;
vms->highmem_mmio = true;
# qemu-system-aarch64 -accel kvm -cpu host \
-machine virt-7.2,compact-highmem={on, off} \
-m 4G,maxmem=511G -monitor stdio
Region compact-highmem=off compact-highmem=on
----------------------------------------------------------------
MEM [1GB 512GB] [1GB 512GB]
HIGH_GIC_REDISTS2 [512GB 512GB+64MB] [disabled]
HIGH_PCIE_ECAM [512GB+256MB 512GB+512MB] [disabled]
HIGH_PCIE_MMIO [disabled] [512GB 1TB]
In order to keep backwords compatibility, we need to disable the
optimization on machine, which is virt-7.1 or ealier than it. It
means the optimization is enabled by default from virt-7.2. Besides,
'compact-highmem' property is added so that the optimization can be
explicitly enabled or disabled on all machine types by users.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-7-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit f40408a9fe5d1db70a75a33d2b26c8af8a5d57b0)
Signed-off-by: Gavin Shan <gshan@redhat.com>
Conflicts:
hw/arm/virt.c
Comment out the handlers of property 'compact-highmem' since
the property isn't exposed.
---
docs/system/arm/virt.rst | 4 ++++
hw/arm/virt.c | 34 ++++++++++++++++++++++++++++++++++
include/hw/arm/virt.h | 1 +
3 files changed, 39 insertions(+)
diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst
index 20442ea2c1..4454706392 100644
--- a/docs/system/arm/virt.rst
+++ b/docs/system/arm/virt.rst
@@ -94,6 +94,10 @@ highmem
address space above 32 bits. The default is ``on`` for machine types
later than ``virt-2.12``.
+compact-highmem
+ Set ``on``/``off`` to enable/disable the compact layout for high memory regions.
+ The default is ``on`` for machine types later than ``virt-7.2``.
+
gic-version
Specify the version of the Generic Interrupt Controller (GIC) to provide.
Valid values are:
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6896e0ca0f..6087511ae9 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -216,6 +216,12 @@ static const MemMapEntry base_memmap[] = {
* Note the extended_memmap is sized so that it eventually also includes the
* base_memmap entries (VIRT_HIGH_GIC_REDIST2 index is greater than the last
* index of base_memmap).
+ *
+ * The memory map for these Highmem IO Regions can be in legacy or compact
+ * layout, depending on 'compact-highmem' property. With legacy layout, the
+ * PA space for one specific region is always reserved, even if the region
+ * has been disabled or doesn't fit into the PA space. However, the PA space
+ * for the region won't be reserved in these circumstances with compact layout.
*/
static MemMapEntry extended_memmap[] = {
/* Additional 64 MB redist region (can contain up to 512 redistributors) */
@@ -2400,6 +2406,22 @@ static void virt_set_highmem(Object *obj, bool value, Error **errp)
vms->highmem = value;
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
+static bool virt_get_compact_highmem(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_compact;
+}
+
+static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_compact = value;
+}
+#endif /* disabled for RHEL */
+
static bool virt_get_its(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -3023,6 +3045,13 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
"Set on/off to enable/disable using "
"physical address space above 32 bits");
+ object_class_property_add_bool(oc, "compact-highmem",
+ virt_get_compact_highmem,
+ virt_set_compact_highmem);
+ object_class_property_set_description(oc, "compact-highmem",
+ "Set on/off to enable/disable compact "
+ "layout for high memory regions");
+
object_class_property_add_str(oc, "gic-version", virt_get_gic_version,
virt_set_gic_version);
object_class_property_set_description(oc, "gic-version",
@@ -3107,6 +3136,7 @@ static void virt_instance_init(Object *obj)
/* High memory is enabled by default */
vms->highmem = true;
+ vms->highmem_compact = !vmc->no_highmem_compact;
vms->gic_version = VIRT_GIC_VERSION_NOSEL;
vms->highmem_ecam = !vmc->no_highmem_ecam;
@@ -3176,8 +3206,12 @@ DEFINE_VIRT_MACHINE_AS_LATEST(7, 2)
static void virt_machine_7_1_options(MachineClass *mc)
{
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
virt_machine_7_2_options(mc);
compat_props_add(mc->compat_props, hw_compat_7_1, hw_compat_7_1_len);
+ /* Compact layout for high memory regions was introduced with 7.2 */
+ vmc->no_highmem_compact = true;
}
DEFINE_VIRT_MACHINE(7, 1)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 15bd291311..85e7d61868 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -125,6 +125,7 @@ struct VirtMachineClass {
bool no_pmu;
bool claim_edge_triggered_timers;
bool smbios_old_sys_ver;
+ bool no_highmem_compact;
bool no_highmem_ecam;
bool no_ged; /* Machines < 4.2 have no support for ACPI GED device */
bool kvm_no_adjvtime;
--
2.31.1

179
SOURCES/kvm-hw-arm-virt-Add-properties-to-disable-high-memory-re.patch
Unescape View File

@ -0,0 +1,179 @@
From 30e86a7c4fbcdc95b74bcb2a15745cb221783091 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 7/8] hw/arm/virt: Add properties to disable high memory
regions
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [7/8] 16f8762393b447a590b31c9e4d8d3c58c6bc9fa8
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
The 3 high memory regions are usually enabled by default, but they may
be not used. For example, VIRT_HIGH_GIC_REDIST2 isn't needed by GICv2.
This leads to waste in the PA space.
Add properties ("highmem-redists", "highmem-ecam", "highmem-mmio") to
allow users selectively disable them if needed. After that, the high
memory region for GICv3 or GICv4 redistributor can be disabled by user,
the number of maximal supported CPUs needs to be calculated based on
'vms->highmem_redists'. The follow-up error message is also improved
to indicate if the high memory region for GICv3 and GICv4 has been
enabled or not.
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20221029224307.138822-8-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 6a48c64eec355ab1aff694eb4522d07a8e461368)
Signed-off-by: Gavin Shan <gshan@redhat.com>
Conflicts:
hw/arm/virt.c
Comment out the handlers of the property 'highmem-redists',
'highmem-ecam' and 'highmem-mmio' since they aren't exposed.
---
docs/system/arm/virt.rst | 13 +++++++
hw/arm/virt.c | 75 ++++++++++++++++++++++++++++++++++++++--
2 files changed, 86 insertions(+), 2 deletions(-)
diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst
index 4454706392..188a4f211f 100644
--- a/docs/system/arm/virt.rst
+++ b/docs/system/arm/virt.rst
@@ -98,6 +98,19 @@ compact-highmem
Set ``on``/``off`` to enable/disable the compact layout for high memory regions.
The default is ``on`` for machine types later than ``virt-7.2``.
+highmem-redists
+ Set ``on``/``off`` to enable/disable the high memory region for GICv3 or
+ GICv4 redistributor. The default is ``on``. Setting this to ``off`` will
+ limit the maximum number of CPUs when GICv3 or GICv4 is used.
+
+highmem-ecam
+ Set ``on``/``off`` to enable/disable the high memory region for PCI ECAM.
+ The default is ``on`` for machine types later than ``virt-3.0``.
+
+highmem-mmio
+ Set ``on``/``off`` to enable/disable the high memory region for PCI MMIO.
+ The default is ``on``.
+
gic-version
Specify the version of the Generic Interrupt Controller (GIC) to provide.
Valid values are:
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6087511ae9..304fa0d6e7 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2142,14 +2142,20 @@ static void machvirt_init(MachineState *machine)
if (vms->gic_version == VIRT_GIC_VERSION_2) {
virt_max_cpus = GIC_NCPU;
} else {
- virt_max_cpus = virt_redist_capacity(vms, VIRT_GIC_REDIST) +
- virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2);
+ virt_max_cpus = virt_redist_capacity(vms, VIRT_GIC_REDIST);
+ if (vms->highmem_redists) {
+ virt_max_cpus += virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2);
+ }
}
if (max_cpus > virt_max_cpus) {
error_report("Number of SMP CPUs requested (%d) exceeds max CPUs "
"supported by machine 'mach-virt' (%d)",
max_cpus, virt_max_cpus);
+ if (vms->gic_version != VIRT_GIC_VERSION_2 && !vms->highmem_redists) {
+ error_printf("Try 'highmem-redists=on' for more CPUs\n");
+ }
+
exit(1);
}
@@ -2420,6 +2426,49 @@ static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
vms->highmem_compact = value;
}
+
+static bool virt_get_highmem_redists(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_redists;
+}
+
+static void virt_set_highmem_redists(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_redists = value;
+}
+
+static bool virt_get_highmem_ecam(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_ecam;
+}
+
+static void virt_set_highmem_ecam(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_ecam = value;
+}
+
+static bool virt_get_highmem_mmio(Object *obj, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ return vms->highmem_mmio;
+}
+
+static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
+{
+ VirtMachineState *vms = VIRT_MACHINE(obj);
+
+ vms->highmem_mmio = value;
+}
+
#endif /* disabled for RHEL */
static bool virt_get_its(Object *obj, Error **errp)
@@ -3052,6 +3101,28 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
"Set on/off to enable/disable compact "
"layout for high memory regions");
+ object_class_property_add_bool(oc, "highmem-redists",
+ virt_get_highmem_redists,
+ virt_set_highmem_redists);
+ object_class_property_set_description(oc, "highmem-redists",
+ "Set on/off to enable/disable high "
+ "memory region for GICv3 or GICv4 "
+ "redistributor");
+
+ object_class_property_add_bool(oc, "highmem-ecam",
+ virt_get_highmem_ecam,
+ virt_set_highmem_ecam);
+ object_class_property_set_description(oc, "highmem-ecam",
+ "Set on/off to enable/disable high "
+ "memory region for PCI ECAM");
+
+ object_class_property_add_bool(oc, "highmem-mmio",
+ virt_get_highmem_mmio,
+ virt_set_highmem_mmio);
+ object_class_property_set_description(oc, "highmem-mmio",
+ "Set on/off to enable/disable high "
+ "memory region for PCI MMIO");
+
object_class_property_add_str(oc, "gic-version", virt_get_gic_version,
virt_set_gic_version);
object_class_property_set_description(oc, "gic-version",
--
2.31.1

51
SOURCES/kvm-hw-arm-virt-Enable-compat-high-memory-region-address.patch
Unescape View File

@ -0,0 +1,51 @@
From 969ea1ff46b52c5fe6d87f2eeb1625871a2dfb2a Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 8/8] hw/arm/virt: Enable compat high memory region address
assignment for 9.2.0 machine
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [8/8] beda1791c0c35dce5c669efd47685302b8468032
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
Upstream: RHEL only
The compact high memory region address assignment is enabled for 9.2.0,
but it's kept as disabled for 9.0.0, to keep the backwards compatibility
on 9.0.0. Note that these newly added properties ('compact-highmem',
'highmem-redists', 'highmem-ecam', and 'highmem-mmio') in the upstream
aren't exposed for the downstream.
Signed-off-by: Gavin Shan <gshan@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 304fa0d6e7..e41c0b462c 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3581,6 +3581,7 @@ static void rhel_virt_instance_init(Object *obj)
/* High memory is enabled by default */
vms->highmem = true;
+ vms->highmem_compact = !vmc->no_highmem_compact;
vms->gic_version = VIRT_GIC_VERSION_NOSEL;
vms->highmem_ecam = !vmc->no_highmem_ecam;
@@ -3659,5 +3660,7 @@ static void rhel900_virt_options(MachineClass *mc)
/* Disable FEAT_LPA2 since old kernels (<= v5.12) don't boot with that feature */
vmc->no_tcg_lpa2 = true;
+ /* Compact layout for high memory regions was introduced with 9.2.0 */
+ vmc->no_highmem_compact = true;
}
DEFINE_RHEL_MACHINE(9, 0, 0)
--
2.31.1

112
SOURCES/kvm-hw-arm-virt-Improve-high-memory-region-address-assig.patch
Unescape View File

@ -0,0 +1,112 @@
From 1c7fad3776a14ca35b24dc2fdb262d4ddf40d6eb Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 5/8] hw/arm/virt: Improve high memory region address
assignment
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [5/8] 4d77fa78b5258a1bd8d30405cec5ba3311d42f92
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
There are three high memory regions, which are VIRT_HIGH_REDIST2,
VIRT_HIGH_PCIE_ECAM and VIRT_HIGH_PCIE_MMIO. Their base addresses
are floating on highest RAM address. However, they can be disabled
in several cases.
(1) One specific high memory region is likely to be disabled by
code by toggling vms->highmem_{redists, ecam, mmio}.
(2) VIRT_HIGH_PCIE_ECAM region is disabled on machine, which is
'virt-2.12' or ealier than it.
(3) VIRT_HIGH_PCIE_ECAM region is disabled when firmware is loaded
on 32-bits system.
(4) One specific high memory region is disabled when it breaks the
PA space limit.
The current implementation of virt_set_{memmap, high_memmap}() isn't
optimized because the high memory region's PA space is always reserved,
regardless of whatever the actual state in the corresponding
vms->highmem_{redists, ecam, mmio} flag. In the code, 'base' and
'vms->highest_gpa' are always increased for case (1), (2) and (3).
It's unnecessary since the assigned PA space for the disabled high
memory region won't be used afterwards.
Improve the address assignment for those three high memory region by
skipping the address assignment for one specific high memory region if
it has been disabled in case (1), (2) and (3). The memory layout may
be changed after the improvement is applied, which leads to potential
migration breakage. So 'vms->highmem_compact' is added to control if
the improvement should be applied. For now, 'vms->highmem_compact' is
set to false, meaning that we don't have memory layout change until it
becomes configurable through property 'compact-highmem' in next patch.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-6-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 4a4ff9edc6a8fdc76082af5b41b059217138c09b)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 15 ++++++++++-----
include/hw/arm/virt.h | 1 +
2 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6e3b9fc060..6896e0ca0f 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1768,18 +1768,23 @@ static void virt_set_high_memmap(VirtMachineState *vms,
vms->memmap[i].size = region_size;
/*
- * Check each device to see if they fit in the PA space,
- * moving highest_gpa as we go.
+ * Check each device to see if it fits in the PA space,
+ * moving highest_gpa as we go. For compatibility, move
+ * highest_gpa for disabled fitting devices as well, if
+ * the compact layout has been disabled.
*
* For each device that doesn't fit, disable it.
*/
fits = (region_base + region_size) <= BIT_ULL(pa_bits);
- if (fits) {
- vms->highest_gpa = region_base + region_size - 1;
+ *region_enabled &= fits;
+ if (vms->highmem_compact && !*region_enabled) {
+ continue;
}
- *region_enabled &= fits;
base = region_base + region_size;
+ if (fits) {
+ vms->highest_gpa = base - 1;
+ }
}
}
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 22b54ec510..15bd291311 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -144,6 +144,7 @@ struct VirtMachineState {
PFlashCFI01 *flash[2];
bool secure;
bool highmem;
+ bool highmem_compact;
bool highmem_ecam;
bool highmem_mmio;
bool highmem_redists;
--
2.31.1

82
SOURCES/kvm-hw-arm-virt-Introduce-variable-region_base-in-virt_s.patch
Unescape View File

@ -0,0 +1,82 @@
From 305a369fd18f29914bf96cc181add532d435d8ed Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 3/8] hw/arm/virt: Introduce variable region_base in
virt_set_high_memmap()
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/8] 15de90df217d680ccc858b679898b3993e1c050a
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This introduces variable 'region_base' for the base address of the
specific high memory region. It's the preparatory work to optimize
high memory region address assignment.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-4-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit fa245799b9407fc7b561da185b3d889df5e16a88)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index ca098d40b8..ddcf7ee2f8 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1739,15 +1739,15 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
static void virt_set_high_memmap(VirtMachineState *vms,
hwaddr base, int pa_bits)
{
- hwaddr region_size;
+ hwaddr region_base, region_size;
bool fits;
int i;
for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
+ region_base = ROUND_UP(base, extended_memmap[i].size);
region_size = extended_memmap[i].size;
- base = ROUND_UP(base, region_size);
- vms->memmap[i].base = base;
+ vms->memmap[i].base = region_base;
vms->memmap[i].size = region_size;
/*
@@ -1756,9 +1756,9 @@ static void virt_set_high_memmap(VirtMachineState *vms,
*
* For each device that doesn't fit, disable it.
*/
- fits = (base + region_size) <= BIT_ULL(pa_bits);
+ fits = (region_base + region_size) <= BIT_ULL(pa_bits);
if (fits) {
- vms->highest_gpa = base + region_size - 1;
+ vms->highest_gpa = region_base + region_size - 1;
}
switch (i) {
@@ -1773,7 +1773,7 @@ static void virt_set_high_memmap(VirtMachineState *vms,
break;
}
- base += region_size;
+ base = region_base + region_size;
}
}
--
2.31.1

95
SOURCES/kvm-hw-arm-virt-Introduce-virt_get_high_memmap_enabled-h.patch
Unescape View File

@ -0,0 +1,95 @@
From a2ddd68c8365ec602db6b2a9cf83bb441ca701cc Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 4/8] hw/arm/virt: Introduce virt_get_high_memmap_enabled()
helper
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/8] 65524de2fc106600bbaff641caa8c4f2f8027114
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This introduces virt_get_high_memmap_enabled() helper, which returns
the pointer to vms->highmem_{redists, ecam, mmio}. The pointer will
be used in the subsequent patches.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-5-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit a5cb1350b19a5c2a58ab4edddf609ed429c13085)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 32 +++++++++++++++++++-------------
1 file changed, 19 insertions(+), 13 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index ddcf7ee2f8..6e3b9fc060 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1736,14 +1736,31 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
return arm_cpu_mp_affinity(idx, clustersz);
}
+static inline bool *virt_get_high_memmap_enabled(VirtMachineState *vms,
+ int index)
+{
+ bool *enabled_array[] = {
+ &vms->highmem_redists,
+ &vms->highmem_ecam,
+ &vms->highmem_mmio,
+ };
+
+ assert(ARRAY_SIZE(extended_memmap) - VIRT_LOWMEMMAP_LAST ==
+ ARRAY_SIZE(enabled_array));
+ assert(index - VIRT_LOWMEMMAP_LAST < ARRAY_SIZE(enabled_array));
+
+ return enabled_array[index - VIRT_LOWMEMMAP_LAST];
+}
+
static void virt_set_high_memmap(VirtMachineState *vms,
hwaddr base, int pa_bits)
{
hwaddr region_base, region_size;
- bool fits;
+ bool *region_enabled, fits;
int i;
for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
+ region_enabled = virt_get_high_memmap_enabled(vms, i);
region_base = ROUND_UP(base, extended_memmap[i].size);
region_size = extended_memmap[i].size;
@@ -1761,18 +1778,7 @@ static void virt_set_high_memmap(VirtMachineState *vms,
vms->highest_gpa = region_base + region_size - 1;
}
- switch (i) {
- case VIRT_HIGH_GIC_REDIST2:
- vms->highmem_redists &= fits;
- break;
- case VIRT_HIGH_PCIE_ECAM:
- vms->highmem_ecam &= fits;
- break;
- case VIRT_HIGH_PCIE_MMIO:
- vms->highmem_mmio &= fits;
- break;
- }
-
+ *region_enabled &= fits;
base = region_base + region_size;
}
}
--
2.31.1

130
SOURCES/kvm-hw-arm-virt-Introduce-virt_set_high_memmap-helper.patch
Unescape View File

@ -0,0 +1,130 @@
From 5dff87c5ea60054709021025c9513ec259433ce2 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 1/8] hw/arm/virt: Introduce virt_set_high_memmap() helper
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/8] 5f6ba5af7a2c21d8473c58e088ee99b11336c673
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This introduces virt_set_high_memmap() helper. The logic of high
memory region address assignment is moved to the helper. The intention
is to make the subsequent optimization for high memory region address
assignment easier.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-2-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 4af6b6edece5ef273d29972d53547f823d2bc1c0)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 74 ++++++++++++++++++++++++++++-----------------------
1 file changed, 41 insertions(+), 33 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index bf18838b87..bea5f54720 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1736,6 +1736,46 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
return arm_cpu_mp_affinity(idx, clustersz);
}
+static void virt_set_high_memmap(VirtMachineState *vms,
+ hwaddr base, int pa_bits)
+{
+ int i;
+
+ for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
+ hwaddr size = extended_memmap[i].size;
+ bool fits;
+
+ base = ROUND_UP(base, size);
+ vms->memmap[i].base = base;
+ vms->memmap[i].size = size;
+
+ /*
+ * Check each device to see if they fit in the PA space,
+ * moving highest_gpa as we go.
+ *
+ * For each device that doesn't fit, disable it.
+ */
+ fits = (base + size) <= BIT_ULL(pa_bits);
+ if (fits) {
+ vms->highest_gpa = base + size - 1;
+ }
+
+ switch (i) {
+ case VIRT_HIGH_GIC_REDIST2:
+ vms->highmem_redists &= fits;
+ break;
+ case VIRT_HIGH_PCIE_ECAM:
+ vms->highmem_ecam &= fits;
+ break;
+ case VIRT_HIGH_PCIE_MMIO:
+ vms->highmem_mmio &= fits;
+ break;
+ }
+
+ base += size;
+ }
+}
+
static void virt_set_memmap(VirtMachineState *vms, int pa_bits)
{
MachineState *ms = MACHINE(vms);
@@ -1791,39 +1831,7 @@ static void virt_set_memmap(VirtMachineState *vms, int pa_bits)
/* We know for sure that at least the memory fits in the PA space */
vms->highest_gpa = memtop - 1;
- for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
- hwaddr size = extended_memmap[i].size;
- bool fits;
-
- base = ROUND_UP(base, size);
- vms->memmap[i].base = base;
- vms->memmap[i].size = size;
-
- /*
- * Check each device to see if they fit in the PA space,
- * moving highest_gpa as we go.
- *
- * For each device that doesn't fit, disable it.
- */
- fits = (base + size) <= BIT_ULL(pa_bits);
- if (fits) {
- vms->highest_gpa = base + size - 1;
- }
-
- switch (i) {
- case VIRT_HIGH_GIC_REDIST2:
- vms->highmem_redists &= fits;
- break;
- case VIRT_HIGH_PCIE_ECAM:
- vms->highmem_ecam &= fits;
- break;
- case VIRT_HIGH_PCIE_MMIO:
- vms->highmem_mmio &= fits;
- break;
- }
-
- base += size;
- }
+ virt_set_high_memmap(vms, base, pa_bits);
if (device_memory_size > 0) {
ms->device_memory = g_malloc0(sizeof(*ms->device_memory));
--
2.31.1

83
SOURCES/kvm-hw-arm-virt-Rename-variable-size-to-region_size-in-v.patch
Unescape View File

@ -0,0 +1,83 @@
From bd5b7edbf8f4425f4b4e0d49a00cbdd48d9c6f48 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Wed, 21 Dec 2022 08:48:45 +0800
Subject: [PATCH 2/8] hw/arm/virt: Rename variable size to region_size in
virt_set_high_memmap()
RH-Author: Gavin Shan <gshan@redhat.com>
RH-MergeRequest: 126: hw/arm/virt: Optimize high memory region address assignment
RH-Bugzilla: 2113840
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/8] 1cadf1b00686cceb45821a58fdcb509bc5da335d
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2113840
This renames variable 'size' to 'region_size' in virt_set_high_memmap().
Its counterpart ('region_base') will be introduced in next patch.
No functional change intended.
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Zhenyu Zhang <zhenyzha@redhat.com>
Message-id: 20221029224307.138822-3-gshan@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 370bea9d1c78796eec235ed6cb4310f489931a62)
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
hw/arm/virt.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index bea5f54720..ca098d40b8 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1739,15 +1739,16 @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx)
static void virt_set_high_memmap(VirtMachineState *vms,
hwaddr base, int pa_bits)
{
+ hwaddr region_size;
+ bool fits;
int i;
for (i = VIRT_LOWMEMMAP_LAST; i < ARRAY_SIZE(extended_memmap); i++) {
- hwaddr size = extended_memmap[i].size;
- bool fits;
+ region_size = extended_memmap[i].size;
- base = ROUND_UP(base, size);
+ base = ROUND_UP(base, region_size);
vms->memmap[i].base = base;
- vms->memmap[i].size = size;
+ vms->memmap[i].size = region_size;
/*
* Check each device to see if they fit in the PA space,
@@ -1755,9 +1756,9 @@ static void virt_set_high_memmap(VirtMachineState *vms,
*
* For each device that doesn't fit, disable it.
*/
- fits = (base + size) <= BIT_ULL(pa_bits);
+ fits = (base + region_size) <= BIT_ULL(pa_bits);
if (fits) {
- vms->highest_gpa = base + size - 1;
+ vms->highest_gpa = base + region_size - 1;
}
switch (i) {
@@ -1772,7 +1773,7 @@ static void virt_set_high_memmap(VirtMachineState *vms,
break;
}
- base += size;
+ base += region_size;
}
}
--
2.31.1

386
SOURCES/kvm-io-Add-support-for-MSG_PEEK-for-socket-channel.patch
Unescape View File

@ -0,0 +1,386 @@
From 3a29b50036b972caae5bca0e5dfc34d910b1d5e9 Mon Sep 17 00:00:00 2001
From: "manish.mishra" <manish.mishra@nutanix.com>
Date: Tue, 20 Dec 2022 18:44:17 +0000
Subject: [PATCH 6/8] io: Add support for MSG_PEEK for socket channel
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 150: migration: Fix multifd crash on channel disorders
RH-Bugzilla: 2169732
RH-Acked-by: quintela1 <quintela@redhat.com>
RH-Acked-by: Leonardo Brás <leobras@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Commit: [1/2] 266563f3e387e97ec710d9bc179e5de26dfd09f1 (peterx/qemu-kvm)
MSG_PEEK peeks at the channel, The data is treated as unread and
the next read shall still return this data. This support is
currently added only for socket class. Extra parameter 'flags'
is added to io_readv calls to pass extra read flags like MSG_PEEK.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Suggested-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: manish.mishra <manish.mishra@nutanix.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 84615a19ddf2bfb38d7b3a0d487d2397ee55e4f3)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
chardev/char-socket.c | 4 ++--
include/io/channel.h | 6 ++++++
io/channel-buffer.c | 1 +
io/channel-command.c | 1 +
io/channel-file.c | 1 +
io/channel-null.c | 1 +
io/channel-socket.c | 19 ++++++++++++++++++-
io/channel-tls.c | 1 +
io/channel-websock.c | 1 +
io/channel.c | 16 ++++++++++++----
migration/channel-block.c | 1 +
migration/rdma.c | 1 +
scsi/qemu-pr-helper.c | 2 +-
tests/qtest/tpm-emu.c | 2 +-
tests/unit/test-io-channel-socket.c | 1 +
util/vhost-user-server.c | 2 +-
16 files changed, 50 insertions(+), 10 deletions(-)
diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 879564aa8a..5afce9a464 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -283,11 +283,11 @@ static ssize_t tcp_chr_recv(Chardev *chr, char *buf, size_t len)
if (qio_channel_has_feature(s->ioc, QIO_CHANNEL_FEATURE_FD_PASS)) {
ret = qio_channel_readv_full(s->ioc, &iov, 1,
&msgfds, &msgfds_num,
- NULL);
+ 0, NULL);
} else {
ret = qio_channel_readv_full(s->ioc, &iov, 1,
NULL, NULL,
- NULL);
+ 0, NULL);
}
if (msgfds_num) {
diff --git a/include/io/channel.h b/include/io/channel.h
index c680ee7480..716235d496 100644
--- a/include/io/channel.h
+++ b/include/io/channel.h
@@ -34,6 +34,8 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
#define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+#define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1
+
typedef enum QIOChannelFeature QIOChannelFeature;
enum QIOChannelFeature {
@@ -41,6 +43,7 @@ enum QIOChannelFeature {
QIO_CHANNEL_FEATURE_SHUTDOWN,
QIO_CHANNEL_FEATURE_LISTEN,
QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
+ QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
};
@@ -114,6 +117,7 @@ struct QIOChannelClass {
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp);
int (*io_close)(QIOChannel *ioc,
Error **errp);
@@ -188,6 +192,7 @@ void qio_channel_set_name(QIOChannel *ioc,
* @niov: the length of the @iov array
* @fds: pointer to an array that will received file handles
* @nfds: pointer filled with number of elements in @fds on return
+ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*)
* @errp: pointer to a NULL-initialized error object
*
* Read data from the IO channel, storing it in the
@@ -224,6 +229,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp);
diff --git a/io/channel-buffer.c b/io/channel-buffer.c
index bf52011be2..8096180f85 100644
--- a/io/channel-buffer.c
+++ b/io/channel-buffer.c
@@ -54,6 +54,7 @@ static ssize_t qio_channel_buffer_readv(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 74516252ba..e7edd091af 100644
--- a/io/channel-command.c
+++ b/io/channel-command.c
@@ -203,6 +203,7 @@ static ssize_t qio_channel_command_readv(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 b67687c2aa..d76663e6ae 100644
--- a/io/channel-file.c
+++ b/io/channel-file.c
@@ -86,6 +86,7 @@ static ssize_t qio_channel_file_readv(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-null.c b/io/channel-null.c
index 75e3781507..4fafdb770d 100644
--- a/io/channel-null.c
+++ b/io/channel-null.c
@@ -60,6 +60,7 @@ qio_channel_null_readv(QIOChannel *ioc,
size_t niov,
int **fds G_GNUC_UNUSED,
size_t *nfds G_GNUC_UNUSED,
+ int flags,
Error **errp)
{
QIOChannelNull *nioc = QIO_CHANNEL_NULL(ioc);
diff --git a/io/channel-socket.c b/io/channel-socket.c
index b76dca9cc1..7aca84f61a 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -173,6 +173,9 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
}
#endif
+ qio_channel_set_feature(QIO_CHANNEL(ioc),
+ QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
+
return 0;
}
@@ -406,6 +409,9 @@ qio_channel_socket_accept(QIOChannelSocket *ioc,
}
#endif /* WIN32 */
+ qio_channel_set_feature(QIO_CHANNEL(cioc),
+ QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
+
trace_qio_channel_socket_accept_complete(ioc, cioc, cioc->fd);
return cioc;
@@ -496,6 +502,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
@@ -517,6 +524,10 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
}
+ if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
+ sflags |= MSG_PEEK;
+ }
+
retry:
ret = recvmsg(sioc->fd, &msg, sflags);
if (ret < 0) {
@@ -624,11 +635,17 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
ssize_t done = 0;
ssize_t i;
+ int sflags = 0;
+
+ if (flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) {
+ sflags |= MSG_PEEK;
+ }
for (i = 0; i < niov; i++) {
ssize_t ret;
@@ -636,7 +653,7 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc,
ret = recv(sioc->fd,
iov[i].iov_base,
iov[i].iov_len,
- 0);
+ sflags);
if (ret < 0) {
if (errno == EAGAIN) {
if (done) {
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 4ce890a538..c730cb8ec5 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -260,6 +260,7 @@ static ssize_t qio_channel_tls_readv(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 fb4932ade7..a12acc27cf 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -1081,6 +1081,7 @@ static ssize_t qio_channel_websock_readv(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 0640941ac5..a8c7f11649 100644
--- a/io/channel.c
+++ b/io/channel.c
@@ -52,6 +52,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
@@ -63,7 +64,14 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
return -1;
}
- return klass->io_readv(ioc, iov, niov, fds, nfds, errp);
+ if ((flags & QIO_CHANNEL_READ_FLAG_MSG_PEEK) &&
+ !qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
+ error_setg_errno(errp, EINVAL,
+ "Channel does not support peek read");
+ return -1;
+ }
+
+ return klass->io_readv(ioc, iov, niov, fds, nfds, flags, errp);
}
@@ -146,7 +154,7 @@ int qio_channel_readv_full_all_eof(QIOChannel *ioc,
while ((nlocal_iov > 0) || local_fds) {
ssize_t len;
len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds,
- local_nfds, errp);
+ local_nfds, 0, errp);
if (len == QIO_CHANNEL_ERR_BLOCK) {
if (qemu_in_coroutine()) {
qio_channel_yield(ioc, G_IO_IN);
@@ -284,7 +292,7 @@ ssize_t qio_channel_readv(QIOChannel *ioc,
size_t niov,
Error **errp)
{
- return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, errp);
+ return qio_channel_readv_full(ioc, iov, niov, NULL, NULL, 0, errp);
}
@@ -303,7 +311,7 @@ ssize_t qio_channel_read(QIOChannel *ioc,
Error **errp)
{
struct iovec iov = { .iov_base = buf, .iov_len = buflen };
- return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, errp);
+ return qio_channel_readv_full(ioc, &iov, 1, NULL, NULL, 0, errp);
}
diff --git a/migration/channel-block.c b/migration/channel-block.c
index f4ab53acdb..b7374363c3 100644
--- a/migration/channel-block.c
+++ b/migration/channel-block.c
@@ -53,6 +53,7 @@ qio_channel_block_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelBlock *bioc = QIO_CHANNEL_BLOCK(ioc);
diff --git a/migration/rdma.c b/migration/rdma.c
index 94a55dd95b..d8b4632094 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2854,6 +2854,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc,
size_t niov,
int **fds,
size_t *nfds,
+ int flags,
Error **errp)
{
QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
diff --git a/scsi/qemu-pr-helper.c b/scsi/qemu-pr-helper.c
index 196b78c00d..199227a556 100644
--- a/scsi/qemu-pr-helper.c
+++ b/scsi/qemu-pr-helper.c
@@ -614,7 +614,7 @@ static int coroutine_fn prh_read(PRHelperClient *client, void *buf, int sz,
iov.iov_base = buf;
iov.iov_len = sz;
n_read = qio_channel_readv_full(QIO_CHANNEL(client->ioc), &iov, 1,
- &fds, &nfds, errp);
+ &fds, &nfds, 0, errp);
if (n_read == QIO_CHANNEL_ERR_BLOCK) {
qio_channel_yield(QIO_CHANNEL(client->ioc), G_IO_IN);
diff --git a/tests/qtest/tpm-emu.c b/tests/qtest/tpm-emu.c
index 2994d1cf42..3cf1acaf7d 100644
--- a/tests/qtest/tpm-emu.c
+++ b/tests/qtest/tpm-emu.c
@@ -106,7 +106,7 @@ void *tpm_emu_ctrl_thread(void *data)
int *pfd = NULL;
size_t nfd = 0;
- qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, &error_abort);
+ qio_channel_readv_full(ioc, &iov, 1, &pfd, &nfd, 0, &error_abort);
cmd = be32_to_cpu(cmd);
g_assert_cmpint(cmd, ==, CMD_SET_DATAFD);
g_assert_cmpint(nfd, ==, 1);
diff --git a/tests/unit/test-io-channel-socket.c b/tests/unit/test-io-channel-socket.c
index b36a5d972a..b964bb202d 100644
--- a/tests/unit/test-io-channel-socket.c
+++ b/tests/unit/test-io-channel-socket.c
@@ -460,6 +460,7 @@ static void test_io_channel_unix_fd_pass(void)
G_N_ELEMENTS(iorecv),
&fdrecv,
&nfdrecv,
+ 0,
&error_abort);
g_assert(nfdrecv == G_N_ELEMENTS(fdsend));
diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
index 232984ace6..145eb17c08 100644
--- a/util/vhost-user-server.c
+++ b/util/vhost-user-server.c
@@ -116,7 +116,7 @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg)
* qio_channel_readv_full may have short reads, keeping calling it
* until getting VHOST_USER_HDR_SIZE or 0 bytes in total
*/
- rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, &local_err);
+ rc = qio_channel_readv_full(ioc, &iov, 1, &fds, &nfds, 0, &local_err);
if (rc < 0) {
if (rc == QIO_CHANNEL_ERR_BLOCK) {
assert(local_err == NULL);
--
2.31.1

99
SOURCES/kvm-iotests-106-214-308-Read-only-one-size-line.patch
Unescape View File

@ -0,0 +1,99 @@
From 6727e92a97f8ee9f367a41111bef3f5cad4a479a Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:02 +0200
Subject: [PATCH 15/20] iotests/106, 214, 308: Read only one size line
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [10/12] 1554e0a92b92ed101a251478ccae43f45f6e071e (hreitz/qemu-kvm-c-9-s)
These tests read size information (sometimes disk size, sometimes
virtual size) from qemu-img info's output. Once qemu-img starts
printing info about child nodes, we are going to see multiple instances
of that per image, but these tests are only interested in the first one,
so use "head -n 1" to get it.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-11-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 74163adda3101b127943f7cbbf8fcccd2d472426)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
tests/qemu-iotests/106 | 4 ++--
tests/qemu-iotests/214 | 6 ++++--
tests/qemu-iotests/308 | 4 ++--
3 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/tests/qemu-iotests/106 b/tests/qemu-iotests/106
index 9d6adb542d..ae0fc46691 100755
--- a/tests/qemu-iotests/106
+++ b/tests/qemu-iotests/106
@@ -66,7 +66,7 @@ for create_mode in off falloc full; do
expected_size=$((expected_size + $GROWTH_SIZE))
fi
- actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size')
+ actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size' | head -n 1)
actual_size=$(echo "$actual_size" | sed -e 's/^[^0-9]*\([0-9]\+\).*$/\1/')
# The actual size may exceed the expected size, depending on the file
@@ -105,7 +105,7 @@ for growth_mode in falloc full; do
_make_test_img -o "extent_size_hint=0" 2G
$QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K
- actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size')
+ actual_size=$($QEMU_IMG info -f "$IMGFMT" "$TEST_IMG" | grep 'disk size' | head -n 1)
actual_size=$(echo "$actual_size" | sed -e 's/^[^0-9]*\([0-9]\+\).*$/\1/')
if [ $actual_size -lt $GROWTH_SIZE ]; then
diff --git a/tests/qemu-iotests/214 b/tests/qemu-iotests/214
index c66e246ba2..55ffcd7f44 100755
--- a/tests/qemu-iotests/214
+++ b/tests/qemu-iotests/214
@@ -102,7 +102,8 @@ let data_size="8 * $cluster_size"
$QEMU_IO -c "write -P 0xaa 0 $data_size" "$TEST_IMG" \
2>&1 | _filter_qemu_io | _filter_testdir
sizeA=$($QEMU_IMG info --output=json "$TEST_IMG" |
- sed -n '/"actual-size":/ s/[^0-9]//gp')
+ sed -n '/"actual-size":/ s/[^0-9]//gp' |
+ head -n 1)
_make_test_img 2M -o cluster_size=$cluster_size
echo "Write compressed data:"
@@ -124,7 +125,8 @@ $QEMU_IO -c "write -P 0xcc $offset $data_size" "json:{\
_filter_qemu_io | _filter_testdir
sizeB=$($QEMU_IMG info --output=json "$TEST_IMG" |
- sed -n '/"actual-size":/ s/[^0-9]//gp')
+ sed -n '/"actual-size":/ s/[^0-9]//gp' |
+ head -n 1)
if [ $sizeA -lt $sizeB ]
then
diff --git a/tests/qemu-iotests/308 b/tests/qemu-iotests/308
index bde4aac2fa..09275e9a10 100755
--- a/tests/qemu-iotests/308
+++ b/tests/qemu-iotests/308
@@ -217,12 +217,12 @@ echo
echo '=== Remove export ==='
# Double-check that $EXT_MP appears as a non-empty file (the raw image)
-$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size'
+$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size' | head -n 1
fuse_export_del 'export-mp'
# See that the file appears empty again
-$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size'
+$QEMU_IMG info -f raw "$EXT_MP" | grep 'virtual size' | head -n 1
echo
echo '=== Writable export ==='
--
2.31.1

171
SOURCES/kvm-iotests-Filter-child-node-information.patch
Unescape View File

@ -0,0 +1,171 @@
From 3102e62f80757729c97e58e2b3d62a6a9de952a7 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:01 +0200
Subject: [PATCH 14/20] iotests: Filter child node information
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [9/12] 0b0a42d54397791f7f149e53c9175b7863707e70 (hreitz/qemu-kvm-c-9-s)
Before we let qemu-img info print child node information, have
common.filter, common.rc, and iotests.py filter it from the test output
so we get as few reference output changes as possible.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-10-hreitz@redhat.com>
Tested-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit bcc6777ad6facede73c0cf8b1700045bf4365f7d)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
tests/qemu-iotests/common.filter | 22 ++++++++++++++--------
tests/qemu-iotests/common.rc | 22 ++++++++++++++--------
tests/qemu-iotests/iotests.py | 18 +++++++++++++++---
3 files changed, 43 insertions(+), 19 deletions(-)
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index 6a13757177..6ddda2ee64 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -224,6 +224,7 @@ _filter_img_info()
discard=0
regex_json_spec_start='^ *"format-specific": \{'
+ regex_json_child_start='^ *"children": \['
gsed -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \
-e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \
-e "s#$TEST_DIR#TEST_DIR#g" \
@@ -252,20 +253,25 @@ _filter_img_info()
-e 's/\(compression type: \)\(zlib\|zstd\)/\1COMPRESSION_TYPE/' \
-e "s/uuid: [-a-f0-9]\\+/uuid: 00000000-0000-0000-0000-000000000000/" | \
while IFS='' read -r line; do
- if [[ $format_specific == 1 ]]; then
- discard=0
- elif [[ $line == "Format specific information:" ]]; then
- discard=1
- elif [[ $line =~ $regex_json_spec_start ]]; then
- discard=2
- regex_json_spec_end="^${line%%[^ ]*}\\},? *$"
+ if [[ $discard == 0 ]]; then
+ if [[ $format_specific == 0 && $line == "Format specific information:" ]]; then
+ discard=1
+ elif [[ $line =~ "Child node '/" ]]; then
+ discard=1
+ elif [[ $line =~ $regex_json_spec_start ]]; then
+ discard=2
+ regex_json_end="^${line%%[^ ]*}\\},? *$"
+ elif [[ $line =~ $regex_json_child_start ]]; then
+ discard=2
+ regex_json_end="^${line%%[^ ]*}\\],? *$"
+ fi
fi
if [[ $discard == 0 ]]; then
echo "$line"
elif [[ $discard == 1 && ! $line ]]; then
echo
discard=0
- elif [[ $discard == 2 && $line =~ $regex_json_spec_end ]]; then
+ elif [[ $discard == 2 && $line =~ $regex_json_end ]]; then
discard=0
fi
done
diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index db757025cb..f4476b62f7 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -711,6 +711,7 @@ _img_info()
discard=0
regex_json_spec_start='^ *"format-specific": \{'
+ regex_json_child_start='^ *"children": \['
$QEMU_IMG info $QEMU_IMG_EXTRA_ARGS "$@" "$TEST_IMG" 2>&1 | \
sed -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \
-e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \
@@ -721,20 +722,25 @@ _img_info()
-e "/^disk size:/ D" \
-e "/actual-size/ D" | \
while IFS='' read -r line; do
- if [[ $format_specific == 1 ]]; then
- discard=0
- elif [[ $line == "Format specific information:" ]]; then
- discard=1
- elif [[ $line =~ $regex_json_spec_start ]]; then
- discard=2
- regex_json_spec_end="^${line%%[^ ]*}\\},? *$"
+ if [[ $discard == 0 ]]; then
+ if [[ $format_specific == 0 && $line == "Format specific information:" ]]; then
+ discard=1
+ elif [[ $line =~ "Child node '/" ]]; then
+ discard=1
+ elif [[ $format_specific == 0 && $line =~ $regex_json_spec_start ]]; then
+ discard=2
+ regex_json_end="^${line%%[^ ]*}\\},? *$"
+ elif [[ $line =~ $regex_json_child_start ]]; then
+ discard=2
+ regex_json_end="^${line%%[^ ]*}\\],? *$"
+ fi
fi
if [[ $discard == 0 ]]; then
echo "$line"
elif [[ $discard == 1 && ! $line ]]; then
echo
discard=0
- elif [[ $discard == 2 && $line =~ $regex_json_spec_end ]]; then
+ elif [[ $discard == 2 && $line =~ $regex_json_end ]]; then
discard=0
fi
done
diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py
index da7d6637e1..94aeb3f3b2 100644
--- a/tests/qemu-iotests/iotests.py
+++ b/tests/qemu-iotests/iotests.py
@@ -329,7 +329,7 @@ def qemu_img_log(*args: str, check: bool = True
def img_info_log(filename: str, filter_path: Optional[str] = None,
use_image_opts: bool = False, extra_args: Sequence[str] = (),
- check: bool = True,
+ check: bool = True, drop_child_info: bool = True,
) -> None:
args = ['info']
if use_image_opts:
@@ -342,7 +342,7 @@ def img_info_log(filename: str, filter_path: Optional[str] = None,
output = qemu_img(*args, check=check).stdout
if not filter_path:
filter_path = filename
- log(filter_img_info(output, filter_path))
+ log(filter_img_info(output, filter_path, drop_child_info))
def qemu_io_wrap_args(args: Sequence[str]) -> List[str]:
if '-f' in args or '--image-opts' in args:
@@ -642,11 +642,23 @@ def _filter(_key, value):
def filter_generated_node_ids(msg):
return re.sub("#block[0-9]+", "NODE_NAME", msg)
-def filter_img_info(output, filename):
+def filter_img_info(output: str, filename: str,
+ drop_child_info: bool = True) -> str:
lines = []
+ drop_indented = False
for line in output.split('\n'):
if 'disk size' in line or 'actual-size' in line:
continue
+
+ # Drop child node info
+ if drop_indented:
+ if line.startswith(' '):
+ continue
+ drop_indented = False
+ if drop_child_info and "Child node '/" in line:
+ drop_indented = True
+ continue
+
line = line.replace(filename, 'TEST_IMG')
line = filter_testfiles(line)
line = line.replace(imgfmt, 'IMGFMT')
--
2.31.1

286
SOURCES/kvm-kvm-Atomic-memslot-updates.patch
Unescape View File

@ -0,0 +1,286 @@
From e13fdc97ff05cdee46c112c2dee70b6ef33e7fa7 Mon Sep 17 00:00:00 2001
From: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Date: Mon, 16 Jan 2023 07:17:31 -0500
Subject: [PATCH 31/31] kvm: Atomic memslot updates
RH-Author: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-MergeRequest: 138: accel: introduce accelerator blocker API
RH-Bugzilla: 1979276
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/3] 9f03181ebcad2474fbe859acbce7b9891caa216b (eesposit/qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1979276
commit f39b7d2b96e3e73c01bb678cd096f7baf0b9ab39
Author: David Hildenbrand <david@redhat.com>
Date: Fri Nov 11 10:47:58 2022 -0500
kvm: Atomic memslot updates
If we update an existing memslot (e.g., resize, split), we temporarily
remove the memslot to re-add it immediately afterwards. These updates
are not atomic, especially not for KVM VCPU threads, such that we can
get spurious faults.
Let's inhibit most KVM ioctls while performing relevant updates, such
that we can perform the update just as if it would happen atomically
without additional kernel support.
We capture the add/del changes and apply them in the notifier commit
stage instead. There, we can check for overlaps and perform the ioctl
inhibiting only if really required (-> overlap).
To keep things simple we don't perform additional checks that wouldn't
actually result in an overlap -- such as !RAM memory regions in some
cases (see kvm_set_phys_mem()).
To minimize cache-line bouncing, use a separate indicator
(in_ioctl_lock) per CPU. Also, make sure to hold the kvm_slots_lock
while performing both actions (removing+re-adding).
We have to wait until all IOCTLs were exited and block new ones from
getting executed.
This approach cannot result in a deadlock as long as the inhibitor does
not hold any locks that might hinder an IOCTL from getting finished and
exited - something fairly unusual. The inhibitor will always hold the BQL.
AFAIKs, one possible candidate would be userfaultfd. If a page cannot be
placed (e.g., during postcopy), because we're waiting for a lock, or if the
userfaultfd thread cannot process a fault, because it is waiting for a
lock, there could be a deadlock. However, the BQL is not applicable here,
because any other guest memory access while holding the BQL would already
result in a deadlock.
Nothing else in the kernel should block forever and wait for userspace
intervention.
Note: pause_all_vcpus()/resume_all_vcpus() or
start_exclusive()/end_exclusive() cannot be used, as they either drop
the BQL or require to be called without the BQL - something inhibitors
cannot handle. We need a low-level locking mechanism that is
deadlock-free even when not releasing the BQL.
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Tested-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-Id: <20221111154758.1372674-4-eesposit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
accel/kvm/kvm-all.c | 101 ++++++++++++++++++++++++++++++++++-----
include/sysemu/kvm_int.h | 8 ++++
2 files changed, 98 insertions(+), 11 deletions(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index ff660fd469..39ed30ab59 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -31,6 +31,7 @@
#include "sysemu/kvm_int.h"
#include "sysemu/runstate.h"
#include "sysemu/cpus.h"
+#include "sysemu/accel-blocker.h"
#include "qemu/bswap.h"
#include "exec/memory.h"
#include "exec/ram_addr.h"
@@ -46,6 +47,7 @@
#include "sysemu/hw_accel.h"
#include "kvm-cpus.h"
#include "sysemu/dirtylimit.h"
+#include "qemu/range.h"
#include "hw/boards.h"
#include "monitor/stats.h"
@@ -1292,6 +1294,7 @@ void kvm_set_max_memslot_size(hwaddr max_slot_size)
kvm_max_slot_size = max_slot_size;
}
+/* Called with KVMMemoryListener.slots_lock held */
static void kvm_set_phys_mem(KVMMemoryListener *kml,
MemoryRegionSection *section, bool add)
{
@@ -1326,14 +1329,12 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
ram = memory_region_get_ram_ptr(mr) + mr_offset;
ram_start_offset = memory_region_get_ram_addr(mr) + mr_offset;
- kvm_slots_lock();
-
if (!add) {
do {
slot_size = MIN(kvm_max_slot_size, size);
mem = kvm_lookup_matching_slot(kml, start_addr, slot_size);
if (!mem) {
- goto out;
+ return;
}
if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
/*
@@ -1371,7 +1372,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
start_addr += slot_size;
size -= slot_size;
} while (size);
- goto out;
+ return;
}
/* register the new slot */
@@ -1396,9 +1397,6 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
ram += slot_size;
size -= slot_size;
} while (size);
-
-out:
- kvm_slots_unlock();
}
static void *kvm_dirty_ring_reaper_thread(void *data)
@@ -1455,18 +1453,95 @@ static void kvm_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
+ KVMMemoryUpdate *update;
+
+ update = g_new0(KVMMemoryUpdate, 1);
+ update->section = *section;
- memory_region_ref(section->mr);
- kvm_set_phys_mem(kml, section, true);
+ QSIMPLEQ_INSERT_TAIL(&kml->transaction_add, update, next);
}
static void kvm_region_del(MemoryListener *listener,
MemoryRegionSection *section)
{
KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
+ KVMMemoryUpdate *update;
+
+ update = g_new0(KVMMemoryUpdate, 1);
+ update->section = *section;
+
+ QSIMPLEQ_INSERT_TAIL(&kml->transaction_del, update, next);
+}
+
+static void kvm_region_commit(MemoryListener *listener)
+{
+ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener,
+ listener);
+ KVMMemoryUpdate *u1, *u2;
+ bool need_inhibit = false;
+
+ if (QSIMPLEQ_EMPTY(&kml->transaction_add) &&
+ QSIMPLEQ_EMPTY(&kml->transaction_del)) {
+ return;
+ }
+
+ /*
+ * We have to be careful when regions to add overlap with ranges to remove.
+ * We have to simulate atomic KVM memslot updates by making sure no ioctl()
+ * is currently active.
+ *
+ * The lists are order by addresses, so it's easy to find overlaps.
+ */
+ u1 = QSIMPLEQ_FIRST(&kml->transaction_del);
+ u2 = QSIMPLEQ_FIRST(&kml->transaction_add);
+ while (u1 && u2) {
+ Range r1, r2;
+
+ range_init_nofail(&r1, u1->section.offset_within_address_space,
+ int128_get64(u1->section.size));
+ range_init_nofail(&r2, u2->section.offset_within_address_space,
+ int128_get64(u2->section.size));
+
+ if (range_overlaps_range(&r1, &r2)) {
+ need_inhibit = true;
+ break;
+ }
+ if (range_lob(&r1) < range_lob(&r2)) {
+ u1 = QSIMPLEQ_NEXT(u1, next);
+ } else {
+ u2 = QSIMPLEQ_NEXT(u2, next);
+ }
+ }
+
+ kvm_slots_lock();
+ if (need_inhibit) {
+ accel_ioctl_inhibit_begin();
+ }
+
+ /* Remove all memslots before adding the new ones. */
+ while (!QSIMPLEQ_EMPTY(&kml->transaction_del)) {
+ u1 = QSIMPLEQ_FIRST(&kml->transaction_del);
+ QSIMPLEQ_REMOVE_HEAD(&kml->transaction_del, next);
- kvm_set_phys_mem(kml, section, false);
- memory_region_unref(section->mr);
+ kvm_set_phys_mem(kml, &u1->section, false);
+ memory_region_unref(u1->section.mr);
+
+ g_free(u1);
+ }
+ while (!QSIMPLEQ_EMPTY(&kml->transaction_add)) {
+ u1 = QSIMPLEQ_FIRST(&kml->transaction_add);
+ QSIMPLEQ_REMOVE_HEAD(&kml->transaction_add, next);
+
+ memory_region_ref(u1->section.mr);
+ kvm_set_phys_mem(kml, &u1->section, true);
+
+ g_free(u1);
+ }
+
+ if (need_inhibit) {
+ accel_ioctl_inhibit_end();
+ }
+ kvm_slots_unlock();
}
static void kvm_log_sync(MemoryListener *listener,
@@ -1610,8 +1685,12 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
kml->slots[i].slot = i;
}
+ QSIMPLEQ_INIT(&kml->transaction_add);
+ QSIMPLEQ_INIT(&kml->transaction_del);
+
kml->listener.region_add = kvm_region_add;
kml->listener.region_del = kvm_region_del;
+ kml->listener.commit = kvm_region_commit;
kml->listener.log_start = kvm_log_start;
kml->listener.log_stop = kvm_log_stop;
kml->listener.priority = 10;
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index 3b4adcdc10..60b520a13e 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -12,6 +12,7 @@
#include "exec/memory.h"
#include "qapi/qapi-types-common.h"
#include "qemu/accel.h"
+#include "qemu/queue.h"
#include "sysemu/kvm.h"
typedef struct KVMSlot
@@ -31,10 +32,17 @@ typedef struct KVMSlot
ram_addr_t ram_start_offset;
} KVMSlot;
+typedef struct KVMMemoryUpdate {
+ QSIMPLEQ_ENTRY(KVMMemoryUpdate) next;
+ MemoryRegionSection section;
+} KVMMemoryUpdate;
+
typedef struct KVMMemoryListener {
MemoryListener listener;
KVMSlot *slots;
int as_id;
+ QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_add;
+ QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_del;
} KVMMemoryListener;
#define KVM_MSI_HASHTAB_SIZE 256
--
2.31.1

577
SOURCES/kvm-linux-headers-Update-to-v6.1.patch
Unescape View File

@ -0,0 +1,577 @@
From cbe35c6a4794107ea1ddecf0b381ba4b1c8799f5 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 7 Feb 2023 15:57:10 -0500
Subject: [PATCH 3/8] linux-headers: Update to v6.1
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 149: Support /dev/userfaultfd
RH-Bugzilla: 2158704
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: quintela1 <quintela@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/3] 15d97026e802a0f01b5f80f81fb4414dc69b2b2d (peterx/qemu-kvm)
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 93e0932b7be2498024cd6ba8446a0fa2cb1769bc)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
include/standard-headers/drm/drm_fourcc.h | 34 ++++-
include/standard-headers/linux/ethtool.h | 63 +++++++-
include/standard-headers/linux/fuse.h | 6 +-
.../linux/input-event-codes.h | 1 +
include/standard-headers/linux/virtio_blk.h | 19 +++
linux-headers/asm-generic/hugetlb_encode.h | 26 ++--
linux-headers/asm-generic/mman-common.h | 2 +
linux-headers/asm-mips/mman.h | 2 +
linux-headers/asm-riscv/kvm.h | 4 +
linux-headers/linux/kvm.h | 1 +
linux-headers/linux/psci.h | 14 ++
linux-headers/linux/userfaultfd.h | 4 +
linux-headers/linux/vfio.h | 142 ++++++++++++++++++
13 files changed, 298 insertions(+), 20 deletions(-)
diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h
index 48b620cbef..b868488f93 100644
--- a/include/standard-headers/drm/drm_fourcc.h
+++ b/include/standard-headers/drm/drm_fourcc.h
@@ -98,18 +98,42 @@ extern "C" {
#define DRM_FORMAT_INVALID 0
/* color index */
+#define DRM_FORMAT_C1 fourcc_code('C', '1', ' ', ' ') /* [7:0] C0:C1:C2:C3:C4:C5:C6:C7 1:1:1:1:1:1:1:1 eight pixels/byte */
+#define DRM_FORMAT_C2 fourcc_code('C', '2', ' ', ' ') /* [7:0] C0:C1:C2:C3 2:2:2:2 four pixels/byte */
+#define DRM_FORMAT_C4 fourcc_code('C', '4', ' ', ' ') /* [7:0] C0:C1 4:4 two pixels/byte */
#define DRM_FORMAT_C8 fourcc_code('C', '8', ' ', ' ') /* [7:0] C */
-/* 8 bpp Red */
+/* 1 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D1 fourcc_code('D', '1', ' ', ' ') /* [7:0] D0:D1:D2:D3:D4:D5:D6:D7 1:1:1:1:1:1:1:1 eight pixels/byte */
+
+/* 2 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D2 fourcc_code('D', '2', ' ', ' ') /* [7:0] D0:D1:D2:D3 2:2:2:2 four pixels/byte */
+
+/* 4 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D4 fourcc_code('D', '4', ' ', ' ') /* [7:0] D0:D1 4:4 two pixels/byte */
+
+/* 8 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D8 fourcc_code('D', '8', ' ', ' ') /* [7:0] D */
+
+/* 1 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R1 fourcc_code('R', '1', ' ', ' ') /* [7:0] R0:R1:R2:R3:R4:R5:R6:R7 1:1:1:1:1:1:1:1 eight pixels/byte */
+
+/* 2 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R2 fourcc_code('R', '2', ' ', ' ') /* [7:0] R0:R1:R2:R3 2:2:2:2 four pixels/byte */
+
+/* 4 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R4 fourcc_code('R', '4', ' ', ' ') /* [7:0] R0:R1 4:4 two pixels/byte */
+
+/* 8 bpp Red (direct relationship between channel value and brightness) */
#define DRM_FORMAT_R8 fourcc_code('R', '8', ' ', ' ') /* [7:0] R */
-/* 10 bpp Red */
+/* 10 bpp Red (direct relationship between channel value and brightness) */
#define DRM_FORMAT_R10 fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */
-/* 12 bpp Red */
+/* 12 bpp Red (direct relationship between channel value and brightness) */
#define DRM_FORMAT_R12 fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */
-/* 16 bpp Red */
+/* 16 bpp Red (direct relationship between channel value and brightness) */
#define DRM_FORMAT_R16 fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */
/* 16 bpp RG */
@@ -204,7 +228,9 @@ extern "C" {
#define DRM_FORMAT_VYUY fourcc_code('V', 'Y', 'U', 'Y') /* [31:0] Y1:Cb0:Y0:Cr0 8:8:8:8 little endian */
#define DRM_FORMAT_AYUV fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */
+#define DRM_FORMAT_AVUY8888 fourcc_code('A', 'V', 'U', 'Y') /* [31:0] A:Cr:Cb:Y 8:8:8:8 little endian */
#define DRM_FORMAT_XYUV8888 fourcc_code('X', 'Y', 'U', 'V') /* [31:0] X:Y:Cb:Cr 8:8:8:8 little endian */
+#define DRM_FORMAT_XVUY8888 fourcc_code('X', 'V', 'U', 'Y') /* [31:0] X:Cr:Cb:Y 8:8:8:8 little endian */
#define DRM_FORMAT_VUY888 fourcc_code('V', 'U', '2', '4') /* [23:0] Cr:Cb:Y 8:8:8 little endian */
#define DRM_FORMAT_VUY101010 fourcc_code('V', 'U', '3', '0') /* Y followed by U then V, 10:10:10. Non-linear modifier only */
diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h
index 4537da20cc..1dc56cdc0a 100644
--- a/include/standard-headers/linux/ethtool.h
+++ b/include/standard-headers/linux/ethtool.h
@@ -736,6 +736,51 @@ enum ethtool_module_power_mode {
ETHTOOL_MODULE_POWER_MODE_HIGH,
};
+/**
+ * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE
+ * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState
+ * @ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN: state of PoDL PSE functions are
+ * unknown
+ * @ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED: PoDL PSE functions are disabled
+ * @ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED: PoDL PSE functions are enabled
+ */
+enum ethtool_podl_pse_admin_state {
+ ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN = 1,
+ ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED,
+ ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED,
+};
+
+/**
+ * enum ethtool_podl_pse_pw_d_status - power detection status of the PoDL PSE.
+ * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus:
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN: PoDL PSE
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED: "The enumeration “disabled” is
+ * asserted true when the PoDL PSE state diagram variable mr_pse_enable is
+ * false"
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING: "The enumeration “searching” is
+ * asserted true when either of the PSE state diagram variables
+ * pi_detecting or pi_classifying is true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING: "The enumeration “deliveringPower”
+ * is asserted true when the PoDL PSE state diagram variable pi_powered is
+ * true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP: "The enumeration “sleep” is asserted
+ * true when the PoDL PSE state diagram variable pi_sleeping is true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE: "The enumeration “idle” is asserted true
+ * when the logical combination of the PoDL PSE state diagram variables
+ * pi_prebiased*!pi_sleeping is true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR: "The enumeration “error” is asserted
+ * true when the PoDL PSE state diagram variable overload_held is true."
+ */
+enum ethtool_podl_pse_pw_d_status {
+ ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN = 1,
+ ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED,
+ ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING,
+ ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING,
+ ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP,
+ ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE,
+ ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR,
+};
+
/**
* struct ethtool_gstrings - string set for data tagging
* @cmd: Command number = %ETHTOOL_GSTRINGS
@@ -1840,6 +1885,20 @@ static inline int ethtool_validate_duplex(uint8_t duplex)
#define MASTER_SLAVE_STATE_SLAVE 3
#define MASTER_SLAVE_STATE_ERR 4
+/* These are used to throttle the rate of data on the phy interface when the
+ * native speed of the interface is higher than the link speed. These should
+ * not be used for phy interfaces which natively support multiple speeds (e.g.
+ * MII or SGMII).
+ */
+/* No rate matching performed. */
+#define RATE_MATCH_NONE 0
+/* The phy sends pause frames to throttle the MAC. */
+#define RATE_MATCH_PAUSE 1
+/* The phy asserts CRS to prevent the MAC from transmitting. */
+#define RATE_MATCH_CRS 2
+/* The MAC is programmed with a sufficiently-large IPG. */
+#define RATE_MATCH_OPEN_LOOP 3
+
/* Which connector port. */
#define PORT_TP 0x00
#define PORT_AUI 0x01
@@ -2033,8 +2092,8 @@ enum ethtool_reset_flags {
* reported consistently by PHYLIB. Read-only.
* @master_slave_cfg: Master/slave port mode.
* @master_slave_state: Master/slave port state.
+ * @rate_matching: Rate adaptation performed by the PHY
* @reserved: Reserved for future use; see the note on reserved space.
- * @reserved1: Reserved for future use; see the note on reserved space.
* @link_mode_masks: Variable length bitmaps.
*
* If autonegotiation is disabled, the speed and @duplex represent the
@@ -2085,7 +2144,7 @@ struct ethtool_link_settings {
uint8_t transceiver;
uint8_t master_slave_cfg;
uint8_t master_slave_state;
- uint8_t reserved1[1];
+ uint8_t rate_matching;
uint32_t reserved[7];
uint32_t link_mode_masks[];
/* layout of link_mode_masks fields:
diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h
index bda06258be..713d259768 100644
--- a/include/standard-headers/linux/fuse.h
+++ b/include/standard-headers/linux/fuse.h
@@ -194,6 +194,9 @@
* - add FUSE_SECURITY_CTX init flag
* - add security context to create, mkdir, symlink, and mknod requests
* - add FUSE_HAS_INODE_DAX, FUSE_ATTR_DAX
+ *
+ * 7.37
+ * - add FUSE_TMPFILE
*/
#ifndef _LINUX_FUSE_H
@@ -225,7 +228,7 @@
#define FUSE_KERNEL_VERSION 7
/** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 36
+#define FUSE_KERNEL_MINOR_VERSION 37
/** The node ID of the root inode */
#define FUSE_ROOT_ID 1
@@ -533,6 +536,7 @@ enum fuse_opcode {
FUSE_SETUPMAPPING = 48,
FUSE_REMOVEMAPPING = 49,
FUSE_SYNCFS = 50,
+ FUSE_TMPFILE = 51,
/* CUSE specific operations */
CUSE_INIT = 4096,
diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h
index 50790aee5a..815f7a1dff 100644
--- a/include/standard-headers/linux/input-event-codes.h
+++ b/include/standard-headers/linux/input-event-codes.h
@@ -862,6 +862,7 @@
#define ABS_TOOL_WIDTH 0x1c
#define ABS_VOLUME 0x20
+#define ABS_PROFILE 0x21
#define ABS_MISC 0x28
diff --git a/include/standard-headers/linux/virtio_blk.h b/include/standard-headers/linux/virtio_blk.h
index 2dcc90826a..e81715cd70 100644
--- a/include/standard-headers/linux/virtio_blk.h
+++ b/include/standard-headers/linux/virtio_blk.h
@@ -40,6 +40,7 @@
#define VIRTIO_BLK_F_MQ 12 /* support more than one vq */
#define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */
#define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */
+#define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */
/* Legacy feature bits */
#ifndef VIRTIO_BLK_NO_LEGACY
@@ -119,6 +120,21 @@ struct virtio_blk_config {
uint8_t write_zeroes_may_unmap;
uint8_t unused1[3];
+
+ /* the next 3 entries are guarded by VIRTIO_BLK_F_SECURE_ERASE */
+ /*
+ * The maximum secure erase sectors (in 512-byte sectors) for
+ * one segment.
+ */
+ __virtio32 max_secure_erase_sectors;
+ /*
+ * The maximum number of secure erase segments in a
+ * secure erase command.
+ */
+ __virtio32 max_secure_erase_seg;
+ /* Secure erase commands must be aligned to this number of sectors. */
+ __virtio32 secure_erase_sector_alignment;
+
} QEMU_PACKED;
/*
@@ -153,6 +169,9 @@ struct virtio_blk_config {
/* Write zeroes command */
#define VIRTIO_BLK_T_WRITE_ZEROES 13
+/* Secure erase command */
+#define VIRTIO_BLK_T_SECURE_ERASE 14
+
#ifndef VIRTIO_BLK_NO_LEGACY
/* Barrier before this op. */
#define VIRTIO_BLK_T_BARRIER 0x80000000
diff --git a/linux-headers/asm-generic/hugetlb_encode.h b/linux-headers/asm-generic/hugetlb_encode.h
index 4f3d5aaa11..de687009bf 100644
--- a/linux-headers/asm-generic/hugetlb_encode.h
+++ b/linux-headers/asm-generic/hugetlb_encode.h
@@ -20,18 +20,18 @@
#define HUGETLB_FLAG_ENCODE_SHIFT 26
#define HUGETLB_FLAG_ENCODE_MASK 0x3f
-#define HUGETLB_FLAG_ENCODE_16KB (14 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_32MB (25 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_512MB (29 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT)
-#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16KB (14U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_64KB (16U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB (19U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB (20U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB (21U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB (23U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB (24U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_32MB (25U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB (28U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512MB (29U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB (30U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB (31U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB (34U << HUGETLB_FLAG_ENCODE_SHIFT)
#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
diff --git a/linux-headers/asm-generic/mman-common.h b/linux-headers/asm-generic/mman-common.h
index 6c1aa92a92..6ce1f1ceb4 100644
--- a/linux-headers/asm-generic/mman-common.h
+++ b/linux-headers/asm-generic/mman-common.h
@@ -77,6 +77,8 @@
#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */
+#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/linux-headers/asm-mips/mman.h b/linux-headers/asm-mips/mman.h
index 1be428663c..c6e1fc77c9 100644
--- a/linux-headers/asm-mips/mman.h
+++ b/linux-headers/asm-mips/mman.h
@@ -103,6 +103,8 @@
#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */
+#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h
index 7351417afd..8985ff234c 100644
--- a/linux-headers/asm-riscv/kvm.h
+++ b/linux-headers/asm-riscv/kvm.h
@@ -48,6 +48,7 @@ struct kvm_sregs {
/* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
struct kvm_riscv_config {
unsigned long isa;
+ unsigned long zicbom_block_size;
};
/* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
@@ -98,6 +99,9 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_M,
KVM_RISCV_ISA_EXT_SVPBMT,
KVM_RISCV_ISA_EXT_SSTC,
+ KVM_RISCV_ISA_EXT_SVINVAL,
+ KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
+ KVM_RISCV_ISA_EXT_ZICBOM,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index ebdafa576d..b2783c5202 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -1175,6 +1175,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
#define KVM_CAP_S390_ZPCI_OP 221
#define KVM_CAP_S390_CPU_TOPOLOGY 222
+#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/linux-headers/linux/psci.h b/linux-headers/linux/psci.h
index 213b2a0f70..e60dfd8907 100644
--- a/linux-headers/linux/psci.h
+++ b/linux-headers/linux/psci.h
@@ -48,12 +48,26 @@
#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7)
#define PSCI_1_0_FN_PSCI_FEATURES PSCI_0_2_FN(10)
+#define PSCI_1_0_FN_CPU_FREEZE PSCI_0_2_FN(11)
+#define PSCI_1_0_FN_CPU_DEFAULT_SUSPEND PSCI_0_2_FN(12)
+#define PSCI_1_0_FN_NODE_HW_STATE PSCI_0_2_FN(13)
#define PSCI_1_0_FN_SYSTEM_SUSPEND PSCI_0_2_FN(14)
#define PSCI_1_0_FN_SET_SUSPEND_MODE PSCI_0_2_FN(15)
+#define PSCI_1_0_FN_STAT_RESIDENCY PSCI_0_2_FN(16)
+#define PSCI_1_0_FN_STAT_COUNT PSCI_0_2_FN(17)
+
#define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18)
+#define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19)
+#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(19)
+#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12)
+#define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13)
#define PSCI_1_0_FN64_SYSTEM_SUSPEND PSCI_0_2_FN64(14)
+#define PSCI_1_0_FN64_STAT_RESIDENCY PSCI_0_2_FN64(16)
+#define PSCI_1_0_FN64_STAT_COUNT PSCI_0_2_FN64(17)
+
#define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18)
+#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(19)
/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h
index a3a377cd44..ba5d0df52f 100644
--- a/linux-headers/linux/userfaultfd.h
+++ b/linux-headers/linux/userfaultfd.h
@@ -12,6 +12,10 @@
#include <linux/types.h>
+/* ioctls for /dev/userfaultfd */
+#define USERFAULTFD_IOC 0xAA
+#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00)
+
/*
* If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
* UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index ede44b5572..bee7e42198 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -986,6 +986,148 @@ enum vfio_device_mig_state {
VFIO_DEVICE_STATE_RUNNING_P2P = 5,
};
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power
+ * state with the platform-based power management. Device use of lower power
+ * states depends on factors managed by the runtime power management core,
+ * including system level support and coordinating support among dependent
+ * devices. Enabling device low power entry does not guarantee lower power
+ * usage by the device, nor is a mechanism provided through this feature to
+ * know the current power state of the device. If any device access happens
+ * (either from the host or through the vfio uAPI) when the device is in the
+ * low power state, then the host will move the device out of the low power
+ * state as necessary prior to the access. Once the access is completed, the
+ * device may re-enter the low power state. For single shot low power support
+ * with wake-up notification, see
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below. Access to mmap'd
+ * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after
+ * calling LOW_POWER_EXIT.
+ */
+#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3
+
+/*
+ * This device feature has the same behavior as
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user
+ * provides an eventfd for wake-up notification. When the device moves out of
+ * the low power state for the wake-up, the host will not allow the device to
+ * re-enter a low power state without a subsequent user call to one of the low
+ * power entry device feature IOCTLs. Access to mmap'd device regions is
+ * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the
+ * low power exit. The low power exit can happen either through LOW_POWER_EXIT
+ * or through any other access (where the wake-up notification has been
+ * generated). The access to mmap'd device regions will not trigger low power
+ * exit.
+ *
+ * The notification through the provided eventfd will be generated only when
+ * the device has entered and is resumed from a low power state after
+ * calling this device feature IOCTL. A device that has not entered low power
+ * state, as managed through the runtime power management core, will not
+ * generate a notification through the provided eventfd on access. Calling the
+ * LOW_POWER_EXIT feature is optional in the case where notification has been
+ * signaled on the provided eventfd that a resume from low power has occurred.
+ */
+struct vfio_device_low_power_entry_with_wakeup {
+ __s32 wakeup_eventfd;
+ __u32 reserved;
+};
+
+#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as
+ * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features.
+ * This device feature IOCTL may itself generate a wakeup eventfd notification
+ * in the latter case if the device had previously entered a low power state.
+ */
+#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging.
+ * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports
+ * DMA logging.
+ *
+ * DMA logging allows a device to internally record what DMAs the device is
+ * initiating and report them back to userspace. It is part of the VFIO
+ * migration infrastructure that allows implementing dirty page tracking
+ * during the pre copy phase of live migration. Only DMA WRITEs are logged,
+ * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE.
+ *
+ * When DMA logging is started a range of IOVAs to monitor is provided and the
+ * device can optimize its logging to cover only the IOVA range given. Each
+ * DMA that the device initiates inside the range will be logged by the device
+ * for later retrieval.
+ *
+ * page_size is an input that hints what tracking granularity the device
+ * should try to achieve. If the device cannot do the hinted page size then
+ * it's the driver choice which page size to pick based on its support.
+ * On output the device will return the page size it selected.
+ *
+ * ranges is a pointer to an array of
+ * struct vfio_device_feature_dma_logging_range.
+ *
+ * The core kernel code guarantees to support by minimum num_ranges that fit
+ * into a single kernel page. User space can try higher values but should give
+ * up if the above can't be achieved as of some driver limitations.
+ *
+ * A single call to start device DMA logging can be issued and a matching stop
+ * should follow at the end. Another start is not allowed in the meantime.
+ */
+struct vfio_device_feature_dma_logging_control {
+ __aligned_u64 page_size;
+ __u32 num_ranges;
+ __u32 __reserved;
+ __aligned_u64 ranges;
+};
+
+struct vfio_device_feature_dma_logging_range {
+ __aligned_u64 iova;
+ __aligned_u64 length;
+};
+
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started
+ * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START
+ */
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log
+ *
+ * Query the device's DMA log for written pages within the given IOVA range.
+ * During querying the log is cleared for the IOVA range.
+ *
+ * bitmap is a pointer to an array of u64s that will hold the output bitmap
+ * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits
+ * is given by:
+ * bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64))
+ *
+ * The input page_size can be any power of two value and does not have to
+ * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver
+ * will format its internal logging to match the reporting page size, possibly
+ * by replicating bits if the internal page size is lower than requested.
+ *
+ * The LOGGING_REPORT will only set bits in the bitmap and never clear or
+ * perform any initialization of the user provided bitmap.
+ *
+ * If any error is returned userspace should assume that the dirty log is
+ * corrupted. Error recovery is to consider all memory dirty and try to
+ * restart the dirty tracking, or to abort/restart the whole migration.
+ *
+ * If DMA logging is not enabled, an error will be returned.
+ *
+ */
+struct vfio_device_feature_dma_logging_report {
+ __aligned_u64 iova;
+ __aligned_u64 length;
+ __aligned_u64 page_size;
+ __aligned_u64 bitmap;
+};
+
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
+
/* -------- API for Type1 VFIO IOMMU -------- */
/**
--
2.31.1

330
SOURCES/kvm-migration-check-magic-value-for-deciding-the-mapping.patch
Unescape View File

@ -0,0 +1,330 @@
From 29eee1fbb84c0e2f0ece9e6d996afa7238ed2912 Mon Sep 17 00:00:00 2001
From: "manish.mishra" <manish.mishra@nutanix.com>
Date: Tue, 20 Dec 2022 18:44:18 +0000
Subject: [PATCH 7/8] migration: check magic value for deciding the mapping of
channels
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 150: migration: Fix multifd crash on channel disorders
RH-Bugzilla: 2169732
RH-Acked-by: quintela1 <quintela@redhat.com>
RH-Acked-by: Leonardo Brás <leobras@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Commit: [2/2] 4fb9408478923415a91fe0527bf4b1a0f022f329 (peterx/qemu-kvm)
Current logic assumes that channel connections on the destination side are
always established in the same order as the source and the first one will
always be the main channel followed by the multifid or post-copy
preemption channel. This may not be always true, as even if a channel has a
connection established on the source side it can be in the pending state on
the destination side and a newer connection can be established first.
Basically causing out of order mapping of channels on the destination side.
Currently, all channels except post-copy preempt send a magic number, this
patch uses that magic number to decide the type of channel. This logic is
applicable only for precopy(multifd) live migration, as mentioned, the
post-copy preempt channel does not send any magic number. Also, tls live
migrations already does tls handshake before creating other channels, so
this issue is not possible with tls, hence this logic is avoided for tls
live migrations. This patch uses read peek to check the magic number of
channels so that current data/control stream management remains
un-effected.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Suggested-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: manish.mishra <manish.mishra@nutanix.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 6720c2b32725e6ac404f22851a0ecd0a71d0cbe2)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
migration/channel.c | 45 +++++++++++++++++++++++++++++++++
migration/channel.h | 5 ++++
migration/migration.c | 54 ++++++++++++++++++++++++++++------------
migration/multifd.c | 19 +++++++-------
migration/multifd.h | 2 +-
migration/postcopy-ram.c | 5 +---
migration/postcopy-ram.h | 2 +-
7 files changed, 101 insertions(+), 31 deletions(-)
diff --git a/migration/channel.c b/migration/channel.c
index 1b0815039f..ca3319a309 100644
--- a/migration/channel.c
+++ b/migration/channel.c
@@ -92,3 +92,48 @@ void migration_channel_connect(MigrationState *s,
migrate_fd_connect(s, error);
error_free(error);
}
+
+
+/**
+ * @migration_channel_read_peek - Peek at migration channel, without
+ * actually removing it from channel buffer.
+ *
+ * @ioc: the channel object
+ * @buf: the memory region to read data into
+ * @buflen: the number of bytes to read in @buf
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Returns 0 if successful, returns -1 and sets @errp if fails.
+ */
+int migration_channel_read_peek(QIOChannel *ioc,
+ const char *buf,
+ const size_t buflen,
+ Error **errp)
+{
+ ssize_t len = 0;
+ struct iovec iov = { .iov_base = (char *)buf, .iov_len = buflen };
+
+ while (true) {
+ len = qio_channel_readv_full(ioc, &iov, 1, NULL, NULL,
+ QIO_CHANNEL_READ_FLAG_MSG_PEEK, errp);
+
+ if (len <= 0 && len != QIO_CHANNEL_ERR_BLOCK) {
+ error_setg(errp,
+ "Failed to peek at channel");
+ return -1;
+ }
+
+ if (len == buflen) {
+ break;
+ }
+
+ /* 1ms sleep. */
+ if (qemu_in_coroutine()) {
+ qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000);
+ } else {
+ g_usleep(1000);
+ }
+ }
+
+ return 0;
+}
diff --git a/migration/channel.h b/migration/channel.h
index 67a461c28a..5bdb8208a7 100644
--- a/migration/channel.h
+++ b/migration/channel.h
@@ -24,4 +24,9 @@ void migration_channel_connect(MigrationState *s,
QIOChannel *ioc,
const char *hostname,
Error *error_in);
+
+int migration_channel_read_peek(QIOChannel *ioc,
+ const char *buf,
+ const size_t buflen,
+ Error **errp);
#endif
diff --git a/migration/migration.c b/migration/migration.c
index f485eea5fb..593dbd25de 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -31,6 +31,7 @@
#include "migration.h"
#include "savevm.h"
#include "qemu-file.h"
+#include "channel.h"
#include "migration/vmstate.h"
#include "block/block.h"
#include "qapi/error.h"
@@ -663,10 +664,6 @@ static bool migration_incoming_setup(QEMUFile *f, Error **errp)
{
MigrationIncomingState *mis = migration_incoming_get_current();
- if (multifd_load_setup(errp) != 0) {
- return false;
- }
-
if (!mis->from_src_file) {
mis->from_src_file = f;
}
@@ -733,31 +730,56 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
{
MigrationIncomingState *mis = migration_incoming_get_current();
Error *local_err = NULL;
- bool start_migration;
QEMUFile *f;
+ bool default_channel = true;
+ uint32_t channel_magic = 0;
+ int ret = 0;
- if (!mis->from_src_file) {
- /* The first connection (multifd may have multiple) */
+ if (migrate_use_multifd() && !migrate_postcopy_ram() &&
+ qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
+ /*
+ * With multiple channels, it is possible that we receive channels
+ * out of order on destination side, causing incorrect mapping of
+ * source channels on destination side. Check channel MAGIC to
+ * decide type of channel. Please note this is best effort, postcopy
+ * preempt channel does not send any magic number so avoid it for
+ * postcopy live migration. Also tls live migration already does
+ * tls handshake while initializing main channel so with tls this
+ * issue is not possible.
+ */
+ ret = migration_channel_read_peek(ioc, (void *)&channel_magic,
+ sizeof(channel_magic), &local_err);
+
+ if (ret != 0) {
+ error_propagate(errp, local_err);
+ return;
+ }
+
+ default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC));
+ } else {
+ default_channel = !mis->from_src_file;
+ }
+
+ if (multifd_load_setup(errp) != 0) {
+ error_setg(errp, "Failed to setup multifd channels");
+ return;
+ }
+
+ if (default_channel) {
f = qemu_file_new_input(ioc);
if (!migration_incoming_setup(f, errp)) {
return;
}
-
- /*
- * Common migration only needs one channel, so we can start
- * right now. Some features need more than one channel, we wait.
- */
- start_migration = !migration_needs_multiple_sockets();
} else {
/* Multiple connections */
assert(migration_needs_multiple_sockets());
if (migrate_use_multifd()) {
- start_migration = multifd_recv_new_channel(ioc, &local_err);
+ multifd_recv_new_channel(ioc, &local_err);
} else {
assert(migrate_postcopy_preempt());
f = qemu_file_new_input(ioc);
- start_migration = postcopy_preempt_new_channel(mis, f);
+ postcopy_preempt_new_channel(mis, f);
}
if (local_err) {
error_propagate(errp, local_err);
@@ -765,7 +787,7 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
}
}
- if (start_migration) {
+ if (migration_has_all_channels()) {
/* If it's a recovery, we're done */
if (postcopy_try_recover()) {
return;
diff --git a/migration/multifd.c b/migration/multifd.c
index 509bbbe3bf..c3385529cf 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -1167,9 +1167,14 @@ int multifd_load_setup(Error **errp)
uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
uint8_t i;
- if (!migrate_use_multifd()) {
+ /*
+ * Return successfully if multiFD recv state is already initialised
+ * or multiFD is not enabled.
+ */
+ if (multifd_recv_state || !migrate_use_multifd()) {
return 0;
}
+
if (!migrate_multi_channels_is_allowed()) {
error_setg(errp, "multifd is not supported by current protocol");
return -1;
@@ -1228,11 +1233,9 @@ bool multifd_recv_all_channels_created(void)
/*
* Try to receive all multifd channels to get ready for the migration.
- * - Return true and do not set @errp when correctly receiving all channels;
- * - Return false and do not set @errp when correctly receiving the current one;
- * - Return false and set @errp when failing to receive the current channel.
+ * Sets @errp when failing to receive the current channel.
*/
-bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
+void multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
{
MultiFDRecvParams *p;
Error *local_err = NULL;
@@ -1245,7 +1248,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
"failed to receive packet"
" via multifd channel %d: ",
qatomic_read(&multifd_recv_state->count));
- return false;
+ return;
}
trace_multifd_recv_new_channel(id);
@@ -1255,7 +1258,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
id);
multifd_recv_terminate_threads(local_err);
error_propagate(errp, local_err);
- return false;
+ return;
}
p->c = ioc;
object_ref(OBJECT(ioc));
@@ -1266,6 +1269,4 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
QEMU_THREAD_JOINABLE);
qatomic_inc(&multifd_recv_state->count);
- return qatomic_read(&multifd_recv_state->count) ==
- migrate_multifd_channels();
}
diff --git a/migration/multifd.h b/migration/multifd.h
index 519f498643..913e4ba274 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -18,7 +18,7 @@ void multifd_save_cleanup(void);
int multifd_load_setup(Error **errp);
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_new_channel(QIOChannel *ioc, Error **errp);
void multifd_recv_sync_main(void);
int multifd_send_sync_main(QEMUFile *f);
int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 0c55df0e52..b98e95dab0 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -1538,7 +1538,7 @@ void postcopy_unregister_shared_ufd(struct PostCopyFD *pcfd)
}
}
-bool postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file)
+void postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file)
{
/*
* The new loading channel has its own threads, so it needs to be
@@ -1547,9 +1547,6 @@ bool postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file)
qemu_file_set_blocking(file, true);
mis->postcopy_qemufile_dst = file;
trace_postcopy_preempt_new_channel();
-
- /* Start the migration immediately */
- return true;
}
/*
diff --git a/migration/postcopy-ram.h b/migration/postcopy-ram.h
index 6147bf7d1d..25881c4127 100644
--- a/migration/postcopy-ram.h
+++ b/migration/postcopy-ram.h
@@ -190,7 +190,7 @@ enum PostcopyChannels {
RAM_CHANNEL_MAX,
};
-bool postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file);
+void postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file);
int postcopy_preempt_setup(MigrationState *s, Error **errp);
int postcopy_preempt_wait_channel(MigrationState *s);
--
2.31.1

325
SOURCES/kvm-net-stream-add-a-new-option-to-automatically-reconne.patch
Unescape View File

@ -0,0 +1,325 @@
From e5834364958a3914d7b8b46b985a1b054728b466 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Thu, 19 Jan 2023 11:16:45 +0100
Subject: [PATCH 2/8] net: stream: add a new option to automatically reconnect
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 148: net: stream: add a new option to automatically reconnect
RH-Bugzilla: 2169232
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: David Gibson (Red Hat) <dgibson@redhat.com>
RH-Commit: [2/2] 9b87647a9ed2e7c1b91bdfa9d0a736e091c892a5 (lvivier/qemu-kvm-centos)
In stream mode, if the server shuts down there is currently
no way to reconnect the client to a new server without removing
the NIC device and the netdev backend (or to reboot).
This patch introduces a reconnect option that specifies a delay
to try to reconnect with the same parameters.
Add a new test in qtest to test the reconnect option and the
connect/disconnect events.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit b95c0d4440950fba6dbef0f781962911fa42abdb)
---
net/stream.c | 53 ++++++++++++++++++-
qapi/net.json | 7 ++-
qemu-options.hx | 6 +--
tests/qtest/netdev-socket.c | 101 ++++++++++++++++++++++++++++++++++++
4 files changed, 162 insertions(+), 5 deletions(-)
diff --git a/net/stream.c b/net/stream.c
index 37ff727e0c..9204b4c96e 100644
--- a/net/stream.c
+++ b/net/stream.c
@@ -39,6 +39,8 @@
#include "io/channel-socket.h"
#include "io/net-listener.h"
#include "qapi/qapi-events-net.h"
+#include "qapi/qapi-visit-sockets.h"
+#include "qapi/clone-visitor.h"
typedef struct NetStreamState {
NetClientState nc;
@@ -49,11 +51,15 @@ typedef struct NetStreamState {
guint ioc_write_tag;
SocketReadState rs;
unsigned int send_index; /* number of bytes sent*/
+ uint32_t reconnect;
+ guint timer_tag;
+ SocketAddress *addr;
} NetStreamState;
static void net_stream_listen(QIONetListener *listener,
QIOChannelSocket *cioc,
void *opaque);
+static void net_stream_arm_reconnect(NetStreamState *s);
static gboolean net_stream_writable(QIOChannel *ioc,
GIOCondition condition,
@@ -170,6 +176,7 @@ static gboolean net_stream_send(QIOChannel *ioc,
qemu_set_info_str(&s->nc, "%s", "");
qapi_event_send_netdev_stream_disconnected(s->nc.name);
+ net_stream_arm_reconnect(s);
return G_SOURCE_REMOVE;
}
@@ -187,6 +194,14 @@ static gboolean net_stream_send(QIOChannel *ioc,
static void net_stream_cleanup(NetClientState *nc)
{
NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc);
+ if (s->timer_tag) {
+ g_source_remove(s->timer_tag);
+ s->timer_tag = 0;
+ }
+ if (s->addr) {
+ qapi_free_SocketAddress(s->addr);
+ s->addr = NULL;
+ }
if (s->ioc) {
if (QIO_CHANNEL_SOCKET(s->ioc)->fd != -1) {
if (s->ioc_read_tag) {
@@ -346,12 +361,37 @@ static void net_stream_client_connected(QIOTask *task, gpointer opaque)
error:
object_unref(OBJECT(s->ioc));
s->ioc = NULL;
+ net_stream_arm_reconnect(s);
+}
+
+static gboolean net_stream_reconnect(gpointer data)
+{
+ NetStreamState *s = data;
+ QIOChannelSocket *sioc;
+
+ s->timer_tag = 0;
+
+ sioc = qio_channel_socket_new();
+ s->ioc = QIO_CHANNEL(sioc);
+ qio_channel_socket_connect_async(sioc, s->addr,
+ net_stream_client_connected, s,
+ NULL, NULL);
+ return G_SOURCE_REMOVE;
+}
+
+static void net_stream_arm_reconnect(NetStreamState *s)
+{
+ if (s->reconnect && s->timer_tag == 0) {
+ s->timer_tag = g_timeout_add_seconds(s->reconnect,
+ net_stream_reconnect, s);
+ }
}
static int net_stream_client_init(NetClientState *peer,
const char *model,
const char *name,
SocketAddress *addr,
+ uint32_t reconnect,
Error **errp)
{
NetStreamState *s;
@@ -364,6 +404,10 @@ static int net_stream_client_init(NetClientState *peer,
s->ioc = QIO_CHANNEL(sioc);
s->nc.link_down = true;
+ s->reconnect = reconnect;
+ if (reconnect) {
+ s->addr = QAPI_CLONE(SocketAddress, addr);
+ }
qio_channel_socket_connect_async(sioc, addr,
net_stream_client_connected, s,
NULL, NULL);
@@ -380,7 +424,14 @@ int net_init_stream(const Netdev *netdev, const char *name,
sock = &netdev->u.stream;
if (!sock->has_server || !sock->server) {
- return net_stream_client_init(peer, "stream", name, sock->addr, errp);
+ return net_stream_client_init(peer, "stream", name, sock->addr,
+ sock->has_reconnect ? sock->reconnect : 0,
+ errp);
+ }
+ if (sock->has_reconnect) {
+ error_setg(errp, "'reconnect' option is incompatible with "
+ "socket in server mode");
+ return -1;
}
return net_stream_server_init(peer, "stream", name, sock->addr, errp);
}
diff --git a/qapi/net.json b/qapi/net.json
index 522ac582ed..d6eb30008b 100644
--- a/qapi/net.json
+++ b/qapi/net.json
@@ -585,6 +585,10 @@
# @addr: socket address to listen on (server=true)
# or connect to (server=false)
# @server: create server socket (default: false)
+# @reconnect: For a client socket, if a socket is disconnected,
+# then attempt a reconnect after the given number of seconds.
+# Setting this to zero disables this function. (default: 0)
+# (since 8.0)
#
# Only SocketAddress types 'unix', 'inet' and 'fd' are supported.
#
@@ -593,7 +597,8 @@
{ 'struct': 'NetdevStreamOptions',
'data': {
'addr': 'SocketAddress',
- '*server': 'bool' } }
+ '*server': 'bool',
+ '*reconnect': 'uint32' } }
##
# @NetdevDgramOptions:
diff --git a/qemu-options.hx b/qemu-options.hx
index ea02ca3a45..48eef4aa2c 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -2766,9 +2766,9 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
"-netdev socket,id=str[,fd=h][,udp=host:port][,localaddr=host:port]\n"
" configure a network backend to connect to another network\n"
" using an UDP tunnel\n"
- "-netdev stream,id=str[,server=on|off],addr.type=inet,addr.host=host,addr.port=port[,to=maxport][,numeric=on|off][,keep-alive=on|off][,mptcp=on|off][,addr.ipv4=on|off][,addr.ipv6=on|off]\n"
- "-netdev stream,id=str[,server=on|off],addr.type=unix,addr.path=path[,abstract=on|off][,tight=on|off]\n"
- "-netdev stream,id=str[,server=on|off],addr.type=fd,addr.str=file-descriptor\n"
+ "-netdev stream,id=str[,server=on|off],addr.type=inet,addr.host=host,addr.port=port[,to=maxport][,numeric=on|off][,keep-alive=on|off][,mptcp=on|off][,addr.ipv4=on|off][,addr.ipv6=on|off][,reconnect=seconds]\n"
+ "-netdev stream,id=str[,server=on|off],addr.type=unix,addr.path=path[,abstract=on|off][,tight=on|off][,reconnect=seconds]\n"
+ "-netdev stream,id=str[,server=on|off],addr.type=fd,addr.str=file-descriptor[,reconnect=seconds]\n"
" configure a network backend to connect to another network\n"
" using a socket connection in stream mode.\n"
"-netdev dgram,id=str,remote.type=inet,remote.host=maddr,remote.port=port[,local.type=inet,local.host=addr]\n"
diff --git a/tests/qtest/netdev-socket.c b/tests/qtest/netdev-socket.c
index 6ba256e173..acc32c378b 100644
--- a/tests/qtest/netdev-socket.c
+++ b/tests/qtest/netdev-socket.c
@@ -11,6 +11,10 @@
#include <glib/gstdio.h>
#include "../unit/socket-helpers.h"
#include "libqtest.h"
+#include "qapi/qmp/qstring.h"
+#include "qemu/sockets.h"
+#include "qapi/qobject-input-visitor.h"
+#include "qapi/qapi-visit-sockets.h"
#define CONNECTION_TIMEOUT 5
@@ -142,6 +146,101 @@ static void test_stream_inet_ipv4(void)
qtest_quit(qts0);
}
+static void wait_stream_connected(QTestState *qts, const char *id,
+ SocketAddress **addr)
+{
+ QDict *resp, *data;
+ QString *qstr;
+ QObject *obj;
+ Visitor *v = NULL;
+
+ resp = qtest_qmp_eventwait_ref(qts, "NETDEV_STREAM_CONNECTED");
+ g_assert_nonnull(resp);
+ data = qdict_get_qdict(resp, "data");
+ g_assert_nonnull(data);
+
+ qstr = qobject_to(QString, qdict_get(data, "netdev-id"));
+ g_assert_nonnull(data);
+
+ g_assert(!strcmp(qstring_get_str(qstr), id));
+
+ obj = qdict_get(data, "addr");
+
+ v = qobject_input_visitor_new(obj);
+ visit_type_SocketAddress(v, NULL, addr, NULL);
+ visit_free(v);
+ qobject_unref(resp);
+}
+
+static void wait_stream_disconnected(QTestState *qts, const char *id)
+{
+ QDict *resp, *data;
+ QString *qstr;
+
+ resp = qtest_qmp_eventwait_ref(qts, "NETDEV_STREAM_DISCONNECTED");
+ g_assert_nonnull(resp);
+ data = qdict_get_qdict(resp, "data");
+ g_assert_nonnull(data);
+
+ qstr = qobject_to(QString, qdict_get(data, "netdev-id"));
+ g_assert_nonnull(data);
+
+ g_assert(!strcmp(qstring_get_str(qstr), id));
+ qobject_unref(resp);
+}
+
+static void test_stream_inet_reconnect(void)
+{
+ QTestState *qts0, *qts1;
+ int port;
+ SocketAddress *addr;
+
+ port = inet_get_free_port(false);
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=true,addr.type=inet,"
+ "addr.ipv4=on,addr.ipv6=off,"
+ "addr.host=127.0.0.1,addr.port=%d", port);
+
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,\r\n", 0);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,server=false,id=st0,addr.type=inet,"
+ "addr.ipv4=on,addr.ipv6=off,reconnect=1,"
+ "addr.host=127.0.0.1,addr.port=%d", port);
+
+ wait_stream_connected(qts0, "st0", &addr);
+ g_assert_cmpint(addr->type, ==, SOCKET_ADDRESS_TYPE_INET);
+ g_assert_cmpstr(addr->u.inet.host, ==, "127.0.0.1");
+ qapi_free_SocketAddress(addr);
+
+ /* kill server */
+ qtest_quit(qts0);
+
+ /* check client has been disconnected */
+ wait_stream_disconnected(qts1, "st0");
+
+ /* restart server */
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=true,addr.type=inet,"
+ "addr.ipv4=on,addr.ipv6=off,"
+ "addr.host=127.0.0.1,addr.port=%d", port);
+
+ /* wait connection events*/
+ wait_stream_connected(qts0, "st0", &addr);
+ g_assert_cmpint(addr->type, ==, SOCKET_ADDRESS_TYPE_INET);
+ g_assert_cmpstr(addr->u.inet.host, ==, "127.0.0.1");
+ qapi_free_SocketAddress(addr);
+
+ wait_stream_connected(qts1, "st0", &addr);
+ g_assert_cmpint(addr->type, ==, SOCKET_ADDRESS_TYPE_INET);
+ g_assert_cmpstr(addr->u.inet.host, ==, "127.0.0.1");
+ g_assert_cmpint(atoi(addr->u.inet.port), ==, port);
+ qapi_free_SocketAddress(addr);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+
static void test_stream_inet_ipv6(void)
{
QTestState *qts0, *qts1;
@@ -418,6 +517,8 @@ int main(int argc, char **argv)
#ifndef _WIN32
qtest_add_func("/netdev/dgram/mcast", test_dgram_mcast);
#endif
+ qtest_add_func("/netdev/stream/inet/reconnect",
+ test_stream_inet_reconnect);
}
if (has_ipv6) {
qtest_add_func("/netdev/stream/inet/ipv6", test_stream_inet_ipv6);
--
2.31.1

67
SOURCES/kvm-qcow2-Fix-theoretical-corruption-in-store_bitmap-err.patch
Unescape View File

@ -0,0 +1,67 @@
From 46ead2c391924b68741d6da28f28f909b80f5914 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 12 Jan 2023 20:14:51 +0100
Subject: [PATCH 01/20] qcow2: Fix theoretical corruption in store_bitmap()
error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 143: qemu-img: Fix exit code for errors closing the image
RH-Bugzilla: 2150180
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [1/4] a6a497947179431567d330d0501247a3749fb9fd (kmwolf/centos-qemu-kvm)
In order to write the bitmap table to the image file, it is converted to
big endian. If the write fails, it is passed to clear_bitmap_table() to
free all of the clusters it had allocated before. However, if we don't
convert it back to native endianness first, we'll free things at a wrong
offset.
In practical terms, the offsets will be so high that we won't actually
free any allocated clusters, but just run into an error, but in theory
this can cause image corruption.
Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230112191454.169353-2-kwolf@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit b03dd9613bcf8fe948581b2b3585510cb525c382)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/qcow2-bitmap.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c
index bcad567c0c..3dff99ba06 100644
--- a/block/qcow2-bitmap.c
+++ b/block/qcow2-bitmap.c
@@ -115,7 +115,7 @@ static int update_header_sync(BlockDriverState *bs)
return bdrv_flush(bs->file->bs);
}
-static inline void bitmap_table_to_be(uint64_t *bitmap_table, size_t size)
+static inline void bitmap_table_bswap_be(uint64_t *bitmap_table, size_t size)
{
size_t i;
@@ -1401,9 +1401,10 @@ static int store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp)
goto fail;
}
- bitmap_table_to_be(tb, tb_size);
+ bitmap_table_bswap_be(tb, tb_size);
ret = bdrv_pwrite(bs->file, tb_offset, tb_size * sizeof(tb[0]), tb, 0);
if (ret < 0) {
+ bitmap_table_bswap_be(tb, tb_size);
error_setg_errno(errp, -ret, "Failed to write bitmap '%s' to file",
bm_name);
goto fail;
--
2.31.1

84
SOURCES/kvm-qed-Don-t-yield-in-bdrv_qed_co_drain_begin.patch
Unescape View File

@ -0,0 +1,84 @@
From f628a08d20b9ab6be24c2ab18b38a934a314c78b Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:40:56 +0100
Subject: [PATCH 14/31] qed: Don't yield in bdrv_qed_co_drain_begin()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [2/16] f18e9aebb7e04a62e309b656bac8f2ab83df657f (sgarzarella/qemu-kvm-c-9-s)
We want to change .bdrv_co_drained_begin() back to be a non-coroutine
callback, so in preparation, avoid yielding in its implementation.
Because we increase bs->in_flight and bdrv_drained_begin() polls, the
behaviour is unchanged.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-2-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6d47eb0c8bf2d50682c7dccae74d24104076fe23)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block/qed.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/block/qed.c b/block/qed.c
index 2f36ad342c..013f826c44 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -282,9 +282,8 @@ static void coroutine_fn qed_unplug_allocating_write_reqs(BDRVQEDState *s)
qemu_co_mutex_unlock(&s->table_lock);
}
-static void coroutine_fn qed_need_check_timer_entry(void *opaque)
+static void coroutine_fn qed_need_check_timer(BDRVQEDState *s)
{
- BDRVQEDState *s = opaque;
int ret;
trace_qed_need_check_timer_cb(s);
@@ -310,9 +309,20 @@ static void coroutine_fn qed_need_check_timer_entry(void *opaque)
(void) ret;
}
+static void coroutine_fn qed_need_check_timer_entry(void *opaque)
+{
+ BDRVQEDState *s = opaque;
+
+ qed_need_check_timer(opaque);
+ bdrv_dec_in_flight(s->bs);
+}
+
static void qed_need_check_timer_cb(void *opaque)
{
+ BDRVQEDState *s = opaque;
Coroutine *co = qemu_coroutine_create(qed_need_check_timer_entry, opaque);
+
+ bdrv_inc_in_flight(s->bs);
qemu_coroutine_enter(co);
}
@@ -363,8 +373,12 @@ static void coroutine_fn bdrv_qed_co_drain_begin(BlockDriverState *bs)
* header is flushed.
*/
if (s->need_check_timer && timer_pending(s->need_check_timer)) {
+ Coroutine *co;
+
qed_cancel_need_check_timer(s);
- qed_need_check_timer_entry(s);
+ co = qemu_coroutine_create(qed_need_check_timer_entry, s);
+ bdrv_inc_in_flight(bs);
+ aio_co_enter(bdrv_get_aio_context(bs), co);
}
}
--
2.31.1

197
SOURCES/kvm-qemu-img-Change-info-key-names-for-protocol-nodes.patch
Unescape View File

@ -0,0 +1,197 @@
From b1970c733dc46b2a8f648997a7e1c5d12900ff54 Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:04 +0200
Subject: [PATCH 17/20] qemu-img: Change info key names for protocol nodes
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [12/12] 67c260aaa05466410503fecee6210bf9d47e8c7c (hreitz/qemu-kvm-c-9-s)
Currently, when querying a qcow2 image, qemu-img info reports something
like this:
image: test.qcow2
file format: qcow2
virtual size: 64 MiB (67108864 bytes)
disk size: 196 KiB
cluster_size: 65536
Format specific information:
compat: 1.1
compression type: zlib
lazy refcounts: false
refcount bits: 16
corrupt: false
extended l2: false
Child node '/file':
image: test.qcow2
file format: file
virtual size: 192 KiB (197120 bytes)
disk size: 196 KiB
Format specific information:
extent size hint: 1048576
Notably, the way the keys are named is specific for image files: The
filename is shown under "image", the BDS driver under "file format", and
the BDS length under "virtual size". This does not make much sense for
nodes that are not actually supposed to be guest images, like the /file
child node shown above.
Give bdrv_node_info_dump() a @protocol parameter that gives a hint that
the respective node is probably just used for data storage and does not
necessarily present the data for a VM guest disk. This renames the keys
so that with this patch, the output becomes:
image: test.qcow2
[...]
Child node '/file':
filename: test.qcow2
protocol type: file
file length: 192 KiB (197120 bytes)
disk size: 196 KiB
Format specific information:
extent size hint: 1048576
(Perhaps we should also rename "Format specific information", but I
could not come up with anything better that will not become problematic
if we guess wrong with the protocol "heuristic".)
This change affects iotest 302, which has protocol node information in
its reference output.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-13-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit d570177b50c389f379f93183155a27d44856ab46)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/monitor/block-hmp-cmds.c | 2 +-
block/qapi.c | 39 ++++++++++++++++++++++++++++------
include/block/qapi.h | 2 +-
qemu-img.c | 3 ++-
tests/qemu-iotests/302.out | 6 +++---
5 files changed, 39 insertions(+), 13 deletions(-)
diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index 72824d4e2e..4d83339a5d 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -734,7 +734,7 @@ static void print_block_info(Monitor *mon, BlockInfo *info,
monitor_printf(mon, "\nImages:\n");
image_info = inserted->image;
while (1) {
- bdrv_node_info_dump(qapi_ImageInfo_base(image_info), 0);
+ bdrv_node_info_dump(qapi_ImageInfo_base(image_info), 0, false);
if (image_info->has_backing_image) {
image_info = image_info->backing_image;
} else {
diff --git a/block/qapi.c b/block/qapi.c
index 3e35603f0c..56f398c500 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -934,24 +934,49 @@ void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
visit_free(v);
}
-void bdrv_node_info_dump(BlockNodeInfo *info, int indentation)
+/**
+ * Print the given @info object in human-readable form. Every field is indented
+ * using the given @indentation (four spaces per indentation level).
+ *
+ * When using this to print a whole block graph, @protocol can be set to true to
+ * signify that the given information is associated with a protocol node, i.e.
+ * just data storage for an image, such that the data it presents is not really
+ * a full VM disk. If so, several fields change name: For example, "virtual
+ * size" is printed as "file length".
+ * (Consider a qcow2 image, which is represented by a qcow2 node and a file
+ * node. Printing a "virtual size" for the file node does not make sense,
+ * because without the qcow2 node, it is not really a guest disk, so it does not
+ * have a "virtual size". Therefore, we call it "file length" instead.)
+ *
+ * @protocol is ignored when @indentation is 0, because we take that to mean
+ * that the associated node is the root node in the queried block graph, and
+ * thus is always to be interpreted as a standalone guest disk.
+ */
+void bdrv_node_info_dump(BlockNodeInfo *info, int indentation, bool protocol)
{
char *size_buf, *dsize_buf;
g_autofree char *ind_s = g_strdup_printf("%*s", indentation * 4, "");
+ if (indentation == 0) {
+ /* Top level, consider this a normal image */
+ protocol = false;
+ }
+
if (!info->has_actual_size) {
dsize_buf = g_strdup("unavailable");
} else {
dsize_buf = size_to_str(info->actual_size);
}
size_buf = size_to_str(info->virtual_size);
- qemu_printf("%simage: %s\n"
- "%sfile format: %s\n"
- "%svirtual size: %s (%" PRId64 " bytes)\n"
+ qemu_printf("%s%s: %s\n"
+ "%s%s: %s\n"
+ "%s%s: %s (%" PRId64 " bytes)\n"
"%sdisk size: %s\n",
- ind_s, info->filename,
- ind_s, info->format,
- ind_s, size_buf, info->virtual_size,
+ ind_s, protocol ? "filename" : "image", info->filename,
+ ind_s, protocol ? "protocol type" : "file format",
+ info->format,
+ ind_s, protocol ? "file length" : "virtual size",
+ size_buf, info->virtual_size,
ind_s, dsize_buf);
g_free(size_buf);
g_free(dsize_buf);
diff --git a/include/block/qapi.h b/include/block/qapi.h
index 38855f2ae9..26113da21a 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -51,5 +51,5 @@ void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
const char *prefix,
int indentation);
-void bdrv_node_info_dump(BlockNodeInfo *info, int indentation);
+void bdrv_node_info_dump(BlockNodeInfo *info, int indentation, bool protocol);
#endif
diff --git a/qemu-img.c b/qemu-img.c
index e281011245..2943625c67 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -2853,7 +2853,8 @@ static void dump_human_image_info(BlockGraphInfo *info, int indentation,
{
BlockChildInfoList *children_list;
- bdrv_node_info_dump(qapi_BlockGraphInfo_base(info), indentation);
+ bdrv_node_info_dump(qapi_BlockGraphInfo_base(info), indentation,
+ info->children == NULL);
for (children_list = info->children; children_list;
children_list = children_list->next)
diff --git a/tests/qemu-iotests/302.out b/tests/qemu-iotests/302.out
index edfa1c4f05..7b5014cdd8 100644
--- a/tests/qemu-iotests/302.out
+++ b/tests/qemu-iotests/302.out
@@ -5,9 +5,9 @@ file format: raw
virtual size: 448 KiB (458752 bytes)
disk size: unavailable
Child node '/file':
- image: nbd+unix:///exp?socket=SOCK_DIR/PID-nbd-sock
- file format: nbd
- virtual size: 448 KiB (458752 bytes)
+ filename: nbd+unix:///exp?socket=SOCK_DIR/PID-nbd-sock
+ protocol type: nbd
+ file length: 448 KiB (458752 bytes)
disk size: unavailable
=== Converted image info ===
--
2.31.1

261
SOURCES/kvm-qemu-img-Let-info-print-block-graph.patch
Unescape View File

@ -0,0 +1,261 @@
From ea73e9de42b446ce1049805c23f7706e4f87ed1f Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:27:03 +0200
Subject: [PATCH 16/20] qemu-img: Let info print block graph
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [11/12] 2c1b8a03c918484449e876acf4c6663766848ad8 (hreitz/qemu-kvm-c-9-s)
For every node in the backing chain, collect its BlockGraphInfo struct
using bdrv_query_block_graph_info(). Print all nodes' information,
indenting child nodes and labelling them with a path constructed from
the child names leading to the node from the root (e.g. /file/file).
Note that we open each image with BDRV_O_NO_BACKING, so its backing
child is omitted from this graph, and thus presented in the previous
manner: By simply concatenating all images' information, separated with
blank lines.
This affects two iotests:
- 065: Here we try to get the format node's format specific information.
The pre-patch code does so by taking all lines from "Format specific
information:" until an empty line. This format specific information
is no longer followed by an empty line, though, but by child node
information, so limit the range by "Child node '/file':".
- 302: Calls qemu_img() for qemu-img info directly, which does not
filter the output, so the child node information ends up in the
output.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-12-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c04d0ab026201d21873a63f768cb69c4554dfec1)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
qapi/block-core.json | 4 +--
qemu-img.c | 69 ++++++++++++++++++++++++++------------
tests/qemu-iotests/065 | 2 +-
tests/qemu-iotests/302.out | 5 +++
4 files changed, 56 insertions(+), 24 deletions(-)
diff --git a/qapi/block-core.json b/qapi/block-core.json
index d703e0fb16..7f331eb8ea 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -5831,9 +5831,9 @@
##
# @DummyBlockCoreForceArrays:
#
-# Not used by QMP; hack to let us use BlockNodeInfoList internally
+# Not used by QMP; hack to let us use BlockGraphInfoList internally
#
# Since: 8.0
##
{ 'struct': 'DummyBlockCoreForceArrays',
- 'data': { 'unused-block-node-info': ['BlockNodeInfo'] } }
+ 'data': { 'unused-block-graph-info': ['BlockGraphInfo'] } }
diff --git a/qemu-img.c b/qemu-img.c
index 30b4ea58bb..e281011245 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -2816,13 +2816,13 @@ static void dump_snapshots(BlockDriverState *bs)
g_free(sn_tab);
}
-static void dump_json_block_node_info_list(BlockNodeInfoList *list)
+static void dump_json_block_graph_info_list(BlockGraphInfoList *list)
{
GString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
- visit_type_BlockNodeInfoList(v, NULL, &list, &error_abort);
+ visit_type_BlockGraphInfoList(v, NULL, &list, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj, true);
assert(str != NULL);
@@ -2832,13 +2832,13 @@ static void dump_json_block_node_info_list(BlockNodeInfoList *list)
g_string_free(str, true);
}
-static void dump_json_block_node_info(BlockNodeInfo *info)
+static void dump_json_block_graph_info(BlockGraphInfo *info)
{
GString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
- visit_type_BlockNodeInfo(v, NULL, &info, &error_abort);
+ visit_type_BlockGraphInfo(v, NULL, &info, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj, true);
assert(str != NULL);
@@ -2848,9 +2848,29 @@ static void dump_json_block_node_info(BlockNodeInfo *info)
g_string_free(str, true);
}
-static void dump_human_image_info_list(BlockNodeInfoList *list)
+static void dump_human_image_info(BlockGraphInfo *info, int indentation,
+ const char *path)
{
- BlockNodeInfoList *elem;
+ BlockChildInfoList *children_list;
+
+ bdrv_node_info_dump(qapi_BlockGraphInfo_base(info), indentation);
+
+ for (children_list = info->children; children_list;
+ children_list = children_list->next)
+ {
+ BlockChildInfo *child = children_list->value;
+ g_autofree char *child_path = NULL;
+
+ printf("%*sChild node '%s%s':\n",
+ indentation * 4, "", path, child->name);
+ child_path = g_strdup_printf("%s%s/", path, child->name);
+ dump_human_image_info(child->info, indentation + 1, child_path);
+ }
+}
+
+static void dump_human_image_info_list(BlockGraphInfoList *list)
+{
+ BlockGraphInfoList *elem;
bool delim = false;
for (elem = list; elem; elem = elem->next) {
@@ -2859,7 +2879,7 @@ static void dump_human_image_info_list(BlockNodeInfoList *list)
}
delim = true;
- bdrv_node_info_dump(elem->value, 0);
+ dump_human_image_info(elem->value, 0, "/");
}
}
@@ -2869,7 +2889,7 @@ static gboolean str_equal_func(gconstpointer a, gconstpointer b)
}
/**
- * Open an image file chain and return an BlockNodeInfoList
+ * Open an image file chain and return an BlockGraphInfoList
*
* @filename: topmost image filename
* @fmt: topmost image format (may be NULL to autodetect)
@@ -2880,13 +2900,13 @@ static gboolean str_equal_func(gconstpointer a, gconstpointer b)
* opening an image file. If there was an error a message will have been
* printed to stderr.
*/
-static BlockNodeInfoList *collect_image_info_list(bool image_opts,
- const char *filename,
- const char *fmt,
- bool chain, bool force_share)
+static BlockGraphInfoList *collect_image_info_list(bool image_opts,
+ const char *filename,
+ const char *fmt,
+ bool chain, bool force_share)
{
- BlockNodeInfoList *head = NULL;
- BlockNodeInfoList **tail = &head;
+ BlockGraphInfoList *head = NULL;
+ BlockGraphInfoList **tail = &head;
GHashTable *filenames;
Error *err = NULL;
@@ -2895,7 +2915,7 @@ static BlockNodeInfoList *collect_image_info_list(bool image_opts,
while (filename) {
BlockBackend *blk;
BlockDriverState *bs;
- BlockNodeInfo *info;
+ BlockGraphInfo *info;
if (g_hash_table_lookup_extended(filenames, filename, NULL, NULL)) {
error_report("Backing file '%s' creates an infinite loop.",
@@ -2912,7 +2932,14 @@ static BlockNodeInfoList *collect_image_info_list(bool image_opts,
}
bs = blk_bs(blk);
- bdrv_query_block_node_info(bs, &info, &err);
+ /*
+ * Note that the returned BlockGraphInfo object will not have
+ * information about this image's backing node, because we have opened
+ * it with BDRV_O_NO_BACKING. Printing this object will therefore not
+ * duplicate the backing chain information that we obtain by walking
+ * the chain manually here.
+ */
+ bdrv_query_block_graph_info(bs, &info, &err);
if (err) {
error_report_err(err);
blk_unref(blk);
@@ -2945,7 +2972,7 @@ static BlockNodeInfoList *collect_image_info_list(bool image_opts,
return head;
err:
- qapi_free_BlockNodeInfoList(head);
+ qapi_free_BlockGraphInfoList(head);
g_hash_table_destroy(filenames);
return NULL;
}
@@ -2956,7 +2983,7 @@ static int img_info(int argc, char **argv)
OutputFormat output_format = OFORMAT_HUMAN;
bool chain = false;
const char *filename, *fmt, *output;
- BlockNodeInfoList *list;
+ BlockGraphInfoList *list;
bool image_opts = false;
bool force_share = false;
@@ -3035,14 +3062,14 @@ static int img_info(int argc, char **argv)
break;
case OFORMAT_JSON:
if (chain) {
- dump_json_block_node_info_list(list);
+ dump_json_block_graph_info_list(list);
} else {
- dump_json_block_node_info(list->value);
+ dump_json_block_graph_info(list->value);
}
break;
}
- qapi_free_BlockNodeInfoList(list);
+ qapi_free_BlockGraphInfoList(list);
return 0;
}
diff --git a/tests/qemu-iotests/065 b/tests/qemu-iotests/065
index b724c89c7c..b76701c71e 100755
--- a/tests/qemu-iotests/065
+++ b/tests/qemu-iotests/065
@@ -56,7 +56,7 @@ class TestQemuImgInfo(TestImageInfoSpecific):
def test_human(self):
data = qemu_img('info', '--output=human', test_img).stdout.split('\n')
data = data[(data.index('Format specific information:') + 1)
- :data.index('')]
+ :data.index("Child node '/file':")]
for field in data:
self.assertTrue(re.match('^ {4}[^ ]', field) is not None)
data = [line.strip() for line in data]
diff --git a/tests/qemu-iotests/302.out b/tests/qemu-iotests/302.out
index 3e7c281b91..edfa1c4f05 100644
--- a/tests/qemu-iotests/302.out
+++ b/tests/qemu-iotests/302.out
@@ -4,6 +4,11 @@ image: nbd+unix:///exp?socket=SOCK_DIR/PID-nbd-sock
file format: raw
virtual size: 448 KiB (458752 bytes)
disk size: unavailable
+Child node '/file':
+ image: nbd+unix:///exp?socket=SOCK_DIR/PID-nbd-sock
+ file format: nbd
+ virtual size: 448 KiB (458752 bytes)
+ disk size: unavailable
=== Converted image info ===
image: TEST_IMG
--
2.31.1

241
SOURCES/kvm-qemu-img-Use-BlockNodeInfo.patch
Unescape View File

@ -0,0 +1,241 @@
From dca4cbe680baff837ca8ac8bd39b77b46af3f64b Mon Sep 17 00:00:00 2001
From: Hanna Reitz <hreitz@redhat.com>
Date: Mon, 20 Jun 2022 18:26:57 +0200
Subject: [PATCH 10/20] qemu-img: Use BlockNodeInfo
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 145: Show protocol-level information in qemu-img info
RH-Bugzilla: 1860292
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [5/12] b599af3ec05951a0ba11d9eae2ee19148d6bf624 (hreitz/qemu-kvm-c-9-s)
qemu-img info never uses ImageInfo's backing-image field, because it
opens the backing chain one by one with BDRV_O_NO_BACKING, and prints
all backing chain nodes' information consecutively. Use BlockNodeInfo
to make it clear that we only print information about a single node, and
that we are not using the backing-image field.
Notably, bdrv_image_info_dump() does not evaluate the backing-image
field, so we can easily make it take a BlockNodeInfo pointer (and
consequentially rename it to bdrv_node_info_dump()). It makes more
sense this way, because again, the interface now makes it syntactically
clear that backing-image is ignored by this function.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-6-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit b1f4cd1589a16fec02f264a09bd3560e4ccce3c2)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/monitor/block-hmp-cmds.c | 2 +-
block/qapi.c | 2 +-
include/block/qapi.h | 2 +-
qapi/block-core.json | 4 +--
qemu-img.c | 48 +++++++++++++++++-----------------
5 files changed, 29 insertions(+), 29 deletions(-)
diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index b6135e9bfe..aa37faa601 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -734,7 +734,7 @@ static void print_block_info(Monitor *mon, BlockInfo *info,
monitor_printf(mon, "\nImages:\n");
image_info = inserted->image;
while (1) {
- bdrv_image_info_dump(image_info);
+ bdrv_node_info_dump(qapi_ImageInfo_base(image_info));
if (image_info->has_backing_image) {
image_info = image_info->backing_image;
} else {
diff --git a/block/qapi.c b/block/qapi.c
index e5022b4481..ad88bf9b38 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -865,7 +865,7 @@ void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
visit_free(v);
}
-void bdrv_image_info_dump(ImageInfo *info)
+void bdrv_node_info_dump(BlockNodeInfo *info)
{
char *size_buf, *dsize_buf;
if (!info->has_actual_size) {
diff --git a/include/block/qapi.h b/include/block/qapi.h
index c7de4e3fa9..22198dcd0c 100644
--- a/include/block/qapi.h
+++ b/include/block/qapi.h
@@ -45,5 +45,5 @@ void bdrv_query_image_info(BlockDriverState *bs,
void bdrv_snapshot_dump(QEMUSnapshotInfo *sn);
void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec,
const char *prefix);
-void bdrv_image_info_dump(ImageInfo *info);
+void bdrv_node_info_dump(BlockNodeInfo *info);
#endif
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 7720da0498..4cf2deeb6c 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -5796,9 +5796,9 @@
##
# @DummyBlockCoreForceArrays:
#
-# Not used by QMP; hack to let us use ImageInfoList internally
+# Not used by QMP; hack to let us use BlockNodeInfoList internally
#
# Since: 8.0
##
{ 'struct': 'DummyBlockCoreForceArrays',
- 'data': { 'unused-image-info': ['ImageInfo'] } }
+ 'data': { 'unused-block-node-info': ['BlockNodeInfo'] } }
diff --git a/qemu-img.c b/qemu-img.c
index 2f85bb7ede..3b2ca3bbcb 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -2816,13 +2816,13 @@ static void dump_snapshots(BlockDriverState *bs)
g_free(sn_tab);
}
-static void dump_json_image_info_list(ImageInfoList *list)
+static void dump_json_block_node_info_list(BlockNodeInfoList *list)
{
GString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
- visit_type_ImageInfoList(v, NULL, &list, &error_abort);
+ visit_type_BlockNodeInfoList(v, NULL, &list, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj, true);
assert(str != NULL);
@@ -2832,13 +2832,13 @@ static void dump_json_image_info_list(ImageInfoList *list)
g_string_free(str, true);
}
-static void dump_json_image_info(ImageInfo *info)
+static void dump_json_block_node_info(BlockNodeInfo *info)
{
GString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
- visit_type_ImageInfo(v, NULL, &info, &error_abort);
+ visit_type_BlockNodeInfo(v, NULL, &info, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj, true);
assert(str != NULL);
@@ -2848,9 +2848,9 @@ static void dump_json_image_info(ImageInfo *info)
g_string_free(str, true);
}
-static void dump_human_image_info_list(ImageInfoList *list)
+static void dump_human_image_info_list(BlockNodeInfoList *list)
{
- ImageInfoList *elem;
+ BlockNodeInfoList *elem;
bool delim = false;
for (elem = list; elem; elem = elem->next) {
@@ -2859,7 +2859,7 @@ static void dump_human_image_info_list(ImageInfoList *list)
}
delim = true;
- bdrv_image_info_dump(elem->value);
+ bdrv_node_info_dump(elem->value);
}
}
@@ -2869,24 +2869,24 @@ static gboolean str_equal_func(gconstpointer a, gconstpointer b)
}
/**
- * Open an image file chain and return an ImageInfoList
+ * Open an image file chain and return an BlockNodeInfoList
*
* @filename: topmost image filename
* @fmt: topmost image format (may be NULL to autodetect)
* @chain: true - enumerate entire backing file chain
* false - only topmost image file
*
- * Returns a list of ImageInfo objects or NULL if there was an error opening an
- * image file. If there was an error a message will have been printed to
- * stderr.
+ * Returns a list of BlockNodeInfo objects or NULL if there was an error
+ * opening an image file. If there was an error a message will have been
+ * printed to stderr.
*/
-static ImageInfoList *collect_image_info_list(bool image_opts,
- const char *filename,
- const char *fmt,
- bool chain, bool force_share)
+static BlockNodeInfoList *collect_image_info_list(bool image_opts,
+ const char *filename,
+ const char *fmt,
+ bool chain, bool force_share)
{
- ImageInfoList *head = NULL;
- ImageInfoList **tail = &head;
+ BlockNodeInfoList *head = NULL;
+ BlockNodeInfoList **tail = &head;
GHashTable *filenames;
Error *err = NULL;
@@ -2895,7 +2895,7 @@ static ImageInfoList *collect_image_info_list(bool image_opts,
while (filename) {
BlockBackend *blk;
BlockDriverState *bs;
- ImageInfo *info;
+ BlockNodeInfo *info;
if (g_hash_table_lookup_extended(filenames, filename, NULL, NULL)) {
error_report("Backing file '%s' creates an infinite loop.",
@@ -2912,7 +2912,7 @@ static ImageInfoList *collect_image_info_list(bool image_opts,
}
bs = blk_bs(blk);
- bdrv_query_image_info(bs, &info, &err);
+ bdrv_query_block_node_info(bs, &info, &err);
if (err) {
error_report_err(err);
blk_unref(blk);
@@ -2945,7 +2945,7 @@ static ImageInfoList *collect_image_info_list(bool image_opts,
return head;
err:
- qapi_free_ImageInfoList(head);
+ qapi_free_BlockNodeInfoList(head);
g_hash_table_destroy(filenames);
return NULL;
}
@@ -2956,7 +2956,7 @@ static int img_info(int argc, char **argv)
OutputFormat output_format = OFORMAT_HUMAN;
bool chain = false;
const char *filename, *fmt, *output;
- ImageInfoList *list;
+ BlockNodeInfoList *list;
bool image_opts = false;
bool force_share = false;
@@ -3035,14 +3035,14 @@ static int img_info(int argc, char **argv)
break;
case OFORMAT_JSON:
if (chain) {
- dump_json_image_info_list(list);
+ dump_json_block_node_info_list(list);
} else {
- dump_json_image_info(list->value);
+ dump_json_block_node_info(list->value);
}
break;
}
- qapi_free_ImageInfoList(list);
+ qapi_free_BlockNodeInfoList(list);
return 0;
}
--
2.31.1

70
SOURCES/kvm-qemu-img-bitmap-Report-errors-while-closing-the-imag.patch
Unescape View File

@ -0,0 +1,70 @@
From d0d3d694b3a8d200442484ae0c9d263e0439cd04 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 12 Jan 2023 20:14:53 +0100
Subject: [PATCH 03/20] qemu-img bitmap: Report errors while closing the image
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 143: qemu-img: Fix exit code for errors closing the image
RH-Bugzilla: 2150180
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [3/4] 4a704fec2e3bcb47b2be1529e27fd1833d58c517 (kmwolf/centos-qemu-kvm)
blk_unref() can't report any errors that happen while closing the image.
For example, if qcow2 hits an -ENOSPC error while writing out dirty
bitmaps when it's closed, it prints error messages to stderr, but
'qemu-img bitmap' won't see any error return value and will therefore
look successful with exit code 0.
In order to fix this, manually inactivate the image first before calling
blk_unref(). This already performs the operations that would be most
likely to fail while closing the image, but it can still return errors.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1330
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230112191454.169353-4-kwolf@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit c5e477110dcb8ef4642dce399777c3dee68fa96c)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
qemu-img.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/qemu-img.c b/qemu-img.c
index 3cbdda9f76..2f85bb7ede 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -4646,6 +4646,7 @@ static int img_bitmap(int argc, char **argv)
QSIMPLEQ_HEAD(, ImgBitmapAction) actions;
ImgBitmapAction *act, *act_next;
const char *op;
+ int inactivate_ret;
QSIMPLEQ_INIT(&actions);
@@ -4830,6 +4831,16 @@ static int img_bitmap(int argc, char **argv)
ret = 0;
out:
+ /*
+ * Manually inactivate the images first because this way we can know whether
+ * an error occurred. blk_unref() doesn't tell us about failures.
+ */
+ inactivate_ret = bdrv_inactivate_all();
+ if (inactivate_ret < 0) {
+ error_report("Error while closing the image: %s", strerror(-inactivate_ret));
+ ret = 1;
+ }
+
blk_unref(src);
blk_unref(blk);
qemu_opts_del(opts);
--
2.31.1

67
SOURCES/kvm-qemu-img-commit-Report-errors-while-closing-the-imag.patch
Unescape View File

@ -0,0 +1,67 @@
From 2f5369f0effaa23be746f9b5d9f6a0bfc346fb7d Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 12 Jan 2023 20:14:52 +0100
Subject: [PATCH 02/20] qemu-img commit: Report errors while closing the image
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 143: qemu-img: Fix exit code for errors closing the image
RH-Bugzilla: 2150180
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [2/4] faedd43355463b1210a3f21ecd430f478bd06f5a (kmwolf/centos-qemu-kvm)
blk_unref() can't report any errors that happen while closing the image.
For example, if qcow2 hits an -ENOSPC error while writing out dirty
bitmaps when it's closed, it prints error messages to stderr, but
'qemu-img commit' won't see any error return value and will therefore
look successful with exit code 0.
In order to fix this, manually inactivate the image first before calling
blk_unref(). This already performs the operations that would be most
likely to fail while closing the image, but it can still return errors.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230112191454.169353-3-kwolf@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 44efba2d713aca076c411594d0c1a2b99155eeb3)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
qemu-img.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/qemu-img.c b/qemu-img.c
index a9b3a8103c..3cbdda9f76 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -449,6 +449,11 @@ static BlockBackend *img_open(bool image_opts,
blk = img_open_file(filename, NULL, fmt, flags, writethrough, quiet,
force_share);
}
+
+ if (blk) {
+ blk_set_force_allow_inactivate(blk);
+ }
+
return blk;
}
@@ -1119,6 +1124,14 @@ unref_backing:
done:
qemu_progress_end();
+ /*
+ * Manually inactivate the image first because this way we can know whether
+ * an error occurred. blk_unref() doesn't tell us about failures.
+ */
+ ret = bdrv_inactivate_all();
+ if (ret < 0 && !local_err) {
+ error_setg_errno(&local_err, -ret, "Error while closing the image");
+ }
blk_unref(blk);
if (local_err) {
--
2.31.1

166
SOURCES/kvm-qemu-iotests-Test-qemu-img-bitmap-commit-exit-code-o.patch
Unescape View File

@ -0,0 +1,166 @@
From 06030aa79fcb2d90d6a670e75d959aa0c3204b5c Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 12 Jan 2023 20:14:54 +0100
Subject: [PATCH 04/20] qemu-iotests: Test qemu-img bitmap/commit exit code on
error
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 143: qemu-img: Fix exit code for errors closing the image
RH-Bugzilla: 2150180
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefano Garzarella <sgarzare@redhat.com>
RH-Commit: [4/4] b96bb671bcfb7ae18015fda14db70f42a83a6ea7 (kmwolf/centos-qemu-kvm)
This tests that when an error happens while writing back bitmaps to the
image file in qcow2_inactivate(), 'qemu-img bitmap/commit' actually
return an error value in their exit code instead of making the operation
look successful to scripts.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230112191454.169353-5-kwolf@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 07a4e1f8e5418f36424cd57d5d061b090a238c65)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
.../qemu-iotests/tests/qemu-img-close-errors | 96 +++++++++++++++++++
.../tests/qemu-img-close-errors.out | 23 +++++
2 files changed, 119 insertions(+)
create mode 100755 tests/qemu-iotests/tests/qemu-img-close-errors
create mode 100644 tests/qemu-iotests/tests/qemu-img-close-errors.out
diff --git a/tests/qemu-iotests/tests/qemu-img-close-errors b/tests/qemu-iotests/tests/qemu-img-close-errors
new file mode 100755
index 0000000000..50bfb6cfa2
--- /dev/null
+++ b/tests/qemu-iotests/tests/qemu-img-close-errors
@@ -0,0 +1,96 @@
+#!/usr/bin/env bash
+# group: rw auto quick
+#
+# Check that errors while closing the image, in particular writing back dirty
+# bitmaps, is correctly reported with a failing qemu-img exit code.
+#
+# Copyright (C) 2023 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/>.
+#
+
+# creator
+owner=kwolf@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+cd ..
+. ./common.rc
+. ./common.filter
+
+_supported_fmt qcow2
+_supported_proto file
+_supported_os Linux
+
+size=1G
+
+# The error we are going to use is ENOSPC. Depending on how many bitmaps we
+# create in the backing file (and therefore increase the used up space), we get
+# failures in different places. With a low number, only merging the bitmap
+# fails, whereas with a higher number, already 'qemu-img commit' fails.
+for max_bitmap in 6 7; do
+ echo
+ echo "=== Test with $max_bitmap bitmaps ==="
+
+ TEST_IMG="$TEST_IMG.base" _make_test_img -q $size
+ for i in $(seq 1 $max_bitmap); do
+ $QEMU_IMG bitmap --add "$TEST_IMG.base" "stale-bitmap-$i"
+ done
+
+ # Simulate a block device of 128 MB by resizing the image file accordingly
+ # and then enforcing the size with the raw driver
+ $QEMU_IO -f raw -c "truncate 128M" "$TEST_IMG.base"
+ BASE_JSON='json:{
+ "driver": "qcow2",
+ "file": {
+ "driver": "raw",
+ "size": 134217728,
+ "file": {
+ "driver": "file",
+ "filename":"'"$TEST_IMG.base"'"
+ }
+ }
+ }'
+
+ _make_test_img -q -b "$BASE_JSON" -F $IMGFMT
+ $QEMU_IMG bitmap --add "$TEST_IMG" "good-bitmap"
+
+ $QEMU_IO -c 'write 0 126m' "$TEST_IMG" | _filter_qemu_io
+
+ $QEMU_IMG commit -d "$TEST_IMG" 2>&1 | _filter_generated_node_ids
+ echo "qemu-img commit exit code: ${PIPESTATUS[0]}"
+
+ $QEMU_IMG bitmap --add "$BASE_JSON" "good-bitmap"
+ echo "qemu-img bitmap --add exit code: $?"
+
+ $QEMU_IMG bitmap --merge "good-bitmap" -b "$TEST_IMG" "$BASE_JSON" \
+ "good-bitmap" 2>&1 | _filter_generated_node_ids
+ echo "qemu-img bitmap --merge exit code: ${PIPESTATUS[0]}"
+done
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
+
diff --git a/tests/qemu-iotests/tests/qemu-img-close-errors.out b/tests/qemu-iotests/tests/qemu-img-close-errors.out
new file mode 100644
index 0000000000..1bfe88f176
--- /dev/null
+++ b/tests/qemu-iotests/tests/qemu-img-close-errors.out
@@ -0,0 +1,23 @@
+QA output created by qemu-img-close-errors
+
+=== Test with 6 bitmaps ===
+wrote 132120576/132120576 bytes at offset 0
+126 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+Image committed.
+qemu-img commit exit code: 0
+qemu-img bitmap --add exit code: 0
+qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'good-bitmap' to file: No space left on device
+qemu-img: Error while closing the image: Invalid argument
+qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'good-bitmap' to file: No space left on device
+qemu-img bitmap --merge exit code: 1
+
+=== Test with 7 bitmaps ===
+wrote 132120576/132120576 bytes at offset 0
+126 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'stale-bitmap-7' to file: No space left on device
+qemu-img: Lost persistent bitmaps during inactivation of node 'NODE_NAME': Failed to write bitmap 'stale-bitmap-7' to file: No space left on device
+qemu-img: Error while closing the image: Invalid argument
+qemu-img commit exit code: 1
+qemu-img bitmap --add exit code: 0
+qemu-img bitmap --merge exit code: 0
+*** done
--
2.31.1

49
SOURCES/kvm-qga-linux-add-usb-support-to-guest-get-fsinfo.patch
Unescape View File

@ -0,0 +1,49 @@
From 48f45171b89b8ed24f2b2484d63b00ea7818b5c3 Mon Sep 17 00:00:00 2001
From: Kfir Manor <kfir@daynix.com>
Date: Sun, 22 Jan 2023 17:33:07 +0200
Subject: [PATCH 9/9] qga/linux: add usb support to guest-get-fsinfo
RH-Author: Kostiantyn Kostiuk <kkostiuk@redhat.com>
RH-MergeRequest: 140: qga/linux: add usb support to guest-get-fsinfo
RH-Bugzilla: 2149191
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: yvugenfi <None>
RH-Commit: [1/1] bae929a2d0d0ad20e7308ede69c26499fc2119c7 (kostyanf14/redhat_centos-stream_src_qemu-kvm)
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2149191
Upstream patch: https://patchew.org/QEMU/20230122153307.1050593-1-kfir@daynix.com/
Signed-off-by: Kfir Manor <kfir@daynix.com>
Reviewed-by: Konstantin Kostiuk <kkostiuk@redhat.com>
Signed-off-by: Konstantin Kostiuk <kkostiuk@redhat.com>
---
qga/commands-posix.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/qga/commands-posix.c b/qga/commands-posix.c
index 32493d6383..f1b2b87c13 100644
--- a/qga/commands-posix.c
+++ b/qga/commands-posix.c
@@ -877,7 +877,9 @@ static bool build_guest_fsinfo_for_pci_dev(char const *syspath,
g_str_equal(driver, "sym53c8xx") ||
g_str_equal(driver, "virtio-pci") ||
g_str_equal(driver, "ahci") ||
- g_str_equal(driver, "nvme"))) {
+ g_str_equal(driver, "nvme") ||
+ g_str_equal(driver, "xhci_hcd") ||
+ g_str_equal(driver, "ehci-pci"))) {
break;
}
@@ -974,6 +976,8 @@ static bool build_guest_fsinfo_for_pci_dev(char const *syspath,
}
} else if (strcmp(driver, "nvme") == 0) {
disk->bus_type = GUEST_DISK_BUS_TYPE_NVME;
+ } else if (strcmp(driver, "ehci-pci") == 0 || strcmp(driver, "xhci_hcd") == 0) {
+ disk->bus_type = GUEST_DISK_BUS_TYPE_USB;
} else {
g_debug("unknown driver '%s' (sysfs path '%s')", driver, syspath);
goto cleanup;
--
2.31.1

43
SOURCES/kvm-redhat-fix-virt-rhel9.2.0-compat-props.patch
Unescape View File

@ -0,0 +1,43 @@
From 546e4213c4e8a7b2e369315a71bc9aec091eed6e Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Mon, 19 Dec 2022 10:30:26 +0100
Subject: redhat: fix virt-rhel9.2.0 compat props
RH-Author: Cornelia Huck <cohuck@redhat.com>
RH-MergeRequest: 127: redhat: fix virt-rhel9.2.0 compat props
RH-Bugzilla: 2154640
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] 49635fdc1d9a934ece78abd160b07c19909f876a (cohuck/qemu-kvm-c9s)
We need to include arm_rhel_compat props in the latest machine.
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
---
hw/arm/virt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 0a94f31dd1..bf18838b87 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3520,6 +3520,7 @@ type_init(rhel_machine_init);
static void rhel920_virt_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, arm_rhel_compat, arm_rhel_compat_len);
}
DEFINE_RHEL_MACHINE_AS_LATEST(9, 2, 0)
@@ -3529,7 +3530,6 @@ static void rhel900_virt_options(MachineClass *mc)
rhel920_virt_options(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 */
--
2.38.1

125
SOURCES/kvm-s390x-pci-coalesce-unmap-operations.patch
Unescape View File

@ -0,0 +1,125 @@
From ed90f91b61844abd2dff2eb970f721a6cf072235 Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Fri, 28 Oct 2022 15:47:57 -0400
Subject: [PATCH 6/9] s390x/pci: coalesce unmap operations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 141: s390x/pci: reset ISM passthrough devices on shutdown and system reset
RH-Bugzilla: 2163701
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/3] 80c3a2c1d720057ae2a80b338ea06c9c6c804532 (clegoate/qemu-kvm-c9s)
Currently, each unmapped page is handled as an individual iommu
region notification. Attempt to group contiguous unmap operations
into fewer notifications to reduce overhead.
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-Id: <20221028194758.204007-3-mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit ef536007c3301bbd6a787e4c2210ea289adaa6f0)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-pci-inst.c | 51 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 51 insertions(+)
diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c
index 7cc4bcf850..66e764f901 100644
--- a/hw/s390x/s390-pci-inst.c
+++ b/hw/s390x/s390-pci-inst.c
@@ -640,6 +640,8 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
}
g_hash_table_remove(iommu->iotlb, &entry->iova);
inc_dma_avail(iommu);
+ /* Don't notify the iommu yet, maybe we can bundle contiguous unmaps */
+ goto out;
} else {
if (cache) {
if (cache->perm == entry->perm &&
@@ -663,15 +665,44 @@ static uint32_t s390_pci_update_iotlb(S390PCIIOMMU *iommu,
dec_dma_avail(iommu);
}
+ /*
+ * All associated iotlb entries have already been cleared, trigger the
+ * unmaps.
+ */
memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
out:
return iommu->dma_limit ? iommu->dma_limit->avail : 1;
}
+static void s390_pci_batch_unmap(S390PCIIOMMU *iommu, uint64_t iova,
+ uint64_t len)
+{
+ uint64_t remain = len, start = iova, end = start + len - 1, mask, size;
+ IOMMUTLBEvent event = {
+ .type = IOMMU_NOTIFIER_UNMAP,
+ .entry = {
+ .target_as = &address_space_memory,
+ .translated_addr = 0,
+ .perm = IOMMU_NONE,
+ },
+ };
+
+ while (remain >= TARGET_PAGE_SIZE) {
+ mask = dma_aligned_pow2_mask(start, end, 64);
+ size = mask + 1;
+ event.entry.iova = start;
+ event.entry.addr_mask = mask;
+ memory_region_notify_iommu(&iommu->iommu_mr, 0, event);
+ start += size;
+ remain -= size;
+ }
+}
+
int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
{
CPUS390XState *env = &cpu->env;
+ uint64_t iova, coalesce = 0;
uint32_t fh;
uint16_t error = 0;
S390PCIBusDevice *pbdev;
@@ -742,6 +773,21 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
break;
}
+ /*
+ * If this is an unmap of a PTE, let's try to coalesce multiple unmaps
+ * into as few notifier events as possible.
+ */
+ if (entry.perm == IOMMU_NONE && entry.len == TARGET_PAGE_SIZE) {
+ if (coalesce == 0) {
+ iova = entry.iova;
+ }
+ coalesce += entry.len;
+ } else if (coalesce > 0) {
+ /* Unleash the coalesced unmap before processing a new map */
+ s390_pci_batch_unmap(iommu, iova, coalesce);
+ coalesce = 0;
+ }
+
start += entry.len;
while (entry.iova < start && entry.iova < end) {
if (dma_avail > 0 || entry.perm == IOMMU_NONE) {
@@ -759,6 +805,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)
}
}
}
+ if (coalesce) {
+ /* Unleash the coalesced unmap before finishing rpcit */
+ s390_pci_batch_unmap(iommu, iova, coalesce);
+ coalesce = 0;
+ }
if (again && dma_avail > 0)
goto retry;
err:
--
2.31.1

147
SOURCES/kvm-s390x-pci-reset-ISM-passthrough-devices-on-shutdown-.patch
Unescape View File

@ -0,0 +1,147 @@
From 1ed1f8fc20a4883bc0bc1f58d299b0278abc5442 Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Fri, 9 Dec 2022 14:57:00 -0500
Subject: [PATCH 8/9] s390x/pci: reset ISM passthrough devices on shutdown and
system reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 141: s390x/pci: reset ISM passthrough devices on shutdown and system reset
RH-Bugzilla: 2163701
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/3] c531352b9d57f51ba938d4c46ee19a5706ade697 (clegoate/qemu-kvm-c9s)
ISM device firmware stores unique state information that can
can cause a wholesale unmap of the associated IOMMU (e.g. when
we get a termination signal for QEMU) to trigger firmware errors
because firmware believes we are attempting to invalidate entries
that are still in-use by the guest OS (when in fact that guest is
in the process of being terminated or rebooted).
To alleviate this, register both a shutdown notifier (for unexpected
termination cases e.g. virsh destroy) as well as a reset callback
(for cases like guest OS reboot). For each of these scenarios, trigger
PCI device reset; this is enough to indicate to firmware that the IOMMU
is no longer in-use by the guest OS, making it safe to invalidate any
associated IOMMU entries.
Fixes: 15d0e7942d3b ("s390x/pci: don't fence interpreted devices without MSI-X")
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-Id: <20221209195700.263824-1-mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
[thuth: Adjusted the hunk in s390-pci-vfio.c due to different context]
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit 03451953c79e6b31f7860ee0c35b28e181d573c1)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-pci-bus.c | 28 ++++++++++++++++++++++++++++
hw/s390x/s390-pci-vfio.c | 2 ++
include/hw/s390x/s390-pci-bus.h | 5 +++++
3 files changed, 35 insertions(+)
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 977e7daa15..02751f3597 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -24,6 +24,8 @@
#include "hw/pci/msi.h"
#include "qemu/error-report.h"
#include "qemu/module.h"
+#include "sysemu/reset.h"
+#include "sysemu/runstate.h"
#ifndef DEBUG_S390PCI_BUS
#define DEBUG_S390PCI_BUS 0
@@ -150,10 +152,30 @@ out:
psccb->header.response_code = cpu_to_be16(rc);
}
+static void s390_pci_shutdown_notifier(Notifier *n, void *opaque)
+{
+ S390PCIBusDevice *pbdev = container_of(n, S390PCIBusDevice,
+ shutdown_notifier);
+
+ pci_device_reset(pbdev->pdev);
+}
+
+static void s390_pci_reset_cb(void *opaque)
+{
+ S390PCIBusDevice *pbdev = opaque;
+
+ pci_device_reset(pbdev->pdev);
+}
+
static void s390_pci_perform_unplug(S390PCIBusDevice *pbdev)
{
HotplugHandler *hotplug_ctrl;
+ if (pbdev->pft == ZPCI_PFT_ISM) {
+ notifier_remove(&pbdev->shutdown_notifier);
+ qemu_unregister_reset(s390_pci_reset_cb, pbdev);
+ }
+
/* Unplug the PCI device */
if (pbdev->pdev) {
DeviceState *pdev = DEVICE(pbdev->pdev);
@@ -1111,6 +1133,12 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
pbdev->fh |= FH_SHM_VFIO;
pbdev->forwarding_assist = false;
}
+ /* Register shutdown notifier and reset callback for ISM devices */
+ if (pbdev->pft == ZPCI_PFT_ISM) {
+ pbdev->shutdown_notifier.notify = s390_pci_shutdown_notifier;
+ qemu_register_shutdown_notifier(&pbdev->shutdown_notifier);
+ qemu_register_reset(s390_pci_reset_cb, pbdev);
+ }
} else {
pbdev->fh |= FH_SHM_EMUL;
/* Always intercept emulated devices */
diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c
index f7bf36cec8..f51190d466 100644
--- a/hw/s390x/s390-pci-vfio.c
+++ b/hw/s390x/s390-pci-vfio.c
@@ -124,6 +124,8 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev,
/* The following values remain 0 until we support other FMB formats */
pbdev->zpci_fn.fmbl = 0;
pbdev->zpci_fn.pft = 0;
+ /* Store function type separately for type-specific behavior */
+ pbdev->pft = cap->pft;
/*
* If appropriate, reduce the size of the supported DMA aperture reported
diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h
index 1c46e3a269..e0a9f9385b 100644
--- a/include/hw/s390x/s390-pci-bus.h
+++ b/include/hw/s390x/s390-pci-bus.h
@@ -39,6 +39,9 @@
#define UID_CHECKING_ENABLED 0x01
#define ZPCI_DTSM 0x40
+/* zPCI Function Types */
+#define ZPCI_PFT_ISM 5
+
OBJECT_DECLARE_SIMPLE_TYPE(S390pciState, S390_PCI_HOST_BRIDGE)
OBJECT_DECLARE_SIMPLE_TYPE(S390PCIBus, S390_PCI_BUS)
OBJECT_DECLARE_SIMPLE_TYPE(S390PCIBusDevice, S390_PCI_DEVICE)
@@ -344,6 +347,7 @@ struct S390PCIBusDevice {
uint16_t noi;
uint16_t maxstbl;
uint8_t sum;
+ uint8_t pft;
S390PCIGroup *pci_group;
ClpRspQueryPci zpci_fn;
S390MsixInfo msix;
@@ -352,6 +356,7 @@ struct S390PCIBusDevice {
MemoryRegion msix_notify_mr;
IndAddr *summary_ind;
IndAddr *indicator;
+ Notifier shutdown_notifier;
bool pci_unplug_request_processed;
bool unplug_requested;
bool interp;
--
2.31.1

91
SOURCES/kvm-s390x-pci-shrink-DMA-aperture-to-be-bound-by-vfio-DM.patch
Unescape View File

@ -0,0 +1,91 @@
From ee69c8c57fe62fc200f749c4ce3927c88803644d Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Fri, 28 Oct 2022 15:47:58 -0400
Subject: [PATCH 7/9] s390x/pci: shrink DMA aperture to be bound by vfio DMA
limit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 141: s390x/pci: reset ISM passthrough devices on shutdown and system reset
RH-Bugzilla: 2163701
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/3] 0956bbb4773dd0085f6aed59d6284c704b4fed3b (clegoate/qemu-kvm-c9s)
Currently, s390x-pci performs accounting against the vfio DMA
limit and triggers the guest to clean up mappings when the limit
is reached. Let's go a step further and also limit the size of
the supported DMA aperture reported to the guest based upon the
initial vfio DMA limit reported for the container (if less than
than the size reported by the firmware/host zPCI layer). This
avoids processing sections of the guest DMA table during global
refresh that, for common use cases, will never be used anway, and
makes exhausting the vfio DMA limit due to mismatch between guest
aperture size and host limit far less likely and more indicitive
of an error.
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-Id: <20221028194758.204007-4-mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit df202e3ff3fccb49868e08f20d0bda86cb953fbe)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-pci-vfio.c | 11 +++++++++++
include/hw/s390x/s390-pci-bus.h | 1 +
2 files changed, 12 insertions(+)
diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c
index 5f0adb0b4a..f7bf36cec8 100644
--- a/hw/s390x/s390-pci-vfio.c
+++ b/hw/s390x/s390-pci-vfio.c
@@ -84,6 +84,7 @@ S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s,
cnt->users = 1;
cnt->avail = avail;
QTAILQ_INSERT_TAIL(&s->zpci_dma_limit, cnt, link);
+ pbdev->iommu->max_dma_limit = avail;
return cnt;
}
@@ -103,6 +104,7 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev,
struct vfio_info_cap_header *hdr;
struct vfio_device_info_cap_zpci_base *cap;
VFIOPCIDevice *vpci = container_of(pbdev->pdev, VFIOPCIDevice, pdev);
+ uint64_t vfio_size;
hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_BASE);
@@ -122,6 +124,15 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev,
/* The following values remain 0 until we support other FMB formats */
pbdev->zpci_fn.fmbl = 0;
pbdev->zpci_fn.pft = 0;
+
+ /*
+ * If appropriate, reduce the size of the supported DMA aperture reported
+ * to the guest based upon the vfio DMA limit.
+ */
+ vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS;
+ if (vfio_size < (cap->end_dma - cap->start_dma + 1)) {
+ pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1;
+ }
}
static bool get_host_fh(S390PCIBusDevice *pbdev, struct vfio_device_info *info,
diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h
index 0605fcea24..1c46e3a269 100644
--- a/include/hw/s390x/s390-pci-bus.h
+++ b/include/hw/s390x/s390-pci-bus.h
@@ -278,6 +278,7 @@ struct S390PCIIOMMU {
uint64_t g_iota;
uint64_t pba;
uint64_t pal;
+ uint64_t max_dma_limit;
GHashTable *iotlb;
S390PCIDMACount *dma_limit;
};
--
2.31.1

109
SOURCES/kvm-s390x-pv-Implement-a-CGS-check-helper.patch
Unescape View File

@ -0,0 +1,109 @@
From 9452246e59a5f16f44fdf9a7d514b947faf1d5fc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Mon, 16 Jan 2023 18:46:05 +0100
Subject: [PATCH 5/9] s390x/pv: Implement a CGS check helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 139: s390x/pv: Implement a CGS check helper
RH-Bugzilla: 2122523
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Commit: [1/1] 8551ce772b10de653b4e1c8be60aae60ec98b421 (clegoate/qemu-kvm-c9s)
When a protected VM is started with the maximum number of CPUs (248),
the service call providing information on the CPUs requires more
buffer space than allocated and QEMU disgracefully aborts :
LOADPARM=[........]
Using virtio-blk.
Using SCSI scheme.
...................................................................................
qemu-system-s390x: KVM_S390_MEM_OP failed: Argument list too long
When protected virtualization is initialized, compute the maximum
number of vCPUs supported by the machine and return useful information
to the user before the machine starts in case of error.
Suggested-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Message-Id: <20230116174607.2459498-2-clg@kaod.org>
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit 75d7150c636569f6687f7e70a33be893be43eb5f)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/pv.c | 40 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/hw/s390x/pv.c b/hw/s390x/pv.c
index 8dfe92d8df..8a1c71436b 100644
--- a/hw/s390x/pv.c
+++ b/hw/s390x/pv.c
@@ -20,6 +20,7 @@
#include "exec/confidential-guest-support.h"
#include "hw/s390x/ipl.h"
#include "hw/s390x/pv.h"
+#include "hw/s390x/sclp.h"
#include "target/s390x/kvm/kvm_s390x.h"
static bool info_valid;
@@ -249,6 +250,41 @@ struct S390PVGuestClass {
ConfidentialGuestSupportClass parent_class;
};
+/*
+ * If protected virtualization is enabled, the amount of data that the
+ * Read SCP Info Service Call can use is limited to one page. The
+ * available space also depends on the Extended-Length SCCB (ELS)
+ * feature which can take more buffer space to store feature
+ * information. This impacts the maximum number of CPUs supported in
+ * the machine.
+ */
+static uint32_t s390_pv_get_max_cpus(void)
+{
+ int offset_cpu = s390_has_feat(S390_FEAT_EXTENDED_LENGTH_SCCB) ?
+ offsetof(ReadInfo, entries) : SCLP_READ_SCP_INFO_FIXED_CPU_OFFSET;
+
+ return (TARGET_PAGE_SIZE - offset_cpu) / sizeof(CPUEntry);
+}
+
+static bool s390_pv_check_cpus(Error **errp)
+{
+ MachineState *ms = MACHINE(qdev_get_machine());
+ uint32_t pv_max_cpus = s390_pv_get_max_cpus();
+
+ if (ms->smp.max_cpus > pv_max_cpus) {
+ error_setg(errp, "Protected VMs support a maximum of %d CPUs",
+ pv_max_cpus);
+ return false;
+ }
+
+ return true;
+}
+
+static bool s390_pv_guest_check(ConfidentialGuestSupport *cgs, Error **errp)
+{
+ return s390_pv_check_cpus(errp);
+}
+
int s390_pv_kvm_init(ConfidentialGuestSupport *cgs, Error **errp)
{
if (!object_dynamic_cast(OBJECT(cgs), TYPE_S390_PV_GUEST)) {
@@ -261,6 +297,10 @@ int s390_pv_kvm_init(ConfidentialGuestSupport *cgs, Error **errp)
return -1;
}
+ if (!s390_pv_guest_check(cgs, errp)) {
+ return -1;
+ }
+
cgs->ready = true;
return 0;
--
2.31.1

70
SOURCES/kvm-s390x-s390-virtio-ccw-Activate-zPCI-features-on-s390.patch
Unescape View File

@ -0,0 +1,70 @@
From 51fcf352a97f2e99a6a3fb8ae663b45436304120 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Tue, 10 Jan 2023 14:25:34 +0100
Subject: [PATCH 11/31] s390x/s390-virtio-ccw: Activate zPCI features on
s390-ccw-virtio-rhel8.6.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cédric Le Goater <clg@redhat.com>
RH-MergeRequest: 133: s390x/s390-virtio-ccw: Activate zPCI features on s390-ccw-virtio-rhel8.6.0
RH-Bugzilla: 2159408
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] 1ed82e56fe74a283a1726c4893dc3387e645072c (clegoate/qemu-kvm-c9s)
commit c7b14d3af7 ("s390x/s390-virtio-ccw: Switch off zPCI enhancements
on older machines") activated zPCI enhancement features (interpretation
and forward assist) silently on the s390-ccw-virtio-rhel8.6.0 machine
for RHEL8.8. It didn't seem to be a problem since migration is not
possible but it broke LEAPP upgrade to RHEL9 when the machine is
defined with a passthrough device. Activate the zPCI features also on
RHEL9.2 for the machines to be alike in both latest RHEL distros.
Upstream Status: RHEL-only
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2159408
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/s390x/s390-virtio-ccw.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index aa142a1a4e..4cdd59c394 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1234,8 +1234,14 @@ static void ccw_machine_rhel860_instance_options(MachineState *machine)
static void ccw_machine_rhel860_class_options(MachineClass *mc)
{
+ static GlobalProperty compat[] = {
+ { TYPE_S390_PCI_DEVICE, "interpret", "on", },
+ { TYPE_S390_PCI_DEVICE, "forwarding-assist", "on", },
+ };
+
ccw_machine_rhel900_class_options(mc);
compat_props_add(mc->compat_props, hw_compat_rhel_8_6, hw_compat_rhel_8_6_len);
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
/* All RHEL machines for prior major releases are deprecated */
mc->deprecation_reason = rhel_old_machine_deprecation;
@@ -1259,8 +1265,14 @@ static void ccw_machine_rhel850_instance_options(MachineState *machine)
static void ccw_machine_rhel850_class_options(MachineClass *mc)
{
+ static GlobalProperty compat[] = {
+ { TYPE_S390_PCI_DEVICE, "interpret", "off", },
+ { TYPE_S390_PCI_DEVICE, "forwarding-assist", "off", },
+ };
+
ccw_machine_rhel860_class_options(mc);
compat_props_add(mc->compat_props, hw_compat_rhel_8_5, hw_compat_rhel_8_5_len);
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
mc->smp_props.prefer_sockets = true;
}
DEFINE_CCW_MACHINE(rhel850, "rhel8.5.0", false);
--
2.31.1

19
SOURCES/kvm-s390x.conf
Unescape View File

@ -0,0 +1,19 @@
# User changes in this file are preserved across upgrades.
#
# Setting "modprobe kvm nested=1" only enables Nested Virtualization until
# the next reboot or module reload. Uncomment the option below to enable
# the feature permanently.
#
#options kvm nested=1
#
#
# Setting "modprobe kvm hpage=1" only enables Huge Page Backing (1MB)
# support until the next reboot or module reload. Uncomment the option
# below to enable the feature permanently.
#
# Note: - Incompatible with "nested=1". Loading the module will fail.
# - Dirty page logging will be performed on a 1MB (not 4KB) basis,
# which can result in a lot of data having to be transferred during
# migration, and therefore taking very long to converge.
#
#options kvm hpage=1

159
SOURCES/kvm-stream-Replace-subtree-drain-with-a-single-node-drai.patch
Unescape View File

@ -0,0 +1,159 @@
From 5defda06ec4c24818a34126c5048be5e274b63f5 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:41:04 +0100
Subject: [PATCH 22/31] stream: Replace subtree drain with a single node drain
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [10/16] a93250b1f6ef296e903df0ba5d8b29bc2ed540a8 (sgarzarella/qemu-kvm-c-9-s)
The subtree drain was introduced in commit b1e1af394d9 as a way to avoid
graph changes between finding the base node and changing the block graph
as necessary on completion of the image streaming job.
The block graph could change between these two points because
bdrv_set_backing_hd() first drains the parent node, which involved
polling and can do anything.
Subtree draining was an imperfect way to make this less likely (because
with it, fewer callbacks are called during this window). Everyone agreed
that it's not really the right solution, and it was only committed as a
stopgap solution.
This replaces the subtree drain with a solution that simply drains the
parent node before we try to find the base node, and then call a version
of bdrv_set_backing_hd() that doesn't drain, but just asserts that the
parent node is already drained.
This way, any graph changes caused by draining happen before we start
looking at the graph and things stay consistent between finding the base
node and changing the graph.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-10-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 92140b9f3f07d80e2c27edcc6e32f392be2135e6)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
block.c | 17 ++++++++++++++---
block/stream.c | 26 ++++++++++++++++----------
include/block/block-global-state.h | 3 +++
3 files changed, 33 insertions(+), 13 deletions(-)
diff --git a/block.c b/block.c
index b3449a312e..5330e89903 100644
--- a/block.c
+++ b/block.c
@@ -3403,14 +3403,15 @@ static int bdrv_set_backing_noperm(BlockDriverState *bs,
return bdrv_set_file_or_backing_noperm(bs, backing_hd, true, tran, errp);
}
-int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
- Error **errp)
+int bdrv_set_backing_hd_drained(BlockDriverState *bs,
+ BlockDriverState *backing_hd,
+ Error **errp)
{
int ret;
Transaction *tran = tran_new();
GLOBAL_STATE_CODE();
- bdrv_drained_begin(bs);
+ assert(bs->quiesce_counter > 0);
ret = bdrv_set_backing_noperm(bs, backing_hd, tran, errp);
if (ret < 0) {
@@ -3420,7 +3421,17 @@ int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
ret = bdrv_refresh_perms(bs, errp);
out:
tran_finalize(tran, ret);
+ return ret;
+}
+int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
+ Error **errp)
+{
+ int ret;
+ GLOBAL_STATE_CODE();
+
+ bdrv_drained_begin(bs);
+ ret = bdrv_set_backing_hd_drained(bs, backing_hd, errp);
bdrv_drained_end(bs);
return ret;
diff --git a/block/stream.c b/block/stream.c
index 694709bd25..8744ad103f 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -64,13 +64,16 @@ static int stream_prepare(Job *job)
bdrv_cor_filter_drop(s->cor_filter_bs);
s->cor_filter_bs = NULL;
- bdrv_subtree_drained_begin(s->above_base);
+ /*
+ * bdrv_set_backing_hd() requires that unfiltered_bs is drained. Drain
+ * already here and use bdrv_set_backing_hd_drained() instead because
+ * the polling during drained_begin() might change the graph, and if we do
+ * this only later, we may end up working with the wrong base node (or it
+ * might even have gone away by the time we want to use it).
+ */
+ bdrv_drained_begin(unfiltered_bs);
base = bdrv_filter_or_cow_bs(s->above_base);
- if (base) {
- bdrv_ref(base);
- }
-
unfiltered_base = bdrv_skip_filters(base);
if (bdrv_cow_child(unfiltered_bs)) {
@@ -82,7 +85,13 @@ static int stream_prepare(Job *job)
}
}
- bdrv_set_backing_hd(unfiltered_bs, base, &local_err);
+ bdrv_set_backing_hd_drained(unfiltered_bs, base, &local_err);
+
+ /*
+ * This call will do I/O, so the graph can change again from here on.
+ * We have already completed the graph change, so we are not in danger
+ * of operating on the wrong node any more if this happens.
+ */
ret = bdrv_change_backing_file(unfiltered_bs, base_id, base_fmt, false);
if (local_err) {
error_report_err(local_err);
@@ -92,10 +101,7 @@ static int stream_prepare(Job *job)
}
out:
- if (base) {
- bdrv_unref(base);
- }
- bdrv_subtree_drained_end(s->above_base);
+ bdrv_drained_end(unfiltered_bs);
return ret;
}
diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h
index c7bd4a2088..00e0cf8aea 100644
--- a/include/block/block-global-state.h
+++ b/include/block/block-global-state.h
@@ -82,6 +82,9 @@ int bdrv_open_file_child(const char *filename,
BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp);
int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
Error **errp);
+int bdrv_set_backing_hd_drained(BlockDriverState *bs,
+ BlockDriverState *backing_hd,
+ Error **errp);
int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
const char *bdref_key, Error **errp);
BlockDriverState *bdrv_open(const char *filename, const char *reference,
--
2.31.1

50
SOURCES/kvm-target-s390x-arch_dump-Fix-memory-corruption-in-s390.patch
Unescape View File

@ -0,0 +1,50 @@
From b330bf0a2ad5af73d3c62997f7f0fa5b61f1796b Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Tue, 14 Feb 2023 14:48:37 +0100
Subject: [PATCH 8/8] target/s390x/arch_dump: Fix memory corruption in
s390x_write_elf64_notes()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 152: Fix memory corruption in s390x_write_elf64_notes()
RH-Bugzilla: 2168172
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Commit: [1/1] 37a2c997b2c8b7524e0b6299891bf3ea7c9a46d0 (thuth/qemu-kvm-cs9)
Bugzilla: https://bugzilla.redhat.com/2168172
Upstream-Status: Posted (and reviewed, but not merged yet)
"note_size" can be smaller than sizeof(note), so unconditionally calling
memset(notep, 0, sizeof(note)) could cause a memory corruption here in
case notep has been allocated dynamically, thus let's use note_size as
length argument for memset() instead.
Fixes: 113d8f4e95 ("s390x: pv: Add dump support")
Message-Id: <20230214141056.680969-1-thuth@redhat.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
target/s390x/arch_dump.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c
index a2329141e8..a7c44ba49d 100644
--- a/target/s390x/arch_dump.c
+++ b/target/s390x/arch_dump.c
@@ -248,7 +248,7 @@ static int s390x_write_elf64_notes(const char *note_name,
notep = g_malloc(note_size);
}
- memset(notep, 0, sizeof(note));
+ memset(notep, 0, note_size);
/* Setup note header data */
notep->hdr.n_descsz = cpu_to_be32(content_size);
--
2.31.1

153
SOURCES/kvm-test-bdrv-drain-Don-t-yield-in-.bdrv_co_drained_begi.patch
Unescape View File

@ -0,0 +1,153 @@
From 093c4a6834f3ec5a05390a3630ae4edec80885b8 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 18 Nov 2022 18:40:57 +0100
Subject: [PATCH 15/31] test-bdrv-drain: Don't yield in
.bdrv_co_drained_begin/end()
RH-Author: Stefano Garzarella <sgarzare@redhat.com>
RH-MergeRequest: 135: block: Simplify drain to prevent QEMU from crashing during snapshot
RH-Bugzilla: 2155112
RH-Acked-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [3/16] 5282d3e13cb85dfb480edb11b7eb2769248465df (sgarzarella/qemu-kvm-c-9-s)
We want to change .bdrv_co_drained_begin/end() back to be non-coroutine
callbacks, so in preparation, avoid yielding in their implementation.
This does almost the same as the existing logic in bdrv_drain_invoke(),
by creating and entering coroutines internally. However, since the test
case is by far the heaviest user of coroutine code in drain callbacks,
it is preferable to have the complexity in the test case rather than the
drain core, which is already complicated enough without this.
The behaviour for bdrv_drain_begin() is unchanged because we increase
bs->in_flight and this is still polled. However, bdrv_drain_end()
doesn't wait for the spawned coroutine to complete any more. This is
fine, we don't rely on bdrv_drain_end() restarting all operations
immediately before the next aio_poll().
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20221118174110.55183-3-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 7bce1c299834557bffd92294608ea528648cfe75)
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
---
tests/unit/test-bdrv-drain.c | 64 ++++++++++++++++++++++++++----------
1 file changed, 46 insertions(+), 18 deletions(-)
diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c
index 09dc4a4891..24f34e24ad 100644
--- a/tests/unit/test-bdrv-drain.c
+++ b/tests/unit/test-bdrv-drain.c
@@ -38,12 +38,22 @@ typedef struct BDRVTestState {
bool sleep_in_drain_begin;
} BDRVTestState;
+static void coroutine_fn sleep_in_drain_begin(void *opaque)
+{
+ BlockDriverState *bs = opaque;
+
+ qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000);
+ bdrv_dec_in_flight(bs);
+}
+
static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs)
{
BDRVTestState *s = bs->opaque;
s->drain_count++;
if (s->sleep_in_drain_begin) {
- qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000);
+ Coroutine *co = qemu_coroutine_create(sleep_in_drain_begin, bs);
+ bdrv_inc_in_flight(bs);
+ aio_co_enter(bdrv_get_aio_context(bs), co);
}
}
@@ -1916,6 +1926,21 @@ static int coroutine_fn bdrv_replace_test_co_preadv(BlockDriverState *bs,
return 0;
}
+static void coroutine_fn bdrv_replace_test_drain_co(void *opaque)
+{
+ BlockDriverState *bs = opaque;
+ BDRVReplaceTestState *s = bs->opaque;
+
+ /* Keep waking io_co up until it is done */
+ while (s->io_co) {
+ aio_co_wake(s->io_co);
+ s->io_co = NULL;
+ qemu_coroutine_yield();
+ }
+ s->drain_co = NULL;
+ bdrv_dec_in_flight(bs);
+}
+
/**
* If .drain_count is 0, wake up .io_co if there is one; and set
* .was_drained.
@@ -1926,20 +1951,27 @@ static void coroutine_fn bdrv_replace_test_co_drain_begin(BlockDriverState *bs)
BDRVReplaceTestState *s = bs->opaque;
if (!s->drain_count) {
- /* Keep waking io_co up until it is done */
- s->drain_co = qemu_coroutine_self();
- while (s->io_co) {
- aio_co_wake(s->io_co);
- s->io_co = NULL;
- qemu_coroutine_yield();
- }
- s->drain_co = NULL;
-
+ s->drain_co = qemu_coroutine_create(bdrv_replace_test_drain_co, bs);
+ bdrv_inc_in_flight(bs);
+ aio_co_enter(bdrv_get_aio_context(bs), s->drain_co);
s->was_drained = true;
}
s->drain_count++;
}
+static void coroutine_fn bdrv_replace_test_read_entry(void *opaque)
+{
+ BlockDriverState *bs = opaque;
+ char data;
+ QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1);
+ int ret;
+
+ /* Queue a read request post-drain */
+ ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0);
+ g_assert(ret >= 0);
+ bdrv_dec_in_flight(bs);
+}
+
/**
* Reduce .drain_count, set .was_undrained once it reaches 0.
* If .drain_count reaches 0 and the node has a backing file, issue a
@@ -1951,17 +1983,13 @@ static void coroutine_fn bdrv_replace_test_co_drain_end(BlockDriverState *bs)
g_assert(s->drain_count > 0);
if (!--s->drain_count) {
- int ret;
-
s->was_undrained = true;
if (bs->backing) {
- char data;
- QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1);
-
- /* Queue a read request post-drain */
- ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0);
- g_assert(ret >= 0);
+ Coroutine *co = qemu_coroutine_create(bdrv_replace_test_read_entry,
+ bs);
+ bdrv_inc_in_flight(bs);
+ aio_co_enter(bdrv_get_aio_context(bs), co);
}
}
}
--
2.31.1

505
SOURCES/kvm-tests-qtest-netdev-test-stream-and-dgram-backends.patch
Unescape View File

@ -0,0 +1,505 @@
From 39d5761fe1f546e764dedf2ea32c55d8f5222696 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 18 Jan 2023 13:04:05 +0100
Subject: [PATCH 1/8] tests/qtest: netdev: test stream and dgram backends
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 148: net: stream: add a new option to automatically reconnect
RH-Bugzilla: 2169232
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: David Gibson (Red Hat) <dgibson@redhat.com>
RH-Commit: [1/2] 75c71b47eea072e14651a96612d402b50d2b8f1e (lvivier/qemu-kvm-centos)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20230118120405.1876329-1-lvivier@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
(cherry picked from commit c95031a19f0d7f418a597243f6f84b031a858997)
---
tests/qtest/meson.build | 2 +
tests/qtest/netdev-socket.c | 448 ++++++++++++++++++++++++++++++++++++
2 files changed, 450 insertions(+)
create mode 100644 tests/qtest/netdev-socket.c
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index 9df3f9f8b9..2e7c6fe5e3 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -27,6 +27,7 @@ qtests_generic = [
'test-hmp',
'qos-test',
'readconfig-test',
+ 'netdev-socket',
]
if config_host.has_key('CONFIG_MODULES')
qtests_generic += [ 'modules-test' ]
@@ -299,6 +300,7 @@ qtests = {
'tpm-tis-device-swtpm-test': [io, tpmemu_files, 'tpm-tis-util.c'],
'tpm-tis-device-test': [io, tpmemu_files, 'tpm-tis-util.c'],
'vmgenid-test': files('boot-sector.c', 'acpi-utils.c'),
+ 'netdev-socket': files('netdev-socket.c', '../unit/socket-helpers.c'),
}
gvnc = dependency('gvnc-1.0', required: false)
diff --git a/tests/qtest/netdev-socket.c b/tests/qtest/netdev-socket.c
new file mode 100644
index 0000000000..6ba256e173
--- /dev/null
+++ b/tests/qtest/netdev-socket.c
@@ -0,0 +1,448 @@
+/*
+ * QTest testcase for netdev stream and dgram
+ *
+ * Copyright (c) 2022 Red Hat, Inc.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/sockets.h"
+#include <glib/gstdio.h>
+#include "../unit/socket-helpers.h"
+#include "libqtest.h"
+
+#define CONNECTION_TIMEOUT 5
+
+#define EXPECT_STATE(q, e, t) \
+do { \
+ char *resp = NULL; \
+ g_test_timer_start(); \
+ do { \
+ g_free(resp); \
+ resp = qtest_hmp(q, "info network"); \
+ if (t) { \
+ strrchr(resp, t)[0] = 0; \
+ } \
+ if (g_str_equal(resp, e)) { \
+ break; \
+ } \
+ } while (g_test_timer_elapsed() < CONNECTION_TIMEOUT); \
+ g_assert_cmpstr(resp, ==, e); \
+ g_free(resp); \
+} while (0)
+
+static gchar *tmpdir;
+
+static int inet_get_free_port_socket_ipv4(int sock)
+{
+ struct sockaddr_in addr;
+ socklen_t len;
+
+ memset(&addr, 0, sizeof(addr));
+ addr.sin_family = AF_INET;
+ addr.sin_addr.s_addr = INADDR_ANY;
+ addr.sin_port = 0;
+ if (bind(sock, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
+ return -1;
+ }
+
+ len = sizeof(addr);
+ if (getsockname(sock, (struct sockaddr *)&addr, &len) < 0) {
+ return -1;
+ }
+
+ return ntohs(addr.sin_port);
+}
+
+static int inet_get_free_port_socket_ipv6(int sock)
+{
+ struct sockaddr_in6 addr;
+ socklen_t len;
+
+ memset(&addr, 0, sizeof(addr));
+ addr.sin6_family = AF_INET6;
+ addr.sin6_addr = in6addr_any;
+ addr.sin6_port = 0;
+ if (bind(sock, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
+ return -1;
+ }
+
+ len = sizeof(addr);
+ if (getsockname(sock, (struct sockaddr *)&addr, &len) < 0) {
+ return -1;
+ }
+
+ return ntohs(addr.sin6_port);
+}
+
+static int inet_get_free_port_multiple(int nb, int *port, bool ipv6)
+{
+ int sock[nb];
+ int i;
+
+ for (i = 0; i < nb; i++) {
+ sock[i] = socket(ipv6 ? AF_INET6 : AF_INET, SOCK_STREAM, 0);
+ if (sock[i] < 0) {
+ break;
+ }
+ port[i] = ipv6 ? inet_get_free_port_socket_ipv6(sock[i]) :
+ inet_get_free_port_socket_ipv4(sock[i]);
+ if (port[i] == -1) {
+ break;
+ }
+ }
+
+ nb = i;
+ for (i = 0; i < nb; i++) {
+ closesocket(sock[i]);
+ }
+
+ return nb;
+}
+
+static int inet_get_free_port(bool ipv6)
+{
+ int nb, port;
+
+ nb = inet_get_free_port_multiple(1, &port, ipv6);
+ g_assert_cmpint(nb, ==, 1);
+
+ return port;
+}
+
+static void test_stream_inet_ipv4(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ int port;
+
+ port = inet_get_free_port(false);
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=true,addr.type=inet,"
+ "addr.ipv4=on,addr.ipv6=off,"
+ "addr.host=127.0.0.1,addr.port=%d", port);
+
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,\r\n", 0);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,server=false,id=st0,addr.type=inet,"
+ "addr.ipv4=on,addr.ipv6=off,"
+ "addr.host=127.0.0.1,addr.port=%d", port);
+
+ expect = g_strdup_printf("st0: index=0,type=stream,tcp:127.0.0.1:%d\r\n",
+ port);
+ EXPECT_STATE(qts1, expect, 0);
+ g_free(expect);
+
+ /* the port is unknown, check only the address */
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,tcp:127.0.0.1", ':');
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+
+static void test_stream_inet_ipv6(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ int port;
+
+ port = inet_get_free_port(true);
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=true,addr.type=inet,"
+ "addr.ipv4=off,addr.ipv6=on,"
+ "addr.host=::1,addr.port=%d", port);
+
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,\r\n", 0);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,server=false,id=st0,addr.type=inet,"
+ "addr.ipv4=off,addr.ipv6=on,"
+ "addr.host=::1,addr.port=%d", port);
+
+ expect = g_strdup_printf("st0: index=0,type=stream,tcp:::1:%d\r\n",
+ port);
+ EXPECT_STATE(qts1, expect, 0);
+ g_free(expect);
+
+ /* the port is unknown, check only the address */
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,tcp:::1", ':');
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+
+static void test_stream_unix(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ gchar *path;
+
+ path = g_strconcat(tmpdir, "/stream_unix", NULL);
+
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=true,"
+ "addr.type=unix,addr.path=%s,",
+ path);
+
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,\r\n", 0);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=false,"
+ "addr.type=unix,addr.path=%s",
+ path);
+
+ expect = g_strdup_printf("st0: index=0,type=stream,unix:%s\r\n", path);
+ EXPECT_STATE(qts1, expect, 0);
+ EXPECT_STATE(qts0, expect, 0);
+ g_free(expect);
+ g_free(path);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+
+#ifdef CONFIG_LINUX
+static void test_stream_unix_abstract(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ gchar *path;
+
+ path = g_strconcat(tmpdir, "/stream_unix_abstract", NULL);
+
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=true,"
+ "addr.type=unix,addr.path=%s,"
+ "addr.abstract=on",
+ path);
+
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,\r\n", 0);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,server=false,"
+ "addr.type=unix,addr.path=%s,addr.abstract=on",
+ path);
+
+ expect = g_strdup_printf("st0: index=0,type=stream,unix:%s\r\n", path);
+ EXPECT_STATE(qts1, expect, 0);
+ EXPECT_STATE(qts0, expect, 0);
+ g_free(expect);
+ g_free(path);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+#endif
+
+#ifndef _WIN32
+static void test_stream_fd(void)
+{
+ QTestState *qts0, *qts1;
+ int sock[2];
+ int ret;
+
+ ret = socketpair(AF_LOCAL, SOCK_STREAM, 0, sock);
+ g_assert_true(ret == 0);
+
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,addr.type=fd,addr.str=%d",
+ sock[0]);
+
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,unix:\r\n", 0);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev stream,id=st0,addr.type=fd,addr.str=%d",
+ sock[1]);
+
+ EXPECT_STATE(qts1, "st0: index=0,type=stream,unix:\r\n", 0);
+ EXPECT_STATE(qts0, "st0: index=0,type=stream,unix:\r\n", 0);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+
+ closesocket(sock[0]);
+ closesocket(sock[1]);
+}
+#endif
+
+static void test_dgram_inet(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ int port[2];
+ int nb;
+
+ nb = inet_get_free_port_multiple(2, port, false);
+ g_assert_cmpint(nb, ==, 2);
+
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,"
+ "local.type=inet,local.host=127.0.0.1,local.port=%d,"
+ "remote.type=inet,remote.host=127.0.0.1,remote.port=%d",
+ port[0], port[1]);
+
+ expect = g_strdup_printf("st0: index=0,type=dgram,"
+ "udp=127.0.0.1:%d/127.0.0.1:%d\r\n",
+ port[0], port[1]);
+ EXPECT_STATE(qts0, expect, 0);
+ g_free(expect);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,"
+ "local.type=inet,local.host=127.0.0.1,local.port=%d,"
+ "remote.type=inet,remote.host=127.0.0.1,remote.port=%d",
+ port[1], port[0]);
+
+ expect = g_strdup_printf("st0: index=0,type=dgram,"
+ "udp=127.0.0.1:%d/127.0.0.1:%d\r\n",
+ port[1], port[0]);
+ EXPECT_STATE(qts1, expect, 0);
+ g_free(expect);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+
+#ifndef _WIN32
+static void test_dgram_mcast(void)
+{
+ QTestState *qts;
+
+ qts = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,"
+ "remote.type=inet,remote.host=230.0.0.1,remote.port=1234");
+
+ EXPECT_STATE(qts, "st0: index=0,type=dgram,mcast=230.0.0.1:1234\r\n", 0);
+
+ qtest_quit(qts);
+}
+
+static void test_dgram_unix(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ gchar *path0, *path1;
+
+ path0 = g_strconcat(tmpdir, "/dgram_unix0", NULL);
+ path1 = g_strconcat(tmpdir, "/dgram_unix1", NULL);
+
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,local.type=unix,local.path=%s,"
+ "remote.type=unix,remote.path=%s",
+ path0, path1);
+
+ expect = g_strdup_printf("st0: index=0,type=dgram,udp=%s:%s\r\n",
+ path0, path1);
+ EXPECT_STATE(qts0, expect, 0);
+ g_free(expect);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,local.type=unix,local.path=%s,"
+ "remote.type=unix,remote.path=%s",
+ path1, path0);
+
+
+ expect = g_strdup_printf("st0: index=0,type=dgram,udp=%s:%s\r\n",
+ path1, path0);
+ EXPECT_STATE(qts1, expect, 0);
+ g_free(expect);
+
+ unlink(path0);
+ g_free(path0);
+ unlink(path1);
+ g_free(path1);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+}
+
+static void test_dgram_fd(void)
+{
+ QTestState *qts0, *qts1;
+ char *expect;
+ int ret;
+ int sv[2];
+
+ ret = socketpair(PF_UNIX, SOCK_DGRAM, 0, sv);
+ g_assert_cmpint(ret, !=, -1);
+
+ qts0 = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,local.type=fd,local.str=%d",
+ sv[0]);
+
+ expect = g_strdup_printf("st0: index=0,type=dgram,fd=%d unix\r\n", sv[0]);
+ EXPECT_STATE(qts0, expect, 0);
+ g_free(expect);
+
+ qts1 = qtest_initf("-nodefaults -M none "
+ "-netdev dgram,id=st0,local.type=fd,local.str=%d",
+ sv[1]);
+
+
+ expect = g_strdup_printf("st0: index=0,type=dgram,fd=%d unix\r\n", sv[1]);
+ EXPECT_STATE(qts1, expect, 0);
+ g_free(expect);
+
+ qtest_quit(qts1);
+ qtest_quit(qts0);
+
+ closesocket(sv[0]);
+ closesocket(sv[1]);
+}
+#endif
+
+int main(int argc, char **argv)
+{
+ int ret;
+ bool has_ipv4, has_ipv6, has_afunix;
+ g_autoptr(GError) err = NULL;
+
+ socket_init();
+ g_test_init(&argc, &argv, NULL);
+
+ if (socket_check_protocol_support(&has_ipv4, &has_ipv6) < 0) {
+ g_error("socket_check_protocol_support() failed\n");
+ }
+
+ tmpdir = g_dir_make_tmp("netdev-socket.XXXXXX", &err);
+ if (tmpdir == NULL) {
+ g_error("Can't create temporary directory in %s: %s",
+ g_get_tmp_dir(), err->message);
+ }
+
+ if (has_ipv4) {
+ qtest_add_func("/netdev/stream/inet/ipv4", test_stream_inet_ipv4);
+ qtest_add_func("/netdev/dgram/inet", test_dgram_inet);
+#ifndef _WIN32
+ qtest_add_func("/netdev/dgram/mcast", test_dgram_mcast);
+#endif
+ }
+ if (has_ipv6) {
+ qtest_add_func("/netdev/stream/inet/ipv6", test_stream_inet_ipv6);
+ }
+
+ socket_check_afunix_support(&has_afunix);
+ if (has_afunix) {
+#ifndef _WIN32
+ qtest_add_func("/netdev/dgram/unix", test_dgram_unix);
+#endif
+ qtest_add_func("/netdev/stream/unix", test_stream_unix);
+#ifdef CONFIG_LINUX
+ qtest_add_func("/netdev/stream/unix/abstract",
+ test_stream_unix_abstract);
+#endif
+#ifndef _WIN32
+ qtest_add_func("/netdev/stream/fd", test_stream_fd);
+ qtest_add_func("/netdev/dgram/fd", test_dgram_fd);
+#endif
+ }
+
+ ret = g_test_run();
+
+ g_rmdir(tmpdir);
+ g_free(tmpdir);
+
+ return ret;
+}
--
2.31.1

169
SOURCES/kvm-util-userfaultfd-Add-uffd_open.patch
Unescape View File

@ -0,0 +1,169 @@
From 80445fed73a7d1a87e8ce96f6cb7d505e437f845 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 1 Feb 2023 16:10:54 -0500
Subject: [PATCH 4/8] util/userfaultfd: Add uffd_open()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 149: Support /dev/userfaultfd
RH-Bugzilla: 2158704
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: quintela1 <quintela@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/3] 4c81696314ab26db47c3415fa2c2501c6a572b5c (peterx/qemu-kvm)
Add a helper to create the uffd handle.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit d5890ea0722831eea76a0efd23a496b3e8815fe8)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
include/qemu/userfaultfd.h | 12 ++++++++++++
migration/postcopy-ram.c | 11 +++++------
tests/qtest/migration-test.c | 4 ++--
util/userfaultfd.c | 13 +++++++++++--
4 files changed, 30 insertions(+), 10 deletions(-)
diff --git a/include/qemu/userfaultfd.h b/include/qemu/userfaultfd.h
index 6b74f92792..d764496f0b 100644
--- a/include/qemu/userfaultfd.h
+++ b/include/qemu/userfaultfd.h
@@ -13,10 +13,20 @@
#ifndef USERFAULTFD_H
#define USERFAULTFD_H
+#ifdef CONFIG_LINUX
+
#include "qemu/osdep.h"
#include "exec/hwaddr.h"
#include <linux/userfaultfd.h>
+/**
+ * uffd_open(): Open an userfaultfd handle for current context.
+ *
+ * @flags: The flags we want to pass in when creating the handle.
+ *
+ * Returns: the uffd handle if >=0, or <0 if error happens.
+ */
+int uffd_open(int flags);
int uffd_query_features(uint64_t *features);
int uffd_create_fd(uint64_t features, bool non_blocking);
void uffd_close_fd(int uffd_fd);
@@ -32,4 +42,6 @@ int uffd_wakeup(int uffd_fd, void *addr, uint64_t length);
int uffd_read_events(int uffd_fd, struct uffd_msg *msgs, int count);
bool uffd_poll_events(int uffd_fd, int tmo);
+#endif /* CONFIG_LINUX */
+
#endif /* USERFAULTFD_H */
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index b9a37ef255..0c55df0e52 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -37,6 +37,7 @@
#include "qemu-file.h"
#include "yank_functions.h"
#include "tls.h"
+#include "qemu/userfaultfd.h"
/* Arbitrary limit on size of each discard command,
* keeps them around ~200 bytes
@@ -226,11 +227,9 @@ static bool receive_ufd_features(uint64_t *features)
int ufd;
bool ret = true;
- /* if we are here __NR_userfaultfd should exists */
- ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ ufd = uffd_open(O_CLOEXEC);
if (ufd == -1) {
- error_report("%s: syscall __NR_userfaultfd failed: %s", __func__,
- strerror(errno));
+ error_report("%s: uffd_open() failed: %s", __func__, strerror(errno));
return false;
}
@@ -375,7 +374,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
goto out;
}
- ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ ufd = uffd_open(O_CLOEXEC);
if (ufd == -1) {
error_report("%s: userfaultfd not available: %s", __func__,
strerror(errno));
@@ -1160,7 +1159,7 @@ static int postcopy_temp_pages_setup(MigrationIncomingState *mis)
int postcopy_ram_incoming_setup(MigrationIncomingState *mis)
{
/* Open the fd for the kernel to give us userfaults */
- mis->userfault_fd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ mis->userfault_fd = uffd_open(O_CLOEXEC | O_NONBLOCK);
if (mis->userfault_fd == -1) {
error_report("%s: Failed to open userfault fd: %s", __func__,
strerror(errno));
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index dbde726adf..0100e1bdbc 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -61,14 +61,14 @@ static bool uffd_feature_thread_id;
#if defined(__linux__) && defined(__NR_userfaultfd) && defined(CONFIG_EVENTFD)
#include <sys/eventfd.h>
#include <sys/ioctl.h>
-#include <linux/userfaultfd.h>
+#include "qemu/userfaultfd.h"
static bool ufd_version_check(void)
{
struct uffdio_api api_struct;
uint64_t ioctl_mask;
- int ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ int ufd = uffd_open(O_CLOEXEC);
if (ufd == -1) {
g_test_message("Skipping test: userfaultfd not available");
diff --git a/util/userfaultfd.c b/util/userfaultfd.c
index f1cd6af2b1..4953b3137d 100644
--- a/util/userfaultfd.c
+++ b/util/userfaultfd.c
@@ -19,6 +19,15 @@
#include <sys/syscall.h>
#include <sys/ioctl.h>
+int uffd_open(int flags)
+{
+#if defined(__NR_userfaultfd)
+ return syscall(__NR_userfaultfd, flags);
+#else
+ return -EINVAL;
+#endif
+}
+
/**
* uffd_query_features: query UFFD features
*
@@ -32,7 +41,7 @@ int uffd_query_features(uint64_t *features)
struct uffdio_api api_struct = { 0 };
int ret = -1;
- uffd_fd = syscall(__NR_userfaultfd, O_CLOEXEC);
+ uffd_fd = uffd_open(O_CLOEXEC);
if (uffd_fd < 0) {
trace_uffd_query_features_nosys(errno);
return -1;
@@ -69,7 +78,7 @@ int uffd_create_fd(uint64_t features, bool non_blocking)
uint64_t ioctl_mask = BIT(_UFFDIO_REGISTER) | BIT(_UFFDIO_UNREGISTER);
flags = O_CLOEXEC | (non_blocking ? O_NONBLOCK : 0);
- uffd_fd = syscall(__NR_userfaultfd, flags);
+ uffd_fd = uffd_open(flags);
if (uffd_fd < 0) {
trace_uffd_create_fd_nosys(errno);
return -1;
--
2.31.1

94
SOURCES/kvm-util-userfaultfd-Support-dev-userfaultfd.patch
Unescape View File

@ -0,0 +1,94 @@
From a91da7741464dadeb306a741b4fb562e49ffea57 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 7 Feb 2023 15:57:11 -0500
Subject: [PATCH 5/8] util/userfaultfd: Support /dev/userfaultfd
RH-Author: Peter Xu <peterx@redhat.com>
RH-MergeRequest: 149: Support /dev/userfaultfd
RH-Bugzilla: 2158704
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: quintela1 <quintela@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/3] 5f427d8c18c210ff8f66724c9e358a7120619e69 (peterx/qemu-kvm)
Teach QEMU to use /dev/userfaultfd when it existed and fallback to the
system call if either it's not there or doesn't have enough permission.
Firstly, as long as the app has permission to access /dev/userfaultfd, it
always have the ability to trap kernel faults which QEMU mostly wants.
Meanwhile, in some context (e.g. containers) the userfaultfd syscall can be
forbidden, so it can be the major way to use postcopy in a restricted
environment with strict seccomp setup.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit c40c0463413b941c13fe5f99a90c02d7d6584828)
Signed-off-by: Peter Xu <peterx@redhat.com>
---
util/trace-events | 1 +
util/userfaultfd.c | 32 ++++++++++++++++++++++++++++++++
2 files changed, 33 insertions(+)
diff --git a/util/trace-events b/util/trace-events
index c8f53d7d9f..16f78d8fe5 100644
--- a/util/trace-events
+++ b/util/trace-events
@@ -93,6 +93,7 @@ qemu_vfio_region_info(const char *desc, uint64_t region_ofs, uint64_t region_siz
qemu_vfio_pci_map_bar(int index, uint64_t region_ofs, uint64_t region_size, int ofs, void *host) "map region bar#%d addr 0x%"PRIx64" size 0x%"PRIx64" ofs 0x%x host %p"
#userfaultfd.c
+uffd_detect_open_mode(int mode) "%d"
uffd_query_features_nosys(int err) "errno: %i"
uffd_query_features_api_failed(int err) "errno: %i"
uffd_create_fd_nosys(int err) "errno: %i"
diff --git a/util/userfaultfd.c b/util/userfaultfd.c
index 4953b3137d..fdff4867e8 100644
--- a/util/userfaultfd.c
+++ b/util/userfaultfd.c
@@ -18,10 +18,42 @@
#include <poll.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
+#include <fcntl.h>
+
+typedef enum {
+ UFFD_UNINITIALIZED = 0,
+ UFFD_USE_DEV_PATH,
+ UFFD_USE_SYSCALL,
+} uffd_open_mode;
int uffd_open(int flags)
{
#if defined(__NR_userfaultfd)
+ static uffd_open_mode open_mode;
+ static int uffd_dev;
+
+ /* Detect how to generate uffd desc when run the 1st time */
+ if (open_mode == UFFD_UNINITIALIZED) {
+ /*
+ * Make /dev/userfaultfd the default approach because it has better
+ * permission controls, meanwhile allows kernel faults without any
+ * privilege requirement (e.g. SYS_CAP_PTRACE).
+ */
+ uffd_dev = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC);
+ if (uffd_dev >= 0) {
+ open_mode = UFFD_USE_DEV_PATH;
+ } else {
+ /* Fallback to the system call */
+ open_mode = UFFD_USE_SYSCALL;
+ }
+ trace_uffd_detect_open_mode(open_mode);
+ }
+
+ if (open_mode == UFFD_USE_DEV_PATH) {
+ assert(uffd_dev >= 0);
+ return ioctl(uffd_dev, USERFAULTFD_IOC_NEW, flags);
+ }
+
return syscall(__NR_userfaultfd, flags);
#else
return -EINVAL;
--
2.31.1

221
SOURCES/kvm-vdpa-add-asid-parameter-to-vhost_vdpa_dma_map-unmap.patch
Unescape View File

@ -0,0 +1,221 @@
From d0e7f24a8d941ab142f2a1973ae18ed1bfdc074f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:41 +0100
Subject: [PATCH 09/14] vdpa: add asid parameter to vhost_vdpa_dma_map/unmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [9/13] 3e7f89e57f73661017ccf0206f2ea77a72ca46bb (eperezmartin/qemu-kvm)
So the caller can choose which ASID is destined.
No need to update the batch functions as they will always be called from
memory listener updates at the moment. Memory listener updates will
always update ASID 0, as it's the passthrough ASID.
All vhost devices's ASID are 0 at this moment.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-10-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit cd831ed5c4add8ed6ee980c3645b241cbef5130f)
---
hw/virtio/trace-events | 4 ++--
hw/virtio/vhost-vdpa.c | 36 +++++++++++++++++++++++-----------
include/hw/virtio/vhost-vdpa.h | 14 ++++++++++---
net/vhost-vdpa.c | 6 +++---
4 files changed, 41 insertions(+), 19 deletions(-)
diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 46f2faf04e..a87c5f39a2 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -30,8 +30,8 @@ vhost_user_write(uint32_t req, uint32_t flags) "req:%d flags:0x%"PRIx32""
vhost_user_create_notifier(int idx, void *n) "idx:%d n:%p"
# vhost-vdpa.c
-vhost_vdpa_dma_map(void *vdpa, int fd, uint32_t msg_type, uint64_t iova, uint64_t size, uint64_t uaddr, uint8_t perm, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" uaddr: 0x%"PRIx64" perm: 0x%"PRIx8" type: %"PRIu8
-vhost_vdpa_dma_unmap(void *vdpa, int fd, uint32_t msg_type, uint64_t iova, uint64_t size, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" type: %"PRIu8
+vhost_vdpa_dma_map(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint64_t uaddr, uint8_t perm, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" uaddr: 0x%"PRIx64" perm: 0x%"PRIx8" type: %"PRIu8
+vhost_vdpa_dma_unmap(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" type: %"PRIu8
vhost_vdpa_listener_begin_batch(void *v, int fd, uint32_t msg_type, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
vhost_vdpa_listener_commit(void *v, int fd, uint32_t msg_type, uint8_t type) "vdpa:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
vhost_vdpa_listener_region_add(void *vdpa, uint64_t iova, uint64_t llend, void *vaddr, bool readonly) "vdpa: %p iova 0x%"PRIx64" llend 0x%"PRIx64" vaddr: %p read-only: %d"
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index dd2768634b..0ecf2bbaa0 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -72,22 +72,28 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section,
return false;
}
-int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
- void *vaddr, bool readonly)
+/*
+ * The caller must set asid = 0 if the device does not support asid.
+ * This is not an ABI break since it is set to 0 by the initializer anyway.
+ */
+int vhost_vdpa_dma_map(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
+ hwaddr size, void *vaddr, bool readonly)
{
struct vhost_msg_v2 msg = {};
int fd = v->device_fd;
int ret = 0;
msg.type = v->msg_type;
+ msg.asid = asid;
msg.iotlb.iova = iova;
msg.iotlb.size = size;
msg.iotlb.uaddr = (uint64_t)(uintptr_t)vaddr;
msg.iotlb.perm = readonly ? VHOST_ACCESS_RO : VHOST_ACCESS_RW;
msg.iotlb.type = VHOST_IOTLB_UPDATE;
- trace_vhost_vdpa_dma_map(v, fd, msg.type, msg.iotlb.iova, msg.iotlb.size,
- msg.iotlb.uaddr, msg.iotlb.perm, msg.iotlb.type);
+ trace_vhost_vdpa_dma_map(v, fd, msg.type, msg.asid, msg.iotlb.iova,
+ msg.iotlb.size, msg.iotlb.uaddr, msg.iotlb.perm,
+ msg.iotlb.type);
if (write(fd, &msg, sizeof(msg)) != sizeof(msg)) {
error_report("failed to write, fd=%d, errno=%d (%s)",
@@ -98,18 +104,24 @@ int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
return ret;
}
-int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, hwaddr size)
+/*
+ * The caller must set asid = 0 if the device does not support asid.
+ * This is not an ABI break since it is set to 0 by the initializer anyway.
+ */
+int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
+ hwaddr size)
{
struct vhost_msg_v2 msg = {};
int fd = v->device_fd;
int ret = 0;
msg.type = v->msg_type;
+ msg.asid = asid;
msg.iotlb.iova = iova;
msg.iotlb.size = size;
msg.iotlb.type = VHOST_IOTLB_INVALIDATE;
- trace_vhost_vdpa_dma_unmap(v, fd, msg.type, msg.iotlb.iova,
+ trace_vhost_vdpa_dma_unmap(v, fd, msg.type, msg.asid, msg.iotlb.iova,
msg.iotlb.size, msg.iotlb.type);
if (write(fd, &msg, sizeof(msg)) != sizeof(msg)) {
@@ -229,8 +241,8 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
}
vhost_vdpa_iotlb_batch_begin_once(v);
- ret = vhost_vdpa_dma_map(v, iova, int128_get64(llsize),
- vaddr, section->readonly);
+ ret = vhost_vdpa_dma_map(v, VHOST_VDPA_GUEST_PA_ASID, iova,
+ int128_get64(llsize), vaddr, section->readonly);
if (ret) {
error_report("vhost vdpa map fail!");
goto fail_map;
@@ -303,7 +315,8 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
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));
+ ret = vhost_vdpa_dma_unmap(v, VHOST_VDPA_GUEST_PA_ASID, iova,
+ int128_get64(llsize));
if (ret) {
error_report("vhost_vdpa dma unmap error!");
}
@@ -876,7 +889,7 @@ static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr addr)
}
size = ROUND_UP(result->size, qemu_real_host_page_size());
- r = vhost_vdpa_dma_unmap(v, result->iova, size);
+ r = vhost_vdpa_dma_unmap(v, v->address_space_id, result->iova, size);
if (unlikely(r < 0)) {
error_report("Unable to unmap SVQ vring: %s (%d)", g_strerror(-r), -r);
return;
@@ -916,7 +929,8 @@ static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle,
return false;
}
- r = vhost_vdpa_dma_map(v, needle->iova, needle->size + 1,
+ r = vhost_vdpa_dma_map(v, v->address_space_id, needle->iova,
+ needle->size + 1,
(void *)(uintptr_t)needle->translated_addr,
needle->perm == IOMMU_RO);
if (unlikely(r != 0)) {
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index 1111d85643..e57dfa1fd1 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -19,6 +19,12 @@
#include "hw/virtio/virtio.h"
#include "standard-headers/linux/vhost_types.h"
+/*
+ * ASID dedicated to map guest's addresses. If SVQ is disabled it maps GPA to
+ * qemu's IOVA. If SVQ is enabled it maps also the SVQ vring here
+ */
+#define VHOST_VDPA_GUEST_PA_ASID 0
+
typedef struct VhostVDPAHostNotifier {
MemoryRegion mr;
void *addr;
@@ -29,6 +35,7 @@ typedef struct vhost_vdpa {
int index;
uint32_t msg_type;
bool iotlb_batch_begin_sent;
+ uint32_t address_space_id;
MemoryListener listener;
struct vhost_vdpa_iova_range iova_range;
uint64_t acked_features;
@@ -42,8 +49,9 @@ typedef struct vhost_vdpa {
VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];
} VhostVDPA;
-int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
- void *vaddr, bool readonly);
-int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, hwaddr size);
+int vhost_vdpa_dma_map(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
+ hwaddr size, void *vaddr, bool readonly);
+int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, uint32_t asid, hwaddr iova,
+ hwaddr size);
#endif
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 85aa0da39a..c2f319eb88 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -258,7 +258,7 @@ static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
return;
}
- r = vhost_vdpa_dma_unmap(v, map->iova, map->size + 1);
+ r = vhost_vdpa_dma_unmap(v, v->address_space_id, map->iova, map->size + 1);
if (unlikely(r != 0)) {
error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
}
@@ -298,8 +298,8 @@ static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size,
return r;
}
- r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf,
- !write);
+ r = vhost_vdpa_dma_map(v, v->address_space_id, map.iova,
+ vhost_vdpa_net_cvq_cmd_page_len(), buf, !write);
if (unlikely(r < 0)) {
goto dma_map_err;
}
--
2.31.1

94
SOURCES/kvm-vdpa-add-shadow_data-to-vhost_vdpa.patch
Unescape View File

@ -0,0 +1,94 @@
From 6282a83619f274ca45a52d61577c10a05a0714dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:43 +0100
Subject: [PATCH 11/14] vdpa: add shadow_data to vhost_vdpa
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [11/13] 9d317add1318b555ba06e19e4c67849069e047b9 (eperezmartin/qemu-kvm)
The memory listener that thells the device how to convert GPA to qemu's
va is registered against CVQ vhost_vdpa. memory listener translations
are always ASID 0, CVQ ones are ASID 1 if supported.
Let's tell the listener if it needs to register them on iova tree or
not.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-12-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 6188d78a19894ac8f2bf9484d48a5235a529d3b7)
---
hw/virtio/vhost-vdpa.c | 6 +++---
include/hw/virtio/vhost-vdpa.h | 2 ++
net/vhost-vdpa.c | 1 +
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 0ecf2bbaa0..dc3498e995 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -224,7 +224,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
vaddr, section->readonly);
llsize = int128_sub(llend, int128_make64(iova));
- if (v->shadow_vqs_enabled) {
+ if (v->shadow_data) {
int r;
mem_region.translated_addr = (hwaddr)(uintptr_t)vaddr,
@@ -251,7 +251,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
return;
fail_map:
- if (v->shadow_vqs_enabled) {
+ if (v->shadow_data) {
vhost_iova_tree_remove(v->iova_tree, mem_region);
}
@@ -296,7 +296,7 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
llsize = int128_sub(llend, int128_make64(iova));
- if (v->shadow_vqs_enabled) {
+ if (v->shadow_data) {
const DMAMap *result;
const void *vaddr = memory_region_get_ram_ptr(section->mr) +
section->offset_within_region +
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index e57dfa1fd1..45b969a311 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -40,6 +40,8 @@ typedef struct vhost_vdpa {
struct vhost_vdpa_iova_range iova_range;
uint64_t acked_features;
bool shadow_vqs_enabled;
+ /* Vdpa must send shadow addresses as IOTLB key for data queues, not GPA */
+ bool shadow_data;
/* IOVA mapping used by the Shadow Virtqueue */
VhostIOVATree *iova_tree;
GPtrArray *shadow_vqs;
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 1757f1d028..eea7a0df12 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -581,6 +581,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
s->always_svq = svq;
s->vhost_vdpa.shadow_vqs_enabled = svq;
s->vhost_vdpa.iova_range = iova_range;
+ s->vhost_vdpa.shadow_data = svq;
s->vhost_vdpa.iova_tree = iova_tree;
if (!is_datapath) {
s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size(),
--
2.31.1

76
SOURCES/kvm-vdpa-add-vhost_vdpa_net_valid_svq_features.patch
Unescape View File

@ -0,0 +1,76 @@
From 0f3a28e1e128754184c4af6a578f27e16c6a61d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:37 +0100
Subject: [PATCH 05/14] vdpa: add vhost_vdpa_net_valid_svq_features
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [5/13] 0b27e04f178ec73cb800f4fb05c17a92576142e4 (eperezmartin/qemu-kvm)
It will be reused at vdpa device start so let's extract in its own
function.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-6-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 36e4647247f200b6fa4d2f656133f567036e8a85)
---
net/vhost-vdpa.c | 26 +++++++++++++++++---------
1 file changed, 17 insertions(+), 9 deletions(-)
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index b06540ac89..16a5ebe2dd 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -106,6 +106,22 @@ VHostNetState *vhost_vdpa_get_vhost_net(NetClientState *nc)
return s->vhost_net;
}
+static bool vhost_vdpa_net_valid_svq_features(uint64_t features, Error **errp)
+{
+ uint64_t invalid_dev_features =
+ features & ~vdpa_svq_device_features &
+ /* Transport are all accepted at this point */
+ ~MAKE_64BIT_MASK(VIRTIO_TRANSPORT_F_START,
+ VIRTIO_TRANSPORT_F_END - VIRTIO_TRANSPORT_F_START);
+
+ if (invalid_dev_features) {
+ error_setg(errp, "vdpa svq does not work with features 0x%" PRIx64,
+ invalid_dev_features);
+ }
+
+ return !invalid_dev_features;
+}
+
static int vhost_vdpa_net_check_device_id(struct vhost_net *net)
{
uint32_t device_id;
@@ -684,15 +700,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
if (opts->x_svq) {
struct vhost_vdpa_iova_range iova_range;
- uint64_t invalid_dev_features =
- features & ~vdpa_svq_device_features &
- /* Transport are all accepted at this point */
- ~MAKE_64BIT_MASK(VIRTIO_TRANSPORT_F_START,
- VIRTIO_TRANSPORT_F_END - VIRTIO_TRANSPORT_F_START);
-
- if (invalid_dev_features) {
- error_setg(errp, "vdpa svq does not work with features 0x%" PRIx64,
- invalid_dev_features);
+ if (!vhost_vdpa_net_valid_svq_features(features, errp)) {
goto err_svq;
}
--
2.31.1

50
SOURCES/kvm-vdpa-allocate-SVQ-array-unconditionally.patch
Unescape View File

@ -0,0 +1,50 @@
From 72f296870805750df8dfe5eaad77dd7d435a8f41 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:40 +0100
Subject: [PATCH 08/14] vdpa: allocate SVQ array unconditionally
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [8/13] 08cd86d0859f82d768794e29241cfeff25df667c (eperezmartin/qemu-kvm)
SVQ may run or not in a device depending on runtime conditions (for
example, if the device can move CVQ to its own group or not).
Allocate the SVQ array unconditionally at startup, since its hard to
move this allocation elsewhere.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-9-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 273e0003f0005cc17292dedae01e5edb0064b69c)
---
hw/virtio/vhost-vdpa.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 84218ce078..dd2768634b 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -532,10 +532,6 @@ static void vhost_vdpa_svq_cleanup(struct vhost_dev *dev)
struct vhost_vdpa *v = dev->opaque;
size_t idx;
- if (!v->shadow_vqs) {
- return;
- }
-
for (idx = 0; idx < v->shadow_vqs->len; ++idx) {
vhost_svq_stop(g_ptr_array_index(v->shadow_vqs, idx));
}
--
2.31.1

193
SOURCES/kvm-vdpa-always-start-CVQ-in-SVQ-mode-if-possible.patch
Unescape View File

@ -0,0 +1,193 @@
From 84c203faa570b85eec006215768c83371c9f0399 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:44 +0100
Subject: [PATCH 12/14] vdpa: always start CVQ in SVQ mode if possible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [12/13] 83f94b3e163ca38d08dbf7c111a4cfa7a44e3dc2 (eperezmartin/qemu-kvm)
Isolate control virtqueue in its own group, allowing to intercept control
commands but letting dataplane run totally passthrough to the guest.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20221215113144.322011-13-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit c1a1008685af0327d9d03f03d43bdb77e7af5bea)
---
hw/virtio/vhost-vdpa.c | 3 +-
net/vhost-vdpa.c | 110 ++++++++++++++++++++++++++++++++++++++++-
2 files changed, 111 insertions(+), 2 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index dc3498e995..72ff06673c 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -638,7 +638,8 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev)
{
uint64_t features;
uint64_t f = 0x1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2 |
- 0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH;
+ 0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH |
+ 0x1ULL << VHOST_BACKEND_F_IOTLB_ASID;
int r;
if (vhost_vdpa_call(dev, VHOST_GET_BACKEND_FEATURES, &features)) {
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index eea7a0df12..07d33dae26 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -101,6 +101,8 @@ static const uint64_t vdpa_svq_device_features =
BIT_ULL(VIRTIO_NET_F_RSC_EXT) |
BIT_ULL(VIRTIO_NET_F_STANDBY);
+#define VHOST_VDPA_NET_CVQ_ASID 1
+
VHostNetState *vhost_vdpa_get_vhost_net(NetClientState *nc)
{
VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
@@ -242,6 +244,40 @@ static NetClientInfo net_vhost_vdpa_info = {
.check_peer_type = vhost_vdpa_check_peer_type,
};
+static int64_t vhost_vdpa_get_vring_group(int device_fd, unsigned vq_index)
+{
+ struct vhost_vring_state state = {
+ .index = vq_index,
+ };
+ int r = ioctl(device_fd, VHOST_VDPA_GET_VRING_GROUP, &state);
+
+ if (unlikely(r < 0)) {
+ error_report("Cannot get VQ %u group: %s", vq_index,
+ g_strerror(errno));
+ return r;
+ }
+
+ return state.num;
+}
+
+static int vhost_vdpa_set_address_space_id(struct vhost_vdpa *v,
+ unsigned vq_group,
+ unsigned asid_num)
+{
+ struct vhost_vring_state asid = {
+ .index = vq_group,
+ .num = asid_num,
+ };
+ int r;
+
+ r = ioctl(v->device_fd, VHOST_VDPA_SET_GROUP_ASID, &asid);
+ if (unlikely(r < 0)) {
+ error_report("Can't set vq group %u asid %u, errno=%d (%s)",
+ asid.index, asid.num, errno, g_strerror(errno));
+ }
+ return r;
+}
+
static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
{
VhostIOVATree *tree = v->iova_tree;
@@ -316,11 +352,75 @@ dma_map_err:
static int vhost_vdpa_net_cvq_start(NetClientState *nc)
{
VhostVDPAState *s;
- int r;
+ struct vhost_vdpa *v;
+ uint64_t backend_features;
+ int64_t cvq_group;
+ int cvq_index, r;
assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
s = DO_UPCAST(VhostVDPAState, nc, nc);
+ v = &s->vhost_vdpa;
+
+ v->shadow_data = s->always_svq;
+ v->shadow_vqs_enabled = s->always_svq;
+ s->vhost_vdpa.address_space_id = VHOST_VDPA_GUEST_PA_ASID;
+
+ if (s->always_svq) {
+ /* SVQ is already configured for all virtqueues */
+ goto out;
+ }
+
+ /*
+ * If we early return in these cases SVQ will not be enabled. The migration
+ * will be blocked as long as vhost-vdpa backends will not offer _F_LOG.
+ *
+ * Calling VHOST_GET_BACKEND_FEATURES as they are not available in v->dev
+ * yet.
+ */
+ r = ioctl(v->device_fd, VHOST_GET_BACKEND_FEATURES, &backend_features);
+ if (unlikely(r < 0)) {
+ error_report("Cannot get vdpa backend_features: %s(%d)",
+ g_strerror(errno), errno);
+ return -1;
+ }
+ if (!(backend_features & VHOST_BACKEND_F_IOTLB_ASID) ||
+ !vhost_vdpa_net_valid_svq_features(v->dev->features, NULL)) {
+ return 0;
+ }
+
+ /*
+ * Check if all the virtqueues of the virtio device are in a different vq
+ * than the last vq. VQ group of last group passed in cvq_group.
+ */
+ cvq_index = v->dev->vq_index_end - 1;
+ cvq_group = vhost_vdpa_get_vring_group(v->device_fd, cvq_index);
+ if (unlikely(cvq_group < 0)) {
+ return cvq_group;
+ }
+ for (int i = 0; i < cvq_index; ++i) {
+ int64_t group = vhost_vdpa_get_vring_group(v->device_fd, i);
+
+ if (unlikely(group < 0)) {
+ return group;
+ }
+
+ if (group == cvq_group) {
+ return 0;
+ }
+ }
+
+ r = vhost_vdpa_set_address_space_id(v, cvq_group, VHOST_VDPA_NET_CVQ_ASID);
+ if (unlikely(r < 0)) {
+ return r;
+ }
+
+ v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
+ v->iova_range.last);
+ v->shadow_vqs_enabled = true;
+ s->vhost_vdpa.address_space_id = VHOST_VDPA_NET_CVQ_ASID;
+
+out:
if (!s->vhost_vdpa.shadow_vqs_enabled) {
return 0;
}
@@ -349,6 +449,14 @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
if (s->vhost_vdpa.shadow_vqs_enabled) {
vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->status);
+ if (!s->always_svq) {
+ /*
+ * If only the CVQ is shadowed we can delete this safely.
+ * If all the VQs are shadows this will be needed by the time the
+ * device is started again to register SVQ vrings and similar.
+ */
+ g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
+ }
}
}
--
2.31.1

44
SOURCES/kvm-vdpa-do-not-handle-VIRTIO_NET_F_GUEST_ANNOUNCE-in-vh.patch
Unescape View File

@ -0,0 +1,44 @@
From fbb177ad84d562a20e51e71c73257d2ef85be2d9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Wed, 21 Dec 2022 12:50:15 +0100
Subject: [PATCH 4/9] vdpa: do not handle VIRTIO_NET_F_GUEST_ANNOUNCE in
vhost-vdpa
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 137: vDPA net SVQ guest announce support
RH-Bugzilla: 2141088
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Jason Wang <jasowang@redhat.com>
RH-Commit: [4/4] b3960a8b3e4ca569b1b1e6ceccf2051d8c4b1079 (eperezmartin/qemu-kvm)
So qemu emulates it even in case the device does not support it.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221221115015.1400889-5-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 980003debddd18306ea2e1364b96598383c0e257)
---
net/vhost-vdpa.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 52ef9cb3a2..b06540ac89 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -72,7 +72,6 @@ const int vdpa_feature_bits[] = {
VIRTIO_F_RING_RESET,
VIRTIO_NET_F_RSS,
VIRTIO_NET_F_HASH_REPORT,
- VIRTIO_NET_F_GUEST_ANNOUNCE,
VIRTIO_NET_F_STATUS,
VHOST_INVALID_FEATURE_BIT
};
--
2.31.1

48
SOURCES/kvm-vdpa-fix-VHOST_BACKEND_F_IOTLB_ASID-flag-check.patch
Unescape View File

@ -0,0 +1,48 @@
From 46e80a9350a02fdb5689638df96bc7389e953cf8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Tue, 17 Jan 2023 11:53:08 +0100
Subject: [PATCH 13/14] vdpa: fix VHOST_BACKEND_F_IOTLB_ASID flag check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [13/13] b7fb4b8e9ea26b6664a9179ed0a88376acf5115f (eperezmartin/qemu-kvm)
VHOST_BACKEND_F_IOTLB_ASID is the feature bit, not the bitmask. Since
the device under test also provided VHOST_BACKEND_F_IOTLB_MSG_V2 and
VHOST_BACKEND_F_IOTLB_BATCH, this went unnoticed.
Fixes: c1a1008685 ("vdpa: always start CVQ in SVQ mode if possible")
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Upstream status: git@github.com:jasowang/qemu.git
(cherry picked from commit 2bd492bca521ee8594f1d5db8dc9aac126fc4f85)
---
net/vhost-vdpa.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 07d33dae26..7d9c4ea09d 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -384,7 +384,7 @@ static int vhost_vdpa_net_cvq_start(NetClientState *nc)
g_strerror(errno), errno);
return -1;
}
- if (!(backend_features & VHOST_BACKEND_F_IOTLB_ASID) ||
+ if (!(backend_features & BIT_ULL(VHOST_BACKEND_F_IOTLB_ASID)) ||
!vhost_vdpa_net_valid_svq_features(v->dev->features, NULL)) {
return 0;
}
--
2.31.1

59
SOURCES/kvm-vdpa-handle-VIRTIO_NET_CTRL_ANNOUNCE-in-vhost_vdpa_n.patch
Unescape View File

@ -0,0 +1,59 @@
From b71724e94c94acd6e09fed2b47be2901799c2353 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Wed, 21 Dec 2022 12:50:14 +0100
Subject: [PATCH 3/9] vdpa: handle VIRTIO_NET_CTRL_ANNOUNCE in
vhost_vdpa_net_handle_ctrl_avail
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 137: vDPA net SVQ guest announce support
RH-Bugzilla: 2141088
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Jason Wang <jasowang@redhat.com>
RH-Commit: [3/4] c4ef5b62a5d41911565b8960a88bb48d746ff6c7 (eperezmartin/qemu-kvm)
Since this capability is emulated by qemu shadowed CVQ cannot forward it
to the device. Process all that command within qemu.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20221221115015.1400889-4-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 3f9a3eeb7ca6acd899e2205a9118928b4cd94e47)
---
net/vhost-vdpa.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 2b4b85d8f8..52ef9cb3a2 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -489,9 +489,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0,
s->cvq_cmd_out_buffer,
vhost_vdpa_net_cvq_cmd_len());
- dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status));
- if (unlikely(dev_written < 0)) {
- goto out;
+ if (*(uint8_t *)s->cvq_cmd_out_buffer == VIRTIO_NET_CTRL_ANNOUNCE) {
+ /*
+ * Guest announce capability is emulated by qemu, so don't forward to
+ * the device.
+ */
+ dev_written = sizeof(status);
+ *s->status = VIRTIO_NET_OK;
+ } else {
+ dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status));
+ if (unlikely(dev_written < 0)) {
+ goto out;
+ }
}
if (unlikely(dev_written < sizeof(status))) {
--
2.31.1

118
SOURCES/kvm-vdpa-move-SVQ-vring-features-check-to-net.patch
Unescape View File

@ -0,0 +1,118 @@
From 63a45add7c9f7bb2b7775ae4cb2d7df22f7f2033 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:39 +0100
Subject: [PATCH 07/14] vdpa: move SVQ vring features check to net/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [7/13] a24189aea4dbde3ed4486f685d0d88aeee1a0ee7 (eperezmartin/qemu-kvm)
The next patches will start control SVQ if possible. However, we don't
know if that will be possible at qemu boot anymore.
Since the moved checks will be already evaluated at net/ to know if it
is ok to shadow CVQ, move them.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-8-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 258a03941fd23108a322d09abc9c55341e09688d)
---
hw/virtio/vhost-vdpa.c | 32 ++------------------------------
net/vhost-vdpa.c | 3 ++-
2 files changed, 4 insertions(+), 31 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 9e7cbf1776..84218ce078 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -389,29 +389,9 @@ static int vhost_vdpa_get_dev_features(struct vhost_dev *dev,
return ret;
}
-static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v,
- Error **errp)
+static void vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v)
{
g_autoptr(GPtrArray) shadow_vqs = NULL;
- uint64_t dev_features, svq_features;
- int r;
- bool ok;
-
- if (!v->shadow_vqs_enabled) {
- return 0;
- }
-
- r = vhost_vdpa_get_dev_features(hdev, &dev_features);
- if (r != 0) {
- error_setg_errno(errp, -r, "Can't get vdpa device features");
- return r;
- }
-
- svq_features = dev_features;
- ok = vhost_svq_valid_features(svq_features, errp);
- if (unlikely(!ok)) {
- return -1;
- }
shadow_vqs = g_ptr_array_new_full(hdev->nvqs, vhost_svq_free);
for (unsigned n = 0; n < hdev->nvqs; ++n) {
@@ -422,7 +402,6 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v,
}
v->shadow_vqs = g_steal_pointer(&shadow_vqs);
- return 0;
}
static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp)
@@ -447,10 +426,7 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp)
dev->opaque = opaque ;
v->listener = vhost_vdpa_memory_listener;
v->msg_type = VHOST_IOTLB_MSG_V2;
- ret = vhost_vdpa_init_svq(dev, v, errp);
- if (ret) {
- goto err;
- }
+ vhost_vdpa_init_svq(dev, v);
if (!vhost_vdpa_first_dev(dev)) {
return 0;
@@ -460,10 +436,6 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp)
VIRTIO_CONFIG_S_DRIVER);
return 0;
-
-err:
- ram_block_discard_disable(false);
- return ret;
}
static void vhost_vdpa_host_notifier_uninit(struct vhost_dev *dev,
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 8d3ed095d0..85aa0da39a 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -117,9 +117,10 @@ static bool vhost_vdpa_net_valid_svq_features(uint64_t features, Error **errp)
if (invalid_dev_features) {
error_setg(errp, "vdpa svq does not work with features 0x%" PRIx64,
invalid_dev_features);
+ return false;
}
- return !invalid_dev_features;
+ return vhost_svq_valid_features(features, errp);
}
static int vhost_vdpa_net_check_device_id(struct vhost_net *net)
--
2.31.1

145
SOURCES/kvm-vdpa-request-iova_range-only-once.patch
Unescape View File

@ -0,0 +1,145 @@
From 760169d538a4e6ba61006f6796cd55af967a7f1e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:38 +0100
Subject: [PATCH 06/14] vdpa: request iova_range only once
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [6/13] 2a8ae2f46ae88f01c5535038f38cb7895098b610 (eperezmartin/qemu-kvm)
Currently iova range is requested once per queue pair in the case of
net. Reduce the number of ioctls asking it once at initialization and
reusing that value for each vhost_vdpa.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20221215113144.322011-7-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasonwang@redhat.com>
(cherry picked from commit a585fad26b2e6ccca156d9e65158ad1c5efd268d)
---
hw/virtio/vhost-vdpa.c | 15 ---------------
net/vhost-vdpa.c | 27 ++++++++++++++-------------
2 files changed, 14 insertions(+), 28 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index e65603022f..9e7cbf1776 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -365,19 +365,6 @@ static int vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status)
return 0;
}
-static void vhost_vdpa_get_iova_range(struct vhost_vdpa *v)
-{
- int ret = vhost_vdpa_call(v->dev, VHOST_VDPA_GET_IOVA_RANGE,
- &v->iova_range);
- if (ret != 0) {
- v->iova_range.first = 0;
- v->iova_range.last = UINT64_MAX;
- }
-
- trace_vhost_vdpa_get_iova_range(v->dev, v->iova_range.first,
- v->iova_range.last);
-}
-
/*
* The use of this function is for requests that only need to be
* applied once. Typically such request occurs at the beginning
@@ -465,8 +452,6 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp)
goto err;
}
- vhost_vdpa_get_iova_range(v);
-
if (!vhost_vdpa_first_dev(dev)) {
return 0;
}
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 16a5ebe2dd..8d3ed095d0 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -549,14 +549,15 @@ static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = {
};
static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
- const char *device,
- const char *name,
- int vdpa_device_fd,
- int queue_pair_index,
- int nvqs,
- bool is_datapath,
- bool svq,
- VhostIOVATree *iova_tree)
+ const char *device,
+ const char *name,
+ int vdpa_device_fd,
+ int queue_pair_index,
+ int nvqs,
+ bool is_datapath,
+ bool svq,
+ struct vhost_vdpa_iova_range iova_range,
+ VhostIOVATree *iova_tree)
{
NetClientState *nc = NULL;
VhostVDPAState *s;
@@ -575,6 +576,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
s->vhost_vdpa.device_fd = vdpa_device_fd;
s->vhost_vdpa.index = queue_pair_index;
s->vhost_vdpa.shadow_vqs_enabled = svq;
+ s->vhost_vdpa.iova_range = iova_range;
s->vhost_vdpa.iova_tree = iova_tree;
if (!is_datapath) {
s->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size(),
@@ -654,6 +656,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
int vdpa_device_fd;
g_autofree NetClientState **ncs = NULL;
g_autoptr(VhostIOVATree) iova_tree = NULL;
+ struct vhost_vdpa_iova_range iova_range;
NetClientState *nc;
int queue_pairs, r, i = 0, has_cvq = 0;
@@ -697,14 +700,12 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
return queue_pairs;
}
+ vhost_vdpa_get_iova_range(vdpa_device_fd, &iova_range);
if (opts->x_svq) {
- struct vhost_vdpa_iova_range iova_range;
-
if (!vhost_vdpa_net_valid_svq_features(features, errp)) {
goto err_svq;
}
- vhost_vdpa_get_iova_range(vdpa_device_fd, &iova_range);
iova_tree = vhost_iova_tree_new(iova_range.first, iova_range.last);
}
@@ -713,7 +714,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
for (i = 0; i < queue_pairs; i++) {
ncs[i] = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
vdpa_device_fd, i, 2, true, opts->x_svq,
- iova_tree);
+ iova_range, iova_tree);
if (!ncs[i])
goto err;
}
@@ -721,7 +722,7 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
if (has_cvq) {
nc = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
vdpa_device_fd, i, 1, false,
- opts->x_svq, iova_tree);
+ opts->x_svq, iova_range, iova_tree);
if (!nc)
goto err;
}
--
2.31.1

62
SOURCES/kvm-vdpa-store-x-svq-parameter-in-VhostVDPAState.patch
Unescape View File

@ -0,0 +1,62 @@
From 28163d7d61b6b0b8312b78d57dabc8f44bf39c46 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:42 +0100
Subject: [PATCH 10/14] vdpa: store x-svq parameter in VhostVDPAState
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [10/13] 53f3b2698b4a5caca434f55e4300103a78778548 (eperezmartin/qemu-kvm)
CVQ can be shadowed two ways:
- Device has x-svq=on parameter (current way)
- The device can isolate CVQ in its own vq group
QEMU needs to check for the second condition dynamically, because CVQ
index is not known before the driver ack the features. Since this is
dynamic, the CVQ isolation could vary with different conditions, making
it possible to go from "not isolated group" to "isolated".
Saving the cmdline parameter in an extra field so we never disable CVQ
SVQ in case the device was started with x-svq cmdline.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-11-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 7f211a28fd5482f76583988beecd8ee61588d45e)
---
net/vhost-vdpa.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index c2f319eb88..1757f1d028 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -38,6 +38,8 @@ typedef struct VhostVDPAState {
void *cvq_cmd_out_buffer;
virtio_net_ctrl_ack *status;
+ /* The device always have SVQ enabled */
+ bool always_svq;
bool started;
} VhostVDPAState;
@@ -576,6 +578,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
s->vhost_vdpa.device_fd = vdpa_device_fd;
s->vhost_vdpa.index = queue_pair_index;
+ s->always_svq = svq;
s->vhost_vdpa.shadow_vqs_enabled = svq;
s->vhost_vdpa.iova_range = iova_range;
s->vhost_vdpa.iova_tree = iova_tree;
--
2.31.1

58
SOURCES/kvm-vdpa-use-v-shadow_vqs_enabled-in-vhost_vdpa_svqs_sta.patch
Unescape View File

@ -0,0 +1,58 @@
From cb974f2f9a0c5b9520b6ac80bd1d1e4a6b12bbdc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= <eperezma@redhat.com>
Date: Thu, 15 Dec 2022 12:31:33 +0100
Subject: [PATCH 01/14] vdpa: use v->shadow_vqs_enabled in
vhost_vdpa_svqs_start & stop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eugenio Pérez <eperezma@redhat.com>
RH-MergeRequest: 136: vDPA ASID support in Qemu
RH-Bugzilla: 2104412
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/13] f0db50a95f87dd011418617be7b80aa6813a1146 (eperezmartin/qemu-kvm)
This function used to trust in v->shadow_vqs != NULL to know if it must
start svq or not.
This is not going to be valid anymore, as qemu is going to allocate svq
array unconditionally (but it will only start them conditionally).
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221215113144.322011-2-eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 712c1a3171cf62d501dac5af58f77d5fea70350d)
---
hw/virtio/vhost-vdpa.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index c5be2645b0..44e6a9b7b3 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -1036,7 +1036,7 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev)
Error *err = NULL;
unsigned i;
- if (!v->shadow_vqs) {
+ if (!v->shadow_vqs_enabled) {
return true;
}
@@ -1089,7 +1089,7 @@ static void vhost_vdpa_svqs_stop(struct vhost_dev *dev)
{
struct vhost_vdpa *v = dev->opaque;
- if (!v->shadow_vqs) {
+ if (!v->shadow_vqs_enabled) {
return;
}
--
2.31.1

185
SOURCES/kvm-vhost-add-support-for-configure-interrupt.patch
Unescape View File

@ -0,0 +1,185 @@
From 42818e2bc6fa537fe52f7f0e6b094774a1eb00e1 Mon Sep 17 00:00:00 2001
From: Cindy Lu <lulu@redhat.com>
Date: Thu, 22 Dec 2022 15:04:48 +0800
Subject: [PATCH 07/31] vhost: add support for configure interrupt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Cindy Lu <lulu@redhat.com>
RH-MergeRequest: 132: vhost-vdpa: support config interrupt in vhost-vdpa
RH-Bugzilla: 1905805
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
RH-Acked-by: Eugenio Pérez <eperezma@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [7/10] d58b439eb093f5dd3b7ca081af0ab75780e42917 (lulu6/qemu-kvm3)
https://bugzilla.redhat.com/show_bug.cgi?id=1905805
Add functions to support configure interrupt.
The configure interrupt process will start in vhost_dev_start
and stop in vhost_dev_stop.
Also add the functions to support vhost_config_pending and
vhost_config_mask.
Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20221222070451.936503-8-lulu@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit f9a09ca3ea69d108d828b7c82f1bd61b2df6fc96)
Signed-off-by: Cindy Lu <lulu@redhat.com>
---
hw/virtio/vhost.c | 78 ++++++++++++++++++++++++++++++++++++++-
include/hw/virtio/vhost.h | 4 ++
2 files changed, 81 insertions(+), 1 deletion(-)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 7fb008bc9e..84dbb39e07 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -1596,7 +1596,68 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,
file.index = hdev->vhost_ops->vhost_get_vq_index(hdev, n);
r = hdev->vhost_ops->vhost_set_vring_call(hdev, &file);
if (r < 0) {
- VHOST_OPS_DEBUG(r, "vhost_set_vring_call failed");
+ error_report("vhost_set_vring_call failed %d", -r);
+ }
+}
+
+bool vhost_config_pending(struct vhost_dev *hdev)
+{
+ assert(hdev->vhost_ops);
+ if ((hdev->started == false) ||
+ (hdev->vhost_ops->vhost_set_config_call == NULL)) {
+ return false;
+ }
+
+ EventNotifier *notifier =
+ &hdev->vqs[VHOST_QUEUE_NUM_CONFIG_INR].masked_config_notifier;
+ return event_notifier_test_and_clear(notifier);
+}
+
+void vhost_config_mask(struct vhost_dev *hdev, VirtIODevice *vdev, bool mask)
+{
+ int fd;
+ int r;
+ EventNotifier *notifier =
+ &hdev->vqs[VHOST_QUEUE_NUM_CONFIG_INR].masked_config_notifier;
+ EventNotifier *config_notifier = &vdev->config_notifier;
+ assert(hdev->vhost_ops);
+
+ if ((hdev->started == false) ||
+ (hdev->vhost_ops->vhost_set_config_call == NULL)) {
+ return;
+ }
+ if (mask) {
+ assert(vdev->use_guest_notifier_mask);
+ fd = event_notifier_get_fd(notifier);
+ } else {
+ fd = event_notifier_get_fd(config_notifier);
+ }
+ r = hdev->vhost_ops->vhost_set_config_call(hdev, fd);
+ if (r < 0) {
+ error_report("vhost_set_config_call failed %d", -r);
+ }
+}
+
+static void vhost_stop_config_intr(struct vhost_dev *dev)
+{
+ int fd = -1;
+ assert(dev->vhost_ops);
+ if (dev->vhost_ops->vhost_set_config_call) {
+ dev->vhost_ops->vhost_set_config_call(dev, fd);
+ }
+}
+
+static void vhost_start_config_intr(struct vhost_dev *dev)
+{
+ int r;
+
+ assert(dev->vhost_ops);
+ int fd = event_notifier_get_fd(&dev->vdev->config_notifier);
+ if (dev->vhost_ops->vhost_set_config_call) {
+ r = dev->vhost_ops->vhost_set_config_call(dev, fd);
+ if (!r) {
+ event_notifier_set(&dev->vdev->config_notifier);
+ }
}
}
@@ -1836,6 +1897,16 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
}
}
+ r = event_notifier_init(
+ &hdev->vqs[VHOST_QUEUE_NUM_CONFIG_INR].masked_config_notifier, 0);
+ if (r < 0) {
+ return r;
+ }
+ event_notifier_test_and_clear(
+ &hdev->vqs[VHOST_QUEUE_NUM_CONFIG_INR].masked_config_notifier);
+ if (!vdev->use_guest_notifier_mask) {
+ vhost_config_mask(hdev, vdev, true);
+ }
if (hdev->log_enabled) {
uint64_t log_base;
@@ -1874,6 +1945,7 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
vhost_device_iotlb_miss(hdev, vq->used_phys, true);
}
}
+ vhost_start_config_intr(hdev);
return 0;
fail_start:
if (vrings) {
@@ -1903,6 +1975,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
/* should only be called after backend is connected */
assert(hdev->vhost_ops);
+ event_notifier_test_and_clear(
+ &hdev->vqs[VHOST_QUEUE_NUM_CONFIG_INR].masked_config_notifier);
+ event_notifier_test_and_clear(&vdev->config_notifier);
trace_vhost_dev_stop(hdev, vdev->name, vrings);
@@ -1925,6 +2000,7 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
}
memory_listener_unregister(&hdev->iommu_listener);
}
+ vhost_stop_config_intr(hdev);
vhost_log_put(hdev, true);
hdev->started = false;
vdev->vhost_started = false;
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 67a6807fac..05bedb2416 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -33,6 +33,7 @@ struct vhost_virtqueue {
unsigned used_size;
EventNotifier masked_notifier;
EventNotifier error_notifier;
+ EventNotifier masked_config_notifier;
struct vhost_dev *dev;
};
@@ -41,6 +42,7 @@ typedef unsigned long vhost_log_chunk_t;
#define VHOST_LOG_BITS (8 * sizeof(vhost_log_chunk_t))
#define VHOST_LOG_CHUNK (VHOST_LOG_PAGE * VHOST_LOG_BITS)
#define VHOST_INVALID_FEATURE_BIT (0xff)
+#define VHOST_QUEUE_NUM_CONFIG_INR 0
struct vhost_log {
unsigned long long size;
@@ -168,6 +170,8 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev);
* Disable direct notifications to vhost device.
*/
void vhost_dev_disable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev);
+bool vhost_config_pending(struct vhost_dev *hdev);
+void vhost_config_mask(struct vhost_dev *hdev, VirtIODevice *vdev, bool mask);
/**
* vhost_dev_is_started() - report status of vhost device
--
2.31.1

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

Write Preview
Loading…
Cancel
Save