1 The Definitive KVM (Kernel-based Virtual Machine) API Documentation
2 ===================================================================
7 The kvm API is a set of ioctls that are issued to control various aspects
8 of a virtual machine. The ioctls belong to three classes
10 - System ioctls: These query and set global attributes which affect the
11 whole kvm subsystem. In addition a system ioctl is used to create
14 - VM ioctls: These query and set attributes that affect an entire virtual
15 machine, for example memory layout. In addition a VM ioctl is used to
16 create virtual cpus (vcpus).
18 Only run VM ioctls from the same process (address space) that was used
21 - vcpu ioctls: These query and set attributes that control the operation
22 of a single virtual cpu.
24 Only run vcpu ioctls from the same thread that was used to create the
31 The kvm API is centered around file descriptors. An initial
32 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
33 can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this
34 handle will create a VM file descriptor which can be used to issue VM
35 ioctls. A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
36 and return a file descriptor pointing to it. Finally, ioctls on a vcpu
37 fd can be used to control the vcpu, including the important task of
38 actually running guest code.
40 In general file descriptors can be migrated among processes by means
41 of fork() and the SCM_RIGHTS facility of unix domain socket. These
42 kinds of tricks are explicitly not supported by kvm. While they will
43 not cause harm to the host, their actual behavior is not guaranteed by
44 the API. The only supported use is one virtual machine per process,
45 and one vcpu per thread.
51 As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
52 incompatible change are allowed. However, there is an extension
53 facility that allows backward-compatible extensions to the API to be
56 The extension mechanism is not based on the Linux version number.
57 Instead, kvm defines extension identifiers and a facility to query
58 whether a particular extension identifier is available. If it is, a
59 set of ioctls is available for application use.
65 This section describes ioctls that can be used to control kvm guests.
66 For each ioctl, the following information is provided along with a
69 Capability: which KVM extension provides this ioctl. Can be 'basic',
70 which means that is will be provided by any kernel that supports
71 API version 12 (see section 4.1), or a KVM_CAP_xyz constant, which
72 means availability needs to be checked with KVM_CHECK_EXTENSION
75 Architectures: which instruction set architectures provide this ioctl.
76 x86 includes both i386 and x86_64.
78 Type: system, vm, or vcpu.
80 Parameters: what parameters are accepted by the ioctl.
82 Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
83 are not detailed, but errors with specific meanings are.
86 4.1 KVM_GET_API_VERSION
92 Returns: the constant KVM_API_VERSION (=12)
94 This identifies the API version as the stable kvm API. It is not
95 expected that this number will change. However, Linux 2.6.20 and
96 2.6.21 report earlier versions; these are not documented and not
97 supported. Applications should refuse to run if KVM_GET_API_VERSION
98 returns a value other than 12. If this check passes, all ioctls
99 described as 'basic' will be available.
107 Parameters: machine type identifier (KVM_VM_*)
108 Returns: a VM fd that can be used to control the new virtual machine.
110 The new VM has no virtual cpus and no memory. An mmap() of a VM fd
111 will access the virtual machine's physical address space; offset zero
112 corresponds to guest physical address zero. Use of mmap() on a VM fd
113 is discouraged if userspace memory allocation (KVM_CAP_USER_MEMORY) is
115 You most certainly want to use 0 as machine type.
117 In order to create user controlled virtual machines on S390, check
118 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
119 privileged user (CAP_SYS_ADMIN).
122 4.3 KVM_GET_MSR_INDEX_LIST
127 Parameters: struct kvm_msr_list (in/out)
128 Returns: 0 on success; -1 on error
130 E2BIG: the msr index list is to be to fit in the array specified by
133 struct kvm_msr_list {
134 __u32 nmsrs; /* number of msrs in entries */
138 This ioctl returns the guest msrs that are supported. The list varies
139 by kvm version and host processor, but does not change otherwise. The
140 user fills in the size of the indices array in nmsrs, and in return
141 kvm adjusts nmsrs to reflect the actual number of msrs and fills in
142 the indices array with their numbers.
144 Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
145 not returned in the MSR list, as different vcpus can have a different number
146 of banks, as set via the KVM_X86_SETUP_MCE ioctl.
149 4.4 KVM_CHECK_EXTENSION
154 Parameters: extension identifier (KVM_CAP_*)
155 Returns: 0 if unsupported; 1 (or some other positive integer) if supported
157 The API allows the application to query about extensions to the core
158 kvm API. Userspace passes an extension identifier (an integer) and
159 receives an integer that describes the extension availability.
160 Generally 0 means no and 1 means yes, but some extensions may report
161 additional information in the integer return value.
164 4.5 KVM_GET_VCPU_MMAP_SIZE
170 Returns: size of vcpu mmap area, in bytes
172 The KVM_RUN ioctl (cf.) communicates with userspace via a shared
173 memory region. This ioctl returns the size of that region. See the
174 KVM_RUN documentation for details.
177 4.6 KVM_SET_MEMORY_REGION
182 Parameters: struct kvm_memory_region (in)
183 Returns: 0 on success, -1 on error
185 This ioctl is obsolete and has been removed.
193 Parameters: vcpu id (apic id on x86)
194 Returns: vcpu fd on success, -1 on error
196 This API adds a vcpu to a virtual machine. The vcpu id is a small integer
197 in the range [0, max_vcpus).
199 The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
200 the KVM_CHECK_EXTENSION ioctl() at run-time.
201 The maximum possible value for max_vcpus can be retrieved using the
202 KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
204 If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
206 If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
207 same as the value returned from KVM_CAP_NR_VCPUS.
209 On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
210 threads in one or more virtual CPU cores. (This is because the
211 hardware requires all the hardware threads in a CPU core to be in the
212 same partition.) The KVM_CAP_PPC_SMT capability indicates the number
213 of vcpus per virtual core (vcore). The vcore id is obtained by
214 dividing the vcpu id by the number of vcpus per vcore. The vcpus in a
215 given vcore will always be in the same physical core as each other
216 (though that might be a different physical core from time to time).
217 Userspace can control the threading (SMT) mode of the guest by its
218 allocation of vcpu ids. For example, if userspace wants
219 single-threaded guest vcpus, it should make all vcpu ids be a multiple
220 of the number of vcpus per vcore.
222 For virtual cpus that have been created with S390 user controlled virtual
223 machines, the resulting vcpu fd can be memory mapped at page offset
224 KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
225 cpu's hardware control block.
228 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
233 Parameters: struct kvm_dirty_log (in/out)
234 Returns: 0 on success, -1 on error
236 /* for KVM_GET_DIRTY_LOG */
237 struct kvm_dirty_log {
241 void __user *dirty_bitmap; /* one bit per page */
246 Given a memory slot, return a bitmap containing any pages dirtied
247 since the last call to this ioctl. Bit 0 is the first page in the
248 memory slot. Ensure the entire structure is cleared to avoid padding
252 4.9 KVM_SET_MEMORY_ALIAS
257 Parameters: struct kvm_memory_alias (in)
258 Returns: 0 (success), -1 (error)
260 This ioctl is obsolete and has been removed.
269 Returns: 0 on success, -1 on error
271 EINTR: an unmasked signal is pending
273 This ioctl is used to run a guest virtual cpu. While there are no
274 explicit parameters, there is an implicit parameter block that can be
275 obtained by mmap()ing the vcpu fd at offset 0, with the size given by
276 KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct
277 kvm_run' (see below).
283 Architectures: all except ARM, arm64
285 Parameters: struct kvm_regs (out)
286 Returns: 0 on success, -1 on error
288 Reads the general purpose registers from the vcpu.
292 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
293 __u64 rax, rbx, rcx, rdx;
294 __u64 rsi, rdi, rsp, rbp;
295 __u64 r8, r9, r10, r11;
296 __u64 r12, r13, r14, r15;
304 Architectures: all except ARM, arm64
306 Parameters: struct kvm_regs (in)
307 Returns: 0 on success, -1 on error
309 Writes the general purpose registers into the vcpu.
311 See KVM_GET_REGS for the data structure.
317 Architectures: x86, ppc
319 Parameters: struct kvm_sregs (out)
320 Returns: 0 on success, -1 on error
322 Reads special registers from the vcpu.
326 struct kvm_segment cs, ds, es, fs, gs, ss;
327 struct kvm_segment tr, ldt;
328 struct kvm_dtable gdt, idt;
329 __u64 cr0, cr2, cr3, cr4, cr8;
332 __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
335 /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
337 interrupt_bitmap is a bitmap of pending external interrupts. At most
338 one bit may be set. This interrupt has been acknowledged by the APIC
339 but not yet injected into the cpu core.
345 Architectures: x86, ppc
347 Parameters: struct kvm_sregs (in)
348 Returns: 0 on success, -1 on error
350 Writes special registers into the vcpu. See KVM_GET_SREGS for the
359 Parameters: struct kvm_translation (in/out)
360 Returns: 0 on success, -1 on error
362 Translates a virtual address according to the vcpu's current address
365 struct kvm_translation {
367 __u64 linear_address;
370 __u64 physical_address;
381 Architectures: x86, ppc
383 Parameters: struct kvm_interrupt (in)
384 Returns: 0 on success, -1 on error
386 Queues a hardware interrupt vector to be injected. This is only
387 useful if in-kernel local APIC or equivalent is not used.
389 /* for KVM_INTERRUPT */
390 struct kvm_interrupt {
397 Note 'irq' is an interrupt vector, not an interrupt pin or line.
401 Queues an external interrupt to be injected. This ioctl is overleaded
402 with 3 different irq values:
406 This injects an edge type external interrupt into the guest once it's ready
407 to receive interrupts. When injected, the interrupt is done.
409 b) KVM_INTERRUPT_UNSET
411 This unsets any pending interrupt.
413 Only available with KVM_CAP_PPC_UNSET_IRQ.
415 c) KVM_INTERRUPT_SET_LEVEL
417 This injects a level type external interrupt into the guest context. The
418 interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
421 Only available with KVM_CAP_PPC_IRQ_LEVEL.
423 Note that any value for 'irq' other than the ones stated above is invalid
424 and incurs unexpected behavior.
435 Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead.
443 Parameters: struct kvm_msrs (in/out)
444 Returns: 0 on success, -1 on error
446 Reads model-specific registers from the vcpu. Supported msr indices can
447 be obtained using KVM_GET_MSR_INDEX_LIST.
450 __u32 nmsrs; /* number of msrs in entries */
453 struct kvm_msr_entry entries[0];
456 struct kvm_msr_entry {
462 Application code should set the 'nmsrs' member (which indicates the
463 size of the entries array) and the 'index' member of each array entry.
464 kvm will fill in the 'data' member.
472 Parameters: struct kvm_msrs (in)
473 Returns: 0 on success, -1 on error
475 Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the
478 Application code should set the 'nmsrs' member (which indicates the
479 size of the entries array), and the 'index' and 'data' members of each
488 Parameters: struct kvm_cpuid (in)
489 Returns: 0 on success, -1 on error
491 Defines the vcpu responses to the cpuid instruction. Applications
492 should use the KVM_SET_CPUID2 ioctl if available.
495 struct kvm_cpuid_entry {
504 /* for KVM_SET_CPUID */
508 struct kvm_cpuid_entry entries[0];
512 4.21 KVM_SET_SIGNAL_MASK
517 Parameters: struct kvm_signal_mask (in)
518 Returns: 0 on success, -1 on error
520 Defines which signals are blocked during execution of KVM_RUN. This
521 signal mask temporarily overrides the threads signal mask. Any
522 unblocked signal received (except SIGKILL and SIGSTOP, which retain
523 their traditional behaviour) will cause KVM_RUN to return with -EINTR.
525 Note the signal will only be delivered if not blocked by the original
528 /* for KVM_SET_SIGNAL_MASK */
529 struct kvm_signal_mask {
540 Parameters: struct kvm_fpu (out)
541 Returns: 0 on success, -1 on error
543 Reads the floating point state from the vcpu.
545 /* for KVM_GET_FPU and KVM_SET_FPU */
550 __u8 ftwx; /* in fxsave format */
566 Parameters: struct kvm_fpu (in)
567 Returns: 0 on success, -1 on error
569 Writes the floating point state to the vcpu.
571 /* for KVM_GET_FPU and KVM_SET_FPU */
576 __u8 ftwx; /* in fxsave format */
587 4.24 KVM_CREATE_IRQCHIP
589 Capability: KVM_CAP_IRQCHIP
590 Architectures: x86, ia64, ARM, arm64
593 Returns: 0 on success, -1 on error
595 Creates an interrupt controller model in the kernel. On x86, creates a virtual
596 ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
597 local APIC. IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
598 only go to the IOAPIC. On ia64, a IOSAPIC is created. On ARM/arm64, a GIC is
604 Capability: KVM_CAP_IRQCHIP
605 Architectures: x86, ia64, arm, arm64
607 Parameters: struct kvm_irq_level
608 Returns: 0 on success, -1 on error
610 Sets the level of a GSI input to the interrupt controller model in the kernel.
611 On some architectures it is required that an interrupt controller model has
612 been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
613 interrupts require the level to be set to 1 and then back to 0.
615 On real hardware, interrupt pins can be active-low or active-high. This
616 does not matter for the level field of struct kvm_irq_level: 1 always
617 means active (asserted), 0 means inactive (deasserted).
619 x86 allows the operating system to program the interrupt polarity
620 (active-low/active-high) for level-triggered interrupts, and KVM used
621 to consider the polarity. However, due to bitrot in the handling of
622 active-low interrupts, the above convention is now valid on x86 too.
623 This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED. Userspace
624 should not present interrupts to the guest as active-low unless this
625 capability is present (or unless it is not using the in-kernel irqchip,
629 ARM/arm64 can signal an interrupt either at the CPU level, or at the
630 in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
631 use PPIs designated for specific cpus. The irq field is interpreted
634 Â bits: | 31 ... 24 | 23 ... 16 | 15 ... 0 |
635 field: | irq_type | vcpu_index | irq_id |
637 The irq_type field has the following values:
638 - irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
639 - irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
640 (the vcpu_index field is ignored)
641 - irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
643 (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
645 In both cases, level is used to assert/deassert the line.
647 struct kvm_irq_level {
650 __s32 status; /* not used for KVM_IRQ_LEVEL */
652 __u32 level; /* 0 or 1 */
658 Capability: KVM_CAP_IRQCHIP
659 Architectures: x86, ia64
661 Parameters: struct kvm_irqchip (in/out)
662 Returns: 0 on success, -1 on error
664 Reads the state of a kernel interrupt controller created with
665 KVM_CREATE_IRQCHIP into a buffer provided by the caller.
668 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
671 char dummy[512]; /* reserving space */
672 struct kvm_pic_state pic;
673 struct kvm_ioapic_state ioapic;
680 Capability: KVM_CAP_IRQCHIP
681 Architectures: x86, ia64
683 Parameters: struct kvm_irqchip (in)
684 Returns: 0 on success, -1 on error
686 Sets the state of a kernel interrupt controller created with
687 KVM_CREATE_IRQCHIP from a buffer provided by the caller.
690 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
693 char dummy[512]; /* reserving space */
694 struct kvm_pic_state pic;
695 struct kvm_ioapic_state ioapic;
700 4.28 KVM_XEN_HVM_CONFIG
702 Capability: KVM_CAP_XEN_HVM
705 Parameters: struct kvm_xen_hvm_config (in)
706 Returns: 0 on success, -1 on error
708 Sets the MSR that the Xen HVM guest uses to initialize its hypercall
709 page, and provides the starting address and size of the hypercall
710 blobs in userspace. When the guest writes the MSR, kvm copies one
711 page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
714 struct kvm_xen_hvm_config {
727 Capability: KVM_CAP_ADJUST_CLOCK
730 Parameters: struct kvm_clock_data (out)
731 Returns: 0 on success, -1 on error
733 Gets the current timestamp of kvmclock as seen by the current guest. In
734 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
737 struct kvm_clock_data {
738 __u64 clock; /* kvmclock current value */
746 Capability: KVM_CAP_ADJUST_CLOCK
749 Parameters: struct kvm_clock_data (in)
750 Returns: 0 on success, -1 on error
752 Sets the current timestamp of kvmclock to the value specified in its parameter.
753 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
756 struct kvm_clock_data {
757 __u64 clock; /* kvmclock current value */
763 4.31 KVM_GET_VCPU_EVENTS
765 Capability: KVM_CAP_VCPU_EVENTS
766 Extended by: KVM_CAP_INTR_SHADOW
769 Parameters: struct kvm_vcpu_event (out)
770 Returns: 0 on success, -1 on error
772 Gets currently pending exceptions, interrupts, and NMIs as well as related
775 struct kvm_vcpu_events {
799 KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
800 interrupt.shadow contains a valid state. Otherwise, this field is undefined.
803 4.32 KVM_SET_VCPU_EVENTS
805 Capability: KVM_CAP_VCPU_EVENTS
806 Extended by: KVM_CAP_INTR_SHADOW
809 Parameters: struct kvm_vcpu_event (in)
810 Returns: 0 on success, -1 on error
812 Set pending exceptions, interrupts, and NMIs as well as related states of the
815 See KVM_GET_VCPU_EVENTS for the data structure.
817 Fields that may be modified asynchronously by running VCPUs can be excluded
818 from the update. These fields are nmi.pending and sipi_vector. Keep the
819 corresponding bits in the flags field cleared to suppress overwriting the
820 current in-kernel state. The bits are:
822 KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
823 KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
825 If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
826 the flags field to signal that interrupt.shadow contains a valid state and
827 shall be written into the VCPU.
830 4.33 KVM_GET_DEBUGREGS
832 Capability: KVM_CAP_DEBUGREGS
835 Parameters: struct kvm_debugregs (out)
836 Returns: 0 on success, -1 on error
838 Reads debug registers from the vcpu.
840 struct kvm_debugregs {
849 4.34 KVM_SET_DEBUGREGS
851 Capability: KVM_CAP_DEBUGREGS
854 Parameters: struct kvm_debugregs (in)
855 Returns: 0 on success, -1 on error
857 Writes debug registers into the vcpu.
859 See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
860 yet and must be cleared on entry.
863 4.35 KVM_SET_USER_MEMORY_REGION
865 Capability: KVM_CAP_USER_MEM
868 Parameters: struct kvm_userspace_memory_region (in)
869 Returns: 0 on success, -1 on error
871 struct kvm_userspace_memory_region {
874 __u64 guest_phys_addr;
875 __u64 memory_size; /* bytes */
876 __u64 userspace_addr; /* start of the userspace allocated memory */
879 /* for kvm_memory_region::flags */
880 #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
881 #define KVM_MEM_READONLY (1UL << 1)
883 This ioctl allows the user to create or modify a guest physical memory
884 slot. When changing an existing slot, it may be moved in the guest
885 physical memory space, or its flags may be modified. It may not be
886 resized. Slots may not overlap in guest physical address space.
888 Memory for the region is taken starting at the address denoted by the
889 field userspace_addr, which must point at user addressable memory for
890 the entire memory slot size. Any object may back this memory, including
891 anonymous memory, ordinary files, and hugetlbfs.
893 It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
894 be identical. This allows large pages in the guest to be backed by large
897 The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
898 KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of
899 writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to
900 use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
901 to make a new slot read-only. In this case, writes to this memory will be
902 posted to userspace as KVM_EXIT_MMIO exits.
904 When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
905 the memory region are automatically reflected into the guest. For example, an
906 mmap() that affects the region will be made visible immediately. Another
907 example is madvise(MADV_DROP).
909 It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
910 The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
911 allocation and is deprecated.
914 4.36 KVM_SET_TSS_ADDR
916 Capability: KVM_CAP_SET_TSS_ADDR
919 Parameters: unsigned long tss_address (in)
920 Returns: 0 on success, -1 on error
922 This ioctl defines the physical address of a three-page region in the guest
923 physical address space. The region must be within the first 4GB of the
924 guest physical address space and must not conflict with any memory slot
925 or any mmio address. The guest may malfunction if it accesses this memory
928 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
929 because of a quirk in the virtualization implementation (see the internals
930 documentation when it pops into existence).
935 Capability: KVM_CAP_ENABLE_CAP
936 Architectures: ppc, s390
938 Parameters: struct kvm_enable_cap (in)
939 Returns: 0 on success; -1 on error
941 +Not all extensions are enabled by default. Using this ioctl the application
942 can enable an extension, making it available to the guest.
944 On systems that do not support this ioctl, it always fails. On systems that
945 do support it, it only works for extensions that are supported for enablement.
947 To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
950 struct kvm_enable_cap {
954 The capability that is supposed to get enabled.
958 A bitfield indicating future enhancements. Has to be 0 for now.
962 Arguments for enabling a feature. If a feature needs initial values to
963 function properly, this is the place to put them.
969 4.38 KVM_GET_MP_STATE
971 Capability: KVM_CAP_MP_STATE
972 Architectures: x86, ia64
974 Parameters: struct kvm_mp_state (out)
975 Returns: 0 on success; -1 on error
977 struct kvm_mp_state {
981 Returns the vcpu's current "multiprocessing state" (though also valid on
982 uniprocessor guests).
986 - KVM_MP_STATE_RUNNABLE: the vcpu is currently running
987 - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP)
988 which has not yet received an INIT signal
989 - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is
991 - KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and
992 is waiting for an interrupt
993 - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector
994 accessible via KVM_GET_VCPU_EVENTS)
996 This ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel
997 irqchip, the multiprocessing state must be maintained by userspace.
1000 4.39 KVM_SET_MP_STATE
1002 Capability: KVM_CAP_MP_STATE
1003 Architectures: x86, ia64
1005 Parameters: struct kvm_mp_state (in)
1006 Returns: 0 on success; -1 on error
1008 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
1011 This ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel
1012 irqchip, the multiprocessing state must be maintained by userspace.
1015 4.40 KVM_SET_IDENTITY_MAP_ADDR
1017 Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
1020 Parameters: unsigned long identity (in)
1021 Returns: 0 on success, -1 on error
1023 This ioctl defines the physical address of a one-page region in the guest
1024 physical address space. The region must be within the first 4GB of the
1025 guest physical address space and must not conflict with any memory slot
1026 or any mmio address. The guest may malfunction if it accesses this memory
1029 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
1030 because of a quirk in the virtualization implementation (see the internals
1031 documentation when it pops into existence).
1034 4.41 KVM_SET_BOOT_CPU_ID
1036 Capability: KVM_CAP_SET_BOOT_CPU_ID
1037 Architectures: x86, ia64
1039 Parameters: unsigned long vcpu_id
1040 Returns: 0 on success, -1 on error
1042 Define which vcpu is the Bootstrap Processor (BSP). Values are the same
1043 as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default
1049 Capability: KVM_CAP_XSAVE
1052 Parameters: struct kvm_xsave (out)
1053 Returns: 0 on success, -1 on error
1059 This ioctl would copy current vcpu's xsave struct to the userspace.
1064 Capability: KVM_CAP_XSAVE
1067 Parameters: struct kvm_xsave (in)
1068 Returns: 0 on success, -1 on error
1074 This ioctl would copy userspace's xsave struct to the kernel.
1079 Capability: KVM_CAP_XCRS
1082 Parameters: struct kvm_xcrs (out)
1083 Returns: 0 on success, -1 on error
1094 struct kvm_xcr xcrs[KVM_MAX_XCRS];
1098 This ioctl would copy current vcpu's xcrs to the userspace.
1103 Capability: KVM_CAP_XCRS
1106 Parameters: struct kvm_xcrs (in)
1107 Returns: 0 on success, -1 on error
1118 struct kvm_xcr xcrs[KVM_MAX_XCRS];
1122 This ioctl would set vcpu's xcr to the value userspace specified.
1125 4.46 KVM_GET_SUPPORTED_CPUID
1127 Capability: KVM_CAP_EXT_CPUID
1130 Parameters: struct kvm_cpuid2 (in/out)
1131 Returns: 0 on success, -1 on error
1136 struct kvm_cpuid_entry2 entries[0];
1139 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
1140 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
1141 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
1143 struct kvm_cpuid_entry2 {
1154 This ioctl returns x86 cpuid features which are supported by both the hardware
1155 and kvm. Userspace can use the information returned by this ioctl to
1156 construct cpuid information (for KVM_SET_CPUID2) that is consistent with
1157 hardware, kernel, and userspace capabilities, and with user requirements (for
1158 example, the user may wish to constrain cpuid to emulate older hardware,
1159 or for feature consistency across a cluster).
1161 Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
1162 with the 'nent' field indicating the number of entries in the variable-size
1163 array 'entries'. If the number of entries is too low to describe the cpu
1164 capabilities, an error (E2BIG) is returned. If the number is too high,
1165 the 'nent' field is adjusted and an error (ENOMEM) is returned. If the
1166 number is just right, the 'nent' field is adjusted to the number of valid
1167 entries in the 'entries' array, which is then filled.
1169 The entries returned are the host cpuid as returned by the cpuid instruction,
1170 with unknown or unsupported features masked out. Some features (for example,
1171 x2apic), may not be present in the host cpu, but are exposed by kvm if it can
1172 emulate them efficiently. The fields in each entry are defined as follows:
1174 function: the eax value used to obtain the entry
1175 index: the ecx value used to obtain the entry (for entries that are
1177 flags: an OR of zero or more of the following:
1178 KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
1179 if the index field is valid
1180 KVM_CPUID_FLAG_STATEFUL_FUNC:
1181 if cpuid for this function returns different values for successive
1182 invocations; there will be several entries with the same function,
1183 all with this flag set
1184 KVM_CPUID_FLAG_STATE_READ_NEXT:
1185 for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
1186 the first entry to be read by a cpu
1187 eax, ebx, ecx, edx: the values returned by the cpuid instruction for
1188 this function/index combination
1190 The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
1191 as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
1192 support. Instead it is reported via
1194 ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
1196 if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
1197 feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
1200 4.47 KVM_PPC_GET_PVINFO
1202 Capability: KVM_CAP_PPC_GET_PVINFO
1205 Parameters: struct kvm_ppc_pvinfo (out)
1206 Returns: 0 on success, !0 on error
1208 struct kvm_ppc_pvinfo {
1214 This ioctl fetches PV specific information that need to be passed to the guest
1215 using the device tree or other means from vm context.
1217 The hcall array defines 4 instructions that make up a hypercall.
1219 If any additional field gets added to this structure later on, a bit for that
1220 additional piece of information will be set in the flags bitmap.
1222 The flags bitmap is defined as:
1224 /* the host supports the ePAPR idle hcall
1225 #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
1227 4.48 KVM_ASSIGN_PCI_DEVICE
1229 Capability: KVM_CAP_DEVICE_ASSIGNMENT
1230 Architectures: x86 ia64
1232 Parameters: struct kvm_assigned_pci_dev (in)
1233 Returns: 0 on success, -1 on error
1235 Assigns a host PCI device to the VM.
1237 struct kvm_assigned_pci_dev {
1238 __u32 assigned_dev_id;
1248 The PCI device is specified by the triple segnr, busnr, and devfn.
1249 Identification in succeeding service requests is done via assigned_dev_id. The
1250 following flags are specified:
1252 /* Depends on KVM_CAP_IOMMU */
1253 #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
1254 /* The following two depend on KVM_CAP_PCI_2_3 */
1255 #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
1256 #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
1258 If KVM_DEV_ASSIGN_PCI_2_3 is set, the kernel will manage legacy INTx interrupts
1259 via the PCI-2.3-compliant device-level mask, thus enable IRQ sharing with other
1260 assigned devices or host devices. KVM_DEV_ASSIGN_MASK_INTX specifies the
1261 guest's view on the INTx mask, see KVM_ASSIGN_SET_INTX_MASK for details.
1263 The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
1264 isolation of the device. Usages not specifying this flag are deprecated.
1266 Only PCI header type 0 devices with PCI BAR resources are supported by
1267 device assignment. The user requesting this ioctl must have read/write
1268 access to the PCI sysfs resource files associated with the device.
1271 4.49 KVM_DEASSIGN_PCI_DEVICE
1273 Capability: KVM_CAP_DEVICE_DEASSIGNMENT
1274 Architectures: x86 ia64
1276 Parameters: struct kvm_assigned_pci_dev (in)
1277 Returns: 0 on success, -1 on error
1279 Ends PCI device assignment, releasing all associated resources.
1281 See KVM_CAP_DEVICE_ASSIGNMENT for the data structure. Only assigned_dev_id is
1282 used in kvm_assigned_pci_dev to identify the device.
1285 4.50 KVM_ASSIGN_DEV_IRQ
1287 Capability: KVM_CAP_ASSIGN_DEV_IRQ
1288 Architectures: x86 ia64
1290 Parameters: struct kvm_assigned_irq (in)
1291 Returns: 0 on success, -1 on error
1293 Assigns an IRQ to a passed-through device.
1295 struct kvm_assigned_irq {
1296 __u32 assigned_dev_id;
1297 __u32 host_irq; /* ignored (legacy field) */
1305 The following flags are defined:
1307 #define KVM_DEV_IRQ_HOST_INTX (1 << 0)
1308 #define KVM_DEV_IRQ_HOST_MSI (1 << 1)
1309 #define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
1311 #define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
1312 #define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
1313 #define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
1315 It is not valid to specify multiple types per host or guest IRQ. However, the
1316 IRQ type of host and guest can differ or can even be null.
1319 4.51 KVM_DEASSIGN_DEV_IRQ
1321 Capability: KVM_CAP_ASSIGN_DEV_IRQ
1322 Architectures: x86 ia64
1324 Parameters: struct kvm_assigned_irq (in)
1325 Returns: 0 on success, -1 on error
1327 Ends an IRQ assignment to a passed-through device.
1329 See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
1330 by assigned_dev_id, flags must correspond to the IRQ type specified on
1331 KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
1334 4.52 KVM_SET_GSI_ROUTING
1336 Capability: KVM_CAP_IRQ_ROUTING
1337 Architectures: x86 ia64
1339 Parameters: struct kvm_irq_routing (in)
1340 Returns: 0 on success, -1 on error
1342 Sets the GSI routing table entries, overwriting any previously set entries.
1344 struct kvm_irq_routing {
1347 struct kvm_irq_routing_entry entries[0];
1350 No flags are specified so far, the corresponding field must be set to zero.
1352 struct kvm_irq_routing_entry {
1358 struct kvm_irq_routing_irqchip irqchip;
1359 struct kvm_irq_routing_msi msi;
1364 /* gsi routing entry types */
1365 #define KVM_IRQ_ROUTING_IRQCHIP 1
1366 #define KVM_IRQ_ROUTING_MSI 2
1368 No flags are specified so far, the corresponding field must be set to zero.
1370 struct kvm_irq_routing_irqchip {
1375 struct kvm_irq_routing_msi {
1383 4.53 KVM_ASSIGN_SET_MSIX_NR
1385 Capability: KVM_CAP_DEVICE_MSIX
1386 Architectures: x86 ia64
1388 Parameters: struct kvm_assigned_msix_nr (in)
1389 Returns: 0 on success, -1 on error
1391 Set the number of MSI-X interrupts for an assigned device. The number is
1392 reset again by terminating the MSI-X assignment of the device via
1393 KVM_DEASSIGN_DEV_IRQ. Calling this service more than once at any earlier
1396 struct kvm_assigned_msix_nr {
1397 __u32 assigned_dev_id;
1402 #define KVM_MAX_MSIX_PER_DEV 256
1405 4.54 KVM_ASSIGN_SET_MSIX_ENTRY
1407 Capability: KVM_CAP_DEVICE_MSIX
1408 Architectures: x86 ia64
1410 Parameters: struct kvm_assigned_msix_entry (in)
1411 Returns: 0 on success, -1 on error
1413 Specifies the routing of an MSI-X assigned device interrupt to a GSI. Setting
1414 the GSI vector to zero means disabling the interrupt.
1416 struct kvm_assigned_msix_entry {
1417 __u32 assigned_dev_id;
1419 __u16 entry; /* The index of entry in the MSI-X table */
1424 4.55 KVM_SET_TSC_KHZ
1426 Capability: KVM_CAP_TSC_CONTROL
1429 Parameters: virtual tsc_khz
1430 Returns: 0 on success, -1 on error
1432 Specifies the tsc frequency for the virtual machine. The unit of the
1436 4.56 KVM_GET_TSC_KHZ
1438 Capability: KVM_CAP_GET_TSC_KHZ
1442 Returns: virtual tsc-khz on success, negative value on error
1444 Returns the tsc frequency of the guest. The unit of the return value is
1445 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
1451 Capability: KVM_CAP_IRQCHIP
1454 Parameters: struct kvm_lapic_state (out)
1455 Returns: 0 on success, -1 on error
1457 #define KVM_APIC_REG_SIZE 0x400
1458 struct kvm_lapic_state {
1459 char regs[KVM_APIC_REG_SIZE];
1462 Reads the Local APIC registers and copies them into the input argument. The
1463 data format and layout are the same as documented in the architecture manual.
1468 Capability: KVM_CAP_IRQCHIP
1471 Parameters: struct kvm_lapic_state (in)
1472 Returns: 0 on success, -1 on error
1474 #define KVM_APIC_REG_SIZE 0x400
1475 struct kvm_lapic_state {
1476 char regs[KVM_APIC_REG_SIZE];
1479 Copies the input argument into the the Local APIC registers. The data format
1480 and layout are the same as documented in the architecture manual.
1485 Capability: KVM_CAP_IOEVENTFD
1488 Parameters: struct kvm_ioeventfd (in)
1489 Returns: 0 on success, !0 on error
1491 This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
1492 within the guest. A guest write in the registered address will signal the
1493 provided event instead of triggering an exit.
1495 struct kvm_ioeventfd {
1497 __u64 addr; /* legal pio/mmio address */
1498 __u32 len; /* 1, 2, 4, or 8 bytes */
1504 For the special case of virtio-ccw devices on s390, the ioevent is matched
1505 to a subchannel/virtqueue tuple instead.
1507 The following flags are defined:
1509 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
1510 #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
1511 #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
1512 #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
1513 (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
1515 If datamatch flag is set, the event will be signaled only if the written value
1516 to the registered address is equal to datamatch in struct kvm_ioeventfd.
1518 For virtio-ccw devices, addr contains the subchannel id and datamatch the
1524 Capability: KVM_CAP_SW_TLB
1527 Parameters: struct kvm_dirty_tlb (in)
1528 Returns: 0 on success, -1 on error
1530 struct kvm_dirty_tlb {
1535 This must be called whenever userspace has changed an entry in the shared
1536 TLB, prior to calling KVM_RUN on the associated vcpu.
1538 The "bitmap" field is the userspace address of an array. This array
1539 consists of a number of bits, equal to the total number of TLB entries as
1540 determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
1541 nearest multiple of 64.
1543 Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
1546 The array is little-endian: the bit 0 is the least significant bit of the
1547 first byte, bit 8 is the least significant bit of the second byte, etc.
1548 This avoids any complications with differing word sizes.
1550 The "num_dirty" field is a performance hint for KVM to determine whether it
1551 should skip processing the bitmap and just invalidate everything. It must
1552 be set to the number of set bits in the bitmap.
1555 4.61 KVM_ASSIGN_SET_INTX_MASK
1557 Capability: KVM_CAP_PCI_2_3
1560 Parameters: struct kvm_assigned_pci_dev (in)
1561 Returns: 0 on success, -1 on error
1563 Allows userspace to mask PCI INTx interrupts from the assigned device. The
1564 kernel will not deliver INTx interrupts to the guest between setting and
1565 clearing of KVM_ASSIGN_SET_INTX_MASK via this interface. This enables use of
1566 and emulation of PCI 2.3 INTx disable command register behavior.
1568 This may be used for both PCI 2.3 devices supporting INTx disable natively and
1569 older devices lacking this support. Userspace is responsible for emulating the
1570 read value of the INTx disable bit in the guest visible PCI command register.
1571 When modifying the INTx disable state, userspace should precede updating the
1572 physical device command register by calling this ioctl to inform the kernel of
1573 the new intended INTx mask state.
1575 Note that the kernel uses the device INTx disable bit to internally manage the
1576 device interrupt state for PCI 2.3 devices. Reads of this register may
1577 therefore not match the expected value. Writes should always use the guest
1578 intended INTx disable value rather than attempting to read-copy-update the
1579 current physical device state. Races between user and kernel updates to the
1580 INTx disable bit are handled lazily in the kernel. It's possible the device
1581 may generate unintended interrupts, but they will not be injected into the
1584 See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
1585 by assigned_dev_id. In the flags field, only KVM_DEV_ASSIGN_MASK_INTX is
1589 4.62 KVM_CREATE_SPAPR_TCE
1591 Capability: KVM_CAP_SPAPR_TCE
1592 Architectures: powerpc
1594 Parameters: struct kvm_create_spapr_tce (in)
1595 Returns: file descriptor for manipulating the created TCE table
1597 This creates a virtual TCE (translation control entry) table, which
1598 is an IOMMU for PAPR-style virtual I/O. It is used to translate
1599 logical addresses used in virtual I/O into guest physical addresses,
1600 and provides a scatter/gather capability for PAPR virtual I/O.
1602 /* for KVM_CAP_SPAPR_TCE */
1603 struct kvm_create_spapr_tce {
1608 The liobn field gives the logical IO bus number for which to create a
1609 TCE table. The window_size field specifies the size of the DMA window
1610 which this TCE table will translate - the table will contain one 64
1611 bit TCE entry for every 4kiB of the DMA window.
1613 When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
1614 table has been created using this ioctl(), the kernel will handle it
1615 in real mode, updating the TCE table. H_PUT_TCE calls for other
1616 liobns will cause a vm exit and must be handled by userspace.
1618 The return value is a file descriptor which can be passed to mmap(2)
1619 to map the created TCE table into userspace. This lets userspace read
1620 the entries written by kernel-handled H_PUT_TCE calls, and also lets
1621 userspace update the TCE table directly which is useful in some
1625 4.63 KVM_ALLOCATE_RMA
1627 Capability: KVM_CAP_PPC_RMA
1628 Architectures: powerpc
1630 Parameters: struct kvm_allocate_rma (out)
1631 Returns: file descriptor for mapping the allocated RMA
1633 This allocates a Real Mode Area (RMA) from the pool allocated at boot
1634 time by the kernel. An RMA is a physically-contiguous, aligned region
1635 of memory used on older POWER processors to provide the memory which
1636 will be accessed by real-mode (MMU off) accesses in a KVM guest.
1637 POWER processors support a set of sizes for the RMA that usually
1638 includes 64MB, 128MB, 256MB and some larger powers of two.
1640 /* for KVM_ALLOCATE_RMA */
1641 struct kvm_allocate_rma {
1645 The return value is a file descriptor which can be passed to mmap(2)
1646 to map the allocated RMA into userspace. The mapped area can then be
1647 passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
1648 RMA for a virtual machine. The size of the RMA in bytes (which is
1649 fixed at host kernel boot time) is returned in the rma_size field of
1650 the argument structure.
1652 The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
1653 is supported; 2 if the processor requires all virtual machines to have
1654 an RMA, or 1 if the processor can use an RMA but doesn't require it,
1655 because it supports the Virtual RMA (VRMA) facility.
1660 Capability: KVM_CAP_USER_NMI
1664 Returns: 0 on success, -1 on error
1666 Queues an NMI on the thread's vcpu. Note this is well defined only
1667 when KVM_CREATE_IRQCHIP has not been called, since this is an interface
1668 between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP
1669 has been called, this interface is completely emulated within the kernel.
1671 To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
1672 following algorithm:
1675 - read the local APIC's state (KVM_GET_LAPIC)
1676 - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
1677 - if so, issue KVM_NMI
1680 Some guests configure the LINT1 NMI input to cause a panic, aiding in
1684 4.65 KVM_S390_UCAS_MAP
1686 Capability: KVM_CAP_S390_UCONTROL
1689 Parameters: struct kvm_s390_ucas_mapping (in)
1690 Returns: 0 in case of success
1692 The parameter is defined like this:
1693 struct kvm_s390_ucas_mapping {
1699 This ioctl maps the memory at "user_addr" with the length "length" to
1700 the vcpu's address space starting at "vcpu_addr". All parameters need to
1701 be aligned by 1 megabyte.
1704 4.66 KVM_S390_UCAS_UNMAP
1706 Capability: KVM_CAP_S390_UCONTROL
1709 Parameters: struct kvm_s390_ucas_mapping (in)
1710 Returns: 0 in case of success
1712 The parameter is defined like this:
1713 struct kvm_s390_ucas_mapping {
1719 This ioctl unmaps the memory in the vcpu's address space starting at
1720 "vcpu_addr" with the length "length". The field "user_addr" is ignored.
1721 All parameters need to be aligned by 1 megabyte.
1724 4.67 KVM_S390_VCPU_FAULT
1726 Capability: KVM_CAP_S390_UCONTROL
1729 Parameters: vcpu absolute address (in)
1730 Returns: 0 in case of success
1732 This call creates a page table entry on the virtual cpu's address space
1733 (for user controlled virtual machines) or the virtual machine's address
1734 space (for regular virtual machines). This only works for minor faults,
1735 thus it's recommended to access subject memory page via the user page
1736 table upfront. This is useful to handle validity intercepts for user
1737 controlled virtual machines to fault in the virtual cpu's lowcore pages
1738 prior to calling the KVM_RUN ioctl.
1741 4.68 KVM_SET_ONE_REG
1743 Capability: KVM_CAP_ONE_REG
1746 Parameters: struct kvm_one_reg (in)
1747 Returns: 0 on success, negative value on failure
1749 struct kvm_one_reg {
1754 Using this ioctl, a single vcpu register can be set to a specific value
1755 defined by user space with the passed in struct kvm_one_reg, where id
1756 refers to the register identifier as described below and addr is a pointer
1757 to a variable with the respective size. There can be architecture agnostic
1758 and architecture specific registers. Each have their own range of operation
1759 and their own constants and width. To keep track of the implemented
1760 registers, find a list below:
1762 Arch | Register | Width (bits)
1764 PPC | KVM_REG_PPC_HIOR | 64
1765 PPC | KVM_REG_PPC_IAC1 | 64
1766 PPC | KVM_REG_PPC_IAC2 | 64
1767 PPC | KVM_REG_PPC_IAC3 | 64
1768 PPC | KVM_REG_PPC_IAC4 | 64
1769 PPC | KVM_REG_PPC_DAC1 | 64
1770 PPC | KVM_REG_PPC_DAC2 | 64
1771 PPC | KVM_REG_PPC_DABR | 64
1772 PPC | KVM_REG_PPC_DSCR | 64
1773 PPC | KVM_REG_PPC_PURR | 64
1774 PPC | KVM_REG_PPC_SPURR | 64
1775 PPC | KVM_REG_PPC_DAR | 64
1776 PPC | KVM_REG_PPC_DSISR | 32
1777 PPC | KVM_REG_PPC_AMR | 64
1778 PPC | KVM_REG_PPC_UAMOR | 64
1779 PPC | KVM_REG_PPC_MMCR0 | 64
1780 PPC | KVM_REG_PPC_MMCR1 | 64
1781 PPC | KVM_REG_PPC_MMCRA | 64
1782 PPC | KVM_REG_PPC_PMC1 | 32
1783 PPC | KVM_REG_PPC_PMC2 | 32
1784 PPC | KVM_REG_PPC_PMC3 | 32
1785 PPC | KVM_REG_PPC_PMC4 | 32
1786 PPC | KVM_REG_PPC_PMC5 | 32
1787 PPC | KVM_REG_PPC_PMC6 | 32
1788 PPC | KVM_REG_PPC_PMC7 | 32
1789 PPC | KVM_REG_PPC_PMC8 | 32
1790 PPC | KVM_REG_PPC_FPR0 | 64
1792 PPC | KVM_REG_PPC_FPR31 | 64
1793 PPC | KVM_REG_PPC_VR0 | 128
1795 PPC | KVM_REG_PPC_VR31 | 128
1796 PPC | KVM_REG_PPC_VSR0 | 128
1798 PPC | KVM_REG_PPC_VSR31 | 128
1799 PPC | KVM_REG_PPC_FPSCR | 64
1800 PPC | KVM_REG_PPC_VSCR | 32
1801 PPC | KVM_REG_PPC_VPA_ADDR | 64
1802 PPC | KVM_REG_PPC_VPA_SLB | 128
1803 PPC | KVM_REG_PPC_VPA_DTL | 128
1804 PPC | KVM_REG_PPC_EPCR | 32
1805 PPC | KVM_REG_PPC_EPR | 32
1806 PPC | KVM_REG_PPC_TCR | 32
1807 PPC | KVM_REG_PPC_TSR | 32
1808 PPC | KVM_REG_PPC_OR_TSR | 32
1809 PPC | KVM_REG_PPC_CLEAR_TSR | 32
1810 PPC | KVM_REG_PPC_MAS0 | 32
1811 PPC | KVM_REG_PPC_MAS1 | 32
1812 PPC | KVM_REG_PPC_MAS2 | 64
1813 PPC | KVM_REG_PPC_MAS7_3 | 64
1814 PPC | KVM_REG_PPC_MAS4 | 32
1815 PPC | KVM_REG_PPC_MAS6 | 32
1816 PPC | KVM_REG_PPC_MMUCFG | 32
1817 PPC | KVM_REG_PPC_TLB0CFG | 32
1818 PPC | KVM_REG_PPC_TLB1CFG | 32
1819 PPC | KVM_REG_PPC_TLB2CFG | 32
1820 PPC | KVM_REG_PPC_TLB3CFG | 32
1821 PPC | KVM_REG_PPC_TLB0PS | 32
1822 PPC | KVM_REG_PPC_TLB1PS | 32
1823 PPC | KVM_REG_PPC_TLB2PS | 32
1824 PPC | KVM_REG_PPC_TLB3PS | 32
1825 PPC | KVM_REG_PPC_EPTCFG | 32
1826 PPC | KVM_REG_PPC_ICP_STATE | 64
1827 PPC | KVM_REG_PPC_TB_OFFSET | 64
1828 PPC | KVM_REG_PPC_SPMC1 | 32
1829 PPC | KVM_REG_PPC_SPMC2 | 32
1830 PPC | KVM_REG_PPC_IAMR | 64
1831 PPC | KVM_REG_PPC_TFHAR | 64
1832 PPC | KVM_REG_PPC_TFIAR | 64
1833 PPC | KVM_REG_PPC_TEXASR | 64
1834 PPC | KVM_REG_PPC_FSCR | 64
1835 PPC | KVM_REG_PPC_PSPB | 32
1836 PPC | KVM_REG_PPC_EBBHR | 64
1837 PPC | KVM_REG_PPC_EBBRR | 64
1838 PPC | KVM_REG_PPC_BESCR | 64
1839 PPC | KVM_REG_PPC_TAR | 64
1840 PPC | KVM_REG_PPC_DPDES | 64
1841 PPC | KVM_REG_PPC_DAWR | 64
1842 PPC | KVM_REG_PPC_DAWRX | 64
1843 PPC | KVM_REG_PPC_CIABR | 64
1844 PPC | KVM_REG_PPC_IC | 64
1845 PPC | KVM_REG_PPC_VTB | 64
1846 PPC | KVM_REG_PPC_CSIGR | 64
1847 PPC | KVM_REG_PPC_TACR | 64
1848 PPC | KVM_REG_PPC_TCSCR | 64
1849 PPC | KVM_REG_PPC_PID | 64
1850 PPC | KVM_REG_PPC_ACOP | 64
1851 PPC | KVM_REG_PPC_VRSAVE | 32
1852 PPC | KVM_REG_PPC_LPCR | 64
1853 PPC | KVM_REG_PPC_PPR | 64
1854 PPC | KVM_REG_PPC_ARCH_COMPAT 32
1855 PPC | KVM_REG_PPC_DABRX | 32
1856 PPC | KVM_REG_PPC_TM_GPR0 | 64
1858 PPC | KVM_REG_PPC_TM_GPR31 | 64
1859 PPC | KVM_REG_PPC_TM_VSR0 | 128
1861 PPC | KVM_REG_PPC_TM_VSR63 | 128
1862 PPC | KVM_REG_PPC_TM_CR | 64
1863 PPC | KVM_REG_PPC_TM_LR | 64
1864 PPC | KVM_REG_PPC_TM_CTR | 64
1865 PPC | KVM_REG_PPC_TM_FPSCR | 64
1866 PPC | KVM_REG_PPC_TM_AMR | 64
1867 PPC | KVM_REG_PPC_TM_PPR | 64
1868 PPC | KVM_REG_PPC_TM_VRSAVE | 64
1869 PPC | KVM_REG_PPC_TM_VSCR | 32
1870 PPC | KVM_REG_PPC_TM_DSCR | 64
1871 PPC | KVM_REG_PPC_TM_TAR | 64
1873 ARM registers are mapped using the lower 32 bits. The upper 16 of that
1874 is the register group type, or coprocessor number:
1876 ARM core registers have the following id bit patterns:
1877 0x4020 0000 0010 <index into the kvm_regs struct:16>
1879 ARM 32-bit CP15 registers have the following id bit patterns:
1880 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
1882 ARM 64-bit CP15 registers have the following id bit patterns:
1883 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
1885 ARM CCSIDR registers are demultiplexed by CSSELR value:
1886 0x4020 0000 0011 00 <csselr:8>
1888 ARM 32-bit VFP control registers have the following id bit patterns:
1889 0x4020 0000 0012 1 <regno:12>
1891 ARM 64-bit FP registers have the following id bit patterns:
1892 0x4030 0000 0012 0 <regno:12>
1895 arm64 registers are mapped using the lower 32 bits. The upper 16 of
1896 that is the register group type, or coprocessor number:
1898 arm64 core/FP-SIMD registers have the following id bit patterns. Note
1899 that the size of the access is variable, as the kvm_regs structure
1900 contains elements ranging from 32 to 128 bits. The index is a 32bit
1901 value in the kvm_regs structure seen as a 32bit array.
1902 0x60x0 0000 0010 <index into the kvm_regs struct:16>
1904 arm64 CCSIDR registers are demultiplexed by CSSELR value:
1905 0x6020 0000 0011 00 <csselr:8>
1907 arm64 system registers have the following id bit patterns:
1908 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
1910 4.69 KVM_GET_ONE_REG
1912 Capability: KVM_CAP_ONE_REG
1915 Parameters: struct kvm_one_reg (in and out)
1916 Returns: 0 on success, negative value on failure
1918 This ioctl allows to receive the value of a single register implemented
1919 in a vcpu. The register to read is indicated by the "id" field of the
1920 kvm_one_reg struct passed in. On success, the register value can be found
1921 at the memory location pointed to by "addr".
1923 The list of registers accessible using this interface is identical to the
1927 4.70 KVM_KVMCLOCK_CTRL
1929 Capability: KVM_CAP_KVMCLOCK_CTRL
1930 Architectures: Any that implement pvclocks (currently x86 only)
1933 Returns: 0 on success, -1 on error
1935 This signals to the host kernel that the specified guest is being paused by
1936 userspace. The host will set a flag in the pvclock structure that is checked
1937 from the soft lockup watchdog. The flag is part of the pvclock structure that
1938 is shared between guest and host, specifically the second bit of the flags
1939 field of the pvclock_vcpu_time_info structure. It will be set exclusively by
1940 the host and read/cleared exclusively by the guest. The guest operation of
1941 checking and clearing the flag must an atomic operation so
1942 load-link/store-conditional, or equivalent must be used. There are two cases
1943 where the guest will clear the flag: when the soft lockup watchdog timer resets
1944 itself or when a soft lockup is detected. This ioctl can be called any time
1945 after pausing the vcpu, but before it is resumed.
1950 Capability: KVM_CAP_SIGNAL_MSI
1953 Parameters: struct kvm_msi (in)
1954 Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
1956 Directly inject a MSI message. Only valid with in-kernel irqchip that handles
1967 No flags are defined so far. The corresponding field must be 0.
1970 4.71 KVM_CREATE_PIT2
1972 Capability: KVM_CAP_PIT2
1975 Parameters: struct kvm_pit_config (in)
1976 Returns: 0 on success, -1 on error
1978 Creates an in-kernel device model for the i8254 PIT. This call is only valid
1979 after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
1980 parameters have to be passed:
1982 struct kvm_pit_config {
1989 #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */
1991 PIT timer interrupts may use a per-VM kernel thread for injection. If it
1992 exists, this thread will have a name of the following pattern:
1994 kvm-pit/<owner-process-pid>
1996 When running a guest with elevated priorities, the scheduling parameters of
1997 this thread may have to be adjusted accordingly.
1999 This IOCTL replaces the obsolete KVM_CREATE_PIT.
2004 Capability: KVM_CAP_PIT_STATE2
2007 Parameters: struct kvm_pit_state2 (out)
2008 Returns: 0 on success, -1 on error
2010 Retrieves the state of the in-kernel PIT model. Only valid after
2011 KVM_CREATE_PIT2. The state is returned in the following structure:
2013 struct kvm_pit_state2 {
2014 struct kvm_pit_channel_state channels[3];
2021 /* disable PIT in HPET legacy mode */
2022 #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
2024 This IOCTL replaces the obsolete KVM_GET_PIT.
2029 Capability: KVM_CAP_PIT_STATE2
2032 Parameters: struct kvm_pit_state2 (in)
2033 Returns: 0 on success, -1 on error
2035 Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
2036 See KVM_GET_PIT2 for details on struct kvm_pit_state2.
2038 This IOCTL replaces the obsolete KVM_SET_PIT.
2041 4.74 KVM_PPC_GET_SMMU_INFO
2043 Capability: KVM_CAP_PPC_GET_SMMU_INFO
2044 Architectures: powerpc
2047 Returns: 0 on success, -1 on error
2049 This populates and returns a structure describing the features of
2050 the "Server" class MMU emulation supported by KVM.
2051 This can in turn be used by userspace to generate the appropriate
2052 device-tree properties for the guest operating system.
2054 The structure contains some global informations, followed by an
2055 array of supported segment page sizes:
2057 struct kvm_ppc_smmu_info {
2061 struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
2064 The supported flags are:
2066 - KVM_PPC_PAGE_SIZES_REAL:
2067 When that flag is set, guest page sizes must "fit" the backing
2068 store page sizes. When not set, any page size in the list can
2069 be used regardless of how they are backed by userspace.
2071 - KVM_PPC_1T_SEGMENTS
2072 The emulated MMU supports 1T segments in addition to the
2075 The "slb_size" field indicates how many SLB entries are supported
2077 The "sps" array contains 8 entries indicating the supported base
2078 page sizes for a segment in increasing order. Each entry is defined
2081 struct kvm_ppc_one_seg_page_size {
2082 __u32 page_shift; /* Base page shift of segment (or 0) */
2083 __u32 slb_enc; /* SLB encoding for BookS */
2084 struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
2087 An entry with a "page_shift" of 0 is unused. Because the array is
2088 organized in increasing order, a lookup can stop when encoutering
2091 The "slb_enc" field provides the encoding to use in the SLB for the
2092 page size. The bits are in positions such as the value can directly
2093 be OR'ed into the "vsid" argument of the slbmte instruction.
2095 The "enc" array is a list which for each of those segment base page
2096 size provides the list of supported actual page sizes (which can be
2097 only larger or equal to the base page size), along with the
2098 corresponding encoding in the hash PTE. Similarly, the array is
2099 8 entries sorted by increasing sizes and an entry with a "0" shift
2100 is an empty entry and a terminator:
2102 struct kvm_ppc_one_page_size {
2103 __u32 page_shift; /* Page shift (or 0) */
2104 __u32 pte_enc; /* Encoding in the HPTE (>>12) */
2107 The "pte_enc" field provides a value that can OR'ed into the hash
2108 PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
2109 into the hash PTE second double word).
2113 Capability: KVM_CAP_IRQFD
2116 Parameters: struct kvm_irqfd (in)
2117 Returns: 0 on success, -1 on error
2119 Allows setting an eventfd to directly trigger a guest interrupt.
2120 kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
2121 kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When
2122 an event is triggered on the eventfd, an interrupt is injected into
2123 the guest using the specified gsi pin. The irqfd is removed using
2124 the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
2127 With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
2128 mechanism allowing emulation of level-triggered, irqfd-based
2129 interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
2130 additional eventfd in the kvm_irqfd.resamplefd field. When operating
2131 in resample mode, posting of an interrupt through kvm_irq.fd asserts
2132 the specified gsi in the irqchip. When the irqchip is resampled, such
2133 as from an EOI, the gsi is de-asserted and the user is notified via
2134 kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
2135 the interrupt if the device making use of it still requires service.
2136 Note that closing the resamplefd is not sufficient to disable the
2137 irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
2138 and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
2140 4.76 KVM_PPC_ALLOCATE_HTAB
2142 Capability: KVM_CAP_PPC_ALLOC_HTAB
2143 Architectures: powerpc
2145 Parameters: Pointer to u32 containing hash table order (in/out)
2146 Returns: 0 on success, -1 on error
2148 This requests the host kernel to allocate an MMU hash table for a
2149 guest using the PAPR paravirtualization interface. This only does
2150 anything if the kernel is configured to use the Book 3S HV style of
2151 virtualization. Otherwise the capability doesn't exist and the ioctl
2152 returns an ENOTTY error. The rest of this description assumes Book 3S
2155 There must be no vcpus running when this ioctl is called; if there
2156 are, it will do nothing and return an EBUSY error.
2158 The parameter is a pointer to a 32-bit unsigned integer variable
2159 containing the order (log base 2) of the desired size of the hash
2160 table, which must be between 18 and 46. On successful return from the
2161 ioctl, it will have been updated with the order of the hash table that
2164 If no hash table has been allocated when any vcpu is asked to run
2165 (with the KVM_RUN ioctl), the host kernel will allocate a
2166 default-sized hash table (16 MB).
2168 If this ioctl is called when a hash table has already been allocated,
2169 the kernel will clear out the existing hash table (zero all HPTEs) and
2170 return the hash table order in the parameter. (If the guest is using
2171 the virtualized real-mode area (VRMA) facility, the kernel will
2172 re-create the VMRA HPTEs on the next KVM_RUN of any vcpu.)
2174 4.77 KVM_S390_INTERRUPT
2178 Type: vm ioctl, vcpu ioctl
2179 Parameters: struct kvm_s390_interrupt (in)
2180 Returns: 0 on success, -1 on error
2182 Allows to inject an interrupt to the guest. Interrupts can be floating
2183 (vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
2185 Interrupt parameters are passed via kvm_s390_interrupt:
2187 struct kvm_s390_interrupt {
2193 type can be one of the following:
2195 KVM_S390_SIGP_STOP (vcpu) - sigp restart
2196 KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
2197 KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
2198 KVM_S390_RESTART (vcpu) - restart
2199 KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
2200 parameters in parm and parm64
2201 KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
2202 KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
2203 KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
2204 KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
2205 I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
2206 I/O interruption parameters in parm (subchannel) and parm64 (intparm,
2207 interruption subclass)
2208 KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
2209 machine check interrupt code in parm64 (note that
2210 machine checks needing further payload are not
2211 supported by this ioctl)
2213 Note that the vcpu ioctl is asynchronous to vcpu execution.
2215 4.78 KVM_PPC_GET_HTAB_FD
2217 Capability: KVM_CAP_PPC_HTAB_FD
2218 Architectures: powerpc
2220 Parameters: Pointer to struct kvm_get_htab_fd (in)
2221 Returns: file descriptor number (>= 0) on success, -1 on error
2223 This returns a file descriptor that can be used either to read out the
2224 entries in the guest's hashed page table (HPT), or to write entries to
2225 initialize the HPT. The returned fd can only be written to if the
2226 KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
2227 can only be read if that bit is clear. The argument struct looks like
2230 /* For KVM_PPC_GET_HTAB_FD */
2231 struct kvm_get_htab_fd {
2237 /* Values for kvm_get_htab_fd.flags */
2238 #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1)
2239 #define KVM_GET_HTAB_WRITE ((__u64)0x2)
2241 The `start_index' field gives the index in the HPT of the entry at
2242 which to start reading. It is ignored when writing.
2244 Reads on the fd will initially supply information about all
2245 "interesting" HPT entries. Interesting entries are those with the
2246 bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
2247 all entries. When the end of the HPT is reached, the read() will
2248 return. If read() is called again on the fd, it will start again from
2249 the beginning of the HPT, but will only return HPT entries that have
2250 changed since they were last read.
2252 Data read or written is structured as a header (8 bytes) followed by a
2253 series of valid HPT entries (16 bytes) each. The header indicates how
2254 many valid HPT entries there are and how many invalid entries follow
2255 the valid entries. The invalid entries are not represented explicitly
2256 in the stream. The header format is:
2258 struct kvm_get_htab_header {
2264 Writes to the fd create HPT entries starting at the index given in the
2265 header; first `n_valid' valid entries with contents from the data
2266 written, then `n_invalid' invalid entries, invalidating any previously
2267 valid entries found.
2269 4.79 KVM_CREATE_DEVICE
2271 Capability: KVM_CAP_DEVICE_CTRL
2273 Parameters: struct kvm_create_device (in/out)
2274 Returns: 0 on success, -1 on error
2276 ENODEV: The device type is unknown or unsupported
2277 EEXIST: Device already created, and this type of device may not
2278 be instantiated multiple times
2280 Other error conditions may be defined by individual device types or
2281 have their standard meanings.
2283 Creates an emulated device in the kernel. The file descriptor returned
2284 in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
2286 If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
2287 device type is supported (not necessarily whether it can be created
2290 Individual devices should not define flags. Attributes should be used
2291 for specifying any behavior that is not implied by the device type
2294 struct kvm_create_device {
2295 __u32 type; /* in: KVM_DEV_TYPE_xxx */
2296 __u32 fd; /* out: device handle */
2297 __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
2300 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
2302 Capability: KVM_CAP_DEVICE_CTRL
2304 Parameters: struct kvm_device_attr
2305 Returns: 0 on success, -1 on error
2307 ENXIO: The group or attribute is unknown/unsupported for this device
2308 EPERM: The attribute cannot (currently) be accessed this way
2309 (e.g. read-only attribute, or attribute that only makes
2310 sense when the device is in a different state)
2312 Other error conditions may be defined by individual device types.
2314 Gets/sets a specified piece of device configuration and/or state. The
2315 semantics are device-specific. See individual device documentation in
2316 the "devices" directory. As with ONE_REG, the size of the data
2317 transferred is defined by the particular attribute.
2319 struct kvm_device_attr {
2320 __u32 flags; /* no flags currently defined */
2321 __u32 group; /* device-defined */
2322 __u64 attr; /* group-defined */
2323 __u64 addr; /* userspace address of attr data */
2326 4.81 KVM_HAS_DEVICE_ATTR
2328 Capability: KVM_CAP_DEVICE_CTRL
2330 Parameters: struct kvm_device_attr
2331 Returns: 0 on success, -1 on error
2333 ENXIO: The group or attribute is unknown/unsupported for this device
2335 Tests whether a device supports a particular attribute. A successful
2336 return indicates the attribute is implemented. It does not necessarily
2337 indicate that the attribute can be read or written in the device's
2338 current state. "addr" is ignored.
2340 4.82 KVM_ARM_VCPU_INIT
2343 Architectures: arm, arm64
2345 Parameters: struct kvm_vcpu_init (in)
2346 Returns: 0 on success; -1 on error
2348 Â EINVAL: Â Â Â the target is unknown, or the combination of features is invalid.
2349 Â ENOENT: Â Â Â a features bit specified is unknown.
2351 This tells KVM what type of CPU to present to the guest, and what
2352 optional features it should have. Â This will cause a reset of the cpu
2353 registers to their initial values. Â If this is not called, KVM_RUN will
2354 return ENOEXEC for that vcpu.
2356 Note that because some registers reflect machine topology, all vcpus
2357 should be created before this ioctl is invoked.
2360 - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
2361 Depends on KVM_CAP_ARM_PSCI.
2362 - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
2363 Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
2366 4.83 KVM_ARM_PREFERRED_TARGET
2369 Architectures: arm, arm64
2371 Parameters: struct struct kvm_vcpu_init (out)
2372 Returns: 0 on success; -1 on error
2374 ENODEV: no preferred target available for the host
2376 This queries KVM for preferred CPU target type which can be emulated
2377 by KVM on underlying host.
2379 The ioctl returns struct kvm_vcpu_init instance containing information
2380 about preferred CPU target type and recommended features for it. The
2381 kvm_vcpu_init->features bitmap returned will have feature bits set if
2382 the preferred target recommends setting these features, but this is
2385 The information returned by this ioctl can be used to prepare an instance
2386 of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
2387 in VCPU matching underlying host.
2390 4.84 KVM_GET_REG_LIST
2393 Architectures: arm, arm64
2395 Parameters: struct kvm_reg_list (in/out)
2396 Returns: 0 on success; -1 on error
2398 Â E2BIG: Â Â Â Â the reg index list is too big to fit in the array specified by
2399 Â Â Â Â Â Â Â Â Â Â Â Â the user (the number required will be written into n).
2401 struct kvm_reg_list {
2402 __u64 n; /* number of registers in reg[] */
2406 This ioctl returns the guest registers that are supported for the
2407 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
2410 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
2412 Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
2413 Architectures: arm, arm64
2415 Parameters: struct kvm_arm_device_address (in)
2416 Returns: 0 on success, -1 on error
2418 ENODEV: The device id is unknown
2419 ENXIO: Device not supported on current system
2420 EEXIST: Address already set
2421 E2BIG: Address outside guest physical address space
2422 EBUSY: Address overlaps with other device range
2424 struct kvm_arm_device_addr {
2429 Specify a device address in the guest's physical address space where guests
2430 can access emulated or directly exposed devices, which the host kernel needs
2431 to know about. The id field is an architecture specific identifier for a
2434 ARM/arm64 divides the id field into two parts, a device id and an
2435 address type id specific to the individual device.
2437 Â bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
2438 field: | 0x00000000 | device id | addr type id |
2440 ARM/arm64 currently only require this when using the in-kernel GIC
2441 support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
2442 as the device id. When setting the base address for the guest's
2443 mapping of the VGIC virtual CPU and distributor interface, the ioctl
2444 must be called after calling KVM_CREATE_IRQCHIP, but before calling
2445 KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
2446 base addresses will return -EEXIST.
2448 Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
2449 should be used instead.
2452 4.86 KVM_PPC_RTAS_DEFINE_TOKEN
2454 Capability: KVM_CAP_PPC_RTAS
2457 Parameters: struct kvm_rtas_token_args
2458 Returns: 0 on success, -1 on error
2460 Defines a token value for a RTAS (Run Time Abstraction Services)
2461 service in order to allow it to be handled in the kernel. The
2462 argument struct gives the name of the service, which must be the name
2463 of a service that has a kernel-side implementation. If the token
2464 value is non-zero, it will be associated with that service, and
2465 subsequent RTAS calls by the guest specifying that token will be
2466 handled by the kernel. If the token value is 0, then any token
2467 associated with the service will be forgotten, and subsequent RTAS
2468 calls by the guest for that service will be passed to userspace to be
2472 5. The kvm_run structure
2473 ------------------------
2475 Application code obtains a pointer to the kvm_run structure by
2476 mmap()ing a vcpu fd. From that point, application code can control
2477 execution by changing fields in kvm_run prior to calling the KVM_RUN
2478 ioctl, and obtain information about the reason KVM_RUN returned by
2479 looking up structure members.
2483 __u8 request_interrupt_window;
2485 Request that KVM_RUN return when it becomes possible to inject external
2486 interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
2493 When KVM_RUN has returned successfully (return value 0), this informs
2494 application code why KVM_RUN has returned. Allowable values for this
2495 field are detailed below.
2497 __u8 ready_for_interrupt_injection;
2499 If request_interrupt_window has been specified, this field indicates
2500 an interrupt can be injected now with KVM_INTERRUPT.
2504 The value of the current interrupt flag. Only valid if in-kernel
2505 local APIC is not used.
2509 /* in (pre_kvm_run), out (post_kvm_run) */
2512 The value of the cr8 register. Only valid if in-kernel local APIC is
2513 not used. Both input and output.
2517 The value of the APIC BASE msr. Only valid if in-kernel local
2518 APIC is not used. Both input and output.
2521 /* KVM_EXIT_UNKNOWN */
2523 __u64 hardware_exit_reason;
2526 If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
2527 reasons. Further architecture-specific information is available in
2528 hardware_exit_reason.
2530 /* KVM_EXIT_FAIL_ENTRY */
2532 __u64 hardware_entry_failure_reason;
2535 If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
2536 to unknown reasons. Further architecture-specific information is
2537 available in hardware_entry_failure_reason.
2539 /* KVM_EXIT_EXCEPTION */
2549 #define KVM_EXIT_IO_IN 0
2550 #define KVM_EXIT_IO_OUT 1
2552 __u8 size; /* bytes */
2555 __u64 data_offset; /* relative to kvm_run start */
2558 If exit_reason is KVM_EXIT_IO, then the vcpu has
2559 executed a port I/O instruction which could not be satisfied by kvm.
2560 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
2561 where kvm expects application code to place the data for the next
2562 KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array.
2565 struct kvm_debug_exit_arch arch;
2578 If exit_reason is KVM_EXIT_MMIO, then the vcpu has
2579 executed a memory-mapped I/O instruction which could not be satisfied
2580 by kvm. The 'data' member contains the written data if 'is_write' is
2581 true, and should be filled by application code otherwise.
2583 NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR,
2584 KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding
2585 operations are complete (and guest state is consistent) only after userspace
2586 has re-entered the kernel with KVM_RUN. The kernel side will first finish
2587 incomplete operations and then check for pending signals. Userspace
2588 can re-enter the guest with an unmasked signal pending to complete
2591 /* KVM_EXIT_HYPERCALL */
2600 Unused. This was once used for 'hypercall to userspace'. To implement
2601 such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
2602 Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
2604 /* KVM_EXIT_TPR_ACCESS */
2611 To be documented (KVM_TPR_ACCESS_REPORTING).
2613 /* KVM_EXIT_S390_SIEIC */
2616 __u64 mask; /* psw upper half */
2617 __u64 addr; /* psw lower half */
2624 /* KVM_EXIT_S390_RESET */
2625 #define KVM_S390_RESET_POR 1
2626 #define KVM_S390_RESET_CLEAR 2
2627 #define KVM_S390_RESET_SUBSYSTEM 4
2628 #define KVM_S390_RESET_CPU_INIT 8
2629 #define KVM_S390_RESET_IPL 16
2630 __u64 s390_reset_flags;
2634 /* KVM_EXIT_S390_UCONTROL */
2636 __u64 trans_exc_code;
2640 s390 specific. A page fault has occurred for a user controlled virtual
2641 machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
2642 resolved by the kernel.
2643 The program code and the translation exception code that were placed
2644 in the cpu's lowcore are presented here as defined by the z Architecture
2645 Principles of Operation Book in the Chapter for Dynamic Address Translation
2662 MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
2663 hypercalls and exit with this exit struct that contains all the guest gprs.
2665 If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
2666 Userspace can now handle the hypercall and when it's done modify the gprs as
2667 necessary. Upon guest entry all guest GPRs will then be replaced by the values
2670 /* KVM_EXIT_PAPR_HCALL */
2677 This is used on 64-bit PowerPC when emulating a pSeries partition,
2678 e.g. with the 'pseries' machine type in qemu. It occurs when the
2679 guest does a hypercall using the 'sc 1' instruction. The 'nr' field
2680 contains the hypercall number (from the guest R3), and 'args' contains
2681 the arguments (from the guest R4 - R12). Userspace should put the
2682 return code in 'ret' and any extra returned values in args[].
2683 The possible hypercalls are defined in the Power Architecture Platform
2684 Requirements (PAPR) document available from www.power.org (free
2685 developer registration required to access it).
2687 /* KVM_EXIT_S390_TSCH */
2689 __u16 subchannel_id;
2690 __u16 subchannel_nr;
2697 s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
2698 and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
2699 interrupt for the target subchannel has been dequeued and subchannel_id,
2700 subchannel_nr, io_int_parm and io_int_word contain the parameters for that
2701 interrupt. ipb is needed for instruction parameter decoding.
2708 On FSL BookE PowerPC chips, the interrupt controller has a fast patch
2709 interrupt acknowledge path to the core. When the core successfully
2710 delivers an interrupt, it automatically populates the EPR register with
2711 the interrupt vector number and acknowledges the interrupt inside
2712 the interrupt controller.
2714 In case the interrupt controller lives in user space, we need to do
2715 the interrupt acknowledge cycle through it to fetch the next to be
2716 delivered interrupt vector using this exit.
2718 It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
2719 external interrupt has just been delivered into the guest. User space
2720 should put the acknowledged interrupt vector into the 'epr' field.
2722 /* Fix the size of the union. */
2727 * shared registers between kvm and userspace.
2728 * kvm_valid_regs specifies the register classes set by the host
2729 * kvm_dirty_regs specified the register classes dirtied by userspace
2730 * struct kvm_sync_regs is architecture specific, as well as the
2731 * bits for kvm_valid_regs and kvm_dirty_regs
2733 __u64 kvm_valid_regs;
2734 __u64 kvm_dirty_regs;
2736 struct kvm_sync_regs regs;
2740 If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
2741 certain guest registers without having to call SET/GET_*REGS. Thus we can
2742 avoid some system call overhead if userspace has to handle the exit.
2743 Userspace can query the validity of the structure by checking
2744 kvm_valid_regs for specific bits. These bits are architecture specific
2745 and usually define the validity of a groups of registers. (e.g. one bit
2746 for general purpose registers)
2751 4.81 KVM_GET_EMULATED_CPUID
2753 Capability: KVM_CAP_EXT_EMUL_CPUID
2756 Parameters: struct kvm_cpuid2 (in/out)
2757 Returns: 0 on success, -1 on error
2762 struct kvm_cpuid_entry2 entries[0];
2765 The member 'flags' is used for passing flags from userspace.
2767 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
2768 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
2769 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
2771 struct kvm_cpuid_entry2 {
2782 This ioctl returns x86 cpuid features which are emulated by
2783 kvm.Userspace can use the information returned by this ioctl to query
2784 which features are emulated by kvm instead of being present natively.
2786 Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
2787 structure with the 'nent' field indicating the number of entries in
2788 the variable-size array 'entries'. If the number of entries is too low
2789 to describe the cpu capabilities, an error (E2BIG) is returned. If the
2790 number is too high, the 'nent' field is adjusted and an error (ENOMEM)
2791 is returned. If the number is just right, the 'nent' field is adjusted
2792 to the number of valid entries in the 'entries' array, which is then
2795 The entries returned are the set CPUID bits of the respective features
2796 which kvm emulates, as returned by the CPUID instruction, with unknown
2797 or unsupported feature bits cleared.
2799 Features like x2apic, for example, may not be present in the host cpu
2800 but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
2801 emulated efficiently and thus not included here.
2803 The fields in each entry are defined as follows:
2805 function: the eax value used to obtain the entry
2806 index: the ecx value used to obtain the entry (for entries that are
2808 flags: an OR of zero or more of the following:
2809 KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
2810 if the index field is valid
2811 KVM_CPUID_FLAG_STATEFUL_FUNC:
2812 if cpuid for this function returns different values for successive
2813 invocations; there will be several entries with the same function,
2814 all with this flag set
2815 KVM_CPUID_FLAG_STATE_READ_NEXT:
2816 for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
2817 the first entry to be read by a cpu
2818 eax, ebx, ecx, edx: the values returned by the cpuid instruction for
2819 this function/index combination
2822 6. Capabilities that can be enabled
2823 -----------------------------------
2825 There are certain capabilities that change the behavior of the virtual CPU when
2826 enabled. To enable them, please see section 4.37. Below you can find a list of
2827 capabilities and what their effect on the vCPU is when enabling them.
2829 The following information is provided along with the description:
2831 Architectures: which instruction set architectures provide this ioctl.
2832 x86 includes both i386 and x86_64.
2834 Parameters: what parameters are accepted by the capability.
2836 Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
2837 are not detailed, but errors with specific meanings are.
2844 Returns: 0 on success; -1 on error
2846 This capability enables interception of OSI hypercalls that otherwise would
2847 be treated as normal system calls to be injected into the guest. OSI hypercalls
2848 were invented by Mac-on-Linux to have a standardized communication mechanism
2849 between the guest and the host.
2851 When this capability is enabled, KVM_EXIT_OSI can occur.
2854 6.2 KVM_CAP_PPC_PAPR
2858 Returns: 0 on success; -1 on error
2860 This capability enables interception of PAPR hypercalls. PAPR hypercalls are
2861 done using the hypercall instruction "sc 1".
2863 It also sets the guest privilege level to "supervisor" mode. Usually the guest
2864 runs in "hypervisor" privilege mode with a few missing features.
2866 In addition to the above, it changes the semantics of SDR1. In this mode, the
2867 HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
2868 HTAB invisible to the guest.
2870 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
2876 Parameters: args[0] is the address of a struct kvm_config_tlb
2877 Returns: 0 on success; -1 on error
2879 struct kvm_config_tlb {
2886 Configures the virtual CPU's TLB array, establishing a shared memory area
2887 between userspace and KVM. The "params" and "array" fields are userspace
2888 addresses of mmu-type-specific data structures. The "array_len" field is an
2889 safety mechanism, and should be set to the size in bytes of the memory that
2890 userspace has reserved for the array. It must be at least the size dictated
2891 by "mmu_type" and "params".
2893 While KVM_RUN is active, the shared region is under control of KVM. Its
2894 contents are undefined, and any modification by userspace results in
2895 boundedly undefined behavior.
2897 On return from KVM_RUN, the shared region will reflect the current state of
2898 the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB
2899 to tell KVM which entries have been changed, prior to calling KVM_RUN again
2902 For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
2903 - The "params" field is of type "struct kvm_book3e_206_tlb_params".
2904 - The "array" field points to an array of type "struct
2905 kvm_book3e_206_tlb_entry".
2906 - The array consists of all entries in the first TLB, followed by all
2907 entries in the second TLB.
2908 - Within a TLB, entries are ordered first by increasing set number. Within a
2909 set, entries are ordered by way (increasing ESEL).
2910 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
2911 where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
2912 - The tsize field of mas1 shall be set to 4K on TLB0, even though the
2913 hardware ignores this value for TLB0.
2915 6.4 KVM_CAP_S390_CSS_SUPPORT
2919 Returns: 0 on success; -1 on error
2921 This capability enables support for handling of channel I/O instructions.
2923 TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
2924 handled in-kernel, while the other I/O instructions are passed to userspace.
2926 When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
2927 SUBCHANNEL intercepts.
2932 Parameters: args[0] defines whether the proxy facility is active
2933 Returns: 0 on success; -1 on error
2935 This capability enables or disables the delivery of interrupts through the
2936 external proxy facility.
2938 When enabled (args[0] != 0), every time the guest gets an external interrupt
2939 delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
2940 to receive the topmost interrupt vector.
2942 When disabled (args[0] == 0), behavior is as if this facility is unsupported.
2944 When this capability is enabled, KVM_EXIT_EPR can occur.
2946 6.6 KVM_CAP_IRQ_MPIC
2949 Parameters: args[0] is the MPIC device fd
2950 args[1] is the MPIC CPU number for this vcpu
2952 This capability connects the vcpu to an in-kernel MPIC device.
2954 6.7 KVM_CAP_IRQ_XICS
2957 Parameters: args[0] is the XICS device fd
2958 args[1] is the XICS CPU number (server ID) for this vcpu
2960 This capability connects the vcpu to an in-kernel XICS device.