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

* Fri Nov 14 2025 Miroslav Rezanina <mrezanin@redhat.com> - 10.1.0-5

Browse Source 
- kvm-io-move-websock-resource-release-to-close-method.patch [RHEL-120116]
- kvm-io-fix-use-after-free-in-websocket-handshake-code.patch [RHEL-120116]
- kvm-vfio-Disable-VFIO-migration-with-MultiFD-support.patch [RHEL-126573]
- kvm-hw-arm-virt-Use-ACPI-PCI-hotplug-by-default-from-10..patch [RHEL-67323]
- kvm-hw-arm-smmu-common-Check-SMMU-has-PCIe-Root-Complex-.patch [RHEL-73800]
- kvm-hw-arm-virt-acpi-build-Re-arrange-SMMUv3-IORT-build.patch [RHEL-73800]
- kvm-hw-arm-virt-acpi-build-Update-IORT-for-multiple-smmu.patch [RHEL-73800]
- kvm-hw-arm-virt-Factor-out-common-SMMUV3-dt-bindings-cod.patch [RHEL-73800]
- kvm-hw-arm-virt-Add-an-SMMU_IO_LEN-macro.patch [RHEL-73800]
- kvm-hw-pci-Introduce-pci_setup_iommu_per_bus-for-per-bus.patch [RHEL-73800]
- kvm-hw-arm-virt-Allow-user-creatable-SMMUv3-dev-instanti.patch [RHEL-73800]
- kvm-qemu-options.hx-Document-the-arm-smmuv3-device.patch [RHEL-73800]
- kvm-bios-tables-test-Allow-for-smmuv3-test-data.patch [RHEL-73800]
- kvm-qtest-bios-tables-test-Add-tests-for-legacy-smmuv3-a.patch [RHEL-73800]
- kvm-qtest-bios-tables-test-Update-tables-for-smmuv3-test.patch [RHEL-73800]
- kvm-qtest-Do-not-run-bios-tables-test-on-aarch64.patch []
- Resolves: RHEL-120116
  (CVE-2025-11234 qemu-kvm: VNC WebSocket handshake use-after-free [rhel-10.2])
- Resolves: RHEL-126573
  (VFIO migration using multifd should be disabled by default)
- Resolves: RHEL-67323
  ([aarch64] Support ACPI based PCI hotplug on ARM)
- Resolves: RHEL-73800
  (NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1)
This commit is contained in:
Miroslav Rezanina 2025-11-14 07:49:21 +01:00
parent 9a3e1e2331
commit 321b8a8d36
17 changed files with 2159 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

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

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

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

53
kvm-qemu-options.hx-Document-the-arm-smmuv3-device.patch Normal file
View File

@ -0,0 +1,53 @@
From bf0ecadea242c05671bf057fc45d8c58862032d3 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:30 +0100
Subject: [PATCH 12/16] qemu-options.hx: Document the arm-smmuv3 device
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: [8/11] 775310b784fd7631a58e8bab1e8fcc36973fceca (eauger1/centos-qemu-kvm)
Now that arm,virt can have user-creatable smmuv3 devices, document it.
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: 20250829082543.7680-9-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 73d3d0187bc6b482d8b15116edce1475c7975b89)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
qemu-options.hx | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/qemu-options.hx b/qemu-options.hx
index 3837456a61..5f146c1860 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -1231,6 +1231,13 @@ SRST
``aw-bits=val`` (val between 32 and 64, default depends on machine)
This decides the address width of the IOVA address space.
+``-device arm-smmuv3,primary-bus=id``
+ This is only supported by ``-machine virt`` (ARM).
+
+ ``primary-bus=id``
+ Accepts either the default root complex (pcie.0) or a
+ pxb-pcie based root complex.
+
ERST
DEF("name", HAS_ARG, QEMU_OPTION_name,
--
2.47.3

30
kvm-qtest-Do-not-run-bios-tables-test-on-aarch64.patch Normal file
View File

@ -0,0 +1,30 @@
From 3b21c60b771087e7d566bf738e04e01a7a1bdf09 Mon Sep 17 00:00:00 2001
From: Miroslav Rezanina <mrezanin@redhat.com>
Date: Fri, 14 Nov 2025 06:46:07 +0100
Subject: [PATCH 16/16] qtest: Do not run bios-tables-test on aarch64
We do several disruptive downstream only changes that make
bios-tables-test to fail. Disabling it for now.
This is done to enable fixing RHEL-126573 and RHEL-67323.
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
---
tests/qtest/meson.build | 1 -
1 file changed, 1 deletion(-)
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index ef44ffaf78..13b52ea41a 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -252,7 +252,6 @@ qtests_arm = \
# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional
qtests_aarch64 = \
- (cpu != 'arm' and unpack_edk2_blobs ? ['bios-tables-test'] : []) + \
(config_all_accel.has_key('CONFIG_TCG') and config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? \
['tpm-tis-device-test', 'tpm-tis-device-swtpm-test'] : []) + \
(config_all_devices.has_key('CONFIG_XLNX_ZYNQMP_ARM') ? ['xlnx-can-test', 'fuzz-xlnx-dp-test'] : []) + \
--
2.47.3

160
kvm-qtest-bios-tables-test-Add-tests-for-legacy-smmuv3-a.patch Normal file
View File

@ -0,0 +1,160 @@
From 51ec91309c99a5d81b53c2762d18c073f672e45a Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:32 +0100
Subject: [PATCH 14/16] qtest/bios-tables-test: Add tests for legacy smmuv3 and
smmuv3 device
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: [10/11] 101ed34313636fdc11f7fbdedbe2f91671b84c4b (eauger1/centos-qemu-kvm)
For the legacy SMMUv3 test, the setup includes three PCIe Root Complexes,
one of which has bypass_iommu enabled. The generated IORT table contains
a single SMMUv3 node, a Root Complex(RC) node and 1 ITS node.
RC node features 4 ID mappings, of which 2 points to SMMU node and the
remaining ones points to ITS.
pcie.0 -> {SMMU0} -> {ITS}
{RC} pcie.1 -> {SMMU0} -> {ITS}
pcie.2 -> {ITS}
[all other ids] -> {ITS}
For the -device arm-smmuv3,... test, the configuration also includes three
Root Complexes, with two connected to separate SMMUv3 devices.
The resulting IORT table contains 1 RC node, 2 SMMU nodes and 1 ITS node.
RC node features 4 ID mappings. 2 of them target the 2 SMMU nodes while
the others targets the ITS.
pcie.0 -> {SMMU0} -> {ITS}
{RC} pcie.1 -> {SMMU1} -> {ITS}
pcie.2 -> {ITS}
[all other ids] -> {ITS}
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: 20250829082543.7680-11-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 3f8cd046c151c471d9a34181320f4a7d3f72b32a)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
tests/qtest/bios-tables-test.c | 86 ++++++++++++++++++++++++++++++++++
1 file changed, 86 insertions(+)
diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c
index 386196edc8..a384aac1be 100644
--- a/tests/qtest/bios-tables-test.c
+++ b/tests/qtest/bios-tables-test.c
@@ -2343,6 +2343,86 @@ static void test_acpi_aarch64_virt_viot(void)
free_test_data(&data);
}
+static void test_acpi_aarch64_virt_smmuv3_legacy(void)
+{
+ test_data data = {
+ .machine = "virt",
+ .arch = "aarch64",
+ .tcg_only = true,
+ .uefi_fl1 = "pc-bios/edk2-aarch64-code.fd",
+ .uefi_fl2 = "pc-bios/edk2-arm-vars.fd",
+ .ram_start = 0x40000000ULL,
+ .scan_len = 128ULL * MiB,
+ };
+
+ /*
+ * cdrom is plugged into scsi controller to avoid conflict
+ * with pxb-pcie. See comments in test_acpi_aarch64_virt_tcg_pxb() for
+ * details.
+ *
+ * The setup includes three PCIe root complexes, one of which has
+ * bypass_iommu enabled. The generated IORT table contains a single
+ * SMMUv3 node and a Root Complex node with three ID mappings. Two
+ * of the ID mappings have output references pointing to the SMMUv3
+ * node and the remaining one points to ITS.
+ */
+ data.variant = ".smmuv3-legacy";
+ test_acpi_one(" -device pcie-root-port,chassis=1,id=pci.1"
+ " -device virtio-scsi-pci,id=scsi0,bus=pci.1"
+ " -drive file="
+ "tests/data/uefi-boot-images/bios-tables-test.aarch64.iso.qcow2,"
+ "if=none,media=cdrom,id=drive-scsi0-0-0-1,readonly=on"
+ " -device scsi-cd,bus=scsi0.0,scsi-id=0,"
+ "drive=drive-scsi0-0-0-1,id=scsi0-0-0-1,bootindex=1"
+ " -cpu cortex-a57"
+ " -M iommu=smmuv3"
+ " -device pxb-pcie,id=pcie.1,bus=pcie.0,bus_nr=0x10"
+ " -device pxb-pcie,id=pcie.2,bus=pcie.0,bus_nr=0x20,bypass_iommu=on",
+ &data);
+ free_test_data(&data);
+}
+
+static void test_acpi_aarch64_virt_smmuv3_dev(void)
+{
+ test_data data = {
+ .machine = "virt",
+ .arch = "aarch64",
+ .tcg_only = true,
+ .uefi_fl1 = "pc-bios/edk2-aarch64-code.fd",
+ .uefi_fl2 = "pc-bios/edk2-arm-vars.fd",
+ .ram_start = 0x40000000ULL,
+ .scan_len = 128ULL * MiB,
+ };
+
+ /*
+ * cdrom is plugged into scsi controller to avoid conflict
+ * with pxb-pcie. See comments in test_acpi_aarch64_virt_tcg_pxb()
+ * for details.
+ *
+ * The setup includes three PCie root complexes, two of which are
+ * connected to separate SMMUv3 devices. The resulting IORT table
+ * contains two SMMUv3 nodes and a Root Complex node with ID mappings
+ * of which two of the ID mappings have output references pointing
+ * to two different SMMUv3 nodes and the remaining ones pointing to
+ * ITS.
+ */
+ data.variant = ".smmuv3-dev";
+ test_acpi_one(" -device pcie-root-port,chassis=1,id=pci.1"
+ " -device virtio-scsi-pci,id=scsi0,bus=pci.1"
+ " -drive file="
+ "tests/data/uefi-boot-images/bios-tables-test.aarch64.iso.qcow2,"
+ "if=none,media=cdrom,id=drive-scsi0-0-0-1,readonly=on"
+ " -device scsi-cd,bus=scsi0.0,scsi-id=0,"
+ "drive=drive-scsi0-0-0-1,id=scsi0-0-0-1,bootindex=1"
+ " -cpu cortex-a57"
+ " -device arm-smmuv3,primary-bus=pcie.0,id=smmuv3.0"
+ " -device pxb-pcie,id=pcie.1,bus=pcie.0,bus_nr=0x10"
+ " -device arm-smmuv3,primary-bus=pcie.1,id=smmuv3.1"
+ " -device pxb-pcie,id=pcie.2,bus=pcie.0,bus_nr=0x20",
+ &data);
+ free_test_data(&data);
+}
+
#ifndef _WIN32
# define DEV_NULL "/dev/null"
#else
@@ -2776,6 +2856,12 @@ int main(int argc, char *argv[])
if (qtest_has_device("virtio-iommu-pci")) {
qtest_add_func("acpi/virt/viot", test_acpi_aarch64_virt_viot);
}
+ qtest_add_func("acpi/virt/smmuv3-legacy",
+ test_acpi_aarch64_virt_smmuv3_legacy);
+ if (qtest_has_device("arm-smmuv3")) {
+ qtest_add_func("acpi/virt/smmuv3-dev",
+ test_acpi_aarch64_virt_smmuv3_dev);
+ }
}
#if 0 /* Disabled for Red Hat Enterprise Linux */
} else if (strcmp(arch, "riscv64") == 0) {
--
2.47.3

282
kvm-qtest-bios-tables-test-Update-tables-for-smmuv3-test.patch Normal file
View File

@ -0,0 +1,282 @@
From d6f27731c3d469f4ba68807a4c1f8ee534cc9d57 Mon Sep 17 00:00:00 2001
From: Shameer Kolothum <skolothumtho@nvidia.com>
Date: Fri, 29 Aug 2025 09:25:33 +0100
Subject: [PATCH 15/16] qtest/bios-tables-test: Update tables for smmuv3 tests
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: [11/11] 88cb1daec4e92b759f12a96daacd46fc4656eacd (eauger1/centos-qemu-kvm)
For the legacy smmuv3 test case, generated IORT has a single SMMUv3 node,
a Root Complex(RC) node and 1 ITS node.
RC node features 4 ID mappings, of which 2 points to SMMU node and the
remaining ones points to ITS.
pcie.0 -> {SMMU0} -> {ITS}
{RC} pcie.1 -> {SMMU0} -> {ITS}
pcie.2 -> {ITS}
[all other ids] -> {ITS}
...
[030h 0048 1] Type : 00
[031h 0049 2] Length : 0018
[033h 0051 1] Revision : 01
[034h 0052 4] Identifier : 00000000
[038h 0056 4] Mapping Count : 00000000
[03Ch 0060 4] Mapping Offset : 00000000
[040h 0064 4] ItsCount : 00000001
[044h 0068 4] Identifiers : 00000000
[048h 0072 1] Type : 04
[049h 0073 2] Length : 0058
[04Bh 0075 1] Revision : 04
[04Ch 0076 4] Identifier : 00000001
[050h 0080 4] Mapping Count : 00000001
[054h 0084 4] Mapping Offset : 00000044
[058h 0088 8] Base Address : 0000000009050000
[060h 0096 4] Flags (decoded below) : 00000001
COHACC Override : 1
HTTU Override : 0
Proximity Domain Valid : 0
[064h 0100 4] Reserved : 00000000
[068h 0104 8] VATOS Address : 0000000000000000
[070h 0112 4] Model : 00000000
[074h 0116 4] Event GSIV : 0000006A
[078h 0120 4] PRI GSIV : 0000006B
[07Ch 0124 4] GERR GSIV : 0000006D
[080h 0128 4] Sync GSIV : 0000006C
[084h 0132 4] Proximity Domain : 00000000
[088h 0136 4] Device ID Mapping Index : 00000000
[08Ch 0140 4] Input base : 00000000
[090h 0144 4] ID Count : 0000FFFF
[094h 0148 4] Output Base : 00000000
[098h 0152 4] Output Reference : 00000030
[09Ch 0156 4] Flags (decoded below) : 00000000
Single Mapping : 0
[0A0h 0160 1] Type : 02
[0A1h 0161 2] Length : 0074
[0A3h 0163 1] Revision : 03
[0A4h 0164 4] Identifier : 00000002
[0A8h 0168 4] Mapping Count : 00000004
[0ACh 0172 4] Mapping Offset : 00000024
[0B0h 0176 8] Memory Properties : [IORT Memory Access Properties]
[0B0h 0176 4] Cache Coherency : 00000001
[0B4h 0180 1] Hints (decoded below) : 00
Transient : 0
Write Allocate : 0
Read Allocate : 0
Override : 0
[0B5h 0181 2] Reserved : 0000
[0B7h 0183 1] Memory Flags (decoded below) : 03
Coherency : 1
Device Attribute : 1
[0B8h 0184 4] ATS Attribute : 00000000
[0BCh 0188 4] PCI Segment Number : 00000000
[0C0h 0192 1] Memory Size Limit : 40
[0C1h 0193 2] PASID Capabilities : 0000
[0C3h 0195 1] Reserved : 00
[0C4h 0196 4] Input base : 00000000
[0C8h 0200 4] ID Count : 000001FF
[0CCh 0204 4] Output Base : 00000000
[0D0h 0208 4] Output Reference : 00000048
[0D4h 0212 4] Flags (decoded below) : 00000000
Single Mapping : 0
[0D8h 0216 4] Input base : 00001000
[0DCh 0220 4] ID Count : 000000FF
[0E0h 0224 4] Output Base : 00001000
[0E4h 0228 4] Output Reference : 00000048
[0E8h 0232 4] Flags (decoded below) : 00000000
Single Mapping : 0
[0ECh 0236 4] Input base : 00000200
[0F0h 0240 4] ID Count : 00000DFF
[0F4h 0244 4] Output Base : 00000200
[0F8h 0248 4] Output Reference : 00000030
[0FCh 0252 4] Flags (decoded below) : 00000000
Single Mapping : 0
[100h 0256 4] Input base : 00001100
[104h 0260 4] ID Count : 0000EEFF
[108h 0264 4] Output Base : 00001100
[10Ch 0268 4] Output Reference : 00000030
[110h 0272 4] Flags (decoded below) : 00000000
Single Mapping : 0
For the smmuv3-dev test case, IORT has 2 SMMUV3 nodes,
1 RC node and 1 ITS node.
RC node features 4 ID mappings. 2 of them target the 2
SMMU nodes while the others targets the ITS.
pcie.0 -> {SMMU0} -> {ITS}
{RC} pcie.1 -> {SMMU1} -> {ITS}
pcie.2 -> {ITS}
[all other ids] -> {ITS}
...
[030h 0048 1] Type : 00
[031h 0049 2] Length : 0018
[033h 0051 1] Revision : 01
[034h 0052 4] Identifier : 00000000
[038h 0056 4] Mapping Count : 00000000
[03Ch 0060 4] Mapping Offset : 00000000
[040h 0064 4] ItsCount : 00000001
[044h 0068 4] Identifiers : 00000000
[048h 0072 1] Type : 04
[049h 0073 2] Length : 0058
[04Bh 0075 1] Revision : 04
[04Ch 0076 4] Identifier : 00000001
[050h 0080 4] Mapping Count : 00000001
[054h 0084 4] Mapping Offset : 00000044
[058h 0088 8] Base Address : 000000000C000000
[060h 0096 4] Flags (decoded below) : 00000001
COHACC Override : 1
HTTU Override : 0
Proximity Domain Valid : 0
[064h 0100 4] Reserved : 00000000
[068h 0104 8] VATOS Address : 0000000000000000
[070h 0112 4] Model : 00000000
[074h 0116 4] Event GSIV : 00000090
[078h 0120 4] PRI GSIV : 00000091
[07Ch 0124 4] GERR GSIV : 00000093
[080h 0128 4] Sync GSIV : 00000092
[084h 0132 4] Proximity Domain : 00000000
[088h 0136 4] Device ID Mapping Index : 00000000
[08Ch 0140 4] Input base : 00000000
[090h 0144 4] ID Count : 0000FFFF
[094h 0148 4] Output Base : 00000000
[098h 0152 4] Output Reference : 00000030
[09Ch 0156 4] Flags (decoded below) : 00000000
Single Mapping : 0
[0A0h 0160 1] Type : 04
[0A1h 0161 2] Length : 0058
[0A3h 0163 1] Revision : 04
[0A4h 0164 4] Identifier : 00000002
[0A8h 0168 4] Mapping Count : 00000001
[0ACh 0172 4] Mapping Offset : 00000044
[0B0h 0176 8] Base Address : 000000000C020000
[0B8h 0184 4] Flags (decoded below) : 00000001
COHACC Override : 1
HTTU Override : 0
Proximity Domain Valid : 0
[0BCh 0188 4] Reserved : 00000000
[0C0h 0192 8] VATOS Address : 0000000000000000
[0C8h 0200 4] Model : 00000000
[0CCh 0204 4] Event GSIV : 00000094
[0D0h 0208 4] PRI GSIV : 00000095
[0D4h 0212 4] GERR GSIV : 00000097
[0D8h 0216 4] Sync GSIV : 00000096
[0DCh 0220 4] Proximity Domain : 00000000
[0E0h 0224 4] Device ID Mapping Index : 00000000
[0E4h 0228 4] Input base : 00000000
[0E8h 0232 4] ID Count : 0000FFFF
[0ECh 0236 4] Output Base : 00000000
[0F0h 0240 4] Output Reference : 00000030
[0F4h 0244 4] Flags (decoded below) : 00000000
Single Mapping : 0
[0F8h 0248 1] Type : 02
[0F9h 0249 2] Length : 0074
[0FBh 0251 1] Revision : 03
[0FCh 0252 4] Identifier : 00000003
[100h 0256 4] Mapping Count : 00000004
[104h 0260 4] Mapping Offset : 00000024
[108h 0264 8] Memory Properties : [IORT Memory Access Properties]
[108h 0264 4] Cache Coherency : 00000001
[10Ch 0268 1] Hints (decoded below) : 00
Transient : 0
Write Allocate : 0
Read Allocate : 0
Override : 0
[10Dh 0269 2] Reserved : 0000
[10Fh 0271 1] Memory Flags (decoded below) : 03
Coherency : 1
Device Attribute : 1
[110h 0272 4] ATS Attribute : 00000000
[114h 0276 4] PCI Segment Number : 00000000
[118h 0280 1] Memory Size Limit : 40
[119h 0281 2] PASID Capabilities : 0000
[11Bh 0283 1] Reserved : 00
[11Ch 0284 4] Input base : 00000000
[120h 0288 4] ID Count : 000001FF
[124h 0292 4] Output Base : 00000000
[128h 0296 4] Output Reference : 00000048
[12Ch 0300 4] Flags (decoded below) : 00000000
Single Mapping : 0
[130h 0304 4] Input base : 00001000
[134h 0308 4] ID Count : 000000FF
[138h 0312 4] Output Base : 00001000
[13Ch 0316 4] Output Reference : 000000A0
[140h 0320 4] Flags (decoded below) : 00000000
Single Mapping : 0
[144h 0324 4] Input base : 00000200
[148h 0328 4] ID Count : 00000DFF
[14Ch 0332 4] Output Base : 00000200
[150h 0336 4] Output Reference : 00000030
[154h 0340 4] Flags (decoded below) : 00000000
Single Mapping : 0
[158h 0344 4] Input base : 00001100
[15Ch 0348 4] ID Count : 0000EEFF
[160h 0352 4] Output Base : 00001100
[164h 0356 4] Output Reference : 00000030
[168h 0360 4] Flags (decoded below) : 00000000
Single Mapping : 0
Note: DSDT changes are not described here as it is not impacted by the
way the SMMUv3 is instantiated.
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: 20250829082543.7680-12-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit d35146a6606cf6ebb4e24bb97dfc0330f074f6e3)
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev | Bin 0 -> 10230 bytes
tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy | Bin 0 -> 10230 bytes
tests/data/acpi/aarch64/virt/IORT.smmuv3-dev | Bin 0 -> 364 bytes
tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy | Bin 0 -> 276 bytes
tests/qtest/bios-tables-test-allowed-diff.h | 4 ----
5 files changed, 4 deletions(-)
diff --git a/tests/qtest/bios-tables-test-allowed-diff.h b/tests/qtest/bios-tables-test-allowed-diff.h
index 2e3e3ccdce..dfb8523c8b 100644
--- a/tests/qtest/bios-tables-test-allowed-diff.h
+++ b/tests/qtest/bios-tables-test-allowed-diff.h
@@ -1,5 +1 @@
/* 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

47
kvm-vfio-Disable-VFIO-migration-with-MultiFD-support.patch Normal file
View File

@ -0,0 +1,47 @@
From 66bd3c1e7702962060d23fdc3084f0ace26b94e6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@redhat.com>
Date: Thu, 6 Nov 2025 16:39:53 +0100
Subject: [PATCH 03/16] vfio: Disable VFIO migration with MultiFD support
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: 421: vfio: Disable VFIO migration with MultiFD support
RH-Jira: RHEL-126573
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Commit: [1/1] b3ec6731c96e5650c66ece6e3b8728a7b94353f2 (clegoate/qemu-kvm-centos)
QEMU 10.0 extends VFIO migration with MultiFD support, which can be
controlled through the 'vfio-pci' device property
'x-migration-multifd-transfer'. By default, this property is set to
'auto', meaning its activation depends on the availability of other
related features. However, it should be set to 'off' in RHEL until
more testing has been completed.
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
hw/vfio/pci.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 9486521a90..83ecffb535 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3686,10 +3686,11 @@ static const Property vfio_pci_dev_properties[] = {
igd_legacy_mode, ON_OFF_AUTO_AUTO),
DEFINE_PROP_ON_OFF_AUTO("enable-migration", VFIOPCIDevice,
vbasedev.enable_migration, ON_OFF_AUTO_AUTO),
+ /* RHEL only. Disable VFIO migration with MultiFD support */
DEFINE_PROP("x-migration-multifd-transfer", VFIOPCIDevice,
vbasedev.migration_multifd_transfer,
vfio_pci_migration_multifd_transfer_prop, OnOffAuto,
- .set_default = true, .defval.i = ON_OFF_AUTO_AUTO),
+ .set_default = true, .defval.i = ON_OFF_AUTO_OFF),
DEFINE_PROP_ON_OFF_AUTO("x-migration-load-config-after-iter", VFIOPCIDevice,
vbasedev.migration_load_config_after_iter,
ON_OFF_AUTO_AUTO),
--
2.47.3

59
qemu-kvm.spec
View File

@ -143,7 +143,7 @@ Obsoletes: %{name}-block-ssh <= %{epoch}:%{version} \
Summary: QEMU is a machine emulator and virtualizer Summary: QEMU is a machine emulator and virtualizer
Name: qemu-kvm Name: qemu-kvm
Version: 10.1.0 Version: 10.1.0
Release: 4%{?rcrel}%{?dist}%{?cc_suffix} Release: 5%{?rcrel}%{?dist}%{?cc_suffix}
# Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
# Epoch 15 used for RHEL 8 # Epoch 15 used for RHEL 8
# Epoch 17 used for RHEL 9 (due to release versioning offset in RHEL 8.5) # Epoch 17 used for RHEL 9 (due to release versioning offset in RHEL 8.5)
@ -226,6 +226,37 @@ Patch34: kvm-x86-create-new-rhel-10.2-specific-pc-q35-machine-typ.patch
Patch35: kvm-x86-create-new-rhel-9.8-specific-pc-q35-machine-type.patch Patch35: kvm-x86-create-new-rhel-9.8-specific-pc-q35-machine-type.patch
# For RHEL-101929 - enable 'usb-bot' device for proper support of USB CD-ROM drives via libvirt # For RHEL-101929 - enable 'usb-bot' device for proper support of USB CD-ROM drives via libvirt
Patch36: kvm-rh-enable-CONFIG_USB_STORAGE_BOT.patch Patch36: kvm-rh-enable-CONFIG_USB_STORAGE_BOT.patch
# For RHEL-120116 - CVE-2025-11234 qemu-kvm: VNC WebSocket handshake use-after-free [rhel-10.2]
Patch37: kvm-io-move-websock-resource-release-to-close-method.patch
# For RHEL-120116 - CVE-2025-11234 qemu-kvm: VNC WebSocket handshake use-after-free [rhel-10.2]
Patch38: kvm-io-fix-use-after-free-in-websocket-handshake-code.patch
# For RHEL-126573 - VFIO migration using multifd should be disabled by default
Patch39: kvm-vfio-Disable-VFIO-migration-with-MultiFD-support.patch
# For RHEL-67323 - [aarch64] Support ACPI based PCI hotplug on ARM
Patch40: kvm-hw-arm-virt-Use-ACPI-PCI-hotplug-by-default-from-10..patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch41: kvm-hw-arm-smmu-common-Check-SMMU-has-PCIe-Root-Complex-.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch42: kvm-hw-arm-virt-acpi-build-Re-arrange-SMMUv3-IORT-build.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch43: kvm-hw-arm-virt-acpi-build-Update-IORT-for-multiple-smmu.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch44: kvm-hw-arm-virt-Factor-out-common-SMMUV3-dt-bindings-cod.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch45: kvm-hw-arm-virt-Add-an-SMMU_IO_LEN-macro.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch46: kvm-hw-pci-Introduce-pci_setup_iommu_per_bus-for-per-bus.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch47: kvm-hw-arm-virt-Allow-user-creatable-SMMUv3-dev-instanti.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch48: kvm-qemu-options.hx-Document-the-arm-smmuv3-device.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch49: kvm-bios-tables-test-Allow-for-smmuv3-test-data.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch50: kvm-qtest-bios-tables-test-Add-tests-for-legacy-smmuv3-a.patch
# For RHEL-73800 - NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1
Patch51: kvm-qtest-bios-tables-test-Update-tables-for-smmuv3-test.patch
Patch52: kvm-qtest-Do-not-run-bios-tables-test-on-aarch64.patch
%if %{have_clang} %if %{have_clang}
BuildRequires: clang BuildRequires: clang
@ -1305,6 +1336,32 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \
%endif %endif
%changelog %changelog
* Fri Nov 14 2025 Miroslav Rezanina <mrezanin@redhat.com> - 10.1.0-5
- kvm-io-move-websock-resource-release-to-close-method.patch [RHEL-120116]
- kvm-io-fix-use-after-free-in-websocket-handshake-code.patch [RHEL-120116]
- kvm-vfio-Disable-VFIO-migration-with-MultiFD-support.patch [RHEL-126573]
- kvm-hw-arm-virt-Use-ACPI-PCI-hotplug-by-default-from-10..patch [RHEL-67323]
- kvm-hw-arm-smmu-common-Check-SMMU-has-PCIe-Root-Complex-.patch [RHEL-73800]
- kvm-hw-arm-virt-acpi-build-Re-arrange-SMMUv3-IORT-build.patch [RHEL-73800]
- kvm-hw-arm-virt-acpi-build-Update-IORT-for-multiple-smmu.patch [RHEL-73800]
- kvm-hw-arm-virt-Factor-out-common-SMMUV3-dt-bindings-cod.patch [RHEL-73800]
- kvm-hw-arm-virt-Add-an-SMMU_IO_LEN-macro.patch [RHEL-73800]
- kvm-hw-pci-Introduce-pci_setup_iommu_per_bus-for-per-bus.patch [RHEL-73800]
- kvm-hw-arm-virt-Allow-user-creatable-SMMUv3-dev-instanti.patch [RHEL-73800]
- kvm-qemu-options.hx-Document-the-arm-smmuv3-device.patch [RHEL-73800]
- kvm-bios-tables-test-Allow-for-smmuv3-test-data.patch [RHEL-73800]
- kvm-qtest-bios-tables-test-Add-tests-for-legacy-smmuv3-a.patch [RHEL-73800]
- kvm-qtest-bios-tables-test-Update-tables-for-smmuv3-test.patch [RHEL-73800]
- kvm-qtest-Do-not-run-bios-tables-test-on-aarch64.patch []
- Resolves: RHEL-120116
(CVE-2025-11234 qemu-kvm: VNC WebSocket handshake use-after-free [rhel-10.2])
- Resolves: RHEL-126573
(VFIO migration using multifd should be disabled by default)
- Resolves: RHEL-67323
([aarch64] Support ACPI based PCI hotplug on ARM)
- Resolves: RHEL-73800
(NVIDIA:Grace-Hopper:Backport support for user-creatable nested SMMUv3 - RHEL 10.1)
* Mon Nov 03 2025 Miroslav Rezanina <mrezanin@redhat.com> - 10.1.0-4 * Mon Nov 03 2025 Miroslav Rezanina <mrezanin@redhat.com> - 10.1.0-4
- kvm-qapi-machine-s390x-add-QAPI-event-SCLP_CPI_INFO_AVAI.patch [RHEL-104009 RHEL-105823 RHEL-73008] - kvm-qapi-machine-s390x-add-QAPI-event-SCLP_CPI_INFO_AVAI.patch [RHEL-104009 RHEL-105823 RHEL-73008]
- kvm-tests-functional-add-tests-for-SCLP-event-CPI.patch [RHEL-104009 RHEL-105823 RHEL-73008] - kvm-tests-functional-add-tests-for-SCLP-event-CPI.patch [RHEL-104009 RHEL-105823 RHEL-73008]