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), a KVM_CAP_xyz constant, which
72 means availability needs to be checked with KVM_CHECK_EXTENSION
73 (see section 4.4), or 'none' which means that while not all kernels
74 support this ioctl, there's no capability bit to check its
75 availability: for kernels that don't support the ioctl,
76 the ioctl returns -ENOTTY.
78 Architectures: which instruction set architectures provide this ioctl.
79 x86 includes both i386 and x86_64.
81 Type: system, vm, or vcpu.
83 Parameters: what parameters are accepted by the ioctl.
85 Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
86 are not detailed, but errors with specific meanings are.
89 4.1 KVM_GET_API_VERSION
95 Returns: the constant KVM_API_VERSION (=12)
97 This identifies the API version as the stable kvm API. It is not
98 expected that this number will change. However, Linux 2.6.20 and
99 2.6.21 report earlier versions; these are not documented and not
100 supported. Applications should refuse to run if KVM_GET_API_VERSION
101 returns a value other than 12. If this check passes, all ioctls
102 described as 'basic' will be available.
110 Parameters: machine type identifier (KVM_VM_*)
111 Returns: a VM fd that can be used to control the new virtual machine.
113 The new VM has no virtual cpus and no memory. An mmap() of a VM fd
114 will access the virtual machine's physical address space; offset zero
115 corresponds to guest physical address zero. Use of mmap() on a VM fd
116 is discouraged if userspace memory allocation (KVM_CAP_USER_MEMORY) is
118 You most certainly want to use 0 as machine type.
120 In order to create user controlled virtual machines on S390, check
121 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
122 privileged user (CAP_SYS_ADMIN).
125 4.3 KVM_GET_MSR_INDEX_LIST
130 Parameters: struct kvm_msr_list (in/out)
131 Returns: 0 on success; -1 on error
133 E2BIG: the msr index list is to be to fit in the array specified by
136 struct kvm_msr_list {
137 __u32 nmsrs; /* number of msrs in entries */
141 This ioctl returns the guest msrs that are supported. The list varies
142 by kvm version and host processor, but does not change otherwise. The
143 user fills in the size of the indices array in nmsrs, and in return
144 kvm adjusts nmsrs to reflect the actual number of msrs and fills in
145 the indices array with their numbers.
147 Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
148 not returned in the MSR list, as different vcpus can have a different number
149 of banks, as set via the KVM_X86_SETUP_MCE ioctl.
152 4.4 KVM_CHECK_EXTENSION
154 Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
156 Type: system ioctl, vm ioctl
157 Parameters: extension identifier (KVM_CAP_*)
158 Returns: 0 if unsupported; 1 (or some other positive integer) if supported
160 The API allows the application to query about extensions to the core
161 kvm API. Userspace passes an extension identifier (an integer) and
162 receives an integer that describes the extension availability.
163 Generally 0 means no and 1 means yes, but some extensions may report
164 additional information in the integer return value.
166 Based on their initialization different VMs may have different capabilities.
167 It is thus encouraged to use the vm ioctl to query for capabilities (available
168 with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
170 4.5 KVM_GET_VCPU_MMAP_SIZE
176 Returns: size of vcpu mmap area, in bytes
178 The KVM_RUN ioctl (cf.) communicates with userspace via a shared
179 memory region. This ioctl returns the size of that region. See the
180 KVM_RUN documentation for details.
183 4.6 KVM_SET_MEMORY_REGION
188 Parameters: struct kvm_memory_region (in)
189 Returns: 0 on success, -1 on error
191 This ioctl is obsolete and has been removed.
199 Parameters: vcpu id (apic id on x86)
200 Returns: vcpu fd on success, -1 on error
202 This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
203 The vcpu id is an integer in the range [0, max_vcpu_id).
205 The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
206 the KVM_CHECK_EXTENSION ioctl() at run-time.
207 The maximum possible value for max_vcpus can be retrieved using the
208 KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
210 If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
212 If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
213 same as the value returned from KVM_CAP_NR_VCPUS.
215 The maximum possible value for max_vcpu_id can be retrieved using the
216 KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.
218 If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id
219 is the same as the value returned from KVM_CAP_MAX_VCPUS.
221 On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
222 threads in one or more virtual CPU cores. (This is because the
223 hardware requires all the hardware threads in a CPU core to be in the
224 same partition.) The KVM_CAP_PPC_SMT capability indicates the number
225 of vcpus per virtual core (vcore). The vcore id is obtained by
226 dividing the vcpu id by the number of vcpus per vcore. The vcpus in a
227 given vcore will always be in the same physical core as each other
228 (though that might be a different physical core from time to time).
229 Userspace can control the threading (SMT) mode of the guest by its
230 allocation of vcpu ids. For example, if userspace wants
231 single-threaded guest vcpus, it should make all vcpu ids be a multiple
232 of the number of vcpus per vcore.
234 For virtual cpus that have been created with S390 user controlled virtual
235 machines, the resulting vcpu fd can be memory mapped at page offset
236 KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
237 cpu's hardware control block.
240 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
245 Parameters: struct kvm_dirty_log (in/out)
246 Returns: 0 on success, -1 on error
248 /* for KVM_GET_DIRTY_LOG */
249 struct kvm_dirty_log {
253 void __user *dirty_bitmap; /* one bit per page */
258 Given a memory slot, return a bitmap containing any pages dirtied
259 since the last call to this ioctl. Bit 0 is the first page in the
260 memory slot. Ensure the entire structure is cleared to avoid padding
263 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
264 the address space for which you want to return the dirty bitmap.
265 They must be less than the value that KVM_CHECK_EXTENSION returns for
266 the KVM_CAP_MULTI_ADDRESS_SPACE capability.
269 4.9 KVM_SET_MEMORY_ALIAS
274 Parameters: struct kvm_memory_alias (in)
275 Returns: 0 (success), -1 (error)
277 This ioctl is obsolete and has been removed.
286 Returns: 0 on success, -1 on error
288 EINTR: an unmasked signal is pending
290 This ioctl is used to run a guest virtual cpu. While there are no
291 explicit parameters, there is an implicit parameter block that can be
292 obtained by mmap()ing the vcpu fd at offset 0, with the size given by
293 KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct
294 kvm_run' (see below).
300 Architectures: all except ARM, arm64
302 Parameters: struct kvm_regs (out)
303 Returns: 0 on success, -1 on error
305 Reads the general purpose registers from the vcpu.
309 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
310 __u64 rax, rbx, rcx, rdx;
311 __u64 rsi, rdi, rsp, rbp;
312 __u64 r8, r9, r10, r11;
313 __u64 r12, r13, r14, r15;
319 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
330 Architectures: all except ARM, arm64
332 Parameters: struct kvm_regs (in)
333 Returns: 0 on success, -1 on error
335 Writes the general purpose registers into the vcpu.
337 See KVM_GET_REGS for the data structure.
343 Architectures: x86, ppc
345 Parameters: struct kvm_sregs (out)
346 Returns: 0 on success, -1 on error
348 Reads special registers from the vcpu.
352 struct kvm_segment cs, ds, es, fs, gs, ss;
353 struct kvm_segment tr, ldt;
354 struct kvm_dtable gdt, idt;
355 __u64 cr0, cr2, cr3, cr4, cr8;
358 __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
361 /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
363 interrupt_bitmap is a bitmap of pending external interrupts. At most
364 one bit may be set. This interrupt has been acknowledged by the APIC
365 but not yet injected into the cpu core.
371 Architectures: x86, ppc
373 Parameters: struct kvm_sregs (in)
374 Returns: 0 on success, -1 on error
376 Writes special registers into the vcpu. See KVM_GET_SREGS for the
385 Parameters: struct kvm_translation (in/out)
386 Returns: 0 on success, -1 on error
388 Translates a virtual address according to the vcpu's current address
391 struct kvm_translation {
393 __u64 linear_address;
396 __u64 physical_address;
407 Architectures: x86, ppc, mips
409 Parameters: struct kvm_interrupt (in)
410 Returns: 0 on success, negative on failure.
412 Queues a hardware interrupt vector to be injected.
414 /* for KVM_INTERRUPT */
415 struct kvm_interrupt {
422 Returns: 0 on success,
423 -EEXIST if an interrupt is already enqueued
424 -EINVAL the the irq number is invalid
425 -ENXIO if the PIC is in the kernel
426 -EFAULT if the pointer is invalid
428 Note 'irq' is an interrupt vector, not an interrupt pin or line. This
429 ioctl is useful if the in-kernel PIC is not used.
433 Queues an external interrupt to be injected. This ioctl is overleaded
434 with 3 different irq values:
438 This injects an edge type external interrupt into the guest once it's ready
439 to receive interrupts. When injected, the interrupt is done.
441 b) KVM_INTERRUPT_UNSET
443 This unsets any pending interrupt.
445 Only available with KVM_CAP_PPC_UNSET_IRQ.
447 c) KVM_INTERRUPT_SET_LEVEL
449 This injects a level type external interrupt into the guest context. The
450 interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
453 Only available with KVM_CAP_PPC_IRQ_LEVEL.
455 Note that any value for 'irq' other than the ones stated above is invalid
456 and incurs unexpected behavior.
460 Queues an external interrupt to be injected into the virtual CPU. A negative
461 interrupt number dequeues the interrupt.
472 Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead.
480 Parameters: struct kvm_msrs (in/out)
481 Returns: 0 on success, -1 on error
483 Reads model-specific registers from the vcpu. Supported msr indices can
484 be obtained using KVM_GET_MSR_INDEX_LIST.
487 __u32 nmsrs; /* number of msrs in entries */
490 struct kvm_msr_entry entries[0];
493 struct kvm_msr_entry {
499 Application code should set the 'nmsrs' member (which indicates the
500 size of the entries array) and the 'index' member of each array entry.
501 kvm will fill in the 'data' member.
509 Parameters: struct kvm_msrs (in)
510 Returns: 0 on success, -1 on error
512 Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the
515 Application code should set the 'nmsrs' member (which indicates the
516 size of the entries array), and the 'index' and 'data' members of each
525 Parameters: struct kvm_cpuid (in)
526 Returns: 0 on success, -1 on error
528 Defines the vcpu responses to the cpuid instruction. Applications
529 should use the KVM_SET_CPUID2 ioctl if available.
532 struct kvm_cpuid_entry {
541 /* for KVM_SET_CPUID */
545 struct kvm_cpuid_entry entries[0];
549 4.21 KVM_SET_SIGNAL_MASK
554 Parameters: struct kvm_signal_mask (in)
555 Returns: 0 on success, -1 on error
557 Defines which signals are blocked during execution of KVM_RUN. This
558 signal mask temporarily overrides the threads signal mask. Any
559 unblocked signal received (except SIGKILL and SIGSTOP, which retain
560 their traditional behaviour) will cause KVM_RUN to return with -EINTR.
562 Note the signal will only be delivered if not blocked by the original
565 /* for KVM_SET_SIGNAL_MASK */
566 struct kvm_signal_mask {
577 Parameters: struct kvm_fpu (out)
578 Returns: 0 on success, -1 on error
580 Reads the floating point state from the vcpu.
582 /* for KVM_GET_FPU and KVM_SET_FPU */
587 __u8 ftwx; /* in fxsave format */
603 Parameters: struct kvm_fpu (in)
604 Returns: 0 on success, -1 on error
606 Writes the floating point state to the vcpu.
608 /* for KVM_GET_FPU and KVM_SET_FPU */
613 __u8 ftwx; /* in fxsave format */
624 4.24 KVM_CREATE_IRQCHIP
626 Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
627 Architectures: x86, ARM, arm64, s390
630 Returns: 0 on success, -1 on error
632 Creates an interrupt controller model in the kernel.
633 On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
634 future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both
635 PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
636 On ARM/arm64, a GICv2 is created. Any other GIC versions require the usage of
637 KVM_CREATE_DEVICE, which also supports creating a GICv2. Using
638 KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2.
639 On s390, a dummy irq routing table is created.
641 Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
642 before KVM_CREATE_IRQCHIP can be used.
647 Capability: KVM_CAP_IRQCHIP
648 Architectures: x86, arm, arm64
650 Parameters: struct kvm_irq_level
651 Returns: 0 on success, -1 on error
653 Sets the level of a GSI input to the interrupt controller model in the kernel.
654 On some architectures it is required that an interrupt controller model has
655 been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
656 interrupts require the level to be set to 1 and then back to 0.
658 On real hardware, interrupt pins can be active-low or active-high. This
659 does not matter for the level field of struct kvm_irq_level: 1 always
660 means active (asserted), 0 means inactive (deasserted).
662 x86 allows the operating system to program the interrupt polarity
663 (active-low/active-high) for level-triggered interrupts, and KVM used
664 to consider the polarity. However, due to bitrot in the handling of
665 active-low interrupts, the above convention is now valid on x86 too.
666 This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED. Userspace
667 should not present interrupts to the guest as active-low unless this
668 capability is present (or unless it is not using the in-kernel irqchip,
672 ARM/arm64 can signal an interrupt either at the CPU level, or at the
673 in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
674 use PPIs designated for specific cpus. The irq field is interpreted
677 Â bits: | 31 ... 24 | 23 ... 16 | 15 ... 0 |
678 field: | irq_type | vcpu_index | irq_id |
680 The irq_type field has the following values:
681 - irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
682 - irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
683 (the vcpu_index field is ignored)
684 - irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
686 (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
688 In both cases, level is used to assert/deassert the line.
690 struct kvm_irq_level {
693 __s32 status; /* not used for KVM_IRQ_LEVEL */
695 __u32 level; /* 0 or 1 */
701 Capability: KVM_CAP_IRQCHIP
704 Parameters: struct kvm_irqchip (in/out)
705 Returns: 0 on success, -1 on error
707 Reads the state of a kernel interrupt controller created with
708 KVM_CREATE_IRQCHIP into a buffer provided by the caller.
711 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
714 char dummy[512]; /* reserving space */
715 struct kvm_pic_state pic;
716 struct kvm_ioapic_state ioapic;
723 Capability: KVM_CAP_IRQCHIP
726 Parameters: struct kvm_irqchip (in)
727 Returns: 0 on success, -1 on error
729 Sets the state of a kernel interrupt controller created with
730 KVM_CREATE_IRQCHIP from a buffer provided by the caller.
733 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
736 char dummy[512]; /* reserving space */
737 struct kvm_pic_state pic;
738 struct kvm_ioapic_state ioapic;
743 4.28 KVM_XEN_HVM_CONFIG
745 Capability: KVM_CAP_XEN_HVM
748 Parameters: struct kvm_xen_hvm_config (in)
749 Returns: 0 on success, -1 on error
751 Sets the MSR that the Xen HVM guest uses to initialize its hypercall
752 page, and provides the starting address and size of the hypercall
753 blobs in userspace. When the guest writes the MSR, kvm copies one
754 page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
757 struct kvm_xen_hvm_config {
770 Capability: KVM_CAP_ADJUST_CLOCK
773 Parameters: struct kvm_clock_data (out)
774 Returns: 0 on success, -1 on error
776 Gets the current timestamp of kvmclock as seen by the current guest. In
777 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
780 struct kvm_clock_data {
781 __u64 clock; /* kvmclock current value */
789 Capability: KVM_CAP_ADJUST_CLOCK
792 Parameters: struct kvm_clock_data (in)
793 Returns: 0 on success, -1 on error
795 Sets the current timestamp of kvmclock to the value specified in its parameter.
796 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
799 struct kvm_clock_data {
800 __u64 clock; /* kvmclock current value */
806 4.31 KVM_GET_VCPU_EVENTS
808 Capability: KVM_CAP_VCPU_EVENTS
809 Extended by: KVM_CAP_INTR_SHADOW
812 Parameters: struct kvm_vcpu_event (out)
813 Returns: 0 on success, -1 on error
815 Gets currently pending exceptions, interrupts, and NMIs as well as related
818 struct kvm_vcpu_events {
848 Only two fields are defined in the flags field:
850 - KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
851 interrupt.shadow contains a valid state.
853 - KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
854 smi contains a valid state.
856 4.32 KVM_SET_VCPU_EVENTS
858 Capability: KVM_CAP_VCPU_EVENTS
859 Extended by: KVM_CAP_INTR_SHADOW
862 Parameters: struct kvm_vcpu_event (in)
863 Returns: 0 on success, -1 on error
865 Set pending exceptions, interrupts, and NMIs as well as related states of the
868 See KVM_GET_VCPU_EVENTS for the data structure.
870 Fields that may be modified asynchronously by running VCPUs can be excluded
871 from the update. These fields are nmi.pending, sipi_vector, smi.smm,
872 smi.pending. Keep the corresponding bits in the flags field cleared to
873 suppress overwriting the current in-kernel state. The bits are:
875 KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
876 KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
877 KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct.
879 If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
880 the flags field to signal that interrupt.shadow contains a valid state and
881 shall be written into the VCPU.
883 KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
886 4.33 KVM_GET_DEBUGREGS
888 Capability: KVM_CAP_DEBUGREGS
891 Parameters: struct kvm_debugregs (out)
892 Returns: 0 on success, -1 on error
894 Reads debug registers from the vcpu.
896 struct kvm_debugregs {
905 4.34 KVM_SET_DEBUGREGS
907 Capability: KVM_CAP_DEBUGREGS
910 Parameters: struct kvm_debugregs (in)
911 Returns: 0 on success, -1 on error
913 Writes debug registers into the vcpu.
915 See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
916 yet and must be cleared on entry.
919 4.35 KVM_SET_USER_MEMORY_REGION
921 Capability: KVM_CAP_USER_MEM
924 Parameters: struct kvm_userspace_memory_region (in)
925 Returns: 0 on success, -1 on error
927 struct kvm_userspace_memory_region {
930 __u64 guest_phys_addr;
931 __u64 memory_size; /* bytes */
932 __u64 userspace_addr; /* start of the userspace allocated memory */
935 /* for kvm_memory_region::flags */
936 #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
937 #define KVM_MEM_READONLY (1UL << 1)
939 This ioctl allows the user to create or modify a guest physical memory
940 slot. When changing an existing slot, it may be moved in the guest
941 physical memory space, or its flags may be modified. It may not be
942 resized. Slots may not overlap in guest physical address space.
944 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
945 specifies the address space which is being modified. They must be
946 less than the value that KVM_CHECK_EXTENSION returns for the
947 KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces
948 are unrelated; the restriction on overlapping slots only applies within
951 Memory for the region is taken starting at the address denoted by the
952 field userspace_addr, which must point at user addressable memory for
953 the entire memory slot size. Any object may back this memory, including
954 anonymous memory, ordinary files, and hugetlbfs.
956 It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
957 be identical. This allows large pages in the guest to be backed by large
960 The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
961 KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of
962 writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to
963 use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
964 to make a new slot read-only. In this case, writes to this memory will be
965 posted to userspace as KVM_EXIT_MMIO exits.
967 When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
968 the memory region are automatically reflected into the guest. For example, an
969 mmap() that affects the region will be made visible immediately. Another
970 example is madvise(MADV_DROP).
972 It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
973 The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
974 allocation and is deprecated.
977 4.36 KVM_SET_TSS_ADDR
979 Capability: KVM_CAP_SET_TSS_ADDR
982 Parameters: unsigned long tss_address (in)
983 Returns: 0 on success, -1 on error
985 This ioctl defines the physical address of a three-page region in the guest
986 physical address space. The region must be within the first 4GB of the
987 guest physical address space and must not conflict with any memory slot
988 or any mmio address. The guest may malfunction if it accesses this memory
991 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
992 because of a quirk in the virtualization implementation (see the internals
993 documentation when it pops into existence).
998 Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
999 Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM),
1000 mips (only KVM_CAP_ENABLE_CAP), ppc, s390
1001 Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
1002 Parameters: struct kvm_enable_cap (in)
1003 Returns: 0 on success; -1 on error
1005 +Not all extensions are enabled by default. Using this ioctl the application
1006 can enable an extension, making it available to the guest.
1008 On systems that do not support this ioctl, it always fails. On systems that
1009 do support it, it only works for extensions that are supported for enablement.
1011 To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
1014 struct kvm_enable_cap {
1018 The capability that is supposed to get enabled.
1022 A bitfield indicating future enhancements. Has to be 0 for now.
1026 Arguments for enabling a feature. If a feature needs initial values to
1027 function properly, this is the place to put them.
1032 The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
1033 for vm-wide capabilities.
1035 4.38 KVM_GET_MP_STATE
1037 Capability: KVM_CAP_MP_STATE
1038 Architectures: x86, s390, arm, arm64
1040 Parameters: struct kvm_mp_state (out)
1041 Returns: 0 on success; -1 on error
1043 struct kvm_mp_state {
1047 Returns the vcpu's current "multiprocessing state" (though also valid on
1048 uniprocessor guests).
1050 Possible values are:
1052 - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64]
1053 - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP)
1054 which has not yet received an INIT signal [x86]
1055 - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is
1056 now ready for a SIPI [x86]
1057 - KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and
1058 is waiting for an interrupt [x86]
1059 - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector
1060 accessible via KVM_GET_VCPU_EVENTS) [x86]
1061 - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64]
1062 - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390]
1063 - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted)
1065 - KVM_MP_STATE_LOAD: the vcpu is in a special load/startup state
1068 On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
1069 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
1070 these architectures.
1074 The only states that are valid are KVM_MP_STATE_STOPPED and
1075 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
1077 4.39 KVM_SET_MP_STATE
1079 Capability: KVM_CAP_MP_STATE
1080 Architectures: x86, s390, arm, arm64
1082 Parameters: struct kvm_mp_state (in)
1083 Returns: 0 on success; -1 on error
1085 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
1088 On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
1089 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
1090 these architectures.
1094 The only states that are valid are KVM_MP_STATE_STOPPED and
1095 KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
1097 4.40 KVM_SET_IDENTITY_MAP_ADDR
1099 Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
1102 Parameters: unsigned long identity (in)
1103 Returns: 0 on success, -1 on error
1105 This ioctl defines the physical address of a one-page region in the guest
1106 physical address space. The region must be within the first 4GB of the
1107 guest physical address space and must not conflict with any memory slot
1108 or any mmio address. The guest may malfunction if it accesses this memory
1111 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
1112 because of a quirk in the virtualization implementation (see the internals
1113 documentation when it pops into existence).
1116 4.41 KVM_SET_BOOT_CPU_ID
1118 Capability: KVM_CAP_SET_BOOT_CPU_ID
1121 Parameters: unsigned long vcpu_id
1122 Returns: 0 on success, -1 on error
1124 Define which vcpu is the Bootstrap Processor (BSP). Values are the same
1125 as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default
1131 Capability: KVM_CAP_XSAVE
1134 Parameters: struct kvm_xsave (out)
1135 Returns: 0 on success, -1 on error
1141 This ioctl would copy current vcpu's xsave struct to the userspace.
1146 Capability: KVM_CAP_XSAVE
1149 Parameters: struct kvm_xsave (in)
1150 Returns: 0 on success, -1 on error
1156 This ioctl would copy userspace's xsave struct to the kernel.
1161 Capability: KVM_CAP_XCRS
1164 Parameters: struct kvm_xcrs (out)
1165 Returns: 0 on success, -1 on error
1176 struct kvm_xcr xcrs[KVM_MAX_XCRS];
1180 This ioctl would copy current vcpu's xcrs to the userspace.
1185 Capability: KVM_CAP_XCRS
1188 Parameters: struct kvm_xcrs (in)
1189 Returns: 0 on success, -1 on error
1200 struct kvm_xcr xcrs[KVM_MAX_XCRS];
1204 This ioctl would set vcpu's xcr to the value userspace specified.
1207 4.46 KVM_GET_SUPPORTED_CPUID
1209 Capability: KVM_CAP_EXT_CPUID
1212 Parameters: struct kvm_cpuid2 (in/out)
1213 Returns: 0 on success, -1 on error
1218 struct kvm_cpuid_entry2 entries[0];
1221 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
1222 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
1223 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
1225 struct kvm_cpuid_entry2 {
1236 This ioctl returns x86 cpuid features which are supported by both the hardware
1237 and kvm. Userspace can use the information returned by this ioctl to
1238 construct cpuid information (for KVM_SET_CPUID2) that is consistent with
1239 hardware, kernel, and userspace capabilities, and with user requirements (for
1240 example, the user may wish to constrain cpuid to emulate older hardware,
1241 or for feature consistency across a cluster).
1243 Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
1244 with the 'nent' field indicating the number of entries in the variable-size
1245 array 'entries'. If the number of entries is too low to describe the cpu
1246 capabilities, an error (E2BIG) is returned. If the number is too high,
1247 the 'nent' field is adjusted and an error (ENOMEM) is returned. If the
1248 number is just right, the 'nent' field is adjusted to the number of valid
1249 entries in the 'entries' array, which is then filled.
1251 The entries returned are the host cpuid as returned by the cpuid instruction,
1252 with unknown or unsupported features masked out. Some features (for example,
1253 x2apic), may not be present in the host cpu, but are exposed by kvm if it can
1254 emulate them efficiently. The fields in each entry are defined as follows:
1256 function: the eax value used to obtain the entry
1257 index: the ecx value used to obtain the entry (for entries that are
1259 flags: an OR of zero or more of the following:
1260 KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
1261 if the index field is valid
1262 KVM_CPUID_FLAG_STATEFUL_FUNC:
1263 if cpuid for this function returns different values for successive
1264 invocations; there will be several entries with the same function,
1265 all with this flag set
1266 KVM_CPUID_FLAG_STATE_READ_NEXT:
1267 for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
1268 the first entry to be read by a cpu
1269 eax, ebx, ecx, edx: the values returned by the cpuid instruction for
1270 this function/index combination
1272 The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
1273 as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
1274 support. Instead it is reported via
1276 ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
1278 if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
1279 feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
1282 4.47 KVM_PPC_GET_PVINFO
1284 Capability: KVM_CAP_PPC_GET_PVINFO
1287 Parameters: struct kvm_ppc_pvinfo (out)
1288 Returns: 0 on success, !0 on error
1290 struct kvm_ppc_pvinfo {
1296 This ioctl fetches PV specific information that need to be passed to the guest
1297 using the device tree or other means from vm context.
1299 The hcall array defines 4 instructions that make up a hypercall.
1301 If any additional field gets added to this structure later on, a bit for that
1302 additional piece of information will be set in the flags bitmap.
1304 The flags bitmap is defined as:
1306 /* the host supports the ePAPR idle hcall
1307 #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
1309 4.48 KVM_ASSIGN_PCI_DEVICE (deprecated)
1314 Parameters: struct kvm_assigned_pci_dev (in)
1315 Returns: 0 on success, -1 on error
1317 Assigns a host PCI device to the VM.
1319 struct kvm_assigned_pci_dev {
1320 __u32 assigned_dev_id;
1330 The PCI device is specified by the triple segnr, busnr, and devfn.
1331 Identification in succeeding service requests is done via assigned_dev_id. The
1332 following flags are specified:
1334 /* Depends on KVM_CAP_IOMMU */
1335 #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
1336 /* The following two depend on KVM_CAP_PCI_2_3 */
1337 #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
1338 #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
1340 If KVM_DEV_ASSIGN_PCI_2_3 is set, the kernel will manage legacy INTx interrupts
1341 via the PCI-2.3-compliant device-level mask, thus enable IRQ sharing with other
1342 assigned devices or host devices. KVM_DEV_ASSIGN_MASK_INTX specifies the
1343 guest's view on the INTx mask, see KVM_ASSIGN_SET_INTX_MASK for details.
1345 The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
1346 isolation of the device. Usages not specifying this flag are deprecated.
1348 Only PCI header type 0 devices with PCI BAR resources are supported by
1349 device assignment. The user requesting this ioctl must have read/write
1350 access to the PCI sysfs resource files associated with the device.
1353 ENOTTY: kernel does not support this ioctl
1355 Other error conditions may be defined by individual device types or
1356 have their standard meanings.
1359 4.49 KVM_DEASSIGN_PCI_DEVICE (deprecated)
1364 Parameters: struct kvm_assigned_pci_dev (in)
1365 Returns: 0 on success, -1 on error
1367 Ends PCI device assignment, releasing all associated resources.
1369 See KVM_ASSIGN_PCI_DEVICE for the data structure. Only assigned_dev_id is
1370 used in kvm_assigned_pci_dev to identify the device.
1373 ENOTTY: kernel does not support this ioctl
1375 Other error conditions may be defined by individual device types or
1376 have their standard meanings.
1378 4.50 KVM_ASSIGN_DEV_IRQ (deprecated)
1380 Capability: KVM_CAP_ASSIGN_DEV_IRQ
1383 Parameters: struct kvm_assigned_irq (in)
1384 Returns: 0 on success, -1 on error
1386 Assigns an IRQ to a passed-through device.
1388 struct kvm_assigned_irq {
1389 __u32 assigned_dev_id;
1390 __u32 host_irq; /* ignored (legacy field) */
1398 The following flags are defined:
1400 #define KVM_DEV_IRQ_HOST_INTX (1 << 0)
1401 #define KVM_DEV_IRQ_HOST_MSI (1 << 1)
1402 #define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
1404 #define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
1405 #define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
1406 #define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
1408 It is not valid to specify multiple types per host or guest IRQ. However, the
1409 IRQ type of host and guest can differ or can even be null.
1412 ENOTTY: kernel does not support this ioctl
1414 Other error conditions may be defined by individual device types or
1415 have their standard meanings.
1418 4.51 KVM_DEASSIGN_DEV_IRQ (deprecated)
1420 Capability: KVM_CAP_ASSIGN_DEV_IRQ
1423 Parameters: struct kvm_assigned_irq (in)
1424 Returns: 0 on success, -1 on error
1426 Ends an IRQ assignment to a passed-through device.
1428 See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
1429 by assigned_dev_id, flags must correspond to the IRQ type specified on
1430 KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
1433 4.52 KVM_SET_GSI_ROUTING
1435 Capability: KVM_CAP_IRQ_ROUTING
1436 Architectures: x86 s390
1438 Parameters: struct kvm_irq_routing (in)
1439 Returns: 0 on success, -1 on error
1441 Sets the GSI routing table entries, overwriting any previously set entries.
1443 struct kvm_irq_routing {
1446 struct kvm_irq_routing_entry entries[0];
1449 No flags are specified so far, the corresponding field must be set to zero.
1451 struct kvm_irq_routing_entry {
1457 struct kvm_irq_routing_irqchip irqchip;
1458 struct kvm_irq_routing_msi msi;
1459 struct kvm_irq_routing_s390_adapter adapter;
1460 struct kvm_irq_routing_hv_sint hv_sint;
1465 /* gsi routing entry types */
1466 #define KVM_IRQ_ROUTING_IRQCHIP 1
1467 #define KVM_IRQ_ROUTING_MSI 2
1468 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
1469 #define KVM_IRQ_ROUTING_HV_SINT 4
1471 No flags are specified so far, the corresponding field must be set to zero.
1473 struct kvm_irq_routing_irqchip {
1478 struct kvm_irq_routing_msi {
1485 On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
1486 feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
1487 address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
1488 address_hi must be zero.
1490 struct kvm_irq_routing_s390_adapter {
1494 __u32 summary_offset;
1498 struct kvm_irq_routing_hv_sint {
1503 4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated)
1508 Parameters: struct kvm_assigned_msix_nr (in)
1509 Returns: 0 on success, -1 on error
1511 Set the number of MSI-X interrupts for an assigned device. The number is
1512 reset again by terminating the MSI-X assignment of the device via
1513 KVM_DEASSIGN_DEV_IRQ. Calling this service more than once at any earlier
1516 struct kvm_assigned_msix_nr {
1517 __u32 assigned_dev_id;
1522 #define KVM_MAX_MSIX_PER_DEV 256
1525 4.54 KVM_ASSIGN_SET_MSIX_ENTRY (deprecated)
1530 Parameters: struct kvm_assigned_msix_entry (in)
1531 Returns: 0 on success, -1 on error
1533 Specifies the routing of an MSI-X assigned device interrupt to a GSI. Setting
1534 the GSI vector to zero means disabling the interrupt.
1536 struct kvm_assigned_msix_entry {
1537 __u32 assigned_dev_id;
1539 __u16 entry; /* The index of entry in the MSI-X table */
1544 ENOTTY: kernel does not support this ioctl
1546 Other error conditions may be defined by individual device types or
1547 have their standard meanings.
1550 4.55 KVM_SET_TSC_KHZ
1552 Capability: KVM_CAP_TSC_CONTROL
1555 Parameters: virtual tsc_khz
1556 Returns: 0 on success, -1 on error
1558 Specifies the tsc frequency for the virtual machine. The unit of the
1562 4.56 KVM_GET_TSC_KHZ
1564 Capability: KVM_CAP_GET_TSC_KHZ
1568 Returns: virtual tsc-khz on success, negative value on error
1570 Returns the tsc frequency of the guest. The unit of the return value is
1571 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
1577 Capability: KVM_CAP_IRQCHIP
1580 Parameters: struct kvm_lapic_state (out)
1581 Returns: 0 on success, -1 on error
1583 #define KVM_APIC_REG_SIZE 0x400
1584 struct kvm_lapic_state {
1585 char regs[KVM_APIC_REG_SIZE];
1588 Reads the Local APIC registers and copies them into the input argument. The
1589 data format and layout are the same as documented in the architecture manual.
1591 If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
1592 enabled, then the format of APIC_ID register depends on the APIC mode
1593 (reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in
1594 the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID
1595 which is stored in bits 31-24 of the APIC register, or equivalently in
1596 byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then
1597 be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.
1599 If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
1600 always uses xAPIC format.
1605 Capability: KVM_CAP_IRQCHIP
1608 Parameters: struct kvm_lapic_state (in)
1609 Returns: 0 on success, -1 on error
1611 #define KVM_APIC_REG_SIZE 0x400
1612 struct kvm_lapic_state {
1613 char regs[KVM_APIC_REG_SIZE];
1616 Copies the input argument into the Local APIC registers. The data format
1617 and layout are the same as documented in the architecture manual.
1619 The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
1620 regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
1621 See the note in KVM_GET_LAPIC.
1626 Capability: KVM_CAP_IOEVENTFD
1629 Parameters: struct kvm_ioeventfd (in)
1630 Returns: 0 on success, !0 on error
1632 This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
1633 within the guest. A guest write in the registered address will signal the
1634 provided event instead of triggering an exit.
1636 struct kvm_ioeventfd {
1638 __u64 addr; /* legal pio/mmio address */
1639 __u32 len; /* 0, 1, 2, 4, or 8 bytes */
1645 For the special case of virtio-ccw devices on s390, the ioevent is matched
1646 to a subchannel/virtqueue tuple instead.
1648 The following flags are defined:
1650 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
1651 #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
1652 #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
1653 #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
1654 (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
1656 If datamatch flag is set, the event will be signaled only if the written value
1657 to the registered address is equal to datamatch in struct kvm_ioeventfd.
1659 For virtio-ccw devices, addr contains the subchannel id and datamatch the
1662 With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
1663 the kernel will ignore the length of guest write and may get a faster vmexit.
1664 The speedup may only apply to specific architectures, but the ioeventfd will
1669 Capability: KVM_CAP_SW_TLB
1672 Parameters: struct kvm_dirty_tlb (in)
1673 Returns: 0 on success, -1 on error
1675 struct kvm_dirty_tlb {
1680 This must be called whenever userspace has changed an entry in the shared
1681 TLB, prior to calling KVM_RUN on the associated vcpu.
1683 The "bitmap" field is the userspace address of an array. This array
1684 consists of a number of bits, equal to the total number of TLB entries as
1685 determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
1686 nearest multiple of 64.
1688 Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
1691 The array is little-endian: the bit 0 is the least significant bit of the
1692 first byte, bit 8 is the least significant bit of the second byte, etc.
1693 This avoids any complications with differing word sizes.
1695 The "num_dirty" field is a performance hint for KVM to determine whether it
1696 should skip processing the bitmap and just invalidate everything. It must
1697 be set to the number of set bits in the bitmap.
1700 4.61 KVM_ASSIGN_SET_INTX_MASK (deprecated)
1702 Capability: KVM_CAP_PCI_2_3
1705 Parameters: struct kvm_assigned_pci_dev (in)
1706 Returns: 0 on success, -1 on error
1708 Allows userspace to mask PCI INTx interrupts from the assigned device. The
1709 kernel will not deliver INTx interrupts to the guest between setting and
1710 clearing of KVM_ASSIGN_SET_INTX_MASK via this interface. This enables use of
1711 and emulation of PCI 2.3 INTx disable command register behavior.
1713 This may be used for both PCI 2.3 devices supporting INTx disable natively and
1714 older devices lacking this support. Userspace is responsible for emulating the
1715 read value of the INTx disable bit in the guest visible PCI command register.
1716 When modifying the INTx disable state, userspace should precede updating the
1717 physical device command register by calling this ioctl to inform the kernel of
1718 the new intended INTx mask state.
1720 Note that the kernel uses the device INTx disable bit to internally manage the
1721 device interrupt state for PCI 2.3 devices. Reads of this register may
1722 therefore not match the expected value. Writes should always use the guest
1723 intended INTx disable value rather than attempting to read-copy-update the
1724 current physical device state. Races between user and kernel updates to the
1725 INTx disable bit are handled lazily in the kernel. It's possible the device
1726 may generate unintended interrupts, but they will not be injected into the
1729 See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
1730 by assigned_dev_id. In the flags field, only KVM_DEV_ASSIGN_MASK_INTX is
1734 4.62 KVM_CREATE_SPAPR_TCE
1736 Capability: KVM_CAP_SPAPR_TCE
1737 Architectures: powerpc
1739 Parameters: struct kvm_create_spapr_tce (in)
1740 Returns: file descriptor for manipulating the created TCE table
1742 This creates a virtual TCE (translation control entry) table, which
1743 is an IOMMU for PAPR-style virtual I/O. It is used to translate
1744 logical addresses used in virtual I/O into guest physical addresses,
1745 and provides a scatter/gather capability for PAPR virtual I/O.
1747 /* for KVM_CAP_SPAPR_TCE */
1748 struct kvm_create_spapr_tce {
1753 The liobn field gives the logical IO bus number for which to create a
1754 TCE table. The window_size field specifies the size of the DMA window
1755 which this TCE table will translate - the table will contain one 64
1756 bit TCE entry for every 4kiB of the DMA window.
1758 When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
1759 table has been created using this ioctl(), the kernel will handle it
1760 in real mode, updating the TCE table. H_PUT_TCE calls for other
1761 liobns will cause a vm exit and must be handled by userspace.
1763 The return value is a file descriptor which can be passed to mmap(2)
1764 to map the created TCE table into userspace. This lets userspace read
1765 the entries written by kernel-handled H_PUT_TCE calls, and also lets
1766 userspace update the TCE table directly which is useful in some
1770 4.63 KVM_ALLOCATE_RMA
1772 Capability: KVM_CAP_PPC_RMA
1773 Architectures: powerpc
1775 Parameters: struct kvm_allocate_rma (out)
1776 Returns: file descriptor for mapping the allocated RMA
1778 This allocates a Real Mode Area (RMA) from the pool allocated at boot
1779 time by the kernel. An RMA is a physically-contiguous, aligned region
1780 of memory used on older POWER processors to provide the memory which
1781 will be accessed by real-mode (MMU off) accesses in a KVM guest.
1782 POWER processors support a set of sizes for the RMA that usually
1783 includes 64MB, 128MB, 256MB and some larger powers of two.
1785 /* for KVM_ALLOCATE_RMA */
1786 struct kvm_allocate_rma {
1790 The return value is a file descriptor which can be passed to mmap(2)
1791 to map the allocated RMA into userspace. The mapped area can then be
1792 passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
1793 RMA for a virtual machine. The size of the RMA in bytes (which is
1794 fixed at host kernel boot time) is returned in the rma_size field of
1795 the argument structure.
1797 The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
1798 is supported; 2 if the processor requires all virtual machines to have
1799 an RMA, or 1 if the processor can use an RMA but doesn't require it,
1800 because it supports the Virtual RMA (VRMA) facility.
1805 Capability: KVM_CAP_USER_NMI
1809 Returns: 0 on success, -1 on error
1811 Queues an NMI on the thread's vcpu. Note this is well defined only
1812 when KVM_CREATE_IRQCHIP has not been called, since this is an interface
1813 between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP
1814 has been called, this interface is completely emulated within the kernel.
1816 To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
1817 following algorithm:
1820 - read the local APIC's state (KVM_GET_LAPIC)
1821 - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
1822 - if so, issue KVM_NMI
1825 Some guests configure the LINT1 NMI input to cause a panic, aiding in
1829 4.65 KVM_S390_UCAS_MAP
1831 Capability: KVM_CAP_S390_UCONTROL
1834 Parameters: struct kvm_s390_ucas_mapping (in)
1835 Returns: 0 in case of success
1837 The parameter is defined like this:
1838 struct kvm_s390_ucas_mapping {
1844 This ioctl maps the memory at "user_addr" with the length "length" to
1845 the vcpu's address space starting at "vcpu_addr". All parameters need to
1846 be aligned by 1 megabyte.
1849 4.66 KVM_S390_UCAS_UNMAP
1851 Capability: KVM_CAP_S390_UCONTROL
1854 Parameters: struct kvm_s390_ucas_mapping (in)
1855 Returns: 0 in case of success
1857 The parameter is defined like this:
1858 struct kvm_s390_ucas_mapping {
1864 This ioctl unmaps the memory in the vcpu's address space starting at
1865 "vcpu_addr" with the length "length". The field "user_addr" is ignored.
1866 All parameters need to be aligned by 1 megabyte.
1869 4.67 KVM_S390_VCPU_FAULT
1871 Capability: KVM_CAP_S390_UCONTROL
1874 Parameters: vcpu absolute address (in)
1875 Returns: 0 in case of success
1877 This call creates a page table entry on the virtual cpu's address space
1878 (for user controlled virtual machines) or the virtual machine's address
1879 space (for regular virtual machines). This only works for minor faults,
1880 thus it's recommended to access subject memory page via the user page
1881 table upfront. This is useful to handle validity intercepts for user
1882 controlled virtual machines to fault in the virtual cpu's lowcore pages
1883 prior to calling the KVM_RUN ioctl.
1886 4.68 KVM_SET_ONE_REG
1888 Capability: KVM_CAP_ONE_REG
1891 Parameters: struct kvm_one_reg (in)
1892 Returns: 0 on success, negative value on failure
1894 struct kvm_one_reg {
1899 Using this ioctl, a single vcpu register can be set to a specific value
1900 defined by user space with the passed in struct kvm_one_reg, where id
1901 refers to the register identifier as described below and addr is a pointer
1902 to a variable with the respective size. There can be architecture agnostic
1903 and architecture specific registers. Each have their own range of operation
1904 and their own constants and width. To keep track of the implemented
1905 registers, find a list below:
1907 Arch | Register | Width (bits)
1909 PPC | KVM_REG_PPC_HIOR | 64
1910 PPC | KVM_REG_PPC_IAC1 | 64
1911 PPC | KVM_REG_PPC_IAC2 | 64
1912 PPC | KVM_REG_PPC_IAC3 | 64
1913 PPC | KVM_REG_PPC_IAC4 | 64
1914 PPC | KVM_REG_PPC_DAC1 | 64
1915 PPC | KVM_REG_PPC_DAC2 | 64
1916 PPC | KVM_REG_PPC_DABR | 64
1917 PPC | KVM_REG_PPC_DSCR | 64
1918 PPC | KVM_REG_PPC_PURR | 64
1919 PPC | KVM_REG_PPC_SPURR | 64
1920 PPC | KVM_REG_PPC_DAR | 64
1921 PPC | KVM_REG_PPC_DSISR | 32
1922 PPC | KVM_REG_PPC_AMR | 64
1923 PPC | KVM_REG_PPC_UAMOR | 64
1924 PPC | KVM_REG_PPC_MMCR0 | 64
1925 PPC | KVM_REG_PPC_MMCR1 | 64
1926 PPC | KVM_REG_PPC_MMCRA | 64
1927 PPC | KVM_REG_PPC_MMCR2 | 64
1928 PPC | KVM_REG_PPC_MMCRS | 64
1929 PPC | KVM_REG_PPC_SIAR | 64
1930 PPC | KVM_REG_PPC_SDAR | 64
1931 PPC | KVM_REG_PPC_SIER | 64
1932 PPC | KVM_REG_PPC_PMC1 | 32
1933 PPC | KVM_REG_PPC_PMC2 | 32
1934 PPC | KVM_REG_PPC_PMC3 | 32
1935 PPC | KVM_REG_PPC_PMC4 | 32
1936 PPC | KVM_REG_PPC_PMC5 | 32
1937 PPC | KVM_REG_PPC_PMC6 | 32
1938 PPC | KVM_REG_PPC_PMC7 | 32
1939 PPC | KVM_REG_PPC_PMC8 | 32
1940 PPC | KVM_REG_PPC_FPR0 | 64
1942 PPC | KVM_REG_PPC_FPR31 | 64
1943 PPC | KVM_REG_PPC_VR0 | 128
1945 PPC | KVM_REG_PPC_VR31 | 128
1946 PPC | KVM_REG_PPC_VSR0 | 128
1948 PPC | KVM_REG_PPC_VSR31 | 128
1949 PPC | KVM_REG_PPC_FPSCR | 64
1950 PPC | KVM_REG_PPC_VSCR | 32
1951 PPC | KVM_REG_PPC_VPA_ADDR | 64
1952 PPC | KVM_REG_PPC_VPA_SLB | 128
1953 PPC | KVM_REG_PPC_VPA_DTL | 128
1954 PPC | KVM_REG_PPC_EPCR | 32
1955 PPC | KVM_REG_PPC_EPR | 32
1956 PPC | KVM_REG_PPC_TCR | 32
1957 PPC | KVM_REG_PPC_TSR | 32
1958 PPC | KVM_REG_PPC_OR_TSR | 32
1959 PPC | KVM_REG_PPC_CLEAR_TSR | 32
1960 PPC | KVM_REG_PPC_MAS0 | 32
1961 PPC | KVM_REG_PPC_MAS1 | 32
1962 PPC | KVM_REG_PPC_MAS2 | 64
1963 PPC | KVM_REG_PPC_MAS7_3 | 64
1964 PPC | KVM_REG_PPC_MAS4 | 32
1965 PPC | KVM_REG_PPC_MAS6 | 32
1966 PPC | KVM_REG_PPC_MMUCFG | 32
1967 PPC | KVM_REG_PPC_TLB0CFG | 32
1968 PPC | KVM_REG_PPC_TLB1CFG | 32
1969 PPC | KVM_REG_PPC_TLB2CFG | 32
1970 PPC | KVM_REG_PPC_TLB3CFG | 32
1971 PPC | KVM_REG_PPC_TLB0PS | 32
1972 PPC | KVM_REG_PPC_TLB1PS | 32
1973 PPC | KVM_REG_PPC_TLB2PS | 32
1974 PPC | KVM_REG_PPC_TLB3PS | 32
1975 PPC | KVM_REG_PPC_EPTCFG | 32
1976 PPC | KVM_REG_PPC_ICP_STATE | 64
1977 PPC | KVM_REG_PPC_TB_OFFSET | 64
1978 PPC | KVM_REG_PPC_SPMC1 | 32
1979 PPC | KVM_REG_PPC_SPMC2 | 32
1980 PPC | KVM_REG_PPC_IAMR | 64
1981 PPC | KVM_REG_PPC_TFHAR | 64
1982 PPC | KVM_REG_PPC_TFIAR | 64
1983 PPC | KVM_REG_PPC_TEXASR | 64
1984 PPC | KVM_REG_PPC_FSCR | 64
1985 PPC | KVM_REG_PPC_PSPB | 32
1986 PPC | KVM_REG_PPC_EBBHR | 64
1987 PPC | KVM_REG_PPC_EBBRR | 64
1988 PPC | KVM_REG_PPC_BESCR | 64
1989 PPC | KVM_REG_PPC_TAR | 64
1990 PPC | KVM_REG_PPC_DPDES | 64
1991 PPC | KVM_REG_PPC_DAWR | 64
1992 PPC | KVM_REG_PPC_DAWRX | 64
1993 PPC | KVM_REG_PPC_CIABR | 64
1994 PPC | KVM_REG_PPC_IC | 64
1995 PPC | KVM_REG_PPC_VTB | 64
1996 PPC | KVM_REG_PPC_CSIGR | 64
1997 PPC | KVM_REG_PPC_TACR | 64
1998 PPC | KVM_REG_PPC_TCSCR | 64
1999 PPC | KVM_REG_PPC_PID | 64
2000 PPC | KVM_REG_PPC_ACOP | 64
2001 PPC | KVM_REG_PPC_VRSAVE | 32
2002 PPC | KVM_REG_PPC_LPCR | 32
2003 PPC | KVM_REG_PPC_LPCR_64 | 64
2004 PPC | KVM_REG_PPC_PPR | 64
2005 PPC | KVM_REG_PPC_ARCH_COMPAT | 32
2006 PPC | KVM_REG_PPC_DABRX | 32
2007 PPC | KVM_REG_PPC_WORT | 64
2008 PPC | KVM_REG_PPC_SPRG9 | 64
2009 PPC | KVM_REG_PPC_DBSR | 32
2010 PPC | KVM_REG_PPC_TM_GPR0 | 64
2012 PPC | KVM_REG_PPC_TM_GPR31 | 64
2013 PPC | KVM_REG_PPC_TM_VSR0 | 128
2015 PPC | KVM_REG_PPC_TM_VSR63 | 128
2016 PPC | KVM_REG_PPC_TM_CR | 64
2017 PPC | KVM_REG_PPC_TM_LR | 64
2018 PPC | KVM_REG_PPC_TM_CTR | 64
2019 PPC | KVM_REG_PPC_TM_FPSCR | 64
2020 PPC | KVM_REG_PPC_TM_AMR | 64
2021 PPC | KVM_REG_PPC_TM_PPR | 64
2022 PPC | KVM_REG_PPC_TM_VRSAVE | 64
2023 PPC | KVM_REG_PPC_TM_VSCR | 32
2024 PPC | KVM_REG_PPC_TM_DSCR | 64
2025 PPC | KVM_REG_PPC_TM_TAR | 64
2027 MIPS | KVM_REG_MIPS_R0 | 64
2029 MIPS | KVM_REG_MIPS_R31 | 64
2030 MIPS | KVM_REG_MIPS_HI | 64
2031 MIPS | KVM_REG_MIPS_LO | 64
2032 MIPS | KVM_REG_MIPS_PC | 64
2033 MIPS | KVM_REG_MIPS_CP0_INDEX | 32
2034 MIPS | KVM_REG_MIPS_CP0_CONTEXT | 64
2035 MIPS | KVM_REG_MIPS_CP0_USERLOCAL | 64
2036 MIPS | KVM_REG_MIPS_CP0_PAGEMASK | 32
2037 MIPS | KVM_REG_MIPS_CP0_WIRED | 32
2038 MIPS | KVM_REG_MIPS_CP0_HWRENA | 32
2039 MIPS | KVM_REG_MIPS_CP0_BADVADDR | 64
2040 MIPS | KVM_REG_MIPS_CP0_COUNT | 32
2041 MIPS | KVM_REG_MIPS_CP0_ENTRYHI | 64
2042 MIPS | KVM_REG_MIPS_CP0_COMPARE | 32
2043 MIPS | KVM_REG_MIPS_CP0_STATUS | 32
2044 MIPS | KVM_REG_MIPS_CP0_CAUSE | 32
2045 MIPS | KVM_REG_MIPS_CP0_EPC | 64
2046 MIPS | KVM_REG_MIPS_CP0_PRID | 32
2047 MIPS | KVM_REG_MIPS_CP0_CONFIG | 32
2048 MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32
2049 MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32
2050 MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32
2051 MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32
2052 MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32
2053 MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32
2054 MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64
2055 MIPS | KVM_REG_MIPS_CP0_KSCRATCH1 | 64
2056 MIPS | KVM_REG_MIPS_CP0_KSCRATCH2 | 64
2057 MIPS | KVM_REG_MIPS_CP0_KSCRATCH3 | 64
2058 MIPS | KVM_REG_MIPS_CP0_KSCRATCH4 | 64
2059 MIPS | KVM_REG_MIPS_CP0_KSCRATCH5 | 64
2060 MIPS | KVM_REG_MIPS_CP0_KSCRATCH6 | 64
2061 MIPS | KVM_REG_MIPS_COUNT_CTL | 64
2062 MIPS | KVM_REG_MIPS_COUNT_RESUME | 64
2063 MIPS | KVM_REG_MIPS_COUNT_HZ | 64
2064 MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32
2065 MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64
2066 MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128
2067 MIPS | KVM_REG_MIPS_FCR_IR | 32
2068 MIPS | KVM_REG_MIPS_FCR_CSR | 32
2069 MIPS | KVM_REG_MIPS_MSA_IR | 32
2070 MIPS | KVM_REG_MIPS_MSA_CSR | 32
2072 ARM registers are mapped using the lower 32 bits. The upper 16 of that
2073 is the register group type, or coprocessor number:
2075 ARM core registers have the following id bit patterns:
2076 0x4020 0000 0010 <index into the kvm_regs struct:16>
2078 ARM 32-bit CP15 registers have the following id bit patterns:
2079 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
2081 ARM 64-bit CP15 registers have the following id bit patterns:
2082 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
2084 ARM CCSIDR registers are demultiplexed by CSSELR value:
2085 0x4020 0000 0011 00 <csselr:8>
2087 ARM 32-bit VFP control registers have the following id bit patterns:
2088 0x4020 0000 0012 1 <regno:12>
2090 ARM 64-bit FP registers have the following id bit patterns:
2091 0x4030 0000 0012 0 <regno:12>
2094 arm64 registers are mapped using the lower 32 bits. The upper 16 of
2095 that is the register group type, or coprocessor number:
2097 arm64 core/FP-SIMD registers have the following id bit patterns. Note
2098 that the size of the access is variable, as the kvm_regs structure
2099 contains elements ranging from 32 to 128 bits. The index is a 32bit
2100 value in the kvm_regs structure seen as a 32bit array.
2101 0x60x0 0000 0010 <index into the kvm_regs struct:16>
2103 arm64 CCSIDR registers are demultiplexed by CSSELR value:
2104 0x6020 0000 0011 00 <csselr:8>
2106 arm64 system registers have the following id bit patterns:
2107 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
2110 MIPS registers are mapped using the lower 32 bits. The upper 16 of that is
2111 the register group type:
2113 MIPS core registers (see above) have the following id bit patterns:
2114 0x7030 0000 0000 <reg:16>
2116 MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
2117 patterns depending on whether they're 32-bit or 64-bit registers:
2118 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit)
2119 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit)
2121 MIPS KVM control registers (see above) have the following id bit patterns:
2122 0x7030 0000 0002 <reg:16>
2124 MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following
2125 id bit patterns depending on the size of the register being accessed. They are
2126 always accessed according to the current guest FPU mode (Status.FR and
2127 Config5.FRE), i.e. as the guest would see them, and they become unpredictable
2128 if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector
2129 registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they
2130 overlap the FPU registers:
2131 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
2132 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
2133 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)
2135 MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the
2136 following id bit patterns:
2137 0x7020 0000 0003 01 <0:3> <reg:5>
2139 MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the
2140 following id bit patterns:
2141 0x7020 0000 0003 02 <0:3> <reg:5>
2144 4.69 KVM_GET_ONE_REG
2146 Capability: KVM_CAP_ONE_REG
2149 Parameters: struct kvm_one_reg (in and out)
2150 Returns: 0 on success, negative value on failure
2152 This ioctl allows to receive the value of a single register implemented
2153 in a vcpu. The register to read is indicated by the "id" field of the
2154 kvm_one_reg struct passed in. On success, the register value can be found
2155 at the memory location pointed to by "addr".
2157 The list of registers accessible using this interface is identical to the
2161 4.70 KVM_KVMCLOCK_CTRL
2163 Capability: KVM_CAP_KVMCLOCK_CTRL
2164 Architectures: Any that implement pvclocks (currently x86 only)
2167 Returns: 0 on success, -1 on error
2169 This signals to the host kernel that the specified guest is being paused by
2170 userspace. The host will set a flag in the pvclock structure that is checked
2171 from the soft lockup watchdog. The flag is part of the pvclock structure that
2172 is shared between guest and host, specifically the second bit of the flags
2173 field of the pvclock_vcpu_time_info structure. It will be set exclusively by
2174 the host and read/cleared exclusively by the guest. The guest operation of
2175 checking and clearing the flag must an atomic operation so
2176 load-link/store-conditional, or equivalent must be used. There are two cases
2177 where the guest will clear the flag: when the soft lockup watchdog timer resets
2178 itself or when a soft lockup is detected. This ioctl can be called any time
2179 after pausing the vcpu, but before it is resumed.
2184 Capability: KVM_CAP_SIGNAL_MSI
2185 Architectures: x86 arm64
2187 Parameters: struct kvm_msi (in)
2188 Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
2190 Directly inject a MSI message. Only valid with in-kernel irqchip that handles
2202 flags: KVM_MSI_VALID_DEVID: devid contains a valid value
2203 devid: If KVM_MSI_VALID_DEVID is set, contains a unique device identifier
2204 for the device that wrote the MSI message.
2205 For PCI, this is usually a BFD identifier in the lower 16 bits.
2207 The per-VM KVM_CAP_MSI_DEVID capability advertises the need to provide
2208 the device ID. If this capability is not set, userland cannot rely on
2209 the kernel to allow the KVM_MSI_VALID_DEVID flag being set.
2211 On x86, address_hi is ignored unless the KVM_CAP_X2APIC_API capability is
2212 enabled. If it is enabled, address_hi bits 31-8 provide bits 31-8 of the
2213 destination id. Bits 7-0 of address_hi must be zero.
2216 4.71 KVM_CREATE_PIT2
2218 Capability: KVM_CAP_PIT2
2221 Parameters: struct kvm_pit_config (in)
2222 Returns: 0 on success, -1 on error
2224 Creates an in-kernel device model for the i8254 PIT. This call is only valid
2225 after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
2226 parameters have to be passed:
2228 struct kvm_pit_config {
2235 #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */
2237 PIT timer interrupts may use a per-VM kernel thread for injection. If it
2238 exists, this thread will have a name of the following pattern:
2240 kvm-pit/<owner-process-pid>
2242 When running a guest with elevated priorities, the scheduling parameters of
2243 this thread may have to be adjusted accordingly.
2245 This IOCTL replaces the obsolete KVM_CREATE_PIT.
2250 Capability: KVM_CAP_PIT_STATE2
2253 Parameters: struct kvm_pit_state2 (out)
2254 Returns: 0 on success, -1 on error
2256 Retrieves the state of the in-kernel PIT model. Only valid after
2257 KVM_CREATE_PIT2. The state is returned in the following structure:
2259 struct kvm_pit_state2 {
2260 struct kvm_pit_channel_state channels[3];
2267 /* disable PIT in HPET legacy mode */
2268 #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
2270 This IOCTL replaces the obsolete KVM_GET_PIT.
2275 Capability: KVM_CAP_PIT_STATE2
2278 Parameters: struct kvm_pit_state2 (in)
2279 Returns: 0 on success, -1 on error
2281 Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
2282 See KVM_GET_PIT2 for details on struct kvm_pit_state2.
2284 This IOCTL replaces the obsolete KVM_SET_PIT.
2287 4.74 KVM_PPC_GET_SMMU_INFO
2289 Capability: KVM_CAP_PPC_GET_SMMU_INFO
2290 Architectures: powerpc
2293 Returns: 0 on success, -1 on error
2295 This populates and returns a structure describing the features of
2296 the "Server" class MMU emulation supported by KVM.
2297 This can in turn be used by userspace to generate the appropriate
2298 device-tree properties for the guest operating system.
2300 The structure contains some global information, followed by an
2301 array of supported segment page sizes:
2303 struct kvm_ppc_smmu_info {
2307 struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
2310 The supported flags are:
2312 - KVM_PPC_PAGE_SIZES_REAL:
2313 When that flag is set, guest page sizes must "fit" the backing
2314 store page sizes. When not set, any page size in the list can
2315 be used regardless of how they are backed by userspace.
2317 - KVM_PPC_1T_SEGMENTS
2318 The emulated MMU supports 1T segments in addition to the
2321 The "slb_size" field indicates how many SLB entries are supported
2323 The "sps" array contains 8 entries indicating the supported base
2324 page sizes for a segment in increasing order. Each entry is defined
2327 struct kvm_ppc_one_seg_page_size {
2328 __u32 page_shift; /* Base page shift of segment (or 0) */
2329 __u32 slb_enc; /* SLB encoding for BookS */
2330 struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
2333 An entry with a "page_shift" of 0 is unused. Because the array is
2334 organized in increasing order, a lookup can stop when encoutering
2337 The "slb_enc" field provides the encoding to use in the SLB for the
2338 page size. The bits are in positions such as the value can directly
2339 be OR'ed into the "vsid" argument of the slbmte instruction.
2341 The "enc" array is a list which for each of those segment base page
2342 size provides the list of supported actual page sizes (which can be
2343 only larger or equal to the base page size), along with the
2344 corresponding encoding in the hash PTE. Similarly, the array is
2345 8 entries sorted by increasing sizes and an entry with a "0" shift
2346 is an empty entry and a terminator:
2348 struct kvm_ppc_one_page_size {
2349 __u32 page_shift; /* Page shift (or 0) */
2350 __u32 pte_enc; /* Encoding in the HPTE (>>12) */
2353 The "pte_enc" field provides a value that can OR'ed into the hash
2354 PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
2355 into the hash PTE second double word).
2359 Capability: KVM_CAP_IRQFD
2360 Architectures: x86 s390 arm arm64
2362 Parameters: struct kvm_irqfd (in)
2363 Returns: 0 on success, -1 on error
2365 Allows setting an eventfd to directly trigger a guest interrupt.
2366 kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
2367 kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When
2368 an event is triggered on the eventfd, an interrupt is injected into
2369 the guest using the specified gsi pin. The irqfd is removed using
2370 the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
2373 With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
2374 mechanism allowing emulation of level-triggered, irqfd-based
2375 interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
2376 additional eventfd in the kvm_irqfd.resamplefd field. When operating
2377 in resample mode, posting of an interrupt through kvm_irq.fd asserts
2378 the specified gsi in the irqchip. When the irqchip is resampled, such
2379 as from an EOI, the gsi is de-asserted and the user is notified via
2380 kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
2381 the interrupt if the device making use of it still requires service.
2382 Note that closing the resamplefd is not sufficient to disable the
2383 irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
2384 and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
2386 On ARM/ARM64, the gsi field in the kvm_irqfd struct specifies the Shared
2387 Peripheral Interrupt (SPI) index, such that the GIC interrupt ID is
2390 4.76 KVM_PPC_ALLOCATE_HTAB
2392 Capability: KVM_CAP_PPC_ALLOC_HTAB
2393 Architectures: powerpc
2395 Parameters: Pointer to u32 containing hash table order (in/out)
2396 Returns: 0 on success, -1 on error
2398 This requests the host kernel to allocate an MMU hash table for a
2399 guest using the PAPR paravirtualization interface. This only does
2400 anything if the kernel is configured to use the Book 3S HV style of
2401 virtualization. Otherwise the capability doesn't exist and the ioctl
2402 returns an ENOTTY error. The rest of this description assumes Book 3S
2405 There must be no vcpus running when this ioctl is called; if there
2406 are, it will do nothing and return an EBUSY error.
2408 The parameter is a pointer to a 32-bit unsigned integer variable
2409 containing the order (log base 2) of the desired size of the hash
2410 table, which must be between 18 and 46. On successful return from the
2411 ioctl, it will have been updated with the order of the hash table that
2414 If no hash table has been allocated when any vcpu is asked to run
2415 (with the KVM_RUN ioctl), the host kernel will allocate a
2416 default-sized hash table (16 MB).
2418 If this ioctl is called when a hash table has already been allocated,
2419 the kernel will clear out the existing hash table (zero all HPTEs) and
2420 return the hash table order in the parameter. (If the guest is using
2421 the virtualized real-mode area (VRMA) facility, the kernel will
2422 re-create the VMRA HPTEs on the next KVM_RUN of any vcpu.)
2424 4.77 KVM_S390_INTERRUPT
2428 Type: vm ioctl, vcpu ioctl
2429 Parameters: struct kvm_s390_interrupt (in)
2430 Returns: 0 on success, -1 on error
2432 Allows to inject an interrupt to the guest. Interrupts can be floating
2433 (vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
2435 Interrupt parameters are passed via kvm_s390_interrupt:
2437 struct kvm_s390_interrupt {
2443 type can be one of the following:
2445 KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm
2446 KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
2447 KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
2448 KVM_S390_RESTART (vcpu) - restart
2449 KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
2450 KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
2451 KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
2452 parameters in parm and parm64
2453 KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
2454 KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
2455 KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
2456 KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
2457 I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
2458 I/O interruption parameters in parm (subchannel) and parm64 (intparm,
2459 interruption subclass)
2460 KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
2461 machine check interrupt code in parm64 (note that
2462 machine checks needing further payload are not
2463 supported by this ioctl)
2465 Note that the vcpu ioctl is asynchronous to vcpu execution.
2467 4.78 KVM_PPC_GET_HTAB_FD
2469 Capability: KVM_CAP_PPC_HTAB_FD
2470 Architectures: powerpc
2472 Parameters: Pointer to struct kvm_get_htab_fd (in)
2473 Returns: file descriptor number (>= 0) on success, -1 on error
2475 This returns a file descriptor that can be used either to read out the
2476 entries in the guest's hashed page table (HPT), or to write entries to
2477 initialize the HPT. The returned fd can only be written to if the
2478 KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
2479 can only be read if that bit is clear. The argument struct looks like
2482 /* For KVM_PPC_GET_HTAB_FD */
2483 struct kvm_get_htab_fd {
2489 /* Values for kvm_get_htab_fd.flags */
2490 #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1)
2491 #define KVM_GET_HTAB_WRITE ((__u64)0x2)
2493 The `start_index' field gives the index in the HPT of the entry at
2494 which to start reading. It is ignored when writing.
2496 Reads on the fd will initially supply information about all
2497 "interesting" HPT entries. Interesting entries are those with the
2498 bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
2499 all entries. When the end of the HPT is reached, the read() will
2500 return. If read() is called again on the fd, it will start again from
2501 the beginning of the HPT, but will only return HPT entries that have
2502 changed since they were last read.
2504 Data read or written is structured as a header (8 bytes) followed by a
2505 series of valid HPT entries (16 bytes) each. The header indicates how
2506 many valid HPT entries there are and how many invalid entries follow
2507 the valid entries. The invalid entries are not represented explicitly
2508 in the stream. The header format is:
2510 struct kvm_get_htab_header {
2516 Writes to the fd create HPT entries starting at the index given in the
2517 header; first `n_valid' valid entries with contents from the data
2518 written, then `n_invalid' invalid entries, invalidating any previously
2519 valid entries found.
2521 4.79 KVM_CREATE_DEVICE
2523 Capability: KVM_CAP_DEVICE_CTRL
2525 Parameters: struct kvm_create_device (in/out)
2526 Returns: 0 on success, -1 on error
2528 ENODEV: The device type is unknown or unsupported
2529 EEXIST: Device already created, and this type of device may not
2530 be instantiated multiple times
2532 Other error conditions may be defined by individual device types or
2533 have their standard meanings.
2535 Creates an emulated device in the kernel. The file descriptor returned
2536 in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
2538 If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
2539 device type is supported (not necessarily whether it can be created
2542 Individual devices should not define flags. Attributes should be used
2543 for specifying any behavior that is not implied by the device type
2546 struct kvm_create_device {
2547 __u32 type; /* in: KVM_DEV_TYPE_xxx */
2548 __u32 fd; /* out: device handle */
2549 __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
2552 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
2554 Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
2555 KVM_CAP_VCPU_ATTRIBUTES for vcpu device
2556 Type: device ioctl, vm ioctl, vcpu ioctl
2557 Parameters: struct kvm_device_attr
2558 Returns: 0 on success, -1 on error
2560 ENXIO: The group or attribute is unknown/unsupported for this device
2561 or hardware support is missing.
2562 EPERM: The attribute cannot (currently) be accessed this way
2563 (e.g. read-only attribute, or attribute that only makes
2564 sense when the device is in a different state)
2566 Other error conditions may be defined by individual device types.
2568 Gets/sets a specified piece of device configuration and/or state. The
2569 semantics are device-specific. See individual device documentation in
2570 the "devices" directory. As with ONE_REG, the size of the data
2571 transferred is defined by the particular attribute.
2573 struct kvm_device_attr {
2574 __u32 flags; /* no flags currently defined */
2575 __u32 group; /* device-defined */
2576 __u64 attr; /* group-defined */
2577 __u64 addr; /* userspace address of attr data */
2580 4.81 KVM_HAS_DEVICE_ATTR
2582 Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
2583 KVM_CAP_VCPU_ATTRIBUTES for vcpu device
2584 Type: device ioctl, vm ioctl, vcpu ioctl
2585 Parameters: struct kvm_device_attr
2586 Returns: 0 on success, -1 on error
2588 ENXIO: The group or attribute is unknown/unsupported for this device
2589 or hardware support is missing.
2591 Tests whether a device supports a particular attribute. A successful
2592 return indicates the attribute is implemented. It does not necessarily
2593 indicate that the attribute can be read or written in the device's
2594 current state. "addr" is ignored.
2596 4.82 KVM_ARM_VCPU_INIT
2599 Architectures: arm, arm64
2601 Parameters: struct kvm_vcpu_init (in)
2602 Returns: 0 on success; -1 on error
2604 Â EINVAL: Â Â Â the target is unknown, or the combination of features is invalid.
2605 Â ENOENT: Â Â Â a features bit specified is unknown.
2607 This tells KVM what type of CPU to present to the guest, and what
2608 optional features it should have. Â This will cause a reset of the cpu
2609 registers to their initial values. Â If this is not called, KVM_RUN will
2610 return ENOEXEC for that vcpu.
2612 Note that because some registers reflect machine topology, all vcpus
2613 should be created before this ioctl is invoked.
2615 Userspace can call this function multiple times for a given vcpu, including
2616 after the vcpu has been run. This will reset the vcpu to its initial
2617 state. All calls to this function after the initial call must use the same
2618 target and same set of feature flags, otherwise EINVAL will be returned.
2621 - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
2622 Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on
2623 and execute guest code when KVM_RUN is called.
2624 - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
2625 Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
2626 - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
2627 Depends on KVM_CAP_ARM_PSCI_0_2.
2628 - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
2629 Depends on KVM_CAP_ARM_PMU_V3.
2632 4.83 KVM_ARM_PREFERRED_TARGET
2635 Architectures: arm, arm64
2637 Parameters: struct struct kvm_vcpu_init (out)
2638 Returns: 0 on success; -1 on error
2640 ENODEV: no preferred target available for the host
2642 This queries KVM for preferred CPU target type which can be emulated
2643 by KVM on underlying host.
2645 The ioctl returns struct kvm_vcpu_init instance containing information
2646 about preferred CPU target type and recommended features for it. The
2647 kvm_vcpu_init->features bitmap returned will have feature bits set if
2648 the preferred target recommends setting these features, but this is
2651 The information returned by this ioctl can be used to prepare an instance
2652 of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
2653 in VCPU matching underlying host.
2656 4.84 KVM_GET_REG_LIST
2659 Architectures: arm, arm64, mips
2661 Parameters: struct kvm_reg_list (in/out)
2662 Returns: 0 on success; -1 on error
2664 Â E2BIG: Â Â Â Â the reg index list is too big to fit in the array specified by
2665 Â Â Â Â Â Â Â Â Â Â Â Â the user (the number required will be written into n).
2667 struct kvm_reg_list {
2668 __u64 n; /* number of registers in reg[] */
2672 This ioctl returns the guest registers that are supported for the
2673 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
2676 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
2678 Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
2679 Architectures: arm, arm64
2681 Parameters: struct kvm_arm_device_address (in)
2682 Returns: 0 on success, -1 on error
2684 ENODEV: The device id is unknown
2685 ENXIO: Device not supported on current system
2686 EEXIST: Address already set
2687 E2BIG: Address outside guest physical address space
2688 EBUSY: Address overlaps with other device range
2690 struct kvm_arm_device_addr {
2695 Specify a device address in the guest's physical address space where guests
2696 can access emulated or directly exposed devices, which the host kernel needs
2697 to know about. The id field is an architecture specific identifier for a
2700 ARM/arm64 divides the id field into two parts, a device id and an
2701 address type id specific to the individual device.
2703 Â bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
2704 field: | 0x00000000 | device id | addr type id |
2706 ARM/arm64 currently only require this when using the in-kernel GIC
2707 support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
2708 as the device id. When setting the base address for the guest's
2709 mapping of the VGIC virtual CPU and distributor interface, the ioctl
2710 must be called after calling KVM_CREATE_IRQCHIP, but before calling
2711 KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
2712 base addresses will return -EEXIST.
2714 Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
2715 should be used instead.
2718 4.86 KVM_PPC_RTAS_DEFINE_TOKEN
2720 Capability: KVM_CAP_PPC_RTAS
2723 Parameters: struct kvm_rtas_token_args
2724 Returns: 0 on success, -1 on error
2726 Defines a token value for a RTAS (Run Time Abstraction Services)
2727 service in order to allow it to be handled in the kernel. The
2728 argument struct gives the name of the service, which must be the name
2729 of a service that has a kernel-side implementation. If the token
2730 value is non-zero, it will be associated with that service, and
2731 subsequent RTAS calls by the guest specifying that token will be
2732 handled by the kernel. If the token value is 0, then any token
2733 associated with the service will be forgotten, and subsequent RTAS
2734 calls by the guest for that service will be passed to userspace to be
2737 4.87 KVM_SET_GUEST_DEBUG
2739 Capability: KVM_CAP_SET_GUEST_DEBUG
2740 Architectures: x86, s390, ppc, arm64
2742 Parameters: struct kvm_guest_debug (in)
2743 Returns: 0 on success; -1 on error
2745 struct kvm_guest_debug {
2748 struct kvm_guest_debug_arch arch;
2751 Set up the processor specific debug registers and configure vcpu for
2752 handling guest debug events. There are two parts to the structure, the
2753 first a control bitfield indicates the type of debug events to handle
2754 when running. Common control bits are:
2756 - KVM_GUESTDBG_ENABLE: guest debugging is enabled
2757 - KVM_GUESTDBG_SINGLESTEP: the next run should single-step
2759 The top 16 bits of the control field are architecture specific control
2760 flags which can include the following:
2762 - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64]
2763 - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390, arm64]
2764 - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86]
2765 - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86]
2766 - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390]
2768 For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints
2769 are enabled in memory so we need to ensure breakpoint exceptions are
2770 correctly trapped and the KVM run loop exits at the breakpoint and not
2771 running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP
2772 we need to ensure the guest vCPUs architecture specific registers are
2773 updated to the correct (supplied) values.
2775 The second part of the structure is architecture specific and
2776 typically contains a set of debug registers.
2778 For arm64 the number of debug registers is implementation defined and
2779 can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
2780 KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
2781 indicating the number of supported registers.
2783 When debug events exit the main run loop with the reason
2784 KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
2785 structure containing architecture specific debug information.
2787 4.88 KVM_GET_EMULATED_CPUID
2789 Capability: KVM_CAP_EXT_EMUL_CPUID
2792 Parameters: struct kvm_cpuid2 (in/out)
2793 Returns: 0 on success, -1 on error
2798 struct kvm_cpuid_entry2 entries[0];
2801 The member 'flags' is used for passing flags from userspace.
2803 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
2804 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
2805 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
2807 struct kvm_cpuid_entry2 {
2818 This ioctl returns x86 cpuid features which are emulated by
2819 kvm.Userspace can use the information returned by this ioctl to query
2820 which features are emulated by kvm instead of being present natively.
2822 Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
2823 structure with the 'nent' field indicating the number of entries in
2824 the variable-size array 'entries'. If the number of entries is too low
2825 to describe the cpu capabilities, an error (E2BIG) is returned. If the
2826 number is too high, the 'nent' field is adjusted and an error (ENOMEM)
2827 is returned. If the number is just right, the 'nent' field is adjusted
2828 to the number of valid entries in the 'entries' array, which is then
2831 The entries returned are the set CPUID bits of the respective features
2832 which kvm emulates, as returned by the CPUID instruction, with unknown
2833 or unsupported feature bits cleared.
2835 Features like x2apic, for example, may not be present in the host cpu
2836 but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
2837 emulated efficiently and thus not included here.
2839 The fields in each entry are defined as follows:
2841 function: the eax value used to obtain the entry
2842 index: the ecx value used to obtain the entry (for entries that are
2844 flags: an OR of zero or more of the following:
2845 KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
2846 if the index field is valid
2847 KVM_CPUID_FLAG_STATEFUL_FUNC:
2848 if cpuid for this function returns different values for successive
2849 invocations; there will be several entries with the same function,
2850 all with this flag set
2851 KVM_CPUID_FLAG_STATE_READ_NEXT:
2852 for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
2853 the first entry to be read by a cpu
2854 eax, ebx, ecx, edx: the values returned by the cpuid instruction for
2855 this function/index combination
2857 4.89 KVM_S390_MEM_OP
2859 Capability: KVM_CAP_S390_MEM_OP
2862 Parameters: struct kvm_s390_mem_op (in)
2863 Returns: = 0 on success,
2864 < 0 on generic error (e.g. -EFAULT or -ENOMEM),
2865 > 0 if an exception occurred while walking the page tables
2867 Read or write data from/to the logical (virtual) memory of a VCPU.
2869 Parameters are specified via the following structure:
2871 struct kvm_s390_mem_op {
2872 __u64 gaddr; /* the guest address */
2873 __u64 flags; /* flags */
2874 __u32 size; /* amount of bytes */
2875 __u32 op; /* type of operation */
2876 __u64 buf; /* buffer in userspace */
2877 __u8 ar; /* the access register number */
2878 __u8 reserved[31]; /* should be set to 0 */
2881 The type of operation is specified in the "op" field. It is either
2882 KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
2883 KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The
2884 KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check
2885 whether the corresponding memory access would create an access exception
2886 (without touching the data in the memory at the destination). In case an
2887 access exception occurred while walking the MMU tables of the guest, the
2888 ioctl returns a positive error number to indicate the type of exception.
2889 This exception is also raised directly at the corresponding VCPU if the
2890 flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field.
2892 The start address of the memory region has to be specified in the "gaddr"
2893 field, and the length of the region in the "size" field. "buf" is the buffer
2894 supplied by the userspace application where the read data should be written
2895 to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written
2896 is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL
2897 when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access
2898 register number to be used.
2900 The "reserved" field is meant for future extensions. It is not used by
2901 KVM with the currently defined set of flags.
2903 4.90 KVM_S390_GET_SKEYS
2905 Capability: KVM_CAP_S390_SKEYS
2908 Parameters: struct kvm_s390_skeys
2909 Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
2910 keys, negative value on error
2912 This ioctl is used to get guest storage key values on the s390
2913 architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
2915 struct kvm_s390_skeys {
2918 __u64 skeydata_addr;
2923 The start_gfn field is the number of the first guest frame whose storage keys
2926 The count field is the number of consecutive frames (starting from start_gfn)
2927 whose storage keys to get. The count field must be at least 1 and the maximum
2928 allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
2929 will cause the ioctl to return -EINVAL.
2931 The skeydata_addr field is the address to a buffer large enough to hold count
2932 bytes. This buffer will be filled with storage key data by the ioctl.
2934 4.91 KVM_S390_SET_SKEYS
2936 Capability: KVM_CAP_S390_SKEYS
2939 Parameters: struct kvm_s390_skeys
2940 Returns: 0 on success, negative value on error
2942 This ioctl is used to set guest storage key values on the s390
2943 architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
2944 See section on KVM_S390_GET_SKEYS for struct definition.
2946 The start_gfn field is the number of the first guest frame whose storage keys
2949 The count field is the number of consecutive frames (starting from start_gfn)
2950 whose storage keys to get. The count field must be at least 1 and the maximum
2951 allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
2952 will cause the ioctl to return -EINVAL.
2954 The skeydata_addr field is the address to a buffer containing count bytes of
2955 storage keys. Each byte in the buffer will be set as the storage key for a
2956 single frame starting at start_gfn for count frames.
2958 Note: If any architecturally invalid key value is found in the given data then
2959 the ioctl will return -EINVAL.
2963 Capability: KVM_CAP_S390_INJECT_IRQ
2966 Parameters: struct kvm_s390_irq (in)
2967 Returns: 0 on success, -1 on error
2969 EINVAL: interrupt type is invalid
2970 type is KVM_S390_SIGP_STOP and flag parameter is invalid value
2971 type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
2972 than the maximum of VCPUs
2973 EBUSY: type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped
2974 type is KVM_S390_SIGP_STOP and a stop irq is already pending
2975 type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
2978 Allows to inject an interrupt to the guest.
2980 Using struct kvm_s390_irq as a parameter allows
2981 to inject additional payload which is not
2982 possible via KVM_S390_INTERRUPT.
2984 Interrupt parameters are passed via kvm_s390_irq:
2986 struct kvm_s390_irq {
2989 struct kvm_s390_io_info io;
2990 struct kvm_s390_ext_info ext;
2991 struct kvm_s390_pgm_info pgm;
2992 struct kvm_s390_emerg_info emerg;
2993 struct kvm_s390_extcall_info extcall;
2994 struct kvm_s390_prefix_info prefix;
2995 struct kvm_s390_stop_info stop;
2996 struct kvm_s390_mchk_info mchk;
3001 type can be one of the following:
3003 KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
3004 KVM_S390_PROGRAM_INT - program check; parameters in .pgm
3005 KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
3006 KVM_S390_RESTART - restart; no parameters
3007 KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
3008 KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
3009 KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
3010 KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
3011 KVM_S390_MCHK - machine check interrupt; parameters in .mchk
3014 Note that the vcpu ioctl is asynchronous to vcpu execution.
3016 4.94 KVM_S390_GET_IRQ_STATE
3018 Capability: KVM_CAP_S390_IRQ_STATE
3021 Parameters: struct kvm_s390_irq_state (out)
3022 Returns: >= number of bytes copied into buffer,
3023 -EINVAL if buffer size is 0,
3024 -ENOBUFS if buffer size is too small to fit all pending interrupts,
3025 -EFAULT if the buffer address was invalid
3027 This ioctl allows userspace to retrieve the complete state of all currently
3028 pending interrupts in a single buffer. Use cases include migration
3029 and introspection. The parameter structure contains the address of a
3030 userspace buffer and its length:
3032 struct kvm_s390_irq_state {
3039 Userspace passes in the above struct and for each pending interrupt a
3040 struct kvm_s390_irq is copied to the provided buffer.
3042 If -ENOBUFS is returned the buffer provided was too small and userspace
3043 may retry with a bigger buffer.
3045 4.95 KVM_S390_SET_IRQ_STATE
3047 Capability: KVM_CAP_S390_IRQ_STATE
3050 Parameters: struct kvm_s390_irq_state (in)
3051 Returns: 0 on success,
3052 -EFAULT if the buffer address was invalid,
3053 -EINVAL for an invalid buffer length (see below),
3054 -EBUSY if there were already interrupts pending,
3055 errors occurring when actually injecting the
3056 interrupt. See KVM_S390_IRQ.
3058 This ioctl allows userspace to set the complete state of all cpu-local
3059 interrupts currently pending for the vcpu. It is intended for restoring
3060 interrupt state after a migration. The input parameter is a userspace buffer
3061 containing a struct kvm_s390_irq_state:
3063 struct kvm_s390_irq_state {
3069 The userspace memory referenced by buf contains a struct kvm_s390_irq
3070 for each interrupt to be injected into the guest.
3071 If one of the interrupts could not be injected for some reason the
3074 len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
3075 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
3076 which is the maximum number of possibly pending cpu-local interrupts.
3080 Capability: KVM_CAP_X86_SMM
3084 Returns: 0 on success, -1 on error
3086 Queues an SMI on the thread's vcpu.
3088 4.97 KVM_CAP_PPC_MULTITCE
3090 Capability: KVM_CAP_PPC_MULTITCE
3094 This capability means the kernel is capable of handling hypercalls
3095 H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
3096 space. This significantly accelerates DMA operations for PPC KVM guests.
3097 User space should expect that its handlers for these hypercalls
3098 are not going to be called if user space previously registered LIOBN
3099 in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
3101 In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
3102 user space might have to advertise it for the guest. For example,
3103 IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
3104 present in the "ibm,hypertas-functions" device-tree property.
3106 The hypercalls mentioned above may or may not be processed successfully
3107 in the kernel based fast path. If they can not be handled by the kernel,
3108 they will get passed on to user space. So user space still has to have
3109 an implementation for these despite the in kernel acceleration.
3111 This capability is always enabled.
3113 4.98 KVM_CREATE_SPAPR_TCE_64
3115 Capability: KVM_CAP_SPAPR_TCE_64
3116 Architectures: powerpc
3118 Parameters: struct kvm_create_spapr_tce_64 (in)
3119 Returns: file descriptor for manipulating the created TCE table
3121 This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
3122 windows, described in 4.62 KVM_CREATE_SPAPR_TCE
3124 This capability uses extended struct in ioctl interface:
3126 /* for KVM_CAP_SPAPR_TCE_64 */
3127 struct kvm_create_spapr_tce_64 {
3131 __u64 offset; /* in pages */
3132 __u64 size; /* in pages */
3135 The aim of extension is to support an additional bigger DMA window with
3136 a variable page size.
3137 KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and
3138 a bus offset of the corresponding DMA window, @size and @offset are numbers
3141 @flags are not used at the moment.
3143 The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.
3145 4.98 KVM_REINJECT_CONTROL
3147 Capability: KVM_CAP_REINJECT_CONTROL
3150 Parameters: struct kvm_reinject_control (in)
3151 Returns: 0 on success,
3152 -EFAULT if struct kvm_reinject_control cannot be read,
3153 -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
3155 i8254 (PIT) has two modes, reinject and !reinject. The default is reinject,
3156 where KVM queues elapsed i8254 ticks and monitors completion of interrupt from
3157 vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its
3158 interrupt whenever there isn't a pending interrupt from i8254.
3159 !reinject mode injects an interrupt as soon as a tick arrives.
3161 struct kvm_reinject_control {
3166 pit_reinject = 0 (!reinject mode) is recommended, unless running an old
3167 operating system that uses the PIT for timing (e.g. Linux 2.4.x).
3169 5. The kvm_run structure
3170 ------------------------
3172 Application code obtains a pointer to the kvm_run structure by
3173 mmap()ing a vcpu fd. From that point, application code can control
3174 execution by changing fields in kvm_run prior to calling the KVM_RUN
3175 ioctl, and obtain information about the reason KVM_RUN returned by
3176 looking up structure members.
3180 __u8 request_interrupt_window;
3182 Request that KVM_RUN return when it becomes possible to inject external
3183 interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
3190 When KVM_RUN has returned successfully (return value 0), this informs
3191 application code why KVM_RUN has returned. Allowable values for this
3192 field are detailed below.
3194 __u8 ready_for_interrupt_injection;
3196 If request_interrupt_window has been specified, this field indicates
3197 an interrupt can be injected now with KVM_INTERRUPT.
3201 The value of the current interrupt flag. Only valid if in-kernel
3202 local APIC is not used.
3206 More architecture-specific flags detailing state of the VCPU that may
3207 affect the device's behavior. The only currently defined flag is
3208 KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
3209 VCPU is in system management mode.
3211 /* in (pre_kvm_run), out (post_kvm_run) */
3214 The value of the cr8 register. Only valid if in-kernel local APIC is
3215 not used. Both input and output.
3219 The value of the APIC BASE msr. Only valid if in-kernel local
3220 APIC is not used. Both input and output.
3223 /* KVM_EXIT_UNKNOWN */
3225 __u64 hardware_exit_reason;
3228 If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
3229 reasons. Further architecture-specific information is available in
3230 hardware_exit_reason.
3232 /* KVM_EXIT_FAIL_ENTRY */
3234 __u64 hardware_entry_failure_reason;
3237 If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
3238 to unknown reasons. Further architecture-specific information is
3239 available in hardware_entry_failure_reason.
3241 /* KVM_EXIT_EXCEPTION */
3251 #define KVM_EXIT_IO_IN 0
3252 #define KVM_EXIT_IO_OUT 1
3254 __u8 size; /* bytes */
3257 __u64 data_offset; /* relative to kvm_run start */
3260 If exit_reason is KVM_EXIT_IO, then the vcpu has
3261 executed a port I/O instruction which could not be satisfied by kvm.
3262 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
3263 where kvm expects application code to place the data for the next
3264 KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array.
3266 /* KVM_EXIT_DEBUG */
3268 struct kvm_debug_exit_arch arch;
3271 If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
3272 for which architecture specific information is returned.
3282 If exit_reason is KVM_EXIT_MMIO, then the vcpu has
3283 executed a memory-mapped I/O instruction which could not be satisfied
3284 by kvm. The 'data' member contains the written data if 'is_write' is
3285 true, and should be filled by application code otherwise.
3287 The 'data' member contains, in its first 'len' bytes, the value as it would
3288 appear if the VCPU performed a load or store of the appropriate width directly
3291 NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
3292 KVM_EXIT_EPR the corresponding
3293 operations are complete (and guest state is consistent) only after userspace
3294 has re-entered the kernel with KVM_RUN. The kernel side will first finish
3295 incomplete operations and then check for pending signals. Userspace
3296 can re-enter the guest with an unmasked signal pending to complete
3299 /* KVM_EXIT_HYPERCALL */
3308 Unused. This was once used for 'hypercall to userspace'. To implement
3309 such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
3310 Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
3312 /* KVM_EXIT_TPR_ACCESS */
3319 To be documented (KVM_TPR_ACCESS_REPORTING).
3321 /* KVM_EXIT_S390_SIEIC */
3324 __u64 mask; /* psw upper half */
3325 __u64 addr; /* psw lower half */
3332 /* KVM_EXIT_S390_RESET */
3333 #define KVM_S390_RESET_POR 1
3334 #define KVM_S390_RESET_CLEAR 2
3335 #define KVM_S390_RESET_SUBSYSTEM 4
3336 #define KVM_S390_RESET_CPU_INIT 8
3337 #define KVM_S390_RESET_IPL 16
3338 __u64 s390_reset_flags;
3342 /* KVM_EXIT_S390_UCONTROL */
3344 __u64 trans_exc_code;
3348 s390 specific. A page fault has occurred for a user controlled virtual
3349 machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
3350 resolved by the kernel.
3351 The program code and the translation exception code that were placed
3352 in the cpu's lowcore are presented here as defined by the z Architecture
3353 Principles of Operation Book in the Chapter for Dynamic Address Translation
3363 Deprecated - was used for 440 KVM.
3370 MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
3371 hypercalls and exit with this exit struct that contains all the guest gprs.
3373 If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
3374 Userspace can now handle the hypercall and when it's done modify the gprs as
3375 necessary. Upon guest entry all guest GPRs will then be replaced by the values
3378 /* KVM_EXIT_PAPR_HCALL */
3385 This is used on 64-bit PowerPC when emulating a pSeries partition,
3386 e.g. with the 'pseries' machine type in qemu. It occurs when the
3387 guest does a hypercall using the 'sc 1' instruction. The 'nr' field
3388 contains the hypercall number (from the guest R3), and 'args' contains
3389 the arguments (from the guest R4 - R12). Userspace should put the
3390 return code in 'ret' and any extra returned values in args[].
3391 The possible hypercalls are defined in the Power Architecture Platform
3392 Requirements (PAPR) document available from www.power.org (free
3393 developer registration required to access it).
3395 /* KVM_EXIT_S390_TSCH */
3397 __u16 subchannel_id;
3398 __u16 subchannel_nr;
3405 s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
3406 and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
3407 interrupt for the target subchannel has been dequeued and subchannel_id,
3408 subchannel_nr, io_int_parm and io_int_word contain the parameters for that
3409 interrupt. ipb is needed for instruction parameter decoding.
3416 On FSL BookE PowerPC chips, the interrupt controller has a fast patch
3417 interrupt acknowledge path to the core. When the core successfully
3418 delivers an interrupt, it automatically populates the EPR register with
3419 the interrupt vector number and acknowledges the interrupt inside
3420 the interrupt controller.
3422 In case the interrupt controller lives in user space, we need to do
3423 the interrupt acknowledge cycle through it to fetch the next to be
3424 delivered interrupt vector using this exit.
3426 It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
3427 external interrupt has just been delivered into the guest. User space
3428 should put the acknowledged interrupt vector into the 'epr' field.
3430 /* KVM_EXIT_SYSTEM_EVENT */
3432 #define KVM_SYSTEM_EVENT_SHUTDOWN 1
3433 #define KVM_SYSTEM_EVENT_RESET 2
3434 #define KVM_SYSTEM_EVENT_CRASH 3
3439 If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
3440 a system-level event using some architecture specific mechanism (hypercall
3441 or some special instruction). In case of ARM/ARM64, this is triggered using
3442 HVC instruction based PSCI call from the vcpu. The 'type' field describes
3443 the system-level event type. The 'flags' field describes architecture
3444 specific flags for the system-level event.
3446 Valid values for 'type' are:
3447 KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
3448 VM. Userspace is not obliged to honour this, and if it does honour
3449 this does not need to destroy the VM synchronously (ie it may call
3450 KVM_RUN again before shutdown finally occurs).
3451 KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
3452 As with SHUTDOWN, userspace can choose to ignore the request, or
3453 to schedule the reset to occur in the future and may call KVM_RUN again.
3454 KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
3455 has requested a crash condition maintenance. Userspace can choose
3456 to ignore the request, or to gather VM memory core dump and/or
3457 reset/shutdown of the VM.
3459 /* KVM_EXIT_IOAPIC_EOI */
3464 Indicates that the VCPU's in-kernel local APIC received an EOI for a
3465 level-triggered IOAPIC interrupt. This exit only triggers when the
3466 IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled);
3467 the userspace IOAPIC should process the EOI and retrigger the interrupt if
3468 it is still asserted. Vector is the LAPIC interrupt vector for which the
3471 struct kvm_hyperv_exit {
3472 #define KVM_EXIT_HYPERV_SYNIC 1
3473 #define KVM_EXIT_HYPERV_HCALL 2
3489 /* KVM_EXIT_HYPERV */
3490 struct kvm_hyperv_exit hyperv;
3491 Indicates that the VCPU exits into userspace to process some tasks
3492 related to Hyper-V emulation.
3493 Valid values for 'type' are:
3494 KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
3495 Hyper-V SynIC state change. Notification is used to remap SynIC
3496 event/message pages and to enable/disable SynIC messages/events processing
3499 /* Fix the size of the union. */
3504 * shared registers between kvm and userspace.
3505 * kvm_valid_regs specifies the register classes set by the host
3506 * kvm_dirty_regs specified the register classes dirtied by userspace
3507 * struct kvm_sync_regs is architecture specific, as well as the
3508 * bits for kvm_valid_regs and kvm_dirty_regs
3510 __u64 kvm_valid_regs;
3511 __u64 kvm_dirty_regs;
3513 struct kvm_sync_regs regs;
3517 If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
3518 certain guest registers without having to call SET/GET_*REGS. Thus we can
3519 avoid some system call overhead if userspace has to handle the exit.
3520 Userspace can query the validity of the structure by checking
3521 kvm_valid_regs for specific bits. These bits are architecture specific
3522 and usually define the validity of a groups of registers. (e.g. one bit
3523 for general purpose registers)
3525 Please note that the kernel is allowed to use the kvm_run structure as the
3526 primary storage for certain register types. Therefore, the kernel may use the
3527 values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
3533 6. Capabilities that can be enabled on vCPUs
3534 --------------------------------------------
3536 There are certain capabilities that change the behavior of the virtual CPU or
3537 the virtual machine when enabled. To enable them, please see section 4.37.
3538 Below you can find a list of capabilities and what their effect on the vCPU or
3539 the virtual machine is when enabling them.
3541 The following information is provided along with the description:
3543 Architectures: which instruction set architectures provide this ioctl.
3544 x86 includes both i386 and x86_64.
3546 Target: whether this is a per-vcpu or per-vm capability.
3548 Parameters: what parameters are accepted by the capability.
3550 Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
3551 are not detailed, but errors with specific meanings are.
3559 Returns: 0 on success; -1 on error
3561 This capability enables interception of OSI hypercalls that otherwise would
3562 be treated as normal system calls to be injected into the guest. OSI hypercalls
3563 were invented by Mac-on-Linux to have a standardized communication mechanism
3564 between the guest and the host.
3566 When this capability is enabled, KVM_EXIT_OSI can occur.
3569 6.2 KVM_CAP_PPC_PAPR
3574 Returns: 0 on success; -1 on error
3576 This capability enables interception of PAPR hypercalls. PAPR hypercalls are
3577 done using the hypercall instruction "sc 1".
3579 It also sets the guest privilege level to "supervisor" mode. Usually the guest
3580 runs in "hypervisor" privilege mode with a few missing features.
3582 In addition to the above, it changes the semantics of SDR1. In this mode, the
3583 HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
3584 HTAB invisible to the guest.
3586 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
3593 Parameters: args[0] is the address of a struct kvm_config_tlb
3594 Returns: 0 on success; -1 on error
3596 struct kvm_config_tlb {
3603 Configures the virtual CPU's TLB array, establishing a shared memory area
3604 between userspace and KVM. The "params" and "array" fields are userspace
3605 addresses of mmu-type-specific data structures. The "array_len" field is an
3606 safety mechanism, and should be set to the size in bytes of the memory that
3607 userspace has reserved for the array. It must be at least the size dictated
3608 by "mmu_type" and "params".
3610 While KVM_RUN is active, the shared region is under control of KVM. Its
3611 contents are undefined, and any modification by userspace results in
3612 boundedly undefined behavior.
3614 On return from KVM_RUN, the shared region will reflect the current state of
3615 the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB
3616 to tell KVM which entries have been changed, prior to calling KVM_RUN again
3619 For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
3620 - The "params" field is of type "struct kvm_book3e_206_tlb_params".
3621 - The "array" field points to an array of type "struct
3622 kvm_book3e_206_tlb_entry".
3623 - The array consists of all entries in the first TLB, followed by all
3624 entries in the second TLB.
3625 - Within a TLB, entries are ordered first by increasing set number. Within a
3626 set, entries are ordered by way (increasing ESEL).
3627 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
3628 where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
3629 - The tsize field of mas1 shall be set to 4K on TLB0, even though the
3630 hardware ignores this value for TLB0.
3632 6.4 KVM_CAP_S390_CSS_SUPPORT
3637 Returns: 0 on success; -1 on error
3639 This capability enables support for handling of channel I/O instructions.
3641 TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
3642 handled in-kernel, while the other I/O instructions are passed to userspace.
3644 When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
3645 SUBCHANNEL intercepts.
3647 Note that even though this capability is enabled per-vcpu, the complete
3648 virtual machine is affected.
3654 Parameters: args[0] defines whether the proxy facility is active
3655 Returns: 0 on success; -1 on error
3657 This capability enables or disables the delivery of interrupts through the
3658 external proxy facility.
3660 When enabled (args[0] != 0), every time the guest gets an external interrupt
3661 delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
3662 to receive the topmost interrupt vector.
3664 When disabled (args[0] == 0), behavior is as if this facility is unsupported.
3666 When this capability is enabled, KVM_EXIT_EPR can occur.
3668 6.6 KVM_CAP_IRQ_MPIC
3671 Parameters: args[0] is the MPIC device fd
3672 args[1] is the MPIC CPU number for this vcpu
3674 This capability connects the vcpu to an in-kernel MPIC device.
3676 6.7 KVM_CAP_IRQ_XICS
3680 Parameters: args[0] is the XICS device fd
3681 args[1] is the XICS CPU number (server ID) for this vcpu
3683 This capability connects the vcpu to an in-kernel XICS device.
3685 6.8 KVM_CAP_S390_IRQCHIP
3691 This capability enables the in-kernel irqchip for s390. Please refer to
3692 "4.24 KVM_CREATE_IRQCHIP" for details.
3694 6.9 KVM_CAP_MIPS_FPU
3698 Parameters: args[0] is reserved for future use (should be 0).
3700 This capability allows the use of the host Floating Point Unit by the guest. It
3701 allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is
3702 done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed
3703 (depending on the current guest FPU register mode), and the Status.FR,
3704 Config5.FRE bits are accessible via the KVM API and also from the guest,
3705 depending on them being supported by the FPU.
3707 6.10 KVM_CAP_MIPS_MSA
3711 Parameters: args[0] is reserved for future use (should be 0).
3713 This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
3714 It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest.
3715 Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
3716 accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
3719 7. Capabilities that can be enabled on VMs
3720 ------------------------------------------
3722 There are certain capabilities that change the behavior of the virtual
3723 machine when enabled. To enable them, please see section 4.37. Below
3724 you can find a list of capabilities and what their effect on the VM
3725 is when enabling them.
3727 The following information is provided along with the description:
3729 Architectures: which instruction set architectures provide this ioctl.
3730 x86 includes both i386 and x86_64.
3732 Parameters: what parameters are accepted by the capability.
3734 Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
3735 are not detailed, but errors with specific meanings are.
3738 7.1 KVM_CAP_PPC_ENABLE_HCALL
3741 Parameters: args[0] is the sPAPR hcall number
3742 args[1] is 0 to disable, 1 to enable in-kernel handling
3744 This capability controls whether individual sPAPR hypercalls (hcalls)
3745 get handled by the kernel or not. Enabling or disabling in-kernel
3746 handling of an hcall is effective across the VM. On creation, an
3747 initial set of hcalls are enabled for in-kernel handling, which
3748 consists of those hcalls for which in-kernel handlers were implemented
3749 before this capability was implemented. If disabled, the kernel will
3750 not to attempt to handle the hcall, but will always exit to userspace
3751 to handle it. Note that it may not make sense to enable some and
3752 disable others of a group of related hcalls, but KVM does not prevent
3753 userspace from doing that.
3755 If the hcall number specified is not one that has an in-kernel
3756 implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
3759 7.2 KVM_CAP_S390_USER_SIGP
3764 This capability controls which SIGP orders will be handled completely in user
3765 space. With this capability enabled, all fast orders will be handled completely
3771 - CONDITIONAL EMERGENCY SIGNAL
3773 All other orders will be handled completely in user space.
3775 Only privileged operation exceptions will be checked for in the kernel (or even
3776 in the hardware prior to interception). If this capability is not enabled, the
3777 old way of handling SIGP orders is used (partially in kernel and user space).
3779 7.3 KVM_CAP_S390_VECTOR_REGISTERS
3783 Returns: 0 on success, negative value on error
3785 Allows use of the vector registers introduced with z13 processor, and
3786 provides for the synchronization between host and user space. Will
3787 return -EINVAL if the machine does not support vectors.
3789 7.4 KVM_CAP_S390_USER_STSI
3794 This capability allows post-handlers for the STSI instruction. After
3795 initial handling in the kernel, KVM exits to user space with
3796 KVM_EXIT_S390_STSI to allow user space to insert further data.
3798 Before exiting to userspace, kvm handlers should fill in s390_stsi field of
3809 @addr - guest address of STSI SYSIB
3813 @ar - access register number
3815 KVM handlers should exit to userspace with rc = -EREMOTE.
3817 7.5 KVM_CAP_SPLIT_IRQCHIP
3820 Parameters: args[0] - number of routes reserved for userspace IOAPICs
3821 Returns: 0 on success, -1 on error
3823 Create a local apic for each processor in the kernel. This can be used
3824 instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
3825 IOAPIC and PIC (and also the PIT, even though this has to be enabled
3828 This capability also enables in kernel routing of interrupt requests;
3829 when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
3830 used in the IRQ routing table. The first args[0] MSI routes are reserved
3831 for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes,
3832 a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
3834 Fails if VCPU has already been created, or if the irqchip is already in the
3835 kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
3842 Allows use of runtime-instrumentation introduced with zEC12 processor.
3843 Will return -EINVAL if the machine does not support runtime-instrumentation.
3844 Will return -EBUSY if a VCPU has already been created.
3846 7.7 KVM_CAP_X2APIC_API
3849 Parameters: args[0] - features that should be enabled
3850 Returns: 0 on success, -EINVAL when args[0] contains invalid features
3852 Valid feature flags in args[0] are
3854 #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
3855 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
3857 Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
3858 KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
3859 allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their
3860 respective sections.
3862 KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
3863 in logical mode or with more than 255 VCPUs. Otherwise, KVM treats 0xff
3864 as a broadcast even in x2APIC mode in order to support physical x2APIC
3865 without interrupt remapping. This is undesirable in logical mode,
3866 where 0xff represents CPUs 0-7 in cluster 0.
3868 7.8 KVM_CAP_S390_USER_INSTR0
3873 With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
3874 be intercepted and forwarded to user space. User space can use this
3875 mechanism e.g. to realize 2-byte software breakpoints. The kernel will
3876 not inject an operating exception for these instructions, user space has
3877 to take care of that.
3879 This capability can be enabled dynamically even if VCPUs were already
3880 created and are running.
3882 8. Other capabilities.
3883 ----------------------
3885 This section lists capabilities that give information about other
3886 features of the KVM implementation.
3888 8.1 KVM_CAP_PPC_HWRNG
3892 This capability, if KVM_CHECK_EXTENSION indicates that it is
3893 available, means that that the kernel has an implementation of the
3894 H_RANDOM hypercall backed by a hardware random-number generator.
3895 If present, the kernel H_RANDOM handler can be enabled for guest use
3896 with the KVM_CAP_PPC_ENABLE_HCALL capability.
3898 8.2 KVM_CAP_HYPERV_SYNIC
3901 This capability, if KVM_CHECK_EXTENSION indicates that it is
3902 available, means that that the kernel has an implementation of the
3903 Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
3904 used to support Windows Hyper-V based guest paravirt drivers(VMBus).
3906 In order to use SynIC, it has to be activated by setting this
3907 capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
3908 will disable the use of APIC hardware virtualization even if supported
3909 by the CPU, as it's incompatible with SynIC auto-EOI behavior.