virt/kvm/api.rst

108   Capability:
135 :Capability: basic
152 :Capability: basic
205 is dependent on the CPU capability and the kernel configuration. The limit can
212 Please note that configuring the IPA size does not affect the capability
221 :Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
265 :Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
284 :Capability: basic
310 :Capability: basic
338 same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
357 :Capability: basic
386 see the description of the capability.
395 :Capability: basic
422 :Capability: basic
462 :Capability: basic
476 :Capability: basic
507 :Capability: basic
520 :Capability: basic
547 :Capability: basic
646 :Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
686 :Capability: basic
708 :Capability: basic
748 :Capability: basic
774 :Capability: basic
812 :Capability: basic
850 :Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
865 Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
872 :Capability: KVM_CAP_IRQCHIP
893 capability is present (or unless it is not using the in-kernel irqchip,
923 Note that on arm64, the KVM_CAP_IRQCHIP capability only conditions
941 :Capability: KVM_CAP_IRQCHIP
966 :Capability: KVM_CAP_IRQCHIP
991 :Capability: KVM_CAP_XEN_HVM
1041 :Capability: KVM_CAP_ADJUST_CLOCK
1091 :Capability: KVM_CAP_ADJUST_CLOCK
1126 :Capability: KVM_CAP_VCPU_EVENTS
1249 :Capability: KVM_CAP_VCPU_EVENTS
1316 :Capability: KVM_CAP_DEBUGREGS
1338 :Capability: KVM_CAP_DEBUGREGS
1353 :Capability: KVM_CAP_USER_MEMORY
1382 KVM_CAP_MULTI_ADDRESS_SPACE capability.  Slots in separate address spaces
1405 use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
1409 When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
1432 :Capability: KVM_CAP_SET_TSS_ADDR
1454 :Capability: KVM_CAP_ENABLE_CAP
1460 :Capability: KVM_CAP_ENABLE_CAP_VM
1474 To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
1483 The capability that is supposed to get enabled.
1509 :Capability: KVM_CAP_MP_STATE
1590 :Capability: KVM_CAP_MP_STATE
1615 :Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
1639 :Capability: KVM_CAP_SET_BOOT_CPU_ID
1654 :Capability: KVM_CAP_XSAVE
1674 :Capability: KVM_CAP_XSAVE and KVM_CAP_XSAVE2
1702 :Capability: KVM_CAP_XCRS
1729 :Capability: KVM_CAP_XCRS
1756 :Capability: KVM_CAP_EXT_CPUID
1848 :Capability: KVM_CAP_PPC_GET_PVINFO
1878 :Capability: KVM_CAP_IRQ_ROUTING
1931   KVM_CAP_MSI_DEVID capability advertises the requirement to provide
1932   the device ID.  If this capability is not available, userspace should
1958 feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
1995 :Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM_TSC_CONTROL
2004 If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also
2011 :Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM_TSC_CONTROL
2025 :Capability: KVM_CAP_IRQCHIP
2056 :Capability: KVM_CAP_IRQCHIP
2073 regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
2080 :Capability: KVM_CAP_IOEVENTFD
2126 :Capability: KVM_CAP_SW_TLB
2162 :Capability: KVM_CAP_SPAPR_TCE
2171 and provides a scatter/gather capability for PAPR virtual I/O.
2201 :Capability: KVM_CAP_USER_NMI
2228 :Capability: KVM_CAP_S390_UCONTROL
2250 :Capability: KVM_CAP_S390_UCONTROL
2272 :Capability: KVM_CAP_S390_UCONTROL
2290 :Capability: KVM_CAP_ONE_REG
2905 :Capability: KVM_CAP_ONE_REG
2935 :Capability: KVM_CAP_KVMCLOCK_CTRL
2959 :Capability: KVM_CAP_SIGNAL_MSI
2981   KVM_CAP_MSI_DEVID capability advertises the requirement to provide
2982   the device ID.  If this capability is not available, userspace
2990 feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
2998 :Capability: KVM_CAP_PIT2
3031 :Capability: KVM_CAP_PIT_STATE2
3059 :Capability: KVM_CAP_PIT_STATE2
3074 :Capability: KVM_CAP_PPC_GET_SMMU_INFO
3149 :Capability: KVM_CAP_IRQFD
3188 :Capability: KVM_CAP_PPC_ALLOC_HTAB
3197 virtualization.  Otherwise the capability doesn't exist and the ioctl
3225 :Capability: basic
3280 :Capability: KVM_CAP_PPC_HTAB_FD
3335 :Capability: KVM_CAP_DEVICE_CTRL
3374 :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
3411 :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
3435 :Capability: basic
3533 :Capability: basic
3562 :Capability: basic
3610 :Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
3659 :Capability: KVM_CAP_PPC_RTAS
3679 :Capability: KVM_CAP_SET_GUEST_DEBUG
3727 For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether
3730 Also when supported, KVM_CAP_SET_GUEST_DEBUG2 capability indicates the
3740 :Capability: KVM_CAP_EXT_EMUL_CPUID
3815 :Capability: KVM_CAP_S390_MEM_OP, KVM_CAP_S390_PROTECTED, KVM_CAP_S390_MEM_OP_EXTENSION
3824 The KVM_CAP_S390_MEM_OP_EXTENSION capability specifies what functionality is
3850 KVM_CAP_S390_MEM_OP capability. "buf" is the buffer supplied by the
3951 SIDA accesses are available if the KVM_CAP_S390_PROTECTED capability is available.
3960 :Capability: KVM_CAP_S390_SKEYS
3992 :Capability: KVM_CAP_S390_SKEYS
4020 :Capability: KVM_CAP_S390_INJECT_IRQ
4080 :Capability: KVM_CAP_S390_IRQ_STATE
4115 :Capability: KVM_CAP_S390_IRQ_STATE
4153 :Capability: KVM_CAP_X86_SMM
4164 :Capability: KVM_CAP_X86_MSR_FILTER
4277 :Capability: KVM_CAP_SPAPR_TCE_64
4286 This capability uses extended struct in ioctl interface::
4310 :Capability: KVM_CAP_REINJECT_CONTROL
4337 :Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3
4371 :Capability: KVM_CAP_PPC_MMU_RADIX
4408 :Capability: KVM_CAP_SPAPR_RESIZE_HPT
4462 :Capability: KVM_CAP_SPAPR_RESIZE_HPT
4507 :Capability: KVM_CAP_MCE
4520 :Capability: KVM_CAP_MCE
4527          -EINVAL if requested MCE capability is not supported.
4539 :Capability: KVM_CAP_MCE
4573 :Capability: KVM_CAP_S390_CMMA_MIGRATION
4674 :Capability: KVM_CAP_S390_CMMA_MIGRATION
4722 :Capability: KVM_CAP_PPC_GET_CPU_CHAR
4769 :Capability: basic
4786 :Capability: basic
4810 :Capability: basic
4822 :Capability: KVM_CAP_HYPERV_EVENTFD
4857 :Capability: KVM_CAP_NESTED_STATE
4931 :Capability: KVM_CAP_NESTED_STATE
4943 :Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
4972 :Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
5007 is enabled; for more information, see the description of the capability.
5014 :Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system)
5127 :Capability: KVM_CAP_PMU_EVENT_FILTER
5174 :Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS
5243 :Capability: basic
5267 :Capability: KVM_CAP_S390_VCPU_RESETS
5279 :Capability: basic
5292 :Capability: KVM_CAP_S390_VCPU_RESETS
5306 :Capability: KVM_CAP_S390_PROTECTED
5367   :Capability: KVM_CAP_S390_PROTECTED_DUMP
5432   :Capability: KVM_CAP_S390_PROTECTED_DUMP
5477   :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE
5494   :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE
5509 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5632 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5645 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5759 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5774 :Capability: KVM_CAP_ARM_MTE
5812 :Capability: KVM_CAP_SREGS2
5845 :Capability: KVM_CAP_SREGS2
5858 :Capability: KVM_CAP_STATS_BINARY_FD
6061 :Capability: KVM_CAP_XSAVE2
6088 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND
6108 :Capability: KVM_CAP_S390_PROTECTED_DUMP
6133 :Capability: KVM_CAP_S390_ZPCI_OP
6180 :Capability: KVM_CAP_COUNTER_OFFSET
6186 This capability indicates that userspace is able to apply a single VM-wide
6220 :Capability: KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES
6246 capability returns the supported ranges, expressed as a set of flags. Each
6268 :Capability: KVM_CAP_USER_MEMORY2
6319 :Capability: KVM_CAP_MEMORY_ATTRIBUTES
6355 :Capability: KVM_CAP_GUEST_MEMFD
6398 :Capability: KVM_CAP_PRE_FAULT_MEMORY
6451 the capability to be present.
6885 KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI
7002 this capability at VM creation. Once this is done, these types of errors will
7031 Used on x86 systems. When the VM capability KVM_CAP_X86_USER_SPACE_MSR is
7142 Used on x86 systems. When the VM capability KVM_CAP_X86_NOTIFY_VMEXIT is
7206       whether this is a per-vcpu or per-vm capability.
7209       what parameters are accepted by the capability.
7224 This capability enables interception of OSI hypercalls that otherwise would
7229 When this capability is enabled, KVM_EXIT_OSI can occur.
7240 This capability enables interception of PAPR hypercalls. PAPR hypercalls are
7250 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
7308 This capability enables support for handling of channel I/O instructions.
7313 When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
7316 Note that even though this capability is enabled per-vcpu, the complete
7327 This capability enables or disables the delivery of interrupts through the
7336 When this capability is enabled, KVM_EXIT_EPR can occur.
7345 This capability connects the vcpu to an in-kernel MPIC device.
7355 This capability connects the vcpu to an in-kernel XICS device.
7364 This capability enables the in-kernel irqchip for s390. Please refer to
7374 This capability allows the use of the host Floating Point Unit by the guest. It
7388 This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
7448 This capability connects the vcpu to an in-kernel XIVE device.
7456 This capability, if KVM_CHECK_EXTENSION indicates that it is
7462 capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
7472 This capability enables a newer version of Hyper-V Synthetic interrupt
7483 This capability indicates that KVM running on top of Hyper-V hypervisor
7487 KVM, enabling this capability effectively disables all hypercall
7536       what parameters are accepted by the capability.
7550 This capability controls whether individual sPAPR hypercalls (hcalls)
7555 before this capability was implemented.  If disabled, the kernel will
7571 This capability controls which SIGP orders will be handled completely in user
7572 space. With this capability enabled, all fast orders will be handled completely
7584 in the hardware prior to interception). If this capability is not enabled, the
7604 This capability allows post-handlers for the STSI instruction. After
7640 This capability also enables in kernel routing of interrupt requests;
7688 With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
7694 This capability can be enabled dynamically even if VCPUs were already
7722 Enabling this capability on a VM provides userspace with a way to set
7727 be 0.  A successful call to enable this capability will result in
7728 vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is
7729 subsequently queried for the VM.  This capability is only supported by
7731 The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT
7740 With this capability a machine check exception in the guest address
7743 machine check handling routine. Without this capability KVM will
7761 Enabling this capability on a VM provides userspace with a way to no
7779 With this capability the KVM support for memory backing with 1m pages
7780 through hugetlbfs can be enabled for a VM. After the capability is
7786 this capability, the VM will not be able to run.
7794 With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
7796 capability does not enable write permissions of this MSR for the guest.
7809 state).  Enabling this capability on a VM depends on the CPU having
7819 With this capability enabled, CR2 will not be modified prior to the
7831 This capability also enables exception.pending in struct
7886 This capability indicates that KVM is running on a host that has
7894 If present, this capability can be enabled for a VM, meaning that KVM
7907 maximum halt-polling time for all vCPUs in the target VM. This capability can
7922 This capability allows userspace to intercept RDMSR and WRMSR instructions if
7930 this capability. With it enabled, MSR accesses that match the mask specified in
7959 Enabling this capability on a VM provides userspace with a way to select a
7964 This capability allows userspace to force VM exits on bus locks detected in the
7966 (which triggers an #AC exception that KVM intercepts). This capability is
7992 This capability can be used to check / enable 2nd DAWR feature provided
8004 This capability enables userspace to copy encryption context from the vm
8041 When this capability is enabled, an emulation failure will result in an exit
8059 This capability indicates that KVM (and the hardware) supports exposing the
8062 available to a guest running in AArch64 mode and enabling this capability will
8070 When this capability is enabled all memory in memslots must be mapped as
8086 This capability enables userspace to migrate the encryption context from the VM
8099 This capability, if enabled, will cause KVM to disable some behavior
8102 Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
8105 The argument to KVM_ENABLE_CAP for this capability is a bitmask of
8208 This capability allows userspace to specify maximum possible APIC ID
8235 This capability allows userspace to configure the notify VM exit on/off
8245 This capability is aimed to mitigate the threat that malicious VMs can
8259 This capability sets the VM's APIC bus clock frequency, used by KVM's in-kernel
8293 ioctl to enable this capability for the new guest and set the size of
8294 the rings.  Enabling the capability is only allowed before creating any
8352 NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that
8361 capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the
8362 ring structures can be backed by per-slot bitmaps. With this capability
8366 can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL
8399 This capability alters PMU virtualization in KVM.
8401 Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
8408 At this time, KVM_PMU_CAP_DISABLE is the only capability.  Setting
8409 this capability will disable PMU virtualization for that VM.  Usermode
8422 This capability disables the NX huge pages mitigation for iTLB MULTIHIT.
8424 The capability has no effect if the nx_huge_pages module parameter is not set.
8426 This capability may only be set before any vCPUs are created.
8436 This capability sets the chunk size used in Eager Page Splitting.
8460 This capability, if enabled, will cause KVM to exit to userspace
8463 Calling KVM_CHECK_EXTENSION for this capability will return a bitmask
8488           capability.
8490 This capability changes the behavior of the registers that identify a PE
8494 When this capability is enabled, KVM allows userspace to change the
8510 This capability, if KVM_CHECK_EXTENSION indicates that it is
8514 with the KVM_CAP_PPC_ENABLE_HCALL capability.
8521 This capability, if KVM_CHECK_EXTENSION indicates that it is
8531 This capability, if KVM_CHECK_EXTENSION indicates that it is
8541 This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
8547 If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
8571 This capability indicates the supported architecture type of the guest, i.e. the
8574 The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
8599 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
8622 number larger than 0 indicating the version of this capability is implemented
8642 Querying this capability returns a bitmap indicating the possible
8652 This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr.  Its
8655 capability is absent, userspace can still query this msr's value.
8662 This capability indicates if the flic device will be able to get/set the
8671 This capability indicates that the PSW is exposed via the kvm_run structure.
8678 This capability indicates that the user space memory used as guest mapping can
8687 This capability indicates that the user space memory used as guest mapping can
8696 This capability indicates that kvm will implement the interfaces to handle
8698 facility 82 should not be provided to the guest without this capability.
8705 This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
8715 This capability indicates that userspace can specify (via the
8718 If KVM advertises this capability, userspace can only specify the ISS field for
8730 This capability indicates that KVM supports paravirtualized Hyper-V IPI send
8739 This capability indicates that the KVM_S390_NORMAL_RESET and
8747 This capability indicates that the Ultravisor has been initialized and
8749 This capability governs the KVM_S390_PV_COMMAND ioctl and the
8758 This capability indicates that KVM supports steal time accounting.
8760 architecture-specific interfaces.  This capability and the architecture-
8771 This capability enables a guest to set information about its control program
8783 If this capability is available, then the CPNC and CPVC can be synchronized
8791 This capability indicates that KVM supports deflection of MSR reads and
8802 This capability indicates that KVM supports that accesses to user defined MSRs
8803 may be rejected. With this capability exposed, KVM exports new VM ioctl
8816 This capability indicates the features that Xen supports for hosting Xen
8881 This capability means the kernel is capable of handling hypercalls
8898 This capability is always enabled.
8905 This capability indicates that the KVM virtual PTP service is
8915 This capability indicates that KVM and the Ultravisor support dumping
8927 This capability indicates that KVM will provide the S390 CPU Topology
8934 to the guest without this capability.
8936 When this capability is present, KVM provides a new attribute group
8951 This capability returns a bitmap of support VM types.  The 1-setting of bit @n
8969 This capability indicates that the kernel is capable of handling
8977 This capability is enabled for hypervisors on platforms like POWER9
8985 This capability indicates that the kernel supports the mode 3 setting for the
8989 This capability allows a guest kernel to use a better-performance mode for
8997 The presence of this capability indicates that KVM_RUN will fill
9017 The presence of this capability indicates that KVM_RUN will update the