rpms/qemu-kvm
8
0
Fork 0
Code Issues Pull Requests Releases Activity

Enable QXL device build

Browse Source 
Enable building for ppc64le

Re-added Spice support

Don't remove slof.bin for ppc64le
This commit is contained in:
Eduard Abdullin 2026-04-14 09:59:23 +00:00 committed by root
parent d48864abfd
commit 5dfc11b153
175 changed files with 25848 additions and 6800 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -1 +1 @@
qemu-9.0.0.tar.xz
qemu-10.1.0.tar.xz

58
0004-Initial-redhat-build.patch
View File

@ -1,4 +1,4 @@
From 91262ecfbd218a95dab8491e4226674f79debf5a Mon Sep 17 00:00:00 2001
From 8a5eef9fcb74b2fa82ac6122caf3c3d38a26b195 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 26 May 2021 10:56:02 +0200
Subject: Initial redhat build
@ -13,25 +13,63 @@ several issues are fixed in QEMU tree:
We disable make check due to issues with some of the tests.
We are rebasing from qemu-kvm-10.0.0-12.el10.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (9.1.0):
- Remove --disable-block-migration and --disable-pvrdma configure options (upstream)
- Removed --disable-avx512f configure option
- Removed qemu-vsmr-helper (changed upstream)
Rebase notes (10.0.0):
- Split --disable-sanitazers configure option (upstream change)
- Removed s390x-netboot.img (upstream)
- accel-tcg module no longer built (upstream)
- Removed new upstream npcm8xx board rom
- Not package hw-uefi-vars.so
- Not package pnv-pnor.bin on build
- Include riscv support
Rebase notes (10.1.0 rc0):
- Remove avocado tests installation (removed upstream)
- dtb files installed in special directory (upstream change)
- Remove ast27x0_bootrom.bin
- Removed --disable-avx* configure options
- Removed 32bit archs conditionals
- Conditional qemu-kvm-block-rbd requirement
- Flip ipxe roms and seavgabios arch condition
Merged patches (9.1.0):
- b206b8f7cb redhat: Remove the s390-netboot.img from the spec file
- 95605107f1 Require new dtrace package
Merged patches (10.0.0):
- 07c8c9b9ff qemu-guest-agent: Update the logfile path of qga-fsfreeze-hook.log
- 1f54babd2a Recommend systemtap-client from qemu-tools
- 3e4d2a0fb8 Also recommend systemtap-devel from qemu-tools
Merged patches (10.1.0 rc0):
- 72119e03ea distro: add an explicit valgrind-devel build dep
---
.distro/Makefile | 101 ++
.distro/Makefile.common | 42 +
.distro/README.tests | 39 +
.distro/modules-load.conf | 4 +
.distro/qemu-guest-agent.service | 1 -
.distro/qemu-kvm.spec.template | 1250 +++++++++++++++++++++++
.distro/qemu-kvm.spec.template | 1795 +++++++++++++++++++++++
.distro/rpminspect.yaml | 6 +-
.distro/scripts/extract_build_cmd.py | 12 +
.distro/scripts/frh.py | 4 +-
.distro/scripts/process-patches.sh | 4 +
.distro/scripts/process-patches.sh | 6 +-
.gitignore | 1 +
README.systemtap | 43 +
scripts/qemu-guest-agent/fsfreeze-hook | 2 +-
scripts/qemu-guest-agent/fsfreeze-hook | 4 +-
scripts/systemtap/conf.d/qemu_kvm.conf | 4 +
scripts/systemtap/script.d/qemu_kvm.stp | 1 +
ui/vnc-auth-sasl.c | 2 +-
16 files changed, 1510 insertions(+), 6 deletions(-)
16 files changed, 2057 insertions(+), 8 deletions(-)
create mode 100644 .distro/Makefile
create mode 100644 .distro/Makefile.common
create mode 100644 .distro/README.tests
@ -91,14 +129,16 @@ index 0000000000..ad913fc990
+3. Translate the trace record to readable format.
+ # /usr/share/qemu-kvm/simpletrace.py --no-header /usr/share/qemu-kvm/trace-events /tmp/trace.log
diff --git a/scripts/qemu-guest-agent/fsfreeze-hook b/scripts/qemu-guest-agent/fsfreeze-hook
index 13aafd4845..e9b84ec028 100755
index c1feb6f5ce..d5d8d4daf8 100755
--- a/scripts/qemu-guest-agent/fsfreeze-hook
+++ b/scripts/qemu-guest-agent/fsfreeze-hook
@@ -8,7 +8,7 @@
@@ -7,8 +7,8 @@
# "freeze" argument before the filesystem is frozen. And for fsfreeze-thaw
# request, it is issued with "thaw" argument after filesystem is thawed.
LOGFILE=/var/log/qga-fsfreeze-hook.log
-LOGFILE=/var/log/qga-fsfreeze-hook.log
-FSFREEZE_D=$(dirname -- "$0")/fsfreeze-hook.d
+LOGFILE=/var/log/qemu-ga/qga-fsfreeze-hook.log
+FSFREEZE_D=$(dirname -- "$(realpath $0)")/fsfreeze-hook.d
# Check whether file $1 is a backup or rpm-generated file and should be ignored
@ -121,7 +161,7 @@ index 0000000000..c04abf9449
@@ -0,0 +1 @@
+probe qemu.kvm.simpletrace.handle_qmp_command,qemu.kvm.simpletrace.monitor_protocol_*,qemu.kvm.simpletrace.migrate_set_state {}
diff --git a/ui/vnc-auth-sasl.c b/ui/vnc-auth-sasl.c
index 47fdae5b21..2a950caa2a 100644
index 3f4cfc471d..09dafba18d 100644
--- a/ui/vnc-auth-sasl.c
+++ b/ui/vnc-auth-sasl.c
@@ -42,7 +42,7 @@

652
0005-Enable-disable-devices-for-RHEL.patch
View File

@ -1,4 +1,4 @@
From 8e767ade83e18995692d3554b6b71c9e15b51d89 Mon Sep 17 00:00:00 2001
From 03cf16ca98c4ed835c4da8c4424bfac5a9ae3aa6 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
@ -6,56 +6,102 @@ 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>
---
.distro/qemu-kvm.spec.template | 18 +--
.../aarch64-softmmu/aarch64-rh-devices.mak | 42 +++++++
.../ppc64-softmmu/ppc64-rh-devices.mak | 37 ++++++
Rebase notes (9.1.0):
- Return value added for kvm_s390_apply_cpu_model
- Added new USB_HID and USB_HUB options
- Fixing valid_cpu_types preprocessing
- Moved x86 cpu deprecation from x86 machine type patch
- Removed unnecessary chunk in cirrus_vga.c
- Not needed hack removal of cpu-v7m.c from build
- Remove ppc64 device configuration
- Remove unnecessary chunks
- Removed CONFIG_VHOST_USER_SCMI and CONFIG_VHOST_USER_SND from some archs
Rebase notes (10.0.0):
- Added CONFIG_PCI_BRIDGE for aarch64 and x86_64 (new upstream)
- Do not add deprecation_note member as it was added upstream (target/arm/cpu.h)
- Rename CONFIG_ARM_GICV3_TCG to CONFIG_ARM_GICV3
- Remove deprecated line change for code commented out
- Do not change minimal revision for piix4
- Remove YongFeng vcpu
- Add rebase devices changes
- Enable virtio-mem on s390x
Rebase notes (10.1.0 rc0):
- Improved riscv cpu chunk re-added
- Comment out unused code
Merged commits (9.1.0):
- f24c7a1fee Disable FDC devices
- fe8c6cb1ce Disable vga-cirrus device
- fccd117a12 Enable vhost-user-snd-pci device
- c0b40cc648 target/cpu-models/x86: Remove the existing deprecated CPU models on c10s
- ce42b3da0e x86/cpu: deprecate cpu models that do not support x86-64-v3
- 01ffa96c3b target/s390x/cpu_models: Disable everything up to the z12 CPU model
- cd57d17e3c target/s390x: Revert the old s390x CPU model disablement code
- 42af7b3ad5 Enable vhost-user-scmi devices
- aa374ce5ea x86/cpu: update deprecation string to match lowest undeprecated model
Merged commits (10.1.0 rc0):
- 312cdc116e Enable vhost-user-gpu-pci for RHIVOS
- be460986c1 Enable amd-iommu device
Merged commits (10.1.0 rc2):
- 6306605028 Declare rtl8139 as deprecated
Merged commits (10.1.0 rc3):
- f06f55a179 Enable uefi variable service for edk2
---
.distro/qemu-kvm.spec.template | 20 +--
.../aarch64-softmmu/aarch64-rh-devices.mak | 49 ++++++++
configs/devices/rh-virtio.mak | 10 ++
.../s390x-softmmu/s390x-rh-devices.mak | 19 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 112 ++++++++++++++++++
hw/arm/virt.c | 2 +
hw/block/fdc.c | 10 ++
hw/cpu/meson.build | 3 +-
.../riscv64-softmmu/riscv64-rh-devices.mak | 39 ++++++
.../s390x-softmmu/s390x-rh-devices.mak | 20 +++
.../x86_64-softmmu/x86_64-rh-devices.mak | 118 ++++++++++++++++++
hw/arm/virt.c | 4 +
hw/cxl/meson.build | 3 +-
hw/display/cirrus_vga.c | 4 +
hw/ide/piix.c | 5 +-
hw/input/pckbd.c | 2 +
hw/net/e1000.c | 2 +
hw/net/rtl8139.c | 4 +
hw/usb/meson.build | 2 +-
hw/virtio/meson.build | 6 +-
target/arm/arm-qmp-cmds.c | 2 +
target/arm/cpu.c | 4 +
target/arm/cpu.h | 3 +
target/arm/cpu64.c | 12 +-
target/arm/cpu.h | 2 +
target/arm/cpu64.c | 7 +-
target/arm/tcg/cpu32.c | 2 +
target/arm/tcg/cpu64.c | 8 ++
target/arm/tcg/meson.build | 2 +-
target/s390x/cpu_models_sysemu.c | 3 +
target/s390x/kvm/kvm.c | 8 ++
target/i386/cpu.c | 20 +++
target/riscv/cpu.c | 6 +
target/s390x/cpu_models.c | 2 +-
tests/qtest/arm-cpu-features.c | 4 +
26 files changed, 309 insertions(+), 16 deletions(-)
24 files changed, 323 insertions(+), 16 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/riscv64-softmmu/riscv64-rh-devices.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..b0191d3c69
index 0000000000..855278f70e
--- /dev/null
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -0,0 +1,42 @@
@@ -0,0 +1,49 @@
+include ../rh-virtio.mak
+
+CONFIG_ARM_GIC_KVM=y
+CONFIG_ARM_GICV3_TCG=y
+CONFIG_ARM_GICV3=y
+CONFIG_ARM_GIC=y
+CONFIG_ARM_SMMUV3=y
+CONFIG_ARM_VIRT=y
+CONFIG_CXL=y
+CONFIG_CXL_MEM_DEVICE=y
+CONFIG_EDID=y
+CONFIG_PCI_BRIDGE=y
+CONFIG_PCIE_PORT=y
+CONFIG_PCIE_PCI_BRIDGE=y
+CONFIG_PCI_DEVICES=y
@ -68,6 +114,8 @@ index 0000000000..b0191d3c69
+CONFIG_USB_XHCI_PCI=y
+CONFIG_USB_STORAGE_CORE=y
+CONFIG_USB_STORAGE_CLASSIC=y
+CONFIG_USB_HUB=y
+CONFIG_USB_HID=y
+CONFIG_VFIO=y
+CONFIG_VFIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
@ -88,49 +136,10 @@ index 0000000000..b0191d3c69
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=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
+CONFIG_VHOST_USER_SND=y
+CONFIG_VHOST_USER_SCMI=y
+CONFIG_VHOST_USER_GPU=y
+CONFIG_UEFI_VARS=y
diff --git a/configs/devices/rh-virtio.mak b/configs/devices/rh-virtio.mak
new file mode 100644
index 0000000000..94ede1b5f6
@ -147,12 +156,57 @@ index 0000000000..94ede1b5f6
+CONFIG_VIRTIO_RNG=y
+CONFIG_VIRTIO_SCSI=y
+CONFIG_VIRTIO_SERIAL=y
diff --git a/configs/devices/riscv64-softmmu/riscv64-rh-devices.mak b/configs/devices/riscv64-softmmu/riscv64-rh-devices.mak
new file mode 100644
index 0000000000..b5e55de916
--- /dev/null
+++ b/configs/devices/riscv64-softmmu/riscv64-rh-devices.mak
@@ -0,0 +1,39 @@
+include ../rh-virtio.mak
+
+CONFIG_RISCV_VIRT=y
+CONFIG_CXL=y
+CONFIG_CXL_MEM_DEVICE=y
+CONFIG_EDID=y
+CONFIG_PCI_BRIDGE=y
+CONFIG_PCIE_PORT=y
+CONFIG_PCIE_PCI_BRIDGE=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_USB_HUB=y
+CONFIG_USB_HID=y
+CONFIG_VFIO=y
+CONFIG_VFIO_PCI=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_IOMMU=y
+CONFIG_XIO3130=y
+CONFIG_ACPI_APEI=y
+CONFIG_TPM=y
+CONFIG_TPM_EMULATOR=y
+CONFIG_TPM_TIS_SYSBUS=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
+CONFIG_IOMMUFD=y
+CONFIG_VHOST_USER_SND=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..24cf6dbd03
index 0000000000..834281d872
--- /dev/null
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -0,0 +1,19 @@
@@ -0,0 +1,20 @@
+include ../rh-virtio.mak
+
+CONFIG_PCI=y
@ -167,6 +221,7 @@ index 0000000000..24cf6dbd03
+CONFIG_VFIO_PCI=y
+CONFIG_VHOST_USER=y
+CONFIG_VIRTIO_CCW=y
+CONFIG_VIRTIO_MEM=y
+CONFIG_WDT_DIAG288=y
+CONFIG_VHOST_VSOCK=y
+CONFIG_VHOST_USER_VSOCK=y
@ -174,10 +229,10 @@ index 0000000000..24cf6dbd03
+CONFIG_IOMMUFD=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..d60ff1bcfc
index 0000000000..828cb8aa6f
--- /dev/null
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -0,0 +1,112 @@
@@ -0,0 +1,118 @@
+include ../rh-virtio.mak
+
+CONFIG_ACPI=y
@ -199,9 +254,9 @@ index 0000000000..d60ff1bcfc
+CONFIG_E1000E_PCI_EXPRESS=y
+CONFIG_E1000_PCI=y
+CONFIG_EDU=y
+CONFIG_FDC=y
+CONFIG_FDC_SYSBUS=y
+CONFIG_FDC_ISA=y
+#CONFIG_FDC=y
+#CONFIG_FDC_SYSBUS=y
+#CONFIG_FDC_ISA=y
+CONFIG_FW_CFG_DMA=y
+CONFIG_HDA=y
+CONFIG_HYPERV=y
@ -240,6 +295,7 @@ index 0000000000..d60ff1bcfc
+CONFIG_PCSPK=y
+CONFIG_PC_ACPI=y
+CONFIG_PC_PCI=y
+CONFIG_PCI_BRIDGE=y
+CONFIG_PCIE_PCI_BRIDGE=y
+CONFIG_PFLASH_CFI01=y
+CONFIG_PVPANIC_ISA=y
@ -264,10 +320,11 @@ index 0000000000..d60ff1bcfc
+CONFIG_USB_XHCI=y
+CONFIG_USB_XHCI_NEC=y
+CONFIG_USB_XHCI_PCI=y
+CONFIG_USB_HUB=y
+CONFIG_USB_HID=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
@ -275,6 +332,7 @@ index 0000000000..d60ff1bcfc
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VGA=y
+CONFIG_VIRTIO_IOMMU=y
+CONFIG_AMD_IOMMU=y
+CONFIG_VMMOUSE=y
+CONFIG_VMPORT=y
+CONFIG_VTD=y
@ -290,11 +348,14 @@ index 0000000000..d60ff1bcfc
+CONFIG_VHOST_USER_VSOCK=y
+CONFIG_VHOST_USER_FS=y
+CONFIG_IOMMUFD=y
+CONFIG_VHOST_USER_SND=y
+CONFIG_VHOST_USER_GPU=y
+CONFIG_UEFI_VARS=y
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index a9a913aead..6c6d155002 100644
index ef6be3660f..b525e00365 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2954,6 +2954,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
@@ -3183,6 +3183,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
MachineClass *mc = MACHINE_CLASS(oc);
HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
static const char * const valid_cpu_types[] = {
@ -302,53 +363,18 @@ index a9a913aead..6c6d155002 100644
#ifdef CONFIG_TCG
ARM_CPU_TYPE_NAME("cortex-a7"),
ARM_CPU_TYPE_NAME("cortex-a15"),
@@ -2971,6 +2972,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
@@ -3198,8 +3199,11 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
ARM_CPU_TYPE_NAME("neoverse-n2"),
#endif /* TARGET_AARCH64 */
#endif /* CONFIG_TCG */
+#endif /* disabled for RHEL */
#ifdef TARGET_AARCH64
+#if 0 /* Disabled for Red Hat Enterprise Linux */
ARM_CPU_TYPE_NAME("cortex-a53"),
+#endif /* disabled for RHEL */
ARM_CPU_TYPE_NAME("cortex-a57"),
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
ARM_CPU_TYPE_NAME("host"),
diff --git a/hw/block/fdc.c b/hw/block/fdc.c
index 6dd94e98bc..a05757fc9a 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 38cdcfbe57..e588ecfd42 100644
--- a/hw/cpu/meson.build
+++ b/hw/cpu/meson.build
@@ -1,4 +1,5 @@
-system_ss.add(files('core.c', 'cluster.c'))
+#system_ss.add(files('core.c', 'cluster.c'))
+system_ss.add(files('core.c'))
system_ss.add(when: 'CONFIG_ARM11MPCORE', if_true: files('arm11mpcore.c'))
system_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview_mpcore.c'))
diff --git a/hw/cxl/meson.build b/hw/cxl/meson.build
index 3e375f61a9..613adb3ebb 100644
--- a/hw/cxl/meson.build
@ -363,33 +389,11 @@ index 3e375f61a9..613adb3ebb 100644
),
if_false: files(
'cxl-host-stubs.c',
diff --git a/hw/display/cirrus_vga.c b/hw/display/cirrus_vga.c
index 150883a971..497365bd80 100644
--- a/hw/display/cirrus_vga.c
+++ b/hw/display/cirrus_vga.c
@@ -36,6 +36,7 @@
#include "qemu/module.h"
#include "qemu/units.h"
#include "qemu/log.h"
+#include "qemu/error-report.h"
#include "sysemu/reset.h"
#include "qapi/error.h"
#include "trace.h"
@@ -2946,6 +2947,9 @@ 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 80efc633d3..9cb82b8eea 100644
index a0f2709c69..8c3962443b 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -191,7 +191,8 @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
@@ -191,7 +191,8 @@ static void piix3_ide_class_init(ObjectClass *klass, const 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);
@ -399,7 +403,7 @@ index 80efc633d3..9cb82b8eea 100644
}
static const TypeInfo piix3_ide_info = {
@@ -215,6 +216,8 @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
@@ -215,6 +216,8 @@ static void piix4_ide_class_init(ObjectClass *klass, const void *data)
k->class_id = PCI_CLASS_STORAGE_IDE;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
dc->hotpluggable = false;
@ -409,10 +413,10 @@ index 80efc633d3..9cb82b8eea 100644
static const TypeInfo piix4_ide_info = {
diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c
index 74f10b640f..2e85ecf476 100644
index 71f5f976e9..794078ed84 100644
--- a/hw/input/pckbd.c
+++ b/hw/input/pckbd.c
@@ -952,6 +952,8 @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
@@ -950,6 +950,8 @@ static void i8042_class_initfn(ObjectClass *klass, const void *data)
dc->vmsd = &vmstate_kbd_isa;
adevc->build_dev_aml = i8042_build_aml;
set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
@ -422,10 +426,10 @@ index 74f10b640f..2e85ecf476 100644
static const TypeInfo i8042_info = {
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index 43f3a4a701..267f182883 100644
index a80a7b0cdb..7eb5a3b19d 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -1746,6 +1746,7 @@ static const E1000Info e1000_devices[] = {
@@ -1732,6 +1732,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
@ -433,7 +437,7 @@ index 43f3a4a701..267f182883 100644
{
.name = "e1000-82544gc",
.device_id = E1000_DEV_ID_82544GC_COPPER,
@@ -1758,6 +1759,7 @@ static const E1000Info e1000_devices[] = {
@@ -1744,6 +1745,7 @@ static const E1000Info e1000_devices[] = {
.revision = 0x03,
.phy_id2 = E1000_PHY_ID2_8254xx_DEFAULT,
},
@ -441,11 +445,33 @@ index 43f3a4a701..267f182883 100644
};
static void e1000_register_types(void)
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 324fb932aa..f4dd693abb 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -57,6 +57,7 @@
#include "system/dma.h"
#include "qemu/module.h"
#include "qemu/timer.h"
+#include "qemu/error-report.h"
#include "qemu/bswap.h"
#include "net/net.h"
#include "net/eth.h"
@@ -3363,6 +3364,9 @@ static void pci_rtl8139_realize(PCIDevice *dev, Error **errp)
DeviceState *d = DEVICE(dev);
uint8_t *pci_conf;
+ warn_report("'rtl8139' is deprecated, "
+ "please use a different Network Interface Card");
+
pci_conf = dev->config;
pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin A */
/* TODO: start of capability list, but no capability
diff --git a/hw/usb/meson.build b/hw/usb/meson.build
index aac3bb35f2..5411ff35df 100644
index 17360a5b5a..3c4fdfc31d 100644
--- a/hw/usb/meson.build
+++ b/hw/usb/meson.build
@@ -55,7 +55,7 @@ system_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reader
@@ -53,7 +53,7 @@ system_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reader
if cacard.found()
usbsmartcard_ss = ss.source_set()
usbsmartcard_ss.add(when: 'CONFIG_USB_SMARTCARD',
@ -455,10 +481,10 @@ index aac3bb35f2..5411ff35df 100644
endif
diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
index d7f18c96e6..aaabbb8b0b 100644
index 3ea7b3cec8..3102d68bec 100644
--- a/hw/virtio/meson.build
+++ b/hw/virtio/meson.build
@@ -20,7 +20,8 @@ if have_vhost
@@ -22,7 +22,8 @@ if have_vhost
system_virtio_ss.add(files('vhost-user-base.c'))
# MMIO Stubs
@ -468,7 +494,7 @@ index d7f18c96e6..aaabbb8b0b 100644
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_GPIO', if_true: files('vhost-user-gpio.c'))
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c'))
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_RNG', if_true: files('vhost-user-rng.c'))
@@ -28,7 +29,8 @@ if have_vhost
@@ -30,7 +31,8 @@ if have_vhost
system_virtio_ss.add(when: 'CONFIG_VHOST_USER_INPUT', if_true: files('vhost-user-input.c'))
# PCI Stubs
@ -479,10 +505,10 @@ index d7f18c96e6..aaabbb8b0b 100644
if_true: files('vhost-user-gpio-pci.c'))
system_virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'],
diff --git a/target/arm/arm-qmp-cmds.c b/target/arm/arm-qmp-cmds.c
index 3cc8cc738b..6f21fea1f5 100644
index d292c974c4..9bb68866e1 100644
--- a/target/arm/arm-qmp-cmds.c
+++ b/target/arm/arm-qmp-cmds.c
@@ -223,6 +223,7 @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type,
@@ -225,6 +225,7 @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type,
static void arm_cpu_add_definition(gpointer data, gpointer user_data)
{
ObjectClass *oc = data;
@ -490,7 +516,7 @@ index 3cc8cc738b..6f21fea1f5 100644
CpuDefinitionInfoList **cpu_list = user_data;
CpuDefinitionInfo *info;
const char *typename;
@@ -231,6 +232,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
@@ -233,6 +234,7 @@ static void arm_cpu_add_definition(gpointer data, gpointer user_data)
info = g_malloc0(sizeof(*info));
info->name = cpu_model_from_type(typename);
info->q_typename = g_strdup(typename);
@ -498,47 +524,24 @@ index 3cc8cc738b..6f21fea1f5 100644
QAPI_LIST_PREPEND(*cpu_list, info);
}
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index ab8d007a86..e5dce20f19 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2546,6 +2546,10 @@ static void cpu_register_class_init(ObjectClass *oc, void *data)
acc->info = data;
cc->gdb_core_xml_file = "arm-core.xml";
+
+ 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 bc0c84873f..e9472c8bb8 100644
index dc9b6dce4c..dc0da8b0ae 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -37,6 +37,8 @@
#define KVM_HAVE_MCE_INJECTION 1
#endif
@@ -34,6 +34,8 @@
#include "target/arm/gtimer.h"
#include "target/arm/cpu-sysregs.h"
+#define RHEL_CPU_DEPRECATION "use 'host' / 'max'"
+
#define EXCP_UDEF 1 /* undefined instruction */
#define EXCP_SWI 2 /* software interrupt */
#define EXCP_PREFETCH_ABORT 3
@@ -1092,6 +1094,7 @@ typedef struct ARMCPUInfo {
const char *name;
void (*initfn)(Object *obj);
void (*class_init)(ObjectClass *oc, void *data);
+ const char *deprecation_note;
} ARMCPUInfo;
/**
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 985b1efe16..46a4e80171 100644
index 26cf7e6dfa..051d5d653b 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -648,6 +648,7 @@ static void aarch64_a57_initfn(Object *obj)
@@ -698,6 +698,7 @@ static void aarch64_a57_initfn(Object *obj)
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
@ -546,7 +549,7 @@ index 985b1efe16..46a4e80171 100644
static void aarch64_a53_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -704,6 +705,7 @@ static void aarch64_a53_initfn(Object *obj)
@@ -759,6 +760,7 @@ static void aarch64_a53_initfn(Object *obj)
cpu->gic_pribits = 5;
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
@ -554,7 +557,7 @@ index 985b1efe16..46a4e80171 100644
static void aarch64_host_initfn(Object *obj)
{
@@ -742,8 +744,11 @@ static void aarch64_max_initfn(Object *obj)
@@ -797,8 +799,11 @@ static void aarch64_max_initfn(Object *obj)
}
static const ARMCPUInfo aarch64_cpus[] = {
@ -567,39 +570,25 @@ index 985b1efe16..46a4e80171 100644
{ .name = "max", .initfn = aarch64_max_initfn },
#if defined(CONFIG_KVM) || defined(CONFIG_HVF)
{ .name = "host", .initfn = aarch64_host_initfn },
@@ -814,8 +819,13 @@ 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/tcg/cpu32.c b/target/arm/tcg/cpu32.c
index de8f2be941..8896295ae3 100644
index a2a23eae0d..c362759d65 100644
--- a/target/arm/tcg/cpu32.c
+++ b/target/arm/tcg/cpu32.c
@@ -92,6 +92,7 @@ void aa32_max_features(ARMCPU *cpu)
cpu->isar.id_dfr1 = t;
@@ -115,6 +115,7 @@ void aa32_max_features(ARMCPU *cpu)
FIELD_DP32_IDREG(isar, ID_DFR1, HPMN0, 1); /* FEAT_HPMN0 */
}
+#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)
@@ -1037,3 +1038,4 @@ static void arm_tcg_cpu_register_types(void)
@@ -1084,3 +1085,4 @@ 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/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index 9f7a9f3d2c..7ec6851c9c 100644
index 35cddbafa4..c7c464a0af 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -29,6 +29,7 @@
@ -607,10 +596,10 @@ index 9f7a9f3d2c..7ec6851c9c 100644
#include "cpregs.h"
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static uint64_t make_ccsidr64(unsigned assoc, unsigned linesize,
unsigned cachesize)
static void aarch64_a35_initfn(Object *obj)
{
@@ -134,6 +135,7 @@ static void aarch64_a35_initfn(Object *obj)
ARMCPU *cpu = ARM_CPU(obj);
@@ -113,6 +114,7 @@ static void aarch64_a35_initfn(Object *obj)
/* These values are the same with A53/A57/A72. */
define_cortex_a72_a57_a53_cp_reginfo(cpu);
}
@ -618,15 +607,15 @@ index 9f7a9f3d2c..7ec6851c9c 100644
static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
@@ -223,6 +225,7 @@ static void cpu_max_get_l0gptsz(Object *obj, Visitor *v, const char *name,
static Property arm_cpu_lpa2_property =
@@ -199,6 +201,7 @@ static void cpu_max_get_l0gptsz(Object *obj, Visitor *v, const char *name,
static const Property arm_cpu_lpa2_property =
DEFINE_PROP_BOOL("lpa2", ARMCPU, prop_lpa2, true);
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void aarch64_a55_initfn(Object *obj)
{
ARMCPU *cpu = ARM_CPU(obj);
@@ -1065,6 +1068,7 @@ static void aarch64_neoverse_n2_initfn(Object *obj)
@@ -1080,6 +1083,7 @@ static void aarch64_neoverse_n2_initfn(Object *obj)
aarch64_add_pauth_properties(obj);
aarch64_add_sve_properties(obj);
}
@ -634,7 +623,7 @@ index 9f7a9f3d2c..7ec6851c9c 100644
/*
* -cpu max: a CPU with as many features enabled as our emulation supports.
@@ -1271,6 +1275,7 @@ void aarch64_max_tcg_initfn(Object *obj)
@@ -1310,6 +1314,7 @@ void aarch64_max_tcg_initfn(Object *obj)
qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property);
}
@ -642,7 +631,7 @@ index 9f7a9f3d2c..7ec6851c9c 100644
static const ARMCPUInfo aarch64_cpus[] = {
{ .name = "cortex-a35", .initfn = aarch64_a35_initfn },
{ .name = "cortex-a55", .initfn = aarch64_a55_initfn },
@@ -1282,14 +1287,17 @@ static const ARMCPUInfo aarch64_cpus[] = {
@@ -1321,14 +1326,17 @@ static const ARMCPUInfo aarch64_cpus[] = {
{ .name = "neoverse-v1", .initfn = aarch64_neoverse_v1_initfn },
{ .name = "neoverse-n2", .initfn = aarch64_neoverse_n2_initfn },
};
@ -654,61 +643,230 @@ index 9f7a9f3d2c..7ec6851c9c 100644
size_t i;
for (i = 0; i < ARRAY_SIZE(aarch64_cpus); ++i) {
aarch64_cpu_register(&aarch64_cpus[i]);
arm_cpu_register(&aarch64_cpus[i]);
}
+#endif
}
type_init(aarch64_cpu_register_types)
diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index 3b1a9f0fc5..6c95d99181 100644
index 895facdc30..f1a9e01c51 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -56,5 +56,5 @@ arm_system_ss.add(files(
@@ -53,7 +53,7 @@ arm_system_ss.add(files(
'psci.c',
))
-arm_system_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('cpu-v7m.c'))
+#arm_system_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('cpu-v7m.c'))
arm_user_ss.add(when: 'TARGET_AARCH64', if_false: files('cpu-v7m.c'))
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 2d99218069..0728bfcc20 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -34,6 +34,9 @@ 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 4ce809c5d4..55fb4855b1 100644
--- a/target/s390x/kvm/kvm.c
+++ b/target/s390x/kvm/kvm.c
@@ -2565,6 +2565,14 @@ void kvm_s390_apply_cpu_model(const S390CPUModel *model, Error **errp)
error_setg(errp, "KVM doesn't support CPU models");
return;
arm_common_ss.add(zlib)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 6d85149e6e..9c756a05f2 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -3163,6 +3163,7 @@ static const CPUCaches xeon_srf_cache_info = {
},
};
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static const CPUCaches yongfeng_cache_info = {
.l1d_cache = &(CPUCacheInfo) {
/* CPUID 0x4.0x0.EAX */
@@ -3261,6 +3262,7 @@ static const CPUCaches yongfeng_cache_info = {
.share_level = CPU_TOPOLOGY_LEVEL_DIE,
},
};
+#endif
/* The following VMX features are not supported by KVM and are left out in the
* CPU definitions:
@@ -3290,9 +3292,13 @@ static const CPUCaches yongfeng_cache_info = {
* PT in VMX operation
*/
+#define RHEL_CPU_DEPRECATION \
+ "use at least 'Haswell' / 'EPYC', or 'host' / 'max'"
+
static const X86CPUDefinition builtin_x86_defs[] = {
{
.name = "qemu64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -3311,6 +3317,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
.xlevel = 0x8000000A,
.model_id = "QEMU Virtual CPU version " QEMU_HW_VERSION,
},
+#if 0 // Deprecated CPU models are removed in RHEL-10
{
.name = "phenom",
.level = 5,
@@ -3679,8 +3686,10 @@ static const X86CPUDefinition builtin_x86_defs[] = {
.xlevel = 0x80000008,
.model_id = "Intel Core 2 Duo P9xxx (Penryn Class Core 2)",
},
+#endif // Removal of deprecated CPU models in RHEL-10
{
.name = "Nehalem",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 11,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -3758,6 +3767,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Westmere",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 11,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -3839,6 +3849,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "SandyBridge",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -3925,6 +3936,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "IvyBridge",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -5551,6 +5563,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Denverton",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 21,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -5661,6 +5674,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Snowridge",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 27,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -5842,6 +5856,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
.xlevel = 0x80000008,
.model_id = "Intel Xeon Phi Processor (Knights Mill)",
},
+#if 0 // Deprecated CPU models are removed in RHEL-10
{
.name = "Opteron_G1",
.level = 5,
@@ -5909,8 +5924,10 @@ static const X86CPUDefinition builtin_x86_defs[] = {
.xlevel = 0x80000008,
.model_id = "AMD Opteron 23xx (Gen 3 Class Opteron)",
},
+#endif
{
.name = "Opteron_G4",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_AMD,
.family = 21,
@@ -5943,6 +5960,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G5",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_AMD,
.family = 21,
@@ -6420,6 +6438,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
{ /* end of list */ }
}
},
+#if 0 // Disabled for Red Hat Enterprise Linux
{
.name = "YongFeng",
.level = 0x1F,
@@ -6565,6 +6584,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
{ /* end of list */ }
}
},
+#endif
{
.name = "EPYC-Turin",
.level = 0xd,
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index d055ddf462..bca50a39be 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -2035,6 +2035,7 @@ static const PropertyInfo prop_marchid = {
.set = prop_marchid_set,
};
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* RVA22U64 defines some 'named features' that are cache
* related: Za64rs, Zic64b, Ziccif, Ziccrse, Ziccamoa
@@ -2143,12 +2144,15 @@ static RISCVCPUProfile RVA23S64 = {
RISCV_PROFILE_EXT_LIST_END
}
+
+ /* 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) */
};
+#endif
RISCVCPUProfile *riscv_profiles[] = {
+#if 0 /* Disabled for Red Hat Enterprise Linux */
&RVA22U64,
&RVA22S64,
&RVA23U64,
&RVA23S64,
+#endif
NULL,
};
@@ -2993,6 +2997,7 @@ static const TypeInfo riscv_cpu_type_infos[] = {
.cfg.pmp_regions = 8
),
+#if 0 /* Disabled for Red Hat Enterprise Linux */
#if defined(TARGET_RISCV32) || \
(defined(TARGET_RISCV64) && !defined(CONFIG_USER_ONLY))
DEFINE_RISCV_CPU(TYPE_RISCV_CPU_BASE32, TYPE_RISCV_DYNAMIC_CPU,
@@ -3287,6 +3292,7 @@ static const TypeInfo riscv_cpu_type_infos[] = {
DEFINE_PROFILE_CPU(TYPE_RISCV_CPU_RVA23U64, TYPE_RISCV_CPU_RV64I, RVA23U64),
DEFINE_PROFILE_CPU(TYPE_RISCV_CPU_RVA23S64, TYPE_RISCV_CPU_RV64I, RVA23S64),
#endif /* TARGET_RISCV64 */
+#endif /* disabled for RHEL */
};
DEFINE_TYPES(riscv_cpu_type_infos)
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index 954a7a99a9..fe29f5c5b7 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -72,7 +72,6 @@ static S390CPUDef s390_cpu_defs[] = {
CPUDEF_INIT(0x2096, 9, 2, 40, 0x00000000U, "z9BC", "IBM System z9 BC GA1"),
CPUDEF_INIT(0x2094, 9, 3, 40, 0x00000000U, "z9EC.3", "IBM System z9 EC GA3"),
CPUDEF_INIT(0x2096, 9, 3, 40, 0x00000000U, "z9BC.2", "IBM System z9 BC GA2"),
-#endif
CPUDEF_INIT(0x2097, 10, 1, 43, 0x00000000U, "z10EC", "IBM System z10 EC GA1"),
CPUDEF_INIT(0x2097, 10, 2, 43, 0x00000000U, "z10EC.2", "IBM System z10 EC GA2"),
CPUDEF_INIT(0x2098, 10, 2, 43, 0x00000000U, "z10BC", "IBM System z10 BC GA1"),
@@ -81,6 +80,7 @@ static S390CPUDef s390_cpu_defs[] = {
CPUDEF_INIT(0x2817, 11, 1, 44, 0x08000000U, "z196", "IBM zEnterprise 196 GA1"),
CPUDEF_INIT(0x2817, 11, 2, 44, 0x08000000U, "z196.2", "IBM zEnterprise 196 GA2"),
CPUDEF_INIT(0x2818, 11, 2, 44, 0x08000000U, "z114", "IBM zEnterprise 114 GA1"),
+#endif
CPUDEF_INIT(0x2827, 12, 1, 44, 0x08000000U, "zEC12", "IBM zEnterprise EC12 GA1"),
CPUDEF_INIT(0x2827, 12, 2, 44, 0x08000000U, "zEC12.2", "IBM zEnterprise EC12 GA2"),
CPUDEF_INIT(0x2828, 12, 2, 44, 0x08000000U, "zBC12", "IBM zEnterprise BC12 GA1"),
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index 9d6e6190d5..f822526acb 100644
index eb8ddebffb..2d3304bb4a 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -452,8 +452,10 @@ static void test_query_cpu_model_expansion(const void *data)
@@ -459,8 +459,10 @@ 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 */
@ -719,7 +877,7 @@ index 9d6e6190d5..f822526acb 100644
/* Enabling and disabling pmu should always work. */
assert_has_feature_enabled(qts, "max", "pmu");
@@ -470,6 +472,7 @@ static void test_query_cpu_model_expansion(const void *data)
@@ -477,6 +479,7 @@ 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");
@ -727,7 +885,7 @@ index 9d6e6190d5..f822526acb 100644
assert_has_feature_enabled(qts, "a64fx", "pmu");
assert_has_feature_enabled(qts, "a64fx", "aarch64");
/*
@@ -482,6 +485,7 @@ static void test_query_cpu_model_expansion(const void *data)
@@ -489,6 +492,7 @@ static void test_query_cpu_model_expansion(const void *data)
"{ 'sve384': true }");
assert_error(qts, "a64fx", "cannot enable sve640",
"{ 'sve640': true }");

497
0006-Machine-type-related-general-changes.patch
View File

@ -1,4 +1,4 @@
From 802da738d5231ef56d25f4ffcfa6e7d97698ee72 Mon Sep 17 00:00:00 2001
From dcaeeab5909a41372c9445e9f97282e8dd3d1d44 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
@ -8,24 +8,50 @@ split to allow easier review. It contains changes not related to any
architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (9.1.0):
- Upstream removed uuid_encoced argument on smbios_set_defaults
Rebase notes (10.0.0 rc0):
- Solve conflicting xhci_pci_properties (downstream vs upstream)
Rebase notes (10.0.0):
- Add riscv changes
- Added upstream compat changes
Rebase notes (10.1.0 rc2):
- Remove downstream change to i8254 (review comment)
Rebase notes (10.1.0):
- Added upstream compat changes from 10.1
Merged commits (9.1.0):
- 043ad5ce97 Add upstream compatibility bits (partial)
- bfbdab5824 rhel 9.4.0 machine type compat for virtio-gpu migration
Merged commits (10.0.0 rc0):
- 03502faf70 Add upstream compatibility bits (partial)
- f53dbf7532 remove stale compat definitions (partial)
- d93fcb3940 virtio-net: disable USO for all RHEL9 (partial)
---
hw/acpi/piix4.c | 2 +-
hw/arm/virt.c | 2 +-
hw/core/machine.c | 269 +++++++++++++++++++++++++++++++++++
hw/core/machine.c | 145 +++++++++++++++++++++++++++++++++++
hw/i386/fw_cfg.c | 3 +-
hw/net/rtl8139.c | 4 +-
hw/smbios/smbios.c | 46 +++++-
hw/timer/i8254_common.c | 2 +-
hw/usb/hcd-xhci-pci.c | 59 ++++++--
hw/riscv/virt.c | 4 +-
hw/smbios/smbios.c | 46 ++++++++++-
hw/usb/hcd-xhci-pci.c | 54 +++++++++----
hw/usb/hcd-xhci-pci.h | 1 +
hw/virtio/virtio-mem.c | 3 +-
include/hw/boards.h | 40 ++++++
include/hw/boards.h | 31 ++++++++
include/hw/firmware/smbios.h | 4 +-
include/hw/i386/pc.h | 3 +
13 files changed, 414 insertions(+), 24 deletions(-)
13 files changed, 277 insertions(+), 25 deletions(-)
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index debe1adb84..e8ddcd716e 100644
index 7a18f18dda..2b3678b8c6 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -245,7 +245,7 @@ static bool vmstate_test_migrate_acpi_index(void *opaque, int version_id)
@ -38,25 +64,25 @@ index debe1adb84..e8ddcd716e 100644
.fields = (const VMStateField[]) {
VMSTATE_PCI_DEVICE(parent_obj, PIIX4PMState),
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 6c6d155002..36e9b4b4e9 100644
index b525e00365..1800981317 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1651,7 +1651,7 @@ static void virt_build_smbios(VirtMachineState *vms)
@@ -1755,7 +1755,7 @@ static void virt_build_smbios(VirtMachineState *vms)
product = "KVM Virtual Machine";
}
smbios_set_defaults("QEMU", product,
vmc->smbios_old_sys_ver ? "1.0" : mc->name,
- true);
+ true, NULL, NULL);
- smbios_set_defaults("QEMU", product, mc->name);
+ smbios_set_defaults("QEMU", product, mc->name, NULL, NULL);
/* build the array of physical mem area from base_memmap */
mem_array.address = vms->memmap[VIRT_MEM].base;
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 37ede0e7d4..695cb89a46 100644
index bd47527479..2a1a42cebc 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -296,6 +296,275 @@ GlobalProperty hw_compat_2_1[] = {
@@ -288,6 +288,151 @@ GlobalProperty hw_compat_2_6[] = {
};
const size_t hw_compat_2_1_len = G_N_ELEMENTS(hw_compat_2_1);
const size_t hw_compat_2_6_len = G_N_ELEMENTS(hw_compat_2_6);
+/*
+ * RHEL only: machine types for previous major releases are deprecated
@ -64,6 +90,78 @@ index 37ede0e7d4..695cb89a46 100644
+const char *rhel_old_machine_deprecation =
+ "machine types for previous major releases are deprecated";
+
+GlobalProperty hw_compat_rhel_10_2[] = {
+ /* hw_compat_rhel_10_2 from hw_compat_10_0 */
+ { "scsi-hd", "dpofua", "off" },
+ /* hw_compat_rhel_10_2 from hw_compat_10_0 */
+ { "vfio-pci", "x-migration-load-config-after-iter", "off" },
+ /* hw_compat_rhel_10_2 from hw_compat_10_0 */
+ { "ramfb", "use-legacy-x86-rom", "true"},
+ /* hw_compat_rhel_10_2 from hw_compat_10_0 */
+ { "vfio-pci-nohotplug", "use-legacy-x86-rom", "true" },
+};
+const size_t hw_compat_rhel_10_2_len = G_N_ELEMENTS(hw_compat_10_0);
+
+GlobalProperty hw_compat_rhel_10_1[] = {
+ /* hw_compat_rhel_10_1 from hw_compat_9_1 */
+ { TYPE_PCI_DEVICE, "x-pcie-ext-tag", "false" },
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ {"arm-cpu", "backcompat-pauth-default-use-qarma5", "true"},
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "virtio-balloon-pci", "vectors", "0" },
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "virtio-balloon-pci-transitional", "vectors", "0" },
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "virtio-balloon-pci-non-transitional", "vectors", "0" },
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "virtio-mem-pci", "vectors", "0" },
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "migration", "multifd-clean-tls-termination", "false" },
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "migration", "send-switchover-start", "off"},
+ /* hw_compat_rhel_10_1 from hw_compat_9_2 */
+ { "vfio-pci", "x-migration-multifd-transfer", "off" },
+};
+const size_t hw_compat_rhel_10_1_len = G_N_ELEMENTS(hw_compat_rhel_10_1);
+
+
+GlobalProperty hw_compat_rhel_10_0[] = {
+ /* hw_compat_rhel_10_0 from hw_compat_9_0 */
+ {"arm-cpu", "backcompat-cntfrq", "true" },
+ /* hw_compat_rhel_10_0 from hw_compat_9_0 */
+ { "scsi-hd", "migrate-emulated-scsi-request", "false" },
+ /* hw_compat_rhel_10_0 from hw_compat_9_0 */
+ { "scsi-cd", "migrate-emulated-scsi-request", "false" },
+ /* hw_compat_rhel_10_0 from hw_compat_9_0 */
+ {"vfio-pci", "skip-vsc-check", "false" },
+ /* hw_compat_rhel_10_0 from hw_compat_9_0 */
+ { "virtio-pci", "x-pcie-pm-no-soft-reset", "off" },
+ /* hw_compat_rhel_10_0 from hw_compat_9_0 */
+ {"sd-card", "spec_version", "2" },
+};
+const size_t hw_compat_rhel_10_0_len = G_N_ELEMENTS(hw_compat_rhel_10_0);
+
+/* Apply this to all RHEL9 boards going backward and forward */
+GlobalProperty hw_compat_rhel_9[] = {
+ /* supported by userspace, but RHEL 9 *kernels* do not support USO. */
+ { TYPE_VIRTIO_NET, "host_uso", "off"},
+ { TYPE_VIRTIO_NET, "guest_uso4", "off"},
+ { TYPE_VIRTIO_NET, "guest_uso6", "off"},
+};
+const size_t hw_compat_rhel_9_len = G_N_ELEMENTS(hw_compat_rhel_9);
+
+GlobalProperty hw_compat_rhel_9_5[] = {
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { "migration", "zero-page-detection", "legacy"},
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { TYPE_VIRTIO_IOMMU_PCI, "granule", "4k" },
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "64" },
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { "virtio-gpu-device", "x-scanout-vmstate-version", "1" },
+};
+const size_t hw_compat_rhel_9_5_len = G_N_ELEMENTS(hw_compat_rhel_9_5);
+
+GlobalProperty hw_compat_rhel_9_4[] = {
+ /* hw_compat_rhel_9_4 from hw_compat_8_0 */
+ { TYPE_VIRTIO_NET, "host_uso", "off"},
@ -130,225 +228,29 @@ index 37ede0e7d4..695cb89a46 100644
+ { "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);
+
MachineState *current_machine;
static char *machine_get_kernel(Object *obj, Error **errp)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index d802d2787f..c7aa39a13e 100644
index 5c0bcd5f8a..07df7281d2 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -64,7 +64,8 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
@@ -75,7 +75,8 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
smbios_set_defaults("QEMU", mc->desc, mc->name,
- pcmc->smbios_uuid_encoded);
+ pcmc->smbios_uuid_encoded,
- smbios_set_defaults("QEMU", mc->desc, mc->name);
+ smbios_set_defaults("QEMU", mc->desc, mc->name,
+ pcmc->smbios_stream_product, pcmc->smbios_stream_version);
}
/* tell smbios about cpuid version and features */
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 897c86ec41..2d0db43f49 100644
index f4dd693abb..ac3a7376ad 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -3169,7 +3169,7 @@ static int rtl8139_pre_save(void *opaque)
@@ -3173,7 +3173,7 @@ static int rtl8139_pre_save(void *opaque)
static const VMStateDescription vmstate_rtl8139 = {
.name = "rtl8139",
@ -357,7 +259,7 @@ index 897c86ec41..2d0db43f49 100644
.minimum_version_id = 3,
.post_load = rtl8139_post_load,
.pre_save = rtl8139_pre_save,
@@ -3250,7 +3250,9 @@ static const VMStateDescription vmstate_rtl8139 = {
@@ -3254,7 +3254,9 @@ static const VMStateDescription vmstate_rtl8139 = {
VMSTATE_UINT32(tally_counters.TxMCol, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkPhy, RTL8139State),
VMSTATE_UINT64(tally_counters.RxOkBrd, RTL8139State),
@ -367,8 +269,30 @@ index 897c86ec41..2d0db43f49 100644
VMSTATE_UINT16(tally_counters.TxAbt, RTL8139State),
VMSTATE_UINT16(tally_counters.TxUndrn, RTL8139State),
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index 47e573f85a..ab5a9ec613 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -1402,7 +1402,7 @@ static void virt_build_smbios(RISCVVirtState *s)
product = "KVM Virtual Machine";
}
- smbios_set_defaults("QEMU", product, mc->name);
+ smbios_set_defaults("QEMU", product, mc->name, NULL, NULL);
if (riscv_is_32bit(&s->soc[0])) {
smbios_set_default_processor_family(0x200);
@@ -1920,7 +1920,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
mc->desc = "RISC-V VirtIO board";
mc->init = virt_machine_init;
mc->max_cpus = VIRT_CPUS_MAX;
- mc->default_cpu_type = TYPE_RISCV_CPU_BASE;
+ mc->default_cpu_type = TYPE_RISCV_CPU_MAX;
mc->block_default_type = IF_VIRTIO;
mc->no_cdrom = 1;
mc->pci_allow_0_address = true;
diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c
index eed5787b15..68608a3403 100644
index 1ac063cfb4..03f7a00ed1 100644
--- a/hw/smbios/smbios.c
+++ b/hw/smbios/smbios.c
@@ -39,6 +39,10 @@ size_t usr_blobs_len;
@ -382,7 +306,7 @@ index eed5787b15..68608a3403 100644
uint8_t *smbios_tables;
size_t smbios_tables_len;
unsigned smbios_table_max;
@@ -629,7 +633,7 @@ static void smbios_build_type_1_table(void)
@@ -627,7 +631,7 @@ static void smbios_build_type_1_table(void)
static void smbios_build_type_2_table(void)
{
@ -391,17 +315,16 @@ index eed5787b15..68608a3403 100644
SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer);
SMBIOS_TABLE_SET_STR(2, product_str, type2.product);
@@ -1018,16 +1022,52 @@ void smbios_set_default_processor_family(uint16_t processor_family)
@@ -1015,15 +1019,51 @@ void smbios_set_default_processor_family(uint16_t processor_family)
}
void smbios_set_defaults(const char *manufacturer, const char *product,
const char *version,
- bool uuid_encoded)
+ bool uuid_encoded,
- const char *version)
+ const char *version,
+ const char *stream_product,
+ const char *stream_version)
{
smbios_have_defaults = true;
smbios_uuid_encoded = uuid_encoded;
+ /*
+ * If @stream_product & @stream_version are non-NULL, then
@ -446,24 +369,11 @@ index eed5787b15..68608a3403 100644
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 28fdabc321..bad13ec224 100644
--- a/hw/timer/i8254_common.c
+++ b/hw/timer/i8254_common.c
@@ -229,7 +229,7 @@ static const VMStateDescription vmstate_pit_common = {
.pre_save = pit_dispatch_pre_save,
.post_load = pit_dispatch_post_load,
.fields = (const 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 4423983308..43b4b71fdf 100644
index b93c80b09d..f4a2f1a1de 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)
@@ -120,6 +120,33 @@ static int xhci_pci_vmstate_post_load(void *opaque, int version_id)
return 0;
}
@ -497,7 +407,7 @@ index 4423983308..43b4b71fdf 100644
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)
@@ -144,23 +171,12 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp)
s->xhci.nec_quirks = true;
}
@ -524,7 +434,7 @@ index 4423983308..43b4b71fdf 100644
}
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)
@@ -172,6 +188,14 @@ static void usb_xhci_pci_realize(struct PCIDevice *dev, Error **errp)
assert(ret > 0);
}
@ -539,42 +449,32 @@ index 4423983308..43b4b71fdf 100644
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[] = {
@@ -221,6 +245,8 @@ static const Property xhci_pci_properties[] = {
DEFINE_PROP_ON_OFF_AUTO("msix", XHCIPciState, msix, ON_OFF_AUTO_AUTO),
DEFINE_PROP_BOOL("conditional-intr-mapping", XHCIPciState,
conditional_intr_mapping, false),
+ /* 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);
static void xhci_class_init(ObjectClass *klass, const void *data)
diff --git a/hw/usb/hcd-xhci-pci.h b/hw/usb/hcd-xhci-pci.h
index 08f70ce97c..1be7527c1b 100644
index 5b61ae8455..3170db064b 100644
--- a/hw/usb/hcd-xhci-pci.h
+++ b/hw/usb/hcd-xhci-pci.h
@@ -40,6 +40,7 @@ typedef struct XHCIPciState {
XHCIState xhci;
@@ -41,6 +41,7 @@ typedef struct XHCIPciState {
OnOffAuto msi;
OnOffAuto msix;
bool conditional_intr_mapping;
+ bool rh_late_msi_cap; /* bz 1912846 */
} XHCIPciState;
#endif
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index ffd119ebac..0e2be2219c 100644
index c46f6f9c3e..1805597879 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -1694,8 +1694,9 @@ static Property virtio_mem_properties[] = {
@@ -1699,8 +1699,9 @@ static const Property virtio_mem_properties[] = {
#endif
DEFINE_PROP_BOOL(VIRTIO_MEM_EARLY_MIGRATION_PROP, VirtIOMEM,
early_migration, true),
@ -582,17 +482,32 @@ index ffd119ebac..0e2be2219c 100644
DEFINE_PROP_BOOL(VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, VirtIOMEM,
- dynamic_memslots, false),
+ dynamic_memslots, true),
DEFINE_PROP_END_OF_LIST(),
};
static uint64_t virtio_mem_rdm_get_min_granularity(const RamDiscardManager *rdm,
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 8b8f6d5c00..0466f9d0f3 100644
index f94713e6e2..a434b21909 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -512,4 +512,44 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
@@ -863,4 +863,35 @@ extern const size_t hw_compat_2_7_len;
extern GlobalProperty hw_compat_2_6[];
extern const size_t hw_compat_2_6_len;
+extern GlobalProperty hw_compat_rhel_10_2[];
+extern const size_t hw_compat_rhel_10_2_len;
+
+extern GlobalProperty hw_compat_rhel_10_1[];
+extern const size_t hw_compat_rhel_10_1_len;
+
+extern GlobalProperty hw_compat_rhel_10_0[];
+extern const size_t hw_compat_rhel_10_0_len;
+
+extern GlobalProperty hw_compat_rhel_9[];
+extern const size_t hw_compat_rhel_9_len;
+
+extern GlobalProperty hw_compat_rhel_9_5[];
+extern const size_t hw_compat_rhel_9_5_len;
+
+extern GlobalProperty hw_compat_rhel_9_4[];
+extern const size_t hw_compat_rhel_9_4_len;
+
@ -608,54 +523,30 @@ index 8b8f6d5c00..0466f9d0f3 100644
+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 8d3fb2fb3b..d9d6d7a169 100644
index f066ab7262..e805d25fbe 100644
--- a/include/hw/firmware/smbios.h
+++ b/include/hw/firmware/smbios.h
@@ -332,7 +332,9 @@ void smbios_entry_add(QemuOpts *opts, Error **errp);
@@ -331,7 +331,9 @@ void smbios_add_usr_blob_size(size_t size);
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 uuid_encoded);
+ bool uuid_encoded,
- const char *version);
+ const char *version,
+ const char *stream_product,
+ const char *stream_version);
void smbios_set_default_processor_family(uint16_t processor_family);
uint8_t *smbios_get_table_legacy(size_t *length, Error **errp);
void smbios_get_tables(MachineState *ms,
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 27a68071d7..ebd8f973f2 100644
index 79b72c54dd..3b4ea24c20 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -112,6 +112,9 @@ struct PCMachineClass {
@@ -103,6 +103,9 @@ struct PCMachineClass {
bool smbios_defaults;
bool smbios_legacy_mode;
bool smbios_uuid_encoded;
SmbiosEntryPointType default_smbios_ep_type;
+ /* New fields needed for Windows HardwareID-6 matching */
+ const char *smbios_stream_product;

430
0007-Add-aarch64-machine-types.patch
View File

@ -1,430 +0,0 @@
From 3afc6e4cb6725d01b8f89207701bca199c9ecc9f 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>
---
hw/arm/virt.c | 299 +++++++++++++++++++++++++++++++++++++++++-
include/hw/arm/virt.h | 8 ++
2 files changed, 306 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 36e9b4b4e9..22bc345137 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -101,6 +101,7 @@ static void arm_virt_compat_set(MachineClass *mc)
arm_virt_compat_len);
}
+#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) \
@@ -128,7 +129,63 @@ static void arm_virt_compat_set(MachineClass *mc)
DEFINE_VIRT_MACHINE_LATEST(major, minor, true)
#define DEFINE_VIRT_MACHINE(major, minor) \
DEFINE_VIRT_MACHINE_LATEST(major, minor, false)
+#endif /* disabled for RHEL */
+
+/*
+ * 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. They may be overriden by older machine compats.
+ *
+ * virtio-net-pci variant romfiles are not needed because edk2 does
+ * fully support the pxe boot. Besides virtio romfiles are not shipped
+ * on rhel/aarch64.
+ */
+GlobalProperty arm_rhel_compat[] = {
+ {"virtio-net-pci", "romfile", "" },
+ {"virtio-net-pci-transitional", "romfile", "" },
+ {"virtio-net-pci-non-transitional", "romfile", "" },
+};
+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
+/*
+ * This cannot be called from the rhel_virt_class_init() because
+ * TYPE_RHEL_MACHINE is abstract and mc->compat_props g_ptr_array_new()
+ * only is called on virt-rhelm.n.s non abstract class init.
+ */
+static void arm_rhel_compat_set(MachineClass *mc)
+{
+ compat_props_add(mc->compat_props, arm_rhel_compat,
+ arm_rhel_compat_len);
+}
+
+#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); \
+ arm_rhel_compat_set(mc); \
+ 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)
/* Number of external interrupt lines to configure the GIC with */
#define NUM_IRQS 256
@@ -2355,6 +2412,7 @@ 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);
@@ -2382,6 +2440,7 @@ 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)
{
@@ -2397,6 +2456,7 @@ 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);
@@ -2410,6 +2470,7 @@ static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
vms->highmem_compact = value;
}
+#endif /* disabled for RHEL */
static bool virt_get_highmem_redists(Object *obj, Error **errp)
{
@@ -2453,7 +2514,6 @@ static void virt_set_highmem_mmio(Object *obj, bool value, Error **errp)
vms->highmem_mmio = value;
}
-
static bool virt_get_its(Object *obj, Error **errp)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
@@ -2468,6 +2528,7 @@ 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);
@@ -2481,6 +2542,7 @@ 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)
{
@@ -2564,6 +2626,7 @@ 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);
@@ -2577,6 +2640,7 @@ 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)
{
@@ -2949,6 +3013,7 @@ 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);
@@ -3463,3 +3528,235 @@ 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);
+ arm_virt_compat_set(mc);
+
+ 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;
+ /* platform instead of architectural choice */
+ mc->cpu_cluster_has_numa_boundary = true;
+ mc->default_ram_id = "mach-virt.ram";
+ mc->default_nic = "virtio-net-pci";
+
+ 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_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",
+ "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->highmem_compact = !vmc->no_highmem_compact;
+ 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 rhel940_virt_options(MachineClass *mc)
+{
+}
+DEFINE_RHEL_MACHINE_AS_LATEST(9, 4, 0)
+
+static void rhel920_virt_options(MachineClass *mc)
+{
+ rhel940_virt_options(mc);
+
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
+
+ /* RHEL 9.4 is the first supported release */
+ mc->deprecation_reason =
+ "machine types for versions prior to 9.4 are deprecated";
+}
+DEFINE_RHEL_MACHINE(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, 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);
+
+ /* 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)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index bb486d36b1..237fc77bda 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -179,9 +179,17 @@ 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);
--
2.39.3

36
0007-meson-temporarily-disable-Wunused-function.patch Normal file
View File

@ -0,0 +1,36 @@
From 7eff7b32584a50d73053b4e3e007621b14ebf766 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 13:32:32 +0100
Subject: meson: temporarily disable -Wunused-function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Deleting the upstream versioned machine types will leave some functions
unused until RHEL machine types are added once again. Temporarily
disable the -Wunused-function warning to preserve bisectability with
fine grained patch splits.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Rebase notes (9.1.0)
- New patch
---
meson.build | 1 +
1 file changed, 1 insertion(+)
diff --git a/meson.build b/meson.build
index 50c774a195..0e0120a613 100644
--- a/meson.build
+++ b/meson.build
@@ -757,6 +757,7 @@ warn_flags = [
'-Wno-string-plus-int',
'-Wno-tautological-type-limit-compare',
'-Wno-typedef-redefinition',
+ '-Wno-unused-function',
]
if host_os != 'darwin'
--
2.39.3

273
0008-Add-s390x-machine-types.patch
View File

@ -1,273 +0,0 @@
From fa1d70b9a9cfe020e7ebe7798ebb70314658ccf7 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>
---
hw/s390x/s390-virtio-ccw.c | 159 +++++++++++++++++++++++++++++++
target/s390x/cpu_models.c | 11 +++
target/s390x/cpu_models.h | 2 +
target/s390x/cpu_models_sysemu.c | 2 +
4 files changed, 174 insertions(+)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index b1dcb3857f..ff753a29e0 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -859,6 +859,7 @@ bool css_migration_enabled(void)
} \
type_init(ccw_machine_register_##suffix)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void ccw_machine_9_0_instance_options(MachineState *machine)
{
}
@@ -1272,6 +1273,164 @@ 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_rhel940_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_machine_rhel940_class_options(MachineClass *mc)
+{
+}
+DEFINE_CCW_MACHINE(rhel940, "rhel9.4.0", true);
+
+static void ccw_machine_rhel920_instance_options(MachineState *machine)
+{
+ ccw_machine_rhel940_instance_options(machine);
+}
+
+static void ccw_machine_rhel920_class_options(MachineClass *mc)
+{
+ ccw_machine_rhel940_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
+ mc->smp_props.drawers_supported = false; /* from ccw_machine_8_1 */
+ mc->smp_props.books_supported = false; /* from ccw_machine_8_1 */
+}
+DEFINE_CCW_MACHINE(rhel920, "rhel9.2.0", false);
+
+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);
+}
+
+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", },
+ };
+
+ 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", false);
+
+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)
+{
+ 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;
+}
+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)
+{
+ 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);
+
+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 8ed3bb6a27..370b3b3065 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -46,6 +46,9 @@
* 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"),
@@ -866,22 +869,30 @@ 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 d7b8912989..1a806a97c4 100644
--- a/target/s390x/cpu_models.h
+++ b/target/s390x/cpu_models.h
@@ -38,6 +38,8 @@ typedef 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;
} S390CPUDef;
/* CPU model based on a CPU definition */
diff --git a/target/s390x/cpu_models_sysemu.c b/target/s390x/cpu_models_sysemu.c
index 0728bfcc20..ca2e5d91e2 100644
--- a/target/s390x/cpu_models_sysemu.c
+++ b/target/s390x/cpu_models_sysemu.c
@@ -59,6 +59,7 @@ 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;
@@ -68,6 +69,7 @@ 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;
--
2.39.3

102
0008-Remove-upstream-machine-types-for-aarch64-s390x-and-.patch Normal file
View File

@ -0,0 +1,102 @@
From fca16c8b4612edfa63d7882379897a9907dde738 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 10 Jul 2024 02:25:51 -0400
Subject: Remove upstream machine types for aarch64, s390x and x86_64
architectures
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
We will replace upstream machine types on supported architectures with RHEL
machine types.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
Rebase notes (9.1.0):
- Split off commits adding RHEL machine types
---
hw/arm/virt.c | 2 ++
hw/i386/pc_piix.c | 2 ++
hw/i386/pc_q35.c | 2 ++
hw/s390x/s390-virtio-ccw.c | 3 +++
4 files changed, 9 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 1800981317..e6e98fef1c 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3459,6 +3459,7 @@ static void machvirt_machine_init(void)
}
type_init(machvirt_machine_init);
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void virt_machine_10_1_options(MachineClass *mc)
{
}
@@ -3634,3 +3635,4 @@ static void virt_machine_4_1_options(MachineClass *mc)
mc->auto_enable_numa_with_memhp = false;
}
DEFINE_VIRT_MACHINE(4, 1)
+#endif /* disabled for RHEL */
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index c03324281b..acf010e20f 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -475,6 +475,7 @@ static void pc_i440fx_init(MachineState *machine)
#define DEFINE_I440FX_MACHINE_AS_LATEST(major, minor) \
DEFINE_PC_VER_MACHINE(pc_i440fx, "pc-i440fx", pc_i440fx_init, true, "pc", major, minor);
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void pc_i440fx_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
@@ -802,6 +803,7 @@ static void pc_i440fx_machine_2_6_options(MachineClass *m)
}
DEFINE_I440FX_MACHINE(2, 6);
+#endif /* Disabled for Red Hat Enterprise Linux */
#ifdef CONFIG_ISAPC
static void isapc_machine_options(MachineClass *m)
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index b309b2b378..2203ffd67e 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -374,6 +374,7 @@ static void pc_q35_machine_options(MachineClass *m)
pc_q35_compat_defaults, pc_q35_compat_defaults_len);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void pc_q35_machine_10_1_options(MachineClass *m)
{
pc_q35_machine_options(m);
@@ -685,3 +686,4 @@ static void pc_q35_machine_2_6_options(MachineClass *m)
}
DEFINE_Q35_MACHINE(2, 6);
+#endif /* Disabled for Red Hat Enterprise Linux */
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index a79bd13275..2fca2bcf4d 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -911,6 +911,7 @@ static const TypeInfo ccw_machine_info = {
DEFINE_CCW_MACHINE_IMPL(false, major, minor)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void ccw_machine_10_1_instance_options(MachineState *machine)
{
}
@@ -1167,6 +1168,8 @@ static void ccw_machine_4_2_class_options(MachineClass *mc)
}
DEFINE_CCW_MACHINE(4, 2);
+#endif /* disabled for RHEL */
+
static void ccw_machine_register_types(void)
{
type_register_static(&ccw_machine_info);
--
2.39.3

195
0009-Adapt-versioned-machine-type-macros-for-RHEL.patch Normal file
View File

@ -0,0 +1,195 @@
From 0bc1a45f789d1aa6b75496739a77dbc77fc2492c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 15:27:03 +0100
Subject: Adapt versioned machine type macros for RHEL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The versioned machine type macros are changed thus:
* All symbol names get 'rhel' inserted eg 'virt_rhel_macine_9_4_0_<blah>'
* All machine type names get 'rhel' inserted eg 'virt-rhel9.4.0-machine'
* Lifecycle is changed to deprecate after 1 major RHEL release,
force non-registration (effectively deletion) after 2 major releases
* Custom message to explain RHEL deprecation/deletion policy
* Remove upstream logic that temporarily disabled deletion since
the upstream constraints in this area don't apply to RHEL
* For automatic deprecation/deletion, RHEL_VERSION is defined
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase changes (10.1.0 rc0):
- Added deprecetion limits change to docs/conf.py
---
.distro/Makefile | 2 +-
.distro/Makefile.common | 1 +
.distro/qemu-kvm.spec.template | 1 +
.distro/scripts/process-patches.sh | 3 +++
docs/conf.py | 4 +--
include/hw/boards.h | 39 ++++++++++++------------------
meson.build | 1 +
meson_options.txt | 2 ++
scripts/meson-buildoptions.sh | 2 ++
9 files changed, 29 insertions(+), 26 deletions(-)
diff --git a/docs/conf.py b/docs/conf.py
index f892a6e1da..0b8861e4bf 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -140,8 +140,8 @@
# MACHINE_VER_DELETION_MAJOR & MACHINE_VER_DEPRECATION_MAJOR
# defined in include/hw/boards.h and the introductory text in
# docs/about/deprecated.rst
-ver_machine_deprecation_version = "%d.%d.0" % (major - 3, minor)
-ver_machine_deletion_version = "%d.%d.0" % (major - 6, minor)
+ver_machine_deprecation_version = "%d.%d.0" % (major - 1, minor)
+ver_machine_deletion_version = "%d.%d.0" % (major - 2, minor)
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
diff --git a/include/hw/boards.h b/include/hw/boards.h
index a434b21909..da2fc92ce8 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -577,16 +577,16 @@ struct MachineState {
* "{prefix}-{major}.{minor}.{micro}-{tag}"
*/
#define _MACHINE_VER_TYPE_NAME2(prefix, major, minor) \
- prefix "-" #major "." #minor TYPE_MACHINE_SUFFIX
+ prefix "-rhel" #major "." #minor TYPE_MACHINE_SUFFIX
#define _MACHINE_VER_TYPE_NAME3(prefix, major, minor, micro) \
- prefix "-" #major "." #minor "." #micro TYPE_MACHINE_SUFFIX
+ prefix "-rhel" #major "." #minor "." #micro TYPE_MACHINE_SUFFIX
#define _MACHINE_VER_TYPE_NAME4(prefix, major, minor, _unused_, tag) \
- prefix "-" #major "." #minor "-" #tag TYPE_MACHINE_SUFFIX
+ prefix "-rhel" #major "." #minor "-" #tag TYPE_MACHINE_SUFFIX
#define _MACHINE_VER_TYPE_NAME5(prefix, major, minor, micro, _unused_, tag) \
- prefix "-" #major "." #minor "." #micro "-" #tag TYPE_MACHINE_SUFFIX
+ prefix "-rhel" #major "." #minor "." #micro "-" #tag TYPE_MACHINE_SUFFIX
#define MACHINE_VER_TYPE_NAME(prefix, ...) \
_MACHINE_VER_PICK(__VA_ARGS__, \
@@ -614,16 +614,16 @@ struct MachineState {
* {prefix}_machine_{major}_{minor}_{micro}_{tag}_{sym}
*/
#define _MACHINE_VER_SYM2(sym, prefix, major, minor) \
- prefix ## _machine_ ## major ## _ ## minor ## _ ## sym
+ prefix ## _rhel_machine_ ## major ## _ ## minor ## _ ## sym
#define _MACHINE_VER_SYM3(sym, prefix, major, minor, micro) \
- prefix ## _machine_ ## major ## _ ## minor ## _ ## micro ## _ ## sym
+ prefix ## _rhel_machine_ ## major ## _ ## minor ## _ ## micro ## _ ## sym
#define _MACHINE_VER_SYM4(sym, prefix, major, minor, _unused_, tag) \
- prefix ## _machine_ ## major ## _ ## minor ## _ ## tag ## _ ## sym
+ prefix ## _rhel_machine_ ## major ## _ ## minor ## _ ## tag ## _ ## sym
#define _MACHINE_VER_SYM5(sym, prefix, major, minor, micro, _unused_, tag) \
- prefix ## _machine_ ## major ## _ ## minor ## _ ## micro ## _ ## tag ## _ ## sym
+ prefix ## _rhel_machine_ ## major ## _ ## minor ## _ ## micro ## _ ## tag ## _ ## sym
#define MACHINE_VER_SYM(sym, prefix, ...) \
_MACHINE_VER_PICK(__VA_ARGS__, \
@@ -642,17 +642,16 @@ struct MachineState {
* and ver_machine_deletion_version logic in docs/conf.py and
* the text in docs/about/deprecated.rst
*/
-#define MACHINE_VER_DELETION_MAJOR 6
-#define MACHINE_VER_DEPRECATION_MAJOR 3
+#define MACHINE_VER_DELETION_MAJOR 2
+#define MACHINE_VER_DEPRECATION_MAJOR 1
/*
* Expands to a static string containing a deprecation
* message for a versioned machine type
*/
#define MACHINE_VER_DEPRECATION_MSG \
- "machines more than " stringify(MACHINE_VER_DEPRECATION_MAJOR) \
- " years old are subject to deletion after " \
- stringify(MACHINE_VER_DELETION_MAJOR) " years"
+ "machines from the previous RHEL major release are " \
+ "subject to deletion in the next RHEL major release"
#define _MACHINE_VER_IS_CURRENT_EXPIRED(cutoff, major, minor) \
(((QEMU_VERSION_MAJOR - major) > cutoff) || \
@@ -683,12 +682,7 @@ struct MachineState {
* If this ever changes the logic below will need modifying....
*/
#define _MACHINE_VER_IS_EXPIRED_IMPL(cutoff, major, minor) \
- ((QEMU_VERSION_MICRO < 50 && \
- _MACHINE_VER_IS_CURRENT_EXPIRED(cutoff, major, minor)) || \
- (QEMU_VERSION_MICRO >= 50 && QEMU_VERSION_MINOR < 2 && \
- _MACHINE_VER_IS_NEXT_MINOR_EXPIRED(cutoff, major, minor)) || \
- (QEMU_VERSION_MICRO >= 50 && QEMU_VERSION_MINOR == 2 && \
- _MACHINE_VER_IS_NEXT_MAJOR_EXPIRED(cutoff, major, minor)))
+ ((RHEL_VERSION - major) >= cutoff)
#define _MACHINE_VER_IS_EXPIRED2(cutoff, major, minor) \
_MACHINE_VER_IS_EXPIRED_IMPL(cutoff, major, minor)
@@ -750,10 +744,9 @@ struct MachineState {
* This must be unconditionally used in the register
* method for all machine types which support versioning.
*
- * Inijtially it will effectively be a no-op, but after a
- * suitable period of time has passed, it will cause
- * execution of the method to return, avoiding registration
- * of the machine
+ * It will automatically avoid registration of machines
+ * that should have been deleted at the start of this
+ * RHEL release
*/
#define MACHINE_VER_DELETION(...) \
do { \
diff --git a/meson.build b/meson.build
index 0e0120a613..23494666d9 100644
--- a/meson.build
+++ b/meson.build
@@ -2636,6 +2636,7 @@ config_host_data.set('QEMU_VERSION', '"@0@"'.format(meson.project_version()))
config_host_data.set('QEMU_VERSION_MAJOR', meson.project_version().split('.')[0])
config_host_data.set('QEMU_VERSION_MINOR', meson.project_version().split('.')[1])
config_host_data.set('QEMU_VERSION_MICRO', meson.project_version().split('.')[2])
+config_host_data.set('RHEL_VERSION', get_option('rhel_version').split('.')[0])
config_host_data.set_quoted('CONFIG_HOST_DSOSUF', host_dsosuf)
config_host_data.set('HAVE_HOST_BLOCK_DEVICE', have_host_block_device)
diff --git a/meson_options.txt b/meson_options.txt
index fff1521e58..f45d7ded45 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -2,6 +2,8 @@
# on the configure script command line. If you add more, list them in
# scripts/meson-buildoptions.py's SKIP_OPTIONS constant too.
+option('rhel_version', type: 'string', value: '0.0',
+ description: 'RHEL major/minor version')
option('qemu_suffix', type : 'string', value: 'qemu',
description: 'Suffix for QEMU data/modules/config directories (can be empty)')
option('docdir', type : 'string', value : 'share/doc',
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index 0ebe6bc52a..4146dbc88d 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -75,6 +75,7 @@ meson_options_help() {
printf "%s\n" ' [QEMU]'
printf "%s\n" ' --qemu-ga-version=VALUE version number for qemu-ga installer'
printf "%s\n" ' --rtsig-map=VALUE default value of QEMU_RTSIG_MAP [NULL]'
+ printf "%s\n" ' --rhel-version=VALUE RHEL major/minor version [0.0]'
printf "%s\n" ' --smbd=VALUE Path to smbd for slirp networking'
printf "%s\n" ' --sysconfdir=VALUE Sysconf data directory [etc]'
printf "%s\n" ' --tls-priority=VALUE Default TLS protocol/cipher priority string'
@@ -465,6 +466,7 @@ _meson_option_parse() {
--disable-relocatable) printf "%s" -Drelocatable=false ;;
--enable-replication) printf "%s" -Dreplication=enabled ;;
--disable-replication) printf "%s" -Dreplication=disabled ;;
+ --rhel-version=*) quote_sh "-Drhel_version=$2" ;;
--enable-rng-none) printf "%s" -Drng_none=true ;;
--disable-rng-none) printf "%s" -Drng_none=false ;;
--rtsig-map=*) quote_sh "-Drtsig_map=$2" ;;
--
2.39.3

920
0009-Add-x86_64-machine-types.patch
View File

@ -1,920 +0,0 @@
From ec10588d2f5d748005e0dca42b299ae15868a900 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>
---
hw/i386/fw_cfg.c | 2 +-
hw/i386/pc.c | 159 ++++++++++++++++++++-
hw/i386/pc_piix.c | 109 ++++++++++++++
hw/i386/pc_q35.c | 285 +++++++++++++++++++++++++++++++++++++
include/hw/boards.h | 2 +
include/hw/i386/pc.h | 33 +++++
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, 617 insertions(+), 4 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index c7aa39a13e..283c3f4c16 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -63,7 +63,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", mc->desc, mc->name,
+ smbios_set_defaults("Red Hat", "KVM", mc->desc,
pcmc->smbios_uuid_encoded,
pcmc->smbios_stream_product, pcmc->smbios_stream_version);
}
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 5c21b0c4db..4a154c1a9a 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -326,6 +326,161 @@ GlobalProperty pc_compat_2_0[] = {
};
const size_t pc_compat_2_0_len = G_N_ELEMENTS(pc_compat_2_0);
+/* 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_3_compat[] = {
+ /* pc_rhel_9_3_compat from pc_compat_8_0 */
+ { "virtio-mem", "unplugged-inaccessible", "auto" },
+};
+const size_t pc_rhel_9_3_compat_len = G_N_ELEMENTS(pc_rhel_9_3_compat);
+
+GlobalProperty pc_rhel_9_2_compat[] = {
+ /* pc_rhel_9_2_compat from pc_compat_7_2 */
+ { "ICH9-LPC", "noreboot", "true" },
+};
+const size_t pc_rhel_9_2_compat_len = G_N_ELEMENTS(pc_rhel_9_2_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;
@@ -1813,6 +1968,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
pcmc->resizable_acpi_blob = true;
x86mc->apic_xrupt_override = 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;
@@ -1823,7 +1979,8 @@ 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 18ba076609..a647262d63 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -52,6 +52,7 @@
#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"
@@ -422,6 +423,7 @@ static void pc_set_south_bridge(Object *obj, int value, Error **errp)
* 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);
@@ -951,3 +953,110 @@ 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->pci_root_uid = 0;
+ pcmc->resizable_acpi_blob = true;
+ m->default_nic = "e1000";
+ 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_DEVICE);
+}
+
+static void pc_machine_rhel760_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ ObjectClass *oc = OBJECT_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;
+ /* From pc_i440fx_7_0_machine_options() */
+ pcmc->enforce_amd_1tb_hole = false;
+ /* From pc_i440fx_8_0_machine_options() */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
+ /* From pc_i440fx_8_1_machine_options() */
+ pcmc->broken_32bit_mem_addr_check = true;
+ /* Introduced in QEMU 8.2 */
+ pcmc->default_south_bridge = TYPE_PIIX3_DEVICE;
+
+ object_class_property_add_enum(oc, "x-south-bridge", "PCSouthBridgeOption",
+ &PCSouthBridgeOption_lookup,
+ pc_get_south_bridge,
+ pc_set_south_bridge);
+ object_class_property_set_description(oc, "x-south-bridge",
+ "Use a different south bridge than PIIX3");
+
+
+ compat_props_add(m->compat_props, hw_compat_rhel_9_4,
+ hw_compat_rhel_9_4_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_3,
+ hw_compat_rhel_9_3_len);
+ compat_props_add(m->compat_props, pc_rhel_9_3_compat,
+ pc_rhel_9_3_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_2,
+ hw_compat_rhel_9_2_len);
+ compat_props_add(m->compat_props, pc_rhel_9_2_compat,
+ pc_rhel_9_2_compat_len);
+ 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 c7bc8a2041..e872dc7e46 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -341,6 +341,7 @@ 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);
@@ -693,3 +694,287 @@ 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->pci_root_uid = 0;
+ m->default_nic = "e1000e";
+ 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);
+ compat_props_add(m->compat_props,
+ pc_q35_compat_defaults, pc_q35_compat_defaults_len);
+}
+
+static void pc_q35_init_rhel940(MachineState *machine)
+{
+ pc_q35_init(machine);
+}
+
+static void pc_q35_machine_rhel940_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_rhel_options(m);
+ m->desc = "RHEL-9.4.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.4.0";
+}
+
+DEFINE_PC_MACHINE(q35_rhel940, "pc-q35-rhel9.4.0", pc_q35_init_rhel940,
+ pc_q35_machine_rhel940_options);
+
+
+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_rhel940_options(m);
+ m->desc = "RHEL-9.2.0 PC (Q35 + ICH9, 2009)";
+ m->alias = NULL;
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.2.0";
+
+ /* From pc_q35_8_0_machine_options() */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
+ /* From pc_q35_8_1_machine_options() */
+ pcmc->broken_32bit_mem_addr_check = true;
+
+ compat_props_add(m->compat_props, hw_compat_rhel_9_4,
+ hw_compat_rhel_9_4_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_3,
+ hw_compat_rhel_9_3_len);
+ compat_props_add(m->compat_props, pc_rhel_9_3_compat,
+ pc_rhel_9_3_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_2,
+ hw_compat_rhel_9_2_len);
+ compat_props_add(m->compat_props, pc_rhel_9_2_compat,
+ pc_rhel_9_2_compat_len);
+}
+
+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);
+}
+
+static void pc_q35_machine_rhel900_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(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->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,
+ 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/include/hw/boards.h b/include/hw/boards.h
index 0466f9d0f3..46b8725c41 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -283,6 +283,8 @@ 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 ebd8f973f2..a984c951ad 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -291,6 +291,39 @@ extern const size_t pc_compat_2_1_len;
extern GlobalProperty pc_compat_2_0[];
extern const size_t pc_compat_2_0_len;
+extern GlobalProperty pc_rhel_compat[];
+extern const size_t pc_rhel_compat_len;
+
+extern GlobalProperty pc_rhel_9_3_compat[];
+extern const size_t pc_rhel_9_3_compat_len;
+
+extern GlobalProperty pc_rhel_9_2_compat[];
+extern const size_t pc_rhel_9_2_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 33760a2ee1..be7b0663cd 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -2190,9 +2190,13 @@ static const CPUCaches epyc_genoa_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,
@@ -2213,6 +2217,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "phenom",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 16,
@@ -2245,6 +2250,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "core2duo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2287,6 +2293,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm64",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 0xd,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -2328,6 +2335,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "qemu32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 4,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2342,6 +2350,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "kvm32",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_INTEL,
.family = 15,
@@ -2372,6 +2381,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "coreduo",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2405,6 +2415,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "486",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 4,
@@ -2417,6 +2428,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 1,
.vendor = CPUID_VENDOR_INTEL,
.family = 5,
@@ -2429,6 +2441,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2441,6 +2454,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "pentium3",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 3,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2453,6 +2467,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "athlon",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 2,
.vendor = CPUID_VENDOR_AMD,
.family = 6,
@@ -2468,6 +2483,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "n270",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2493,6 +2509,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Conroe",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -2533,6 +2550,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Penryn",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 10,
.vendor = CPUID_VENDOR_INTEL,
.family = 6,
@@ -4394,6 +4412,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G1",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -4414,6 +4433,7 @@ static const X86CPUDefinition builtin_x86_defs[] = {
},
{
.name = "Opteron_G2",
+ .deprecation_note = RHEL_CPU_DEPRECATION,
.level = 5,
.vendor = CPUID_VENDOR_AMD,
.family = 15,
@@ -4436,6 +4456,7 @@ 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 9c791b7b05..b91af5051f 100644
--- a/target/i386/kvm/kvm-cpu.c
+++ b/target/i386/kvm/kvm-cpu.c
@@ -138,6 +138,7 @@ 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 e68cbe9293..739f33db47 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3715,6 +3715,7 @@ 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);
@@ -4069,6 +4070,9 @@ 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 78f1cf8186..ac954c9b06 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);
--
2.39.3

231
0010-Enable-make-check.patch
View File

@ -1,231 +0,0 @@
From 241ad69d849fce983685fc754fc0572c5b737cbe 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>
---
.distro/qemu-kvm.spec.template | 4 ++--
tests/avocado/replay_kernel.py | 2 +-
tests/avocado/reverse_debugging.py | 2 +-
tests/avocado/tcg_plugins.py | 6 ++---
tests/qemu-iotests/meson.build | 34 ++++++++++++++---------------
tests/qemu-iotests/testenv.py | 3 +++
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 | 1 -
tests/qtest/virtio-net-failover.c | 1 +
13 files changed, 33 insertions(+), 30 deletions(-)
diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py
index 10d99403a4..c3422ea1e4 100644
--- a/tests/avocado/replay_kernel.py
+++ b/tests/avocado/replay_kernel.py
@@ -166,7 +166,7 @@ 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 92855a02a5..87822074b6 100644
--- a/tests/avocado/reverse_debugging.py
+++ b/tests/avocado/reverse_debugging.py
@@ -230,7 +230,7 @@ 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 15fd87b2c1..f0d9d89c93 100644
--- a/tests/avocado/tcg_plugins.py
+++ b/tests/avocado/tcg_plugins.py
@@ -66,7 +66,7 @@ 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 +
@@ -96,7 +96,7 @@ 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 +
@@ -126,7 +126,7 @@ 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/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build
index fad340ad59..3c0d5241f6 100644
--- a/tests/qemu-iotests/meson.build
+++ b/tests/qemu-iotests/meson.build
@@ -51,21 +51,21 @@ foreach format, speed: qemu_iotests_formats
check: true,
)
- foreach item: rc.stdout().strip().split()
- args = [qemu_iotests_check_cmd,
- '-tap', '-' + format, item,
- '--source-dir', meson.current_source_dir(),
- '--build-dir', meson.current_build_dir()]
- # Some individual tests take as long as 45 seconds
- # Bump the timeout to 3 minutes for some headroom
- # on slow machines to minimize spurious failures
- test('io-' + format + '-' + item,
- python,
- args: args,
- depends: qemu_iotests_binaries,
- env: qemu_iotests_env,
- protocol: 'tap',
- timeout: 180,
- suite: suites)
- endforeach
+# foreach item: rc.stdout().strip().split()
+# args = [qemu_iotests_check_cmd,
+# '-tap', '-' + format, item,
+# '--source-dir', meson.current_source_dir(),
+# '--build-dir', meson.current_build_dir()]
+# # Some individual tests take as long as 45 seconds
+# # Bump the timeout to 3 minutes for some headroom
+# # on slow machines to minimize spurious failures
+# test('io-' + format + '-' + item,
+# python,
+# args: args,
+# depends: qemu_iotests_binaries,
+# env: qemu_iotests_env,
+# protocol: 'tap',
+# timeout: 180,
+# suite: suites)
+# endforeach
endforeach
diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py
index 588f30a4f1..3929a3634f 100644
--- a/tests/qemu-iotests/testenv.py
+++ b/tests/qemu-iotests/testenv.py
@@ -244,6 +244,9 @@ def __init__(self, source_dir: str, build_dir: str,
if self.qemu_prog.endswith(f'qemu-system-{suffix}'):
self.qemu_options += f' -machine {machine}'
+ if self.qemu_prog.endswith('qemu-system-x86_64'):
+ self.qemu_options += ' -cpu Nehalem'
+
# QEMU_DEFAULT_MACHINE
self.qemu_default_machine = get_default_machine(self.qemu_prog)
diff --git a/tests/qtest/fuzz-e1000e-test.c b/tests/qtest/fuzz-e1000e-test.c
index 5052883fb6..8242190170 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-rhel9.4.0");
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..9f1965b530 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-rhel9.4.0 -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 663bb6c485..2efc43e3f7 100644
--- a/tests/qtest/intel-hda-test.c
+++ b/tests/qtest/intel-hda-test.c
@@ -42,7 +42,7 @@ 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 "
AUDIODEV
"-device intel-hda,id=" HDA_ID CODEC_DEVICES);
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index 3aed6efcb8..119613237e 100644
--- a/tests/qtest/libqos/meson.build
+++ b/tests/qtest/libqos/meson.build
@@ -44,7 +44,7 @@ libqos_srcs = files(
'virtio-rng.c',
'virtio-scsi.c',
'virtio-serial.c',
- 'virtio-iommu.c',
+# 'virtio-iommu.c',
'virtio-gpio.c',
'virtio-scmi.c',
'generic-pcihost.c',
diff --git a/tests/qtest/lpc-ich9-test.c b/tests/qtest/lpc-ich9-test.c
index 8ac95b89f7..0e118b76eb 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-rhel9.4.0 "
"-nographic -monitor none -serial none");
qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index 36c5c13a7b..a2887d6057 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -101,7 +101,6 @@ qtests_i386 = \
'drive_del-test',
'tco-test',
'cpu-plug-test',
- 'q35-test',
'vmgenid-test',
'migration-test',
'test-x86-cpuid-compat',
diff --git a/tests/qtest/virtio-net-failover.c b/tests/qtest/virtio-net-failover.c
index 73dfabc272..a9dd304781 100644
--- a/tests/qtest/virtio-net-failover.c
+++ b/tests/qtest/virtio-net-failover.c
@@ -26,6 +26,7 @@
#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 "
--
2.39.3

37
0010-Increase-deletion-schedule-to-4-releases.patch Normal file
View File

@ -0,0 +1,37 @@
From 7c4955a929940701a7613fe3db516adbcc97576b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 18:45:58 +0100
Subject: Increase deletion schedule to 4 releases
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Until RHEL 10 pc machine type is introduced, we have to keep
7.6.0 machine types as a special exception to our normal rule of
deleting machine types after 2 releases due to being a default
machine type.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Rebase notes (9.1.0)
- New patch
---
include/hw/boards.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/hw/boards.h b/include/hw/boards.h
index da2fc92ce8..aca254ea18 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -642,7 +642,7 @@ struct MachineState {
* and ver_machine_deletion_version logic in docs/conf.py and
* the text in docs/about/deprecated.rst
*/
-#define MACHINE_VER_DELETION_MAJOR 2
+#define MACHINE_VER_DELETION_MAJOR 4
#define MACHINE_VER_DEPRECATION_MAJOR 1
/*
--
2.39.3

399
0011-Add-downstream-aarch64-versioned-virt-machine-types.patch Normal file
View File

@ -0,0 +1,399 @@
From 59b7559dfa658e325e8c1e23f13f48cf6952ac2e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 13:25:47 +0100
Subject: Add downstream aarch64 versioned 'virt' machine types
Adding changes to add RHEL machine types for aarch64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (9.1.0):
- Merge copy+pasted base machine definition back with upstream
base machine definition to reduce RHEL delta, as is done with
other targets
- Convert to new DEFINE_VIRT_MACHINE macros
- do not remove cpu validation (review comment)
- use ifdef instead of removal for disabling unwanted upstream code
Rebase notes (10.0.0)
- Removed unwanted sysbus dev
- Set no_nested_smmu
- Use upstream compat
Rebase notes (10.1.0):
- Use rebase compat
Merged patches (9.1.0):
- 043ad5ce97 Add upstream compatibility bits (partial)
Merged patches (10.0.0 rc0):
- 03502faf70 Add upstream compatibility bits
- 17c3bccf2f arm: ensure compatibility of virt-rhel9*
- 12e5b038be arm: create new virt machine type for rhel 9.6
- fb1bc2766e arm: create virt machine type for rhel10
- 727307e5ed hw/arm/virt: Fix Manufacturer and Product Name in emulated SMBIOS mode
- d93fcb3940 virtio-net: disable USO for all RHEL9 (partial)
- 0440f3d003 arm: disable pauth for virt-rhel9* in RHEL10
---
hw/arm/virt.c | 154 +++++++++++++++++++++++++++++++++++++-----
include/hw/arm/virt.h | 1 +
2 files changed, 137 insertions(+), 18 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e6e98fef1c..d37d1bb3cf 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -97,6 +97,32 @@ static GlobalProperty arm_virt_compat[] = {
};
static const size_t arm_virt_compat_len = G_N_ELEMENTS(arm_virt_compat);
+/*
+ * RHEL9 kernels have pauth disabled while RHEL10 has it enabled,
+ * since qemu will setup the VM with pauth when KVM supports it we
+ * have to disable it for virt-rhel9* to support upgrades / migration.
+ */
+GlobalProperty arm_rhel9_compat[] = {
+ {TYPE_ARM_CPU, "pauth", "off", .optional = true},
+};
+const size_t arm_rhel9_compat_len = G_N_ELEMENTS(arm_rhel9_compat);
+
+/*
+ * 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. They may be overriden by older machine compats.
+ *
+ * virtio-net-pci variant romfiles are not needed because edk2 does
+ * fully support the pxe boot. Besides virtio romfiles are not shipped
+ * on rhel/aarch64.
+ */
+GlobalProperty arm_rhel_compat[] = {
+ {"virtio-net-pci", "romfile", "" },
+ {"virtio-net-pci-transitional", "romfile", "" },
+ {"virtio-net-pci-non-transitional", "romfile", "" },
+};
+const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
+
/*
* This cannot be called from the virt_machine_class_init() because
* TYPE_VIRT_MACHINE is abstract and mc->compat_props g_ptr_array_new()
@@ -106,6 +132,8 @@ static void arm_virt_compat_set(MachineClass *mc)
{
compat_props_add(mc->compat_props, arm_virt_compat,
arm_virt_compat_len);
+ compat_props_add(mc->compat_props, arm_rhel_compat,
+ arm_rhel_compat_len);
}
#define DEFINE_VIRT_MACHINE_IMPL(latest, ...) \
@@ -116,10 +144,11 @@ static void arm_virt_compat_set(MachineClass *mc)
MachineClass *mc = MACHINE_CLASS(oc); \
arm_virt_compat_set(mc); \
MACHINE_VER_SYM(options, virt, __VA_ARGS__)(mc); \
- mc->desc = "QEMU " MACHINE_VER_STR(__VA_ARGS__) " ARM Virtual Machine"; \
+ mc->desc = "RHEL " MACHINE_VER_STR(__VA_ARGS__) " ARM Virtual Machine"; \
MACHINE_VER_DEPRECATION(__VA_ARGS__); \
if (latest) { \
mc->alias = "virt"; \
+ mc->is_default = 1; \
} \
} \
static const TypeInfo MACHINE_VER_SYM(info, virt, __VA_ARGS__) = \
@@ -135,10 +164,10 @@ static void arm_virt_compat_set(MachineClass *mc)
} \
type_init(MACHINE_VER_SYM(register, virt, __VA_ARGS__));
-#define DEFINE_VIRT_MACHINE_AS_LATEST(major, minor) \
- DEFINE_VIRT_MACHINE_IMPL(true, major, minor)
-#define DEFINE_VIRT_MACHINE(major, minor) \
- DEFINE_VIRT_MACHINE_IMPL(false, major, minor)
+#define DEFINE_VIRT_MACHINE_AS_LATEST(major, minor, micro) \
+ DEFINE_VIRT_MACHINE_IMPL(true, major, minor, micro)
+#define DEFINE_VIRT_MACHINE(major, minor, micro) \
+ DEFINE_VIRT_MACHINE_IMPL(false, major, minor, micro)
/* Number of external interrupt lines to configure the GIC with */
@@ -1746,16 +1775,26 @@ static void virt_build_smbios(VirtMachineState *vms)
{
MachineClass *mc = MACHINE_GET_CLASS(vms);
MachineState *ms = MACHINE(vms);
+ VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
uint8_t *smbios_tables, *smbios_anchor;
size_t smbios_tables_len, smbios_anchor_len;
struct smbios_phys_mem_area mem_array;
+ const char *manufacturer = "QEMU";
const char *product = "QEMU Virtual Machine";
+ const char *version = mc->name;
if (kvm_enabled()) {
product = "KVM Virtual Machine";
}
- smbios_set_defaults("QEMU", product, mc->name, NULL, NULL);
+ if (!vmc->manufacturer_product_compat) {
+ manufacturer = "Red Hat";
+ product = "KVM";
+ version = mc->desc;
+ }
+
+ smbios_set_defaults(manufacturer, product, version,
+ NULL, NULL);
/* build the array of physical mem area from base_memmap */
mem_array.address = vms->memmap[VIRT_MEM].base;
@@ -2517,6 +2556,7 @@ 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);
@@ -2544,6 +2584,7 @@ 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)
{
@@ -2559,6 +2600,7 @@ 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);
@@ -2572,6 +2614,7 @@ static void virt_set_compact_highmem(Object *obj, bool value, Error **errp)
vms->highmem_compact = value;
}
+#endif /* disabled for RHEL */
static bool virt_get_highmem_redists(Object *obj, Error **errp)
{
@@ -2664,6 +2707,7 @@ 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);
@@ -2677,6 +2721,7 @@ 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)
{
@@ -2760,6 +2805,7 @@ 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);
@@ -2773,6 +2819,7 @@ 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)
{
@@ -3213,16 +3260,16 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
NULL
};
+ mc->family = "virt-rhel-Z";
mc->init = machvirt_init;
- /* Start with max_cpus set to 512, which is the maximum supported by KVM.
- * The value may be reduced later when we have more information about the
- * configuration of the particular instance.
- */
- mc->max_cpus = 512;
+ /* Maximum supported VCPU count for all virt-rhel* machines */
+ mc->max_cpus = 384;
+#if 0 /* Disabled for Red Hat Enterprise Linux */
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_VFIO_CALXEDA_XGMAC);
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_VFIO_AMD_XGBE);
- machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE);
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_VFIO_PLATFORM);
+#endif
+ machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE);
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_UEFI_VARS_SYSBUS);
#ifdef CONFIG_TPM
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS);
@@ -3234,11 +3281,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
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;
-#ifdef CONFIG_TCG
- mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a15");
-#else
- mc->default_cpu_type = ARM_CPU_TYPE_NAME("max");
-#endif
+ mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a57");
mc->valid_cpu_types = valid_cpu_types;
mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
mc->kvm_type = virt_kvm_type;
@@ -3263,6 +3306,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
NULL, NULL);
object_class_property_set_description(oc, "acpi",
"Enable ACPI");
+#if 0 /* disabled for RHEL */
object_class_property_add_bool(oc, "secure", virt_get_secure,
virt_set_secure);
object_class_property_set_description(oc, "secure",
@@ -3275,6 +3319,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
"Set on/off to enable/disable emulating a "
"guest CPU which implements the ARM "
"Virtualization Extensions");
+#endif /* disabled for RHEL */
object_class_property_add_bool(oc, "highmem", virt_get_highmem,
virt_set_highmem);
@@ -3282,12 +3327,14 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
"Set on/off to enable/disable using "
"physical address space above 32 bits");
+#if 0 /* disabled for RHEL */
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");
+#endif /* disabled for RHEL */
object_class_property_add_bool(oc, "highmem-redists",
virt_get_highmem_redists,
@@ -3323,7 +3370,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
virt_set_gic_version);
object_class_property_set_description(oc, "gic-version",
"Set GIC version. "
- "Valid values are 2, 3, 4, host and max");
+ "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",
@@ -3343,11 +3390,13 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
"Set on/off to enable/disable reporting host memory errors "
"to a KVM guest using ACPI and guest external abort exceptions");
+#if 0 /* disabled for RHEL */
object_class_property_add_bool(oc, "mte", virt_get_mte, virt_set_mte);
object_class_property_set_description(oc, "mte",
"Set on/off to enable/disable emulating a "
"guest CPU which implements the ARM "
"Memory Tagging Extension");
+#endif /* disabled for RHEL */
object_class_property_add_bool(oc, "its", virt_get_its,
virt_set_its);
@@ -3355,6 +3404,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
"Set on/off to enable/disable "
"ITS instantiation");
+#if 0 /* disabled for RHEL */
object_class_property_add_bool(oc, "dtb-randomness",
virt_get_dtb_randomness,
virt_set_dtb_randomness);
@@ -3367,6 +3417,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
virt_set_dtb_randomness);
object_class_property_set_description(oc, "dtb-kaslr-seed",
"Deprecated synonym of dtb-randomness");
+#endif /* disabled for RHEL */
object_class_property_add_str(oc, "x-oem-id",
virt_get_oem_id,
@@ -3636,3 +3687,70 @@ static void virt_machine_4_1_options(MachineClass *mc)
}
DEFINE_VIRT_MACHINE(4, 1)
#endif /* disabled for RHEL */
+
+static void virt_rhel_machine_10_0_0_options(MachineClass *mc)
+{
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
+ /* QEMU 9.1 and earlier have only a stage-1 SMMU, not a nested s1+2 one */
+ vmc->no_nested_smmu = true;
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_2, hw_compat_rhel_10_2_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_1, hw_compat_rhel_10_1_len);
+}
+DEFINE_VIRT_MACHINE_AS_LATEST(10, 0, 0)
+
+static void virt_rhel_machine_9_6_0_options(MachineClass *mc)
+{
+ virt_rhel_machine_10_0_0_options(mc);
+
+ compat_props_add(mc->compat_props, arm_rhel9_compat, arm_rhel9_compat_len);
+ /* NB: remember to move this line to the *latest* RHEL 9 machine */
+ compat_props_add(mc->compat_props, hw_compat_rhel_9, hw_compat_rhel_9_len);
+}
+DEFINE_VIRT_MACHINE(9, 6, 0)
+
+static void virt_rhel_machine_9_4_0_options(MachineClass *mc)
+{
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
+ virt_rhel_machine_9_6_0_options(mc);
+
+ /* From virt_machine_9_0_options() */
+ mc->smbios_memory_device_size = 16 * GiB;
+
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_0, hw_compat_rhel_10_0_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5, hw_compat_rhel_9_5_len);
+
+ vmc->manufacturer_product_compat = true;
+}
+DEFINE_VIRT_MACHINE(9, 4, 0)
+
+static void virt_rhel_machine_9_2_0_options(MachineClass *mc)
+{
+ virt_rhel_machine_9_4_0_options(mc);
+
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
+
+ /* RHEL 9.4 is the first supported release */
+ mc->deprecation_reason =
+ "machine types for versions prior to 9.4 are deprecated";
+}
+DEFINE_VIRT_MACHINE(9, 2, 0)
+
+static void virt_rhel_machine_9_0_0_options(MachineClass *mc)
+{
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
+ virt_rhel_machine_9_2_0_options(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);
+
+ /* 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_VIRT_MACHINE(9, 0, 0)
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 365a28b082..94c79d6c6d 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -132,6 +132,7 @@ struct VirtMachineClass {
bool no_tcg_lpa2;
bool no_ns_el2_virt_timer_irq;
bool no_nested_smmu;
+ bool manufacturer_product_compat;
};
struct VirtMachineState {
--
2.39.3

262
0012-Add-downstream-s390x-versioned-s390-ccw-virtio-machi.patch Normal file
View File

@ -0,0 +1,262 @@
From 0976e78ca34a38fbc21c71c2f05e884c0264b62e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 13:44:36 +0100
Subject: Add downstream s390x versioned 's390-ccw-virtio' machine types
Adding changes to add RHEL machine types for s390x architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
--
Rebase notes(9.1.0):
- Convert to new DEFINE_CCW_MACHINE macros
Rebase notes (10.0.0):
- Use upstream compat
- Disabled relaxed-translation for older types
Rebase notes (10.1.0):
- Use rebase compat
Merged patches (9.1.0):
- 043ad5ce97 Add upstream compatibility bits (partial)
- 04596b496e s390x: remove deprecated rhel machine types
Merged patches (10.0.0 rc0):
- 03502faf70 Add upstream compatibility bits (partial)
- d27437e5ba redhat: Add QEMU 9.1 compat handling to the s390x machine types
- 926a9d0ca2 redhat: Add rhel9.6.0 and rhel10.0.0 machine types
- d93fcb3940 virtio-net: disable USO for all RHEL9 (partial)
---
hw/s390x/s390-virtio-ccw.c | 106 +++++++++++++++++++++++++++++--
target/s390x/cpu_models.c | 11 ++++
target/s390x/cpu_models.h | 2 +
target/s390x/cpu_models_system.c | 2 +
4 files changed, 116 insertions(+), 5 deletions(-)
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 2fca2bcf4d..9be423858d 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -716,6 +716,7 @@ static void s390_nmi(NMIState *n, int cpu_index, Error **errp)
s390_cpu_restart(S390_CPU(cs));
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static ram_addr_t s390_fixup_ram_size(ram_addr_t sz)
{
/* same logic as in sclp.c */
@@ -735,6 +736,7 @@ static ram_addr_t s390_fixup_ram_size(ram_addr_t sz)
}
return newsz;
}
+#endif /* disabled for RHEL */
static inline bool machine_get_aes_key_wrap(Object *obj, Error **errp)
{
@@ -883,7 +885,7 @@ static const TypeInfo ccw_machine_info = {
{ \
MachineClass *mc = MACHINE_CLASS(oc); \
MACHINE_VER_SYM(class_options, ccw, __VA_ARGS__)(mc); \
- mc->desc = "Virtual s390x machine (version " MACHINE_VER_STR(__VA_ARGS__) ")"; \
+ mc->desc = "Virtual s390x machine (version rhel" MACHINE_VER_STR(__VA_ARGS__) ")"; \
mc->init = MACHINE_VER_SYM(mach_init, ccw, __VA_ARGS__); \
MACHINE_VER_DEPRECATION(__VA_ARGS__); \
if (latest) { \
@@ -904,11 +906,11 @@ static const TypeInfo ccw_machine_info = {
} \
type_init(MACHINE_VER_SYM(register, ccw, __VA_ARGS__))
-#define DEFINE_CCW_MACHINE_AS_LATEST(major, minor) \
- DEFINE_CCW_MACHINE_IMPL(true, major, minor)
+#define DEFINE_CCW_MACHINE_AS_LATEST(major, minor, micro) \
+ DEFINE_CCW_MACHINE_IMPL(true, major, minor, micro)
-#define DEFINE_CCW_MACHINE(major, minor) \
- DEFINE_CCW_MACHINE_IMPL(false, major, minor)
+#define DEFINE_CCW_MACHINE(major, minor, micro) \
+ DEFINE_CCW_MACHINE_IMPL(false, major, minor, micro)
#if 0 /* Disabled for Red Hat Enterprise Linux */
@@ -1170,6 +1172,100 @@ DEFINE_CCW_MACHINE(4, 2);
#endif /* disabled for RHEL */
+static void ccw_rhel_machine_10_0_0_instance_options(MachineState *machine)
+{
+}
+
+static void ccw_rhel_machine_10_0_0_class_options(MachineClass *mc)
+{
+ S390CcwMachineClass *s390mc = S390_CCW_MACHINE_CLASS(mc);
+ static GlobalProperty compat[] = {
+ { TYPE_S390_PCI_DEVICE, "relaxed-translation", "off", },
+ };
+
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_2, hw_compat_rhel_10_2_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_1, hw_compat_rhel_10_1_len);
+ s390mc->use_cpi = false;
+}
+DEFINE_CCW_MACHINE_AS_LATEST(10, 0, 0);
+
+static void ccw_rhel_machine_9_6_0_instance_options(MachineState *machine)
+{
+ ccw_rhel_machine_10_0_0_instance_options(machine);
+}
+
+static void ccw_rhel_machine_9_6_0_class_options(MachineClass *mc)
+{
+ ccw_rhel_machine_10_0_0_class_options(mc);
+
+ /* NB: remember to move this line to the *latest* RHEL 9 machine */
+ compat_props_add(mc->compat_props, hw_compat_rhel_9, hw_compat_rhel_9_len);
+}
+DEFINE_CCW_MACHINE(9, 6, 0);
+
+static void ccw_rhel_machine_9_4_0_instance_options(MachineState *machine)
+{
+ ccw_rhel_machine_9_6_0_instance_options(machine);
+}
+
+static void ccw_rhel_machine_9_4_0_class_options(MachineClass *mc)
+{
+ static GlobalProperty compat[] = {
+ { TYPE_QEMU_S390_FLIC, "migrate-all-state", "off", },
+ };
+
+ ccw_rhel_machine_9_6_0_class_options(mc);
+
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_0, hw_compat_rhel_10_0_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5, hw_compat_rhel_9_5_len);
+ compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat));
+}
+DEFINE_CCW_MACHINE(9, 4, 0);
+
+static void ccw_rhel_machine_9_2_0_instance_options(MachineState *machine)
+{
+ ccw_rhel_machine_9_4_0_instance_options(machine);
+}
+
+static void ccw_rhel_machine_9_2_0_class_options(MachineClass *mc)
+{
+ ccw_rhel_machine_9_4_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_4, hw_compat_rhel_9_4_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_3, hw_compat_rhel_9_3_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_2, hw_compat_rhel_9_2_len);
+ mc->smp_props.drawers_supported = false; /* from ccw_machine_8_1 */
+ mc->smp_props.books_supported = false; /* from ccw_machine_8_1 */
+}
+DEFINE_CCW_MACHINE(9, 2, 0);
+
+static void ccw_rhel_machine_9_0_0_instance_options(MachineState *machine)
+{
+ static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_2 };
+
+ ccw_rhel_machine_9_2_0_instance_options(machine);
+
+ s390_set_qemu_cpu_model(0x3906, 14, 2, qemu_cpu_feat);
+ s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAIE);
+}
+
+static void ccw_rhel_machine_9_0_0_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", },
+ };
+
+ ccw_rhel_machine_9_2_0_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(9, 0, 0);
+
static void ccw_machine_register_types(void)
{
type_register_static(&ccw_machine_info);
diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c
index fe29f5c5b7..2a7fc949a4 100644
--- a/target/s390x/cpu_models.c
+++ b/target/s390x/cpu_models.c
@@ -47,6 +47,9 @@
* 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[] = {
/*
* Linux requires at least z10 nowadays, and IBM only supports recent CPUs
@@ -931,22 +934,30 @@ static void s390_host_cpu_model_class_init(ObjectClass *oc, const void *data)
static void s390_base_cpu_model_class_init(ObjectClass *oc, const 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, const 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, const void *data)
diff --git a/target/s390x/cpu_models.h b/target/s390x/cpu_models.h
index f701bc0b53..670a567c67 100644
--- a/target/s390x/cpu_models.h
+++ b/target/s390x/cpu_models.h
@@ -38,6 +38,8 @@ typedef 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;
} S390CPUDef;
/* CPU model based on a CPU definition */
diff --git a/target/s390x/cpu_models_system.c b/target/s390x/cpu_models_system.c
index 5b84604867..d715bdc870 100644
--- a/target/s390x/cpu_models_system.c
+++ b/target/s390x/cpu_models_system.c
@@ -56,6 +56,7 @@ 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;
@@ -65,6 +66,7 @@ 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;
--
2.39.3

517
0013-Add-downstream-x86_64-versioned-pc-q35-machine-types.patch Normal file
View File

@ -0,0 +1,517 @@
From f7424ca0a529f1f3a76a4044b535d1ecd7b5b114 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 13:44:41 +0100
Subject: Add downstream x86_64 versioned 'pc' & 'q35' machine types
Adding changes to add RHEL machine types for x86_64 architecture.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (9.1.0):
- Merged pc_q35_machine_rhel_options back into
pc_q35_machine_options to reduce delta to upstream
- Convert to new DEFINE_(I440FX|Q35)_MACHINE macros
- Moved x86 cpu deprecation note to device disable patch
Rebase notes (10.0.0 rc0):
- Do not use bugfix macro for q35
- Use upstream compat
- Add downstream specific compat
- Fixing rhel-9.4 compat issue
Rebase notes (10.1.0):
- Use rebase compat
Merged patches (9.1.0):
- 043ad5ce97 Add upstream compatibility bits (partial)
Merged patches (10.0.0 rc0):
- 03502faf70 Add upstream compatibility bits
- 6be70c681b x86: ensure compatibility of pc-q35-rhel9*
- d6b6ae511c x86: create new pc-q35 machine type for rhel 9.6
- fcf4da60bd x86: create pc-i440fx machine type for rhel10
- 4acb295fa2 x86: create pc-q35 machine type for rhel10
- 0489497df8 x86: remove deprecated rhel machine types
- f53dbf7532 remove stale compat definitions (partial)
- 379e14ba88 pc: q35: Bump max_cpus to 4096 vcpus
- d93fcb3940 virtio-net: disable USO for all RHEL9 (partial)
---
hw/i386/fw_cfg.c | 2 +-
hw/i386/pc.c | 70 ++++++++++++++++++++-
hw/i386/pc_piix.c | 55 +++++++++++++++--
hw/i386/pc_q35.c | 123 ++++++++++++++++++++++++++++++++++---
include/hw/boards.h | 2 +
include/hw/i386/pc.h | 21 +++++++
target/i386/kvm/kvm-cpu.c | 1 +
target/i386/kvm/kvm.c | 4 ++
tests/qtest/meson.build | 2 +-
tests/qtest/pvpanic-test.c | 5 +-
10 files changed, 267 insertions(+), 18 deletions(-)
diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c
index 07df7281d2..8009f5f31f 100644
--- a/hw/i386/fw_cfg.c
+++ b/hw/i386/fw_cfg.c
@@ -75,7 +75,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
if (pcmc->smbios_defaults) {
/* These values are guest ABI, do not change */
- smbios_set_defaults("QEMU", mc->desc, mc->name,
+ smbios_set_defaults("Red Hat", "KVM", mc->desc,
pcmc->smbios_stream_product, pcmc->smbios_stream_version);
}
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 2f58e73d33..439abe8f46 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -273,6 +273,72 @@ const size_t pc_compat_2_6_len = G_N_ELEMENTS(pc_compat_2_6);
*/
#define PC_FW_DATA (0x20000 + 0x8000)
+/* 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_10_2_compat[] = {
+ /* pc_rhel_10_2_compat from pc_compat_10_0 */
+ { TYPE_X86_CPU, "x-consistent-cache", "false" },
+ { TYPE_X86_CPU, "x-vendor-cpuid-only-v2", "false" },
+};
+const size_t pc_rhel_10_2_compat_len = G_N_ELEMENTS(pc_compat_10_0);
+
+GlobalProperty pc_rhel_10_1_compat[] = {
+ /* pc_rhel_10_1_compat from pc_compat_9_1 */
+ { "ICH9-LPC", "x-smi-swsmi-timer", "off" },
+ { "ICH9-LPC", "x-smi-periodic-timer", "off" },
+ { TYPE_INTEL_IOMMU_DEVICE, "stale-tm", "on" },
+ { TYPE_INTEL_IOMMU_DEVICE, "aw-bits", "39" },
+};
+const size_t pc_rhel_10_1_compat_len = G_N_ELEMENTS(pc_rhel_10_1_compat);
+
+GlobalProperty pc_rhel_10_0_compat[] = {
+ /* pc_rhel_10_0_compat from pc_compat_9_0 */
+ { TYPE_X86_CPU, "x-amd-topoext-features-only", "false" },
+ { TYPE_X86_CPU, "x-l1-cache-per-thread", "false" },
+ { TYPE_X86_CPU, "guest-phys-bits", "0" },
+ { "sev-guest", "legacy-vm-type", "on" },
+ { TYPE_X86_CPU, "legacy-multi-node", "on" },
+};
+const size_t pc_rhel_10_0_compat_len = G_N_ELEMENTS(pc_rhel_10_0_compat);
+
+GlobalProperty pc_rhel_9_3_compat[] = {
+ /* pc_rhel_9_3_compat from pc_compat_8_0 */
+ { "virtio-mem", "unplugged-inaccessible", "auto" },
+};
+const size_t pc_rhel_9_3_compat_len = G_N_ELEMENTS(pc_rhel_9_3_compat);
+
+GlobalProperty pc_rhel_9_2_compat[] = {
+ /* pc_rhel_9_2_compat from pc_compat_7_2 */
+ { "ICH9-LPC", "noreboot", "true" },
+};
+const size_t pc_rhel_9_2_compat_len = G_N_ELEMENTS(pc_rhel_9_2_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);
+
GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled)
{
GSIState *s;
@@ -1754,6 +1820,7 @@ static void pc_machine_class_init(ObjectClass *oc, const void *data)
pcmc->kvmclock_create_always = true;
x86mc->apic_xrupt_override = 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->auto_enable_numa_with_memhp = true;
@@ -1761,7 +1828,8 @@ static void pc_machine_class_init(ObjectClass *oc, const 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 acf010e20f..d546c4a8a9 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 "system/xen.h"
+#include "migration/migration.h"
#ifdef CONFIG_XEN
#include <xen/hvm/hvm_info_table.h>
#include "hw/xen/xen_pt.h"
@@ -469,11 +470,11 @@ static void pc_i440fx_init(MachineState *machine)
pc_init1(machine, TYPE_I440FX_PCI_DEVICE);
}
-#define DEFINE_I440FX_MACHINE(major, minor) \
- DEFINE_PC_VER_MACHINE(pc_i440fx, "pc-i440fx", pc_i440fx_init, false, NULL, major, minor);
+#define DEFINE_I440FX_MACHINE(major, minor, micro) \
+ DEFINE_PC_VER_MACHINE(pc_i440fx, "pc-i440fx", pc_i440fx_init, false, NULL, major, minor, micro);
-#define DEFINE_I440FX_MACHINE_AS_LATEST(major, minor) \
- DEFINE_PC_VER_MACHINE(pc_i440fx, "pc-i440fx", pc_i440fx_init, true, "pc", major, minor);
+#define DEFINE_I440FX_MACHINE_AS_LATEST(major, minor, micro) \
+ DEFINE_PC_VER_MACHINE(pc_i440fx, "pc-i440fx", pc_i440fx_init, true, "pc", major, minor, micro);
#if 0 /* Disabled for Red Hat Enterprise Linux */
static void pc_i440fx_machine_options(MachineClass *m)
@@ -853,3 +854,49 @@ static void xenfv_machine_3_1_options(MachineClass *m)
DEFINE_PC_MACHINE(xenfv, "xenfv-3.1", pc_xen_hvm_init,
xenfv_machine_3_1_options);
#endif
+
+/* Red Hat Enterprise Linux machine types */
+
+static void pc_machine_rhel10_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ ObjectClass *oc = OBJECT_CLASS(m);
+ pcmc->default_south_bridge = TYPE_PIIX3_DEVICE;
+ pcmc->pci_root_uid = 0;
+ pcmc->default_cpu_version = 1;
+
+ m->family = "pc_piix_Y";
+ m->default_machine_opts = "firmware=bios-256k.bin";
+ m->default_display = "std";
+ m->default_nic = "e1000";
+ m->no_parallel = 1;
+ m->no_floppy = 1;
+ machine_class_allow_dynamic_sysbus_dev(m, TYPE_RAMFB_DEVICE);
+
+ object_class_property_add_enum(oc, "x-south-bridge", "PCSouthBridgeOption",
+ &PCSouthBridgeOption_lookup,
+ pc_get_south_bridge,
+ pc_set_south_bridge);
+ object_class_property_set_description(oc, "x-south-bridge",
+ "Use a different south bridge than PIIX3");
+ compat_props_add(m->compat_props,
+ pc_piix_compat_defaults, pc_piix_compat_defaults_len);
+}
+
+static void pc_i440fx_rhel_machine_10_0_0_options(MachineClass *m)
+{
+ pc_machine_rhel10_options(m);
+
+ m->desc = "RHEL 10.0.0 PC (i440FX + PIIX, 1996)";
+ m->deprecation_reason = rhel_old_machine_deprecation;
+
+ compat_props_add(m->compat_props, hw_compat_rhel_10_2,
+ hw_compat_rhel_10_2_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_10_1,
+ hw_compat_rhel_10_1_len);
+ compat_props_add(m->compat_props, pc_rhel_10_2_compat,
+ pc_rhel_10_2_compat_len);
+ compat_props_add(m->compat_props, pc_rhel_10_1_compat,
+ pc_rhel_10_1_compat_len);
+}
+DEFINE_I440FX_MACHINE_AS_LATEST(10, 0, 0);
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 2203ffd67e..e5d10c0335 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -340,11 +340,11 @@ static void pc_q35_init(MachineState *machine)
#endif
}
-#define DEFINE_Q35_MACHINE(major, minor) \
- DEFINE_PC_VER_MACHINE(pc_q35, "pc-q35", pc_q35_init, false, NULL, major, minor);
+#define DEFINE_Q35_MACHINE(major, minor, micro) \
+ DEFINE_PC_VER_MACHINE(pc_q35, "pc-q35", pc_q35_init, false, NULL, major, minor, micro);
-#define DEFINE_Q35_MACHINE_AS_LATEST(major, minor) \
- DEFINE_PC_VER_MACHINE(pc_q35, "pc-q35", pc_q35_init, false, "q35", major, minor);
+#define DEFINE_Q35_MACHINE_AS_LATEST(major, minor, micro) \
+ DEFINE_PC_VER_MACHINE(pc_q35, "pc-q35", pc_q35_init, false, "q35", major, minor, micro);
#define DEFINE_Q35_MACHINE_BUGFIX(major, minor, micro) \
DEFINE_PC_VER_MACHINE(pc_q35, "pc-q35", pc_q35_init, false, NULL, major, minor, micro);
@@ -355,21 +355,21 @@ static void pc_q35_machine_options(MachineClass *m)
pcmc->pci_root_uid = 0;
pcmc->default_cpu_version = 1;
- m->family = "pc_q35";
- m->desc = "Standard PC (Q35 + ICH9, 2009)";
+ m->family = "pc_q35_Z";
m->units_per_default_bus = 1;
- m->default_machine_opts = "firmware=bios-256k.bin";
+ m->default_machine_opts = "firmware=bios-256k.bin,hpet=off";
m->default_display = "std";
m->default_nic = "e1000e";
- m->default_kernel_irqchip_split = false;
m->no_floppy = 1;
m->max_cpus = 4096;
- m->no_parallel = !module_object_class_by_name(TYPE_ISA_PARALLEL);
+ m->no_parallel = 1;
+ m->alias = "q35";
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);
machine_class_allow_dynamic_sysbus_dev(m, TYPE_VMBUS_BRIDGE);
machine_class_allow_dynamic_sysbus_dev(m, TYPE_UEFI_VARS_X64);
+ compat_props_add(m->compat_props, pc_rhel_compat, pc_rhel_compat_len);
compat_props_add(m->compat_props,
pc_q35_compat_defaults, pc_q35_compat_defaults_len);
}
@@ -687,3 +687,108 @@ static void pc_q35_machine_2_6_options(MachineClass *m)
DEFINE_Q35_MACHINE(2, 6);
#endif /* Disabled for Red Hat Enterprise Linux */
+
+/* Red Hat Enterprise Linux machine types */
+
+static void pc_q35_rhel_machine_10_0_0_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_machine_options(m);
+ m->desc = "RHEL-10.0.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "10.0.0";
+
+ compat_props_add(m->compat_props, hw_compat_rhel_10_2,
+ hw_compat_rhel_10_2_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_10_1,
+ hw_compat_rhel_10_1_len);
+ compat_props_add(m->compat_props, pc_rhel_10_2_compat,
+ pc_rhel_10_2_compat_len);
+ compat_props_add(m->compat_props, pc_rhel_10_1_compat,
+ pc_rhel_10_1_compat_len);
+}
+DEFINE_Q35_MACHINE_AS_LATEST(10, 0, 0);
+
+static void pc_q35_rhel_machine_9_6_0_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_rhel_machine_10_0_0_options(m);
+ m->desc = "RHEL-9.6.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.6.0";
+
+ /* NB: remember to move this line to the *latest* RHEL 9 machine */
+ compat_props_add(m->compat_props, hw_compat_rhel_9, hw_compat_rhel_9_len);
+}
+
+DEFINE_Q35_MACHINE(9, 6, 0);
+
+static void pc_q35_rhel_machine_9_4_0_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_rhel_machine_9_6_0_options(m);
+
+ /* older RHEL machines continue to support 710 vcpus */
+ m->max_cpus = 710;
+ m->desc = "RHEL-9.4.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.4.0";
+
+ /* From pc_q35_machine_9_0_options() */
+ pcmc->isa_bios_alias = false;
+ m->smbios_memory_device_size = 16 * GiB;
+
+ compat_props_add(m->compat_props, hw_compat_rhel_10_0,
+ hw_compat_rhel_10_0_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
+ compat_props_add(m->compat_props, pc_rhel_10_0_compat,
+ pc_rhel_10_0_compat_len);
+}
+
+DEFINE_Q35_MACHINE(9, 4, 0);
+
+static void pc_q35_rhel_machine_9_2_0_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_rhel_machine_9_4_0_options(m);
+ m->desc = "RHEL-9.2.0 PC (Q35 + ICH9, 2009)";
+ pcmc->smbios_stream_product = "RHEL";
+ pcmc->smbios_stream_version = "9.2.0";
+
+ /* From pc_q35_8_0_machine_options() */
+ pcmc->default_smbios_ep_type = SMBIOS_ENTRY_POINT_TYPE_32;
+ /* From pc_q35_8_1_machine_options() */
+ pcmc->broken_32bit_mem_addr_check = true;
+
+ compat_props_add(m->compat_props, hw_compat_rhel_9_4,
+ hw_compat_rhel_9_4_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_3,
+ hw_compat_rhel_9_3_len);
+ compat_props_add(m->compat_props, pc_rhel_9_3_compat,
+ pc_rhel_9_3_compat_len);
+ compat_props_add(m->compat_props, hw_compat_rhel_9_2,
+ hw_compat_rhel_9_2_len);
+ compat_props_add(m->compat_props, pc_rhel_9_2_compat,
+ pc_rhel_9_2_compat_len);
+}
+
+DEFINE_Q35_MACHINE(9, 2, 0);
+
+static void pc_q35_rhel_machine_9_0_0_options(MachineClass *m)
+{
+ PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+ pc_q35_rhel_machine_9_2_0_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->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,
+ hw_compat_rhel_9_0_len);
+ compat_props_add(m->compat_props, pc_rhel_9_0_compat,
+ pc_rhel_9_0_compat_len);
+}
+
+DEFINE_Q35_MACHINE(9, 0, 0);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index aca254ea18..22c3abd51e 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -308,6 +308,8 @@ 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 3b4ea24c20..633df2fcf8 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -301,6 +301,27 @@ extern const size_t pc_compat_2_7_len;
extern GlobalProperty pc_compat_2_6[];
extern const size_t pc_compat_2_6_len;
+extern GlobalProperty pc_rhel_compat[];
+extern const size_t pc_rhel_compat_len;
+
+extern GlobalProperty pc_rhel_10_2_compat[];
+extern const size_t pc_rhel_10_2_compat_len;
+
+extern GlobalProperty pc_rhel_10_1_compat[];
+extern const size_t pc_rhel_10_1_compat_len;
+
+extern GlobalProperty pc_rhel_10_0_compat[];
+extern const size_t pc_rhel_10_0_compat_len;
+
+extern GlobalProperty pc_rhel_9_3_compat[];
+extern const size_t pc_rhel_9_3_compat_len;
+
+extern GlobalProperty pc_rhel_9_2_compat[];
+extern const size_t pc_rhel_9_2_compat_len;
+
+extern GlobalProperty pc_rhel_9_0_compat[];
+extern const size_t pc_rhel_9_0_compat_len;
+
#define DEFINE_PC_MACHINE(suffix, namestr, initfn, optsfn) \
static void pc_machine_##suffix##_class_init(ObjectClass *oc, \
const void *data) \
diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c
index 89a7953659..74c0b036e3 100644
--- a/target/i386/kvm/kvm-cpu.c
+++ b/target/i386/kvm/kvm-cpu.c
@@ -175,6 +175,7 @@ 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 369626f8c8..0eb39d22d6 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -4389,6 +4389,7 @@ 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);
@@ -4786,6 +4787,9 @@ 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/meson.build b/tests/qtest/meson.build
index 669d07c06b..b96aa06084 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -49,6 +49,7 @@ qtests_filter = \
(get_option('default_devices') and host_os != 'windows' ? ['test-filter-mirror'] : []) + \
(get_option('default_devices') and host_os != 'windows' ? ['test-filter-redirector'] : [])
+# RHEL: Removed intel-iommu-test as it's not working with 10.0 machine type
qtests_i386 = \
(slirp.found() ? ['pxe-test'] : []) + \
qtests_filter + \
@@ -94,7 +95,6 @@ qtests_i386 = \
(config_all_devices.has_key('CONFIG_SB16') ? ['fuzz-sb16-test'] : []) + \
(config_all_devices.has_key('CONFIG_SDHCI_PCI') ? ['fuzz-sdcard-test'] : []) + \
(config_all_devices.has_key('CONFIG_ESP_PCI') ? ['am53c974-test'] : []) + \
- (config_all_devices.has_key('CONFIG_VTD') ? ['intel-iommu-test'] : []) + \
(host_os != 'windows' and \
config_all_devices.has_key('CONFIG_ACPI_ERST') ? ['erst-test'] : []) + \
(config_all_devices.has_key('CONFIG_PCIE_PORT') and \
diff --git a/tests/qtest/pvpanic-test.c b/tests/qtest/pvpanic-test.c
index 5606baf47b..094c56b0cd 100644
--- a/tests/qtest/pvpanic-test.c
+++ b/tests/qtest/pvpanic-test.c
@@ -18,7 +18,7 @@ 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, ==, PVPANIC_EVENTS);
@@ -41,7 +41,8 @@ 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, ==, PVPANIC_EVENTS);
--
2.39.3

58
0014-Disable-virtio-net-pci-romfile-loading-on-riscv64.patch Normal file
View File

@ -0,0 +1,58 @@
From 7bc17dffbc537e8546249c7c2d19e426ad50e61f Mon Sep 17 00:00:00 2001
From: Andrea Bolognani <abologna@redhat.com>
Date: Tue, 10 Jun 2025 14:27:29 +0200
Subject: Disable virtio-net-pci romfile loading on riscv64
RH-Author: Andrea Bolognani <None>
RH-MergeRequest: 373: Various small fixes
RH-Jira: RHEL-96057
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/4] b490ef3c3ab6a47f90c67016f685e19a65d97100 (abologna/centos-stream-qemu-kvm)
Same motivation for disabling it as on aarch64.
Signed-off-by: Andrea Bolognani <abologna@redhat.com>
Patch-name: kvm-Disable-virtio-net-pci-romfile-loading-on-riscv64.patch
Patch-id: 51
Patch-present-in-specfile: True
---
hw/riscv/virt.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index ab5a9ec613..3b187d6c98 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -59,6 +59,18 @@
#include "hw/virtio/virtio-iommu.h"
#include "hw/uefi/var-service-api.h"
+/*
+ * virtio-net-pci variant romfiles are not needed because edk2 does
+ * fully support the pxe boot. Besides virtio romfiles are not shipped
+ * on rhel/riscv64.
+ */
+static GlobalProperty riscv_virt_compat[] = {
+ {"virtio-net-pci", "romfile", "" },
+ {"virtio-net-pci-transitional", "romfile", "" },
+ {"virtio-net-pci-non-transitional", "romfile", "" },
+};
+const size_t riscv_virt_compat_len = G_N_ELEMENTS(riscv_virt_compat);
+
/* KVM AIA only supports APLIC MSI. APLIC Wired is always emulated by QEMU. */
static bool virt_use_kvm_aia_aplic_imsic(RISCVVirtAIAType aia_type)
{
@@ -1978,6 +1990,9 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
NULL, NULL);
object_class_property_set_description(oc, "iommu-sys",
"Enable IOMMU platform device");
+
+ compat_props_add(mc->compat_props, riscv_virt_compat,
+ riscv_virt_compat_len);
}
static const TypeInfo virt_machine_typeinfo = {
--
2.39.3

145
0015-Add-upstream-compatibility-bits.patch
View File

@ -1,145 +0,0 @@
From 043ad5ce9789dbbfe1a888de58f6039ea7ae47a4 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 20 Mar 2024 05:34:32 -0400
Subject: Add upstream compatibility bits
Adding new compats structure for changes introduced during rebase to QEMU 9.0.0.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
Rebase notes (9.0.0 rc2):
- Add aw-bits setting for aarch compat record (overwritten for 9.4 and older)
---
hw/arm/virt.c | 6 ++++--
hw/core/machine.c | 10 ++++++++++
hw/i386/pc_piix.c | 3 ++-
hw/i386/pc_q35.c | 3 +++
hw/s390x/s390-virtio-ccw.c | 1 +
include/hw/boards.h | 3 +++
6 files changed, 23 insertions(+), 3 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 22bc345137..3f0496cdb9 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -85,6 +85,7 @@
#include "hw/char/pl011.h"
#include "qemu/guest-random.h"
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static GlobalProperty arm_virt_compat[] = {
{ TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "48" },
};
@@ -101,7 +102,6 @@ static void arm_virt_compat_set(MachineClass *mc)
arm_virt_compat_len);
}
-#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) \
@@ -144,6 +144,8 @@ GlobalProperty arm_rhel_compat[] = {
{"virtio-net-pci", "romfile", "" },
{"virtio-net-pci-transitional", "romfile", "" },
{"virtio-net-pci-non-transitional", "romfile", "" },
+ /* arm_rhel_compat from arm_virt_compat, added for 9.0.0 rebase */
+ { TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "48" },
};
const size_t arm_rhel_compat_len = G_N_ELEMENTS(arm_rhel_compat);
@@ -3534,7 +3536,6 @@ static void rhel_machine_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
- arm_virt_compat_set(mc);
mc->family = "virt-rhel-Z";
mc->init = machvirt_init;
@@ -3728,6 +3729,7 @@ type_init(rhel_machine_init);
static void rhel940_virt_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5, hw_compat_rhel_9_5_len);
}
DEFINE_RHEL_MACHINE_AS_LATEST(9, 4, 0)
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 695cb89a46..0f256d9633 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -302,6 +302,16 @@ const size_t hw_compat_2_1_len = G_N_ELEMENTS(hw_compat_2_1);
const char *rhel_old_machine_deprecation =
"machine types for previous major releases are deprecated";
+GlobalProperty hw_compat_rhel_9_5[] = {
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { "migration", "zero-page-detection", "legacy"},
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { TYPE_VIRTIO_IOMMU_PCI, "granule", "4k" },
+ /* hw_compat_rhel_9_5 from hw_compat_8_2 */
+ { TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "64" },
+};
+const size_t hw_compat_rhel_9_5_len = G_N_ELEMENTS(hw_compat_rhel_9_5);
+
GlobalProperty hw_compat_rhel_9_4[] = {
/* hw_compat_rhel_9_4 from hw_compat_8_0 */
{ TYPE_VIRTIO_NET, "host_uso", "off"},
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index a647262d63..6b260682eb 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -1015,7 +1015,8 @@ static void pc_machine_rhel760_options(MachineClass *m)
object_class_property_set_description(oc, "x-south-bridge",
"Use a different south bridge than PIIX3");
-
+ compat_props_add(m->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_4,
hw_compat_rhel_9_4_len);
compat_props_add(m->compat_props, hw_compat_rhel_9_3,
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index e872dc7e46..2b54944c0f 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -733,6 +733,9 @@ static void pc_q35_machine_rhel940_options(MachineClass *m)
m->desc = "RHEL-9.4.0 PC (Q35 + ICH9, 2009)";
pcmc->smbios_stream_product = "RHEL";
pcmc->smbios_stream_version = "9.4.0";
+
+ compat_props_add(m->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
}
DEFINE_PC_MACHINE(q35_rhel940, "pc-q35-rhel9.4.0", pc_q35_init_rhel940,
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index ff753a29e0..9ad54682c6 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -1282,6 +1282,7 @@ static void ccw_machine_rhel940_instance_options(MachineState *machine)
static void ccw_machine_rhel940_class_options(MachineClass *mc)
{
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5, hw_compat_rhel_9_5_len);
}
DEFINE_CCW_MACHINE(rhel940, "rhel9.4.0", true);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 46b8725c41..cca62f906b 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -514,6 +514,9 @@ extern const size_t hw_compat_2_2_len;
extern GlobalProperty hw_compat_2_1[];
extern const size_t hw_compat_2_1_len;
+extern GlobalProperty hw_compat_rhel_9_5[];
+extern const size_t hw_compat_rhel_9_5_len;
+
extern GlobalProperty hw_compat_rhel_9_4[];
extern const size_t hw_compat_rhel_9_4_len;
--
2.39.3

32
0015-Revert-meson-temporarily-disable-Wunused-function.patch Normal file
View File

@ -0,0 +1,32 @@
From d132184ec50656d9ed675801695a66f620fe0821 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20P=2E=20Berrang=C3=A9?= <berrange@redhat.com>
Date: Wed, 3 Jul 2024 13:47:04 +0100
Subject: Revert "meson: temporarily disable -Wunused-function"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This reverts commit c682111eaa73d9b985187b8be330338f50b78a7a.
No longer needed after introduction of downstream machines.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
---
meson.build | 1 -
1 file changed, 1 deletion(-)
diff --git a/meson.build b/meson.build
index 23494666d9..ef2e5be6e2 100644
--- a/meson.build
+++ b/meson.build
@@ -757,7 +757,6 @@ warn_flags = [
'-Wno-string-plus-int',
'-Wno-tautological-type-limit-compare',
'-Wno-typedef-redefinition',
- '-Wno-unused-function',
]
if host_os != 'darwin'
--
2.39.3

29
0016-Disable-FDC-devices.patch
View File

@ -1,29 +0,0 @@
From f24c7a1feef2a6f153582c06f10871b78a014bf1 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 26 Apr 2024 05:58:31 -0400
Subject: Disable FDC devices
---
configs/devices/x86_64-softmmu/x86_64-rh-devices.mak | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
index d60ff1bcfc..ee75bb4c21 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -19,9 +19,9 @@ 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_FDC=y
+#CONFIG_FDC_SYSBUS=y
+#CONFIG_FDC_ISA=y
CONFIG_FW_CFG_DMA=y
CONFIG_HDA=y
CONFIG_HYPERV=y
--
2.39.3

365
0016-Enable-make-check.patch Normal file
View File

@ -0,0 +1,365 @@
From 0f4d74ce6ff137291962909aaebc1dbf3dd27508 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 notes (9.1.0):
- Disable fdc-test
- Use q35 machine type for new pvpanic test
Rebase notes (10.0.0 rc0)
- Disable mem_addr_space functional test
- Updated removal of q35 test (upstream change)
Rebase notes (10.0.0):
- Add riscv changes
Rebase notes (10.1.0 rc0):
- Comment out unused code
---
.distro/qemu-kvm.spec.template | 4 +--
tests/functional/meson.build | 2 +-
tests/functional/test_aarch64_tcg_plugins.py | 4 +--
tests/qemu-iotests/meson.build | 34 ++++++++++----------
tests/qemu-iotests/testenv.py | 3 ++
tests/qtest/bios-tables-test.c | 10 ++++++
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/machine-none-test.c | 2 +-
tests/qtest/meson.build | 1 -
tests/qtest/pvpanic-test.c | 2 +-
tests/qtest/riscv-csr-test.c | 4 +++
tests/qtest/virtio-net-failover.c | 1 +
16 files changed, 47 insertions(+), 30 deletions(-)
diff --git a/tests/functional/meson.build b/tests/functional/meson.build
index 311c6f1806..c7f9051c90 100644
--- a/tests/functional/meson.build
+++ b/tests/functional/meson.build
@@ -319,7 +319,7 @@ tests_sparc64_system_thorough = [
tests_x86_64_system_quick = [
'cpu_queries',
- 'mem_addr_space',
+# 'mem_addr_space',
'migration',
'pc_cpu_hotplug_props',
'virtio_version',
diff --git a/tests/functional/test_aarch64_tcg_plugins.py b/tests/functional/test_aarch64_tcg_plugins.py
index cb7e9298fb..9efa826b01 100755
--- a/tests/functional/test_aarch64_tcg_plugins.py
+++ b/tests/functional/test_aarch64_tcg_plugins.py
@@ -64,7 +64,7 @@ class PluginKernelNormal(PluginKernelBase):
def test_aarch64_virt_insn(self):
self.set_machine('virt')
- self.cpu='cortex-a53'
+ self.cpu='cortex-a57'
kernel_path = self.ASSET_KERNEL.fetch()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
'console=ttyAMA0')
@@ -90,7 +90,7 @@ def test_aarch64_virt_insn(self):
def test_aarch64_virt_insn_icount(self):
self.set_machine('virt')
- self.cpu='cortex-a53'
+ self.cpu='cortex-a57'
kernel_path = self.ASSET_KERNEL.fetch()
kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
'console=ttyAMA0')
diff --git a/tests/qemu-iotests/meson.build b/tests/qemu-iotests/meson.build
index fad340ad59..3c0d5241f6 100644
--- a/tests/qemu-iotests/meson.build
+++ b/tests/qemu-iotests/meson.build
@@ -51,21 +51,21 @@ foreach format, speed: qemu_iotests_formats
check: true,
)
- foreach item: rc.stdout().strip().split()
- args = [qemu_iotests_check_cmd,
- '-tap', '-' + format, item,
- '--source-dir', meson.current_source_dir(),
- '--build-dir', meson.current_build_dir()]
- # Some individual tests take as long as 45 seconds
- # Bump the timeout to 3 minutes for some headroom
- # on slow machines to minimize spurious failures
- test('io-' + format + '-' + item,
- python,
- args: args,
- depends: qemu_iotests_binaries,
- env: qemu_iotests_env,
- protocol: 'tap',
- timeout: 180,
- suite: suites)
- endforeach
+# foreach item: rc.stdout().strip().split()
+# args = [qemu_iotests_check_cmd,
+# '-tap', '-' + format, item,
+# '--source-dir', meson.current_source_dir(),
+# '--build-dir', meson.current_build_dir()]
+# # Some individual tests take as long as 45 seconds
+# # Bump the timeout to 3 minutes for some headroom
+# # on slow machines to minimize spurious failures
+# test('io-' + format + '-' + item,
+# python,
+# args: args,
+# depends: qemu_iotests_binaries,
+# env: qemu_iotests_env,
+# protocol: 'tap',
+# timeout: 180,
+# suite: suites)
+# endforeach
endforeach
diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py
index 6326e46b7b..bc849ae9cf 100644
--- a/tests/qemu-iotests/testenv.py
+++ b/tests/qemu-iotests/testenv.py
@@ -252,6 +252,9 @@ def __init__(self, source_dir: str, build_dir: str,
if self.qemu_prog.endswith(f'qemu-system-{suffix}'):
self.qemu_options += f' -machine {machine}'
+ if self.qemu_prog.endswith('qemu-system-x86_64'):
+ self.qemu_options += ' -cpu Nehalem'
+
# QEMU_DEFAULT_MACHINE
self.qemu_default_machine = get_default_machine(self.qemu_prog)
diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c
index e7e6926c81..386196edc8 100644
--- a/tests/qtest/bios-tables-test.c
+++ b/tests/qtest/bios-tables-test.c
@@ -1755,6 +1755,7 @@ static void test_acpi_microvm_ioapic2_tcg(void)
free_test_data(&data);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void test_acpi_riscv64_virt_tcg_numamem(void)
{
test_data data = {
@@ -1780,6 +1781,7 @@ static void test_acpi_riscv64_virt_tcg_numamem(void)
&data);
free_test_data(&data);
}
+#endif /* disabled for RHEL */
static void test_acpi_aarch64_virt_tcg_numamem(void)
{
@@ -1856,6 +1858,7 @@ static void test_acpi_aarch64_virt_tcg_acpi_spcr(void)
free_test_data(&data);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void test_acpi_riscv64_virt_tcg_acpi_spcr(void)
{
test_data data = {
@@ -1874,6 +1877,7 @@ static void test_acpi_riscv64_virt_tcg_acpi_spcr(void)
"-machine spcr=off", &data);
free_test_data(&data);
}
+#endif
static void test_acpi_tcg_acpi_hmat(const char *machine, const char *arch)
{
@@ -2171,6 +2175,7 @@ static void test_acpi_microvm_acpi_erst(void)
}
#endif /* CONFIG_POSIX */
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void test_acpi_riscv64_virt_tcg(void)
{
test_data data = {
@@ -2192,6 +2197,7 @@ static void test_acpi_riscv64_virt_tcg(void)
test_acpi_one("-cpu rva22s64 ", &data);
free_test_data(&data);
}
+#endif /* disabled for RHEL */
static void test_acpi_aarch64_virt_tcg(void)
{
@@ -2526,6 +2532,7 @@ static void test_acpi_aarch64_virt_oem_fields(void)
g_free(args);
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
#define LOONGARCH64_INIT_TEST_DATA(data) \
test_data data = { \
.machine = "virt", \
@@ -2594,6 +2601,7 @@ static void test_acpi_loongarch64_virt_oem_fields(void)
free_test_data(&data);
g_free(args);
}
+#endif
int main(int argc, char *argv[])
{
@@ -2769,6 +2777,7 @@ int main(int argc, char *argv[])
qtest_add_func("acpi/virt/viot", test_acpi_aarch64_virt_viot);
}
}
+#if 0 /* Disabled for Red Hat Enterprise Linux */
} else if (strcmp(arch, "riscv64") == 0) {
if (has_tcg && qtest_has_device("virtio-blk-pci")) {
qtest_add_func("acpi/virt", test_acpi_riscv64_virt_tcg);
@@ -2788,6 +2797,7 @@ int main(int argc, char *argv[])
qtest_add_func("acpi/virt/oem-fields",
test_acpi_loongarch64_virt_oem_fields);
}
+#endif /* disabled for RHEL */
}
ret = g_test_run();
boot_sector_cleanup(disk);
diff --git a/tests/qtest/fuzz-e1000e-test.c b/tests/qtest/fuzz-e1000e-test.c
index 5052883fb6..8242190170 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-rhel9.4.0");
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..9f1965b530 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-rhel9.4.0 -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 663bb6c485..2efc43e3f7 100644
--- a/tests/qtest/intel-hda-test.c
+++ b/tests/qtest/intel-hda-test.c
@@ -42,7 +42,7 @@ 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 "
AUDIODEV
"-device intel-hda,id=" HDA_ID CODEC_DEVICES);
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index 1ddaf7b095..1cb403e90d 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',
'virtio-scmi.c',
'generic-pcihost.c',
diff --git a/tests/qtest/lpc-ich9-test.c b/tests/qtest/lpc-ich9-test.c
index 8ac95b89f7..0e118b76eb 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-rhel9.4.0 "
"-nographic -monitor none -serial none");
qtest_outl(s, 0xcf8, 0x8000f840); /* PMBASE */
diff --git a/tests/qtest/machine-none-test.c b/tests/qtest/machine-none-test.c
index b6a87d27ed..423ba12159 100644
--- a/tests/qtest/machine-none-test.c
+++ b/tests/qtest/machine-none-test.c
@@ -49,7 +49,7 @@ static struct arch2cpu cpus_map[] = {
{ "xtensa", "dc233c" },
{ "xtensaeb", "fsf" },
{ "hppa", "hppa" },
- { "riscv64", "rv64" },
+ { "riscv64", "max" },
{ "riscv32", "rv32" },
{ "rx", "rx62n" },
{ "loongarch64", "la464"},
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index b96aa06084..ef44ffaf78 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -91,7 +91,6 @@ qtests_i386 = \
(config_all_devices.has_key('CONFIG_LSI_SCSI_PCI') ? ['fuzz-lsi53c895a-test'] : []) + \
(config_all_devices.has_key('CONFIG_VIRTIO_SCSI') ? ['fuzz-virtio-scsi-test'] : []) + \
(config_all_devices.has_key('CONFIG_VIRTIO_BALLOON') ? ['virtio-balloon-test'] : []) + \
- (config_all_devices.has_key('CONFIG_Q35') ? ['q35-test'] : []) + \
(config_all_devices.has_key('CONFIG_SB16') ? ['fuzz-sb16-test'] : []) + \
(config_all_devices.has_key('CONFIG_SDHCI_PCI') ? ['fuzz-sdcard-test'] : []) + \
(config_all_devices.has_key('CONFIG_ESP_PCI') ? ['am53c974-test'] : []) + \
diff --git a/tests/qtest/pvpanic-test.c b/tests/qtest/pvpanic-test.c
index 094c56b0cd..338f94dcd9 100644
--- a/tests/qtest/pvpanic-test.c
+++ b/tests/qtest/pvpanic-test.c
@@ -65,7 +65,7 @@ static void test_pvshutdown(void)
QDict *response, *data;
QTestState *qts;
- qts = qtest_init("-device pvpanic");
+ qts = qtest_init("-M q35 -device pvpanic");
val = qtest_inb(qts, 0x505);
g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
diff --git a/tests/qtest/riscv-csr-test.c b/tests/qtest/riscv-csr-test.c
index ff5c29e6c6..cc3b08a976 100644
--- a/tests/qtest/riscv-csr-test.c
+++ b/tests/qtest/riscv-csr-test.c
@@ -20,6 +20,7 @@
#define CSR_MVENDORID 0xf11
#define CSR_MISELECT 0x350
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void run_test_csr(void)
{
uint64_t res;
@@ -45,12 +46,15 @@ static void run_test_csr(void)
qtest_quit(qts);
}
+#endif /* disabled for RHEL */
int main(int argc, char **argv)
{
g_test_init(&argc, &argv, NULL);
+#if 0 /* Disabled for Red Hat Enterprise Linux */
qtest_add_func("/cpu/csr", run_test_csr);
+#endif /* disabled for RHEL */
return g_test_run();
}
diff --git a/tests/qtest/virtio-net-failover.c b/tests/qtest/virtio-net-failover.c
index 5baf81c3e6..aa87bf5698 100644
--- a/tests/qtest/virtio-net-failover.c
+++ b/tests/qtest/virtio-net-failover.c
@@ -27,6 +27,7 @@
#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 "
--
2.39.3

24
0017-Disable-vga-cirrus-device.patch
View File

@ -1,24 +0,0 @@
From fe8c6cb1cecb3cde16871c4ec7368e4d004fa42a Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 26 Apr 2024 05:59:53 -0400
Subject: Disable vga-cirrus device
---
configs/devices/x86_64-softmmu/x86_64-rh-devices.mak | 1 -
1 file changed, 1 deletion(-)
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
index ee75bb4c21..fe69f04ead 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -87,7 +87,6 @@ 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
--
2.39.3

97
0011-vfio-cap-number-of-devices-that-can-be-assigned.patch → 0017-vfio-cap-number-of-devices-that-can-be-assigned.patch
View File

@ -1,8 +1,17 @@
From 8ba1a6d1a432e2ae82ae532253c2b254e6ce82a7 Mon Sep 17 00:00:00 2001
From 0f17fef61fc05f7617e47fcbc6a6c13efa5435d8 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
@ -17,16 +26,50 @@ 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 | 31 ++++++++++++++++++++++++++++++-
hw/vfio/pci.h | 1 +
2 files changed, 31 insertions(+), 1 deletion(-)
Rebase changes (8.2.0):
- Update to upstream changes
Rebased notes (10.1.0)
- Update to upstream changes
- Introduced vfio_device_count()
---
hw/vfio/container.c | 14 ++++++++++++++
hw/vfio/pci.c | 21 +++++++++++++++++++++
hw/vfio/pci.h | 1 +
include/hw/vfio/vfio-device.h | 1 +
4 files changed, 37 insertions(+)
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 3e13feaa74..b912b9396b 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -44,6 +44,20 @@ typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
static VFIOGroupList vfio_group_list =
QLIST_HEAD_INITIALIZER(vfio_group_list);
+int vfio_device_count(void)
+{
+ int i = 0;
+ VFIOGroup *group;
+ VFIODevice *vbasedev_iter;
+
+ QLIST_FOREACH(group, &vfio_group_list, next) {
+ QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
+ i++;
+ }
+ }
+ return i;
+}
+
static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state)
{
switch (container->iommu_type) {
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 64780d1b79..57ac63c10c 100644
index 07257d0fa0..48da233cb2 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -50,6 +50,9 @@
@@ -52,6 +52,9 @@
/* Protected by BQL */
static KVMRouteChange vfio_route_change;
@ -36,19 +79,9 @@ index 64780d1b79..57ac63c10c 100644
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);
@@ -2946,13 +2949,36 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
ERRP_GUARD();
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
VFIODevice *vbasedev = &vdev->vbasedev;
+ VFIODevice *vbasedev_iter;
+ VFIOGroup *group;
char *tmp, *subsys;
Error *err = NULL;
- int i, ret;
+ int ret, i = 0;
bool is_mdev;
@@ -3355,6 +3358,21 @@ static void vfio_pci_realize(PCIDevice *pdev, Error **errp)
char uuid[UUID_STR_LEN];
char *name;
g_autofree char *name = NULL;
+ if (device_limit && device_limit != vdev->assigned_device_limit) {
+ error_setg(errp, "Assigned device limit has been redefined. "
@ -59,13 +92,7 @@ index 64780d1b79..57ac63c10c 100644
+ 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) {
+ if (vfio_device_count() >= vdev->assigned_device_limit) {
+ error_setg(errp, "Maximum supported vfio devices (%d) "
+ "already attached", vdev->assigned_device_limit);
+ return;
@ -74,7 +101,7 @@ index 64780d1b79..57ac63c10c 100644
if (vbasedev->fd < 0 && !vbasedev->sysfsdev) {
if (!(~vdev->host.domain || ~vdev->host.bus ||
~vdev->host.slot || ~vdev->host.function)) {
@@ -3370,6 +3396,9 @@ static Property vfio_pci_dev_properties[] = {
@@ -3687,6 +3705,9 @@ static const 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),
@ -85,10 +112,10 @@ index 64780d1b79..57ac63c10c 100644
false),
DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioeventfd,
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 6e64a2654e..b7de39c010 100644
index 810a842f4a..81555d8774 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -142,6 +142,7 @@ struct VFIOPCIDevice {
@@ -145,6 +145,7 @@ struct VFIOPCIDevice {
EventNotifier err_notifier;
EventNotifier req_notifier;
int (*resetfn)(struct VFIOPCIDevice *);
@ -96,6 +123,18 @@ index 6e64a2654e..b7de39c010 100644
uint32_t vendor_id;
uint32_t device_id;
uint32_t sub_vendor_id;
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 6e4d5ccdac..9290774299 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -140,6 +140,7 @@ struct VFIODeviceOps {
#define strwriteerror(ret) \
(ret < 0 ? strerror(-ret) : "short write")
+int vfio_device_count(void);
void vfio_device_irq_disable(VFIODevice *vbasedev, int index);
void vfio_device_irq_unmask(VFIODevice *vbasedev, int index);
void vfio_device_irq_mask(VFIODevice *vbasedev, int index);
--
2.39.3

8
0012-Add-support-statement-to-help-output.patch → 0018-Add-support-statement-to-help-output.patch
View File

@ -1,4 +1,4 @@
From 7bc7a2d39bb2c00bcc8e573f05e629f5f21edc35 Mon Sep 17 00:00:00 2001
From 74a65ebea34ca36e3f510bc80274ce039df4e383 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
@ -12,10 +12,10 @@ Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
1 file changed, 9 insertions(+)
diff --git a/system/vl.c b/system/vl.c
index c644222982..03c3b0aa94 100644
index 3b7057e6c6..d3e6158753 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -869,9 +869,17 @@ static void version(void)
@@ -872,9 +872,17 @@ static void version(void)
QEMU_COPYRIGHT "\n");
}
@ -33,7 +33,7 @@ index c644222982..03c3b0aa94 100644
printf("usage: %s [options] [disk_image]\n\n"
"'disk_image' is a raw hard disk image for IDE hard disk 0\n\n",
g_get_prgname());
@@ -897,6 +905,7 @@ static void help(int exitcode)
@@ -900,6 +908,7 @@ static void help(int exitcode)
"\n"
QEMU_HELP_BOTTOM "\n");

6
0013-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch → 0019-Use-qemu-kvm-in-documentation-instead-of-qemu-system.patch
View File

@ -1,4 +1,4 @@
From ec651d300d350a37219b09f5baab827ae6891006 Mon Sep 17 00:00:00 2001
From 50b5abd584d9157677d694260a797be793fcf985 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>
@ -27,10 +27,10 @@ index 52d6454b93..d74dbdeca9 100644
.. |I2C| replace:: I\ :sup:`2`\ C
.. |I2S| replace:: I\ :sup:`2`\ S
diff --git a/qemu-options.hx b/qemu-options.hx
index 8ce85d4559..4fc27ee2e2 100644
index ab23f14d21..3837456a61 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3493,11 +3493,11 @@ SRST
@@ -3858,11 +3858,11 @@ SRST
::

6
0014-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch → 0020-qcow2-Deprecation-warning-when-opening-v2-images-rw.patch
View File

@ -1,4 +1,4 @@
From 080f22d8fb8ca63996f1b6ecb3637033529d8016 Mon Sep 17 00:00:00 2001
From f1ec21d5adafcd06563a6c5404c5d631f470ab0c 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
@ -25,7 +25,7 @@ Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2 files changed, 7 insertions(+)
diff --git a/block/qcow2.c b/block/qcow2.c
index 956128b409..0e8b2f7518 100644
index 4aa9f9e068..6df65aab93 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1358,6 +1358,12 @@ qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
@ -42,7 +42,7 @@ index 956128b409..0e8b2f7518 100644
s->qcow_version = header.version;
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index 2846c83808..83472953a2 100644
index 511a55b1e8..35c0fc0d20 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -83,6 +83,7 @@ _filter_qemu()

46
0021-file-posix-Define-DM_MPATH_PROBE_PATHS.patch Normal file
View File

@ -0,0 +1,46 @@
From 90041be5316257fc98eb62af1e8a927e53d2d612 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Tue, 29 Apr 2025 17:05:41 +0200
Subject: file-posix: Define DM_MPATH_PROBE_PATHS
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 370: file-posix: Fix multipath failover with SCSI passthrough
RH-Jira: RHEL-65852
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/2] 6680f4a3f15a768b1ca51aafea452c3d0886f12e (kmwolf/centos-qemu-kvm)
While the kernel side isn't merged yet and we're still using old kernel
headers, just define DM_MPATH_PROBE_PATHS manually.
This is a downstream-only patch that can be removed after the next minor
release.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Patch-name: kvm-file-posix-Define-DM_MPATH_PROBE_PATHS.patch
Patch-id: 41
Patch-present-in-specfile: True
---
block/file-posix.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/block/file-posix.c b/block/file-posix.c
index 8c738674ce..cb2e94d7db 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -156,6 +156,11 @@
*/
#define SG_IO_MAX_RETRIES 8
+/* TODO Remove this when the kernel side is merged */
+#if !defined(DM_MPATH_PROBE_PATHS) && defined(DM_GET_TARGET_VERSION)
+#define DM_MPATH_PROBE_PATHS _IO(DM_IOCTL, DM_GET_TARGET_VERSION_CMD + 1)
+#endif
+
typedef struct BDRVRawState {
int fd;
bool use_lock;
--
2.39.3

266
2001-Add-ppc64-support.patch
View File

@ -1,27 +1,76 @@
From 078107cb85368f95afc5f48ec7712a3c9213b157 Mon Sep 17 00:00:00 2001
From 9928955dc717c10f4c1084ef1ba71308fef68376 Mon Sep 17 00:00:00 2001
From: eabdullin <ed.abdullin.1@gmail.com>
Date: Tue, 26 Nov 2024 13:11:35 +0300
Date: Tue, 15 Oct 2024 10:48:05 +0300
Subject: [PATCH] Add ppc64 support
---
hw/ppc/spapr.c | 101 ++++++++++++++++++++++++++++++++++++++++
hw/ppc/spapr_cpu_core.c | 16 +++++++
include/hw/ppc/spapr.h | 3 ++
target/ppc/compat.c | 11 +++++
target/ppc/cpu-models.c | 9 +++-
target/ppc/cpu.h | 1 +
target/ppc/kvm.c | 27 +++++++++++
target/ppc/kvm_ppc.h | 13 ++++++
8 files changed, 180 insertions(+), 1 deletion(-)
.../ppc64-softmmu/ppc64-rh-devices.mak | 39 ++++++
hw/ppc/spapr.c | 128 +++++++++++++++++-
hw/ppc/spapr_cpu_core.c | 15 ++
include/hw/ppc/spapr.h | 3 +
target/ppc/compat.c | 11 ++
target/ppc/cpu-models.c | 8 ++
target/ppc/cpu.h | 1 +
target/ppc/kvm.c | 27 ++++
target/ppc/kvm_ppc.h | 13 ++
target/ppc/misc_helper.c | 8 --
10 files changed, 240 insertions(+), 13 deletions(-)
create mode 100644 configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
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 000000000..4b801b126
--- /dev/null
+++ b/configs/devices/ppc64-softmmu/ppc64-rh-devices.mak
@@ -0,0 +1,39 @@
+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_USB_HUB=y
+CONFIG_USB_HID=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/hw/ppc/spapr.c b/hw/ppc/spapr.c
index e9bc97fee..3e1713838 100644
index b0a0f8c68..5369bbba4 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1718,6 +1718,13 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
pef_kvm_reset(machine->cgs, &error_fatal);
@@ -1717,7 +1717,13 @@ static void spapr_machine_reset(MachineState *machine, ResetType type)
}
spapr_caps_apply(spapr);
spapr_nested_reset(spapr);
-
+ if (spapr->svm_allowed) {
+#ifdef CONFIG_KVM
+ kvmppc_svm_allow(&error_fatal);
@ -29,10 +78,10 @@ index e9bc97fee..3e1713838 100644
+ error_setg(&error_fatal, "No PEF support in tcg, try x-svm-allowed=off");
+#endif
+ }
first_ppc_cpu = POWERPC_CPU(first_cpu);
if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
@@ -3421,6 +3428,20 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
@@ -3408,6 +3414,21 @@ static void spapr_set_host_serial(Object *obj, const char *value, Error **errp)
spapr->host_serial = g_strdup(value);
}
@ -49,11 +98,12 @@ index e9bc97fee..3e1713838 100644
+
+ spapr->svm_allowed = value;
+}
+
+
static void spapr_instance_init(Object *obj)
{
SpaprMachineState *spapr = SPAPR_MACHINE(obj);
@@ -3499,6 +3520,12 @@ static void spapr_instance_init(Object *obj)
@@ -3486,6 +3507,12 @@ 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");
@ -66,7 +116,7 @@ index e9bc97fee..3e1713838 100644
}
static void spapr_machine_finalizefn(Object *obj)
@@ -4754,6 +4781,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
@@ -4706,6 +4733,7 @@ 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;
@ -74,28 +124,27 @@ index e9bc97fee..3e1713838 100644
}
static const TypeInfo spapr_machine_info = {
@@ -4805,6 +4833,7 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
@@ -4761,11 +4789,12 @@ static void spapr_machine_latest_class_options(MachineClass *mc)
} \
type_init(spapr_machine_register_##suffix)
type_init(MACHINE_VER_SYM(register, spapr, __VA_ARGS__))
-#define DEFINE_SPAPR_MACHINE_AS_LATEST(major, minor) \
- DEFINE_SPAPR_MACHINE_IMPL(true, major, minor)
-#define DEFINE_SPAPR_MACHINE(major, minor) \
- DEFINE_SPAPR_MACHINE_IMPL(false, major, minor)
+#define DEFINE_SPAPR_MACHINE_AS_LATEST(major, minor, micro) \
+ DEFINE_SPAPR_MACHINE_IMPL(true, major, minor, micro)
+#define DEFINE_SPAPR_MACHINE(major, minor, micro) \
+ DEFINE_SPAPR_MACHINE_IMPL(false, major, minor, micro)
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/*
* pseries-9.0
* pseries-10.0
*/
@@ -5013,6 +5042,9 @@ static bool phb_placement_4_0(SpaprMachineState *spapr, uint32_t index,
}
return true;
@@ -5060,6 +5089,95 @@ static void spapr_machine_3_0_class_options(MachineClass *mc)
}
+#endif
+
+#if 0 /* Disabled for Red Hat Enterprise Linux */
static void spapr_machine_4_0_class_options(MachineClass *mc)
{
SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
@@ -5338,6 +5370,75 @@ 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);
DEFINE_SPAPR_MACHINE(3, 0);
+#endif /* disabled for RHEL */
+
+static void spapr_rhel_machine_default_class_options(MachineClass *mc)
@ -109,78 +158,98 @@ index e9bc97fee..3e1713838 100644
+ mc->max_cpus = 384;
+}
+
+static void spapr_machine_rhel950_class_options(MachineClass *mc)
+static void spapr_rhel_machine_10_0_0_class_options(MachineClass *mc)
+{
+ SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
+
+ /* The default machine type must apply the RHEL specific defaults */
+ spapr_rhel_machine_default_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
+ compat_props_add(mc->compat_props, hw_compat_rhel_10_0,
+ hw_compat_rhel_10_0_len);
+ smc->pre_6_2_numa_affinity = true;
+ mc->smp_props.prefer_sockets = true;
+}
+
+DEFINE_SPAPR_MACHINE(rhel950, "rhel9.5.0", true);
+DEFINE_SPAPR_MACHINE_AS_LATEST(10, 0, 0);
+
+static void spapr_machine_rhel940_class_options(MachineClass *mc)
+static void spapr_rhel_machine_9_6_0_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel950_class_options(mc);
+ spapr_rhel_machine_10_0_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9,
+ hw_compat_rhel_9_len);
+}
+
+DEFINE_SPAPR_MACHINE(9, 6, 0);
+
+static void spapr_rhel_machine_9_5_0_class_options(MachineClass *mc)
+{
+ spapr_rhel_machine_9_6_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_5,
+ hw_compat_rhel_9_5_len);
+}
+
+DEFINE_SPAPR_MACHINE(9, 5, 0);
+
+static void spapr_rhel_machine_9_4_0_class_options(MachineClass *mc)
+{
+ spapr_rhel_machine_9_5_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_4,
+ hw_compat_rhel_9_4_len);
+}
+
+DEFINE_SPAPR_MACHINE(rhel940, "rhel9.4.0", false);
+DEFINE_SPAPR_MACHINE(9, 4, 0);
+
+static void spapr_machine_rhel930_class_options(MachineClass *mc)
+static void spapr_rhel_machine_9_3_0_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel940_class_options(mc);
+ spapr_rhel_machine_9_4_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_3,
+ hw_compat_rhel_9_3_len);
+}
+
+DEFINE_SPAPR_MACHINE(rhel930, "rhel9.3.0", false);
+DEFINE_SPAPR_MACHINE(9, 3, 0);
+
+static void spapr_machine_rhel920_class_options(MachineClass *mc)
+static void spapr_rhel_machine_9_2_0_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel930_class_options(mc);
+ spapr_rhel_machine_9_3_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_2,
+ hw_compat_rhel_9_2_len);
+}
+
+DEFINE_SPAPR_MACHINE(rhel920, "rhel9.2.0", false);
+DEFINE_SPAPR_MACHINE(9, 2, 0);
+
+static void spapr_machine_rhel910_class_options(MachineClass *mc)
+static void spapr_rhel_machine_9_1_0_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel920_class_options(mc);
+ spapr_rhel_machine_9_2_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_1,
+ hw_compat_rhel_9_1_len);
+}
+
+DEFINE_SPAPR_MACHINE(rhel910, "rhel9.1.0", false);
+DEFINE_SPAPR_MACHINE(9, 1, 0);
+
+static void spapr_machine_rhel900_class_options(MachineClass *mc)
+static void spapr_rhel_machine_9_0_0_class_options(MachineClass *mc)
+{
+ spapr_machine_rhel910_class_options(mc);
+ spapr_rhel_machine_9_1_0_class_options(mc);
+ compat_props_add(mc->compat_props, hw_compat_rhel_9_0,
+ hw_compat_rhel_9_0_len);
+}
+
+DEFINE_SPAPR_MACHINE(rhel900, "rhel9.0.0", false);
+DEFINE_SPAPR_MACHINE(9, 0, 0);
static void spapr_machine_register_types(void)
{
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index e7c9edd03..c33c321d1 100644
index faf9170ba..df3bde0db 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 "system/reset.h"
#include "system/hw_accel.h"
#include "qemu/error-report.h"
+#include "cpu-models.h"
static void spapr_reset_vcpu(PowerPCCPU *cpu)
{
@@ -264,6 +265,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
@@ -268,6 +269,7 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
{
CPUPPCState *env = &cpu->env;
CPUState *cs = CPU(cpu);
@ -188,7 +257,7 @@ index e7c9edd03..c33c321d1 100644
if (!qdev_realize(DEVICE(cpu), NULL, errp)) {
return false;
@@ -280,6 +282,18 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr,
@@ -286,6 +288,17 @@ 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);
@ -202,12 +271,11 @@ index e7c9edd03..c33c321d1 100644
+ "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;
@@ -389,10 +403,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = {
@@ -401,10 +414,12 @@ static const TypeInfo spapr_cpu_core_type_infos[] = {
.instance_size = sizeof(SpaprCpuCore),
.class_size = sizeof(SpaprCpuCoreClass),
},
@ -221,10 +289,10 @@ index e7c9edd03..c33c321d1 100644
DEFINE_SPAPR_CPU_CORE_TYPE("power7p_v2.1"),
DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"),
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 4aaf23d28..183a13702 100644
index 39bd5bd5e..e50e8328d 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -157,6 +157,7 @@ struct SpaprMachineClass {
@@ -156,6 +156,7 @@ struct SpaprMachineClass {
bool pre_5_2_numa_associativity;
bool pre_6_2_numa_affinity;
@ -242,10 +310,10 @@ index 4aaf23d28..183a13702 100644
/*< public >*/
char *kvm_type;
diff --git a/target/ppc/compat.c b/target/ppc/compat.c
index ebef2ccce..ab7ed7680 100644
index 55de3bd5d..1bf6994da 100644
--- a/target/ppc/compat.c
+++ b/target/ppc/compat.c
@@ -114,6 +114,17 @@ static const CompatInfo *compat_by_pvr(uint32_t pvr)
@@ -121,6 +121,17 @@ static const CompatInfo *compat_by_pvr(uint32_t pvr)
return NULL;
}
@ -264,7 +332,7 @@ index ebef2ccce..ab7ed7680 100644
uint32_t min_compat_pvr, uint32_t max_compat_pvr)
{
diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c
index f2301b43f..4c38fa517 100644
index ece348178..6cfa71eec 100644
--- a/target/ppc/cpu-models.c
+++ b/target/ppc/cpu-models.c
@@ -66,6 +66,7 @@
@ -294,7 +362,7 @@ index f2301b43f..4c38fa517 100644
POWERPC_DEF("power7_v2.3", CPU_POWERPC_POWER7_v23, POWER7,
"POWER7 v2.3")
POWERPC_DEF("power7p_v2.1", CPU_POWERPC_POWER7P_v21, POWER7,
@@ -895,12 +899,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
@@ -897,12 +901,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "7457a", "7457a_v1.2" },
{ "apollo7pm", "7457a_v1.0" },
#if defined(TARGET_PPC64)
@ -309,11 +377,10 @@ index f2301b43f..4c38fa517 100644
{ "power7", "power7_v2.3" },
{ "power7+", "power7p_v2.1" },
{ "power7+_v2.1", "power7p_v2.1" },
@@ -910,13 +916,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power9", "power9_v2.2" },
{ "power10", "power10_v2.0" },
@@ -914,12 +920,14 @@ PowerPCCPUAlias ppc_cpu_aliases[] = {
{ "power11", "power11_v2.0" },
#endif
-
+#if 0 /* Disabled for Red Hat Enterprise Linux */
/* Generic PowerPCs */
#if defined(TARGET_PPC64)
@ -326,10 +393,10 @@ index f2301b43f..4c38fa517 100644
{ NULL, NULL }
};
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 67e6b2eff..11187aeb9 100644
index 3ee83517d..121e57482 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1655,6 +1655,7 @@ static inline int ppc_env_mmu_index(CPUPPCState *env, bool ifetch)
@@ -1686,6 +1686,7 @@ static inline int ppc_env_mmu_index(CPUPPCState *env, bool ifetch)
/* Compatibility modes */
#if defined(TARGET_PPC64)
@ -338,26 +405,26 @@ index 67e6b2eff..11187aeb9 100644
uint32_t min_compat_pvr, uint32_t max_compat_pvr);
bool ppc_type_check_compat(const char *cputype, uint32_t compat_pvr,
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 8231feb2d..59f640cf7 100644
index 992356cb7..43c468343 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -89,6 +89,7 @@ static int cap_large_decr;
static int cap_fwnmi;
@@ -93,6 +93,7 @@ static int cap_fwnmi;
static int cap_rpt_invalidate;
static int cap_ail_mode_3;
static int cap_dawr1;
+static int cap_ppc_secure_guest;
static uint32_t debug_inst_opcode;
@@ -141,6 +142,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
#ifdef CONFIG_PSERIES
static int cap_papr;
@@ -151,6 +152,7 @@ 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);
/*
@@ -2564,6 +2566,16 @@ bool kvmppc_supports_ail_3(void)
cap_dawr1 = kvm_vm_check_extension(s, KVM_CAP_PPC_DAWR1);
@@ -2609,6 +2611,16 @@ bool kvmppc_supports_ail_3(void)
return cap_ail_mode_3;
}
@ -374,10 +441,10 @@ index 8231feb2d..59f640cf7 100644
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void)
{
uint32_t host_pvr = mfpvr();
@@ -2964,3 +2976,18 @@ bool kvm_arch_cpu_check_are_resettable(void)
void kvm_arch_accel_class_init(ObjectClass *oc)
{
@@ -3024,3 +3036,18 @@ static void kvm_cpu_accel_register_types(void)
type_register_static(&kvm_cpu_accel_type_info);
}
type_init(kvm_cpu_accel_register_types);
+
+void kvmppc_svm_allow(Error **errp)
+{
@ -394,7 +461,7 @@ index 8231feb2d..59f640cf7 100644
+ }
+}
diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index 1975fb5ee..d1017f98b 100644
index a8768c1df..59f50cb79 100644
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -46,6 +46,7 @@ int kvmppc_booke_watchdog_enable(PowerPCCPU *cpu);
@ -405,7 +472,7 @@ index 1975fb5ee..d1017f98b 100644
bool kvmppc_spapr_use_multitce(void);
int kvmppc_spapr_enable_inkernel_multitce(void);
void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t page_shift,
@@ -79,6 +80,8 @@ int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable);
@@ -81,6 +82,8 @@ int kvmppc_enable_cap_large_decr(PowerPCCPU *cpu, int enable);
int kvmppc_has_cap_rpt_invalidate(void);
bool kvmppc_supports_ail_3(void);
int kvmppc_enable_hwrng(void);
@ -414,7 +481,7 @@ index 1975fb5ee..d1017f98b 100644
int kvmppc_put_books_sregs(PowerPCCPU *cpu);
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void);
void kvmppc_check_papr_resize_hpt(Error **errp);
@@ -427,6 +430,16 @@ static inline bool kvmppc_supports_ail_3(void)
@@ -439,6 +442,16 @@ static inline bool kvmppc_supports_ail_3(void)
return false;
}
@ -431,6 +498,31 @@ index 1975fb5ee..d1017f98b 100644
static inline int kvmppc_enable_hwrng(void)
{
return -1;
diff --git a/target/ppc/misc_helper.c b/target/ppc/misc_helper.c
index 46ae454af..607ed3735 100644
--- a/target/ppc/misc_helper.c
+++ b/target/ppc/misc_helper.c
@@ -332,10 +332,6 @@ target_ulong helper_load_sprd(CPUPPCState *env)
PnvCore *pc = pnv_cpu_state(cpu)->pnv_core;
target_ulong sprc = env->spr[SPR_POWER_SPRC];
- if (pc->big_core) {
- pc = pnv_chip_find_core(pc->chip, CPU_CORE(pc)->core_id & ~0x1);
- }
-
switch (sprc & 0x3e0) {
case 0: /* SCRATCH0-3 */
case 1: /* SCRATCH4-7 */
@@ -372,10 +368,6 @@ void helper_store_sprd(CPUPPCState *env, target_ulong val)
PnvCore *pc = pnv_cpu_state(cpu)->pnv_core;
int nr;
- if (pc->big_core) {
- pc = pnv_chip_find_core(pc->chip, CPU_CORE(pc)->core_id & ~0x1);
- }
-
switch (sprc & 0x3e0) {
case 0: /* SCRATCH0-3 */
case 1: /* SCRATCH4-7 */
--
2.39.5 (Apple Git-154)

9
2002-Enable-QXL-device-build.patch
View File

@ -8,14 +8,13 @@ Subject: [PATCH] Enable QXL device build
1 file changed, 1 insertion(+)
diff --git a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
index 276397f3b..cc1e5bd41 100644
index 45a8a1529..2769c1eb4 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -111,3 +111,4 @@ CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
@@ -118,3 +118,4 @@ CONFIG_VHOST_USER_FS=y
CONFIG_VHOST_USER_SND=y
CONFIG_VHOST_USER_SCMI=y
CONFIG_VHOST_USER_GPU=y
CONFIG_UEFI_VARS=y
+CONFIG_QXL=y
--
2.43.5

50
kvm-Enable-vhost-user-scmi-devices.patch
View File

@ -1,50 +0,0 @@
From ca89f2eb9588bfebe2796a579a563bd974dadf72 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 24 Jul 2024 07:31:12 -0400
Subject: [PATCH] Enable vhost-user-scmi devices
RH-Author: Miroslav Rezanina <mrezanin@redhat.com>
RH-MergeRequest: 258: Enable vhost-user-scmi devices
RH-Jira: RHEL-50165
RH-Acked-by: Sandro Bonazzola <None>
RH-Commit: [1/1] edf95ef0fab99eb079beb16409fdab2a3cb0b94b (mrezanin/centos-src-qemu-kvm)
Enabling vhost-user-scmi and vhost-user-scmi-pci devices for qemu-kvm.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
configs/devices/aarch64-softmmu/aarch64-rh-devices.mak | 1 +
configs/devices/s390x-softmmu/s390x-rh-devices.mak | 1 +
configs/devices/x86_64-softmmu/x86_64-rh-devices.mak | 1 +
3 files changed, 3 insertions(+)
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
index 0a95438e25..4495d033e5 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -41,3 +41,4 @@ CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
CONFIG_VHOST_USER_SND=y
+CONFIG_VHOST_USER_SCMI=y
diff --git a/configs/devices/s390x-softmmu/s390x-rh-devices.mak b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
index 719f802565..963ec43b6c 100644
--- a/configs/devices/s390x-softmmu/s390x-rh-devices.mak
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -18,3 +18,4 @@ CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
CONFIG_VHOST_USER_SND=y
+CONFIG_VHOST_USER_SCMI=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
index b85bb1fe53..276397f3be 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -110,3 +110,4 @@ CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
CONFIG_VHOST_USER_SND=y
+CONFIG_VHOST_USER_SCMI=y
--
2.39.3

50
kvm-Enable-vhost-user-snd-pci-device.patch
View File

@ -1,50 +0,0 @@
From d7256c0d15a3ae142c80462c66e0d68120ebd001 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Wed, 22 May 2024 03:56:55 -0400
Subject: [PATCH] Enable vhost-user-snd-pci device
RH-Author: Miroslav Rezanina <mrezanin@redhat.com>
RH-MergeRequest: 242: Enable vhost-user-snd-pci device
RH-Jira: RHEL-37563
RH-Acked-by: Sandro Bonazzola <None>
RH-Commit: [1/1] 014f47770fc9f7d4bd0e7fac9a072911325f3283 (mrezanin/centos-src-qemu-kvm)
RHIVOS requires vhost-user-snd-pci device. Enabling it for aarch64 and x86_64 only.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
configs/devices/aarch64-softmmu/aarch64-rh-devices.mak | 1 +
configs/devices/s390x-softmmu/s390x-rh-devices.mak | 1 +
configs/devices/x86_64-softmmu/x86_64-rh-devices.mak | 1 +
3 files changed, 3 insertions(+)
diff --git a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
index b0191d3c69..0a95438e25 100644
--- a/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
+++ b/configs/devices/aarch64-softmmu/aarch64-rh-devices.mak
@@ -40,3 +40,4 @@ CONFIG_VHOST_VSOCK=y
CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
+CONFIG_VHOST_USER_SND=y
diff --git a/configs/devices/s390x-softmmu/s390x-rh-devices.mak b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
index 24cf6dbd03..719f802565 100644
--- a/configs/devices/s390x-softmmu/s390x-rh-devices.mak
+++ b/configs/devices/s390x-softmmu/s390x-rh-devices.mak
@@ -17,3 +17,4 @@ CONFIG_VHOST_VSOCK=y
CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
+CONFIG_VHOST_USER_SND=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
index fe69f04ead..b85bb1fe53 100644
--- a/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
+++ b/configs/devices/x86_64-softmmu/x86_64-rh-devices.mak
@@ -109,3 +109,4 @@ CONFIG_VHOST_VSOCK=y
CONFIG_VHOST_USER_VSOCK=y
CONFIG_VHOST_USER_FS=y
CONFIG_IOMMUFD=y
+CONFIG_VHOST_USER_SND=y
--
2.39.3

37
kvm-Fix-the-typo-of-vfio-pci-device-s-enable-migration-o.patch Normal file
View File

@ -0,0 +1,37 @@
From 0509eb94d2f166cfd3a24aa5fd14e1af76af8dea Mon Sep 17 00:00:00 2001
From: Yanghang Liu <yanghliu@redhat.com>
Date: Mon, 24 Nov 2025 23:02:37 +0800
Subject: [PATCH 4/4] Fix the typo of vfio-pci device's enable-migration option
RH-Author: YangHang Liu <None>
RH-MergeRequest: 428: RHEL10: Fix the typo of vfio-pci device's enable-migration option
RH-Jira: RHEL-130704
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] bcf8b2089f687d02b5f0a48dd1e3dfc4664946e0 (yanghliu/qemu-kvm)
Signed-off-by: Yanghang Liu <yanghliu@redhat.com>
Reported-by: Mario Casquero <mcasquer@redhat.com>
Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
(cherry picked from commit 5f9ac963735598c1efbdce9c4a09f0a64e13d613)
Signed-off-by: Yanghang Liu <yanghliu@redhat.com>
---
hw/vfio/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 83ecffb535..7c057ee2f9 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3847,7 +3847,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, const void *data)
"(DEBUG)");
object_class_property_set_description(klass, /* 5.2, 8.0 non-experimetal */
"enable-migration",
- "Enale device migration. Also requires a host VFIO PCI "
+ "Enable device migration. Also requires a host VFIO PCI "
"variant or mdev driver with migration support enabled");
object_class_property_set_description(klass, /* 8.1 */
"vf-token",
--
2.47.3

54
kvm-MAINTAINERS-Add-maintainers-for-mshv-accelerator.patch Normal file
View File

@ -0,0 +1,54 @@
From 5807bd68ad5c038a57ffb2f665f732dfc51d8868 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:47 +0200
Subject: [PATCH 30/32] MAINTAINERS: Add maintainers for mshv accelerator
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [28/30] 0178a9a61285bd708b5f589888c36b74efd4a4bf
Adding Magnus Kulke and Wei Liu to the maintainers file for the
respective folders/files.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-28-magnuskulke@linux.microsoft.com
[Rename "MAHV CPUs" to mention x86. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 1872bd9f2dad5113b0c27d352ec49683e0953c7f)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
MAINTAINERS | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index a07086ed76..d4696f00d7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -546,6 +546,21 @@ F: target/i386/whpx/
F: accel/stubs/whpx-stub.c
F: include/system/whpx.h
+MSHV
+M: Magnus Kulke <magnus.kulke@linux.microsoft.com>
+R: Wei Liu <wei.liu@kernel.org>
+S: Supported
+F: accel/mshv/
+F: include/system/mshv.h
+F: include/hw/hyperv/hvgdk*.h
+F: include/hw/hyperv/hvhdk*.h
+
+X86 MSHV CPUs
+M: Magnus Kulke <magnus.kulke@linux.microsoft.com>
+R: Wei Liu <wei.liu@kernel.org>
+S: Supported
+F: target/i386/mshv/
+
X86 Instruction Emulator
M: Cameron Esfahani <dirty@apple.com>
M: Roman Bolshakov <rbolshakov@ddn.com>
--
2.47.3

81
kvm-Revert-hw-arm-virt-Use-ACPI-PCI-hotplug-by-default-f.patch Normal file
View File

@ -0,0 +1,81 @@
From eee1f8abab9cbcb64ab690737f1a8db293d87c05 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 11 Feb 2026 09:57:37 -0500
Subject: [PATCH 7/7] Revert "hw/arm/virt: Use ACPI PCI hotplug by default from
10.2 onwards"
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 465: Revert "hw/arm/virt: Use ACPI PCI hotplug by default from 10.2 onwards"
RH-Jira: RHEL-134989 RHEL-146584
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [1/1] e22612dc81813762f8d7f4bc9f75df0b9f2135e0 (eauger1/centos-qemu-kvm)
JIRA: https://issues.redhat.com/browse/RHEL-134989
JIRA: https://issues.redhat.com/browse/RHEL-146584
UPSTREAM: RHEL-only
This reverts commit 58cba97a715fa3f506234e718191fcc34286f333.
Conflicts: small contextual conflict when reverting changes in
hw/arm/virt.c due to subsequent fix by commit
fa0a758781fc ("arm: fix oob access in compat handling")
Unfortunately the change of the default for the PCI hotplug method
introduced some regressions that cannot be fixed in 10.2 cycle. An
example is hotplugging a virtio-net-pci device with page-per-vq=true.
This induces an increase in the BAR size which is larger than the
default size the FW accomodates. At the moment we do not have any
workaround for those devices with large BARs, ie. we noticed
pcie-root-port pref64-reserve does not work as on x86 and we do not
have any way to opt-in for legacy PCIe hotplug at libvirt
level. So let's revert the change until we get all those stuff
properly fixed.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 1cfb386f64..752dc08720 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -95,16 +95,9 @@
static GlobalProperty arm_virt_compat[] = {
{ TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "48" },
- { TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "on" },
};
static const size_t arm_virt_compat_len = G_N_ELEMENTS(arm_virt_compat);
-GlobalProperty arm_acpi_pci_hp_disabled_compat[] = {
- { TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "off" },
-};
-static const size_t arm_acpi_pci_hp_disabled_compat_len =
- G_N_ELEMENTS(arm_acpi_pci_hp_disabled_compat);
-
/*
* RHEL9 kernels have pauth disabled while RHEL10 has it enabled,
* since qemu will setup the VM with pauth when KVM supports it we
@@ -112,7 +105,6 @@ static const size_t arm_acpi_pci_hp_disabled_compat_len =
*/
GlobalProperty arm_rhel9_compat[] = {
{TYPE_ARM_CPU, "pauth", "off", .optional = true},
- {TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "off" },
};
const size_t arm_rhel9_compat_len = G_N_ELEMENTS(arm_rhel9_compat);
@@ -3768,8 +3760,6 @@ static void virt_rhel_machine_10_0_0_options(MachineClass *mc)
/* QEMU 9.1 and earlier have only a stage-1 SMMU, not a nested s1+2 one */
vmc->no_nested_smmu = true;
- compat_props_add(mc->compat_props, arm_acpi_pci_hp_disabled_compat,
- arm_acpi_pci_hp_disabled_compat_len);
compat_props_add(mc->compat_props, hw_compat_rhel_10_2, hw_compat_rhel_10_2_len);
compat_props_add(mc->compat_props, hw_compat_rhel_10_1, hw_compat_rhel_10_1_len);
}
--
2.47.3

67
kvm-Revert-monitor-use-aio_co_reschedule_self.patch
View File

@ -1,67 +0,0 @@
From 53cc7daf2b6356f236a493cbe63d01afc5636fd3 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 6 May 2024 15:06:21 -0400
Subject: [PATCH 13/14] Revert "monitor: use aio_co_reschedule_self()"
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 253: Revert "monitor: use aio_co_reschedule_self()"
RH-Jira: RHEL-43409 RHEL-43410
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [1/2] 772eccc9da09e6c1793d46ab6cf9ee6615812154 (kmwolf/centos-qemu-kvm)
Commit 1f25c172f837 ("monitor: use aio_co_reschedule_self()") was a code
cleanup that uses aio_co_reschedule_self() instead of open coding
coroutine rescheduling.
Bug RHEL-34618 was reported and Kevin Wolf <kwolf@redhat.com> identified
the root cause. I missed that aio_co_reschedule_self() ->
qemu_get_current_aio_context() only knows about
qemu_aio_context/IOThread AioContexts and not about iohandler_ctx. It
does not function correctly when going back from the iohandler_ctx to
qemu_aio_context.
Go back to open coding the AioContext transitions to avoid this bug.
This reverts commit 1f25c172f83704e350c0829438d832384084a74d.
Cc: qemu-stable@nongnu.org
Buglink: https://issues.redhat.com/browse/RHEL-34618
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20240506190622.56095-2-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 719c6819ed9a9838520fa732f9861918dc693bda)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
qapi/qmp-dispatch.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/qapi/qmp-dispatch.c b/qapi/qmp-dispatch.c
index f3488afeef..176b549473 100644
--- a/qapi/qmp-dispatch.c
+++ b/qapi/qmp-dispatch.c
@@ -212,7 +212,8 @@ QDict *coroutine_mixed_fn qmp_dispatch(const QmpCommandList *cmds, QObject *requ
* executing the command handler so that it can make progress if it
* involves an AIO_WAIT_WHILE().
*/
- aio_co_reschedule_self(qemu_get_aio_context());
+ aio_co_schedule(qemu_get_aio_context(), qemu_coroutine_self());
+ qemu_coroutine_yield();
}
monitor_set_cur(qemu_coroutine_self(), cur_mon);
@@ -226,7 +227,9 @@ QDict *coroutine_mixed_fn qmp_dispatch(const QmpCommandList *cmds, QObject *requ
* Move back to iohandler_ctx so that nested event loops for
* qemu_aio_context don't start new monitor commands.
*/
- aio_co_reschedule_self(iohandler_get_aio_context());
+ aio_co_schedule(iohandler_get_aio_context(),
+ qemu_coroutine_self());
+ qemu_coroutine_yield();
}
} else {
/*
--
2.39.3

131
kvm-accel-Add-Meson-and-config-support-for-MSHV-accelera.patch Normal file
View File

@ -0,0 +1,131 @@
From 502e461dabe1eecc22f6a7d22755b8407ee74683 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:21 +0200
Subject: [PATCH 03/32] accel: Add Meson and config support for MSHV
accelerator
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/30] 04ab9685b09f4d837715bf624d87566f472cb6c2
Introduce a Meson feature option and default-config entry to allow
building QEMU with MSHV (Microsoft Hypervisor) acceleration support.
This is the first step toward implementing an MSHV backend in QEMU.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Link: https://lore.kernel.org/r/20250916164847.77883-2-magnuskulke@linux.microsoft.com
[Add error for unavailable accelerator. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 37e12da5df8eb74042f11e9e7bec8a50b8090adb)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/Kconfig | 3 +++
meson.build | 13 +++++++++++++
meson_options.txt | 2 ++
scripts/meson-buildoptions.sh | 3 +++
4 files changed, 21 insertions(+)
diff --git a/accel/Kconfig b/accel/Kconfig
index 4263cab722..a60f114923 100644
--- a/accel/Kconfig
+++ b/accel/Kconfig
@@ -13,6 +13,9 @@ config TCG
config KVM
bool
+config MSHV
+ bool
+
config XEN
bool
select FSDEV_9P if VIRTFS
diff --git a/meson.build b/meson.build
index ef2e5be6e2..96254f8075 100644
--- a/meson.build
+++ b/meson.build
@@ -334,6 +334,7 @@ elif cpu == 'x86_64'
'CONFIG_HVF': ['x86_64-softmmu'],
'CONFIG_NVMM': ['i386-softmmu', 'x86_64-softmmu'],
'CONFIG_WHPX': ['i386-softmmu', 'x86_64-softmmu'],
+ 'CONFIG_MSHV': ['x86_64-softmmu'],
}
endif
@@ -884,6 +885,14 @@ accelerators = []
if get_option('kvm').allowed() and host_os == 'linux'
accelerators += 'CONFIG_KVM'
endif
+
+if get_option('mshv').allowed() and host_os == 'linux'
+ if get_option('mshv').enabled() and host_machine.cpu() != 'x86_64'
+ error('mshv accelerator requires x64_64 host')
+ endif
+ accelerators += 'CONFIG_MSHV'
+endif
+
if get_option('whpx').allowed() and host_os == 'windows'
if get_option('whpx').enabled() and host_machine.cpu() != 'x86_64'
error('WHPX requires 64-bit host')
@@ -953,6 +962,9 @@ endif
if 'CONFIG_WHPX' not in accelerators and get_option('whpx').enabled()
error('WHPX not available on this platform')
endif
+if 'CONFIG_MSHV' not in accelerators and get_option('mshv').enabled()
+ error('mshv not available on this platform')
+endif
xen = not_found
if get_option('xen').enabled() or (get_option('xen').auto() and have_system)
@@ -4821,6 +4833,7 @@ if have_system
summary_info += {'HVF support': config_all_accel.has_key('CONFIG_HVF')}
summary_info += {'WHPX support': config_all_accel.has_key('CONFIG_WHPX')}
summary_info += {'NVMM support': config_all_accel.has_key('CONFIG_NVMM')}
+ summary_info += {'MSHV support': config_all_accel.has_key('CONFIG_MSHV')}
summary_info += {'Xen support': xen.found()}
if xen.found()
summary_info += {'xen ctrl version': xen.version()}
diff --git a/meson_options.txt b/meson_options.txt
index f45d7ded45..2267dee8a0 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -73,6 +73,8 @@ option('malloc', type : 'combo', choices : ['system', 'tcmalloc', 'jemalloc'],
option('kvm', type: 'feature', value: 'auto',
description: 'KVM acceleration support')
+option('mshv', type: 'feature', value: 'auto',
+ description: 'MSHV acceleration support')
option('whpx', type: 'feature', value: 'auto',
description: 'WHPX acceleration support')
option('hvf', type: 'feature', value: 'auto',
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index 4146dbc88d..9aff126c28 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -155,6 +155,7 @@ meson_options_help() {
printf "%s\n" ' membarrier membarrier system call (for Linux 4.14+ or Windows'
printf "%s\n" ' modules modules support (non Windows)'
printf "%s\n" ' mpath Multipath persistent reservation passthrough'
+ printf "%s\n" ' mshv MSHV acceleration support'
printf "%s\n" ' multiprocess Out of process device emulation support'
printf "%s\n" ' netmap netmap network backend support'
printf "%s\n" ' nettle nettle cryptography support'
@@ -409,6 +410,8 @@ _meson_option_parse() {
--disable-modules) printf "%s" -Dmodules=disabled ;;
--enable-mpath) printf "%s" -Dmpath=enabled ;;
--disable-mpath) printf "%s" -Dmpath=disabled ;;
+ --enable-mshv) printf "%s" -Dmshv=enabled ;;
+ --disable-mshv) printf "%s" -Dmshv=disabled ;;
--enable-multiprocess) printf "%s" -Dmultiprocess=enabled ;;
--disable-multiprocess) printf "%s" -Dmultiprocess=disabled ;;
--enable-netmap) printf "%s" -Dnetmap=enabled ;;
--
2.47.3

291
kvm-accel-mshv-Add-accelerator-skeleton.patch Normal file
View File

@ -0,0 +1,291 @@
From a491ddf980ed1c8a54ba06db007d770817554b91 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Thu, 2 Oct 2025 18:25:02 +0200
Subject: [PATCH 09/32] accel/mshv: Add accelerator skeleton
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [7/30] 2bf55db3c9fbc6ce5964090f192be3699ae2ea00
Introduce the initial scaffold for the MSHV (Microsoft Hypervisor)
accelerator backend. This includes the basic directory structure and
stub implementations needed to integrate with QEMU's accelerator
framework.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-8-magnuskulke@linux.microsoft.com
[Move include of linux/mshv.h in the per-target section; create
include/system/mshv_int.h. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit d0d2918f968c55628e17e2733b799fcefb50f16b)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/meson.build | 1 +
accel/mshv/meson.build | 6 ++
accel/mshv/mshv-all.c | 144 ++++++++++++++++++++++++++++++++++++++
include/system/mshv.h | 12 ++++
include/system/mshv_int.h | 41 +++++++++++
5 files changed, 204 insertions(+)
create mode 100644 accel/mshv/meson.build
create mode 100644 accel/mshv/mshv-all.c
create mode 100644 include/system/mshv_int.h
diff --git a/accel/meson.build b/accel/meson.build
index 6349efe682..983dfd0bd5 100644
--- a/accel/meson.build
+++ b/accel/meson.build
@@ -10,6 +10,7 @@ if have_system
subdir('kvm')
subdir('xen')
subdir('stubs')
+ subdir('mshv')
endif
# qtest
diff --git a/accel/mshv/meson.build b/accel/mshv/meson.build
new file mode 100644
index 0000000000..4c03ac7921
--- /dev/null
+++ b/accel/mshv/meson.build
@@ -0,0 +1,6 @@
+mshv_ss = ss.source_set()
+mshv_ss.add(if_true: files(
+ 'mshv-all.c'
+))
+
+specific_ss.add_all(when: 'CONFIG_MSHV', if_true: mshv_ss)
diff --git a/accel/mshv/mshv-all.c b/accel/mshv/mshv-all.c
new file mode 100644
index 0000000000..ae12f0f58b
--- /dev/null
+++ b/accel/mshv/mshv-all.c
@@ -0,0 +1,144 @@
+/*
+ * QEMU MSHV support
+ *
+ * Copyright Microsoft, Corp. 2025
+ *
+ * Authors:
+ * Ziqiao Zhou <ziqiaozhou@microsoft.com>
+ * Magnus Kulke <magnuskulke@microsoft.com>
+ * Jinank Jain <jinankjain@microsoft.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/event_notifier.h"
+#include "qemu/module.h"
+#include "qemu/main-loop.h"
+#include "hw/boards.h"
+
+#include "hw/hyperv/hvhdk.h"
+#include "hw/hyperv/hvhdk_mini.h"
+#include "hw/hyperv/hvgdk.h"
+#include "linux/mshv.h"
+
+#include "qemu/accel.h"
+#include "qemu/guest-random.h"
+#include "accel/accel-ops.h"
+#include "accel/accel-cpu-ops.h"
+#include "system/cpus.h"
+#include "system/runstate.h"
+#include "system/accel-blocker.h"
+#include "system/address-spaces.h"
+#include "system/mshv.h"
+#include "system/mshv_int.h"
+#include "system/reset.h"
+#include "trace.h"
+#include <err.h>
+#include <stdint.h>
+#include <sys/ioctl.h>
+
+#define TYPE_MSHV_ACCEL ACCEL_CLASS_NAME("mshv")
+
+DECLARE_INSTANCE_CHECKER(MshvState, MSHV_STATE, TYPE_MSHV_ACCEL)
+
+bool mshv_allowed;
+
+MshvState *mshv_state;
+
+static int mshv_init(AccelState *as, MachineState *ms)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static void mshv_start_vcpu_thread(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static void mshv_cpu_synchronize_post_init(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static void mshv_cpu_synchronize_post_reset(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static void mshv_cpu_synchronize_pre_loadvm(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static void mshv_cpu_synchronize(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static bool mshv_cpus_are_resettable(void)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+static void mshv_accel_class_init(ObjectClass *oc, const void *data)
+{
+ AccelClass *ac = ACCEL_CLASS(oc);
+
+ ac->name = "MSHV";
+ ac->init_machine = mshv_init;
+ ac->allowed = &mshv_allowed;
+}
+
+static void mshv_accel_instance_init(Object *obj)
+{
+ MshvState *s = MSHV_STATE(obj);
+
+ s->vm = 0;
+}
+
+static const TypeInfo mshv_accel_type = {
+ .name = TYPE_MSHV_ACCEL,
+ .parent = TYPE_ACCEL,
+ .instance_init = mshv_accel_instance_init,
+ .class_init = mshv_accel_class_init,
+ .instance_size = sizeof(MshvState),
+};
+
+static void mshv_accel_ops_class_init(ObjectClass *oc, const void *data)
+{
+ AccelOpsClass *ops = ACCEL_OPS_CLASS(oc);
+
+ ops->create_vcpu_thread = mshv_start_vcpu_thread;
+ ops->synchronize_post_init = mshv_cpu_synchronize_post_init;
+ ops->synchronize_post_reset = mshv_cpu_synchronize_post_reset;
+ ops->synchronize_state = mshv_cpu_synchronize;
+ ops->synchronize_pre_loadvm = mshv_cpu_synchronize_pre_loadvm;
+ ops->cpus_are_resettable = mshv_cpus_are_resettable;
+ ops->handle_interrupt = generic_handle_interrupt;
+}
+
+static const TypeInfo mshv_accel_ops_type = {
+ .name = ACCEL_OPS_NAME("mshv"),
+ .parent = TYPE_ACCEL_OPS,
+ .class_init = mshv_accel_ops_class_init,
+ .abstract = true,
+};
+
+static void mshv_type_init(void)
+{
+ type_register_static(&mshv_accel_type);
+ type_register_static(&mshv_accel_ops_type);
+}
+
+type_init(mshv_type_init);
diff --git a/include/system/mshv.h b/include/system/mshv.h
index 2a504ed81f..434ea9682e 100644
--- a/include/system/mshv.h
+++ b/include/system/mshv.h
@@ -14,8 +14,17 @@
#ifndef QEMU_MSHV_H
#define QEMU_MSHV_H
+#include "qemu/osdep.h"
+#include "qemu/accel.h"
+#include "hw/hyperv/hyperv-proto.h"
+#include "hw/hyperv/hvhdk.h"
+#include "qapi/qapi-types-common.h"
+#include "system/memory.h"
+#include "accel/accel-ops.h"
+
#ifdef COMPILING_PER_TARGET
#ifdef CONFIG_MSHV
+#include <linux/mshv.h>
#define CONFIG_MSHV_IS_POSSIBLE
#endif
#else
@@ -30,6 +39,9 @@ extern bool mshv_allowed;
#endif
#define mshv_msi_via_irqfd_enabled() false
+typedef struct MshvState MshvState;
+extern MshvState *mshv_state;
+
/* interrupt */
int mshv_irqchip_add_msi_route(int vector, PCIDevice *dev);
int mshv_irqchip_update_msi_route(int virq, MSIMessage msg, PCIDevice *dev);
diff --git a/include/system/mshv_int.h b/include/system/mshv_int.h
new file mode 100644
index 0000000000..132491b599
--- /dev/null
+++ b/include/system/mshv_int.h
@@ -0,0 +1,41 @@
+/*
+ * QEMU MSHV support
+ *
+ * Copyright Microsoft, Corp. 2025
+ *
+ * Authors: Ziqiao Zhou <ziqiaozhou@microsoft.com>
+ * Magnus Kulke <magnuskulke@microsoft.com>
+ * Jinank Jain <jinankjain@microsoft.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ */
+
+#ifndef QEMU_MSHV_INT_H
+#define QEMU_MSHV_INT_H
+
+struct AccelCPUState {
+ int cpufd;
+ bool dirty;
+};
+
+typedef struct MshvMemoryListener {
+ MemoryListener listener;
+ int as_id;
+} MshvMemoryListener;
+
+typedef struct MshvAddressSpace {
+ MshvMemoryListener *ml;
+ AddressSpace *as;
+} MshvAddressSpace;
+
+struct MshvState {
+ AccelState parent_obj;
+ int vm;
+ MshvMemoryListener memory_listener;
+ /* number of listeners */
+ int nr_as;
+ MshvAddressSpace *as;
+};
+
+#endif
--
2.47.3

417
kvm-accel-mshv-Add-vCPU-creation-and-execution-loop.patch Normal file
View File

@ -0,0 +1,417 @@
From da65137c39b3662f0288b5149b14c82d2cfa4000 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:30 +0200
Subject: [PATCH 13/32] accel/mshv: Add vCPU creation and execution loop
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [11/30] e235ebda329666192a3bf95fb4fee018f5f5f10e
Create MSHV vCPUs using MSHV_CREATE_VP and initialize their state.
Register the MSHV CPU execution loop loop with the QEMU accelerator
framework to enable guest code execution.
The target/i386 functionality is still mostly stubbed out and will be
populated in a later commit in this series.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-11-magnuskulke@linux.microsoft.com
[Fix g_free/g_clear_pointer confusion; rename qemu_wait_io_event;
mshv.h/mshv_int.h split. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 4dc5d4257259764b6fcd035870517fc4140d8962)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/mshv/mshv-all.c | 186 +++++++++++++++++++++++++++++++++---
accel/mshv/trace-events | 2 +
include/system/mshv.h | 2 +-
include/system/mshv_int.h | 20 ++++
target/i386/mshv/mshv-cpu.c | 63 ++++++++++++
5 files changed, 260 insertions(+), 13 deletions(-)
diff --git a/accel/mshv/mshv-all.c b/accel/mshv/mshv-all.c
index 653195c57c..e02421d79d 100644
--- a/accel/mshv/mshv-all.c
+++ b/accel/mshv/mshv-all.c
@@ -393,6 +393,24 @@ int mshv_hvcall(int fd, const struct mshv_root_hvcall *args)
return ret;
}
+static int mshv_init_vcpu(CPUState *cpu)
+{
+ int vm_fd = mshv_state->vm;
+ uint8_t vp_index = cpu->cpu_index;
+ int ret;
+
+ mshv_arch_init_vcpu(cpu);
+ cpu->accel = g_new0(AccelCPUState, 1);
+
+ ret = mshv_create_vcpu(vm_fd, vp_index, &cpu->accel->cpufd);
+ if (ret < 0) {
+ return -1;
+ }
+
+ cpu->accel->dirty = true;
+
+ return 0;
+}
static int mshv_init(AccelState *as, MachineState *ms)
{
@@ -415,6 +433,8 @@ static int mshv_init(AccelState *as, MachineState *ms)
return -1;
}
+ mshv_init_mmio_emu();
+
mshv_init_msicontrol();
ret = create_vm(mshv_fd, &vm_fd);
@@ -444,40 +464,182 @@ static int mshv_init(AccelState *as, MachineState *ms)
return 0;
}
+static int mshv_destroy_vcpu(CPUState *cpu)
+{
+ int cpu_fd = mshv_vcpufd(cpu);
+ int vm_fd = mshv_state->vm;
+
+ mshv_remove_vcpu(vm_fd, cpu_fd);
+ mshv_vcpufd(cpu) = 0;
+
+ mshv_arch_destroy_vcpu(cpu);
+ g_clear_pointer(&cpu->accel, g_free);
+ return 0;
+}
+
+static int mshv_cpu_exec(CPUState *cpu)
+{
+ hv_message mshv_msg;
+ enum MshvVmExit exit_reason;
+ int ret = 0;
+
+ bql_unlock();
+ cpu_exec_start(cpu);
+
+ do {
+ if (cpu->accel->dirty) {
+ ret = mshv_arch_put_registers(cpu);
+ if (ret) {
+ error_report("Failed to put registers after init: %s",
+ strerror(-ret));
+ ret = -1;
+ break;
+ }
+ cpu->accel->dirty = false;
+ }
+
+ ret = mshv_run_vcpu(mshv_state->vm, cpu, &mshv_msg, &exit_reason);
+ if (ret < 0) {
+ error_report("Failed to run on vcpu %d", cpu->cpu_index);
+ abort();
+ }
+
+ switch (exit_reason) {
+ case MshvVmExitIgnore:
+ break;
+ default:
+ ret = EXCP_INTERRUPT;
+ break;
+ }
+ } while (ret == 0);
+
+ cpu_exec_end(cpu);
+ bql_lock();
+
+ if (ret < 0) {
+ cpu_dump_state(cpu, stderr, CPU_DUMP_CODE);
+ vm_stop(RUN_STATE_INTERNAL_ERROR);
+ }
+
+ return ret;
+}
+
+static void *mshv_vcpu_thread(void *arg)
+{
+ CPUState *cpu = arg;
+ int ret;
+
+ rcu_register_thread();
+
+ bql_lock();
+ qemu_thread_get_self(cpu->thread);
+ cpu->thread_id = qemu_get_thread_id();
+ current_cpu = cpu;
+ ret = mshv_init_vcpu(cpu);
+ if (ret < 0) {
+ error_report("Failed to init vcpu %d", cpu->cpu_index);
+ goto cleanup;
+ }
+
+ /* signal CPU creation */
+ cpu_thread_signal_created(cpu);
+ qemu_guest_random_seed_thread_part2(cpu->random_seed);
+
+ do {
+ qemu_process_cpu_events(cpu);
+ if (cpu_can_run(cpu)) {
+ mshv_cpu_exec(cpu);
+ }
+ } while (!cpu->unplug || cpu_can_run(cpu));
+
+ mshv_destroy_vcpu(cpu);
+cleanup:
+ cpu_thread_signal_destroyed(cpu);
+ bql_unlock();
+ rcu_unregister_thread();
+ return NULL;
+}
+
static void mshv_start_vcpu_thread(CPUState *cpu)
{
- error_report("unimplemented");
- abort();
+ char thread_name[VCPU_THREAD_NAME_SIZE];
+
+ cpu->thread = g_malloc0(sizeof(QemuThread));
+ cpu->halt_cond = g_malloc0(sizeof(QemuCond));
+
+ qemu_cond_init(cpu->halt_cond);
+
+ trace_mshv_start_vcpu_thread(thread_name, cpu->cpu_index);
+ qemu_thread_create(cpu->thread, thread_name, mshv_vcpu_thread, cpu,
+ QEMU_THREAD_JOINABLE);
+}
+
+static void do_mshv_cpu_synchronize_post_init(CPUState *cpu,
+ run_on_cpu_data arg)
+{
+ int ret = mshv_arch_put_registers(cpu);
+ if (ret < 0) {
+ error_report("Failed to put registers after init: %s", strerror(-ret));
+ abort();
+ }
+
+ cpu->accel->dirty = false;
}
static void mshv_cpu_synchronize_post_init(CPUState *cpu)
{
- error_report("unimplemented");
- abort();
+ run_on_cpu(cpu, do_mshv_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
}
static void mshv_cpu_synchronize_post_reset(CPUState *cpu)
{
- error_report("unimplemented");
- abort();
+ int ret = mshv_arch_put_registers(cpu);
+ if (ret) {
+ error_report("Failed to put registers after reset: %s",
+ strerror(-ret));
+ cpu_dump_state(cpu, stderr, CPU_DUMP_CODE);
+ vm_stop(RUN_STATE_INTERNAL_ERROR);
+ }
+ cpu->accel->dirty = false;
+}
+
+static void do_mshv_cpu_synchronize_pre_loadvm(CPUState *cpu,
+ run_on_cpu_data arg)
+{
+ cpu->accel->dirty = true;
}
static void mshv_cpu_synchronize_pre_loadvm(CPUState *cpu)
{
- error_report("unimplemented");
- abort();
+ run_on_cpu(cpu, do_mshv_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL);
+}
+
+static void do_mshv_cpu_synchronize(CPUState *cpu, run_on_cpu_data arg)
+{
+ if (!cpu->accel->dirty) {
+ int ret = mshv_load_regs(cpu);
+ if (ret < 0) {
+ error_report("Failed to load registers for vcpu %d",
+ cpu->cpu_index);
+
+ cpu_dump_state(cpu, stderr, CPU_DUMP_CODE);
+ vm_stop(RUN_STATE_INTERNAL_ERROR);
+ }
+
+ cpu->accel->dirty = true;
+ }
}
static void mshv_cpu_synchronize(CPUState *cpu)
{
- error_report("unimplemented");
- abort();
+ if (!cpu->accel->dirty) {
+ run_on_cpu(cpu, do_mshv_cpu_synchronize, RUN_ON_CPU_NULL);
+ }
}
static bool mshv_cpus_are_resettable(void)
{
- error_report("unimplemented");
- abort();
+ return false;
}
static void mshv_accel_class_init(ObjectClass *oc, const void *data)
diff --git a/accel/mshv/trace-events b/accel/mshv/trace-events
index 6130c4abf8..a4dffeb24a 100644
--- a/accel/mshv/trace-events
+++ b/accel/mshv/trace-events
@@ -3,6 +3,8 @@
#
# SPDX-License-Identifier: GPL-2.0-or-later
+mshv_start_vcpu_thread(const char* thread, uint32_t cpu) "thread=%s cpu_index=%d"
+
mshv_set_memory(bool add, uint64_t gpa, uint64_t size, uint64_t user_addr, bool readonly, int ret) "add=%d gpa=0x%" PRIx64 " size=0x%" PRIx64 " user=0x%" PRIx64 " readonly=%d result=%d"
mshv_mem_ioeventfd_add(uint64_t addr, uint32_t size, uint32_t data) "addr=0x%" PRIx64 " size=%d data=0x%x"
mshv_mem_ioeventfd_del(uint64_t addr, uint32_t size, uint32_t data) "addr=0x%" PRIx64 " size=%d data=0x%x"
diff --git a/include/system/mshv.h b/include/system/mshv.h
index 1011e81df4..bbc42f4dc3 100644
--- a/include/system/mshv.h
+++ b/include/system/mshv.h
@@ -41,7 +41,7 @@ extern bool mshv_allowed;
#define mshv_msi_via_irqfd_enabled() mshv_enabled()
#else /* CONFIG_MSHV_IS_POSSIBLE */
#define mshv_enabled() false
-#define mshv_msi_via_irqfd_enabled() false
+#define mshv_msi_via_irqfd_enabled() mshv_enabled()
#endif
typedef struct MshvState MshvState;
diff --git a/include/system/mshv_int.h b/include/system/mshv_int.h
index b36124a0ea..fb80f69772 100644
--- a/include/system/mshv_int.h
+++ b/include/system/mshv_int.h
@@ -14,6 +14,8 @@
#ifndef QEMU_MSHV_INT_H
#define QEMU_MSHV_INT_H
+typedef struct hyperv_message hv_message;
+
struct AccelCPUState {
int cpufd;
bool dirty;
@@ -44,6 +46,24 @@ typedef struct MshvMsiControl {
GHashTable *gsi_routes;
} MshvMsiControl;
+#define mshv_vcpufd(cpu) (cpu->accel->cpufd)
+
+/* cpu */
+typedef enum MshvVmExit {
+ MshvVmExitIgnore = 0,
+ MshvVmExitShutdown = 1,
+ MshvVmExitSpecial = 2,
+} MshvVmExit;
+
+void mshv_init_mmio_emu(void);
+int mshv_create_vcpu(int vm_fd, uint8_t vp_index, int *cpu_fd);
+void mshv_remove_vcpu(int vm_fd, int cpu_fd);
+int mshv_run_vcpu(int vm_fd, CPUState *cpu, hv_message *msg, MshvVmExit *exit);
+int mshv_load_regs(CPUState *cpu);
+int mshv_store_regs(CPUState *cpu);
+int mshv_arch_put_registers(const CPUState *cpu);
+void mshv_arch_init_vcpu(CPUState *cpu);
+void mshv_arch_destroy_vcpu(CPUState *cpu);
void mshv_arch_amend_proc_features(
union hv_partition_synthetic_processor_features *features);
int mshv_arch_post_init_vm(int vm_fd);
diff --git a/target/i386/mshv/mshv-cpu.c b/target/i386/mshv/mshv-cpu.c
index de0c26bc6c..02d71ebc14 100644
--- a/target/i386/mshv/mshv-cpu.c
+++ b/target/i386/mshv/mshv-cpu.c
@@ -22,15 +22,78 @@
#include "hw/hyperv/hvgdk_mini.h"
#include "hw/hyperv/hvhdk_mini.h"
+#include "cpu.h"
+#include "emulate/x86_decode.h"
+#include "emulate/x86_emu.h"
+#include "emulate/x86_flags.h"
+
#include "trace-accel_mshv.h"
#include "trace.h"
+int mshv_store_regs(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+int mshv_load_regs(CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+int mshv_arch_put_registers(const CPUState *cpu)
+{
+ error_report("unimplemented");
+ abort();
+}
+
void mshv_arch_amend_proc_features(
union hv_partition_synthetic_processor_features *features)
{
features->access_guest_idle_reg = 1;
}
+int mshv_run_vcpu(int vm_fd, CPUState *cpu, hv_message *msg, MshvVmExit *exit)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+void mshv_remove_vcpu(int vm_fd, int cpu_fd)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+int mshv_create_vcpu(int vm_fd, uint8_t vp_index, int *cpu_fd)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+void mshv_init_mmio_emu(void)
+{
+ error_report("unimplemented");
+ abort();
+}
+
+void mshv_arch_init_vcpu(CPUState *cpu)
+{
+ X86CPU *x86_cpu = X86_CPU(cpu);
+ CPUX86State *env = &x86_cpu->env;
+
+ env->emu_mmio_buf = g_new(char, 4096);
+}
+
+void mshv_arch_destroy_vcpu(CPUState *cpu)
+{
+ X86CPU *x86_cpu = X86_CPU(cpu);
+ CPUX86State *env = &x86_cpu->env;
+
+ g_clear_pointer(&env->emu_mmio_buf, g_free);
+}
+
/*
* Default Microsoft Hypervisor behavior for unimplemented MSR is to send a
* fault to the guest if it tries to access it. It is possible to override
--
2.47.3

75
kvm-accel-mshv-Add-vCPU-signal-handling.patch Normal file
View File

@ -0,0 +1,75 @@
From 38112aed4e07ec8f43b552f887bc2077e443ba4b Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:31 +0200
Subject: [PATCH 14/32] accel/mshv: Add vCPU signal handling
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [12/30] c3c9c5d9ad4d335a12c9d54499e4a2902b523441
Implement signal handling for MSHV vCPUs to support asynchronous
interrupts from the main thread.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-12-magnuskulke@linux.microsoft.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 575df4df54e060661db45e6f80293b29ea8901c1)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/mshv/mshv-all.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/accel/mshv/mshv-all.c b/accel/mshv/mshv-all.c
index e02421d79d..fa1f8f35bd 100644
--- a/accel/mshv/mshv-all.c
+++ b/accel/mshv/mshv-all.c
@@ -524,6 +524,35 @@ static int mshv_cpu_exec(CPUState *cpu)
return ret;
}
+/*
+ * The signal handler is triggered when QEMU's main thread receives a SIG_IPI
+ * (SIGUSR1). This signal causes the current CPU thread to be kicked, forcing a
+ * VM exit on the CPU. The VM exit generates an exit reason that breaks the loop
+ * (see mshv_cpu_exec). If the exit is due to a Ctrl+A+x command, the system
+ * will shut down. For other cases, the system will continue running.
+ */
+static void sa_ipi_handler(int sig)
+{
+ /* TODO: call IOCTL to set_immediate_exit, once implemented. */
+
+ qemu_cpu_kick_self();
+}
+
+static void init_signal(CPUState *cpu)
+{
+ /* init cpu signals */
+ struct sigaction sigact;
+ sigset_t set;
+
+ memset(&sigact, 0, sizeof(sigact));
+ sigact.sa_handler = sa_ipi_handler;
+ sigaction(SIG_IPI, &sigact, NULL);
+
+ pthread_sigmask(SIG_BLOCK, NULL, &set);
+ sigdelset(&set, SIG_IPI);
+ pthread_sigmask(SIG_SETMASK, &set, NULL);
+}
+
static void *mshv_vcpu_thread(void *arg)
{
CPUState *cpu = arg;
@@ -540,6 +569,7 @@ static void *mshv_vcpu_thread(void *arg)
error_report("Failed to init vcpu %d", cpu->cpu_index);
goto cleanup;
}
+ init_signal(cpu);
/* signal CPU creation */
cpu_thread_signal_created(cpu);
--
2.47.3

695
kvm-accel-mshv-Handle-overlapping-mem-mappings.patch Normal file
View File

@ -0,0 +1,695 @@
From c6e4e7657d407507a5e8cc6daadc6f309e8a42e9 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:43 +0200
Subject: [PATCH 26/32] accel/mshv: Handle overlapping mem mappings
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [24/30] abe9045eadeabccae811682dccd8679f41c32cc0
QEMU maps certain regions into the guest multiple times, as seen in the
trace below. Currently the MSHV kernel driver will reject those
mappings. To workaround this, a record is kept (a static global list of
"slots", inspired by what the HVF accelerator has implemented). An
overlapping region is not registered at the hypervisor, and marked as
mapped=false. If there is an UNMAPPED_GPA exit, we can look for a slot
that is unmapped and would cover the GPA. In this case we map out the
conflicting slot and map in the requested region.
mshv_set_phys_mem add=1 name=pc.bios
mshv_map_memory => u_a=7ffff4e00000 gpa=00fffc0000 size=00040000
mshv_set_phys_mem add=1 name=ioapic
mshv_set_phys_mem add=1 name=hpet
mshv_set_phys_mem add=0 name=pc.ram
mshv_unmap_memory u_a=7fff67e00000 gpa=0000000000 size=80000000
mshv_set_phys_mem add=1 name=pc.ram
mshv_map_memory u_a=7fff67e00000 gpa=0000000000 size=000c0000
mshv_set_phys_mem add=1 name=pc.rom
mshv_map_memory u_a=7ffff4c00000 gpa=00000c0000 size=00020000
mshv_set_phys_mem add=1 name=pc.bios
mshv_remap_attempt => u_a=7ffff4e20000 gpa=00000e0000 size=00020000
The mapping table is guarded by a mutex for concurrent modification and
RCU mechanisms for concurrent reads. Writes occur rarely, but we'll have
to verify whether an unmapped region exist for each UNMAPPED_GPA exit,
which happens frequently.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-24-magnuskulke@linux.microsoft.com
[Fix format strings for trace-events; mshv.h/mshv_int.h split. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit efc4093358511a58846a409b965213aa1bb9f31a)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/mshv/mem.c | 406 +++++++++++++++++++++++++++++++++---
accel/mshv/mshv-all.c | 2 +
accel/mshv/trace-events | 5 +
include/system/mshv_int.h | 22 +-
target/i386/mshv/mshv-cpu.c | 43 ++++
5 files changed, 448 insertions(+), 30 deletions(-)
diff --git a/accel/mshv/mem.c b/accel/mshv/mem.c
index e55c38d4db..0e2164af3e 100644
--- a/accel/mshv/mem.c
+++ b/accel/mshv/mem.c
@@ -11,7 +11,9 @@
*/
#include "qemu/osdep.h"
+#include "qemu/lockable.h"
#include "qemu/error-report.h"
+#include "qemu/rcu.h"
#include "linux/mshv.h"
#include "system/address-spaces.h"
#include "system/mshv.h"
@@ -20,6 +22,137 @@
#include <sys/ioctl.h>
#include "trace.h"
+typedef struct SlotsRCUReclaim {
+ struct rcu_head rcu;
+ GList *old_head;
+ MshvMemorySlot *removed_slot;
+} SlotsRCUReclaim;
+
+static void rcu_reclaim_slotlist(struct rcu_head *rcu)
+{
+ SlotsRCUReclaim *r = container_of(rcu, SlotsRCUReclaim, rcu);
+ g_list_free(r->old_head);
+ g_free(r->removed_slot);
+ g_free(r);
+}
+
+static void publish_slots(GList *new_head, GList *old_head,
+ MshvMemorySlot *removed_slot)
+{
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ assert(manager);
+ qatomic_store_release(&manager->slots, new_head);
+
+ SlotsRCUReclaim *r = g_new(SlotsRCUReclaim, 1);
+ r->old_head = old_head;
+ r->removed_slot = removed_slot;
+
+ call_rcu1(&r->rcu, rcu_reclaim_slotlist);
+}
+
+/* Needs to be called with mshv_state->msm.mutex held */
+static int remove_slot(MshvMemorySlot *slot)
+{
+ GList *old_head, *new_head;
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ assert(manager);
+ old_head = qatomic_load_acquire(&manager->slots);
+
+ if (!g_list_find(old_head, slot)) {
+ error_report("slot requested for removal not found");
+ return -1;
+ }
+
+ new_head = g_list_copy(old_head);
+ new_head = g_list_remove(new_head, slot);
+ manager->n_slots--;
+
+ publish_slots(new_head, old_head, slot);
+
+ return 0;
+}
+
+/* Needs to be called with mshv_state->msm.mutex held */
+static MshvMemorySlot *append_slot(uint64_t gpa, uint64_t userspace_addr,
+ uint64_t size, bool readonly)
+{
+ GList *old_head, *new_head;
+ MshvMemorySlot *slot;
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ assert(manager);
+
+ old_head = qatomic_load_acquire(&manager->slots);
+
+ if (manager->n_slots >= MSHV_MAX_MEM_SLOTS) {
+ error_report("no free memory slots available");
+ return NULL;
+ }
+
+ slot = g_new0(MshvMemorySlot, 1);
+ slot->guest_phys_addr = gpa;
+ slot->userspace_addr = userspace_addr;
+ slot->memory_size = size;
+ slot->readonly = readonly;
+
+ new_head = g_list_copy(old_head);
+ new_head = g_list_append(new_head, slot);
+ manager->n_slots++;
+
+ publish_slots(new_head, old_head, NULL);
+
+ return slot;
+}
+
+static int slot_overlaps(const MshvMemorySlot *slot1,
+ const MshvMemorySlot *slot2)
+{
+ uint64_t start_1 = slot1->userspace_addr,
+ start_2 = slot2->userspace_addr;
+ size_t len_1 = slot1->memory_size,
+ len_2 = slot2->memory_size;
+
+ if (slot1 == slot2) {
+ return -1;
+ }
+
+ return ranges_overlap(start_1, len_1, start_2, len_2) ? 0 : -1;
+}
+
+static bool is_mapped(MshvMemorySlot *slot)
+{
+ /* Subsequent reads of mapped field see a fully-initialized slot */
+ return qatomic_load_acquire(&slot->mapped);
+}
+
+/*
+ * Find slot that is:
+ * - overlapping in userspace
+ * - currently mapped in the guest
+ *
+ * Needs to be called with mshv_state->msm.mutex or RCU read lock held.
+ */
+static MshvMemorySlot *find_overlap_mem_slot(GList *head, MshvMemorySlot *slot)
+{
+ GList *found;
+ MshvMemorySlot *overlap_slot;
+
+ found = g_list_find_custom(head, slot, (GCompareFunc) slot_overlaps);
+
+ if (!found) {
+ return NULL;
+ }
+
+ overlap_slot = found->data;
+ if (!overlap_slot || !is_mapped(overlap_slot)) {
+ return NULL;
+ }
+
+ return overlap_slot;
+}
+
static int set_guest_memory(int vm_fd,
const struct mshv_user_mem_region *region)
{
@@ -27,38 +160,169 @@ static int set_guest_memory(int vm_fd,
ret = ioctl(vm_fd, MSHV_SET_GUEST_MEMORY, region);
if (ret < 0) {
- error_report("failed to set guest memory");
- return -errno;
+ error_report("failed to set guest memory: %s", strerror(errno));
+ return -1;
}
return 0;
}
-static int map_or_unmap(int vm_fd, const MshvMemoryRegion *mr, bool map)
+static int map_or_unmap(int vm_fd, const MshvMemorySlot *slot, bool map)
{
struct mshv_user_mem_region region = {0};
- region.guest_pfn = mr->guest_phys_addr >> MSHV_PAGE_SHIFT;
- region.size = mr->memory_size;
- region.userspace_addr = mr->userspace_addr;
+ region.guest_pfn = slot->guest_phys_addr >> MSHV_PAGE_SHIFT;
+ region.size = slot->memory_size;
+ region.userspace_addr = slot->userspace_addr;
if (!map) {
region.flags |= (1 << MSHV_SET_MEM_BIT_UNMAP);
- trace_mshv_unmap_memory(mr->userspace_addr, mr->guest_phys_addr,
- mr->memory_size);
+ trace_mshv_unmap_memory(slot->userspace_addr, slot->guest_phys_addr,
+ slot->memory_size);
return set_guest_memory(vm_fd, &region);
}
region.flags = BIT(MSHV_SET_MEM_BIT_EXECUTABLE);
- if (!mr->readonly) {
+ if (!slot->readonly) {
region.flags |= BIT(MSHV_SET_MEM_BIT_WRITABLE);
}
- trace_mshv_map_memory(mr->userspace_addr, mr->guest_phys_addr,
- mr->memory_size);
+ trace_mshv_map_memory(slot->userspace_addr, slot->guest_phys_addr,
+ slot->memory_size);
return set_guest_memory(vm_fd, &region);
}
+static int slot_matches_region(const MshvMemorySlot *slot1,
+ const MshvMemorySlot *slot2)
+{
+ return (slot1->guest_phys_addr == slot2->guest_phys_addr &&
+ slot1->userspace_addr == slot2->userspace_addr &&
+ slot1->memory_size == slot2->memory_size) ? 0 : -1;
+}
+
+/* Needs to be called with mshv_state->msm.mutex held */
+static MshvMemorySlot *find_mem_slot_by_region(uint64_t gpa, uint64_t size,
+ uint64_t userspace_addr)
+{
+ MshvMemorySlot ref_slot = {
+ .guest_phys_addr = gpa,
+ .userspace_addr = userspace_addr,
+ .memory_size = size,
+ };
+ GList *found;
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ assert(manager);
+ found = g_list_find_custom(manager->slots, &ref_slot,
+ (GCompareFunc) slot_matches_region);
+
+ return found ? found->data : NULL;
+}
+
+static int slot_covers_gpa(const MshvMemorySlot *slot, uint64_t *gpa_p)
+{
+ uint64_t gpa_offset, gpa = *gpa_p;
+
+ gpa_offset = gpa - slot->guest_phys_addr;
+ return (slot->guest_phys_addr <= gpa && gpa_offset < slot->memory_size)
+ ? 0 : -1;
+}
+
+/* Needs to be called with mshv_state->msm.mutex or RCU read lock held */
+static MshvMemorySlot *find_mem_slot_by_gpa(GList *head, uint64_t gpa)
+{
+ GList *found;
+ MshvMemorySlot *slot;
+
+ trace_mshv_find_slot_by_gpa(gpa);
+
+ found = g_list_find_custom(head, &gpa, (GCompareFunc) slot_covers_gpa);
+ if (found) {
+ slot = found->data;
+ trace_mshv_found_slot(slot->userspace_addr, slot->guest_phys_addr,
+ slot->memory_size);
+ return slot;
+ }
+
+ return NULL;
+}
+
+/* Needs to be called with mshv_state->msm.mutex held */
+static void set_mapped(MshvMemorySlot *slot, bool mapped)
+{
+ /* prior writes to mapped field becomes visible before readers see slot */
+ qatomic_store_release(&slot->mapped, mapped);
+}
+
+MshvRemapResult mshv_remap_overlap_region(int vm_fd, uint64_t gpa)
+{
+ MshvMemorySlot *gpa_slot, *overlap_slot;
+ GList *head;
+ int ret;
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ /* fast path, called often by unmapped_gpa vm exit */
+ WITH_RCU_READ_LOCK_GUARD() {
+ assert(manager);
+ head = qatomic_load_acquire(&manager->slots);
+ /* return early if no slot is found */
+ gpa_slot = find_mem_slot_by_gpa(head, gpa);
+ if (gpa_slot == NULL) {
+ return MshvRemapNoMapping;
+ }
+
+ /* return early if no overlapping slot is found */
+ overlap_slot = find_overlap_mem_slot(head, gpa_slot);
+ if (overlap_slot == NULL) {
+ return MshvRemapNoOverlap;
+ }
+ }
+
+ /*
+ * We'll modify the mapping list, so we need to upgrade to mutex and
+ * recheck.
+ */
+ assert(manager);
+ QEMU_LOCK_GUARD(&manager->mutex);
+
+ /* return early if no slot is found */
+ gpa_slot = find_mem_slot_by_gpa(manager->slots, gpa);
+ if (gpa_slot == NULL) {
+ return MshvRemapNoMapping;
+ }
+
+ /* return early if no overlapping slot is found */
+ overlap_slot = find_overlap_mem_slot(manager->slots, gpa_slot);
+ if (overlap_slot == NULL) {
+ return MshvRemapNoOverlap;
+ }
+
+ /* unmap overlapping slot */
+ ret = map_or_unmap(vm_fd, overlap_slot, false);
+ if (ret < 0) {
+ error_report("failed to unmap overlap region");
+ abort();
+ }
+ set_mapped(overlap_slot, false);
+ warn_report("mapped out userspace_addr=0x%016lx gpa=0x%010lx size=0x%lx",
+ overlap_slot->userspace_addr,
+ overlap_slot->guest_phys_addr,
+ overlap_slot->memory_size);
+
+ /* map region for gpa */
+ ret = map_or_unmap(vm_fd, gpa_slot, true);
+ if (ret < 0) {
+ error_report("failed to map new region");
+ abort();
+ }
+ set_mapped(gpa_slot, true);
+ warn_report("mapped in userspace_addr=0x%016lx gpa=0x%010lx size=0x%lx",
+ gpa_slot->userspace_addr, gpa_slot->guest_phys_addr,
+ gpa_slot->memory_size);
+
+ return MshvRemapOk;
+}
+
static int handle_unmapped_mmio_region_read(uint64_t gpa, uint64_t size,
uint8_t *data)
{
@@ -124,20 +388,97 @@ int mshv_guest_mem_write(uint64_t gpa, const uint8_t *data, uintptr_t size,
return -1;
}
-static int set_memory(const MshvMemoryRegion *mshv_mr, bool add)
+static int tracked_unmap(int vm_fd, uint64_t gpa, uint64_t size,
+ uint64_t userspace_addr)
{
- int ret = 0;
+ int ret;
+ MshvMemorySlot *slot;
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ assert(manager);
+
+ QEMU_LOCK_GUARD(&manager->mutex);
+
+ slot = find_mem_slot_by_region(gpa, size, userspace_addr);
+ if (!slot) {
+ trace_mshv_skip_unset_mem(userspace_addr, gpa, size);
+ /* no work to do */
+ return 0;
+ }
+
+ if (!is_mapped(slot)) {
+ /* remove slot, no need to unmap */
+ return remove_slot(slot);
+ }
- if (!mshv_mr) {
- error_report("Invalid mshv_mr");
+ ret = map_or_unmap(vm_fd, slot, false);
+ if (ret < 0) {
+ error_report("failed to unmap memory region");
+ return ret;
+ }
+ return remove_slot(slot);
+}
+
+static int tracked_map(int vm_fd, uint64_t gpa, uint64_t size, bool readonly,
+ uint64_t userspace_addr)
+{
+ MshvMemorySlot *slot, *overlap_slot;
+ int ret;
+ MshvMemorySlotManager *manager = &mshv_state->msm;
+
+ assert(manager);
+
+ QEMU_LOCK_GUARD(&manager->mutex);
+
+ slot = find_mem_slot_by_region(gpa, size, userspace_addr);
+ if (slot) {
+ error_report("memory region already mapped at gpa=0x%lx, "
+ "userspace_addr=0x%lx, size=0x%lx",
+ slot->guest_phys_addr, slot->userspace_addr,
+ slot->memory_size);
return -1;
}
- trace_mshv_set_memory(add, mshv_mr->guest_phys_addr,
- mshv_mr->memory_size,
- mshv_mr->userspace_addr, mshv_mr->readonly,
- ret);
- return map_or_unmap(mshv_state->vm, mshv_mr, add);
+ slot = append_slot(gpa, userspace_addr, size, readonly);
+
+ overlap_slot = find_overlap_mem_slot(manager->slots, slot);
+ if (overlap_slot) {
+ trace_mshv_remap_attempt(slot->userspace_addr,
+ slot->guest_phys_addr,
+ slot->memory_size);
+ warn_report("attempt to map region [0x%lx-0x%lx], while "
+ "[0x%lx-0x%lx] is already mapped in the guest",
+ userspace_addr, userspace_addr + size - 1,
+ overlap_slot->userspace_addr,
+ overlap_slot->userspace_addr +
+ overlap_slot->memory_size - 1);
+
+ /* do not register mem slot in hv, but record for later swap-in */
+ set_mapped(slot, false);
+
+ return 0;
+ }
+
+ ret = map_or_unmap(vm_fd, slot, true);
+ if (ret < 0) {
+ error_report("failed to map memory region");
+ return -1;
+ }
+ set_mapped(slot, true);
+
+ return 0;
+}
+
+static int set_memory(uint64_t gpa, uint64_t size, bool readonly,
+ uint64_t userspace_addr, bool add)
+{
+ int vm_fd = mshv_state->vm;
+
+ if (add) {
+ return tracked_map(vm_fd, gpa, size, readonly, userspace_addr);
+ }
+
+ return tracked_unmap(vm_fd, gpa, size, userspace_addr);
}
/*
@@ -173,7 +514,9 @@ void mshv_set_phys_mem(MshvMemoryListener *mml, MemoryRegionSection *section,
bool writable = !area->readonly && !area->rom_device;
hwaddr start_addr, mr_offset, size;
void *ram;
- MshvMemoryRegion mshv_mr = {0};
+
+ size = align_section(section, &start_addr);
+ trace_mshv_set_phys_mem(add, section->mr->name, start_addr);
size = align_section(section, &start_addr);
trace_mshv_set_phys_mem(add, section->mr->name, start_addr);
@@ -200,14 +543,21 @@ void mshv_set_phys_mem(MshvMemoryListener *mml, MemoryRegionSection *section,
ram = memory_region_get_ram_ptr(area) + mr_offset;
- mshv_mr.guest_phys_addr = start_addr;
- mshv_mr.memory_size = size;
- mshv_mr.readonly = !writable;
- mshv_mr.userspace_addr = (uint64_t)ram;
-
- ret = set_memory(&mshv_mr, add);
+ ret = set_memory(start_addr, size, !writable, (uint64_t)ram, add);
if (ret < 0) {
- error_report("Failed to set memory region");
+ error_report("failed to set memory region");
abort();
}
}
+
+void mshv_init_memory_slot_manager(MshvState *mshv_state)
+{
+ MshvMemorySlotManager *manager;
+
+ assert(mshv_state);
+ manager = &mshv_state->msm;
+
+ manager->n_slots = 0;
+ manager->slots = NULL;
+ qemu_mutex_init(&manager->mutex);
+}
diff --git a/accel/mshv/mshv-all.c b/accel/mshv/mshv-all.c
index fa1f8f35bd..5edfcbad9d 100644
--- a/accel/mshv/mshv-all.c
+++ b/accel/mshv/mshv-all.c
@@ -437,6 +437,8 @@ static int mshv_init(AccelState *as, MachineState *ms)
mshv_init_msicontrol();
+ mshv_init_memory_slot_manager(s);
+
ret = create_vm(mshv_fd, &vm_fd);
if (ret < 0) {
close(mshv_fd);
diff --git a/accel/mshv/trace-events b/accel/mshv/trace-events
index a4dffeb24a..36f0d59b38 100644
--- a/accel/mshv/trace-events
+++ b/accel/mshv/trace-events
@@ -26,3 +26,8 @@ mshv_map_memory(uint64_t userspace_addr, uint64_t gpa, uint64_t size) "\tu_a=0x%
mshv_unmap_memory(uint64_t userspace_addr, uint64_t gpa, uint64_t size) "\tu_a=0x%" PRIx64 " gpa=0x%010" PRIx64 " size=0x%08" PRIx64
mshv_set_phys_mem(bool add, const char *name, uint64_t gpa) "\tadd=%d name=%s gpa=0x%010" PRIx64
mshv_handle_mmio(uint64_t gva, uint64_t gpa, uint64_t size, uint8_t access_type) "\tgva=0x%" PRIx64 " gpa=0x%010" PRIx64 " size=0x%" PRIx64 " access_type=%d"
+
+mshv_found_slot(uint64_t userspace_addr, uint64_t gpa, uint64_t size) "\tu_a=0x%" PRIx64 " gpa=0x%010" PRIx64 " size=0x%08" PRIx64
+mshv_skip_unset_mem(uint64_t userspace_addr, uint64_t gpa, uint64_t size) "\tu_a=0x%" PRIx64 " gpa=0x%010" PRIx64 " size=0x%08" PRIx64
+mshv_remap_attempt(uint64_t userspace_addr, uint64_t gpa, uint64_t size) "\tu_a=0x%" PRIx64 " gpa=0x%010" PRIx64 " size=0x%08" PRIx64
+mshv_find_slot_by_gpa(uint64_t gpa) "\tgpa=0x%010" PRIx64
diff --git a/include/system/mshv_int.h b/include/system/mshv_int.h
index b29d39911d..6350c69e9d 100644
--- a/include/system/mshv_int.h
+++ b/include/system/mshv_int.h
@@ -16,6 +16,8 @@
#define MSHV_MSR_ENTRIES_COUNT 64
+#define MSHV_MAX_MEM_SLOTS 32
+
typedef struct hyperv_message hv_message;
struct AccelCPUState {
@@ -33,6 +35,12 @@ typedef struct MshvAddressSpace {
AddressSpace *as;
} MshvAddressSpace;
+typedef struct MshvMemorySlotManager {
+ size_t n_slots;
+ GList *slots;
+ QemuMutex mutex;
+} MshvMemorySlotManager;
+
struct MshvState {
AccelState parent_obj;
int vm;
@@ -41,6 +49,7 @@ struct MshvState {
int nr_as;
MshvAddressSpace *as;
int fd;
+ MshvMemorySlotManager msm;
};
typedef struct MshvMsiControl {
@@ -71,6 +80,12 @@ typedef enum MshvVmExit {
MshvVmExitSpecial = 2,
} MshvVmExit;
+typedef enum MshvRemapResult {
+ MshvRemapOk = 0,
+ MshvRemapNoMapping = 1,
+ MshvRemapNoOverlap = 2,
+} MshvRemapResult;
+
void mshv_init_mmio_emu(void);
int mshv_create_vcpu(int vm_fd, uint8_t vp_index, int *cpu_fd);
void mshv_remove_vcpu(int vm_fd, int cpu_fd);
@@ -94,19 +109,22 @@ int mshv_hvcall(int fd, const struct mshv_root_hvcall *args);
#endif
/* memory */
-typedef struct MshvMemoryRegion {
+typedef struct MshvMemorySlot {
uint64_t guest_phys_addr;
uint64_t memory_size;
uint64_t userspace_addr;
bool readonly;
-} MshvMemoryRegion;
+ bool mapped;
+} MshvMemorySlot;
+MshvRemapResult mshv_remap_overlap_region(int vm_fd, uint64_t gpa);
int mshv_guest_mem_read(uint64_t gpa, uint8_t *data, uintptr_t size,
bool is_secure_mode, bool instruction_fetch);
int mshv_guest_mem_write(uint64_t gpa, const uint8_t *data, uintptr_t size,
bool is_secure_mode);
void mshv_set_phys_mem(MshvMemoryListener *mml, MemoryRegionSection *section,
bool add);
+void mshv_init_memory_slot_manager(MshvState *mshv_state);
/* msr */
typedef struct MshvMsrEntry {
diff --git a/target/i386/mshv/mshv-cpu.c b/target/i386/mshv/mshv-cpu.c
index 7edc032cea..de87142bff 100644
--- a/target/i386/mshv/mshv-cpu.c
+++ b/target/i386/mshv/mshv-cpu.c
@@ -1170,6 +1170,43 @@ static int handle_mmio(CPUState *cpu, const struct hyperv_message *msg,
return 0;
}
+static int handle_unmapped_mem(int vm_fd, CPUState *cpu,
+ const struct hyperv_message *msg,
+ MshvVmExit *exit_reason)
+{
+ struct hv_x64_memory_intercept_message info = { 0 };
+ uint64_t gpa;
+ int ret;
+ enum MshvRemapResult remap_result;
+
+ ret = set_memory_info(msg, &info);
+ if (ret < 0) {
+ error_report("failed to convert message to memory info");
+ return -1;
+ }
+
+ gpa = info.guest_physical_address;
+
+ /* attempt to remap the region, in case of overlapping userspace mappings */
+ remap_result = mshv_remap_overlap_region(vm_fd, gpa);
+ *exit_reason = MshvVmExitIgnore;
+
+ switch (remap_result) {
+ case MshvRemapNoMapping:
+ /* if we didn't find a mapping, it is probably mmio */
+ return handle_mmio(cpu, msg, exit_reason);
+ case MshvRemapOk:
+ break;
+ case MshvRemapNoOverlap:
+ /* This should not happen, but we are forgiving it */
+ warn_report("found no overlap for unmapped region");
+ *exit_reason = MshvVmExitSpecial;
+ break;
+ }
+
+ return 0;
+}
+
static int set_ioport_info(const struct hyperv_message *msg,
hv_x64_io_port_intercept_message *info)
{
@@ -1507,6 +1544,12 @@ int mshv_run_vcpu(int vm_fd, CPUState *cpu, hv_message *msg, MshvVmExit *exit)
case HVMSG_UNRECOVERABLE_EXCEPTION:
return MshvVmExitShutdown;
case HVMSG_UNMAPPED_GPA:
+ ret = handle_unmapped_mem(vm_fd, cpu, msg, &exit_reason);
+ if (ret < 0) {
+ error_report("failed to handle unmapped memory");
+ return -1;
+ }
+ return exit_reason;
case HVMSG_GPA_INTERCEPT:
ret = handle_mmio(cpu, msg, &exit_reason);
if (ret < 0) {
--
2.47.3

1302
kvm-accel-mshv-Initialize-VM-partition.patch Normal file
View File

File diff suppressed because it is too large Load Diff

172
kvm-accel-mshv-Register-memory-region-listeners.patch Normal file
View File

@ -0,0 +1,172 @@
From 1c84d5e352e60196218f657292e7f26226ab9647 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:28 +0200
Subject: [PATCH 10/32] accel/mshv: Register memory region listeners
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [8/30] ecd0d05d8f04c400ad1d9c428f89b23b12889968
Add memory listener hooks for the MSHV accelerator to track guest
memory regions. This enables the backend to respond to region
additions, removals and will be used to manage guest memory mappings
inside the hypervisor.
Actually registering physical memory in the hypervisor is still stubbed
out.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-9-magnuskulke@linux.microsoft.com
[mshv.h/mshv_int.h split. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 5006ea1344d134356a9b2e1afd521cf8df0c6a85)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/mshv/mem.c | 25 +++++++++++++++
accel/mshv/meson.build | 1 +
accel/mshv/mshv-all.c | 67 +++++++++++++++++++++++++++++++++++++--
include/system/mshv_int.h | 4 +++
4 files changed, 95 insertions(+), 2 deletions(-)
create mode 100644 accel/mshv/mem.c
diff --git a/accel/mshv/mem.c b/accel/mshv/mem.c
new file mode 100644
index 0000000000..9889918c31
--- /dev/null
+++ b/accel/mshv/mem.c
@@ -0,0 +1,25 @@
+/*
+ * QEMU MSHV support
+ *
+ * Copyright Microsoft, Corp. 2025
+ *
+ * Authors:
+ * Magnus Kulke <magnuskulke@microsoft.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/error-report.h"
+#include "system/address-spaces.h"
+#include "system/mshv.h"
+#include "system/mshv_int.h"
+
+void mshv_set_phys_mem(MshvMemoryListener *mml, MemoryRegionSection *section,
+ bool add)
+{
+ error_report("unimplemented");
+ abort();
+}
+
diff --git a/accel/mshv/meson.build b/accel/mshv/meson.build
index 4c03ac7921..8a6beb3fb1 100644
--- a/accel/mshv/meson.build
+++ b/accel/mshv/meson.build
@@ -1,5 +1,6 @@
mshv_ss = ss.source_set()
mshv_ss.add(if_true: files(
+ 'mem.c',
'mshv-all.c'
))
diff --git a/accel/mshv/mshv-all.c b/accel/mshv/mshv-all.c
index ae12f0f58b..a684a36677 100644
--- a/accel/mshv/mshv-all.c
+++ b/accel/mshv/mshv-all.c
@@ -49,10 +49,73 @@ bool mshv_allowed;
MshvState *mshv_state;
+static void mem_region_add(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ MshvMemoryListener *mml;
+ mml = container_of(listener, MshvMemoryListener, listener);
+ memory_region_ref(section->mr);
+ mshv_set_phys_mem(mml, section, true);
+}
+
+static void mem_region_del(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ MshvMemoryListener *mml;
+ mml = container_of(listener, MshvMemoryListener, listener);
+ mshv_set_phys_mem(mml, section, false);
+ memory_region_unref(section->mr);
+}
+
+static MemoryListener mshv_memory_listener = {
+ .name = "mshv",
+ .priority = MEMORY_LISTENER_PRIORITY_ACCEL,
+ .region_add = mem_region_add,
+ .region_del = mem_region_del,
+};
+
+static MemoryListener mshv_io_listener = {
+ .name = "mshv", .priority = MEMORY_LISTENER_PRIORITY_DEV_BACKEND,
+ /* MSHV does not support PIO eventfd */
+};
+
+static void register_mshv_memory_listener(MshvState *s, MshvMemoryListener *mml,
+ AddressSpace *as, int as_id,
+ const char *name)
+{
+ int i;
+
+ mml->listener = mshv_memory_listener;
+ mml->listener.name = name;
+ memory_listener_register(&mml->listener, as);
+ for (i = 0; i < s->nr_as; ++i) {
+ if (!s->as[i].as) {
+ s->as[i].as = as;
+ s->as[i].ml = mml;
+ break;
+ }
+ }
+}
+
static int mshv_init(AccelState *as, MachineState *ms)
{
- error_report("unimplemented");
- abort();
+ MshvState *s;
+ s = MSHV_STATE(as);
+
+ accel_blocker_init();
+
+ s->vm = 0;
+
+ s->nr_as = 1;
+ s->as = g_new0(MshvAddressSpace, s->nr_as);
+
+ mshv_state = s;
+
+ register_mshv_memory_listener(s, &s->memory_listener, &address_space_memory,
+ 0, "mshv-memory");
+ memory_listener_register(&mshv_io_listener, &address_space_io);
+
+ return 0;
}
static void mshv_start_vcpu_thread(CPUState *cpu)
diff --git a/include/system/mshv_int.h b/include/system/mshv_int.h
index 132491b599..cfa177ff72 100644
--- a/include/system/mshv_int.h
+++ b/include/system/mshv_int.h
@@ -38,4 +38,8 @@ struct MshvState {
MshvAddressSpace *as;
};
+/* memory */
+void mshv_set_phys_mem(MshvMemoryListener *mml, MemoryRegionSection *section,
+ bool add);
+
#endif
--
2.47.3

39
kvm-accel-mshv-initialize-thread-name.patch Normal file
View File

@ -0,0 +1,39 @@
From f102098ed05c9157f2cffb4ffef8324c4f83f005 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 22 Oct 2025 14:52:48 +0200
Subject: [PATCH 31/32] accel/mshv: initialize thread name
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [29/30] 3e7286070c5ce162001fd407ebb1fa3920e300fa
The initialization was dropped when the code was copied from existing
accelerators. Coverity knows (CID 1641400). Fix it.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 2cd3c1d35a06a62b25afa80c5baf381ce4b56805)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/mshv/mshv-all.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/accel/mshv/mshv-all.c b/accel/mshv/mshv-all.c
index 45174f7c4e..80428d130d 100644
--- a/accel/mshv/mshv-all.c
+++ b/accel/mshv/mshv-all.c
@@ -596,6 +596,9 @@ static void mshv_start_vcpu_thread(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
+ snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/MSHV",
+ cpu->cpu_index);
+
cpu->thread = g_malloc0(sizeof(QemuThread));
cpu->halt_cond = g_malloc0(sizeof(QemuCond));
--
2.47.3

42
kvm-accel-mshv-use-return-value-of-handle_pio_str_read.patch Normal file
View File

@ -0,0 +1,42 @@
From 257a0cba46705253cb708f8b74ceb736b80c2c27 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 22 Oct 2025 14:54:30 +0200
Subject: [PATCH 32/32] accel/mshv: use return value of handle_pio_str_read
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [30/30] 60404a4d9211cf711fd4581d9f586510c3897bd4
Coverity complains because we assign to ret here but
then never read it again before we overwrite it with
the call to set_x64_registers().
Analyzed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 1557adc82698416bc68033765cfffb0a0b91c6bf)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
target/i386/mshv/mshv-cpu.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/target/i386/mshv/mshv-cpu.c b/target/i386/mshv/mshv-cpu.c
index 1f7b9cb37e..1c3db02188 100644
--- a/target/i386/mshv/mshv-cpu.c
+++ b/target/i386/mshv/mshv-cpu.c
@@ -1489,6 +1489,10 @@ static int handle_pio_str(CPUState *cpu, hv_x64_io_port_intercept_message *info)
reg_values[0] = info->rsi;
} else {
ret = handle_pio_str_read(cpu, info, repeat, port, direction_flag);
+ if (ret < 0) {
+ error_report("Failed to handle pio str read");
+ return -1;
+ }
reg_names[0] = HV_X64_REGISTER_RDI;
reg_values[0] = info->rdi;
}
--
2.47.3

64
kvm-aio-warn-about-iohandler_ctx-special-casing.patch
View File

@ -1,64 +0,0 @@
From 6c8da957fd534b3546354a8b8252c01cf9ee3511 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 6 May 2024 15:06:22 -0400
Subject: [PATCH 14/14] aio: warn about iohandler_ctx special casing
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 253: Revert "monitor: use aio_co_reschedule_self()"
RH-Jira: RHEL-43409 RHEL-43410
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [2/2] 895231553731f09f51275c1abbf50c3440fe977f (kmwolf/centos-qemu-kvm)
The main loop has two AioContexts: qemu_aio_context and iohandler_ctx.
The main loop runs them both, but nested aio_poll() calls on
qemu_aio_context exclude iohandler_ctx.
Which one should qemu_get_current_aio_context() return when called from
the main loop? Document that it's always qemu_aio_context.
This has subtle effects on functions that use
qemu_get_current_aio_context(). For example, aio_co_reschedule_self()
does not work when moving from iohandler_ctx to qemu_aio_context because
qemu_get_current_aio_context() does not differentiate these two
AioContexts.
Document this in order to reduce the chance of future bugs.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20240506190622.56095-3-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit e669e800fc9ef8806af5c5578249ab758a4f8a5a)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
include/block/aio.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/include/block/aio.h b/include/block/aio.h
index 8378553eb9..4ee81936ed 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -629,6 +629,9 @@ void aio_co_schedule(AioContext *ctx, Coroutine *co);
*
* Move the currently running coroutine to new_ctx. If the coroutine is already
* running in new_ctx, do nothing.
+ *
+ * Note that this function cannot reschedule from iohandler_ctx to
+ * qemu_aio_context.
*/
void coroutine_fn aio_co_reschedule_self(AioContext *new_ctx);
@@ -661,6 +664,9 @@ void aio_co_enter(AioContext *ctx, Coroutine *co);
* If called from an IOThread this will be the IOThread's AioContext. If
* called from the main thread or with the "big QEMU lock" taken it
* will be the main loop AioContext.
+ *
+ * Note that the return value is never the main loop's iohandler_ctx and the
+ * return value is the main loop AioContext instead.
*/
AioContext *qemu_get_current_aio_context(void);
--
2.39.3

50
kvm-arm-create-new-rhel-10.2-specific-virt-machine-type.patch Normal file
View File

@ -0,0 +1,50 @@
From 1e99cb806fb7d6a341bf8f7c238aa7261af7dbd0 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Wed, 29 Oct 2025 15:53:41 +0100
Subject: [PATCH 06/10] arm: create new rhel 10.2 specific virt machine type
RH-Author: Sebastian Ott <sebott@redhat.com>
RH-MergeRequest: 416: x86, arm: create new rhel 9.8, 10.2 specific machine types
RH-Jira: RHEL-105826 RHEL-105828
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [1/4] 829eed93aefddcc4684ddacff3cd6ff3f991f442 (seott1/cos-qemu-kvm)
Signed-off-by: Sebastian Ott <sebott@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 d37d1bb3cf..e68979d2c5 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3688,16 +3688,23 @@ static void virt_machine_4_1_options(MachineClass *mc)
DEFINE_VIRT_MACHINE(4, 1)
#endif /* disabled for RHEL */
+static void virt_rhel_machine_10_2_0_options(MachineClass *mc)
+{
+}
+DEFINE_VIRT_MACHINE_AS_LATEST(10, 2, 0)
+
static void virt_rhel_machine_10_0_0_options(MachineClass *mc)
{
VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+ virt_rhel_machine_10_2_0_options(mc);
+
/* QEMU 9.1 and earlier have only a stage-1 SMMU, not a nested s1+2 one */
vmc->no_nested_smmu = true;
compat_props_add(mc->compat_props, hw_compat_rhel_10_2, hw_compat_rhel_10_2_len);
compat_props_add(mc->compat_props, hw_compat_rhel_10_1, hw_compat_rhel_10_1_len);
}
-DEFINE_VIRT_MACHINE_AS_LATEST(10, 0, 0)
+DEFINE_VIRT_MACHINE(10, 0, 0)
static void virt_rhel_machine_9_6_0_options(MachineClass *mc)
{
--
2.47.3

49
kvm-arm-create-new-rhel-9.8-specific-virt-machine-type.patch Normal file
View File

@ -0,0 +1,49 @@
From c6b6b0d2969f8baf5f09bc1d4953df5e7445820c Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Wed, 29 Oct 2025 16:05:12 +0100
Subject: [PATCH 07/10] arm: create new rhel 9.8 specific virt machine type
RH-Author: Sebastian Ott <sebott@redhat.com>
RH-MergeRequest: 416: x86, arm: create new rhel 9.8, 10.2 specific machine types
RH-Jira: RHEL-105826 RHEL-105828
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Commit: [2/4] fb3fc4decafd0c6e94ef31c0120b843512089573 (seott1/cos-qemu-kvm)
Signed-off-by: Sebastian Ott <sebott@redhat.com>
---
hw/arm/virt.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e68979d2c5..dcdd53043e 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -3706,14 +3706,19 @@ static void virt_rhel_machine_10_0_0_options(MachineClass *mc)
}
DEFINE_VIRT_MACHINE(10, 0, 0)
-static void virt_rhel_machine_9_6_0_options(MachineClass *mc)
+static void virt_rhel_machine_9_8_0_options(MachineClass *mc)
{
- virt_rhel_machine_10_0_0_options(mc);
-
+ /* NB: remember to move these lines to the *latest* RHEL 9 machine */
compat_props_add(mc->compat_props, arm_rhel9_compat, arm_rhel9_compat_len);
- /* NB: remember to move this line to the *latest* RHEL 9 machine */
compat_props_add(mc->compat_props, hw_compat_rhel_9, hw_compat_rhel_9_len);
}
+DEFINE_VIRT_MACHINE(9, 8, 0)
+
+static void virt_rhel_machine_9_6_0_options(MachineClass *mc)
+{
+ virt_rhel_machine_10_0_0_options(mc);
+ virt_rhel_machine_9_8_0_options(mc);
+}
DEFINE_VIRT_MACHINE(9, 6, 0)
static void virt_rhel_machine_9_4_0_options(MachineClass *mc)
--
2.47.3

44
kvm-arm-fix-oob-access-in-compat-handling.patch Normal file
View File

@ -0,0 +1,44 @@
From c2c080f94d9107273650ebdaf50ca78e8cb2f866 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Tue, 25 Nov 2025 09:19:30 +0100
Subject: [PATCH 2/2] arm: fix oob access in compat handling
RH-Author: Sebastian Ott <sebott@redhat.com>
RH-MergeRequest: 430: arm: fix oob access in compat handling
RH-Jira: RHEL-130478
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Eric Auger <eric.auger@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Commit: [1/1] 5d6ab0821b0ffce732862969f275aa50f6917bf1 (seott1/cos-qemu-kvm)
Upstream: RHEL only
Fixes: 58cba97a "hw/arm/virt: Use ACPI PCI hotplug by default from 10.2 onwards"
Due to incorrect length information arm_acpi_pci_hp_disabled_compat[]
was accessed out of bounds. This led to the weird side effect that the
1st member of arm_rhel9_compat[] was applied to the virt-rhel10.0
machine type causing migration failures. Fix the length.
Signed-off-by: Sebastian Ott <sebott@redhat.com>
---
hw/arm/virt.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index e8e64fe7fe..1cfb386f64 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -102,7 +102,8 @@ static const size_t arm_virt_compat_len = G_N_ELEMENTS(arm_virt_compat);
GlobalProperty arm_acpi_pci_hp_disabled_compat[] = {
{ TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "off" },
};
-static const size_t arm_acpi_pci_hp_disabled_compat_len = G_N_ELEMENTS(arm_virt_compat);
+static const size_t arm_acpi_pci_hp_disabled_compat_len =
+ G_N_ELEMENTS(arm_acpi_pci_hp_disabled_compat);
/*
* RHEL9 kernels have pauth disabled while RHEL10 has it enabled,
--
2.47.3

154
kvm-arm-kvm-report-registers-we-failed-to-set.patch Normal file
View File

@ -0,0 +1,154 @@
From d635b553683b9a057d7a1a4b7e3348c88dcab6d6 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cohuck@redhat.com>
Date: Thu, 11 Sep 2025 17:41:59 +0200
Subject: [PATCH 1/4] arm/kvm: report registers we failed to set
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 410: arm/kvm: report registers we failed to set
RH-Jira: RHEL-119368
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [1/1] 82b4496284ff0a4dd2dd0eae7bb1cf114dded61e (eauger1/centos-qemu-kvm)
If we fail migration because of a mismatch of some registers between
source and destination, the error message is not very informative:
qemu-system-aarch64: error while loading state for instance 0x0 ofdevice 'cpu'
qemu-system-aarch64: Failed to put registers after init: Invalid argument
At least try to give the user a hint which registers had a problem,
even if they cannot really do anything about it right now.
Sample output:
Could not set register op0:3 op1:0 crn:0 crm:0 op2:0 to c00fac31 (is 413fd0c1)
We could be even more helpful once we support writable ID registers,
at which point the user might actually be able to configure something
that is migratable.
Suggested-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Message-id: 20250911154159.158046-1-cohuck@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 19f6dcfe6b8b2a3523362812fc696ab83050d316)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
target/arm/kvm.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 86 insertions(+)
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index 6672344855..c1ec6654ca 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -900,6 +900,58 @@ bool write_kvmstate_to_list(ARMCPU *cpu)
return ok;
}
+/* pretty-print a KVM register */
+#define CP_REG_ARM64_SYSREG_OP(_reg, _op) \
+ ((uint8_t)((_reg & CP_REG_ARM64_SYSREG_ ## _op ## _MASK) >> \
+ CP_REG_ARM64_SYSREG_ ## _op ## _SHIFT))
+
+static gchar *kvm_print_sve_register_name(uint64_t regidx)
+{
+ uint16_t sve_reg = regidx & 0x000000000000ffff;
+
+ if (regidx == KVM_REG_ARM64_SVE_VLS) {
+ return g_strdup_printf("SVE VLS");
+ }
+ /* zreg, preg, ffr */
+ switch (sve_reg & 0xfc00) {
+ case 0:
+ return g_strdup_printf("SVE zreg n:%d slice:%d",
+ (sve_reg & 0x03e0) >> 5, sve_reg & 0x001f);
+ case 0x04:
+ return g_strdup_printf("SVE preg n:%d slice:%d",
+ (sve_reg & 0x01e0) >> 5, sve_reg & 0x001f);
+ case 0x06:
+ return g_strdup_printf("SVE ffr slice:%d", sve_reg & 0x001f);
+ default:
+ return g_strdup_printf("SVE ???");
+ }
+}
+
+static gchar *kvm_print_register_name(uint64_t regidx)
+{
+ switch ((regidx & KVM_REG_ARM_COPROC_MASK)) {
+ case KVM_REG_ARM_CORE:
+ return g_strdup_printf("core reg %"PRIx64, regidx);
+ case KVM_REG_ARM_DEMUX:
+ return g_strdup_printf("demuxed reg %"PRIx64, regidx);
+ case KVM_REG_ARM64_SYSREG:
+ return g_strdup_printf("op0:%d op1:%d crn:%d crm:%d op2:%d",
+ CP_REG_ARM64_SYSREG_OP(regidx, OP0),
+ CP_REG_ARM64_SYSREG_OP(regidx, OP1),
+ CP_REG_ARM64_SYSREG_OP(regidx, CRN),
+ CP_REG_ARM64_SYSREG_OP(regidx, CRM),
+ CP_REG_ARM64_SYSREG_OP(regidx, OP2));
+ case KVM_REG_ARM_FW:
+ return g_strdup_printf("fw reg %d", (int)(regidx & 0xffff));
+ case KVM_REG_ARM64_SVE:
+ return kvm_print_sve_register_name(regidx);
+ case KVM_REG_ARM_FW_FEAT_BMAP:
+ return g_strdup_printf("fw feat reg %d", (int)(regidx & 0xffff));
+ default:
+ return g_strdup_printf("%"PRIx64, regidx);
+ }
+}
+
bool write_list_to_kvmstate(ARMCPU *cpu, int level)
{
CPUState *cs = CPU(cpu);
@@ -927,11 +979,45 @@ bool write_list_to_kvmstate(ARMCPU *cpu, int level)
g_assert_not_reached();
}
if (ret) {
+ gchar *reg_str = kvm_print_register_name(regidx);
+
/* We might fail for "unknown register" and also for
* "you tried to set a register which is constant with
* a different value from what it actually contains".
*/
ok = false;
+ switch (ret) {
+ case -ENOENT:
+ error_report("Could not set register %s: unknown to KVM",
+ reg_str);
+ break;
+ case -EINVAL:
+ if ((regidx & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32) {
+ if (!kvm_get_one_reg(cs, regidx, &v32)) {
+ error_report("Could not set register %s to %x (is %x)",
+ reg_str, (uint32_t)cpu->cpreg_values[i],
+ v32);
+ } else {
+ error_report("Could not set register %s to %x",
+ reg_str, (uint32_t)cpu->cpreg_values[i]);
+ }
+ } else /* U64 */ {
+ uint64_t v64;
+
+ if (!kvm_get_one_reg(cs, regidx, &v64)) {
+ error_report("Could not set register %s to %"PRIx64" (is %"PRIx64")",
+ reg_str, cpu->cpreg_values[i], v64);
+ } else {
+ error_report("Could not set register %s to %"PRIx64,
+ reg_str, cpu->cpreg_values[i]);
+ }
+ }
+ break;
+ default:
+ error_report("Could not set register %s: %s",
+ reg_str, strerror(-ret));
+ }
+ g_free(reg_str);
}
}
return ok;
--
2.47.3

54
kvm-bios-tables-test-Allow-for-smmuv3-test-data.patch Normal file
View File

@ -0,0 +1,54 @@
From b4eeed1e8633df76598de0fe6ca5df4be359222c Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:31 +0100
Subject: [PATCH 13/16] bios-tables-test: Allow for smmuv3 test data.
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [9/11] cf98e2e7589b794775c1d9c4f564e3cd536b886e (eauger1/centos-qemu-kvm)
The tests to be added exercise both legacy(iommu=smmuv3) and new
-device arm-smmuv3,.. cases.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Message-id: 20250829082543.7680-10-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit c69520c13d6ea45a69a7a49361806fa05b19046d)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev | 0
tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy | 0
tests/data/acpi/aarch64/virt/IORT.smmuv3-dev | 0
tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy | 0
tests/qtest/bios-tables-test-allowed-diff.h | 4 ++++
5 files changed, 4 insertions(+)
create mode 100644 tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev
create mode 100644 tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy
create mode 100644 tests/data/acpi/aarch64/virt/IORT.smmuv3-dev
create mode 100644 tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy
diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
index dfb8523c8b..2e3e3ccdce 100644
--- a/tests/qtest/bios-tables-test-allowed-diff.h
+++ b/tests/qtest/bios-tables-test-allowed-diff.h
@@ -1 +1,5 @@
/* List of comma-separated changed AML files to ignore */
+"tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy",
+"tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev",
+"tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy",
+"tests/data/acpi/aarch64/virt/IORT.smmuv3-dev",
--
2.47.3

255
kvm-block-Expose-block-limits-for-images-in-QMP.patch Normal file
View File

@ -0,0 +1,255 @@
From c8b07a9c5c6926a63c2db56c3de8046b2160417d Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 24 Oct 2025 14:30:38 +0200
Subject: [PATCH 3/6] block: Expose block limits for images in QMP
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 439: block: Expose block limits in monitor and qemu-img info
RH-Jira: RHEL-110003
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/4] a2d45f05abd5bedbad2f10ae4dc7a5cce909a2fe (kmwolf/centos-qemu-kvm)
This information can be useful both for debugging and for management
tools trying to configure guest devices with the optimal limits
(possibly across multiple hosts). There is no reason not to make it
available, so just add it to BlockNodeInfo.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20251024123041.51254-3-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit d2634e18286a5772f04cc724e64f8b16a2124587)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/qapi.c | 34 ++++++++++++++--
qapi/block-core.json | 66 ++++++++++++++++++++++++++++++++
tests/qemu-iotests/184 | 5 ++-
tests/qemu-iotests/184.out | 8 ----
tests/qemu-iotests/common.filter | 3 +-
5 files changed, 102 insertions(+), 14 deletions(-)
diff --git a/block/qapi.c b/block/qapi.c
index 12fbf8d1b7..54521d0a68 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -235,7 +235,8 @@ int bdrv_query_snapshot_info_list(BlockDriverState *bs,
* in @info, setting @errp on error.
*/
static void GRAPH_RDLOCK
-bdrv_do_query_node_info(BlockDriverState *bs, BlockNodeInfo *info, Error **errp)
+bdrv_do_query_node_info(BlockDriverState *bs, BlockNodeInfo *info, bool limits,
+ Error **errp)
{
int64_t size;
const char *backing_filename;
@@ -269,6 +270,33 @@ bdrv_do_query_node_info(BlockDriverState *bs, BlockNodeInfo *info, Error **errp)
info->dirty_flag = bdi.is_dirty;
info->has_dirty_flag = true;
}
+
+ if (limits) {
+ info->limits = g_new(BlockLimitsInfo, 1);
+ *info->limits = (BlockLimitsInfo) {
+ .request_alignment = bs->bl.request_alignment,
+ .has_max_discard = bs->bl.max_pdiscard != 0,
+ .max_discard = bs->bl.max_pdiscard,
+ .has_discard_alignment = bs->bl.pdiscard_alignment != 0,
+ .discard_alignment = bs->bl.pdiscard_alignment,
+ .has_max_write_zeroes = bs->bl.max_pwrite_zeroes != 0,
+ .max_write_zeroes = bs->bl.max_pwrite_zeroes,
+ .has_write_zeroes_alignment = bs->bl.pwrite_zeroes_alignment != 0,
+ .write_zeroes_alignment = bs->bl.pwrite_zeroes_alignment,
+ .has_opt_transfer = bs->bl.opt_transfer != 0,
+ .opt_transfer = bs->bl.opt_transfer,
+ .has_max_transfer = bs->bl.max_transfer != 0,
+ .max_transfer = bs->bl.max_transfer,
+ .has_max_hw_transfer = bs->bl.max_hw_transfer != 0,
+ .max_hw_transfer = bs->bl.max_hw_transfer,
+ .max_iov = bs->bl.max_iov,
+ .has_max_hw_iov = bs->bl.max_hw_iov != 0,
+ .max_hw_iov = bs->bl.max_hw_iov,
+ .min_mem_alignment = bs->bl.min_mem_alignment,
+ .opt_mem_alignment = bs->bl.opt_mem_alignment,
+ };
+ }
+
info->format_specific = bdrv_get_specific_info(bs, &err);
if (err) {
error_propagate(errp, err);
@@ -343,7 +371,7 @@ void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo *info;
info = g_new0(ImageInfo, 1);
- bdrv_do_query_node_info(bs, qapi_ImageInfo_base(info), errp);
+ bdrv_do_query_node_info(bs, qapi_ImageInfo_base(info), true, errp);
if (*errp) {
goto fail;
}
@@ -397,7 +425,7 @@ void bdrv_query_block_graph_info(BlockDriverState *bs,
BdrvChild *c;
info = g_new0(BlockGraphInfo, 1);
- bdrv_do_query_node_info(bs, qapi_BlockGraphInfo_base(info), errp);
+ bdrv_do_query_node_info(bs, qapi_BlockGraphInfo_base(info), false, errp);
if (*errp) {
goto fail;
}
diff --git a/qapi/block-core.json b/qapi/block-core.json
index dc6eb4ae23..2c037183f0 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -275,6 +275,69 @@
'file': 'ImageInfoSpecificFileWrapper'
} }
+##
+# @BlockLimitsInfo:
+#
+# @request-alignment: Alignment requirement, in bytes, for
+# offset/length of I/O requests.
+#
+# @max-discard: Maximum number of bytes that can be discarded at once.
+# If not present, there is no specific maximum.
+#
+# @discard-alignment: Optimal alignment for discard requests in bytes.
+# Note that this doesn't have to be a power of two. If not
+# present, discards don't have a alignment requirement different
+# from @request-alignment.
+#
+# @max-write-zeroes: Maximum number of bytes that can be zeroed out at
+# once. If not present, there is no specific maximum.
+#
+# @write-zeroes-alignment: Optimal alignment for write zeroes requests
+# in bytes. Note that this doesn't have to be a power of two. If
+# not present, write_zeroes doesn't have a alignment requirement
+# different from @request-alignment.
+#
+# @opt-transfer: Optimal transfer length in bytes. If not present,
+# there is no preferred size.
+#
+# @max-transfer: Maximal transfer length in bytes. If not present,
+# there is no specific maximum.
+#
+# @max-hw-transfer: Maximal hardware transfer length in bytes.
+# Applies whenever transfers to the device bypass the kernel I/O
+# scheduler, for example with SG_IO. If not present, there is no
+# specific maximum.
+#
+# @max-iov: Maximum number of scatter/gather elements
+#
+# @max-hw-iov: Maximum number of scatter/gather elements allowed by
+# the hardware. Applies whenever transfers to the device bypass
+# the kernel I/O scheduler, for example with SG_IO. If not
+# present, the hardware limits is unknown and @max-iov is always
+# used.
+#
+# @min-mem-alignment: Minimal required memory alignment in bytes for
+# zero-copy I/O to succeed. For unaligned requests, a bounce
+# buffer will be used.
+#
+# @opt-mem-alignment: Optimal memory alignment in bytes. This is the
+# alignment used for any buffer allocations QEMU performs
+# internally.
+##
+{ 'struct': 'BlockLimitsInfo',
+ 'data': { 'request-alignment': 'uint32',
+ '*max-discard': 'uint64',
+ '*discard-alignment': 'uint32',
+ '*max-write-zeroes': 'uint64',
+ '*write-zeroes-alignment': 'uint32',
+ '*opt-transfer': 'uint32',
+ '*max-transfer': 'uint32',
+ '*max-hw-transfer': 'uint32',
+ 'max-iov': 'int',
+ '*max-hw-iov': 'int',
+ 'min-mem-alignment': 'size',
+ 'opt-mem-alignment': 'size' } }
+
##
# @BlockNodeInfo:
#
@@ -304,6 +367,8 @@
#
# @snapshots: list of VM snapshots
#
+# @limits: block limits that are used for I/O on the node (Since 10.2)
+#
# @format-specific: structure supplying additional format-specific
# information (since 1.7)
#
@@ -315,6 +380,7 @@
'*cluster-size': 'int', '*encrypted': 'bool', '*compressed': 'bool',
'*backing-filename': 'str', '*full-backing-filename': 'str',
'*backing-filename-format': 'str', '*snapshots': ['SnapshotInfo'],
+ '*limits': 'BlockLimitsInfo',
'*format-specific': 'ImageInfoSpecific' } }
##
diff --git a/tests/qemu-iotests/184 b/tests/qemu-iotests/184
index e4cbcd8634..6d0afe9d38 100755
--- a/tests/qemu-iotests/184
+++ b/tests/qemu-iotests/184
@@ -45,8 +45,9 @@ do_run_qemu()
run_qemu()
{
- do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_qmp\
- | _filter_qemu_io | _filter_generated_node_ids
+ do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_qmp \
+ | _filter_qemu_io | _filter_generated_node_ids \
+ | _filter_img_info
}
test_throttle=$($QEMU_IMG --help|grep throttle)
diff --git a/tests/qemu-iotests/184.out b/tests/qemu-iotests/184.out
index ef99bb2e9a..52692b6b3b 100644
--- a/tests/qemu-iotests/184.out
+++ b/tests/qemu-iotests/184.out
@@ -41,12 +41,6 @@ Testing:
},
"iops_wr": 0,
"ro": false,
- "children": [
- {
- "node-name": "disk0",
- "child": "file"
- }
- ],
"node-name": "throttle0",
"backing_file_depth": 1,
"drv": "throttle",
@@ -75,8 +69,6 @@ Testing:
},
"iops_wr": 0,
"ro": false,
- "children": [
- ],
"node-name": "disk0",
"backing_file_depth": 0,
"drv": "null-co",
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index 35c0fc0d20..cd8b506dba 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -230,6 +230,7 @@ _filter_img_info()
discard=0
regex_json_spec_start='^ *"format-specific": \{'
regex_json_child_start='^ *"children": \['
+ regex_json_limit_start='^ *"limits": \{'
gsed -e "s#$REMOTE_TEST_DIR#TEST_DIR#g" \
-e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \
-e "s#$TEST_DIR#TEST_DIR#g" \
@@ -262,7 +263,7 @@ _filter_img_info()
discard=1
elif [[ $line =~ "Child node '/" ]]; then
discard=1
- elif [[ $line =~ $regex_json_spec_start ]]; then
+ elif [[ $line =~ $regex_json_spec_start || $line =~ $regex_json_limit_start ]]; then
discard=2
regex_json_end="^${line%%[^ ]*}\\},? *$"
elif [[ $line =~ $regex_json_child_start ]]; then
--
2.47.3

64
kvm-block-Fix-BDS-use-after-free-during-shutdown.patch Normal file
View File

@ -0,0 +1,64 @@
From 8f3dbb64c2217e7c46df964311f210c6a3c9e8be Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Mon, 15 Dec 2025 16:07:14 +0100
Subject: [PATCH] block: Fix BDS use after free during shutdown
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 446: Fix crash that happens when powering-off a guest during migration
RH-Jira: RHEL-108142
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] af2687210d89fef5c4229a84371236c2b9bbdf5b (thuth/qemu-kvm-cs)
JIRA: https://issues.redhat.com/browse/RHEL-108142
During shutdown, blockdev_close_all_bdrv_states() drops any block node
references that are still owned by the monitor (i.e. the user). However,
in doing so, it forgot to also remove the node from monitor_bdrv_states
(which qmp_blockdev_del() correctly does), which means that later calls
of bdrv_first()/bdrv_next() will still return the (now stale) pointer to
the node.
Usually there is no such call after this point, but in some cases it can
happen. In the reported case, there was an ongoing migration, and the
migration thread wasn't shut down yet: migration_shutdown() called by
qemu_cleanup() doesn't actually wait for the migration to be shut down,
but may just move it to MIGRATION_STATUS_CANCELLING. The next time
migration_iteration_finish() runs, it sees the status and tries to
re-activate all block devices that migration may have previously
inactivated. This is where bdrv_first()/bdrv_next() get called and the
access to the already freed node happens.
It is debatable if migration_shutdown() should really return before
migration has settled, but leaving a dangling pointer in the list of
monitor-owned block nodes is clearly a bug either way and fixing it
solves the immediate problem, so fix it.
Reported-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20251215150714.130214-1-kwolf@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Tested-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 307bc43095b8ab1765fd66c26003d5da06681c05)
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
blockdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/blockdev.c b/blockdev.c
index b451fee6e1..76c8dd0573 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -685,6 +685,7 @@ void blockdev_close_all_bdrv_states(void)
GLOBAL_STATE_CODE();
QTAILQ_FOREACH_SAFE(bs, &monitor_bdrv_states, monitor_list, next_bs) {
+ QTAILQ_REMOVE(&monitor_bdrv_states, bs, monitor_list);
bdrv_unref(bs);
}
}
--
2.47.3

98
kvm-block-Improve-comments-in-BlockLimits.patch Normal file
View File

@ -0,0 +1,98 @@
From e5745092ebc473f359cb2eef67ff375a1e942a74 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 24 Oct 2025 14:30:37 +0200
Subject: [PATCH 2/6] block: Improve comments in BlockLimits
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 439: block: Expose block limits in monitor and qemu-img info
RH-Jira: RHEL-110003
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/4] 06c55e52ff339d2bc4559b109b0a6dd625caa7f0 (kmwolf/centos-qemu-kvm)
Patches to expose the limits in QAPI have made clear that the existing
documentation of BlockLimits could be improved: The meaning of
min_mem_alignment and opt_mem_alignment could be clearer, and talking
about better alignment values isn't helpful when we only detect these
values and never choose them.
Make the changes in the BlockLimits documentation now, so that the
patches exposing the fields in QAPI can use descriptions consistent with
it.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20251024123041.51254-2-kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 46dd683d56b1328cb2bc923914bfd7ac590064f7)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
include/block/block_int-common.h | 30 +++++++++++++++++-------------
1 file changed, 17 insertions(+), 13 deletions(-)
diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h
index 034c0634c8..5206f32d53 100644
--- a/include/block/block_int-common.h
+++ b/include/block/block_int-common.h
@@ -817,10 +817,10 @@ typedef struct BlockLimits {
int64_t max_pdiscard;
/*
- * Optimal alignment for discard requests in bytes. A power of 2
- * is best but not mandatory. Must be a multiple of
- * bl.request_alignment, and must be less than max_pdiscard if
- * that is set. May be 0 if bl.request_alignment is good enough
+ * Optimal alignment for discard requests in bytes. Note that this doesn't
+ * have to be a power of two. Must be a multiple of bl.request_alignment,
+ * and must be less than max_pdiscard if that is set. May be 0 if
+ * bl.request_alignment is good enough.
*/
uint32_t pdiscard_alignment;
@@ -831,11 +831,10 @@ typedef struct BlockLimits {
int64_t max_pwrite_zeroes;
/*
- * Optimal alignment for write zeroes requests in bytes. A power
- * of 2 is best but not mandatory. Must be a multiple of
- * bl.request_alignment, and must be less than max_pwrite_zeroes
- * if that is set. May be 0 if bl.request_alignment is good
- * enough
+ * Optimal alignment for write zeroes requests in bytes. Note that this
+ * doesn't have to be a power of two. Must be a multiple of
+ * bl.request_alignment, and must be less than max_pwrite_zeroes if that is
+ * set. May be 0 if bl.request_alignment is good enough.
*/
uint32_t pwrite_zeroes_alignment;
@@ -863,18 +862,23 @@ typedef struct BlockLimits {
uint64_t max_hw_transfer;
/*
- * Maximal number of scatter/gather elements allowed by the hardware.
+ * Maximum number of scatter/gather elements allowed by the hardware.
* Applies whenever transfers to the device bypass the kernel I/O
* scheduler, for example with SG_IO. If larger than max_iov
* or if zero, blk_get_max_hw_iov will fall back to max_iov.
*/
int max_hw_iov;
-
- /* memory alignment, in bytes so that no bounce buffer is needed */
+ /*
+ * Minimal required memory alignment in bytes for zero-copy I/O to succeed.
+ * For unaligned requests, a bounce buffer will be used.
+ */
size_t min_mem_alignment;
- /* memory alignment, in bytes, for bounce buffer */
+ /*
+ * Optimal memory alignment in bytes. This is the alignment used for any
+ * buffer allocations QEMU performs internally.
+ */
size_t opt_mem_alignment;
/* maximum number of iovec elements */
--
2.47.3

98
kvm-block-Never-drop-BLOCK_IO_ERROR-with-action-stop-for.patch Normal file
View File

@ -0,0 +1,98 @@
From 2704bca029bc3c7a3e430d3af8b7696d7d2b1e37 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 4 Mar 2026 13:28:00 +0100
Subject: [PATCH 2/2] block: Never drop BLOCK_IO_ERROR with action=stop for
rate limiting
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 472: block: Never drop BLOCK_IO_ERROR with action=stop for rate limiting
RH-Jira: RHEL-144004
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/1] 96b29a65a4a49fb159970892124e5b4bbdcdfeb7 (kmwolf/centos-qemu-kvm)
Commit 2155d2dd introduced rate limiting for BLOCK_IO_ERROR to emit an
event only once a second. This makes sense for cases in which the guest
keeps running and can submit more requests that would possibly also fail
because there is a problem with the backend.
However, if the error policy is configured so that the VM is stopped on
errors, this is both unnecessary because stopping the VM means that the
guest can't issue more requests and in fact harmful because stopping the
VM is an important state change that management tools need to keep track
of even if it happens more than once in a given second. If an event is
dropped, the management tool would see a VM randomly going to paused
state without an associated error, so it has a hard time deciding how to
handle the situation.
This patch disables rate limiting for action=stop by not relying on the
event type alone any more in monitor_qapi_event_queue_no_reenter(), but
checking action for BLOCK_IO_ERROR, too. If the error is reported to the
guest or ignored, the rate limiting stays in place.
Fixes: 2155d2dd7f73 ('block-backend: per-device throttling of BLOCK_IO_ERROR reports')
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20260304122800.51923-1-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 544ddbb6373d61292a0e2dc269809cd6bd5edec6)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
monitor/monitor.c | 21 ++++++++++++++++++++-
qapi/block-core.json | 2 +-
2 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/monitor/monitor.c b/monitor/monitor.c
index c5a5d30877..ae7cf64de0 100644
--- a/monitor/monitor.c
+++ b/monitor/monitor.c
@@ -363,14 +363,33 @@ monitor_qapi_event_queue_no_reenter(QAPIEvent event, QDict *qdict)
{
MonitorQAPIEventConf *evconf;
MonitorQAPIEventState *evstate;
+ bool throttled;
assert(event < QAPI_EVENT__MAX);
evconf = &monitor_qapi_event_conf[event];
trace_monitor_protocol_event_queue(event, qdict, evconf->rate);
+ throttled = evconf->rate;
+
+ /*
+ * Rate limit BLOCK_IO_ERROR only for action != "stop".
+ *
+ * If the VM is stopped after an I/O error, this is important information
+ * for the management tool to keep track of the state of QEMU and we can't
+ * merge any events. At the same time, stopping the VM means that the guest
+ * can't send additional requests and the number of events is already
+ * limited, so we can do without rate limiting.
+ */
+ if (event == QAPI_EVENT_BLOCK_IO_ERROR) {
+ QDict *data = qobject_to(QDict, qdict_get(qdict, "data"));
+ const char *action = qdict_get_str(data, "action");
+ if (!strcmp(action, "stop")) {
+ throttled = false;
+ }
+ }
QEMU_LOCK_GUARD(&monitor_lock);
- if (!evconf->rate) {
+ if (!throttled) {
/* Unthrottled event */
monitor_qapi_event_emit(event, qdict);
} else {
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 2c037183f0..0236936139 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -5783,7 +5783,7 @@
# .. note:: If action is "stop", a `STOP` event will eventually follow
# the `BLOCK_IO_ERROR` event.
#
-# .. note:: This event is rate-limited.
+# .. note:: This event is rate-limited, except if action is "stop".
#
# Since: 0.13
#
--
2.47.3

252
kvm-block-Parse-filenames-only-when-explicitly-requested.patch
View File

@ -1,252 +0,0 @@
From 53153ebcf066e962cd73d7fcfeca53039be2a945 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 25 Apr 2024 14:56:02 +0200
Subject: [PATCH 4/4] block: Parse filenames only when explicitly requested
RH-Author: Hana Czenczek <hczenczek@redhat.com>
RH-MergeRequest: 1: CVE 2024-4467 (PRDSC)
RH-Jira: RHEL-46239
RH-CVE: CVE-2024-4467
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Commit: [4/4] f44c2941d4419e60f16dea3e9adca164e75aa78d
When handling image filenames from legacy options such as -drive or from
tools, these filenames are parsed for protocol prefixes, including for
the json:{} pseudo-protocol.
This behaviour is intended for filenames that come directly from the
command line and for backing files, which may come from the image file
itself. Higher level management tools generally take care to verify that
untrusted images don't contain a bad (or any) backing file reference;
'qemu-img info' is a suitable tool for this.
However, for other files that can be referenced in images, such as
qcow2 data files or VMDK extents, the string from the image file is
usually not verified by management tools - and 'qemu-img info' wouldn't
be suitable because in contrast to backing files, it already opens these
other referenced files. So here the string should be interpreted as a
literal local filename. More complex configurations need to be specified
explicitly on the command line or in QMP.
This patch changes bdrv_open_inherit() so that it only parses filenames
if a new parameter parse_filename is true. It is set for the top level
in bdrv_open(), for the file child and for the backing file child. All
other callers pass false and disable filename parsing this way.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Upstream: N/A, embargoed
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block.c | 90 ++++++++++++++++++++++++++++++++++++---------------------
1 file changed, 57 insertions(+), 33 deletions(-)
diff --git a/block.c b/block.c
index 468cf5e67d..50bdd197b7 100644
--- a/block.c
+++ b/block.c
@@ -86,6 +86,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
BlockDriverState *parent,
const BdrvChildClass *child_class,
BdrvChildRole child_role,
+ bool parse_filename,
Error **errp);
static bool bdrv_recurse_has_child(BlockDriverState *bs,
@@ -2058,7 +2059,8 @@ static void parse_json_protocol(QDict *options, const char **pfilename,
* block driver has been specified explicitly.
*/
static int bdrv_fill_options(QDict **options, const char *filename,
- int *flags, Error **errp)
+ int *flags, bool allow_parse_filename,
+ Error **errp)
{
const char *drvname;
bool protocol = *flags & BDRV_O_PROTOCOL;
@@ -2100,7 +2102,7 @@ static int bdrv_fill_options(QDict **options, const char *filename,
if (protocol && filename) {
if (!qdict_haskey(*options, "filename")) {
qdict_put_str(*options, "filename", filename);
- parse_filename = true;
+ parse_filename = allow_parse_filename;
} else {
error_setg(errp, "Can't specify 'file' and 'filename' options at "
"the same time");
@@ -3663,7 +3665,8 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
}
backing_hd = bdrv_open_inherit(backing_filename, reference, options, 0, bs,
- &child_of_bds, bdrv_backing_role(bs), errp);
+ &child_of_bds, bdrv_backing_role(bs), true,
+ errp);
if (!backing_hd) {
bs->open_flags |= BDRV_O_NO_BACKING;
error_prepend(errp, "Could not open backing file: ");
@@ -3697,7 +3700,8 @@ free_exit:
static BlockDriverState *
bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
BlockDriverState *parent, const BdrvChildClass *child_class,
- BdrvChildRole child_role, bool allow_none, Error **errp)
+ BdrvChildRole child_role, bool allow_none,
+ bool parse_filename, Error **errp)
{
BlockDriverState *bs = NULL;
QDict *image_options;
@@ -3728,7 +3732,8 @@ bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
}
bs = bdrv_open_inherit(filename, reference, image_options, 0,
- parent, child_class, child_role, errp);
+ parent, child_class, child_role, parse_filename,
+ errp);
if (!bs) {
goto done;
}
@@ -3738,6 +3743,33 @@ done:
return bs;
}
+static BdrvChild *bdrv_open_child_common(const char *filename,
+ QDict *options, const char *bdref_key,
+ BlockDriverState *parent,
+ const BdrvChildClass *child_class,
+ BdrvChildRole child_role,
+ bool allow_none, bool parse_filename,
+ Error **errp)
+{
+ BlockDriverState *bs;
+ BdrvChild *child;
+
+ GLOBAL_STATE_CODE();
+
+ bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_class,
+ child_role, allow_none, parse_filename, errp);
+ if (bs == NULL) {
+ return NULL;
+ }
+
+ bdrv_graph_wrlock();
+ child = bdrv_attach_child(parent, bs, bdref_key, child_class, child_role,
+ errp);
+ bdrv_graph_wrunlock();
+
+ return child;
+}
+
/*
* Opens a disk image whose options are given as BlockdevRef in another block
* device's options.
@@ -3761,27 +3793,15 @@ BdrvChild *bdrv_open_child(const char *filename,
BdrvChildRole child_role,
bool allow_none, Error **errp)
{
- BlockDriverState *bs;
- BdrvChild *child;
-
- GLOBAL_STATE_CODE();
-
- bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_class,
- child_role, allow_none, errp);
- if (bs == NULL) {
- return NULL;
- }
-
- bdrv_graph_wrlock();
- child = bdrv_attach_child(parent, bs, bdref_key, child_class, child_role,
- errp);
- bdrv_graph_wrunlock();
-
- return child;
+ return bdrv_open_child_common(filename, options, bdref_key, parent,
+ child_class, child_role, allow_none, false,
+ errp);
}
/*
- * Wrapper on bdrv_open_child() for most popular case: open primary child of bs.
+ * This does mostly the same as bdrv_open_child(), but for opening the primary
+ * child of a node. A notable difference from bdrv_open_child() is that it
+ * enables filename parsing for protocol names (including json:).
*
* @parent can move to a different AioContext in this function.
*/
@@ -3796,8 +3816,8 @@ int bdrv_open_file_child(const char *filename,
role = parent->drv->is_filter ?
(BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY) : BDRV_CHILD_IMAGE;
- if (!bdrv_open_child(filename, options, bdref_key, parent,
- &child_of_bds, role, false, errp))
+ if (!bdrv_open_child_common(filename, options, bdref_key, parent,
+ &child_of_bds, role, false, true, errp))
{
return -EINVAL;
}
@@ -3842,7 +3862,8 @@ BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp)
}
- bs = bdrv_open_inherit(NULL, reference, qdict, 0, NULL, NULL, 0, errp);
+ bs = bdrv_open_inherit(NULL, reference, qdict, 0, NULL, NULL, 0, false,
+ errp);
obj = NULL;
qobject_unref(obj);
visit_free(v);
@@ -3932,7 +3953,7 @@ static BlockDriverState * no_coroutine_fn
bdrv_open_inherit(const char *filename, const char *reference, QDict *options,
int flags, BlockDriverState *parent,
const BdrvChildClass *child_class, BdrvChildRole child_role,
- Error **errp)
+ bool parse_filename, Error **errp)
{
int ret;
BlockBackend *file = NULL;
@@ -3980,9 +4001,11 @@ bdrv_open_inherit(const char *filename, const char *reference, QDict *options,
}
/* json: syntax counts as explicit options, as if in the QDict */
- parse_json_protocol(options, &filename, &local_err);
- if (local_err) {
- goto fail;
+ if (parse_filename) {
+ parse_json_protocol(options, &filename, &local_err);
+ if (local_err) {
+ goto fail;
+ }
}
bs->explicit_options = qdict_clone_shallow(options);
@@ -4007,7 +4030,8 @@ bdrv_open_inherit(const char *filename, const char *reference, QDict *options,
parent->open_flags, parent->options);
}
- ret = bdrv_fill_options(&options, filename, &flags, &local_err);
+ ret = bdrv_fill_options(&options, filename, &flags, parse_filename,
+ &local_err);
if (ret < 0) {
goto fail;
}
@@ -4076,7 +4100,7 @@ bdrv_open_inherit(const char *filename, const char *reference, QDict *options,
file_bs = bdrv_open_child_bs(filename, options, "file", bs,
&child_of_bds, BDRV_CHILD_IMAGE,
- true, &local_err);
+ true, true, &local_err);
if (local_err) {
goto fail;
}
@@ -4225,7 +4249,7 @@ BlockDriverState *bdrv_open(const char *filename, const char *reference,
GLOBAL_STATE_CODE();
return bdrv_open_inherit(filename, reference, options, flags, NULL,
- NULL, 0, errp);
+ NULL, 0, true, errp);
}
/* Return true if the NULL-terminated @list contains @str */
--
2.39.3

73
kvm-block-backend-Fix-race-when-resuming-queued-requests.patch Normal file
View File

@ -0,0 +1,73 @@
From 1393ba1b8f4ee2b7ec9dcb12317ec2d53c7d793e Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Wed, 19 Nov 2025 18:27:20 +0100
Subject: [PATCH 01/32] block-backend: Fix race when resuming queued requests
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 432: block-backend: Fix race when resuming queued requests [c10s]
RH-Jira: RHEL-129540
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [1/1] fa7ead79ae44d89054ed574deb3fbd196536fef3 (kmwolf/centos-qemu-kvm)
When new requests arrive at a BlockBackend that is currently drained,
these requests are queued until the drain section ends.
There is a race window between blk_root_drained_end() waking up a queued
request in an iothread from the main thread and blk_wait_while_drained()
actually being woken up in the iothread and calling blk_inc_in_flight().
If the BlockBackend is drained again during this window, drain won't
wait for this request and it will sneak in when the BlockBackend is
already supposed to be quiesced. This causes assertion failures in
bdrv_drain_all_begin() and can have other unintended consequences.
Fix this by increasing the in_flight counter immediately when scheduling
the request to be resumed so that the next drain will wait for it to
complete.
Cc: qemu-stable@nongnu.org
Reported-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20251119172720.135424-1-kwolf@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Tested-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Reviewed-by: Fiona Ebner <f.ebner@proxmox.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 8eeaa706ba73251063cb80d87ae838d2d5b08e9a)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/block-backend.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index f8d6ba65c1..d6df369188 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1318,9 +1318,9 @@ static void coroutine_fn blk_wait_while_drained(BlockBackend *blk)
* section.
*/
qemu_mutex_lock(&blk->queued_requests_lock);
+ /* blk_root_drained_end() has the corresponding blk_inc_in_flight() */
blk_dec_in_flight(blk);
qemu_co_queue_wait(&blk->queued_requests, &blk->queued_requests_lock);
- blk_inc_in_flight(blk);
qemu_mutex_unlock(&blk->queued_requests_lock);
}
}
@@ -2767,9 +2767,11 @@ static void blk_root_drained_end(BdrvChild *child)
blk->dev_ops->drained_end(blk->dev_opaque);
}
qemu_mutex_lock(&blk->queued_requests_lock);
- while (qemu_co_enter_next(&blk->queued_requests,
- &blk->queued_requests_lock)) {
+ while (!qemu_co_queue_empty(&blk->queued_requests)) {
/* Resume all queued requests */
+ blk_inc_in_flight(blk);
+ qemu_co_enter_next(&blk->queued_requests,
+ &blk->queued_requests_lock);
}
qemu_mutex_unlock(&blk->queued_requests_lock);
}
--
2.47.3

66
kvm-block-io-Take-reqs_lock-for-tracked_requests.patch Normal file
View File

@ -0,0 +1,66 @@
From c2e109dd6504a8fb06fddf3b5e86956a4699bdef Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Mon, 10 Nov 2025 16:48:45 +0100
Subject: [PATCH 03/19] block/io: Take reqs_lock for tracked_requests
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 454: Multithreading fixes for rbd, curl, qcow2
RH-Jira: RHEL-79118
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/5] 91512b6569546b6e82eca0034608fb5c7b426916 (hreitz/qemu-kvm-c-9-s)
bdrv_co_get_self_request() does not take a lock around iterating through
bs->tracked_requests. With multiqueue, it may thus iterate over a list
that is in the process of being modified, producing an assertion
failure:
../block/file-posix.c:3702: raw_do_pwrite_zeroes: Assertion `req' failed.
[0] abort() at /lib64/libc.so.6
[1] __assert_fail_base.cold() at /lib64/libc.so.6
[2] raw_do_pwrite_zeroes() at ../block/file-posix.c:3702
[3] bdrv_co_do_pwrite_zeroes() at ../block/io.c:1910
[4] bdrv_aligned_pwritev() at ../block/io.c:2109
[5] bdrv_co_do_zero_pwritev() at ../block/io.c:2192
[6] bdrv_co_pwritev_part() at ../block/io.c:2292
[7] bdrv_co_pwritev() at ../block/io.c:2225
[8] handle_alloc_space() at ../block/qcow2.c:2573
[9] qcow2_co_pwritev_task() at ../block/qcow2.c:2625
Fix this by taking reqs_lock.
Cc: qemu-stable@nongnu.org
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20251110154854.151484-11-hreitz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 9b9ee60c07f52009f9bb659f54c42afae95c1d94)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/io.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/block/io.c b/block/io.c
index 9bd8ba8431..37df1e0253 100644
--- a/block/io.c
+++ b/block/io.c
@@ -721,11 +721,14 @@ BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs)
Coroutine *self = qemu_coroutine_self();
IO_CODE();
+ qemu_mutex_lock(&bs->reqs_lock);
QLIST_FOREACH(req, &bs->tracked_requests, list) {
if (req->co == self) {
+ qemu_mutex_unlock(&bs->reqs_lock);
return req;
}
}
+ qemu_mutex_unlock(&bs->reqs_lock);
return NULL;
}
--
2.47.3

167
kvm-block-io_uring-avoid-potentially-getting-stuck-after.patch Normal file
View File

@ -0,0 +1,167 @@
From 4ad89aa6a9efcbc0420e332acab2dd06e55be2fa Mon Sep 17 00:00:00 2001
From: Fiona Ebner <f.ebner@proxmox.com>
Date: Tue, 25 Nov 2025 14:31:03 +0100
Subject: [PATCH 3/4] block/io_uring: avoid potentially getting stuck after
resubmit at the end of ioq_submit()
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 479: linux-aio/io-uring: Resubmit tails of short requests
RH-Jira: RHEL-158224
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [3/4] fd599da3ffcd6b37ceff35587ae9dbc1698b0f57 (hreitz/qemu-kvm-c-9-s)
Note that this issue seems already fixed as a consequence of the large
io_uring rework with 047dabef97 ("block/io_uring: use aio_add_sqe()")
in current master, so this is purely for QEMU stable branches.
At the end of ioq_submit(), there is an opportunistic call to
luring_process_completions(). This is the single caller of
luring_process_completions() that doesn't use the
luring_process_completions_and_submit() wrapper.
Other callers use the wrapper, because luring_process_completions()
might require a subsequent call to ioq_submit() after resubmitting a
request. As noted for luring_resubmit():
> Resubmit a request by appending it to submit_queue. The caller must ensure
> that ioq_submit() is called later so that submit_queue requests are started.
So the caller at the end of ioq_submit() violates the contract and can
in fact be problematic if no other requests come in later. In such a
case, the request intended to be resubmitted will never be actually be
submitted via io_uring_submit().
A reproducer exposing this issue is [0], which is based on user
reports from [1]. Another reproducer is iotest 109 with '-i io_uring'.
I had the most success to trigger the issue with [0] when using a
BTRFS RAID 1 storage. With tmpfs, it can take quite a few iterations,
but also triggers eventually on my machine. With iotest 109 with '-i
io_uring' the issue triggers reliably on my ext4 file system.
Have ioq_submit() submit any resubmitted requests after calling
luring_process_completions(). The return value from io_uring_submit()
is checked to be non-negative before the opportunistic processing of
completions and going for the new resubmit logic, to ensure that a
failure of io_uring_submit() is not missed. Also note that the return
value already was not necessarily the total number of submissions,
since the loop might've been iterated more than once even before the
current change.
Only trigger the resubmission logic if it is actually necessary to
avoid changing behavior more than necessary. For example iotest 109
would produce more 'mirror ready' events if always resubmitting after
luring_process_completions() at the end of ioq_submit().
Note iotest 109 still does not pass as is when run with '-i io_uring',
because of two offset values for BLOCK_JOB_COMPLETED events being zero
instead of non-zero as in the expected output. Note that the two
affected test cases are expected failures and still fail, so they just
fail "faster". The test cases are actually not triggering the resubmit
logic, so the reason seems to be different ordering of requests and
completions of the current aio=io_uring implementation versus
aio=threads.
[0]:
> #!/bin/bash -e
> #file=/mnt/btrfs/disk.raw
> file=/tmp/disk.raw
> filesize=256
> readsize=512
> rm -f $file
> truncate -s $filesize $file
> ./qemu-system-x86_64 --trace '*uring*' --qmp stdio \
> --blockdev raw,node-name=node0,file.driver=file,file.cache.direct=off,file.filename=$file,file.aio=io_uring \
> <<EOF
> {"execute": "qmp_capabilities"}
> {"execute": "human-monitor-command", "arguments": { "command-line": "qemu-io node0 \"read 0 $readsize \"" }}
> {"execute": "quit"}
> EOF
[1]: https://forum.proxmox.com/threads/170045/
Cc: qemu-stable@nongnu.org
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
(cherry picked from commit 2bb0153cd806b8f6b4f82b353bd0113cd1c488a5)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/io_uring.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/block/io_uring.c b/block/io_uring.c
index dd4f304910..5dbafc8f7b 100644
--- a/block/io_uring.c
+++ b/block/io_uring.c
@@ -120,11 +120,14 @@ static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb,
* event loop. When there are no events left to complete the BH is being
* canceled.
*
+ * Returns whether ioq_submit() must be called again afterwards since requests
+ * were resubmitted via luring_resubmit().
*/
-static void luring_process_completions(LuringState *s)
+static bool luring_process_completions(LuringState *s)
{
struct io_uring_cqe *cqes;
int total_bytes;
+ bool resubmit = false;
defer_call_begin();
@@ -182,6 +185,7 @@ static void luring_process_completions(LuringState *s)
*/
if (ret == -EINTR || ret == -EAGAIN) {
luring_resubmit(s, luringcb);
+ resubmit = true;
continue;
}
} else if (!luringcb->qiov) {
@@ -194,6 +198,7 @@ static void luring_process_completions(LuringState *s)
if (luringcb->is_read) {
if (ret > 0) {
luring_resubmit_short_read(s, luringcb, ret);
+ resubmit = true;
continue;
} else {
/* Pad with zeroes */
@@ -224,6 +229,8 @@ end:
qemu_bh_cancel(s->completion_bh);
defer_call_end();
+
+ return resubmit;
}
static int ioq_submit(LuringState *s)
@@ -231,6 +238,7 @@ static int ioq_submit(LuringState *s)
int ret = 0;
LuringAIOCB *luringcb, *luringcb_next;
+resubmit:
while (s->io_q.in_queue > 0) {
/*
* Try to fetch sqes from the ring for requests waiting in
@@ -260,12 +268,14 @@ static int ioq_submit(LuringState *s)
}
s->io_q.blocked = (s->io_q.in_queue > 0);
- if (s->io_q.in_flight) {
+ if (ret >= 0 && s->io_q.in_flight) {
/*
* We can try to complete something just right away if there are
* still requests in-flight.
*/
- luring_process_completions(s);
+ if (luring_process_completions(s)) {
+ goto resubmit;
+ }
}
return ret;
}
--
2.47.3

172
kvm-curl-Fix-coroutine-waking.patch Normal file
View File

@ -0,0 +1,172 @@
From 14d1e6aa70f97aa75c8f3f78e3c730e286e3b683 Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Mon, 10 Nov 2025 16:48:40 +0100
Subject: [PATCH 02/19] curl: Fix coroutine waking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 454: Multithreading fixes for rbd, curl, qcow2
RH-Jira: RHEL-79118
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/5] 20268ed1de88de45a7525d01dbb64899b8c4e443 (hreitz/qemu-kvm-c-9-s)
If we wake a coroutine from a different context, we must ensure that it
will yield exactly once (now or later), awaiting that wake.
curl’s current .ret == -EINPROGRESS loop may lead to the coroutine not
yielding if the request finishes before the loop gets run. To fix it,
we must drop the loop and yield exactly once, if we need to yield.
Finding out that latter part ("if we need to yield") makes it a bit
complicated: Requests may be served from a cache internal to the curl
block driver, or fail before being submitted. In these cases, we must
not yield. However, if we find a matching but still ongoing request in
the cache, we will have to await that, i.e. still yield.
To address this, move the yield inside of the respective functions:
- Inside of curl_find_buf() when awaiting ongoing concurrent requests,
- Inside of curl_setup_preadv() when having created a new request.
Rename curl_setup_preadv() to curl_do_preadv() to reflect this.
(Can be reproduced with multiqueue by adding a usleep(100000) before the
`while (acb.ret == -EINPROGRESS)` loop.)
Also, add a comment why aio_co_wake() is safe regardless of whether the
coroutine and curl_multi_check_completion() run in the same context.
Cc: qemu-stable@nongnu.org
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20251110154854.151484-6-hreitz@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 53d5c7ffac7bd4e0d12174432ebb2b3e88614b15)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/curl.c | 45 +++++++++++++++++++++++++++++++--------------
1 file changed, 31 insertions(+), 14 deletions(-)
diff --git a/block/curl.c b/block/curl.c
index 5467678024..d69bcdff79 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -262,8 +262,8 @@ read_end:
}
/* Called with s->mutex held. */
-static bool curl_find_buf(BDRVCURLState *s, uint64_t start, uint64_t len,
- CURLAIOCB *acb)
+static bool coroutine_fn
+curl_find_buf(BDRVCURLState *s, uint64_t start, uint64_t len, CURLAIOCB *acb)
{
int i;
uint64_t end = start + len;
@@ -311,6 +311,10 @@ static bool curl_find_buf(BDRVCURLState *s, uint64_t start, uint64_t len,
for (j=0; j<CURL_NUM_ACB; j++) {
if (!state->acb[j]) {
state->acb[j] = acb;
+ /* Await ongoing request */
+ qemu_mutex_unlock(&s->mutex);
+ qemu_coroutine_yield();
+ qemu_mutex_lock(&s->mutex);
return true;
}
}
@@ -382,6 +386,16 @@ static void curl_multi_check_completion(BDRVCURLState *s)
acb->ret = error ? -EIO : 0;
state->acb[i] = NULL;
qemu_mutex_unlock(&s->mutex);
+ /*
+ * Current AioContext is the BDS context, which may or may not
+ * be the request (coroutine) context.
+ * - If it is, the coroutine must have yielded or the FD handler
+ * (curl_multi_do()/curl_multi_timeout_do()) could not have
+ * been called and we would not be here
+ * - If it is not, it doesn't matter whether it has already
+ * yielded or not; it will be scheduled once it does yield
+ * So aio_co_wake() is safe to call.
+ */
aio_co_wake(acb->co);
qemu_mutex_lock(&s->mutex);
}
@@ -882,7 +896,7 @@ out_noclean:
return -EINVAL;
}
-static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
+static void coroutine_fn curl_do_preadv(BlockDriverState *bs, CURLAIOCB *acb)
{
CURLState *state;
int running;
@@ -894,10 +908,13 @@ static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
qemu_mutex_lock(&s->mutex);
- // In case we have the requested data already (e.g. read-ahead),
- // we can just call the callback and be done.
+ /*
+ * In case we have the requested data already (e.g. read-ahead),
+ * we can just call the callback and be done. This may have to
+ * await an ongoing request, in which case it itself will yield.
+ */
if (curl_find_buf(s, start, acb->bytes, acb)) {
- goto out;
+ goto dont_yield;
}
// No cache found, so let's start a new request
@@ -912,7 +929,7 @@ static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
if (curl_init_state(s, state) < 0) {
curl_clean_state(state);
acb->ret = -EIO;
- goto out;
+ goto dont_yield;
}
acb->start = 0;
@@ -927,7 +944,7 @@ static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
if (state->buf_len && state->orig_buf == NULL) {
curl_clean_state(state);
acb->ret = -ENOMEM;
- goto out;
+ goto dont_yield;
}
state->acb[0] = acb;
@@ -939,13 +956,16 @@ static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
acb->ret = -EIO;
curl_clean_state(state);
- goto out;
+ goto dont_yield;
}
/* Tell curl it needs to kick things off */
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
+ qemu_mutex_unlock(&s->mutex);
+ qemu_coroutine_yield();
+ return;
-out:
+dont_yield:
qemu_mutex_unlock(&s->mutex);
}
@@ -961,10 +981,7 @@ static int coroutine_fn curl_co_preadv(BlockDriverState *bs,
.bytes = bytes
};
- curl_setup_preadv(bs, &acb);
- while (acb.ret == -EINPROGRESS) {
- qemu_coroutine_yield();
- }
+ curl_do_preadv(bs, &acb);
return acb.ret;
}
--
2.47.3

143
kvm-docs-Add-mshv-to-documentation.patch Normal file
View File

@ -0,0 +1,143 @@
From a42a299252fd1c53600387a81924adee6fa761f6 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:46 +0200
Subject: [PATCH 29/32] docs: Add mshv to documentation
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [27/30] 6450fc04dede6796c6a6383904792da34fb11de1
Added mshv to the list of accelerators in doc text.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-27-magnuskulke@linux.microsoft.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 3af71a1a6a7a497df7d3026239d6136b56e3d5ab)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
docs/about/build-platforms.rst | 2 +-
docs/devel/codebase.rst | 2 +-
docs/glossary.rst | 7 +++----
docs/system/introduction.rst | 3 +++
qemu-options.hx | 16 ++++++++--------
5 files changed, 16 insertions(+), 14 deletions(-)
diff --git a/docs/about/build-platforms.rst b/docs/about/build-platforms.rst
index 8671c3be9c..06ba0ddc9a 100644
--- a/docs/about/build-platforms.rst
+++ b/docs/about/build-platforms.rst
@@ -55,7 +55,7 @@ Those hosts are officially supported, with various accelerators:
* - SPARC
- tcg
* - x86
- - hvf (64 bit only), kvm, nvmm, tcg, whpx (64 bit only), xen
+ - hvf (64 bit only), mshv (64 bit only), kvm, nvmm, tcg, whpx (64 bit only), xen
Other host architectures are not supported. It is possible to build QEMU system
emulation on an unsupported host architecture using the configure
diff --git a/docs/devel/codebase.rst b/docs/devel/codebase.rst
index 2a3143787a..69d8827117 100644
--- a/docs/devel/codebase.rst
+++ b/docs/devel/codebase.rst
@@ -48,7 +48,7 @@ yet, so sometimes the source code is all you have.
* `accel <https://gitlab.com/qemu-project/qemu/-/tree/master/accel>`_:
Infrastructure and architecture agnostic code related to the various
`accelerators <Accelerators>` supported by QEMU
- (TCG, KVM, hvf, whpx, xen, nvmm).
+ (TCG, KVM, hvf, whpx, xen, nvmm, mshv).
Contains interfaces for operations that will be implemented per
`target <https://gitlab.com/qemu-project/qemu/-/tree/master/target>`_.
* `audio <https://gitlab.com/qemu-project/qemu/-/tree/master/audio>`_:
diff --git a/docs/glossary.rst b/docs/glossary.rst
index 4fa044bfb6..2857731bc4 100644
--- a/docs/glossary.rst
+++ b/docs/glossary.rst
@@ -12,7 +12,7 @@ Accelerator
A specific API used to accelerate execution of guest instructions. It can be
hardware-based, through a virtualization API provided by the host OS (kvm, hvf,
-whpx, ...), or software-based (tcg). See this description of `supported
+whpx, mshv, ...), or software-based (tcg). See this description of `supported
accelerators<Accelerators>`.
Board
@@ -101,9 +101,8 @@ manage a virtual machine. QEMU is a virtualizer, that interacts with various
hypervisors.
In the context of QEMU, an hypervisor is an API, provided by the Host OS,
-allowing to execute virtual machines. Linux implementation is KVM (and supports
-Xen as well). For MacOS, it's HVF. Windows defines WHPX. And NetBSD provides
-NVMM.
+allowing to execute virtual machines. Linux provides a choice of KVM, Xen
+or MSHV; MacOS provides HVF; Windows provides WHPX; NetBSD provides NVMM.
.. _machine:
diff --git a/docs/system/introduction.rst b/docs/system/introduction.rst
index 4cd46b5b8f..9c57523b6c 100644
--- a/docs/system/introduction.rst
+++ b/docs/system/introduction.rst
@@ -23,6 +23,9 @@ Tiny Code Generator (TCG) capable of emulating many CPUs.
* - Xen
- Linux (as dom0)
- Arm, x86
+ * - MSHV
+ - Linux (as dom0)
+ - x86
* - Hypervisor Framework (hvf)
- MacOS
- x86 (64 bit only), Arm (64 bit only)
diff --git a/qemu-options.hx b/qemu-options.hx
index 5f146c1860..8eca7faa94 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -28,7 +28,7 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \
"-machine [type=]name[,prop[=value][,...]]\n"
" selects emulated machine ('-machine help' for list)\n"
" property accel=accel1[:accel2[:...]] selects accelerator\n"
- " supported accelerators are kvm, xen, hvf, nvmm, whpx or tcg (default: tcg)\n"
+ " supported accelerators are kvm, xen, hvf, nvmm, whpx, mshv or tcg (default: tcg)\n"
" vmport=on|off|auto controls emulation of vmport (default: auto)\n"
" dump-guest-core=on|off include guest memory in a core dump (default=on)\n"
" mem-merge=on|off controls memory merge support (default: on)\n"
@@ -66,10 +66,10 @@ SRST
``accel=accels1[:accels2[:...]]``
This is used to enable an accelerator. Depending on the target
- architecture, kvm, xen, hvf, nvmm, whpx or tcg can be available.
- By default, tcg is used. If there is more than one accelerator
- specified, the next one is used if the previous one fails to
- initialize.
+ architecture, kvm, xen, hvf, nvmm, whpx, mshv or tcg can be
+ available. By default, tcg is used. If there is more than one
+ accelerator specified, the next one is used if the previous one
+ fails to initialize.
``vmport=on|off|auto``
Enables emulation of VMWare IO port, for vmmouse etc. auto says
@@ -226,7 +226,7 @@ ERST
DEF("accel", HAS_ARG, QEMU_OPTION_accel,
"-accel [accel=]accelerator[,prop[=value][,...]]\n"
- " select accelerator (kvm, xen, hvf, nvmm, whpx or tcg; use 'help' for a list)\n"
+ " select accelerator (kvm, xen, hvf, nvmm, whpx, mshv or tcg; use 'help' for a list)\n"
" igd-passthru=on|off (enable Xen integrated Intel graphics passthrough, default=off)\n"
" kernel-irqchip=on|off|split controls accelerated irqchip support (default=on)\n"
" kvm-shadow-mem=size of KVM shadow MMU in bytes\n"
@@ -241,8 +241,8 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel,
SRST
``-accel name[,prop=value[,...]]``
This is used to enable an accelerator. Depending on the target
- architecture, kvm, xen, hvf, nvmm, whpx or tcg can be available. By
- default, tcg is used. If there is more than one accelerator
+ architecture, kvm, xen, hvf, nvmm, whpx, mshv or tcg can be available.
+ By default, tcg is used. If there is more than one accelerator
specified, the next one is used if the previous one fails to
initialize.
--
2.47.3

118
kvm-docs-add-SCSI-migrate-pr-documentation.patch Normal file
View File

@ -0,0 +1,118 @@
From a47cd8b532de2235c3be76a79f42d40c32a4fa58 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Thu, 29 Jan 2026 16:20:35 -0500
Subject: [PATCH 6/7] docs: add SCSI migrate-pr documentation
RH-Author: Stefan Hajnoczi <stefanha@redhat.com>
RH-MergeRequest: 464: scsi: persistent reservation live migration
RH-Jira: RHEL-132749
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Commit: [5/5] e081d8f5e12d1228cd3de395964c0cb4d483559e (stefanha/centos-stream-qemu-kvm)
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 20260129212035.219676-6-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit a67819adb2212977360e9290bd005badb07dd2e4)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
docs/system/device-emulation.rst | 1 +
docs/system/devices/scsi/index.rst | 10 +++++
docs/system/devices/scsi/migrate-pr.rst | 54 +++++++++++++++++++++++++
3 files changed, 65 insertions(+)
create mode 100644 docs/system/devices/scsi/index.rst
create mode 100644 docs/system/devices/scsi/migrate-pr.rst
diff --git a/docs/system/device-emulation.rst b/docs/system/device-emulation.rst
index 911381643f..72a9dbd54d 100644
--- a/docs/system/device-emulation.rst
+++ b/docs/system/device-emulation.rst
@@ -91,6 +91,7 @@ Emulated Devices
devices/keyboard.rst
devices/net.rst
devices/nvme.rst
+ devices/scsi/index.rst
devices/usb.rst
devices/vhost-user.rst
devices/virtio-gpu.rst
diff --git a/docs/system/devices/scsi/index.rst b/docs/system/devices/scsi/index.rst
new file mode 100644
index 0000000000..4f0929b0ca
--- /dev/null
+++ b/docs/system/devices/scsi/index.rst
@@ -0,0 +1,10 @@
+SCSI Devices
+============
+
+Several SCSI devices are available in QEMU. They are primarily used for block
+storage.
+
+.. toctree::
+ :maxdepth: 1
+
+ migrate-pr.rst
diff --git a/docs/system/devices/scsi/migrate-pr.rst b/docs/system/devices/scsi/migrate-pr.rst
new file mode 100644
index 0000000000..a8f2790a86
--- /dev/null
+++ b/docs/system/devices/scsi/migrate-pr.rst
@@ -0,0 +1,54 @@
+..
+ SPDX-License-Identifier: GPL-2.0-or-later
+
+.. _scsi_migrate_pr:
+
+SCSI Persistent Reservation Live Migration
+==========================================
+
+This document explains how to live migrate SCSI Persistent Reservations.
+
+The ``scsi-block`` device migrates SCSI Persistent Reservations when the
+``migrate-pr=on`` parameter is given. Migration is enabled by default in
+versioned machine types since QEMU 11.0. It is disabled by default on older
+machine types and needs to be explicitly enabled with ``--device
+scsi-block,migrate-pr=on,...``.
+
+When migration is enabled, QEMU snoops PERSISTENT RESERVATION OUT commands and
+tracks the reservation key registered by the guest as well as reservations that
+the guest acquires. This information is migrated along with the guest and the
+destination QEMU submits a PERSISTENT RESERVATION OUT command with the PREEMPT
+service action to atomically transfer the reservation to the destination before
+the guest starts running on the destination.
+
+The following persistent reservation capabilities reported by the PERSISTENT
+RESERVATION IN command with the REPORT CAPABILITIES service action are masked
+from the guest by QEMU when migration is enabled:
+
+ * Specify Initiator Ports Capable (SIP_C)
+ * All Target Ports Capable (ATC_C)
+
+When migration is disabled, the ``scsi-block`` device is live migrated but
+reservations remain in place on the source. Usually this is not the intended
+behavior unless there is another mechanism to update reservations during
+migration. The PERSISTENT RESERVATION IN command also does not mask
+capabilities reported to the guest when migration is disabled.
+
+Limitations
+-----------
+
+QEMU does not remember snooped reservation details across restart, so software
+inside the guest must acquire the reservation after boot in order for live
+migration to work. Similarly, if the reservation is acquired outside the guest
+then it will not live migrate along with the guest.
+
+Snooping only considers the PERSISTENT RESERVATION OUT commands from the guest
+and does not track reservation changes made by other SCSI initiators. QEMU's
+snooped reservation details can become stale if another SCSI initiator
+makes changes to the reservation.
+
+Guests running on the same host share a single SCSI initiator identity unless
+Fibre Channel N_Port ID Virtualization is configured. As a consequence,
+multiple guests on the same hosts may observe unexpected behavior if they use
+the same physical LUN. From the LUN's perspective all guests are the same
+initiator and there is no way to distinguish between guests.
--
2.47.3

69
kvm-e1000e-Prevent-crash-from-legacy-interrupt-firing-af.patch Normal file
View File

@ -0,0 +1,69 @@
From a2f30bafa346ef50932c359eaf71574ed3c1239d Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Thu, 7 Aug 2025 13:08:06 +0200
Subject: [PATCH] e1000e: Prevent crash from legacy interrupt firing after
MSI-X enable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 403: e1000e: Prevent crash from legacy interrupt firing after MSI-X enable
RH-Jira: RHEL-112882
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: Jason Wang <jasowang@redhat.com>
RH-Commit: [1/1] 8241a58b76307f27ad3d3b3b2106e00b153b7b53 (lvivier/qemu-kvm-centos)
JIRA: https://issues.redhat.com/browse/RHEL-112882
A race condition between guest driver actions and QEMU timers can lead
to an assertion failure when the guest switches the e1000e from legacy
interrupt mode to MSI-X. If a legacy interrupt delay timer (TIDV or
RDTR) is active, but the guest enables MSI-X before the timer fires,
the pending interrupt cause can trigger an assert in
e1000e_intmgr_collect_delayed_causes().
This patch removes the assertion and executes the code that clears the
pending legacy causes. This change is safe and introduces no unintended
behavioral side effects, as it only alters a state that previously led
to termination.
- when core->delayed_causes == 0 the function was already a no-op and
remains so.
- when core->delayed_causes != 0 the function would previously
crash due to the assertion failure. The patch now defines a safe
outcome by clearing the cause and returning. Since behavior after
the assertion never existed, this simply corrects the crash.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1863
Suggested-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Message-ID: <20250807110806.409065-1-lvivier@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
(cherry picked from commit 8e4649cac9bcddc050d2df07908075e9e69bccc7)
---
hw/net/e1000e_core.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index 2413858790..06657bb3ac 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -341,11 +341,6 @@ e1000e_intmgr_collect_delayed_causes(E1000ECore *core)
{
uint32_t res;
- if (msix_enabled(core->owner)) {
- assert(core->delayed_causes == 0);
- return 0;
- }
-
res = core->delayed_causes;
core->delayed_causes = 0;
--
2.47.3

123
kvm-file-posix-Handle-suspended-dm-multipath-better-for-.patch Normal file
View File

@ -0,0 +1,123 @@
From 56703080fdf6630d6d844c736f3195b3b7b80f74 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Fri, 28 Nov 2025 23:14:40 +0100
Subject: [PATCH 02/32] file-posix: Handle suspended dm-multipath better for
SG_IO
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 436: file-posix: Handle suspended dm-multipath better for SG_IO
RH-Jira: RHEL-121543
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: [1/1] f90d36aba5b374dcb9d5986f968c2dbde4bdd18d (kmwolf/centos-qemu-kvm)
When introducing DM_MPATH_PROBE_PATHS, we already anticipated that
dm-multipath devices might be suspended for a short time when the DM
tables are reloaded and that they return -EAGAIN in this case. We then
wait for a millisecond and retry.
However, meanwhile it has also turned out that libmpathpersist (which is
used by qemu-pr-helper) may need to perform more complex recovery
operations to get reservations back to expected state if a path failure
happened in the middle of a PR operation. In this case, the device is
suspended for a longer time compared to the case we originally expected.
This patch changes hdev_co_ioctl() to treat -EAGAIN separately so that
it doesn't result in an immediate failure if the device is suspended for
more than 1ms, and moves to incremental backoff to cover both quick and
slow cases without excessive delays.
Buglink: https://issues.redhat.com/browse/RHEL-121543
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20251128221440.89125-1-kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 2c3165a1a61c299b4a3ae30899e1cc738d20e004)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/file-posix.c | 56 ++++++++++++++++++++++++++++------------------
1 file changed, 34 insertions(+), 22 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index cb2e94d7db..ffca37130b 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -4289,25 +4289,8 @@ hdev_open_Mac_error:
static bool coroutine_fn sgio_path_error(int ret, sg_io_hdr_t *io_hdr)
{
if (ret < 0) {
- switch (ret) {
- case -ENODEV:
- return true;
- case -EAGAIN:
- /*
- * The device is probably suspended. This happens while the dm table
- * is reloaded, e.g. because a path is added or removed. This is an
- * operation that should complete within 1ms, so just wait a bit and
- * retry.
- *
- * If the device was suspended for another reason, we'll wait and
- * retry SG_IO_MAX_RETRIES times. This is a tolerable delay before
- * we return an error and potentially stop the VM.
- */
- qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000);
- return true;
- default:
- return false;
- }
+ /* Path errors sometimes result in -ENODEV */
+ return ret == -ENODEV;
}
if (io_hdr->host_status != SCSI_HOST_OK) {
@@ -4376,6 +4359,7 @@ hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
{
BDRVRawState *s = bs->opaque;
RawPosixAIOData acb;
+ uint64_t eagain_sleep_ns = 1 * SCALE_MS;
int retries = SG_IO_MAX_RETRIES;
int ret;
@@ -4404,9 +4388,37 @@ hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
},
};
- do {
- ret = raw_thread_pool_submit(handle_aiocb_ioctl, &acb);
- } while (req == SG_IO && retries-- && hdev_co_ioctl_sgio_retry(&acb, ret));
+retry:
+ ret = raw_thread_pool_submit(handle_aiocb_ioctl, &acb);
+ if (req == SG_IO && s->use_mpath) {
+ if (ret == -EAGAIN && eagain_sleep_ns < NANOSECONDS_PER_SECOND) {
+ /*
+ * If this is a multipath device, it is probably suspended.
+ *
+ * This can happen while the dm table is reloaded, e.g. because a
+ * path is added or removed. This is an operation that should
+ * complete within 1ms, so just wait a bit and retry.
+ *
+ * There are also some cases in which libmpathpersist must recover
+ * from path failure during its operation, which can leave the
+ * device suspended for a bit longer while the library brings back
+ * reservations into the expected state.
+ *
+ * Use increasing delays to cover both cases without waiting
+ * excessively, and stop after a bit more than a second (1023 ms).
+ * This is a tolerable delay before we return an error and
+ * potentially stop the VM.
+ */
+ qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, eagain_sleep_ns);
+ eagain_sleep_ns *= 2;
+ goto retry;
+ }
+
+ /* Even for ret == 0, the SG_IO header can contain an error */
+ if (retries-- && hdev_co_ioctl_sgio_retry(&acb, ret)) {
+ goto retry;
+ }
+ }
return ret;
}
--
2.47.3

36
kvm-fix-pc_rhel_10_2_compat_len.patch Normal file
View File

@ -0,0 +1,36 @@
From c4415936b6033aff4b2e38b1c470c920e14fa35a Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Mon, 12 Jan 2026 09:19:07 +0100
Subject: [PATCH 1/4] fix pc_rhel_10_2_compat_len
RH-Author: Gerd Hoffmann <kraxel@redhat.com>
RH-MergeRequest: 447: q35: increase default tseg size
RH-Jira: RHEL-126707
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/2] b9291186e031c0c018dfdc87960b04817421ecec (kraxel.rh/centos-src-qemu-kvm)
There is an (apparently) cut+paste error in the definition
pc_rhel_10_2_compat_len variable, it calculates the length
of the wrong array. Fix it.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
hw/i386/pc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 446d4a7c93..394a84eb8a 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -304,7 +304,7 @@ GlobalProperty pc_rhel_10_2_compat[] = {
{ TYPE_X86_CPU, "x-arch-cap-always-on", "true" },
{ TYPE_X86_CPU, "x-pdcm-on-even-without-pmu", "true" },
};
-const size_t pc_rhel_10_2_compat_len = G_N_ELEMENTS(pc_compat_10_0);
+const size_t pc_rhel_10_2_compat_len = G_N_ELEMENTS(pc_rhel_10_2_compat);
GlobalProperty pc_rhel_10_1_compat[] = {
/* pc_rhel_10_1_compat from pc_compat_9_1 */
--
2.47.3

131
kvm-hw-arm-smmu-common-Check-SMMU-has-PCIe-Root-Complex-.patch Normal file
View File

@ -0,0 +1,131 @@
From ad929c3b2e90eeb1f81a3f7074cdaaa922b073b9 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:23 +0100
Subject: [PATCH 05/16] hw/arm/smmu-common: Check SMMU has PCIe Root Complex
association
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [1/11] 9e7a87070ebfef643848d31fe66f5b4e82bfe0cf (eauger1/centos-qemu-kvm)
We only allow default PCIe Root Complex(pcie.0) or pxb-pcie based extra
root complexes to be associated with SMMU.
Although this change does not affect functionality at present, it is
required when we add support for user-creatable SMMUv3 devices in
future patches.
Note: Added a specific check to identify pxb-pcie to avoid matching
pxb-cxl host bridges, which are also of type PCI_HOST_BRIDGE. This
restriction can be relaxed once support for CXL devices on arm/virt
is added and validated with SMMUv3.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nathan Chen <nathanc@nvidia.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Message-id: 20250829082543.7680-2-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit d9e6b8424fd2523a0361972d5dd841471879479c)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/smmu-common.c | 31 ++++++++++++++++++++++++++---
hw/pci-bridge/pci_expander_bridge.c | 1 -
include/hw/pci/pci_bridge.h | 1 +
3 files changed, 29 insertions(+), 4 deletions(-)
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
index 0dcaf2f589..7f64ea48d0 100644
--- a/hw/arm/smmu-common.c
+++ b/hw/arm/smmu-common.c
@@ -20,6 +20,7 @@
#include "trace.h"
#include "exec/target_page.h"
#include "hw/core/cpu.h"
+#include "hw/pci/pci_bridge.h"
#include "hw/qdev-properties.h"
#include "qapi/error.h"
#include "qemu/jhash.h"
@@ -925,6 +926,7 @@ static void smmu_base_realize(DeviceState *dev, Error **errp)
{
SMMUState *s = ARM_SMMU(dev);
SMMUBaseClass *sbc = ARM_SMMU_GET_CLASS(dev);
+ PCIBus *pci_bus = s->primary_bus;
Error *local_err = NULL;
sbc->parent_realize(dev, &local_err);
@@ -937,11 +939,34 @@ static void smmu_base_realize(DeviceState *dev, Error **errp)
g_free, g_free);
s->smmu_pcibus_by_busptr = g_hash_table_new(NULL, NULL);
- if (s->primary_bus) {
- pci_setup_iommu(s->primary_bus, &smmu_ops, s);
- } else {
+ if (!pci_bus) {
error_setg(errp, "SMMU is not attached to any PCI bus!");
+ return;
+ }
+
+ /*
+ * We only allow default PCIe Root Complex(pcie.0) or pxb-pcie based extra
+ * root complexes to be associated with SMMU.
+ */
+ if (pci_bus_is_express(pci_bus) && pci_bus_is_root(pci_bus) &&
+ object_dynamic_cast(OBJECT(pci_bus)->parent, TYPE_PCI_HOST_BRIDGE)) {
+ /*
+ * This condition matches either the default pcie.0, pxb-pcie, or
+ * pxb-cxl. For both pxb-pcie and pxb-cxl, parent_dev will be set.
+ * Currently, we don't allow pxb-cxl as it requires further
+ * verification. Therefore, make sure this is indeed pxb-pcie.
+ */
+ if (pci_bus->parent_dev) {
+ if (!object_dynamic_cast(OBJECT(pci_bus), TYPE_PXB_PCIE_BUS)) {
+ goto out_err;
+ }
+ }
+ pci_setup_iommu(pci_bus, &smmu_ops, s);
+ return;
}
+out_err:
+ error_setg(errp, "SMMU should be attached to a default PCIe root complex"
+ "(pcie.0) or a pxb-pcie based root complex");
}
/*
diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c
index 3a29dfefc2..1bcceddbc4 100644
--- a/hw/pci-bridge/pci_expander_bridge.c
+++ b/hw/pci-bridge/pci_expander_bridge.c
@@ -34,7 +34,6 @@ typedef struct PXBBus PXBBus;
DECLARE_INSTANCE_CHECKER(PXBBus, PXB_BUS,
TYPE_PXB_BUS)
-#define TYPE_PXB_PCIE_BUS "pxb-pcie-bus"
DECLARE_INSTANCE_CHECKER(PXBBus, PXB_PCIE_BUS,
TYPE_PXB_PCIE_BUS)
diff --git a/include/hw/pci/pci_bridge.h b/include/hw/pci/pci_bridge.h
index 8cdacbc4e1..a055fd8d32 100644
--- a/include/hw/pci/pci_bridge.h
+++ b/include/hw/pci/pci_bridge.h
@@ -104,6 +104,7 @@ typedef struct PXBPCIEDev {
PXBDev parent_obj;
} PXBPCIEDev;
+#define TYPE_PXB_PCIE_BUS "pxb-pcie-bus"
#define TYPE_PXB_CXL_BUS "pxb-cxl-bus"
#define TYPE_PXB_DEV "pxb"
OBJECT_DECLARE_SIMPLE_TYPE(PXBDev, PXB_DEV)
--
2.47.3

61
kvm-hw-arm-virt-Add-an-SMMU_IO_LEN-macro.patch Normal file
View File

@ -0,0 +1,61 @@
From c62e5defde6f02bdd316b772169571d0de5d2d83 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:27 +0100
Subject: [PATCH 09/16] hw/arm/virt: Add an SMMU_IO_LEN macro
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [5/11] 72c82e228bb256db07fbe28728ad47dbd8b04dc3 (eauger1/centos-qemu-kvm)
This is useful as the subsequent support for new SMMUv3 dev will also
use the same.
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nathan Chen <nathanc@nvidia.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Message-id: 20250829082543.7680-6-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 466197fc7a25658f9187d538c26887f5738d1ac9)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 9b95a7c9a9..b435efafe1 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -186,6 +186,9 @@ static void arm_virt_compat_set(MachineClass *mc)
#define LEGACY_RAMLIMIT_GB 255
#define LEGACY_RAMLIMIT_BYTES (LEGACY_RAMLIMIT_GB * GiB)
+/* MMIO region size for SMMUv3 */
+#define SMMU_IO_LEN 0x20000
+
/* Addresses and sizes of our components.
* 0..128MB is space for a flash device so we can run bootrom code such as UEFI.
* 128MB..256MB is used for miscellaneous device I/O.
@@ -217,7 +220,7 @@ static const MemMapEntry base_memmap[] = {
[VIRT_FW_CFG] = { 0x09020000, 0x00000018 },
[VIRT_GPIO] = { 0x09030000, 0x00001000 },
[VIRT_UART1] = { 0x09040000, 0x00001000 },
- [VIRT_SMMU] = { 0x09050000, 0x00020000 },
+ [VIRT_SMMU] = { 0x09050000, SMMU_IO_LEN },
[VIRT_PCDIMM_ACPI] = { 0x09070000, MEMORY_HOTPLUG_IO_LEN },
[VIRT_ACPI_GED] = { 0x09080000, ACPI_GED_EVT_SEL_LEN },
[VIRT_NVDIMM_ACPI] = { 0x09090000, NVDIMM_ACPI_IO_LEN},
--
2.47.3

215
kvm-hw-arm-virt-Allow-user-creatable-SMMUv3-dev-instanti.patch Normal file
View File

@ -0,0 +1,215 @@
From 20b24c8ae68ff5059392188762c8d8b24c3dfa28 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:29 +0100
Subject: [PATCH 11/16] hw/arm/virt: Allow user-creatable SMMUv3 dev
instantiation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [7/11] 8f4a03c34d5c699023b3916f4919caf669f7a87c (eauger1/centos-qemu-kvm)
Allow cold-plugging of an SMMUv3 device on the virt machine when no
global (legacy) SMMUv3 is present or when a virtio-iommu is specified.
This user-created SMMUv3 device is tied to a specific PCI bus provided
by the user, so ensure the IOMMU ops are configured accordingly.
Due to current limitations in QEMU’s device tree support, specifically
its inability to properly present pxb-pcie based root complexes and
their devices, the device tree support for the new SMMUv3 device is
limited to cases where it is attached to the default pcie.0 root complex.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nathan Chen <nathanc@nvidia.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Message-id: 20250829082543.7680-8-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 66d2f665e163cf1afccd171e3c16f8d3acb3d94a)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/smmu-common.c | 8 +++++-
hw/arm/smmuv3.c | 2 ++
hw/arm/virt.c | 51 ++++++++++++++++++++++++++++++++++++
hw/core/sysbus-fdt.c | 3 +++
include/hw/arm/smmu-common.h | 1 +
5 files changed, 64 insertions(+), 1 deletion(-)
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
index 7f64ea48d0..62a7612184 100644
--- a/hw/arm/smmu-common.c
+++ b/hw/arm/smmu-common.c
@@ -961,7 +961,12 @@ static void smmu_base_realize(DeviceState *dev, Error **errp)
goto out_err;
}
}
- pci_setup_iommu(pci_bus, &smmu_ops, s);
+
+ if (s->smmu_per_bus) {
+ pci_setup_iommu_per_bus(pci_bus, &smmu_ops, s);
+ } else {
+ pci_setup_iommu(pci_bus, &smmu_ops, s);
+ }
return;
}
out_err:
@@ -986,6 +991,7 @@ static void smmu_base_reset_exit(Object *obj, ResetType type)
static const Property smmu_dev_properties[] = {
DEFINE_PROP_UINT8("bus_num", SMMUState, bus_num, 0),
+ DEFINE_PROP_BOOL("smmu_per_bus", SMMUState, smmu_per_bus, false),
DEFINE_PROP_LINK("primary-bus", SMMUState, primary_bus,
TYPE_PCI_BUS, PCIBus *),
};
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
index ab67972353..bcf8af8dc7 100644
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -1996,6 +1996,8 @@ static void smmuv3_class_init(ObjectClass *klass, const void *data)
device_class_set_parent_realize(dc, smmu_realize,
&c->parent_realize);
device_class_set_props(dc, smmuv3_properties);
+ dc->hotpluggable = false;
+ dc->user_creatable = true;
}
static int smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index b435efafe1..e8e64fe7fe 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -56,6 +56,7 @@
#include "qemu/cutils.h"
#include "qemu/error-report.h"
#include "qemu/module.h"
+#include "hw/pci/pci_bus.h"
#include "hw/pci-host/gpex.h"
#include "hw/pci-bridge/pci_expander_bridge.h"
#include "hw/virtio/virtio-pci.h"
@@ -1510,6 +1511,29 @@ static void create_smmuv3_dt_bindings(const VirtMachineState *vms, hwaddr base,
g_free(node);
}
+static void create_smmuv3_dev_dtb(VirtMachineState *vms,
+ DeviceState *dev, PCIBus *bus)
+{
+ PlatformBusDevice *pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev);
+ SysBusDevice *sbdev = SYS_BUS_DEVICE(dev);
+ int irq = platform_bus_get_irqn(pbus, sbdev, 0);
+ hwaddr base = platform_bus_get_mmio_addr(pbus, sbdev, 0);
+ MachineState *ms = MACHINE(vms);
+
+ if (!(vms->bootinfo.firmware_loaded && virt_is_acpi_enabled(vms)) &&
+ strcmp("pcie.0", bus->qbus.name)) {
+ warn_report("SMMUv3 device only supported with pcie.0 for DT");
+ return;
+ }
+ base += vms->memmap[VIRT_PLATFORM_BUS].base;
+ irq += vms->irqmap[VIRT_PLATFORM_BUS];
+
+ vms->iommu_phandle = qemu_fdt_alloc_phandle(ms->fdt);
+ create_smmuv3_dt_bindings(vms, base, SMMU_IO_LEN, irq);
+ qemu_fdt_setprop_cells(ms->fdt, vms->pciehb_nodename, "iommu-map",
+ 0x0, vms->iommu_phandle, 0x0, 0x10000);
+}
+
static void create_smmu(const VirtMachineState *vms,
PCIBus *bus)
{
@@ -3057,6 +3081,16 @@ static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
qlist_append_str(reserved_regions, resv_prop_str);
qdev_prop_set_array(dev, "reserved-regions", reserved_regions);
g_free(resv_prop_str);
+ } else if (object_dynamic_cast(OBJECT(dev), TYPE_ARM_SMMUV3)) {
+ if (vms->legacy_smmuv3_present || vms->iommu == VIRT_IOMMU_VIRTIO) {
+ error_setg(errp, "virt machine already has %s set. "
+ "Doesn't support incompatible iommus",
+ (vms->legacy_smmuv3_present) ?
+ "iommu=smmuv3" : "virtio-iommu");
+ } else if (vms->iommu == VIRT_IOMMU_NONE) {
+ /* The new SMMUv3 device is specific to the PCI bus */
+ object_property_set_bool(OBJECT(dev), "smmu_per_bus", true, NULL);
+ }
}
}
@@ -3080,6 +3114,22 @@ static void virt_machine_device_plug_cb(HotplugHandler *hotplug_dev,
virtio_md_pci_plug(VIRTIO_MD_PCI(dev), MACHINE(hotplug_dev), errp);
}
+ if (object_dynamic_cast(OBJECT(dev), TYPE_ARM_SMMUV3)) {
+ if (!vms->legacy_smmuv3_present && vms->platform_bus_dev) {
+ PCIBus *bus;
+
+ bus = PCI_BUS(object_property_get_link(OBJECT(dev), "primary-bus",
+ &error_abort));
+ if (pci_bus_bypass_iommu(bus)) {
+ error_setg(errp, "Bypass option cannot be set for SMMUv3 "
+ "associated PCIe RC");
+ return;
+ }
+
+ create_smmuv3_dev_dtb(vms, dev, bus);
+ }
+ }
+
if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
PCIDevice *pdev = PCI_DEVICE(dev);
@@ -3286,6 +3336,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
#endif
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE);
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_UEFI_VARS_SYSBUS);
+ machine_class_allow_dynamic_sysbus_dev(mc, TYPE_ARM_SMMUV3);
#ifdef CONFIG_TPM
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS);
#endif
diff --git a/hw/core/sysbus-fdt.c b/hw/core/sysbus-fdt.c
index 1e1966813f..673e083d31 100644
--- a/hw/core/sysbus-fdt.c
+++ b/hw/core/sysbus-fdt.c
@@ -31,6 +31,7 @@
#include "qemu/error-report.h"
#include "system/device_tree.h"
#include "system/tpm.h"
+#include "hw/arm/smmuv3.h"
#include "hw/platform-bus.h"
#include "hw/vfio/vfio-platform.h"
#include "hw/vfio/vfio-calxeda-xgmac.h"
@@ -518,6 +519,8 @@ static const BindingEntry bindings[] = {
#ifdef CONFIG_TPM
TYPE_BINDING(TYPE_TPM_TIS_SYSBUS, add_tpm_tis_fdt_node),
#endif
+ /* No generic DT support for smmuv3 dev. Support added for arm virt only */
+ TYPE_BINDING(TYPE_ARM_SMMUV3, no_fdt_node),
TYPE_BINDING(TYPE_RAMFB_DEVICE, no_fdt_node),
TYPE_BINDING(TYPE_UEFI_VARS_SYSBUS, add_uefi_vars_node),
TYPE_BINDING("", NULL), /* last element */
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
index e5e2d09294..80d0fecfde 100644
--- a/include/hw/arm/smmu-common.h
+++ b/include/hw/arm/smmu-common.h
@@ -161,6 +161,7 @@ struct SMMUState {
QLIST_HEAD(, SMMUDevice) devices_with_notifiers;
uint8_t bus_num;
PCIBus *primary_bus;
+ bool smmu_per_bus; /* SMMU is specific to the primary_bus */
};
struct SMMUBaseClass {
--
2.47.3

118
kvm-hw-arm-virt-Factor-out-common-SMMUV3-dt-bindings-cod.patch Normal file
View File

@ -0,0 +1,118 @@
From 1b3c413355ee5f3917e8e39dbf7a281f8e31a0f5 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:26 +0100
Subject: [PATCH 08/16] hw/arm/virt: Factor out common SMMUV3 dt bindings code
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [4/11] db5d2a44f4cd1583c839b93ae551a2ddbd68b83b (eauger1/centos-qemu-kvm)
No functional changes intended. This will be useful when we
add support for user-creatable smmuv3 device.
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nathan Chen <nathanc@nvidia.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Message-id: 20250829082543.7680-5-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 7a276b7570266ec39611f9d91089741ec7e9295b)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 54 +++++++++++++++++++++++++++------------------------
1 file changed, 29 insertions(+), 25 deletions(-)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 0cc9e5f068..9b95a7c9a9 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1479,19 +1479,43 @@ static void create_pcie_irq_map(const MachineState *ms,
0x7 /* PCI irq */);
}
+static void create_smmuv3_dt_bindings(const VirtMachineState *vms, hwaddr base,
+ hwaddr size, int irq)
+{
+ char *node;
+ const char compat[] = "arm,smmu-v3";
+ const char irq_names[] = "eventq\0priq\0cmdq-sync\0gerror";
+ MachineState *ms = MACHINE(vms);
+
+ node = g_strdup_printf("/smmuv3@%" PRIx64, base);
+ qemu_fdt_add_subnode(ms->fdt, node);
+ qemu_fdt_setprop(ms->fdt, node, "compatible", compat, sizeof(compat));
+ qemu_fdt_setprop_sized_cells(ms->fdt, node, "reg", 2, base, 2, size);
+
+ qemu_fdt_setprop_cells(ms->fdt, node, "interrupts",
+ GIC_FDT_IRQ_TYPE_SPI, irq , GIC_FDT_IRQ_FLAGS_EDGE_LO_HI,
+ GIC_FDT_IRQ_TYPE_SPI, irq + 1, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI,
+ GIC_FDT_IRQ_TYPE_SPI, irq + 2, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI,
+ GIC_FDT_IRQ_TYPE_SPI, irq + 3, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI);
+
+ qemu_fdt_setprop(ms->fdt, node, "interrupt-names", irq_names,
+ sizeof(irq_names));
+
+ qemu_fdt_setprop(ms->fdt, node, "dma-coherent", NULL, 0);
+ qemu_fdt_setprop_cell(ms->fdt, node, "#iommu-cells", 1);
+ qemu_fdt_setprop_cell(ms->fdt, node, "phandle", vms->iommu_phandle);
+ g_free(node);
+}
+
static void create_smmu(const VirtMachineState *vms,
PCIBus *bus)
{
VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms);
- char *node;
- const char compat[] = "arm,smmu-v3";
int irq = vms->irqmap[VIRT_SMMU];
int i;
hwaddr base = vms->memmap[VIRT_SMMU].base;
hwaddr size = vms->memmap[VIRT_SMMU].size;
- const char irq_names[] = "eventq\0priq\0cmdq-sync\0gerror";
DeviceState *dev;
- MachineState *ms = MACHINE(vms);
if (vms->iommu != VIRT_IOMMU_SMMUV3 || !vms->iommu_phandle) {
return;
@@ -1510,27 +1534,7 @@ static void create_smmu(const VirtMachineState *vms,
sysbus_connect_irq(SYS_BUS_DEVICE(dev), i,
qdev_get_gpio_in(vms->gic, irq + i));
}
-
- node = g_strdup_printf("/smmuv3@%" PRIx64, base);
- qemu_fdt_add_subnode(ms->fdt, node);
- qemu_fdt_setprop(ms->fdt, node, "compatible", compat, sizeof(compat));
- qemu_fdt_setprop_sized_cells(ms->fdt, node, "reg", 2, base, 2, size);
-
- qemu_fdt_setprop_cells(ms->fdt, node, "interrupts",
- GIC_FDT_IRQ_TYPE_SPI, irq , GIC_FDT_IRQ_FLAGS_EDGE_LO_HI,
- GIC_FDT_IRQ_TYPE_SPI, irq + 1, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI,
- GIC_FDT_IRQ_TYPE_SPI, irq + 2, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI,
- GIC_FDT_IRQ_TYPE_SPI, irq + 3, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI);
-
- qemu_fdt_setprop(ms->fdt, node, "interrupt-names", irq_names,
- sizeof(irq_names));
-
- qemu_fdt_setprop(ms->fdt, node, "dma-coherent", NULL, 0);
-
- qemu_fdt_setprop_cell(ms->fdt, node, "#iommu-cells", 1);
-
- qemu_fdt_setprop_cell(ms->fdt, node, "phandle", vms->iommu_phandle);
- g_free(node);
+ create_smmuv3_dt_bindings(vms, base, size, irq);
}
static void create_virtio_iommu_dt_bindings(VirtMachineState *vms)
--
2.47.3

66
kvm-hw-arm-virt-Use-ACPI-PCI-hotplug-by-default-from-10..patch Normal file
View File

@ -0,0 +1,66 @@
From 5264d9ea8c029dab0663a3da82f4d8241ad0f1b9 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Fri, 7 Nov 2025 05:23:16 -0500
Subject: [PATCH 04/16] hw/arm/virt: Use ACPI PCI hotplug by default from 10.2
onwards
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 422: hw/arm/virt: Use ACPI PCI hotplug by default from 10.2 onwards
RH-Jira: RHEL-67323
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Commit: [1/1] 4539ba6526fef80adb9893a643eb001449397447 (eauger1/centos-qemu-kvm)
UPSTREAM: RHEL-only
Use ACPI PCI hotplug by default from 10.2 onwards. For older
rhel10 machine types and all rhel9 machine types ACPI PCI hotplug
is kept disabled.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index dcdd53043e..542d702513 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -94,9 +94,15 @@
static GlobalProperty arm_virt_compat[] = {
{ TYPE_VIRTIO_IOMMU_PCI, "aw-bits", "48" },
+ { TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "on" },
};
static const size_t arm_virt_compat_len = G_N_ELEMENTS(arm_virt_compat);
+GlobalProperty arm_acpi_pci_hp_disabled_compat[] = {
+ { TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "off" },
+};
+static const size_t arm_acpi_pci_hp_disabled_compat_len = G_N_ELEMENTS(arm_virt_compat);
+
/*
* RHEL9 kernels have pauth disabled while RHEL10 has it enabled,
* since qemu will setup the VM with pauth when KVM supports it we
@@ -104,6 +110,7 @@ static const size_t arm_virt_compat_len = G_N_ELEMENTS(arm_virt_compat);
*/
GlobalProperty arm_rhel9_compat[] = {
{TYPE_ARM_CPU, "pauth", "off", .optional = true},
+ {TYPE_ACPI_GED, "acpi-pci-hotplug-with-bridge-support", "off" },
};
const size_t arm_rhel9_compat_len = G_N_ELEMENTS(arm_rhel9_compat);
@@ -3701,6 +3708,8 @@ static void virt_rhel_machine_10_0_0_options(MachineClass *mc)
/* QEMU 9.1 and earlier have only a stage-1 SMMU, not a nested s1+2 one */
vmc->no_nested_smmu = true;
+ compat_props_add(mc->compat_props, arm_acpi_pci_hp_disabled_compat,
+ arm_acpi_pci_hp_disabled_compat_len);
compat_props_add(mc->compat_props, hw_compat_rhel_10_2, hw_compat_rhel_10_2_len);
compat_props_add(mc->compat_props, hw_compat_rhel_10_1, hw_compat_rhel_10_1_len);
}
--
2.47.3

291
kvm-hw-arm-virt-acpi-build-Re-arrange-SMMUv3-IORT-build.patch Normal file
View File

@ -0,0 +1,291 @@
From 221e12accdd5e699d727cd862760829e973a7b2a Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:24 +0100
Subject: [PATCH 06/16] hw/arm/virt-acpi-build: Re-arrange SMMUv3 IORT build
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [2/11] 73e2dd4f48ffaf614c79241bc73cbb0457849131 (eauger1/centos-qemu-kvm)
Introduce a new struct AcpiIortSMMUv3Dev to hold all the information
required for SMMUv3 IORT node and use that for populating the node.
The current machine wide SMMUv3 is named as legacy SMMUv3 as we will
soon add support for user-creatable SMMUv3 devices. These changes will
be useful to have common code paths when we add that support.
Tested-by: Nathan Chen <nathanc@nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Message-id: 20250829082543.7680-3-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 0e6a5bfb0eb17f57fb923b7905bd1435204bdd62)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt-acpi-build.c | 137 ++++++++++++++++++++++++++-------------
hw/arm/virt.c | 1 +
include/hw/arm/virt.h | 1 +
3 files changed, 94 insertions(+), 45 deletions(-)
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index b01fc4f8ef..bef4fabe56 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -305,29 +305,65 @@ static int iort_idmap_compare(gconstpointer a, gconstpointer b)
return idmap_a->input_base - idmap_b->input_base;
}
+typedef struct AcpiIortSMMUv3Dev {
+ int irq;
+ hwaddr base;
+ GArray *rc_smmu_idmaps;
+ /* Offset of the SMMUv3 IORT Node relative to the start of the IORT */
+ size_t offset;
+} AcpiIortSMMUv3Dev;
+
+/*
+ * Populate the struct AcpiIortSMMUv3Dev for the legacy SMMUv3 and
+ * return the total number of associated idmaps.
+ */
+static int populate_smmuv3_legacy_dev(GArray *sdev_blob)
+{
+ VirtMachineState *vms = VIRT_MACHINE(qdev_get_machine());
+ AcpiIortSMMUv3Dev sdev;
+
+ sdev.rc_smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
+ object_child_foreach_recursive(object_get_root(), iort_host_bridges,
+ sdev.rc_smmu_idmaps);
+ /*
+ * There can be only one legacy SMMUv3("iommu=smmuv3") as it is a machine
+ * wide one. Since it may cover multiple PCIe RCs(based on "bypass_iommu"
+ * property), may have multiple SMMUv3 idmaps. Sort it by input_base.
+ */
+ g_array_sort(sdev.rc_smmu_idmaps, iort_idmap_compare);
+
+ sdev.base = vms->memmap[VIRT_SMMU].base;
+ sdev.irq = vms->irqmap[VIRT_SMMU] + ARM_SPI_BASE;
+ g_array_append_val(sdev_blob, sdev);
+ return sdev.rc_smmu_idmaps->len;
+}
+
/* Compute ID ranges (RIDs) from RC that are directed to the ITS Group node */
-static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmu_idmaps)
+static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmuv3_devs)
{
AcpiIortIdMapping *idmap;
AcpiIortIdMapping next_range = {0};
+ AcpiIortSMMUv3Dev *sdev;
- /*
- * Based on the RID ranges that are directed to the SMMU, determine the
- * bypassed RID ranges, i.e., the ones that are directed to the ITS Group
- * node and do not pass through the SMMU, by subtracting the SMMU-bound
- * ranges from the full RID range (0x0000–0xFFFF).
- */
- for (int i = 0; i < smmu_idmaps->len; i++) {
- idmap = &g_array_index(smmu_idmaps, AcpiIortIdMapping, i);
+ for (int i = 0; i < smmuv3_devs->len; i++) {
+ sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i);
+ /*
+ * Based on the RID ranges that are directed to the SMMU, determine the
+ * bypassed RID ranges, i.e., the ones that are directed to the ITS
+ * Group node and do not pass through the SMMU, by subtracting the
+ * SMMU-bound ranges from the full RID range (0x0000–0xFFFF).
+ */
+ for (int j = 0; j < sdev->rc_smmu_idmaps->len; j++) {
+ idmap = &g_array_index(sdev->rc_smmu_idmaps, AcpiIortIdMapping, j);
- if (next_range.input_base < idmap->input_base) {
- next_range.id_count = idmap->input_base - next_range.input_base;
- g_array_append_val(its_idmaps, next_range);
- }
+ if (next_range.input_base < idmap->input_base) {
+ next_range.id_count = idmap->input_base - next_range.input_base;
+ g_array_append_val(its_idmaps, next_range);
+ }
- next_range.input_base = idmap->input_base + idmap->id_count;
+ next_range.input_base = idmap->input_base + idmap->id_count;
+ }
}
-
/*
* Append the last RC -> ITS ID mapping.
*
@@ -341,7 +377,6 @@ static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmu_idmaps)
}
}
-
/*
* Input Output Remapping Table (IORT)
* Conforms to "IO Remapping Table System Software on ARM Platforms",
@@ -351,9 +386,12 @@ static void
build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
{
int i, nb_nodes, rc_mapping_count;
- size_t node_size, smmu_offset = 0;
+ AcpiIortSMMUv3Dev *sdev;
+ size_t node_size;
+ int num_smmus = 0;
uint32_t id = 0;
- GArray *rc_smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
+ int rc_smmu_idmaps_len = 0;
+ GArray *smmuv3_devs = g_array_new(false, true, sizeof(AcpiIortSMMUv3Dev));
GArray *rc_its_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
AcpiTable table = { .sig = "IORT", .rev = 3, .oem_id = vms->oem_id,
@@ -361,22 +399,21 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
/* Table 2 The IORT */
acpi_table_begin(&table, table_data);
- if (vms->iommu == VIRT_IOMMU_SMMUV3) {
- object_child_foreach_recursive(object_get_root(),
- iort_host_bridges, rc_smmu_idmaps);
-
- /* Sort the smmu idmap by input_base */
- g_array_sort(rc_smmu_idmaps, iort_idmap_compare);
+ if (vms->legacy_smmuv3_present) {
+ rc_smmu_idmaps_len = populate_smmuv3_legacy_dev(smmuv3_devs);
+ }
- nb_nodes = 2; /* RC and SMMUv3 */
- rc_mapping_count = rc_smmu_idmaps->len;
+ num_smmus = smmuv3_devs->len;
+ if (num_smmus) {
+ nb_nodes = num_smmus + 1; /* RC and SMMUv3 */
+ rc_mapping_count = rc_smmu_idmaps_len;
if (vms->its) {
/*
* Knowing the ID ranges from the RC to the SMMU, it's possible to
* determine the ID ranges from RC that go directly to ITS.
*/
- create_rc_its_idmaps(rc_its_idmaps, rc_smmu_idmaps);
+ create_rc_its_idmaps(rc_its_idmaps, smmuv3_devs);
nb_nodes++; /* ITS */
rc_mapping_count += rc_its_idmaps->len;
@@ -411,9 +448,10 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
build_append_int_noprefix(table_data, 0 /* MADT translation_id */, 4);
}
- if (vms->iommu == VIRT_IOMMU_SMMUV3) {
- int irq = vms->irqmap[VIRT_SMMU] + ARM_SPI_BASE;
+ for (i = 0; i < num_smmus; i++) {
+ sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i);
int smmu_mapping_count, offset_to_id_array;
+ int irq = sdev->irq;
if (vms->its) {
smmu_mapping_count = 1; /* ITS Group node */
@@ -422,7 +460,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
smmu_mapping_count = 0; /* No ID mappings */
offset_to_id_array = 0; /* No ID mappings array */
}
- smmu_offset = table_data->len - table.table_offset;
+ sdev->offset = table_data->len - table.table_offset;
/* Table 9 SMMUv3 Format */
build_append_int_noprefix(table_data, 4 /* SMMUv3 */, 1); /* Type */
node_size = SMMU_V3_ENTRY_SIZE +
@@ -435,7 +473,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
/* Reference to ID Array */
build_append_int_noprefix(table_data, offset_to_id_array, 4);
/* Base address */
- build_append_int_noprefix(table_data, vms->memmap[VIRT_SMMU].base, 8);
+ build_append_int_noprefix(table_data, sdev->base, 8);
/* Flags */
build_append_int_noprefix(table_data, 1 /* COHACC Override */, 4);
build_append_int_noprefix(table_data, 0, 4); /* Reserved */
@@ -486,21 +524,26 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
build_append_int_noprefix(table_data, 0, 3); /* Reserved */
/* Output Reference */
- if (vms->iommu == VIRT_IOMMU_SMMUV3) {
+ if (num_smmus) {
AcpiIortIdMapping *range;
- /*
- * Map RIDs (input) from RC to SMMUv3 nodes: RC -> SMMUv3.
- *
- * N.B.: The mapping from SMMUv3 to ITS Group node (SMMUv3 -> ITS) is
- * defined in the SMMUv3 table, where all SMMUv3 IDs are mapped to the
- * ITS Group node, if ITS is available.
- */
- for (i = 0; i < rc_smmu_idmaps->len; i++) {
- range = &g_array_index(rc_smmu_idmaps, AcpiIortIdMapping, i);
- /* Output IORT node is the SMMUv3 node. */
- build_iort_id_mapping(table_data, range->input_base,
- range->id_count, smmu_offset);
+ for (i = 0; i < num_smmus; i++) {
+ sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i);
+
+ /*
+ * Map RIDs (input) from RC to SMMUv3 nodes: RC -> SMMUv3.
+ *
+ * N.B.: The mapping from SMMUv3 to ITS Group node (SMMUv3 -> ITS)
+ * is defined in the SMMUv3 table, where all SMMUv3 IDs are mapped
+ * to the ITS Group node, if ITS is available.
+ */
+ for (int j = 0; j < sdev->rc_smmu_idmaps->len; j++) {
+ range = &g_array_index(sdev->rc_smmu_idmaps,
+ AcpiIortIdMapping, j);
+ /* Output IORT node is the SMMUv3 node. */
+ build_iort_id_mapping(table_data, range->input_base,
+ range->id_count, sdev->offset);
+ }
}
if (vms->its) {
@@ -525,8 +568,12 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
}
acpi_table_end(linker, &table);
- g_array_free(rc_smmu_idmaps, true);
g_array_free(rc_its_idmaps, true);
+ for (i = 0; i < num_smmus; i++) {
+ sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i);
+ g_array_free(sdev->rc_smmu_idmaps, true);
+ }
+ g_array_free(smmuv3_devs, true);
}
/*
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 542d702513..0cc9e5f068 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1686,6 +1686,7 @@ static void create_pcie(VirtMachineState *vms)
qemu_fdt_setprop_cells(ms->fdt, nodename, "iommu-map",
0x0, vms->iommu_phandle, 0x0, 0x10000);
}
+ vms->legacy_smmuv3_present = true;
break;
default:
g_assert_not_reached();
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 94c79d6c6d..98b877c8b9 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -180,6 +180,7 @@ struct VirtMachineState {
char *oem_table_id;
bool ns_el2_virt_timer_irq;
CXLState cxl_devices_state;
+ bool legacy_smmuv3_present;
};
#define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM)
--
2.47.3

170
kvm-hw-arm-virt-acpi-build-Update-IORT-for-multiple-smmu.patch Normal file
View File

@ -0,0 +1,170 @@
From f89d89a3758ebd8725e677431f1e7493c65381c2 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:25 +0100
Subject: [PATCH 07/16] hw/arm/virt-acpi-build: Update IORT for multiple smmuv3
devices
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [3/11] 9cb15768a319676af16cd2cdef8b8fabfa7b6f13 (eauger1/centos-qemu-kvm)
With the soon to be introduced user-creatable SMMUv3 devices for
virt, it is possible to have multiple SMMUv3 devices associated
with different PCIe root complexes.
Update IORT nodes accordingly.
An example IORT Id mappings for a Qemu virt machine with two
PCIe Root Complexes each assocaited with a SMMUv3 will
be something like below,
-device arm-smmuv3,primary-bus=pcie.0,id=smmuv3.0
-device arm-smmuv3,primary-bus=pcie.1,id=smmuv3.1
...
+--------------------+ +--------------------+
| Root Complex 0 | | Root Complex 1 |
| | | |
| Requestor IDs | | Requestor IDs |
| 0x0000 - 0x00FF | | 0x0100 - 0x01FF |
+---------+----------+ +---------+----------+
| |
| |
| Stream ID Mapping |
v v
+--------------------+ +--------------------+
| SMMUv3 Node 0 | | SMMUv3 Node 1 |
| | | |
| Stream IDs 0x0000- | | Stream IDs 0x0100- |
| 0x00FF mapped from | | 0x01FF mapped from |
| RC0 Requestor IDs | | RC1 Requestor IDs |
+--------------------+ +--------------------+
| |
| |
+----------------+---------------+
|
|Device ID Mapping
v
+----------------------------+
| ITS Node 0 |
| |
| Device IDs: |
| 0x0000 - 0x00FF (from RC0) |
| 0x0100 - 0x01FF (from RC1) |
| 0x0200 - 0xFFFF (No SMMU) |
+----------------------------+
Tested-by: Nathan Chen <nathanc@nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Message-id: 20250829082543.7680-4-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 01e9a18730e6f56f713ed074603a8b0f2982ed26)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/arm/virt-acpi-build.c | 64 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 64 insertions(+)
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index bef4fabe56..96830f7c4e 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -45,6 +45,7 @@
#include "hw/acpi/generic_event_device.h"
#include "hw/acpi/tpm.h"
#include "hw/acpi/hmat.h"
+#include "hw/arm/smmuv3.h"
#include "hw/cxl/cxl.h"
#include "hw/pci/pcie_host.h"
#include "hw/pci/pci.h"
@@ -338,6 +339,67 @@ static int populate_smmuv3_legacy_dev(GArray *sdev_blob)
return sdev.rc_smmu_idmaps->len;
}
+static int smmuv3_dev_idmap_compare(gconstpointer a, gconstpointer b)
+{
+ AcpiIortSMMUv3Dev *sdev_a = (AcpiIortSMMUv3Dev *)a;
+ AcpiIortSMMUv3Dev *sdev_b = (AcpiIortSMMUv3Dev *)b;
+ AcpiIortIdMapping *map_a = &g_array_index(sdev_a->rc_smmu_idmaps,
+ AcpiIortIdMapping, 0);
+ AcpiIortIdMapping *map_b = &g_array_index(sdev_b->rc_smmu_idmaps,
+ AcpiIortIdMapping, 0);
+ return map_a->input_base - map_b->input_base;
+}
+
+static int iort_smmuv3_devices(Object *obj, void *opaque)
+{
+ VirtMachineState *vms = VIRT_MACHINE(qdev_get_machine());
+ GArray *sdev_blob = opaque;
+ AcpiIortIdMapping idmap;
+ PlatformBusDevice *pbus;
+ AcpiIortSMMUv3Dev sdev;
+ int min_bus, max_bus;
+ SysBusDevice *sbdev;
+ PCIBus *bus;
+
+ if (!object_dynamic_cast(obj, TYPE_ARM_SMMUV3)) {
+ return 0;
+ }
+
+ bus = PCI_BUS(object_property_get_link(obj, "primary-bus", &error_abort));
+ pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev);
+ sbdev = SYS_BUS_DEVICE(obj);
+ sdev.base = platform_bus_get_mmio_addr(pbus, sbdev, 0);
+ sdev.base += vms->memmap[VIRT_PLATFORM_BUS].base;
+ sdev.irq = platform_bus_get_irqn(pbus, sbdev, 0);
+ sdev.irq += vms->irqmap[VIRT_PLATFORM_BUS];
+ sdev.irq += ARM_SPI_BASE;
+
+ pci_bus_range(bus, &min_bus, &max_bus);
+ sdev.rc_smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
+ idmap.input_base = min_bus << 8,
+ idmap.id_count = (max_bus - min_bus + 1) << 8,
+ g_array_append_val(sdev.rc_smmu_idmaps, idmap);
+ g_array_append_val(sdev_blob, sdev);
+ return 0;
+}
+
+/*
+ * Populate the struct AcpiIortSMMUv3Dev for all SMMUv3 devices and
+ * return the total number of idmaps.
+ */
+static int populate_smmuv3_dev(GArray *sdev_blob)
+{
+ object_child_foreach_recursive(object_get_root(),
+ iort_smmuv3_devices, sdev_blob);
+ /* Sort the smmuv3 devices(if any) by smmu idmap input_base */
+ g_array_sort(sdev_blob, smmuv3_dev_idmap_compare);
+ /*
+ * Since each SMMUv3 dev is assocaited with specific host bridge,
+ * total number of idmaps equals to total number of smmuv3 devices.
+ */
+ return sdev_blob->len;
+}
+
/* Compute ID ranges (RIDs) from RC that are directed to the ITS Group node */
static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmuv3_devs)
{
@@ -401,6 +463,8 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
if (vms->legacy_smmuv3_present) {
rc_smmu_idmaps_len = populate_smmuv3_legacy_dev(smmuv3_devs);
+ } else {
+ rc_smmu_idmaps_len = populate_smmuv3_dev(smmuv3_devs);
}
num_smmus = smmuv3_devs->len;
--
2.47.3

386
kvm-hw-intc-Generalize-APIC-helper-names-from-kvm_-to-ac.patch Normal file
View File

@ -0,0 +1,386 @@
From ea903da8f0546ded20f84a3c4f46139a8206609e Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:24 +0200
Subject: [PATCH 06/32] hw/intc: Generalize APIC helper names from kvm_* to
accel_*
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/30] 2622233d15ed5138cb143d2a5b54fb05c8574654
Rename APIC helper functions to use an accel_* prefix instead of kvm_*
to support use by accelerators other than KVM. This is a preparatory
step for integrating MSHV support with common APIC logic.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250916164847.77883-5-magnuskulke@linux.microsoft.com
[Remove dead definition of mshv_msi_via_irqfd_enabled. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 638ac1c78457dd93ccd795b9c6c2673af8c7dd21)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
accel/accel-irq.c | 106 +++++++++++++++++++++++++++++++++++++
accel/meson.build | 2 +-
hw/intc/ioapic.c | 20 ++++---
hw/virtio/virtio-pci.c | 21 ++++----
include/system/accel-irq.h | 37 +++++++++++++
include/system/mshv.h | 17 ++++++
6 files changed, 185 insertions(+), 18 deletions(-)
create mode 100644 accel/accel-irq.c
create mode 100644 include/system/accel-irq.h
diff --git a/accel/accel-irq.c b/accel/accel-irq.c
new file mode 100644
index 0000000000..7f864e35c4
--- /dev/null
+++ b/accel/accel-irq.c
@@ -0,0 +1,106 @@
+/*
+ * Accelerated irqchip abstraction
+ *
+ * Copyright Microsoft, Corp. 2025
+ *
+ * Authors: Ziqiao Zhou <ziqiaozhou@microsoft.com>
+ * Magnus Kulke <magnuskulke@microsoft.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "hw/pci/msi.h"
+
+#include "system/kvm.h"
+#include "system/mshv.h"
+#include "system/accel-irq.h"
+
+int accel_irqchip_add_msi_route(KVMRouteChange *c, int vector, PCIDevice *dev)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ return mshv_irqchip_add_msi_route(vector, dev);
+ }
+#endif
+ if (kvm_enabled()) {
+ return kvm_irqchip_add_msi_route(c, vector, dev);
+ }
+ return -ENOSYS;
+}
+
+int accel_irqchip_update_msi_route(int vector, MSIMessage msg, PCIDevice *dev)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ return mshv_irqchip_update_msi_route(vector, msg, dev);
+ }
+#endif
+ if (kvm_enabled()) {
+ return kvm_irqchip_update_msi_route(kvm_state, vector, msg, dev);
+ }
+ return -ENOSYS;
+}
+
+void accel_irqchip_commit_route_changes(KVMRouteChange *c)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ mshv_irqchip_commit_routes();
+ }
+#endif
+ if (kvm_enabled()) {
+ kvm_irqchip_commit_route_changes(c);
+ }
+}
+
+void accel_irqchip_commit_routes(void)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ mshv_irqchip_commit_routes();
+ }
+#endif
+ if (kvm_enabled()) {
+ kvm_irqchip_commit_routes(kvm_state);
+ }
+}
+
+void accel_irqchip_release_virq(int virq)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ mshv_irqchip_release_virq(virq);
+ }
+#endif
+ if (kvm_enabled()) {
+ kvm_irqchip_release_virq(kvm_state, virq);
+ }
+}
+
+int accel_irqchip_add_irqfd_notifier_gsi(EventNotifier *n, EventNotifier *rn,
+ int virq)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ return mshv_irqchip_add_irqfd_notifier_gsi(n, rn, virq);
+ }
+#endif
+ if (kvm_enabled()) {
+ return kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, rn, virq);
+ }
+ return -ENOSYS;
+}
+
+int accel_irqchip_remove_irqfd_notifier_gsi(EventNotifier *n, int virq)
+{
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+ if (mshv_msi_via_irqfd_enabled()) {
+ return mshv_irqchip_remove_irqfd_notifier_gsi(n, virq);
+ }
+#endif
+ if (kvm_enabled()) {
+ return kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, n, virq);
+ }
+ return -ENOSYS;
+}
diff --git a/accel/meson.build b/accel/meson.build
index 25b0f100b5..6349efe682 100644
--- a/accel/meson.build
+++ b/accel/meson.build
@@ -1,6 +1,6 @@
common_ss.add(files('accel-common.c'))
specific_ss.add(files('accel-target.c'))
-system_ss.add(files('accel-system.c', 'accel-blocker.c', 'accel-qmp.c'))
+system_ss.add(files('accel-system.c', 'accel-blocker.c', 'accel-qmp.c', 'accel-irq.c'))
user_ss.add(files('accel-user.c'))
subdir('tcg')
diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index 133bef852d..e431d00311 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -30,12 +30,18 @@
#include "hw/intc/ioapic_internal.h"
#include "hw/pci/msi.h"
#include "hw/qdev-properties.h"
+#include "system/accel-irq.h"
#include "system/kvm.h"
#include "system/system.h"
#include "hw/i386/apic-msidef.h"
#include "hw/i386/x86-iommu.h"
#include "trace.h"
+
+#if defined(CONFIG_KVM) || defined(CONFIG_MSHV)
+#define ACCEL_GSI_IRQFD_POSSIBLE
+#endif
+
#define APIC_DELIVERY_MODE_SHIFT 8
#define APIC_POLARITY_SHIFT 14
#define APIC_TRIG_MODE_SHIFT 15
@@ -191,10 +197,10 @@ static void ioapic_set_irq(void *opaque, int vector, int level)
static void ioapic_update_kvm_routes(IOAPICCommonState *s)
{
-#ifdef CONFIG_KVM
+#ifdef ACCEL_GSI_IRQFD_POSSIBLE
int i;
- if (kvm_irqchip_is_split()) {
+ if (accel_irqchip_is_split()) {
for (i = 0; i < IOAPIC_NUM_PINS; i++) {
MSIMessage msg;
struct ioapic_entry_info info;
@@ -202,15 +208,15 @@ static void ioapic_update_kvm_routes(IOAPICCommonState *s)
if (!info.masked) {
msg.address = info.addr;
msg.data = info.data;
- kvm_irqchip_update_msi_route(kvm_state, i, msg, NULL);
+ accel_irqchip_update_msi_route(i, msg, NULL);
}
}
- kvm_irqchip_commit_routes(kvm_state);
+ accel_irqchip_commit_routes();
}
#endif
}
-#ifdef CONFIG_KVM
+#ifdef ACCEL_KERNEL_GSI_IRQFD_POSSIBLE
static void ioapic_iec_notifier(void *private, bool global,
uint32_t index, uint32_t mask)
{
@@ -428,11 +434,11 @@ static const MemoryRegionOps ioapic_io_ops = {
static void ioapic_machine_done_notify(Notifier *notifier, void *data)
{
-#ifdef CONFIG_KVM
+#ifdef ACCEL_KERNEL_GSI_IRQFD_POSSIBLE
IOAPICCommonState *s = container_of(notifier, IOAPICCommonState,
machine_done);
- if (kvm_irqchip_is_split()) {
+ if (accel_irqchip_is_split()) {
X86IOMMUState *iommu = x86_iommu_get_default();
if (iommu) {
/* Register this IOAPIC with IOMMU IEC notifier, so that
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 767216d795..0cdc16217f 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -34,6 +34,7 @@
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "hw/loader.h"
+#include "system/accel-irq.h"
#include "system/kvm.h"
#include "hw/virtio/virtio-pci.h"
#include "qemu/range.h"
@@ -825,11 +826,11 @@ static int kvm_virtio_pci_vq_vector_use(VirtIOPCIProxy *proxy,
if (irqfd->users == 0) {
KVMRouteChange c = kvm_irqchip_begin_route_changes(kvm_state);
- ret = kvm_irqchip_add_msi_route(&c, vector, &proxy->pci_dev);
+ ret = accel_irqchip_add_msi_route(&c, vector, &proxy->pci_dev);
if (ret < 0) {
return ret;
}
- kvm_irqchip_commit_route_changes(&c);
+ accel_irqchip_commit_route_changes(&c);
irqfd->virq = ret;
}
irqfd->users++;
@@ -841,7 +842,7 @@ static void kvm_virtio_pci_vq_vector_release(VirtIOPCIProxy *proxy,
{
VirtIOIRQFD *irqfd = &proxy->vector_irqfd[vector];
if (--irqfd->users == 0) {
- kvm_irqchip_release_virq(kvm_state, irqfd->virq);
+ accel_irqchip_release_virq(irqfd->virq);
}
}
@@ -850,7 +851,7 @@ static int kvm_virtio_pci_irqfd_use(VirtIOPCIProxy *proxy,
unsigned int vector)
{
VirtIOIRQFD *irqfd = &proxy->vector_irqfd[vector];
- return kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL, irqfd->virq);
+ return accel_irqchip_add_irqfd_notifier_gsi(n, NULL, irqfd->virq);
}
static void kvm_virtio_pci_irqfd_release(VirtIOPCIProxy *proxy,
@@ -860,7 +861,7 @@ static void kvm_virtio_pci_irqfd_release(VirtIOPCIProxy *proxy,
VirtIOIRQFD *irqfd = &proxy->vector_irqfd[vector];
int ret;
- ret = kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, n, irqfd->virq);
+ ret = accel_irqchip_remove_irqfd_notifier_gsi(n, irqfd->virq);
assert(ret == 0);
}
static int virtio_pci_get_notifier(VirtIOPCIProxy *proxy, int queue_no,
@@ -995,12 +996,12 @@ static int virtio_pci_one_vector_unmask(VirtIOPCIProxy *proxy,
if (proxy->vector_irqfd) {
irqfd = &proxy->vector_irqfd[vector];
if (irqfd->msg.data != msg.data || irqfd->msg.address != msg.address) {
- ret = kvm_irqchip_update_msi_route(kvm_state, irqfd->virq, msg,
- &proxy->pci_dev);
+ ret = accel_irqchip_update_msi_route(irqfd->virq, msg,
+ &proxy->pci_dev);
if (ret < 0) {
return ret;
}
- kvm_irqchip_commit_routes(kvm_state);
+ accel_irqchip_commit_routes();
}
}
@@ -1229,7 +1230,7 @@ static int virtio_pci_set_guest_notifiers(DeviceState *d, int nvqs, bool assign)
VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
int r, n;
bool with_irqfd = msix_enabled(&proxy->pci_dev) &&
- kvm_msi_via_irqfd_enabled();
+ accel_msi_via_irqfd_enabled() ;
nvqs = MIN(nvqs, VIRTIO_QUEUE_MAX);
@@ -1433,7 +1434,7 @@ static void virtio_pci_set_vector(VirtIODevice *vdev,
uint16_t new_vector)
{
bool kvm_irqfd = (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
- msix_enabled(&proxy->pci_dev) && kvm_msi_via_irqfd_enabled();
+ msix_enabled(&proxy->pci_dev) && accel_msi_via_irqfd_enabled();
if (new_vector == old_vector) {
return;
diff --git a/include/system/accel-irq.h b/include/system/accel-irq.h
new file mode 100644
index 0000000000..671fb7dfdb
--- /dev/null
+++ b/include/system/accel-irq.h
@@ -0,0 +1,37 @@
+/*
+ * Accelerated irqchip abstraction
+ *
+ * Copyright Microsoft, Corp. 2025
+ *
+ * Authors: Ziqiao Zhou <ziqiaozhou@microsoft.com>
+ * Magnus Kulke <magnuskulke@microsoft.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef SYSTEM_ACCEL_IRQ_H
+#define SYSTEM_ACCEL_IRQ_H
+#include "hw/pci/msi.h"
+#include "qemu/osdep.h"
+#include "system/kvm.h"
+#include "system/mshv.h"
+
+static inline bool accel_msi_via_irqfd_enabled(void)
+{
+ return mshv_msi_via_irqfd_enabled() || kvm_msi_via_irqfd_enabled();
+}
+
+static inline bool accel_irqchip_is_split(void)
+{
+ return mshv_msi_via_irqfd_enabled() || kvm_irqchip_is_split();
+}
+
+int accel_irqchip_add_msi_route(KVMRouteChange *c, int vector, PCIDevice *dev);
+int accel_irqchip_update_msi_route(int vector, MSIMessage msg, PCIDevice *dev);
+void accel_irqchip_commit_route_changes(KVMRouteChange *c);
+void accel_irqchip_commit_routes(void);
+void accel_irqchip_release_virq(int virq);
+int accel_irqchip_add_irqfd_notifier_gsi(EventNotifier *n, EventNotifier *rn,
+ int virq);
+int accel_irqchip_remove_irqfd_notifier_gsi(EventNotifier *n, int virq);
+#endif
diff --git a/include/system/mshv.h b/include/system/mshv.h
index 342f1ef6a9..2a504ed81f 100644
--- a/include/system/mshv.h
+++ b/include/system/mshv.h
@@ -22,4 +22,21 @@
#define CONFIG_MSHV_IS_POSSIBLE
#endif
+#ifdef CONFIG_MSHV_IS_POSSIBLE
+extern bool mshv_allowed;
+#define mshv_enabled() (mshv_allowed)
+#else /* CONFIG_MSHV_IS_POSSIBLE */
+#define mshv_enabled() false
+#endif
+#define mshv_msi_via_irqfd_enabled() false
+
+/* interrupt */
+int mshv_irqchip_add_msi_route(int vector, PCIDevice *dev);
+int mshv_irqchip_update_msi_route(int virq, MSIMessage msg, PCIDevice *dev);
+void mshv_irqchip_commit_routes(void);
+void mshv_irqchip_release_virq(int virq);
+int mshv_irqchip_add_irqfd_notifier_gsi(const EventNotifier *n,
+ const EventNotifier *rn, int virq);
+int mshv_irqchip_remove_irqfd_notifier_gsi(const EventNotifier *n, int virq);
+
#endif
--
2.47.3

68
kvm-hw-intc-ioapic-Fix-ACCEL_KERNEL_GSI_IRQFD_POSSIBLE-t.patch Normal file
View File

@ -0,0 +1,68 @@
From 7ecba7856c08f410391ccb12620aeb304d800815 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Thu, 6 Nov 2025 11:51:48 +0100
Subject: [PATCH 3/4] hw/intc/ioapic: Fix ACCEL_KERNEL_GSI_IRQFD_POSSIBLE typo
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: 449: hw/intc/ioapic: Fix ACCEL_KERNEL_GSI_IRQFD_POSSIBLE typo
RH-Jira: RHEL-139028
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] 61c1a3f68e0a5403a90f1d1f2cb793cc83e0cea9 (clegoate/qemu-kvm-centos)
Commit 638ac1c78457 introduced a regression in interrupt remapping
when running a VM configured with an intel-iommu device and an
assigned PCI VF. During boot, Linux reports repeated messages :
[ 15.416794] __common_interrupt: 2.37 No irq handler for vector
[ 15.417266] __common_interrupt: 2.37 No irq handler for vector
[ 15.417733] __common_interrupt: 2.37 No irq handler for vector
[ 15.418202] __common_interrupt: 2.37 No irq handler for vector
[ 15.418670] __common_interrupt: 2.37 No irq handler for vector
and may eventually hang.
The issue is caused by the incorrect use of the macro
ACCEL_KERNEL_GSI_IRQFD_POSSIBLE, which should instead be
ACCEL_GSI_IRQFD_POSSIBLE.
Fixes: 638ac1c78457 ("hw/intc: Generalize APIC helper names from kvm_* to accel_*")
Cc: Magnus Kulke <magnuskulke@linux.microsoft.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20251106105148.737093-1-clg@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
(cherry picked from commit 3abfbb571143ba865488b6c11f8ad75dda97d1a3)
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/intc/ioapic.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index e431d00311..38e4384648 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -216,7 +216,7 @@ static void ioapic_update_kvm_routes(IOAPICCommonState *s)
#endif
}
-#ifdef ACCEL_KERNEL_GSI_IRQFD_POSSIBLE
+#ifdef ACCEL_GSI_IRQFD_POSSIBLE
static void ioapic_iec_notifier(void *private, bool global,
uint32_t index, uint32_t mask)
{
@@ -434,7 +434,7 @@ static const MemoryRegionOps ioapic_io_ops = {
static void ioapic_machine_done_notify(Notifier *notifier, void *data)
{
-#ifdef ACCEL_KERNEL_GSI_IRQFD_POSSIBLE
+#ifdef ACCEL_GSI_IRQFD_POSSIBLE
IOAPICCommonState *s = container_of(notifier, IOAPICCommonState,
machine_done);
--
2.47.3

150
kvm-hw-pci-Introduce-pci_setup_iommu_per_bus-for-per-bus.patch Normal file
View File

@ -0,0 +1,150 @@
From 34d06db7ea02cd3a0a07082fef93e08bfbf0b06a Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:28 +0100
Subject: [PATCH 10/16] hw/pci: Introduce pci_setup_iommu_per_bus() for per-bus
IOMMU ops retrieval
RH-Author: Eric Auger <eric.auger@redhat.com>
RH-MergeRequest: 423: hw/arm/virt: Add support for user creatable SMMUv3 device
RH-Jira: RHEL-73800
RH-Acked-by: Gavin Shan <gshan@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Sebastian Ott <sebott@redhat.com>
RH-Acked-by: Donald Dutile <None>
RH-Commit: [6/11] 0c41f77254cd66a3648c14c5d4ba2dfdbd396665 (eauger1/centos-qemu-kvm)
Currently, pci_setup_iommu() registers IOMMU ops for a given PCIBus.
However, when retrieving IOMMU ops for a device using
pci_device_get_iommu_bus_devfn(), the function checks the parent_dev
and fetches IOMMU ops from the parent device, even if the current
bus does not have any associated IOMMU ops.
This behavior works for now because QEMU's IOMMU implementations are
globally scoped, and host bridges rely on the bypass_iommu property
to skip IOMMU translation when needed.
However, this model will break with the soon to be introduced
arm-smmuv3 device, which allows users to associate the IOMMU
with a specific PCIe root complex (e.g., the default pcie.0
or a pxb-pcie root complex).
For example, consider the following setup with multiple root
complexes:
-device arm-smmuv3,primary-bus=pcie.0,id=smmuv3.0 \
...
-device pxb-pcie,id=pcie.1,bus_nr=8,bus=pcie.0 \
-device pcie-root-port,id=pcie.port1,bus=pcie.1 \
-device virtio-net-pci,bus=pcie.port1
In Qemu, pxb-pcie acts as a special root complex whose parent is
effectively the default root complex(pcie.0). Hence, though pcie.1
has no associated SMMUv3 as per above, pci_device_get_iommu_bus_devfn()
will incorrectly return the IOMMU ops from pcie.0 due to the fallback
via parent_dev.
To fix this, introduce a new helper pci_setup_iommu_per_bus() that
explicitly sets the new iommu_per_bus field in the PCIBus structure.
This helper will be used in a subsequent patch that adds support for
the new arm-smmuv3 device.
Update pci_device_get_iommu_bus_devfn() to use iommu_per_bus when
determining the correct IOMMU ops, ensuring accurate behavior for
per-bus IOMMUs.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nathan Chen <nathanc@nvidia.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Message-id: 20250829082543.7680-7-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 951bc76fb669eab96cc60e38a50097ad4435163e)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
hw/pci/pci.c | 31 +++++++++++++++++++++++++++++++
include/hw/pci/pci.h | 2 ++
include/hw/pci/pci_bus.h | 1 +
3 files changed, 34 insertions(+)
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index c70b5ceeba..0012cc12e7 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -2909,6 +2909,19 @@ static void pci_device_get_iommu_bus_devfn(PCIDevice *dev,
}
}
+ /*
+ * When multiple PCI Express Root Buses are defined using pxb-pcie,
+ * the IOMMU configuration may be specific to each root bus. However,
+ * pxb-pcie acts as a special root complex whose parent is effectively
+ * the default root complex(pcie.0). Ensure that we retrieve the
+ * correct IOMMU ops(if any) in such cases.
+ */
+ if (pci_bus_is_express(iommu_bus) && pci_bus_is_root(iommu_bus)) {
+ if (parent_bus->iommu_per_bus) {
+ break;
+ }
+ }
+
iommu_bus = parent_bus;
}
@@ -3169,6 +3182,24 @@ void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque)
bus->iommu_opaque = opaque;
}
+/*
+ * Similar to pci_setup_iommu(), but sets iommu_per_bus to true,
+ * indicating that the IOMMU is specific to this bus. This is used by
+ * IOMMU implementations that are tied to a specific PCIe root complex.
+ *
+ * In QEMU, pxb-pcie behaves as a special root complex whose parent is
+ * effectively the default root complex (pcie.0). The iommu_per_bus
+ * is checked in pci_device_get_iommu_bus_devfn() to ensure the correct
+ * IOMMU ops are returned, avoiding the use of the parent’s IOMMU when
+ * it's not appropriate.
+ */
+void pci_setup_iommu_per_bus(PCIBus *bus, const PCIIOMMUOps *ops,
+ void *opaque)
+{
+ pci_setup_iommu(bus, ops, opaque);
+ bus->iommu_per_bus = true;
+}
+
static void pci_dev_get_w64(PCIBus *b, PCIDevice *dev, void *opaque)
{
Range *range = opaque;
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 6b7d3ac8a3..6bccb25ac2 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -773,6 +773,8 @@ int pci_iommu_unregister_iotlb_notifier(PCIDevice *dev, uint32_t pasid,
*/
void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque);
+void pci_setup_iommu_per_bus(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque);
+
pcibus_t pci_bar_address(PCIDevice *d,
int reg, uint8_t type, pcibus_t size);
diff --git a/include/hw/pci/pci_bus.h b/include/hw/pci/pci_bus.h
index 2261312546..c738446788 100644
--- a/include/hw/pci/pci_bus.h
+++ b/include/hw/pci/pci_bus.h
@@ -35,6 +35,7 @@ struct PCIBus {
enum PCIBusFlags flags;
const PCIIOMMUOps *iommu_ops;
void *iommu_opaque;
+ bool iommu_per_bus;
uint8_t devfn_min;
uint32_t slot_reserved_mask;
pci_set_irq_fn set_irq;
--
2.47.3

83
kvm-hw-s390x-Fix-a-possible-crash-with-passed-through-vi.patch Normal file
View File

@ -0,0 +1,83 @@
From f607a40a84b80b2cb33ef3bb42b60b84af596cc9 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Tue, 18 Nov 2025 18:40:47 +0100
Subject: [PATCH 3/4] hw/s390x: Fix a possible crash with passed-through virtio
devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 427: s390x: Fix a possible crash with passed-through virtio devices
RH-Jira: RHEL-128085
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: Cédric Le Goater <clg@redhat.com>
RH-Commit: [1/1] a368a65a46a8d85f7ae83cfb5af23b1a341ea9d4 (thuth/qemu-kvm-cs)
JIRA: https://issues.redhat.com/browse/RHEL-128085
Consider the following nested setup: An L1 host uses some virtio device
(e.g. virtio-keyboard) for the L2 guest, and this L2 guest passes this
device through to the L3 guest. Since the L3 guest sees a virtio device,
it might send virtio notifications to the QEMU in L2 for that device.
But since the QEMU in L2 defined this device as vfio-ccw, the function
handle_virtio_ccw_notify() cannot handle this and crashes: It calls
virtio_ccw_get_vdev() that casts sch->driver_data into a VirtioCcwDevice,
but since "sch" belongs to a vfio-ccw device, that driver_data rather
points to a CcwDevice instead. So as soon as QEMU tries to use some
VirtioCcwDevice specific data from that device, we've lost.
We must not take virtio notifications for such devices. Thus fix the
issue by adding a check to the handle_virtio_ccw_notify() handler to
refuse all devices that are not our own virtio devices. Like in the
other branches that detect wrong settings, we return -EINVAL from the
function, which will later be placed in GPR2 to inform the guest about
the error.
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Tested-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-ID: <20251118174047.73103-1-thuth@redhat.com>
(cherry picked from commit e5cb62e7b6f99d45a42f0cd358d76d6ee2cef5cd)
---
hw/s390x/s390-hypercall.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/hw/s390x/s390-hypercall.c b/hw/s390x/s390-hypercall.c
index ac1b08b2cd..508dd97ca0 100644
--- a/hw/s390x/s390-hypercall.c
+++ b/hw/s390x/s390-hypercall.c
@@ -10,6 +10,7 @@
*/
#include "qemu/osdep.h"
+#include "qemu/error-report.h"
#include "cpu.h"
#include "hw/s390x/s390-virtio-ccw.h"
#include "hw/s390x/s390-hypercall.h"
@@ -42,6 +43,19 @@ static int handle_virtio_ccw_notify(uint64_t subch_id, uint64_t data)
if (!sch || !css_subch_visible(sch)) {
return -EINVAL;
}
+ if (sch->id.cu_type != VIRTIO_CCW_CU_TYPE) {
+ /*
+ * This might happen in nested setups: If the L1 host defined the
+ * L2 guest with a virtio device (e.g. virtio-keyboard), and the
+ * L2 guest passes this device through to the L3 guest, the L3 guest
+ * might send virtio notifications to the QEMU in L2 for that device.
+ * But since the QEMU in L2 defined this device as vfio-ccw, it's not
+ * a VirtIODevice that we can handle here!
+ */
+ warn_report_once("Got virtio notification for unsupported device "
+ "on subchannel %02x.%1x.%04x!", cssid, ssid, schid);
+ return -EINVAL;
+ }
vdev = virtio_ccw_get_vdev(sch);
if (vq_idx >= VIRTIO_QUEUE_MAX || !virtio_queue_get_num(vdev, vq_idx)) {
--
2.47.3

89
kvm-hw-uefi-add-variable-digest-to-vmstate.patch Normal file
View File

@ -0,0 +1,89 @@
From b12eac2c22066ee4ff568a4108b38d7bdcd958cc Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Wed, 4 Mar 2026 08:05:34 +0100
Subject: [PATCH 1/2] hw/uefi: add variable digest to vmstate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Gerd Hoffmann <kraxel@redhat.com>
RH-MergeRequest: 471: hw/uefi: add variable digest to vmstate
RH-Jira: RHEL-153058
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] c300b30db6bafaacd11b8383531f04873bc8b428 (kraxel.rh/centos-src-qemu-kvm)
Add digest to vmstate if needed. Also clear digest before loading
to make sure it is initialized.
Fixes: db1ecfb473ac ("hw/uefi: add var-service-vars.c")
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20260304075954.584423-1-kraxel@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
(cherry picked from commit b28c3ad1d63c2fe167b6f93fad1616ecd769e599)
Resolves: RHEL-153058
---
hw/uefi/var-service-vars.c | 36 ++++++++++++++++++++++++++++++++++++
1 file changed, 36 insertions(+)
diff --git a/hw/uefi/var-service-vars.c b/hw/uefi/var-service-vars.c
index 8533533ea5..ed4e0a6494 100644
--- a/hw/uefi/var-service-vars.c
+++ b/hw/uefi/var-service-vars.c
@@ -37,8 +37,40 @@ const VMStateDescription vmstate_uefi_time = {
},
};
+static int uefi_vars_pre_load(void *opaque)
+{
+ uefi_variable *var = opaque;
+
+ /* clear digest which is optional in the live migration data stream */
+ var->digest = NULL;
+ var->digest_size = 0;
+ return 0;
+}
+
+static bool uefi_vars_digest_is_needed(void *opaque)
+{
+ uefi_variable *var = opaque;
+
+ if ((var->attributes & EFI_VARIABLE_TIME_BASED_AUTHENTICATED_WRITE_ACCESS) &&
+ !uefi_vars_is_sb_any(var)) {
+ return true;
+ }
+ return false;
+}
+
+const VMStateDescription vmstate_uefi_variable_digest = {
+ .name = "uefi-variable-digest",
+ .needed = uefi_vars_digest_is_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT32(digest_size, uefi_variable),
+ VMSTATE_VBUFFER_ALLOC_UINT32(digest, uefi_variable, 0, NULL, digest_size),
+ VMSTATE_END_OF_LIST()
+ },
+};
+
const VMStateDescription vmstate_uefi_variable = {
.name = "uefi-variable",
+ .pre_load = uefi_vars_pre_load,
.fields = (VMStateField[]) {
VMSTATE_UINT8_ARRAY_V(guid.data, uefi_variable, sizeof(QemuUUID), 0),
VMSTATE_UINT32(name_size, uefi_variable),
@@ -49,6 +81,10 @@ const VMStateDescription vmstate_uefi_variable = {
VMSTATE_STRUCT(time, uefi_variable, 0, vmstate_uefi_time, efi_time),
VMSTATE_END_OF_LIST()
},
+ .subsections = (const VMStateDescription * const []) {
+ &vmstate_uefi_variable_digest,
+ NULL
+ }
};
uefi_variable *uefi_vars_find_variable(uefi_vars_state *uv, QemuUUID guid,
--
2.47.3

1264
kvm-include-hw-hyperv-Add-MSHV-ABI-header-definitions.patch Normal file
View File

File diff suppressed because it is too large Load Diff

189
kvm-io-fix-use-after-free-in-websocket-handshake-code.patch Normal file
View File

@ -0,0 +1,189 @@
From 728cf99416aaaae2cc0fca6ee88f28ccec33d697 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jmaloy@redhat.com>
Date: Tue, 4 Nov 2025 17:28:47 -0500
Subject: [PATCH 02/16] io: fix use after free in websocket handshake code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 419: io: move websock resource release to close method
RH-Jira: RHEL-120116
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/2] acdb5414387815a8b2f0a84a151990875947e855 (jmaloy/jmaloy-qemu-kvm-2)
JIRA: https://issues.redhat.com/browse/RHEL-120116
CVE: CVE-2025-11234
commit b7a1f2ca45c7865b9e98e02ae605a65fc9458ae9
Author: Daniel P. Berrangé <berrange@redhat.com>
Date: Tue Sep 30 12:03:15 2025 +0100
io: fix use after free in websocket handshake code
If the QIOChannelWebsock object is freed while it is waiting to
complete a handshake, a GSource is leaked. This can lead to the
callback firing later on and triggering a use-after-free in the
use of the channel. This was observed in the VNC server with the
following trace from valgrind:
==2523108== Invalid read of size 4
==2523108== at 0x4054A24: vnc_disconnect_start (vnc.c:1296)
==2523108== by 0x4054A24: vnc_client_error (vnc.c:1392)
==2523108== by 0x4068A09: vncws_handshake_done (vnc-ws.c:105)
==2523108== by 0x44863B4: qio_task_complete (task.c:197)
==2523108== by 0x448343D: qio_channel_websock_handshake_io (channel-websock.c:588)
==2523108== by 0x6EDB862: UnknownInlinedFun (gmain.c:3398)
==2523108== by 0x6EDB862: g_main_context_dispatch_unlocked.lto_priv.0 (gmain.c:4249)
==2523108== by 0x6EDBAE4: g_main_context_dispatch (gmain.c:4237)
==2523108== by 0x45EC79F: glib_pollfds_poll (main-loop.c:287)
==2523108== by 0x45EC79F: os_host_main_loop_wait (main-loop.c:310)
==2523108== by 0x45EC79F: main_loop_wait (main-loop.c:589)
==2523108== by 0x423A56D: qemu_main_loop (runstate.c:835)
==2523108== by 0x454F300: qemu_default_main (main.c:37)
==2523108== by 0x73D6574: (below main) (libc_start_call_main.h:58)
==2523108== Address 0x57a6e0dc is 28 bytes inside a block of size 103,608 free'd
==2523108== at 0x5F2FE43: free (vg_replace_malloc.c:989)
==2523108== by 0x6EDC444: g_free (gmem.c:208)
==2523108== by 0x4053F23: vnc_update_client (vnc.c:1153)
==2523108== by 0x4053F23: vnc_refresh (vnc.c:3225)
==2523108== by 0x4042881: dpy_refresh (console.c:880)
==2523108== by 0x4042881: gui_update (console.c:90)
==2523108== by 0x45EFA1B: timerlist_run_timers.part.0 (qemu-timer.c:562)
==2523108== by 0x45EFC8F: timerlist_run_timers (qemu-timer.c:495)
==2523108== by 0x45EFC8F: qemu_clock_run_timers (qemu-timer.c:576)
==2523108== by 0x45EFC8F: qemu_clock_run_all_timers (qemu-timer.c:663)
==2523108== by 0x45EC765: main_loop_wait (main-loop.c:600)
==2523108== by 0x423A56D: qemu_main_loop (runstate.c:835)
==2523108== by 0x454F300: qemu_default_main (main.c:37)
==2523108== by 0x73D6574: (below main) (libc_start_call_main.h:58)
==2523108== Block was alloc'd at
==2523108== at 0x5F343F3: calloc (vg_replace_malloc.c:1675)
==2523108== by 0x6EE2F81: g_malloc0 (gmem.c:133)
==2523108== by 0x4057DA3: vnc_connect (vnc.c:3245)
==2523108== by 0x448591B: qio_net_listener_channel_func (net-listener.c:54)
==2523108== by 0x6EDB862: UnknownInlinedFun (gmain.c:3398)
==2523108== by 0x6EDB862: g_main_context_dispatch_unlocked.lto_priv.0 (gmain.c:4249)
==2523108== by 0x6EDBAE4: g_main_context_dispatch (gmain.c:4237)
==2523108== by 0x45EC79F: glib_pollfds_poll (main-loop.c:287)
==2523108== by 0x45EC79F: os_host_main_loop_wait (main-loop.c:310)
==2523108== by 0x45EC79F: main_loop_wait (main-loop.c:589)
==2523108== by 0x423A56D: qemu_main_loop (runstate.c:835)
==2523108== by 0x454F300: qemu_default_main (main.c:37)
==2523108== by 0x73D6574: (below main) (libc_start_call_main.h:58)
==2523108==
The above can be reproduced by launching QEMU with
$ qemu-system-x86_64 -vnc localhost:0,websocket=5700
and then repeatedly running:
for i in {1..100}; do
(echo -n "GET / HTTP/1.1" && sleep 0.05) | nc -w 1 localhost 5700 &
done
CVE-2025-11234
Reported-by: Grant Millar | Cylo <rid@cylo.io>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
include/io/channel-websock.h | 3 ++-
io/channel-websock.c | 22 ++++++++++++++++------
2 files changed, 18 insertions(+), 7 deletions(-)
diff --git a/include/io/channel-websock.h b/include/io/channel-websock.h
index e180827c57..6700cf8946 100644
--- a/include/io/channel-websock.h
+++ b/include/io/channel-websock.h
@@ -61,7 +61,8 @@ struct QIOChannelWebsock {
size_t payload_remain;
size_t pong_remain;
QIOChannelWebsockMask mask;
- guint io_tag;
+ guint hs_io_tag; /* tracking handshake task */
+ guint io_tag; /* tracking watch task */
Error *io_err;
gboolean io_eof;
uint8_t opcode;
diff --git a/io/channel-websock.c b/io/channel-websock.c
index a19b902ff9..ec5e09f9ab 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -545,6 +545,7 @@ static gboolean qio_channel_websock_handshake_send(QIOChannel *ioc,
trace_qio_channel_websock_handshake_fail(ioc, error_get_pretty(err));
qio_task_set_error(task, err);
qio_task_complete(task);
+ wioc->hs_io_tag = 0;
return FALSE;
}
@@ -560,6 +561,7 @@ static gboolean qio_channel_websock_handshake_send(QIOChannel *ioc,
trace_qio_channel_websock_handshake_complete(ioc);
qio_task_complete(task);
}
+ wioc->hs_io_tag = 0;
return FALSE;
}
trace_qio_channel_websock_handshake_pending(ioc, G_IO_OUT);
@@ -586,6 +588,7 @@ static gboolean qio_channel_websock_handshake_io(QIOChannel *ioc,
trace_qio_channel_websock_handshake_fail(ioc, error_get_pretty(err));
qio_task_set_error(task, err);
qio_task_complete(task);
+ wioc->hs_io_tag = 0;
return FALSE;
}
if (ret == 0) {
@@ -597,7 +600,7 @@ static gboolean qio_channel_websock_handshake_io(QIOChannel *ioc,
error_propagate(&wioc->io_err, err);
trace_qio_channel_websock_handshake_reply(ioc);
- qio_channel_add_watch(
+ wioc->hs_io_tag = qio_channel_add_watch(
wioc->master,
G_IO_OUT,
qio_channel_websock_handshake_send,
@@ -907,11 +910,12 @@ void qio_channel_websock_handshake(QIOChannelWebsock *ioc,
trace_qio_channel_websock_handshake_start(ioc);
trace_qio_channel_websock_handshake_pending(ioc, G_IO_IN);
- qio_channel_add_watch(ioc->master,
- G_IO_IN,
- qio_channel_websock_handshake_io,
- task,
- NULL);
+ ioc->hs_io_tag = qio_channel_add_watch(
+ ioc->master,
+ G_IO_IN,
+ qio_channel_websock_handshake_io,
+ task,
+ NULL);
}
@@ -922,6 +926,9 @@ static void qio_channel_websock_finalize(Object *obj)
buffer_free(&ioc->encinput);
buffer_free(&ioc->encoutput);
buffer_free(&ioc->rawinput);
+ if (ioc->hs_io_tag) {
+ g_source_remove(ioc->hs_io_tag);
+ }
if (ioc->io_tag) {
g_source_remove(ioc->io_tag);
}
@@ -1222,6 +1229,9 @@ static int qio_channel_websock_close(QIOChannel *ioc,
buffer_free(&wioc->encinput);
buffer_free(&wioc->encoutput);
buffer_free(&wioc->rawinput);
+ if (wioc->hs_io_tag) {
+ g_clear_handle_id(&wioc->hs_io_tag, g_source_remove);
+ }
if (wioc->io_tag) {
g_clear_handle_id(&wioc->io_tag, g_source_remove);
}
--
2.47.3

84
kvm-io-move-websock-resource-release-to-close-method.patch Normal file
View File

@ -0,0 +1,84 @@
From 9aaede253bb55035f0a1171fb1c4eda847ca9493 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jmaloy@redhat.com>
Date: Tue, 4 Nov 2025 17:23:29 -0500
Subject: [PATCH 01/16] io: move websock resource release to close method
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 419: io: move websock resource release to close method
RH-Jira: RHEL-120116
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/2] ca3067b2afed8d770626436b77fdd90bd5cb22e7 (jmaloy/jmaloy-qemu-kvm-2)
JIRA: https://issues.redhat.com/browse/RHEL-120116
CVE: CVE-2025-11234
commit 322c3c4f3abee616a18b3bfe563ec29dd67eae63
Author: Daniel P. Berrangé <berrange@redhat.com>
Date: Tue Sep 30 11:58:35 2025 +0100
io: move websock resource release to close method
The QIOChannelWebsock object releases all its resources in the
finalize callback. This is later than desired, as callers expect
to be able to call qio_channel_close() to fully close a channel
and release resources related to I/O.
The logic in the finalize method is at most a failsafe to handle
cases where a consumer forgets to call qio_channel_close.
This adds equivalent logic to the close method to release the
resources, using g_clear_handle_id/g_clear_pointer to be robust
against repeated invocations. The finalize method is tweaked
so that the GSource is removed before releasing the underlying
channel.
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
io/channel-websock.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/io/channel-websock.c b/io/channel-websock.c
index 08ddb274f0..a19b902ff9 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -922,13 +922,13 @@ static void qio_channel_websock_finalize(Object *obj)
buffer_free(&ioc->encinput);
buffer_free(&ioc->encoutput);
buffer_free(&ioc->rawinput);
- object_unref(OBJECT(ioc->master));
if (ioc->io_tag) {
g_source_remove(ioc->io_tag);
}
if (ioc->io_err) {
error_free(ioc->io_err);
}
+ object_unref(OBJECT(ioc->master));
}
@@ -1219,6 +1219,15 @@ static int qio_channel_websock_close(QIOChannel *ioc,
QIOChannelWebsock *wioc = QIO_CHANNEL_WEBSOCK(ioc);
trace_qio_channel_websock_close(ioc);
+ buffer_free(&wioc->encinput);
+ buffer_free(&wioc->encoutput);
+ buffer_free(&wioc->rawinput);
+ if (wioc->io_tag) {
+ g_clear_handle_id(&wioc->io_tag, g_source_remove);
+ }
+ if (wioc->io_err) {
+ g_clear_pointer(&wioc->io_err, error_free);
+ }
return qio_channel_close(wioc->master, errp);
}
--
2.47.3

278
kvm-io-uring-Resubmit-tails-of-short-writes.patch Normal file
View File

@ -0,0 +1,278 @@
From 1bdac2a8c4ac77133cb0c2b4d40819bff1a35fc4 Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Tue, 24 Mar 2026 09:43:36 +0100
Subject: [PATCH 4/4] io-uring: Resubmit tails of short writes
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 479: linux-aio/io-uring: Resubmit tails of short requests
RH-Jira: RHEL-158224
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [4/4] 7ff66622acbb5dbdbacafe71bffd0a277ac919d9 (hreitz/qemu-kvm-c-9-s)
Short writes can happen, too, not just short reads. The difference to
aio=native is that the kernel will actually retry the tail of short
requests internally already -- so it is harder to reproduce. But if the
tail of a short request returns an error to the kernel, we will see it
in userspace still. To reproduce this, apply the following patch on top
of the one shown in HEAD^ (again %s/escaped // to apply):
escaped diff --git a/block/export/fuse.c b/block/export/fuse.c
escaped index 67dc50a412..2b98489a32 100644
escaped --- a/block/export/fuse.c
escaped +++ b/block/export/fuse.c
@@ -1059,8 +1059,15 @@ fuse_co_read(FuseExport *exp, void **bufptr, uint64_t offset, uint32_t size)
int64_t blk_len;
void *buf;
int ret;
+ static uint32_t error_size;
- size = MIN(size, 4096);
+ if (error_size == size) {
+ error_size = 0;
+ return -EIO;
+ } else if (size > 4096) {
+ error_size = size - 4096;
+ size = 4096;
+ }
/* Limited by max_read, should not happen */
if (size > FUSE_MAX_READ_BYTES) {
@@ -1111,8 +1118,15 @@ fuse_co_write(FuseExport *exp, struct fuse_write_out *out,
{
int64_t blk_len;
int ret;
+ static uint32_t error_size;
- size = MIN(size, 4096);
+ if (error_size == size) {
+ error_size = 0;
+ return -EIO;
+ } else if (size > 4096) {
+ error_size = size - 4096;
+ size = 4096;
+ }
QEMU_BUILD_BUG_ON(FUSE_MAX_WRITE_BYTES > BDRV_REQUEST_MAX_BYTES);
/* Limited by max_write, should not happen */
I know this is a bit artificial because to produce this, there must be
an I/O error somewhere anyway, but if it does happen, qemu will
understand it to mean ENOSPC for short writes, which is incorrect. So I
believe we need to resubmit the tail to maybe have it succeed now, or at
least get the correct error code.
Reproducer as before:
$ ./qemu-img create -f raw test.raw 8k
Formatting 'test.raw', fmt=raw size=8192
$ ./qemu-io -f raw -c 'write -P 42 0 8k' test.raw
wrote 8192/8192 bytes at offset 0
8 KiB, 1 ops; 00.00 sec (64.804 MiB/sec and 8294.9003 ops/sec)
$ hexdump -C test.raw
00000000 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a |****************|
*
00002000
$ storage-daemon/qemu-storage-daemon \
--blockdev file,node-name=test,filename=test.raw \
--export fuse,id=exp,node-name=test,mountpoint=test.raw,writable=true
$ ./qemu-io --image-opts -c 'read -P 23 0 8k' \
driver=file,filename=test.raw,cache.direct=on,aio=io_uring
read 8192/8192 bytes at offset 0
8 KiB, 1 ops; 00.00 sec (58.481 MiB/sec and 7485.5342 ops/sec)
$ ./qemu-io --image-opts -c 'write -P 23 0 8k' \
driver=file,filename=test.raw,cache.direct=on,aio=io_uring
write failed: No space left on device
$ hexdump -C test.raw
00000000 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 |................|
*
00001000 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a |****************|
*
00002000
So short reads already work (because there is code for that), but short
writes incorrectly produce ENOSPC. This patch fixes that by
resubmitting not only the tail of short reads but short writes also.
(And this patch uses the opportunity to make it so qemu_iovec_destroy()
is called only if req->resubmit_qiov.iov is non-NULL. Functionally a
non-op, but this is how the code generally checks whether the
resubmit_qiov has been set up or not.)
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20260324084338.37453-4-hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit cf9cdaea6e24d13dfdf8402f6829d2ca4dca864b)
Conflicts:
- block/io_uring.c, block/trace-events
Missing 047dabef97bd0c4af3c3dc453b19e20345de3602 ("block/io_uring: use
aio_add_sqe()") downstream, which changed quite a few things about the
io-uring code. Backporting it seems excessive, though, especially
given that it would pull in even more dependencies (general aio and
aio-posix changes that come right before 047dabef).
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/io_uring.c | 77 +++++++++++++++++++++++++---------------------
block/trace-events | 2 +-
2 files changed, 43 insertions(+), 36 deletions(-)
diff --git a/block/io_uring.c b/block/io_uring.c
index 5dbafc8f7b..582550f8e9 100644
--- a/block/io_uring.c
+++ b/block/io_uring.c
@@ -31,14 +31,14 @@ typedef struct LuringAIOCB {
struct io_uring_sqe sqeq;
ssize_t ret;
QEMUIOVector *qiov;
- bool is_read;
+ int type;
QSIMPLEQ_ENTRY(LuringAIOCB) next;
/*
- * Buffered reads may require resubmission, see
- * luring_resubmit_short_read().
+ * Short reads/writes require resubmission, see
+ * luring_resubmit_short_io().
*/
- int total_read;
+ int total_done;
QEMUIOVector resubmit_qiov;
} LuringAIOCB;
@@ -73,22 +73,27 @@ static void luring_resubmit(LuringState *s, LuringAIOCB *luringcb)
}
/**
- * luring_resubmit_short_read:
+ * luring_resubmit_short_io:
*
- * Short reads are rare but may occur. The remaining read request needs to be
- * resubmitted.
+ * Short reads and writes are rare but may occur. The remaining request needs
+ * to be resubmitted.
+ *
+ * For example, short reads can be reproduced by a FUSE export deliberately
+ * executing short reads. The tail of short writes is generally resubmitted by
+ * io-uring in the kernel, but if that resubmission encounters an I/O error, the
+ * already submitted portion will be returned as a short write.
*/
-static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb,
- int nread)
+static void luring_resubmit_short_io(LuringState *s, LuringAIOCB *luringcb,
+ int ndone)
{
QEMUIOVector *resubmit_qiov;
size_t remaining;
- trace_luring_resubmit_short_read(s, luringcb, nread);
+ trace_luring_resubmit_short_io(s, luringcb, ndone);
- /* Update read position */
- luringcb->total_read += nread;
- remaining = luringcb->qiov->size - luringcb->total_read;
+ /* Update I/O position */
+ luringcb->total_done += ndone;
+ remaining = luringcb->qiov->size - luringcb->total_done;
/* Shorten qiov */
resubmit_qiov = &luringcb->resubmit_qiov;
@@ -97,11 +102,11 @@ static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb,
} else {
qemu_iovec_reset(resubmit_qiov);
}
- qemu_iovec_concat(resubmit_qiov, luringcb->qiov, luringcb->total_read,
+ qemu_iovec_concat(resubmit_qiov, luringcb->qiov, luringcb->total_done,
remaining);
/* Update sqe */
- luringcb->sqeq.off += nread;
+ luringcb->sqeq.off += ndone;
luringcb->sqeq.addr = (uintptr_t)luringcb->resubmit_qiov.iov;
luringcb->sqeq.len = luringcb->resubmit_qiov.niov;
@@ -165,8 +170,8 @@ static bool luring_process_completions(LuringState *s)
s->io_q.in_flight--;
trace_luring_process_completion(s, luringcb, ret);
- /* total_read is non-zero only for resubmitted read requests */
- total_bytes = ret + luringcb->total_read;
+ /* total_done is non-zero only for resubmitted requests */
+ total_bytes = ret + luringcb->total_done;
if (ret < 0) {
/*
@@ -192,27 +197,29 @@ static bool luring_process_completions(LuringState *s)
goto end;
} else if (total_bytes == luringcb->qiov->size) {
ret = 0;
- /* Only read/write */
+ } else if (ret > 0 && (luringcb->type == QEMU_AIO_READ ||
+ luringcb->type == QEMU_AIO_WRITE)) {
+ luring_resubmit_short_io(s, luringcb, ret);
+ resubmit = true;
+ continue;
+ } else if (luringcb->type == QEMU_AIO_READ) {
+ /* Read ret == 0: EOF, pad with zeroes */
+ qemu_iovec_memset(luringcb->qiov, total_bytes, 0,
+ luringcb->qiov->size - total_bytes);
+ ret = 0;
} else {
- /* Short Read/Write */
- if (luringcb->is_read) {
- if (ret > 0) {
- luring_resubmit_short_read(s, luringcb, ret);
- resubmit = true;
- continue;
- } else {
- /* Pad with zeroes */
- qemu_iovec_memset(luringcb->qiov, total_bytes, 0,
- luringcb->qiov->size - total_bytes);
- ret = 0;
- }
- } else {
- ret = -ENOSPC;
- }
+ /*
+ * Normal write ret == 0 means ENOSPC.
+ * For zone-append, we treat any 0 <= ret < qiov->size as ENOSPC,
+ * too, because resubmitting the tail seems a little unsafe.
+ */
+ ret = -ENOSPC;
}
end:
luringcb->ret = ret;
- qemu_iovec_destroy(&luringcb->resubmit_qiov);
+ if (luringcb->resubmit_qiov.iov) {
+ qemu_iovec_destroy(&luringcb->resubmit_qiov);
+ }
/*
* If the coroutine is already entered it must be in ioq_submit()
@@ -409,7 +416,7 @@ int coroutine_fn luring_co_submit(BlockDriverState *bs, int fd, uint64_t offset,
.co = qemu_coroutine_self(),
.ret = -EINPROGRESS,
.qiov = qiov,
- .is_read = (type == QEMU_AIO_READ),
+ .type = type,
};
trace_luring_co_submit(bs, s, &luringcb, fd, offset, qiov ? qiov->size : 0,
type);
diff --git a/block/trace-events b/block/trace-events
index 8e789e1f12..99b8c12bc8 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -70,7 +70,7 @@ luring_do_submit_done(void *s, int ret) "LuringState %p submitted to kernel %d"
luring_co_submit(void *bs, void *s, void *luringcb, int fd, uint64_t offset, size_t nbytes, int type) "bs %p s %p luringcb %p fd %d offset %" PRId64 " nbytes %zd type %d"
luring_process_completion(void *s, void *aiocb, int ret) "LuringState %p luringcb %p ret %d"
luring_io_uring_submit(void *s, int ret) "LuringState %p ret %d"
-luring_resubmit_short_read(void *s, void *luringcb, int nread) "LuringState %p luringcb %p nread %d"
+luring_resubmit_short_io(void *s, void *luringcb, int ndone) "LuringState %p luringcb %p ndone %d"
# qcow2.c
qcow2_add_task(void *co, void *bs, void *pool, const char *action, int cluster_type, uint64_t host_offset, uint64_t offset, uint64_t bytes, void *qiov, size_t qiov_offset) "co %p bs %p pool %p: %s: cluster_type %d file_cluster_offset %" PRIu64 " offset %" PRIu64 " bytes %" PRIu64 " qiov %p qiov_offset %zu"
--
2.47.3

61
kvm-iotests-244-Don-t-store-data-file-with-protocol-in-i.patch
View File

@ -1,61 +0,0 @@
From 80e197ac72a4b0c810f69833e1f9e552a415e82a Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 25 Apr 2024 14:49:40 +0200
Subject: [PATCH 2/4] iotests/244: Don't store data-file with protocol in image
RH-Author: Hana Czenczek <hczenczek@redhat.com>
RH-MergeRequest: 1: CVE 2024-4467 (PRDSC)
RH-Jira: RHEL-46239
RH-CVE: CVE-2024-4467
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Commit: [2/4] 92e00dab8be1570b13172353d77d2af44cb4e22b
We want to disable filename parsing for data files because it's too easy
to abuse in malicious image files. Make the test ready for the change by
passing the data file explicitly in command line options.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Upstream: N/A, embargoed
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
tests/qemu-iotests/244 | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244
index 3e61fa25bb..bb9cc6512f 100755
--- a/tests/qemu-iotests/244
+++ b/tests/qemu-iotests/244
@@ -215,9 +215,22 @@ $QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG"
$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG"
# blkdebug doesn't support copy offloading, so this tests the error path
-$QEMU_IMG amend -f $IMGFMT -o "data_file=blkdebug::$TEST_IMG.data" "$TEST_IMG"
-$QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG"
-$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG"
+test_img_with_blkdebug="json:{
+ 'driver': 'qcow2',
+ 'file': {
+ 'driver': 'file',
+ 'filename': '$TEST_IMG'
+ },
+ 'data-file': {
+ 'driver': 'blkdebug',
+ 'image': {
+ 'driver': 'file',
+ 'filename': '$TEST_IMG.data'
+ }
+ }
+}"
+$QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$test_img_with_blkdebug"
+$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$test_img_with_blkdebug"
echo
echo "=== Flushing should flush the data file ==="
--
2.39.3

64
kvm-iotests-270-Don-t-store-data-file-with-json-prefix-i.patch
View File

@ -1,64 +0,0 @@
From bf01c03b0120f5ed8e54c2a30b7830901b22b893 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 25 Apr 2024 14:49:40 +0200
Subject: [PATCH 3/4] iotests/270: Don't store data-file with json: prefix in
image
RH-Author: Hana Czenczek <hczenczek@redhat.com>
RH-MergeRequest: 1: CVE 2024-4467 (PRDSC)
RH-Jira: RHEL-46239
RH-CVE: CVE-2024-4467
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Eric Blake <eblake@redhat.com>
RH-Commit: [3/4] 705bcc2819ce8e0f8b9d660a93bc48de26413aec
We want to disable filename parsing for data files because it's too easy
to abuse in malicious image files. Make the test ready for the change by
passing the data file explicitly in command line options.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
Upstream: N/A, embargoed
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
tests/qemu-iotests/270 | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/tests/qemu-iotests/270 b/tests/qemu-iotests/270
index 74352342db..c37b674aa2 100755
--- a/tests/qemu-iotests/270
+++ b/tests/qemu-iotests/270
@@ -60,8 +60,16 @@ _make_test_img -o cluster_size=2M,data_file="$TEST_IMG.orig" \
# "write" 2G of data without using any space.
# (qemu-img create does not like it, though, because null-co does not
# support image creation.)
-$QEMU_IMG amend -o data_file="json:{'driver':'null-co',,'size':'4294967296'}" \
- "$TEST_IMG"
+test_img_with_null_data="json:{
+ 'driver': '$IMGFMT',
+ 'file': {
+ 'filename': '$TEST_IMG'
+ },
+ 'data-file': {
+ 'driver': 'null-co',
+ 'size':'4294967296'
+ }
+}"
# This gives us a range of:
# 2^31 - 512 + 768 - 1 = 2^31 + 255 > 2^31
@@ -74,7 +82,7 @@ $QEMU_IMG amend -o data_file="json:{'driver':'null-co',,'size':'4294967296'}" \
# on L2 boundaries, we need large L2 tables; hence the cluster size of
# 2 MB. (Anything from 256 kB should work, though, because then one L2
# table covers 8 GB.)
-$QEMU_IO -c "write 768 $((2 ** 31 - 512))" "$TEST_IMG" | _filter_qemu_io
+$QEMU_IO -c "write 768 $((2 ** 31 - 512))" "$test_img_with_null_data" | _filter_qemu_io
_check_test_img
--
2.39.3

276
kvm-iotests-test-NBD-TLS-iothread.patch
View File

@ -1,276 +0,0 @@
From 2f12be8abfc90dc383a221441f60bdaae6b617d2 Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Fri, 17 May 2024 21:50:15 -0500
Subject: [PATCH 4/4] iotests: test NBD+TLS+iothread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/4] 39a37bf3ae6e7046577de151ef2f6fd1fd694e62 (ebblake/centos-qemu-kvm)
Prevent regressions when using NBD with TLS in the presence of
iothreads, adding coverage the fix to qio channels made in the
previous patch.
The shell function pick_unused_port() was copied from
nbdkit.git/tests/functions.sh.in, where it had all authors from Red
Hat, agreeing to the resulting relicensing from 2-clause BSD to GPLv2.
CC: qemu-stable@nongnu.org
CC: "Richard W.M. Jones" <rjones@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240531180639.1392905-6-eblake@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit a73c99378022ebb785481e84cfe1e81097546268)
Jira: https://issues.redhat.com/browse/RHEL-40959
Signed-off-by: Eric Blake <eblake@redhat.com>
---
tests/qemu-iotests/tests/nbd-tls-iothread | 168 ++++++++++++++++++
tests/qemu-iotests/tests/nbd-tls-iothread.out | 54 ++++++
2 files changed, 222 insertions(+)
create mode 100755 tests/qemu-iotests/tests/nbd-tls-iothread
create mode 100644 tests/qemu-iotests/tests/nbd-tls-iothread.out
diff --git a/tests/qemu-iotests/tests/nbd-tls-iothread b/tests/qemu-iotests/tests/nbd-tls-iothread
new file mode 100755
index 0000000000..a2fb07206e
--- /dev/null
+++ b/tests/qemu-iotests/tests/nbd-tls-iothread
@@ -0,0 +1,168 @@
+#!/usr/bin/env bash
+# group: rw quick
+#
+# Test of NBD+TLS+iothread
+#
+# Copyright (C) 2024 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=eblake@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_qemu
+ _cleanup_test_img
+ rm -f "$dst_image"
+ tls_x509_cleanup
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+cd ..
+. ./common.rc
+. ./common.filter
+. ./common.qemu
+. ./common.tls
+. ./common.nbd
+
+_supported_fmt qcow2 # Hardcoded to qcow2 command line and QMP below
+_supported_proto file
+
+# pick_unused_port
+#
+# Picks and returns an "unused" port, setting the global variable
+# $port.
+#
+# This is inherently racy, but we need it because qemu does not currently
+# permit NBD+TLS over a Unix domain socket
+pick_unused_port ()
+{
+ if ! (ss --version) >/dev/null 2>&1; then
+ _notrun "ss utility required, skipped this test"
+ fi
+
+ # Start at a random port to make it less likely that two parallel
+ # tests will conflict.
+ port=$(( 50000 + (RANDOM%15000) ))
+ while ss -ltn | grep -sqE ":$port\b"; do
+ ((port++))
+ if [ $port -eq 65000 ]; then port=50000; fi
+ done
+ echo picked unused port
+}
+
+tls_x509_init
+
+size=1G
+DST_IMG="$TEST_DIR/dst.qcow2"
+
+echo
+echo "== preparing TLS creds and spare port =="
+
+pick_unused_port
+tls_x509_create_root_ca "ca1"
+tls_x509_create_server "ca1" "server1"
+tls_x509_create_client "ca1" "client1"
+tls_obj_base=tls-creds-x509,id=tls0,verify-peer=true,dir="${tls_dir}"
+
+echo
+echo "== preparing image =="
+
+_make_test_img $size
+$QEMU_IMG create -f qcow2 "$DST_IMG" $size | _filter_img_create
+
+echo
+echo === Starting Src QEMU ===
+echo
+
+_launch_qemu -machine q35 \
+ -object iothread,id=iothread0 \
+ -object "${tls_obj_base}"/client1,endpoint=client \
+ -device '{"driver":"pcie-root-port", "id":"root0", "multifunction":true,
+ "bus":"pcie.0"}' \
+ -device '{"driver":"virtio-scsi-pci", "id":"virtio_scsi_pci0",
+ "bus":"root0", "iothread":"iothread0"}' \
+ -device '{"driver":"scsi-hd", "id":"image1", "drive":"drive_image1",
+ "bus":"virtio_scsi_pci0.0"}' \
+ -blockdev '{"driver":"file", "cache":{"direct":true, "no-flush":false},
+ "filename":"'"$TEST_IMG"'", "node-name":"drive_sys1"}' \
+ -blockdev '{"driver":"qcow2", "node-name":"drive_image1",
+ "file":"drive_sys1"}'
+h1=$QEMU_HANDLE
+_send_qemu_cmd $h1 '{"execute": "qmp_capabilities"}' 'return'
+
+echo
+echo === Starting Dst VM2 ===
+echo
+
+_launch_qemu -machine q35 \
+ -object iothread,id=iothread0 \
+ -object "${tls_obj_base}"/server1,endpoint=server \
+ -device '{"driver":"pcie-root-port", "id":"root0", "multifunction":true,
+ "bus":"pcie.0"}' \
+ -device '{"driver":"virtio-scsi-pci", "id":"virtio_scsi_pci0",
+ "bus":"root0", "iothread":"iothread0"}' \
+ -device '{"driver":"scsi-hd", "id":"image1", "drive":"drive_image1",
+ "bus":"virtio_scsi_pci0.0"}' \
+ -blockdev '{"driver":"file", "cache":{"direct":true, "no-flush":false},
+ "filename":"'"$DST_IMG"'", "node-name":"drive_sys1"}' \
+ -blockdev '{"driver":"qcow2", "node-name":"drive_image1",
+ "file":"drive_sys1"}' \
+ -incoming defer
+h2=$QEMU_HANDLE
+_send_qemu_cmd $h2 '{"execute": "qmp_capabilities"}' 'return'
+
+echo
+echo === Dst VM: Enable NBD server for incoming storage migration ===
+echo
+
+_send_qemu_cmd $h2 '{"execute": "nbd-server-start", "arguments":
+ {"addr": {"type": "inet", "data": {"host": "127.0.0.1", "port": "'$port'"}},
+ "tls-creds": "tls0"}}' '{"return": {}}' | sed "s/\"$port\"/PORT/g"
+_send_qemu_cmd $h2 '{"execute": "block-export-add", "arguments":
+ {"node-name": "drive_image1", "type": "nbd", "writable": true,
+ "id": "drive_image1"}}' '{"return": {}}'
+
+echo
+echo === Src VM: Mirror to dst NBD for outgoing storage migration ===
+echo
+
+_send_qemu_cmd $h1 '{"execute": "blockdev-add", "arguments":
+ {"node-name": "mirror", "driver": "nbd",
+ "server": {"type": "inet", "host": "127.0.0.1", "port": "'$port'"},
+ "export": "drive_image1", "tls-creds": "tls0",
+ "tls-hostname": "127.0.0.1"}}' '{"return": {}}' | sed "s/\"$port\"/PORT/g"
+_send_qemu_cmd $h1 '{"execute": "blockdev-mirror", "arguments":
+ {"sync": "full", "device": "drive_image1", "target": "mirror",
+ "job-id": "drive_image1_53"}}' '{"return": {}}'
+_timed_wait_for $h1 '"ready"'
+
+echo
+echo === Cleaning up ===
+echo
+
+_send_qemu_cmd $h1 '{"execute":"quit"}' ''
+_send_qemu_cmd $h2 '{"execute":"quit"}' ''
+
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/tests/nbd-tls-iothread.out b/tests/qemu-iotests/tests/nbd-tls-iothread.out
new file mode 100644
index 0000000000..1d83d4f903
--- /dev/null
+++ b/tests/qemu-iotests/tests/nbd-tls-iothread.out
@@ -0,0 +1,54 @@
+QA output created by nbd-tls-iothread
+
+== preparing TLS creds and spare port ==
+picked unused port
+Generating a self signed certificate...
+Generating a signed certificate...
+Generating a signed certificate...
+
+== preparing image ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
+Formatting 'TEST_DIR/dst.IMGFMT', fmt=IMGFMT size=1073741824
+
+=== Starting Src QEMU ===
+
+{"execute": "qmp_capabilities"}
+{"return": {}}
+
+=== Starting Dst VM2 ===
+
+{"execute": "qmp_capabilities"}
+{"return": {}}
+
+=== Dst VM: Enable NBD server for incoming storage migration ===
+
+{"execute": "nbd-server-start", "arguments":
+ {"addr": {"type": "inet", "data": {"host": "127.0.0.1", "port": PORT}},
+ "tls-creds": "tls0"}}
+{"return": {}}
+{"execute": "block-export-add", "arguments":
+ {"node-name": "drive_image1", "type": "nbd", "writable": true,
+ "id": "drive_image1"}}
+{"return": {}}
+
+=== Src VM: Mirror to dst NBD for outgoing storage migration ===
+
+{"execute": "blockdev-add", "arguments":
+ {"node-name": "mirror", "driver": "nbd",
+ "server": {"type": "inet", "host": "127.0.0.1", "port": PORT},
+ "export": "drive_image1", "tls-creds": "tls0",
+ "tls-hostname": "127.0.0.1"}}
+{"return": {}}
+{"execute": "blockdev-mirror", "arguments":
+ {"sync": "full", "device": "drive_image1", "target": "mirror",
+ "job-id": "drive_image1_53"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "drive_image1_53"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "drive_image1_53"}}
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "drive_image1_53"}}
+
+=== Cleaning up ===
+
+{"execute":"quit"}
+{"execute":"quit"}
+*** done
--
2.39.3

127
kvm-linux-aio-Put-all-parameters-into-qemu_laiocb.patch Normal file
View File

@ -0,0 +1,127 @@
From 30c3962bbef6ce083f326988f35741dd21aaf09d Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Tue, 24 Mar 2026 09:43:34 +0100
Subject: [PATCH 1/4] linux-aio: Put all parameters into qemu_laiocb
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 479: linux-aio/io-uring: Resubmit tails of short requests
RH-Jira: RHEL-158224
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/4] f449ea0c49a093bbec59b24fb44308e7f58c9ed2 (hreitz/qemu-kvm-c-9-s)
Put all request parameters into the qemu_laiocb struct, which will allow
re-submitting the tail of short reads/writes.
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20260324084338.37453-2-hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit cc03b62df47a09c507e199cc043f57bdc941cc67)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/linux-aio.c | 34 ++++++++++++++++++++++------------
1 file changed, 22 insertions(+), 12 deletions(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index c200e7ad20..c2c5e11946 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -41,9 +41,15 @@ struct qemu_laiocb {
LinuxAioState *ctx;
struct iocb iocb;
ssize_t ret;
+ off_t offset;
size_t nbytes;
QEMUIOVector *qiov;
- bool is_read;
+
+ int fd;
+ int type;
+ BdrvRequestFlags flags;
+
+ uint64_t dev_max_batch;
QSIMPLEQ_ENTRY(qemu_laiocb) next;
};
@@ -87,7 +93,7 @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
ret = 0;
} else if (ret >= 0) {
/* Short reads mean EOF, pad with zeros. */
- if (laiocb->is_read) {
+ if (laiocb->type == QEMU_AIO_READ) {
qemu_iovec_memset(laiocb->qiov, ret, 0,
laiocb->qiov->size - ret);
} else {
@@ -367,23 +373,23 @@ static void laio_deferred_fn(void *opaque)
}
}
-static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
- int type, BdrvRequestFlags flags,
- uint64_t dev_max_batch)
+static int laio_do_submit(struct qemu_laiocb *laiocb)
{
LinuxAioState *s = laiocb->ctx;
struct iocb *iocbs = &laiocb->iocb;
QEMUIOVector *qiov = laiocb->qiov;
+ int fd = laiocb->fd;
+ off_t offset = laiocb->offset;
- switch (type) {
+ switch (laiocb->type) {
case QEMU_AIO_WRITE:
#ifdef HAVE_IO_PREP_PWRITEV2
{
- int laio_flags = (flags & BDRV_REQ_FUA) ? RWF_DSYNC : 0;
+ int laio_flags = (laiocb->flags & BDRV_REQ_FUA) ? RWF_DSYNC : 0;
io_prep_pwritev2(iocbs, fd, qiov->iov, qiov->niov, offset, laio_flags);
}
#else
- assert(flags == 0);
+ assert(laiocb->flags == 0);
io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
#endif
break;
@@ -399,7 +405,7 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
/* Currently Linux kernel does not support other operations */
default:
fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
- __func__, type);
+ __func__, laiocb->type);
return -EIO;
}
io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
@@ -407,7 +413,7 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
QSIMPLEQ_INSERT_TAIL(&s->io_q.pending, laiocb, next);
s->io_q.in_queue++;
if (!s->io_q.blocked) {
- if (s->io_q.in_queue >= laio_max_batch(s, dev_max_batch)) {
+ if (s->io_q.in_queue >= laio_max_batch(s, laiocb->dev_max_batch)) {
ioq_submit(s);
} else {
defer_call(laio_deferred_fn, s);
@@ -425,14 +431,18 @@ int coroutine_fn laio_co_submit(int fd, uint64_t offset, QEMUIOVector *qiov,
AioContext *ctx = qemu_get_current_aio_context();
struct qemu_laiocb laiocb = {
.co = qemu_coroutine_self(),
+ .offset = offset,
.nbytes = qiov ? qiov->size : 0,
.ctx = aio_get_linux_aio(ctx),
.ret = -EINPROGRESS,
- .is_read = (type == QEMU_AIO_READ),
.qiov = qiov,
+ .fd = fd,
+ .type = type,
+ .flags = flags,
+ .dev_max_batch = dev_max_batch,
};
- ret = laio_do_submit(fd, &laiocb, offset, type, flags, dev_max_batch);
+ ret = laio_do_submit(&laiocb);
if (ret < 0) {
return ret;
}
--
2.47.3

215
kvm-linux-aio-Resubmit-tails-of-short-reads-writes.patch Normal file
View File

@ -0,0 +1,215 @@
From ad3a6c9b3487226d9622120eaea8218bd6050a04 Mon Sep 17 00:00:00 2001
From: Hanna Czenczek <hreitz@redhat.com>
Date: Tue, 24 Mar 2026 09:43:35 +0100
Subject: [PATCH 2/4] linux-aio: Resubmit tails of short reads/writes
RH-Author: Hanna Czenczek <hreitz@redhat.com>
RH-MergeRequest: 479: linux-aio/io-uring: Resubmit tails of short requests
RH-Jira: RHEL-158224
RH-Acked-by: Kevin Wolf <kwolf@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [2/4] f97271e609a150acc04a15ffc85c40e7bcb00060 (hreitz/qemu-kvm-c-9-s)
Short reads/writes can happen. One way to reproduce them is via our
FUSE export, with the following diff applied (%s/escaped // to apply --
if you put plain diffs in commit messages, git-am will apply them, and I
would rather avoid breaking FUSE accidentally via this patch):
escaped diff --git a/block/export/fuse.c b/block/export/fuse.c
escaped index a2a478d293..67dc50a412 100644
escaped --- a/block/export/fuse.c
escaped +++ b/block/export/fuse.c
@@ -828,7 +828,7 @@ static ssize_t coroutine_fn GRAPH_RDLOCK
fuse_co_init(FuseExport *exp, struct fuse_init_out *out,
const struct fuse_init_in_compat *in)
{
- const uint32_t supported_flags = FUSE_ASYNC_READ | FUSE_ASYNC_DIO;
+ const uint32_t supported_flags = FUSE_ASYNC_READ;
if (in->major != 7) {
error_report("FUSE major version mismatch: We have 7, but kernel has %"
@@ -1060,6 +1060,8 @@ fuse_co_read(FuseExport *exp, void **bufptr, uint64_t offset, uint32_t size)
void *buf;
int ret;
+ size = MIN(size, 4096);
+
/* Limited by max_read, should not happen */
if (size > FUSE_MAX_READ_BYTES) {
return -EINVAL;
@@ -1110,6 +1112,8 @@ fuse_co_write(FuseExport *exp, struct fuse_write_out *out,
int64_t blk_len;
int ret;
+ size = MIN(size, 4096);
+
QEMU_BUILD_BUG_ON(FUSE_MAX_WRITE_BYTES > BDRV_REQUEST_MAX_BYTES);
/* Limited by max_write, should not happen */
if (size > FUSE_MAX_WRITE_BYTES) {
Then:
$ ./qemu-img create -f raw test.raw 8k
Formatting 'test.raw', fmt=raw size=8192
$ ./qemu-io -f raw -c 'write -P 42 0 8k' test.raw
wrote 8192/8192 bytes at offset 0
8 KiB, 1 ops; 00.00 sec (64.804 MiB/sec and 8294.9003 ops/sec)
$ hexdump -C test.raw
00000000 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a |****************|
*
00002000
With aio=threads, short I/O works:
$ storage-daemon/qemu-storage-daemon \
--blockdev file,node-name=test,filename=test.raw \
--export fuse,id=exp,node-name=test,mountpoint=test.raw,writable=true
Other shell:
$ ./qemu-io --image-opts -c 'read -P 42 0 8k' \
driver=file,filename=test.raw,cache.direct=on,aio=threads
read 8192/8192 bytes at offset 0
8 KiB, 1 ops; 00.00 sec (36.563 MiB/sec and 4680.0923 ops/sec)
$ ./qemu-io --image-opts -c 'write -P 23 0 8k' \
driver=file,filename=test.raw,cache.direct=on,aio=threads
wrote 8192/8192 bytes at offset 0
8 KiB, 1 ops; 00.00 sec (35.995 MiB/sec and 4607.2970 ops/sec)
$ hexdump -C test.raw
00000000 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 |................|
*
00002000
But with aio=native, it does not:
$ ./qemu-io --image-opts -c 'read -P 23 0 8k' \
driver=file,filename=test.raw,cache.direct=on,aio=native
Pattern verification failed at offset 0, 8192 bytes
read 8192/8192 bytes at offset 0
8 KiB, 1 ops; 00.00 sec (86.155 MiB/sec and 11027.7900 ops/sec)
$ ./qemu-io --image-opts -c 'write -P 42 0 8k' \
driver=file,filename=test.raw,cache.direct=on,aio=native
write failed: No space left on device
$ hexdump -C test.raw
00000000 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a |****************|
*
00001000 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 |................|
*
00002000
This patch fixes that.
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-ID: <20260324084338.37453-3-hreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 7eca3d4883be8d328377001a9ea7ae9882b00f3c)
Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
---
block/linux-aio.c | 56 ++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 50 insertions(+), 6 deletions(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index c2c5e11946..84397de54c 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -45,6 +45,10 @@ struct qemu_laiocb {
size_t nbytes;
QEMUIOVector *qiov;
+ /* For handling short reads/writes */
+ size_t total_done;
+ QEMUIOVector resubmit_qiov;
+
int fd;
int type;
BdrvRequestFlags flags;
@@ -74,28 +78,61 @@ struct LinuxAioState {
};
static void ioq_submit(LinuxAioState *s);
+static int laio_do_submit(struct qemu_laiocb *laiocb);
static inline ssize_t io_event_ret(struct io_event *ev)
{
return (ssize_t)(((uint64_t)ev->res2 << 32) | ev->res);
}
+/**
+ * Retry tail of short requests.
+ */
+static int laio_resubmit_short_io(struct qemu_laiocb *laiocb, size_t done)
+{
+ QEMUIOVector *resubmit_qiov = &laiocb->resubmit_qiov;
+
+ laiocb->total_done += done;
+
+ if (!resubmit_qiov->iov) {
+ qemu_iovec_init(resubmit_qiov, laiocb->qiov->niov);
+ } else {
+ qemu_iovec_reset(resubmit_qiov);
+ }
+ qemu_iovec_concat(resubmit_qiov, laiocb->qiov,
+ laiocb->total_done, laiocb->nbytes - laiocb->total_done);
+
+ return laio_do_submit(laiocb);
+}
+
/*
* Completes an AIO request.
*/
static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
{
- int ret;
+ ssize_t ret;
ret = laiocb->ret;
if (ret != -ECANCELED) {
- if (ret == laiocb->nbytes) {
+ if (ret == laiocb->nbytes - laiocb->total_done) {
ret = 0;
+ } else if (ret > 0 && (laiocb->type == QEMU_AIO_READ ||
+ laiocb->type == QEMU_AIO_WRITE)) {
+ ret = laio_resubmit_short_io(laiocb, ret);
+ if (!ret) {
+ return;
+ }
} else if (ret >= 0) {
- /* Short reads mean EOF, pad with zeros. */
+ /*
+ * For normal reads and writes, we only get here if ret == 0, which
+ * means EOF for reads and ENOSPC for writes.
+ * For zone-append, we get here with any ret >= 0, which we just
+ * treat as ENOSPC, too (safer than resubmitting, probably, but not
+ * 100 % clear).
+ */
if (laiocb->type == QEMU_AIO_READ) {
- qemu_iovec_memset(laiocb->qiov, ret, 0,
- laiocb->qiov->size - ret);
+ qemu_iovec_memset(laiocb->qiov, laiocb->total_done, 0,
+ laiocb->qiov->size - laiocb->total_done);
} else {
ret = -ENOSPC;
}
@@ -103,6 +140,9 @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
}
laiocb->ret = ret;
+ if (laiocb->resubmit_qiov.iov) {
+ qemu_iovec_destroy(&laiocb->resubmit_qiov);
+ }
/*
* If the coroutine is already entered it must be in ioq_submit() and
@@ -379,7 +419,11 @@ static int laio_do_submit(struct qemu_laiocb *laiocb)
struct iocb *iocbs = &laiocb->iocb;
QEMUIOVector *qiov = laiocb->qiov;
int fd = laiocb->fd;
- off_t offset = laiocb->offset;
+ off_t offset = laiocb->offset + laiocb->total_done;
+
+ if (laiocb->resubmit_qiov.iov) {
+ qiov = &laiocb->resubmit_qiov;
+ }
switch (laiocb->type) {
case QEMU_AIO_WRITE:
--
2.47.3

126
kvm-linux-aio-add-IO_CMD_FDSYNC-command-support.patch
View File

@ -1,126 +0,0 @@
From 11faa773637f76f573f5320c063f7e55263c3a84 Mon Sep 17 00:00:00 2001
From: Prasad Pandit <pjp@fedoraproject.org>
Date: Thu, 25 Apr 2024 12:34:12 +0530
Subject: [PATCH 1/5] linux-aio: add IO_CMD_FDSYNC command support
RH-Author: Prasad Pandit <None>
RH-MergeRequest: 260: linux-aio: add IO_CMD_FDSYNC command support
RH-Jira: RHEL-51901
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/1] 2830edc801f9fbbc373631cf5b12a396f4b2bced (pjp/cs-qemu-kvm)
Libaio defines IO_CMD_FDSYNC command to sync all outstanding
asynchronous I/O operations, by flushing out file data to the
disk storage. Enable linux-aio to submit such aio request.
When using aio=native without fdsync() support, QEMU creates
pthreads, and destroying these pthreads results in TLB flushes.
In a real-time guest environment, TLB flushes cause a latency
spike. This patch helps to avoid such spikes.
Jira: https://issues.redhat.com/browse/RHEL-51901
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Prasad Pandit <pjp@fedoraproject.org>
Message-ID: <20240425070412.37248-1-ppandit@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 24687abf237e3c15816d689a8e4b08d7c3190dcb)
Signed-off-by: Prasad Pandit <pjp@fedoraproject.org>
---
block/file-posix.c | 9 +++++++++
block/linux-aio.c | 21 ++++++++++++++++++++-
include/block/raw-aio.h | 1 +
3 files changed, 30 insertions(+), 1 deletion(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index 35684f7e21..9831b08fb6 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -159,6 +159,7 @@ typedef struct BDRVRawState {
bool has_discard:1;
bool has_write_zeroes:1;
bool use_linux_aio:1;
+ bool has_laio_fdsync:1;
bool use_linux_io_uring:1;
int page_cache_inconsistent; /* errno from fdatasync failure */
bool has_fallocate;
@@ -718,6 +719,9 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
ret = -EINVAL;
goto fail;
}
+ if (s->use_linux_aio) {
+ s->has_laio_fdsync = laio_has_fdsync(s->fd);
+ }
#else
if (s->use_linux_aio) {
error_setg(errp, "aio=native was specified, but is not supported "
@@ -2599,6 +2603,11 @@ static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)
if (raw_check_linux_io_uring(s)) {
return luring_co_submit(bs, s->fd, 0, NULL, QEMU_AIO_FLUSH);
}
+#endif
+#ifdef CONFIG_LINUX_AIO
+ if (s->has_laio_fdsync && raw_check_linux_aio(s)) {
+ return laio_co_submit(s->fd, 0, NULL, QEMU_AIO_FLUSH, 0);
+ }
#endif
return raw_thread_pool_submit(handle_aiocb_flush, &acb);
}
diff --git a/block/linux-aio.c b/block/linux-aio.c
index ec05d946f3..e3b5ec9aba 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -384,6 +384,9 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
case QEMU_AIO_READ:
io_prep_preadv(iocbs, fd, qiov->iov, qiov->niov, offset);
break;
+ case QEMU_AIO_FLUSH:
+ io_prep_fdsync(iocbs, fd);
+ break;
/* Currently Linux kernel does not support other operations */
default:
fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
@@ -412,7 +415,7 @@ int coroutine_fn laio_co_submit(int fd, uint64_t offset, QEMUIOVector *qiov,
AioContext *ctx = qemu_get_current_aio_context();
struct qemu_laiocb laiocb = {
.co = qemu_coroutine_self(),
- .nbytes = qiov->size,
+ .nbytes = qiov ? qiov->size : 0,
.ctx = aio_get_linux_aio(ctx),
.ret = -EINPROGRESS,
.is_read = (type == QEMU_AIO_READ),
@@ -486,3 +489,19 @@ void laio_cleanup(LinuxAioState *s)
}
g_free(s);
}
+
+bool laio_has_fdsync(int fd)
+{
+ struct iocb cb;
+ struct iocb *cbs[] = {&cb, NULL};
+
+ io_context_t ctx = 0;
+ io_setup(1, &ctx);
+
+ /* check if host kernel supports IO_CMD_FDSYNC */
+ io_prep_fdsync(&cb, fd);
+ int ret = io_submit(ctx, 1, cbs);
+
+ io_destroy(ctx);
+ return (ret == -EINVAL) ? false : true;
+}
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index 20e000b8ef..626706827f 100644
--- a/include/block/raw-aio.h
+++ b/include/block/raw-aio.h
@@ -60,6 +60,7 @@ void laio_cleanup(LinuxAioState *s);
int coroutine_fn laio_co_submit(int fd, uint64_t offset, QEMUIOVector *qiov,
int type, uint64_t dev_max_batch);
+bool laio_has_fdsync(int);
void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context);
void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context);
#endif
--
2.39.3

941
kvm-linux-headers-Update-to-Linux-v6.17-rc1.patch Normal file
View File

@ -0,0 +1,941 @@
From b5bbab573e01c1225e7368dba469086a78bc1570 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 22 Sep 2025 16:18:17 +0200
Subject: [PATCH 08/19] linux-headers: Update to Linux v6.17-rc1
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 456: backport support for GSO over UDP tunnel offload
RH-Jira: RHEL-143785
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Commit: [3/14] 5b5aab965427deef98614bcfc99c4b3b9818b46d (lvivier/qemu-kvm-centos)
JIRA: https://issues.redhat.com/browse/RHEL-143785
Update headers to include the virtio GSO over UDP tunnel features
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <0b1f3c011f90583ab52aa4fef04df6db35cc4a69.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 8de6cd5452eb9c58c0d105dbc9718bd0e83cc70f)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
include/standard-headers/drm/drm_fourcc.h | 56 ++++++-
include/standard-headers/linux/ethtool.h | 4 +-
.../linux/input-event-codes.h | 8 +
include/standard-headers/linux/input.h | 1 +
include/standard-headers/linux/pci_regs.h | 9 +
include/standard-headers/linux/vhost_types.h | 5 +
include/standard-headers/linux/virtio_net.h | 33 ++++
linux-headers/LICENSES/preferred/GPL-2.0 | 10 +-
linux-headers/asm-arm64/unistd_64.h | 2 +
linux-headers/asm-generic/unistd.h | 8 +-
linux-headers/asm-loongarch/unistd_64.h | 2 +
linux-headers/asm-mips/unistd_n32.h | 2 +
linux-headers/asm-mips/unistd_n64.h | 2 +
linux-headers/asm-mips/unistd_o32.h | 2 +
linux-headers/asm-powerpc/kvm.h | 13 --
linux-headers/asm-powerpc/unistd_32.h | 2 +
linux-headers/asm-powerpc/unistd_64.h | 2 +
linux-headers/asm-riscv/kvm.h | 1 +
linux-headers/asm-riscv/unistd_32.h | 2 +
linux-headers/asm-riscv/unistd_64.h | 2 +
linux-headers/asm-s390/unistd_32.h | 2 +
linux-headers/asm-s390/unistd_64.h | 2 +
linux-headers/asm-x86/unistd_32.h | 2 +
linux-headers/asm-x86/unistd_64.h | 2 +
linux-headers/asm-x86/unistd_x32.h | 2 +
linux-headers/linux/iommufd.h | 154 +++++++++++++++++-
linux-headers/linux/kvm.h | 2 +
linux-headers/linux/vfio.h | 12 +-
linux-headers/linux/vhost.h | 35 ++++
29 files changed, 352 insertions(+), 27 deletions(-)
diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h
index c8309d378b..cef077dfb3 100644
--- a/include/standard-headers/drm/drm_fourcc.h
+++ b/include/standard-headers/drm/drm_fourcc.h
@@ -209,6 +209,10 @@ extern "C" {
#define DRM_FORMAT_RGBA1010102 fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */
#define DRM_FORMAT_BGRA1010102 fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */
+/* 48 bpp RGB */
+#define DRM_FORMAT_RGB161616 fourcc_code('R', 'G', '4', '8') /* [47:0] R:G:B 16:16:16 little endian */
+#define DRM_FORMAT_BGR161616 fourcc_code('B', 'G', '4', '8') /* [47:0] B:G:R 16:16:16 little endian */
+
/* 64 bpp RGB */
#define DRM_FORMAT_XRGB16161616 fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */
#define DRM_FORMAT_XBGR16161616 fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */
@@ -217,7 +221,7 @@ extern "C" {
#define DRM_FORMAT_ABGR16161616 fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */
/*
- * Floating point 64bpp RGB
+ * Half-Floating point - 16b/component
* IEEE 754-2008 binary16 half-precision float
* [15:0] sign:exponent:mantissa 1:5:10
*/
@@ -227,6 +231,20 @@ extern "C" {
#define DRM_FORMAT_ARGB16161616F fourcc_code('A', 'R', '4', 'H') /* [63:0] A:R:G:B 16:16:16:16 little endian */
#define DRM_FORMAT_ABGR16161616F fourcc_code('A', 'B', '4', 'H') /* [63:0] A:B:G:R 16:16:16:16 little endian */
+#define DRM_FORMAT_R16F fourcc_code('R', ' ', ' ', 'H') /* [15:0] R 16 little endian */
+#define DRM_FORMAT_GR1616F fourcc_code('G', 'R', ' ', 'H') /* [31:0] G:R 16:16 little endian */
+#define DRM_FORMAT_BGR161616F fourcc_code('B', 'G', 'R', 'H') /* [47:0] B:G:R 16:16:16 little endian */
+
+/*
+ * Floating point - 32b/component
+ * IEEE 754-2008 binary32 float
+ * [31:0] sign:exponent:mantissa 1:8:23
+ */
+#define DRM_FORMAT_R32F fourcc_code('R', ' ', ' ', 'F') /* [31:0] R 32 little endian */
+#define DRM_FORMAT_GR3232F fourcc_code('G', 'R', ' ', 'F') /* [63:0] R:G 32:32 little endian */
+#define DRM_FORMAT_BGR323232F fourcc_code('B', 'G', 'R', 'F') /* [95:0] R:G:B 32:32:32 little endian */
+#define DRM_FORMAT_ABGR32323232F fourcc_code('A', 'B', '8', 'F') /* [127:0] R:G:B:A 32:32:32:32 little endian */
+
/*
* RGBA format with 10-bit components packed in 64-bit per pixel, with 6 bits
* of unused padding per component:
@@ -376,6 +394,42 @@ extern "C" {
*/
#define DRM_FORMAT_Q401 fourcc_code('Q', '4', '0', '1')
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^6=64. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [6:10] little endian
+ * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian
+ * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian
+ */
+#define DRM_FORMAT_S010 fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S210 fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S410 fourcc_code('S', '4', '1', '0') /* non-subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^4=16. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [4:12] little endian
+ * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian
+ * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian
+ */
+#define DRM_FORMAT_S012 fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S212 fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S412 fourcc_code('S', '4', '1', '2') /* non-subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+
+/*
+ * 3 plane YCbCr
+ * index 0 = Y plane, [15:0] Y little endian
+ * index 1 = Cr plane, [15:0] Cr little endian
+ * index 2 = Cb plane, [15:0] Cb little endian
+ */
+#define DRM_FORMAT_S016 fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S216 fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S416 fourcc_code('S', '4', '1', '6') /* non-subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+
/*
* 3 plane YCbCr
* index 0: Y plane, [7:0] Y
diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h
index cef0d207a6..eb80314028 100644
--- a/include/standard-headers/linux/ethtool.h
+++ b/include/standard-headers/linux/ethtool.h
@@ -2314,7 +2314,7 @@ enum {
IPV6_USER_FLOW = 0x0e, /* spec only (usr_ip6_spec; nfc only) */
IPV4_FLOW = 0x10, /* hash only */
IPV6_FLOW = 0x11, /* hash only */
- ETHER_FLOW = 0x12, /* spec only (ether_spec) */
+ ETHER_FLOW = 0x12, /* hash or spec (ether_spec) */
/* Used for GTP-U IPv4 and IPv6.
* The format of GTP packets only includes
@@ -2371,7 +2371,7 @@ enum {
/* Flag to enable RSS spreading of traffic matching rule (nfc only) */
#define FLOW_RSS 0x20000000
-/* L3-L4 network traffic flow hash options */
+/* L2-L4 network traffic flow hash options */
#define RXH_L2DA (1 << 1)
#define RXH_VLAN (1 << 2)
#define RXH_L3_PROTO (1 << 3)
diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h
index a82ff795e0..00dc9caac9 100644
--- a/include/standard-headers/linux/input-event-codes.h
+++ b/include/standard-headers/linux/input-event-codes.h
@@ -601,6 +601,11 @@
#define BTN_DPAD_LEFT 0x222
#define BTN_DPAD_RIGHT 0x223
+#define BTN_GRIPL 0x224
+#define BTN_GRIPR 0x225
+#define BTN_GRIPL2 0x226
+#define BTN_GRIPR2 0x227
+
#define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */
#define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */
#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */
@@ -765,6 +770,9 @@
#define KEY_KBD_LCD_MENU4 0x2bb
#define KEY_KBD_LCD_MENU5 0x2bc
+/* Performance Boost key (Alienware)/G-Mode key (Dell) */
+#define KEY_PERFORMANCE 0x2bd
+
#define BTN_TRIGGER_HAPPY 0x2c0
#define BTN_TRIGGER_HAPPY1 0x2c0
#define BTN_TRIGGER_HAPPY2 0x2c1
diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h
index 942ea6aaa9..d4512c20b5 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -272,6 +272,7 @@ struct input_mask {
#define BUS_CEC 0x1E
#define BUS_INTEL_ISHTP 0x1F
#define BUS_AMD_SFH 0x20
+#define BUS_SDW 0x21
/*
* MT_TOOL types
diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h
index a3a3e942de..f5b17745de 100644
--- a/include/standard-headers/linux/pci_regs.h
+++ b/include/standard-headers/linux/pci_regs.h
@@ -745,6 +745,7 @@
#define PCI_EXT_CAP_ID_L1SS 0x1E /* L1 PM Substates */
#define PCI_EXT_CAP_ID_PTM 0x1F /* Precision Time Measurement */
#define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */
+#define PCI_EXT_CAP_ID_VF_REBAR 0x24 /* VF Resizable BAR */
#define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */
#define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */
#define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */
@@ -1141,6 +1142,14 @@
#define PCI_DVSEC_HEADER2 0x8 /* Designated Vendor-Specific Header2 */
#define PCI_DVSEC_HEADER2_ID(x) ((x) & 0xffff)
+/* VF Resizable BARs, same layout as PCI_REBAR */
+#define PCI_VF_REBAR_CAP PCI_REBAR_CAP
+#define PCI_VF_REBAR_CAP_SIZES PCI_REBAR_CAP_SIZES
+#define PCI_VF_REBAR_CTRL PCI_REBAR_CTRL
+#define PCI_VF_REBAR_CTRL_BAR_IDX PCI_REBAR_CTRL_BAR_IDX
+#define PCI_VF_REBAR_CTRL_NBAR_MASK PCI_REBAR_CTRL_NBAR_MASK
+#define PCI_VF_REBAR_CTRL_BAR_SIZE PCI_REBAR_CTRL_BAR_SIZE
+
/* Data Link Feature */
#define PCI_DLF_CAP 0x04 /* Capabilities Register */
#define PCI_DLF_EXCHANGE_ENABLE 0x80000000 /* Data Link Feature Exchange Enable */
diff --git a/include/standard-headers/linux/vhost_types.h b/include/standard-headers/linux/vhost_types.h
index fd54044936..79b53a931a 100644
--- a/include/standard-headers/linux/vhost_types.h
+++ b/include/standard-headers/linux/vhost_types.h
@@ -110,6 +110,11 @@ struct vhost_msg_v2 {
};
};
+struct vhost_features_array {
+ uint64_t count; /* number of entries present in features array */
+ uint64_t features[] ;
+};
+
struct vhost_memory_region {
uint64_t guest_phys_addr;
uint64_t memory_size; /* bytes */
diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h
index 982e854f14..93abaae0b9 100644
--- a/include/standard-headers/linux/virtio_net.h
+++ b/include/standard-headers/linux/virtio_net.h
@@ -70,6 +70,28 @@
* with the same MAC.
*/
#define VIRTIO_NET_F_SPEED_DUPLEX 63 /* Device set linkspeed and duplex */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO 65 /* Driver can receive
+ * GSO-over-UDP-tunnel packets
+ */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM 66 /* Driver handles
+ * GSO-over-UDP-tunnel
+ * packets with partial csum
+ * for the outer header
+ */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO 67 /* Device can receive
+ * GSO-over-UDP-tunnel packets
+ */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM 68 /* Device handles
+ * GSO-over-UDP-tunnel
+ * packets with partial csum
+ * for the outer header
+ */
+
+/* Offloads bits corresponding to VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO{,_CSUM}
+ * features
+ */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED 46
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED 47
#ifndef VIRTIO_NET_NO_LEGACY
#define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */
@@ -131,12 +153,17 @@ struct virtio_net_hdr_v1 {
#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 /* Use csum_start, csum_offset */
#define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */
#define VIRTIO_NET_HDR_F_RSC_INFO 4 /* rsc info in csum_ fields */
+#define VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM 8 /* UDP tunnel csum offload */
uint8_t flags;
#define VIRTIO_NET_HDR_GSO_NONE 0 /* Not a GSO frame */
#define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */
#define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */
#define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */
#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4& IPv6 UDP (USO) */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 0x20 /* UDPv4 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6 0x40 /* UDPv6 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 | \
+ VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6)
#define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */
uint8_t gso_type;
__virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
@@ -181,6 +208,12 @@ struct virtio_net_hdr_v1_hash {
uint16_t padding;
};
+struct virtio_net_hdr_v1_hash_tunnel {
+ struct virtio_net_hdr_v1_hash hash_hdr;
+ uint16_t outer_th_offset;
+ uint16_t inner_nh_offset;
+};
+
#ifndef VIRTIO_NET_NO_LEGACY
/* This header comes first in the scatter-gather list.
* For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must
diff --git a/linux-headers/LICENSES/preferred/GPL-2.0 b/linux-headers/LICENSES/preferred/GPL-2.0
index ff0812fd89..ea8e93dc44 100644
--- a/linux-headers/LICENSES/preferred/GPL-2.0
+++ b/linux-headers/LICENSES/preferred/GPL-2.0
@@ -20,8 +20,8 @@ License-Text:
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.
- 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
@@ -322,10 +322,8 @@ the "copyright" line and a pointer to where the full notice is found.
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, write to the Free Software
- Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-
+ You should have received a copy of the GNU General Public License along
+ with this program; if not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
diff --git a/linux-headers/asm-arm64/unistd_64.h b/linux-headers/asm-arm64/unistd_64.h
index ee9aaebdf3..4ae25c2b91 100644
--- a/linux-headers/asm-arm64/unistd_64.h
+++ b/linux-headers/asm-arm64/unistd_64.h
@@ -324,6 +324,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_64_H */
diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h
index 2892a45023..04e0077fb4 100644
--- a/linux-headers/asm-generic/unistd.h
+++ b/linux-headers/asm-generic/unistd.h
@@ -852,8 +852,14 @@ __SYSCALL(__NR_removexattrat, sys_removexattrat)
#define __NR_open_tree_attr 467
__SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
+/* fs/inode.c */
+#define __NR_file_getattr 468
+__SYSCALL(__NR_file_getattr, sys_file_getattr)
+#define __NR_file_setattr 469
+__SYSCALL(__NR_file_setattr, sys_file_setattr)
+
#undef __NR_syscalls
-#define __NR_syscalls 468
+#define __NR_syscalls 470
/*
* 32 bit systems traditionally used different
diff --git a/linux-headers/asm-loongarch/unistd_64.h b/linux-headers/asm-loongarch/unistd_64.h
index 50d22df8f7..5033fc8f2f 100644
--- a/linux-headers/asm-loongarch/unistd_64.h
+++ b/linux-headers/asm-loongarch/unistd_64.h
@@ -320,6 +320,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_64_H */
diff --git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h
index bdcc2f460b..c99c10e5bf 100644
--- a/linux-headers/asm-mips/unistd_n32.h
+++ b/linux-headers/asm-mips/unistd_n32.h
@@ -396,5 +396,7 @@
#define __NR_listxattrat (__NR_Linux + 465)
#define __NR_removexattrat (__NR_Linux + 466)
#define __NR_open_tree_attr (__NR_Linux + 467)
+#define __NR_file_getattr (__NR_Linux + 468)
+#define __NR_file_setattr (__NR_Linux + 469)
#endif /* _ASM_UNISTD_N32_H */
diff --git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h
index 3b6b0193b6..0d975bb185 100644
--- a/linux-headers/asm-mips/unistd_n64.h
+++ b/linux-headers/asm-mips/unistd_n64.h
@@ -372,5 +372,7 @@
#define __NR_listxattrat (__NR_Linux + 465)
#define __NR_removexattrat (__NR_Linux + 466)
#define __NR_open_tree_attr (__NR_Linux + 467)
+#define __NR_file_getattr (__NR_Linux + 468)
+#define __NR_file_setattr (__NR_Linux + 469)
#endif /* _ASM_UNISTD_N64_H */
diff --git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h
index 4609a4b4d3..86ac0ac84b 100644
--- a/linux-headers/asm-mips/unistd_o32.h
+++ b/linux-headers/asm-mips/unistd_o32.h
@@ -442,5 +442,7 @@
#define __NR_listxattrat (__NR_Linux + 465)
#define __NR_removexattrat (__NR_Linux + 466)
#define __NR_open_tree_attr (__NR_Linux + 467)
+#define __NR_file_getattr (__NR_Linux + 468)
+#define __NR_file_setattr (__NR_Linux + 469)
#endif /* _ASM_UNISTD_O32_H */
diff --git a/linux-headers/asm-powerpc/kvm.h b/linux-headers/asm-powerpc/kvm.h
index eaeda00178..077c5437f5 100644
--- a/linux-headers/asm-powerpc/kvm.h
+++ b/linux-headers/asm-powerpc/kvm.h
@@ -1,18 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * 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, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
- *
* Copyright IBM Corp. 2007
*
* Authors: Hollis Blanchard <hollisb@us.ibm.com>
diff --git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h
index 5d38a427e0..d7a32c5e06 100644
--- a/linux-headers/asm-powerpc/unistd_32.h
+++ b/linux-headers/asm-powerpc/unistd_32.h
@@ -449,6 +449,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_32_H */
diff --git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h
index 860a488e4d..ff35c51fc6 100644
--- a/linux-headers/asm-powerpc/unistd_64.h
+++ b/linux-headers/asm-powerpc/unistd_64.h
@@ -421,6 +421,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_64_H */
diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h
index 5f59fd226c..ef27d4289d 100644
--- a/linux-headers/asm-riscv/kvm.h
+++ b/linux-headers/asm-riscv/kvm.h
@@ -18,6 +18,7 @@
#define __KVM_HAVE_IRQ_LINE
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
#define KVM_INTERRUPT_SET -1U
#define KVM_INTERRUPT_UNSET -2U
diff --git a/linux-headers/asm-riscv/unistd_32.h b/linux-headers/asm-riscv/unistd_32.h
index a5e769f1d9..6083373e88 100644
--- a/linux-headers/asm-riscv/unistd_32.h
+++ b/linux-headers/asm-riscv/unistd_32.h
@@ -315,6 +315,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_32_H */
diff --git a/linux-headers/asm-riscv/unistd_64.h b/linux-headers/asm-riscv/unistd_64.h
index 8df4d64841..f0c7585c60 100644
--- a/linux-headers/asm-riscv/unistd_64.h
+++ b/linux-headers/asm-riscv/unistd_64.h
@@ -325,6 +325,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_64_H */
diff --git a/linux-headers/asm-s390/unistd_32.h b/linux-headers/asm-s390/unistd_32.h
index 85eedbd18e..37b8f6f358 100644
--- a/linux-headers/asm-s390/unistd_32.h
+++ b/linux-headers/asm-s390/unistd_32.h
@@ -440,5 +440,7 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_S390_UNISTD_32_H */
diff --git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h
index c03b1b9701..0652ba6331 100644
--- a/linux-headers/asm-s390/unistd_64.h
+++ b/linux-headers/asm-s390/unistd_64.h
@@ -388,5 +388,7 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_S390_UNISTD_64_H */
diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h
index 491d6b4eb6..8f784a5634 100644
--- a/linux-headers/asm-x86/unistd_32.h
+++ b/linux-headers/asm-x86/unistd_32.h
@@ -458,6 +458,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_32_H */
diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h
index 7cf88bf9bd..2f55bebb81 100644
--- a/linux-headers/asm-x86/unistd_64.h
+++ b/linux-headers/asm-x86/unistd_64.h
@@ -381,6 +381,8 @@
#define __NR_listxattrat 465
#define __NR_removexattrat 466
#define __NR_open_tree_attr 467
+#define __NR_file_getattr 468
+#define __NR_file_setattr 469
#endif /* _ASM_UNISTD_64_H */
diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h
index 82959111e6..8cc8673f15 100644
--- a/linux-headers/asm-x86/unistd_x32.h
+++ b/linux-headers/asm-x86/unistd_x32.h
@@ -334,6 +334,8 @@
#define __NR_listxattrat (__X32_SYSCALL_BIT + 465)
#define __NR_removexattrat (__X32_SYSCALL_BIT + 466)
#define __NR_open_tree_attr (__X32_SYSCALL_BIT + 467)
+#define __NR_file_getattr (__X32_SYSCALL_BIT + 468)
+#define __NR_file_setattr (__X32_SYSCALL_BIT + 469)
#define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512)
#define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513)
#define __NR_ioctl (__X32_SYSCALL_BIT + 514)
diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h
index cb0f7d6b4d..2105a03955 100644
--- a/linux-headers/linux/iommufd.h
+++ b/linux-headers/linux/iommufd.h
@@ -56,6 +56,7 @@ enum {
IOMMUFD_CMD_VDEVICE_ALLOC = 0x91,
IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92,
IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93,
+ IOMMUFD_CMD_HW_QUEUE_ALLOC = 0x94,
};
/**
@@ -590,17 +591,44 @@ struct iommu_hw_info_arm_smmuv3 {
__u32 aidr;
};
+/**
+ * struct iommu_hw_info_tegra241_cmdqv - NVIDIA Tegra241 CMDQV Hardware
+ * Information (IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV)
+ *
+ * @flags: Must be 0
+ * @version: Version number for the CMDQ-V HW for PARAM bits[03:00]
+ * @log2vcmdqs: Log2 of the total number of VCMDQs for PARAM bits[07:04]
+ * @log2vsids: Log2 of the total number of SID replacements for PARAM bits[15:12]
+ * @__reserved: Must be 0
+ *
+ * VMM can use these fields directly in its emulated global PARAM register. Note
+ * that only one Virtual Interface (VINTF) should be exposed to a VM, i.e. PARAM
+ * bits[11:08] should be set to 0 for log2 of the total number of VINTFs.
+ */
+struct iommu_hw_info_tegra241_cmdqv {
+ __u32 flags;
+ __u8 version;
+ __u8 log2vcmdqs;
+ __u8 log2vsids;
+ __u8 __reserved;
+};
+
/**
* enum iommu_hw_info_type - IOMMU Hardware Info Types
- * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardware
+ * @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware
* info
+ * @IOMMU_HW_INFO_TYPE_DEFAULT: Input to request for a default type
* @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type
* @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type
+ * @IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM
+ * SMMUv3) info type
*/
enum iommu_hw_info_type {
IOMMU_HW_INFO_TYPE_NONE = 0,
+ IOMMU_HW_INFO_TYPE_DEFAULT = 0,
IOMMU_HW_INFO_TYPE_INTEL_VTD = 1,
IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2,
+ IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV = 3,
};
/**
@@ -625,6 +653,15 @@ enum iommufd_hw_capabilities {
IOMMU_HW_CAP_PCI_PASID_PRIV = 1 << 2,
};
+/**
+ * enum iommufd_hw_info_flags - Flags for iommu_hw_info
+ * @IOMMU_HW_INFO_FLAG_INPUT_TYPE: If set, @in_data_type carries an input type
+ * for user space to request for a specific info
+ */
+enum iommufd_hw_info_flags {
+ IOMMU_HW_INFO_FLAG_INPUT_TYPE = 1 << 0,
+};
+
/**
* struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO)
* @size: sizeof(struct iommu_hw_info)
@@ -634,6 +671,12 @@ enum iommufd_hw_capabilities {
* data that kernel supports
* @data_uptr: User pointer to a user-space buffer used by the kernel to fill
* the iommu type specific hardware information data
+ * @in_data_type: This shares the same field with @out_data_type, making it be
+ * a bidirectional field. When IOMMU_HW_INFO_FLAG_INPUT_TYPE is
+ * set, an input type carried via this @in_data_type field will
+ * be valid, requesting for the info data to the given type. If
+ * IOMMU_HW_INFO_FLAG_INPUT_TYPE is unset, any input value will
+ * be seen as IOMMU_HW_INFO_TYPE_DEFAULT
* @out_data_type: Output the iommu hardware info type as defined in the enum
* iommu_hw_info_type.
* @out_capabilities: Output the generic iommu capability info type as defined
@@ -663,7 +706,10 @@ struct iommu_hw_info {
__u32 dev_id;
__u32 data_len;
__aligned_u64 data_uptr;
- __u32 out_data_type;
+ union {
+ __u32 in_data_type;
+ __u32 out_data_type;
+ };
__u8 out_max_pasid_log2;
__u8 __reserved[3];
__aligned_u64 out_capabilities;
@@ -951,10 +997,29 @@ struct iommu_fault_alloc {
* enum iommu_viommu_type - Virtual IOMMU Type
* @IOMMU_VIOMMU_TYPE_DEFAULT: Reserved for future use
* @IOMMU_VIOMMU_TYPE_ARM_SMMUV3: ARM SMMUv3 driver specific type
+ * @IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM
+ * SMMUv3) enabled ARM SMMUv3 type
*/
enum iommu_viommu_type {
IOMMU_VIOMMU_TYPE_DEFAULT = 0,
IOMMU_VIOMMU_TYPE_ARM_SMMUV3 = 1,
+ IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV = 2,
+};
+
+/**
+ * struct iommu_viommu_tegra241_cmdqv - NVIDIA Tegra241 CMDQV Virtual Interface
+ * (IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV)
+ * @out_vintf_mmap_offset: mmap offset argument for VINTF's page0
+ * @out_vintf_mmap_length: mmap length argument for VINTF's page0
+ *
+ * Both @out_vintf_mmap_offset and @out_vintf_mmap_length are reported by kernel
+ * for user space to mmap the VINTF page0 from the host physical address space
+ * to the guest physical address space so that a guest kernel can directly R/W
+ * access to the VINTF page0 in order to control its virtual command queues.
+ */
+struct iommu_viommu_tegra241_cmdqv {
+ __aligned_u64 out_vintf_mmap_offset;
+ __aligned_u64 out_vintf_mmap_length;
};
/**
@@ -965,6 +1030,9 @@ enum iommu_viommu_type {
* @dev_id: The device's physical IOMMU will be used to back the virtual IOMMU
* @hwpt_id: ID of a nesting parent HWPT to associate to
* @out_viommu_id: Output virtual IOMMU ID for the allocated object
+ * @data_len: Length of the type specific data
+ * @__reserved: Must be 0
+ * @data_uptr: User pointer to a driver-specific virtual IOMMU data
*
* Allocate a virtual IOMMU object, representing the underlying physical IOMMU's
* virtualization support that is a security-isolated slice of the real IOMMU HW
@@ -985,6 +1053,9 @@ struct iommu_viommu_alloc {
__u32 dev_id;
__u32 hwpt_id;
__u32 out_viommu_id;
+ __u32 data_len;
+ __u32 __reserved;
+ __aligned_u64 data_uptr;
};
#define IOMMU_VIOMMU_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VIOMMU_ALLOC)
@@ -995,10 +1066,15 @@ struct iommu_viommu_alloc {
* @dev_id: The physical device to allocate a virtual instance on the vIOMMU
* @out_vdevice_id: Object handle for the vDevice. Pass to IOMMU_DESTORY
* @virt_id: Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID
- * of AMD IOMMU, and vRID of a nested Intel VT-d to a Context Table
+ * of AMD IOMMU, and vRID of Intel VT-d
*
* Allocate a virtual device instance (for a physical device) against a vIOMMU.
* This instance holds the device's information (related to its vIOMMU) in a VM.
+ * User should use IOMMU_DESTROY to destroy the virtual device before
+ * destroying the physical device (by closing vfio_cdev fd). Otherwise the
+ * virtual device would be forcibly destroyed on physical device destruction,
+ * its vdevice_id would be permanently leaked (unremovable & unreusable) until
+ * iommu fd closed.
*/
struct iommu_vdevice_alloc {
__u32 size;
@@ -1075,10 +1151,12 @@ struct iommufd_vevent_header {
* enum iommu_veventq_type - Virtual Event Queue Type
* @IOMMU_VEVENTQ_TYPE_DEFAULT: Reserved for future use
* @IOMMU_VEVENTQ_TYPE_ARM_SMMUV3: ARM SMMUv3 Virtual Event Queue
+ * @IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV Extension IRQ
*/
enum iommu_veventq_type {
IOMMU_VEVENTQ_TYPE_DEFAULT = 0,
IOMMU_VEVENTQ_TYPE_ARM_SMMUV3 = 1,
+ IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV = 2,
};
/**
@@ -1102,6 +1180,19 @@ struct iommu_vevent_arm_smmuv3 {
__aligned_le64 evt[4];
};
+/**
+ * struct iommu_vevent_tegra241_cmdqv - Tegra241 CMDQV IRQ
+ * (IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV)
+ * @lvcmdq_err_map: 128-bit logical vcmdq error map, little-endian.
+ * (Refer to register LVCMDQ_ERR_MAPs per VINTF )
+ *
+ * The 128-bit register value from HW exclusively reflect the error bits for a
+ * Virtual Interface represented by a vIOMMU object. Read and report directly.
+ */
+struct iommu_vevent_tegra241_cmdqv {
+ __aligned_le64 lvcmdq_err_map[2];
+};
+
/**
* struct iommu_veventq_alloc - ioctl(IOMMU_VEVENTQ_ALLOC)
* @size: sizeof(struct iommu_veventq_alloc)
@@ -1141,4 +1232,61 @@ struct iommu_veventq_alloc {
__u32 __reserved;
};
#define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC)
+
+/**
+ * enum iommu_hw_queue_type - HW Queue Type
+ * @IOMMU_HW_QUEUE_TYPE_DEFAULT: Reserved for future use
+ * @IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM
+ * SMMUv3) Virtual Command Queue (VCMDQ)
+ */
+enum iommu_hw_queue_type {
+ IOMMU_HW_QUEUE_TYPE_DEFAULT = 0,
+ /*
+ * TEGRA241_CMDQV requirements (otherwise, allocation will fail)
+ * - alloc starts from the lowest @index=0 in ascending order
+ * - destroy starts from the last allocated @index in descending order
+ * - @base_addr must be aligned to @length in bytes and mapped in IOAS
+ * - @length must be a power of 2, with a minimum 32 bytes and a maximum
+ * 2 ^ idr[1].CMDQS * 16 bytes (use GET_HW_INFO call to read idr[1]
+ * from struct iommu_hw_info_arm_smmuv3)
+ * - suggest to back the queue memory with contiguous physical pages or
+ * a single huge page with alignment of the queue size, and limit the
+ * emulated vSMMU's IDR1.CMDQS to log2(huge page size / 16 bytes)
+ */
+ IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV = 1,
+};
+
+/**
+ * struct iommu_hw_queue_alloc - ioctl(IOMMU_HW_QUEUE_ALLOC)
+ * @size: sizeof(struct iommu_hw_queue_alloc)
+ * @flags: Must be 0
+ * @viommu_id: Virtual IOMMU ID to associate the HW queue with
+ * @type: One of enum iommu_hw_queue_type
+ * @index: The logical index to the HW queue per virtual IOMMU for a multi-queue
+ * model
+ * @out_hw_queue_id: The ID of the new HW queue
+ * @nesting_parent_iova: Base address of the queue memory in the guest physical
+ * address space
+ * @length: Length of the queue memory
+ *
+ * Allocate a HW queue object for a vIOMMU-specific HW-accelerated queue, which
+ * allows HW to access a guest queue memory described using @nesting_parent_iova
+ * and @length.
+ *
+ * A vIOMMU can allocate multiple queues, but it must use a different @index per
+ * type to separate each allocation, e.g::
+ *
+ * Type1 HW queue0, Type1 HW queue1, Type2 HW queue0, ...
+ */
+struct iommu_hw_queue_alloc {
+ __u32 size;
+ __u32 flags;
+ __u32 viommu_id;
+ __u32 type;
+ __u32 index;
+ __u32 out_hw_queue_id;
+ __aligned_u64 nesting_parent_iova;
+ __aligned_u64 length;
+};
+#define IOMMU_HW_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HW_QUEUE_ALLOC)
#endif
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index 32c5885a3c..be704965d8 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -636,6 +636,7 @@ struct kvm_ioeventfd {
#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
+#define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4)
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
@@ -952,6 +953,7 @@ struct kvm_enable_cap {
#define KVM_CAP_ARM_EL2 240
#define KVM_CAP_ARM_EL2_E2H0 241
#define KVM_CAP_RISCV_MP_STATE_RESET 242
+#define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
struct kvm_irq_routing_irqchip {
__u32 irqchip;
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 79bf8c0cc5..4d96d1fc12 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -905,10 +905,12 @@ struct vfio_device_feature {
* VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18,
* struct vfio_device_bind_iommufd)
* @argsz: User filled size of this data.
- * @flags: Must be 0.
+ * @flags: Must be 0 or a bit flags of VFIO_DEVICE_BIND_*
* @iommufd: iommufd to bind.
* @out_devid: The device id generated by this bind. devid is a handle for
* this device/iommufd bond and can be used in IOMMUFD commands.
+ * @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte
+ * UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN.
*
* Bind a vfio_device to the specified iommufd.
*
@@ -917,13 +919,21 @@ struct vfio_device_feature {
*
* Unbind is automatically conducted when device fd is closed.
*
+ * A token is sometimes required to open the device, unless this is known to be
+ * needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is
+ * ignored. The only case today is a PF/VF relationship where the VF bind must
+ * be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to
+ * the PF.
+ *
* Return: 0 on success, -errno on failure.
*/
struct vfio_device_bind_iommufd {
__u32 argsz;
__u32 flags;
+#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0)
__s32 iommufd;
__u32 out_devid;
+ __aligned_u64 token_uuid_ptr;
};
#define VFIO_DEVICE_BIND_IOMMUFD _IO(VFIO_TYPE, VFIO_BASE + 18)
diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h
index d4b3e2ae13..283348b64a 100644
--- a/linux-headers/linux/vhost.h
+++ b/linux-headers/linux/vhost.h
@@ -235,4 +235,39 @@
*/
#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x82, \
struct vhost_vring_state)
+
+/* Extended features manipulation */
+#define VHOST_GET_FEATURES_ARRAY _IOR(VHOST_VIRTIO, 0x83, \
+ struct vhost_features_array)
+#define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
+ struct vhost_features_array)
+
+/* fork_owner values for vhost */
+#define VHOST_FORK_OWNER_KTHREAD 0
+#define VHOST_FORK_OWNER_TASK 1
+
+/**
+ * VHOST_SET_FORK_FROM_OWNER - Set the fork_owner flag for the vhost device,
+ * This ioctl must called before VHOST_SET_OWNER.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @param fork_owner: An 8-bit value that determines the vhost thread mode
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_TASK(default value):
+ * - Vhost will create vhost worker as tasks forked from the owner,
+ * inheriting all of the owner's attributes.
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD:
+ * - Vhost will create vhost workers as kernel threads.
+ */
+#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x83, __u8)
+
+/**
+ * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @return: An 8-bit value indicating the current thread mode.
+ */
+#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x84, __u8)
+
#endif
--
2.47.3

47
kvm-linux-headers-deal-with-counted_by-annotation.patch Normal file
View File

@ -0,0 +1,47 @@
From aa56db1a8eb6ede62e58ab4827fc8a7ba8a2ec4a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 22 Sep 2025 16:18:16 +0200
Subject: [PATCH 07/19] linux-headers: deal with counted_by annotation
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 456: backport support for GSO over UDP tunnel offload
RH-Jira: RHEL-143785
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Commit: [2/14] dacb8059a0de06a0b9665152e0725da7da08467e (lvivier/qemu-kvm-centos)
JIRA: https://issues.redhat.com/browse/RHEL-143785
Such annotation is present into the kernel uAPI headers since
v6.7, and will be used soon by the vhost_type.h. Deal with it
just stripping it.
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a1430f43cc954d2a931fa60581bda6d6af4bc771.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit c3d9dcd87f0d228ea3ac5a42076da829cff401f0)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
scripts/update-linux-headers.sh | 1 +
1 file changed, 1 insertion(+)
diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh
index 828a7809f7..844d9cb9f5 100755
--- a/scripts/update-linux-headers.sh
+++ b/scripts/update-linux-headers.sh
@@ -90,6 +90,7 @@ cp_portable() {
-e 's/<linux\/\([^>]*\)>/"standard-headers\/linux\/\1"/' \
-e "$arch_cmd" \
-e 's/__bitwise//' \
+ -e 's/__counted_by(\w*)//' \
-e 's/__attribute__((packed))/QEMU_PACKED/' \
-e 's/__inline__/inline/' \
-e 's/__BITS_PER_LONG/HOST_LONG_BITS/' \
--
2.47.3

329
kvm-linux-headers-linux-Add-mshv.h-headers.patch Normal file
View File

@ -0,0 +1,329 @@
From 38642c3d90746f63ecc1f961ac7ef52b019c1132 Mon Sep 17 00:00:00 2001
From: Magnus Kulke <magnuskulke@linux.microsoft.com>
Date: Tue, 16 Sep 2025 18:48:26 +0200
Subject: [PATCH 08/32] linux-headers/linux: Add mshv.h headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 437: el10: x86: enablement for Azure L1VH OCP readiness
RH-Jira: RHEL-134212
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [6/30] ef60621970d29f626815bdeb68bc8bdfe0061d0e
This file has been added to the tree by running `update-linux-header.sh`
on linux v6.16.
Signed-off-by: Magnus Kulke <magnuskulke@linux.microsoft.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Link: https://lore.kernel.org/r/20250916164847.77883-7-magnuskulke@linux.microsoft.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit a6d6878650a0f4982918e8cd9d7ea6c3c3c681f7)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
linux-headers/linux/mshv.h | 291 +++++++++++++++++++++++++++++++++++++
1 file changed, 291 insertions(+)
create mode 100644 linux-headers/linux/mshv.h
diff --git a/linux-headers/linux/mshv.h b/linux-headers/linux/mshv.h
new file mode 100644
index 0000000000..5bc83db6a3
--- /dev/null
+++ b/linux-headers/linux/mshv.h
@@ -0,0 +1,291 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Userspace interfaces for /dev/mshv* devices and derived fds
+ *
+ * This file is divided into sections containing data structures and IOCTLs for
+ * a particular set of related devices or derived file descriptors.
+ *
+ * The IOCTL definitions are at the end of each section. They are grouped by
+ * device/fd, so that new IOCTLs can easily be added with a monotonically
+ * increasing number.
+ */
+#ifndef _LINUX_MSHV_H
+#define _LINUX_MSHV_H
+
+#include <linux/types.h>
+
+#define MSHV_IOCTL 0xB8
+
+/*
+ *******************************************
+ * Entry point to main VMM APIs: /dev/mshv *
+ *******************************************
+ */
+
+enum {
+ MSHV_PT_BIT_LAPIC,
+ MSHV_PT_BIT_X2APIC,
+ MSHV_PT_BIT_GPA_SUPER_PAGES,
+ MSHV_PT_BIT_COUNT,
+};
+
+#define MSHV_PT_FLAGS_MASK ((1 << MSHV_PT_BIT_COUNT) - 1)
+
+enum {
+ MSHV_PT_ISOLATION_NONE,
+ MSHV_PT_ISOLATION_COUNT,
+};
+
+/**
+ * struct mshv_create_partition - arguments for MSHV_CREATE_PARTITION
+ * @pt_flags: Bitmask of 1 << MSHV_PT_BIT_*
+ * @pt_isolation: MSHV_PT_ISOLATION_*
+ *
+ * Returns a file descriptor to act as a handle to a guest partition.
+ * At this point the partition is not yet initialized in the hypervisor.
+ * Some operations must be done with the partition in this state, e.g. setting
+ * so-called "early" partition properties. The partition can then be
+ * initialized with MSHV_INITIALIZE_PARTITION.
+ */
+struct mshv_create_partition {
+ __u64 pt_flags;
+ __u64 pt_isolation;
+};
+
+/* /dev/mshv */
+#define MSHV_CREATE_PARTITION _IOW(MSHV_IOCTL, 0x00, struct mshv_create_partition)
+
+/*
+ ************************
+ * Child partition APIs *
+ ************************
+ */
+
+struct mshv_create_vp {
+ __u32 vp_index;
+};
+
+enum {
+ MSHV_SET_MEM_BIT_WRITABLE,
+ MSHV_SET_MEM_BIT_EXECUTABLE,
+ MSHV_SET_MEM_BIT_UNMAP,
+ MSHV_SET_MEM_BIT_COUNT
+};
+
+#define MSHV_SET_MEM_FLAGS_MASK ((1 << MSHV_SET_MEM_BIT_COUNT) - 1)
+
+/* The hypervisor's "native" page size */
+#define MSHV_HV_PAGE_SIZE 0x1000
+
+/**
+ * struct mshv_user_mem_region - arguments for MSHV_SET_GUEST_MEMORY
+ * @size: Size of the memory region (bytes). Must be aligned to
+ * MSHV_HV_PAGE_SIZE
+ * @guest_pfn: Base guest page number to map
+ * @userspace_addr: Base address of userspace memory. Must be aligned to
+ * MSHV_HV_PAGE_SIZE
+ * @flags: Bitmask of 1 << MSHV_SET_MEM_BIT_*. If (1 << MSHV_SET_MEM_BIT_UNMAP)
+ * is set, ignore other bits.
+ * @rsvd: MBZ
+ *
+ * Map or unmap a region of userspace memory to Guest Physical Addresses (GPA).
+ * Mappings can't overlap in GPA space or userspace.
+ * To unmap, these fields must match an existing mapping.
+ */
+struct mshv_user_mem_region {
+ __u64 size;
+ __u64 guest_pfn;
+ __u64 userspace_addr;
+ __u8 flags;
+ __u8 rsvd[7];
+};
+
+enum {
+ MSHV_IRQFD_BIT_DEASSIGN,
+ MSHV_IRQFD_BIT_RESAMPLE,
+ MSHV_IRQFD_BIT_COUNT,
+};
+
+#define MSHV_IRQFD_FLAGS_MASK ((1 << MSHV_IRQFD_BIT_COUNT) - 1)
+
+struct mshv_user_irqfd {
+ __s32 fd;
+ __s32 resamplefd;
+ __u32 gsi;
+ __u32 flags;
+};
+
+enum {
+ MSHV_IOEVENTFD_BIT_DATAMATCH,
+ MSHV_IOEVENTFD_BIT_PIO,
+ MSHV_IOEVENTFD_BIT_DEASSIGN,
+ MSHV_IOEVENTFD_BIT_COUNT,
+};
+
+#define MSHV_IOEVENTFD_FLAGS_MASK ((1 << MSHV_IOEVENTFD_BIT_COUNT) - 1)
+
+struct mshv_user_ioeventfd {
+ __u64 datamatch;
+ __u64 addr; /* legal pio/mmio address */
+ __u32 len; /* 1, 2, 4, or 8 bytes */
+ __s32 fd;
+ __u32 flags;
+ __u8 rsvd[4];
+};
+
+struct mshv_user_irq_entry {
+ __u32 gsi;
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+};
+
+struct mshv_user_irq_table {
+ __u32 nr;
+ __u32 rsvd; /* MBZ */
+ struct mshv_user_irq_entry entries[];
+};
+
+enum {
+ MSHV_GPAP_ACCESS_TYPE_ACCESSED,
+ MSHV_GPAP_ACCESS_TYPE_DIRTY,
+ MSHV_GPAP_ACCESS_TYPE_COUNT /* Count of enum members */
+};
+
+enum {
+ MSHV_GPAP_ACCESS_OP_NOOP,
+ MSHV_GPAP_ACCESS_OP_CLEAR,
+ MSHV_GPAP_ACCESS_OP_SET,
+ MSHV_GPAP_ACCESS_OP_COUNT /* Count of enum members */
+};
+
+/**
+ * struct mshv_gpap_access_bitmap - arguments for MSHV_GET_GPAP_ACCESS_BITMAP
+ * @access_type: MSHV_GPAP_ACCESS_TYPE_* - The type of access to record in the
+ * bitmap
+ * @access_op: MSHV_GPAP_ACCESS_OP_* - Allows an optional clear or set of all
+ * the access states in the range, after retrieving the current
+ * states.
+ * @rsvd: MBZ
+ * @page_count: Number of pages
+ * @gpap_base: Base gpa page number
+ * @bitmap_ptr: Output buffer for bitmap, at least (page_count + 7) / 8 bytes
+ *
+ * Retrieve a bitmap of either ACCESSED or DIRTY bits for a given range of guest
+ * memory, and optionally clear or set the bits.
+ */
+struct mshv_gpap_access_bitmap {
+ __u8 access_type;
+ __u8 access_op;
+ __u8 rsvd[6];
+ __u64 page_count;
+ __u64 gpap_base;
+ __u64 bitmap_ptr;
+};
+
+/**
+ * struct mshv_root_hvcall - arguments for MSHV_ROOT_HVCALL
+ * @code: Hypercall code (HVCALL_*)
+ * @reps: in: Rep count ('repcount')
+ * out: Reps completed ('repcomp'). MBZ unless rep hvcall
+ * @in_sz: Size of input incl rep data. <= MSHV_HV_PAGE_SIZE
+ * @out_sz: Size of output buffer. <= MSHV_HV_PAGE_SIZE. MBZ if out_ptr is 0
+ * @status: in: MBZ
+ * out: HV_STATUS_* from hypercall
+ * @rsvd: MBZ
+ * @in_ptr: Input data buffer (struct hv_input_*). If used with partition or
+ * vp fd, partition id field is populated by kernel.
+ * @out_ptr: Output data buffer (optional)
+ */
+struct mshv_root_hvcall {
+ __u16 code;
+ __u16 reps;
+ __u16 in_sz;
+ __u16 out_sz;
+ __u16 status;
+ __u8 rsvd[6];
+ __u64 in_ptr;
+ __u64 out_ptr;
+};
+
+/* Partition fds created with MSHV_CREATE_PARTITION */
+#define MSHV_INITIALIZE_PARTITION _IO(MSHV_IOCTL, 0x00)
+#define MSHV_CREATE_VP _IOW(MSHV_IOCTL, 0x01, struct mshv_create_vp)
+#define MSHV_SET_GUEST_MEMORY _IOW(MSHV_IOCTL, 0x02, struct mshv_user_mem_region)
+#define MSHV_IRQFD _IOW(MSHV_IOCTL, 0x03, struct mshv_user_irqfd)
+#define MSHV_IOEVENTFD _IOW(MSHV_IOCTL, 0x04, struct mshv_user_ioeventfd)
+#define MSHV_SET_MSI_ROUTING _IOW(MSHV_IOCTL, 0x05, struct mshv_user_irq_table)
+#define MSHV_GET_GPAP_ACCESS_BITMAP _IOWR(MSHV_IOCTL, 0x06, struct mshv_gpap_access_bitmap)
+/* Generic hypercall */
+#define MSHV_ROOT_HVCALL _IOWR(MSHV_IOCTL, 0x07, struct mshv_root_hvcall)
+
+/*
+ ********************************
+ * VP APIs for child partitions *
+ ********************************
+ */
+
+#define MSHV_RUN_VP_BUF_SZ 256
+
+/*
+ * VP state pages may be mapped to userspace via mmap().
+ * To specify which state page, use MSHV_VP_MMAP_OFFSET_ values multiplied by
+ * the system page size.
+ * e.g.
+ * long page_size = sysconf(_SC_PAGE_SIZE);
+ * void *reg_page = mmap(NULL, MSHV_HV_PAGE_SIZE, PROT_READ|PROT_WRITE,
+ * MAP_SHARED, vp_fd,
+ * MSHV_VP_MMAP_OFFSET_REGISTERS * page_size);
+ */
+enum {
+ MSHV_VP_MMAP_OFFSET_REGISTERS,
+ MSHV_VP_MMAP_OFFSET_INTERCEPT_MESSAGE,
+ MSHV_VP_MMAP_OFFSET_GHCB,
+ MSHV_VP_MMAP_OFFSET_COUNT
+};
+
+/**
+ * struct mshv_run_vp - argument for MSHV_RUN_VP
+ * @msg_buf: On success, the intercept message is copied here. It can be
+ * interpreted using the relevant hypervisor definitions.
+ */
+struct mshv_run_vp {
+ __u8 msg_buf[MSHV_RUN_VP_BUF_SZ];
+};
+
+enum {
+ MSHV_VP_STATE_LAPIC, /* Local interrupt controller state (either arch) */
+ MSHV_VP_STATE_XSAVE, /* XSAVE data in compacted form (x86_64) */
+ MSHV_VP_STATE_SIMP,
+ MSHV_VP_STATE_SIEFP,
+ MSHV_VP_STATE_SYNTHETIC_TIMERS,
+ MSHV_VP_STATE_COUNT,
+};
+
+/**
+ * struct mshv_get_set_vp_state - arguments for MSHV_[GET,SET]_VP_STATE
+ * @type: MSHV_VP_STATE_*
+ * @rsvd: MBZ
+ * @buf_sz: in: 4k page-aligned size of buffer
+ * out: Actual size of data (on EINVAL, check this to see if buffer
+ * was too small)
+ * @buf_ptr: 4k page-aligned data buffer
+ */
+struct mshv_get_set_vp_state {
+ __u8 type;
+ __u8 rsvd[3];
+ __u32 buf_sz;
+ __u64 buf_ptr;
+};
+
+/* VP fds created with MSHV_CREATE_VP */
+#define MSHV_RUN_VP _IOR(MSHV_IOCTL, 0x00, struct mshv_run_vp)
+#define MSHV_GET_VP_STATE _IOWR(MSHV_IOCTL, 0x01, struct mshv_get_set_vp_state)
+#define MSHV_SET_VP_STATE _IOWR(MSHV_IOCTL, 0x02, struct mshv_get_set_vp_state)
+/*
+ * Generic hypercall
+ * Defined above in partition IOCTLs, avoid redefining it here
+ * #define MSHV_ROOT_HVCALL _IOWR(MSHV_IOCTL, 0x07, struct mshv_root_hvcall)
+ */
+
+#endif
--
2.47.3

162
kvm-mirror-Fix-missed-dirty-bitmap-writes-during-startup.patch Normal file
View File

@ -0,0 +1,162 @@
From 19a86e8f7e88b47ac40014cd716146f0754939c2 Mon Sep 17 00:00:00 2001
From: Kevin Wolf <kwolf@redhat.com>
Date: Thu, 19 Feb 2026 21:24:46 +0100
Subject: [PATCH] mirror: Fix missed dirty bitmap writes during startup
RH-Author: Kevin Wolf <kwolf@redhat.com>
RH-MergeRequest: 474: mirror: Fix missed dirty bitmap writes during startup
RH-Jira: RHEL-155601
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Commit: [1/1] a888c4b2085d5fc3639bf6721f1f4e974db65dba (kmwolf/centos-qemu-kvm)
Currently, mirror disables the block layer's dirty bitmap before its own
replacement is working. This means that during startup, there is a
window in which the allocation status of blocks in the source has
already been checked, but new writes coming in aren't tracked yet,
resulting in a corrupted copy:
1. Dirty bitmap is disabled in mirror_start_job()
2. Some request are started in mirror_top_bs while s->job == NULL
3. mirror_dirty_init() -> bdrv_co_is_allocated_above() runs and because
the request hasn't completed yet, the block isn't allocated
4. The request completes, still sees s->job == NULL and skips the
bitmap, and nothing else will mark it dirty either
One ingredient is that mirror_top_opaque->job is only set after the
job is fully initialized. For the rationale, see commit 32125b1460
("mirror: Fix access of uninitialised fields during start").
Fix this by giving mirror_top_bs access to dirty_bitmap and enabling it
to track writes from the beginning. Disabling the block layer's tracking
and enabling the mirror_top_bs one happens in a drained section, so
there is no danger of races with in-flight requests any more. All of
this happens well before the block allocation status is checked, so we
can be sure that no writes will be missed.
Cc: qemu-stable@nongnu.org
Closes: https://gitlab.com/qemu-project/qemu/-/issues/3273
Fixes: 32125b14606a ('mirror: Fix access of uninitialised fields during start')
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20260219202446.312493-1-kwolf@redhat.com>
Reviewed-by: Fiona Ebner <f.ebner@proxmox.com>
Tested-by: Jean-Louis Dupond <jean-louis@dupond.be>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 0f51f9c3420b31bb383e456dd7bf24d3056eeb73)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/mirror.c | 52 +++++++++++++++++++++++++++++++-------------------
1 file changed, 32 insertions(+), 20 deletions(-)
diff --git a/block/mirror.c b/block/mirror.c
index b344182c74..f01be99b55 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -99,6 +99,7 @@ typedef struct MirrorBlockJob {
typedef struct MirrorBDSOpaque {
MirrorBlockJob *job;
+ BdrvDirtyBitmap *dirty_bitmap;
bool stop;
bool is_commit;
} MirrorBDSOpaque;
@@ -1672,9 +1673,11 @@ bdrv_mirror_top_do_write(BlockDriverState *bs, MirrorMethod method,
abort();
}
- if (!copy_to_target && s->job && s->job->dirty_bitmap) {
- qatomic_set(&s->job->actively_synced, false);
- bdrv_set_dirty_bitmap(s->job->dirty_bitmap, offset, bytes);
+ if (!copy_to_target) {
+ if (s->job) {
+ qatomic_set(&s->job->actively_synced, false);
+ }
+ bdrv_set_dirty_bitmap(s->dirty_bitmap, offset, bytes);
}
if (ret < 0) {
@@ -1901,13 +1904,35 @@ static BlockJob *mirror_start_job(
bdrv_drained_begin(bs);
ret = bdrv_append(mirror_top_bs, bs, errp);
- bdrv_drained_end(bs);
-
if (ret < 0) {
+ bdrv_drained_end(bs);
+ bdrv_unref(mirror_top_bs);
+ return NULL;
+ }
+
+ bs_opaque->dirty_bitmap = bdrv_create_dirty_bitmap(mirror_top_bs,
+ granularity,
+ NULL, errp);
+ if (!bs_opaque->dirty_bitmap) {
+ bdrv_drained_end(bs);
bdrv_unref(mirror_top_bs);
return NULL;
}
+ /*
+ * The mirror job doesn't use the block layer's dirty tracking because it
+ * needs to be able to switch seemlessly between background copy mode (which
+ * does need dirty tracking) and write blocking mode (which doesn't) and
+ * doing that would require draining the node. Instead, mirror_top_bs takes
+ * care of updating the dirty bitmap as appropriate.
+ *
+ * Note that write blocking mode only becomes effective after mirror_run()
+ * sets mirror_top_opaque->job (see should_copy_to_target()). Until then,
+ * we're still in background copy mode irrespective of @copy_mode.
+ */
+ bdrv_disable_dirty_bitmap(bs_opaque->dirty_bitmap);
+ bdrv_drained_end(bs);
+
/* Make sure that the source is not resized while the job is running */
s = block_job_create(job_id, driver, NULL, mirror_top_bs,
BLK_PERM_CONSISTENT_READ,
@@ -2002,24 +2027,13 @@ static BlockJob *mirror_start_job(
s->base_overlay = bdrv_find_overlay(bs, base);
s->granularity = granularity;
s->buf_size = ROUND_UP(buf_size, granularity);
+ s->dirty_bitmap = bs_opaque->dirty_bitmap;
s->unmap = unmap;
if (auto_complete) {
s->should_complete = true;
}
bdrv_graph_rdunlock_main_loop();
- s->dirty_bitmap = bdrv_create_dirty_bitmap(s->mirror_top_bs, granularity,
- NULL, errp);
- if (!s->dirty_bitmap) {
- goto fail;
- }
-
- /*
- * The dirty bitmap is set by bdrv_mirror_top_do_write() when not in active
- * mode.
- */
- bdrv_disable_dirty_bitmap(s->dirty_bitmap);
-
bdrv_graph_wrlock_drained();
ret = block_job_add_bdrv(&s->common, "source", bs, 0,
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE |
@@ -2099,9 +2113,6 @@ fail:
g_free(s->replaces);
blk_unref(s->target);
bs_opaque->job = NULL;
- if (s->dirty_bitmap) {
- bdrv_release_dirty_bitmap(s->dirty_bitmap);
- }
job_early_fail(&s->common.job);
}
@@ -2115,6 +2126,7 @@ fail:
bdrv_graph_wrunlock();
bdrv_drained_end(bs);
+ bdrv_release_dirty_bitmap(bs_opaque->dirty_bitmap);
bdrv_unref(mirror_top_bs);
return NULL;
--
2.47.3

235
kvm-monitor-generalize-query-mshv-info-mshv-to-query-acc.patch Normal file
View File

@ -0,0 +1,235 @@
From afb70cb5eea1e9dad7b5414713d2394ef2c88329 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 13 Oct 2025 12:49:04 +0200
Subject: [PATCH 1/6] monitor: generalize query-mshv/"info mshv" to
query-accelerators/"info accelerators"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Igor Mammedov <imammedo@redhat.com>
RH-MergeRequest: 443: [REHL10.2] L1HV: monitor: generalize query-mshv/"info mshv" to query-accelerators/"info accelerators"
RH-Jira: RHEL-134212
RH-Acked-by: MST <mst@redhat.com>
RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
RH-Commit: [1/1] af946c572c3dab34cee6399bf4438e2722dd7e44 (imammedo/qemu-kvm-cs)
The recently-introduced query-mshv command is a duplicate of query-kvm,
and neither provides a full view of which accelerators are supported
by a particular binary of QEMU and which is in use.
KVM was the first accelerator added to QEMU, predating QOM and TYPE_ACCEL,
so it got a pass. But now, instead of adding a badly designed copy, solve
the problem completely for all accelerators with a command that provides
the whole picture:
>> {"execute": "query-accelerators"}
<< {"return": {"enabled": "tcg", "present": ["kvm", "mshv", "qtest", "tcg", "xen"]}}
Cc: Praveen K Paladugu <prapal@microsoft.com>
Cc: Magnus Kulke <magnuskulke@linux.microsoft.com>
Suggested-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 71d5babbd6fffc7def1ecbf29f9753e3a2807761)
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
---
hmp-commands-info.hx | 15 ++++++++----
hw/core/machine-hmp-cmds.c | 23 +++++++++++--------
hw/core/machine-qmp-cmds.c | 24 +++++++++++++------
include/monitor/hmp.h | 2 +-
qapi/accelerator.json | 47 +++++++++++++++++++++++++++++---------
5 files changed, 77 insertions(+), 34 deletions(-)
diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx
index eaaa880c1b..3ed636e4e8 100644
--- a/hmp-commands-info.hx
+++ b/hmp-commands-info.hx
@@ -308,16 +308,21 @@ SRST
ERST
{
- .name = "mshv",
+ .name = "accelerators",
.args_type = "",
.params = "",
- .help = "show MSHV information",
- .cmd = hmp_info_mshv,
+ .help = "show present and enabled information",
+ .cmd = hmp_info_accelerators,
},
SRST
- ``info mshv``
- Show MSHV information.
+ ``info accelerators``
+ Show which accelerators are compiled into a QEMU binary, and what accelerator
+ is in use. For example::
+
+ kvm qtest [tcg]
+
+ indicates that TCG in use, and that KVM and qtest are also available.
ERST
{
diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c
index 682ed9f49b..74a56600be 100644
--- a/hw/core/machine-hmp-cmds.c
+++ b/hw/core/machine-hmp-cmds.c
@@ -163,19 +163,22 @@ void hmp_info_kvm(Monitor *mon, const QDict *qdict)
qapi_free_KvmInfo(info);
}
-void hmp_info_mshv(Monitor *mon, const QDict *qdict)
+void hmp_info_accelerators(Monitor *mon, const QDict *qdict)
{
- MshvInfo *info;
-
- info = qmp_query_mshv(NULL);
- monitor_printf(mon, "mshv support: ");
- if (info->present) {
- monitor_printf(mon, "%s\n", info->enabled ? "enabled" : "disabled");
- } else {
- monitor_printf(mon, "not compiled\n");
+ AcceleratorInfo *info;
+ AcceleratorList *accel;
+
+ info = qmp_query_accelerators(NULL);
+ for (accel = info->present; accel; accel = accel->next) {
+ char trail = accel->next ? ' ' : '\n';
+ if (info->enabled == accel->value) {
+ monitor_printf(mon, "[%s]%c", Accelerator_str(accel->value), trail);
+ } else {
+ monitor_printf(mon, "%s%c", Accelerator_str(accel->value), trail);
+ }
}
- qapi_free_MshvInfo(info);
+ qapi_free_AcceleratorInfo(info);
}
void hmp_info_uuid(Monitor *mon, const QDict *qdict)
diff --git a/hw/core/machine-qmp-cmds.c b/hw/core/machine-qmp-cmds.c
index e24bf0d97b..51d5c230f7 100644
--- a/hw/core/machine-qmp-cmds.c
+++ b/hw/core/machine-qmp-cmds.c
@@ -31,15 +31,25 @@
#include <sys/stat.h>
/*
- * QMP query for MSHV
+ * QMP query for enabled and present accelerators
*/
-MshvInfo *qmp_query_mshv(Error **errp)
+AcceleratorInfo *qmp_query_accelerators(Error **errp)
{
- MshvInfo *info = g_malloc0(sizeof(*info));
-
- info->enabled = mshv_enabled();
- info->present = accel_find("mshv");
-
+ AcceleratorInfo *info = g_malloc0(sizeof(*info));
+ AccelClass *current_class = ACCEL_GET_CLASS(current_accel());
+ int i;
+
+ for (i = ACCELERATOR__MAX; i-- > 0; ) {
+ const char *s = Accelerator_str(i);
+ AccelClass *this_class = accel_find(s);
+
+ if (this_class) {
+ QAPI_LIST_PREPEND(info->present, i);
+ if (this_class == current_class) {
+ info->enabled = i;
+ }
+ }
+ }
return info;
}
diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h
index 31bd812e5f..897dfaa2b6 100644
--- a/include/monitor/hmp.h
+++ b/include/monitor/hmp.h
@@ -24,7 +24,7 @@ strList *hmp_split_at_comma(const char *str);
void hmp_info_name(Monitor *mon, const QDict *qdict);
void hmp_info_version(Monitor *mon, const QDict *qdict);
void hmp_info_kvm(Monitor *mon, const QDict *qdict);
-void hmp_info_mshv(Monitor *mon, const QDict *qdict);
+void hmp_info_accelerators(Monitor *mon, const QDict *qdict);
void hmp_info_status(Monitor *mon, const QDict *qdict);
void hmp_info_uuid(Monitor *mon, const QDict *qdict);
void hmp_info_chardev(Monitor *mon, const QDict *qdict);
diff --git a/qapi/accelerator.json b/qapi/accelerator.json
index 664e027246..2b92060884 100644
--- a/qapi/accelerator.json
+++ b/qapi/accelerator.json
@@ -56,30 +56,55 @@
'features': [ 'unstable' ] }
##
-# @MshvInfo:
+# @Accelerator:
#
# Information about support for MSHV acceleration
#
-# @enabled: true if MSHV acceleration is active
+# @hvf: Apple Hypervisor.framework
#
-# @present: true if MSHV acceleration is built into this executable
+# @kvm: KVM
+#
+# @mshv: Hyper-V
+#
+# @nvmm: NetBSD NVMM
+#
+# @qtest: QTest (dummy accelerator)
+#
+# @tcg: TCG (dynamic translation)
+#
+# @whpx: Windows Hypervisor Platform
+#
+# @xen: Xen
+#
+# Since: 10.2.0
+##
+{ 'enum': 'Accelerator', 'data': ['hvf', 'kvm', 'mshv', 'nvmm', 'qtest', 'tcg', 'whpx', 'xen'] }
+
+##
+# @AcceleratorInfo:
+#
+# Information about support for various accelerators
+#
+# @enabled: the accelerator that is in use
+#
+# @present: the list of accelerators that are built into this executable
#
# Since: 10.2.0
##
-{ 'struct': 'MshvInfo', 'data': {'enabled': 'bool', 'present': 'bool'} }
+{ 'struct': 'AcceleratorInfo', 'data': {'enabled': 'Accelerator', 'present': ['Accelerator']} }
##
-# @query-mshv:
+# @query-accelerators:
#
-# Return information about MSHV acceleration
+# Return information about accelerators
#
-# Returns: @MshvInfo
+# Returns: @AcceleratorInfo
#
-# Since: 10.0.92
+# Since: 10.2.0
#
# .. qmp-example::
#
-# -> { "execute": "query-mshv" }
-# <- { "return": { "enabled": true, "present": true } }
+# -> { "execute": "query-accelerators" }
+# <- { "return": { "enabled": "mshv", "present": ["kvm", "mshv", "qtest", "tcg"] } }
##
-{ 'command': 'query-mshv', 'returns': 'MshvInfo' }
+{ 'command': 'query-accelerators', 'returns': 'AcceleratorInfo' }
--
2.47.3

101
kvm-nbd-server-CVE-2024-7409-Avoid-use-after-free-when-c.patch
View File

@ -1,101 +0,0 @@
From 3732f1491d8981e85f699fcd125d903aba77fa32 Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Thu, 22 Aug 2024 09:35:29 -0500
Subject: [PATCH] nbd/server: CVE-2024-7409: Avoid use-after-free when closing
server
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 267: nbd/server: CVE-2024-7409: Avoid use-after-free when closing server
RH-Jira: RHEL-52599
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Hanna Czenczek <hreitz@redhat.com>
RH-Commit: e7d52e5d1372eaec00325d4854772ee78fe650b7 (ebblake/centos-qemu-kvm)
Commit 3e7ef738 plugged the use-after-free of the global nbd_server
object, but overlooked a use-after-free of nbd_server->listener.
Although this race is harder to hit, notice that our shutdown path
first drops the reference count of nbd_server->listener, then triggers
actions that can result in a pending client reaching the
nbd_blockdev_client_closed() callback, which in turn calls
qio_net_listener_set_client_func on a potentially stale object.
If we know we don't want any more clients to connect, and have already
told the listener socket to shut down, then we should not be trying to
update the listener socket's associated function.
Reproducer:
> #!/usr/bin/python3
>
> import os
> from threading import Thread
>
> def start_stop():
> while 1:
> os.system('virsh qemu-monitor-command VM \'{"execute": "nbd-server-start",
+"arguments":{"addr":{"type":"unix","data":{"path":"/tmp/nbd-sock"}}}}\'')
> os.system('virsh qemu-monitor-command VM \'{"execute": "nbd-server-stop"}\'')
>
> def nbd_list():
> while 1:
> os.system('/path/to/build/qemu-nbd -L -k /tmp/nbd-sock')
>
> def test():
> sst = Thread(target=start_stop)
> sst.start()
> nlt = Thread(target=nbd_list)
> nlt.start()
>
> sst.join()
> nlt.join()
>
> test()
Fixes: CVE-2024-7409
Fixes: 3e7ef738c8 ("nbd/server: CVE-2024-7409: Close stray clients at server-stop")
CC: qemu-stable@nongnu.org
Reported-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240822143617.800419-2-eblake@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 3874f5f73c441c52f1c699c848d463b0eda01e4c)
Jira: https://issues.redhat.com/browse/RHEL-52599
Signed-off-by: Eric Blake <eblake@redhat.com>
---
blockdev-nbd.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/blockdev-nbd.c b/blockdev-nbd.c
index f73409ae49..b36f41b7c5 100644
--- a/blockdev-nbd.c
+++ b/blockdev-nbd.c
@@ -92,10 +92,13 @@ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
static void nbd_update_server_watch(NBDServerData *s)
{
- if (!s->max_connections || s->connections < s->max_connections) {
- qio_net_listener_set_client_func(s->listener, nbd_accept, NULL, NULL);
- } else {
- qio_net_listener_set_client_func(s->listener, NULL, NULL, NULL);
+ if (s->listener) {
+ if (!s->max_connections || s->connections < s->max_connections) {
+ qio_net_listener_set_client_func(s->listener, nbd_accept, NULL,
+ NULL);
+ } else {
+ qio_net_listener_set_client_func(s->listener, NULL, NULL, NULL);
+ }
}
}
@@ -113,6 +116,7 @@ static void nbd_server_free(NBDServerData *server)
*/
qio_net_listener_disconnect(server->listener);
object_unref(OBJECT(server->listener));
+ server->listener = NULL;
QLIST_FOREACH_SAFE(conn, &server->conns, next, tmp) {
qio_channel_shutdown(QIO_CHANNEL(conn->cioc), QIO_CHANNEL_SHUTDOWN_BOTH,
NULL);
--
2.39.3

184
kvm-nbd-server-CVE-2024-7409-Cap-default-max-connections.patch
View File

@ -1,184 +0,0 @@
From 20b179691fcd3a58aaf76269e66bd102dfbd0d2e Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Tue, 6 Aug 2024 13:53:00 -0500
Subject: [PATCH 3/5] nbd/server: CVE-2024-7409: Cap default max-connections to
100
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 263: nbd/server: fix CVE-2024-7409 (qemu crash on nbd-server-stop) [RHEL 10.0]
RH-Jira: RHEL-52599
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/4] ad547c43ee9bae4cf6476408176aa7a7892427ff (redhat/centos-stream/src/qemu-kvm)
Allowing an unlimited number of clients to any web service is a recipe
for a rudimentary denial of service attack: the client merely needs to
open lots of sockets without closing them, until qemu no longer has
any more fds available to allocate.
For qemu-nbd, we default to allowing only 1 connection unless more are
explicitly asked for (-e or --shared); this was historically picked as
a nice default (without an explicit -t, a non-persistent qemu-nbd goes
away after a client disconnects, without needing any additional
follow-up commands), and we are not going to change that interface now
(besides, someday we want to point people towards qemu-storage-daemon
instead of qemu-nbd).
But for qemu proper, and the newer qemu-storage-daemon, the QMP
nbd-server-start command has historically had a default of unlimited
number of connections, in part because unlike qemu-nbd it is
inherently persistent until nbd-server-stop. Allowing multiple client
sockets is particularly useful for clients that can take advantage of
MULTI_CONN (creating parallel sockets to increase throughput),
although known clients that do so (such as libnbd's nbdcopy) typically
use only 8 or 16 connections (the benefits of scaling diminish once
more sockets are competing for kernel attention). Picking a number
large enough for typical use cases, but not unlimited, makes it
slightly harder for a malicious client to perform a denial of service
merely by opening lots of connections withot progressing through the
handshake.
This change does not eliminate CVE-2024-7409 on its own, but reduces
the chance for fd exhaustion or unlimited memory usage as an attack
surface. On the other hand, by itself, it makes it more obvious that
with a finite limit, we have the problem of an unauthenticated client
holding 100 fds opened as a way to block out a legitimate client from
being able to connect; thus, later patches will further add timeouts
to reject clients that are not making progress.
This is an INTENTIONAL change in behavior, and will break any client
of nbd-server-start that was not passing an explicit max-connections
parameter, yet expects more than 100 simultaneous connections. We are
not aware of any such client (as stated above, most clients aware of
MULTI_CONN get by just fine on 8 or 16 connections, and probably cope
with later connections failing by relying on the earlier connections;
libvirt has not yet been passing max-connections, but generally
creates NBD servers with the intent for a single client for the sake
of live storage migration; meanwhile, the KubeSAN project anticipates
a large cluster sharing multiple clients [up to 8 per node, and up to
100 nodes in a cluster], but it currently uses qemu-nbd with an
explicit --shared=0 rather than qemu-storage-daemon with
nbd-server-start).
We considered using a deprecation period (declare that omitting
max-parameters is deprecated, and make it mandatory in 3 releases -
then we don't need to pick an arbitrary default); that has zero risk
of breaking any apps that accidentally depended on more than 100
connections, and where such breakage might not be noticed under unit
testing but only under the larger loads of production usage. But it
does not close the denial-of-service hole until far into the future,
and requires all apps to change to add the parameter even if 100 was
good enough. It also has a drawback that any app (like libvirt) that
is accidentally relying on an unlimited default should seriously
consider their own CVE now, at which point they are going to change to
pass explicit max-connections sooner than waiting for 3 qemu releases.
Finally, if our changed default breaks an app, that app can always
pass in an explicit max-parameters with a larger value.
It is also intentional that the HMP interface to nbd-server-start is
not changed to expose max-connections (any client needing to fine-tune
things should be using QMP).
Suggested-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240807174943.771624-12-eblake@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
[ericb: Expand commit message to summarize Dan's argument for why we
break corner-case back-compat behavior without a deprecation period]
Signed-off-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit c8a76dbd90c2f48df89b75bef74917f90a59b623)
Jira: https://issues.redhat.com/browse/RHEL-52599
Signed-off-by: Eric Blake <eblake@redhat.com>
---
block/monitor/block-hmp-cmds.c | 3 ++-
blockdev-nbd.c | 8 ++++++++
include/block/nbd.h | 7 +++++++
qapi/block-export.json | 4 ++--
4 files changed, 19 insertions(+), 3 deletions(-)
diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c
index d954bec6f1..bdf2eb50b6 100644
--- a/block/monitor/block-hmp-cmds.c
+++ b/block/monitor/block-hmp-cmds.c
@@ -402,7 +402,8 @@ void hmp_nbd_server_start(Monitor *mon, const QDict *qdict)
goto exit;
}
- nbd_server_start(addr, NULL, NULL, 0, &local_err);
+ nbd_server_start(addr, NULL, NULL, NBD_DEFAULT_MAX_CONNECTIONS,
+ &local_err);
qapi_free_SocketAddress(addr);
if (local_err != NULL) {
goto exit;
diff --git a/blockdev-nbd.c b/blockdev-nbd.c
index 267a1de903..24ba5382db 100644
--- a/blockdev-nbd.c
+++ b/blockdev-nbd.c
@@ -170,6 +170,10 @@ void nbd_server_start(SocketAddress *addr, const char *tls_creds,
void nbd_server_start_options(NbdServerOptions *arg, Error **errp)
{
+ if (!arg->has_max_connections) {
+ arg->max_connections = NBD_DEFAULT_MAX_CONNECTIONS;
+ }
+
nbd_server_start(arg->addr, arg->tls_creds, arg->tls_authz,
arg->max_connections, errp);
}
@@ -182,6 +186,10 @@ void qmp_nbd_server_start(SocketAddressLegacy *addr,
{
SocketAddress *addr_flat = socket_address_flatten(addr);
+ if (!has_max_connections) {
+ max_connections = NBD_DEFAULT_MAX_CONNECTIONS;
+ }
+
nbd_server_start(addr_flat, tls_creds, tls_authz, max_connections, errp);
qapi_free_SocketAddress(addr_flat);
}
diff --git a/include/block/nbd.h b/include/block/nbd.h
index 1d4d65922d..d4f8b21aec 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -39,6 +39,13 @@ extern const BlockExportDriver blk_exp_nbd;
*/
#define NBD_DEFAULT_HANDSHAKE_MAX_SECS 10
+/*
+ * NBD_DEFAULT_MAX_CONNECTIONS: Number of client sockets to allow at
+ * once; must be large enough to allow a MULTI_CONN-aware client like
+ * nbdcopy to create its typical number of 8-16 sockets.
+ */
+#define NBD_DEFAULT_MAX_CONNECTIONS 100
+
/* Handshake phase structs - this struct is passed on the wire */
typedef struct NBDOption {
diff --git a/qapi/block-export.json b/qapi/block-export.json
index 3919a2d5b9..f45e4fd481 100644
--- a/qapi/block-export.json
+++ b/qapi/block-export.json
@@ -28,7 +28,7 @@
# @max-connections: The maximum number of connections to allow at the
# same time, 0 for unlimited. Setting this to 1 also stops the
# server from advertising multiple client support (since 5.2;
-# default: 0)
+# default: 100)
#
# Since: 4.2
##
@@ -63,7 +63,7 @@
# @max-connections: The maximum number of connections to allow at the
# same time, 0 for unlimited. Setting this to 1 also stops the
# server from advertising multiple client support (since 5.2;
-# default: 0).
+# default: 100).
#
# Errors:
# - if the server is already running
--
2.39.3

173
kvm-nbd-server-CVE-2024-7409-Close-stray-clients-at-serv.patch
View File

@ -1,173 +0,0 @@
From 1b4bf69b064815a41ac18ef7276ceab0b9e0eb5b Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Wed, 7 Aug 2024 12:23:13 -0500
Subject: [PATCH 5/5] nbd/server: CVE-2024-7409: Close stray clients at
server-stop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 263: nbd/server: fix CVE-2024-7409 (qemu crash on nbd-server-stop) [RHEL 10.0]
RH-Jira: RHEL-52599
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/4] 6c5c7b5daa2b450122e98eb08ade1e1db56d20ae (redhat/centos-stream/src/qemu-kvm)
A malicious client can attempt to connect to an NBD server, and then
intentionally delay progress in the handshake, including if it does
not know the TLS secrets. Although the previous two patches reduce
this behavior by capping the default max-connections parameter and
killing slow clients, they did not eliminate the possibility of a
client waiting to close the socket until after the QMP nbd-server-stop
command is executed, at which point qemu would SEGV when trying to
dereference the NULL nbd_server global which is no longer present.
This amounts to a denial of service attack. Worse, if another NBD
server is started before the malicious client disconnects, I cannot
rule out additional adverse effects when the old client interferes
with the connection count of the new server (although the most likely
is a crash due to an assertion failure when checking
nbd_server->connections > 0).
For environments without this patch, the CVE can be mitigated by
ensuring (such as via a firewall) that only trusted clients can
connect to an NBD server. Note that using frameworks like libvirt
that ensure that TLS is used and that nbd-server-stop is not executed
while any trusted clients are still connected will only help if there
is also no possibility for an untrusted client to open a connection
but then stall on the NBD handshake.
Given the previous patches, it would be possible to guarantee that no
clients remain connected by having nbd-server-stop sleep for longer
than the default handshake deadline before finally freeing the global
nbd_server object, but that could make QMP non-responsive for a long
time. So intead, this patch fixes the problem by tracking all client
sockets opened while the server is running, and forcefully closing any
such sockets remaining without a completed handshake at the time of
nbd-server-stop, then waiting until the coroutines servicing those
sockets notice the state change. nbd-server-stop now has a second
AIO_WAIT_WHILE_UNLOCKED (the first is indirectly through the
blk_exp_close_all_type() that disconnects all clients that completed
handshakes), but forced socket shutdown is enough to progress the
coroutines and quickly tear down all clients before the server is
freed, thus finally fixing the CVE.
This patch relies heavily on the fact that nbd/server.c guarantees
that it only calls nbd_blockdev_client_closed() from the main loop
(see the assertion in nbd_client_put() and the hoops used in
nbd_client_put_nonzero() to achieve that); if we did not have that
guarantee, we would also need a mutex protecting our accesses of the
list of connections to survive re-entrancy from independent iothreads.
Although I did not actually try to test old builds, it looks like this
problem has existed since at least commit 862172f45c (v2.12.0, 2017) -
even back when that patch started using a QIONetListener to handle
listening on multiple sockets, nbd_server_free() was already unaware
that the nbd_blockdev_client_closed callback can be reached later by a
client thread that has not completed handshakes (and therefore the
client's socket never got added to the list closed in
nbd_export_close_all), despite that patch intentionally tearing down
the QIONetListener to prevent new clients.
Reported-by: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
Fixes: CVE-2024-7409
CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240807174943.771624-14-eblake@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit 3e7ef738c8462c45043a1d39f702a0990406a3b3)
Jira: https://issues.redhat.com/browse/RHEL-52599
Signed-off-by: Eric Blake <eblake@redhat.com>
---
blockdev-nbd.c | 35 ++++++++++++++++++++++++++++++++++-
1 file changed, 34 insertions(+), 1 deletion(-)
diff --git a/blockdev-nbd.c b/blockdev-nbd.c
index 24ba5382db..f73409ae49 100644
--- a/blockdev-nbd.c
+++ b/blockdev-nbd.c
@@ -21,12 +21,18 @@
#include "io/channel-socket.h"
#include "io/net-listener.h"
+typedef struct NBDConn {
+ QIOChannelSocket *cioc;
+ QLIST_ENTRY(NBDConn) next;
+} NBDConn;
+
typedef struct NBDServerData {
QIONetListener *listener;
QCryptoTLSCreds *tlscreds;
char *tlsauthz;
uint32_t max_connections;
uint32_t connections;
+ QLIST_HEAD(, NBDConn) conns;
} NBDServerData;
static NBDServerData *nbd_server;
@@ -51,6 +57,14 @@ int nbd_server_max_connections(void)
static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
{
+ NBDConn *conn = nbd_client_owner(client);
+
+ assert(qemu_in_main_thread() && nbd_server);
+
+ object_unref(OBJECT(conn->cioc));
+ QLIST_REMOVE(conn, next);
+ g_free(conn);
+
nbd_client_put(client);
assert(nbd_server->connections > 0);
nbd_server->connections--;
@@ -60,14 +74,20 @@ static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
gpointer opaque)
{
+ NBDConn *conn = g_new0(NBDConn, 1);
+
+ assert(qemu_in_main_thread() && nbd_server);
nbd_server->connections++;
+ object_ref(OBJECT(cioc));
+ conn->cioc = cioc;
+ QLIST_INSERT_HEAD(&nbd_server->conns, conn, next);
nbd_update_server_watch(nbd_server);
qio_channel_set_name(QIO_CHANNEL(cioc), "nbd-server");
/* TODO - expose handshake timeout as QMP option */
nbd_client_new(cioc, NBD_DEFAULT_HANDSHAKE_MAX_SECS,
nbd_server->tlscreds, nbd_server->tlsauthz,
- nbd_blockdev_client_closed, NULL);
+ nbd_blockdev_client_closed, conn);
}
static void nbd_update_server_watch(NBDServerData *s)
@@ -81,12 +101,25 @@ static void nbd_update_server_watch(NBDServerData *s)
static void nbd_server_free(NBDServerData *server)
{
+ NBDConn *conn, *tmp;
+
if (!server) {
return;
}
+ /*
+ * Forcefully close the listener socket, and any clients that have
+ * not yet disconnected on their own.
+ */
qio_net_listener_disconnect(server->listener);
object_unref(OBJECT(server->listener));
+ QLIST_FOREACH_SAFE(conn, &server->conns, next, tmp) {
+ qio_channel_shutdown(QIO_CHANNEL(conn->cioc), QIO_CHANNEL_SHUTDOWN_BOTH,
+ NULL);
+ }
+
+ AIO_WAIT_WHILE_UNLOCKED(NULL, server->connections > 0);
+
if (server->tlscreds) {
object_unref(OBJECT(server->tlscreds));
}
--
2.39.3

134
kvm-nbd-server-CVE-2024-7409-Drop-non-negotiating-client.patch
View File

@ -1,134 +0,0 @@
From 97012ea86a4a0a28fef68e43b989d858c8392e2a Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Thu, 8 Aug 2024 16:05:08 -0500
Subject: [PATCH 4/5] nbd/server: CVE-2024-7409: Drop non-negotiating clients
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 263: nbd/server: fix CVE-2024-7409 (qemu crash on nbd-server-stop) [RHEL 10.0]
RH-Jira: RHEL-52599
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/4] c3dad94d423d2f431d1e605c412099b9fe0bd76e (redhat/centos-stream/src/qemu-kvm)
A client that opens a socket but does not negotiate is merely hogging
qemu's resources (an open fd and a small amount of memory); and a
malicious client that can access the port where NBD is listening can
attempt a denial of service attack by intentionally opening and
abandoning lots of unfinished connections. The previous patch put a
default bound on the number of such ongoing connections, but once that
limit is hit, no more clients can connect (including legitimate ones).
The solution is to insist that clients complete handshake within a
reasonable time limit, defaulting to 10 seconds. A client that has
not successfully completed NBD_OPT_GO by then (including the case of
where the client didn't know TLS credentials to even reach the point
of NBD_OPT_GO) is wasting our time and does not deserve to stay
connected. Later patches will allow fine-tuning the limit away from
the default value (including disabling it for doing integration
testing of the handshake process itself).
Note that this patch in isolation actually makes it more likely to see
qemu SEGV after nbd-server-stop, as any client socket still connected
when the server shuts down will now be closed after 10 seconds rather
than at the client's whims. That will be addressed in the next patch.
For a demo of this patch in action:
$ qemu-nbd -f raw -r -t -e 10 file &
$ nbdsh --opt-mode -c '
H = list()
for i in range(20):
print(i)
H.insert(i, nbd.NBD())
H[i].set_opt_mode(True)
H[i].connect_uri("nbd://localhost")
'
$ kill $!
where later connections get to start progressing once earlier ones are
forcefully dropped for taking too long, rather than hanging.
Suggested-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240807174943.771624-13-eblake@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
[eblake: rebase to changes earlier in series, reduce scope of timer]
Signed-off-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit b9b72cb3ce15b693148bd09cef7e50110566d8a0)
Jira: https://issues.redhat.com/browse/RHEL-52599
Signed-off-by: Eric Blake <eblake@redhat.com>
---
nbd/server.c | 28 +++++++++++++++++++++++++++-
nbd/trace-events | 1 +
2 files changed, 28 insertions(+), 1 deletion(-)
diff --git a/nbd/server.c b/nbd/server.c
index e50012499f..39285cc971 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -3186,22 +3186,48 @@ static void nbd_client_receive_next_request(NBDClient *client)
}
}
+static void nbd_handshake_timer_cb(void *opaque)
+{
+ QIOChannel *ioc = opaque;
+
+ trace_nbd_handshake_timer_cb();
+ qio_channel_shutdown(ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+}
+
static coroutine_fn void nbd_co_client_start(void *opaque)
{
NBDClient *client = opaque;
Error *local_err = NULL;
+ QEMUTimer *handshake_timer = NULL;
qemu_co_mutex_init(&client->send_lock);
- /* TODO - utilize client->handshake_max_secs */
+ /*
+ * Create a timer to bound the time spent in negotiation. If the
+ * timer expires, it is likely nbd_negotiate will fail because the
+ * socket was shutdown.
+ */
+ if (client->handshake_max_secs > 0) {
+ handshake_timer = aio_timer_new(qemu_get_aio_context(),
+ QEMU_CLOCK_REALTIME,
+ SCALE_NS,
+ nbd_handshake_timer_cb,
+ client->sioc);
+ timer_mod(handshake_timer,
+ qemu_clock_get_ns(QEMU_CLOCK_REALTIME) +
+ client->handshake_max_secs * NANOSECONDS_PER_SECOND);
+ }
+
if (nbd_negotiate(client, &local_err)) {
if (local_err) {
error_report_err(local_err);
}
+ timer_free(handshake_timer);
client_close(client, false);
return;
}
+ timer_free(handshake_timer);
WITH_QEMU_LOCK_GUARD(&client->lock) {
nbd_client_receive_next_request(client);
}
diff --git a/nbd/trace-events b/nbd/trace-events
index 00ae3216a1..cbd0a4ab7e 100644
--- a/nbd/trace-events
+++ b/nbd/trace-events
@@ -76,6 +76,7 @@ nbd_co_receive_request_payload_received(uint64_t cookie, uint64_t len) "Payload
nbd_co_receive_ext_payload_compliance(uint64_t from, uint64_t len) "client sent non-compliant write without payload flag: from=0x%" PRIx64 ", len=0x%" PRIx64
nbd_co_receive_align_compliance(const char *op, uint64_t from, uint64_t len, uint32_t align) "client sent non-compliant unaligned %s request: from=0x%" PRIx64 ", len=0x%" PRIx64 ", align=0x%" PRIx32
nbd_trip(void) "Reading request"
+nbd_handshake_timer_cb(void) "client took too long to negotiate"
# client-connection.c
nbd_connect_thread_sleep(uint64_t timeout) "timeout %" PRIu64
--
2.39.3

330
kvm-nbd-server-Mark-negotiation-functions-as-coroutine_f.patch
View File

@ -1,330 +0,0 @@
From 55e78a14c6a6956a3ac65f36b9b8b8c49eff959b Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Mon, 8 Apr 2024 11:00:44 -0500
Subject: [PATCH 2/4] nbd/server: Mark negotiation functions as coroutine_fn
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/4] f364e5cd2a9eac2d4f6af2841479f1dfb2f8df58 (ebblake/centos-qemu-kvm)
nbd_negotiate() is already marked coroutine_fn. And given the fix in
the previous patch to have nbd_negotiate_handle_starttls not create
and wait on a g_main_loop (as that would violate coroutine
constraints), it is worth marking the rest of the related static
functions reachable only during option negotiation as also being
coroutine_fn.
Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240408160214.1200629-6-eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
[eblake: drop one spurious coroutine_fn marking]
Signed-off-by: Eric Blake <eblake@redhat.com>
Jira: https://issues.redhat.com/browse/RHEL-40959
(cherry picked from commit 4fa333e08dd96395a99ea8dd9e4c73a29dd23344)
Signed-off-by: Eric Blake <eblake@redhat.com>
---
nbd/server.c | 102 +++++++++++++++++++++++++++++----------------------
1 file changed, 59 insertions(+), 43 deletions(-)
diff --git a/nbd/server.c b/nbd/server.c
index 98ae0e1632..892797bb11 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -195,8 +195,9 @@ static inline void set_be_option_rep(NBDOptionReply *rep, uint32_t option,
/* Send a reply header, including length, but no payload.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
- uint32_t len, Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
+ uint32_t len, Error **errp)
{
NBDOptionReply rep;
@@ -211,15 +212,15 @@ static int nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
/* Send a reply header with default 0 length.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_send_rep(NBDClient *client, uint32_t type,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_rep(NBDClient *client, uint32_t type, Error **errp)
{
return nbd_negotiate_send_rep_len(client, type, 0, errp);
}
/* Send an error reply.
* Return -errno on error, 0 on success. */
-static int G_GNUC_PRINTF(4, 0)
+static coroutine_fn int G_GNUC_PRINTF(4, 0)
nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type,
Error **errp, const char *fmt, va_list va)
{
@@ -259,7 +260,7 @@ nbd_sanitize_name(const char *name)
/* Send an error reply.
* Return -errno on error, 0 on success. */
-static int G_GNUC_PRINTF(4, 5)
+static coroutine_fn int G_GNUC_PRINTF(4, 5)
nbd_negotiate_send_rep_err(NBDClient *client, uint32_t type,
Error **errp, const char *fmt, ...)
{
@@ -275,7 +276,7 @@ nbd_negotiate_send_rep_err(NBDClient *client, uint32_t type,
/* Drop remainder of the current option, and send a reply with the
* given error type and message. Return -errno on read or write
* failure; or 0 if connection is still live. */
-static int G_GNUC_PRINTF(4, 0)
+static coroutine_fn int G_GNUC_PRINTF(4, 0)
nbd_opt_vdrop(NBDClient *client, uint32_t type, Error **errp,
const char *fmt, va_list va)
{
@@ -288,7 +289,7 @@ nbd_opt_vdrop(NBDClient *client, uint32_t type, Error **errp,
return ret;
}
-static int G_GNUC_PRINTF(4, 5)
+static coroutine_fn int G_GNUC_PRINTF(4, 5)
nbd_opt_drop(NBDClient *client, uint32_t type, Error **errp,
const char *fmt, ...)
{
@@ -302,7 +303,7 @@ nbd_opt_drop(NBDClient *client, uint32_t type, Error **errp,
return ret;
}
-static int G_GNUC_PRINTF(3, 4)
+static coroutine_fn int G_GNUC_PRINTF(3, 4)
nbd_opt_invalid(NBDClient *client, Error **errp, const char *fmt, ...)
{
int ret;
@@ -319,8 +320,9 @@ nbd_opt_invalid(NBDClient *client, Error **errp, const char *fmt, ...)
* If @check_nul, require that no NUL bytes appear in buffer.
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success. */
-static int nbd_opt_read(NBDClient *client, void *buffer, size_t size,
- bool check_nul, Error **errp)
+static coroutine_fn int
+nbd_opt_read(NBDClient *client, void *buffer, size_t size,
+ bool check_nul, Error **errp)
{
if (size > client->optlen) {
return nbd_opt_invalid(client, errp,
@@ -343,7 +345,8 @@ static int nbd_opt_read(NBDClient *client, void *buffer, size_t size,
/* Drop size bytes from the unparsed payload of the current option.
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success. */
-static int nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
+static coroutine_fn int
+nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
{
if (size > client->optlen) {
return nbd_opt_invalid(client, errp,
@@ -366,8 +369,9 @@ static int nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success.
*/
-static int nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
- Error **errp)
+static coroutine_fn int
+nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
+ Error **errp)
{
int ret;
uint32_t len;
@@ -402,8 +406,8 @@ static int nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
/* Send a single NBD_REP_SERVER reply to NBD_OPT_LIST, including payload.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp, Error **errp)
{
ERRP_GUARD();
size_t name_len, desc_len;
@@ -444,7 +448,8 @@ static int nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp,
/* Process the NBD_OPT_LIST command, with a potential series of replies.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_handle_list(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_handle_list(NBDClient *client, Error **errp)
{
NBDExport *exp;
assert(client->opt == NBD_OPT_LIST);
@@ -459,7 +464,8 @@ static int nbd_negotiate_handle_list(NBDClient *client, Error **errp)
return nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
}
-static void nbd_check_meta_export(NBDClient *client, NBDExport *exp)
+static coroutine_fn void
+nbd_check_meta_export(NBDClient *client, NBDExport *exp)
{
if (exp != client->contexts.exp) {
client->contexts.count = 0;
@@ -468,8 +474,9 @@ static void nbd_check_meta_export(NBDClient *client, NBDExport *exp)
/* Send a reply to NBD_OPT_EXPORT_NAME.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
+ Error **errp)
{
ERRP_GUARD();
g_autofree char *name = NULL;
@@ -536,9 +543,9 @@ static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
/* Send a single NBD_REP_INFO, with a buffer @buf of @length bytes.
* The buffer does NOT include the info type prefix.
* Return -errno on error, 0 if ready to send more. */
-static int nbd_negotiate_send_info(NBDClient *client,
- uint16_t info, uint32_t length, void *buf,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_info(NBDClient *client, uint16_t info, uint32_t length,
+ void *buf, Error **errp)
{
int rc;
@@ -565,7 +572,8 @@ static int nbd_negotiate_send_info(NBDClient *client,
* -errno transmission error occurred or @fatal was requested, errp is set
* 0 error message successfully sent to client, errp is not set
*/
-static int nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
+static coroutine_fn int
+nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
{
int ret;
@@ -583,7 +591,8 @@ static int nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
/* Handle NBD_OPT_INFO and NBD_OPT_GO.
* Return -errno on error, 0 if ready for next option, and 1 to move
* into transmission phase. */
-static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_handle_info(NBDClient *client, Error **errp)
{
int rc;
g_autofree char *name = NULL;
@@ -755,7 +764,8 @@ struct NBDTLSServerHandshakeData {
Coroutine *co;
};
-static void nbd_server_tls_handshake(QIOTask *task, void *opaque)
+static void
+nbd_server_tls_handshake(QIOTask *task, void *opaque)
{
struct NBDTLSServerHandshakeData *data = opaque;
@@ -768,8 +778,8 @@ static void nbd_server_tls_handshake(QIOTask *task, void *opaque)
/* Handle NBD_OPT_STARTTLS. Return NULL to drop connection, or else the
* new channel for all further (now-encrypted) communication. */
-static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
- Error **errp)
+static coroutine_fn QIOChannel *
+nbd_negotiate_handle_starttls(NBDClient *client, Error **errp)
{
QIOChannel *ioc;
QIOChannelTLS *tioc;
@@ -821,10 +831,9 @@ static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
*
* For NBD_OPT_LIST_META_CONTEXT @context_id is ignored, 0 is used instead.
*/
-static int nbd_negotiate_send_meta_context(NBDClient *client,
- const char *context,
- uint32_t context_id,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_meta_context(NBDClient *client, const char *context,
+ uint32_t context_id, Error **errp)
{
NBDOptionReplyMetaContext opt;
struct iovec iov[] = {
@@ -849,8 +858,9 @@ static int nbd_negotiate_send_meta_context(NBDClient *client,
* Return true if @query matches @pattern, or if @query is empty when
* the @client is performing _LIST_.
*/
-static bool nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
- const char *query)
+static coroutine_fn bool
+nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
+ const char *query)
{
if (!*query) {
trace_nbd_negotiate_meta_query_parse("empty");
@@ -867,7 +877,8 @@ static bool nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
/*
* Return true and adjust @str in place if it begins with @prefix.
*/
-static bool nbd_strshift(const char **str, const char *prefix)
+static coroutine_fn bool
+nbd_strshift(const char **str, const char *prefix)
{
size_t len = strlen(prefix);
@@ -883,8 +894,9 @@ static bool nbd_strshift(const char **str, const char *prefix)
* Handle queries to 'base' namespace. For now, only the base:allocation
* context is available. Return true if @query has been handled.
*/
-static bool nbd_meta_base_query(NBDClient *client, NBDMetaContexts *meta,
- const char *query)
+static coroutine_fn bool
+nbd_meta_base_query(NBDClient *client, NBDMetaContexts *meta,
+ const char *query)
{
if (!nbd_strshift(&query, "base:")) {
return false;
@@ -903,8 +915,9 @@ static bool nbd_meta_base_query(NBDClient *client, NBDMetaContexts *meta,
* and qemu:allocation-depth contexts are available. Return true if @query
* has been handled.
*/
-static bool nbd_meta_qemu_query(NBDClient *client, NBDMetaContexts *meta,
- const char *query)
+static coroutine_fn bool
+nbd_meta_qemu_query(NBDClient *client, NBDMetaContexts *meta,
+ const char *query)
{
size_t i;
@@ -968,8 +981,9 @@ static bool nbd_meta_qemu_query(NBDClient *client, NBDMetaContexts *meta,
*
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success. */
-static int nbd_negotiate_meta_query(NBDClient *client,
- NBDMetaContexts *meta, Error **errp)
+static coroutine_fn int
+nbd_negotiate_meta_query(NBDClient *client,
+ NBDMetaContexts *meta, Error **errp)
{
int ret;
g_autofree char *query = NULL;
@@ -1008,7 +1022,8 @@ static int nbd_negotiate_meta_query(NBDClient *client,
* Handle NBD_OPT_LIST_META_CONTEXT and NBD_OPT_SET_META_CONTEXT
*
* Return -errno on I/O error, or 0 if option was completely handled. */
-static int nbd_negotiate_meta_queries(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_meta_queries(NBDClient *client, Error **errp)
{
int ret;
g_autofree char *export_name = NULL;
@@ -1136,7 +1151,8 @@ static int nbd_negotiate_meta_queries(NBDClient *client, Error **errp)
* 1 if client sent NBD_OPT_ABORT, i.e. on valid disconnect,
* errp is not set
*/
-static int nbd_negotiate_options(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_options(NBDClient *client, Error **errp)
{
uint32_t flags;
bool fixedNewstyle = false;
--
2.39.3

175
kvm-nbd-server-Plumb-in-new-args-to-nbd_client_add.patch
View File

@ -1,175 +0,0 @@
From 785893c171d994bbcffe0585953ca0d290f3c27e Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Wed, 7 Aug 2024 08:50:01 -0500
Subject: [PATCH 2/5] nbd/server: Plumb in new args to nbd_client_add()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 263: nbd/server: fix CVE-2024-7409 (qemu crash on nbd-server-stop) [RHEL 10.0]
RH-Jira: RHEL-52599
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/4] 68e9f83d467704d3dfbf0a879b2bb4d9a568f81c (redhat/centos-stream/src/qemu-kvm)
Upcoming patches to fix a CVE need to track an opaque pointer passed
in by the owner of a client object, as well as request for a time
limit on how fast negotiation must complete. Prepare for that by
changing the signature of nbd_client_new() and adding an accessor to
get at the opaque pointer, although for now the two servers
(qemu-nbd.c and blockdev-nbd.c) do not change behavior even though
they pass in a new default timeout value.
Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240807174943.771624-11-eblake@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
[eblake: s/LIMIT/MAX_SECS/ as suggested by Dan]
Signed-off-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit fb1c2aaa981e0a2fa6362c9985f1296b74f055ac)
Jira: https://issues.redhat.com/browse/RHEL-52599
Signed-off-by: Eric Blake <eblake@redhat.com>
---
blockdev-nbd.c | 6 ++++--
include/block/nbd.h | 11 ++++++++++-
nbd/server.c | 20 +++++++++++++++++---
qemu-nbd.c | 4 +++-
4 files changed, 34 insertions(+), 7 deletions(-)
diff --git a/blockdev-nbd.c b/blockdev-nbd.c
index 213012435f..267a1de903 100644
--- a/blockdev-nbd.c
+++ b/blockdev-nbd.c
@@ -64,8 +64,10 @@ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
nbd_update_server_watch(nbd_server);
qio_channel_set_name(QIO_CHANNEL(cioc), "nbd-server");
- nbd_client_new(cioc, nbd_server->tlscreds, nbd_server->tlsauthz,
- nbd_blockdev_client_closed);
+ /* TODO - expose handshake timeout as QMP option */
+ nbd_client_new(cioc, NBD_DEFAULT_HANDSHAKE_MAX_SECS,
+ nbd_server->tlscreds, nbd_server->tlsauthz,
+ nbd_blockdev_client_closed, NULL);
}
static void nbd_update_server_watch(NBDServerData *s)
diff --git a/include/block/nbd.h b/include/block/nbd.h
index 4e7bd6342f..1d4d65922d 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -33,6 +33,12 @@ typedef struct NBDMetaContexts NBDMetaContexts;
extern const BlockExportDriver blk_exp_nbd;
+/*
+ * NBD_DEFAULT_HANDSHAKE_MAX_SECS: Number of seconds in which client must
+ * succeed at NBD_OPT_GO before being forcefully dropped as too slow.
+ */
+#define NBD_DEFAULT_HANDSHAKE_MAX_SECS 10
+
/* Handshake phase structs - this struct is passed on the wire */
typedef struct NBDOption {
@@ -403,9 +409,12 @@ AioContext *nbd_export_aio_context(NBDExport *exp);
NBDExport *nbd_export_find(const char *name);
void nbd_client_new(QIOChannelSocket *sioc,
+ uint32_t handshake_max_secs,
QCryptoTLSCreds *tlscreds,
const char *tlsauthz,
- void (*close_fn)(NBDClient *, bool));
+ void (*close_fn)(NBDClient *, bool),
+ void *owner);
+void *nbd_client_owner(NBDClient *client);
void nbd_client_get(NBDClient *client);
void nbd_client_put(NBDClient *client);
diff --git a/nbd/server.c b/nbd/server.c
index 892797bb11..e50012499f 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -124,12 +124,14 @@ struct NBDMetaContexts {
struct NBDClient {
int refcount; /* atomic */
void (*close_fn)(NBDClient *client, bool negotiated);
+ void *owner;
QemuMutex lock;
NBDExport *exp;
QCryptoTLSCreds *tlscreds;
char *tlsauthz;
+ uint32_t handshake_max_secs;
QIOChannelSocket *sioc; /* The underlying data channel */
QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
@@ -3191,6 +3193,7 @@ static coroutine_fn void nbd_co_client_start(void *opaque)
qemu_co_mutex_init(&client->send_lock);
+ /* TODO - utilize client->handshake_max_secs */
if (nbd_negotiate(client, &local_err)) {
if (local_err) {
error_report_err(local_err);
@@ -3205,14 +3208,17 @@ static coroutine_fn void nbd_co_client_start(void *opaque)
}
/*
- * Create a new client listener using the given channel @sioc.
+ * Create a new client listener using the given channel @sioc and @owner.
* Begin servicing it in a coroutine. When the connection closes, call
- * @close_fn with an indication of whether the client completed negotiation.
+ * @close_fn with an indication of whether the client completed negotiation
+ * within @handshake_max_secs seconds (0 for unbounded).
*/
void nbd_client_new(QIOChannelSocket *sioc,
+ uint32_t handshake_max_secs,
QCryptoTLSCreds *tlscreds,
const char *tlsauthz,
- void (*close_fn)(NBDClient *, bool))
+ void (*close_fn)(NBDClient *, bool),
+ void *owner)
{
NBDClient *client;
Coroutine *co;
@@ -3225,13 +3231,21 @@ void nbd_client_new(QIOChannelSocket *sioc,
object_ref(OBJECT(client->tlscreds));
}
client->tlsauthz = g_strdup(tlsauthz);
+ client->handshake_max_secs = handshake_max_secs;
client->sioc = sioc;
qio_channel_set_delay(QIO_CHANNEL(sioc), false);
object_ref(OBJECT(client->sioc));
client->ioc = QIO_CHANNEL(sioc);
object_ref(OBJECT(client->ioc));
client->close_fn = close_fn;
+ client->owner = owner;
co = qemu_coroutine_create(nbd_co_client_start, client);
qemu_coroutine_enter(co);
}
+
+void *
+nbd_client_owner(NBDClient *client)
+{
+ return client->owner;
+}
diff --git a/qemu-nbd.c b/qemu-nbd.c
index d7b3ccab21..48e2fa5858 100644
--- a/qemu-nbd.c
+++ b/qemu-nbd.c
@@ -390,7 +390,9 @@ static void nbd_accept(QIONetListener *listener, QIOChannelSocket *cioc,
nb_fds++;
nbd_update_server_watch();
- nbd_client_new(cioc, tlscreds, tlsauthz, nbd_client_closed);
+ /* TODO - expose handshake timeout as command line option */
+ nbd_client_new(cioc, NBD_DEFAULT_HANDSHAKE_MAX_SECS,
+ tlscreds, tlsauthz, nbd_client_closed, NULL);
}
static void nbd_update_server_watch(void)
--
2.39.3

208
kvm-nbd-server-do-not-poll-within-a-coroutine-context.patch
View File

@ -1,208 +0,0 @@
From 484fe3af54a3e421be9e370d47eabe0d8cc5c50d Mon Sep 17 00:00:00 2001
From: Zhu Yangyang <zhuyangyang14@huawei.com>
Date: Mon, 8 Apr 2024 11:00:43 -0500
Subject: [PATCH 1/4] nbd/server: do not poll within a coroutine context
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/4] 379f38d46d204890e47a5eb744292d728badc7db (ebblake/centos-qemu-kvm)
Coroutines are not supposed to block. Instead, they should yield.
The client performs TLS upgrade outside of an AIOContext, during
synchronous handshake; this still requires g_main_loop. But the
server responds to TLS upgrade inside a coroutine, so a nested
g_main_loop is wrong. Since the two callbacks no longer share more
than the setting of data.complete and data.error, it's just as easy to
use static helpers instead of trying to share a common code path. It
is also possible to add assertions that no other code is interfering
with the eventual path to qio reaching the callback, whether or not it
required a yield or main loop.
Fixes: f95910f ("nbd: implement TLS support in the protocol negotiation")
Signed-off-by: Zhu Yangyang <zhuyangyang14@huawei.com>
[eblake: move callbacks to their use point, add assertions]
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240408160214.1200629-5-eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Jira: https://issues.redhat.com/browse/RHEL-40959
(cherry picked from commit ae6d91a7e9b77abb029ed3fa9fad461422286942)
Signed-off-by: Eric Blake <eblake@redhat.com>
---
nbd/client.c | 28 ++++++++++++++++++++++++----
nbd/common.c | 11 -----------
nbd/nbd-internal.h | 10 ----------
nbd/server.c | 28 +++++++++++++++++++++++-----
4 files changed, 47 insertions(+), 30 deletions(-)
diff --git a/nbd/client.c b/nbd/client.c
index 29ffc609a4..c89c750467 100644
--- a/nbd/client.c
+++ b/nbd/client.c
@@ -596,13 +596,31 @@ static int nbd_request_simple_option(QIOChannel *ioc, int opt, bool strict,
return 1;
}
+/* Callback to learn when QIO TLS upgrade is complete */
+struct NBDTLSClientHandshakeData {
+ bool complete;
+ Error *error;
+ GMainLoop *loop;
+};
+
+static void nbd_client_tls_handshake(QIOTask *task, void *opaque)
+{
+ struct NBDTLSClientHandshakeData *data = opaque;
+
+ qio_task_propagate_error(task, &data->error);
+ data->complete = true;
+ if (data->loop) {
+ g_main_loop_quit(data->loop);
+ }
+}
+
static QIOChannel *nbd_receive_starttls(QIOChannel *ioc,
QCryptoTLSCreds *tlscreds,
const char *hostname, Error **errp)
{
int ret;
QIOChannelTLS *tioc;
- struct NBDTLSHandshakeData data = { 0 };
+ struct NBDTLSClientHandshakeData data = { 0 };
ret = nbd_request_simple_option(ioc, NBD_OPT_STARTTLS, true, errp);
if (ret <= 0) {
@@ -619,18 +637,20 @@ static QIOChannel *nbd_receive_starttls(QIOChannel *ioc,
return NULL;
}
qio_channel_set_name(QIO_CHANNEL(tioc), "nbd-client-tls");
- data.loop = g_main_loop_new(g_main_context_default(), FALSE);
trace_nbd_receive_starttls_tls_handshake();
qio_channel_tls_handshake(tioc,
- nbd_tls_handshake,
+ nbd_client_tls_handshake,
&data,
NULL,
NULL);
if (!data.complete) {
+ data.loop = g_main_loop_new(g_main_context_default(), FALSE);
g_main_loop_run(data.loop);
+ assert(data.complete);
+ g_main_loop_unref(data.loop);
}
- g_main_loop_unref(data.loop);
+
if (data.error) {
error_propagate(errp, data.error);
object_unref(OBJECT(tioc));
diff --git a/nbd/common.c b/nbd/common.c
index 3247c1d618..589a748cfe 100644
--- a/nbd/common.c
+++ b/nbd/common.c
@@ -47,17 +47,6 @@ int nbd_drop(QIOChannel *ioc, size_t size, Error **errp)
}
-void nbd_tls_handshake(QIOTask *task,
- void *opaque)
-{
- struct NBDTLSHandshakeData *data = opaque;
-
- qio_task_propagate_error(task, &data->error);
- data->complete = true;
- g_main_loop_quit(data->loop);
-}
-
-
const char *nbd_opt_lookup(uint32_t opt)
{
switch (opt) {
diff --git a/nbd/nbd-internal.h b/nbd/nbd-internal.h
index dfa02f77ee..91895106a9 100644
--- a/nbd/nbd-internal.h
+++ b/nbd/nbd-internal.h
@@ -72,16 +72,6 @@ static inline int nbd_write(QIOChannel *ioc, const void *buffer, size_t size,
return qio_channel_write_all(ioc, buffer, size, errp) < 0 ? -EIO : 0;
}
-struct NBDTLSHandshakeData {
- GMainLoop *loop;
- bool complete;
- Error *error;
-};
-
-
-void nbd_tls_handshake(QIOTask *task,
- void *opaque);
-
int nbd_drop(QIOChannel *ioc, size_t size, Error **errp);
#endif
diff --git a/nbd/server.c b/nbd/server.c
index c3484cc1eb..98ae0e1632 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -748,6 +748,23 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
return rc;
}
+/* Callback to learn when QIO TLS upgrade is complete */
+struct NBDTLSServerHandshakeData {
+ bool complete;
+ Error *error;
+ Coroutine *co;
+};
+
+static void nbd_server_tls_handshake(QIOTask *task, void *opaque)
+{
+ struct NBDTLSServerHandshakeData *data = opaque;
+
+ qio_task_propagate_error(task, &data->error);
+ data->complete = true;
+ if (!qemu_coroutine_entered(data->co)) {
+ aio_co_wake(data->co);
+ }
+}
/* Handle NBD_OPT_STARTTLS. Return NULL to drop connection, or else the
* new channel for all further (now-encrypted) communication. */
@@ -756,7 +773,7 @@ static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
{
QIOChannel *ioc;
QIOChannelTLS *tioc;
- struct NBDTLSHandshakeData data = { 0 };
+ struct NBDTLSServerHandshakeData data = { 0 };
assert(client->opt == NBD_OPT_STARTTLS);
@@ -777,17 +794,18 @@ static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
qio_channel_set_name(QIO_CHANNEL(tioc), "nbd-server-tls");
trace_nbd_negotiate_handle_starttls_handshake();
- data.loop = g_main_loop_new(g_main_context_default(), FALSE);
+ data.co = qemu_coroutine_self();
qio_channel_tls_handshake(tioc,
- nbd_tls_handshake,
+ nbd_server_tls_handshake,
&data,
NULL,
NULL);
if (!data.complete) {
- g_main_loop_run(data.loop);
+ qemu_coroutine_yield();
+ assert(data.complete);
}
- g_main_loop_unref(data.loop);
+
if (data.error) {
object_unref(OBJECT(tioc));
error_propagate(errp, data.error);
--
2.39.3

366
kvm-net-bundle-all-offloads-in-a-single-struct.patch Normal file
View File

@ -0,0 +1,366 @@
From e98a5779344e632fab5cce16508fb6fbdb847332 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 22 Sep 2025 16:18:15 +0200
Subject: [PATCH 06/19] net: bundle all offloads in a single struct
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 456: backport support for GSO over UDP tunnel offload
RH-Jira: RHEL-143785
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Commit: [1/14] 6895db45d4c3490df93d5156a72fa11f706fa5d2 (lvivier/qemu-kvm-centos)
JIRA: https://issues.redhat.com/browse/RHEL-143785
The set_offload() argument list is already pretty long and
we are going to introduce soon a bunch of additional offloads.
Replace the offload arguments with a single struct and update
all the relevant call-sites.
No functional changes intended.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a9d4dd043b8c71b791e9ff05e17ef06072d9714e.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit e5fd02d8253abdc25c0eb145765734890c256b71)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/net/e1000e_core.c | 5 +++--
hw/net/igb_core.c | 5 +++--
hw/net/virtio-net.c | 19 +++++++++++--------
hw/net/vmxnet3.c | 13 +++++--------
include/net/net.h | 15 ++++++++++++---
net/net.c | 5 ++---
net/netmap.c | 3 +--
net/tap-bsd.c | 3 +--
net/tap-linux.c | 21 ++++++++++++---------
net/tap-solaris.c | 4 ++--
net/tap-stub.c | 3 +--
net/tap.c | 8 ++++----
net/tap_int.h | 4 ++--
13 files changed, 59 insertions(+), 49 deletions(-)
diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index 06657bb3ac..8fef598b49 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -2822,8 +2822,9 @@ e1000e_update_rx_offloads(E1000ECore *core)
trace_e1000e_rx_set_cso(cso_state);
if (core->has_vnet) {
- qemu_set_offload(qemu_get_queue(core->owner_nic)->peer,
- cso_state, 0, 0, 0, 0, 0, 0);
+ NetOffloads ol = { .csum = cso_state };
+
+ qemu_set_offload(qemu_get_queue(core->owner_nic)->peer, &ol);
}
}
diff --git a/hw/net/igb_core.c b/hw/net/igb_core.c
index 39e3ce1c8f..45d8fd795b 100644
--- a/hw/net/igb_core.c
+++ b/hw/net/igb_core.c
@@ -3058,8 +3058,9 @@ igb_update_rx_offloads(IGBCore *core)
trace_e1000e_rx_set_cso(cso_state);
if (core->has_vnet) {
- qemu_set_offload(qemu_get_queue(core->owner_nic)->peer,
- cso_state, 0, 0, 0, 0, 0, 0);
+ NetOffloads ol = {.csum = cso_state };
+
+ qemu_set_offload(qemu_get_queue(core->owner_nic)->peer, &ol);
}
}
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 6b5b5dace3..b86ba1fd27 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -773,14 +773,17 @@ static uint64_t virtio_net_bad_features(VirtIODevice *vdev)
static void virtio_net_apply_guest_offloads(VirtIONet *n)
{
- qemu_set_offload(qemu_get_queue(n->nic)->peer,
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_CSUM)),
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO4)),
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO6)),
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_ECN)),
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)),
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO4)),
- !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO6)));
+ NetOffloads ol = {
+ .csum = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_CSUM)),
+ .tso4 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO4)),
+ .tso6 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO6)),
+ .ecn = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_ECN)),
+ .ufo = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)),
+ .uso4 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO4)),
+ .uso6 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO6)),
+ };
+
+ qemu_set_offload(qemu_get_queue(n->nic)->peer, &ol);
}
static uint64_t virtio_net_guest_offloads_by_features(uint64_t features)
diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c
index af73aa8ef2..03732375a7 100644
--- a/hw/net/vmxnet3.c
+++ b/hw/net/vmxnet3.c
@@ -1322,14 +1322,11 @@ static void vmxnet3_update_features(VMXNET3State *s)
s->lro_supported, rxcso_supported,
s->rx_vlan_stripping);
if (s->peer_has_vhdr) {
- qemu_set_offload(qemu_get_queue(s->nic)->peer,
- rxcso_supported,
- s->lro_supported,
- s->lro_supported,
- 0,
- 0,
- 0,
- 0);
+ NetOffloads ol = { .csum = rxcso_supported,
+ .tso4 = s->lro_supported,
+ .tso6 = s->lro_supported };
+
+ qemu_set_offload(qemu_get_queue(s->nic)->peer, &ol);
}
}
diff --git a/include/net/net.h b/include/net/net.h
index 84ee18e0f9..48ba333d02 100644
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -35,6 +35,16 @@ typedef struct NICConf {
int32_t bootindex;
} NICConf;
+typedef struct NetOffloads {
+ bool csum;
+ bool tso4;
+ bool tso6;
+ bool ecn;
+ bool ufo;
+ bool uso4;
+ bool uso6;
+} NetOffloads;
+
#define DEFINE_NIC_PROPERTIES(_state, _conf) \
DEFINE_PROP_MACADDR("mac", _state, _conf.macaddr), \
DEFINE_PROP_NETDEV("netdev", _state, _conf.peers)
@@ -57,7 +67,7 @@ typedef bool (HasUfo)(NetClientState *);
typedef bool (HasUso)(NetClientState *);
typedef bool (HasVnetHdr)(NetClientState *);
typedef bool (HasVnetHdrLen)(NetClientState *, int);
-typedef void (SetOffload)(NetClientState *, int, int, int, int, int, int, int);
+typedef void (SetOffload)(NetClientState *, const NetOffloads *);
typedef int (GetVnetHdrLen)(NetClientState *);
typedef void (SetVnetHdrLen)(NetClientState *, int);
typedef bool (GetVnetHashSupportedTypes)(NetClientState *, uint32_t *);
@@ -189,8 +199,7 @@ bool qemu_has_ufo(NetClientState *nc);
bool qemu_has_uso(NetClientState *nc);
bool qemu_has_vnet_hdr(NetClientState *nc);
bool qemu_has_vnet_hdr_len(NetClientState *nc, int len);
-void qemu_set_offload(NetClientState *nc, int csum, int tso4, int tso6,
- int ecn, int ufo, int uso4, int uso6);
+void qemu_set_offload(NetClientState *nc, const NetOffloads *ol);
int qemu_get_vnet_hdr_len(NetClientState *nc);
void qemu_set_vnet_hdr_len(NetClientState *nc, int len);
bool qemu_get_vnet_hash_supported_types(NetClientState *nc, uint32_t *types);
diff --git a/net/net.c b/net/net.c
index da275db86e..63872b6855 100644
--- a/net/net.c
+++ b/net/net.c
@@ -540,14 +540,13 @@ bool qemu_has_vnet_hdr_len(NetClientState *nc, int len)
return nc->info->has_vnet_hdr_len(nc, len);
}
-void qemu_set_offload(NetClientState *nc, int csum, int tso4, int tso6,
- int ecn, int ufo, int uso4, int uso6)
+void qemu_set_offload(NetClientState *nc, const NetOffloads *ol)
{
if (!nc || !nc->info->set_offload) {
return;
}
- nc->info->set_offload(nc, csum, tso4, tso6, ecn, ufo, uso4, uso6);
+ nc->info->set_offload(nc, ol);
}
int qemu_get_vnet_hdr_len(NetClientState *nc)
diff --git a/net/netmap.c b/net/netmap.c
index 297510e190..6cd8f2bdc5 100644
--- a/net/netmap.c
+++ b/net/netmap.c
@@ -366,8 +366,7 @@ static void netmap_set_vnet_hdr_len(NetClientState *nc, int len)
}
}
-static void netmap_set_offload(NetClientState *nc, int csum, int tso4, int tso6,
- int ecn, int ufo, int uso4, int uso6)
+static void netmap_set_offload(NetClientState *nc, const NetOffloads *ol)
{
NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index b4c84441ba..86b6edee94 100644
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -231,8 +231,7 @@ int tap_fd_set_vnet_be(int fd, int is_be)
return -EINVAL;
}
-void tap_fd_set_offload(int fd, int csum, int tso4,
- int tso6, int ecn, int ufo, int uso4, int uso6)
+void tap_fd_set_offload(int fd, const NetOffloads *ol)
{
}
diff --git a/net/tap-linux.c b/net/tap-linux.c
index 22ec2f45d2..a1c58f74f5 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -239,8 +239,7 @@ int tap_fd_set_vnet_be(int fd, int is_be)
abort();
}
-void tap_fd_set_offload(int fd, int csum, int tso4,
- int tso6, int ecn, int ufo, int uso4, int uso6)
+void tap_fd_set_offload(int fd, const NetOffloads *ol)
{
unsigned int offload = 0;
@@ -249,20 +248,24 @@ void tap_fd_set_offload(int fd, int csum, int tso4,
return;
}
- if (csum) {
+ if (ol->csum) {
offload |= TUN_F_CSUM;
- if (tso4)
+ if (ol->tso4) {
offload |= TUN_F_TSO4;
- if (tso6)
+ }
+ if (ol->tso6) {
offload |= TUN_F_TSO6;
- if ((tso4 || tso6) && ecn)
+ }
+ if ((ol->tso4 || ol->tso6) && ol->ecn) {
offload |= TUN_F_TSO_ECN;
- if (ufo)
+ }
+ if (ol->ufo) {
offload |= TUN_F_UFO;
- if (uso4) {
+ }
+ if (ol->uso4) {
offload |= TUN_F_USO4;
}
- if (uso6) {
+ if (ol->uso6) {
offload |= TUN_F_USO6;
}
}
diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index 51b7830bef..833c066bee 100644
--- a/net/tap-solaris.c
+++ b/net/tap-solaris.c
@@ -27,6 +27,7 @@
#include "tap_int.h"
#include "qemu/ctype.h"
#include "qemu/cutils.h"
+#include "net/net.h"
#include <sys/ethernet.h>
#include <sys/sockio.h>
@@ -235,8 +236,7 @@ int tap_fd_set_vnet_be(int fd, int is_be)
return -EINVAL;
}
-void tap_fd_set_offload(int fd, int csum, int tso4,
- int tso6, int ecn, int ufo, int uso4, int uso6)
+void tap_fd_set_offload(int fd, const NetOffloads *ol)
{
}
diff --git a/net/tap-stub.c b/net/tap-stub.c
index 38673434cb..67d14ad4d5 100644
--- a/net/tap-stub.c
+++ b/net/tap-stub.c
@@ -66,8 +66,7 @@ int tap_fd_set_vnet_be(int fd, int is_be)
return -EINVAL;
}
-void tap_fd_set_offload(int fd, int csum, int tso4,
- int tso6, int ecn, int ufo, int uso4, int uso6)
+void tap_fd_set_offload(int fd, const NetOffloads *ol)
{
}
diff --git a/net/tap.c b/net/tap.c
index f7df702f97..72046a43aa 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -285,15 +285,14 @@ static int tap_set_vnet_be(NetClientState *nc, bool is_be)
return tap_fd_set_vnet_be(s->fd, is_be);
}
-static void tap_set_offload(NetClientState *nc, int csum, int tso4,
- int tso6, int ecn, int ufo, int uso4, int uso6)
+static void tap_set_offload(NetClientState *nc, const NetOffloads *ol)
{
TAPState *s = DO_UPCAST(TAPState, nc, nc);
if (s->fd < 0) {
return;
}
- tap_fd_set_offload(s->fd, csum, tso4, tso6, ecn, ufo, uso4, uso6);
+ tap_fd_set_offload(s->fd, ol);
}
static void tap_exit_notify(Notifier *notifier, void *data)
@@ -391,6 +390,7 @@ static TAPState *net_tap_fd_init(NetClientState *peer,
int fd,
int vnet_hdr)
{
+ NetOffloads ol = {};
NetClientState *nc;
TAPState *s;
@@ -404,7 +404,7 @@ static TAPState *net_tap_fd_init(NetClientState *peer,
s->has_ufo = tap_probe_has_ufo(s->fd);
s->has_uso = tap_probe_has_uso(s->fd);
s->enabled = true;
- tap_set_offload(&s->nc, 0, 0, 0, 0, 0, 0, 0);
+ tap_set_offload(&s->nc, &ol);
/*
* Make sure host header length is set correctly in tap:
* it might have been modified by another instance of qemu.
diff --git a/net/tap_int.h b/net/tap_int.h
index 8857ff299d..f8bbe1cb0c 100644
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -27,6 +27,7 @@
#define NET_TAP_INT_H
#include "qapi/qapi-types-net.h"
+#include "net/net.h"
int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
int vnet_hdr_required, int mq_required, Error **errp);
@@ -37,8 +38,7 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp);
int tap_probe_vnet_hdr(int fd, Error **errp);
int tap_probe_has_ufo(int fd);
int tap_probe_has_uso(int fd);
-void tap_fd_set_offload(int fd, int csum, int tso4, int tso6, int ecn, int ufo,
- int uso4, int uso6);
+void tap_fd_set_offload(int fd, const NetOffloads *ol);
void tap_fd_set_vnet_hdr_len(int fd, int len);
int tap_fd_set_vnet_le(int fd, int vnet_is_le);
int tap_fd_set_vnet_be(int fd, int vnet_is_be);
--
2.47.3

209
kvm-net-implement-UDP-tunnel-features-offloading.patch Normal file
View File

@ -0,0 +1,209 @@
From 97f8e0bbaddf37dcf147f6405a8a96921469d60d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 22 Sep 2025 16:18:28 +0200
Subject: [PATCH 19/19] net: implement UDP tunnel features offloading
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 456: backport support for GSO over UDP tunnel offload
RH-Jira: RHEL-143785
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Commit: [14/14] 5ff3488d210020730a71b944519a9938f1628dcc (lvivier/qemu-kvm-centos)
JIRA: https://issues.redhat.com/browse/RHEL-143785
When any host or guest GSO over UDP tunnel offload is enabled the
virtio net header includes the additional tunnel-related fields,
update the size accordingly.
Push the GSO over UDP tunnel offloads all the way down to the tap
device extending the newly introduced NetFeatures struct, and
eventually enable the associated features.
As per virtio specification, to convert features bit to offload bit,
map the extended features into the reserved range.
Finally, make the vhost backend aware of the exact header layout, to
copy it correctly. The tunnel-related field are present if either
the guest or the host negotiated any UDP tunnel related feature:
add them to the kernel supported features list, to allow qemu
transfer to the backend the needed information.
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <093b4bc68368046bffbcab2202227632d6e4e83b.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit a5289563ad74a2a37e8d2101d82935454c71fef4)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/net/virtio-net.c | 34 ++++++++++++++++++++++++++--------
include/net/net.h | 2 ++
net/net.c | 3 ++-
net/tap-linux.c | 6 ++++++
net/tap.c | 2 ++
5 files changed, 38 insertions(+), 9 deletions(-)
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 0abb8c8a62..f021663f92 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -103,6 +103,12 @@
#define VIRTIO_NET_F2O_SHIFT (VIRTIO_NET_OFFLOAD_MAP_MIN - \
VIRTIO_NET_FEATURES_MAP_MIN + 64)
+static bool virtio_has_tunnel_hdr(const uint64_t *features)
+{
+ return virtio_has_feature_ex(features, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO) ||
+ virtio_has_feature_ex(features, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO);
+}
+
static const VirtIOFeature feature_sizes[] = {
{.flags = 1ULL << VIRTIO_NET_F_MAC,
.end = endof(struct virtio_net_config, mac)},
@@ -659,7 +665,8 @@ static bool peer_has_tunnel(VirtIONet *n)
}
static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
- int version_1, int hash_report)
+ int version_1, int hash_report,
+ int tunnel)
{
int i;
NetClientState *nc;
@@ -667,9 +674,11 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
n->mergeable_rx_bufs = mergeable_rx_bufs;
if (version_1) {
- n->guest_hdr_len = hash_report ?
- sizeof(struct virtio_net_hdr_v1_hash) :
- sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ n->guest_hdr_len = tunnel ?
+ sizeof(struct virtio_net_hdr_v1_hash_tunnel) :
+ (hash_report ?
+ sizeof(struct virtio_net_hdr_v1_hash) :
+ sizeof(struct virtio_net_hdr_mrg_rxbuf));
n->rss_data.populate_hash = !!hash_report;
} else {
n->guest_hdr_len = n->mergeable_rx_bufs ?
@@ -803,6 +812,10 @@ static void virtio_net_apply_guest_offloads(VirtIONet *n)
.ufo = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)),
.uso4 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO4)),
.uso6 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO6)),
+ .tnl = !!(n->curr_guest_offloads &
+ (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED)),
+ .tnl_csum = !!(n->curr_guest_offloads &
+ (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED)),
};
qemu_set_offload(qemu_get_queue(n->nic)->peer, &ol);
@@ -824,7 +837,9 @@ virtio_net_guest_offloads_by_features(const uint64_t *features)
(1ULL << VIRTIO_NET_F_GUEST_ECN) |
(1ULL << VIRTIO_NET_F_GUEST_UFO) |
(1ULL << VIRTIO_NET_F_GUEST_USO4) |
- (1ULL << VIRTIO_NET_F_GUEST_USO6);
+ (1ULL << VIRTIO_NET_F_GUEST_USO6) |
+ (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED) |
+ (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED);
return guest_offloads_mask & virtio_net_features_to_offload(features);
}
@@ -937,7 +952,8 @@ static void virtio_net_set_features(VirtIODevice *vdev,
virtio_has_feature_ex(features,
VIRTIO_F_VERSION_1),
virtio_has_feature_ex(features,
- VIRTIO_NET_F_HASH_REPORT));
+ VIRTIO_NET_F_HASH_REPORT),
+ virtio_has_tunnel_hdr(features));
n->rsc4_enabled = virtio_has_feature_ex(features, VIRTIO_NET_F_RSC_EXT) &&
virtio_has_feature_ex(features, VIRTIO_NET_F_GUEST_TSO4);
@@ -3163,13 +3179,15 @@ static int virtio_net_post_load_device(void *opaque, int version_id)
VirtIONet *n = opaque;
VirtIODevice *vdev = VIRTIO_DEVICE(n);
int i, link_down;
+ bool has_tunnel_hdr = virtio_has_tunnel_hdr(vdev->guest_features_ex);
trace_virtio_net_post_load_device();
virtio_net_set_mrg_rx_bufs(n, n->mergeable_rx_bufs,
virtio_vdev_has_feature(vdev,
VIRTIO_F_VERSION_1),
virtio_vdev_has_feature(vdev,
- VIRTIO_NET_F_HASH_REPORT));
+ VIRTIO_NET_F_HASH_REPORT),
+ has_tunnel_hdr);
/* MAC_TABLE_ENTRIES may be different from the saved image */
if (n->mac_table.in_use > MAC_TABLE_ENTRIES) {
@@ -3989,7 +4007,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
n->vqs[0].tx_waiting = 0;
n->tx_burst = n->net_conf.txburst;
- virtio_net_set_mrg_rx_bufs(n, 0, 0, 0);
+ virtio_net_set_mrg_rx_bufs(n, 0, 0, 0, 0);
n->promisc = 1; /* for compatibility */
n->mac_table.macs = g_malloc0(MAC_TABLE_ENTRIES * ETH_ALEN);
diff --git a/include/net/net.h b/include/net/net.h
index 9a9084690d..72b476ee1d 100644
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -43,6 +43,8 @@ typedef struct NetOffloads {
bool ufo;
bool uso4;
bool uso6;
+ bool tnl;
+ bool tnl_csum;
} NetOffloads;
#define DEFINE_NIC_PROPERTIES(_state, _conf) \
diff --git a/net/net.c b/net/net.c
index 9536184a0c..27e0d27807 100644
--- a/net/net.c
+++ b/net/net.c
@@ -575,7 +575,8 @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len)
assert(len == sizeof(struct virtio_net_hdr_mrg_rxbuf) ||
len == sizeof(struct virtio_net_hdr) ||
- len == sizeof(struct virtio_net_hdr_v1_hash));
+ len == sizeof(struct virtio_net_hdr_v1_hash) ||
+ len == sizeof(struct virtio_net_hdr_v1_hash_tunnel));
nc->vnet_hdr_len = len;
nc->info->set_vnet_hdr_len(nc, len);
diff --git a/net/tap-linux.c b/net/tap-linux.c
index e2628be798..8e275d2ea4 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -279,6 +279,12 @@ void tap_fd_set_offload(int fd, const NetOffloads *ol)
if (ol->uso6) {
offload |= TUN_F_USO6;
}
+ if (ol->tnl) {
+ offload |= TUN_F_UDP_TUNNEL_GSO;
+ }
+ if (ol->tnl_csum) {
+ offload |= TUN_F_UDP_TUNNEL_GSO_CSUM;
+ }
}
if (ioctl(fd, TUNSETOFFLOAD, offload) != 0) {
diff --git a/net/tap.c b/net/tap.c
index 9f65e3fb3d..dc2a2859ec 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -62,6 +62,8 @@ static const int kernel_feature_bits[] = {
VIRTIO_F_NOTIFICATION_DATA,
VIRTIO_NET_F_RSC_EXT,
VIRTIO_NET_F_HASH_REPORT,
+ VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO,
+ VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO,
VHOST_INVALID_FEATURE_BIT
};
--
2.47.3

317
kvm-net-implement-tunnel-probing.patch Normal file
View File

@ -0,0 +1,317 @@
From 0cad25c7acac95a4af0d46f4d0207de4ac973370 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 22 Sep 2025 16:18:27 +0200
Subject: [PATCH 18/19] net: implement tunnel probing
RH-Author: Laurent Vivier <lvivier@redhat.com>
RH-MergeRequest: 456: backport support for GSO over UDP tunnel offload
RH-Jira: RHEL-143785
RH-Acked-by: Cindy Lu <lulu@redhat.com>
RH-Acked-by: MST <mst@redhat.com>
RH-Commit: [13/14] 3cd000a61b90ffc176f950686fb9d36d93bbee3f (lvivier/qemu-kvm-centos)
JIRA: https://issues.redhat.com/browse/RHEL-143785
Tap devices support GSO over UDP tunnel offload. Probe for such
feature in a similar manner to other offloads.
GSO over UDP tunnel needs to be enabled in addition to a "plain"
offload (TSO or USO).
No need to check separately for the outer header checksum offload:
the kernel is going to support both of them or none.
The new features are disabled by default to avoid compat issues,
and could be enabled, after that hw_compat_10_1 will be added,
together with the related compat entries.
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a987a8a7613cbf33bb2209c7c7f5889b512638a7.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit fffac046282c99801b62fa7fa1032cdc261bca6d)
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
hw/net/virtio-net.c | 41 +++++++++++++++++++++++++++++++++++++++++
include/net/net.h | 3 +++
net/net.c | 9 +++++++++
net/tap-bsd.c | 5 +++++
net/tap-linux.c | 11 +++++++++++
net/tap-linux.h | 9 +++++++++
net/tap-solaris.c | 5 +++++
net/tap-stub.c | 5 +++++
net/tap.c | 11 +++++++++++
net/tap_int.h | 1 +
10 files changed, 100 insertions(+)
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 89cf008401..0abb8c8a62 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -649,6 +649,15 @@ static int peer_has_uso(VirtIONet *n)
return qemu_has_uso(qemu_get_queue(n->nic)->peer);
}
+static bool peer_has_tunnel(VirtIONet *n)
+{
+ if (!peer_has_vnet_hdr(n)) {
+ return false;
+ }
+
+ return qemu_has_tunnel(qemu_get_queue(n->nic)->peer);
+}
+
static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
int version_1, int hash_report)
{
@@ -3073,6 +3082,13 @@ static void virtio_net_get_features(VirtIODevice *vdev, uint64_t *features,
virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO4);
virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO6);
+ virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO);
+ virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO);
+ virtio_clear_feature_ex(features,
+ VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM);
+ virtio_clear_feature_ex(features,
+ VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM);
+
virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT);
}
@@ -3086,6 +3102,15 @@ static void virtio_net_get_features(VirtIODevice *vdev, uint64_t *features,
virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO6);
}
+ if (!peer_has_tunnel(n)) {
+ virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO);
+ virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO);
+ virtio_clear_feature_ex(features,
+ VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM);
+ virtio_clear_feature_ex(features,
+ VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM);
+ }
+
if (!get_vhost_net(nc->peer)) {
if (!use_own_hash) {
virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT);
@@ -4248,6 +4273,22 @@ static const Property virtio_net_properties[] = {
rss_data.specified_hash_types,
VIRTIO_NET_HASH_REPORT_UDPv6_EX - 1,
ON_OFF_AUTO_AUTO),
+ VIRTIO_DEFINE_PROP_FEATURE("host_tunnel", VirtIONet,
+ host_features_ex,
+ VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO,
+ false),
+ VIRTIO_DEFINE_PROP_FEATURE("host_tunnel_csum", VirtIONet,
+ host_features_ex,
+ VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM,
+ false),
+ VIRTIO_DEFINE_PROP_FEATURE("guest_tunnel", VirtIONet,
+ host_features_ex,
+ VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO,
+ false),
+ VIRTIO_DEFINE_PROP_FEATURE("guest_tunnel_csum", VirtIONet,
+ host_features_ex,
+ VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM,
+ false),
};
static void virtio_net_class_init(ObjectClass *klass, const void *data)
diff --git a/include/net/net.h b/include/net/net.h
index 48ba333d02..9a9084690d 100644
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -65,6 +65,7 @@ typedef void (NetClientDestructor)(NetClientState *);
typedef RxFilterInfo *(QueryRxFilter)(NetClientState *);
typedef bool (HasUfo)(NetClientState *);
typedef bool (HasUso)(NetClientState *);
+typedef bool (HasTunnel)(NetClientState *);
typedef bool (HasVnetHdr)(NetClientState *);
typedef bool (HasVnetHdrLen)(NetClientState *, int);
typedef void (SetOffload)(NetClientState *, const NetOffloads *);
@@ -95,6 +96,7 @@ typedef struct NetClientInfo {
NetPoll *poll;
HasUfo *has_ufo;
HasUso *has_uso;
+ HasTunnel *has_tunnel;
HasVnetHdr *has_vnet_hdr;
HasVnetHdrLen *has_vnet_hdr_len;
SetOffload *set_offload;
@@ -197,6 +199,7 @@ void qemu_set_info_str(NetClientState *nc,
void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]);
bool qemu_has_ufo(NetClientState *nc);
bool qemu_has_uso(NetClientState *nc);
+bool qemu_has_tunnel(NetClientState *nc);
bool qemu_has_vnet_hdr(NetClientState *nc);
bool qemu_has_vnet_hdr_len(NetClientState *nc, int len);
void qemu_set_offload(NetClientState *nc, const NetOffloads *ol);
diff --git a/net/net.c b/net/net.c
index 63872b6855..9536184a0c 100644
--- a/net/net.c
+++ b/net/net.c
@@ -522,6 +522,15 @@ bool qemu_has_uso(NetClientState *nc)
return nc->info->has_uso(nc);
}
+bool qemu_has_tunnel(NetClientState *nc)
+{
+ if (!nc || !nc->info->has_tunnel) {
+ return false;
+ }
+
+ return nc->info->has_tunnel(nc);
+}
+
bool qemu_has_vnet_hdr(NetClientState *nc)
{
if (!nc || !nc->info->has_vnet_hdr) {
diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index 86b6edee94..751d4c819c 100644
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -217,6 +217,11 @@ int tap_probe_has_uso(int fd)
return 0;
}
+bool tap_probe_has_tunnel(int fd)
+{
+ return false;
+}
+
void tap_fd_set_vnet_hdr_len(int fd, int len)
{
}
diff --git a/net/tap-linux.c b/net/tap-linux.c
index a1c58f74f5..e2628be798 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -196,6 +196,17 @@ int tap_probe_has_uso(int fd)
return 1;
}
+bool tap_probe_has_tunnel(int fd)
+{
+ unsigned offload;
+
+ offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_UDP_TUNNEL_GSO;
+ if (ioctl(fd, TUNSETOFFLOAD, offload) < 0) {
+ return false;
+ }
+ return true;
+}
+
void tap_fd_set_vnet_hdr_len(int fd, int len)
{
if (ioctl(fd, TUNSETVNETHDRSZ, &len) == -1) {
diff --git a/net/tap-linux.h b/net/tap-linux.h
index 9a58cecb7f..8cd6b5874b 100644
--- a/net/tap-linux.h
+++ b/net/tap-linux.h
@@ -53,4 +53,13 @@
#define TUN_F_USO4 0x20 /* I can handle USO for IPv4 packets */
#define TUN_F_USO6 0x40 /* I can handle USO for IPv6 packets */
+/* I can handle TSO/USO for UDP tunneled packets */
+#define TUN_F_UDP_TUNNEL_GSO 0x080
+
+/*
+ * I can handle TSO/USO for UDP tunneled packets requiring csum offload for
+ * the outer header
+ */
+#define TUN_F_UDP_TUNNEL_GSO_CSUM 0x100
+
#endif /* QEMU_TAP_LINUX_H */
diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index 833c066bee..ac1ae25761 100644
--- a/net/tap-solaris.c
+++ b/net/tap-solaris.c
@@ -222,6 +222,11 @@ int tap_probe_has_uso(int fd)
return 0;
}
+bool tap_probe_has_tunnel(int fd)
+{
+ return false;
+}
+
void tap_fd_set_vnet_hdr_len(int fd, int len)
{
}
diff --git a/net/tap-stub.c b/net/tap-stub.c
index 67d14ad4d5..f7a5e0c163 100644
--- a/net/tap-stub.c
+++ b/net/tap-stub.c
@@ -52,6 +52,11 @@ int tap_probe_has_uso(int fd)
return 0;
}
+bool tap_probe_has_tunnel(int fd)
+{
+ return false;
+}
+
void tap_fd_set_vnet_hdr_len(int fd, int len)
{
}
diff --git a/net/tap.c b/net/tap.c
index 72046a43aa..9f65e3fb3d 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -76,6 +76,7 @@ typedef struct TAPState {
bool using_vnet_hdr;
bool has_ufo;
bool has_uso;
+ bool has_tunnel;
bool enabled;
VHostNetState *vhost_net;
unsigned host_vnet_hdr_len;
@@ -246,6 +247,14 @@ static bool tap_has_uso(NetClientState *nc)
return s->has_uso;
}
+static bool tap_has_tunnel(NetClientState *nc)
+{
+ TAPState *s = DO_UPCAST(TAPState, nc, nc);
+
+ assert(nc->info->type == NET_CLIENT_DRIVER_TAP);
+ return s->has_tunnel;
+}
+
static bool tap_has_vnet_hdr(NetClientState *nc)
{
TAPState *s = DO_UPCAST(TAPState, nc, nc);
@@ -374,6 +383,7 @@ static NetClientInfo net_tap_info = {
.cleanup = tap_cleanup,
.has_ufo = tap_has_ufo,
.has_uso = tap_has_uso,
+ .has_tunnel = tap_has_tunnel,
.has_vnet_hdr = tap_has_vnet_hdr,
.has_vnet_hdr_len = tap_has_vnet_hdr_len,
.set_offload = tap_set_offload,
@@ -403,6 +413,7 @@ static TAPState *net_tap_fd_init(NetClientState *peer,
s->using_vnet_hdr = false;
s->has_ufo = tap_probe_has_ufo(s->fd);
s->has_uso = tap_probe_has_uso(s->fd);
+ s->has_tunnel = tap_probe_has_tunnel(s->fd);
s->enabled = true;
tap_set_offload(&s->nc, &ol);
/*
diff --git a/net/tap_int.h b/net/tap_int.h
index f8bbe1cb0c..b76a05044b 100644
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -38,6 +38,7 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp);
int tap_probe_vnet_hdr(int fd, Error **errp);
int tap_probe_has_ufo(int fd);
int tap_probe_has_uso(int fd);
+bool tap_probe_has_tunnel(int fd);
void tap_fd_set_offload(int fd, const NetOffloads *ol);
void tap_fd_set_vnet_hdr_len(int fd, int len);
int tap_fd_set_vnet_le(int fd, int vnet_is_le);
--
2.47.3

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